Token | listen |
Token ID | 6004 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Masquerade | +0.787 |
Goat | +0.760 |
Caps | +0.715 |
================================================================ | +0.705 |
� | +0.675 |
Neg logit contributions | |
itton | -0.867 |
pez | -0.845 |
ocard | -0.831 |
atts | -0.784 |
ourage | -0.781 |
Token | to |
Token ID | 284 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
itton | +0.708 |
pez | +0.688 |
ocard | +0.681 |
atts | +0.644 |
ourage | +0.636 |
Neg logit contributions | |
Masquerade | -0.548 |
Goat | -0.524 |
Caps | -0.487 |
================================================================ | -0.481 |
� | -0.467 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
itton | +0.121 |
pez | +0.117 |
ocard | +0.116 |
atts | +0.109 |
ourage | +0.109 |
Neg logit contributions | |
Masquerade | -0.100 |
Goat | -0.096 |
Caps | -0.090 |
================================================================ | -0.088 |
� | -0.085 |
Token | clar |
Token ID | 10212 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
itton | +0.268 |
pez | +0.261 |
ocard | +0.257 |
atts | +0.242 |
ourage | +0.241 |
Neg logit contributions | |
Masquerade | -0.233 |
Goat | -0.226 |
Caps | -0.211 |
================================================================ | -0.206 |
� | -0.201 |
Token | inet |
Token ID | 42504 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
itton | +0.951 |
pez | +0.920 |
ocard | +0.910 |
atts | +0.861 |
ourage | +0.850 |
Neg logit contributions | |
Masquerade | -0.788 |
Goat | -0.758 |
Caps | -0.705 |
================================================================ | -0.696 |
� | -0.678 |
Token | quint |
Token ID | 28533 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
itton | +0.886 |
pez | +0.859 |
ocard | +0.849 |
atts | +0.800 |
ourage | +0.792 |
Neg logit contributions | |
Masquerade | -0.782 |
Goat | -0.753 |
Caps | -0.705 |
================================================================ | -0.694 |
� | -0.677 |
Token | et |
Token ID | 316 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
itton | +5.356 |
pez | +5.219 |
ocard | +4.965 |
atts | +4.753 |
ourage | +4.637 |
Neg logit contributions | |
Masquerade | -7.049 |
Goat | -6.911 |
================================================================ | -6.437 |
Caps | -6.396 |
� | -6.250 |
Token | without |
Token ID | 1231 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
itton | +1.130 |
pez | +1.095 |
ocard | +1.083 |
atts | +1.022 |
ourage | +1.011 |
Neg logit contributions | |
Masquerade | -0.970 |
Goat | -0.933 |
Caps | -0.872 |
================================================================ | -0.859 |
� | -0.836 |
Token | fearing |
Token ID | 33188 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Masquerade | +0.771 |
Goat | +0.747 |
Caps | +0.698 |
================================================================ | +0.683 |
� | +0.662 |
Neg logit contributions | |
itton | -0.853 |
pez | -0.834 |
ocard | -0.819 |
atts | -0.768 |
ourage | -0.763 |
Token | that |
Token ID | 326 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
itton | +1.433 |
pez | +1.384 |
ocard | +1.372 |
atts | +1.298 |
ourage | +1.280 |
Neg logit contributions | |
Masquerade | -1.219 |
Goat | -1.167 |
Caps | -1.093 |
================================================================ | -1.081 |
� | -1.056 |
Token | some |
Token ID | 617 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
itton | +0.443 |
pez | +0.432 |
ocard | +0.426 |
atts | +0.402 |
ourage | +0.400 |
Neg logit contributions | |
Masquerade | -0.352 |
Goat | -0.340 |
Caps | -0.316 |
================================================================ | -0.308 |
� | -0.300 |
Token | im |
Token ID | 320 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Masquerade | +1.286 |
Goat | +1.245 |
Caps | +1.170 |
================================================================ | +1.154 |
� | +1.121 |
Neg logit contributions | |
itton | -1.381 |
pez | -1.349 |
ocard | -1.330 |
atts | -1.250 |
ourage | -1.233 |
Token | r |
Token ID | 81 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Masquerade | +0.523 |
Goat | +0.504 |
Caps | +0.477 |
================================================================ | +0.468 |
� | +0.454 |
Neg logit contributions | |
itton | -0.578 |
pez | -0.556 |
ocard | -0.552 |
atts | -0.521 |
ourage | -0.515 |
Token | man |
Token ID | 805 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
itton | +0.433 |
pez | +0.420 |
ocard | +0.418 |
atts | +0.389 |
ourage | +0.386 |
Neg logit contributions | |
Masquerade | -0.406 |
Goat | -0.392 |
Caps | -0.369 |
================================================================ | -0.363 |
� | -0.354 |
Token | became |
Token ID | 2627 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Masquerade | +0.133 |
Goat | +0.128 |
Caps | +0.120 |
================================================================ | +0.118 |
� | +0.115 |
Neg logit contributions | |
itton | -0.163 |
pez | -0.158 |
ocard | -0.156 |
atts | -0.147 |
ourage | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Masquerade | +1.371 |
Goat | +1.326 |
Caps | +1.242 |
================================================================ | +1.219 |
� | +1.189 |
Neg logit contributions | |
itton | -1.571 |
pez | -1.522 |
ocard | -1.502 |
atts | -1.413 |
ourage | -1.395 |
Token | quint |
Token ID | 28533 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Masquerade | +0.105 |
Goat | +0.102 |
Caps | +0.096 |
================================================================ | +0.094 |
� | +0.092 |
Neg logit contributions | |
itton | -0.103 |
pez | -0.100 |
ocard | -0.098 |
atts | -0.092 |
ourage | -0.091 |
Token | essential |
Token ID | 31195 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
itton | +4.480 |
pez | +4.300 |
ocard | +4.174 |
ourage | +3.861 |
atts | +3.797 |
Neg logit contributions | |
Masquerade | -7.134 |
Goat | -6.881 |
Caps | -6.540 |
================================================================ | -6.531 |
� | -6.356 |
Token | Czech |
Token ID | 16639 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
itton | +1.548 |
pez | +1.498 |
ocard | +1.485 |
atts | +1.398 |
ourage | +1.382 |
Neg logit contributions | |
Masquerade | -1.380 |
Goat | -1.326 |
Caps | -1.239 |
================================================================ | -1.226 |
� | -1.198 |
Token | hero |
Token ID | 4293 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
itton | +0.404 |
pez | +0.392 |
ocard | +0.386 |
atts | +0.366 |
ourage | +0.360 |
Neg logit contributions | |
Masquerade | -0.343 |
Goat | -0.330 |
Caps | -0.309 |
================================================================ | -0.304 |
� | -0.295 |
Token | , |
Token ID | 11 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
itton | +0.349 |
pez | +0.338 |
ocard | +0.335 |
atts | +0.317 |
ourage | +0.314 |
Neg logit contributions | |
Masquerade | -0.250 |
Goat | -0.240 |
Caps | -0.222 |
================================================================ | -0.219 |
� | -0.213 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
itton | +0.091 |
pez | +0.088 |
ocard | +0.087 |
atts | +0.082 |
ourage | +0.081 |
Neg logit contributions | |
Masquerade | -0.082 |
Goat | -0.079 |
Caps | -0.074 |
================================================================ | -0.073 |
� | -0.071 |
Token | attack |
Token ID | 20358 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
Masquerade | +0.201 |
Goat | +0.196 |
Caps | +0.187 |
================================================================ | +0.186 |
mentation | +0.182 |
Neg logit contributions | |
itton | -0.120 |
pez | -0.114 |
ocard | -0.112 |
atts | -0.102 |
ourage | -0.100 |
Token | data |
Token ID | 1366 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Masquerade | +0.078 |
Goat | +0.076 |
Caps | +0.072 |
================================================================ | +0.070 |
� | +0.068 |
Neg logit contributions | |
itton | -0.081 |
pez | -0.078 |
ocard | -0.077 |
atts | -0.072 |
ourage | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
itton | +0.658 |
pez | +0.637 |
ocard | +0.632 |
atts | +0.595 |
ourage | +0.591 |
Neg logit contributions | |
Masquerade | -0.520 |
Goat | -0.500 |
Caps | -0.468 |
================================================================ | -0.457 |
� | -0.445 |
Token | Airbus |
Token ID | 39173 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
itton | +0.670 |
pez | +0.650 |
ocard | +0.643 |
atts | +0.607 |
ourage | +0.600 |
Neg logit contributions | |
Masquerade | -0.564 |
Goat | -0.542 |
Caps | -0.507 |
================================================================ | -0.499 |
� | -0.485 |
Token | later |
Token ID | 1568 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
itton | +1.970 |
pez | +1.908 |
ocard | +1.886 |
atts | +1.779 |
ourage | +1.757 |
Neg logit contributions | |
Masquerade | -1.772 |
Goat | -1.703 |
Caps | -1.592 |
================================================================ | -1.574 |
� | -1.533 |
Token | rede |
Token ID | 21459 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
itton | +0.148 |
pez | +0.144 |
ocard | +0.143 |
atts | +0.133 |
ourage | +0.132 |
Neg logit contributions | |
Masquerade | -0.133 |
Goat | -0.129 |
Caps | -0.122 |
================================================================ | -0.118 |
� | -0.115 |
Token | - |
Token ID | 532 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
itton | +3.360 |
pez | +3.326 |
ocard | +3.246 |
atts | +2.981 |
ourage | +2.855 |
Neg logit contributions | |
Masquerade | -8.014 |
Goat | -7.750 |
Caps | -7.347 |
� | -7.323 |
================================================================ | -7.258 |
Token | signed |
Token ID | 4488 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
itton | +0.265 |
pez | +0.256 |
ocard | +0.253 |
atts | +0.237 |
ourage | +0.235 |
Neg logit contributions | |
Masquerade | -0.259 |
Goat | -0.250 |
Caps | -0.236 |
================================================================ | -0.233 |
� | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
Masquerade | +1.096 |
Goat | +1.061 |
Caps | +0.999 |
================================================================ | +0.966 |
� | +0.948 |
Neg logit contributions | |
itton | -1.254 |
pez | -1.220 |
ocard | -1.203 |
atts | -1.133 |
ourage | -1.124 |
Token | algorithm |
Token ID | 11862 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
Masquerade | +0.091 |
Goat | +0.088 |
Caps | +0.083 |
================================================================ | +0.081 |
� | +0.079 |
Neg logit contributions | |
itton | -0.095 |
pez | -0.092 |
ocard | -0.091 |
atts | -0.085 |
ourage | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Masquerade | +1.281 |
Goat | +1.234 |
Caps | +1.158 |
================================================================ | +1.126 |
� | +1.095 |
Neg logit contributions | |
itton | -1.635 |
pez | -1.585 |
ocard | -1.561 |
atts | -1.476 |
ourage | -1.468 |
Token | when |
Token ID | 618 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Masquerade | +1.950 |
Goat | +1.890 |
Caps | +1.756 |
================================================================ | +1.727 |
� | +1.669 |
Neg logit contributions | |
itton | -2.371 |
ocard | -2.286 |
pez | -2.283 |
atts | -2.154 |
ourage | -2.125 |
Token | I |
Token ID | 314 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Masquerade | +0.158 |
Goat | +0.153 |
Caps | +0.143 |
================================================================ | +0.139 |
� | +0.136 |
Neg logit contributions | |
itton | -0.194 |
pez | -0.188 |
ocard | -0.186 |
atts | -0.176 |
ourage | -0.175 |
Token | ordered |
Token ID | 6149 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
Masquerade | +0.365 |
Goat | +0.354 |
Caps | +0.331 |
================================================================ | +0.323 |
� | +0.312 |
Neg logit contributions | |
itton | -0.461 |
pez | -0.446 |
ocard | -0.442 |
atts | -0.418 |
ourage | -0.415 |
Token | the |
Token ID | 262 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
itton | +1.235 |
pez | +1.196 |
ocard | +1.182 |
atts | +1.113 |
ourage | +1.100 |
Neg logit contributions | |
Masquerade | -1.122 |
Goat | -1.079 |
Caps | -1.011 |
================================================================ | -0.997 |
� | -0.972 |
Token | Y |
Token ID | 575 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
itton | +0.069 |
pez | +0.067 |
ocard | +0.066 |
atts | +0.062 |
ourage | +0.062 |
Neg logit contributions | |
Masquerade | -0.056 |
Goat | -0.054 |
Caps | -0.050 |
================================================================ | -0.049 |
� | -0.048 |
Token | YR |
Token ID | 38162 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
itton | +1.098 |
pez | +1.058 |
ocard | +1.044 |
atts | +0.974 |
ourage | +0.961 |
Neg logit contributions | |
Masquerade | -1.309 |
Goat | -1.267 |
Caps | -1.197 |
================================================================ | -1.182 |
� | -1.158 |
Token | Diff |
Token ID | 10631 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
itton | +5.713 |
pez | +5.531 |
ocard | +5.400 |
atts | +5.076 |
ourage | +4.947 |
Neg logit contributions | |
Masquerade | -5.512 |
Goat | -5.165 |
================================================================ | -5.041 |
� | -4.843 |
mentation | -4.837 |
Token | usion |
Token ID | 4241 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
itton | +0.132 |
pez | +0.127 |
ocard | +0.126 |
atts | +0.118 |
ourage | +0.117 |
Neg logit contributions | |
Masquerade | -0.131 |
Goat | -0.126 |
Caps | -0.119 |
================================================================ | -0.117 |
� | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
itton | +0.107 |
pez | +0.104 |
ocard | +0.103 |
atts | +0.097 |
ourage | +0.096 |
Neg logit contributions | |
Masquerade | -0.090 |
Goat | -0.086 |
Caps | -0.081 |
================================================================ | -0.079 |
� | -0.077 |
Token | In |
Token ID | 554 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
itton | +0.573 |
pez | +0.555 |
ocard | +0.549 |
atts | +0.519 |
ourage | +0.513 |
Neg logit contributions | |
Masquerade | -0.482 |
Goat | -0.464 |
Caps | -0.434 |
================================================================ | -0.425 |
� | -0.413 |
Token | terms |
Token ID | 2846 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Masquerade | +0.038 |
Goat | +0.037 |
Caps | +0.035 |
================================================================ | +0.034 |
� | +0.033 |
Neg logit contributions | |
itton | -0.045 |
pez | -0.044 |
ocard | -0.043 |
atts | -0.041 |
ourage | -0.040 |
Token | me |
Token ID | 502 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
Masquerade | +0.027 |
Goat | +0.026 |
Caps | +0.024 |
================================================================ | +0.024 |
� | +0.023 |
Neg logit contributions | |
itton | -0.031 |
pez | -0.030 |
ocard | -0.030 |
atts | -0.028 |
ourage | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Masquerade | +0.061 |
Goat | +0.059 |
Caps | +0.055 |
================================================================ | +0.054 |
� | +0.052 |
Neg logit contributions | |
itton | -0.075 |
pez | -0.073 |
ocard | -0.072 |
atts | -0.068 |
ourage | -0.067 |
Token | what |
Token ID | 644 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
itton | +0.594 |
pez | +0.576 |
ocard | +0.569 |
atts | +0.538 |
ourage | +0.531 |
Neg logit contributions | |
Masquerade | -0.502 |
Goat | -0.483 |
Caps | -0.451 |
================================================================ | -0.443 |
� | -0.431 |
Token | is |
Token ID | 318 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
itton | +0.231 |
pez | +0.224 |
ocard | +0.221 |
atts | +0.209 |
ourage | +0.207 |
Neg logit contributions | |
Masquerade | -0.189 |
Goat | -0.181 |
Caps | -0.169 |
================================================================ | -0.166 |
� | -0.161 |
Token | this |
Token ID | 428 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
itton | +0.828 |
pez | +0.802 |
ocard | +0.793 |
atts | +0.747 |
ourage | +0.739 |
Neg logit contributions | |
Masquerade | -0.732 |
Goat | -0.704 |
Caps | -0.659 |
================================================================ | -0.649 |
� | -0.632 |
Token | quint |
Token ID | 28533 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
Masquerade | +0.860 |
Goat | +0.823 |
Caps | +0.765 |
================================================================ | +0.749 |
� | +0.725 |
Neg logit contributions | |
itton | -1.062 |
pez | -1.032 |
ocard | -1.021 |
atts | -0.967 |
ourage | -0.952 |
Token | ess |
Token ID | 408 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
itton | +3.762 |
pez | +3.538 |
ocard | +3.363 |
ourage | +3.156 |
atts | +3.043 |
Neg logit contributions | |
Masquerade | -7.635 |
Goat | -7.408 |
Caps | -7.078 |
================================================================ | -7.015 |
� | -6.888 |
Token | ence |
Token ID | 594 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
itton | +0.506 |
pez | +0.489 |
ocard | +0.482 |
atts | +0.448 |
ourage | +0.441 |
Neg logit contributions | |
Masquerade | -0.632 |
Goat | -0.612 |
Caps | -0.578 |
================================================================ | -0.571 |
� | -0.560 |
Token | of |
Token ID | 286 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
itton | +1.117 |
pez | +1.083 |
ocard | +1.070 |
atts | +1.010 |
ourage | +1.000 |
Neg logit contributions | |
Masquerade | -0.957 |
Goat | -0.920 |
Caps | -0.860 |
================================================================ | -0.850 |
� | -0.827 |
Token | dust |
Token ID | 8977 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
Masquerade | +0.087 |
Goat | +0.083 |
Caps | +0.078 |
================================================================ | +0.077 |
� | +0.075 |
Neg logit contributions | |
itton | -0.103 |
pez | -0.099 |
ocard | -0.098 |
atts | -0.093 |
ourage | -0.092 |
Token | ? |
Token ID | 30 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Masquerade | +0.059 |
Goat | +0.056 |
Caps | +0.052 |
================================================================ | +0.051 |
� | +0.050 |
Neg logit contributions | |
itton | -0.083 |
pez | -0.081 |
ocard | -0.080 |
atts | -0.076 |
ourage | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
itton | +0.912 |
pez | +0.884 |
ocard | +0.876 |
atts | +0.829 |
ourage | +0.820 |
Neg logit contributions | |
Masquerade | -0.701 |
Goat | -0.672 |
Caps | -0.625 |
================================================================ | -0.615 |
� | -0.598 |
Token | Some |
Token ID | 2773 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
itton | +0.360 |
pez | +0.349 |
ocard | +0.344 |
atts | +0.325 |
ourage | +0.321 |
Neg logit contributions | |
Masquerade | -0.301 |
Goat | -0.291 |
Caps | -0.273 |
================================================================ | -0.266 |
� | -0.258 |
Token | of |
Token ID | 286 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
itton | +0.857 |
pez | +0.830 |
ocard | +0.821 |
atts | +0.773 |
ourage | +0.765 |
Neg logit contributions | |
Masquerade | -0.761 |
Goat | -0.737 |
Caps | -0.692 |
================================================================ | -0.676 |
� | -0.663 |
Token | these |
Token ID | 777 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
itton | +0.305 |
pez | +0.294 |
ocard | +0.292 |
atts | +0.275 |
ourage | +0.272 |
Neg logit contributions | |
Masquerade | -0.262 |
Goat | -0.254 |
Caps | -0.238 |
================================================================ | -0.232 |
� | -0.227 |
Token | minor |
Token ID | 4159 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Masquerade | +0.711 |
Goat | +0.693 |
Caps | +0.654 |
================================================================ | +0.634 |
� | +0.624 |
Neg logit contributions | |
itton | -0.761 |
pez | -0.735 |
ocard | -0.725 |
atts | -0.684 |
ourage | -0.675 |
Token | overs |
Token ID | 10753 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Masquerade | +0.418 |
Goat | +0.406 |
Caps | +0.385 |
================================================================ | +0.375 |
� | +0.369 |
Neg logit contributions | |
itton | -0.391 |
pez | -0.377 |
ocard | -0.372 |
atts | -0.349 |
ourage | -0.344 |
Token | ights |
Token ID | 2337 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
itton | +2.743 |
pez | +2.606 |
ocard | +2.532 |
atts | +2.272 |
ourage | +2.191 |
Neg logit contributions | |
Masquerade | -8.173 |
Goat | -7.953 |
Caps | -7.609 |
================================================================ | -7.604 |
� | -7.506 |
Token | consisted |
Token ID | 19954 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
itton | +1.866 |
pez | +1.808 |
ocard | +1.788 |
atts | +1.687 |
ourage | +1.668 |
Neg logit contributions | |
Masquerade | -1.604 |
Goat | -1.542 |
Caps | -1.441 |
================================================================ | -1.421 |
� | -1.383 |
Token | of |
Token ID | 286 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
itton | +0.080 |
pez | +0.077 |
ocard | +0.076 |
atts | +0.071 |
ourage | +0.071 |
Neg logit contributions | |
Masquerade | -0.080 |
Goat | -0.077 |
Caps | -0.073 |
================================================================ | -0.071 |
� | -0.070 |
Token | such |
Token ID | 884 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
Masquerade | +0.886 |
Goat | +0.864 |
Caps | +0.816 |
================================================================ | +0.786 |
� | +0.771 |
Neg logit contributions | |
itton | -0.949 |
pez | -0.916 |
ocard | -0.908 |
atts | -0.849 |
ourage | -0.843 |
Token | trivial |
Token ID | 20861 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
itton | +0.174 |
pez | +0.169 |
ocard | +0.167 |
atts | +0.158 |
ourage | +0.156 |
Neg logit contributions | |
Masquerade | -0.140 |
Goat | -0.135 |
Caps | -0.126 |
================================================================ | -0.124 |
� | -0.121 |
Token | a |
Token ID | 257 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
itton | +1.058 |
pez | +1.025 |
ocard | +1.012 |
atts | +0.955 |
ourage | +0.945 |
Neg logit contributions | |
Masquerade | -0.925 |
Goat | -0.891 |
Caps | -0.834 |
================================================================ | -0.819 |
� | -0.798 |
Token | few |
Token ID | 1178 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
itton | +0.980 |
pez | +0.949 |
ocard | +0.937 |
atts | +0.884 |
ourage | +0.875 |
Neg logit contributions | |
Masquerade | -0.874 |
Goat | -0.842 |
Caps | -0.789 |
================================================================ | -0.775 |
� | -0.755 |
Token | copies |
Token ID | 9088 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Masquerade | +0.961 |
Goat | +0.930 |
Caps | +0.872 |
================================================================ | +0.851 |
� | +0.821 |
Neg logit contributions | |
itton | -1.135 |
pez | -1.097 |
ocard | -1.078 |
atts | -1.024 |
ourage | -1.019 |
Token | of |
Token ID | 286 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
itton | +1.933 |
pez | +1.868 |
ocard | +1.846 |
atts | +1.733 |
ourage | +1.703 |
Neg logit contributions | |
Masquerade | -1.968 |
Goat | -1.894 |
Caps | -1.778 |
================================================================ | -1.762 |
� | -1.720 |
Token | the |
Token ID | 262 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
itton | +0.448 |
pez | +0.435 |
ocard | +0.430 |
atts | +0.406 |
ourage | +0.402 |
Neg logit contributions | |
Masquerade | -0.362 |
Goat | -0.348 |
Caps | -0.324 |
================================================================ | -0.318 |
� | -0.310 |
Token | Canon |
Token ID | 19507 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
itton | +0.437 |
pez | +0.424 |
ocard | +0.419 |
atts | +0.397 |
ourage | +0.393 |
Neg logit contributions | |
Masquerade | -0.344 |
Goat | -0.330 |
Caps | -0.308 |
================================================================ | -0.302 |
� | -0.294 |
Token | 24 |
Token ID | 1987 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
itton | +5.572 |
pez | +5.348 |
ocard | +5.321 |
atts | +5.008 |
ourage | +4.939 |
Neg logit contributions | |
Masquerade | -5.180 |
Goat | -4.968 |
Caps | -4.625 |
================================================================ | -4.616 |
� | -4.501 |
Token | - |
Token ID | 12 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
itton | +0.064 |
pez | +0.062 |
ocard | +0.061 |
atts | +0.058 |
ourage | +0.058 |
Neg logit contributions | |
Masquerade | -0.046 |
Goat | -0.044 |
Caps | -0.041 |
================================================================ | -0.040 |
� | -0.039 |
Token | 70 |
Token ID | 2154 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
Masquerade | +0.097 |
Goat | +0.093 |
Caps | +0.087 |
================================================================ | +0.086 |
� | +0.084 |
Neg logit contributions | |
itton | -0.125 |
ocard | -0.121 |
pez | -0.120 |
atts | -0.114 |
ourage | -0.113 |
Token | Mk |
Token ID | 24798 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
itton | +1.284 |
pez | +1.244 |
ocard | +1.230 |
atts | +1.159 |
ourage | +1.145 |
Neg logit contributions | |
Masquerade | -1.153 |
Goat | -1.109 |
Caps | -1.038 |
================================================================ | -1.024 |
� | -0.998 |
Token | II |
Token ID | 2873 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
Masquerade | +1.035 |
Goat | +1.004 |
Caps | +0.941 |
================================================================ | +0.918 |
� | +0.906 |
Neg logit contributions | |
itton | -1.305 |
pez | -1.265 |
ocard | -1.259 |
ourage | -1.183 |
atts | -1.176 |
Token | : |
Token ID | 25 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
itton | +0.923 |
pez | +0.894 |
ocard | +0.884 |
atts | +0.833 |
ourage | +0.824 |
Neg logit contributions | |
Masquerade | -0.804 |
Goat | -0.773 |
Caps | -0.724 |
================================================================ | -0.713 |
� | -0.694 |
Token | Size |
Token ID | 12849 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Masquerade | +0.524 |
Goat | +0.502 |
Caps | +0.468 |
================================================================ | +0.456 |
� | +0.443 |
Neg logit contributions | |
itton | -0.739 |
pez | -0.717 |
ocard | -0.711 |
atts | -0.674 |
ourage | -0.667 |
Token | C |
Token ID | 327 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Masquerade | +0.388 |
Goat | +0.372 |
Caps | +0.348 |
================================================================ | +0.336 |
� | +0.326 |
Neg logit contributions | |
itton | -0.549 |
pez | -0.532 |
ocard | -0.529 |
atts | -0.500 |
ourage | -0.496 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
Masquerade | +1.410 |
Goat | +1.356 |
Caps | +1.271 |
================================================================ | +1.237 |
� | +1.210 |
Neg logit contributions | |
itton | -1.802 |
pez | -1.749 |
ocard | -1.739 |
atts | -1.641 |
ourage | -1.623 |
Token | Y |
Token ID | 575 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Masquerade | +0.103 |
Goat | +0.099 |
Caps | +0.094 |
================================================================ | +0.092 |
� | +0.090 |
Neg logit contributions | |
itton | -0.111 |
pez | -0.107 |
ocard | -0.106 |
atts | -0.100 |
ourage | -0.099 |
Token | YR |
Token ID | 38162 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
itton | +1.113 |
pez | +1.078 |
ocard | +1.067 |
atts | +1.006 |
ourage | +0.995 |
Neg logit contributions | |
Masquerade | -0.955 |
Goat | -0.919 |
Caps | -0.859 |
================================================================ | -0.845 |
� | -0.824 |
Token | DS |
Token ID | 17400 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
itton | +5.736 |
pez | +5.553 |
ocard | +5.420 |
atts | +5.137 |
ourage | +5.085 |
Neg logit contributions | |
Masquerade | -5.028 |
Goat | -4.725 |
================================================================ | -4.486 |
Caps | -4.405 |
acly | -4.266 |
Token | cent |
Token ID | 1247 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
itton | +1.669 |
pez | +1.615 |
ocard | +1.591 |
atts | +1.504 |
ourage | +1.488 |
Neg logit contributions | |
Masquerade | -1.400 |
Goat | -1.338 |
Caps | -1.243 |
================================================================ | -1.239 |
� | -1.200 |
Token | ering |
Token ID | 1586 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Masquerade | +0.372 |
Goat | +0.353 |
Caps | +0.322 |
================================================================ | +0.316 |
� | +0.304 |
Neg logit contributions | |
itton | -0.700 |
pez | -0.682 |
ocard | -0.676 |
atts | -0.644 |
ourage | -0.639 |
Token |
|
Token ID | 198 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
Masquerade | +0.838 |
Goat | +0.806 |
Caps | +0.754 |
================================================================ | +0.737 |
� | +0.720 |
Neg logit contributions | |
itton | -1.036 |
pez | -1.005 |
ocard | -0.996 |
atts | -0.940 |
ourage | -0.930 |
Token |
|
Token ID | 198 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
Masquerade | +0.011 |
Goat | +0.011 |
Caps | +0.010 |
================================================================ | +0.010 |
� | +0.009 |
Neg logit contributions | |
itton | -0.015 |
pez | -0.014 |
ocard | -0.014 |
atts | -0.013 |
ourage | -0.013 |
Token | back |
Token ID | 1891 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
itton | +1.231 |
pez | +1.188 |
ocard | +1.176 |
atts | +1.090 |
ourage | +1.076 |
Neg logit contributions | |
Masquerade | -1.602 |
Goat | -1.549 |
Caps | -1.467 |
================================================================ | -1.452 |
� | -1.426 |
Token | of |
Token ID | 286 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
itton | +0.192 |
pez | +0.184 |
ocard | +0.178 |
ourage | +0.169 |
atts | +0.169 |
Neg logit contributions | |
Masquerade | -0.160 |
Goat | -0.159 |
Caps | -0.150 |
================================================================ | -0.143 |
� | -0.138 |
Token | Notre |
Token ID | 23382 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Masquerade | +0.202 |
Goat | +0.200 |
Caps | +0.189 |
================================================================ | +0.185 |
� | +0.181 |
Neg logit contributions | |
itton | -0.169 |
pez | -0.163 |
ocard | -0.157 |
atts | -0.149 |
ourage | -0.147 |
Token | Dame |
Token ID | 20377 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
itton | +1.642 |
pez | +1.594 |
ocard | +1.532 |
atts | +1.392 |
ourage | +1.375 |
Neg logit contributions | |
Masquerade | -3.453 |
Goat | -3.351 |
================================================================ | -3.245 |
Caps | -3.218 |
acly | -3.153 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
itton | +2.121 |
pez | +2.062 |
ocard | +2.028 |
atts | +1.928 |
ourage | +1.911 |
Neg logit contributions | |
Masquerade | -1.581 |
Goat | -1.507 |
Caps | -1.405 |
================================================================ | -1.392 |
� | -1.344 |
Token | Nightmare |
Token ID | 23951 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Masquerade | +0.198 |
Goat | +0.190 |
Caps | +0.176 |
================================================================ | +0.172 |
� | +0.167 |
Neg logit contributions | |
itton | -0.278 |
pez | -0.271 |
ocard | -0.268 |
atts | -0.254 |
ourage | -0.251 |
Token | on |
Token ID | 319 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
itton | +5.218 |
pez | +4.957 |
ocard | +4.919 |
atts | +4.685 |
ourage | +4.593 |
Neg logit contributions | |
Masquerade | -5.538 |
Goat | -5.330 |
Caps | -5.045 |
================================================================ | -5.044 |
� | -4.894 |
Token | Elm |
Token ID | 35189 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
itton | +0.496 |
pez | +0.477 |
ocard | +0.476 |
atts | +0.434 |
ourage | +0.427 |
Neg logit contributions | |
Masquerade | -0.645 |
Goat | -0.639 |
Caps | -0.598 |
================================================================ | -0.579 |
� | -0.575 |
Token | Street |
Token ID | 3530 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
Masquerade | +0.128 |
Goat | +0.124 |
Caps | +0.114 |
================================================================ | +0.112 |
� | +0.109 |
Neg logit contributions | |
itton | -0.163 |
pez | -0.159 |
ocard | -0.157 |
atts | -0.148 |
ourage | -0.146 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
itton | +0.013 |
pez | +0.012 |
ocard | +0.012 |
atts | +0.012 |
ourage | +0.012 |
Neg logit contributions | |
Masquerade | -0.009 |
Goat | -0.009 |
Caps | -0.008 |
================================================================ | -0.008 |
� | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Masquerade | +0.266 |
Goat | +0.256 |
Caps | +0.236 |
================================================================ | +0.231 |
� | +0.224 |
Neg logit contributions | |
itton | -0.370 |
pez | -0.360 |
ocard | -0.356 |
atts | -0.337 |
ourage | -0.333 |
Token | , |
Token ID | 11 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
Masquerade | +0.165 |
Goat | +0.160 |
Caps | +0.149 |
================================================================ | +0.147 |
� | +0.143 |
Neg logit contributions | |
itton | -0.186 |
pez | -0.179 |
ocard | -0.178 |
atts | -0.166 |
ourage | -0.166 |
Token | according |
Token ID | 1864 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
itton | +0.786 |
pez | +0.768 |
ocard | +0.759 |
atts | +0.711 |
ourage | +0.701 |
Neg logit contributions | |
Masquerade | -0.731 |
Goat | -0.706 |
Caps | -0.661 |
================================================================ | -0.647 |
� | -0.632 |
Token | to |
Token ID | 284 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Masquerade | +0.020 |
Goat | +0.020 |
Caps | +0.018 |
================================================================ | +0.018 |
� | +0.017 |
Neg logit contributions | |
itton | -0.031 |
pez | -0.030 |
ocard | -0.030 |
atts | -0.028 |
ourage | -0.028 |
Token | one |
Token ID | 530 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
itton | +0.185 |
pez | +0.182 |
ocard | +0.180 |
atts | +0.168 |
ourage | +0.166 |
Neg logit contributions | |
Masquerade | -0.174 |
Goat | -0.168 |
Caps | -0.158 |
================================================================ | -0.153 |
� | -0.151 |
Token | of |
Token ID | 286 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
itton | +0.671 |
pez | +0.652 |
ocard | +0.646 |
atts | +0.607 |
ourage | +0.601 |
Neg logit contributions | |
Masquerade | -0.589 |
Goat | -0.567 |
Caps | -0.531 |
================================================================ | -0.522 |
� | -0.508 |
Token | Lois |
Token ID | 42879 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
itton | +0.587 |
pez | +0.570 |
ocard | +0.563 |
atts | +0.530 |
ourage | +0.525 |
Neg logit contributions | |
Masquerade | -0.519 |
Goat | -0.501 |
Caps | -0.468 |
================================================================ | -0.459 |
� | -0.449 |
Token | G |
Token ID | 402 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
itton | +4.064 |
pez | +3.689 |
ocard | +3.663 |
atts | +3.416 |
ourage | +3.278 |
Neg logit contributions | |
Masquerade | -6.583 |
Goat | -6.364 |
================================================================ | -6.109 |
Caps | -6.046 |
� | -5.986 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Masquerade | +0.582 |
Goat | +0.558 |
Caps | +0.517 |
================================================================ | +0.504 |
� | +0.491 |
Neg logit contributions | |
itton | -0.844 |
pez | -0.824 |
ocard | -0.814 |
atts | -0.774 |
ourage | -0.764 |
Token | Lerner |
Token ID | 49750 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
itton | +0.483 |
pez | +0.462 |
ocard | +0.454 |
atts | +0.424 |
ourage | +0.419 |
Neg logit contributions | |
Masquerade | -0.628 |
Goat | -0.606 |
Caps | -0.574 |
================================================================ | -0.572 |
� | -0.560 |
Token | � |
Token ID | 447 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
itton | +4.218 |
pez | +4.088 |
ocard | +3.983 |
atts | +3.852 |
ourage | +3.782 |
Neg logit contributions | |
Masquerade | -3.610 |
Goat | -3.448 |
Caps | -3.224 |
================================================================ | -3.208 |
� | -3.106 |
Token | � |
Token ID | 247 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
itton | +0.328 |
pez | +0.320 |
ocard | +0.318 |
atts | +0.303 |
ourage | +0.301 |
Neg logit contributions | |
Masquerade | -0.150 |
Goat | -0.143 |
Caps | -0.128 |
================================================================ | -0.126 |
� | -0.126 |
Token | never |
Token ID | 1239 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Masquerade | +0.088 |
Goat | +0.084 |
Caps | +0.079 |
================================================================ | +0.078 |
� | +0.076 |
Neg logit contributions | |
itton | -0.094 |
pez | -0.091 |
ocard | -0.091 |
atts | -0.085 |
ourage | -0.084 |
Token | occurred |
Token ID | 5091 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Masquerade | +0.452 |
Goat | +0.434 |
Caps | +0.404 |
================================================================ | +0.395 |
� | +0.384 |
Neg logit contributions | |
itton | -0.589 |
pez | -0.572 |
ocard | -0.568 |
atts | -0.534 |
ourage | -0.530 |
Token | before |
Token ID | 878 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Masquerade | +0.789 |
Goat | +0.756 |
Caps | +0.702 |
================================================================ | +0.684 |
� | +0.666 |
Neg logit contributions | |
itton | -1.149 |
ocard | -1.102 |
pez | -1.101 |
atts | -1.043 |
ourage | -1.035 |
Token | - |
Token ID | 532 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Masquerade | +0.349 |
Goat | +0.335 |
Caps | +0.313 |
================================================================ | +0.307 |
� | +0.296 |
Neg logit contributions | |
itton | -0.448 |
pez | -0.431 |
ocard | -0.430 |
atts | -0.407 |
ourage | -0.402 |
Token | A |
Token ID | 317 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Masquerade | +0.051 |
Goat | +0.049 |
Caps | +0.045 |
================================================================ | +0.044 |
� | +0.043 |
Neg logit contributions | |
itton | -0.065 |
pez | -0.063 |
ocard | -0.063 |
atts | -0.059 |
ourage | -0.059 |
Token | Nightmare |
Token ID | 23951 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Masquerade | +1.557 |
Goat | +1.495 |
Caps | +1.385 |
================================================================ | +1.358 |
� | +1.320 |
Neg logit contributions | |
itton | -1.806 |
pez | -1.759 |
ocard | -1.738 |
atts | -1.636 |
ourage | -1.624 |
Token | on |
Token ID | 319 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
itton | +5.045 |
pez | +4.754 |
ocard | +4.752 |
atts | +4.460 |
ourage | +4.387 |
Neg logit contributions | |
Masquerade | -5.501 |
Goat | -5.348 |
Caps | -5.081 |
================================================================ | -5.072 |
� | -4.966 |
Token | Elm |
Token ID | 35189 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
itton | +0.087 |
pez | +0.084 |
ocard | +0.083 |
atts | +0.077 |
ourage | +0.075 |
Neg logit contributions | |
Masquerade | -0.124 |
Goat | -0.121 |
Caps | -0.114 |
================================================================ | -0.112 |
� | -0.111 |
Token | Street |
Token ID | 3530 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Masquerade | +0.456 |
Goat | +0.441 |
Caps | +0.407 |
================================================================ | +0.400 |
� | +0.389 |
Neg logit contributions | |
itton | -0.583 |
pez | -0.569 |
ocard | -0.562 |
atts | -0.530 |
ourage | -0.523 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Masquerade | +0.359 |
Goat | +0.343 |
Caps | +0.320 |
================================================================ | +0.313 |
� | +0.304 |
Neg logit contributions | |
itton | -0.467 |
pez | -0.452 |
ocard | -0.449 |
atts | -0.424 |
ourage | -0.419 |
Token | Friday |
Token ID | 3217 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
Masquerade | +0.206 |
Goat | +0.198 |
Caps | +0.185 |
================================================================ | +0.181 |
� | +0.175 |
Neg logit contributions | |
itton | -0.235 |
pez | -0.227 |
ocard | -0.226 |
atts | -0.213 |
ourage | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Masquerade | +0.366 |
Goat | +0.351 |
Caps | +0.326 |
================================================================ | +0.319 |
� | +0.313 |
Neg logit contributions | |
itton | -0.502 |
pez | -0.486 |
ocard | -0.482 |
atts | -0.455 |
ourage | -0.452 |
Token | The |
Token ID | 383 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
itton | +0.121 |
pez | +0.117 |
ocard | +0.116 |
atts | +0.110 |
ourage | +0.109 |
Neg logit contributions | |
Masquerade | -0.097 |
Goat | -0.093 |
Caps | -0.087 |
================================================================ | -0.085 |
� | -0.083 |
Token | list |
Token ID | 1351 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Masquerade | +0.153 |
Goat | +0.147 |
Caps | +0.138 |
================================================================ | +0.135 |
� | +0.132 |
Neg logit contributions | |
itton | -0.172 |
pez | -0.166 |
ocard | -0.164 |
atts | -0.155 |
ourage | -0.153 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
itton | +0.251 |
pez | +0.244 |
ocard | +0.240 |
atts | +0.226 |
ourage | +0.224 |
Neg logit contributions | |
Masquerade | -0.222 |
Goat | -0.215 |
Caps | -0.201 |
================================================================ | -0.198 |
� | -0.193 |
Token | egregious |
Token ID | 34372 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
Masquerade | +0.221 |
Goat | +0.214 |
Caps | +0.201 |
================================================================ | +0.196 |
� | +0.193 |
Neg logit contributions | |
itton | -0.248 |
pez | -0.240 |
ocard | -0.238 |
atts | -0.223 |
ourage | -0.221 |
Token | overs |
Token ID | 10753 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
itton | +1.176 |
pez | +1.137 |
ocard | +1.123 |
atts | +1.055 |
ourage | +1.042 |
Neg logit contributions | |
Masquerade | -1.190 |
Goat | -1.146 |
Caps | -1.077 |
================================================================ | -1.065 |
� | -1.038 |
Token | ights |
Token ID | 2337 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
itton | +2.311 |
pez | +2.138 |
ocard | +2.077 |
atts | +1.834 |
ourage | +1.747 |
Neg logit contributions | |
Masquerade | -8.277 |
Goat | -8.116 |
Caps | -7.760 |
================================================================ | -7.725 |
� | -7.626 |
Token | by |
Token ID | 416 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
itton | +1.690 |
pez | +1.638 |
ocard | +1.620 |
atts | +1.530 |
ourage | +1.513 |
Neg logit contributions | |
Masquerade | -1.447 |
Goat | -1.389 |
Caps | -1.298 |
================================================================ | -1.281 |
� | -1.247 |
Token | the |
Token ID | 262 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
itton | +0.636 |
pez | +0.616 |
ocard | +0.609 |
atts | +0.574 |
ourage | +0.567 |
Neg logit contributions | |
Masquerade | -0.568 |
Goat | -0.548 |
Caps | -0.513 |
================================================================ | -0.504 |
� | -0.492 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Masquerade | +0.156 |
Goat | +0.150 |
Caps | +0.141 |
================================================================ | +0.137 |
� | +0.134 |
Neg logit contributions | |
itton | -0.176 |
pez | -0.170 |
ocard | -0.168 |
atts | -0.158 |
ourage | -0.157 |
Token | that |
Token ID | 326 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Masquerade | +0.434 |
Goat | +0.417 |
Caps | +0.389 |
================================================================ | +0.383 |
� | +0.372 |
Neg logit contributions | |
itton | -0.543 |
pez | -0.527 |
ocard | -0.521 |
atts | -0.492 |
ourage | -0.486 |
Token | - |
Token ID | 12 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
itton | +2.092 |
pez | +2.019 |
ocard | +1.991 |
atts | +1.862 |
ourage | +1.838 |
Neg logit contributions | |
Masquerade | -2.337 |
Goat | -2.258 |
Caps | -2.131 |
================================================================ | -2.104 |
� | -2.056 |
Token | pres |
Token ID | 18302 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
itton | +0.163 |
pez | +0.157 |
ocard | +0.154 |
atts | +0.145 |
ourage | +0.142 |
Neg logit contributions | |
Masquerade | -0.167 |
Goat | -0.160 |
Caps | -0.152 |
================================================================ | -0.152 |
� | -0.147 |
Token | cript |
Token ID | 6519 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
itton | +1.531 |
pez | +1.460 |
ocard | +1.433 |
atts | +1.319 |
ourage | +1.292 |
Neg logit contributions | |
Masquerade | -2.556 |
Goat | -2.486 |
Caps | -2.368 |
================================================================ | -2.340 |
� | -2.301 |
Token | ive |
Token ID | 425 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Masquerade | +0.578 |
Goat | +0.551 |
Caps | +0.508 |
================================================================ | +0.497 |
� | +0.481 |
Neg logit contributions | |
itton | -0.982 |
pez | -0.956 |
ocard | -0.948 |
atts | -0.901 |
ourage | -0.893 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Masquerade | +1.503 |
Goat | +1.455 |
Caps | +1.396 |
================================================================ | +1.347 |
mentation | +1.321 |
Neg logit contributions | |
itton | -1.269 |
pez | -1.217 |
ocard | -1.187 |
atts | -1.110 |
ourage | -1.099 |
Token | overs |
Token ID | 10753 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Masquerade | +0.278 |
Goat | +0.269 |
Caps | +0.255 |
================================================================ | +0.250 |
� | +0.245 |
Neg logit contributions | |
itton | -0.271 |
pez | -0.261 |
ocard | -0.256 |
atts | -0.241 |
ourage | -0.237 |
Token | impl |
Token ID | 23928 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
itton | +4.837 |
pez | +4.701 |
ocard | +4.621 |
atts | +4.343 |
ourage | +4.263 |
Neg logit contributions | |
Masquerade | -5.655 |
Goat | -5.484 |
Caps | -5.157 |
================================================================ | -5.102 |
� | -4.998 |
Token | ified |
Token ID | 1431 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
itton | +1.859 |
pez | +1.786 |
ocard | +1.752 |
atts | +1.618 |
ourage | +1.603 |
Neg logit contributions | |
Masquerade | -2.904 |
Goat | -2.826 |
Caps | -2.668 |
================================================================ | -2.637 |
� | -2.586 |
Token | recommendations |
Token ID | 10763 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Masquerade | +1.189 |
Goat | +1.149 |
Caps | +1.100 |
================================================================ | +1.063 |
� | +1.041 |
Neg logit contributions | |
itton | -1.000 |
pez | -0.956 |
ocard | -0.936 |
atts | -0.873 |
ourage | -0.867 |
Token | that |
Token ID | 326 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
Masquerade | +0.139 |
Goat | +0.134 |
Caps | +0.124 |
================================================================ | +0.122 |
� | +0.118 |
Neg logit contributions | |
itton | -0.193 |
pez | -0.187 |
ocard | -0.185 |
atts | -0.175 |
ourage | -0.174 |
Token | force |
Token ID | 2700 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
itton | +0.169 |
pez | +0.163 |
ocard | +0.160 |
atts | +0.152 |
ourage | +0.149 |
Neg logit contributions | |
Masquerade | -0.145 |
Goat | -0.139 |
Caps | -0.131 |
================================================================ | -0.127 |
� | -0.124 |
Token | population |
Token ID | 3265 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
Masquerade | +0.765 |
Goat | +0.737 |
Caps | +0.696 |
================================================================ | +0.680 |
� | +0.659 |
Neg logit contributions | |
itton | -0.866 |
pez | -0.835 |
ocard | -0.822 |
atts | -0.774 |
ourage | -0.772 |
Token | becomes |
Token ID | 4329 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
Masquerade | +1.156 |
Goat | +1.098 |
Caps | +1.034 |
================================================================ | +0.990 |
mentation | +0.956 |
Neg logit contributions | |
itton | -2.039 |
pez | -1.980 |
ocard | -1.955 |
ourage | -1.858 |
atts | -1.845 |
Token | older |
Token ID | 4697 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Masquerade | +1.247 |
Goat | +1.187 |
Caps | +1.100 |
================================================================ | +1.070 |
� | +1.046 |
Neg logit contributions | |
itton | -2.045 |
pez | -1.994 |
ocard | -1.961 |
ourage | -1.855 |
atts | -1.853 |
Token | and |
Token ID | 290 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Masquerade | +0.590 |
Goat | +0.565 |
Caps | +0.524 |
================================================================ | +0.513 |
� | +0.499 |
Neg logit contributions | |
itton | -0.856 |
pez | -0.829 |
ocard | -0.823 |
atts | -0.778 |
ourage | -0.772 |
Token | more |
Token ID | 517 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
Masquerade | +0.322 |
Goat | +0.308 |
Caps | +0.287 |
================================================================ | +0.282 |
� | +0.273 |
Neg logit contributions | |
itton | -0.426 |
pez | -0.413 |
ocard | -0.408 |
atts | -0.385 |
ourage | -0.383 |
Token | ethn |
Token ID | 33961 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
itton | +0.150 |
pez | +0.145 |
ocard | +0.143 |
atts | +0.135 |
ourage | +0.133 |
Neg logit contributions | |
Masquerade | -0.134 |
Goat | -0.128 |
Caps | -0.120 |
================================================================ | -0.119 |
� | -0.116 |
Token | ically |
Token ID | 1146 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
itton | +2.434 |
ocard | +2.396 |
pez | +2.327 |
ourage | +1.951 |
atts | +1.947 |
Neg logit contributions | |
Masquerade | -8.050 |
Goat | -7.813 |
Caps | -7.455 |
================================================================ | -7.338 |
� | -7.217 |
Token | diverse |
Token ID | 10084 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
itton | +0.543 |
pez | +0.526 |
ocard | +0.520 |
atts | +0.492 |
ourage | +0.486 |
Neg logit contributions | |
Masquerade | -0.445 |
Goat | -0.427 |
Caps | -0.399 |
================================================================ | -0.393 |
� | -0.382 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Masquerade | +0.037 |
Goat | +0.036 |
Caps | +0.034 |
================================================================ | +0.033 |
� | +0.032 |
Neg logit contributions | |
itton | -0.047 |
pez | -0.046 |
ocard | -0.045 |
atts | -0.043 |
ourage | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
itton | +0.532 |
pez | +0.515 |
ocard | +0.509 |
atts | +0.480 |
ourage | +0.474 |
Neg logit contributions | |
Masquerade | -0.472 |
Goat | -0.455 |
Caps | -0.426 |
================================================================ | -0.419 |
� | -0.409 |
Token | additional |
Token ID | 3224 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
itton | +0.148 |
pez | +0.144 |
ocard | +0.141 |
atts | +0.133 |
ourage | +0.131 |
Neg logit contributions | |
Masquerade | -0.142 |
Goat | -0.137 |
Caps | -0.129 |
================================================================ | -0.126 |
� | -0.123 |
Token | Po |
Token ID | 18833 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Masquerade | +1.094 |
Goat | +1.042 |
Caps | +0.966 |
================================================================ | +0.948 |
� | +0.891 |
Neg logit contributions | |
itton | -1.885 |
pez | -1.864 |
ocard | -1.807 |
ourage | -1.725 |
atts | -1.698 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
itton | +2.549 |
pez | +2.473 |
ocard | +2.449 |
atts | +2.329 |
ourage | +2.296 |
Neg logit contributions | |
Masquerade | -1.844 |
Goat | -1.764 |
Caps | -1.634 |
================================================================ | -1.616 |
� | -1.565 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
itton | +0.239 |
pez | +0.232 |
ocard | +0.229 |
atts | +0.217 |
ourage | +0.214 |
Neg logit contributions | |
Masquerade | -0.197 |
Goat | -0.189 |
Caps | -0.177 |
================================================================ | -0.173 |
� | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
itton | +0.321 |
pez | +0.311 |
ocard | +0.308 |
atts | +0.291 |
ourage | +0.288 |
Neg logit contributions | |
Masquerade | -0.245 |
Goat | -0.236 |
Caps | -0.221 |
================================================================ | -0.218 |
� | -0.209 |
Token | Business |
Token ID | 24749 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
itton | +0.161 |
pez | +0.155 |
ocard | +0.153 |
atts | +0.144 |
ourage | +0.143 |
Neg logit contributions | |
Masquerade | -0.145 |
Goat | -0.140 |
Caps | -0.132 |
================================================================ | -0.131 |
� | -0.127 |
Token | Insider |
Token ID | 22167 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Masquerade | +0.345 |
Goat | +0.335 |
Caps | +0.319 |
================================================================ | +0.315 |
� | +0.308 |
Neg logit contributions | |
itton | -0.262 |
pez | -0.254 |
ocard | -0.251 |
atts | -0.231 |
ourage | -0.228 |
Token | explains |
Token ID | 6688 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
itton | +4.995 |
pez | +4.840 |
ocard | +4.777 |
atts | +4.509 |
ourage | +4.454 |
Neg logit contributions | |
Masquerade | -5.185 |
Goat | -4.966 |
================================================================ | -4.679 |
Caps | -4.640 |
� | -4.591 |
Token | : |
Token ID | 25 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
Masquerade | +0.965 |
Goat | +0.926 |
Caps | +0.866 |
================================================================ | +0.843 |
� | +0.824 |
Neg logit contributions | |
itton | -1.261 |
pez | -1.220 |
ocard | -1.209 |
atts | -1.141 |
ourage | -1.129 |
Token | " |
Token ID | 366 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Masquerade | +0.038 |
Goat | +0.037 |
Caps | +0.035 |
================================================================ | +0.034 |
� | +0.033 |
Neg logit contributions | |
itton | -0.047 |
pez | -0.046 |
ocard | -0.045 |
atts | -0.043 |
ourage | -0.042 |
Token | Ess |
Token ID | 29508 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
itton | +0.841 |
pez | +0.813 |
ocard | +0.804 |
atts | +0.753 |
ourage | +0.744 |
Neg logit contributions | |
Masquerade | -0.855 |
Goat | -0.825 |
Caps | -0.777 |
================================================================ | -0.767 |
� | -0.748 |
Token | entially |
Token ID | 3746 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
itton | +3.235 |
pez | +3.065 |
ocard | +2.997 |
atts | +2.763 |
ourage | +2.755 |
Neg logit contributions | |
Masquerade | -5.306 |
Goat | -5.121 |
Caps | -4.836 |
================================================================ | -4.814 |
� | -4.666 |
Token | country |
Token ID | 1499 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Masquerade | +0.395 |
Goat | +0.382 |
Caps | +0.362 |
================================================================ | +0.358 |
� | +0.350 |
Neg logit contributions | |
itton | -0.315 |
pez | -0.303 |
ocard | -0.299 |
atts | -0.278 |
ourage | -0.274 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Masquerade | +0.868 |
Goat | +0.836 |
Caps | +0.778 |
================================================================ | +0.764 |
� | +0.742 |
Neg logit contributions | |
itton | -1.144 |
pez | -1.107 |
ocard | -1.104 |
atts | -1.042 |
ourage | -1.025 |
Token | there |
Token ID | 612 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
itton | +0.339 |
pez | +0.329 |
ocard | +0.326 |
atts | +0.308 |
ourage | +0.304 |
Neg logit contributions | |
Masquerade | -0.268 |
Goat | -0.257 |
Caps | -0.240 |
================================================================ | -0.236 |
� | -0.229 |
Token | is |
Token ID | 318 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
Masquerade | +1.236 |
Goat | +1.195 |
Caps | +1.109 |
================================================================ | +1.080 |
mentation | +1.057 |
Neg logit contributions | |
itton | -1.774 |
pez | -1.716 |
ocard | -1.700 |
atts | -1.612 |
ourage | -1.589 |
Token | some |
Token ID | 617 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Masquerade | +0.113 |
Goat | +0.109 |
Caps | +0.102 |
================================================================ | +0.100 |
� | +0.098 |
Neg logit contributions | |
itton | -0.124 |
pez | -0.120 |
ocard | -0.119 |
atts | -0.111 |
ourage | -0.110 |
Token | une |
Token ID | 17809 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Masquerade | +0.169 |
Goat | +0.162 |
Caps | +0.152 |
================================================================ | +0.149 |
� | +0.145 |
Neg logit contributions | |
itton | -0.194 |
pez | -0.188 |
ocard | -0.186 |
atts | -0.175 |
ourage | -0.173 |
Token | ase |
Token ID | 589 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
itton | +4.329 |
pez | +4.155 |
ocard | +4.073 |
atts | +3.841 |
ourage | +3.828 |
Neg logit contributions | |
Masquerade | -5.744 |
Goat | -5.646 |
Caps | -5.300 |
� | -5.183 |
================================================================ | -5.173 |
Token | about |
Token ID | 546 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Masquerade | +0.758 |
Goat | +0.731 |
Caps | +0.688 |
================================================================ | +0.676 |
� | +0.654 |
Neg logit contributions | |
itton | -0.748 |
pez | -0.717 |
ocard | -0.711 |
atts | -0.666 |
ourage | -0.653 |
Token | their |
Token ID | 511 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
itton | +0.187 |
pez | +0.181 |
ocard | +0.180 |
atts | +0.170 |
ourage | +0.168 |
Neg logit contributions | |
Masquerade | -0.152 |
Goat | -0.146 |
Caps | -0.137 |
================================================================ | -0.134 |
� | -0.131 |
Token | ambition |
Token ID | 20505 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
itton | +0.661 |
pez | +0.640 |
ocard | +0.631 |
atts | +0.592 |
ourage | +0.585 |
Neg logit contributions | |
Masquerade | -0.659 |
Goat | -0.634 |
Caps | -0.597 |
================================================================ | -0.587 |
� | -0.572 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Masquerade | +0.385 |
Goat | +0.368 |
Caps | +0.342 |
================================================================ | +0.336 |
� | +0.325 |
Neg logit contributions | |
itton | -0.534 |
pez | -0.517 |
ocard | -0.513 |
atts | -0.485 |
ourage | -0.480 |
Token | prescribed |
Token ID | 14798 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
itton | +2.953 |
pez | +2.930 |
ocard | +2.820 |
atts | +2.611 |
ourage | +2.570 |
Neg logit contributions | |
Masquerade | -4.306 |
Goat | -4.152 |
================================================================ | -3.938 |
Caps | -3.909 |
� | -3.837 |
Token | therapeutic |
Token ID | 21546 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
itton | +2.519 |
pez | +2.449 |
ocard | +2.418 |
atts | +2.234 |
ourage | +2.223 |
Neg logit contributions | |
Masquerade | -3.000 |
Goat | -2.889 |
================================================================ | -2.718 |
Caps | -2.714 |
� | -2.660 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
itton | +0.814 |
pez | +0.781 |
ocard | +0.772 |
atts | +0.720 |
ourage | +0.710 |
Neg logit contributions | |
Masquerade | -0.996 |
Goat | -0.965 |
Caps | -0.915 |
================================================================ | -0.901 |
� | -0.880 |
Token | RI |
Token ID | 7112 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
itton | +3.843 |
pez | +3.743 |
ocard | +3.704 |
atts | +3.480 |
ourage | +3.455 |
Neg logit contributions | |
Masquerade | -2.759 |
Goat | -2.597 |
Caps | -2.407 |
================================================================ | -2.394 |
� | -2.289 |
Token | or |
Token ID | 393 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Masquerade | +0.860 |
Goat | +0.829 |
Caps | +0.779 |
================================================================ | +0.756 |
� | +0.733 |
Neg logit contributions | |
itton | -1.192 |
pez | -1.146 |
ocard | -1.140 |
atts | -1.085 |
ourage | -1.069 |
Token | benz |
Token ID | 39601 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
itton | +0.583 |
pez | +0.560 |
ocard | +0.553 |
atts | +0.520 |
ourage | +0.511 |
Neg logit contributions | |
Masquerade | -0.641 |
Goat | -0.621 |
Caps | -0.586 |
================================================================ | -0.576 |
� | -0.563 |
Token | od |
Token ID | 375 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
itton | +5.688 |
pez | +5.640 |
ocard | +5.608 |
atts | +5.209 |
ourage | +5.208 |
Neg logit contributions | |
Masquerade | -4.435 |
Goat | -4.260 |
Caps | -3.936 |
================================================================ | -3.839 |
� | -3.767 |
Token | iazep |
Token ID | 48826 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
itton | +0.312 |
pez | +0.291 |
ocard | +0.286 |
atts | +0.258 |
ourage | +0.247 |
Neg logit contributions | |
Masquerade | -0.756 |
Goat | -0.741 |
Caps | -0.711 |
================================================================ | -0.706 |
� | -0.691 |
Token | ine |
Token ID | 500 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
itton | +1.620 |
pez | +1.569 |
ocard | +1.549 |
atts | +1.450 |
ourage | +1.439 |
Neg logit contributions | |
Masquerade | -1.567 |
Goat | -1.507 |
Caps | -1.411 |
================================================================ | -1.397 |
� | -1.361 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
itton | +0.992 |
pez | +0.960 |
ocard | +0.950 |
atts | +0.898 |
ourage | +0.887 |
Neg logit contributions | |
Masquerade | -0.837 |
Goat | -0.805 |
Caps | -0.753 |
================================================================ | -0.740 |
� | -0.720 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
itton | +0.491 |
pez | +0.477 |
ocard | +0.472 |
atts | +0.448 |
ourage | +0.443 |
Neg logit contributions | |
Masquerade | -0.346 |
Goat | -0.331 |
Caps | -0.307 |
================================================================ | -0.302 |
� | -0.293 |
Token | ically |
Token ID | 1146 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
itton | +1.739 |
pez | +1.622 |
ocard | +1.580 |
atts | +1.366 |
ourage | +1.320 |
Neg logit contributions | |
Masquerade | -5.531 |
Goat | -5.389 |
Caps | -5.159 |
================================================================ | -5.125 |
� | -5.052 |
Token | one |
Token ID | 530 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Masquerade | +0.081 |
Goat | +0.078 |
Caps | +0.073 |
================================================================ | +0.072 |
� | +0.070 |
Neg logit contributions | |
itton | -0.088 |
pez | -0.085 |
ocard | -0.084 |
atts | -0.079 |
ourage | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Masquerade | +0.284 |
Goat | +0.274 |
Caps | +0.257 |
================================================================ | +0.253 |
� | +0.247 |
Neg logit contributions | |
itton | -0.298 |
pez | -0.288 |
ocard | -0.285 |
atts | -0.268 |
ourage | -0.265 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
itton | +0.272 |
pez | +0.263 |
ocard | +0.260 |
atts | +0.244 |
ourage | +0.241 |
Neg logit contributions | |
Masquerade | -0.259 |
Goat | -0.250 |
Caps | -0.234 |
================================================================ | -0.231 |
� | -0.226 |
Token | most |
Token ID | 749 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
itton | +0.250 |
pez | +0.241 |
ocard | +0.237 |
atts | +0.222 |
ourage | +0.221 |
Neg logit contributions | |
Masquerade | -0.257 |
Goat | -0.249 |
Caps | -0.235 |
================================================================ | -0.230 |
� | -0.225 |
Token | inh |
Token ID | 25783 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
itton | +2.177 |
pez | +2.099 |
ocard | +2.081 |
atts | +1.937 |
ourage | +1.912 |
Neg logit contributions | |
Masquerade | -2.590 |
Goat | -2.498 |
Caps | -2.360 |
================================================================ | -2.335 |
� | -2.283 |
Token | osp |
Token ID | 2117 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
itton | +3.192 |
ocard | +3.015 |
pez | +3.006 |
atts | +2.695 |
ourage | +2.640 |
Neg logit contributions | |
Masquerade | -7.001 |
Goat | -6.769 |
Caps | -6.443 |
================================================================ | -6.347 |
� | -6.323 |
Token | itable |
Token ID | 4674 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Masquerade | +1.210 |
Goat | +1.189 |
Caps | +1.142 |
================================================================ | +1.135 |
� | +1.115 |
Neg logit contributions | |
itton | -0.574 |
ocard | -0.554 |
pez | -0.546 |
atts | -0.487 |
horm | -0.472 |
Token | and |
Token ID | 290 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
itton | +0.266 |
pez | +0.256 |
ocard | +0.253 |
atts | +0.238 |
ourage | +0.237 |
Neg logit contributions | |
Masquerade | -0.254 |
Goat | -0.246 |
Caps | -0.232 |
================================================================ | -0.227 |
� | -0.221 |
Token | challenging |
Token ID | 9389 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
Masquerade | +0.105 |
Goat | +0.102 |
Caps | +0.097 |
================================================================ | +0.095 |
� | +0.093 |
Neg logit contributions | |
itton | -0.096 |
pez | -0.093 |
ocard | -0.091 |
atts | -0.085 |
ourage | -0.084 |
Token | places |
Token ID | 4113 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
itton | +1.472 |
pez | +1.422 |
ocard | +1.406 |
atts | +1.321 |
ourage | +1.305 |
Neg logit contributions | |
Masquerade | -1.448 |
Goat | -1.397 |
Caps | -1.312 |
================================================================ | -1.294 |
� | -1.262 |
Token | a |
Token ID | 257 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Masquerade | +0.039 |
Goat | +0.038 |
Caps | +0.035 |
================================================================ | +0.035 |
� | +0.034 |
Neg logit contributions | |
itton | -0.045 |
pez | -0.044 |
ocard | -0.044 |
atts | -0.041 |
ourage | -0.041 |
Token | way |
Token ID | 835 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
itton | +0.550 |
pez | +0.532 |
ocard | +0.526 |
atts | +0.495 |
ourage | +0.489 |
Neg logit contributions | |
Masquerade | -0.501 |
Goat | -0.482 |
Caps | -0.453 |
================================================================ | -0.445 |
� | -0.434 |
Token | , |
Token ID | 11 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
itton | +0.249 |
pez | +0.241 |
ocard | +0.239 |
atts | +0.226 |
ourage | +0.223 |
Neg logit contributions | |
Masquerade | -0.197 |
Goat | -0.189 |
Caps | -0.176 |
================================================================ | -0.173 |
� | -0.169 |
Token | Julia |
Token ID | 22300 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
itton | +0.496 |
pez | +0.480 |
ocard | +0.475 |
atts | +0.447 |
ourage | +0.442 |
Neg logit contributions | |
Masquerade | -0.441 |
Goat | -0.424 |
Caps | -0.398 |
================================================================ | -0.390 |
� | -0.381 |
Token | H |
Token ID | 367 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Masquerade | +2.155 |
Goat | +2.074 |
Caps | +1.942 |
================================================================ | +1.894 |
� | +1.866 |
Neg logit contributions | |
itton | -2.433 |
pez | -2.355 |
ocard | -2.351 |
atts | -2.193 |
ourage | -2.183 |
Token | ahn |
Token ID | 15386 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Masquerade | +0.368 |
Goat | +0.356 |
================================================================ | +0.336 |
Caps | +0.336 |
mentation | +0.324 |
Neg logit contributions | |
itton | -0.338 |
pez | -0.328 |
ocard | -0.325 |
atts | -0.302 |
ourage | -0.297 |
Token | is |
Token ID | 318 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
itton | +5.249 |
pez | +5.150 |
ocard | +5.002 |
atts | +4.769 |
ourage | +4.681 |
Neg logit contributions | |
Masquerade | -4.522 |
Goat | -4.401 |
Caps | -4.052 |
================================================================ | -4.030 |
� | -3.929 |
Token | the |
Token ID | 262 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
itton | +0.280 |
pez | +0.271 |
ocard | +0.267 |
atts | +0.251 |
ourage | +0.249 |
Neg logit contributions | |
Masquerade | -0.262 |
Goat | -0.252 |
Caps | -0.237 |
================================================================ | -0.233 |
� | -0.227 |
Token | Patty |
Token ID | 42417 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Masquerade | +0.048 |
Goat | +0.046 |
Caps | +0.043 |
================================================================ | +0.042 |
� | +0.041 |
Neg logit contributions | |
itton | -0.055 |
pez | -0.054 |
ocard | -0.053 |
atts | -0.050 |
ourage | -0.049 |
Token | Hear |
Token ID | 26319 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
Masquerade | +0.722 |
Goat | +0.702 |
Caps | +0.650 |
================================================================ | +0.631 |
� | +0.619 |
Neg logit contributions | |
itton | -0.926 |
pez | -0.899 |
ocard | -0.894 |
atts | -0.839 |
ourage | -0.836 |
Token | st |
Token ID | 301 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
itton | +0.135 |
pez | +0.130 |
ocard | +0.128 |
atts | +0.119 |
ourage | +0.118 |
Neg logit contributions | |
Masquerade | -0.167 |
Goat | -0.162 |
Caps | -0.153 |
================================================================ | -0.151 |
� | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
Masquerade | +0.930 |
Goat | +0.893 |
Caps | +0.833 |
================================================================ | +0.815 |
� | +0.793 |
Neg logit contributions | |
itton | -1.135 |
pez | -1.102 |
ocard | -1.092 |
atts | -1.027 |
ourage | -1.015 |
Token | attended |
Token ID | 9141 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Masquerade | +0.150 |
Goat | +0.144 |
Caps | +0.135 |
================================================================ | +0.132 |
� | +0.128 |
Neg logit contributions | |
itton | -0.176 |
pez | -0.172 |
ocard | -0.170 |
atts | -0.159 |
ourage | -0.158 |
Token | by |
Token ID | 416 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
Masquerade | +0.437 |
Goat | +0.421 |
Caps | +0.396 |
================================================================ | +0.389 |
� | +0.381 |
Neg logit contributions | |
itton | -0.434 |
pez | -0.418 |
ocard | -0.416 |
atts | -0.390 |
ourage | -0.385 |
Token | Julia |
Token ID | 22300 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Masquerade | +0.093 |
Goat | +0.089 |
Caps | +0.084 |
================================================================ | +0.083 |
� | +0.081 |
Neg logit contributions | |
itton | -0.098 |
pez | -0.095 |
ocard | -0.094 |
atts | -0.088 |
ourage | -0.087 |
Token | H |
Token ID | 367 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Masquerade | +2.361 |
Goat | +2.282 |
Caps | +2.127 |
================================================================ | +2.022 |
� | +2.009 |
Neg logit contributions | |
itton | -3.225 |
pez | -3.129 |
ocard | -3.083 |
atts | -2.929 |
ourage | -2.910 |
Token | ahn |
Token ID | 15386 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Masquerade | +0.858 |
Goat | +0.830 |
Caps | +0.783 |
================================================================ | +0.775 |
� | +0.752 |
Neg logit contributions | |
itton | -0.761 |
pez | -0.736 |
ocard | -0.725 |
atts | -0.679 |
ourage | -0.669 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
itton | +5.348 |
pez | +5.204 |
ocard | +5.064 |
atts | +4.857 |
ourage | +4.777 |
Neg logit contributions | |
Masquerade | -4.485 |
Goat | -4.266 |
================================================================ | -3.969 |
Caps | -3.947 |
� | -3.826 |
Token | costs |
Token ID | 3484 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
Masquerade | +0.325 |
Goat | +0.313 |
Caps | +0.293 |
================================================================ | +0.287 |
� | +0.280 |
Neg logit contributions | |
itton | -0.392 |
pez | -0.378 |
ocard | -0.376 |
atts | -0.354 |
ourage | -0.350 |
Token | about |
Token ID | 546 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Masquerade | +1.141 |
Goat | +1.083 |
Caps | +1.019 |
================================================================ | +0.990 |
� | +0.970 |
Neg logit contributions | |
itton | -1.401 |
pez | -1.354 |
ocard | -1.346 |
atts | -1.269 |
ourage | -1.258 |
Token | $ |
Token ID | 720 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
itton | +0.271 |
pez | +0.263 |
ocard | +0.260 |
atts | +0.245 |
ourage | +0.242 |
Neg logit contributions | |
Masquerade | -0.241 |
Goat | -0.232 |
Caps | -0.217 |
================================================================ | -0.214 |
� | -0.209 |
Token | 40 |
Token ID | 1821 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
itton | +0.738 |
pez | +0.716 |
ocard | +0.709 |
atts | +0.668 |
ourage | +0.662 |
Neg logit contributions | |
Masquerade | -0.582 |
Goat | -0.559 |
Caps | -0.523 |
================================================================ | -0.516 |
� | -0.500 |
Token | objectives |
Token ID | 15221 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
itton | +0.609 |
pez | +0.590 |
ocard | +0.583 |
atts | +0.551 |
ourage | +0.544 |
Neg logit contributions | |
Masquerade | -0.532 |
Goat | -0.514 |
Caps | -0.482 |
================================================================ | -0.471 |
� | -0.458 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
itton | +1.602 |
pez | +1.555 |
ocard | +1.539 |
atts | +1.456 |
ourage | +1.441 |
Neg logit contributions | |
Masquerade | -1.208 |
Goat | -1.158 |
Caps | -1.077 |
================================================================ | -1.060 |
� | -1.030 |
Token | but |
Token ID | 475 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
itton | +0.569 |
pez | +0.556 |
ocard | +0.548 |
atts | +0.520 |
ourage | +0.514 |
Neg logit contributions | |
Masquerade | -0.403 |
Goat | -0.388 |
Caps | -0.360 |
================================================================ | -0.353 |
� | -0.342 |
Token | , |
Token ID | 11 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
itton | +1.510 |
pez | +1.464 |
ocard | +1.447 |
atts | +1.369 |
ourage | +1.350 |
Neg logit contributions | |
Masquerade | -1.281 |
Goat | -1.234 |
Caps | -1.155 |
================================================================ | -1.132 |
� | -1.103 |
Token | like |
Token ID | 588 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Masquerade | +0.110 |
Goat | +0.107 |
Caps | +0.100 |
================================================================ | +0.097 |
� | +0.095 |
Neg logit contributions | |
itton | -0.126 |
pez | -0.121 |
ocard | -0.120 |
atts | -0.114 |
ourage | -0.112 |
Token | Sid |
Token ID | 15686 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Masquerade | +0.461 |
Goat | +0.444 |
Caps | +0.418 |
================================================================ | +0.401 |
� | +0.392 |
Neg logit contributions | |
itton | -0.575 |
pez | -0.558 |
ocard | -0.552 |
atts | -0.524 |
ourage | -0.515 |
Token | ew |
Token ID | 413 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Masquerade | +4.255 |
Goat | +4.091 |
Caps | +3.707 |
================================================================ | +3.608 |
� | +3.582 |
Neg logit contributions | |
itton | -7.237 |
pez | -7.058 |
ocard | -6.850 |
atts | -6.614 |
ourage | -6.586 |
Token | inder |
Token ID | 5540 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
itton | +1.687 |
pez | +1.644 |
ocard | +1.626 |
atts | +1.561 |
ourage | +1.538 |
Neg logit contributions | |
Masquerade | -1.005 |
Goat | -0.956 |
Caps | -0.883 |
================================================================ | -0.864 |
� | -0.839 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Masquerade | +0.359 |
Goat | +0.345 |
Caps | +0.322 |
================================================================ | +0.313 |
� | +0.304 |
Neg logit contributions | |
itton | -0.468 |
pez | -0.454 |
ocard | -0.450 |
atts | -0.424 |
ourage | -0.421 |
Token | slippery |
Token ID | 32911 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Masquerade | +0.292 |
Goat | +0.281 |
Caps | +0.264 |
================================================================ | +0.256 |
� | +0.249 |
Neg logit contributions | |
itton | -0.375 |
pez | -0.363 |
ocard | -0.359 |
atts | -0.340 |
ourage | -0.336 |
Token | terrain |
Token ID | 15510 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Masquerade | +1.353 |
Goat | +1.308 |
Caps | +1.228 |
================================================================ | +1.198 |
� | +1.162 |
Neg logit contributions | |
itton | -1.489 |
pez | -1.441 |
ocard | -1.424 |
atts | -1.344 |
ourage | -1.327 |
Token | fish |
Token ID | 11084 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
itton | +1.049 |
pez | +1.023 |
ocard | +1.013 |
atts | +0.969 |
ourage | +0.961 |
Neg logit contributions | |
Masquerade | -0.470 |
Goat | -0.441 |
Caps | -0.398 |
================================================================ | -0.389 |
� | -0.373 |
Token | � |
Token ID | 447 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
itton | +0.926 |
pez | +0.897 |
ocard | +0.888 |
atts | +0.837 |
ourage | +0.828 |
Neg logit contributions | |
Masquerade | -0.799 |
Goat | -0.768 |
Caps | -0.718 |
================================================================ | -0.708 |
� | -0.689 |
Token | � |
Token ID | 251 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Masquerade | +0.153 |
Goat | +0.144 |
Caps | +0.131 |
================================================================ | +0.128 |
� | +0.124 |
Neg logit contributions | |
itton | -0.322 |
pez | -0.314 |
ocard | -0.312 |
atts | -0.298 |
ourage | -0.295 |
Token | debuted |
Token ID | 26376 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
itton | +0.440 |
pez | +0.425 |
ocard | +0.420 |
atts | +0.395 |
ourage | +0.392 |
Neg logit contributions | |
Masquerade | -0.407 |
Goat | -0.392 |
Caps | -0.367 |
================================================================ | -0.361 |
� | -0.353 |
Token | at |
Token ID | 379 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
itton | +0.331 |
pez | +0.320 |
ocard | +0.317 |
atts | +0.298 |
ourage | +0.295 |
Neg logit contributions | |
Masquerade | -0.308 |
Goat | -0.297 |
Caps | -0.278 |
================================================================ | -0.274 |
� | -0.267 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Masquerade | +1.474 |
Goat | +1.419 |
Caps | +1.342 |
================================================================ | +1.297 |
� | +1.265 |
Neg logit contributions | |
itton | -1.608 |
pez | -1.557 |
ocard | -1.535 |
atts | -1.446 |
ourage | -1.435 |
Token | ance |
Token ID | 590 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Masquerade | +5.850 |
Goat | +5.544 |
Caps | +5.338 |
================================================================ | +5.149 |
mentation | +5.090 |
Neg logit contributions | |
pez | -5.686 |
itton | -5.659 |
ocard | -5.295 |
horm | -5.019 |
atts | -4.957 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Masquerade | +0.805 |
Goat | +0.775 |
Caps | +0.727 |
================================================================ | +0.707 |
� | +0.689 |
Neg logit contributions | |
itton | -0.986 |
pez | -0.956 |
ocard | -0.947 |
atts | -0.890 |
ourage | -0.883 |
Token | was |
Token ID | 373 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Masquerade | +0.334 |
Goat | +0.322 |
Caps | +0.303 |
================================================================ | +0.295 |
� | +0.289 |
Neg logit contributions | |
itton | -0.366 |
pez | -0.354 |
ocard | -0.351 |
atts | -0.330 |
ourage | -0.327 |
Token | acquired |
Token ID | 9477 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Masquerade | +0.280 |
Goat | +0.271 |
Caps | +0.255 |
================================================================ | +0.248 |
� | +0.243 |
Neg logit contributions | |
itton | -0.306 |
pez | -0.296 |
ocard | -0.293 |
atts | -0.275 |
ourage | -0.273 |
Token | by |
Token ID | 416 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Masquerade | +1.029 |
Goat | +0.996 |
Caps | +0.933 |
================================================================ | +0.913 |
� | +0.892 |
Neg logit contributions | |
itton | -1.058 |
pez | -1.021 |
ocard | -1.011 |
atts | -0.952 |
ourage | -0.940 |
Token | the |
Token ID | 262 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
Masquerade | +0.830 |
Goat | +0.804 |
Caps | +0.750 |
================================================================ | +0.736 |
� | +0.719 |
Neg logit contributions | |
itton | -0.950 |
pez | -0.921 |
ocard | -0.909 |
atts | -0.857 |
ourage | -0.849 |
Token | entrance |
Token ID | 10384 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
itton | +0.152 |
pez | +0.147 |
ocard | +0.145 |
atts | +0.137 |
ourage | +0.135 |
Neg logit contributions | |
Masquerade | -0.138 |
Goat | -0.133 |
Caps | -0.125 |
================================================================ | -0.122 |
� | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
itton | +0.274 |
pez | +0.266 |
ocard | +0.263 |
atts | +0.249 |
ourage | +0.246 |
Neg logit contributions | |
Masquerade | -0.212 |
Goat | -0.203 |
Caps | -0.189 |
================================================================ | -0.186 |
� | -0.181 |
Token | the |
Token ID | 262 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
Masquerade | +0.229 |
Goat | +0.221 |
Caps | +0.205 |
================================================================ | +0.201 |
� | +0.196 |
Neg logit contributions | |
itton | -0.287 |
pez | -0.278 |
ocard | -0.275 |
atts | -0.260 |
ourage | -0.257 |
Token | Bangladesh |
Token ID | 19483 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
itton | +0.177 |
pez | +0.173 |
ocard | +0.172 |
atts | +0.164 |
ourage | +0.163 |
Neg logit contributions | |
Masquerade | -0.069 |
Goat | -0.065 |
Caps | -0.058 |
================================================================ | -0.056 |
� | -0.054 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
itton | +2.226 |
pez | +2.162 |
ocard | +2.142 |
atts | +2.017 |
ourage | +1.998 |
Neg logit contributions | |
Masquerade | -1.869 |
Goat | -1.785 |
Caps | -1.667 |
================================================================ | -1.653 |
� | -1.607 |
Token | arb |
Token ID | 38039 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Masquerade | +4.891 |
Goat | +4.867 |
Caps | +4.627 |
================================================================ | +4.537 |
mentation | +4.490 |
Neg logit contributions | |
itton | -6.145 |
pez | -5.953 |
ocard | -5.853 |
horm | -5.660 |
situational | -5.528 |
Token | ans |
Token ID | 504 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Masquerade | +0.931 |
Goat | +0.911 |
Caps | +0.868 |
================================================================ | +0.846 |
mentation | +0.828 |
Neg logit contributions | |
itton | -0.963 |
pez | -0.928 |
ocard | -0.920 |
atts | -0.856 |
ourage | -0.843 |
Token | , |
Token ID | 11 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
Masquerade | +1.082 |
Goat | +1.042 |
Caps | +0.972 |
================================================================ | +0.948 |
� | +0.919 |
Neg logit contributions | |
itton | -1.428 |
pez | -1.384 |
ocard | -1.370 |
atts | -1.299 |
ourage | -1.282 |
Token | southeast |
Token ID | 26015 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
Masquerade | +0.155 |
Goat | +0.151 |
Caps | +0.141 |
================================================================ | +0.137 |
� | +0.134 |
Neg logit contributions | |
itton | -0.173 |
pez | -0.168 |
ocard | -0.166 |
atts | -0.156 |
ourage | -0.154 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Masquerade | +1.430 |
Goat | +1.408 |
Caps | +1.312 |
================================================================ | +1.284 |
� | +1.261 |
Neg logit contributions | |
itton | -1.596 |
pez | -1.554 |
ocard | -1.528 |
atts | -1.431 |
ourage | -1.423 |
Token | This |
Token ID | 770 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
itton | +1.460 |
pez | +1.413 |
ocard | +1.397 |
atts | +1.315 |
ourage | +1.299 |
Neg logit contributions | |
Masquerade | -1.348 |
Goat | -1.300 |
Caps | -1.219 |
================================================================ | -1.200 |
� | -1.169 |
Token | aerial |
Token ID | 17789 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Masquerade | +0.903 |
Goat | +0.883 |
Caps | +0.830 |
================================================================ | +0.806 |
� | +0.786 |
Neg logit contributions | |
itton | -0.931 |
pez | -0.895 |
ocard | -0.889 |
atts | -0.840 |
ourage | -0.824 |
Token | photograph |
Token ID | 8408 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
itton | +0.577 |
pez | +0.553 |
ocard | +0.545 |
atts | +0.509 |
ourage | +0.497 |
Neg logit contributions | |
Masquerade | -0.721 |
Goat | -0.701 |
Caps | -0.664 |
================================================================ | -0.651 |
� | -0.639 |
Token | of |
Token ID | 286 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
itton | +1.988 |
pez | +1.925 |
ocard | +1.902 |
atts | +1.790 |
ourage | +1.769 |
Neg logit contributions | |
Masquerade | -1.885 |
Goat | -1.815 |
Caps | -1.702 |
================================================================ | -1.683 |
� | -1.640 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Masquerade | +0.076 |
Goat | +0.074 |
Caps | +0.069 |
================================================================ | +0.067 |
� | +0.066 |
Neg logit contributions | |
itton | -0.085 |
pez | -0.083 |
ocard | -0.082 |
atts | -0.077 |
ourage | -0.076 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
itton | +0.230 |
pez | +0.223 |
ocard | +0.220 |
atts | +0.208 |
ourage | +0.206 |
Neg logit contributions | |
Masquerade | -0.191 |
Goat | -0.185 |
Caps | -0.173 |
================================================================ | -0.169 |
� | -0.165 |
Token | arb |
Token ID | 38039 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Goat | +4.705 |
Masquerade | +4.698 |
Caps | +4.426 |
mentation | +4.377 |
================================================================ | +4.363 |
Neg logit contributions | |
itton | -5.954 |
pez | -5.677 |
ocard | -5.668 |
horm | -5.513 |
situational | -5.370 |
Token | ans |
Token ID | 504 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Masquerade | +0.957 |
Goat | +0.939 |
Caps | +0.896 |
================================================================ | +0.870 |
mentation | +0.852 |
Neg logit contributions | |
itton | -1.014 |
pez | -0.974 |
ocard | -0.972 |
atts | -0.898 |
horm | -0.891 |
Token | , |
Token ID | 11 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
Masquerade | +0.992 |
Goat | +0.956 |
Caps | +0.894 |
================================================================ | +0.874 |
� | +0.842 |
Neg logit contributions | |
itton | -1.199 |
pez | -1.153 |
ocard | -1.145 |
atts | -1.086 |
ourage | -1.070 |
Token | made |
Token ID | 925 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
itton | +0.133 |
pez | +0.129 |
ocard | +0.127 |
atts | +0.120 |
ourage | +0.118 |
Neg logit contributions | |
Masquerade | -0.119 |
Goat | -0.116 |
Caps | -0.108 |
================================================================ | -0.105 |
� | -0.103 |
Token | in |
Token ID | 287 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
itton | +0.039 |
ocard | +0.037 |
pez | +0.037 |
atts | +0.035 |
ourage | +0.034 |
Neg logit contributions | |
Masquerade | -0.039 |
Goat | -0.038 |
Caps | -0.036 |
================================================================ | -0.035 |
� | -0.034 |
Token | catastrophe |
Token ID | 27767 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Masquerade | +0.545 |
Goat | +0.529 |
Caps | +0.493 |
================================================================ | +0.480 |
� | +0.462 |
Neg logit contributions | |
itton | -0.703 |
pez | -0.684 |
ocard | -0.675 |
atts | -0.641 |
ourage | -0.632 |
Token | is |
Token ID | 318 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
itton | +0.732 |
pez | +0.711 |
ocard | +0.703 |
atts | +0.665 |
ourage | +0.657 |
Neg logit contributions | |
Masquerade | -0.554 |
Goat | -0.531 |
Caps | -0.495 |
================================================================ | -0.485 |
� | -0.470 |
Token | unprecedented |
Token ID | 13029 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
itton | +0.125 |
pez | +0.121 |
ocard | +0.120 |
atts | +0.112 |
ourage | +0.111 |
Neg logit contributions | |
Masquerade | -0.119 |
Goat | -0.115 |
Caps | -0.108 |
================================================================ | -0.106 |
� | -0.103 |
Token | in |
Token ID | 287 |
Feature activation | -4.31e-04 |
Pos logit contributions | |
itton | +2.260 |
pez | +2.190 |
ocard | +2.164 |
atts | +2.042 |
ourage | +2.019 |
Neg logit contributions | |
Masquerade | -1.991 |
Goat | -1.912 |
Caps | -1.789 |
================================================================ | -1.766 |
� | -1.726 |
Token | the |
Token ID | 262 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Masquerade | +0.001 |
Goat | +0.001 |
Caps | +0.001 |
================================================================ | +0.001 |
� | +0.001 |
Neg logit contributions | |
itton | -0.001 |
pez | -0.001 |
ocard | -0.001 |
atts | -0.001 |
ourage | -0.001 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
itton | +0.102 |
pez | +0.099 |
ocard | +0.097 |
atts | +0.092 |
ourage | +0.091 |
Neg logit contributions | |
Masquerade | -0.083 |
Goat | -0.080 |
Caps | -0.075 |
================================================================ | -0.073 |
� | -0.071 |
Token | arb |
Token ID | 38039 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Goat | +4.711 |
Masquerade | +4.701 |
Caps | +4.465 |
================================================================ | +4.384 |
mentation | +4.297 |
Neg logit contributions | |
itton | -5.844 |
pez | -5.633 |
ocard | -5.523 |
horm | -5.356 |
situational | -5.232 |
Token | ans |
Token ID | 504 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
Masquerade | +0.440 |
Goat | +0.429 |
Caps | +0.406 |
================================================================ | +0.399 |
� | +0.388 |
Neg logit contributions | |
itton | -0.433 |
pez | -0.418 |
ocard | -0.413 |
atts | -0.385 |
ourage | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
Masquerade | +1.018 |
Goat | +0.978 |
Caps | +0.910 |
================================================================ | +0.893 |
� | +0.863 |
Neg logit contributions | |
itton | -1.410 |
pez | -1.369 |
ocard | -1.355 |
atts | -1.283 |
ourage | -1.271 |
Token | and |
Token ID | 290 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
itton | +0.147 |
pez | +0.143 |
ocard | +0.141 |
atts | +0.133 |
ourage | +0.132 |
Neg logit contributions | |
Masquerade | -0.118 |
Goat | -0.114 |
Caps | -0.106 |
================================================================ | -0.104 |
� | -0.101 |
Token | we |
Token ID | 356 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Masquerade | +0.133 |
Goat | +0.130 |
Caps | +0.122 |
================================================================ | +0.118 |
� | +0.114 |
Neg logit contributions | |
itton | -0.161 |
pez | -0.156 |
ocard | -0.154 |
atts | -0.145 |
ourage | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
itton | +0.284 |
pez | +0.276 |
ocard | +0.272 |
atts | +0.257 |
ourage | +0.255 |
Neg logit contributions | |
Masquerade | -0.235 |
Goat | -0.227 |
Caps | -0.211 |
================================================================ | -0.207 |
� | -0.202 |
Token | waters |
Token ID | 10150 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
itton | +0.278 |
pez | +0.270 |
ocard | +0.266 |
atts | +0.252 |
ourage | +0.250 |
Neg logit contributions | |
Masquerade | -0.213 |
Goat | -0.205 |
Caps | -0.190 |
================================================================ | -0.186 |
� | -0.181 |
Token | of |
Token ID | 286 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
itton | +1.153 |
pez | +1.117 |
ocard | +1.105 |
atts | +1.042 |
ourage | +1.031 |
Neg logit contributions | |
Masquerade | -0.986 |
Goat | -0.948 |
Caps | -0.886 |
================================================================ | -0.873 |
� | -0.851 |
Token | Bangladesh |
Token ID | 19483 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
itton | +0.257 |
pez | +0.250 |
ocard | +0.246 |
atts | +0.233 |
ourage | +0.230 |
Neg logit contributions | |
Masquerade | -0.213 |
Goat | -0.205 |
Caps | -0.191 |
================================================================ | -0.187 |
� | -0.183 |
Token | 's |
Token ID | 338 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
itton | +2.864 |
pez | +2.771 |
ocard | +2.739 |
atts | +2.599 |
ourage | +2.577 |
Neg logit contributions | |
Masquerade | -2.301 |
Goat | -2.191 |
Caps | -2.046 |
================================================================ | -2.021 |
� | -1.966 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
itton | +1.072 |
pez | +1.038 |
ocard | +1.027 |
atts | +0.969 |
ourage | +0.958 |
Neg logit contributions | |
Masquerade | -0.929 |
Goat | -0.893 |
Caps | -0.835 |
================================================================ | -0.823 |
� | -0.802 |
Token | arb |
Token ID | 38039 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Goat | +4.821 |
Masquerade | +4.818 |
Caps | +4.550 |
================================================================ | +4.376 |
ppa | +4.247 |
Neg logit contributions | |
pez | -5.654 |
itton | -5.622 |
ocard | -5.484 |
horm | -5.136 |
ourage | -5.118 |
Token | ans |
Token ID | 504 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Goat | +0.231 |
Masquerade | +0.229 |
Caps | +0.221 |
================================================================ | +0.215 |
mentation | +0.208 |
Neg logit contributions | |
itton | -0.260 |
pez | -0.254 |
ocard | -0.246 |
atts | -0.231 |
horm | -0.228 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
Masquerade | +0.800 |
Goat | +0.772 |
Caps | +0.720 |
================================================================ | +0.707 |
� | +0.687 |
Neg logit contributions | |
itton | -1.014 |
pez | -0.983 |
ocard | -0.976 |
atts | -0.921 |
ourage | -0.911 |
Token | the |
Token ID | 262 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
itton | +0.043 |
pez | +0.042 |
ocard | +0.041 |
atts | +0.039 |
ourage | +0.038 |
Neg logit contributions | |
Masquerade | -0.038 |
Goat | -0.037 |
Caps | -0.035 |
================================================================ | -0.034 |
� | -0.033 |
Token | largest |
Token ID | 4387 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
itton | +0.105 |
pez | +0.102 |
ocard | +0.100 |
atts | +0.094 |
ourage | +0.094 |
Neg logit contributions | |
Masquerade | -0.095 |
Goat | -0.093 |
Caps | -0.087 |
================================================================ | -0.085 |
� | -0.083 |
Token | ested |
Token ID | 7287 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Masquerade | +2.768 |
Goat | +2.697 |
Caps | +2.558 |
================================================================ | +2.550 |
mentation | +2.507 |
Neg logit contributions | |
itton | -1.977 |
pez | -1.881 |
ocard | -1.850 |
horm | -1.739 |
atts | -1.696 |
Token | . |
Token ID | 13 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
Masquerade | +1.401 |
Goat | +1.342 |
Caps | +1.229 |
================================================================ | +1.224 |
� | +1.178 |
Neg logit contributions | |
itton | -1.971 |
ocard | -1.897 |
pez | -1.896 |
atts | -1.783 |
ourage | -1.763 |
Token | BT |
Token ID | 19313 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Masquerade | +0.098 |
Goat | +0.094 |
Caps | +0.088 |
================================================================ | +0.086 |
� | +0.084 |
Neg logit contributions | |
itton | -0.122 |
pez | -0.119 |
ocard | -0.117 |
atts | -0.111 |
ourage | -0.109 |
Token | W |
Token ID | 54 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
itton | +0.361 |
pez | +0.351 |
ocard | +0.347 |
atts | +0.327 |
ourage | +0.324 |
Neg logit contributions | |
Masquerade | -0.294 |
Goat | -0.284 |
Caps | -0.264 |
================================================================ | -0.261 |
� | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
itton | +1.243 |
pez | +1.205 |
ocard | +1.192 |
atts | +1.126 |
ourage | +1.114 |
Neg logit contributions | |
Masquerade | -1.024 |
Goat | -0.983 |
Caps | -0.917 |
================================================================ | -0.904 |
� | -0.880 |
Token | Sid |
Token ID | 15686 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
itton | +0.042 |
pez | +0.041 |
ocard | +0.040 |
atts | +0.038 |
ourage | +0.038 |
Neg logit contributions | |
Masquerade | -0.036 |
Goat | -0.035 |
Caps | -0.032 |
================================================================ | -0.032 |
� | -0.031 |
Token | Davis |
Token ID | 7802 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Masquerade | +4.883 |
Goat | +4.716 |
Caps | +4.364 |
================================================================ | +4.267 |
� | +4.197 |
Neg logit contributions | |
itton | -5.901 |
pez | -5.669 |
ocard | -5.587 |
ourage | -5.244 |
atts | -5.233 |
Token | updated |
Token ID | 6153 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
itton | +1.096 |
pez | +1.063 |
ocard | +1.051 |
atts | +0.993 |
ourage | +0.982 |
Neg logit contributions | |
Masquerade | -0.906 |
Goat | -0.871 |
Caps | -0.813 |
================================================================ | -0.801 |
� | -0.779 |
Token | this |
Token ID | 428 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
itton | +0.243 |
pez | +0.235 |
ocard | +0.232 |
atts | +0.219 |
ourage | +0.217 |
Neg logit contributions | |
Masquerade | -0.210 |
Goat | -0.202 |
Caps | -0.189 |
================================================================ | -0.186 |
� | -0.181 |
Token | movie |
Token ID | 3807 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Masquerade | +1.561 |
Goat | +1.508 |
Caps | +1.400 |
================================================================ | +1.373 |
� | +1.326 |
Neg logit contributions | |
itton | -1.921 |
pez | -1.861 |
ocard | -1.841 |
atts | -1.744 |
ourage | -1.734 |
Token | in |
Token ID | 287 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
itton | +0.950 |
pez | +0.919 |
ocard | +0.909 |
atts | +0.856 |
ourage | +0.847 |
Neg logit contributions | |
Masquerade | -0.854 |
Goat | -0.822 |
Caps | -0.769 |
================================================================ | -0.758 |
� | -0.738 |
Token | Min |
Token ID | 1855 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Masquerade | +0.039 |
Goat | +0.037 |
Caps | +0.035 |
================================================================ | +0.034 |
� | +0.033 |
Neg logit contributions | |
itton | -0.043 |
pez | -0.042 |
ocard | -0.042 |
atts | -0.039 |
ourage | -0.039 |
Token | ova |
Token ID | 10071 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
itton | +0.638 |
pez | +0.616 |
ocard | +0.609 |
atts | +0.572 |
ourage | +0.565 |
Neg logit contributions | |
Masquerade | -0.631 |
Goat | -0.609 |
Caps | -0.572 |
================================================================ | -0.565 |
� | -0.551 |
Token | � |
Token ID | 564 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Masquerade | +0.046 |
Goat | +0.043 |
Caps | +0.040 |
================================================================ | +0.040 |
� | +0.038 |
Neg logit contributions | |
itton | -0.066 |
pez | -0.064 |
ocard | -0.064 |
atts | -0.060 |
ourage | -0.060 |
Token | � |
Token ID | 250 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Masquerade | +1.059 |
Goat | +1.025 |
Caps | +0.961 |
================================================================ | +0.953 |
� | +0.948 |
Neg logit contributions | |
itton | -1.066 |
pez | -1.028 |
ocard | -1.022 |
atts | -0.960 |
ourage | -0.949 |
Token | ir |
Token ID | 343 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Masquerade | +0.440 |
Goat | +0.419 |
Caps | +0.393 |
================================================================ | +0.387 |
� | +0.376 |
Neg logit contributions | |
itton | -0.576 |
pez | -0.560 |
ocard | -0.555 |
atts | -0.524 |
ourage | -0.518 |
Token | respective |
Token ID | 36990 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
itton | +0.662 |
pez | +0.648 |
ocard | +0.634 |
atts | +0.597 |
ourage | +0.589 |
Neg logit contributions | |
Masquerade | -0.633 |
Goat | -0.613 |
Caps | -0.574 |
================================================================ | -0.570 |
� | -0.553 |
Token | of |
Token ID | 286 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Masquerade | +4.650 |
Goat | +4.464 |
Caps | +4.218 |
================================================================ | +4.141 |
� | +4.113 |
Neg logit contributions | |
itton | -5.785 |
pez | -5.691 |
ocard | -5.526 |
atts | -5.245 |
ourage | -5.215 |
Token | which |
Token ID | 543 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Masquerade | +0.506 |
Goat | +0.487 |
Caps | +0.456 |
================================================================ | +0.448 |
� | +0.436 |
Neg logit contributions | |
itton | -0.555 |
pez | -0.539 |
ocard | -0.532 |
atts | -0.500 |
ourage | -0.495 |
Token | unit |
Token ID | 4326 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
itton | +0.580 |
pez | +0.561 |
ocard | +0.555 |
atts | +0.521 |
ourage | +0.515 |
Neg logit contributions | |
Masquerade | -0.565 |
Goat | -0.545 |
Caps | -0.512 |
================================================================ | -0.505 |
� | -0.493 |
Token | is |
Token ID | 318 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
itton | +0.201 |
pez | +0.196 |
ocard | +0.193 |
atts | +0.182 |
ourage | +0.180 |
Neg logit contributions | |
Masquerade | -0.159 |
Goat | -0.153 |
Caps | -0.143 |
================================================================ | -0.140 |
� | -0.137 |
Token | accused |
Token ID | 5371 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
Masquerade | +0.326 |
Goat | +0.314 |
Caps | +0.295 |
================================================================ | +0.287 |
� | +0.280 |
Neg logit contributions | |
itton | -0.391 |
pez | -0.378 |
ocard | -0.376 |
atts | -0.353 |
ourage | -0.349 |
Token | except |
Token ID | 2845 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
Masquerade | +0.091 |
Goat | +0.088 |
Caps | +0.082 |
================================================================ | +0.081 |
� | +0.079 |
Neg logit contributions | |
itton | -0.114 |
pez | -0.111 |
ocard | -0.110 |
atts | -0.104 |
ourage | -0.103 |
Token | by |
Token ID | 416 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
itton | +1.254 |
pez | +1.207 |
ocard | +1.198 |
atts | +1.120 |
ourage | +1.103 |
Neg logit contributions | |
Masquerade | -1.349 |
Goat | -1.310 |
Caps | -1.233 |
================================================================ | -1.214 |
� | -1.185 |
Token | water |
Token ID | 1660 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
itton | +0.595 |
pez | +0.576 |
ocard | +0.570 |
atts | +0.537 |
ourage | +0.531 |
Neg logit contributions | |
Masquerade | -0.521 |
Goat | -0.503 |
Caps | -0.470 |
================================================================ | -0.462 |
� | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
itton | +0.793 |
pez | +0.768 |
ocard | +0.760 |
atts | +0.715 |
ourage | +0.706 |
Neg logit contributions | |
Masquerade | -0.726 |
Goat | -0.701 |
Caps | -0.658 |
================================================================ | -0.646 |
� | -0.631 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
itton | +0.686 |
pez | +0.668 |
ocard | +0.662 |
atts | +0.631 |
ourage | +0.624 |
Neg logit contributions | |
Masquerade | -0.387 |
Goat | -0.370 |
Caps | -0.339 |
================================================================ | -0.331 |
� | -0.321 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
itton | +0.496 |
pez | +0.486 |
ocard | +0.482 |
atts | +0.463 |
ourage | +0.459 |
Neg logit contributions | |
Masquerade | -0.155 |
Goat | -0.144 |
Caps | -0.125 |
================================================================ | -0.120 |
� | -0.114 |
Token | arb |
Token ID | 38039 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Masquerade | +4.399 |
Goat | +4.367 |
Caps | +4.146 |
================================================================ | +4.093 |
mentation | +4.076 |
Neg logit contributions | |
itton | -5.561 |
pez | -5.284 |
ocard | -5.277 |
horm | -5.062 |
situational | -4.972 |
Token | ans |
Token ID | 504 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Masquerade | +0.953 |
Goat | +0.931 |
Caps | +0.890 |
================================================================ | +0.869 |
mentation | +0.847 |
Neg logit contributions | |
itton | -1.003 |
pez | -0.963 |
ocard | -0.960 |
atts | -0.884 |
ourage | -0.878 |
Token | is |
Token ID | 318 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Masquerade | +0.930 |
Goat | +0.896 |
Caps | +0.834 |
================================================================ | +0.815 |
� | +0.785 |
Neg logit contributions | |
itton | -1.238 |
pez | -1.191 |
ocard | -1.185 |
atts | -1.119 |
ourage | -1.108 |
Token | a |
Token ID | 257 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
Masquerade | +0.255 |
Goat | +0.247 |
Caps | +0.231 |
================================================================ | +0.228 |
� | +0.222 |
Neg logit contributions | |
itton | -0.275 |
pez | -0.265 |
ocard | -0.263 |
atts | -0.246 |
ourage | -0.244 |
Token | place |
Token ID | 1295 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
itton | +0.060 |
pez | +0.058 |
ocard | +0.057 |
atts | +0.054 |
ourage | +0.053 |
Neg logit contributions | |
Masquerade | -0.059 |
Goat | -0.057 |
Caps | -0.054 |
================================================================ | -0.053 |
� | -0.051 |
Token | chief |
Token ID | 4039 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Masquerade | +0.004 |
Goat | +0.004 |
Caps | +0.004 |
================================================================ | +0.004 |
� | +0.004 |
Neg logit contributions | |
itton | -0.005 |
pez | -0.004 |
ocard | -0.004 |
atts | -0.004 |
ourage | -0.004 |
Token | forest |
Token ID | 8222 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
itton | +0.609 |
pez | +0.590 |
ocard | +0.583 |
atts | +0.548 |
ourage | +0.542 |
Neg logit contributions | |
Masquerade | -0.581 |
Goat | -0.560 |
Caps | -0.526 |
================================================================ | -0.518 |
� | -0.506 |
Token | official |
Token ID | 1743 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
itton | +1.234 |
pez | +1.192 |
ocard | +1.180 |
atts | +1.105 |
ourage | +1.094 |
Neg logit contributions | |
Masquerade | -1.279 |
Goat | -1.228 |
Caps | -1.156 |
================================================================ | -1.143 |
� | -1.117 |
Token | of |
Token ID | 286 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
itton | +1.074 |
pez | +1.037 |
ocard | +1.024 |
atts | +0.961 |
ourage | +0.948 |
Neg logit contributions | |
Masquerade | -1.079 |
Goat | -1.042 |
Caps | -0.981 |
================================================================ | -0.965 |
� | -0.943 |
Token | the |
Token ID | 262 |
Feature activation | +4.54e-03 |
Pos logit contributions | |
itton | +0.028 |
pez | +0.027 |
ocard | +0.026 |
atts | +0.025 |
ourage | +0.025 |
Neg logit contributions | |
Masquerade | -0.022 |
Goat | -0.022 |
Caps | -0.020 |
================================================================ | -0.020 |
� | -0.019 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
itton | +0.009 |
pez | +0.009 |
ocard | +0.009 |
atts | +0.008 |
ourage | +0.008 |
Neg logit contributions | |
Masquerade | -0.006 |
Goat | -0.006 |
Caps | -0.006 |
================================================================ | -0.005 |
� | -0.005 |
Token | arb |
Token ID | 38039 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Masquerade | +4.452 |
Goat | +4.439 |
Caps | +4.218 |
================================================================ | +4.107 |
mentation | +4.041 |
Neg logit contributions | |
itton | -5.507 |
pez | -5.296 |
ocard | -5.232 |
horm | -5.037 |
situational | -4.897 |
Token | ans |
Token ID | 504 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Masquerade | +0.334 |
Goat | +0.326 |
Caps | +0.309 |
================================================================ | +0.302 |
mentation | +0.294 |
Neg logit contributions | |
itton | -0.332 |
pez | -0.320 |
ocard | -0.316 |
atts | -0.295 |
ourage | -0.291 |
Token | in |
Token ID | 287 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
Masquerade | +0.909 |
Goat | +0.884 |
Caps | +0.830 |
================================================================ | +0.806 |
� | +0.783 |
Neg logit contributions | |
itton | -1.020 |
pez | -0.986 |
ocard | -0.977 |
atts | -0.921 |
ourage | -0.904 |
Token | Bangladesh |
Token ID | 19483 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Masquerade | +0.119 |
Goat | +0.115 |
Caps | +0.107 |
================================================================ | +0.105 |
� | +0.102 |
Neg logit contributions | |
itton | -0.141 |
pez | -0.137 |
ocard | -0.135 |
atts | -0.127 |
ourage | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
itton | +2.126 |
pez | +2.062 |
ocard | +2.036 |
atts | +1.927 |
ourage | +1.911 |
Neg logit contributions | |
Masquerade | -1.789 |
Goat | -1.710 |
Caps | -1.597 |
================================================================ | -1.578 |
� | -1.537 |
Token | re |
Token ID | 260 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
itton | +0.002 |
pez | +0.002 |
ocard | +0.002 |
atts | +0.002 |
ourage | +0.002 |
Neg logit contributions | |
Masquerade | -0.001 |
Goat | -0.001 |
Caps | -0.001 |
================================================================ | -0.001 |
� | -0.001 |
Token | ment |
Token ID | 434 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
itton | +1.140 |
pez | +1.115 |
ocard | +1.106 |
atts | +1.063 |
ourage | +1.055 |
Neg logit contributions | |
Masquerade | -0.356 |
Goat | -0.328 |
Caps | -0.284 |
================================================================ | -0.276 |
� | -0.260 |
Token | or |
Token ID | 393 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Masquerade | +0.028 |
Goat | +0.027 |
Caps | +0.025 |
================================================================ | +0.025 |
� | +0.024 |
Neg logit contributions | |
itton | -0.036 |
pez | -0.035 |
ocard | -0.034 |
atts | -0.032 |
ourage | -0.032 |
Token | sending |
Token ID | 7216 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
itton | +0.459 |
pez | +0.444 |
ocard | +0.438 |
atts | +0.412 |
ourage | +0.407 |
Neg logit contributions | |
Masquerade | -0.450 |
Goat | -0.435 |
Caps | -0.410 |
================================================================ | -0.402 |
� | -0.390 |
Token | so |
Token ID | 523 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
itton | +0.761 |
pez | +0.733 |
ocard | +0.726 |
atts | +0.684 |
ourage | +0.676 |
Neg logit contributions | |
Masquerade | -0.663 |
Goat | -0.639 |
Caps | -0.601 |
================================================================ | -0.587 |
� | -0.572 |
Token | apy |
Token ID | 12826 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Masquerade | +0.158 |
Goat | +0.151 |
Caps | +0.141 |
================================================================ | +0.139 |
� | +0.135 |
Neg logit contributions | |
itton | -0.203 |
pez | -0.197 |
ocard | -0.195 |
atts | -0.184 |
ourage | -0.182 |
Token | water |
Token ID | 1660 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Masquerade | +4.816 |
Goat | +4.725 |
Caps | +4.526 |
================================================================ | +4.283 |
mentation | +4.138 |
Neg logit contributions | |
itton | -5.226 |
pez | -4.944 |
ocard | -4.878 |
atts | -4.582 |
ourage | -4.528 |
Token | back |
Token ID | 736 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
itton | +0.658 |
pez | +0.637 |
ocard | +0.631 |
atts | +0.594 |
ourage | +0.589 |
Neg logit contributions | |
Masquerade | -0.520 |
Goat | -0.500 |
Caps | -0.467 |
================================================================ | -0.458 |
� | -0.444 |
Token | into |
Token ID | 656 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
itton | +0.520 |
pez | +0.505 |
ocard | +0.500 |
atts | +0.473 |
ourage | +0.469 |
Neg logit contributions | |
Masquerade | -0.364 |
Goat | -0.349 |
Caps | -0.324 |
================================================================ | -0.318 |
� | -0.308 |
Token | the |
Token ID | 262 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
Masquerade | +0.709 |
Goat | +0.688 |
Caps | +0.646 |
================================================================ | +0.624 |
� | +0.612 |
Neg logit contributions | |
itton | -0.809 |
pez | -0.779 |
ocard | -0.769 |
atts | -0.727 |
ourage | -0.717 |
Token | bowl |
Token ID | 9396 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Masquerade | +0.128 |
Goat | +0.123 |
Caps | +0.116 |
================================================================ | +0.113 |
� | +0.111 |
Neg logit contributions | |
itton | -0.133 |
pez | -0.128 |
ocard | -0.126 |
atts | -0.120 |
ourage | -0.118 |
Token | sund |
Token ID | 37437 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Masquerade | +0.523 |
Goat | +0.507 |
Caps | +0.472 |
================================================================ | +0.459 |
� | +0.447 |
Neg logit contributions | |
itton | -0.657 |
pez | -0.639 |
ocard | -0.629 |
atts | -0.596 |
ourage | -0.588 |
Token | ari |
Token ID | 2743 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Masquerade | +4.040 |
Goat | +3.948 |
Caps | +3.689 |
================================================================ | +3.603 |
acly | +3.560 |
Neg logit contributions | |
itton | -4.234 |
pez | -4.119 |
ocard | -4.055 |
atts | -3.854 |
ourage | -3.746 |
Token | tree |
Token ID | 5509 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Masquerade | +1.952 |
Goat | +1.907 |
Caps | +1.783 |
================================================================ | +1.728 |
� | +1.698 |
Neg logit contributions | |
itton | -2.305 |
pez | -2.230 |
ocard | -2.206 |
atts | -2.093 |
ourage | -2.064 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
itton | +0.600 |
pez | +0.582 |
ocard | +0.575 |
atts | +0.543 |
ourage | +0.537 |
Neg logit contributions | |
Masquerade | -0.498 |
Goat | -0.478 |
Caps | -0.446 |
================================================================ | -0.440 |
� | -0.428 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
itton | +0.077 |
pez | +0.075 |
ocard | +0.074 |
atts | +0.070 |
ourage | +0.069 |
Neg logit contributions | |
Masquerade | -0.059 |
Goat | -0.057 |
Caps | -0.053 |
================================================================ | -0.052 |
� | -0.051 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
itton | +0.048 |
pez | +0.047 |
ocard | +0.046 |
atts | +0.044 |
ourage | +0.044 |
Neg logit contributions | |
Masquerade | -0.032 |
Goat | -0.031 |
Caps | -0.028 |
================================================================ | -0.028 |
� | -0.027 |
Token | arb |
Token ID | 38039 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Masquerade | +4.343 |
Goat | +4.296 |
Caps | +4.052 |
================================================================ | +4.029 |
mentation | +3.995 |
Neg logit contributions | |
itton | -5.273 |
pez | -5.036 |
ocard | -5.012 |
horm | -4.780 |
situational | -4.707 |
Token | ans |
Token ID | 504 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Masquerade | +0.536 |
Goat | +0.522 |
Caps | +0.495 |
================================================================ | +0.485 |
mentation | +0.471 |
Neg logit contributions | |
itton | -0.528 |
pez | -0.508 |
ocard | -0.504 |
atts | -0.469 |
ourage | -0.463 |
Token | is |
Token ID | 318 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Masquerade | +0.958 |
Goat | +0.926 |
Caps | +0.869 |
================================================================ | +0.843 |
� | +0.818 |
Neg logit contributions | |
itton | -1.182 |
pez | -1.139 |
ocard | -1.133 |
atts | -1.072 |
ourage | -1.058 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
Masquerade | +0.193 |
Goat | +0.188 |
Caps | +0.176 |
================================================================ | +0.173 |
� | +0.168 |
Neg logit contributions | |
itton | -0.218 |
pez | -0.211 |
ocard | -0.209 |
atts | -0.196 |
ourage | -0.194 |
Token | vast |
Token ID | 5909 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Masquerade | +0.025 |
Goat | +0.024 |
Caps | +0.023 |
================================================================ | +0.022 |
� | +0.022 |
Neg logit contributions | |
itton | -0.026 |
pez | -0.025 |
ocard | -0.025 |
atts | -0.023 |
ourage | -0.023 |
Token | center |
Token ID | 3641 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Masquerade | +0.389 |
Goat | +0.375 |
Caps | +0.353 |
================================================================ | +0.347 |
� | +0.339 |
Neg logit contributions | |
itton | -0.391 |
pez | -0.379 |
ocard | -0.374 |
atts | -0.352 |
ourage | -0.347 |
Token | for |
Token ID | 329 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
itton | +0.581 |
pez | +0.563 |
ocard | +0.557 |
atts | +0.528 |
ourage | +0.522 |
Neg logit contributions | |
Masquerade | -0.448 |
Goat | -0.430 |
Caps | -0.400 |
================================================================ | -0.394 |
� | -0.383 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
itton | +0.422 |
pez | +0.409 |
ocard | +0.404 |
atts | +0.380 |
ourage | +0.376 |
Neg logit contributions | |
Masquerade | -0.386 |
Goat | -0.372 |
Caps | -0.349 |
================================================================ | -0.343 |
� | -0.335 |
Token | city |
Token ID | 1748 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Masquerade | +0.052 |
Goat | +0.050 |
Caps | +0.047 |
================================================================ | +0.046 |
� | +0.045 |
Neg logit contributions | |
itton | -0.058 |
pez | -0.056 |
ocard | -0.056 |
atts | -0.053 |
ourage | -0.052 |
Token | ," |
Token ID | 553 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
Masquerade | +0.889 |
Goat | +0.856 |
Caps | +0.789 |
================================================================ | +0.771 |
� | +0.746 |
Neg logit contributions | |
itton | -1.365 |
pez | -1.324 |
ocard | -1.311 |
atts | -1.241 |
ourage | -1.226 |
Token | Ful |
Token ID | 28040 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Masquerade | +1.040 |
Goat | +0.996 |
Caps | +0.918 |
================================================================ | +0.895 |
� | +0.861 |
Neg logit contributions | |
itton | -1.619 |
pez | -1.574 |
ocard | -1.558 |
atts | -1.486 |
ourage | -1.459 |
Token | op |
Token ID | 404 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
Masquerade | +2.536 |
Goat | +2.435 |
Caps | +2.275 |
================================================================ | +2.200 |
ppa | +2.191 |
Neg logit contributions | |
itton | -6.919 |
ocard | -6.695 |
pez | -6.658 |
horm | -6.609 |
atts | -6.411 |
Token | said |
Token ID | 531 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Masquerade | +1.283 |
Goat | +1.233 |
Caps | +1.153 |
================================================================ | +1.128 |
� | +1.108 |
Neg logit contributions | |
itton | -1.548 |
pez | -1.497 |
ocard | -1.488 |
atts | -1.399 |
ourage | -1.386 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Masquerade | +0.915 |
Goat | +0.877 |
Caps | +0.814 |
================================================================ | +0.795 |
� | +0.779 |
Neg logit contributions | |
itton | -1.181 |
pez | -1.142 |
ocard | -1.133 |
atts | -1.072 |
ourage | -1.054 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
itton | +0.204 |
pez | +0.197 |
ocard | +0.195 |
atts | +0.184 |
ourage | +0.183 |
Neg logit contributions | |
Masquerade | -0.173 |
Goat | -0.166 |
Caps | -0.155 |
================================================================ | -0.153 |
� | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
itton | +0.441 |
pez | +0.427 |
ocard | +0.423 |
atts | +0.399 |
ourage | +0.395 |
Neg logit contributions | |
Masquerade | -0.339 |
Goat | -0.327 |
Caps | -0.306 |
================================================================ | -0.302 |
� | -0.289 |
Token | th |
Token ID | 400 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Masquerade | +0.700 |
Goat | +0.673 |
Caps | +0.628 |
================================================================ | +0.617 |
� | +0.599 |
Neg logit contributions | |
itton | -0.858 |
pez | -0.832 |
ocard | -0.824 |
atts | -0.778 |
ourage | -0.770 |
Token | Season |
Token ID | 7369 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Masquerade | +0.081 |
Goat | +0.077 |
Caps | +0.071 |
================================================================ | +0.069 |
� | +0.067 |
Neg logit contributions | |
itton | -0.128 |
pez | -0.124 |
ocard | -0.123 |
atts | -0.117 |
ourage | -0.116 |
Token | : |
Token ID | 25 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Masquerade | +0.379 |
Goat | +0.364 |
Caps | +0.341 |
================================================================ | +0.336 |
� | +0.325 |
Neg logit contributions | |
itton | -0.434 |
pez | -0.420 |
ocard | -0.416 |
atts | -0.393 |
ourage | -0.388 |
Token | Ghost |
Token ID | 9897 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Masquerade | +1.055 |
Goat | +1.016 |
Caps | +0.952 |
================================================================ | +0.929 |
� | +0.897 |
Neg logit contributions | |
itton | -1.257 |
pez | -1.218 |
ocard | -1.208 |
atts | -1.141 |
ourage | -1.124 |
Token | Island |
Token ID | 5451 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
itton | +0.804 |
pez | +0.778 |
ocard | +0.768 |
atts | +0.722 |
ourage | +0.712 |
Neg logit contributions | |
Masquerade | -0.768 |
Goat | -0.740 |
Caps | -0.696 |
================================================================ | -0.681 |
� | -0.665 |
Token | TBA |
Token ID | 48591 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
Masquerade | +0.211 |
Goat | +0.202 |
Caps | +0.189 |
================================================================ | +0.185 |
� | +0.179 |
Neg logit contributions | |
itton | -0.264 |
pez | -0.256 |
ocard | -0.254 |
atts | -0.240 |
ourage | -0.237 |
Token | TBA |
Token ID | 48591 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Masquerade | +4.219 |
Goat | +4.023 |
Caps | +3.725 |
================================================================ | +3.591 |
Pengu | +3.400 |
Neg logit contributions | |
itton | -5.691 |
pez | -5.600 |
ocard | -5.556 |
atts | -5.158 |
ourage | -5.113 |
Token | The |
Token ID | 383 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Masquerade | +4.380 |
Goat | +4.208 |
Caps | +3.897 |
================================================================ | +3.762 |
Pengu | +3.584 |
Neg logit contributions | |
itton | -5.544 |
pez | -5.423 |
ocard | -5.402 |
atts | -5.027 |
ourage | -4.970 |
Token | Complete |
Token ID | 13248 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
Masquerade | +1.046 |
Goat | +1.005 |
Caps | +0.934 |
================================================================ | +0.914 |
� | +0.881 |
Neg logit contributions | |
itton | -1.276 |
pez | -1.243 |
ocard | -1.223 |
atts | -1.156 |
ourage | -1.143 |
Token | Thirty |
Token ID | 29948 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
Masquerade | +1.245 |
Goat | +1.203 |
Caps | +1.131 |
================================================================ | +1.111 |
� | +1.083 |
Neg logit contributions | |
itton | -1.177 |
pez | -1.140 |
ocard | -1.125 |
atts | -1.051 |
ourage | -1.037 |
Token | - |
Token ID | 12 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
itton | +0.015 |
pez | +0.015 |
ocard | +0.015 |
atts | +0.014 |
ourage | +0.014 |
Neg logit contributions | |
Masquerade | -0.010 |
Goat | -0.009 |
Caps | -0.009 |
================================================================ | -0.008 |
� | -0.008 |
Token | Season |
Token ID | 7369 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Masquerade | +0.081 |
Goat | +0.077 |
Caps | +0.071 |
================================================================ | +0.069 |
� | +0.067 |
Neg logit contributions | |
itton | -0.128 |
pez | -0.124 |
ocard | -0.123 |
atts | -0.117 |
ourage | -0.116 |
Token | : |
Token ID | 25 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Masquerade | +0.379 |
Goat | +0.364 |
Caps | +0.341 |
================================================================ | +0.336 |
� | +0.325 |
Neg logit contributions | |
itton | -0.434 |
pez | -0.420 |
ocard | -0.416 |
atts | -0.393 |
ourage | -0.388 |
Token | Ghost |
Token ID | 9897 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Masquerade | +1.055 |
Goat | +1.016 |
Caps | +0.952 |
================================================================ | +0.929 |
� | +0.897 |
Neg logit contributions | |
itton | -1.257 |
pez | -1.218 |
ocard | -1.208 |
atts | -1.141 |
ourage | -1.124 |
Token | Island |
Token ID | 5451 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
itton | +0.804 |
pez | +0.778 |
ocard | +0.768 |
atts | +0.722 |
ourage | +0.712 |
Neg logit contributions | |
Masquerade | -0.768 |
Goat | -0.740 |
Caps | -0.696 |
================================================================ | -0.681 |
� | -0.665 |
Token | TBA |
Token ID | 48591 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
Masquerade | +0.211 |
Goat | +0.202 |
Caps | +0.189 |
================================================================ | +0.185 |
� | +0.179 |
Neg logit contributions | |
itton | -0.264 |
pez | -0.256 |
ocard | -0.254 |
atts | -0.240 |
ourage | -0.237 |
Token | TBA |
Token ID | 48591 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Masquerade | +4.219 |
Goat | +4.023 |
Caps | +3.725 |
================================================================ | +3.591 |
Pengu | +3.400 |
Neg logit contributions | |
itton | -5.691 |
pez | -5.600 |
ocard | -5.556 |
atts | -5.158 |
ourage | -5.113 |
Token | The |
Token ID | 383 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Masquerade | +4.380 |
Goat | +4.208 |
Caps | +3.897 |
================================================================ | +3.762 |
Pengu | +3.584 |
Neg logit contributions | |
itton | -5.544 |
pez | -5.423 |
ocard | -5.402 |
atts | -5.027 |
ourage | -4.970 |
Token | Complete |
Token ID | 13248 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
Masquerade | +1.046 |
Goat | +1.005 |
Caps | +0.934 |
================================================================ | +0.914 |
� | +0.881 |
Neg logit contributions | |
itton | -1.276 |
pez | -1.243 |
ocard | -1.223 |
atts | -1.156 |
ourage | -1.143 |
Token | Thirty |
Token ID | 29948 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
Masquerade | +1.245 |
Goat | +1.203 |
Caps | +1.131 |
================================================================ | +1.111 |
� | +1.083 |
Neg logit contributions | |
itton | -1.177 |
pez | -1.140 |
ocard | -1.125 |
atts | -1.051 |
ourage | -1.037 |
Token | - |
Token ID | 12 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
itton | +0.015 |
pez | +0.015 |
ocard | +0.015 |
atts | +0.014 |
ourage | +0.014 |
Neg logit contributions | |
Masquerade | -0.010 |
Goat | -0.009 |
Caps | -0.009 |
================================================================ | -0.008 |
� | -0.008 |
Token | Se |
Token ID | 4653 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
Masquerade | +0.593 |
Goat | +0.581 |
Caps | +0.552 |
================================================================ | +0.549 |
� | +0.538 |
Neg logit contributions | |
itton | -0.347 |
pez | -0.330 |
ocard | -0.327 |
atts | -0.302 |
ourage | -0.293 |
Token | 13 |
Token ID | 1511 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Masquerade | +0.001 |
Goat | +0.001 |
Caps | +0.001 |
================================================================ | +0.001 |
� | +0.001 |
Neg logit contributions | |
itton | -0.001 |
pez | -0.001 |
ocard | -0.001 |
atts | -0.001 |
ourage | -0.001 |
Token | days |
Token ID | 1528 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
Masquerade | +0.192 |
Goat | +0.184 |
Caps | +0.173 |
================================================================ | +0.170 |
� | +0.165 |
Neg logit contributions | |
itton | -0.221 |
pez | -0.214 |
ocard | -0.212 |
atts | -0.200 |
ourage | -0.198 |
Token | ). |
Token ID | 737 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
itton | +1.862 |
pez | +1.810 |
ocard | +1.791 |
atts | +1.702 |
ourage | +1.682 |
Neg logit contributions | |
Masquerade | -1.318 |
Goat | -1.255 |
Caps | -1.162 |
================================================================ | -1.145 |
� | -1.113 |
Token | Even |
Token ID | 3412 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
Masquerade | +1.015 |
Goat | +0.982 |
Caps | +0.920 |
================================================================ | +0.896 |
� | +0.866 |
Neg logit contributions | |
itton | -1.329 |
pez | -1.290 |
ocard | -1.274 |
atts | -1.209 |
ourage | -1.196 |
Token | emperor |
Token ID | 23129 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
itton | +0.114 |
pez | +0.110 |
ocard | +0.109 |
atts | +0.103 |
ourage | +0.102 |
Neg logit contributions | |
Masquerade | -0.097 |
Goat | -0.094 |
Caps | -0.088 |
================================================================ | -0.086 |
� | -0.084 |
Token | pengu |
Token ID | 38373 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Masquerade | +0.800 |
Goat | +0.760 |
Caps | +0.682 |
================================================================ | +0.661 |
� | +0.631 |
Neg logit contributions | |
itton | -1.908 |
pez | -1.862 |
ocard | -1.845 |
atts | -1.766 |
ourage | -1.757 |
Token | in |
Token ID | 259 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Masquerade | +3.603 |
Goat | +3.513 |
Caps | +3.373 |
================================================================ | +3.220 |
� | +3.139 |
Neg logit contributions | |
itton | -5.806 |
ocard | -5.507 |
pez | -5.421 |
ourage | -5.251 |
horm | -5.207 |
Token | dads |
Token ID | 47713 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
Masquerade | +0.764 |
Goat | +0.736 |
Caps | +0.697 |
================================================================ | +0.685 |
� | +0.669 |
Neg logit contributions | |
itton | -0.712 |
pez | -0.686 |
ocard | -0.677 |
atts | -0.633 |
ourage | -0.627 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
itton | +0.045 |
pez | +0.043 |
ocard | +0.043 |
atts | +0.040 |
ourage | +0.040 |
Neg logit contributions | |
Masquerade | -0.039 |
Goat | -0.037 |
Caps | -0.035 |
================================================================ | -0.034 |
� | -0.034 |
Token | who |
Token ID | 508 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
itton | +0.413 |
pez | +0.400 |
ocard | +0.396 |
atts | +0.373 |
ourage | +0.369 |
Neg logit contributions | |
Masquerade | -0.351 |
Goat | -0.338 |
Caps | -0.317 |
================================================================ | -0.311 |
� | -0.303 |
Token | famously |
Token ID | 20524 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
itton | +0.675 |
pez | +0.653 |
ocard | +0.646 |
atts | +0.607 |
ourage | +0.600 |
Neg logit contributions | |
Masquerade | -0.651 |
Goat | -0.626 |
Caps | -0.591 |
================================================================ | -0.579 |
� | -0.564 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Masquerade | +0.140 |
Goat | +0.135 |
Caps | +0.125 |
================================================================ | +0.123 |
� | +0.119 |
Neg logit contributions | |
itton | -0.183 |
pez | -0.177 |
ocard | -0.176 |
atts | -0.166 |
ourage | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Masquerade | +0.170 |
Goat | +0.163 |
Caps | +0.153 |
================================================================ | +0.150 |
� | +0.146 |
Neg logit contributions | |
itton | -0.198 |
pez | -0.191 |
ocard | -0.189 |
atts | -0.179 |
ourage | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Masquerade | +0.188 |
Goat | +0.181 |
Caps | +0.170 |
================================================================ | +0.168 |
mentation | +0.159 |
Neg logit contributions | |
itton | -0.257 |
pez | -0.248 |
ocard | -0.245 |
atts | -0.232 |
ourage | -0.230 |
Token | Expl |
Token ID | 18438 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
Masquerade | +0.349 |
Goat | +0.336 |
Caps | +0.315 |
================================================================ | +0.313 |
� | +0.303 |
Neg logit contributions | |
itton | -0.391 |
pez | -0.377 |
ocard | -0.374 |
atts | -0.352 |
ourage | -0.348 |
Token | ained |
Token ID | 1328 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
itton | +1.399 |
pez | +1.353 |
ocard | +1.337 |
atts | +1.257 |
ourage | +1.243 |
Neg logit contributions | |
Masquerade | -1.404 |
Goat | -1.352 |
Caps | -1.270 |
================================================================ | -1.254 |
� | -1.222 |
Token | Murd |
Token ID | 20305 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Masquerade | +1.359 |
Goat | +1.306 |
Caps | +1.214 |
================================================================ | +1.181 |
� | +1.145 |
Neg logit contributions | |
itton | -1.789 |
pez | -1.729 |
ocard | -1.710 |
atts | -1.624 |
ourage | -1.606 |
Token | y |
Token ID | 88 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Masquerade | +3.475 |
Goat | +3.300 |
Caps | +3.090 |
================================================================ | +2.993 |
mentation | +2.976 |
Neg logit contributions | |
itton | -5.903 |
ocard | -5.714 |
pez | -5.697 |
horm | -5.521 |
ourage | -5.334 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
itton | +0.255 |
pez | +0.247 |
ocard | +0.244 |
atts | +0.230 |
ourage | +0.228 |
Neg logit contributions | |
Masquerade | -0.213 |
Goat | -0.205 |
Caps | -0.191 |
================================================================ | -0.188 |
� | -0.183 |
Token | � |
Token ID | 564 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
Masquerade | +0.028 |
Goat | +0.027 |
Caps | +0.025 |
================================================================ | +0.025 |
� | +0.024 |
Neg logit contributions | |
itton | -0.031 |
pez | -0.030 |
ocard | -0.029 |
atts | -0.028 |
ourage | -0.027 |
Token | � |
Token ID | 250 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Masquerade | +0.668 |
Goat | +0.629 |
Caps | +0.561 |
================================================================ | +0.552 |
� | +0.540 |
Neg logit contributions | |
itton | -1.612 |
pez | -1.574 |
ocard | -1.562 |
atts | -1.496 |
ourage | -1.484 |
Token | We |
Token ID | 1135 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Masquerade | +0.562 |
Goat | +0.540 |
Caps | +0.506 |
================================================================ | +0.503 |
� | +0.487 |
Neg logit contributions | |
itton | -0.624 |
pez | -0.602 |
ocard | -0.594 |
atts | -0.558 |
ourage | -0.552 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
itton | +0.155 |
pez | +0.150 |
ocard | +0.149 |
atts | +0.140 |
ourage | +0.139 |
Neg logit contributions | |
Masquerade | -0.117 |
Goat | -0.113 |
Caps | -0.106 |
================================================================ | -0.104 |
� | -0.100 |
Token | William |
Token ID | 17121 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Masquerade | +0.020 |
Goat | +0.019 |
Caps | +0.018 |
================================================================ | +0.018 |
� | +0.017 |
Neg logit contributions | |
itton | -0.022 |
pez | -0.021 |
ocard | -0.021 |
atts | -0.020 |
ourage | -0.020 |
Token | Carpenter |
Token ID | 32659 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
itton | +0.505 |
pez | +0.490 |
ocard | +0.485 |
atts | +0.461 |
ourage | +0.456 |
Neg logit contributions | |
Masquerade | -0.359 |
Goat | -0.343 |
Caps | -0.318 |
================================================================ | -0.314 |
� | -0.304 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
itton | +0.096 |
pez | +0.093 |
ocard | +0.092 |
atts | +0.087 |
ourage | +0.086 |
Neg logit contributions | |
Masquerade | -0.076 |
Goat | -0.073 |
Caps | -0.068 |
================================================================ | -0.067 |
� | -0.065 |
Token | Mont |
Token ID | 5575 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Masquerade | +0.053 |
Goat | +0.051 |
Caps | +0.048 |
================================================================ | +0.046 |
� | +0.045 |
Neg logit contributions | |
itton | -0.073 |
pez | -0.071 |
ocard | -0.070 |
atts | -0.066 |
ourage | -0.066 |
Token | pel |
Token ID | 30242 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Masquerade | +0.301 |
Goat | +0.283 |
Caps | +0.253 |
================================================================ | +0.246 |
� | +0.233 |
Neg logit contributions | |
itton | -0.738 |
pez | -0.719 |
ocard | -0.715 |
atts | -0.684 |
ourage | -0.678 |
Token | ier |
Token ID | 959 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Masquerade | +4.828 |
Goat | +4.689 |
Caps | +4.399 |
mentation | +4.394 |
================================================================ | +4.376 |
Neg logit contributions | |
itton | -4.358 |
pez | -4.316 |
ocard | -4.257 |
horm | -4.104 |
atts | -4.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
itton | +0.242 |
pez | +0.235 |
ocard | +0.232 |
atts | +0.220 |
ourage | +0.217 |
Neg logit contributions | |
Masquerade | -0.201 |
Goat | -0.193 |
Caps | -0.180 |
================================================================ | -0.178 |
� | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Masquerade | +0.037 |
Goat | +0.035 |
Caps | +0.033 |
================================================================ | +0.033 |
� | +0.031 |
Neg logit contributions | |
itton | -0.049 |
pez | -0.048 |
ocard | -0.047 |
atts | -0.045 |
ourage | -0.044 |
Token | Con |
Token ID | 3103 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Masquerade | +0.198 |
Goat | +0.192 |
Caps | +0.180 |
================================================================ | +0.179 |
� | +0.173 |
Neg logit contributions | |
itton | -0.221 |
pez | -0.213 |
ocard | -0.211 |
atts | -0.198 |
ourage | -0.197 |
Token | Hogan |
Token ID | 25316 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Masquerade | +0.534 |
Goat | +0.520 |
Caps | +0.490 |
================================================================ | +0.484 |
� | +0.470 |
Neg logit contributions | |
itton | -0.481 |
pez | -0.467 |
ocard | -0.460 |
atts | -0.431 |
ourage | -0.422 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
itton | +1.027 |
pez | +0.996 |
ocard | +0.985 |
atts | +0.930 |
ourage | +0.920 |
Neg logit contributions | |
Masquerade | -0.863 |
Goat | -0.829 |
Caps | -0.773 |
================================================================ | -0.762 |
� | -0.743 |
Token | teeth |
Token ID | 9941 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
itton | +0.577 |
pez | +0.559 |
ocard | +0.553 |
atts | +0.521 |
ourage | +0.515 |
Neg logit contributions | |
Masquerade | -0.509 |
Goat | -0.490 |
Caps | -0.459 |
================================================================ | -0.452 |
� | -0.441 |
Token | are |
Token ID | 389 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Masquerade | +1.879 |
Goat | +1.806 |
Caps | +1.704 |
================================================================ | +1.658 |
� | +1.615 |
Neg logit contributions | |
itton | -2.315 |
pez | -2.252 |
ocard | -2.214 |
atts | -2.112 |
ourage | -2.075 |
Token | formed |
Token ID | 7042 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
itton | +0.298 |
pez | +0.288 |
ocard | +0.286 |
atts | +0.269 |
ourage | +0.266 |
Neg logit contributions | |
Masquerade | -0.268 |
Goat | -0.259 |
Caps | -0.243 |
================================================================ | -0.239 |
� | -0.233 |
Token | from |
Token ID | 422 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Masquerade | +1.050 |
Goat | +1.017 |
Caps | +0.958 |
================================================================ | +0.936 |
� | +0.914 |
Neg logit contributions | |
itton | -1.087 |
pez | -1.041 |
ocard | -1.036 |
atts | -0.977 |
ourage | -0.959 |
Token | dent |
Token ID | 18794 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Masquerade | +0.523 |
Goat | +0.506 |
Caps | +0.475 |
================================================================ | +0.465 |
� | +0.453 |
Neg logit contributions | |
itton | -0.588 |
pez | -0.569 |
ocard | -0.561 |
atts | -0.533 |
ourage | -0.525 |
Token | in |
Token ID | 259 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Masquerade | +4.739 |
Goat | +4.646 |
Caps | +4.429 |
================================================================ | +4.271 |
mentation | +4.248 |
Neg logit contributions | |
itton | -4.681 |
pez | -4.564 |
ocard | -4.360 |
atts | -4.236 |
horm | -4.135 |
Token | , |
Token ID | 11 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Masquerade | +0.648 |
Goat | +0.621 |
Caps | +0.577 |
================================================================ | +0.568 |
� | +0.552 |
Neg logit contributions | |
itton | -0.846 |
pez | -0.821 |
ocard | -0.813 |
atts | -0.768 |
ourage | -0.761 |
Token | a |
Token ID | 257 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Masquerade | +0.072 |
Goat | +0.070 |
Caps | +0.065 |
================================================================ | +0.064 |
� | +0.063 |
Neg logit contributions | |
itton | -0.081 |
pez | -0.079 |
ocard | -0.078 |
atts | -0.074 |
ourage | -0.073 |
Token | liquid |
Token ID | 8122 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
Masquerade | +0.041 |
Goat | +0.039 |
Caps | +0.037 |
================================================================ | +0.036 |
� | +0.035 |
Neg logit contributions | |
itton | -0.047 |
pez | -0.046 |
ocard | -0.045 |
atts | -0.043 |
ourage | -0.042 |
Token | that |
Token ID | 326 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
Masquerade | +1.376 |
Goat | +1.330 |
Caps | +1.244 |
================================================================ | +1.213 |
� | +1.184 |
Neg logit contributions | |
itton | -1.706 |
pez | -1.653 |
ocard | -1.639 |
atts | -1.557 |
ourage | -1.530 |
Token | even |
Token ID | 772 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
itton | +1.159 |
pez | +1.122 |
ocard | +1.110 |
atts | +1.047 |
ourage | +1.035 |
Neg logit contributions | |
Masquerade | -1.008 |
Goat | -0.970 |
Caps | -0.909 |
================================================================ | -0.893 |
� | -0.870 |
Token | in |
Token ID | 287 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Masquerade | +0.194 |
Goat | +0.187 |
Caps | +0.176 |
================================================================ | +0.171 |
� | +0.166 |
Neg logit contributions | |
itton | -0.235 |
pez | -0.226 |
ocard | -0.223 |
atts | -0.211 |
ourage | -0.209 |
Token | a |
Token ID | 257 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
itton | +0.132 |
pez | +0.128 |
ocard | +0.126 |
atts | +0.119 |
ourage | +0.118 |
Neg logit contributions | |
Masquerade | -0.113 |
Goat | -0.109 |
Caps | -0.102 |
================================================================ | -0.100 |
� | -0.098 |
Token | land |
Token ID | 1956 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
itton | +0.555 |
pez | +0.537 |
ocard | +0.531 |
atts | +0.500 |
ourage | +0.495 |
Neg logit contributions | |
Masquerade | -0.495 |
Goat | -0.477 |
Caps | -0.446 |
================================================================ | -0.439 |
� | -0.428 |
Token | of |
Token ID | 286 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
Masquerade | +0.524 |
Goat | +0.503 |
Caps | +0.466 |
================================================================ | +0.456 |
� | +0.444 |
Neg logit contributions | |
itton | -0.774 |
pez | -0.751 |
ocard | -0.745 |
atts | -0.708 |
ourage | -0.700 |
Token | glaciers |
Token ID | 40509 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Masquerade | +0.085 |
Goat | +0.082 |
Caps | +0.077 |
================================================================ | +0.075 |
� | +0.073 |
Neg logit contributions | |
itton | -0.097 |
pez | -0.094 |
ocard | -0.092 |
atts | -0.087 |
ourage | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Masquerade | +3.937 |
Goat | +3.802 |
Caps | +3.610 |
================================================================ | +3.444 |
� | +3.345 |
Neg logit contributions | |
itton | -5.617 |
ocard | -5.442 |
pez | -5.378 |
ourage | -5.072 |
atts | -5.042 |
Token | Jak |
Token ID | 25845 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
itton | +0.406 |
pez | +0.394 |
ocard | +0.389 |
atts | +0.367 |
ourage | +0.363 |
Neg logit contributions | |
Masquerade | -0.342 |
Goat | -0.329 |
Caps | -0.308 |
================================================================ | -0.302 |
� | -0.294 |
Token | ob |
Token ID | 672 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Masquerade | +1.209 |
Goat | +1.183 |
Caps | +1.135 |
================================================================ | +1.119 |
� | +1.098 |
Neg logit contributions | |
itton | -0.634 |
pez | -0.597 |
ocard | -0.590 |
atts | -0.536 |
ourage | -0.527 |
Token | sh |
Token ID | 1477 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
itton | +0.393 |
pez | +0.379 |
ocard | +0.375 |
atts | +0.350 |
ourage | +0.346 |
Neg logit contributions | |
Masquerade | -0.429 |
Goat | -0.415 |
Caps | -0.391 |
================================================================ | -0.386 |
� | -0.377 |
Token | av |
Token ID | 615 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
itton | +0.784 |
pez | +0.751 |
ocard | +0.740 |
atts | +0.682 |
ourage | +0.671 |
Neg logit contributions | |
Masquerade | -1.214 |
Goat | -1.178 |
Caps | -1.119 |
================================================================ | -1.106 |
� | -1.088 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
itton | +1.913 |
pez | +1.858 |
ocard | +1.837 |
atts | +1.744 |
ourage | +1.731 |
Neg logit contributions | |
Masquerade | -1.372 |
Goat | -1.314 |
Caps | -1.211 |
================================================================ | -1.193 |
� | -1.163 |
Token |
|
Token ID | 198 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
itton | +0.269 |
pez | +0.261 |
ocard | +0.258 |
atts | +0.244 |
ourage | +0.241 |
Neg logit contributions | |
Masquerade | -0.222 |
Goat | -0.213 |
Caps | -0.199 |
================================================================ | -0.196 |
� | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
itton | +0.165 |
pez | +0.160 |
ocard | +0.158 |
atts | +0.149 |
ourage | +0.148 |
Neg logit contributions | |
Masquerade | -0.125 |
Goat | -0.120 |
Caps | -0.113 |
================================================================ | -0.111 |
� | -0.106 |
Token | � |
Token ID | 447 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Masquerade | +0.012 |
Goat | +0.011 |
Caps | +0.010 |
================================================================ | +0.010 |
� | +0.010 |
Neg logit contributions | |
itton | -0.012 |
pez | -0.012 |
ocard | -0.011 |
atts | -0.011 |
ourage | -0.011 |
Token | � |
Token ID | 250 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
itton | +0.560 |
pez | +0.547 |
ocard | +0.542 |
atts | +0.519 |
ourage | +0.514 |
Neg logit contributions | |
Masquerade | -0.236 |
Goat | -0.222 |
Caps | -0.199 |
================================================================ | -0.194 |
� | -0.186 |
Token | Tr |
Token ID | 2898 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
itton | +0.074 |
pez | +0.072 |
ocard | +0.071 |
atts | +0.066 |
ourage | +0.065 |
Neg logit contributions | |
Masquerade | -0.069 |
Goat | -0.066 |
Caps | -0.063 |
================================================================ | -0.062 |
� | -0.060 |
Token | uman |
Token ID | 3778 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
itton | +4.116 |
pez | +3.972 |
ocard | +3.940 |
atts | +3.746 |
ourage | +3.705 |
Neg logit contributions | |
Masquerade | -2.998 |
Goat | -2.865 |
Caps | -2.649 |
================================================================ | -2.604 |
� | -2.525 |
Token | was |
Token ID | 373 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
itton | +0.423 |
pez | +0.410 |
ocard | +0.406 |
atts | +0.384 |
ourage | +0.380 |
Neg logit contributions | |
Masquerade | -0.329 |
Goat | -0.316 |
Caps | -0.295 |
================================================================ | -0.290 |
� | -0.282 |
Token | g |
Token ID | 308 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
itton | +0.023 |
pez | +0.022 |
ocard | +0.022 |
atts | +0.020 |
ourage | +0.020 |
Neg logit contributions | |
Masquerade | -0.022 |
Goat | -0.021 |
Caps | -0.020 |
================================================================ | -0.019 |
� | -0.019 |
Token | rieved |
Token ID | 28130 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Masquerade | +0.797 |
Goat | +0.776 |
Caps | +0.733 |
================================================================ | +0.725 |
� | +0.708 |
Neg logit contributions | |
itton | -0.683 |
pez | -0.657 |
ocard | -0.649 |
atts | -0.604 |
ourage | -0.593 |
Token | by |
Token ID | 416 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
itton | +1.030 |
pez | +1.001 |
ocard | +0.986 |
atts | +0.928 |
ourage | +0.919 |
Neg logit contributions | |
Masquerade | -0.963 |
Goat | -0.927 |
Caps | -0.867 |
================================================================ | -0.858 |
� | -0.836 |
Token | - |
Token ID | 12 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Masquerade | +0.242 |
Goat | +0.232 |
Caps | +0.215 |
================================================================ | +0.210 |
� | +0.204 |
Neg logit contributions | |
itton | -0.366 |
pez | -0.356 |
ocard | -0.352 |
atts | -0.334 |
ourage | -0.331 |
Token | wife |
Token ID | 22095 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Masquerade | +0.371 |
Goat | +0.359 |
Caps | +0.337 |
================================================================ | +0.335 |
� | +0.326 |
Neg logit contributions | |
itton | -0.366 |
pez | -0.351 |
ocard | -0.346 |
atts | -0.325 |
ourage | -0.319 |
Token | of |
Token ID | 286 |
Feature activation | +6.49e-03 |
Pos logit contributions | |
Masquerade | +1.146 |
Goat | +1.109 |
Caps | +1.038 |
================================================================ | +1.020 |
� | +1.001 |
Neg logit contributions | |
itton | -1.193 |
pez | -1.157 |
ocard | -1.140 |
atts | -1.070 |
ourage | -1.059 |
Token | Right |
Token ID | 6498 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
itton | +0.012 |
pez | +0.011 |
ocard | +0.011 |
atts | +0.010 |
ourage | +0.010 |
Neg logit contributions | |
Masquerade | -0.010 |
Goat | -0.010 |
Caps | -0.009 |
================================================================ | -0.009 |
� | -0.009 |
Token | eous |
Token ID | 15303 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
itton | +2.175 |
pez | +2.111 |
ocard | +2.093 |
atts | +1.976 |
ourage | +1.958 |
Neg logit contributions | |
Masquerade | -1.781 |
Goat | -1.703 |
Caps | -1.587 |
================================================================ | -1.575 |
� | -1.525 |
Token | Brothers |
Token ID | 16055 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Masquerade | +0.233 |
Goat | +0.225 |
Caps | +0.210 |
================================================================ | +0.205 |
� | +0.200 |
Neg logit contributions | |
itton | -0.252 |
pez | -0.244 |
ocard | -0.241 |
atts | -0.227 |
ourage | -0.224 |
Token | singer |
Token ID | 14015 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
itton | +3.594 |
pez | +3.486 |
ocard | +3.448 |
atts | +3.235 |
ourage | +3.224 |
Neg logit contributions | |
Masquerade | -3.114 |
Goat | -2.967 |
================================================================ | -2.802 |
Caps | -2.799 |
� | -2.712 |
Token | Bill |
Token ID | 3941 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
itton | +0.535 |
pez | +0.519 |
ocard | +0.513 |
atts | +0.485 |
ourage | +0.480 |
Neg logit contributions | |
Masquerade | -0.421 |
Goat | -0.404 |
Caps | -0.376 |
================================================================ | -0.370 |
� | -0.360 |
Token | Med |
Token ID | 2019 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Masquerade | +0.548 |
Goat | +0.525 |
Caps | +0.486 |
================================================================ | +0.477 |
� | +0.463 |
Neg logit contributions | |
itton | -0.789 |
pez | -0.767 |
ocard | -0.759 |
atts | -0.719 |
ourage | -0.713 |
Token | ley |
Token ID | 1636 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
itton | +0.064 |
pez | +0.062 |
ocard | +0.061 |
atts | +0.058 |
ourage | +0.058 |
Neg logit contributions | |
Masquerade | -0.046 |
Goat | -0.044 |
Caps | -0.041 |
================================================================ | -0.040 |
� | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
itton | +1.010 |
pez | +0.982 |
ocard | +0.971 |
atts | +0.921 |
ourage | +0.912 |
Neg logit contributions | |
Masquerade | -0.726 |
Goat | -0.694 |
Caps | -0.644 |
================================================================ | -0.634 |
� | -0.615 |
Token | play |
Token ID | 711 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
itton | +0.006 |
pez | +0.006 |
ocard | +0.006 |
atts | +0.006 |
ourage | +0.006 |
Neg logit contributions | |
Masquerade | -0.005 |
Goat | -0.005 |
Caps | -0.005 |
================================================================ | -0.005 |
� | -0.005 |
Token | physical |
Token ID | 3518 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
itton | +0.446 |
pez | +0.431 |
ocard | +0.428 |
atts | +0.403 |
ourage | +0.397 |
Neg logit contributions | |
Masquerade | -0.404 |
Goat | -0.388 |
Caps | -0.365 |
================================================================ | -0.355 |
� | -0.348 |
Token | and |
Token ID | 290 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
itton | +0.924 |
pez | +0.897 |
ocard | +0.888 |
atts | +0.841 |
ourage | +0.832 |
Neg logit contributions | |
Masquerade | -0.689 |
Goat | -0.660 |
Caps | -0.614 |
================================================================ | -0.604 |
� | -0.587 |
Token | re |
Token ID | 302 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
itton | +0.131 |
pez | +0.128 |
ocard | +0.126 |
atts | +0.119 |
ourage | +0.117 |
Neg logit contributions | |
Masquerade | -0.116 |
Goat | -0.111 |
Caps | -0.105 |
================================================================ | -0.102 |
� | -0.099 |
Token | - |
Token ID | 12 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
itton | +2.833 |
pez | +2.748 |
ocard | +2.712 |
atts | +2.572 |
ourage | +2.553 |
Neg logit contributions | |
Masquerade | -2.168 |
Goat | -2.079 |
Caps | -1.930 |
================================================================ | -1.901 |
� | -1.851 |
Token | route |
Token ID | 38629 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
itton | +0.486 |
pez | +0.470 |
ocard | +0.464 |
atts | +0.434 |
ourage | +0.426 |
Neg logit contributions | |
Masquerade | -0.505 |
Goat | -0.483 |
Caps | -0.458 |
================================================================ | -0.454 |
mentation | -0.441 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
itton | +3.530 |
pez | +3.415 |
ocard | +3.340 |
atts | +3.174 |
ourage | +3.150 |
Neg logit contributions | |
Masquerade | -3.296 |
Goat | -3.158 |
================================================================ | -2.957 |
Caps | -2.942 |
� | -2.881 |
Token | to |
Token ID | 284 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Masquerade | +0.365 |
Goat | +0.351 |
Caps | +0.330 |
================================================================ | +0.319 |
� | +0.310 |
Neg logit contributions | |
itton | -0.475 |
pez | -0.460 |
ocard | -0.460 |
atts | -0.430 |
ourage | -0.425 |
Token | throw |
Token ID | 3714 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
itton | +0.447 |
pez | +0.434 |
ocard | +0.429 |
atts | +0.404 |
ourage | +0.400 |
Neg logit contributions | |
Masquerade | -0.396 |
Goat | -0.381 |
Caps | -0.357 |
================================================================ | -0.351 |
� | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
itton | +0.791 |
pez | +0.766 |
ocard | +0.760 |
atts | +0.714 |
ourage | +0.706 |
Neg logit contributions | |
Masquerade | -0.697 |
Goat | -0.671 |
Caps | -0.629 |
================================================================ | -0.618 |
� | -0.602 |
Token | timing |
Token ID | 10576 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
itton | +0.715 |
pez | +0.695 |
ocard | +0.688 |
atts | +0.654 |
ourage | +0.647 |
Neg logit contributions | |
Masquerade | -0.477 |
Goat | -0.456 |
Caps | -0.421 |
================================================================ | -0.414 |
� | -0.401 |
Token | hes |
Token ID | 956 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
Masquerade | +1.440 |
Goat | +1.395 |
Caps | +1.324 |
================================================================ | +1.291 |
� | +1.271 |
Neg logit contributions | |
itton | -1.355 |
pez | -1.313 |
ocard | -1.286 |
atts | -1.195 |
ourage | -1.175 |
Token | story |
Token ID | 1621 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Masquerade | +0.053 |
Goat | +0.051 |
Caps | +0.048 |
================================================================ | +0.047 |
� | +0.046 |
Neg logit contributions | |
itton | -0.057 |
pez | -0.056 |
ocard | -0.055 |
atts | -0.052 |
ourage | -0.051 |
Token | " |
Token ID | 1 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
itton | +0.991 |
pez | +0.964 |
ocard | +0.954 |
atts | +0.906 |
ourage | +0.897 |
Neg logit contributions | |
Masquerade | -0.657 |
Goat | -0.628 |
Caps | -0.581 |
================================================================ | -0.570 |
� | -0.553 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Masquerade | +0.594 |
Goat | +0.574 |
Caps | +0.535 |
================================================================ | +0.524 |
� | +0.511 |
Neg logit contributions | |
itton | -0.828 |
pez | -0.802 |
ocard | -0.799 |
atts | -0.753 |
ourage | -0.749 |
Token | ( |
Token ID | 7 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
Masquerade | +1.364 |
Goat | +1.311 |
================================================================ | +1.253 |
Caps | +1.234 |
� | +1.193 |
Neg logit contributions | |
itton | -1.501 |
pez | -1.444 |
ocard | -1.430 |
atts | -1.343 |
ourage | -1.331 |
Token | Phys |
Token ID | 43215 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Masquerade | +0.031 |
Goat | +0.030 |
Caps | +0.029 |
================================================================ | +0.028 |
� | +0.027 |
Neg logit contributions | |
itton | -0.032 |
pez | -0.031 |
ocard | -0.031 |
atts | -0.029 |
ourage | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
itton | +4.216 |
ocard | +4.136 |
pez | +4.071 |
atts | +3.892 |
ourage | +3.795 |
Neg logit contributions | |
Masquerade | -2.917 |
Goat | -2.791 |
Caps | -2.580 |
================================================================ | -2.572 |
mentation | -2.465 |
Token | org |
Token ID | 2398 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Masquerade | +0.009 |
Goat | +0.008 |
Caps | +0.008 |
================================================================ | +0.007 |
� | +0.007 |
Neg logit contributions | |
itton | -0.019 |
pez | -0.019 |
ocard | -0.019 |
atts | -0.018 |
ourage | -0.018 |
Token | ) |
Token ID | 8 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
Masquerade | +0.284 |
Goat | +0.270 |
Caps | +0.253 |
================================================================ | +0.248 |
� | +0.241 |
Neg logit contributions | |
itton | -0.374 |
pez | -0.367 |
ocard | -0.363 |
atts | -0.341 |
ourage | -0.338 |
Token | -- |
Token ID | 1377 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
itton | +0.086 |
pez | +0.084 |
ocard | +0.083 |
atts | +0.079 |
ourage | +0.078 |
Neg logit contributions | |
Masquerade | -0.056 |
Goat | -0.054 |
Caps | -0.050 |
================================================================ | -0.049 |
� | -0.048 |
Token | An |
Token ID | 1052 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Masquerade | +0.659 |
Goat | +0.637 |
Caps | +0.597 |
================================================================ | +0.583 |
� | +0.565 |
Neg logit contributions | |
itton | -0.791 |
pez | -0.766 |
ocard | -0.757 |
atts | -0.715 |
ourage | -0.708 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
itton | +0.577 |
pez | +0.559 |
ocard | +0.553 |
atts | +0.520 |
ourage | +0.514 |
Neg logit contributions | |
Masquerade | -0.527 |
Goat | -0.509 |
Caps | -0.480 |
================================================================ | -0.470 |
� | -0.457 |
Token | 73 |
Token ID | 8854 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
itton | +0.486 |
pez | +0.469 |
ocard | +0.464 |
atts | +0.437 |
ourage | +0.432 |
Neg logit contributions | |
Masquerade | -0.455 |
Goat | -0.440 |
Caps | -0.414 |
================================================================ | -0.407 |
� | -0.396 |
Token | rd |
Token ID | 4372 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
itton | +1.398 |
pez | +1.356 |
ocard | +1.340 |
atts | +1.266 |
ourage | +1.252 |
Neg logit contributions | |
Masquerade | -1.163 |
Goat | -1.116 |
Caps | -1.041 |
================================================================ | -1.026 |
� | -0.999 |
Token | minute |
Token ID | 5664 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
itton | +0.435 |
pez | +0.421 |
ocard | +0.416 |
atts | +0.390 |
ourage | +0.385 |
Neg logit contributions | |
Masquerade | -0.451 |
Goat | -0.436 |
Caps | -0.411 |
================================================================ | -0.404 |
� | -0.395 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
itton | +1.764 |
pez | +1.711 |
ocard | +1.690 |
atts | +1.594 |
ourage | +1.579 |
Neg logit contributions | |
Masquerade | -1.505 |
Goat | -1.446 |
Caps | -1.348 |
================================================================ | -1.333 |
� | -1.299 |
Token | Ireland |
Token ID | 7517 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
itton | +0.908 |
pez | +0.879 |
ocard | +0.870 |
atts | +0.822 |
ourage | +0.810 |
Neg logit contributions | |
Masquerade | -0.788 |
Goat | -0.759 |
Caps | -0.712 |
================================================================ | -0.696 |
� | -0.678 |
Token | also |
Token ID | 635 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
itton | +3.992 |
pez | +3.877 |
ocard | +3.811 |
atts | +3.593 |
ourage | +3.561 |
Neg logit contributions | |
Masquerade | -3.625 |
Goat | -3.478 |
Caps | -3.228 |
================================================================ | -3.216 |
� | -3.128 |
Token | had |
Token ID | 550 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
itton | +0.333 |
pez | +0.321 |
ocard | +0.321 |
atts | +0.301 |
ourage | +0.297 |
Neg logit contributions | |
Masquerade | -0.307 |
Goat | -0.295 |
Caps | -0.279 |
================================================================ | -0.272 |
� | -0.266 |
Token | a |
Token ID | 257 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
itton | +0.773 |
pez | +0.749 |
ocard | +0.740 |
atts | +0.698 |
ourage | +0.690 |
Neg logit contributions | |
Masquerade | -0.689 |
Goat | -0.665 |
Caps | -0.624 |
================================================================ | -0.611 |
� | -0.595 |
Token | number |
Token ID | 1271 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
itton | +0.826 |
pez | +0.798 |
ocard | +0.789 |
atts | +0.743 |
ourage | +0.733 |
Neg logit contributions | |
Masquerade | -0.819 |
Goat | -0.791 |
Caps | -0.746 |
================================================================ | -0.729 |
� | -0.712 |
Token | of |
Token ID | 286 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
itton | +0.644 |
pez | +0.624 |
ocard | +0.616 |
atts | +0.579 |
ourage | +0.572 |
Neg logit contributions | |
Masquerade | -0.637 |
Goat | -0.615 |
Caps | -0.577 |
================================================================ | -0.568 |
� | -0.556 |
Token | a |
Token ID | 257 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
itton | +0.794 |
pez | +0.772 |
ocard | +0.764 |
atts | +0.722 |
ourage | +0.713 |
Neg logit contributions | |
Masquerade | -0.664 |
Goat | -0.641 |
Caps | -0.604 |
================================================================ | -0.591 |
� | -0.573 |
Token | failed |
Token ID | 4054 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
itton | +0.676 |
pez | +0.653 |
ocard | +0.647 |
atts | +0.609 |
ourage | +0.602 |
Neg logit contributions | |
Masquerade | -0.637 |
Goat | -0.616 |
Caps | -0.580 |
================================================================ | -0.568 |
� | -0.556 |
Token | sensor |
Token ID | 12694 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
itton | +0.812 |
pez | +0.784 |
ocard | +0.773 |
atts | +0.725 |
ourage | +0.717 |
Neg logit contributions | |
Masquerade | -0.861 |
Goat | -0.831 |
Caps | -0.787 |
================================================================ | -0.770 |
� | -0.752 |
Token | providing |
Token ID | 4955 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
itton | +1.041 |
pez | +1.010 |
ocard | +0.995 |
atts | +0.940 |
ourage | +0.930 |
Neg logit contributions | |
Masquerade | -0.913 |
Goat | -0.879 |
Caps | -0.826 |
================================================================ | -0.812 |
� | -0.790 |
Token | false |
Token ID | 3991 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
itton | +1.312 |
pez | +1.264 |
ocard | +1.251 |
atts | +1.168 |
ourage | +1.158 |
Neg logit contributions | |
Masquerade | -1.339 |
Goat | -1.295 |
Caps | -1.222 |
================================================================ | -1.200 |
� | -1.170 |
Token | information |
Token ID | 1321 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
itton | +0.809 |
pez | +0.779 |
ocard | +0.770 |
atts | +0.717 |
ourage | +0.711 |
Neg logit contributions | |
Masquerade | -0.865 |
Goat | -0.837 |
Caps | -0.791 |
================================================================ | -0.776 |
� | -0.757 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
itton | +0.353 |
pez | +0.341 |
ocard | +0.337 |
atts | +0.318 |
ourage | +0.315 |
Neg logit contributions | |
Masquerade | -0.279 |
Goat | -0.268 |
Caps | -0.251 |
================================================================ | -0.245 |
� | -0.237 |
Token | which |
Token ID | 543 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
itton | +1.054 |
pez | +1.021 |
ocard | +1.008 |
atts | +0.949 |
ourage | +0.938 |
Neg logit contributions | |
Masquerade | -0.942 |
Goat | -0.910 |
Caps | -0.854 |
================================================================ | -0.838 |
� | -0.816 |
Token | Remote |
Token ID | 21520 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
itton | +1.563 |
pez | +1.513 |
ocard | +1.494 |
atts | +1.404 |
ourage | +1.388 |
Neg logit contributions | |
Masquerade | -1.489 |
Goat | -1.436 |
Caps | -1.352 |
================================================================ | -1.328 |
� | -1.296 |
Token | Agent |
Token ID | 15906 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
itton | +1.734 |
pez | +1.676 |
ocard | +1.662 |
atts | +1.556 |
ourage | +1.542 |
Neg logit contributions | |
Masquerade | -1.797 |
Goat | -1.725 |
Caps | -1.617 |
================================================================ | -1.609 |
� | -1.583 |
Token | recognized |
Token ID | 8018 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
itton | +1.295 |
pez | +1.255 |
ocard | +1.244 |
atts | +1.168 |
ourage | +1.157 |
Neg logit contributions | |
Masquerade | -1.140 |
Goat | -1.099 |
Caps | -1.033 |
================================================================ | -1.015 |
� | -0.988 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
itton | +0.155 |
pez | +0.150 |
ocard | +0.149 |
atts | +0.140 |
ourage | +0.139 |
Neg logit contributions | |
Masquerade | -0.129 |
Goat | -0.124 |
Caps | -0.116 |
================================================================ | -0.114 |
� | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
itton | +0.097 |
pez | +0.094 |
ocard | +0.093 |
atts | +0.088 |
ourage | +0.087 |
Neg logit contributions | |
Masquerade | -0.073 |
Goat | -0.070 |
Caps | -0.066 |
================================================================ | -0.065 |
� | -0.062 |
Token | The |
Token ID | 464 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Masquerade | +0.083 |
Goat | +0.080 |
Caps | +0.075 |
================================================================ | +0.075 |
� | +0.072 |
Neg logit contributions | |
itton | -0.091 |
pez | -0.087 |
ocard | -0.087 |
atts | -0.081 |
ourage | -0.080 |
Token | city |
Token ID | 1748 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Masquerade | +0.332 |
Goat | +0.320 |
Caps | +0.299 |
================================================================ | +0.292 |
� | +0.285 |
Neg logit contributions | |
itton | -0.402 |
pez | -0.390 |
ocard | -0.385 |
atts | -0.363 |
ourage | -0.360 |
Token | is |
Token ID | 318 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Masquerade | +0.909 |
Goat | +0.875 |
Caps | +0.820 |
================================================================ | +0.801 |
� | +0.784 |
Neg logit contributions | |
itton | -1.105 |
pez | -1.069 |
ocard | -1.061 |
atts | -1.001 |
ourage | -0.990 |
Token | claiming |
Token ID | 8512 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Masquerade | +0.280 |
Goat | +0.271 |
Caps | +0.256 |
================================================================ | +0.250 |
� | +0.246 |
Neg logit contributions | |
itton | -0.283 |
pez | -0.274 |
ocard | -0.273 |
atts | -0.254 |
ourage | -0.252 |
Token | at |
Token ID | 379 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
itton | +0.724 |
pez | +0.703 |
ocard | +0.696 |
atts | +0.658 |
ourage | +0.651 |
Neg logit contributions | |
Masquerade | -0.554 |
Goat | -0.533 |
Caps | -0.495 |
================================================================ | -0.486 |
� | -0.473 |
Token | least |
Token ID | 1551 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Masquerade | +1.287 |
Goat | +1.242 |
Caps | +1.148 |
================================================================ | +1.117 |
� | +1.088 |
Neg logit contributions | |
itton | -1.826 |
pez | -1.778 |
ocard | -1.756 |
atts | -1.665 |
ourage | -1.651 |
Token | short |
Token ID | 1790 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
itton | +0.274 |
pez | +0.265 |
ocard | +0.263 |
atts | +0.247 |
ourage | +0.244 |
Neg logit contributions | |
Masquerade | -0.260 |
Goat | -0.251 |
Caps | -0.235 |
================================================================ | -0.231 |
� | -0.226 |
Token | - |
Token ID | 12 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
Masquerade | +0.486 |
Goat | +0.468 |
Caps | +0.432 |
================================================================ | +0.419 |
� | +0.410 |
Neg logit contributions | |
itton | -0.762 |
pez | -0.744 |
ocard | -0.736 |
atts | -0.699 |
ourage | -0.693 |
Token | term |
Token ID | 4354 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
itton | +0.011 |
pez | +0.011 |
ocard | +0.011 |
atts | +0.010 |
ourage | +0.010 |
Neg logit contributions | |
Masquerade | -0.005 |
Goat | -0.005 |
Caps | -0.005 |
================================================================ | -0.005 |
� | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Masquerade | +0.905 |
Goat | +0.878 |
Caps | +0.824 |
================================================================ | +0.791 |
� | +0.774 |
Neg logit contributions | |
itton | -1.183 |
pez | -1.152 |
ocard | -1.138 |
atts | -1.082 |
ourage | -1.064 |
Token | � |
Token ID | 447 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
itton | +0.694 |
pez | +0.673 |
ocard | +0.666 |
atts | +0.628 |
ourage | +0.621 |
Neg logit contributions | |
Masquerade | -0.585 |
Goat | -0.563 |
Caps | -0.528 |
================================================================ | -0.519 |
� | -0.506 |
Token | � |
Token ID | 247 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
itton | +0.571 |
pez | +0.553 |
ocard | +0.544 |
atts | +0.509 |
ourage | +0.503 |
Neg logit contributions | |
Masquerade | -0.614 |
Goat | -0.592 |
Caps | -0.559 |
================================================================ | -0.549 |
� | -0.531 |
Token | re |
Token ID | 260 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
itton | +0.387 |
pez | +0.374 |
ocard | +0.371 |
atts | +0.350 |
ourage | +0.346 |
Neg logit contributions | |
Masquerade | -0.322 |
Goat | -0.309 |
Caps | -0.289 |
================================================================ | -0.285 |
� | -0.278 |
Token | learning |
Token ID | 4673 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
itton | +1.038 |
pez | +1.004 |
ocard | +0.997 |
atts | +0.934 |
ourage | +0.927 |
Neg logit contributions | |
Masquerade | -0.935 |
Goat | -0.902 |
Caps | -0.850 |
================================================================ | -0.836 |
� | -0.815 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
itton | +0.352 |
pez | +0.342 |
ocard | +0.338 |
atts | +0.318 |
ourage | +0.314 |
Neg logit contributions | |
Masquerade | -0.320 |
Goat | -0.308 |
Caps | -0.289 |
================================================================ | -0.284 |
� | -0.277 |
Token | We |
Token ID | 775 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
itton | +0.491 |
pez | +0.477 |
ocard | +0.471 |
atts | +0.446 |
ourage | +0.441 |
Neg logit contributions | |
Masquerade | -0.390 |
Goat | -0.375 |
Caps | -0.349 |
================================================================ | -0.343 |
� | -0.334 |
Token | learned |
Token ID | 4499 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
itton | +0.890 |
pez | +0.864 |
ocard | +0.855 |
atts | +0.807 |
ourage | +0.798 |
Neg logit contributions | |
Masquerade | -0.735 |
Goat | -0.706 |
Caps | -0.661 |
================================================================ | -0.650 |
� | -0.634 |
Token | a |
Token ID | 257 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
itton | +0.860 |
pez | +0.835 |
ocard | +0.829 |
atts | +0.781 |
ourage | +0.767 |
Neg logit contributions | |
Masquerade | -0.768 |
Goat | -0.740 |
Caps | -0.695 |
================================================================ | -0.679 |
� | -0.661 |
Token | lot |
Token ID | 1256 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
itton | +0.915 |
pez | +0.889 |
ocard | +0.879 |
atts | +0.832 |
ourage | +0.822 |
Neg logit contributions | |
Masquerade | -0.734 |
Goat | -0.705 |
Caps | -0.657 |
================================================================ | -0.645 |
� | -0.629 |
Token | once |
Token ID | 1752 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Masquerade | +0.934 |
Goat | +0.899 |
Caps | +0.847 |
================================================================ | +0.825 |
� | +0.798 |
Neg logit contributions | |
itton | -1.100 |
pez | -1.068 |
ocard | -1.059 |
atts | -0.997 |
ourage | -0.985 |
Token | and |
Token ID | 290 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
itton | +0.383 |
pez | +0.372 |
ocard | +0.367 |
atts | +0.347 |
ourage | +0.345 |
Neg logit contributions | |
Masquerade | -0.283 |
Goat | -0.272 |
Caps | -0.253 |
================================================================ | -0.248 |
� | -0.241 |
Token | scar |
Token ID | 10153 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
itton | +0.485 |
pez | +0.470 |
ocard | +0.462 |
atts | +0.439 |
ourage | +0.433 |
Neg logit contributions | |
Masquerade | -0.402 |
Goat | -0.388 |
Caps | -0.362 |
================================================================ | -0.354 |
� | -0.346 |
Token | ring |
Token ID | 1806 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Masquerade | +1.545 |
Goat | +1.468 |
Caps | +1.338 |
================================================================ | +1.315 |
mentation | +1.271 |
Neg logit contributions | |
itton | -2.861 |
pez | -2.782 |
ocard | -2.754 |
atts | -2.633 |
ourage | -2.608 |
Token | if |
Token ID | 611 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Masquerade | +1.165 |
Goat | +1.124 |
Caps | +1.044 |
================================================================ | +1.028 |
� | +0.987 |
Neg logit contributions | |
itton | -1.535 |
pez | -1.491 |
ocard | -1.467 |
atts | -1.385 |
ourage | -1.377 |
Token | she |
Token ID | 673 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
itton | +1.033 |
pez | +1.002 |
ocard | +0.992 |
atts | +0.938 |
ourage | +0.928 |
Neg logit contributions | |
Masquerade | -0.854 |
Goat | -0.819 |
Caps | -0.763 |
================================================================ | -0.755 |
� | -0.735 |
Token | didn |
Token ID | 1422 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
itton | +0.021 |
pez | +0.021 |
ocard | +0.020 |
atts | +0.019 |
ourage | +0.019 |
Neg logit contributions | |
Masquerade | -0.019 |
Goat | -0.018 |
Caps | -0.017 |
================================================================ | -0.017 |
� | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
itton | +1.550 |
pez | +1.500 |
ocard | +1.483 |
atts | +1.395 |
ourage | +1.379 |
Neg logit contributions | |
Masquerade | -1.454 |
Goat | -1.401 |
Caps | -1.315 |
================================================================ | -1.297 |
� | -1.263 |
Token | act |
Token ID | 719 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Masquerade | +0.294 |
Goat | +0.284 |
Caps | +0.265 |
================================================================ | +0.260 |
� | +0.252 |
Neg logit contributions | |
itton | -0.356 |
pez | -0.345 |
ocard | -0.342 |
atts | -0.322 |
ourage | -0.318 |
Token | right |
Token ID | 826 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
itton | +0.022 |
pez | +0.021 |
ocard | +0.021 |
atts | +0.020 |
ourage | +0.019 |
Neg logit contributions | |
Masquerade | -0.022 |
Goat | -0.021 |
Caps | -0.020 |
================================================================ | -0.020 |
� | -0.019 |
Token | away |
Token ID | 1497 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
itton | +1.831 |
pez | +1.778 |
ocard | +1.760 |
atts | +1.664 |
ourage | +1.647 |
Neg logit contributions | |
Masquerade | -1.480 |
Goat | -1.420 |
Caps | -1.323 |
================================================================ | -1.305 |
� | -1.270 |
Token | ' |
Token ID | 6 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
itton | +0.698 |
pez | +0.677 |
ocard | +0.670 |
atts | +0.635 |
ourage | +0.628 |
Neg logit contributions | |
Masquerade | -0.533 |
Goat | -0.510 |
Caps | -0.474 |
================================================================ | -0.467 |
� | -0.455 |
Token | ** |
Token ID | 1174 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Masquerade | +0.412 |
Goat | +0.396 |
================================================================ | +0.373 |
Caps | +0.372 |
� | +0.358 |
Neg logit contributions | |
itton | -0.467 |
pez | -0.451 |
ocard | -0.446 |
atts | -0.420 |
ourage | -0.415 |
Token | In |
Token ID | 554 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
itton | +0.441 |
pez | +0.428 |
ocard | +0.423 |
atts | +0.399 |
ourage | +0.394 |
Neg logit contributions | |
Masquerade | -0.384 |
Goat | -0.369 |
Caps | -0.346 |
================================================================ | -0.341 |
� | -0.331 |
Token | many |
Token ID | 867 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Masquerade | +0.845 |
Goat | +0.816 |
Caps | +0.765 |
================================================================ | +0.750 |
� | +0.731 |
Neg logit contributions | |
itton | -0.975 |
pez | -0.943 |
ocard | -0.933 |
atts | -0.878 |
ourage | -0.870 |
Token | banks |
Token ID | 6341 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Masquerade | +1.200 |
Goat | +1.155 |
Caps | +1.094 |
================================================================ | +1.069 |
� | +1.040 |
Neg logit contributions | |
itton | -1.211 |
pez | -1.162 |
ocard | -1.149 |
atts | -1.087 |
ourage | -1.075 |
Token | one |
Token ID | 530 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
itton | +0.322 |
pez | +0.312 |
ocard | +0.310 |
atts | +0.293 |
ourage | +0.289 |
Neg logit contributions | |
Masquerade | -0.262 |
Goat | -0.251 |
Caps | -0.235 |
================================================================ | -0.231 |
� | -0.225 |
Token | doesn |
Token ID | 1595 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
itton | +0.308 |
pez | +0.298 |
ocard | +0.295 |
atts | +0.279 |
ourage | +0.277 |
Neg logit contributions | |
Masquerade | -0.247 |
Goat | -0.238 |
Caps | -0.222 |
================================================================ | -0.218 |
� | -0.212 |
Token | 't |
Token ID | 470 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
itton | +0.664 |
pez | +0.642 |
ocard | +0.637 |
atts | +0.598 |
ourage | +0.592 |
Neg logit contributions | |
Masquerade | -0.591 |
Goat | -0.569 |
Caps | -0.535 |
================================================================ | -0.530 |
� | -0.511 |
Token | need |
Token ID | 761 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Masquerade | +0.392 |
Goat | +0.375 |
Caps | +0.351 |
================================================================ | +0.341 |
� | +0.327 |
Neg logit contributions | |
itton | -0.554 |
pez | -0.539 |
ocard | -0.534 |
atts | -0.506 |
ourage | -0.501 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Masquerade | +0.244 |
Goat | +0.235 |
Caps | +0.218 |
================================================================ | +0.215 |
� | +0.209 |
Neg logit contributions | |
itton | -0.317 |
pez | -0.308 |
ocard | -0.304 |
atts | -0.287 |
ourage | -0.285 |
Token | take |
Token ID | 1011 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
itton | +0.177 |
pez | +0.172 |
ocard | +0.170 |
atts | +0.160 |
ourage | +0.158 |
Neg logit contributions | |
Masquerade | -0.158 |
Goat | -0.152 |
Caps | -0.143 |
================================================================ | -0.139 |
� | -0.135 |
Token | any |
Token ID | 597 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
itton | +1.365 |
pez | +1.321 |
ocard | +1.305 |
atts | +1.232 |
ourage | +1.217 |
Neg logit contributions | |
Masquerade | -1.194 |
Goat | -1.150 |
Caps | -1.077 |
================================================================ | -1.056 |
� | -1.032 |
Token | went |
Token ID | 1816 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
itton | +0.009 |
pez | +0.009 |
ocard | +0.008 |
atts | +0.008 |
ourage | +0.008 |
Neg logit contributions | |
Masquerade | -0.008 |
Goat | -0.008 |
Caps | -0.007 |
================================================================ | -0.007 |
� | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
itton | +0.278 |
pez | +0.269 |
ocard | +0.268 |
atts | +0.252 |
ourage | +0.249 |
Neg logit contributions | |
Masquerade | -0.218 |
Goat | -0.210 |
Caps | -0.196 |
================================================================ | -0.192 |
� | -0.187 |
Token | bat |
Token ID | 7365 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
Masquerade | +0.015 |
Goat | +0.015 |
Caps | +0.014 |
================================================================ | +0.013 |
� | +0.013 |
Neg logit contributions | |
itton | -0.017 |
pez | -0.017 |
ocard | -0.017 |
atts | -0.016 |
ourage | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Masquerade | +1.213 |
Goat | +1.185 |
Caps | +1.104 |
================================================================ | +1.082 |
� | +1.050 |
Neg logit contributions | |
itton | -1.366 |
pez | -1.318 |
ocard | -1.298 |
atts | -1.214 |
ourage | -1.201 |
Token | a |
Token ID | 257 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
itton | +0.549 |
pez | +0.532 |
ocard | +0.527 |
atts | +0.497 |
ourage | +0.491 |
Neg logit contributions | |
Masquerade | -0.455 |
Goat | -0.440 |
Caps | -0.410 |
================================================================ | -0.400 |
� | -0.392 |
Token | community |
Token ID | 2055 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
itton | +0.624 |
pez | +0.604 |
ocard | +0.598 |
atts | +0.564 |
ourage | +0.557 |
Neg logit contributions | |
Masquerade | -0.539 |
Goat | -0.518 |
Caps | -0.485 |
================================================================ | -0.477 |
� | -0.465 |
Token | resident |
Token ID | 6623 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Masquerade | +0.849 |
Goat | +0.824 |
Caps | +0.768 |
================================================================ | +0.754 |
� | +0.733 |
Neg logit contributions | |
itton | -0.970 |
pez | -0.942 |
ocard | -0.933 |
atts | -0.880 |
ourage | -0.866 |
Token | after |
Token ID | 706 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
itton | +1.714 |
pez | +1.660 |
ocard | +1.645 |
atts | +1.553 |
ourage | +1.538 |
Neg logit contributions | |
Masquerade | -1.445 |
Goat | -1.378 |
Caps | -1.294 |
================================================================ | -1.281 |
� | -1.247 |
Token | the |
Token ID | 262 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
Masquerade | +0.436 |
Goat | +0.421 |
Caps | +0.392 |
================================================================ | +0.382 |
� | +0.375 |
Neg logit contributions | |
itton | -0.501 |
pez | -0.486 |
ocard | -0.481 |
atts | -0.453 |
ourage | -0.448 |
Token | D |
Token ID | 360 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
itton | +0.066 |
pez | +0.064 |
ocard | +0.063 |
atts | +0.059 |
ourage | +0.059 |
Neg logit contributions | |
Masquerade | -0.057 |
Goat | -0.055 |
Caps | -0.051 |
================================================================ | -0.050 |
� | -0.049 |
Token | NR |
Token ID | 24723 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Masquerade | +0.610 |
Goat | +0.594 |
Caps | +0.559 |
================================================================ | +0.553 |
� | +0.538 |
Neg logit contributions | |
itton | -0.560 |
pez | -0.544 |
ocard | -0.537 |
atts | -0.501 |
ourage | -0.495 |
Token | Barron |
Token ID | 47412 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
itton | +3.169 |
pez | +3.083 |
ocard | +3.050 |
atts | +2.899 |
ourage | +2.861 |
Neg logit contributions | |
Masquerade | -2.172 |
Goat | -2.056 |
================================================================ | -1.920 |
Caps | -1.910 |
� | -1.860 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Masquerade | +1.387 |
Goat | +1.344 |
Caps | +1.247 |
================================================================ | +1.213 |
� | +1.191 |
Neg logit contributions | |
itton | -1.856 |
pez | -1.816 |
ocard | -1.795 |
atts | -1.695 |
ourage | -1.677 |
Token | director |
Token ID | 3437 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Masquerade | +0.382 |
Goat | +0.368 |
Caps | +0.343 |
================================================================ | +0.335 |
� | +0.326 |
Neg logit contributions | |
itton | -0.505 |
pez | -0.490 |
ocard | -0.485 |
atts | -0.459 |
ourage | -0.453 |
Token | of |
Token ID | 286 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
itton | +1.006 |
pez | +0.974 |
ocard | +0.963 |
atts | +0.906 |
ourage | +0.894 |
Neg logit contributions | |
Masquerade | -1.056 |
Goat | -1.018 |
Caps | -0.959 |
================================================================ | -0.946 |
� | -0.923 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Masquerade | +0.155 |
Goat | +0.149 |
Caps | +0.140 |
================================================================ | +0.138 |
� | +0.134 |
Neg logit contributions | |
itton | -0.177 |
pez | -0.171 |
ocard | -0.169 |
atts | -0.159 |
ourage | -0.158 |
Token | new |
Token ID | 649 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Masquerade | +0.198 |
Goat | +0.190 |
Caps | +0.176 |
================================================================ | +0.172 |
� | +0.166 |
Neg logit contributions | |
itton | -0.281 |
pez | -0.273 |
ocard | -0.270 |
atts | -0.255 |
ourage | -0.253 |
Token | law |
Token ID | 1099 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
itton | +0.140 |
pez | +0.135 |
ocard | +0.134 |
atts | +0.127 |
ourage | +0.125 |
Neg logit contributions | |
Masquerade | -0.115 |
Goat | -0.110 |
Caps | -0.103 |
================================================================ | -0.102 |
� | -0.099 |
Token | center |
Token ID | 3641 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Masquerade | +1.101 |
Goat | +1.060 |
Caps | +0.996 |
================================================================ | +0.977 |
� | +0.955 |
Neg logit contributions | |
itton | -1.211 |
pez | -1.176 |
ocard | -1.159 |
atts | -1.091 |
ourage | -1.076 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
itton | +1.239 |
pez | +1.203 |
ocard | +1.192 |
atts | +1.132 |
ourage | +1.122 |
Neg logit contributions | |
Masquerade | -0.868 |
Goat | -0.830 |
Caps | -0.769 |
================================================================ | -0.757 |
� | -0.735 |
Token | � |
Token ID | 564 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
itton | +0.242 |
pez | +0.235 |
ocard | +0.232 |
atts | +0.219 |
ourage | +0.217 |
Neg logit contributions | |
Masquerade | -0.206 |
Goat | -0.197 |
Caps | -0.184 |
================================================================ | -0.182 |
� | -0.177 |
Token | � |
Token ID | 250 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Masquerade | +0.578 |
Goat | +0.545 |
Caps | +0.487 |
================================================================ | +0.481 |
� | +0.469 |
Neg logit contributions | |
itton | -1.400 |
pez | -1.366 |
ocard | -1.357 |
atts | -1.299 |
ourage | -1.288 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Masquerade | +0.016 |
Goat | +0.015 |
Caps | +0.014 |
================================================================ | +0.014 |
� | +0.014 |
Neg logit contributions | |
itton | -0.019 |
pez | -0.018 |
ocard | -0.018 |
atts | -0.017 |
ourage | -0.017 |
Token | asteroid |
Token ID | 27460 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
itton | +0.227 |
pez | +0.220 |
ocard | +0.217 |
atts | +0.205 |
ourage | +0.203 |
Neg logit contributions | |
Masquerade | -0.204 |
Goat | -0.197 |
Caps | -0.184 |
================================================================ | -0.181 |
� | -0.177 |
Token | 99 |
Token ID | 7388 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Masquerade | +0.942 |
Goat | +0.917 |
Caps | +0.863 |
================================================================ | +0.842 |
� | +0.820 |
Neg logit contributions | |
itton | -0.975 |
pez | -0.946 |
ocard | -0.937 |
atts | -0.881 |
ourage | -0.869 |
Token | 69 |
Token ID | 3388 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
itton | +0.734 |
pez | +0.712 |
ocard | +0.704 |
atts | +0.664 |
ourage | +0.658 |
Neg logit contributions | |
Masquerade | -0.602 |
Goat | -0.577 |
Caps | -0.539 |
================================================================ | -0.531 |
� | -0.517 |
Token | Bra |
Token ID | 9718 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
itton | +1.837 |
pez | +1.776 |
ocard | +1.756 |
atts | +1.657 |
ourage | +1.642 |
Neg logit contributions | |
Masquerade | -1.589 |
Goat | -1.519 |
Caps | -1.415 |
================================================================ | -1.406 |
� | -1.368 |
Token | ille |
Token ID | 8270 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Masquerade | +0.523 |
Goat | +0.495 |
================================================================ | +0.453 |
Caps | +0.451 |
� | +0.432 |
Neg logit contributions | |
itton | -0.955 |
pez | -0.931 |
ocard | -0.928 |
atts | -0.885 |
ourage | -0.876 |
Token | was |
Token ID | 373 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Masquerade | +1.269 |
Goat | +1.223 |
Caps | +1.155 |
================================================================ | +1.117 |
� | +1.083 |
Neg logit contributions | |
itton | -1.561 |
pez | -1.511 |
ocard | -1.503 |
atts | -1.412 |
ourage | -1.395 |
Token | only |
Token ID | 691 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
itton | +0.297 |
pez | +0.286 |
ocard | +0.286 |
atts | +0.267 |
ourage | +0.265 |
Neg logit contributions | |
Masquerade | -0.283 |
Goat | -0.275 |
Caps | -0.260 |
================================================================ | -0.253 |
� | -0.246 |
Token | a |
Token ID | 257 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
itton | +1.105 |
pez | +1.066 |
ocard | +1.062 |
atts | +0.995 |
ourage | +0.984 |
Neg logit contributions | |
Masquerade | -1.026 |
Goat | -0.991 |
Caps | -0.934 |
================================================================ | -0.911 |
� | -0.891 |
Token | partial |
Token ID | 13027 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
itton | +0.421 |
pez | +0.407 |
ocard | +0.404 |
atts | +0.381 |
ourage | +0.377 |
Neg logit contributions | |
Masquerade | -0.383 |
Goat | -0.370 |
Caps | -0.347 |
================================================================ | -0.337 |
� | -0.331 |
Token | success |
Token ID | 1943 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
itton | +0.071 |
pez | +0.069 |
ocard | +0.068 |
atts | +0.064 |
ourage | +0.064 |
Neg logit contributions | |
Masquerade | -0.057 |
Goat | -0.055 |
Caps | -0.051 |
================================================================ | -0.051 |
� | -0.049 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
itton | +0.132 |
pez | +0.128 |
ocard | +0.126 |
atts | +0.118 |
ourage | +0.117 |
Neg logit contributions | |
Masquerade | -0.126 |
Goat | -0.122 |
Caps | -0.115 |
================================================================ | -0.113 |
� | -0.110 |
Token | aware |
Token ID | 3910 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Masquerade | +1.963 |
Goat | +1.874 |
Caps | +1.764 |
================================================================ | +1.705 |
� | +1.658 |
Neg logit contributions | |
itton | -2.784 |
pez | -2.721 |
ocard | -2.676 |
atts | -2.525 |
ourage | -2.509 |
Token | that |
Token ID | 326 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
Masquerade | +1.231 |
Goat | +1.183 |
Caps | +1.115 |
================================================================ | +1.092 |
� | +1.068 |
Neg logit contributions | |
itton | -1.478 |
pez | -1.428 |
ocard | -1.414 |
atts | -1.334 |
ourage | -1.321 |
Token | more |
Token ID | 517 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
itton | +0.011 |
pez | +0.011 |
ocard | +0.010 |
atts | +0.010 |
ourage | +0.010 |
Neg logit contributions | |
Masquerade | -0.009 |
Goat | -0.009 |
Caps | -0.008 |
================================================================ | -0.008 |
� | -0.008 |
Token | subsidies |
Token ID | 16230 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Masquerade | +0.222 |
Goat | +0.213 |
Caps | +0.198 |
================================================================ | +0.195 |
� | +0.189 |
Neg logit contributions | |
itton | -0.304 |
pez | -0.295 |
ocard | -0.292 |
atts | -0.276 |
ourage | -0.274 |
Token | will |
Token ID | 481 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
itton | +0.521 |
pez | +0.504 |
ocard | +0.499 |
atts | +0.472 |
ourage | +0.466 |
Neg logit contributions | |
Masquerade | -0.431 |
Goat | -0.415 |
Caps | -0.388 |
================================================================ | -0.381 |
� | -0.371 |
Token | only |
Token ID | 691 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Masquerade | +0.391 |
Goat | +0.378 |
Caps | +0.357 |
================================================================ | +0.345 |
� | +0.335 |
Neg logit contributions | |
itton | -0.480 |
pez | -0.463 |
ocard | -0.460 |
atts | -0.437 |
ourage | -0.430 |
Token | exacerbate |
Token ID | 49522 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
itton | +0.797 |
pez | +0.766 |
ocard | +0.762 |
atts | +0.720 |
ourage | +0.710 |
Neg logit contributions | |
Masquerade | -0.663 |
Goat | -0.640 |
Caps | -0.600 |
================================================================ | -0.583 |
� | -0.568 |
Token | their |
Token ID | 511 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
itton | +1.074 |
pez | +1.039 |
ocard | +1.028 |
atts | +0.967 |
ourage | +0.956 |
Neg logit contributions | |
Masquerade | -1.007 |
Goat | -0.970 |
Caps | -0.909 |
================================================================ | -0.897 |
� | -0.875 |
Token | pain |
Token ID | 2356 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
itton | +0.867 |
pez | +0.835 |
ocard | +0.818 |
atts | +0.769 |
ourage | +0.762 |
Neg logit contributions | |
Masquerade | -0.958 |
Goat | -0.925 |
Caps | -0.879 |
================================================================ | -0.863 |
� | -0.840 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Masquerade | +0.378 |
Goat | +0.363 |
Caps | +0.337 |
================================================================ | +0.332 |
� | +0.321 |
Neg logit contributions | |
itton | -0.536 |
pez | -0.519 |
ocard | -0.514 |
atts | -0.488 |
ourage | -0.483 |
Token | received |
Token ID | 2722 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
itton | +0.376 |
pez | +0.363 |
ocard | +0.359 |
atts | +0.338 |
ourage | +0.334 |
Neg logit contributions | |
Masquerade | -0.357 |
Goat | -0.344 |
Caps | -0.323 |
================================================================ | -0.317 |
� | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
itton | +0.183 |
pez | +0.176 |
ocard | +0.174 |
atts | +0.164 |
ourage | +0.162 |
Neg logit contributions | |
Masquerade | -0.160 |
Goat | -0.154 |
Caps | -0.144 |
================================================================ | -0.142 |
� | -0.138 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
itton | +0.116 |
pez | +0.113 |
ocard | +0.111 |
atts | +0.105 |
ourage | +0.104 |
Neg logit contributions | |
Masquerade | -0.095 |
Goat | -0.091 |
Caps | -0.085 |
================================================================ | -0.084 |
� | -0.081 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Masquerade | +0.172 |
Goat | +0.167 |
Caps | +0.156 |
================================================================ | +0.153 |
� | +0.148 |
Neg logit contributions | |
itton | -0.192 |
pez | -0.186 |
ocard | -0.183 |
atts | -0.173 |
ourage | -0.171 |
Token | to |
Token ID | 284 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Masquerade | +0.526 |
Goat | +0.506 |
Caps | +0.470 |
================================================================ | +0.461 |
� | +0.446 |
Neg logit contributions | |
itton | -0.728 |
pez | -0.707 |
ocard | -0.698 |
atts | -0.662 |
ourage | -0.656 |
Token | learn |
Token ID | 2193 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
itton | +0.109 |
pez | +0.106 |
ocard | +0.104 |
atts | +0.099 |
ourage | +0.098 |
Neg logit contributions | |
Masquerade | -0.093 |
Goat | -0.090 |
Caps | -0.084 |
================================================================ | -0.083 |
� | -0.080 |
Token | more |
Token ID | 517 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Masquerade | +0.076 |
Goat | +0.073 |
Caps | +0.067 |
================================================================ | +0.066 |
� | +0.064 |
Neg logit contributions | |
itton | -0.102 |
pez | -0.099 |
ocard | -0.098 |
atts | -0.093 |
ourage | -0.092 |
Token | about |
Token ID | 546 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
itton | +0.678 |
pez | +0.659 |
ocard | +0.652 |
atts | +0.617 |
ourage | +0.611 |
Neg logit contributions | |
Masquerade | -0.506 |
Goat | -0.485 |
Caps | -0.451 |
================================================================ | -0.444 |
� | -0.431 |
Token | social |
Token ID | 1919 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
itton | +0.760 |
pez | +0.736 |
ocard | +0.728 |
atts | +0.688 |
ourage | +0.680 |
Neg logit contributions | |
Masquerade | -0.625 |
Goat | -0.601 |
Caps | -0.561 |
================================================================ | -0.551 |
� | -0.536 |
Token | justice |
Token ID | 5316 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Masquerade | +0.116 |
Goat | +0.112 |
Caps | +0.105 |
================================================================ | +0.103 |
� | +0.101 |
Neg logit contributions | |
itton | -0.120 |
pez | -0.116 |
ocard | -0.115 |
atts | -0.108 |
ourage | -0.106 |
Token | from |
Token ID | 422 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Masquerade | +1.495 |
Goat | +1.447 |
Caps | +1.341 |
================================================================ | +1.310 |
mentation | +1.264 |
Neg logit contributions | |
itton | -1.953 |
pez | -1.897 |
ocard | -1.883 |
atts | -1.766 |
ourage | -1.748 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Masquerade | +0.822 |
Goat | +0.791 |
Caps | +0.733 |
================================================================ | +0.715 |
� | +0.692 |
Neg logit contributions | |
itton | -1.142 |
pez | -1.102 |
ocard | -1.094 |
atts | -1.037 |
ourage | -1.026 |
Token | I |
Token ID | 314 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Masquerade | +0.214 |
Goat | +0.206 |
Caps | +0.192 |
================================================================ | +0.189 |
� | +0.183 |
Neg logit contributions | |
itton | -0.272 |
pez | -0.264 |
ocard | -0.261 |
atts | -0.247 |
ourage | -0.244 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
itton | +0.455 |
pez | +0.443 |
ocard | +0.439 |
atts | +0.417 |
ourage | +0.414 |
Neg logit contributions | |
Masquerade | -0.281 |
Goat | -0.268 |
Caps | -0.246 |
================================================================ | -0.242 |
� | -0.234 |
Token | you |
Token ID | 345 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Masquerade | +0.193 |
Goat | +0.186 |
Caps | +0.173 |
================================================================ | +0.170 |
� | +0.165 |
Neg logit contributions | |
itton | -0.243 |
pez | -0.236 |
ocard | -0.233 |
atts | -0.220 |
ourage | -0.218 |
Token | were |
Token ID | 547 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
itton | +0.907 |
pez | +0.878 |
ocard | +0.869 |
atts | +0.819 |
ourage | +0.810 |
Neg logit contributions | |
Masquerade | -0.791 |
Goat | -0.761 |
Caps | -0.711 |
================================================================ | -0.701 |
� | -0.683 |
Token | melting |
Token ID | 24203 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
itton | +1.123 |
pez | +1.087 |
ocard | +1.074 |
atts | +1.010 |
ourage | +0.998 |
Neg logit contributions | |
Masquerade | -1.082 |
Goat | -1.043 |
Caps | -0.979 |
================================================================ | -0.966 |
� | -0.942 |
Token | me |
Token ID | 502 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Masquerade | +2.536 |
Goat | +2.471 |
Caps | +2.315 |
================================================================ | +2.227 |
� | +2.157 |
Neg logit contributions | |
itton | -3.102 |
pez | -2.999 |
ocard | -2.959 |
ourage | -2.798 |
atts | -2.793 |
Token | from |
Token ID | 422 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Masquerade | +0.425 |
Goat | +0.409 |
Caps | +0.383 |
================================================================ | +0.377 |
� | +0.367 |
Neg logit contributions | |
itton | -0.482 |
pez | -0.467 |
ocard | -0.461 |
atts | -0.435 |
ourage | -0.430 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
itton | +0.318 |
pez | +0.308 |
ocard | +0.304 |
atts | +0.287 |
ourage | +0.284 |
Neg logit contributions | |
Masquerade | -0.285 |
Goat | -0.274 |
Caps | -0.257 |
================================================================ | -0.253 |
� | -0.247 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Masquerade | +0.034 |
Goat | +0.033 |
Caps | +0.031 |
================================================================ | +0.030 |
� | +0.030 |
Neg logit contributions | |
itton | -0.040 |
pez | -0.039 |
ocard | -0.039 |
atts | -0.037 |
ourage | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Masquerade | +2.776 |
Goat | +2.688 |
Caps | +2.523 |
================================================================ | +2.436 |
� | +2.374 |
Neg logit contributions | |
itton | -3.569 |
pez | -3.443 |
ocard | -3.409 |
atts | -3.239 |
ourage | -3.190 |
Token | many |
Token ID | 867 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
itton | +0.510 |
pez | +0.492 |
ocard | +0.484 |
atts | +0.455 |
ourage | +0.448 |
Neg logit contributions | |
Masquerade | -0.529 |
Goat | -0.511 |
Caps | -0.483 |
================================================================ | -0.471 |
� | -0.461 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
Masquerade | +0.721 |
Goat | +0.694 |
Caps | +0.657 |
================================================================ | +0.641 |
� | +0.625 |
Neg logit contributions | |
itton | -0.726 |
pez | -0.700 |
ocard | -0.691 |
atts | -0.649 |
ourage | -0.638 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
itton | +0.163 |
pez | +0.158 |
ocard | +0.157 |
atts | +0.148 |
ourage | +0.147 |
Neg logit contributions | |
Masquerade | -0.121 |
Goat | -0.116 |
Caps | -0.107 |
================================================================ | -0.105 |
� | -0.102 |
Token | who |
Token ID | 508 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
itton | +0.602 |
pez | +0.583 |
ocard | +0.576 |
atts | +0.541 |
ourage | +0.533 |
Neg logit contributions | |
Masquerade | -0.588 |
Goat | -0.568 |
Caps | -0.534 |
================================================================ | -0.523 |
� | -0.511 |
Token | affection |
Token ID | 17696 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
itton | +0.560 |
pez | +0.541 |
ocard | +0.536 |
atts | +0.504 |
ourage | +0.496 |
Neg logit contributions | |
Masquerade | -0.528 |
Goat | -0.510 |
Caps | -0.480 |
================================================================ | -0.469 |
� | -0.457 |
Token | ately |
Token ID | 1286 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Masquerade | +0.030 |
Goat | +0.029 |
Caps | +0.027 |
================================================================ | +0.027 |
� | +0.026 |
Neg logit contributions | |
itton | -0.031 |
pez | -0.030 |
ocard | -0.029 |
atts | -0.027 |
ourage | -0.027 |
Token | called |
Token ID | 1444 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Masquerade | +2.975 |
Goat | +2.911 |
Caps | +2.741 |
================================================================ | +2.634 |
mentation | +2.603 |
Neg logit contributions | |
itton | -2.814 |
pez | -2.735 |
ocard | -2.701 |
atts | -2.524 |
ourage | -2.453 |
Token | him |
Token ID | 683 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
itton | +0.711 |
pez | +0.690 |
ocard | +0.682 |
atts | +0.645 |
ourage | +0.638 |
Neg logit contributions | |
Masquerade | -0.574 |
Goat | -0.551 |
Caps | -0.514 |
================================================================ | -0.505 |
� | -0.492 |
Token | " |
Token ID | 366 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Masquerade | +1.163 |
Goat | +1.131 |
Caps | +1.046 |
================================================================ | +1.022 |
� | +0.996 |
Neg logit contributions | |
itton | -1.446 |
pez | -1.399 |
ocard | -1.383 |
atts | -1.306 |
ourage | -1.289 |
Token | Short |
Token ID | 16438 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
itton | +0.919 |
pez | +0.892 |
ocard | +0.882 |
atts | +0.835 |
ourage | +0.826 |
Neg logit contributions | |
Masquerade | -0.733 |
Goat | -0.701 |
Caps | -0.655 |
================================================================ | -0.643 |
� | -0.626 |
Token | y |
Token ID | 88 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Masquerade | +0.723 |
Goat | +0.697 |
Caps | +0.649 |
================================================================ | +0.630 |
� | +0.620 |
Neg logit contributions | |
itton | -0.960 |
pez | -0.934 |
ocard | -0.923 |
atts | -0.872 |
ourage | -0.865 |
Token | technology |
Token ID | 3037 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Masquerade | +0.869 |
Goat | +0.838 |
Caps | +0.778 |
================================================================ | +0.759 |
� | +0.730 |
Neg logit contributions | |
itton | -1.215 |
pez | -1.175 |
ocard | -1.164 |
atts | -1.097 |
ourage | -1.086 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Masquerade | +0.987 |
Goat | +0.952 |
Caps | +0.889 |
================================================================ | +0.869 |
� | +0.836 |
Neg logit contributions | |
itton | -1.381 |
pez | -1.328 |
ocard | -1.323 |
atts | -1.242 |
ourage | -1.229 |
Token | what |
Token ID | 644 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Masquerade | +0.212 |
Goat | +0.203 |
Caps | +0.188 |
================================================================ | +0.183 |
� | +0.178 |
Neg logit contributions | |
itton | -0.320 |
pez | -0.311 |
ocard | -0.308 |
atts | -0.292 |
ourage | -0.289 |
Token | Snap |
Token ID | 16026 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Masquerade | +0.359 |
Goat | +0.344 |
Caps | +0.318 |
================================================================ | +0.310 |
� | +0.301 |
Neg logit contributions | |
itton | -0.536 |
pez | -0.520 |
ocard | -0.515 |
atts | -0.489 |
ourage | -0.484 |
Token | and |
Token ID | 290 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
Masquerade | +1.072 |
Goat | +1.031 |
Caps | +0.962 |
================================================================ | +0.939 |
� | +0.909 |
Neg logit contributions | |
itton | -1.437 |
pez | -1.390 |
ocard | -1.383 |
atts | -1.300 |
ourage | -1.290 |
Token | Flat |
Token ID | 21939 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
itton | +0.020 |
pez | +0.020 |
ocard | +0.019 |
atts | +0.018 |
ourage | +0.018 |
Neg logit contributions | |
Masquerade | -0.013 |
Goat | -0.012 |
Caps | -0.011 |
================================================================ | -0.011 |
� | -0.011 |
Token | pak |
Token ID | 41091 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
Masquerade | +1.344 |
Goat | +1.277 |
Caps | +1.131 |
================================================================ | +1.044 |
ppa | +0.991 |
Neg logit contributions | |
itton | -5.353 |
ocard | -5.210 |
pez | -5.169 |
horm | -4.993 |
atts | -4.955 |
Token | offer |
Token ID | 2897 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Masquerade | +1.315 |
Goat | +1.262 |
Caps | +1.182 |
================================================================ | +1.140 |
� | +1.100 |
Neg logit contributions | |
itton | -1.777 |
ocard | -1.711 |
pez | -1.703 |
atts | -1.597 |
ourage | -1.588 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
itton | +0.923 |
pez | +0.899 |
ocard | +0.889 |
atts | +0.843 |
ourage | +0.835 |
Neg logit contributions | |
Masquerade | -0.658 |
Goat | -0.629 |
Caps | -0.583 |
================================================================ | -0.573 |
� | -0.557 |
Token | so |
Token ID | 523 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Masquerade | +0.018 |
Goat | +0.017 |
Caps | +0.016 |
================================================================ | +0.015 |
� | +0.015 |
Neg logit contributions | |
itton | -0.031 |
pez | -0.030 |
ocard | -0.030 |
atts | -0.028 |
ourage | -0.028 |
Token | I |
Token ID | 314 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Masquerade | +0.441 |
Goat | +0.426 |
Caps | +0.398 |
================================================================ | +0.388 |
� | +0.378 |
Neg logit contributions | |
itton | -0.532 |
pez | -0.516 |
ocard | -0.510 |
atts | -0.481 |
ourage | -0.475 |
Token | goes |
Token ID | 2925 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Masquerade | +0.661 |
Goat | +0.637 |
Caps | +0.594 |
================================================================ | +0.582 |
� | +0.568 |
Neg logit contributions | |
itton | -0.859 |
pez | -0.833 |
ocard | -0.822 |
atts | -0.781 |
ourage | -0.771 |
Token | : |
Token ID | 25 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Masquerade | +0.489 |
Goat | +0.472 |
Caps | +0.440 |
================================================================ | +0.431 |
� | +0.421 |
Neg logit contributions | |
itton | -0.606 |
pez | -0.586 |
ocard | -0.582 |
atts | -0.549 |
ourage | -0.544 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
Masquerade | +0.334 |
Goat | +0.322 |
Caps | +0.302 |
================================================================ | +0.295 |
� | +0.287 |
Neg logit contributions | |
itton | -0.426 |
pez | -0.413 |
ocard | -0.409 |
atts | -0.387 |
ourage | -0.381 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
itton | +0.003 |
pez | +0.003 |
ocard | +0.003 |
atts | +0.003 |
ourage | +0.003 |
Neg logit contributions | |
Masquerade | -0.002 |
Goat | -0.002 |
Caps | -0.002 |
================================================================ | -0.002 |
� | -0.002 |
Token | About |
Token ID | 8585 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
itton | +0.005 |
pez | +0.005 |
ocard | +0.005 |
atts | +0.004 |
ourage | +0.004 |
Neg logit contributions | |
Masquerade | -0.004 |
Goat | -0.004 |
Caps | -0.004 |
================================================================ | -0.004 |
� | -0.004 |
Token | Aleppo |
Token ID | 18593 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
itton | +1.175 |
pez | +1.140 |
ocard | +1.128 |
atts | +1.066 |
ourage | +1.054 |
Neg logit contributions | |
Masquerade | -0.939 |
Goat | -0.902 |
Caps | -0.842 |
================================================================ | -0.828 |
� | -0.806 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Masquerade | +2.635 |
Goat | +2.539 |
Caps | +2.384 |
================================================================ | +2.322 |
� | +2.222 |
Neg logit contributions | |
itton | -3.590 |
pez | -3.507 |
ocard | -3.483 |
atts | -3.314 |
ourage | -3.239 |
Token | Syria |
Token ID | 4392 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Masquerade | +0.525 |
Goat | +0.504 |
Caps | +0.472 |
================================================================ | +0.460 |
� | +0.447 |
Neg logit contributions | |
itton | -0.751 |
pez | -0.730 |
ocard | -0.723 |
atts | -0.686 |
ourage | -0.675 |
Token | , |
Token ID | 11 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Masquerade | +0.639 |
Goat | +0.614 |
Caps | +0.576 |
================================================================ | +0.565 |
� | +0.546 |
Neg logit contributions | |
itton | -0.828 |
pez | -0.804 |
ocard | -0.798 |
atts | -0.755 |
ourage | -0.743 |
Token | I |
Token ID | 314 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
itton | +0.050 |
pez | +0.048 |
ocard | +0.048 |
atts | +0.045 |
ourage | +0.045 |
Neg logit contributions | |
Masquerade | -0.037 |
Goat | -0.036 |
Caps | -0.033 |
================================================================ | -0.033 |
� | -0.032 |
Token | truly |
Token ID | 4988 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Masquerade | +0.313 |
Goat | +0.302 |
Caps | +0.283 |
================================================================ | +0.279 |
� | +0.272 |
Neg logit contributions | |
itton | -0.367 |
pez | -0.355 |
ocard | -0.351 |
atts | -0.332 |
ourage | -0.327 |
Token | Make |
Token ID | 12050 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
Masquerade | +0.038 |
Goat | +0.036 |
Caps | +0.034 |
================================================================ | +0.034 |
� | +0.033 |
Neg logit contributions | |
itton | -0.042 |
pez | -0.041 |
ocard | -0.040 |
atts | -0.038 |
ourage | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Masquerade | +0.073 |
Goat | +0.070 |
Caps | +0.066 |
================================================================ | +0.065 |
� | +0.063 |
Neg logit contributions | |
itton | -0.080 |
pez | -0.078 |
ocard | -0.076 |
atts | -0.072 |
ourage | -0.071 |
Token | file |
Token ID | 2393 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
itton | +0.333 |
pez | +0.322 |
ocard | +0.318 |
atts | +0.301 |
ourage | +0.297 |
Neg logit contributions | |
Masquerade | -0.305 |
Goat | -0.293 |
Caps | -0.275 |
================================================================ | -0.270 |
� | -0.264 |
Token | now |
Token ID | 783 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
itton | +1.883 |
pez | +1.823 |
ocard | +1.804 |
atts | +1.694 |
ourage | +1.674 |
Neg logit contributions | |
Masquerade | -1.784 |
Goat | -1.718 |
Caps | -1.611 |
================================================================ | -1.589 |
� | -1.551 |
Token | with |
Token ID | 351 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Masquerade | +0.548 |
Goat | +0.528 |
Caps | +0.492 |
================================================================ | +0.485 |
� | +0.468 |
Neg logit contributions | |
itton | -0.686 |
pez | -0.666 |
ocard | -0.659 |
atts | -0.624 |
ourage | -0.615 |
Token | proof |
Token ID | 6617 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
itton | +0.025 |
pez | +0.024 |
ocard | +0.024 |
atts | +0.022 |
ourage | +0.022 |
Neg logit contributions | |
Masquerade | -0.022 |
Goat | -0.022 |
Caps | -0.020 |
================================================================ | -0.020 |
� | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Masquerade | +3.022 |
Goat | +2.923 |
Caps | +2.731 |
================================================================ | +2.676 |
� | +2.632 |
Neg logit contributions | |
itton | -3.776 |
pez | -3.696 |
ocard | -3.584 |
atts | -3.411 |
ourage | -3.395 |
Token | your |
Token ID | 534 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
itton | +0.043 |
pez | +0.042 |
ocard | +0.041 |
atts | +0.039 |
ourage | +0.038 |
Neg logit contributions | |
Masquerade | -0.045 |
Goat | -0.043 |
Caps | -0.041 |
================================================================ | -0.040 |
� | -0.039 |
Token | presence |
Token ID | 4931 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
itton | +0.925 |
pez | +0.893 |
ocard | +0.872 |
atts | +0.826 |
ourage | +0.818 |
Neg logit contributions | |
Masquerade | -0.959 |
Goat | -0.926 |
Caps | -0.871 |
================================================================ | -0.858 |
� | -0.835 |
Token | [ |
Token ID | 685 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Masquerade | +0.146 |
Goat | +0.141 |
Caps | +0.132 |
================================================================ | +0.130 |
� | +0.126 |
Neg logit contributions | |
itton | -0.163 |
pez | -0.157 |
ocard | -0.155 |
atts | -0.147 |
ourage | -0.145 |
Token | and |
Token ID | 392 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Masquerade | +0.234 |
Goat | +0.225 |
Caps | +0.211 |
================================================================ | +0.210 |
� | +0.204 |
Neg logit contributions | |
itton | -0.261 |
pez | -0.254 |
ocard | -0.251 |
atts | -0.236 |
ourage | -0.233 |