Token | of |
Token ID | 286 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
�� | +2.541 |
edIn | +2.500 |
gie | +2.223 |
orney | +2.200 |
leton | +2.157 |
Neg logit contributions | |
agers | -2.760 |
ework | -2.456 |
ardon | -2.435 |
lass | -2.388 |
apt | -2.387 |
Token | a |
Token ID | 257 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
agers | +0.259 |
ework | +0.233 |
ardon | +0.228 |
apt | +0.224 |
outs | +0.223 |
Neg logit contributions | |
�� | -0.248 |
edIn | -0.243 |
orney | -0.216 |
gie | -0.214 |
leton | -0.210 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
�� | +0.144 |
edIn | +0.142 |
orney | +0.125 |
gie | +0.124 |
leton | +0.121 |
Neg logit contributions | |
agers | -0.160 |
ework | -0.145 |
ardon | -0.142 |
apt | -0.140 |
lass | -0.139 |
Token | by |
Token ID | 1525 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
�� | +2.832 |
edIn | +2.784 |
gie | +2.521 |
orney | +2.465 |
leton | +2.423 |
Neg logit contributions | |
agers | -3.151 |
ework | -2.803 |
ardon | -2.765 |
lass | -2.695 |
apt | -2.690 |
Token | past |
Token ID | 1613 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
�� | +0.529 |
edIn | +0.520 |
gie | +0.460 |
orney | +0.459 |
leton | +0.449 |
Neg logit contributions | |
agers | -0.557 |
ework | -0.499 |
ardon | -0.489 |
apt | -0.480 |
lass | -0.480 |
Token | comet |
Token ID | 31733 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
�� | +1.250 |
edIn | +1.235 |
orney | +1.078 |
gie | +1.078 |
leton | +1.052 |
Neg logit contributions | |
agers | -1.469 |
ework | -1.332 |
ardon | -1.300 |
apt | -1.281 |
lass | -1.279 |
Token | 107 |
Token ID | 16226 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
�� | +6.818 |
edIn | +6.767 |
gie | +6.167 |
leton | +5.993 |
orney | +5.957 |
Neg logit contributions | |
agers | -6.962 |
ework | -6.370 |
lass | -6.228 |
ardon | -6.180 |
apt | -5.996 |
Token | P |
Token ID | 47 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
�� | +2.040 |
edIn | +1.997 |
orney | +1.773 |
gie | +1.772 |
leton | +1.736 |
Neg logit contributions | |
agers | -2.061 |
ework | -1.847 |
ardon | -1.799 |
lass | -1.782 |
apt | -1.764 |
Token | / |
Token ID | 14 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
agers | +0.274 |
ework | +0.245 |
ardon | +0.240 |
apt | +0.236 |
lass | +0.235 |
Neg logit contributions | |
�� | -0.281 |
edIn | -0.276 |
orney | -0.246 |
gie | -0.245 |
leton | -0.240 |
Token | Wilson |
Token ID | 37349 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
�� | +1.232 |
edIn | +1.220 |
orney | +1.075 |
gie | +1.074 |
leton | +1.057 |
Neg logit contributions | |
agers | -1.316 |
ework | -1.186 |
ardon | -1.153 |
lass | -1.135 |
apt | -1.129 |
Token | – |
Token ID | 1906 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
agers | +1.289 |
ework | +1.156 |
ardon | +1.133 |
apt | +1.114 |
outs | +1.109 |
Neg logit contributions | |
�� | -1.251 |
edIn | -1.230 |
orney | -1.087 |
gie | -1.080 |
leton | -1.059 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
�� | +0.120 |
edIn | +0.118 |
orney | +0.105 |
gie | +0.104 |
�� | +0.102 |
Neg logit contributions | |
agers | -0.119 |
ework | -0.106 |
ardon | -0.104 |
apt | -0.102 |
outs | -0.102 |
Token | in |
Token ID | 287 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
�� | +0.433 |
edIn | +0.426 |
orney | +0.379 |
gie | +0.377 |
leton | +0.367 |
Neg logit contributions | |
agers | -0.471 |
ework | -0.424 |
ardon | -0.416 |
apt | -0.410 |
lass | -0.409 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
�� | +0.551 |
edIn | +0.541 |
orney | +0.480 |
gie | +0.475 |
leton | +0.465 |
Neg logit contributions | |
agers | -0.618 |
ework | -0.558 |
ardon | -0.546 |
lass | -0.536 |
apt | -0.536 |
Token | US |
Token ID | 1294 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
�� | +0.194 |
edIn | +0.191 |
orney | +0.168 |
gie | +0.167 |
leton | +0.164 |
Neg logit contributions | |
agers | -0.222 |
ework | -0.200 |
ardon | -0.196 |
apt | -0.193 |
lass | -0.192 |
Token | against |
Token ID | 1028 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
�� | +1.393 |
edIn | +1.367 |
orney | +1.221 |
gie | +1.207 |
leton | +1.172 |
Neg logit contributions | |
agers | -1.592 |
ework | -1.434 |
ardon | -1.406 |
lass | -1.383 |
apt | -1.380 |
Token | Airbus |
Token ID | 39173 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
�� | +0.251 |
edIn | +0.247 |
orney | +0.217 |
gie | +0.215 |
leton | +0.211 |
Neg logit contributions | |
agers | -0.294 |
ework | -0.266 |
ardon | -0.260 |
apt | -0.256 |
outs | -0.255 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
�� | +5.815 |
edIn | +5.769 |
gie | +5.106 |
orney | +4.991 |
leton | +4.865 |
Neg logit contributions | |
agers | -7.902 |
ework | -7.305 |
lass | -6.962 |
ardon | -6.908 |
apt | -6.879 |
Token | aerospace |
Token ID | 40439 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
�� | +0.677 |
edIn | +0.662 |
orney | +0.583 |
gie | +0.579 |
leton | +0.567 |
Neg logit contributions | |
agers | -0.759 |
ework | -0.684 |
ardon | -0.671 |
apt | -0.661 |
outs | -0.658 |
Token | company |
Token ID | 1664 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
�� | +4.212 |
edIn | +4.149 |
gie | +3.667 |
orney | +3.648 |
leton | +3.539 |
Neg logit contributions | |
agers | -5.467 |
ework | -4.971 |
ardon | -4.832 |
lass | -4.748 |
apt | -4.734 |
Token | North |
Token ID | 2258 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
�� | +0.407 |
edIn | +0.397 |
orney | +0.342 |
gie | +0.338 |
leton | +0.329 |
Neg logit contributions | |
agers | -0.620 |
ework | -0.566 |
ardon | -0.556 |
apt | -0.550 |
outs | -0.548 |
Token | rop |
Token ID | 1773 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
�� | +1.383 |
edIn | +1.354 |
orney | +1.185 |
gie | +1.177 |
leton | +1.155 |
Neg logit contributions | |
agers | -1.755 |
ework | -1.592 |
ardon | -1.557 |
apt | -1.533 |
outs | -1.527 |
Token | recent |
Token ID | 2274 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
agers | +0.134 |
ework | +0.120 |
ardon | +0.117 |
apt | +0.116 |
outs | +0.115 |
Neg logit contributions | |
�� | -0.133 |
edIn | -0.130 |
orney | -0.116 |
gie | -0.115 |
leton | -0.113 |
Token | years |
Token ID | 812 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
agers | +1.400 |
ework | +1.243 |
ardon | +1.216 |
apt | +1.202 |
outs | +1.193 |
Neg logit contributions | |
�� | -1.487 |
edIn | -1.458 |
orney | -1.306 |
gie | -1.291 |
�� | -1.267 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
agers | +1.269 |
ework | +1.142 |
ardon | +1.119 |
apt | +1.104 |
outs | +1.101 |
Neg logit contributions | |
�� | -1.169 |
edIn | -1.150 |
orney | -1.011 |
gie | -1.000 |
�� | -0.985 |
Token | such |
Token ID | 884 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
�� | +0.205 |
edIn | +0.202 |
orney | +0.177 |
gie | +0.176 |
leton | +0.172 |
Neg logit contributions | |
agers | -0.249 |
ework | -0.225 |
ardon | -0.221 |
apt | -0.217 |
lass | -0.217 |
Token | as |
Token ID | 355 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
�� | +0.032 |
edIn | +0.031 |
orney | +0.028 |
gie | +0.027 |
�� | +0.027 |
Neg logit contributions | |
agers | -0.035 |
ework | -0.031 |
ardon | -0.030 |
apt | -0.030 |
outs | -0.030 |
Token | Nasa |
Token ID | 48673 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
agers | +1.264 |
ework | +1.133 |
ardon | +1.112 |
apt | +1.104 |
outs | +1.092 |
Neg logit contributions | |
�� | -1.151 |
edIn | -1.123 |
orney | -0.998 |
gie | -0.985 |
�� | -0.980 |
Token | 's |
Token ID | 338 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
�� | +4.405 |
edIn | +4.365 |
orney | +3.607 |
gie | +3.577 |
leton | +3.377 |
Neg logit contributions | |
agers | -9.052 |
ework | -8.484 |
lass | -8.313 |
ardon | -8.263 |
outs | -8.127 |
Token | six |
Token ID | 2237 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
�� | +0.703 |
edIn | +0.686 |
orney | +0.596 |
gie | +0.589 |
leton | +0.577 |
Neg logit contributions | |
agers | -0.977 |
ework | -0.888 |
ardon | -0.872 |
apt | -0.861 |
outs | -0.857 |
Token | - |
Token ID | 12 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
�� | +0.187 |
edIn | +0.183 |
orney | +0.161 |
gie | +0.158 |
leton | +0.156 |
Neg logit contributions | |
agers | -0.235 |
ework | -0.213 |
ardon | -0.208 |
apt | -0.206 |
outs | -0.205 |
Token | ton |
Token ID | 1122 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
�� | +0.153 |
edIn | +0.150 |
orney | +0.134 |
gie | +0.133 |
leton | +0.131 |
Neg logit contributions | |
agers | -0.146 |
ework | -0.130 |
ardon | -0.127 |
apt | -0.125 |
outs | -0.124 |
Token | ne |
Token ID | 710 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
�� | +1.823 |
edIn | +1.798 |
gie | +1.635 |
orney | +1.633 |
leton | +1.608 |
Neg logit contributions | |
agers | -1.145 |
ework | -0.987 |
ardon | -0.961 |
apt | -0.940 |
outs | -0.935 |
Token | August |
Token ID | 2932 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
�� | +0.057 |
edIn | +0.056 |
orney | +0.050 |
gie | +0.050 |
leton | +0.049 |
Neg logit contributions | |
agers | -0.057 |
ework | -0.051 |
ardon | -0.050 |
apt | -0.049 |
lass | -0.049 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
�� | +2.298 |
edIn | +2.268 |
gie | +2.055 |
orney | +2.044 |
leton | +2.010 |
Neg logit contributions | |
agers | -1.844 |
ework | -1.635 |
ardon | -1.586 |
lass | -1.559 |
apt | -1.557 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
�� | +0.255 |
edIn | +0.250 |
orney | +0.220 |
gie | +0.219 |
leton | +0.214 |
Neg logit contributions | |
agers | -0.284 |
ework | -0.256 |
ardon | -0.251 |
apt | -0.247 |
outs | -0.246 |
Token | by |
Token ID | 1525 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
�� | +2.394 |
edIn | +2.366 |
gie | +2.134 |
orney | +2.101 |
leton | +2.060 |
Neg logit contributions | |
agers | -2.585 |
ework | -2.308 |
ardon | -2.273 |
lass | -2.226 |
apt | -2.218 |
Token | of |
Token ID | 286 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +0.272 |
edIn | +0.267 |
orney | +0.237 |
gie | +0.236 |
leton | +0.231 |
Neg logit contributions | |
agers | -0.280 |
ework | -0.251 |
ardon | -0.246 |
apt | -0.242 |
lass | -0.241 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
�� | +0.281 |
edIn | +0.276 |
orney | +0.239 |
gie | +0.238 |
leton | +0.232 |
Neg logit contributions | |
agers | -0.386 |
ework | -0.351 |
ardon | -0.344 |
apt | -0.339 |
lass | -0.338 |
Token | 1999 |
Token ID | 7358 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
�� | +6.146 |
edIn | +6.122 |
gie | +5.599 |
leton | +5.387 |
orney | +5.369 |
Neg logit contributions | |
agers | -6.996 |
ework | -6.443 |
lass | -6.214 |
ardon | -6.212 |
apt | -6.044 |
Token | K |
Token ID | 509 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
�� | +0.374 |
edIn | +0.367 |
orney | +0.325 |
gie | +0.323 |
leton | +0.316 |
Neg logit contributions | |
agers | -0.405 |
ework | -0.364 |
ardon | -0.357 |
apt | -0.351 |
outs | -0.349 |
Token | K |
Token ID | 42 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
agers | +0.850 |
ework | +0.759 |
ardon | +0.743 |
apt | +0.731 |
outs | +0.727 |
Neg logit contributions | |
�� | -0.897 |
edIn | -0.881 |
orney | -0.785 |
gie | -0.781 |
leton | -0.766 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
agers | +0.949 |
ework | +0.853 |
ardon | +0.836 |
apt | +0.825 |
outs | +0.819 |
Neg logit contributions | |
�� | -0.893 |
edIn | -0.878 |
orney | -0.777 |
gie | -0.772 |
leton | -0.757 |
Token | as |
Token ID | 355 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
�� | +1.318 |
edIn | +1.295 |
gie | +1.140 |
orney | +1.138 |
leton | +1.109 |
Neg logit contributions | |
agers | -1.488 |
ework | -1.340 |
ardon | -1.313 |
lass | -1.292 |
apt | -1.289 |
Token | with |
Token ID | 351 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
�� | +0.230 |
edIn | +0.226 |
orney | +0.200 |
gie | +0.199 |
leton | +0.194 |
Neg logit contributions | |
agers | -0.254 |
ework | -0.229 |
ardon | -0.224 |
apt | -0.221 |
lass | -0.220 |
Token | these |
Token ID | 777 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
�� | +0.160 |
edIn | +0.157 |
orney | +0.138 |
gie | +0.137 |
leton | +0.134 |
Neg logit contributions | |
agers | -0.184 |
ework | -0.166 |
ardon | -0.162 |
apt | -0.160 |
lass | -0.159 |
Token | two |
Token ID | 734 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
agers | +0.094 |
ework | +0.085 |
ardon | +0.083 |
apt | +0.081 |
lass | +0.081 |
Neg logit contributions | |
�� | -0.092 |
edIn | -0.090 |
orney | -0.080 |
gie | -0.080 |
leton | -0.078 |
Token | sides |
Token ID | 5389 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
�� | +0.827 |
edIn | +0.813 |
gie | +0.723 |
orney | +0.723 |
leton | +0.708 |
Neg logit contributions | |
agers | -0.804 |
ework | -0.721 |
ardon | -0.707 |
apt | -0.693 |
lass | -0.692 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
�� | +1.673 |
edIn | +1.648 |
gie | +1.490 |
orney | +1.478 |
leton | +1.454 |
Neg logit contributions | |
agers | -1.548 |
ework | -1.386 |
ardon | -1.354 |
lass | -1.331 |
apt | -1.329 |
Token | Costa |
Token ID | 18133 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
�� | +0.245 |
edIn | +0.241 |
orney | +0.213 |
gie | +0.212 |
leton | +0.208 |
Neg logit contributions | |
agers | -0.261 |
ework | -0.236 |
ardon | -0.230 |
apt | -0.227 |
lass | -0.226 |
Token | Rica |
Token ID | 31656 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
�� | +2.909 |
edIn | +2.757 |
gie | +2.130 |
orney | +2.127 |
leton | +2.046 |
Neg logit contributions | |
agers | -10.292 |
ework | -9.738 |
lass | -9.577 |
ardon | -9.554 |
apt | -9.517 |
Token | demonstrating |
Token ID | 21135 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
�� | +0.756 |
edIn | +0.744 |
orney | +0.661 |
gie | +0.659 |
leton | +0.646 |
Neg logit contributions | |
agers | -0.776 |
ework | -0.699 |
ardon | -0.682 |
apt | -0.671 |
lass | -0.670 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
�� | +0.053 |
edIn | +0.053 |
orney | +0.047 |
gie | +0.047 |
leton | +0.046 |
Neg logit contributions | |
agers | -0.051 |
ework | -0.045 |
ardon | -0.044 |
apt | -0.043 |
lass | -0.043 |
Token | value |
Token ID | 1988 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
agers | +0.212 |
ework | +0.189 |
ardon | +0.184 |
apt | +0.181 |
outs | +0.181 |
Neg logit contributions | |
�� | -0.226 |
edIn | -0.223 |
orney | -0.199 |
gie | -0.198 |
leton | -0.194 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
�� | +0.223 |
edIn | +0.218 |
orney | +0.193 |
gie | +0.192 |
leton | +0.188 |
Neg logit contributions | |
agers | -0.237 |
ework | -0.214 |
ardon | -0.212 |
lass | -0.207 |
apt | -0.207 |
Token | The |
Token ID | 464 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +0.111 |
edIn | +0.109 |
orney | +0.095 |
gie | +0.095 |
leton | +0.093 |
Neg logit contributions | |
agers | -0.136 |
ework | -0.123 |
ardon | -0.120 |
apt | -0.118 |
lass | -0.118 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
�� | +0.297 |
edIn | +0.291 |
orney | +0.255 |
gie | +0.253 |
leton | +0.247 |
Neg logit contributions | |
agers | -0.370 |
ework | -0.335 |
ardon | -0.328 |
apt | -0.324 |
lass | -0.322 |
Token | by |
Token ID | 1525 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
�� | +2.109 |
edIn | +2.082 |
gie | +1.862 |
orney | +1.844 |
leton | +1.811 |
Neg logit contributions | |
agers | -2.204 |
ework | -1.970 |
ardon | -1.939 |
apt | -1.898 |
lass | -1.894 |
Token | of |
Token ID | 286 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
agers | +0.240 |
ework | +0.216 |
ardon | +0.212 |
apt | +0.209 |
outs | +0.208 |
Neg logit contributions | |
�� | -0.217 |
edIn | -0.213 |
orney | -0.188 |
gie | -0.187 |
leton | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
agers | +0.341 |
ework | +0.311 |
ardon | +0.305 |
apt | +0.301 |
lass | +0.300 |
Neg logit contributions | |
�� | -0.240 |
edIn | -0.235 |
orney | -0.203 |
gie | -0.202 |
leton | -0.197 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
�� | +0.255 |
edIn | +0.250 |
orney | +0.216 |
gie | +0.214 |
leton | +0.209 |
Neg logit contributions | |
agers | -0.370 |
ework | -0.337 |
ardon | -0.331 |
apt | -0.327 |
lass | -0.325 |
Token | 99 |
Token ID | 7388 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
�� | +6.745 |
edIn | +6.616 |
gie | +6.113 |
orney | +5.824 |
leton | +5.811 |
Neg logit contributions | |
agers | -6.271 |
ework | -5.645 |
ardon | -5.557 |
lass | -5.546 |
outs | -5.386 |
Token | 69 |
Token ID | 3388 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
�� | +0.424 |
edIn | +0.417 |
orney | +0.374 |
gie | +0.372 |
leton | +0.366 |
Neg logit contributions | |
agers | -0.359 |
ework | -0.320 |
ardon | -0.311 |
apt | -0.305 |
lass | -0.305 |
Token | Bra |
Token ID | 9718 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
�� | +1.404 |
edIn | +1.376 |
gie | +1.210 |
orney | +1.205 |
leton | +1.180 |
Neg logit contributions | |
agers | -1.579 |
ework | -1.422 |
ardon | -1.389 |
lass | -1.370 |
outs | -1.364 |
Token | ille |
Token ID | 8270 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
�� | +0.996 |
edIn | +0.984 |
orney | +0.909 |
gie | +0.906 |
leton | +0.894 |
Neg logit contributions | |
agers | -0.397 |
ework | -0.324 |
ardon | -0.310 |
apt | -0.300 |
lass | -0.298 |
Token | was |
Token ID | 373 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
�� | +0.074 |
edIn | +0.073 |
orney | +0.064 |
gie | +0.064 |
leton | +0.062 |
Neg logit contributions | |
agers | -0.088 |
ework | -0.080 |
ardon | -0.078 |
apt | -0.077 |
lass | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
agers | +2.128 |
ework | +1.919 |
ardon | +1.868 |
apt | +1.855 |
outs | +1.842 |
Neg logit contributions | |
�� | -2.212 |
edIn | -2.172 |
orney | -1.925 |
gie | -1.904 |
�� | -1.882 |
Token | yet |
Token ID | 1865 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
agers | +0.329 |
ework | +0.294 |
ardon | +0.287 |
apt | +0.283 |
outs | +0.281 |
Neg logit contributions | |
�� | -0.353 |
edIn | -0.346 |
orney | -0.309 |
gie | -0.307 |
leton | -0.301 |
Token | we |
Token ID | 356 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
�� | +0.483 |
edIn | +0.474 |
orney | +0.423 |
gie | +0.421 |
leton | +0.413 |
Neg logit contributions | |
agers | -0.453 |
ework | -0.404 |
ardon | -0.394 |
apt | -0.388 |
outs | -0.386 |
Token | let |
Token ID | 1309 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
�� | +0.777 |
edIn | +0.761 |
orney | +0.664 |
gie | +0.660 |
leton | +0.645 |
Neg logit contributions | |
agers | -1.001 |
ework | -0.908 |
ardon | -0.890 |
apt | -0.878 |
lass | -0.874 |
Token | the |
Token ID | 262 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
agers | +0.234 |
ework | +0.208 |
ardon | +0.203 |
apt | +0.201 |
outs | +0.200 |
Neg logit contributions | |
�� | -0.260 |
edIn | -0.255 |
orney | -0.228 |
gie | -0.226 |
leton | -0.223 |
Token | shuttle |
Token ID | 20992 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
agers | +0.466 |
ework | +0.420 |
ardon | +0.411 |
apt | +0.405 |
outs | +0.403 |
Neg logit contributions | |
�� | -0.418 |
edIn | -0.410 |
orney | -0.362 |
gie | -0.359 |
leton | -0.352 |
Token | lapse |
Token ID | 42689 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
�� | +5.800 |
edIn | +5.678 |
gie | +5.218 |
orney | +5.126 |
leton | +5.074 |
Neg logit contributions | |
agers | -6.789 |
ework | -6.354 |
ardon | -6.160 |
lass | -6.042 |
apt | -5.911 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
�� | +0.941 |
edIn | +0.925 |
orney | +0.815 |
gie | +0.813 |
leton | +0.796 |
Neg logit contributions | |
agers | -1.062 |
ework | -0.958 |
ardon | -0.936 |
apt | -0.920 |
lass | -0.919 |
Token | instead |
Token ID | 2427 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
agers | +0.421 |
ework | +0.381 |
ardon | +0.373 |
apt | +0.369 |
outs | +0.367 |
Neg logit contributions | |
�� | -0.366 |
edIn | -0.358 |
orney | -0.315 |
gie | -0.313 |
leton | -0.306 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
agers | +0.915 |
ework | +0.819 |
ardon | +0.799 |
apt | +0.788 |
outs | +0.784 |
Neg logit contributions | |
�� | -0.952 |
edIn | -0.938 |
orney | -0.835 |
gie | -0.830 |
leton | -0.813 |
Token | building |
Token ID | 2615 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
agers | +0.189 |
ework | +0.168 |
ardon | +0.164 |
apt | +0.162 |
outs | +0.161 |
Neg logit contributions | |
�� | -0.211 |
edIn | -0.208 |
orney | -0.186 |
gie | -0.185 |
leton | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
agers | +0.160 |
ework | +0.144 |
ardon | +0.140 |
apt | +0.139 |
lass | +0.138 |
Neg logit contributions | |
�� | -0.151 |
edIn | -0.148 |
orney | -0.130 |
gie | -0.130 |
leton | -0.127 |
Token | cerebral |
Token ID | 31169 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
agers | +0.018 |
ework | +0.016 |
ardon | +0.015 |
apt | +0.015 |
lass | +0.015 |
Neg logit contributions | |
�� | -0.018 |
edIn | -0.018 |
orney | -0.016 |
gie | -0.016 |
leton | -0.016 |
Token | journalist |
Token ID | 10099 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
�� | +0.260 |
edIn | +0.256 |
orney | +0.227 |
gie | +0.226 |
leton | +0.222 |
Neg logit contributions | |
agers | -0.271 |
ework | -0.243 |
ardon | -0.237 |
apt | -0.234 |
outs | -0.233 |
Token | played |
Token ID | 2826 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
�� | +0.092 |
edIn | +0.090 |
orney | +0.080 |
gie | +0.080 |
leton | +0.078 |
Neg logit contributions | |
agers | -0.095 |
ework | -0.085 |
ardon | -0.083 |
apt | -0.082 |
lass | -0.082 |
Token | by |
Token ID | 416 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
agers | +1.111 |
ework | +1.000 |
ardon | +0.978 |
apt | +0.963 |
outs | +0.959 |
Neg logit contributions | |
�� | -1.041 |
edIn | -1.023 |
orney | -0.903 |
gie | -0.899 |
leton | -0.880 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
agers | +0.272 |
ework | +0.246 |
ardon | +0.241 |
apt | +0.238 |
lass | +0.237 |
Neg logit contributions | |
�� | -0.216 |
edIn | -0.212 |
orney | -0.185 |
gie | -0.184 |
leton | -0.180 |
Token | Ke |
Token ID | 3873 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
�� | +4.921 |
edIn | +4.838 |
orney | +4.211 |
gie | +4.205 |
leton | +4.073 |
Neg logit contributions | |
agers | -7.852 |
ework | -7.322 |
ardon | -7.060 |
lass | -7.016 |
apt | -6.928 |
Token | aton |
Token ID | 13951 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
agers | +0.832 |
ework | +0.751 |
ardon | +0.737 |
apt | +0.726 |
outs | +0.722 |
Neg logit contributions | |
�� | -0.724 |
edIn | -0.710 |
orney | -0.623 |
gie | -0.620 |
�� | -0.605 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
�� | +0.367 |
edIn | +0.360 |
orney | +0.315 |
gie | +0.313 |
leton | +0.306 |
Neg logit contributions | |
agers | -0.458 |
ework | -0.415 |
ardon | -0.407 |
apt | -0.401 |
lass | -0.399 |
Token | who |
Token ID | 508 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
�� | +0.204 |
edIn | +0.201 |
orney | +0.179 |
gie | +0.178 |
leton | +0.174 |
Neg logit contributions | |
agers | -0.202 |
ework | -0.181 |
ardon | -0.177 |
apt | -0.174 |
lass | -0.173 |
Token | proudly |
Token ID | 23017 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
�� | +0.635 |
edIn | +0.623 |
orney | +0.547 |
gie | +0.544 |
leton | +0.532 |
Neg logit contributions | |
agers | -0.751 |
ework | -0.679 |
ardon | -0.664 |
apt | -0.655 |
lass | -0.652 |
Token | have |
Token ID | 423 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
agers | +0.452 |
ework | +0.408 |
ardon | +0.400 |
apt | +0.397 |
outs | +0.394 |
Neg logit contributions | |
�� | -0.380 |
edIn | -0.372 |
orney | -0.327 |
gie | -0.322 |
�� | -0.319 |
Token | a |
Token ID | 257 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
agers | +0.248 |
ework | +0.222 |
ardon | +0.217 |
apt | +0.214 |
outs | +0.213 |
Neg logit contributions | |
�� | -0.253 |
edIn | -0.248 |
orney | -0.221 |
gie | -0.220 |
leton | -0.215 |
Token | follow |
Token ID | 1061 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
agers | +0.045 |
ework | +0.041 |
ardon | +0.040 |
apt | +0.039 |
outs | +0.039 |
Neg logit contributions | |
�� | -0.039 |
edIn | -0.038 |
orney | -0.033 |
gie | -0.033 |
leton | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
�� | +0.087 |
edIn | +0.085 |
orney | +0.075 |
gie | +0.074 |
leton | +0.073 |
Neg logit contributions | |
agers | -0.102 |
ework | -0.092 |
ardon | -0.090 |
apt | -0.089 |
lass | -0.089 |
Token | on |
Token ID | 261 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
�� | +0.509 |
edIn | +0.504 |
orney | +0.463 |
gie | +0.462 |
leton | +0.456 |
Neg logit contributions | |
agers | -0.231 |
ework | -0.192 |
ardon | -0.185 |
apt | -0.178 |
lass | -0.177 |
Token | shuttle |
Token ID | 20992 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
agers | +0.096 |
ework | +0.087 |
ardon | +0.086 |
apt | +0.085 |
outs | +0.084 |
Neg logit contributions | |
�� | -0.073 |
edIn | -0.072 |
orney | -0.063 |
gie | -0.062 |
�� | -0.061 |
Token | immediately |
Token ID | 3393 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
�� | +5.730 |
edIn | +5.552 |
gie | +5.064 |
orney | +4.967 |
leton | +4.956 |
Neg logit contributions | |
agers | -6.737 |
ework | -6.149 |
ardon | -5.977 |
lass | -5.969 |
outs | -5.767 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
�� | +0.513 |
edIn | +0.504 |
orney | +0.444 |
gie | +0.441 |
leton | +0.431 |
Neg logit contributions | |
agers | -0.599 |
ework | -0.542 |
ardon | -0.530 |
apt | -0.521 |
lass | -0.520 |
Token | � |
Token ID | 447 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
�� | +0.073 |
edIn | +0.072 |
orney | +0.062 |
gie | +0.062 |
leton | +0.060 |
Neg logit contributions | |
agers | -0.106 |
ework | -0.096 |
ardon | -0.095 |
apt | -0.093 |
outs | -0.093 |
Token | � |
Token ID | 251 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
agers | +0.218 |
ework | +0.200 |
ardon | +0.196 |
apt | +0.194 |
lass | +0.193 |
Neg logit contributions | |
�� | -0.131 |
edIn | -0.128 |
orney | -0.109 |
gie | -0.109 |
leton | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
�� | +0.079 |
edIn | +0.078 |
orney | +0.068 |
gie | +0.068 |
leton | +0.066 |
Neg logit contributions | |
agers | -0.095 |
ework | -0.086 |
ardon | -0.084 |
apt | -0.083 |
lass | -0.083 |
Token | It |
Token ID | 632 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
�� | +0.759 |
edIn | +0.745 |
orney | +0.663 |
gie | +0.660 |
leton | +0.647 |
Neg logit contributions | |
agers | -0.757 |
ework | -0.678 |
ardon | -0.661 |
apt | -0.649 |
lass | -0.648 |
Token | is |
Token ID | 318 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
�� | +0.445 |
edIn | +0.435 |
orney | +0.380 |
gie | +0.379 |
leton | +0.368 |
Neg logit contributions | |
agers | -0.623 |
ework | -0.569 |
ardon | -0.558 |
lass | -0.549 |
apt | -0.548 |
Token | considered |
Token ID | 3177 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
agers | +0.011 |
ework | +0.010 |
ardon | +0.009 |
apt | +0.009 |
lass | +0.009 |
Neg logit contributions | |
�� | -0.012 |
edIn | -0.011 |
orney | -0.010 |
gie | -0.010 |
leton | -0.010 |
Token | similar |
Token ID | 2092 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
agers | +0.722 |
ework | +0.649 |
ardon | +0.634 |
apt | +0.624 |
lass | +0.621 |
Neg logit contributions | |
�� | -0.691 |
edIn | -0.679 |
orney | -0.602 |
gie | -0.598 |
leton | -0.586 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
agers | +1.577 |
ework | +1.422 |
ardon | +1.394 |
apt | +1.374 |
lass | +1.367 |
Neg logit contributions | |
�� | -1.399 |
edIn | -1.377 |
orney | -1.211 |
gie | -1.203 |
leton | -1.178 |
Token | Costa |
Token ID | 18133 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
agers | +0.284 |
ework | +0.256 |
ardon | +0.251 |
apt | +0.248 |
lass | +0.247 |
Neg logit contributions | |
�� | -0.243 |
edIn | -0.238 |
orney | -0.209 |
gie | -0.208 |
leton | -0.204 |
Token | ac |
Token ID | 936 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
�� | +5.727 |
edIn | +5.580 |
orney | +4.977 |
gie | +4.957 |
leton | +4.932 |
Neg logit contributions | |
agers | -6.694 |
ework | -6.114 |
ardon | -5.940 |
apt | -5.858 |
lass | -5.822 |
Token | ro |
Token ID | 305 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
�� | +1.635 |
edIn | +1.608 |
orney | +1.446 |
gie | +1.431 |
leton | +1.414 |
Neg logit contributions | |
agers | -1.818 |
ework | -1.638 |
ardon | -1.597 |
apt | -1.566 |
outs | -1.559 |
Token | ker |
Token ID | 6122 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
agers | +1.030 |
ework | +0.899 |
ardon | +0.876 |
apt | +0.859 |
outs | +0.853 |
Neg logit contributions | |
�� | -1.472 |
edIn | -1.448 |
orney | -1.309 |
gie | -1.302 |
leton | -1.280 |
Token | ato |
Token ID | 5549 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
agers | +0.137 |
ework | +0.122 |
ardon | +0.119 |
apt | +0.117 |
lass | +0.117 |
Neg logit contributions | |
�� | -0.150 |
edIn | -0.147 |
orney | -0.131 |
gie | -0.131 |
leton | -0.128 |
Token | el |
Token ID | 417 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
agers | +0.141 |
ework | +0.125 |
ardon | +0.121 |
apt | +0.119 |
lass | +0.119 |
Neg logit contributions | |
�� | -0.170 |
edIn | -0.168 |
orney | -0.151 |
gie | -0.150 |
leton | -0.148 |
Token | I |
Token ID | 40 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
�� | +0.396 |
edIn | +0.389 |
orney | +0.343 |
gie | +0.341 |
leton | +0.334 |
Neg logit contributions | |
agers | -0.449 |
ework | -0.406 |
ardon | -0.397 |
apt | -0.391 |
lass | -0.389 |
Token | ke |
Token ID | 365 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
agers | +0.712 |
ework | +0.638 |
ardon | +0.623 |
apt | +0.616 |
lass | +0.611 |
Neg logit contributions | |
�� | -0.709 |
edIn | -0.695 |
orney | -0.617 |
gie | -0.611 |
leton | -0.600 |
Token | m |
Token ID | 76 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
�� | +0.306 |
edIn | +0.300 |
orney | +0.267 |
gie | +0.266 |
leton | +0.261 |
Neg logit contributions | |
agers | -0.298 |
ework | -0.266 |
ardon | -0.260 |
apt | -0.256 |
lass | -0.255 |
Token | ura |
Token ID | 5330 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
agers | +0.932 |
ework | +0.833 |
ardon | +0.816 |
apt | +0.804 |
outs | +0.798 |
Neg logit contributions | |
�� | -0.952 |
edIn | -0.934 |
orney | -0.830 |
gie | -0.825 |
leton | -0.808 |
Token | and |
Token ID | 290 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
agers | +1.085 |
ework | +0.978 |
ardon | +0.958 |
apt | +0.953 |
outs | +0.942 |
Neg logit contributions | |
�� | -1.020 |
edIn | -0.994 |
orney | -0.882 |
gie | -0.865 |
�� | -0.859 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
agers | +0.168 |
ework | +0.151 |
ardon | +0.148 |
apt | +0.146 |
outs | +0.145 |
Neg logit contributions | |
�� | -0.144 |
edIn | -0.141 |
orney | -0.124 |
gie | -0.123 |
�� | -0.121 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
�� | +5.821 |
edIn | +5.793 |
gie | +5.269 |
leton | +5.095 |
orney | +5.081 |
Neg logit contributions | |
agers | -6.413 |
ework | -5.868 |
ardon | -5.698 |
lass | -5.683 |
apt | -5.569 |
Token | 352 |
Token ID | 33394 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
�� | +1.089 |
edIn | +1.068 |
gie | +0.946 |
orney | +0.944 |
leton | +0.923 |
Neg logit contributions | |
agers | -1.162 |
ework | -1.046 |
ardon | -1.021 |
apt | -1.003 |
lass | -1.002 |
Token | McAuliffe |
Token ID | 48044 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
agers | +0.087 |
ework | +0.078 |
ardon | +0.076 |
apt | +0.075 |
lass | +0.075 |
Neg logit contributions | |
�� | -0.081 |
edIn | -0.080 |
orney | -0.071 |
gie | -0.070 |
leton | -0.069 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
agers | +1.383 |
ework | +1.246 |
ardon | +1.224 |
apt | +1.212 |
outs | +1.199 |
Neg logit contributions | |
�� | -1.291 |
edIn | -1.266 |
orney | -1.112 |
gie | -1.100 |
�� | -1.088 |
Token | 11 |
Token ID | 1157 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
agers | +1.747 |
ework | +1.559 |
ardon | +1.528 |
apt | +1.508 |
outs | +1.498 |
Neg logit contributions | |
�� | -1.811 |
edIn | -1.774 |
orney | -1.580 |
gie | -1.563 |
�� | -1.538 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
agers | +0.328 |
ework | +0.295 |
ardon | +0.289 |
apt | +0.285 |
outs | +0.283 |
Neg logit contributions | |
�� | -0.301 |
edIn | -0.295 |
orney | -0.261 |
gie | -0.260 |
leton | -0.254 |
Token | targets |
Token ID | 6670 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
�� | +0.003 |
edIn | +0.003 |
orney | +0.002 |
gie | +0.002 |
leton | +0.002 |
Neg logit contributions | |
agers | -0.003 |
ework | -0.003 |
ardon | -0.003 |
apt | -0.003 |
outs | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
�� | +1.399 |
edIn | +1.378 |
orney | +1.205 |
gie | +1.205 |
leton | +1.173 |
Neg logit contributions | |
agers | -1.710 |
ework | -1.547 |
ardon | -1.524 |
apt | -1.500 |
lass | -1.497 |
Token | changed |
Token ID | 3421 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
agers | +0.370 |
ework | +0.332 |
ardon | +0.325 |
apt | +0.320 |
outs | +0.318 |
Neg logit contributions | |
�� | -0.349 |
edIn | -0.343 |
orney | -0.303 |
gie | -0.301 |
leton | -0.295 |
Token | to |
Token ID | 284 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
agers | +0.619 |
ework | +0.558 |
ardon | +0.546 |
apt | +0.538 |
outs | +0.535 |
Neg logit contributions | |
�� | -0.560 |
edIn | -0.549 |
orney | -0.485 |
gie | -0.482 |
leton | -0.471 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
agers | +0.145 |
ework | +0.131 |
ardon | +0.128 |
apt | +0.126 |
outs | +0.126 |
Neg logit contributions | |
�� | -0.125 |
edIn | -0.122 |
orney | -0.108 |
gie | -0.107 |
leton | -0.105 |
Token | 99 |
Token ID | 7388 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
�� | +5.877 |
edIn | +5.862 |
gie | +5.326 |
orney | +5.181 |
leton | +5.147 |
Neg logit contributions | |
agers | -6.258 |
ework | -5.790 |
ardon | -5.616 |
lass | -5.553 |
apt | -5.462 |
Token | 69 |
Token ID | 3388 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
�� | +0.882 |
edIn | +0.866 |
orney | +0.775 |
gie | +0.772 |
leton | +0.760 |
Neg logit contributions | |
agers | -0.802 |
ework | -0.716 |
ardon | -0.696 |
apt | -0.684 |
lass | -0.683 |
Token | Bra |
Token ID | 9718 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
�� | +1.229 |
edIn | +1.202 |
orney | +1.063 |
gie | +1.060 |
leton | +1.039 |
Neg logit contributions | |
agers | -1.356 |
ework | -1.222 |
ardon | -1.192 |
lass | -1.176 |
apt | -1.172 |
Token | ille |
Token ID | 8270 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
agers | +0.033 |
ework | +0.027 |
ardon | +0.026 |
apt | +0.025 |
outs | +0.024 |
Neg logit contributions | |
�� | -0.084 |
edIn | -0.082 |
orney | -0.076 |
gie | -0.076 |
�� | -0.075 |
Token | ( |
Token ID | 357 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
agers | +0.244 |
ework | +0.219 |
ardon | +0.214 |
apt | +0.211 |
outs | +0.210 |
Neg logit contributions | |
�� | -0.228 |
edIn | -0.223 |
orney | -0.198 |
gie | -0.196 |
leton | -0.192 |
Token | ing |
Token ID | 278 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
�� | +0.703 |
edIn | +0.687 |
orney | +0.553 |
gie | +0.547 |
leton | +0.524 |
Neg logit contributions | |
agers | -1.681 |
ework | -1.561 |
ardon | -1.537 |
lass | -1.513 |
apt | -1.513 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
�� | +1.804 |
edIn | +1.772 |
orney | +1.571 |
gie | +1.570 |
leton | +1.538 |
Neg logit contributions | |
agers | -1.808 |
ework | -1.628 |
ardon | -1.596 |
lass | -1.558 |
apt | -1.554 |
Token | next |
Token ID | 1306 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
�� | +0.027 |
edIn | +0.027 |
orney | +0.024 |
gie | +0.023 |
leton | +0.023 |
Neg logit contributions | |
agers | -0.029 |
ework | -0.026 |
ardon | -0.026 |
apt | -0.025 |
lass | -0.025 |
Token | generation |
Token ID | 5270 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
�� | +0.577 |
edIn | +0.566 |
orney | +0.500 |
gie | +0.496 |
leton | +0.486 |
Neg logit contributions | |
agers | -0.646 |
ework | -0.582 |
ardon | -0.569 |
apt | -0.561 |
outs | -0.559 |
Token | of |
Token ID | 286 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
agers | +3.876 |
ework | +3.410 |
apt | +3.344 |
ardon | +3.305 |
outs | +3.299 |
Neg logit contributions | |
�� | -4.131 |
edIn | -4.114 |
orney | -3.686 |
�� | -3.599 |
gie | -3.589 |
Token | space |
Token ID | 2272 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
agers | +0.553 |
ework | +0.505 |
ardon | +0.495 |
apt | +0.488 |
lass | +0.487 |
Neg logit contributions | |
�� | -0.386 |
edIn | -0.377 |
orney | -0.326 |
gie | -0.324 |
leton | -0.316 |
Token | exploration |
Token ID | 13936 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
�� | +5.538 |
edIn | +5.399 |
gie | +4.762 |
orney | +4.738 |
leton | +4.683 |
Neg logit contributions | |
agers | -6.659 |
ework | -6.198 |
ardon | -6.087 |
lass | -5.995 |
slave | -5.833 |
Token | that |
Token ID | 326 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
�� | +2.128 |
edIn | +2.072 |
gie | +1.824 |
orney | +1.823 |
leton | +1.784 |
Neg logit contributions | |
agers | -2.492 |
ework | -2.280 |
ardon | -2.228 |
lass | -2.193 |
outs | -2.161 |
Token | is |
Token ID | 318 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
�� | +0.360 |
edIn | +0.353 |
orney | +0.309 |
gie | +0.307 |
leton | +0.300 |
Neg logit contributions | |
agers | -0.443 |
ework | -0.401 |
ardon | -0.393 |
apt | -0.387 |
lass | -0.386 |
Token | going |
Token ID | 1016 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
agers | +0.014 |
ework | +0.012 |
ardon | +0.012 |
apt | +0.012 |
lass | +0.012 |
Neg logit contributions | |
�� | -0.016 |
edIn | -0.016 |
orney | -0.014 |
gie | -0.014 |
leton | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
agers | +0.017 |
ework | +0.015 |
ardon | +0.015 |
lass | +0.015 |
apt | +0.015 |
Neg logit contributions | |
�� | -0.014 |
edIn | -0.013 |
orney | -0.012 |
gie | -0.012 |
leton | -0.011 |
Token | during |
Token ID | 1141 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
�� | +1.113 |
edIn | +1.094 |
orney | +0.960 |
gie | +0.955 |
leton | +0.934 |
Neg logit contributions | |
agers | -1.327 |
ework | -1.202 |
ardon | -1.176 |
apt | -1.158 |
lass | -1.155 |
Token | a |
Token ID | 257 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
�� | +1.390 |
edIn | +1.367 |
orney | +1.216 |
gie | +1.210 |
leton | +1.188 |
Neg logit contributions | |
agers | -1.355 |
ework | -1.215 |
ardon | -1.189 |
lass | -1.166 |
apt | -1.164 |
Token | busy |
Token ID | 8179 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
agers | +0.086 |
ework | +0.076 |
ardon | +0.074 |
apt | +0.073 |
outs | +0.073 |
Neg logit contributions | |
�� | -0.094 |
edIn | -0.093 |
orney | -0.083 |
gie | -0.082 |
leton | -0.081 |
Token | time |
Token ID | 640 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
�� | +1.166 |
edIn | +1.146 |
orney | +1.020 |
gie | +1.017 |
leton | +0.995 |
Neg logit contributions | |
agers | -1.169 |
ework | -1.047 |
ardon | -1.023 |
apt | -1.006 |
lass | -1.003 |
Token | for |
Token ID | 329 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
agers | +0.476 |
ework | +0.428 |
ardon | +0.418 |
apt | +0.412 |
outs | +0.410 |
Neg logit contributions | |
�� | -0.461 |
edIn | -0.453 |
orney | -0.402 |
gie | -0.399 |
leton | -0.391 |
Token | space |
Token ID | 2272 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
�� | +0.862 |
edIn | +0.842 |
orney | +0.723 |
gie | +0.718 |
leton | +0.699 |
Neg logit contributions | |
agers | -1.320 |
ework | -1.206 |
ardon | -1.184 |
apt | -1.169 |
outs | -1.164 |
Token | station |
Token ID | 4429 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
�� | +5.121 |
edIn | +5.065 |
orney | +4.426 |
gie | +4.406 |
leton | +4.337 |
Neg logit contributions | |
agers | -7.102 |
ework | -6.585 |
ardon | -6.480 |
lass | -6.332 |
slave | -6.228 |
Token | operations |
Token ID | 4560 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
�� | +2.770 |
edIn | +2.722 |
orney | +2.377 |
gie | +2.376 |
leton | +2.332 |
Neg logit contributions | |
agers | -3.407 |
ework | -3.107 |
ardon | -3.050 |
lass | -3.013 |
apt | -2.976 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
�� | +0.891 |
edIn | +0.876 |
orney | +0.773 |
gie | +0.771 |
leton | +0.753 |
Neg logit contributions | |
agers | -1.053 |
ework | -0.951 |
ardon | -0.933 |
lass | -0.916 |
apt | -0.914 |
Token | A |
Token ID | 317 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
�� | +0.224 |
edIn | +0.218 |
orney | +0.189 |
gie | +0.187 |
�� | +0.184 |
Neg logit contributions | |
agers | -0.304 |
ework | -0.276 |
ardon | -0.271 |
apt | -0.268 |
outs | -0.267 |
Token | Soy |
Token ID | 30022 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
�� | +0.820 |
edIn | +0.805 |
orney | +0.708 |
gie | +0.704 |
leton | +0.688 |
Neg logit contributions | |
agers | -0.961 |
ework | -0.868 |
ardon | -0.850 |
apt | -0.838 |
lass | -0.834 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +4.264 |
edIn | +4.212 |
gie | +3.714 |
orney | +3.669 |
leton | +3.571 |
Neg logit contributions | |
agers | -5.433 |
ework | -4.988 |
ardon | -4.822 |
lass | -4.776 |
apt | -4.741 |
Token | was |
Token ID | 373 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
�� | +1.271 |
edIn | +1.247 |
orney | +1.095 |
gie | +1.091 |
leton | +1.066 |
Neg logit contributions | |
agers | -1.513 |
ework | -1.367 |
ardon | -1.343 |
apt | -1.319 |
lass | -1.317 |
Token | intended |
Token ID | 5292 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
�� | +0.119 |
edIn | +0.117 |
orney | +0.104 |
gie | +0.104 |
leton | +0.102 |
Neg logit contributions | |
agers | -0.117 |
ework | -0.105 |
ardon | -0.103 |
apt | -0.101 |
lass | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
�� | +1.029 |
edIn | +1.008 |
orney | +0.883 |
gie | +0.874 |
leton | +0.862 |
Neg logit contributions | |
agers | -1.273 |
ework | -1.160 |
ardon | -1.130 |
lass | -1.118 |
apt | -1.118 |
Token | visit |
Token ID | 3187 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
�� | +0.511 |
edIn | +0.502 |
orney | +0.445 |
gie | +0.443 |
leton | +0.433 |
Neg logit contributions | |
agers | -0.546 |
ework | -0.491 |
ardon | -0.481 |
apt | -0.473 |
lass | -0.471 |
Token | comet |
Token ID | 31733 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
�� | +2.292 |
edIn | +2.266 |
orney | +1.986 |
gie | +1.980 |
leton | +1.939 |
Neg logit contributions | |
agers | -2.545 |
ework | -2.313 |
ardon | -2.250 |
lass | -2.217 |
apt | -2.199 |
Token | 76 |
Token ID | 8684 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
�� | +5.664 |
edIn | +5.599 |
gie | +4.982 |
leton | +4.897 |
orney | +4.849 |
Neg logit contributions | |
agers | -6.620 |
ework | -6.021 |
ardon | -5.959 |
lass | -5.873 |
apt | -5.747 |
Token | P |
Token ID | 47 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
�� | +0.075 |
edIn | +0.074 |
orney | +0.066 |
gie | +0.065 |
leton | +0.064 |
Neg logit contributions | |
agers | -0.078 |
ework | -0.070 |
ardon | -0.068 |
apt | -0.067 |
outs | -0.067 |
Token | / |
Token ID | 14 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
agers | +0.782 |
ework | +0.699 |
ardon | +0.684 |
apt | +0.674 |
outs | +0.669 |
Neg logit contributions | |
�� | -0.807 |
edIn | -0.792 |
orney | -0.706 |
gie | -0.701 |
leton | -0.687 |
Token | West |
Token ID | 15045 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
�� | +1.052 |
edIn | +1.037 |
gie | +0.908 |
orney | +0.908 |
leton | +0.889 |
Neg logit contributions | |
agers | -1.197 |
ework | -1.083 |
ardon | -1.056 |
lass | -1.038 |
apt | -1.038 |
Token | – |
Token ID | 1906 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
agers | +1.002 |
ework | +0.898 |
ardon | +0.882 |
apt | +0.877 |
outs | +0.872 |
Neg logit contributions | |
�� | -0.871 |
edIn | -0.847 |
orney | -0.751 |
gie | -0.739 |
�� | -0.733 |
Token | extremely |
Token ID | 4457 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
�� | +2.233 |
edIn | +2.209 |
gie | +1.945 |
orney | +1.942 |
leton | +1.886 |
Neg logit contributions | |
agers | -2.408 |
ework | -2.173 |
ardon | -2.122 |
lass | -2.094 |
apt | -2.084 |
Token | detailed |
Token ID | 6496 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
�� | +2.443 |
edIn | +2.413 |
gie | +2.172 |
orney | +2.150 |
leton | +2.104 |
Neg logit contributions | |
agers | -2.364 |
ework | -2.126 |
ardon | -2.088 |
lass | -2.035 |
apt | -2.033 |
Token | images |
Token ID | 4263 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
�� | +0.092 |
edIn | +0.090 |
orney | +0.080 |
gie | +0.079 |
leton | +0.078 |
Neg logit contributions | |
agers | -0.096 |
ework | -0.086 |
ardon | -0.085 |
apt | -0.083 |
outs | -0.083 |
Token | of |
Token ID | 286 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
�� | +0.813 |
edIn | +0.794 |
gie | +0.716 |
orney | +0.708 |
leton | +0.690 |
Neg logit contributions | |
agers | -0.893 |
ework | -0.804 |
ardon | -0.789 |
lass | -0.776 |
apt | -0.773 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
�� | +0.055 |
edIn | +0.054 |
orney | +0.048 |
gie | +0.048 |
leton | +0.047 |
Neg logit contributions | |
agers | -0.060 |
ework | -0.054 |
ardon | -0.053 |
apt | -0.052 |
lass | -0.052 |
Token | comet |
Token ID | 31733 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
�� | +0.358 |
edIn | +0.349 |
orney | +0.298 |
gie | +0.296 |
leton | +0.287 |
Neg logit contributions | |
agers | -0.585 |
ework | -0.536 |
ardon | -0.526 |
apt | -0.520 |
lass | -0.518 |
Token | 's |
Token ID | 338 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
�� | +5.204 |
edIn | +5.114 |
gie | +4.690 |
orney | +4.474 |
leton | +4.460 |
Neg logit contributions | |
agers | -6.893 |
ardon | -6.176 |
ework | -6.175 |
lass | -6.155 |
apt | -6.018 |
Token | surface |
Token ID | 4417 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
�� | +0.880 |
edIn | +0.866 |
orney | +0.746 |
gie | +0.744 |
leton | +0.724 |
Neg logit contributions | |
agers | -1.286 |
ework | -1.173 |
ardon | -1.151 |
apt | -1.135 |
lass | -1.131 |
Token | . |
Token ID | 13 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
�� | +3.121 |
edIn | +3.096 |
gie | +2.830 |
orney | +2.741 |
leton | +2.675 |
Neg logit contributions | |
agers | -4.311 |
ework | -3.864 |
ardon | -3.822 |
lass | -3.797 |
apt | -3.754 |
Token | Such |
Token ID | 8013 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
�� | +0.504 |
edIn | +0.494 |
orney | +0.431 |
gie | +0.428 |
leton | +0.418 |
Neg logit contributions | |
agers | -0.647 |
ework | -0.587 |
ardon | -0.575 |
apt | -0.568 |
outs | -0.565 |
Token | images |
Token ID | 4263 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
�� | +0.787 |
edIn | +0.774 |
orney | +0.685 |
gie | +0.685 |
leton | +0.667 |
Neg logit contributions | |
agers | -0.827 |
ework | -0.745 |
ardon | -0.730 |
apt | -0.717 |
lass | -0.716 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
agers | +0.791 |
ework | +0.713 |
ardon | +0.697 |
apt | +0.687 |
lass | +0.684 |
Neg logit contributions | |
�� | -0.708 |
edIn | -0.694 |
orney | -0.613 |
gie | -0.609 |
leton | -0.596 |
Token | � |
Token ID | 447 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
agers | +0.315 |
ework | +0.288 |
ardon | +0.282 |
apt | +0.279 |
outs | +0.278 |
Neg logit contributions | |
�� | -0.208 |
edIn | -0.204 |
orney | -0.175 |
gie | -0.174 |
leton | -0.169 |
Token | � |
Token ID | 251 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
�� | +0.161 |
edIn | +0.158 |
orney | +0.134 |
gie | +0.133 |
leton | +0.129 |
Neg logit contributions | |
agers | -0.276 |
ework | -0.253 |
ardon | -0.249 |
apt | -0.246 |
lass | -0.245 |
Token | Even |
Token ID | 3412 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
�� | +0.042 |
edIn | +0.042 |
orney | +0.036 |
gie | +0.036 |
leton | +0.035 |
Neg logit contributions | |
agers | -0.052 |
ework | -0.048 |
ardon | -0.047 |
apt | -0.046 |
lass | -0.046 |
Token | Darrell |
Token ID | 44882 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
�� | +0.986 |
edIn | +0.969 |
orney | +0.859 |
gie | +0.856 |
leton | +0.838 |
Neg logit contributions | |
agers | -1.033 |
ework | -0.929 |
ardon | -0.908 |
apt | -0.893 |
lass | -0.890 |
Token | Duff |
Token ID | 50209 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
�� | +0.131 |
edIn | +0.129 |
orney | +0.110 |
gie | +0.109 |
leton | +0.106 |
Neg logit contributions | |
agers | -0.204 |
ework | -0.187 |
ardon | -0.183 |
apt | -0.181 |
outs | -0.180 |
Token | ie |
Token ID | 494 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
�� | +4.103 |
edIn | +4.056 |
gie | +3.787 |
orney | +3.733 |
leton | +3.604 |
Neg logit contributions | |
agers | -7.937 |
ework | -7.282 |
apt | -7.128 |
ufact | -7.095 |
ardon | -7.043 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
�� | +3.787 |
edIn | +3.673 |
gie | +3.342 |
orney | +3.303 |
leton | +3.228 |
Neg logit contributions | |
agers | -4.769 |
ework | -4.372 |
ardon | -4.267 |
lass | -4.232 |
apt | -4.160 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
�� | +0.441 |
edIn | +0.433 |
orney | +0.385 |
gie | +0.382 |
leton | +0.374 |
Neg logit contributions | |
agers | -0.463 |
ework | -0.416 |
ardon | -0.407 |
apt | -0.399 |
outs | -0.399 |
Token | sole |
Token ID | 6195 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
agers | +0.251 |
ework | +0.225 |
ardon | +0.220 |
apt | +0.216 |
lass | +0.215 |
Neg logit contributions | |
�� | -0.247 |
edIn | -0.242 |
orney | -0.215 |
gie | -0.214 |
leton | -0.210 |
Token | economist |
Token ID | 17646 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
�� | +0.803 |
edIn | +0.789 |
orney | +0.706 |
gie | +0.702 |
leton | +0.691 |
Neg logit contributions | |
agers | -0.729 |
ework | -0.647 |
ardon | -0.634 |
apt | -0.621 |
lass | -0.618 |
Token | age |
Token ID | 2479 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
�� | +0.588 |
edIn | +0.579 |
orney | +0.521 |
gie | +0.517 |
leton | +0.511 |
Neg logit contributions | |
agers | -0.488 |
ework | -0.434 |
ardon | -0.422 |
apt | -0.413 |
outs | -0.413 |
Token | 87 |
Token ID | 10083 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
agers | +0.141 |
ework | +0.126 |
ardon | +0.123 |
apt | +0.121 |
outs | +0.120 |
Neg logit contributions | |
�� | -0.153 |
edIn | -0.150 |
orney | -0.134 |
gie | -0.133 |
leton | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
agers | +0.787 |
ework | +0.712 |
ardon | +0.698 |
apt | +0.688 |
outs | +0.685 |
Neg logit contributions | |
�� | -0.643 |
edIn | -0.630 |
orney | -0.552 |
gie | -0.548 |
leton | -0.536 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
�� | +0.906 |
edIn | +0.894 |
orney | +0.785 |
gie | +0.779 |
leton | +0.765 |
Neg logit contributions | |
agers | -1.157 |
ework | -1.056 |
ardon | -1.027 |
apt | -1.013 |
lass | -1.013 |
Token | By |
Token ID | 3886 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
�� | +2.242 |
edIn | +2.237 |
gie | +1.955 |
orney | +1.943 |
leton | +1.912 |
Neg logit contributions | |
agers | -2.628 |
ework | -2.375 |
ardon | -2.317 |
lass | -2.285 |
ufact | -2.261 |
Token | Cait |
Token ID | 34118 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
�� | +0.948 |
edIn | +0.928 |
orney | +0.820 |
gie | +0.818 |
leton | +0.799 |
Neg logit contributions | |
agers | -1.086 |
ework | -0.981 |
ardon | -0.959 |
apt | -0.946 |
lass | -0.939 |
Token | lin |
Token ID | 2815 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
�� | +6.905 |
edIn | +6.801 |
orney | +6.416 |
leton | +6.406 |
gie | +6.357 |
Neg logit contributions | |
agers | -5.278 |
ework | -4.455 |
ardon | -4.415 |
apt | -4.315 |
outs | -4.296 |
Token | Hue |
Token ID | 31788 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
�� | +0.165 |
edIn | +0.162 |
orney | +0.142 |
gie | +0.141 |
leton | +0.138 |
Neg logit contributions | |
agers | -0.194 |
ework | -0.175 |
ardon | -0.171 |
apt | -0.169 |
outs | -0.168 |
Token | y |
Token ID | 88 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
agers | +0.059 |
ework | +0.052 |
ardon | +0.051 |
apt | +0.050 |
lass | +0.050 |
Neg logit contributions | |
�� | -0.064 |
edIn | -0.063 |
orney | -0.056 |
gie | -0.056 |
leton | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
�� | +0.892 |
edIn | +0.876 |
orney | +0.776 |
gie | +0.772 |
leton | +0.757 |
Neg logit contributions | |
agers | -1.000 |
ework | -0.902 |
ardon | -0.881 |
apt | -0.868 |
lass | -0.863 |
Token | Burn |
Token ID | 29053 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
�� | +0.600 |
edIn | +0.591 |
orney | +0.520 |
gie | +0.517 |
leton | +0.506 |
Neg logit contributions | |
agers | -0.699 |
ework | -0.632 |
ardon | -0.618 |
apt | -0.608 |
lass | -0.605 |
Token | task |
Token ID | 35943 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
�� | +0.055 |
edIn | +0.055 |
gie | +0.049 |
orney | +0.049 |
leton | +0.049 |
Neg logit contributions | |
agers | -0.044 |
ework | -0.039 |
ardon | -0.038 |
lass | -0.037 |
apt | -0.037 |
Token | ed |
Token ID | 276 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
agers | +0.102 |
ework | +0.093 |
ardon | +0.091 |
apt | +0.090 |
lass | +0.090 |
Neg logit contributions | |
�� | -0.069 |
edIn | -0.067 |
orney | -0.058 |
gie | -0.058 |
leton | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
�� | +1.137 |
edIn | +1.121 |
orney | +0.988 |
gie | +0.984 |
leton | +0.961 |
Neg logit contributions | |
agers | -1.315 |
ework | -1.188 |
ardon | -1.158 |
lass | -1.145 |
apt | -1.143 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
�� | +0.318 |
edIn | +0.312 |
orney | +0.273 |
gie | +0.271 |
leton | +0.265 |
Neg logit contributions | |
agers | -0.397 |
ework | -0.360 |
ardon | -0.353 |
apt | -0.348 |
outs | -0.346 |
Token | by |
Token ID | 416 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
�� | +2.560 |
edIn | +2.531 |
gie | +2.248 |
orney | +2.230 |
leton | +2.172 |
Neg logit contributions | |
agers | -2.810 |
ework | -2.529 |
ardon | -2.455 |
lass | -2.430 |
apt | -2.425 |
Token | comet |
Token ID | 31733 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
agers | +0.356 |
ework | +0.322 |
ardon | +0.316 |
apt | +0.312 |
outs | +0.310 |
Neg logit contributions | |
�� | -0.285 |
edIn | -0.279 |
orney | -0.244 |
gie | -0.242 |
leton | -0.237 |
Token | 19 |
Token ID | 678 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
�� | +5.796 |
edIn | +5.748 |
gie | +5.249 |
orney | +5.104 |
leton | +5.084 |
Neg logit contributions | |
agers | -6.168 |
ework | -5.598 |
lass | -5.435 |
ardon | -5.426 |
apt | -5.321 |
Token | P |
Token ID | 47 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
�� | +0.902 |
edIn | +0.883 |
orney | +0.787 |
gie | +0.787 |
leton | +0.773 |
Neg logit contributions | |
agers | -0.886 |
ework | -0.793 |
ardon | -0.774 |
lass | -0.758 |
apt | -0.758 |
Token | / |
Token ID | 14 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
agers | +1.123 |
ework | +1.003 |
ardon | +0.980 |
apt | +0.965 |
outs | +0.958 |
Neg logit contributions | |
�� | -1.197 |
edIn | -1.177 |
orney | -1.050 |
gie | -1.043 |
leton | -1.023 |
Token | B |
Token ID | 33 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
�� | +0.753 |
edIn | +0.743 |
orney | +0.651 |
gie | +0.650 |
leton | +0.639 |
Neg logit contributions | |
agers | -0.852 |
ework | -0.772 |
ardon | -0.751 |
lass | -0.739 |
apt | -0.737 |
Token | or |
Token ID | 273 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
�� | +0.298 |
edIn | +0.295 |
orney | +0.270 |
gie | +0.268 |
leton | +0.265 |
Neg logit contributions | |
agers | -0.180 |
ework | -0.155 |
ardon | -0.149 |
outs | -0.145 |
lass | -0.145 |
Token | of |
Token ID | 1659 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
�� | +0.602 |
edIn | +0.597 |
gie | +0.548 |
orney | +0.548 |
leton | +0.537 |
Neg logit contributions | |
agers | -0.451 |
ework | -0.399 |
ardon | -0.389 |
lass | -0.375 |
apt | -0.373 |
Token | - |
Token ID | 12 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
�� | +1.145 |
edIn | +1.127 |
orney | +0.986 |
gie | +0.980 |
leton | +0.958 |
Neg logit contributions | |
agers | -1.532 |
ework | -1.392 |
ardon | -1.364 |
apt | -1.342 |
lass | -1.339 |
Token | attack |
Token ID | 20358 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�� | +1.166 |
edIn | +1.155 |
orney | +1.050 |
gie | +1.046 |
leton | +1.028 |
Neg logit contributions | |
agers | -0.962 |
ework | -0.856 |
ardon | -0.831 |
lass | -0.813 |
apt | -0.807 |
Token | data |
Token ID | 1366 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
agers | +0.567 |
ework | +0.509 |
ardon | +0.498 |
apt | +0.490 |
lass | +0.488 |
Neg logit contributions | |
�� | -0.535 |
edIn | -0.526 |
orney | -0.466 |
gie | -0.464 |
leton | -0.454 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
agers | +0.799 |
ework | +0.721 |
ardon | +0.706 |
apt | +0.696 |
lass | +0.693 |
Neg logit contributions | |
�� | -0.696 |
edIn | -0.683 |
orney | -0.602 |
gie | -0.598 |
leton | -0.585 |
Token | Airbus |
Token ID | 39173 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
�� | +0.424 |
edIn | +0.416 |
orney | +0.364 |
gie | +0.362 |
leton | +0.354 |
Neg logit contributions | |
agers | -0.522 |
ework | -0.473 |
ardon | -0.463 |
apt | -0.457 |
lass | -0.455 |
Token | later |
Token ID | 1568 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
�� | +5.412 |
edIn | +5.354 |
gie | +4.771 |
orney | +4.759 |
leton | +4.547 |
Neg logit contributions | |
agers | -6.633 |
ework | -6.074 |
ardon | -5.886 |
apt | -5.820 |
lass | -5.811 |
Token | rede |
Token ID | 21459 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
agers | +1.494 |
ework | +1.344 |
ardon | +1.312 |
outs | +1.292 |
apt | +1.291 |
Neg logit contributions | |
�� | -1.436 |
edIn | -1.407 |
orney | -1.228 |
gie | -1.217 |
�� | -1.209 |
Token | - |
Token ID | 532 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
�� | +1.302 |
edIn | +1.280 |
orney | +1.150 |
gie | +1.144 |
leton | +1.123 |
Neg logit contributions | |
agers | -1.083 |
ework | -0.959 |
ardon | -0.935 |
apt | -0.919 |
outs | -0.914 |
Token | signed |
Token ID | 4488 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
�� | +1.114 |
edIn | +1.105 |
orney | +0.983 |
gie | +0.979 |
leton | +0.961 |
Neg logit contributions | |
agers | -1.002 |
ework | -0.890 |
ardon | -0.868 |
lass | -0.853 |
apt | -0.852 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
�� | +0.856 |
edIn | +0.847 |
orney | +0.754 |
gie | +0.752 |
leton | +0.733 |
Neg logit contributions | |
agers | -0.836 |
ework | -0.747 |
ardon | -0.729 |
apt | -0.718 |
lass | -0.715 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
�� | +0.947 |
edIn | +0.927 |
gie | +0.820 |
orney | +0.818 |
leton | +0.805 |
Neg logit contributions | |
agers | -1.081 |
ework | -0.974 |
ardon | -0.953 |
lass | -0.935 |
apt | -0.934 |
Token | was |
Token ID | 373 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
agers | +0.215 |
ework | +0.194 |
ardon | +0.190 |
apt | +0.188 |
lass | +0.187 |
Neg logit contributions | |
�� | -0.174 |
edIn | -0.170 |
orney | -0.149 |
gie | -0.148 |
leton | -0.145 |
Token | where |
Token ID | 810 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
agers | +0.545 |
ework | +0.489 |
ardon | +0.478 |
apt | +0.471 |
lass | +0.469 |
Neg logit contributions | |
�� | -0.529 |
edIn | -0.520 |
orney | -0.461 |
gie | -0.459 |
leton | -0.449 |
Token | J |
Token ID | 449 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
�� | +1.019 |
edIn | +0.999 |
orney | +0.876 |
gie | +0.876 |
leton | +0.858 |
Neg logit contributions | |
agers | -1.238 |
ework | -1.118 |
ardon | -1.095 |
apt | -1.077 |
outs | -1.071 |
Token | iri |
Token ID | 14783 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
agers | +0.805 |
ework | +0.714 |
ardon | +0.697 |
apt | +0.685 |
outs | +0.681 |
Neg logit contributions | |
�� | -0.934 |
edIn | -0.918 |
orney | -0.820 |
gie | -0.818 |
leton | -0.802 |
Token | Rak |
Token ID | 34299 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
agers | +0.076 |
ework | +0.069 |
ardon | +0.067 |
apt | +0.066 |
lass | +0.066 |
Neg logit contributions | |
�� | -0.063 |
edIn | -0.062 |
orney | -0.054 |
gie | -0.054 |
leton | -0.053 |
Token | held |
Token ID | 2714 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
agers | +6.088 |
ework | +5.416 |
ardon | +5.281 |
apt | +5.276 |
outs | +5.185 |
Neg logit contributions | |
�� | -7.330 |
edIn | -7.098 |
�� | -6.202 |
gie | -6.177 |
�� | -6.176 |
Token | forth |
Token ID | 6071 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
agers | +0.383 |
ework | +0.343 |
ardon | +0.335 |
apt | +0.329 |
lass | +0.327 |
Neg logit contributions | |
�� | -0.399 |
edIn | -0.392 |
orney | -0.350 |
gie | -0.349 |
leton | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
agers | +1.427 |
ework | +1.284 |
ardon | +1.259 |
apt | +1.245 |
outs | +1.237 |
Neg logit contributions | |
�� | -1.332 |
edIn | -1.302 |
orney | -1.152 |
gie | -1.140 |
�� | -1.123 |
Token | other |
Token ID | 584 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
agers | +0.544 |
ework | +0.489 |
ardon | +0.478 |
apt | +0.471 |
lass | +0.469 |
Neg logit contributions | |
�� | -0.530 |
edIn | -0.521 |
orney | -0.462 |
gie | -0.458 |
leton | -0.449 |
Token | night |
Token ID | 1755 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
agers | +0.875 |
ework | +0.802 |
ardon | +0.783 |
outs | +0.775 |
lass | +0.774 |
Neg logit contributions | |
�� | -0.601 |
edIn | -0.588 |
orney | -0.505 |
gie | -0.498 |
leton | -0.486 |
Token | scale |
Token ID | 5046 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
agers | +0.219 |
ework | +0.196 |
ardon | +0.192 |
apt | +0.189 |
lass | +0.188 |
Neg logit contributions | |
�� | -0.223 |
edIn | -0.219 |
orney | -0.195 |
gie | -0.194 |
leton | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
agers | +0.783 |
ework | +0.701 |
ardon | +0.685 |
apt | +0.674 |
lass | +0.671 |
Neg logit contributions | |
�� | -0.793 |
edIn | -0.779 |
orney | -0.693 |
gie | -0.690 |
leton | -0.676 |
Token | violence |
Token ID | 3685 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
agers | +0.130 |
ework | +0.117 |
ardon | +0.114 |
apt | +0.112 |
outs | +0.112 |
Neg logit contributions | |
�� | -0.128 |
edIn | -0.126 |
orney | -0.112 |
gie | -0.111 |
leton | -0.109 |
Token | of |
Token ID | 286 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
agers | +3.397 |
ework | +3.025 |
ardon | +2.933 |
outs | +2.922 |
apt | +2.915 |
Neg logit contributions | |
�� | -3.629 |
edIn | -3.536 |
orney | -3.150 |
gie | -3.122 |
�� | -3.073 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
agers | +0.588 |
ework | +0.528 |
ardon | +0.516 |
apt | +0.508 |
lass | +0.506 |
Neg logit contributions | |
�� | -0.574 |
edIn | -0.565 |
orney | -0.501 |
gie | -0.498 |
leton | -0.488 |
Token | forc |
Token ID | 24686 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
�� | +0.047 |
edIn | +0.047 |
orney | +0.042 |
gie | +0.042 |
leton | +0.041 |
Neg logit contributions | |
agers | -0.042 |
ework | -0.038 |
ardon | -0.037 |
apt | -0.036 |
lass | -0.036 |
Token | ible |
Token ID | 856 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
agers | +7.206 |
ework | +6.713 |
outs | +6.382 |
ardon | +6.376 |
apt | +6.291 |
Neg logit contributions | |
�� | -6.274 |
edIn | -5.733 |
�� | -5.442 |
�� | -5.371 |
gie | -5.157 |
Token | recruitment |
Token ID | 19624 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
agers | +0.674 |
ework | +0.597 |
ardon | +0.582 |
apt | +0.572 |
outs | +0.568 |
Neg logit contributions | |
�� | -0.804 |
edIn | -0.791 |
orney | -0.710 |
gie | -0.706 |
leton | -0.694 |
Token | by |
Token ID | 416 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
agers | +2.740 |
ework | +2.466 |
ardon | +2.392 |
outs | +2.370 |
apt | +2.366 |
Neg logit contributions | |
�� | -2.781 |
edIn | -2.716 |
orney | -2.420 |
gie | -2.388 |
�� | -2.367 |
Token | al |
Token ID | 435 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
agers | +0.757 |
ework | +0.677 |
ardon | +0.662 |
apt | +0.649 |
lass | +0.646 |
Neg logit contributions | |
�� | -0.805 |
edIn | -0.795 |
orney | -0.708 |
gie | -0.705 |
leton | -0.692 |
Token | - |
Token ID | 12 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
�� | +0.389 |
edIn | +0.380 |
orney | +0.332 |
gie | +0.329 |
�� | +0.322 |
Neg logit contributions | |
agers | -0.485 |
ework | -0.439 |
ardon | -0.430 |
apt | -0.425 |
outs | -0.424 |
Token | as |
Token ID | 355 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
agers | +1.372 |
ework | +1.242 |
ardon | +1.211 |
apt | +1.193 |
lass | +1.189 |
Neg logit contributions | |
�� | -1.206 |
edIn | -1.184 |
orney | -1.048 |
gie | -1.042 |
leton | -1.022 |
Token | Ken |
Token ID | 7148 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
agers | +1.731 |
ework | +1.555 |
ardon | +1.525 |
apt | +1.505 |
outs | +1.496 |
Neg logit contributions | |
�� | -1.568 |
edIn | -1.540 |
orney | -1.352 |
gie | -1.343 |
�� | -1.319 |
Token | an |
Token ID | 272 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
agers | +2.360 |
ework | +2.119 |
ardon | +2.090 |
apt | +2.063 |
lass | +2.053 |
Neg logit contributions | |
�� | -2.116 |
edIn | -2.075 |
orney | -1.818 |
gie | -1.795 |
�� | -1.772 |
Token | Adams |
Token ID | 12620 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
agers | +2.860 |
ework | +2.572 |
ardon | +2.539 |
apt | +2.497 |
lass | +2.486 |
Neg logit contributions | |
�� | -2.498 |
edIn | -2.446 |
orney | -2.131 |
gie | -2.109 |
�� | -2.097 |
Token | - |
Token ID | 12 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
�� | +1.302 |
edIn | +1.277 |
orney | +1.139 |
gie | +1.134 |
leton | +1.112 |
Neg logit contributions | |
agers | -1.481 |
ework | -1.342 |
ardon | -1.303 |
apt | -1.286 |
lass | -1.281 |
Token | Kin |
Token ID | 49681 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
agers | +0.318 |
ework | +0.288 |
ardon | +0.282 |
apt | +0.278 |
lass | +0.277 |
Neg logit contributions | |
�� | -0.266 |
edIn | -0.261 |
orney | -0.229 |
gie | -0.228 |
leton | -0.223 |
Token | ard |
Token ID | 446 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
agers | +6.129 |
ework | +5.446 |
ardon | +5.370 |
lass | +5.314 |
outs | +5.245 |
Neg logit contributions | |
�� | -7.264 |
edIn | -7.024 |
�� | -6.163 |
�� | -6.144 |
gie | -6.100 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
agers | +0.608 |
ework | +0.545 |
ardon | +0.532 |
apt | +0.523 |
lass | +0.521 |
Neg logit contributions | |
�� | -0.602 |
edIn | -0.591 |
orney | -0.527 |
gie | -0.524 |
leton | -0.514 |
Token | naming |
Token ID | 19264 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
agers | +0.433 |
ework | +0.389 |
ardon | +0.379 |
apt | +0.373 |
lass | +0.373 |
Neg logit contributions | |
�� | -0.437 |
edIn | -0.429 |
orney | -0.383 |
gie | -0.381 |
leton | -0.374 |
Token | him |
Token ID | 683 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
agers | +1.116 |
ework | +0.983 |
ardon | +0.960 |
apt | +0.945 |
outs | +0.939 |
Neg logit contributions | |
�� | -1.366 |
edIn | -1.340 |
orney | -1.206 |
gie | -1.200 |
leton | -1.177 |
Token | even |
Token ID | 772 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
agers | +1.356 |
ework | +1.217 |
ardon | +1.194 |
apt | +1.179 |
outs | +1.173 |
Neg logit contributions | |
�� | -1.233 |
edIn | -1.206 |
orney | -1.063 |
gie | -1.057 |
�� | -1.033 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
�� | +1.864 |
edIn | +1.830 |
gie | +1.621 |
orney | +1.620 |
leton | +1.567 |
Neg logit contributions | |
agers | -2.268 |
ework | -2.059 |
ardon | -2.020 |
lass | -1.981 |
apt | -1.979 |
Token | Girl |
Token ID | 7430 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
�� | +0.448 |
edIn | +0.440 |
orney | +0.387 |
gie | +0.386 |
leton | +0.375 |
Neg logit contributions | |
agers | -0.581 |
ework | -0.528 |
ardon | -0.518 |
lass | -0.510 |
apt | -0.510 |
Token | In |
Token ID | 554 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
�� | +1.331 |
edIn | +1.311 |
gie | +1.168 |
orney | +1.159 |
leton | +1.134 |
Neg logit contributions | |
agers | -1.526 |
ework | -1.385 |
ardon | -1.364 |
lass | -1.337 |
apt | -1.333 |
Token | Public |
Token ID | 5094 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
�� | +0.397 |
edIn | +0.388 |
orney | +0.342 |
gie | +0.341 |
leton | +0.333 |
Neg logit contributions | |
agers | -0.471 |
ework | -0.426 |
ardon | -0.418 |
apt | -0.411 |
lass | -0.410 |
Token | - |
Token ID | 12 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
agers | +1.138 |
ework | +1.025 |
ardon | +1.002 |
apt | +0.990 |
outs | +0.985 |
Neg logit contributions | |
�� | -1.021 |
edIn | -1.000 |
orney | -0.881 |
gie | -0.873 |
leton | -0.856 |
Token | Writ |
Token ID | 20257 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
�� | +0.315 |
edIn | +0.309 |
orney | +0.272 |
gie | +0.271 |
leton | +0.265 |
Neg logit contributions | |
agers | -0.370 |
ework | -0.335 |
ardon | -0.328 |
apt | -0.322 |
lass | -0.321 |
Token | ters |
Token ID | 1010 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
agers | +6.032 |
ework | +5.445 |
outs | +5.186 |
lass | +5.129 |
ardon | +5.120 |
Neg logit contributions | |
�� | -7.042 |
edIn | -6.683 |
�� | -6.139 |
�� | -6.122 |
orney | -6.026 |
Token | Strike |
Token ID | 12282 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
agers | +0.137 |
ework | +0.124 |
ardon | +0.122 |
apt | +0.120 |
lass | +0.120 |
Neg logit contributions | |
�� | -0.113 |
edIn | -0.111 |
orney | -0.097 |
gie | -0.097 |
leton | -0.095 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
agers | +0.955 |
ework | +0.865 |
ardon | +0.847 |
apt | +0.836 |
outs | +0.836 |
Neg logit contributions | |
�� | -0.751 |
edIn | -0.733 |
orney | -0.641 |
gie | -0.635 |
leton | -0.621 |
Token | 01 |
Token ID | 486 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
�� | +0.670 |
edIn | +0.659 |
orney | +0.574 |
gie | +0.573 |
leton | +0.558 |
Neg logit contributions | |
agers | -0.860 |
ework | -0.780 |
ardon | -0.764 |
apt | -0.751 |
lass | -0.750 |
Token | 04 |
Token ID | 3023 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
�� | +1.688 |
edIn | +1.653 |
gie | +1.451 |
orney | +1.451 |
leton | +1.423 |
Neg logit contributions | |
agers | -2.079 |
ework | -1.887 |
ardon | -1.831 |
lass | -1.805 |
outs | -1.803 |
Token | ), |
Token ID | 828 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
agers | +0.749 |
ework | +0.651 |
ardon | +0.633 |
lass | +0.619 |
apt | +0.617 |
Neg logit contributions | |
�� | -1.126 |
edIn | -1.111 |
orney | -1.010 |
gie | -1.005 |
leton | -0.987 |
Token | which |
Token ID | 543 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
agers | +1.101 |
ework | +0.987 |
ardon | +0.965 |
apt | +0.950 |
lass | +0.946 |
Neg logit contributions | |
�� | -1.079 |
edIn | -1.060 |
orney | -0.941 |
gie | -0.936 |
leton | -0.917 |
Token | was |
Token ID | 373 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
�� | +0.370 |
edIn | +0.363 |
orney | +0.317 |
gie | +0.315 |
leton | +0.307 |
Neg logit contributions | |
agers | -0.486 |
ework | -0.441 |
ardon | -0.433 |
apt | -0.426 |
lass | -0.425 |
Token | dominated |
Token ID | 13354 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
agers | +0.865 |
ework | +0.782 |
ardon | +0.766 |
apt | +0.754 |
lass | +0.752 |
Neg logit contributions | |
�� | -0.738 |
edIn | -0.724 |
orney | -0.638 |
gie | -0.635 |
leton | -0.620 |
Token | by |
Token ID | 416 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
agers | +1.746 |
ework | +1.563 |
ardon | +1.533 |
apt | +1.509 |
outs | +1.504 |
Neg logit contributions | |
�� | -1.679 |
edIn | -1.645 |
orney | -1.452 |
gie | -1.440 |
leton | -1.418 |
Token | Kik |
Token ID | 40571 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
agers | +0.591 |
ework | +0.531 |
ardon | +0.520 |
apt | +0.511 |
lass | +0.508 |
Neg logit contributions | |
�� | -0.569 |
edIn | -0.560 |
orney | -0.497 |
gie | -0.496 |
leton | -0.485 |
Token | uy |
Token ID | 4669 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
agers | +6.867 |
ework | +6.078 |
ardon | +6.054 |
apt | +6.019 |
outs | +5.963 |
Neg logit contributions | |
�� | -5.905 |
edIn | -5.677 |
�� | -4.949 |
gie | -4.854 |
�� | -4.838 |
Token | u |
Token ID | 84 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
agers | +0.095 |
ework | +0.084 |
ardon | +0.082 |
apt | +0.080 |
outs | +0.080 |
Neg logit contributions | |
�� | -0.115 |
edIn | -0.113 |
orney | -0.102 |
gie | -0.101 |
leton | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
agers | +1.060 |
ework | +0.951 |
ardon | +0.930 |
apt | +0.915 |
lass | +0.911 |
Neg logit contributions | |
�� | -1.037 |
edIn | -1.018 |
orney | -0.904 |
gie | -0.899 |
leton | -0.881 |
Token | Luo |
Token ID | 25956 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
agers | +0.137 |
ework | +0.123 |
ardon | +0.121 |
apt | +0.118 |
lass | +0.118 |
Neg logit contributions | |
�� | -0.127 |
edIn | -0.125 |
orney | -0.111 |
gie | -0.110 |
leton | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
agers | +0.372 |
ework | +0.335 |
ardon | +0.328 |
apt | +0.323 |
lass | +0.321 |
Neg logit contributions | |
�� | -0.344 |
edIn | -0.338 |
orney | -0.299 |
gie | -0.297 |
leton | -0.291 |
Token | East |
Token ID | 3687 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
agers | +0.091 |
ework | +0.083 |
ardon | +0.081 |
apt | +0.079 |
lass | +0.079 |
Neg logit contributions | |
�� | -0.082 |
edIn | -0.081 |
orney | -0.071 |
gie | -0.071 |
leton | -0.069 |
Token | Germany |
Token ID | 4486 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
agers | +1.742 |
ework | +1.571 |
ardon | +1.538 |
apt | +1.515 |
outs | +1.510 |
Neg logit contributions | |
�� | -1.544 |
edIn | -1.514 |
orney | -1.335 |
gie | -1.326 |
leton | -1.296 |
Token |
|
Token ID | 198 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
agers | +0.711 |
ework | +0.641 |
ardon | +0.628 |
apt | +0.619 |
outs | +0.616 |
Neg logit contributions | |
�� | -0.631 |
edIn | -0.619 |
orney | -0.546 |
gie | -0.542 |
leton | -0.531 |
Token |
|
Token ID | 198 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
�� | +0.620 |
edIn | +0.613 |
gie | +0.538 |
orney | +0.538 |
leton | +0.526 |
Neg logit contributions | |
agers | -0.734 |
ework | -0.665 |
ardon | -0.650 |
apt | -0.638 |
lass | -0.636 |
Token | BER |
Token ID | 13246 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
�� | +0.527 |
edIn | +0.523 |
gie | +0.460 |
orney | +0.458 |
leton | +0.448 |
Neg logit contributions | |
agers | -0.597 |
ework | -0.538 |
ardon | -0.528 |
apt | -0.517 |
lass | -0.516 |
Token | LIN |
Token ID | 34509 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
�� | +1.275 |
edIn | +1.250 |
gie | +1.165 |
orney | +1.145 |
leton | +1.140 |
Neg logit contributions | |
agers | -0.710 |
ework | -0.613 |
ardon | -0.589 |
lass | -0.574 |
outs | -0.573 |
Token | - |
Token ID | 532 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
agers | +5.583 |
ework | +4.867 |
ardon | +4.818 |
outs | +4.736 |
lass | +4.725 |
Neg logit contributions | |
�� | -6.792 |
edIn | -6.668 |
�� | -5.974 |
orney | -5.969 |
�� | -5.871 |
Token | The |
Token ID | 383 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
�� | +0.343 |
edIn | +0.338 |
gie | +0.295 |
orney | +0.295 |
leton | +0.288 |
Neg logit contributions | |
agers | -0.421 |
ework | -0.382 |
ardon | -0.374 |
apt | -0.369 |
lass | -0.367 |
Token | Associated |
Token ID | 10575 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
�� | +0.527 |
edIn | +0.519 |
orney | +0.456 |
gie | +0.455 |
leton | +0.443 |
Neg logit contributions | |
agers | -0.619 |
ework | -0.563 |
ardon | -0.549 |
apt | -0.543 |
outs | -0.539 |
Token | Press |
Token ID | 4332 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
�� | +0.805 |
edIn | +0.792 |
orney | +0.698 |
gie | +0.698 |
leton | +0.679 |
Neg logit contributions | |
agers | -0.984 |
ework | -0.893 |
ardon | -0.873 |
apt | -0.861 |
lass | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
agers | +2.484 |
ework | +2.221 |
ardon | +2.180 |
outs | +2.134 |
lass | +2.133 |
Neg logit contributions | |
�� | -2.449 |
edIn | -2.407 |
gie | -2.087 |
orney | -2.084 |
�� | -2.080 |
Token | � |
Token ID | 447 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
�� | +0.079 |
edIn | +0.077 |
orney | +0.068 |
gie | +0.068 |
leton | +0.066 |
Neg logit contributions | |
agers | -0.092 |
ework | -0.083 |
ardon | -0.081 |
apt | -0.080 |
outs | -0.080 |
Token | � |
Token ID | 247 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
�� | +0.260 |
edIn | +0.255 |
orney | +0.218 |
gie | +0.216 |
leton | +0.211 |
Neg logit contributions | |
agers | -0.412 |
ework | -0.378 |
ardon | -0.371 |
apt | -0.366 |
outs | -0.365 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
�� | +0.631 |
edIn | +0.621 |
orney | +0.543 |
gie | +0.542 |
leton | +0.529 |
Neg logit contributions | |
agers | -0.784 |
ework | -0.711 |
ardon | -0.696 |
apt | -0.685 |
lass | -0.683 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
�� | +0.686 |
edIn | +0.675 |
orney | +0.595 |
gie | +0.593 |
leton | +0.580 |
Neg logit contributions | |
agers | -0.786 |
ework | -0.709 |
ardon | -0.694 |
apt | -0.683 |
lass | -0.680 |
Token | BER |
Token ID | 13246 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
�� | +0.636 |
edIn | +0.628 |
gie | +0.548 |
orney | +0.547 |
leton | +0.534 |
Neg logit contributions | |
agers | -0.773 |
ework | -0.700 |
ardon | -0.686 |
apt | -0.674 |
lass | -0.673 |
Token | LIN |
Token ID | 34509 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
�� | +1.326 |
edIn | +1.298 |
gie | +1.221 |
orney | +1.192 |
leton | +1.183 |
Neg logit contributions | |
agers | -0.750 |
ework | -0.650 |
ardon | -0.623 |
apt | -0.604 |
outs | -0.603 |
Token | — |
Token ID | 851 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
agers | +5.460 |
ework | +4.840 |
ardon | +4.748 |
outs | +4.688 |
apt | +4.663 |
Neg logit contributions | |
�� | -6.501 |
edIn | -6.369 |
orney | -5.694 |
�� | -5.662 |
�� | -5.560 |
Token | The |
Token ID | 383 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
�� | +0.416 |
edIn | +0.407 |
orney | +0.354 |
gie | +0.352 |
leton | +0.344 |
Neg logit contributions | |
agers | -0.552 |
ework | -0.502 |
ardon | -0.492 |
apt | -0.486 |
lass | -0.483 |
Token | public |
Token ID | 1171 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
�� | +0.619 |
edIn | +0.609 |
orney | +0.535 |
gie | +0.535 |
leton | +0.522 |
Neg logit contributions | |
agers | -0.705 |
ework | -0.638 |
ardon | -0.625 |
apt | -0.615 |
outs | -0.611 |
Token | mood |
Token ID | 10038 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
agers | +0.904 |
ework | +0.816 |
ardon | +0.797 |
apt | +0.787 |
outs | +0.783 |
Neg logit contributions | |
�� | -0.802 |
edIn | -0.785 |
orney | -0.692 |
gie | -0.686 |
leton | -0.671 |
Token | is |
Token ID | 318 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
agers | +1.028 |
ework | +0.926 |
ardon | +0.906 |
outs | +0.892 |
apt | +0.892 |
Neg logit contributions | |
�� | -0.927 |
edIn | -0.904 |
orney | -0.797 |
gie | -0.788 |
�� | -0.773 |
Token | list |
Token ID | 1351 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
agers | +0.434 |
ework | +0.388 |
ardon | +0.379 |
apt | +0.373 |
lass | +0.371 |
Neg logit contributions | |
�� | -0.444 |
edIn | -0.436 |
orney | -0.388 |
gie | -0.386 |
leton | -0.379 |
Token | of |
Token ID | 286 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
�� | +0.036 |
edIn | +0.035 |
gie | +0.031 |
orney | +0.031 |
leton | +0.030 |
Neg logit contributions | |
agers | -0.036 |
ework | -0.033 |
ardon | -0.032 |
lass | -0.031 |
apt | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
agers | +0.494 |
ework | +0.443 |
ardon | +0.433 |
apt | +0.426 |
lass | +0.424 |
Neg logit contributions | |
�� | -0.488 |
edIn | -0.479 |
orney | -0.426 |
gie | -0.423 |
leton | -0.415 |
Token | ten |
Token ID | 3478 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
�� | +0.137 |
edIn | +0.134 |
orney | +0.118 |
gie | +0.118 |
leton | +0.116 |
Neg logit contributions | |
agers | -0.146 |
ework | -0.131 |
ardon | -0.128 |
apt | -0.126 |
lass | -0.126 |
Token | least |
Token ID | 1551 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
�� | +0.525 |
edIn | +0.514 |
gie | +0.454 |
orney | +0.453 |
leton | +0.442 |
Neg logit contributions | |
agers | -0.571 |
ework | -0.515 |
ardon | -0.504 |
apt | -0.496 |
lass | -0.494 |
Token | indebted |
Token ID | 37816 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
�� | +0.913 |
edIn | +0.902 |
gie | +0.800 |
orney | +0.795 |
leton | +0.785 |
Neg logit contributions | |
agers | -0.886 |
ework | -0.793 |
ardon | -0.778 |
lass | -0.760 |
apt | -0.756 |
Token | nations |
Token ID | 7027 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
agers | +5.241 |
ework | +4.596 |
outs | +4.485 |
apt | +4.408 |
lass | +4.407 |
Neg logit contributions | |
�� | -6.529 |
edIn | -6.382 |
�� | -5.933 |
orney | -5.919 |
leton | -5.705 |
Token | in |
Token ID | 287 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
agers | +1.154 |
ework | +1.037 |
ardon | +1.013 |
apt | +0.998 |
outs | +0.994 |
Neg logit contributions | |
�� | -1.112 |
edIn | -1.092 |
orney | -0.968 |
gie | -0.961 |
leton | -0.943 |
Token | the |
Token ID | 262 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
agers | +0.102 |
ework | +0.092 |
ardon | +0.089 |
apt | +0.087 |
lass | +0.087 |
Neg logit contributions | |
�� | -0.098 |
edIn | -0.096 |
gie | -0.085 |
orney | -0.085 |
leton | -0.083 |
Token | world |
Token ID | 995 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
agers | +0.153 |
ework | +0.138 |
ardon | +0.135 |
apt | +0.132 |
outs | +0.132 |
Neg logit contributions | |
�� | -0.137 |
edIn | -0.134 |
gie | -0.118 |
orney | -0.118 |
leton | -0.116 |
Token | that |
Token ID | 326 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
agers | +0.317 |
ework | +0.285 |
ardon | +0.279 |
apt | +0.274 |
lass | +0.274 |
Neg logit contributions | |
�� | -0.291 |
edIn | -0.286 |
orney | -0.253 |
gie | -0.253 |
leton | -0.246 |
Token | citizens |
Token ID | 4290 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
�� | +0.534 |
edIn | +0.528 |
gie | +0.464 |
orney | +0.464 |
leton | +0.457 |
Neg logit contributions | |
agers | -0.559 |
ework | -0.508 |
ardon | -0.493 |
apt | -0.487 |
lass | -0.484 |
Token | : |
Token ID | 25 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
agers | +0.527 |
ework | +0.476 |
ardon | +0.464 |
apt | +0.456 |
lass | +0.454 |
Neg logit contributions | |
�� | -0.488 |
edIn | -0.480 |
orney | -0.425 |
gie | -0.425 |
leton | -0.415 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
�� | +0.414 |
edIn | +0.407 |
orney | +0.360 |
gie | +0.357 |
leton | +0.350 |
Neg logit contributions | |
agers | -0.454 |
ework | -0.409 |
ardon | -0.400 |
apt | -0.393 |
lass | -0.391 |
Token | rain |
Token ID | 6290 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
agers | +0.300 |
ework | +0.270 |
ardon | +0.263 |
apt | +0.259 |
lass | +0.258 |
Neg logit contributions | |
�� | -0.292 |
edIn | -0.287 |
orney | -0.254 |
gie | -0.253 |
leton | -0.248 |
Token | water |
Token ID | 7050 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
agers | +1.569 |
ework | +1.410 |
ardon | +1.378 |
apt | +1.357 |
lass | +1.350 |
Neg logit contributions | |
�� | -1.496 |
edIn | -1.470 |
orney | -1.303 |
gie | -1.296 |
leton | -1.270 |
Token | runoff |
Token ID | 37536 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
agers | +3.211 |
ework | +2.880 |
ardon | +2.816 |
outs | +2.798 |
apt | +2.781 |
Neg logit contributions | |
�� | -3.030 |
edIn | -2.958 |
orney | -2.603 |
�� | -2.559 |
gie | -2.547 |
Token | from |
Token ID | 422 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
agers | +5.807 |
ework | +5.139 |
outs | +5.119 |
ardon | +5.053 |
out | +5.006 |
Neg logit contributions | |
�� | -6.123 |
edIn | -5.912 |
�� | -5.244 |
orney | -5.179 |
�� | -5.079 |
Token | the |
Token ID | 262 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
agers | +1.271 |
ework | +1.137 |
ardon | +1.113 |
apt | +1.096 |
outs | +1.092 |
Neg logit contributions | |
�� | -1.255 |
edIn | -1.230 |
orney | -1.095 |
gie | -1.086 |
leton | -1.064 |
Token | airst |
Token ID | 20253 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
agers | +0.124 |
ework | +0.112 |
ardon | +0.110 |
apt | +0.108 |
lass | +0.108 |
Neg logit contributions | |
�� | -0.107 |
edIn | -0.105 |
orney | -0.092 |
gie | -0.092 |
leton | -0.090 |
Token | rip |
Token ID | 5528 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
�� | +1.201 |
edIn | +1.186 |
orney | +1.080 |
gie | +1.075 |
leton | +1.055 |
Neg logit contributions | |
agers | -0.889 |
ework | -0.780 |
ardon | -0.757 |
apt | -0.743 |
outs | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
agers | +1.087 |
ework | +0.980 |
ardon | +0.959 |
outs | +0.945 |
apt | +0.944 |
Neg logit contributions | |
�� | -0.943 |
edIn | -0.920 |
orney | -0.808 |
gie | -0.798 |
�� | -0.785 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
agers | +0.229 |
ework | +0.206 |
ardon | +0.201 |
apt | +0.197 |
lass | +0.197 |
Neg logit contributions | |
�� | -0.235 |
edIn | -0.231 |
orney | -0.205 |
gie | -0.204 |
leton | -0.200 |
Token | villain |
Token ID | 16687 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
�� | +0.467 |
edIn | +0.458 |
orney | +0.407 |
gie | +0.405 |
leton | +0.397 |
Neg logit contributions | |
agers | -0.486 |
ework | -0.439 |
ardon | -0.428 |
apt | -0.421 |
lass | -0.419 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
�� | +0.031 |
edIn | +0.030 |
orney | +0.027 |
gie | +0.027 |
leton | +0.026 |
Neg logit contributions | |
agers | -0.032 |
ework | -0.029 |
ardon | -0.028 |
apt | -0.028 |
lass | -0.028 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
�� | +0.564 |
edIn | +0.552 |
orney | +0.491 |
gie | +0.487 |
leton | +0.477 |
Neg logit contributions | |
agers | -0.609 |
ework | -0.549 |
ardon | -0.535 |
apt | -0.528 |
lass | -0.525 |
Token | Ben |
Token ID | 3932 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
�� | +1.897 |
edIn | +1.847 |
orney | +1.655 |
gie | +1.648 |
leton | +1.609 |
Neg logit contributions | |
agers | -2.141 |
ework | -1.936 |
ardon | -1.887 |
lass | -1.857 |
apt | -1.853 |
Token | Mend |
Token ID | 20442 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
agers | +1.230 |
ework | +1.106 |
ardon | +1.082 |
apt | +1.066 |
lass | +1.061 |
Neg logit contributions | |
�� | -1.152 |
edIn | -1.131 |
orney | -1.001 |
gie | -0.995 |
leton | -0.974 |
Token | el |
Token ID | 417 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
agers | +4.907 |
ardon | +4.318 |
ework | +4.316 |
apt | +4.173 |
outs | +4.162 |
Neg logit contributions | |
�� | -6.911 |
edIn | -6.709 |
gie | -6.013 |
�� | -5.975 |
orney | -5.958 |
Token | so |
Token ID | 568 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
�� | +0.103 |
edIn | +0.101 |
orney | +0.088 |
gie | +0.087 |
�� | +0.085 |
Neg logit contributions | |
agers | -0.130 |
ework | -0.118 |
ardon | -0.116 |
apt | -0.114 |
lass | -0.114 |
Token | hn |
Token ID | 21116 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
agers | +0.302 |
ework | +0.270 |
ardon | +0.266 |
apt | +0.261 |
lass | +0.259 |
Neg logit contributions | |
�� | -0.353 |
edIn | -0.344 |
orney | -0.305 |
�� | -0.302 |
gie | -0.301 |
Token | ( |
Token ID | 357 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
�� | +0.982 |
edIn | +0.960 |
orney | +0.852 |
gie | +0.847 |
leton | +0.828 |
Neg logit contributions | |
agers | -1.195 |
ework | -1.087 |
ardon | -1.059 |
apt | -1.044 |
lass | -1.041 |
Token | � |
Token ID | 447 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
agers | +1.387 |
ework | +1.245 |
ardon | +1.215 |
apt | +1.195 |
lass | +1.190 |
Neg logit contributions | |
�� | -1.362 |
edIn | -1.339 |
orney | -1.188 |
gie | -1.182 |
leton | -1.159 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
agers | +0.214 |
ework | +0.191 |
ardon | +0.187 |
apt | +0.184 |
outs | +0.183 |
Neg logit contributions | |
�� | -0.222 |
edIn | -0.218 |
orney | -0.194 |
gie | -0.193 |
leton | -0.190 |
Token | criminal |
Token ID | 4301 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
agers | +0.177 |
ework | +0.159 |
ardon | +0.155 |
apt | +0.152 |
lass | +0.152 |
Neg logit contributions | |
�� | -0.182 |
edIn | -0.179 |
orney | -0.160 |
gie | -0.159 |
leton | -0.156 |
Token | acts |
Token ID | 6529 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +0.467 |
edIn | +0.458 |
orney | +0.410 |
gie | +0.409 |
leton | +0.400 |
Neg logit contributions | |
agers | -0.451 |
ework | -0.402 |
ardon | -0.394 |
lass | -0.388 |
apt | -0.387 |
Token | ( |
Token ID | 357 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
�� | +1.258 |
edIn | +1.235 |
orney | +1.092 |
gie | +1.088 |
leton | +1.061 |
Neg logit contributions | |
agers | -1.520 |
ework | -1.372 |
ardon | -1.345 |
lass | -1.326 |
apt | -1.315 |
Token | you |
Token ID | 5832 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
agers | +1.405 |
ework | +1.246 |
ardon | +1.216 |
apt | +1.197 |
outs | +1.190 |
Neg logit contributions | |
�� | -1.651 |
edIn | -1.623 |
orney | -1.456 |
gie | -1.446 |
leton | -1.421 |
Token | ven |
Token ID | 8710 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
agers | +1.107 |
ework | +1.003 |
ardon | +0.983 |
apt | +0.969 |
lass | +0.965 |
Neg logit contributions | |
�� | -0.886 |
edIn | -0.869 |
orney | -0.759 |
gie | -0.754 |
leton | -0.737 |
Token | al |
Token ID | 282 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
agers | +5.982 |
ework | +5.418 |
ardon | +5.218 |
apt | +5.157 |
outs | +5.140 |
Neg logit contributions | |
�� | -5.762 |
edIn | -5.585 |
�� | -4.862 |
�� | -4.861 |
gie | -4.821 |
Token | whore |
Token ID | 40107 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
�� | +1.237 |
edIn | +1.222 |
orney | +1.102 |
gie | +1.091 |
leton | +1.075 |
Neg logit contributions | |
agers | -1.163 |
ework | -1.037 |
ardon | -1.013 |
lass | -0.995 |
apt | -0.990 |
Token | - |
Token ID | 12 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
agers | +5.025 |
ework | +4.491 |
ardon | +4.385 |
apt | +4.384 |
outs | +4.359 |
Neg logit contributions | |
�� | -5.071 |
edIn | -4.993 |
orney | -4.352 |
�� | -4.307 |
�� | -4.237 |
Token | be |
Token ID | 1350 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
agers | +1.081 |
ework | +0.961 |
ardon | +0.938 |
apt | +0.922 |
outs | +0.918 |
Neg logit contributions | |
�� | -1.217 |
edIn | -1.196 |
orney | -1.070 |
gie | -1.064 |
leton | -1.045 |
Token | asts |
Token ID | 5773 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
agers | +0.857 |
ework | +0.768 |
ardon | +0.751 |
apt | +0.739 |
lass | +0.736 |
Neg logit contributions | |
�� | -0.853 |
edIn | -0.838 |
orney | -0.744 |
gie | -0.740 |
leton | -0.725 |
Token | s |
Token ID | 82 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
agers | +0.743 |
ework | +0.675 |
ardon | +0.662 |
apt | +0.653 |
lass | +0.650 |
Neg logit contributions | |
�� | -0.563 |
edIn | -0.552 |
orney | -0.480 |
gie | -0.477 |
leton | -0.466 |
Token | – |
Token ID | 784 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
�� | +0.479 |
edIn | +0.471 |
gie | +0.416 |
orney | +0.416 |
leton | +0.405 |
Neg logit contributions | |
agers | -0.542 |
ework | -0.489 |
ardon | -0.480 |
apt | -0.472 |
lass | -0.470 |
Token | in |
Token ID | 287 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
�� | +1.416 |
edIn | +1.389 |
gie | +1.231 |
orney | +1.228 |
leton | +1.199 |
Neg logit contributions | |
agers | -1.464 |
ework | -1.320 |
ardon | -1.292 |
lass | -1.264 |
outs | -1.258 |
Token | effect |
Token ID | 1245 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
agers | +0.396 |
ework | +0.355 |
ardon | +0.347 |
apt | +0.340 |
outs | +0.339 |
Neg logit contributions | |
�� | -0.406 |
edIn | -0.399 |
orney | -0.355 |
gie | -0.353 |
leton | -0.346 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
agers | +0.412 |
ework | +0.370 |
ardon | +0.361 |
apt | +0.355 |
lass | +0.354 |
Neg logit contributions | |
�� | -0.409 |
edIn | -0.401 |
orney | -0.356 |
gie | -0.355 |
leton | -0.348 |
Token | forc |
Token ID | 24686 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
agers | +0.454 |
ework | +0.406 |
ardon | +0.397 |
apt | +0.391 |
outs | +0.389 |
Neg logit contributions | |
�� | -0.461 |
edIn | -0.453 |
orney | -0.403 |
gie | -0.400 |
leton | -0.393 |
Token | ings |
Token ID | 654 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
agers | +2.544 |
ework | +2.035 |
outs | +1.812 |
ardon | +1.686 |
apt | +1.654 |
Neg logit contributions | |
�� | -9.333 |
edIn | -8.888 |
�� | -8.523 |
�� | -8.511 |
gie | -8.391 |
Token | that |
Token ID | 326 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
agers | +0.393 |
ework | +0.352 |
ardon | +0.344 |
apt | +0.338 |
lass | +0.337 |
Neg logit contributions | |
�� | -0.401 |
edIn | -0.394 |
orney | -0.351 |
gie | -0.350 |
leton | -0.343 |
Token | occur |
Token ID | 3051 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
agers | +0.123 |
ework | +0.111 |
ardon | +0.109 |
apt | +0.107 |
lass | +0.107 |
Neg logit contributions | |
�� | -0.107 |
edIn | -0.104 |
orney | -0.092 |
gie | -0.091 |
leton | -0.089 |
Token | because |
Token ID | 780 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
�� | +1.042 |
edIn | +1.025 |
orney | +0.906 |
gie | +0.903 |
leton | +0.884 |
Neg logit contributions | |
agers | -1.124 |
ework | -1.013 |
ardon | -0.990 |
apt | -0.972 |
lass | -0.970 |
Token | a |
Token ID | 257 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
agers | +1.860 |
ework | +1.658 |
ardon | +1.614 |
apt | +1.597 |
outs | +1.589 |
Neg logit contributions | |
�� | -1.934 |
edIn | -1.901 |
orney | -1.698 |
gie | -1.684 |
leton | -1.652 |
Token | . |
Token ID | 13 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
�� | +1.429 |
edIn | +1.406 |
orney | +1.240 |
gie | +1.235 |
leton | +1.213 |
Neg logit contributions | |
agers | -1.603 |
ework | -1.448 |
ardon | -1.413 |
apt | -1.393 |
lass | -1.386 |
Token | THE |
Token ID | 3336 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
�� | +0.662 |
edIn | +0.649 |
orney | +0.568 |
gie | +0.565 |
leton | +0.552 |
Neg logit contributions | |
agers | -0.828 |
ework | -0.751 |
ardon | -0.735 |
apt | -0.725 |
outs | -0.721 |
Token | R |
Token ID | 371 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
�� | +0.196 |
edIn | +0.192 |
orney | +0.169 |
gie | +0.168 |
leton | +0.164 |
Neg logit contributions | |
agers | -0.232 |
ework | -0.210 |
ardon | -0.206 |
apt | -0.203 |
lass | -0.202 |
Token | AC |
Token ID | 2246 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
agers | +2.274 |
ework | +2.037 |
ardon | +1.976 |
apt | +1.952 |
outs | +1.940 |
Neg logit contributions | |
�� | -2.358 |
edIn | -2.320 |
gie | -2.053 |
orney | -2.049 |
�� | -2.009 |
Token | ING |
Token ID | 2751 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
�� | +0.659 |
edIn | +0.649 |
orney | +0.563 |
gie | +0.562 |
leton | +0.552 |
Neg logit contributions | |
agers | -0.903 |
ework | -0.814 |
ardon | -0.805 |
apt | -0.793 |
outs | -0.791 |
Token | LIN |
Token ID | 43277 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
�� | +0.599 |
edIn | +0.585 |
gie | +0.519 |
orney | +0.516 |
leton | +0.506 |
Neg logit contributions | |
agers | -0.707 |
ework | -0.639 |
ardon | -0.627 |
apt | -0.617 |
lass | -0.612 |
Token | ES |
Token ID | 1546 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
agers | +4.652 |
ework | +4.185 |
outs | +3.908 |
lass | +3.835 |
apt | +3.824 |
Neg logit contributions | |
�� | -6.812 |
edIn | -6.703 |
orney | -6.114 |
�� | -6.048 |
gie | -5.982 |
Token | " |
Token ID | 366 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
�� | +0.029 |
edIn | +0.028 |
orney | +0.025 |
gie | +0.025 |
leton | +0.024 |
Neg logit contributions | |
agers | -0.033 |
ework | -0.030 |
ardon | -0.030 |
apt | -0.029 |
outs | -0.029 |
Token | It |
Token ID | 1026 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
agers | +1.292 |
ework | +1.167 |
ardon | +1.143 |
apt | +1.128 |
outs | +1.124 |
Neg logit contributions | |
�� | -1.095 |
edIn | -1.071 |
orney | -0.944 |
gie | -0.935 |
leton | -0.914 |
Token | 's |
Token ID | 338 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
agers | +0.974 |
ework | +0.888 |
ardon | +0.873 |
apt | +0.861 |
outs | +0.859 |
Neg logit contributions | |
�� | -0.652 |
edIn | -0.638 |
orney | -0.545 |
gie | -0.540 |
leton | -0.529 |
Token | all |
Token ID | 477 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
�� | +0.834 |
edIn | +0.819 |
gie | +0.737 |
orney | +0.736 |
leton | +0.717 |
Neg logit contributions | |
agers | -0.858 |
ework | -0.773 |
ardon | -0.754 |
apt | -0.744 |
lass | -0.738 |
Token | their |
Token ID | 511 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
agers | +1.524 |
ework | +1.363 |
ardon | +1.328 |
apt | +1.313 |
lass | +1.308 |
Neg logit contributions | |
�� | -1.526 |
edIn | -1.492 |
orney | -1.329 |
gie | -1.321 |
leton | -1.290 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
agers | +1.265 |
ework | +1.133 |
ardon | +1.108 |
apt | +1.093 |
lass | +1.090 |
Neg logit contributions | |
�� | -1.234 |
edIn | -1.205 |
orney | -1.070 |
gie | -1.063 |
leton | -1.038 |
Token | hit |
Token ID | 2277 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
�� | +0.229 |
edIn | +0.225 |
orney | +0.197 |
gie | +0.196 |
leton | +0.192 |
Neg logit contributions | |
agers | -0.279 |
ework | -0.253 |
ardon | -0.248 |
apt | -0.244 |
lass | -0.243 |
Token | a |
Token ID | 257 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
agers | +0.285 |
ework | +0.254 |
ardon | +0.248 |
apt | +0.243 |
outs | +0.242 |
Neg logit contributions | |
�� | -0.312 |
edIn | -0.308 |
orney | -0.275 |
gie | -0.274 |
leton | -0.269 |
Token | land |
Token ID | 1956 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
agers | +1.129 |
ework | +1.017 |
ardon | +0.988 |
apt | +0.981 |
lass | +0.980 |
Neg logit contributions | |
�� | -1.043 |
edIn | -1.019 |
orney | -0.901 |
gie | -0.894 |
�� | -0.875 |
Token | mine |
Token ID | 3810 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
agers | +0.095 |
ework | +0.083 |
ardon | +0.081 |
apt | +0.079 |
lass | +0.079 |
Neg logit contributions | |
�� | -0.139 |
edIn | -0.137 |
orney | -0.125 |
gie | -0.124 |
leton | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
agers | +5.342 |
ework | +4.795 |
ardon | +4.648 |
out | +4.646 |
lass | +4.622 |
Neg logit contributions | |
�� | -6.058 |
edIn | -5.794 |
�� | -5.301 |
orney | -5.121 |
�� | -4.971 |
Token | the |
Token ID | 262 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
agers | +0.632 |
ework | +0.568 |
ardon | +0.555 |
apt | +0.544 |
outs | +0.542 |
Neg logit contributions | |
�� | -0.622 |
edIn | -0.614 |
orney | -0.543 |
gie | -0.542 |
leton | -0.532 |
Token | same |
Token ID | 976 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
agers | +0.644 |
ework | +0.578 |
ardon | +0.565 |
apt | +0.557 |
lass | +0.554 |
Neg logit contributions | |
�� | -0.611 |
edIn | -0.600 |
orney | -0.532 |
gie | -0.529 |
leton | -0.518 |
Token | area |
Token ID | 1989 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
agers | +2.005 |
ework | +1.798 |
ardon | +1.742 |
lass | +1.730 |
outs | +1.721 |
Neg logit contributions | |
�� | -2.119 |
edIn | -2.049 |
orney | -1.835 |
gie | -1.818 |
�� | -1.799 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
agers | +0.170 |
ework | +0.154 |
ardon | +0.151 |
apt | +0.148 |
lass | +0.148 |
Neg logit contributions | |
�� | -0.144 |
edIn | -0.141 |
orney | -0.124 |
gie | -0.124 |
leton | -0.121 |
Token | ón |
Token ID | 18840 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
�� | +0.425 |
edIn | +0.419 |
orney | +0.373 |
gie | +0.370 |
leton | +0.361 |
Neg logit contributions | |
agers | -0.433 |
ework | -0.387 |
ardon | -0.377 |
apt | -0.371 |
lass | -0.371 |
Token | Un |
Token ID | 791 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
agers | +0.038 |
ework | +0.035 |
ardon | +0.034 |
apt | +0.034 |
lass | +0.034 |
Neg logit contributions | |
�� | -0.029 |
edIn | -0.028 |
orney | -0.024 |
gie | -0.024 |
leton | -0.024 |
Token | ilateral |
Token ID | 14796 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
agers | +1.825 |
ework | +1.630 |
ardon | +1.603 |
apt | +1.582 |
outs | +1.563 |
Neg logit contributions | |
�� | -1.978 |
edIn | -1.932 |
orney | -1.732 |
gie | -1.713 |
�� | -1.684 |
Token | de |
Token ID | 390 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
�� | +2.239 |
edIn | +2.219 |
gie | +1.938 |
orney | +1.927 |
leton | +1.879 |
Neg logit contributions | |
agers | -2.694 |
ework | -2.440 |
ardon | -2.368 |
apt | -2.337 |
lass | -2.337 |
Token | Ind |
Token ID | 1423 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
�� | +0.621 |
edIn | +0.607 |
orney | +0.514 |
gie | +0.512 |
leton | +0.496 |
Neg logit contributions | |
agers | -1.063 |
ework | -0.977 |
ardon | -0.956 |
apt | -0.945 |
lass | -0.941 |
Token | epend |
Token ID | 2690 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
agers | +1.120 |
ework | +0.990 |
ardon | +0.964 |
apt | +0.947 |
lass | +0.941 |
Neg logit contributions | |
�� | -1.385 |
edIn | -1.364 |
orney | -1.227 |
gie | -1.221 |
leton | -1.199 |
Token | encia |
Token ID | 29634 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
agers | +4.882 |
ework | +4.290 |
ardon | +4.210 |
apt | +4.181 |
outs | +4.133 |
Neg logit contributions | |
�� | -6.355 |
edIn | -6.082 |
�� | -5.632 |
�� | -5.543 |
orney | -5.426 |
Token | ) |
Token ID | 8 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
agers | +1.198 |
ework | +1.087 |
ardon | +1.066 |
apt | +1.052 |
outs | +1.047 |
Neg logit contributions | |
�� | -0.940 |
edIn | -0.921 |
orney | -0.805 |
gie | -0.798 |
leton | -0.781 |
Token | could |
Token ID | 714 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
agers | +1.088 |
ework | +0.985 |
ardon | +0.964 |
apt | +0.951 |
outs | +0.947 |
Neg logit contributions | |
�� | -0.905 |
edIn | -0.888 |
orney | -0.779 |
gie | -0.773 |
leton | -0.757 |
Token | be |
Token ID | 307 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
agers | +0.056 |
ework | +0.050 |
ardon | +0.049 |
apt | +0.048 |
lass | +0.048 |
Neg logit contributions | |
�� | -0.051 |
edIn | -0.050 |
orney | -0.044 |
gie | -0.044 |
leton | -0.043 |
Token | re |
Token ID | 302 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
�� | +0.387 |
edIn | +0.379 |
orney | +0.340 |
gie | +0.339 |
leton | +0.333 |
Neg logit contributions | |
agers | -0.352 |
ework | -0.314 |
ardon | -0.305 |
lass | -0.300 |
apt | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
agers | +1.183 |
ework | +1.059 |
ardon | +1.034 |
apt | +1.018 |
lass | +1.013 |
Neg logit contributions | |
�� | -1.220 |
edIn | -1.199 |
orney | -1.068 |
gie | -1.062 |
leton | -1.041 |
Token | compliment |
Token ID | 19370 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
agers | +0.480 |
ework | +0.427 |
ardon | +0.417 |
apt | +0.410 |
lass | +0.408 |
Neg logit contributions | |
�� | -0.548 |
edIn | -0.539 |
orney | -0.482 |
gie | -0.479 |
leton | -0.471 |
Token | , |
Token ID | 11 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
agers | +0.492 |
ework | +0.446 |
ardon | +0.437 |
apt | +0.431 |
lass | +0.429 |
Neg logit contributions | |
�� | -0.393 |
edIn | -0.386 |
orney | -0.338 |
gie | -0.336 |
leton | -0.328 |
Token | � |
Token ID | 447 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
�� | +0.114 |
edIn | +0.112 |
orney | +0.099 |
gie | +0.099 |
leton | +0.096 |
Neg logit contributions | |
agers | -0.128 |
ework | -0.115 |
ardon | -0.112 |
apt | -0.111 |
lass | -0.110 |
Token | � |
Token ID | 251 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
agers | +0.389 |
ework | +0.358 |
ardon | +0.355 |
apt | +0.347 |
lass | +0.347 |
Neg logit contributions | |
edIn | -0.233 |
�� | -0.233 |
gie | -0.195 |
orney | -0.195 |
leton | -0.190 |
Token | Rich |
Token ID | 3998 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
agers | +0.307 |
ework | +0.277 |
ardon | +0.270 |
apt | +0.266 |
lass | +0.265 |
Neg logit contributions | |
�� | -0.282 |
edIn | -0.277 |
orney | -0.245 |
gie | -0.243 |
leton | -0.238 |
Token | man |
Token ID | 805 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
agers | +5.819 |
ework | +5.141 |
ardon | +5.117 |
lass | +5.081 |
apt | +5.074 |
Neg logit contributions | |
�� | -5.261 |
edIn | -5.179 |
orney | -4.424 |
�� | -4.357 |
�� | -4.346 |
Token | tells |
Token ID | 4952 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
agers | +0.799 |
ework | +0.722 |
ardon | +0.709 |
apt | +0.699 |
outs | +0.697 |
Neg logit contributions | |
�� | -0.652 |
edIn | -0.639 |
orney | -0.558 |
gie | -0.553 |
leton | -0.542 |
Token | me |
Token ID | 502 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
agers | +1.198 |
ework | +1.073 |
ardon | +1.050 |
apt | +1.033 |
lass | +1.029 |
Neg logit contributions | |
�� | -1.178 |
edIn | -1.157 |
orney | -1.026 |
gie | -1.021 |
leton | -1.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
agers | +1.362 |
ework | +1.225 |
ardon | +1.198 |
apt | +1.180 |
outs | +1.175 |
Neg logit contributions | |
�� | -1.270 |
edIn | -1.247 |
orney | -1.103 |
gie | -1.096 |
leton | -1.074 |
Token | � |
Token ID | 564 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
agers | +0.319 |
ework | +0.289 |
ardon | +0.283 |
apt | +0.279 |
lass | +0.278 |
Neg logit contributions | |
�� | -0.261 |
edIn | -0.256 |
orney | -0.224 |
gie | -0.222 |
leton | -0.217 |
Token | involved |
Token ID | 2950 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
�� | +0.334 |
edIn | +0.328 |
orney | +0.290 |
gie | +0.289 |
leton | +0.282 |
Neg logit contributions | |
agers | -0.383 |
ework | -0.346 |
ardon | -0.339 |
apt | -0.334 |
lass | -0.332 |
Token | civilians |
Token ID | 10380 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
�� | +0.763 |
edIn | +0.759 |
gie | +0.676 |
orney | +0.673 |
leton | +0.660 |
Neg logit contributions | |
agers | -0.729 |
ework | -0.661 |
ardon | -0.645 |
apt | -0.632 |
lass | -0.628 |
Token | ," |
Token ID | 553 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
agers | +1.388 |
ework | +1.240 |
ardon | +1.210 |
apt | +1.190 |
lass | +1.185 |
Neg logit contributions | |
�� | -1.474 |
edIn | -1.449 |
orney | -1.293 |
gie | -1.287 |
leton | -1.262 |
Token | Tak |
Token ID | 15804 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
agers | +0.570 |
ework | +0.510 |
ardon | +0.499 |
apt | +0.490 |
lass | +0.488 |
Neg logit contributions | |
�� | -0.579 |
edIn | -0.569 |
orney | -0.507 |
gie | -0.504 |
leton | -0.494 |
Token | ashi |
Token ID | 12144 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
agers | +3.115 |
ework | +2.734 |
ardon | +2.689 |
outs | +2.669 |
apt | +2.655 |
Neg logit contributions | |
�� | -3.738 |
edIn | -3.614 |
�� | -3.191 |
gie | -3.184 |
orney | -3.178 |
Token | Kin |
Token ID | 16645 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
agers | +1.576 |
ework | +1.418 |
ardon | +1.392 |
outs | +1.375 |
apt | +1.373 |
Neg logit contributions | |
�� | -1.323 |
edIn | -1.286 |
orney | -1.125 |
gie | -1.118 |
�� | -1.097 |
Token | osh |
Token ID | 3768 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
agers | +5.058 |
ework | +4.429 |
ardon | +4.331 |
lass | +4.266 |
outs | +4.260 |
Neg logit contributions | |
�� | -6.176 |
edIn | -5.984 |
�� | -5.367 |
�� | -5.256 |
gie | -5.170 |
Token | ita |
Token ID | 5350 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
agers | +0.719 |
ework | +0.579 |
ardon | +0.556 |
apt | +0.537 |
outs | +0.534 |
Neg logit contributions | |
�� | -1.914 |
edIn | -1.891 |
orney | -1.740 |
gie | -1.731 |
�� | -1.713 |
Token | , |
Token ID | 11 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
agers | +1.449 |
ework | +1.300 |
ardon | +1.271 |
apt | +1.251 |
lass | +1.245 |
Neg logit contributions | |
�� | -1.404 |
edIn | -1.379 |
orney | -1.223 |
gie | -1.217 |
leton | -1.192 |
Token | chief |
Token ID | 4039 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
agers | +0.072 |
ework | +0.065 |
ardon | +0.064 |
apt | +0.063 |
lass | +0.063 |
Neg logit contributions | |
�� | -0.069 |
edIn | -0.068 |
orney | -0.060 |
gie | -0.060 |
leton | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
agers | +0.051 |
ework | +0.046 |
ardon | +0.045 |
apt | +0.044 |
lass | +0.044 |
Neg logit contributions | |
�� | -0.050 |
edIn | -0.049 |
orney | -0.044 |
gie | -0.044 |
leton | -0.042 |
Token | handle |
Token ID | 5412 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
agers | +0.148 |
ework | +0.133 |
ardon | +0.130 |
apt | +0.128 |
lass | +0.127 |
Neg logit contributions | |
�� | -0.139 |
edIn | -0.136 |
orney | -0.121 |
gie | -0.120 |
leton | -0.118 |
Token | for |
Token ID | 329 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
�� | +0.353 |
edIn | +0.346 |
gie | +0.308 |
orney | +0.308 |
leton | +0.301 |
Neg logit contributions | |
agers | -0.388 |
ework | -0.349 |
ardon | -0.341 |
apt | -0.336 |
lass | -0.335 |
Token | teams |
Token ID | 3466 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
�� | +0.794 |
edIn | +0.782 |
orney | +0.696 |
gie | +0.694 |
leton | +0.683 |
Neg logit contributions | |
agers | -0.782 |
ework | -0.705 |
ardon | -0.690 |
apt | -0.679 |
lass | -0.678 |
Token | that |
Token ID | 326 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
�� | +0.373 |
edIn | +0.366 |
gie | +0.329 |
orney | +0.328 |
leton | +0.321 |
Neg logit contributions | |
agers | -0.355 |
ework | -0.319 |
ardon | -0.310 |
apt | -0.306 |
lass | -0.305 |
Token | will |
Token ID | 481 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
�� | +0.603 |
edIn | +0.591 |
orney | +0.522 |
gie | +0.521 |
leton | +0.510 |
Neg logit contributions | |
agers | -0.678 |
ework | -0.611 |
ardon | -0.600 |
apt | -0.590 |
lass | -0.588 |
Token | load |
Token ID | 3440 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
agers | +0.404 |
ework | +0.362 |
ardon | +0.353 |
apt | +0.348 |
outs | +0.347 |
Neg logit contributions | |
�� | -0.401 |
edIn | -0.394 |
orney | -0.350 |
gie | -0.346 |
leton | -0.339 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
agers | +4.935 |
ework | +4.396 |
outs | +4.302 |
ardon | +4.244 |
apt | +4.201 |
Neg logit contributions | |
�� | -6.074 |
edIn | -5.884 |
orney | -5.322 |
gie | -5.200 |
�� | -5.144 |
Token | box |
Token ID | 3091 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
agers | +0.406 |
ework | +0.365 |
ardon | +0.357 |
apt | +0.352 |
lass | +0.350 |
Neg logit contributions | |
�� | -0.382 |
edIn | -0.375 |
orney | -0.332 |
gie | -0.331 |
leton | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
agers | +0.786 |
ework | +0.707 |
ardon | +0.692 |
apt | +0.681 |
lass | +0.678 |
Neg logit contributions | |
�� | -0.733 |
edIn | -0.720 |
orney | -0.637 |
gie | -0.635 |
leton | -0.621 |
Token | like |
Token ID | 588 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
agers | +0.206 |
ework | +0.185 |
ardon | +0.181 |
apt | +0.179 |
outs | +0.178 |
Neg logit contributions | |
�� | -0.187 |
edIn | -0.183 |
orney | -0.162 |
gie | -0.161 |
leton | -0.157 |
Token | Baylor |
Token ID | 28245 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
agers | +1.262 |
ework | +1.130 |
ardon | +1.107 |
apt | +1.089 |
outs | +1.087 |
Neg logit contributions | |
�� | -1.249 |
edIn | -1.226 |
orney | -1.088 |
gie | -1.078 |
leton | -1.055 |
Token | included |
Token ID | 3017 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
agers | +0.141 |
ework | +0.126 |
ardon | +0.124 |
apt | +0.122 |
lass | +0.121 |
Neg logit contributions | |
�� | -0.138 |
edIn | -0.135 |
orney | -0.120 |
gie | -0.120 |
leton | -0.117 |
Token | ( |
Token ID | 357 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
agers | +0.376 |
ework | +0.338 |
ardon | +0.330 |
apt | +0.325 |
outs | +0.324 |
Neg logit contributions | |
�� | -0.363 |
edIn | -0.357 |
orney | -0.316 |
gie | -0.314 |
leton | -0.308 |
Token | how |
Token ID | 4919 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
agers | +1.022 |
ework | +0.906 |
ardon | +0.883 |
apt | +0.867 |
outs | +0.863 |
Neg logit contributions | |
�� | -1.226 |
edIn | -1.206 |
orney | -1.083 |
gie | -1.077 |
leton | -1.058 |
Token | the |
Token ID | 262 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
�� | +0.347 |
edIn | +0.341 |
orney | +0.300 |
gie | +0.298 |
leton | +0.292 |
Neg logit contributions | |
agers | -0.395 |
ework | -0.357 |
ardon | -0.349 |
apt | -0.344 |
outs | -0.343 |
Token | nerds |
Token ID | 47088 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
agers | +0.744 |
ework | +0.663 |
ardon | +0.647 |
apt | +0.635 |
lass | +0.632 |
Neg logit contributions | |
�� | -0.829 |
edIn | -0.815 |
orney | -0.729 |
gie | -0.726 |
leton | -0.712 |
Token | revol |
Token ID | 35891 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
agers | +1.570 |
ework | +1.418 |
ardon | +1.388 |
apt | +1.371 |
outs | +1.362 |
Neg logit contributions | |
�� | -1.385 |
edIn | -1.361 |
orney | -1.199 |
gie | -1.175 |
�� | -1.167 |
Token | ted |
Token ID | 1513 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
agers | +4.094 |
ework | +3.489 |
apt | +3.415 |
ardon | +3.331 |
lass | +3.292 |
Neg logit contributions | |
�� | -6.895 |
edIn | -6.807 |
orney | -6.189 |
�� | -6.187 |
�� | -6.125 |
Token | !), |
Token ID | 26290 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
�� | +0.590 |
edIn | +0.579 |
orney | +0.519 |
gie | +0.519 |
leton | +0.508 |
Neg logit contributions | |
agers | -0.551 |
ework | -0.491 |
ardon | -0.477 |
lass | -0.469 |
apt | -0.468 |
Token | Ko |
Token ID | 17634 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
agers | +1.278 |
ework | +1.139 |
ardon | +1.116 |
apt | +1.103 |
outs | +1.097 |
Neg logit contributions | |
�� | -1.240 |
edIn | -1.219 |
orney | -1.079 |
gie | -1.073 |
�� | -1.054 |
Token | ji |
Token ID | 7285 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
agers | +1.069 |
ework | +0.941 |
ardon | +0.920 |
outs | +0.906 |
apt | +0.900 |
Neg logit contributions | |
�� | -1.325 |
edIn | -1.291 |
�� | -1.155 |
orney | -1.148 |
gie | -1.138 |
Token | took |
Token ID | 1718 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
�� | +0.636 |
edIn | +0.623 |
orney | +0.552 |
gie | +0.549 |
leton | +0.538 |
Neg logit contributions | |
agers | -0.685 |
ework | -0.616 |
ardon | -0.603 |
apt | -0.592 |
lass | -0.592 |
Token | feel |
Token ID | 1254 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
agers | +1.662 |
ework | +1.504 |
ardon | +1.464 |
apt | +1.448 |
outs | +1.442 |
Neg logit contributions | |
�� | -1.443 |
edIn | -1.414 |
orney | -1.235 |
gie | -1.214 |
�� | -1.203 |
Token | that |
Token ID | 326 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
�� | +0.018 |
edIn | +0.017 |
orney | +0.016 |
gie | +0.016 |
leton | +0.015 |
Neg logit contributions | |
agers | -0.016 |
ework | -0.015 |
ardon | -0.014 |
apt | -0.014 |
lass | -0.014 |
Token | there |
Token ID | 612 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
agers | +0.266 |
ework | +0.237 |
ardon | +0.231 |
apt | +0.228 |
outs | +0.227 |
Neg logit contributions | |
�� | -0.281 |
edIn | -0.276 |
orney | -0.246 |
gie | -0.245 |
leton | -0.240 |
Token | can |
Token ID | 460 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
�� | +0.655 |
edIn | +0.639 |
orney | +0.555 |
gie | +0.551 |
leton | +0.538 |
Neg logit contributions | |
agers | -0.921 |
ework | -0.838 |
ardon | -0.822 |
apt | -0.812 |
lass | -0.807 |
Token | be |
Token ID | 307 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
agers | +0.453 |
ework | +0.405 |
ardon | +0.395 |
apt | +0.389 |
lass | +0.388 |
Neg logit contributions | |
�� | -0.474 |
edIn | -0.465 |
orney | -0.415 |
gie | -0.413 |
leton | -0.405 |
Token | revol |
Token ID | 35891 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
agers | +0.486 |
ework | +0.434 |
ardon | +0.424 |
apt | +0.417 |
lass | +0.415 |
Neg logit contributions | |
�� | -0.515 |
edIn | -0.506 |
orney | -0.451 |
gie | -0.449 |
leton | -0.441 |
Token | ting |
Token ID | 889 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
agers | +4.268 |
ework | +3.615 |
outs | +3.519 |
apt | +3.493 |
out | +3.466 |
Neg logit contributions | |
�� | -6.801 |
edIn | -6.646 |
�� | -6.078 |
�� | -6.066 |
orney | -5.970 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
�� | +0.566 |
edIn | +0.556 |
orney | +0.495 |
gie | +0.494 |
leton | +0.485 |
Neg logit contributions | |
agers | -0.557 |
ework | -0.499 |
ardon | -0.489 |
apt | -0.479 |
lass | -0.477 |
Token | terrifying |
Token ID | 17623 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
agers | +0.171 |
ework | +0.153 |
ardon | +0.149 |
apt | +0.146 |
lass | +0.146 |
Neg logit contributions | |
�� | -0.186 |
edIn | -0.183 |
orney | -0.163 |
gie | -0.163 |
leton | -0.160 |
Token | consequences |
Token ID | 6948 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
�� | +0.757 |
edIn | +0.741 |
orney | +0.657 |
gie | +0.653 |
leton | +0.643 |
Neg logit contributions | |
agers | -0.825 |
ework | -0.744 |
ardon | -0.731 |
apt | -0.715 |
lass | -0.715 |
Token | for |
Token ID | 329 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
�� | +0.156 |
edIn | +0.153 |
gie | +0.136 |
orney | +0.135 |
leton | +0.133 |
Neg logit contributions | |
agers | -0.174 |
ework | -0.157 |
ardon | -0.154 |
apt | -0.151 |
lass | -0.151 |
Token | remaining |
Token ID | 5637 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
agers | +0.199 |
ework | +0.180 |
ardon | +0.176 |
apt | +0.174 |
outs | +0.173 |
Neg logit contributions | |
�� | -0.167 |
edIn | -0.163 |
orney | -0.143 |
gie | -0.142 |
leton | -0.139 |
Token | mission |
Token ID | 4365 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
agers | +0.053 |
ework | +0.048 |
ardon | +0.047 |
apt | +0.047 |
outs | +0.046 |
Neg logit contributions | |
�� | -0.045 |
edIn | -0.044 |
orney | -0.039 |
gie | -0.039 |
�� | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
�� | +2.805 |
edIn | +2.759 |
gie | +2.419 |
orney | +2.408 |
leton | +2.349 |
Neg logit contributions | |
agers | -3.325 |
ework | -2.987 |
ardon | -2.942 |
lass | -2.907 |
apt | -2.887 |
Token | including |
Token ID | 1390 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
agers | +0.080 |
ework | +0.072 |
ardon | +0.071 |
apt | +0.070 |
outs | +0.069 |
Neg logit contributions | |
�� | -0.074 |
edIn | -0.073 |
orney | -0.064 |
gie | -0.064 |
leton | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
�� | +0.192 |
edIn | +0.188 |
orney | +0.167 |
gie | +0.166 |
leton | +0.163 |
Neg logit contributions | |
agers | -0.198 |
ework | -0.178 |
ardon | -0.174 |
apt | -0.171 |
outs | -0.171 |
Token | Comet |
Token ID | 36238 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
agers | +0.126 |
ework | +0.113 |
ardon | +0.111 |
apt | +0.110 |
outs | +0.109 |
Neg logit contributions | |
�� | -0.111 |
edIn | -0.109 |
orney | -0.096 |
gie | -0.095 |
leton | -0.093 |
Token | Bor |
Token ID | 12182 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
�� | +5.404 |
edIn | +5.333 |
gie | +4.772 |
orney | +4.642 |
leton | +4.607 |
Neg logit contributions | |
agers | -5.924 |
ework | -5.380 |
ardon | -5.284 |
lass | -5.234 |
apt | -5.137 |
Token | rell |
Token ID | 11252 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
�� | +0.021 |
edIn | +0.021 |
orney | +0.018 |
gie | +0.018 |
leton | +0.018 |
Neg logit contributions | |
agers | -0.017 |
ework | -0.015 |
ardon | -0.015 |
apt | -0.015 |
lass | -0.015 |
Token | y |
Token ID | 88 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
agers | +0.499 |
ework | +0.435 |
ardon | +0.420 |
apt | +0.413 |
outs | +0.412 |
Neg logit contributions | |
�� | -0.755 |
edIn | -0.740 |
orney | -0.667 |
�� | -0.661 |
gie | -0.661 |
Token | encounter |
Token ID | 8791 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
�� | +1.666 |
edIn | +1.639 |
gie | +1.429 |
orney | +1.425 |
leton | +1.387 |
Neg logit contributions | |
agers | -2.130 |
ework | -1.931 |
ardon | -1.893 |
lass | -1.865 |
apt | -1.863 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
�� | +2.218 |
edIn | +2.207 |
gie | +1.934 |
orney | +1.923 |
leton | +1.870 |
Neg logit contributions | |
agers | -2.704 |
ework | -2.438 |
ardon | -2.392 |
lass | -2.370 |
apt | -2.352 |
Token | on |
Token ID | 319 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
�� | +1.574 |
edIn | +1.549 |
orney | +1.367 |
gie | +1.359 |
leton | +1.328 |
Neg logit contributions | |
agers | -1.902 |
ework | -1.720 |
ardon | -1.686 |
lass | -1.658 |
apt | -1.658 |
Token | his |
Token ID | 465 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
�� | +0.304 |
edIn | +0.299 |
orney | +0.265 |
gie | +0.263 |
leton | +0.258 |
Neg logit contributions | |
agers | -0.318 |
ework | -0.286 |
ardon | -0.279 |
apt | -0.275 |
outs | -0.274 |
Token | associations |
Token ID | 15814 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
agers | +1.423 |
ework | +1.275 |
ardon | +1.248 |
outs | +1.230 |
apt | +1.230 |
Neg logit contributions | |
�� | -1.401 |
edIn | -1.373 |
orney | -1.213 |
gie | -1.201 |
�� | -1.184 |
Token | with |
Token ID | 351 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
�� | +0.142 |
edIn | +0.139 |
orney | +0.123 |
gie | +0.122 |
leton | +0.119 |
Neg logit contributions | |
agers | -0.165 |
ework | -0.149 |
ardon | -0.146 |
apt | -0.144 |
lass | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
�� | +0.252 |
edIn | +0.248 |
orney | +0.221 |
gie | +0.220 |
leton | +0.215 |
Neg logit contributions | |
agers | -0.242 |
ework | -0.216 |
ardon | -0.211 |
apt | -0.208 |
lass | -0.207 |
Token | fossil |
Token ID | 12584 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
�� | +0.335 |
edIn | +0.329 |
orney | +0.295 |
gie | +0.293 |
leton | +0.288 |
Neg logit contributions | |
agers | -0.300 |
ework | -0.267 |
ardon | -0.261 |
apt | -0.256 |
lass | -0.255 |
Token | fuel |
Token ID | 5252 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
�� | +2.967 |
edIn | +2.876 |
gie | +2.528 |
orney | +2.500 |
leton | +2.466 |
Neg logit contributions | |
agers | -4.833 |
ework | -4.459 |
ardon | -4.382 |
lass | -4.358 |
apt | -4.318 |
Token | industry |
Token ID | 2831 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
agers | +0.565 |
ework | +0.501 |
ardon | +0.488 |
apt | +0.480 |
outs | +0.477 |
Neg logit contributions | |
�� | -0.668 |
edIn | -0.658 |
orney | -0.590 |
gie | -0.586 |
leton | -0.576 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
agers | +0.620 |
ework | +0.561 |
ardon | +0.549 |
apt | +0.543 |
outs | +0.541 |
Neg logit contributions | |
�� | -0.532 |
edIn | -0.521 |
orney | -0.455 |
gie | -0.452 |
leton | -0.443 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
�� | +0.062 |
edIn | +0.061 |
orney | +0.053 |
gie | +0.053 |
leton | +0.052 |
Neg logit contributions | |
agers | -0.072 |
ework | -0.065 |
ardon | -0.064 |
apt | -0.063 |
lass | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
�� | +0.170 |
edIn | +0.167 |
orney | +0.148 |
gie | +0.147 |
leton | +0.144 |
Neg logit contributions | |
agers | -0.194 |
ework | -0.175 |
ardon | -0.171 |
apt | -0.169 |
lass | -0.168 |
Token | Force |
Token ID | 5221 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
�� | +3.024 |
edIn | +2.934 |
gie | +2.479 |
leton | +2.438 |
orney | +2.397 |
Neg logit contributions | |
agers | -6.756 |
ework | -6.162 |
ardon | -6.058 |
apt | -6.015 |
lass | -5.954 |
Token | Base |
Token ID | 7308 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
agers | +0.688 |
ework | +0.636 |
ardon | +0.627 |
apt | +0.620 |
outs | +0.618 |
Neg logit contributions | |
�� | -0.324 |
edIn | -0.314 |
orney | -0.259 |
gie | -0.255 |
leton | -0.246 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
�� | +2.427 |
edIn | +2.384 |
gie | +2.105 |
orney | +2.099 |
leton | +2.059 |
Neg logit contributions | |
agers | -2.711 |
ework | -2.437 |
ardon | -2.380 |
apt | -2.342 |
lass | -2.337 |
Token | Cal |
Token ID | 2199 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
�� | +0.256 |
edIn | +0.250 |
orney | +0.219 |
gie | +0.216 |
leton | +0.211 |
Neg logit contributions | |
agers | -0.334 |
ework | -0.303 |
ardon | -0.298 |
apt | -0.294 |
outs | -0.292 |
Token | .: |
Token ID | 11207 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
�� | +0.737 |
edIn | +0.725 |
orney | +0.647 |
gie | +0.643 |
leton | +0.632 |
Neg logit contributions | |
agers | -0.704 |
ework | -0.628 |
ardon | -0.614 |
apt | -0.602 |
lass | -0.599 |
Token | Air |
Token ID | 3701 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
agers | +0.194 |
ework | +0.177 |
ardon | +0.174 |
apt | +0.171 |
outs | +0.171 |
Neg logit contributions | |
�� | -0.139 |
edIn | -0.136 |
orney | -0.118 |
gie | -0.117 |
�� | -0.114 |
Token | Force |
Token ID | 5221 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
�� | +3.306 |
edIn | +3.193 |
gie | +2.800 |
leton | +2.772 |
orney | +2.702 |
Neg logit contributions | |
agers | -5.474 |
ework | -4.943 |
ardon | -4.880 |
apt | -4.796 |
lass | -4.746 |
Token | Flight |
Token ID | 13365 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
agers | +0.433 |
ework | +0.393 |
ardon | +0.385 |
apt | +0.380 |
outs | +0.379 |
Neg logit contributions | |
�� | -0.329 |
edIn | -0.323 |
orney | -0.281 |
gie | -0.278 |
leton | -0.272 |
Token | Test |
Token ID | 6208 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
�� | +4.101 |
edIn | +4.010 |
gie | +3.470 |
orney | +3.436 |
leton | +3.419 |
Neg logit contributions | |
agers | -6.385 |
ework | -5.826 |
ardon | -5.688 |
apt | -5.650 |
lass | -5.555 |
Token | Center |
Token ID | 3337 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
�� | +1.357 |
edIn | +1.345 |
orney | +1.158 |
gie | +1.149 |
leton | +1.126 |
Neg logit contributions | |
agers | -2.151 |
ework | -1.971 |
ardon | -1.939 |
apt | -1.906 |
lass | -1.902 |
Token | History |
Token ID | 7443 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
�� | +3.363 |
edIn | +3.286 |
gie | +2.938 |
orney | +2.879 |
leton | +2.877 |
Neg logit contributions | |
agers | -3.958 |
ework | -3.587 |
ardon | -3.516 |
lass | -3.480 |
apt | -3.430 |
Token | 3 |
Token ID | 513 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
agers | +4.241 |
ardon | +3.816 |
ework | +3.801 |
lass | +3.738 |
outs | +3.708 |
Neg logit contributions | |
�� | -3.710 |
edIn | -3.587 |
orney | -3.171 |
gie | -3.114 |
leton | -3.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
�� | +0.859 |
edIn | +0.833 |
orney | +0.726 |
gie | +0.723 |
leton | +0.704 |
Neg logit contributions | |
agers | -1.202 |
ework | -1.095 |
ardon | -1.066 |
apt | -1.055 |
outs | -1.049 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
�� | +0.718 |
edIn | +0.704 |
orney | +0.618 |
gie | +0.616 |
leton | +0.602 |
Neg logit contributions | |
agers | -0.912 |
ework | -0.827 |
ardon | -0.808 |
apt | -0.797 |
lass | -0.796 |
Token | - |
Token ID | 12 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
�� | +1.384 |
edIn | +1.331 |
orney | +1.163 |
gie | +1.157 |
leton | +1.146 |
Neg logit contributions | |
agers | -1.954 |
ework | -1.771 |
ardon | -1.726 |
apt | -1.719 |
lass | -1.698 |
Token | liter |
Token ID | 17201 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
�� | +0.264 |
edIn | +0.259 |
orney | +0.236 |
gie | +0.236 |
leton | +0.232 |
Neg logit contributions | |
agers | -0.168 |
ework | -0.146 |
ardon | -0.140 |
apt | -0.138 |
lass | -0.136 |
Token | Eco |
Token ID | 38719 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
�� | +0.661 |
edIn | +0.650 |
orney | +0.566 |
gie | +0.564 |
leton | +0.553 |
Neg logit contributions | |
agers | -0.851 |
ework | -0.776 |
ardon | -0.751 |
apt | -0.748 |
outs | -0.742 |
Token | Boost |
Token ID | 45686 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
�� | +2.735 |
edIn | +2.643 |
gie | +2.119 |
leton | +2.024 |
orney | +2.020 |
Neg logit contributions | |
agers | -7.729 |
ework | -7.258 |
ardon | -7.002 |
outs | -6.949 |
lass | -6.912 |
Token | ® |
Token ID | 7461 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
�� | +1.070 |
edIn | +1.045 |
orney | +0.908 |
gie | +0.906 |
leton | +0.888 |
Neg logit contributions | |
agers | -1.443 |
ework | -1.322 |
apt | -1.273 |
ardon | -1.272 |
outs | -1.268 |
Token | engine |
Token ID | 3113 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
�� | +2.453 |
edIn | +2.413 |
gie | +2.184 |
orney | +2.165 |
leton | +2.144 |
Neg logit contributions | |
agers | -1.943 |
ework | -1.750 |
outs | -1.649 |
apt | -1.642 |
ardon | -1.637 |
Token | that |
Token ID | 326 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
�� | +0.078 |
edIn | +0.077 |
gie | +0.069 |
orney | +0.068 |
leton | +0.066 |
Neg logit contributions | |
agers | -0.093 |
ework | -0.084 |
ardon | -0.081 |
apt | -0.081 |
lass | -0.080 |
Token | produces |
Token ID | 11073 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
�� | +0.402 |
edIn | +0.394 |
orney | +0.344 |
gie | +0.343 |
leton | +0.333 |
Neg logit contributions | |
agers | -0.545 |
ework | -0.497 |
ardon | -0.486 |
apt | -0.481 |
lass | -0.479 |
Token | Ar |
Token ID | 943 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
�� | +0.502 |
edIn | +0.493 |
orney | +0.432 |
gie | +0.430 |
leton | +0.421 |
Neg logit contributions | |
agers | -0.602 |
ework | -0.544 |
ardon | -0.533 |
apt | -0.525 |
lass | -0.523 |
Token | is |
Token ID | 271 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
agers | +1.524 |
ework | +1.346 |
ardon | +1.313 |
apt | +1.293 |
outs | +1.284 |
Neg logit contributions | |
�� | -1.837 |
edIn | -1.803 |
orney | -1.616 |
gie | -1.605 |
�� | -1.575 |
Token | with |
Token ID | 351 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
�� | +0.643 |
edIn | +0.631 |
orney | +0.559 |
gie | +0.556 |
leton | +0.544 |
Neg logit contributions | |
agers | -0.685 |
ework | -0.616 |
ardon | -0.603 |
apt | -0.593 |
lass | -0.591 |
Token | fellow |
Token ID | 5891 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
�� | +0.673 |
edIn | +0.661 |
orney | +0.581 |
gie | +0.580 |
leton | +0.567 |
Neg logit contributions | |
agers | -0.770 |
ework | -0.696 |
ardon | -0.680 |
apt | -0.670 |
lass | -0.667 |
Token | American |
Token ID | 1605 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +0.004 |
edIn | +0.004 |
orney | +0.003 |
gie | +0.003 |
leton | +0.003 |
Neg logit contributions | |
agers | -0.005 |
ework | -0.004 |
ardon | -0.004 |
apt | -0.004 |
outs | -0.004 |
Token | Eddie |
Token ID | 19478 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
�� | +0.309 |
edIn | +0.303 |
orney | +0.267 |
gie | +0.264 |
leton | +0.259 |
Neg logit contributions | |
agers | -0.359 |
ework | -0.324 |
ardon | -0.317 |
apt | -0.313 |
outs | -0.312 |
Token | Johnson |
Token ID | 5030 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
�� | +3.847 |
edIn | +3.724 |
gie | +3.296 |
orney | +3.282 |
leton | +3.252 |
Neg logit contributions | |
agers | -4.708 |
ework | -4.299 |
ardon | -4.214 |
apt | -4.110 |
lass | -4.110 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
�� | +1.841 |
edIn | +1.801 |
orney | +1.597 |
gie | +1.596 |
leton | +1.558 |
Neg logit contributions | |
agers | -2.023 |
ework | -1.826 |
ardon | -1.788 |
lass | -1.757 |
apt | -1.753 |
Token | he |
Token ID | 339 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
�� | +0.511 |
edIn | +0.502 |
orney | +0.444 |
gie | +0.442 |
leton | +0.432 |
Neg logit contributions | |
agers | -0.549 |
ework | -0.494 |
ardon | -0.483 |
apt | -0.476 |
lass | -0.474 |
Token | returned |
Token ID | 4504 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
�� | +0.019 |
edIn | +0.018 |
orney | +0.016 |
gie | +0.016 |
�� | +0.015 |
Neg logit contributions | |
agers | -0.024 |
ework | -0.021 |
ardon | -0.021 |
apt | -0.021 |
outs | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
�� | +0.840 |
edIn | +0.825 |
orney | +0.725 |
gie | +0.722 |
leton | +0.706 |
Neg logit contributions | |
agers | -0.980 |
ework | -0.885 |
ardon | -0.867 |
apt | -0.853 |
lass | -0.851 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
�� | +0.357 |
edIn | +0.351 |
orney | +0.314 |
gie | +0.313 |
leton | +0.305 |
Neg logit contributions | |
agers | -0.359 |
ework | -0.322 |
ardon | -0.314 |
apt | -0.311 |
lass | -0.309 |
Token | punishment |
Token ID | 9837 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
�� | +0.322 |
edIn | +0.316 |
orney | +0.282 |
gie | +0.281 |
leton | +0.274 |
Neg logit contributions | |
agers | -0.317 |
ework | -0.285 |
ardon | -0.278 |
apt | -0.274 |
lass | -0.273 |
Token | unusually |
Token ID | 23708 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
�� | +0.002 |
edIn | +0.002 |
orney | +0.002 |
gie | +0.002 |
leton | +0.002 |
Neg logit contributions | |
agers | -0.002 |
ework | -0.002 |
ardon | -0.002 |
apt | -0.002 |
lass | -0.002 |
Token | harsh |
Token ID | 11859 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
�� | +0.430 |
edIn | +0.422 |
orney | +0.375 |
gie | +0.375 |
leton | +0.366 |
Neg logit contributions | |
agers | -0.465 |
ework | -0.419 |
ardon | -0.410 |
apt | -0.404 |
lass | -0.402 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
agers | +0.104 |
ework | +0.093 |
ardon | +0.091 |
apt | +0.090 |
lass | +0.090 |
Neg logit contributions | |
�� | -0.094 |
edIn | -0.093 |
orney | -0.082 |
gie | -0.082 |
leton | -0.080 |
Token | but |
Token ID | 475 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
�� | +0.238 |
edIn | +0.234 |
orney | +0.207 |
gie | +0.205 |
leton | +0.201 |
Neg logit contributions | |
agers | -0.276 |
ework | -0.249 |
ardon | -0.243 |
apt | -0.240 |
lass | -0.239 |
Token | it |
Token ID | 340 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
�� | +1.159 |
edIn | +1.146 |
orney | +1.024 |
gie | +1.018 |
leton | +0.993 |
Neg logit contributions | |
agers | -1.165 |
ework | -1.050 |
ardon | -1.023 |
apt | -1.009 |
lass | -1.001 |
Token | is |
Token ID | 318 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
�� | +0.258 |
edIn | +0.253 |
orney | +0.221 |
gie | +0.220 |
leton | +0.215 |
Neg logit contributions | |
agers | -0.335 |
ework | -0.304 |
ardon | -0.298 |
apt | -0.294 |
lass | -0.293 |
Token | an |
Token ID | 281 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
�� | +0.327 |
edIn | +0.321 |
orney | +0.288 |
gie | +0.287 |
leton | +0.280 |
Neg logit contributions | |
agers | -0.326 |
ework | -0.292 |
ardon | -0.285 |
apt | -0.281 |
lass | -0.280 |
Token | odd |
Token ID | 5629 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
agers | +0.074 |
ework | +0.066 |
ardon | +0.064 |
apt | +0.063 |
lass | +0.063 |
Neg logit contributions | |
�� | -0.085 |
edIn | -0.084 |
orney | -0.075 |
gie | -0.075 |
leton | -0.073 |
Token | circumstance |
Token ID | 25179 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
�� | +2.082 |
edIn | +2.049 |
gie | +1.846 |
orney | +1.840 |
leton | +1.802 |
Neg logit contributions | |
agers | -1.946 |
ework | -1.730 |
ardon | -1.684 |
apt | -1.667 |
lass | -1.666 |
Token | R |
Token ID | 49 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
agers | +0.153 |
ework | +0.134 |
ardon | +0.130 |
apt | +0.128 |
lass | +0.127 |
Neg logit contributions | |
�� | -0.211 |
edIn | -0.208 |
orney | -0.188 |
gie | -0.187 |
leton | -0.184 |
Token | reads |
Token ID | 9743 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
agers | +2.517 |
ework | +2.277 |
ardon | +2.226 |
apt | +2.219 |
outs | +2.206 |
Neg logit contributions | |
�� | -2.069 |
edIn | -2.014 |
orney | -1.771 |
gie | -1.743 |
�� | -1.734 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
agers | +2.566 |
ework | +2.302 |
ardon | +2.261 |
outs | +2.240 |
apt | +2.237 |
Neg logit contributions | |
�� | -2.621 |
edIn | -2.566 |
orney | -2.291 |
gie | -2.245 |
�� | -2.234 |
Token | images |
Token ID | 4263 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
agers | +0.389 |
ework | +0.350 |
ardon | +0.343 |
apt | +0.339 |
outs | +0.338 |
Neg logit contributions | |
�� | -0.352 |
edIn | -0.345 |
orney | -0.305 |
gie | -0.302 |
leton | -0.296 |
Token | just |
Token ID | 655 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
�� | +0.087 |
edIn | +0.085 |
gie | +0.076 |
orney | +0.076 |
leton | +0.074 |
Neg logit contributions | |
agers | -0.092 |
ework | -0.082 |
ardon | -0.081 |
apt | -0.079 |
lass | -0.079 |
Token | fine |
Token ID | 3734 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
�� | +0.279 |
edIn | +0.274 |
orney | +0.244 |
gie | +0.244 |
leton | +0.239 |
Neg logit contributions | |
agers | -0.262 |
ework | -0.233 |
ardon | -0.228 |
apt | -0.224 |
lass | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
�� | +0.854 |
edIn | +0.840 |
gie | +0.745 |
orney | +0.738 |
leton | +0.724 |
Neg logit contributions | |
agers | -0.952 |
ework | -0.856 |
ardon | -0.838 |
lass | -0.824 |
apt | -0.822 |
Token | but |
Token ID | 475 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
agers | +0.321 |
ework | +0.292 |
ardon | +0.286 |
apt | +0.282 |
outs | +0.281 |
Neg logit contributions | |
�� | -0.257 |
edIn | -0.252 |
orney | -0.221 |
gie | -0.219 |
leton | -0.214 |
Token | doesn |
Token ID | 1595 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
�� | +0.473 |
edIn | +0.466 |
orney | +0.413 |
gie | +0.411 |
leton | +0.402 |
Neg logit contributions | |
agers | -0.494 |
ework | -0.444 |
ardon | -0.433 |
apt | -0.426 |
lass | -0.425 |
Token | � |
Token ID | 447 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
�� | +1.354 |
edIn | +1.344 |
gie | +1.178 |
orney | +1.174 |
leton | +1.154 |
Neg logit contributions | |
agers | -1.817 |
ework | -1.656 |
ardon | -1.619 |
lass | -1.595 |
apt | -1.584 |
Token | � |
Token ID | 247 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
agers | +0.536 |
ework | +0.487 |
ardon | +0.480 |
apt | +0.471 |
lass | +0.468 |
Neg logit contributions | |
�� | -0.403 |
edIn | -0.402 |
orney | -0.347 |
gie | -0.347 |
leton | -0.339 |
Token | it |
Token ID | 340 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
agers | +0.069 |
ework | +0.061 |
ardon | +0.060 |
apt | +0.059 |
outs | +0.058 |
Neg logit contributions | |
�� | -0.082 |
edIn | -0.080 |
orney | -0.072 |
gie | -0.072 |
leton | -0.071 |
Token | like |
Token ID | 588 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
agers | +0.570 |
ework | +0.514 |
ardon | +0.503 |
apt | +0.496 |
lass | +0.494 |
Neg logit contributions | |
�� | -0.513 |
edIn | -0.504 |
orney | -0.443 |
gie | -0.439 |
leton | -0.430 |
Token | 36 |
Token ID | 4570 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
agers | +1.061 |
ework | +0.946 |
ardon | +0.923 |
apt | +0.910 |
lass | +0.905 |
Neg logit contributions | |
�� | -1.121 |
edIn | -1.102 |
orney | -0.982 |
gie | -0.976 |
leton | -0.957 |
Token | se |
Token ID | 384 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
�� | +0.180 |
edIn | +0.177 |
orney | +0.156 |
gie | +0.155 |
leton | +0.152 |
Neg logit contributions | |
agers | -0.199 |
ework | -0.179 |
ardon | -0.175 |
apt | -0.173 |
outs | -0.172 |
Token | ag |
Token ID | 363 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
agers | +0.690 |
ework | +0.619 |
ardon | +0.604 |
apt | +0.595 |
lass | +0.592 |
Neg logit contributions | |
�� | -0.687 |
edIn | -0.675 |
orney | -0.600 |
gie | -0.597 |
leton | -0.585 |
Token | ull |
Token ID | 724 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
agers | +2.702 |
ework | +2.484 |
lass | +2.443 |
apt | +2.429 |
ardon | +2.414 |
Neg logit contributions | |
�� | -2.117 |
edIn | -2.063 |
gie | -1.770 |
�� | -1.770 |
�� | -1.758 |
Token | s |
Token ID | 82 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
�� | +1.409 |
edIn | +1.389 |
gie | +1.209 |
orney | +1.203 |
leton | +1.167 |
Neg logit contributions | |
agers | -2.017 |
ework | -1.848 |
ardon | -1.810 |
lass | -1.777 |
apt | -1.777 |
Token | fighting |
Token ID | 4330 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
�� | +0.589 |
edIn | +0.577 |
orney | +0.510 |
gie | +0.510 |
leton | +0.496 |
Neg logit contributions | |
agers | -0.691 |
ework | -0.626 |
ardon | -0.612 |
apt | -0.602 |
lass | -0.600 |
Token | over |
Token ID | 625 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
agers | +1.961 |
ework | +1.748 |
ardon | +1.709 |
outs | +1.687 |
apt | +1.686 |
Neg logit contributions | |
�� | -2.042 |
edIn | -1.989 |
orney | -1.780 |
gie | -1.754 |
�� | -1.737 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +1.814 |
edIn | +1.793 |
gie | +1.603 |
orney | +1.598 |
leton | +1.564 |
Neg logit contributions | |
agers | -1.771 |
ework | -1.594 |
ardon | -1.555 |
apt | -1.518 |
outs | -1.515 |
Token | hot |
Token ID | 3024 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
agers | +0.196 |
ework | +0.176 |
ardon | +0.172 |
apt | +0.170 |
lass | +0.169 |
Neg logit contributions | |
�� | -0.183 |
edIn | -0.180 |
orney | -0.159 |
gie | -0.157 |
leton | -0.154 |
Token | smoother |
Token ID | 32686 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
agers | +0.188 |
ework | +0.168 |
ardon | +0.164 |
apt | +0.161 |
outs | +0.160 |
Neg logit contributions | |
�� | -0.204 |
edIn | -0.200 |
orney | -0.179 |
gie | -0.178 |
leton | -0.175 |
Token | on |
Token ID | 319 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
agers | +1.045 |
ework | +0.940 |
ardon | +0.921 |
apt | +0.906 |
outs | +0.904 |
Neg logit contributions | |
�� | -0.978 |
edIn | -0.958 |
orney | -0.846 |
gie | -0.838 |
leton | -0.823 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
�� | +0.244 |
edIn | +0.241 |
gie | +0.214 |
orney | +0.213 |
leton | +0.208 |
Neg logit contributions | |
agers | -0.238 |
ework | -0.214 |
ardon | -0.208 |
apt | -0.205 |
lass | -0.205 |
Token | MG |
Token ID | 34809 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
�� | +0.031 |
edIn | +0.030 |
orney | +0.027 |
gie | +0.027 |
leton | +0.026 |
Neg logit contributions | |
agers | -0.034 |
ework | -0.030 |
ardon | -0.030 |
apt | -0.029 |
lass | -0.029 |
Token | 279 |
Token ID | 26050 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
agers | +3.460 |
ework | +3.079 |
ardon | +2.993 |
outs | +2.943 |
apt | +2.935 |
Neg logit contributions | |
�� | -4.197 |
edIn | -4.147 |
orney | -3.725 |
gie | -3.711 |
leton | -3.634 |
Token | Q |
Token ID | 48 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
�� | +0.252 |
edIn | +0.247 |
orney | +0.216 |
gie | +0.215 |
leton | +0.210 |
Neg logit contributions | |
agers | -0.314 |
ework | -0.284 |
ardon | -0.278 |
apt | -0.274 |
lass | -0.273 |
Token | , |
Token ID | 11 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
�� | +1.558 |
edIn | +1.539 |
gie | +1.351 |
orney | +1.351 |
leton | +1.315 |
Neg logit contributions | |
agers | -1.797 |
ework | -1.622 |
ardon | -1.582 |
apt | -1.560 |
lass | -1.558 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
�� | +0.081 |
edIn | +0.079 |
orney | +0.069 |
gie | +0.069 |
leton | +0.068 |
Neg logit contributions | |
agers | -0.095 |
ework | -0.086 |
ardon | -0.084 |
apt | -0.083 |
lass | -0.083 |
Token | you |
Token ID | 345 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
agers | +0.109 |
ework | +0.097 |
ardon | +0.095 |
apt | +0.094 |
lass | +0.093 |
Neg logit contributions | |
�� | -0.108 |
edIn | -0.106 |
orney | -0.094 |
gie | -0.094 |
leton | -0.092 |
Token | also |
Token ID | 635 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
�� | +0.421 |
edIn | +0.413 |
orney | +0.362 |
gie | +0.361 |
leton | +0.352 |
Neg logit contributions | |
agers | -0.551 |
ework | -0.501 |
ardon | -0.491 |
apt | -0.484 |
lass | -0.482 |
Token | have |
Token ID | 423 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
agers | +0.850 |
ework | +0.769 |
ardon | +0.752 |
apt | +0.741 |
outs | +0.740 |
Neg logit contributions | |
�� | -0.718 |
edIn | -0.705 |
orney | -0.616 |
gie | -0.610 |
leton | -0.597 |
Token | media |
Token ID | 2056 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
�� | +0.693 |
edIn | +0.681 |
orney | +0.610 |
gie | +0.607 |
leton | +0.596 |
Neg logit contributions | |
agers | -0.608 |
ework | -0.541 |
ardon | -0.527 |
apt | -0.518 |
lass | -0.516 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
agers | +2.258 |
ework | +2.031 |
ardon | +1.988 |
apt | +1.974 |
outs | +1.966 |
Neg logit contributions | |
�� | -2.042 |
edIn | -1.996 |
orney | -1.751 |
gie | -1.722 |
�� | -1.719 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
�� | +0.271 |
edIn | +0.266 |
orney | +0.234 |
gie | +0.232 |
leton | +0.227 |
Neg logit contributions | |
agers | -0.320 |
ework | -0.290 |
ardon | -0.284 |
apt | -0.280 |
outs | -0.279 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
�� | +0.541 |
edIn | +0.531 |
orney | +0.469 |
gie | +0.466 |
leton | +0.456 |
Neg logit contributions | |
agers | -0.611 |
ework | -0.551 |
ardon | -0.539 |
apt | -0.531 |
lass | -0.529 |
Token | But |
Token ID | 1537 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
�� | +0.483 |
edIn | +0.478 |
gie | +0.415 |
orney | +0.413 |
leton | +0.406 |
Neg logit contributions | |
agers | -0.620 |
ework | -0.563 |
ardon | -0.551 |
apt | -0.541 |
lass | -0.541 |
Token | what |
Token ID | 644 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
�� | +0.763 |
edIn | +0.751 |
orney | +0.666 |
gie | +0.665 |
leton | +0.651 |
Neg logit contributions | |
agers | -0.778 |
ework | -0.699 |
ardon | -0.682 |
apt | -0.672 |
lass | -0.668 |
Token | made |
Token ID | 925 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
�� | +0.989 |
edIn | +0.970 |
orney | +0.854 |
gie | +0.853 |
leton | +0.834 |
Neg logit contributions | |
agers | -1.113 |
ework | -1.005 |
ardon | -0.983 |
apt | -0.967 |
lass | -0.963 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
�� | +0.659 |
edIn | +0.650 |
gie | +0.574 |
orney | +0.574 |
leton | +0.561 |
Neg logit contributions | |
agers | -0.700 |
ework | -0.631 |
ardon | -0.615 |
apt | -0.607 |
lass | -0.604 |
Token | reactions |
Token ID | 12737 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
agers | +0.282 |
ework | +0.253 |
ardon | +0.247 |
apt | +0.244 |
outs | +0.243 |
Neg logit contributions | |
�� | -0.268 |
edIn | -0.263 |
orney | -0.234 |
gie | -0.231 |
leton | -0.227 |
Token | of |
Token ID | 286 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
�� | +1.015 |
edIn | +0.989 |
orney | +0.878 |
gie | +0.877 |
leton | +0.853 |
Neg logit contributions | |
agers | -1.145 |
ework | -1.034 |
ardon | -1.011 |
apt | -0.993 |
lass | -0.990 |
Token | Belle |
Token ID | 31974 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
agers | +0.454 |
ework | +0.407 |
ardon | +0.398 |
apt | +0.392 |
lass | +0.390 |
Neg logit contributions | |
�� | -0.443 |
edIn | -0.435 |
orney | -0.386 |
gie | -0.384 |
leton | -0.376 |
Token | 94 |
Token ID | 5824 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
�� | +0.233 |
edIn | +0.231 |
gie | +0.208 |
orney | +0.206 |
leton | +0.203 |
Neg logit contributions | |
agers | -0.217 |
ework | -0.194 |
ardon | -0.189 |
lass | -0.184 |
apt | -0.184 |
Token | ) |
Token ID | 8 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
agers | +1.270 |
ework | +1.112 |
ardon | +1.081 |
apt | +1.060 |
outs | +1.054 |
Neg logit contributions | |
�� | -1.799 |
edIn | -1.775 |
orney | -1.607 |
gie | -1.598 |
leton | -1.571 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
agers | +0.751 |
ework | +0.677 |
ardon | +0.662 |
apt | +0.653 |
outs | +0.650 |
Neg logit contributions | |
�� | -0.671 |
edIn | -0.658 |
orney | -0.581 |
gie | -0.577 |
leton | -0.565 |
Token | ( |
Token ID | 7 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
�� | +2.016 |
edIn | +2.010 |
gie | +1.755 |
orney | +1.745 |
leton | +1.718 |
Neg logit contributions | |
agers | -2.377 |
ework | -2.149 |
ardon | -2.098 |
lass | -2.068 |
ufact | -2.042 |
Token | PC |
Token ID | 5662 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
�� | +0.352 |
edIn | +0.347 |
gie | +0.309 |
orney | +0.309 |
leton | +0.303 |
Neg logit contributions | |
agers | -0.319 |
ework | -0.285 |
ardon | -0.278 |
lass | -0.272 |
apt | -0.271 |
Token | M |
Token ID | 44 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
�� | +0.460 |
edIn | +0.449 |
orney | +0.398 |
gie | +0.396 |
leton | +0.388 |
Neg logit contributions | |
agers | -0.512 |
ework | -0.463 |
ardon | -0.451 |
apt | -0.444 |
lass | -0.442 |
Token | ) |
Token ID | 8 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
agers | +2.696 |
ework | +2.417 |
ardon | +2.359 |
apt | +2.330 |
outs | +2.309 |
Neg logit contributions | |
�� | -2.727 |
edIn | -2.682 |
orney | -2.370 |
gie | -2.369 |
�� | -2.318 |
Token | Many |
Token ID | 4650 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
agers | +0.805 |
ework | +0.728 |
ardon | +0.713 |
apt | +0.703 |
outs | +0.699 |
Neg logit contributions | |
�� | -0.685 |
edIn | -0.671 |
orney | -0.590 |
gie | -0.587 |
leton | -0.573 |
Token | were |
Token ID | 547 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
agers | +0.344 |
ework | +0.308 |
ardon | +0.301 |
apt | +0.296 |
lass | +0.295 |
Neg logit contributions | |
�� | -0.355 |
edIn | -0.349 |
orney | -0.311 |
gie | -0.309 |
leton | -0.303 |
Token | curious |
Token ID | 11040 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
�� | +0.364 |
edIn | +0.357 |
orney | +0.323 |
gie | +0.323 |
leton | +0.315 |
Neg logit contributions | |
agers | -0.327 |
ework | -0.295 |
ardon | -0.285 |
lass | -0.280 |
apt | -0.280 |
Token | just |
Token ID | 655 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
�� | +0.615 |
edIn | +0.608 |
gie | +0.541 |
orney | +0.541 |
leton | +0.530 |
Neg logit contributions | |
agers | -0.615 |
ework | -0.553 |
ardon | -0.539 |
apt | -0.530 |
lass | -0.530 |
Token | house |
Token ID | 2156 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
agers | +0.458 |
ework | +0.407 |
ardon | +0.397 |
apt | +0.389 |
lass | +0.388 |
Neg logit contributions | |
�� | -0.530 |
edIn | -0.522 |
orney | -0.468 |
gie | -0.466 |
leton | -0.457 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
agers | +2.075 |
ework | +1.868 |
ardon | +1.826 |
apt | +1.804 |
outs | +1.794 |
Neg logit contributions | |
�� | -1.941 |
edIn | -1.907 |
orney | -1.681 |
gie | -1.660 |
�� | -1.630 |
Token | arrest |
Token ID | 3251 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
agers | +0.526 |
ework | +0.473 |
ardon | +0.462 |
apt | +0.455 |
lass | +0.453 |
Neg logit contributions | |
�� | -0.498 |
edIn | -0.489 |
orney | -0.433 |
gie | -0.430 |
leton | -0.421 |
Token | you |
Token ID | 345 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
agers | +1.056 |
ework | +0.939 |
ardon | +0.916 |
apt | +0.901 |
lass | +0.896 |
Neg logit contributions | |
�� | -1.191 |
edIn | -1.172 |
orney | -1.049 |
gie | -1.044 |
leton | -1.024 |
Token | in |
Token ID | 287 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
�� | +0.248 |
edIn | +0.244 |
orney | +0.216 |
gie | +0.215 |
leton | +0.210 |
Neg logit contributions | |
agers | -0.291 |
ework | -0.264 |
ardon | -0.257 |
apt | -0.253 |
lass | -0.253 |
Token | front |
Token ID | 2166 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
agers | +0.499 |
ework | +0.447 |
ardon | +0.435 |
lass | +0.428 |
apt | +0.425 |
Neg logit contributions | |
�� | -0.526 |
edIn | -0.517 |
orney | -0.462 |
gie | -0.459 |
leton | -0.453 |
Token | of |
Token ID | 286 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
�� | +0.241 |
edIn | +0.237 |
orney | +0.211 |
gie | +0.209 |
leton | +0.205 |
Neg logit contributions | |
agers | -0.232 |
ework | -0.207 |
ardon | -0.202 |
apt | -0.199 |
outs | -0.198 |
Token | your |
Token ID | 534 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
agers | +0.645 |
ework | +0.574 |
ardon | +0.560 |
apt | +0.549 |
lass | +0.547 |
Neg logit contributions | |
�� | -0.735 |
edIn | -0.725 |
orney | -0.650 |
gie | -0.647 |
leton | -0.635 |
Token | children |
Token ID | 1751 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
agers | +0.572 |
ework | +0.507 |
ardon | +0.494 |
apt | +0.485 |
lass | +0.483 |
Neg logit contributions | |
�� | -0.684 |
edIn | -0.674 |
orney | -0.607 |
gie | -0.603 |
leton | -0.593 |
Token | . |
Token ID | 13 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
agers | +0.805 |
ework | +0.730 |
ardon | +0.716 |
apt | +0.705 |
lass | +0.703 |
Neg logit contributions | |
�� | -0.636 |
edIn | -0.623 |
orney | -0.545 |
gie | -0.542 |
leton | -0.529 |
Token | L |
Token ID | 406 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
agers | +0.767 |
ework | +0.697 |
ardon | +0.687 |
apt | +0.679 |
outs | +0.675 |
Neg logit contributions | |
�� | -0.585 |
edIn | -0.570 |
orney | -0.496 |
gie | -0.490 |
�� | -0.484 |
Token | people |
Token ID | 661 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
�� | +0.609 |
edIn | +0.599 |
orney | +0.543 |
gie | +0.542 |
leton | +0.531 |
Neg logit contributions | |
agers | -0.426 |
ework | -0.374 |
ardon | -0.364 |
apt | -0.357 |
lass | -0.356 |
Token | may |
Token ID | 743 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
agers | +0.663 |
ework | +0.600 |
ardon | +0.587 |
apt | +0.579 |
lass | +0.576 |
Neg logit contributions | |
�� | -0.551 |
edIn | -0.541 |
orney | -0.474 |
gie | -0.471 |
leton | -0.461 |
Token | be |
Token ID | 307 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
agers | +1.361 |
ework | +1.217 |
ardon | +1.188 |
apt | +1.170 |
outs | +1.166 |
Neg logit contributions | |
�� | -1.346 |
edIn | -1.327 |
orney | -1.173 |
gie | -1.155 |
�� | -1.147 |
Token | sexually |
Token ID | 11363 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
agers | +0.091 |
ework | +0.081 |
ardon | +0.079 |
apt | +0.078 |
lass | +0.078 |
Neg logit contributions | |
�� | -0.095 |
edIn | -0.094 |
orney | -0.084 |
gie | -0.083 |
leton | -0.082 |
Token | attracted |
Token ID | 12725 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
agers | +0.828 |
ework | +0.753 |
ardon | +0.738 |
apt | +0.727 |
lass | +0.724 |
Neg logit contributions | |
�� | -0.634 |
edIn | -0.619 |
orney | -0.542 |
gie | -0.540 |
leton | -0.526 |
Token | to |
Token ID | 284 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
agers | +0.730 |
ework | +0.659 |
ardon | +0.645 |
apt | +0.635 |
lass | +0.633 |
Neg logit contributions | |
�� | -0.632 |
edIn | -0.620 |
orney | -0.545 |
gie | -0.542 |
leton | -0.530 |
Token | individuals |
Token ID | 3925 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
�� | +0.144 |
edIn | +0.141 |
orney | +0.127 |
gie | +0.126 |
leton | +0.124 |
Neg logit contributions | |
agers | -0.130 |
ework | -0.116 |
ardon | -0.113 |
apt | -0.111 |
lass | -0.110 |
Token | who |
Token ID | 508 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
�� | +0.882 |
edIn | +0.863 |
gie | +0.778 |
orney | +0.771 |
leton | +0.755 |
Neg logit contributions | |
agers | -0.945 |
ework | -0.859 |
ardon | -0.838 |
lass | -0.827 |
apt | -0.824 |
Token | identify |
Token ID | 5911 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
�� | +0.578 |
edIn | +0.566 |
gie | +0.498 |
orney | +0.495 |
leton | +0.485 |
Neg logit contributions | |
agers | -0.731 |
ework | -0.663 |
ardon | -0.650 |
apt | -0.642 |
lass | -0.640 |
Token | as |
Token ID | 355 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
�� | +0.897 |
edIn | +0.881 |
gie | +0.776 |
orney | +0.774 |
leton | +0.756 |
Neg logit contributions | |
agers | -1.036 |
ework | -0.939 |
ardon | -0.917 |
apt | -0.902 |
lass | -0.902 |
Token | male |
Token ID | 4257 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
agers | +0.846 |
ework | +0.752 |
ardon | +0.734 |
apt | +0.721 |
lass | +0.717 |
Neg logit contributions | |
�� | -0.964 |
edIn | -0.948 |
orney | -0.849 |
gie | -0.845 |
leton | -0.829 |
Token | initially |
Token ID | 7317 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
�� | +0.626 |
edIn | +0.621 |
orney | +0.538 |
gie | +0.538 |
leton | +0.521 |
Neg logit contributions | |
agers | -0.794 |
ework | -0.722 |
ardon | -0.711 |
apt | -0.695 |
lass | -0.694 |
Token | increases |
Token ID | 5732 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
agers | +0.921 |
ework | +0.833 |
ardon | +0.816 |
apt | +0.804 |
lass | +0.801 |
Neg logit contributions | |
�� | -0.767 |
edIn | -0.753 |
orney | -0.661 |
gie | -0.657 |
leton | -0.642 |
Token | with |
Token ID | 351 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
agers | +1.410 |
ework | +1.268 |
ardon | +1.233 |
apt | +1.224 |
outs | +1.217 |
Neg logit contributions | |
�� | -1.336 |
edIn | -1.304 |
orney | -1.154 |
gie | -1.142 |
�� | -1.132 |
Token | experience |
Token ID | 1998 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
agers | +0.054 |
ework | +0.048 |
ardon | +0.047 |
apt | +0.046 |
lass | +0.046 |
Neg logit contributions | |
�� | -0.061 |
edIn | -0.060 |
orney | -0.054 |
gie | -0.054 |
leton | -0.053 |
Token | but |
Token ID | 475 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
�� | +0.987 |
edIn | +0.965 |
orney | +0.858 |
gie | +0.850 |
leton | +0.832 |
Neg logit contributions | |
agers | -1.151 |
ework | -1.035 |
ardon | -1.021 |
lass | -0.999 |
apt | -0.997 |
Token | may |
Token ID | 743 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
�� | +1.018 |
edIn | +1.004 |
orney | +0.883 |
gie | +0.877 |
leton | +0.857 |
Neg logit contributions | |
agers | -1.238 |
ework | -1.123 |
ardon | -1.104 |
apt | -1.084 |
lass | -1.081 |
Token | gradually |
Token ID | 11835 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
agers | +0.632 |
ework | +0.567 |
ardon | +0.552 |
apt | +0.546 |
outs | +0.544 |
Neg logit contributions | |
�� | -0.611 |
edIn | -0.599 |
orney | -0.528 |
gie | -0.524 |
�� | -0.515 |
Token | level |
Token ID | 1241 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
agers | +1.257 |
ework | +1.129 |
ardon | +1.099 |
apt | +1.090 |
outs | +1.085 |
Neg logit contributions | |
�� | -1.203 |
edIn | -1.180 |
orney | -1.036 |
gie | -1.027 |
�� | -1.012 |
Token | off |
Token ID | 572 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
agers | +0.397 |
ework | +0.355 |
ardon | +0.347 |
apt | +0.343 |
outs | +0.341 |
Neg logit contributions | |
�� | -0.425 |
edIn | -0.417 |
orney | -0.371 |
gie | -0.369 |
leton | -0.362 |
Token | or |
Token ID | 393 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
agers | +0.602 |
ework | +0.543 |
ardon | +0.531 |
apt | +0.524 |
outs | +0.521 |
Neg logit contributions | |
�� | -0.528 |
edIn | -0.518 |
orney | -0.456 |
gie | -0.453 |
leton | -0.444 |
Token | even |
Token ID | 772 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
�� | +1.083 |
edIn | +1.064 |
orney | +0.940 |
gie | +0.936 |
leton | +0.916 |
Neg logit contributions | |
agers | -1.215 |
ework | -1.095 |
ardon | -1.072 |
apt | -1.054 |
lass | -1.052 |
Token | Partnership |
Token ID | 23270 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
�� | +0.620 |
edIn | +0.610 |
gie | +0.523 |
orney | +0.523 |
leton | +0.493 |
Neg logit contributions | |
agers | -1.029 |
ework | -0.961 |
ardon | -0.940 |
apt | -0.927 |
lass | -0.925 |
Token | is |
Token ID | 318 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
agers | +0.551 |
ework | +0.496 |
ardon | +0.485 |
apt | +0.478 |
outs | +0.476 |
Neg logit contributions | |
�� | -0.505 |
edIn | -0.496 |
orney | -0.438 |
gie | -0.435 |
leton | -0.426 |
Token | a |
Token ID | 257 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
agers | +0.662 |
ework | +0.591 |
ardon | +0.577 |
apt | +0.568 |
lass | +0.565 |
Neg logit contributions | |
�� | -0.701 |
edIn | -0.689 |
orney | -0.615 |
gie | -0.612 |
leton | -0.600 |
Token | series |
Token ID | 2168 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
agers | +0.280 |
ework | +0.252 |
ardon | +0.246 |
apt | +0.242 |
lass | +0.241 |
Neg logit contributions | |
�� | -0.265 |
edIn | -0.260 |
orney | -0.230 |
gie | -0.229 |
leton | -0.224 |
Token | of |
Token ID | 286 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
agers | +0.167 |
ework | +0.150 |
ardon | +0.147 |
apt | +0.144 |
lass | +0.144 |
Neg logit contributions | |
�� | -0.168 |
edIn | -0.165 |
orney | -0.147 |
gie | -0.147 |
leton | -0.144 |
Token | trade |
Token ID | 3292 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
agers | +0.308 |
ework | +0.278 |
ardon | +0.272 |
apt | +0.267 |
outs | +0.267 |
Neg logit contributions | |
�� | -0.275 |
edIn | -0.270 |
orney | -0.238 |
gie | -0.236 |
leton | -0.232 |
Token | negotiations |
Token ID | 9825 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
agers | +0.097 |
ework | +0.089 |
ardon | +0.087 |
apt | +0.086 |
lass | +0.086 |
Neg logit contributions | |
�� | -0.066 |
edIn | -0.065 |
orney | -0.056 |
gie | -0.056 |
leton | -0.054 |
Token | being |
Token ID | 852 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
agers | +0.636 |
ework | +0.571 |
ardon | +0.558 |
apt | +0.549 |
lass | +0.547 |
Neg logit contributions | |
�� | -0.611 |
edIn | -0.600 |
orney | -0.533 |
gie | -0.530 |
leton | -0.519 |
Token | carried |
Token ID | 5281 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
�� | +0.178 |
edIn | +0.174 |
orney | +0.154 |
gie | +0.153 |
leton | +0.150 |
Neg logit contributions | |
agers | -0.211 |
ework | -0.191 |
ardon | -0.188 |
apt | -0.185 |
lass | -0.184 |
Token | out |
Token ID | 503 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
agers | +0.162 |
ework | +0.144 |
ardon | +0.140 |
apt | +0.138 |
outs | +0.137 |
Neg logit contributions | |
�� | -0.197 |
edIn | -0.194 |
orney | -0.174 |
gie | -0.173 |
leton | -0.170 |
Token | mostly |
Token ID | 4632 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
agers | +0.972 |
ework | +0.873 |
ardon | +0.851 |
apt | +0.839 |
outs | +0.839 |
Neg logit contributions | |
�� | -0.956 |
edIn | -0.937 |
orney | -0.828 |
gie | -0.821 |
�� | -0.812 |
Token | push |
Token ID | 4574 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
agers | +0.712 |
ework | +0.639 |
ardon | +0.629 |
apt | +0.623 |
outs | +0.620 |
Neg logit contributions | |
�� | -0.627 |
edIn | -0.615 |
orney | -0.536 |
gie | -0.527 |
�� | -0.525 |
Token | hemp |
Token ID | 28246 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
agers | +1.527 |
ework | +1.366 |
ardon | +1.334 |
apt | +1.314 |
outs | +1.311 |
Neg logit contributions | |
�� | -1.572 |
edIn | -1.543 |
orney | -1.370 |
gie | -1.361 |
leton | -1.339 |
Token | across |
Token ID | 1973 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
agers | +1.177 |
ework | +1.049 |
ardon | +1.026 |
outs | +1.010 |
apt | +1.009 |
Neg logit contributions | |
�� | -1.214 |
edIn | -1.188 |
orney | -1.055 |
gie | -1.043 |
�� | -1.032 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
�� | +1.819 |
edIn | +1.770 |
orney | +1.589 |
gie | +1.565 |
leton | +1.544 |
Neg logit contributions | |
agers | -1.889 |
ework | -1.706 |
ardon | -1.647 |
apt | -1.632 |
lass | -1.622 |
Token | finish |
Token ID | 5461 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
agers | +0.521 |
ework | +0.466 |
ardon | +0.455 |
apt | +0.448 |
lass | +0.445 |
Neg logit contributions | |
�� | -0.547 |
edIn | -0.538 |
orney | -0.480 |
gie | -0.477 |
leton | -0.469 |
Token | line |
Token ID | 1627 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
�� | +0.477 |
edIn | +0.471 |
orney | +0.432 |
gie | +0.431 |
leton | +0.422 |
Neg logit contributions | |
agers | -0.276 |
ework | -0.235 |
ardon | -0.228 |
apt | -0.224 |
lass | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
agers | +3.836 |
ework | +3.417 |
ardon | +3.362 |
outs | +3.327 |
apt | +3.315 |
Neg logit contributions | |
�� | -4.010 |
edIn | -3.942 |
orney | -3.473 |
�� | -3.448 |
�� | -3.405 |
Token | not |
Token ID | 407 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
agers | +0.426 |
ework | +0.388 |
ardon | +0.379 |
apt | +0.373 |
lass | +0.373 |
Neg logit contributions | |
�� | -0.339 |
edIn | -0.332 |
orney | -0.291 |
gie | -0.289 |
leton | -0.282 |
Token | only |
Token ID | 691 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
agers | +1.134 |
ework | +1.008 |
ardon | +0.987 |
apt | +0.975 |
outs | +0.966 |
Neg logit contributions | |
�� | -1.285 |
edIn | -1.265 |
orney | -1.127 |
gie | -1.121 |
�� | -1.100 |
Token | for |
Token ID | 329 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
�� | +1.381 |
edIn | +1.357 |
gie | +1.205 |
orney | +1.203 |
leton | +1.170 |
Neg logit contributions | |
agers | -1.563 |
ework | -1.415 |
ardon | -1.372 |
lass | -1.362 |
apt | -1.356 |
Token | Hawaii |
Token ID | 13708 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
�� | +0.895 |
edIn | +0.882 |
orney | +0.784 |
gie | +0.783 |
leton | +0.765 |
Neg logit contributions | |
agers | -0.899 |
ework | -0.816 |
ardon | -0.792 |
apt | -0.784 |
lass | -0.783 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�� | +0.002 |
edIn | +0.002 |
orney | +0.002 |
gie | +0.002 |
leton | +0.002 |
Neg logit contributions | |
agers | -0.002 |
ework | -0.002 |
ardon | -0.002 |
apt | -0.002 |
lass | -0.002 |
Token | � |
Token ID | 447 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
�� | +0.234 |
edIn | +0.229 |
orney | +0.201 |
gie | +0.199 |
leton | +0.195 |
Neg logit contributions | |
agers | -0.295 |
ework | -0.267 |
ardon | -0.261 |
apt | -0.257 |
lass | -0.257 |
Token | � |
Token ID | 251 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
�� | +0.263 |
edIn | +0.256 |
orney | +0.216 |
gie | +0.214 |
leton | +0.207 |
Neg logit contributions | |
agers | -0.470 |
ework | -0.432 |
ardon | -0.424 |
apt | -0.420 |
lass | -0.418 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
�� | +0.042 |
edIn | +0.042 |
orney | +0.037 |
gie | +0.036 |
leton | +0.036 |
Neg logit contributions | |
agers | -0.051 |
ework | -0.046 |
ardon | -0.045 |
apt | -0.045 |
lass | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
�� | +0.243 |
edIn | +0.238 |
orney | +0.210 |
gie | +0.209 |
leton | +0.205 |
Neg logit contributions | |
agers | -0.275 |
ework | -0.248 |
ardon | -0.243 |
apt | -0.239 |
lass | -0.238 |
Token | Maria |
Token ID | 46827 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
�� | +0.261 |
edIn | +0.257 |
orney | +0.224 |
gie | +0.223 |
leton | +0.219 |
Neg logit contributions | |
agers | -0.327 |
ework | -0.296 |
ardon | -0.291 |
lass | -0.285 |
apt | -0.285 |
Token | Crist |
Token ID | 24568 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
agers | +4.236 |
ework | +3.795 |
ardon | +3.764 |
outs | +3.688 |
lass | +3.679 |
Neg logit contributions | |
�� | -3.509 |
edIn | -3.437 |
orney | -2.980 |
�� | -2.926 |
gie | -2.921 |
Token | ini |
Token ID | 5362 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
agers | +0.180 |
ework | +0.161 |
ardon | +0.157 |
apt | +0.154 |
lass | +0.153 |
Neg logit contributions | |
�� | -0.194 |
edIn | -0.191 |
orney | -0.171 |
gie | -0.170 |
leton | -0.167 |
Token | would |
Token ID | 561 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
�� | +0.907 |
edIn | +0.889 |
orney | +0.785 |
gie | +0.781 |
leton | +0.764 |
Neg logit contributions | |
agers | -1.035 |
ework | -0.936 |
ardon | -0.913 |
apt | -0.900 |
lass | -0.899 |
Token | not |
Token ID | 407 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
agers | +1.560 |
ework | +1.400 |
ardon | +1.373 |
apt | +1.352 |
outs | +1.339 |
Neg logit contributions | |
�� | -1.545 |
edIn | -1.522 |
orney | -1.334 |
gie | -1.324 |
�� | -1.311 |
Token | argue |
Token ID | 7267 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
agers | +1.235 |
ework | +1.109 |
ardon | +1.092 |
apt | +1.070 |
outs | +1.066 |
Neg logit contributions | |
�� | -1.157 |
edIn | -1.139 |
orney | -0.994 |
gie | -0.982 |
�� | -0.978 |
Token | Sherman |
Token ID | 23198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
�� | +0.715 |
edIn | +0.706 |
orney | +0.633 |
gie | +0.632 |
leton | +0.619 |
Neg logit contributions | |
agers | -0.629 |
ework | -0.559 |
ardon | -0.545 |
apt | -0.535 |
lass | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
�� | +1.470 |
edIn | +1.449 |
orney | +1.275 |
gie | +1.272 |
leton | +1.248 |
Neg logit contributions | |
agers | -1.751 |
ework | -1.609 |
ardon | -1.554 |
lass | -1.536 |
apt | -1.523 |
Token | Seahawks |
Token ID | 16732 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
agers | +0.066 |
ework | +0.059 |
ardon | +0.058 |
apt | +0.057 |
lass | +0.057 |
Neg logit contributions | |
�� | -0.062 |
edIn | -0.061 |
orney | -0.054 |
gie | -0.054 |
leton | -0.053 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
�� | +2.370 |
edIn | +2.358 |
gie | +2.118 |
orney | +2.098 |
leton | +2.071 |
Neg logit contributions | |
agers | -2.222 |
ework | -1.989 |
ardon | -1.933 |
lass | -1.897 |
apt | -1.891 |
Token | AL |
Token ID | 8355 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
�� | +0.929 |
edIn | +0.912 |
orney | +0.818 |
gie | +0.817 |
leton | +0.803 |
Neg logit contributions | |
agers | -0.792 |
ework | -0.702 |
ardon | -0.684 |
apt | -0.669 |
lass | -0.669 |
Token | READ |
Token ID | 15675 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
agers | +0.137 |
ework | +0.122 |
ardon | +0.119 |
apt | +0.116 |
lass | +0.116 |
Neg logit contributions | |
�� | -0.155 |
edIn | -0.152 |
gie | -0.136 |
orney | -0.136 |
leton | -0.133 |
Token | Y |
Token ID | 56 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
agers | +2.741 |
ework | +2.398 |
ardon | +2.318 |
outs | +2.312 |
apt | +2.305 |
Neg logit contributions | |
�� | -3.775 |
edIn | -3.756 |
orney | -3.408 |
gie | -3.335 |
�� | -3.315 |
Token | COMP |
Token ID | 24301 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
agers | +0.139 |
ework | +0.126 |
ardon | +0.123 |
apt | +0.121 |
lass | +0.121 |
Neg logit contributions | |
�� | -0.120 |
edIn | -0.117 |
orney | -0.103 |
gie | -0.103 |
leton | -0.101 |
Token | ET |
Token ID | 2767 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
agers | +2.381 |
ework | +2.121 |
ardon | +2.075 |
apt | +2.048 |
outs | +2.030 |
Neg logit contributions | |
�� | -2.796 |
edIn | -2.747 |
orney | -2.475 |
gie | -2.463 |
�� | -2.411 |
Token | ED |
Token ID | 1961 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
�� | +0.116 |
edIn | +0.114 |
orney | +0.101 |
gie | +0.100 |
leton | +0.098 |
Neg logit contributions | |
agers | -0.122 |
ework | -0.110 |
ardon | -0.107 |
apt | -0.106 |
outs | -0.105 |
Token | : |
Token ID | 25 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
�� | +0.436 |
edIn | +0.429 |
orney | +0.376 |
gie | +0.374 |
leton | +0.366 |
Neg logit contributions | |
agers | -0.521 |
ework | -0.471 |
ardon | -0.461 |
apt | -0.454 |
lass | -0.452 |
Token | I |
Token ID | 40 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
�� | +0.321 |
edIn | +0.317 |
gie | +0.278 |
orney | +0.276 |
leton | +0.271 |
Neg logit contributions | |
agers | -0.398 |
ework | -0.361 |
ardon | -0.353 |
lass | -0.346 |
apt | -0.344 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
agers | +0.123 |
ework | +0.111 |
ardon | +0.109 |
apt | +0.107 |
lass | +0.107 |
Neg logit contributions | |
�� | -0.109 |
edIn | -0.107 |
orney | -0.095 |
gie | -0.094 |
leton | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
agers | +0.767 |
ework | +0.686 |
ardon | +0.669 |
apt | +0.657 |
lass | +0.654 |
Neg logit contributions | |
�� | -0.817 |
edIn | -0.803 |
orney | -0.717 |
gie | -0.715 |
leton | -0.701 |
Token | movie |
Token ID | 3807 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
agers | +0.219 |
ework | +0.196 |
ardon | +0.192 |
apt | +0.187 |
lass | +0.187 |
Neg logit contributions | |
�� | -0.229 |
edIn | -0.225 |
gie | -0.201 |
orney | -0.201 |
leton | -0.196 |
Token | The |
Token ID | 383 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
�� | +0.091 |
edIn | +0.089 |
gie | +0.078 |
orney | +0.078 |
leton | +0.076 |
Neg logit contributions | |
agers | -0.103 |
ework | -0.093 |
ardon | -0.091 |
apt | -0.089 |
lass | -0.089 |
Token | Pur |
Token ID | 9330 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
�� | +0.583 |
edIn | +0.572 |
orney | +0.508 |
gie | +0.508 |
leton | +0.497 |
Neg logit contributions | |
agers | -0.590 |
ework | -0.532 |
ardon | -0.517 |
apt | -0.508 |
lass | -0.506 |
Token | ge |
Token ID | 469 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
agers | +3.936 |
ework | +3.459 |
ardon | +3.441 |
apt | +3.390 |
out | +3.379 |
Neg logit contributions | |
�� | -3.360 |
edIn | -3.183 |
�� | -2.895 |
�� | -2.859 |
orney | -2.722 |
Token | but |
Token ID | 475 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
agers | +0.468 |
ework | +0.420 |
ardon | +0.411 |
apt | +0.406 |
outs | +0.404 |
Neg logit contributions | |
�� | -0.435 |
edIn | -0.426 |
orney | -0.377 |
gie | -0.374 |
leton | -0.367 |
Token | with |
Token ID | 351 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
�� | +0.695 |
edIn | +0.682 |
orney | +0.607 |
gie | +0.605 |
leton | +0.593 |
Neg logit contributions | |
agers | -0.712 |
ework | -0.642 |
ardon | -0.626 |
apt | -0.612 |
lass | -0.611 |
Token | everything |
Token ID | 2279 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
�� | +0.337 |
edIn | +0.331 |
gie | +0.296 |
orney | +0.295 |
leton | +0.288 |
Neg logit contributions | |
agers | -0.329 |
ework | -0.296 |
ardon | -0.288 |
lass | -0.281 |
apt | -0.280 |
Token | it |
Token ID | 340 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
�� | +1.398 |
edIn | +1.366 |
gie | +1.228 |
orney | +1.220 |
leton | +1.190 |
Neg logit contributions | |
agers | -1.486 |
ework | -1.337 |
ardon | -1.306 |
lass | -1.280 |
apt | -1.272 |
Token | the |
Token ID | 1169 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
�� | +0.476 |
edIn | +0.470 |
gie | +0.428 |
orney | +0.425 |
leton | +0.418 |
Neg logit contributions | |
agers | -0.365 |
ework | -0.321 |
ardon | -0.310 |
apt | -0.306 |
lass | -0.305 |
Token | e |
Token ID | 68 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
�� | +0.509 |
edIn | +0.499 |
orney | +0.438 |
gie | +0.436 |
leton | +0.426 |
Neg logit contributions | |
agers | -0.610 |
ework | -0.552 |
ardon | -0.541 |
apt | -0.533 |
lass | -0.531 |
Token | - |
Token ID | 12 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
�� | +0.559 |
edIn | +0.549 |
orney | +0.483 |
gie | +0.478 |
leton | +0.469 |
Neg logit contributions | |
agers | -0.626 |
ework | -0.564 |
ardon | -0.555 |
apt | -0.544 |
outs | -0.543 |
Token | well |
Token ID | 4053 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
�� | +0.043 |
edIn | +0.042 |
orney | +0.038 |
gie | +0.037 |
leton | +0.037 |
Neg logit contributions | |
agers | -0.038 |
ework | -0.034 |
ardon | -0.033 |
apt | -0.032 |
lass | -0.032 |
Token | from |
Token ID | 422 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
agers | +0.096 |
ework | +0.086 |
ardon | +0.085 |
apt | +0.084 |
outs | +0.083 |
Neg logit contributions | |
�� | -0.085 |
edIn | -0.083 |
orney | -0.073 |
gie | -0.072 |
leton | -0.071 |
Token | Mitch |
Token ID | 20472 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
agers | +0.534 |
ework | +0.479 |
ardon | +0.468 |
apt | +0.461 |
lass | +0.458 |
Neg logit contributions | |
�� | -0.526 |
edIn | -0.517 |
orney | -0.459 |
gie | -0.456 |
leton | -0.447 |
Token | McConnell |
Token ID | 18184 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
agers | +3.283 |
ardon | +2.909 |
ework | +2.900 |
outs | +2.842 |
apt | +2.841 |
Neg logit contributions | |
�� | -3.366 |
edIn | -3.349 |
orney | -2.900 |
�� | -2.886 |
gie | -2.882 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
agers | +2.873 |
ework | +2.582 |
ardon | +2.534 |
apt | +2.518 |
outs | +2.518 |
Neg logit contributions | |
�� | -2.412 |
edIn | -2.363 |
orney | -2.051 |
gie | -2.027 |
�� | -2.005 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
�� | +0.296 |
edIn | +0.291 |
orney | +0.257 |
gie | +0.255 |
leton | +0.251 |
Neg logit contributions | |
agers | -0.311 |
ework | -0.279 |
ardon | -0.273 |
apt | -0.269 |
outs | -0.268 |
Token | Grassley |
Token ID | 44050 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
�� | +0.175 |
edIn | +0.170 |
orney | +0.153 |
gie | +0.150 |
�� | +0.148 |
Neg logit contributions | |
agers | -0.167 |
ework | -0.149 |
ardon | -0.146 |
outs | -0.145 |
apt | -0.145 |
Token | would |
Token ID | 561 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
agers | +3.020 |
ework | +2.720 |
ardon | +2.677 |
apt | +2.654 |
outs | +2.653 |
Neg logit contributions | |
�� | -2.429 |
edIn | -2.378 |
orney | -2.070 |
gie | -2.030 |
leton | -2.003 |