Token | different |
Token ID | 1180 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ni | +0.072 |
Yang | +0.071 |
NES | +0.066 |
erers | +0.065 |
Pokemon | +0.063 |
Neg logit contributions | |
�� | -0.126 |
apo | -0.119 |
antha | -0.115 |
mosqu | -0.110 |
utenant | -0.109 |
Token | Best |
Token ID | 6705 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
�� | +2.124 |
apo | +1.994 |
antha | +1.914 |
mosqu | +1.823 |
utenant | +1.809 |
Neg logit contributions | |
ni | -1.689 |
Yang | -1.684 |
NES | -1.598 |
erers | -1.563 |
Pokemon | -1.526 |
Token | of |
Token ID | 286 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ni | +0.266 |
Yang | +0.262 |
NES | +0.246 |
erers | +0.241 |
Pokemon | +0.233 |
Neg logit contributions | |
�� | -0.449 |
apo | -0.423 |
antha | -0.408 |
mosqu | -0.391 |
utenant | -0.389 |
Token | the |
Token ID | 262 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
�� | +0.756 |
apo | +0.705 |
antha | +0.677 |
mosqu | +0.647 |
utenant | +0.643 |
Neg logit contributions | |
ni | -0.575 |
Yang | -0.567 |
NES | -0.537 |
erers | -0.528 |
Pokemon | -0.514 |
Token | Year |
Token ID | 6280 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
�� | +0.815 |
apo | +0.750 |
antha | +0.715 |
mosqu | +0.680 |
utenant | +0.674 |
Neg logit contributions | |
ni | -0.821 |
Yang | -0.812 |
NES | -0.775 |
erers | -0.763 |
Pokemon | -0.745 |
Token | awards |
Token ID | 13304 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
�� | +0.836 |
apo | +0.765 |
antha | +0.726 |
mosqu | +0.680 |
utenant | +0.675 |
Neg logit contributions | |
ni | -1.060 |
Yang | -1.051 |
NES | -1.008 |
erers | -0.995 |
Pokemon | -0.975 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
�� | +6.178 |
apo | +5.835 |
antha | +5.707 |
mosqu | +5.384 |
utenant | +5.279 |
Neg logit contributions | |
Yang | -4.186 |
ni | -4.118 |
NES | -3.978 |
erers | -3.823 |
Pokemon | -3.756 |
Token | Top |
Token ID | 5849 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
�� | +0.040 |
apo | +0.037 |
antha | +0.035 |
mosqu | +0.034 |
utenant | +0.034 |
Neg logit contributions | |
ni | -0.026 |
Yang | -0.025 |
NES | -0.024 |
erers | -0.024 |
Pokemon | -0.023 |
Token | Ten |
Token ID | 9368 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ni | +0.404 |
Yang | +0.394 |
NES | +0.375 |
erers | +0.367 |
Pokemon | +0.356 |
Neg logit contributions | |
�� | -0.580 |
apo | -0.545 |
antha | -0.521 |
mosqu | -0.505 |
utenant | -0.496 |
Token | awards |
Token ID | 13304 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ni | +0.261 |
Yang | +0.255 |
NES | +0.243 |
erers | +0.238 |
Pokemon | +0.231 |
Neg logit contributions | |
�� | -0.348 |
apo | -0.323 |
antha | -0.312 |
mosqu | -0.298 |
utenant | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
�� | +4.769 |
apo | +4.493 |
antha | +4.359 |
mosqu | +4.133 |
utenant | +4.087 |
Neg logit contributions | |
Yang | -3.102 |
ni | -3.081 |
NES | -2.920 |
erers | -2.840 |
Pokemon | -2.767 |
Token | 's |
Token ID | 338 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ni | +0.434 |
Yang | +0.426 |
NES | +0.401 |
erers | +0.397 |
Pokemon | +0.383 |
Neg logit contributions | |
�� | -0.618 |
apo | -0.571 |
antha | -0.551 |
mosqu | -0.531 |
utenant | -0.522 |
Token | paired |
Token ID | 20312 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ni | +0.887 |
Yang | +0.864 |
NES | +0.823 |
erers | +0.805 |
Num | +0.783 |
Neg logit contributions | |
�� | -1.286 |
apo | -1.189 |
antha | -1.143 |
mosqu | -1.096 |
utenant | -1.085 |
Token | with |
Token ID | 351 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ni | +0.210 |
Yang | +0.207 |
NES | +0.196 |
erers | +0.191 |
Pokemon | +0.186 |
Neg logit contributions | |
�� | -0.333 |
apo | -0.313 |
antha | -0.301 |
mosqu | -0.288 |
utenant | -0.286 |
Token | " |
Token ID | 366 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
ni | +0.317 |
Yang | +0.312 |
NES | +0.296 |
erers | +0.290 |
Pokemon | +0.282 |
Neg logit contributions | |
�� | -0.451 |
apo | -0.421 |
antha | -0.404 |
mosqu | -0.387 |
utenant | -0.384 |
Token | Del |
Token ID | 13856 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ni | +0.126 |
Yang | +0.125 |
NES | +0.118 |
erers | +0.115 |
Pokemon | +0.113 |
Neg logit contributions | |
�� | -0.189 |
apo | -0.176 |
antha | -0.170 |
mosqu | -0.163 |
utenant | -0.162 |
Token | iver |
Token ID | 1428 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
�� | +0.964 |
apo | +0.876 |
antha | +0.841 |
mosqu | +0.797 |
utenant | +0.788 |
Neg logit contributions | |
ni | -1.053 |
Yang | -1.035 |
NES | -0.988 |
erers | -0.977 |
Pokemon | -0.955 |
Token | ance |
Token ID | 590 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
�� | +4.907 |
apo | +4.785 |
antha | +4.574 |
utenant | +4.279 |
artisan | +4.173 |
Neg logit contributions | |
Yang | -4.889 |
ni | -4.871 |
NES | -4.746 |
erers | -4.575 |
Pokemon | -4.534 |
Token | " |
Token ID | 1 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ni | +0.045 |
Yang | +0.045 |
NES | +0.042 |
erers | +0.041 |
Pokemon | +0.039 |
Neg logit contributions | |
�� | -0.087 |
apo | -0.082 |
antha | -0.079 |
mosqu | -0.076 |
utenant | -0.076 |
Token | on |
Token ID | 319 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
�� | +1.188 |
apo | +1.119 |
antha | +1.080 |
mosqu | +1.032 |
utenant | +1.029 |
Neg logit contributions | |
ni | -0.733 |
Yang | -0.725 |
NES | -0.680 |
erers | -0.668 |
Pokemon | -0.649 |
Token | Aug |
Token ID | 2447 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ni | +0.017 |
Yang | +0.017 |
NES | +0.016 |
erers | +0.016 |
Pokemon | +0.015 |
Neg logit contributions | |
�� | -0.031 |
apo | -0.030 |
antha | -0.029 |
mosqu | -0.027 |
utenant | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ni | +1.083 |
Yang | +1.036 |
NES | +0.981 |
erers | +0.957 |
Pokemon | +0.910 |
Neg logit contributions | |
�� | -2.151 |
apo | -1.963 |
mosqu | -1.943 |
antha | -1.917 |
utenant | -1.835 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
�� | +0.406 |
apo | +0.380 |
antha | +0.365 |
mosqu | +0.349 |
utenant | +0.346 |
Neg logit contributions | |
ni | -0.288 |
Yang | -0.284 |
NES | -0.268 |
erers | -0.263 |
Pokemon | -0.256 |
Token | first |
Token ID | 717 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ni | +0.054 |
Yang | +0.053 |
NES | +0.050 |
erers | +0.049 |
Pokemon | +0.048 |
Neg logit contributions | |
�� | -0.077 |
apo | -0.072 |
antha | -0.069 |
mosqu | -0.066 |
utenant | -0.065 |
Token | recipient |
Token ID | 17800 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
�� | +0.089 |
apo | +0.082 |
antha | +0.079 |
mosqu | +0.075 |
utenant | +0.074 |
Neg logit contributions | |
ni | -0.077 |
Yang | -0.075 |
NES | -0.072 |
erers | -0.070 |
Pokemon | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
�� | +1.987 |
apo | +1.869 |
antha | +1.808 |
utenant | +1.734 |
mosqu | +1.729 |
Neg logit contributions | |
ni | -1.098 |
Yang | -1.083 |
NES | -1.015 |
erers | -1.007 |
Pokemon | -0.963 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
�� | +0.530 |
apo | +0.491 |
antha | +0.470 |
mosqu | +0.448 |
utenant | +0.445 |
Neg logit contributions | |
ni | -0.455 |
Yang | -0.451 |
NES | -0.428 |
erers | -0.419 |
Pokemon | -0.411 |
Token | award |
Token ID | 5764 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
�� | +0.249 |
apo | +0.230 |
antha | +0.220 |
mosqu | +0.209 |
utenant | +0.208 |
Neg logit contributions | |
ni | -0.224 |
Yang | -0.221 |
NES | -0.210 |
erers | -0.206 |
Pokemon | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
�� | +5.758 |
apo | +5.491 |
antha | +5.269 |
utenant | +4.985 |
mosqu | +4.893 |
Neg logit contributions | |
ni | -4.015 |
Yang | -3.986 |
erers | -3.859 |
NES | -3.823 |
Pokemon | -3.689 |
Token | which |
Token ID | 543 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ni | +0.059 |
Yang | +0.059 |
NES | +0.055 |
erers | +0.054 |
Pokemon | +0.052 |
Neg logit contributions | |
�� | -0.097 |
apo | -0.091 |
antha | -0.087 |
mosqu | -0.084 |
utenant | -0.083 |
Token | was |
Token ID | 373 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
ni | +0.584 |
Yang | +0.575 |
NES | +0.532 |
erers | +0.527 |
Pokemon | +0.508 |
Neg logit contributions | |
�� | -1.013 |
apo | -0.944 |
antha | -0.911 |
mosqu | -0.876 |
utenant | -0.872 |
Token | presented |
Token ID | 5545 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
ni | +0.009 |
Yang | +0.009 |
NES | +0.008 |
erers | +0.008 |
Pokemon | +0.008 |
Neg logit contributions | |
�� | -0.012 |
apo | -0.012 |
antha | -0.011 |
mosqu | -0.011 |
utenant | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
�� | +1.400 |
apo | +1.311 |
antha | +1.260 |
mosqu | +1.197 |
utenant | +1.195 |
Neg logit contributions | |
ni | -1.068 |
Yang | -1.057 |
NES | -1.002 |
erers | -0.986 |
Pokemon | -0.961 |
Token | will |
Token ID | 481 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ni | +0.790 |
Yang | +0.766 |
erers | +0.716 |
NES | +0.714 |
Pokemon | +0.679 |
Neg logit contributions | |
�� | -1.303 |
apo | -1.207 |
antha | -1.162 |
mosqu | -1.127 |
utenant | -1.113 |
Token | never |
Token ID | 1239 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
�� | +0.840 |
apo | +0.778 |
antha | +0.747 |
mosqu | +0.715 |
utenant | +0.705 |
Neg logit contributions | |
ni | -0.681 |
Yang | -0.668 |
NES | -0.635 |
erers | -0.625 |
Pokemon | -0.607 |
Token | win |
Token ID | 1592 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
�� | +2.087 |
apo | +1.956 |
antha | +1.879 |
mosqu | +1.783 |
utenant | +1.782 |
Neg logit contributions | |
ni | -1.591 |
Yang | -1.582 |
NES | -1.497 |
erers | -1.468 |
Pokemon | -1.436 |
Token | any |
Token ID | 597 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
�� | +0.971 |
apo | +0.905 |
antha | +0.870 |
mosqu | +0.829 |
utenant | +0.823 |
Neg logit contributions | |
ni | -0.757 |
Yang | -0.748 |
NES | -0.710 |
erers | -0.697 |
Pokemon | -0.680 |
Token | culinary |
Token ID | 35956 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
ni | +0.980 |
Yang | +0.962 |
NES | +0.919 |
erers | +0.902 |
Pokemon | +0.883 |
Neg logit contributions | |
�� | -1.142 |
apo | -1.059 |
antha | -1.009 |
mosqu | -0.971 |
utenant | -0.959 |
Token | awards |
Token ID | 13304 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
�� | +0.549 |
apo | +0.509 |
antha | +0.486 |
mosqu | +0.465 |
utenant | +0.460 |
Neg logit contributions | |
ni | -0.477 |
Yang | -0.471 |
NES | -0.448 |
erers | -0.442 |
Pokemon | -0.431 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
�� | +5.682 |
apo | +5.393 |
antha | +5.206 |
utenant | +4.937 |
mosqu | +4.845 |
Neg logit contributions | |
Yang | -4.064 |
ni | -3.985 |
NES | -3.792 |
erers | -3.752 |
Pokemon | -3.623 |
Token | Try |
Token ID | 9993 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
�� | +0.515 |
apo | +0.480 |
antha | +0.460 |
mosqu | +0.447 |
utenant | +0.437 |
Neg logit contributions | |
ni | -0.371 |
Yang | -0.368 |
NES | -0.348 |
erers | -0.340 |
Pokemon | -0.333 |
Token | some |
Token ID | 617 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
ni | +1.078 |
Yang | +1.052 |
NES | +1.006 |
erers | +0.988 |
Num | +0.964 |
Neg logit contributions | |
�� | -1.314 |
apo | -1.224 |
antha | -1.161 |
mosqu | -1.110 |
utenant | -1.100 |
Token | each |
Token ID | 1123 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
�� | +0.179 |
apo | +0.167 |
antha | +0.161 |
mosqu | +0.154 |
utenant | +0.153 |
Neg logit contributions | |
ni | -0.120 |
Yang | -0.118 |
NES | -0.112 |
erers | -0.110 |
Pokemon | -0.106 |
Token | way |
Token ID | 835 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
�� | +1.102 |
apo | +1.033 |
antha | +0.995 |
mosqu | +0.952 |
utenant | +0.946 |
Neg logit contributions | |
ni | -0.730 |
Yang | -0.721 |
NES | -0.679 |
erers | -0.667 |
Pokemon | -0.648 |
Token | s |
Token ID | 82 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
�� | +0.425 |
apo | +0.397 |
antha | +0.384 |
mosqu | +0.371 |
utenant | +0.366 |
Neg logit contributions | |
ni | -0.240 |
Yang | -0.235 |
NES | -0.220 |
erers | -0.216 |
Pokemon | -0.209 |
Token | also |
Token ID | 635 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
�� | +0.087 |
apo | +0.081 |
antha | +0.078 |
mosqu | +0.075 |
utenant | +0.074 |
Neg logit contributions | |
ni | -0.062 |
Yang | -0.060 |
NES | -0.057 |
erers | -0.056 |
Pokemon | -0.054 |
Token | quite |
Token ID | 2407 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ni | +0.653 |
Yang | +0.634 |
NES | +0.605 |
erers | +0.589 |
Pokemon | +0.573 |
Neg logit contributions | |
�� | -0.897 |
apo | -0.828 |
antha | -0.796 |
mosqu | -0.767 |
utenant | -0.758 |
Token | a |
Token ID | 257 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
�� | +1.687 |
apo | +1.576 |
antha | +1.513 |
mosqu | +1.440 |
utenant | +1.431 |
Neg logit contributions | |
ni | -1.320 |
Yang | -1.308 |
NES | -1.240 |
erers | -1.218 |
Pokemon | -1.189 |
Token | bit |
Token ID | 1643 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
ni | +0.480 |
Yang | +0.469 |
NES | +0.439 |
erers | +0.432 |
Pokemon | +0.417 |
Neg logit contributions | |
�� | -0.745 |
apo | -0.691 |
antha | -0.669 |
mosqu | -0.642 |
utenant | -0.637 |
Token | swe |
Token ID | 3490 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ni | +0.093 |
Yang | +0.091 |
NES | +0.086 |
erers | +0.085 |
Pokemon | +0.082 |
Neg logit contributions | |
�� | -0.126 |
apo | -0.117 |
antha | -0.113 |
mosqu | -0.108 |
utenant | -0.107 |
Token | eter |
Token ID | 2357 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
apo | +5.681 |
�� | +5.674 |
antha | +5.441 |
ffee | +5.103 |
utenant | +5.091 |
Neg logit contributions | |
Yang | -4.068 |
ni | -3.950 |
NES | -3.845 |
Pokemon | -3.619 |
Num | -3.587 |
Token | so |
Token ID | 523 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
�� | +1.703 |
apo | +1.602 |
antha | +1.546 |
mosqu | +1.484 |
utenant | +1.476 |
Neg logit contributions | |
ni | -0.959 |
Yang | -0.944 |
NES | -0.884 |
erers | -0.866 |
Pokemon | -0.838 |
Token | you |
Token ID | 345 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
�� | +0.511 |
apo | +0.474 |
antha | +0.457 |
mosqu | +0.438 |
utenant | +0.434 |
Neg logit contributions | |
ni | -0.390 |
Yang | -0.384 |
NES | -0.362 |
erers | -0.360 |
Pokemon | -0.348 |
Token | may |
Token ID | 743 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
ni | +0.166 |
Yang | +0.162 |
NES | +0.151 |
erers | +0.150 |
Pokemon | +0.143 |
Neg logit contributions | |
�� | -0.309 |
apo | -0.290 |
antha | -0.281 |
mosqu | -0.271 |
utenant | -0.268 |
Token | want |
Token ID | 765 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ni | +1.043 |
Yang | +0.997 |
NES | +0.946 |
erers | +0.933 |
Li | +0.885 |
Neg logit contributions | |
�� | -1.861 |
apo | -1.735 |
antha | -1.679 |
mosqu | -1.639 |
utenant | -1.587 |
Token | govern |
Token ID | 47866 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
�� | +0.369 |
apo | +0.343 |
antha | +0.329 |
mosqu | +0.314 |
utenant | +0.312 |
Neg logit contributions | |
ni | -0.302 |
Yang | -0.298 |
NES | -0.283 |
erers | -0.278 |
Pokemon | -0.272 |
Token | ed |
Token ID | 276 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
�� | +1.000 |
apo | +0.935 |
antha | +0.900 |
mosqu | +0.860 |
utenant | +0.854 |
Neg logit contributions | |
ni | -0.702 |
Yang | -0.694 |
NES | -0.655 |
erers | -0.644 |
Pokemon | -0.627 |
Token | organisation |
Token ID | 12684 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ni | +0.358 |
Yang | +0.354 |
NES | +0.335 |
erers | +0.329 |
Pokemon | +0.321 |
Neg logit contributions | |
�� | -0.430 |
apo | -0.398 |
antha | -0.382 |
utenant | -0.361 |
mosqu | -0.361 |
Token | " |
Token ID | 366 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�� | +0.946 |
apo | +0.884 |
antha | +0.854 |
mosqu | +0.820 |
utenant | +0.815 |
Neg logit contributions | |
ni | -0.561 |
Yang | -0.554 |
NES | -0.518 |
erers | -0.508 |
Pokemon | -0.492 |
Token | del |
Token ID | 12381 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
�� | +0.393 |
apo | +0.365 |
antha | +0.351 |
mosqu | +0.335 |
utenant | +0.333 |
Neg logit contributions | |
ni | -0.304 |
Yang | -0.301 |
NES | -0.285 |
erers | -0.279 |
Pokemon | -0.273 |
Token | ivers |
Token ID | 1191 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
�� | +1.400 |
apo | +1.286 |
antha | +1.210 |
mosqu | +1.126 |
utenant | +1.124 |
Neg logit contributions | |
ni | -1.931 |
Yang | -1.925 |
NES | -1.851 |
erers | -1.821 |
Pokemon | -1.791 |
Token | emergency |
Token ID | 6334 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
�� | +5.502 |
apo | +5.289 |
antha | +5.076 |
mosqu | +4.835 |
utenant | +4.800 |
Neg logit contributions | |
ni | -4.091 |
Yang | -4.079 |
NES | -3.914 |
erers | -3.782 |
Pokemon | -3.752 |
Token | aid |
Token ID | 6133 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
�� | +1.868 |
apo | +1.758 |
antha | +1.697 |
mosqu | +1.626 |
utenant | +1.618 |
Neg logit contributions | |
ni | -1.086 |
Yang | -1.072 |
NES | -1.007 |
erers | -0.985 |
Pokemon | -0.956 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
�� | +1.180 |
apo | +1.108 |
antha | +1.069 |
mosqu | +1.023 |
utenant | +1.018 |
Neg logit contributions | |
ni | -0.724 |
Yang | -0.715 |
NES | -0.672 |
erers | -0.658 |
Pokemon | -0.639 |
Token | people |
Token ID | 661 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
�� | +0.459 |
apo | +0.423 |
antha | +0.405 |
mosqu | +0.386 |
utenant | +0.384 |
Neg logit contributions | |
ni | -0.380 |
Yang | -0.374 |
NES | -0.354 |
erers | -0.350 |
Pokemon | -0.338 |
Token | affected |
Token ID | 5676 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ni | +0.098 |
Yang | +0.097 |
NES | +0.092 |
erers | +0.090 |
Pokemon | +0.088 |
Neg logit contributions | |
�� | -0.133 |
apo | -0.124 |
antha | -0.119 |
mosqu | -0.114 |
utenant | -0.113 |
Token | oit |
Token ID | 30711 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
�� | +0.465 |
apo | +0.422 |
antha | +0.410 |
mosqu | +0.392 |
utenant | +0.387 |
Neg logit contributions | |
ni | -0.366 |
Yang | -0.357 |
NES | -0.335 |
erers | -0.332 |
Pokemon | -0.323 |
Token | , |
Token ID | 11 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
�� | +2.195 |
apo | +2.082 |
antha | +1.991 |
mosqu | +1.901 |
utenant | +1.900 |
Neg logit contributions | |
Yang | -1.391 |
ni | -1.391 |
NES | -1.299 |
erers | -1.277 |
Pokemon | -1.244 |
Token | F |
Token ID | 376 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
ni | +0.105 |
Yang | +0.103 |
NES | +0.098 |
erers | +0.096 |
Pokemon | +0.093 |
Neg logit contributions | |
�� | -0.149 |
apo | -0.138 |
antha | -0.133 |
mosqu | -0.128 |
utenant | -0.127 |
Token | ond |
Token ID | 623 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ni | +0.097 |
Yang | +0.095 |
NES | +0.091 |
erers | +0.090 |
Pokemon | +0.088 |
Neg logit contributions | |
�� | -0.099 |
apo | -0.091 |
antha | -0.087 |
mosqu | -0.083 |
utenant | -0.082 |
Token | du |
Token ID | 7043 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ni | +0.998 |
Yang | +0.945 |
erers | +0.915 |
NES | +0.874 |
Li | +0.829 |
Neg logit contributions | |
�� | -2.342 |
antha | -2.102 |
apo | -2.100 |
mosqu | -2.037 |
utenant | -2.001 |
Token | Lac |
Token ID | 23115 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
�� | +2.237 |
apo | +2.067 |
antha | +1.943 |
utenant | +1.853 |
mosqu | +1.853 |
Neg logit contributions | |
ni | -2.632 |
Yang | -2.616 |
NES | -2.515 |
erers | -2.473 |
Pokemon | -2.422 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
�� | +5.441 |
apo | +5.248 |
antha | +4.946 |
utenant | +4.790 |
mosqu | +4.703 |
Neg logit contributions | |
Yang | -3.890 |
ni | -3.835 |
NES | -3.670 |
Pokemon | -3.550 |
erers | -3.532 |
Token | Green |
Token ID | 3469 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
ni | +0.218 |
Yang | +0.215 |
NES | +0.203 |
erers | +0.199 |
Pokemon | +0.194 |
Neg logit contributions | |
�� | -0.307 |
apo | -0.286 |
antha | -0.276 |
mosqu | -0.264 |
utenant | -0.261 |
Token | Bay |
Token ID | 4696 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
�� | +1.037 |
apo | +0.962 |
antha | +0.922 |
mosqu | +0.875 |
utenant | +0.869 |
Neg logit contributions | |
ni | -0.927 |
Yang | -0.917 |
NES | -0.873 |
erers | -0.859 |
Pokemon | -0.839 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
�� | +1.540 |
apo | +1.456 |
antha | +1.401 |
mosqu | +1.335 |
utenant | +1.334 |
Neg logit contributions | |
Yang | -0.968 |
ni | -0.966 |
NES | -0.900 |
erers | -0.885 |
Pokemon | -0.870 |
Token | Ken |
Token ID | 7148 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ni | +0.013 |
Yang | +0.013 |
NES | +0.012 |
erers | +0.012 |
Pokemon | +0.012 |
Neg logit contributions | |
�� | -0.019 |
apo | -0.018 |
antha | -0.017 |
mosqu | -0.017 |
utenant | -0.017 |
Token | officers |
Token ID | 3790 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
�� | +0.961 |
apo | +0.899 |
antha | +0.865 |
mosqu | +0.825 |
utenant | +0.820 |
Neg logit contributions | |
ni | -0.699 |
Yang | -0.692 |
NES | -0.654 |
erers | -0.642 |
Pokemon | -0.626 |
Token | from |
Token ID | 422 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
�� | +0.177 |
apo | +0.166 |
antha | +0.160 |
mosqu | +0.153 |
utenant | +0.152 |
Neg logit contributions | |
ni | -0.115 |
Yang | -0.114 |
NES | -0.107 |
erers | -0.105 |
Pokemon | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
�� | +0.675 |
apo | +0.628 |
antha | +0.602 |
mosqu | +0.572 |
utenant | +0.569 |
Neg logit contributions | |
ni | -0.571 |
Yang | -0.565 |
NES | -0.537 |
erers | -0.528 |
Pokemon | -0.516 |
Token | Anaheim |
Token ID | 31100 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
�� | +0.433 |
apo | +0.404 |
antha | +0.389 |
mosqu | +0.371 |
utenant | +0.369 |
Neg logit contributions | |
ni | -0.319 |
Yang | -0.315 |
NES | -0.298 |
erers | -0.293 |
Pokemon | -0.285 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ni | +0.370 |
Yang | +0.367 |
NES | +0.349 |
erers | +0.344 |
Pokemon | +0.336 |
Neg logit contributions | |
�� | -0.396 |
apo | -0.367 |
antha | -0.351 |
mosqu | -0.333 |
utenant | -0.330 |
Token | Santa |
Token ID | 8909 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
�� | +0.273 |
apo | +0.254 |
antha | +0.244 |
mosqu | +0.233 |
utenant | +0.230 |
Neg logit contributions | |
ni | -0.225 |
Yang | -0.223 |
NES | -0.211 |
erers | -0.208 |
Pokemon | -0.203 |
Token | Ana |
Token ID | 17639 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
�� | +4.027 |
apo | +3.778 |
antha | +3.558 |
mosqu | +3.347 |
utenant | +3.315 |
Neg logit contributions | |
ni | -5.396 |
Yang | -5.381 |
NES | -5.279 |
erers | -5.156 |
Pokemon | -5.074 |
Token | police |
Token ID | 1644 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
�� | +1.566 |
apo | +1.461 |
antha | +1.391 |
mosqu | +1.322 |
utenant | +1.313 |
Neg logit contributions | |
ni | -1.457 |
Yang | -1.447 |
NES | -1.381 |
erers | -1.359 |
Pokemon | -1.328 |
Token | departments |
Token ID | 13346 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ni | +0.540 |
Yang | +0.529 |
NES | +0.500 |
erers | +0.490 |
Pokemon | +0.476 |
Neg logit contributions | |
�� | -0.776 |
apo | -0.718 |
antha | -0.696 |
mosqu | -0.661 |
utenant | -0.658 |
Token | attempted |
Token ID | 7482 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
�� | +0.255 |
apo | +0.239 |
antha | +0.230 |
mosqu | +0.220 |
utenant | +0.219 |
Neg logit contributions | |
ni | -0.163 |
Yang | -0.161 |
NES | -0.151 |
erers | -0.148 |
Pokemon | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ni | +1.501 |
Yang | +1.486 |
NES | +1.411 |
erers | +1.384 |
Pokemon | +1.347 |
Neg logit contributions | |
�� | -1.899 |
apo | -1.778 |
antha | -1.700 |
mosqu | -1.624 |
utenant | -1.614 |
Token | himself |
Token ID | 2241 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
�� | +0.057 |
apo | +0.053 |
antha | +0.051 |
mosqu | +0.049 |
utenant | +0.049 |
Neg logit contributions | |
ni | -0.035 |
Yang | -0.034 |
NES | -0.032 |
erers | -0.032 |
Pokemon | -0.031 |
Token | down |
Token ID | 866 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
ni | +0.957 |
Yang | +0.920 |
NES | +0.856 |
erers | +0.850 |
Num | +0.823 |
Neg logit contributions | |
�� | -1.451 |
apo | -1.358 |
antha | -1.304 |
mosqu | -1.278 |
aples | -1.238 |
Token | in |
Token ID | 287 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ni | +0.012 |
Yang | +0.012 |
NES | +0.011 |
erers | +0.011 |
Pokemon | +0.011 |
Neg logit contributions | |
�� | -0.018 |
apo | -0.017 |
antha | -0.016 |
mosqu | -0.015 |
utenant | -0.015 |
Token | Anton |
Token ID | 9261 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ni | +0.238 |
Yang | +0.233 |
NES | +0.219 |
erers | +0.215 |
Pokemon | +0.209 |
Neg logit contributions | |
�� | -0.331 |
apo | -0.307 |
antha | -0.297 |
mosqu | -0.283 |
utenant | -0.280 |
Token | in |
Token ID | 259 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
�� | +1.903 |
apo | +1.769 |
antha | +1.699 |
mosqu | +1.623 |
utenant | +1.611 |
Neg logit contributions | |
ni | -1.495 |
Yang | -1.476 |
NES | -1.395 |
erers | -1.376 |
Pokemon | -1.337 |
Token | Scalia |
Token ID | 32575 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ni | +0.508 |
Yang | +0.494 |
NES | +0.472 |
erers | +0.468 |
Num | +0.465 |
Neg logit contributions | |
�� | -0.369 |
apo | -0.330 |
mosqu | -0.305 |
antha | -0.300 |
utenant | -0.294 |
Token | � |
Token ID | 447 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
�� | +4.994 |
apo | +4.627 |
antha | +4.428 |
utenant | +4.199 |
mosqu | +4.181 |
Neg logit contributions | |
Yang | -4.428 |
ni | -4.397 |
NES | -4.269 |
erers | -4.157 |
Pokemon | -4.100 |
Token | � |
Token ID | 247 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
�� | +0.464 |
apo | +0.440 |
antha | +0.424 |
mosqu | +0.404 |
utenant | +0.400 |
Neg logit contributions | |
ni | -0.353 |
Yang | -0.349 |
NES | -0.329 |
erers | -0.324 |
Pokemon | -0.315 |
Token | s |
Token ID | 82 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
�� | +0.179 |
apo | +0.168 |
antha | +0.162 |
mosqu | +0.156 |
utenant | +0.154 |
Neg logit contributions | |
ni | -0.116 |
Yang | -0.113 |
NES | -0.106 |
erers | -0.105 |
Pokemon | -0.101 |
Token | seat |
Token ID | 5852 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
�� | +0.089 |
apo | +0.084 |
antha | +0.081 |
mosqu | +0.077 |
utenant | +0.077 |
Neg logit contributions | |
ni | -0.059 |
Yang | -0.058 |
NES | -0.054 |
erers | -0.053 |
Pokemon | -0.052 |
Token | without |
Token ID | 1231 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
�� | +1.359 |
apo | +1.277 |
antha | +1.232 |
mosqu | +1.179 |
utenant | +1.173 |
Neg logit contributions | |
ni | -0.826 |
Yang | -0.815 |
NES | -0.766 |
erers | -0.751 |
Pokemon | -0.729 |
Token | been |
Token ID | 587 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
�� | +0.318 |
apo | +0.299 |
antha | +0.286 |
mosqu | +0.275 |
utenant | +0.273 |
Neg logit contributions | |
ni | -0.209 |
Yang | -0.205 |
NES | -0.194 |
erers | -0.191 |
Pokemon | -0.184 |
Token | photographed |
Token ID | 25880 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
ni | +0.443 |
Yang | +0.433 |
NES | +0.410 |
erers | +0.404 |
Pokemon | +0.391 |
Neg logit contributions | |
�� | -0.616 |
apo | -0.578 |
antha | -0.553 |
mosqu | -0.531 |
utenant | -0.526 |
Token | receiving |
Token ID | 6464 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ni | +1.344 |
Yang | +1.311 |
NES | +1.223 |
erers | +1.219 |
Li | +1.180 |
Neg logit contributions | |
�� | -2.047 |
apo | -1.922 |
antha | -1.824 |
mosqu | -1.754 |
utenant | -1.751 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
�� | +3.181 |
apo | +2.988 |
antha | +2.871 |
mosqu | +2.733 |
utenant | +2.714 |
Neg logit contributions | |
ni | -2.458 |
Yang | -2.442 |
NES | -2.314 |
erers | -2.270 |
Pokemon | -2.214 |
Token | business |
Token ID | 1597 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
�� | +0.301 |
apo | +0.281 |
antha | +0.268 |
mosqu | +0.257 |
utenant | +0.257 |
Neg logit contributions | |
ni | -0.208 |
Yang | -0.204 |
NES | -0.192 |
erers | -0.189 |
Pokemon | -0.183 |
Token | award |
Token ID | 5764 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
�� | +1.133 |
apo | +1.059 |
antha | +1.016 |
mosqu | +0.974 |
utenant | +0.969 |
Neg logit contributions | |
ni | -0.769 |
Yang | -0.757 |
NES | -0.713 |
erers | -0.700 |
Pokemon | -0.680 |
Token | from |
Token ID | 422 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
�� | +5.422 |
apo | +5.172 |
antha | +5.013 |
utenant | +4.703 |
mosqu | +4.679 |
Neg logit contributions | |
Yang | -3.872 |
ni | -3.848 |
NES | -3.649 |
erers | -3.592 |
Pokemon | -3.516 |
Token | Theresa |
Token ID | 20251 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
�� | +0.654 |
apo | +0.608 |
antha | +0.582 |
mosqu | +0.554 |
utenant | +0.550 |
Neg logit contributions | |
ni | -0.559 |
Yang | -0.552 |
NES | -0.525 |
erers | -0.517 |
Pokemon | -0.504 |
Token | May |
Token ID | 1737 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ni | +1.259 |
Yang | +1.238 |
NES | +1.147 |
erers | +1.120 |
Li | +1.066 |
Neg logit contributions | |
�� | -2.557 |
apo | -2.401 |
antha | -2.350 |
mosqu | -2.254 |
utenant | -2.234 |
Token | and |
Token ID | 290 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
ni | +0.640 |
Yang | +0.625 |
NES | +0.587 |
erers | +0.577 |
Pokemon | +0.556 |
Neg logit contributions | |
�� | -0.963 |
apo | -0.893 |
antha | -0.866 |
mosqu | -0.830 |
utenant | -0.822 |
Token | his |
Token ID | 465 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
ni | +0.006 |
Yang | +0.006 |
NES | +0.006 |
erers | +0.006 |
Pokemon | +0.005 |
Neg logit contributions | |
�� | -0.009 |
apo | -0.008 |
antha | -0.008 |
mosqu | -0.007 |
utenant | -0.007 |
Token | full |
Token ID | 1336 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ni | +0.354 |
Yang | +0.346 |
NES | +0.330 |
erers | +0.323 |
Pokemon | +0.312 |
Neg logit contributions | |
�� | -0.478 |
apo | -0.443 |
antha | -0.427 |
mosqu | -0.411 |
utenant | -0.406 |
Token | list |
Token ID | 1351 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ni | +0.197 |
Yang | +0.194 |
NES | +0.184 |
erers | +0.179 |
Pokemon | +0.173 |
Neg logit contributions | |
�� | -0.294 |
apo | -0.274 |
antha | -0.264 |
mosqu | -0.253 |
utenant | -0.252 |
Token | of |
Token ID | 286 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
ni | +0.733 |
Yang | +0.725 |
NES | +0.676 |
erers | +0.663 |
Pokemon | +0.643 |
Neg logit contributions | |
�� | -1.369 |
apo | -1.291 |
antha | -1.246 |
mosqu | -1.194 |
utenant | -1.191 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
�� | +0.092 |
apo | +0.084 |
antha | +0.080 |
mosqu | +0.076 |
utenant | +0.075 |
Neg logit contributions | |
ni | -0.094 |
Yang | -0.092 |
NES | -0.089 |
erers | -0.087 |
Num | -0.085 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
�� | +0.228 |
apo | +0.211 |
antha | +0.201 |
mosqu | +0.192 |
utenant | +0.192 |
Neg logit contributions | |
ni | -0.202 |
Yang | -0.198 |
NES | -0.190 |
erers | -0.187 |
Num | -0.181 |
Token | award |
Token ID | 5764 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
�� | +0.571 |
apo | +0.529 |
antha | +0.505 |
mosqu | +0.482 |
utenant | +0.480 |
Neg logit contributions | |
ni | -0.539 |
Yang | -0.528 |
NES | -0.507 |
erers | -0.499 |
Num | -0.485 |
Token | winners |
Token ID | 14591 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
�� | +4.221 |
apo | +3.925 |
antha | +3.795 |
mosqu | +3.524 |
utenant | +3.442 |
Neg logit contributions | |
Yang | -5.017 |
ni | -4.956 |
NES | -4.833 |
Pokemon | -4.679 |
erers | -4.650 |
Token | ( |
Token ID | 357 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
�� | +1.122 |
apo | +1.061 |
antha | +1.022 |
mosqu | +0.975 |
utenant | +0.972 |
Neg logit contributions | |
ni | -0.658 |
Yang | -0.651 |
NES | -0.614 |
erers | -0.599 |
Pokemon | -0.581 |
Token | as |
Token ID | 292 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
�� | +0.015 |
apo | +0.014 |
antha | +0.013 |
mosqu | +0.013 |
utenant | +0.012 |
Neg logit contributions | |
ni | -0.011 |
Yang | -0.011 |
NES | -0.011 |
erers | -0.011 |
Pokemon | -0.010 |
Token | well |
Token ID | 880 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
�� | +0.879 |
apo | +0.830 |
antha | +0.803 |
mosqu | +0.773 |
utenant | +0.768 |
Neg logit contributions | |
ni | -0.421 |
Yang | -0.414 |
NES | -0.385 |
erers | -0.376 |
Pokemon | -0.363 |
Token | as |
Token ID | 355 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ni | +0.523 |
Yang | +0.518 |
NES | +0.487 |
erers | +0.479 |
Pokemon | +0.463 |
Neg logit contributions | |
�� | -0.797 |
apo | -0.736 |
antha | -0.714 |
mosqu | -0.697 |
utenant | -0.674 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
�� | +0.263 |
apo | +0.244 |
antha | +0.235 |
mosqu | +0.223 |
utenant | +0.222 |
Neg logit contributions | |
ni | -0.211 |
Yang | -0.209 |
NES | -0.198 |
erers | -0.195 |
Pokemon | -0.190 |
Token | University |
Token ID | 2059 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
ni | +0.220 |
Yang | +0.217 |
NES | +0.205 |
erers | +0.200 |
Pokemon | +0.194 |
Neg logit contributions | |
�� | -0.348 |
apo | -0.324 |
antha | -0.313 |
mosqu | -0.300 |
utenant | -0.299 |
Token | of |
Token ID | 286 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ni | +0.034 |
Yang | +0.033 |
NES | +0.031 |
erers | +0.030 |
Pokemon | +0.029 |
Neg logit contributions | |
�� | -0.073 |
apo | -0.068 |
antha | -0.066 |
mosqu | -0.064 |
utenant | -0.063 |
Token | California |
Token ID | 3442 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ni | +0.240 |
Yang | +0.237 |
NES | +0.224 |
erers | +0.219 |
Pokemon | +0.213 |
Neg logit contributions | |
�� | -0.363 |
apo | -0.340 |
antha | -0.327 |
mosqu | -0.313 |
utenant | -0.311 |
Token | , |
Token ID | 11 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
�� | +0.855 |
apo | +0.803 |
antha | +0.771 |
mosqu | +0.737 |
utenant | +0.733 |
Neg logit contributions | |
ni | -0.568 |
Yang | -0.560 |
NES | -0.528 |
erers | -0.520 |
Pokemon | -0.506 |
Token | Santa |
Token ID | 8909 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
�� | +0.169 |
apo | +0.157 |
antha | +0.149 |
mosqu | +0.141 |
utenant | +0.140 |
Neg logit contributions | |
ni | -0.173 |
Yang | -0.171 |
NES | -0.164 |
erers | -0.161 |
Pokemon | -0.158 |
Token | Barbara |
Token ID | 16685 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
�� | +4.109 |
apo | +3.915 |
antha | +3.625 |
mosqu | +3.431 |
utenant | +3.376 |
Neg logit contributions | |
ni | -5.105 |
Yang | -5.103 |
NES | -4.974 |
erers | -4.891 |
Pokemon | -4.822 |
Token | , |
Token ID | 11 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
�� | +0.868 |
apo | +0.820 |
antha | +0.788 |
mosqu | +0.754 |
utenant | +0.749 |
Neg logit contributions | |
ni | -0.531 |
Yang | -0.524 |
NES | -0.495 |
erers | -0.486 |
Pokemon | -0.473 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ni | +0.051 |
Yang | +0.050 |
NES | +0.047 |
erers | +0.046 |
Pokemon | +0.045 |
Neg logit contributions | |
�� | -0.099 |
apo | -0.094 |
antha | -0.091 |
mosqu | -0.087 |
utenant | -0.087 |
Token | an |
Token ID | 281 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
�� | +0.052 |
apo | +0.049 |
antha | +0.048 |
mosqu | +0.045 |
utenant | +0.045 |
Neg logit contributions | |
ni | -0.035 |
Yang | -0.034 |
NES | -0.033 |
erers | -0.032 |
Pokemon | -0.031 |
Token | organizer |
Token ID | 26311 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ni | +0.216 |
Yang | +0.213 |
NES | +0.201 |
erers | +0.197 |
Pokemon | +0.191 |
Neg logit contributions | |
�� | -0.333 |
apo | -0.312 |
antha | -0.300 |
mosqu | -0.287 |
utenant | -0.286 |
Token | can |
Token ID | 460 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
�� | +0.738 |
apo | +0.692 |
antha | +0.668 |
mosqu | +0.640 |
utenant | +0.635 |
Neg logit contributions | |
ni | -0.462 |
Yang | -0.455 |
NES | -0.428 |
erers | -0.421 |
Pokemon | -0.408 |
Token | sur |
Token ID | 969 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ni | +0.391 |
Yang | +0.379 |
NES | +0.360 |
erers | +0.353 |
Pokemon | +0.340 |
Neg logit contributions | |
�� | -0.615 |
apo | -0.571 |
antha | -0.553 |
mosqu | -0.535 |
utenant | -0.523 |
Token | m |
Token ID | 76 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
�� | +0.505 |
apo | +0.466 |
antha | +0.445 |
mosqu | +0.420 |
utenant | +0.417 |
Neg logit contributions | |
ni | -0.525 |
Yang | -0.520 |
NES | -0.496 |
erers | -0.489 |
Pokemon | -0.479 |
Token | ise |
Token ID | 786 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
ni | +0.371 |
Yang | +0.360 |
NES | +0.343 |
erers | +0.336 |
Pokemon | +0.330 |
Neg logit contributions | |
�� | -0.457 |
apo | -0.421 |
antha | -0.402 |
mosqu | -0.385 |
utenant | -0.380 |
Token | that |
Token ID | 326 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
�� | +0.168 |
apo | +0.156 |
antha | +0.150 |
mosqu | +0.143 |
utenant | +0.142 |
Neg logit contributions | |
ni | -0.132 |
Yang | -0.131 |
NES | -0.124 |
erers | -0.122 |
Pokemon | -0.119 |
Token | Lac |
Token ID | 23115 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
�� | +0.594 |
apo | +0.549 |
antha | +0.527 |
mosqu | +0.501 |
utenant | +0.499 |
Neg logit contributions | |
ni | -0.492 |
Yang | -0.488 |
NES | -0.461 |
erers | -0.456 |
Pokemon | -0.444 |
Token | an |
Token ID | 272 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
�� | +4.651 |
apo | +4.350 |
antha | +4.169 |
mosqu | +3.890 |
utenant | +3.876 |
Neg logit contributions | |
ni | -4.618 |
Yang | -4.606 |
NES | -4.418 |
erers | -4.319 |
Pokemon | -4.283 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
�� | +0.731 |
apo | +0.684 |
antha | +0.660 |
mosqu | +0.632 |
utenant | +0.627 |
Neg logit contributions | |
ni | -0.480 |
Yang | -0.472 |
NES | -0.444 |
erers | -0.437 |
Pokemon | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
�� | +1.211 |
apo | +1.129 |
antha | +1.084 |
mosqu | +1.032 |
utenant | +1.026 |
Neg logit contributions | |
ni | -0.951 |
Yang | -0.940 |
NES | -0.891 |
erers | -0.876 |
Pokemon | -0.854 |
Token | analyst |
Token ID | 12499 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
�� | +0.968 |
apo | +0.904 |
antha | +0.869 |
mosqu | +0.828 |
utenant | +0.824 |
Neg logit contributions | |
ni | -0.721 |
Yang | -0.713 |
NES | -0.674 |
erers | -0.663 |
Pokemon | -0.646 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
�� | +2.282 |
apo | +2.133 |
antha | +2.053 |
mosqu | +1.957 |
utenant | +1.947 |
Neg logit contributions | |
ni | -1.674 |
Yang | -1.656 |
NES | -1.568 |
erers | -1.538 |
Pokemon | -1.500 |
Token | F |
Token ID | 376 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
�� | +1.305 |
apo | +1.213 |
antha | +1.162 |
mosqu | +1.101 |
utenant | +1.095 |
Neg logit contributions | |
ni | -1.170 |
Yang | -1.159 |
NES | -1.103 |
erers | -1.086 |
Pokemon | -1.061 |
Token | andom |
Token ID | 3749 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
�� | +0.050 |
apo | +0.046 |
antha | +0.045 |
mosqu | +0.042 |
utenant | +0.042 |
Neg logit contributions | |
ni | -0.037 |
Yang | -0.036 |
NES | -0.034 |
erers | -0.034 |
Pokemon | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ni | +0.578 |
Yang | +0.572 |
NES | +0.544 |
erers | +0.536 |
Pokemon | +0.524 |
Neg logit contributions | |
�� | -0.577 |
apo | -0.533 |
antha | -0.508 |
mosqu | -0.485 |
utenant | -0.478 |
Token | sex |
Token ID | 1714 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
�� | +0.651 |
apo | +0.602 |
antha | +0.575 |
mosqu | +0.547 |
utenant | +0.543 |
Neg logit contributions | |
ni | -0.608 |
Yang | -0.601 |
NES | -0.573 |
erers | -0.563 |
Pokemon | -0.551 |
Token | iest |
Token ID | 6386 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ni | +1.607 |
Yang | +1.576 |
NES | +1.502 |
erers | +1.477 |
Pokemon | +1.442 |
Neg logit contributions | |
�� | -1.580 |
apo | -1.439 |
antha | -1.373 |
mosqu | -1.320 |
utenant | -1.297 |
Token | award |
Token ID | 5764 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ni | +0.488 |
Yang | +0.478 |
NES | +0.458 |
erers | +0.448 |
Pokemon | +0.438 |
Neg logit contributions | |
�� | -0.566 |
apo | -0.525 |
antha | -0.503 |
mosqu | -0.480 |
utenant | -0.476 |
Token | for |
Token ID | 329 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
�� | +5.415 |
apo | +5.071 |
antha | +4.884 |
mosqu | +4.615 |
utenant | +4.586 |
Neg logit contributions | |
Yang | -3.763 |
ni | -3.679 |
NES | -3.500 |
erers | -3.469 |
Pokemon | -3.366 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
�� | +0.500 |
apo | +0.465 |
antha | +0.446 |
mosqu | +0.424 |
utenant | +0.422 |
Neg logit contributions | |
ni | -0.423 |
Yang | -0.417 |
NES | -0.397 |
erers | -0.390 |
Pokemon | -0.381 |
Token | on |
Token ID | 319 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ni | +0.204 |
Yang | +0.200 |
NES | +0.189 |
erers | +0.185 |
Pokemon | +0.180 |
Neg logit contributions | |
�� | -0.319 |
apo | -0.297 |
antha | -0.287 |
mosqu | -0.274 |
utenant | -0.273 |
Token | - |
Token ID | 12 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ni | +0.346 |
Yang | +0.344 |
NES | +0.323 |
erers | +0.318 |
Pokemon | +0.309 |
Neg logit contributions | |
�� | -0.516 |
apo | -0.484 |
antha | -0.466 |
mosqu | -0.445 |
utenant | -0.443 |
Token | screen |
Token ID | 9612 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
�� | +0.298 |
apo | +0.282 |
antha | +0.271 |
mosqu | +0.256 |
utenant | +0.256 |
Neg logit contributions | |
ni | -0.209 |
Yang | -0.208 |
NES | -0.195 |
erers | -0.193 |
Pokemon | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
�� | +1.160 |
apo | +1.082 |
antha | +1.033 |
mosqu | +0.989 |
utenant | +0.982 |
Neg logit contributions | |
ni | -0.889 |
Yang | -0.875 |
NES | -0.829 |
erers | -0.815 |
Pokemon | -0.792 |
Token | full |
Token ID | 1336 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ni | +0.250 |
Yang | +0.246 |
NES | +0.234 |
erers | +0.229 |
Num | +0.223 |
Neg logit contributions | |
�� | -0.318 |
apo | -0.295 |
antha | -0.280 |
mosqu | -0.268 |
utenant | -0.268 |
Token | list |
Token ID | 1351 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ni | +0.248 |
Yang | +0.243 |
NES | +0.230 |
erers | +0.226 |
Pokemon | +0.217 |
Neg logit contributions | |
�� | -0.377 |
apo | -0.352 |
antha | -0.337 |
utenant | -0.324 |
mosqu | -0.323 |
Token | of |
Token ID | 286 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ni | +0.534 |
Yang | +0.528 |
NES | +0.491 |
erers | +0.482 |
Pokemon | +0.468 |
Neg logit contributions | |
�� | -1.003 |
apo | -0.944 |
antha | -0.913 |
mosqu | -0.875 |
utenant | -0.871 |
Token | previous |
Token ID | 2180 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
�� | +0.292 |
apo | +0.267 |
antha | +0.250 |
utenant | +0.237 |
mosqu | +0.237 |
Neg logit contributions | |
ni | -0.310 |
Yang | -0.305 |
NES | -0.291 |
erers | -0.288 |
Num | -0.281 |
Token | award |
Token ID | 5764 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
�� | +0.770 |
apo | +0.708 |
antha | +0.671 |
utenant | +0.636 |
mosqu | +0.635 |
Neg logit contributions | |
ni | -0.761 |
Yang | -0.749 |
NES | -0.715 |
erers | -0.707 |
Pokemon | -0.686 |
Token | winners |
Token ID | 14591 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
�� | +3.873 |
apo | +3.538 |
antha | +3.431 |
mosqu | +3.203 |
utenant | +3.112 |
Neg logit contributions | |
Yang | -5.250 |
ni | -5.200 |
NES | -5.050 |
Pokemon | -4.906 |
erers | -4.897 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
�� | +1.378 |
apo | +1.290 |
antha | +1.243 |
mosqu | +1.178 |
utenant | +1.174 |
Neg logit contributions | |
ni | -1.062 |
Yang | -1.050 |
NES | -0.995 |
erers | -0.981 |
Pokemon | -0.957 |
Token |
|
Token ID | 198 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
ni | +0.257 |
Yang | +0.253 |
NES | +0.238 |
erers | +0.233 |
Pokemon | +0.226 |
Neg logit contributions | |
�� | -0.422 |
apo | -0.395 |
antha | -0.380 |
mosqu | -0.366 |
utenant | -0.363 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ni | +0.139 |
Yang | +0.136 |
NES | +0.127 |
erers | +0.125 |
Pokemon | +0.121 |
Neg logit contributions | |
�� | -0.240 |
apo | -0.222 |
antha | -0.215 |
mosqu | -0.212 |
utenant | -0.204 |
Token | S |
Token ID | 50 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ni | +0.256 |
Yang | +0.254 |
NES | +0.239 |
erers | +0.231 |
Pokemon | +0.228 |
Neg logit contributions | |
�� | -0.380 |
apo | -0.352 |
antha | -0.339 |
mosqu | -0.329 |
utenant | -0.324 |
Token | for |
Token ID | 329 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ni | +0.338 |
Yang | +0.332 |
NES | +0.310 |
erers | +0.306 |
Pokemon | +0.295 |
Neg logit contributions | |
�� | -0.569 |
apo | -0.530 |
antha | -0.511 |
mosqu | -0.491 |
utenant | -0.485 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
�� | +0.523 |
apo | +0.484 |
antha | +0.463 |
mosqu | +0.440 |
utenant | +0.437 |
Neg logit contributions | |
ni | -0.475 |
Yang | -0.469 |
NES | -0.447 |
erers | -0.439 |
Pokemon | -0.429 |
Token | W |
Token ID | 370 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ni | +0.062 |
Yang | +0.062 |
NES | +0.059 |
erers | +0.058 |
Pokemon | +0.057 |
Neg logit contributions | |
�� | -0.059 |
apo | -0.055 |
antha | -0.052 |
mosqu | -0.049 |
utenant | -0.049 |
Token | off |
Token ID | 2364 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
ni | +0.095 |
Yang | +0.094 |
NES | +0.088 |
erers | +0.086 |
Pokemon | +0.083 |
Neg logit contributions | |
�� | -0.162 |
apo | -0.151 |
antha | -0.147 |
mosqu | -0.142 |
utenant | -0.140 |
Token | ord |
Token ID | 585 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ni | +0.457 |
Yang | +0.447 |
NES | +0.425 |
erers | +0.424 |
Pokemon | +0.409 |
Neg logit contributions | |
�� | -0.461 |
apo | -0.417 |
antha | -0.396 |
mosqu | -0.385 |
utenant | -0.378 |
Token | Award |
Token ID | 11289 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ni | +0.670 |
Yang | +0.659 |
NES | +0.626 |
erers | +0.619 |
Pokemon | +0.600 |
Neg logit contributions | |
�� | -0.725 |
apo | -0.669 |
antha | -0.638 |
mosqu | -0.612 |
utenant | -0.606 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e-04 |
Pos logit contributions | |
�� | +5.367 |
apo | +5.065 |
antha | +4.889 |
utenant | +4.562 |
mosqu | +4.556 |
Neg logit contributions | |
ni | -3.674 |
Yang | -3.658 |
NES | -3.510 |
erers | -3.433 |
Pokemon | -3.317 |
Token | please |
Token ID | 3387 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
ni | +0.001 |
Yang | +0.001 |
NES | +0.001 |
erers | +0.001 |
Pokemon | +0.001 |
Neg logit contributions | |
�� | -0.001 |
apo | -0.001 |
antha | -0.001 |
mosqu | -0.001 |
utenant | -0.001 |
Token | download |
Token ID | 4321 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
�� | +0.137 |
apo | +0.129 |
antha | +0.125 |
mosqu | +0.120 |
utenant | +0.119 |
Neg logit contributions | |
ni | -0.067 |
Yang | -0.066 |
NES | -0.061 |
erers | -0.060 |
Pokemon | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
�� | +0.697 |
apo | +0.649 |
antha | +0.622 |
mosqu | +0.593 |
utenant | +0.589 |
Neg logit contributions | |
ni | -0.572 |
Yang | -0.566 |
NES | -0.538 |
erers | -0.528 |
Pokemon | -0.516 |
Token | W |
Token ID | 370 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
�� | +0.474 |
apo | +0.442 |
antha | +0.424 |
mosqu | +0.405 |
utenant | +0.403 |
Neg logit contributions | |
ni | -0.356 |
Yang | -0.351 |
NES | -0.333 |
erers | -0.327 |
Pokemon | -0.318 |
Token | for |
Token ID | 329 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
�� | +0.398 |
apo | +0.374 |
antha | +0.360 |
mosqu | +0.345 |
utenant | +0.344 |
Neg logit contributions | |
ni | -0.237 |
Yang | -0.234 |
NES | -0.220 |
erers | -0.215 |
Pokemon | -0.209 |
Token | consideration |
Token ID | 9110 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
�� | +0.133 |
apo | +0.121 |
antha | +0.114 |
utenant | +0.108 |
mosqu | +0.108 |
Neg logit contributions | |
ni | -0.135 |
Yang | -0.134 |
NES | -0.128 |
erers | -0.126 |
Pokemon | -0.123 |
Token | for |
Token ID | 329 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
�� | +0.986 |
apo | +0.928 |
antha | +0.897 |
mosqu | +0.860 |
utenant | +0.856 |
Neg logit contributions | |
ni | -0.534 |
Yang | -0.526 |
NES | -0.491 |
erers | -0.481 |
Pokemon | -0.466 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
�� | +0.187 |
apo | +0.171 |
antha | +0.162 |
mosqu | +0.154 |
utenant | +0.153 |
Neg logit contributions | |
ni | -0.187 |
Yang | -0.185 |
NES | -0.175 |
erers | -0.173 |
NW | -0.169 |
Token | 2019 |
Token ID | 13130 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
ni | +0.032 |
Yang | +0.032 |
NES | +0.030 |
erers | +0.030 |
Num | +0.029 |
Neg logit contributions | |
�� | -0.031 |
apo | -0.028 |
antha | -0.027 |
mosqu | -0.025 |
utenant | -0.025 |
Token | award |
Token ID | 5764 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
�� | +0.109 |
apo | +0.102 |
antha | +0.097 |
utenant | +0.093 |
mosqu | +0.093 |
Neg logit contributions | |
ni | -0.083 |
Yang | -0.082 |
NES | -0.077 |
erers | -0.076 |
NW | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
�� | +5.519 |
apo | +5.234 |
antha | +5.042 |
mosqu | +4.856 |
utenant | +4.775 |
Neg logit contributions | |
Yang | -3.447 |
ni | -3.432 |
NES | -3.289 |
erers | -3.109 |
Pokemon | -3.066 |
Token | December |
Token ID | 3426 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
�� | +0.579 |
apo | +0.543 |
antha | +0.525 |
mosqu | +0.504 |
utenant | +0.500 |
Neg logit contributions | |
ni | -0.309 |
Yang | -0.304 |
NES | -0.285 |
erers | -0.278 |
Pokemon | -0.268 |
Token | 21 |
Token ID | 2310 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
ni | +0.268 |
Yang | +0.263 |
NES | +0.244 |
erers | +0.237 |
Pokemon | +0.229 |
Neg logit contributions | |
�� | -0.575 |
apo | -0.536 |
antha | -0.518 |
mosqu | -0.510 |
utenant | -0.498 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
ni | +0.518 |
Yang | +0.509 |
NES | +0.478 |
erers | +0.468 |
Pokemon | +0.451 |
Neg logit contributions | |
�� | -0.938 |
apo | -0.883 |
antha | -0.855 |
mosqu | -0.820 |
utenant | -0.816 |
Token | 2018 |
Token ID | 2864 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ni | +0.548 |
Yang | +0.540 |
NES | +0.515 |
erers | +0.508 |
Pokemon | +0.495 |
Neg logit contributions | |
�� | -0.581 |
apo | -0.532 |
antha | -0.508 |
mosqu | -0.485 |
utenant | -0.479 |
Token | year |
Token ID | 1941 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ni | +0.738 |
Yang | +0.727 |
NES | +0.691 |
erers | +0.684 |
Pokemon | +0.675 |
Neg logit contributions | |
�� | -0.579 |
apo | -0.501 |
antha | -0.489 |
mosqu | -0.487 |
utenant | -0.446 |
Token | - |
Token ID | 12 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
ni | +1.116 |
Yang | +1.085 |
erers | +0.998 |
NES | +0.994 |
CG | +0.960 |
Neg logit contributions | |
�� | -2.099 |
apo | -1.951 |
antha | -1.896 |
mosqu | -1.850 |
aples | -1.784 |
Token | old |
Token ID | 727 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ni | +0.079 |
Yang | +0.078 |
NES | +0.074 |
erers | +0.073 |
Pokemon | +0.072 |
Neg logit contributions | |
�� | -0.075 |
apo | -0.068 |
antha | -0.065 |
mosqu | -0.064 |
utenant | -0.061 |
Token | N |
Token ID | 399 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ni | +1.748 |
Yang | +1.731 |
NES | +1.605 |
erers | +1.598 |
Li | +1.554 |
Neg logit contributions | |
�� | -2.329 |
apo | -2.148 |
antha | -2.051 |
mosqu | -1.957 |
utenant | -1.940 |
Token | eng |
Token ID | 1516 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
�� | +1.060 |
apo | +0.996 |
antha | +0.954 |
utenant | +0.900 |
mosqu | +0.899 |
Neg logit contributions | |
ni | -0.871 |
Yang | -0.866 |
NES | -0.825 |
erers | -0.808 |
Pokemon | -0.793 |
Token | Mou |
Token ID | 49902 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
�� | +0.006 |
apo | +0.006 |
antha | +0.005 |
mosqu | +0.005 |
utenant | +0.005 |
Neg logit contributions | |
ni | -0.004 |
Yang | -0.004 |
NES | -0.004 |
erers | -0.004 |
Pokemon | -0.003 |
Token | a |
Token ID | 64 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
�� | +5.292 |
apo | +5.121 |
antha | +4.898 |
utenant | +4.671 |
mosqu | +4.618 |
Neg logit contributions | |
ni | -3.537 |
Yang | -3.535 |
NES | -3.403 |
erers | -3.320 |
Pokemon | -3.319 |
Token | shot |
Token ID | 2823 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
�� | +0.687 |
apo | +0.645 |
antha | +0.622 |
mosqu | +0.595 |
utenant | +0.592 |
Neg logit contributions | |
ni | -0.424 |
Yang | -0.419 |
NES | -0.393 |
erers | -0.386 |
Pokemon | -0.374 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ni | +0.156 |
Yang | +0.154 |
NES | +0.143 |
erers | +0.141 |
Pokemon | +0.136 |
Neg logit contributions | |
�� | -0.260 |
apo | -0.243 |
antha | -0.234 |
mosqu | -0.224 |
utenant | -0.223 |
Token | killed |
Token ID | 2923 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
�� | +0.027 |
apo | +0.025 |
antha | +0.023 |
mosqu | +0.022 |
utenant | +0.022 |
Neg logit contributions | |
ni | -0.035 |
Yang | -0.034 |
NES | -0.033 |
erers | -0.033 |
Pokemon | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
�� | +1.996 |
apo | +1.879 |
antha | +1.807 |
mosqu | +1.728 |
utenant | +1.720 |
Neg logit contributions | |
ni | -1.431 |
Yang | -1.416 |
NES | -1.348 |
erers | -1.322 |
Pokemon | -1.289 |
Token | California |
Token ID | 3442 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
�� | +1.039 |
apo | +0.963 |
antha | +0.921 |
mosqu | +0.874 |
utenant | +0.868 |
Neg logit contributions | |
ni | -0.959 |
Yang | -0.949 |
NES | -0.905 |
erers | -0.890 |
Pokemon | -0.870 |
Token | 's |
Token ID | 338 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
�� | +1.151 |
apo | +1.083 |
antha | +1.044 |
mosqu | +1.001 |
utenant | +0.996 |
Neg logit contributions | |
ni | -0.679 |
Yang | -0.671 |
NES | -0.628 |
erers | -0.616 |
Pokemon | -0.597 |
Token | Great |
Token ID | 3878 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
�� | +1.123 |
apo | +1.049 |
antha | +1.008 |
mosqu | +0.961 |
utenant | +0.956 |
Neg logit contributions | |
ni | -0.851 |
Yang | -0.843 |
NES | -0.798 |
erers | -0.784 |
Pokemon | -0.764 |
Token | America |
Token ID | 2253 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ni | +1.403 |
Yang | +1.387 |
NES | +1.301 |
erers | +1.280 |
Pokemon | +1.257 |
Neg logit contributions | |
�� | -1.710 |
apo | -1.571 |
antha | -1.513 |
mosqu | -1.453 |
utenant | -1.440 |
Token | in |
Token ID | 287 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ni | +0.913 |
Yang | +0.897 |
NES | +0.849 |
erers | +0.834 |
Pokemon | +0.811 |
Neg logit contributions | |
�� | -1.302 |
apo | -1.211 |
antha | -1.166 |
mosqu | -1.111 |
utenant | -1.111 |
Token | Santa |
Token ID | 8909 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ni | +0.356 |
Yang | +0.350 |
NES | +0.334 |
erers | +0.327 |
Pokemon | +0.321 |
Neg logit contributions | |
�� | -0.419 |
apo | -0.388 |
antha | -0.371 |
mosqu | -0.356 |
utenant | -0.349 |
Token | Clara |
Token ID | 27443 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
�� | +4.067 |
apo | +3.820 |
antha | +3.641 |
mosqu | +3.432 |
utenant | +3.402 |
Neg logit contributions | |
ni | -4.831 |
Yang | -4.815 |
NES | -4.658 |
erers | -4.614 |
Pokemon | -4.472 |
Token | , |
Token ID | 11 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
�� | +0.827 |
apo | +0.775 |
antha | +0.748 |
mosqu | +0.716 |
utenant | +0.711 |
Neg logit contributions | |
ni | -0.517 |
Yang | -0.510 |
NES | -0.480 |
erers | -0.470 |
Pokemon | -0.457 |
Token | California |
Token ID | 3442 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
�� | +0.173 |
apo | +0.162 |
antha | +0.156 |
mosqu | +0.149 |
utenant | +0.148 |
Neg logit contributions | |
ni | -0.126 |
Yang | -0.125 |
NES | -0.118 |
erers | -0.116 |
Pokemon | -0.113 |
Token | was |
Token ID | 373 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
�� | +1.059 |
apo | +0.997 |
antha | +0.961 |
mosqu | +0.920 |
utenant | +0.917 |
Neg logit contributions | |
ni | -0.637 |
Yang | -0.630 |
NES | -0.591 |
erers | -0.580 |
Pokemon | -0.562 |
Token | originally |
Token ID | 6198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
�� | +1.262 |
apo | +1.184 |
antha | +1.142 |
mosqu | +1.089 |
utenant | +1.087 |
Neg logit contributions | |
ni | -0.839 |
Yang | -0.832 |
NES | -0.782 |
erers | -0.769 |
Pokemon | -0.747 |
Token | email |
Token ID | 3053 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�� | +0.152 |
apo | +0.141 |
antha | +0.134 |
mosqu | +0.128 |
utenant | +0.127 |
Neg logit contributions | |
ni | -0.135 |
Yang | -0.133 |
NES | -0.128 |
erers | -0.125 |
Pokemon | -0.123 |
Token | application |
Token ID | 3586 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
�� | +0.437 |
apo | +0.408 |
antha | +0.390 |
mosqu | +0.376 |
utenant | +0.375 |
Neg logit contributions | |
ni | -0.266 |
Yang | -0.260 |
NES | -0.244 |
erers | -0.237 |
Pokemon | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ni | +0.584 |
Yang | +0.554 |
NES | +0.537 |
erers | +0.519 |
Li | +0.494 |
Neg logit contributions | |
�� | -1.148 |
apo | -1.060 |
mosqu | -1.043 |
antha | -1.034 |
utenant | -0.996 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
�� | +0.346 |
apo | +0.322 |
antha | +0.312 |
mosqu | +0.304 |
utenant | +0.296 |
Neg logit contributions | |
ni | -0.207 |
Yang | -0.204 |
NES | -0.192 |
erers | -0.187 |
Pokemon | -0.182 |
Token | Ass |
Token ID | 8021 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +0.081 |
apo | +0.076 |
antha | +0.073 |
mosqu | +0.070 |
utenant | +0.069 |
Neg logit contributions | |
ni | -0.054 |
Yang | -0.053 |
NES | -0.050 |
erers | -0.049 |
Pokemon | -0.048 |
Token | assin |
Token ID | 44961 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
�� | +1.966 |
apo | +1.814 |
antha | +1.725 |
mosqu | +1.622 |
utenant | +1.613 |
Neg logit contributions | |
ni | -2.222 |
Yang | -2.205 |
NES | -2.110 |
erers | -2.079 |
Pokemon | -2.038 |
Token | � |
Token ID | 447 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
�� | +4.819 |
apo | +4.487 |
antha | +4.318 |
utenant | +4.078 |
mosqu | +4.027 |
Neg logit contributions | |
ni | -4.176 |
Yang | -4.154 |
NES | -3.943 |
erers | -3.880 |
Pokemon | -3.805 |
Token | � |
Token ID | 247 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ni | +0.006 |
Yang | +0.006 |
NES | +0.005 |
erers | +0.005 |
Pokemon | +0.005 |
Neg logit contributions | |
�� | -0.006 |
apo | -0.006 |
antha | -0.005 |
mosqu | -0.005 |
utenant | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
�� | +0.488 |
apo | +0.457 |
antha | +0.440 |
mosqu | +0.421 |
utenant | +0.417 |
Neg logit contributions | |
ni | -0.331 |
Yang | -0.326 |
NES | -0.308 |
erers | -0.302 |
Pokemon | -0.294 |
Token | Creed |
Token ID | 24299 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
�� | +1.090 |
apo | +1.017 |
antha | +0.977 |
mosqu | +0.932 |
utenant | +0.925 |
Neg logit contributions | |
ni | -0.839 |
Yang | -0.828 |
NES | -0.785 |
erers | -0.771 |
Pokemon | -0.752 |
Token | ® |
Token ID | 7461 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
�� | +2.364 |
apo | +2.205 |
antha | +2.120 |
mosqu | +2.014 |
utenant | +2.010 |
Neg logit contributions | |
ni | -1.797 |
Yang | -1.785 |
NES | -1.685 |
erers | -1.662 |
Pokemon | -1.615 |
Token | scrap |
Token ID | 15881 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ni | +0.028 |
Yang | +0.027 |
NES | +0.026 |
erers | +0.025 |
Pokemon | +0.025 |
Neg logit contributions | |
�� | -0.039 |
apo | -0.037 |
antha | -0.035 |
mosqu | -0.034 |
utenant | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ni | +0.156 |
Yang | +0.153 |
NES | +0.144 |
erers | +0.141 |
Pokemon | +0.136 |
Neg logit contributions | |
�� | -0.256 |
apo | -0.240 |
antha | -0.231 |
mosqu | -0.222 |
utenant | -0.221 |
Token |
|
Token ID | 198 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ni | +0.036 |
Yang | +0.036 |
NES | +0.034 |
erers | +0.033 |
Pokemon | +0.032 |
Neg logit contributions | |
�� | -0.051 |
apo | -0.048 |
antha | -0.046 |
mosqu | -0.044 |
utenant | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ni | +0.459 |
Yang | +0.448 |
NES | +0.420 |
erers | +0.409 |
Pokemon | +0.397 |
Neg logit contributions | |
�� | -0.815 |
apo | -0.748 |
antha | -0.729 |
mosqu | -0.724 |
utenant | -0.688 |
Token | Article |
Token ID | 14906 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ni | +0.606 |
Yang | +0.600 |
NES | +0.563 |
erers | +0.549 |
Pokemon | +0.536 |
Neg logit contributions | |
�� | -0.977 |
apo | -0.911 |
antha | -0.882 |
mosqu | -0.852 |
utenant | -0.840 |
Token | Continued |
Token ID | 22168 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ni | +1.172 |
Yang | +1.078 |
NES | +0.937 |
erers | +0.861 |
CG | +0.809 |
Neg logit contributions | |
�� | -6.079 |
apo | -5.762 |
antha | -5.587 |
mosqu | -5.504 |
aples | -5.420 |
Token | Below |
Token ID | 10383 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ni | +2.989 |
Yang | +2.748 |
NES | +2.568 |
Num | +2.558 |
erers | +2.521 |
Neg logit contributions | |
�� | -9.497 |
mosqu | -9.042 |
apo | -8.925 |
antha | -8.570 |
utenant | -8.247 |
Token |
|
Token ID | 198 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
ni | +1.609 |
Yang | +1.573 |
NES | +1.464 |
erers | +1.418 |
Pokemon | +1.390 |
Neg logit contributions | |
�� | -3.214 |
mosqu | -2.964 |
apo | -2.917 |
antha | -2.868 |
utenant | -2.697 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ni | +0.983 |
Yang | +0.960 |
NES | +0.896 |
erers | +0.870 |
Pokemon | +0.846 |
Neg logit contributions | |
�� | -1.834 |
apo | -1.673 |
mosqu | -1.650 |
antha | -1.636 |
utenant | -1.538 |
Token | The |
Token ID | 464 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
ni | +1.068 |
Yang | +1.062 |
NES | +0.995 |
erers | +0.967 |
Pokemon | +0.951 |
Neg logit contributions | |
�� | -1.708 |
apo | -1.585 |
antha | -1.538 |
mosqu | -1.493 |
utenant | -1.462 |
Token | T |
Token ID | 309 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ni | +0.100 |
Yang | +0.099 |
NES | +0.093 |
erers | +0.092 |
Pokemon | +0.089 |
Neg logit contributions | |
�� | -0.157 |
apo | -0.147 |
antha | -0.142 |
mosqu | -0.136 |
utenant | -0.135 |
Token | mess |
Token ID | 2085 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
�� | +0.841 |
apo | +0.787 |
antha | +0.756 |
mosqu | +0.725 |
utenant | +0.717 |
Neg logit contributions | |
ni | -0.588 |
Yang | -0.577 |
NES | -0.547 |
erers | -0.538 |
Pokemon | -0.520 |
Token | seriously |
Token ID | 6411 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
�� | +0.309 |
apo | +0.290 |
antha | +0.281 |
mosqu | +0.273 |
aples | +0.267 |
Neg logit contributions | |
ni | -0.181 |
Yang | -0.175 |
NES | -0.164 |
erers | -0.164 |
Pokemon | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
�� | +1.190 |
apo | +1.116 |
antha | +1.075 |
mosqu | +1.029 |
utenant | +1.023 |
Neg logit contributions | |
ni | -0.778 |
Yang | -0.767 |
NES | -0.723 |
erers | -0.709 |
Pokemon | -0.689 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
�� | +0.352 |
apo | +0.329 |
antha | +0.318 |
mosqu | +0.307 |
utenant | +0.302 |
Neg logit contributions | |
ni | -0.214 |
Yang | -0.211 |
NES | -0.198 |
erers | -0.194 |
Pokemon | -0.189 |
Token | Article |
Token ID | 14906 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ni | +0.071 |
Yang | +0.070 |
NES | +0.065 |
erers | +0.063 |
Pokemon | +0.062 |
Neg logit contributions | |
�� | -0.142 |
apo | -0.133 |
antha | -0.129 |
mosqu | -0.125 |
utenant | -0.123 |
Token | Continued |
Token ID | 22168 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ni | +1.013 |
Yang | +0.895 |
NES | +0.769 |
erers | +0.707 |
CG | +0.666 |
Neg logit contributions | |
�� | -5.823 |
apo | -5.494 |
antha | -5.363 |
mosqu | -5.345 |
DragonMagazine | -5.193 |
Token | Below |
Token ID | 10383 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ni | +2.860 |
Yang | +2.672 |
NES | +2.486 |
Num | +2.453 |
erers | +2.434 |
Neg logit contributions | |
�� | -9.039 |
mosqu | -8.632 |
apo | -8.511 |
antha | -8.184 |
mble | -7.876 |
Token |
|
Token ID | 198 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ni | +1.445 |
Yang | +1.416 |
NES | +1.322 |
erers | +1.280 |
Pokemon | +1.253 |
Neg logit contributions | |
�� | -2.822 |
mosqu | -2.588 |
apo | -2.580 |
antha | -2.534 |
utenant | -2.382 |
Token |
|
Token ID | 198 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ni | +0.668 |
Yang | +0.654 |
NES | +0.611 |
erers | +0.594 |
Pokemon | +0.577 |
Neg logit contributions | |
�� | -1.208 |
apo | -1.110 |
antha | -1.082 |
mosqu | -1.081 |
utenant | -1.019 |
Token | � |
Token ID | 447 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ni | +0.802 |
Yang | +0.795 |
NES | +0.745 |
erers | +0.721 |
Pokemon | +0.711 |
Neg logit contributions | |
�� | -1.247 |
apo | -1.157 |
antha | -1.121 |
mosqu | -1.090 |
utenant | -1.066 |
Token | � |
Token ID | 250 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ni | +0.291 |
Yang | +0.288 |
NES | +0.275 |
erers | +0.271 |
Pokemon | +0.265 |
Neg logit contributions | |
�� | -0.290 |
apo | -0.269 |
antha | -0.257 |
mosqu | -0.243 |
utenant | -0.241 |
Token | last |
Token ID | 938 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
�� | +0.951 |
apo | +0.888 |
antha | +0.853 |
mosqu | +0.814 |
utenant | +0.809 |
Neg logit contributions | |
ni | -0.696 |
Yang | -0.687 |
NES | -0.650 |
erers | -0.639 |
Pokemon | -0.622 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
ni | +0.255 |
Yang | +0.251 |
NES | +0.236 |
erers | +0.232 |
Pokemon | +0.226 |
Neg logit contributions | |
�� | -0.394 |
apo | -0.370 |
antha | -0.355 |
utenant | -0.339 |
mosqu | -0.339 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ni | +0.119 |
Yang | +0.117 |
NES | +0.110 |
erers | +0.107 |
Pokemon | +0.105 |
Neg logit contributions | |
�� | -0.189 |
apo | -0.176 |
antha | -0.170 |
mosqu | -0.164 |
utenant | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ni | +0.153 |
Yang | +0.151 |
NES | +0.141 |
erers | +0.138 |
Pokemon | +0.134 |
Neg logit contributions | |
�� | -0.263 |
apo | -0.243 |
antha | -0.236 |
mosqu | -0.232 |
utenant | -0.223 |
Token | Article |
Token ID | 14906 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ni | +0.324 |
Yang | +0.320 |
NES | +0.298 |
erers | +0.290 |
Pokemon | +0.283 |
Neg logit contributions | |
�� | -0.596 |
apo | -0.560 |
antha | -0.542 |
mosqu | -0.523 |
utenant | -0.518 |
Token | Continued |
Token ID | 22168 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ni | +0.749 |
Yang | +0.726 |
NES | +0.644 |
erers | +0.620 |
Pokemon | +0.593 |
Neg logit contributions | |
�� | -2.521 |
apo | -2.384 |
antha | -2.303 |
mosqu | -2.262 |
utenant | -2.221 |
Token | Below |
Token ID | 10383 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ni | +2.701 |
Yang | +2.451 |
NES | +2.292 |
Num | +2.272 |
erers | +2.223 |
Neg logit contributions | |
�� | -8.851 |
mosqu | -8.354 |
apo | -8.300 |
antha | -7.956 |
utenant | -7.717 |
Token |
|
Token ID | 198 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ni | +1.543 |
Yang | +1.511 |
NES | +1.402 |
erers | +1.357 |
Pokemon | +1.332 |
Neg logit contributions | |
�� | -3.069 |
mosqu | -2.822 |
apo | -2.792 |
antha | -2.737 |
utenant | -2.578 |
Token |
|
Token ID | 198 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ni | +0.848 |
Yang | +0.827 |
NES | +0.773 |
erers | +0.750 |
Pokemon | +0.729 |
Neg logit contributions | |
�� | -1.575 |
apo | -1.440 |
mosqu | -1.414 |
antha | -1.404 |
utenant | -1.321 |
Token | T |
Token ID | 51 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ni | +0.865 |
Yang | +0.859 |
NES | +0.796 |
erers | +0.771 |
Pokemon | +0.764 |
Neg logit contributions | |
�� | -1.498 |
apo | -1.392 |
antha | -1.353 |
mosqu | -1.315 |
utenant | -1.289 |
Token | od |
Token ID | 375 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
ni | +0.710 |
Yang | +0.700 |
NES | +0.665 |
erers | +0.658 |
Pokemon | +0.634 |
Neg logit contributions | |
�� | -0.855 |
apo | -0.785 |
antha | -0.754 |
mosqu | -0.723 |
utenant | -0.716 |
Token | the |
Token ID | 262 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ni | +0.494 |
Yang | +0.489 |
NES | +0.463 |
erers | +0.453 |
Pokemon | +0.444 |
Neg logit contributions | |
�� | -0.632 |
apo | -0.585 |
antha | -0.561 |
utenant | -0.533 |
mosqu | -0.530 |
Token | levels |
Token ID | 2974 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ni | +0.694 |
Yang | +0.689 |
NES | +0.644 |
erers | +0.626 |
Pokemon | +0.615 |
Neg logit contributions | |
�� | -1.076 |
apo | -0.999 |
antha | -0.961 |
utenant | -0.923 |
mosqu | -0.915 |
Token | of |
Token ID | 286 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ni | +0.596 |
Yang | +0.584 |
NES | +0.549 |
erers | +0.540 |
Pokemon | +0.522 |
Neg logit contributions | |
�� | -1.073 |
apo | -1.012 |
antha | -0.975 |
mosqu | -0.940 |
utenant | -0.931 |
Token | uranium |
Token ID | 22010 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ni | +0.510 |
Yang | +0.505 |
NES | +0.471 |
erers | +0.458 |
Pokemon | +0.449 |
Neg logit contributions | |
�� | -0.788 |
apo | -0.728 |
antha | -0.701 |
utenant | -0.672 |
mosqu | -0.664 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ni | +2.875 |
Yang | +2.810 |
NES | +2.603 |
Li | +2.478 |
erers | +2.468 |
Neg logit contributions | |
�� | -5.317 |
apo | -4.876 |
antha | -4.761 |
utenant | -4.581 |
mosqu | -4.536 |
Token | thor |
Token ID | 41899 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ni | +0.297 |
Yang | +0.293 |
NES | +0.275 |
erers | +0.268 |
Pokemon | +0.260 |
Neg logit contributions | |
�� | -0.499 |
apo | -0.467 |
antha | -0.451 |
mosqu | -0.432 |
utenant | -0.431 |
Token | ium |
Token ID | 1505 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ni | +2.486 |
Yang | +2.218 |
NES | +1.900 |
erers | +1.824 |
CG | +1.732 |
Neg logit contributions | |
�� | -8.565 |
apo | -7.800 |
antha | -7.602 |
mosqu | -7.584 |
utenant | -7.422 |
Token | and |
Token ID | 290 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
ni | +1.458 |
Yang | +1.437 |
NES | +1.340 |
erers | +1.310 |
Pokemon | +1.267 |
Neg logit contributions | |
�� | -2.898 |
apo | -2.735 |
antha | -2.644 |
mosqu | -2.540 |
utenant | -2.527 |
Token | lead |
Token ID | 1085 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ni | +0.093 |
Yang | +0.091 |
NES | +0.086 |
erers | +0.084 |
Pokemon | +0.081 |
Neg logit contributions | |
�� | -0.153 |
apo | -0.144 |
antha | -0.139 |
mosqu | -0.133 |
utenant | -0.132 |
Token | present |
Token ID | 1944 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
ni | +0.562 |
Yang | +0.557 |
NES | +0.523 |
erers | +0.513 |
Pokemon | +0.496 |
Neg logit contributions | |
�� | -0.849 |
apo | -0.787 |
antha | -0.762 |
utenant | -0.726 |
mosqu | -0.725 |
Token | in |
Token ID | 287 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
�� | +0.212 |
apo | +0.196 |
antha | +0.188 |
mosqu | +0.181 |
utenant | +0.179 |
Neg logit contributions | |
ni | -0.156 |
Yang | -0.154 |
NES | -0.146 |
erers | -0.143 |
Pokemon | -0.139 |
Token | Club |
Token ID | 6289 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
�� | +2.715 |
apo | +2.514 |
antha | +2.391 |
mosqu | +2.246 |
utenant | +2.236 |
Neg logit contributions | |
ni | -3.008 |
Yang | -2.982 |
NES | -2.861 |
erers | -2.821 |
Pokemon | -2.762 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ni | +0.150 |
Yang | +0.149 |
NES | +0.139 |
erers | +0.136 |
Pokemon | +0.131 |
Neg logit contributions | |
�� | -0.279 |
apo | -0.263 |
antha | -0.254 |
mosqu | -0.244 |
utenant | -0.243 |
Token | Natural |
Token ID | 12068 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
�� | +0.310 |
apo | +0.288 |
antha | +0.277 |
mosqu | +0.265 |
utenant | +0.263 |
Neg logit contributions | |
ni | -0.235 |
Yang | -0.232 |
NES | -0.220 |
erers | -0.216 |
Pokemon | -0.210 |
Token | Resources |
Token ID | 13864 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
ni | +0.543 |
Yang | +0.533 |
NES | +0.494 |
erers | +0.459 |
DO | +0.446 |
Neg logit contributions | |
�� | -1.509 |
apo | -1.427 |
antha | -1.383 |
utenant | -1.337 |
mosqu | -1.335 |
Token | Defense |
Token ID | 5947 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ni | +1.644 |
Yang | +1.621 |
NES | +1.562 |
erers | +1.497 |
Pokemon | +1.492 |
Neg logit contributions | |
�� | -1.774 |
apo | -1.641 |
antha | -1.570 |
mosqu | -1.493 |
utenant | -1.477 |
Token | Coun |
Token ID | 3545 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ni | +2.332 |
Yang | +2.328 |
NES | +2.229 |
erers | +2.186 |
Pokemon | +2.132 |
Neg logit contributions | |
�� | -2.215 |
apo | -2.040 |
antha | -1.935 |
utenant | -1.833 |
mosqu | -1.831 |
Token | ci |
Token ID | 979 |
Feature activation | +8.28e-03 |
Pos logit contributions | |
ni | +4.234 |
Yang | +4.007 |
NES | +3.865 |
erers | +3.725 |
NW | +3.677 |
Neg logit contributions | |
�� | -6.083 |
apo | -5.631 |
antha | -5.440 |
mosqu | -5.279 |
DragonMagazine | -5.177 |
Token | , |
Token ID | 11 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
�� | +0.018 |
apo | +0.016 |
antha | +0.016 |
mosqu | +0.015 |
utenant | +0.015 |
Neg logit contributions | |
ni | -0.015 |
Yang | -0.015 |
NES | -0.014 |
erers | -0.014 |
Pokemon | -0.014 |
Token | World |
Token ID | 2159 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ni | +0.150 |
Yang | +0.148 |
NES | +0.141 |
erers | +0.138 |
Pokemon | +0.134 |
Neg logit contributions | |
�� | -0.203 |
apo | -0.189 |
antha | -0.182 |
mosqu | -0.174 |
utenant | -0.173 |
Token | Wildlife |
Token ID | 18006 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ni | +0.639 |
Yang | +0.630 |
NES | +0.596 |
erers | +0.587 |
Pokemon | +0.571 |
Neg logit contributions | |
�� | -0.830 |
apo | -0.767 |
antha | -0.738 |
mosqu | -0.706 |
utenant | -0.705 |
Token | Fund |
Token ID | 7557 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
�� | +1.780 |
apo | +1.691 |
antha | +1.619 |
mosqu | +1.584 |
aples | +1.554 |
Neg logit contributions | |
ni | -0.884 |
Yang | -0.878 |
NES | -0.825 |
erers | -0.791 |
Pokemon | -0.778 |
Token | . |
Token ID | 13 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ni | +1.302 |
Yang | +1.245 |
NES | +1.162 |
erers | +1.140 |
Pokemon | +1.086 |
Neg logit contributions | |
�� | -2.782 |
apo | -2.523 |
mosqu | -2.506 |
antha | -2.480 |
�醒 | -2.373 |
Token | 8 |
Token ID | 807 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ni | +0.610 |
Yang | +0.596 |
NES | +0.558 |
erers | +0.540 |
Pokemon | +0.526 |
Neg logit contributions | |
�� | -1.198 |
apo | -1.113 |
antha | -1.079 |
mosqu | -1.069 |
utenant | -1.027 |
Token | in |
Token ID | 287 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ni | +0.665 |
Yang | +0.646 |
NES | +0.608 |
erers | +0.593 |
Pokemon | +0.575 |
Neg logit contributions | |
�� | -1.163 |
apo | -1.086 |
antha | -1.054 |
mosqu | -1.016 |
utenant | -1.001 |
Token | Vaughan |
Token ID | 47451 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ni | +0.558 |
Yang | +0.549 |
NES | +0.514 |
erers | +0.504 |
Pokemon | +0.488 |
Neg logit contributions | |
�� | -0.961 |
apo | -0.895 |
antha | -0.866 |
mosqu | -0.836 |
utenant | -0.826 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ni | +1.832 |
Yang | +1.778 |
NES | +1.679 |
erers | +1.632 |
Pokemon | +1.575 |
Neg logit contributions | |
�� | -3.373 |
apo | -3.149 |
antha | -3.053 |
mosqu | -2.933 |
utenant | -2.921 |
Token | Ont |
Token ID | 9463 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ni | +0.317 |
Yang | +0.310 |
NES | +0.285 |
erers | +0.277 |
Pokemon | +0.266 |
Neg logit contributions | |
�� | -0.815 |
apo | -0.770 |
antha | -0.746 |
mosqu | -0.719 |
utenant | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ni | +3.306 |
Yang | +3.140 |
NES | +2.971 |
erers | +2.906 |
Pokemon | +2.744 |
Neg logit contributions | |
�� | -6.827 |
apo | -6.396 |
antha | -6.207 |
mosqu | -5.976 |
utenant | -5.955 |
Token | The |
Token ID | 383 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
ni | +0.196 |
Yang | +0.192 |
NES | +0.182 |
erers | +0.177 |
Pokemon | +0.172 |
Neg logit contributions | |
�� | -0.309 |
apo | -0.287 |
antha | -0.276 |
mosqu | -0.265 |
utenant | -0.262 |
Token | three |
Token ID | 1115 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ni | +0.126 |
Yang | +0.124 |
NES | +0.118 |
erers | +0.116 |
Pokemon | +0.112 |
Neg logit contributions | |
�� | -0.175 |
apo | -0.163 |
antha | -0.156 |
mosqu | -0.149 |
utenant | -0.149 |
Token | players |
Token ID | 1938 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
�� | +0.016 |
apo | +0.015 |
antha | +0.014 |
mosqu | +0.013 |
utenant | +0.013 |
Neg logit contributions | |
ni | -0.010 |
Yang | -0.010 |
NES | -0.009 |
erers | -0.009 |
Pokemon | -0.009 |
Token | will |
Token ID | 481 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
�� | +0.153 |
apo | +0.143 |
antha | +0.138 |
mosqu | +0.132 |
utenant | +0.131 |
Neg logit contributions | |
ni | -0.092 |
Yang | -0.090 |
NES | -0.085 |
erers | -0.083 |
Pokemon | -0.080 |
Token | experience |
Token ID | 1998 |
Feature activation | -8.28e-04 |
Pos logit contributions | |
ni | +0.974 |
Yang | +0.961 |
NES | +0.951 |
NW | +0.909 |
erers | +0.899 |
Neg logit contributions | |
�� | -1.788 |
apo | -1.647 |
mosqu | -1.639 |
antha | -1.585 |
�醒 | -1.533 |
Token | ! |
Token ID | 0 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
ni | +0.001 |
Yang | +0.001 |
NES | +0.001 |
erers | +0.001 |
Pokemon | +0.001 |
Neg logit contributions | |
�� | -0.002 |
apo | -0.002 |
antha | -0.002 |
mosqu | -0.002 |
utenant | -0.002 |
Token | # |
Token ID | 1303 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
ni | +0.804 |
Yang | +0.796 |
NES | +0.750 |
erers | +0.729 |
Pokemon | +0.718 |
Neg logit contributions | |
�� | -1.220 |
apo | -1.136 |
antha | -1.092 |
mosqu | -1.057 |
utenant | -1.041 |
Token | T |
Token ID | 51 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ni | +1.476 |
Yang | +1.452 |
NES | +1.381 |
erers | +1.338 |
Pokemon | +1.333 |
Neg logit contributions | |
�� | -1.986 |
apo | -1.828 |
antha | -1.769 |
mosqu | -1.693 |
utenant | -1.687 |
Token | ravis |
Token ID | 16956 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ni | +0.270 |
Yang | +0.267 |
NES | +0.253 |
erers | +0.248 |
Pokemon | +0.242 |
Neg logit contributions | |
�� | -0.361 |
apo | -0.335 |
antha | -0.322 |
mosqu | -0.309 |
utenant | -0.306 |
Token | Roman |
Token ID | 32454 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
�� | +1.167 |
apo | +1.095 |
antha | +1.054 |
mosqu | +1.009 |
utenant | +1.004 |
Neg logit contributions | |
ni | -0.751 |
Yang | -0.741 |
NES | -0.698 |
erers | -0.686 |
Pokemon | -0.665 |
Token | F |
Token ID | 37 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ni | +4.349 |
Yang | +4.213 |
NES | +3.971 |
Pokemon | +3.775 |
erers | +3.757 |
Neg logit contributions | |
�� | -5.627 |
apo | -5.122 |
antha | -4.948 |
mosqu | -4.832 |
utenant | -4.784 |
Token | lynn |
Token ID | 12935 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ni | +1.505 |
Yang | +1.477 |
NES | +1.414 |
erers | +1.400 |
Pokemon | +1.361 |
Neg logit contributions | |
�� | -1.611 |
apo | -1.481 |
antha | -1.433 |
mosqu | -1.370 |
utenant | -1.347 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ni | +0.855 |
Yang | +0.844 |
NES | +0.796 |
erers | +0.774 |
Pokemon | +0.761 |
Neg logit contributions | |
�� | -1.293 |
apo | -1.206 |
antha | -1.164 |
mosqu | -1.115 |
utenant | -1.104 |
Token | . |
Token ID | 13 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ni | +2.305 |
Yang | +2.173 |
NES | +2.068 |
erers | +1.957 |
Pokemon | +1.914 |
Neg logit contributions | |
�� | -5.409 |
mosqu | -4.968 |
apo | -4.823 |
antha | -4.709 |
�醒 | -4.636 |
Token | twitter |
Token ID | 6956 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ni | +1.072 |
Yang | +1.044 |
NES | +0.987 |
erers | +0.963 |
Pokemon | +0.948 |
Neg logit contributions | |
�� | -1.663 |
apo | -1.538 |
antha | -1.482 |
mosqu | -1.472 |
utenant | -1.411 |
Token | Industrial |
Token ID | 19034 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
�� | +0.603 |
apo | +0.564 |
antha | +0.545 |
mosqu | +0.526 |
utenant | +0.517 |
Neg logit contributions | |
ni | -0.382 |
Yang | -0.377 |
NES | -0.356 |
erers | -0.347 |
Pokemon | -0.337 |
Token | due |
Token ID | 2233 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ni | +1.158 |
Yang | +1.144 |
NES | +1.072 |
erers | +1.055 |
Pokemon | +1.017 |
Neg logit contributions | |
�� | -1.963 |
apo | -1.840 |
antha | -1.776 |
mosqu | -1.705 |
utenant | -1.690 |
Token | process |
Token ID | 1429 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ni | +1.901 |
Yang | +1.861 |
erers | +1.745 |
NES | +1.731 |
CG | +1.695 |
Neg logit contributions | |
�� | -2.402 |
apo | -2.182 |
antha | -2.131 |
mosqu | -2.093 |
utenant | -1.993 |
Token | is |
Token ID | 318 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ni | +0.533 |
Yang | +0.522 |
NES | +0.488 |
erers | +0.479 |
Pokemon | +0.461 |
Neg logit contributions | |
�� | -0.923 |
apo | -0.858 |
antha | -0.831 |
mosqu | -0.800 |
utenant | -0.792 |
Token | that |
Token ID | 326 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
ni | +0.239 |
Yang | +0.235 |
NES | +0.223 |
erers | +0.219 |
CG | +0.212 |
Neg logit contributions | |
�� | -0.314 |
apo | -0.290 |
antha | -0.280 |
mosqu | -0.269 |
utenant | -0.262 |
Token | bare |
Token ID | 6247 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
�� | +0.173 |
apo | +0.160 |
antha | +0.154 |
mosqu | +0.147 |
utenant | +0.144 |
Neg logit contributions | |
ni | -0.135 |
Yang | -0.133 |
NES | -0.126 |
erers | -0.125 |
Pokemon | -0.120 |
Token | minimum |
Token ID | 5288 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ni | +3.393 |
Yang | +3.245 |
NES | +3.097 |
erers | +2.990 |
CG | +2.899 |
Neg logit contributions | |
�� | -6.292 |
apo | -5.948 |
antha | -5.793 |
mosqu | -5.671 |
adish | -5.470 |
Token | standards |
Token ID | 5423 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ni | +1.992 |
Yang | +1.941 |
NES | +1.850 |
erers | +1.802 |
CG | +1.774 |
Neg logit contributions | |
�� | -2.961 |
apo | -2.724 |
antha | -2.633 |
mosqu | -2.549 |
utenant | -2.500 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
�� | +0.679 |
apo | +0.636 |
antha | +0.613 |
mosqu | +0.586 |
utenant | +0.583 |
Neg logit contributions | |
ni | -0.449 |
Yang | -0.443 |
NES | -0.418 |
erers | -0.410 |
Pokemon | -0.398 |
Token | due |
Token ID | 2233 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
ni | +0.215 |
Yang | +0.213 |
NES | +0.200 |
erers | +0.198 |
Pokemon | +0.192 |
Neg logit contributions | |
�� | -0.291 |
apo | -0.270 |
antha | -0.259 |
mosqu | -0.249 |
utenant | -0.245 |
Token | process |
Token ID | 1429 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ni | +1.275 |
Yang | +1.261 |
NES | +1.190 |
erers | +1.179 |
Pokemon | +1.149 |
Neg logit contributions | |
�� | -1.488 |
apo | -1.382 |
antha | -1.331 |
mosqu | -1.258 |
utenant | -1.246 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ni | +0.908 |
Yang | +0.894 |
NES | +0.834 |
erers | +0.821 |
Pokemon | +0.795 |
Neg logit contributions | |
�� | -1.562 |
apo | -1.461 |
antha | -1.409 |
mosqu | -1.352 |
utenant | -1.338 |
Token | Lewis |
Token ID | 10174 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
ni | +0.218 |
Yang | +0.215 |
NES | +0.203 |
erers | +0.200 |
Pokemon | +0.194 |
Neg logit contributions | |
�� | -0.312 |
apo | -0.291 |
antha | -0.279 |
mosqu | -0.267 |
utenant | -0.265 |
Token | Hamilton |
Token ID | 11582 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ni | +0.093 |
Yang | +0.091 |
NES | +0.084 |
erers | +0.082 |
Pokemon | +0.079 |
Neg logit contributions | |
�� | -0.218 |
apo | -0.206 |
antha | -0.200 |
mosqu | -0.193 |
utenant | -0.191 |
Token | cut |
Token ID | 2005 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ni | +1.853 |
Yang | +1.790 |
NES | +1.667 |
erers | +1.661 |
Pokemon | +1.583 |
Neg logit contributions | |
�� | -3.186 |
apo | -2.937 |
antha | -2.837 |
mosqu | -2.751 |
utenant | -2.694 |
Token | his |
Token ID | 465 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ni | +0.744 |
Yang | +0.728 |
NES | +0.690 |
erers | +0.681 |
Pokemon | +0.659 |
Neg logit contributions | |
�� | -1.041 |
apo | -0.973 |
antha | -0.932 |
mosqu | -0.892 |
utenant | -0.883 |
Token | teeth |
Token ID | 9941 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ni | +0.545 |
Yang | +0.531 |
NES | +0.492 |
erers | +0.482 |
Pokemon | +0.457 |
Neg logit contributions | |
�� | -1.225 |
apo | -1.154 |
antha | -1.116 |
mosqu | -1.077 |
utenant | -1.068 |
Token | on |
Token ID | 319 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
ni | +3.441 |
Yang | +3.374 |
Li | +3.148 |
NES | +3.139 |
erers | +3.088 |
Neg logit contributions | |
�� | -6.198 |
apo | -5.695 |
antha | -5.467 |
DragonMagazine | -5.311 |
�醒 | -5.292 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ni | +1.336 |
Yang | +1.315 |
NES | +1.251 |
erers | +1.229 |
Pokemon | +1.195 |
Neg logit contributions | |
�� | -1.788 |
apo | -1.662 |
antha | -1.590 |
utenant | -1.518 |
mosqu | -1.511 |
Token | k |
Token ID | 479 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ni | +0.382 |
Yang | +0.375 |
NES | +0.359 |
erers | +0.350 |
Li | +0.339 |
Neg logit contributions | |
�� | -0.548 |
apo | -0.510 |
antha | -0.487 |
utenant | -0.468 |
mosqu | -0.467 |
Token | art |
Token ID | 433 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
�� | +0.288 |
apo | +0.258 |
antha | +0.243 |
mosqu | +0.230 |
utenant | +0.226 |
Neg logit contributions | |
ni | -0.423 |
Yang | -0.419 |
NES | -0.402 |
erers | -0.398 |
Pokemon | -0.390 |
Token | ing |
Token ID | 278 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
�� | +1.046 |
apo | +0.965 |
antha | +0.926 |
mosqu | +0.882 |
utenant | +0.877 |
Neg logit contributions | |
ni | -0.945 |
Yang | -0.934 |
NES | -0.888 |
erers | -0.879 |
Pokemon | -0.852 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
�� | +0.185 |
apo | +0.174 |
antha | +0.168 |
mosqu | +0.161 |
utenant | +0.160 |
Neg logit contributions | |
ni | -0.107 |
Yang | -0.105 |
NES | -0.099 |
erers | -0.097 |
Pokemon | -0.094 |
Token | � |
Token ID | 447 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ni | +0.233 |
Yang | +0.229 |
NES | +0.215 |
erers | +0.210 |
Pokemon | +0.204 |
Neg logit contributions | |
�� | -0.405 |
apo | -0.380 |
antha | -0.367 |
mosqu | -0.353 |
utenant | -0.350 |
Token | � |
Token ID | 251 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ni | +0.328 |
Yang | +0.325 |
NES | +0.312 |
erers | +0.308 |
Pokemon | +0.302 |
Neg logit contributions | |
�� | -0.243 |
apo | -0.222 |
antha | -0.210 |
mosqu | -0.196 |
utenant | -0.194 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ni | +0.029 |
Yang | +0.029 |
NES | +0.027 |
erers | +0.027 |
Pokemon | +0.026 |
Neg logit contributions | |
�� | -0.043 |
apo | -0.041 |
antha | -0.039 |
utenant | -0.037 |
mosqu | -0.037 |
Token | R |
Token ID | 49 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
�� | +1.775 |
apo | +1.677 |
antha | +1.608 |
utenant | +1.524 |
mosqu | +1.517 |
Neg logit contributions | |
ni | -1.213 |
Yang | -1.193 |
NES | -1.126 |
erers | -1.118 |
Pokemon | -1.071 |
Token | amon |
Token ID | 16487 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ni | +0.536 |
Yang | +0.529 |
NES | +0.504 |
erers | +0.494 |
Pokemon | +0.482 |
Neg logit contributions | |
�� | -0.651 |
apo | -0.602 |
antha | -0.578 |
mosqu | -0.553 |
utenant | -0.549 |
Token | Hare |
Token ID | 42285 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ni | +4.250 |
Yang | +4.034 |
NES | +3.834 |
erers | +3.738 |
Num | +3.691 |
Neg logit contributions | |
�� | -5.533 |
apo | -4.997 |
antha | -4.755 |
utenant | -4.612 |
mosqu | -4.603 |
Token | wood |
Token ID | 3822 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
�� | +0.574 |
apo | +0.537 |
antha | +0.517 |
mosqu | +0.495 |
utenant | +0.492 |
Neg logit contributions | |
ni | -0.384 |
Yang | -0.376 |
NES | -0.357 |
erers | -0.348 |
Pokemon | -0.339 |
Token | met |
Token ID | 1138 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ni | +0.310 |
Yang | +0.304 |
NES | +0.286 |
erers | +0.280 |
Pokemon | +0.272 |
Neg logit contributions | |
�� | -0.500 |
apo | -0.469 |
antha | -0.452 |
mosqu | -0.434 |
utenant | -0.430 |
Token | with |
Token ID | 351 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ni | +0.376 |
Yang | +0.370 |
NES | +0.350 |
erers | +0.345 |
Pokemon | +0.335 |
Neg logit contributions | |
�� | -0.493 |
apo | -0.458 |
antha | -0.438 |
mosqu | -0.421 |
utenant | -0.417 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ni | +0.887 |
Yang | +0.876 |
NES | +0.830 |
erers | +0.820 |
Pokemon | +0.801 |
Neg logit contributions | |
�� | -1.090 |
apo | -1.014 |
antha | -0.966 |
mosqu | -0.920 |
utenant | -0.914 |
Token | disp |
Token ID | 4596 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
�� | +0.682 |
apo | +0.634 |
antha | +0.607 |
mosqu | +0.576 |
utenant | +0.572 |
Neg logit contributions | |
ni | -0.613 |
Yang | -0.608 |
NES | -0.579 |
erers | -0.570 |
Pokemon | -0.557 |
Token | ersion |
Token ID | 6900 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
�� | +0.349 |
apo | +0.313 |
antha | +0.294 |
mosqu | +0.274 |
utenant | +0.271 |
Neg logit contributions | |
ni | -0.546 |
Yang | -0.541 |
NES | -0.520 |
erers | -0.515 |
Pokemon | -0.505 |
Token | as |
Token ID | 355 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
�� | +1.357 |
apo | +1.276 |
antha | +1.226 |
mosqu | +1.164 |
utenant | +1.163 |
Neg logit contributions | |
ni | -0.962 |
Yang | -0.958 |
NES | -0.905 |
erers | -0.885 |
Pokemon | -0.865 |
Token | such |
Token ID | 884 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
ni | +0.335 |
Yang | +0.327 |
NES | +0.308 |
erers | +0.305 |
Pokemon | +0.296 |
Neg logit contributions | |
�� | -0.424 |
apo | -0.391 |
antha | -0.377 |
mosqu | -0.361 |
utenant | -0.357 |
Token | ! |
Token ID | 0 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ni | +0.136 |
Yang | +0.134 |
NES | +0.127 |
erers | +0.125 |
Pokemon | +0.121 |
Neg logit contributions | |
�� | -0.195 |
apo | -0.182 |
antha | -0.175 |
mosqu | -0.168 |
utenant | -0.167 |
Token | Ont |
Token ID | 45984 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ni | +0.688 |
Yang | +0.677 |
NES | +0.634 |
erers | +0.618 |
Pokemon | +0.608 |
Neg logit contributions | |
�� | -1.006 |
apo | -0.932 |
antha | -0.899 |
mosqu | -0.868 |
utenant | -0.855 |
Token | ology |
Token ID | 1435 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ni | +5.059 |
Yang | +4.830 |
erers | +4.623 |
NES | +4.584 |
NW | +4.457 |
Neg logit contributions | |
�� | -4.455 |
apo | -3.991 |
antha | -3.807 |
mosqu | -3.686 |
utenant | -3.560 |
Token | returned |
Token ID | 4504 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
ni | +1.002 |
Yang | +0.971 |
NES | +0.910 |
erers | +0.898 |
Pokemon | +0.864 |
Neg logit contributions | |
�� | -1.665 |
apo | -1.551 |
antha | -1.500 |
mosqu | -1.449 |
utenant | -1.425 |
Token | to |
Token ID | 284 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ni | +0.818 |
Yang | +0.801 |
NES | +0.756 |
erers | +0.745 |
Pokemon | +0.721 |
Neg logit contributions | |
�� | -1.183 |
apo | -1.100 |
antha | -1.062 |
mosqu | -1.016 |
utenant | -1.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
�� | +0.350 |
apo | +0.325 |
antha | +0.312 |
mosqu | +0.297 |
utenant | +0.296 |
Neg logit contributions | |
ni | -0.281 |
Yang | -0.277 |
NES | -0.263 |
erers | -0.259 |
Pokemon | -0.252 |
Token | Meg |
Token ID | 8336 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
ni | +0.053 |
Yang | +0.052 |
NES | +0.049 |
erers | +0.048 |
Pokemon | +0.046 |
Neg logit contributions | |
�� | -0.073 |
apo | -0.068 |
antha | -0.065 |
mosqu | -0.062 |
utenant | -0.062 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ni | +1.405 |
Yang | +1.364 |
NES | +1.296 |
erers | +1.275 |
Pokemon | +1.228 |
Neg logit contributions | |
�� | -1.549 |
apo | -1.363 |
antha | -1.307 |
mosqu | -1.301 |
utenant | -1.265 |
Token | chio |
Token ID | 40900 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
�� | +0.854 |
apo | +0.802 |
antha | +0.775 |
mosqu | +0.739 |
utenant | +0.735 |
Neg logit contributions | |
ni | -0.557 |
Yang | -0.554 |
NES | -0.522 |
erers | -0.513 |
Pokemon | -0.498 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
�� | +0.477 |
apo | +0.449 |
antha | +0.433 |
mosqu | +0.414 |
utenant | +0.413 |
Neg logit contributions | |
ni | -0.288 |
Yang | -0.286 |
NES | -0.269 |
erers | -0.264 |
Pokemon | -0.256 |
Token | a |
Token ID | 257 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
ni | +0.227 |
Yang | +0.225 |
NES | +0.213 |
erers | +0.210 |
Pokemon | +0.205 |
Neg logit contributions | |
�� | -0.277 |
apo | -0.258 |
antha | -0.249 |
mosqu | -0.236 |
utenant | -0.235 |
Token | pale |
Token ID | 14005 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
ni | +0.116 |
Yang | +0.114 |
NES | +0.107 |
erers | +0.105 |
Pokemon | +0.101 |
Neg logit contributions | |
�� | -0.211 |
apo | -0.199 |
antha | -0.192 |
mosqu | -0.183 |
utenant | -0.183 |
Token | ont |
Token ID | 756 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ni | +0.712 |
Yang | +0.679 |
NES | +0.596 |
erers | +0.568 |
Pokemon | +0.533 |
Neg logit contributions | |
�� | -2.940 |
apo | -2.778 |
antha | -2.705 |
mosqu | -2.635 |
utenant | -2.611 |
Token | ologist |
Token ID | 7451 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
ni | +5.566 |
Yang | +5.303 |
erers | +5.071 |
NES | +5.065 |
Num | +4.965 |
Neg logit contributions | |
�� | -3.966 |
apo | -3.485 |
antha | -3.221 |
mosqu | -3.180 |
aples | -3.036 |
Token | at |
Token ID | 379 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ni | +1.315 |
Yang | +1.295 |
NES | +1.220 |
erers | +1.204 |
Pokemon | +1.170 |
Neg logit contributions | |
�� | -1.659 |
apo | -1.559 |
antha | -1.485 |
mosqu | -1.418 |
aples | -1.393 |
Token | Montana |
Token ID | 18311 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
�� | +0.501 |
apo | +0.466 |
antha | +0.447 |
mosqu | +0.426 |
utenant | +0.424 |
Neg logit contributions | |
ni | -0.402 |
Yang | -0.397 |
NES | -0.377 |
erers | -0.371 |
Pokemon | -0.361 |
Token | State |
Token ID | 1812 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ni | +0.354 |
Yang | +0.347 |
NES | +0.329 |
erers | +0.319 |
Pokemon | +0.311 |
Neg logit contributions | |
�� | -0.492 |
apo | -0.458 |
antha | -0.442 |
mosqu | -0.421 |
utenant | -0.419 |
Token | University |
Token ID | 2059 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ni | +0.788 |
Yang | +0.774 |
NES | +0.725 |
erers | +0.706 |
Pokemon | +0.682 |
Neg logit contributions | |
�� | -1.510 |
apo | -1.419 |
antha | -1.377 |
mosqu | -1.319 |
utenant | -1.313 |
Token | it |
Token ID | 340 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
�� | +1.668 |
apo | +1.569 |
antha | +1.512 |
mosqu | +1.446 |
utenant | +1.441 |
Neg logit contributions | |
ni | -1.026 |
Yang | -1.016 |
NES | -0.955 |
erers | -0.936 |
Pokemon | -0.907 |
Token | is |
Token ID | 318 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
�� | +0.003 |
apo | +0.003 |
antha | +0.003 |
mosqu | +0.003 |
utenant | +0.003 |
Neg logit contributions | |
ni | -0.002 |
Yang | -0.002 |
NES | -0.002 |
erers | -0.002 |
Pokemon | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ni | +0.293 |
Yang | +0.287 |
NES | +0.272 |
erers | +0.264 |
Pokemon | +0.258 |
Neg logit contributions | |
�� | -0.462 |
apo | -0.431 |
antha | -0.417 |
mosqu | -0.401 |
utenant | -0.396 |
Token | without |
Token ID | 1231 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
ni | +0.237 |
Yang | +0.234 |
NES | +0.222 |
erers | +0.217 |
Pokemon | +0.213 |
Neg logit contributions | |
�� | -0.308 |
apo | -0.285 |
antha | -0.273 |
mosqu | -0.262 |
utenant | -0.260 |
Token | further |
Token ID | 2252 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
�� | +1.143 |
apo | +1.069 |
antha | +1.025 |
mosqu | +0.984 |
utenant | +0.978 |
Neg logit contributions | |
ni | -0.819 |
Yang | -0.812 |
NES | -0.768 |
erers | -0.751 |
Pokemon | -0.733 |
Token | ado |
Token ID | 50129 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
�� | +0.767 |
apo | +0.722 |
antha | +0.697 |
mosqu | +0.668 |
utenant | +0.665 |
Neg logit contributions | |
ni | -0.433 |
Yang | -0.428 |
NES | -0.401 |
erers | -0.392 |
Pokemon | -0.380 |
Token | : |
Token ID | 25 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ni | +3.478 |
Yang | +3.332 |
NES | +3.181 |
erers | +3.081 |
Num | +3.026 |
Neg logit contributions | |
�� | -5.826 |
apo | -5.393 |
antha | -5.267 |
mosqu | -5.069 |
utenant | -5.004 |
Token | one |
Token ID | 530 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ni | +0.617 |
Yang | +0.608 |
NES | +0.574 |
erers | +0.563 |
Pokemon | +0.548 |
Neg logit contributions | |
�� | -0.933 |
apo | -0.869 |
antha | -0.835 |
mosqu | -0.804 |
utenant | -0.796 |
Token | man |
Token ID | 582 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
�� | +1.474 |
apo | +1.385 |
antha | +1.338 |
mosqu | +1.285 |
utenant | +1.276 |
Neg logit contributions | |
ni | -0.835 |
Yang | -0.823 |
NES | -0.771 |
erers | -0.755 |
Pokemon | -0.732 |
Token | � |
Token ID | 447 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ni | +0.111 |
Yang | +0.109 |
NES | +0.103 |
erers | +0.102 |
Pokemon | +0.099 |
Neg logit contributions | |
�� | -0.157 |
apo | -0.146 |
antha | -0.141 |
mosqu | -0.135 |
utenant | -0.134 |
Token | � |
Token ID | 247 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
�� | +0.115 |
apo | +0.111 |
antha | +0.108 |
mosqu | +0.105 |
utenant | +0.100 |
Neg logit contributions | |
ni | -0.079 |
Yang | -0.079 |
NES | -0.074 |
erers | -0.073 |
Num | -0.070 |
Token | very |
Token ID | 845 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ni | +0.174 |
Yang | +0.171 |
NES | +0.162 |
erers | +0.160 |
Pokemon | +0.155 |
Neg logit contributions | |
�� | -0.225 |
apo | -0.210 |
antha | -0.201 |
mosqu | -0.191 |
utenant | -0.190 |
Token | small |
Token ID | 1402 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
ni | +0.469 |
Yang | +0.461 |
NES | +0.435 |
erers | +0.427 |
Pokemon | +0.415 |
Neg logit contributions | |
�� | -0.670 |
apo | -0.626 |
antha | -0.603 |
mosqu | -0.576 |
utenant | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ni | +0.982 |
Yang | +0.967 |
NES | +0.923 |
erers | +0.900 |
CG | +0.876 |
Neg logit contributions | |
�� | -1.254 |
apo | -1.160 |
antha | -1.118 |
mosqu | -1.060 |
utenant | -1.053 |
Token | US |
Token ID | 1294 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ni | +0.175 |
Yang | +0.172 |
NES | +0.163 |
erers | +0.160 |
Pokemon | +0.155 |
Neg logit contributions | |
�� | -0.248 |
apo | -0.231 |
antha | -0.222 |
mosqu | -0.212 |
utenant | -0.210 |
Token | Naval |
Token ID | 20818 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ni | +0.477 |
Yang | +0.469 |
NES | +0.448 |
erers | +0.439 |
Pokemon | +0.425 |
Neg logit contributions | |
�� | -0.607 |
apo | -0.562 |
antha | -0.543 |
mosqu | -0.516 |
utenant | -0.509 |
Token | React |
Token ID | 21492 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
�� | +2.685 |
apo | +2.550 |
antha | +2.442 |
utenant | +2.330 |
mosqu | +2.324 |
Neg logit contributions | |
ni | -1.943 |
Yang | -1.929 |
NES | -1.825 |
erers | -1.793 |
Pokemon | -1.757 |
Token | ors |
Token ID | 669 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ni | +2.632 |
Yang | +2.498 |
erers | +2.351 |
NES | +2.290 |
Li | +2.159 |
Neg logit contributions | |
�� | -6.780 |
apo | -6.179 |
antha | -6.079 |
mosqu | -5.949 |
aples | -5.836 |
Token | � |
Token ID | 447 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ni | +0.577 |
Yang | +0.568 |
NES | +0.536 |
erers | +0.524 |
Pokemon | +0.510 |
Neg logit contributions | |
�� | -0.867 |
apo | -0.808 |
antha | -0.778 |
mosqu | -0.745 |
utenant | -0.737 |
Token | � |
Token ID | 247 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
ni | +0.526 |
Yang | +0.520 |
NES | +0.496 |
erers | +0.492 |
Pokemon | +0.480 |
Neg logit contributions | |
�� | -0.484 |
apo | -0.455 |
antha | -0.436 |
mosqu | -0.410 |
utenant | -0.405 |
Token | average |
Token ID | 2811 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.148 |
apo | +0.139 |
antha | +0.134 |
mosqu | +0.128 |
utenant | +0.127 |
Neg logit contributions | |
ni | -0.097 |
Yang | -0.095 |
NES | -0.090 |
erers | -0.088 |
Pokemon | -0.086 |
Token | annual |
Token ID | 5079 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ni | +0.183 |
Yang | +0.180 |
NES | +0.170 |
erers | +0.166 |
Pokemon | +0.160 |
Neg logit contributions | |
�� | -0.288 |
apo | -0.269 |
antha | -0.259 |
mosqu | -0.248 |
utenant | -0.246 |
Token | an |
Token ID | 281 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
�� | +1.566 |
apo | +1.471 |
antha | +1.410 |
mosqu | +1.350 |
utenant | +1.340 |
Neg logit contributions | |
ni | -1.150 |
Yang | -1.143 |
NES | -1.080 |
erers | -1.062 |
Pokemon | -1.033 |
Token | event |
Token ID | 1785 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
�� | +1.151 |
apo | +1.076 |
antha | +1.035 |
mosqu | +0.988 |
utenant | +0.983 |
Neg logit contributions | |
ni | -0.821 |
Yang | -0.811 |
NES | -0.767 |
erers | -0.752 |
Pokemon | -0.733 |
Token | filled |
Token ID | 5901 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
�� | +0.292 |
apo | +0.274 |
antha | +0.264 |
mosqu | +0.253 |
utenant | +0.251 |
Neg logit contributions | |
ni | -0.186 |
Yang | -0.183 |
NES | -0.172 |
erers | -0.169 |
Pokemon | -0.164 |
Token | with |
Token ID | 351 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
�� | +1.854 |
apo | +1.718 |
antha | +1.640 |
mosqu | +1.603 |
utenant | +1.571 |
Neg logit contributions | |
ni | -1.396 |
Yang | -1.395 |
NES | -1.311 |
erers | -1.283 |
Pokemon | -1.266 |
Token | Tor |
Token ID | 4022 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ni | +1.163 |
Yang | +1.132 |
NES | +1.071 |
erers | +1.063 |
Pokemon | +1.033 |
Neg logit contributions | |
�� | -1.538 |
apo | -1.425 |
antha | -1.382 |
mosqu | -1.304 |
utenant | -1.301 |
Token | ont |
Token ID | 756 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ni | +0.324 |
Yang | +0.295 |
erers | +0.233 |
NES | +0.231 |
Pokemon | +0.197 |
Neg logit contributions | |
�� | -2.200 |
apo | -2.087 |
antha | -2.050 |
utenant | -1.973 |
mosqu | -1.971 |
Token | on |
Token ID | 261 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ni | +2.181 |
Yang | +1.998 |
erers | +1.823 |
NES | +1.743 |
Pokemon | +1.667 |
Neg logit contributions | |
�� | -7.186 |
apo | -6.733 |
antha | -6.583 |
utenant | -6.362 |
mosqu | -6.351 |
Token | ians |
Token ID | 1547 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
ni | +1.446 |
Yang | +1.397 |
NES | +1.308 |
erers | +1.306 |
Pokemon | +1.252 |
Neg logit contributions | |
�� | -2.121 |
apo | -1.997 |
antha | -1.924 |
mosqu | -1.826 |
utenant | -1.821 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
ni | +1.437 |
Yang | +1.400 |
NES | +1.313 |
erers | +1.293 |
Pokemon | +1.251 |
Neg logit contributions | |
�� | -2.348 |
apo | -2.202 |
antha | -2.131 |
mosqu | -2.037 |
utenant | -2.022 |
Token | at |
Token ID | 379 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ni | +0.067 |
Yang | +0.066 |
NES | +0.063 |
erers | +0.062 |
Pokemon | +0.060 |
Neg logit contributions | |
�� | -0.094 |
apo | -0.088 |
antha | -0.085 |
mosqu | -0.081 |
utenant | -0.081 |
Token | least |
Token ID | 1551 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
�� | +0.243 |
apo | +0.225 |
antha | +0.218 |
mosqu | +0.207 |
utenant | +0.206 |
Neg logit contributions | |
ni | -0.182 |
Yang | -0.179 |
NES | -0.170 |
erers | -0.167 |
Pokemon | -0.162 |
Token | it |
Token ID | 340 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
�� | +0.158 |
apo | +0.147 |
antha | +0.141 |
mosqu | +0.135 |
utenant | +0.134 |
Neg logit contributions | |
ni | -0.116 |
Yang | -0.115 |
NES | -0.108 |
erers | -0.106 |
Pokemon | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ni | +0.381 |
Yang | +0.374 |
NES | +0.350 |
erers | +0.343 |
Pokemon | +0.332 |
Neg logit contributions | |
�� | -0.676 |
apo | -0.635 |
antha | -0.613 |
mosqu | -0.590 |
utenant | -0.586 |
Token | � |
Token ID | 447 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
ni | +0.298 |
Yang | +0.296 |
NES | +0.277 |
erers | +0.270 |
Pokemon | +0.264 |
Neg logit contributions | |
�� | -0.451 |
apo | -0.421 |
antha | -0.406 |
mosqu | -0.393 |
utenant | -0.385 |
Token | � |
Token ID | 251 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ni | +0.114 |
Yang | +0.113 |
NES | +0.109 |
erers | +0.107 |
Pokemon | +0.105 |
Neg logit contributions | |
�� | -0.079 |
apo | -0.072 |
antha | -0.068 |
mosqu | -0.064 |
utenant | -0.063 |
Token | Functional |
Token ID | 44224 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
�� | +0.057 |
apo | +0.054 |
antha | +0.052 |
mosqu | +0.050 |
utenant | +0.049 |
Neg logit contributions | |
ni | -0.040 |
Yang | -0.040 |
NES | -0.038 |
erers | -0.037 |
Pokemon | -0.036 |
Token | MRI |
Token ID | 30278 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ni | +0.847 |
Yang | +0.833 |
NES | +0.789 |
erers | +0.768 |
Pokemon | +0.748 |
Neg logit contributions | |
�� | -1.294 |
apo | -1.211 |
antha | -1.166 |
mosqu | -1.120 |
utenant | -1.111 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ni | +3.513 |
Yang | +3.425 |
NES | +3.190 |
Li | +3.134 |
erers | +3.104 |
Neg logit contributions | |
�� | -5.603 |
apo | -5.279 |
antha | -5.097 |
mosqu | -4.900 |
aples | -4.835 |
Token | other |
Token ID | 584 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ni | +0.322 |
Yang | +0.318 |
NES | +0.299 |
erers | +0.292 |
Pokemon | +0.285 |
Neg logit contributions | |
�� | -0.456 |
apo | -0.427 |
antha | -0.410 |
mosqu | -0.393 |
utenant | -0.390 |
Token | non |
Token ID | 1729 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
ni | +0.351 |
Yang | +0.344 |
NES | +0.323 |
erers | +0.318 |
Pokemon | +0.309 |
Neg logit contributions | |
�� | -0.517 |
apo | -0.481 |
antha | -0.465 |
mosqu | -0.445 |
utenant | -0.442 |
Token | in |
Token ID | 259 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
�� | +0.222 |
apo | +0.207 |
antha | +0.199 |
mosqu | +0.191 |
utenant | +0.189 |
Neg logit contributions | |
ni | -0.163 |
Yang | -0.161 |
NES | -0.152 |
erers | -0.149 |
Pokemon | -0.146 |
Token | vasive |
Token ID | 23747 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ni | +0.411 |
Yang | +0.400 |
NES | +0.367 |
erers | +0.365 |
Pokemon | +0.353 |
Neg logit contributions | |
�� | -0.791 |
apo | -0.733 |
antha | -0.713 |
mosqu | -0.691 |
utenant | -0.678 |
Token | pattern |
Token ID | 3912 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ni | +0.466 |
Yang | +0.460 |
NES | +0.436 |
erers | +0.427 |
Pokemon | +0.418 |
Neg logit contributions | |
�� | -0.611 |
apo | -0.569 |
antha | -0.544 |
mosqu | -0.521 |
utenant | -0.517 |
Token | of |
Token ID | 286 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ni | +0.226 |
Yang | +0.222 |
NES | +0.207 |
erers | +0.203 |
Pokemon | +0.197 |
Neg logit contributions | |
�� | -0.406 |
apo | -0.381 |
antha | -0.367 |
mosqu | -0.354 |
utenant | -0.351 |
Token | ownership |
Token ID | 9238 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ni | +0.183 |
Yang | +0.179 |
NES | +0.169 |
erers | +0.167 |
Pokemon | +0.162 |
Neg logit contributions | |
�� | -0.245 |
apo | -0.229 |
antha | -0.217 |
mosqu | -0.209 |
utenant | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
�� | +0.608 |
apo | +0.571 |
antha | +0.551 |
mosqu | +0.527 |
utenant | +0.525 |
Neg logit contributions | |
ni | -0.370 |
Yang | -0.366 |
NES | -0.344 |
erers | -0.337 |
Pokemon | -0.327 |
Token | consumer |
Token ID | 7172 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ni | +0.759 |
Yang | +0.743 |
NES | +0.703 |
erers | +0.690 |
Pokemon | +0.671 |
Neg logit contributions | |
�� | -1.125 |
apo | -1.044 |
antha | -1.000 |
mosqu | -0.958 |
utenant | -0.953 |
Token | dur |
Token ID | 22365 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ni | +0.571 |
Yang | +0.563 |
NES | +0.526 |
erers | +0.521 |
Pokemon | +0.505 |
Neg logit contributions | |
�� | -0.863 |
apo | -0.811 |
antha | -0.779 |
mosqu | -0.747 |
utenant | -0.742 |
Token | ables |
Token ID | 2977 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ni | +3.946 |
Yang | +3.708 |
erers | +3.650 |
NES | +3.433 |
NW | +3.419 |
Neg logit contributions | |
�� | -5.483 |
mosqu | -4.796 |
apo | -4.756 |
antha | -4.558 |
utenant | -4.464 |
Token | among |
Token ID | 1871 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ni | +0.956 |
Yang | +0.938 |
NES | +0.878 |
erers | +0.866 |
Pokemon | +0.842 |
Neg logit contributions | |
�� | -1.528 |
apo | -1.429 |
antha | -1.378 |
mosqu | -1.324 |
utenant | -1.310 |
Token | Indian |
Token ID | 3942 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ni | +1.112 |
Yang | +1.080 |
NES | +1.020 |
erers | +1.017 |
Pokemon | +0.977 |
Neg logit contributions | |
�� | -1.582 |
apo | -1.474 |
antha | -1.404 |
mosqu | -1.356 |
utenant | -1.332 |
Token | households |
Token ID | 12503 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
�� | +0.512 |
apo | +0.478 |
antha | +0.458 |
mosqu | +0.436 |
utenant | +0.433 |
Neg logit contributions | |
ni | -0.420 |
Yang | -0.414 |
NES | -0.393 |
erers | -0.387 |
Pokemon | -0.377 |
Token | . |
Token ID | 13 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
ni | +0.066 |
Yang | +0.065 |
NES | +0.061 |
erers | +0.060 |
Pokemon | +0.058 |
Neg logit contributions | |
�� | -0.105 |
apo | -0.098 |
antha | -0.095 |
mosqu | -0.091 |
utenant | -0.090 |
Token | was |
Token ID | 9776 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ni | +0.340 |
Yang | +0.337 |
NES | +0.322 |
erers | +0.317 |
Pokemon | +0.310 |
Neg logit contributions | |
�� | -0.322 |
apo | -0.297 |
antha | -0.284 |
mosqu | -0.268 |
utenant | -0.266 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
�� | +0.562 |
apo | +0.521 |
antha | +0.499 |
mosqu | +0.473 |
utenant | +0.471 |
Neg logit contributions | |
ni | -0.516 |
Yang | -0.513 |
NES | -0.490 |
erers | -0.479 |
Pokemon | -0.470 |
Token | entrance |
Token ID | 10384 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
�� | +0.380 |
apo | +0.356 |
antha | +0.343 |
mosqu | +0.328 |
utenant | +0.326 |
Neg logit contributions | |
ni | -0.255 |
Yang | -0.252 |
NES | -0.238 |
erers | -0.233 |
Pokemon | -0.227 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ni | +0.765 |
Yang | +0.754 |
NES | +0.706 |
erers | +0.699 |
Pokemon | +0.675 |
Neg logit contributions | |
�� | -1.134 |
apo | -1.064 |
antha | -1.023 |
utenant | -0.980 |
mosqu | -0.977 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
�� | +0.246 |
apo | +0.229 |
antha | +0.219 |
mosqu | +0.208 |
utenant | +0.207 |
Neg logit contributions | |
ni | -0.214 |
Yang | -0.211 |
NES | -0.201 |
erers | -0.198 |
Pokemon | -0.193 |
Token | TTC |
Token ID | 42662 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ni | +0.511 |
Yang | +0.503 |
NES | +0.474 |
erers | +0.465 |
Pokemon | +0.452 |
Neg logit contributions | |
�� | -0.748 |
apo | -0.702 |
antha | -0.675 |
mosqu | -0.640 |
utenant | -0.638 |
Token | station |
Token ID | 4429 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
ni | +3.648 |
Yang | +3.524 |
NES | +3.315 |
erers | +3.264 |
CG | +3.192 |
Neg logit contributions | |
�� | -5.344 |
apo | -4.987 |
antha | -4.911 |
utenant | -4.608 |
adish | -4.558 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
�� | +0.184 |
apo | +0.172 |
antha | +0.166 |
mosqu | +0.159 |
utenant | +0.158 |
Neg logit contributions | |
ni | -0.113 |
Yang | -0.112 |
NES | -0.105 |
erers | -0.103 |
Pokemon | -0.100 |
Token | Panel |
Token ID | 18810 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ni | +0.082 |
Yang | +0.081 |
NES | +0.077 |
erers | +0.076 |
Pokemon | +0.073 |
Neg logit contributions | |
�� | -0.111 |
apo | -0.104 |
antha | -0.100 |
mosqu | -0.096 |
utenant | -0.095 |
Token | ists |
Token ID | 1023 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
ni | +1.498 |
Yang | +1.466 |
NES | +1.370 |
erers | +1.364 |
Pokemon | +1.302 |
Neg logit contributions | |
�� | -2.633 |
apo | -2.484 |
antha | -2.390 |
mosqu | -2.294 |
utenant | -2.276 |
Token | lamented |
Token ID | 40176 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
�� | +0.154 |
apo | +0.145 |
antha | +0.140 |
mosqu | +0.134 |
utenant | +0.133 |
Neg logit contributions | |
ni | -0.087 |
Yang | -0.086 |
NES | -0.080 |
erers | -0.078 |
Pokemon | -0.076 |
Token | ing |
Token ID | 278 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
�� | +1.135 |
apo | +1.053 |
antha | +1.005 |
mosqu | +0.948 |
utenant | +0.944 |
Neg logit contributions | |
ni | -1.128 |
Yang | -1.118 |
NES | -1.069 |
erers | -1.047 |
Pokemon | -1.028 |
Token | very |
Token ID | 845 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
�� | +0.258 |
apo | +0.240 |
antha | +0.232 |
mosqu | +0.221 |
utenant | +0.220 |
Neg logit contributions | |
ni | -0.174 |
Yang | -0.171 |
NES | -0.160 |
erers | -0.160 |
Pokemon | -0.153 |
Token | tightly |
Token ID | 17707 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ni | +0.366 |
Yang | +0.360 |
NES | +0.336 |
erers | +0.329 |
Pokemon | +0.318 |
Neg logit contributions | |
�� | -0.692 |
apo | -0.651 |
antha | -0.630 |
mosqu | -0.605 |
utenant | -0.601 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
�� | +1.273 |
apo | +1.198 |
antha | +1.156 |
mosqu | +1.107 |
utenant | +1.102 |
Neg logit contributions | |
ni | -0.744 |
Yang | -0.735 |
NES | -0.690 |
erers | -0.675 |
Pokemon | -0.655 |
Token | so |
Token ID | 523 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
�� | +0.313 |
apo | +0.293 |
antha | +0.283 |
mosqu | +0.271 |
utenant | +0.269 |
Neg logit contributions | |
ni | -0.191 |
Yang | -0.189 |
NES | -0.177 |
erers | -0.174 |
Pokemon | -0.168 |
Token | Giov |
Token ID | 36089 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
�� | +0.228 |
apo | +0.210 |
antha | +0.203 |
mosqu | +0.193 |
utenant | +0.192 |
Neg logit contributions | |
ni | -0.188 |
Yang | -0.186 |
NES | -0.176 |
erers | -0.174 |
Pokemon | -0.169 |
Token | ani |
Token ID | 3216 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ni | +3.997 |
Yang | +3.739 |
NES | +3.459 |
erers | +3.393 |
DO | +3.388 |
Neg logit contributions | |
�� | -5.443 |
antha | -4.728 |
apo | -4.651 |
mosqu | -4.529 |
DragonMagazine | -4.489 |
Token | dos |
Token ID | 23430 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
�� | +0.323 |
apo | +0.298 |
antha | +0.289 |
mosqu | +0.277 |
utenant | +0.273 |
Neg logit contributions | |
ni | -0.235 |
Yang | -0.230 |
NES | -0.218 |
erers | -0.214 |
Pokemon | -0.206 |
Token | Santos |
Token ID | 28458 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ni | +2.201 |
Yang | +2.098 |
NES | +1.988 |
Num | +1.967 |
erers | +1.966 |
Neg logit contributions | |
�� | -2.873 |
apo | -2.486 |
antha | -2.476 |
mosqu | -2.388 |
DragonMagazine | -2.358 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ni | +0.372 |
Yang | +0.364 |
NES | +0.340 |
erers | +0.337 |
Pokemon | +0.323 |
Neg logit contributions | |
�� | -0.609 |
apo | -0.566 |
antha | -0.549 |
mosqu | -0.526 |
utenant | -0.521 |
Token | O |
Token ID | 440 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
�� | +0.254 |
apo | +0.236 |
antha | +0.228 |
mosqu | +0.217 |
utenant | +0.216 |
Neg logit contributions | |
ni | -0.195 |
Yang | -0.192 |
NES | -0.182 |
erers | -0.179 |
Pokemon | -0.174 |
Token | shallow |
Token ID | 19337 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ni | +0.482 |
Yang | +0.469 |
NES | +0.442 |
erers | +0.436 |
Pokemon | +0.423 |
Neg logit contributions | |
�� | -0.639 |
apo | -0.594 |
antha | -0.577 |
mosqu | -0.549 |
utenant | -0.545 |
Token | grave |
Token ID | 12296 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
�� | +2.400 |
apo | +2.231 |
antha | +2.134 |
utenant | +2.024 |
mosqu | +2.023 |
Neg logit contributions | |
ni | -2.046 |
Yang | -2.032 |
NES | -1.930 |
erers | -1.901 |
Pokemon | -1.855 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
�� | +0.647 |
apo | +0.605 |
antha | +0.585 |
mosqu | +0.561 |
utenant | +0.557 |
Neg logit contributions | |
ni | -0.388 |
Yang | -0.382 |
NES | -0.359 |
erers | -0.351 |
Pokemon | -0.341 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
�� | +0.059 |
apo | +0.055 |
antha | +0.053 |
utenant | +0.051 |
mosqu | +0.050 |
Neg logit contributions | |
ni | -0.039 |
Yang | -0.039 |
NES | -0.036 |
erers | -0.036 |
Pokemon | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
�� | +0.420 |
apo | +0.389 |
antha | +0.377 |
mosqu | +0.369 |
utenant | +0.357 |
Neg logit contributions | |
ni | -0.247 |
Yang | -0.243 |
NES | -0.228 |
erers | -0.223 |
Pokemon | -0.217 |
Token | Hung |
Token ID | 39505 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
�� | +0.004 |
apo | +0.003 |
antha | +0.003 |
mosqu | +0.003 |
utenant | +0.003 |
Neg logit contributions | |
ni | -0.002 |
Yang | -0.002 |
NES | -0.002 |
erers | -0.002 |
Pokemon | -0.002 |
Token | ry |
Token ID | 563 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ni | +3.025 |
Yang | +2.964 |
erers | +2.752 |
NES | +2.722 |
Pokemon | +2.510 |
Neg logit contributions | |
�� | -5.996 |
apo | -5.541 |
antha | -5.377 |
mosqu | -5.360 |
utenant | -5.175 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ni | +0.954 |
Yang | +0.937 |
NES | +0.886 |
erers | +0.879 |
Pokemon | +0.844 |
Neg logit contributions | |
�� | -1.443 |
apo | -1.327 |
antha | -1.294 |
mosqu | -1.229 |
utenant | -1.219 |
Token | dis |
Token ID | 595 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
ni | +0.362 |
Yang | +0.357 |
NES | +0.334 |
erers | +0.327 |
Pokemon | +0.316 |
Neg logit contributions | |
�� | -0.632 |
apo | -0.595 |
antha | -0.574 |
mosqu | -0.551 |
utenant | -0.548 |
Token | he |
Token ID | 258 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
�� | +0.204 |
apo | +0.190 |
antha | +0.181 |
mosqu | +0.172 |
utenant | +0.171 |
Neg logit contributions | |
ni | -0.187 |
Yang | -0.186 |
NES | -0.177 |
erers | -0.174 |
Pokemon | -0.170 |
Token | ve |
Token ID | 303 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
�� | +0.046 |
apo | +0.042 |
antha | +0.041 |
mosqu | +0.039 |
aples | +0.038 |
Neg logit contributions | |
ni | -0.049 |
Yang | -0.048 |
NES | -0.046 |
erers | -0.046 |
Pokemon | -0.044 |
Token | take |
Token ID | 1011 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ni | +0.082 |
Yang | +0.080 |
NES | +0.075 |
erers | +0.073 |
Pokemon | +0.070 |
Neg logit contributions | |
�� | -0.166 |
apo | -0.155 |
antha | -0.151 |
mosqu | -0.145 |
utenant | -0.143 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
�� | +0.800 |
apo | +0.744 |
antha | +0.714 |
mosqu | +0.678 |
utenant | +0.674 |
Neg logit contributions | |
ni | -0.658 |
Yang | -0.650 |
NES | -0.619 |
erers | -0.609 |
Pokemon | -0.593 |
Token | chance |
Token ID | 2863 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
�� | +0.056 |
apo | +0.052 |
antha | +0.050 |
mosqu | +0.048 |
utenant | +0.047 |
Neg logit contributions | |
ni | -0.038 |
Yang | -0.038 |
NES | -0.036 |
erers | -0.035 |
Pokemon | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
ni | +0.933 |
Yang | +0.911 |
NES | +0.860 |
erers | +0.840 |
Pokemon | +0.811 |
Neg logit contributions | |
�� | -1.696 |
apo | -1.593 |
antha | -1.533 |
mosqu | -1.473 |
utenant | -1.461 |
Token | When |
Token ID | 1649 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
�� | +0.189 |
apo | +0.176 |
antha | +0.169 |
mosqu | +0.163 |
utenant | +0.160 |
Neg logit contributions | |
ni | -0.130 |
Yang | -0.128 |
NES | -0.122 |
erers | -0.120 |
Pokemon | -0.116 |
Token | writing |
Token ID | 3597 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ni | +1.177 |
Yang | +1.143 |
NES | +1.106 |
erers | +1.083 |
Pokemon | +1.048 |
Neg logit contributions | |
�� | -1.618 |
apo | -1.500 |
antha | -1.437 |
utenant | -1.373 |
mosqu | -1.364 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
�� | +2.821 |
apo | +2.642 |
antha | +2.540 |
mosqu | +2.428 |
utenant | +2.412 |
Neg logit contributions | |
ni | -2.104 |
Yang | -2.090 |
NES | -1.966 |
erers | -1.930 |
Pokemon | -1.885 |
Token | tape |
Token ID | 9154 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ni | +0.018 |
Yang | +0.017 |
NES | +0.016 |
erers | +0.016 |
Pokemon | +0.016 |
Neg logit contributions | |
�� | -0.023 |
apo | -0.022 |
antha | -0.021 |
mosqu | -0.020 |
utenant | -0.020 |
Token | tell |
Token ID | 1560 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ni | +0.416 |
Yang | +0.401 |
NES | +0.387 |
erers | +0.381 |
Pokemon | +0.367 |
Neg logit contributions | |
�� | -0.604 |
apo | -0.561 |
antha | -0.542 |
mosqu | -0.517 |
utenant | -0.514 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ni | +0.057 |
Yang | +0.056 |
NES | +0.054 |
erers | +0.053 |
Pokemon | +0.052 |
Neg logit contributions | |
�� | -0.069 |
apo | -0.064 |
antha | -0.062 |
mosqu | -0.058 |
utenant | -0.058 |
Token | writer |
Token ID | 6260 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
�� | +0.399 |
apo | +0.374 |
antha | +0.361 |
mosqu | +0.345 |
utenant | +0.343 |
Neg logit contributions | |
ni | -0.252 |
Yang | -0.248 |
NES | -0.234 |
erers | -0.230 |
Pokemon | -0.223 |
Token | likely |
Token ID | 1884 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
�� | +0.970 |
apo | +0.909 |
antha | +0.875 |
mosqu | +0.835 |
utenant | +0.831 |
Neg logit contributions | |
ni | -0.667 |
Yang | -0.660 |
NES | -0.623 |
erers | -0.612 |
Pokemon | -0.595 |
Token | used |
Token ID | 973 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
�� | +0.457 |
apo | +0.427 |
antha | +0.411 |
mosqu | +0.394 |
utenant | +0.391 |
Neg logit contributions | |
ni | -0.311 |
Yang | -0.306 |
NES | -0.288 |
erers | -0.283 |
Pokemon | -0.276 |
Token | by |
Token ID | 416 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
�� | +0.380 |
apo | +0.356 |
antha | +0.342 |
mosqu | +0.326 |
utenant | +0.324 |
Neg logit contributions | |
ni | -0.276 |
Yang | -0.273 |
NES | -0.258 |
erers | -0.254 |
Pokemon | -0.247 |
Token | the |
Token ID | 262 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
�� | +3.247 |
apo | +3.039 |
antha | +2.896 |
utenant | +2.747 |
mosqu | +2.746 |
Neg logit contributions | |
ni | -2.597 |
Yang | -2.591 |
NES | -2.455 |
erers | -2.408 |
Pokemon | -2.357 |
Token | Abraham |
Token ID | 16660 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
�� | +0.177 |
apo | +0.165 |
antha | +0.158 |
mosqu | +0.151 |
utenant | +0.150 |
Neg logit contributions | |
ni | -0.144 |
Yang | -0.142 |
NES | -0.135 |
erers | -0.133 |
Pokemon | -0.129 |
Token | Lincoln |
Token ID | 12406 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
�� | +0.498 |
apo | +0.461 |
antha | +0.447 |
mosqu | +0.421 |
utenant | +0.420 |
Neg logit contributions | |
ni | -0.465 |
Yang | -0.459 |
NES | -0.437 |
erers | -0.433 |
Pokemon | -0.420 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
�� | +2.864 |
apo | +2.678 |
antha | +2.536 |
utenant | +2.424 |
mosqu | +2.417 |
Neg logit contributions | |
ni | -2.374 |
Yang | -2.366 |
NES | -2.248 |
erers | -2.193 |
Pokemon | -2.160 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
�� | +0.369 |
apo | +0.343 |
antha | +0.331 |
mosqu | +0.316 |
utenant | +0.311 |
Neg logit contributions | |
ni | -0.294 |
Yang | -0.289 |
NES | -0.275 |
erers | -0.271 |
Pokemon | -0.263 |
Token | president |
Token ID | 1893 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
�� | +0.036 |
apo | +0.034 |
antha | +0.033 |
mosqu | +0.031 |
utenant | +0.031 |
Neg logit contributions | |
ni | -0.027 |
Yang | -0.027 |
NES | -0.025 |
erers | -0.025 |
Pokemon | -0.024 |
Token | who |
Token ID | 508 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
�� | +1.975 |
apo | +1.856 |
antha | +1.792 |
mosqu | +1.715 |
utenant | +1.715 |
Neg logit contributions | |
ni | -1.121 |
Yang | -1.112 |
NES | -1.042 |
erers | -1.018 |
Pokemon | -0.991 |
Token | actually |
Token ID | 1682 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ni | +0.157 |
Yang | +0.154 |
NES | +0.145 |
erers | +0.143 |
Pokemon | +0.138 |
Neg logit contributions | |
�� | -0.245 |
apo | -0.229 |
antha | -0.221 |
mosqu | -0.212 |
utenant | -0.209 |
Token | move |
Token ID | 21084 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
ni | +0.394 |
Yang | +0.392 |
NES | +0.373 |
erers | +0.369 |
Pokemon | +0.359 |
Neg logit contributions | |
�� | -0.421 |
apo | -0.393 |
antha | -0.374 |
mosqu | -0.355 |
utenant | -0.352 |
Token | clause |
Token ID | 13444 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
�� | +0.242 |
apo | +0.227 |
antha | +0.219 |
mosqu | +0.209 |
utenant | +0.208 |
Neg logit contributions | |
ni | -0.152 |
Yang | -0.150 |
NES | -0.141 |
erers | -0.139 |
Pokemon | -0.135 |
Token | can |
Token ID | 460 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
�� | +0.980 |
apo | +0.917 |
antha | +0.883 |
mosqu | +0.846 |
utenant | +0.841 |
Neg logit contributions | |
ni | -0.621 |
Yang | -0.612 |
NES | -0.576 |
erers | -0.564 |
Pokemon | -0.548 |
Token | be |
Token ID | 307 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ni | +0.383 |
Yang | +0.376 |
NES | +0.356 |
erers | +0.350 |
Pokemon | +0.339 |
Neg logit contributions | |
�� | -0.555 |
apo | -0.518 |
antha | -0.499 |
mosqu | -0.478 |
utenant | -0.474 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
ni | +0.685 |
Yang | +0.671 |
NES | +0.635 |
erers | +0.626 |
Pokemon | +0.605 |
Neg logit contributions | |
�� | -0.926 |
apo | -0.862 |
antha | -0.829 |
mosqu | -0.794 |
utenant | -0.786 |
Token | by |
Token ID | 416 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ni | +1.083 |
Yang | +1.065 |
NES | +1.011 |
erers | +0.990 |
Pokemon | +0.963 |
Neg logit contributions | |
�� | -1.508 |
apo | -1.411 |
antha | -1.357 |
mosqu | -1.296 |
utenant | -1.282 |
Token | his |
Token ID | 465 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
�� | +2.731 |
apo | +2.535 |
antha | +2.433 |
mosqu | +2.310 |
utenant | +2.296 |
Neg logit contributions | |
ni | -2.482 |
Yang | -2.476 |
NES | -2.346 |
erers | -2.313 |
Pokemon | -2.267 |
Token | team |
Token ID | 1074 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
�� | +0.553 |
apo | +0.518 |
antha | +0.498 |
mosqu | +0.475 |
utenant | +0.472 |
Neg logit contributions | |
ni | -0.386 |
Yang | -0.379 |
NES | -0.360 |
erers | -0.353 |
Pokemon | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
�� | +0.140 |
apo | +0.131 |
antha | +0.127 |
mosqu | +0.121 |
utenant | +0.120 |
Neg logit contributions | |
ni | -0.099 |
Yang | -0.098 |
NES | -0.093 |
erers | -0.091 |
Pokemon | -0.088 |
Token | waive |
Token ID | 40307 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ni | +0.430 |
Yang | +0.422 |
NES | +0.402 |
erers | +0.396 |
Pokemon | +0.385 |
Neg logit contributions | |
�� | -0.524 |
apo | -0.484 |
antha | -0.465 |
mosqu | -0.445 |
utenant | -0.439 |
Token | his |
Token ID | 465 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
�� | +1.031 |
apo | +0.960 |
antha | +0.923 |
mosqu | +0.878 |
utenant | +0.873 |
Neg logit contributions | |
ni | -0.817 |
Yang | -0.807 |
NES | -0.766 |
erers | -0.752 |
Pokemon | -0.734 |
Token | fi |
Token ID | 12463 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ni | +0.013 |
Yang | +0.013 |
NES | +0.012 |
erers | +0.012 |
Pokemon | +0.012 |
Neg logit contributions | |
�� | -0.021 |
apo | -0.019 |
antha | -0.019 |
mosqu | -0.018 |
utenant | -0.018 |
Token | W |
Token ID | 54 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
�� | +1.314 |
apo | +1.240 |
antha | +1.193 |
mosqu | +1.139 |
utenant | +1.136 |
Neg logit contributions | |
ni | -0.799 |
Yang | -0.790 |
NES | -0.742 |
erers | -0.730 |
Pokemon | -0.707 |
Token | u |
Token ID | 84 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ni | +1.119 |
Yang | +1.091 |
NES | +1.029 |
erers | +0.989 |
NW | +0.973 |
Neg logit contributions | |
�� | -1.710 |
apo | -1.568 |
antha | -1.528 |
mosqu | -1.486 |
utenant | -1.456 |
Token | — |
Token ID | 851 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ni | +0.184 |
Yang | +0.180 |
NES | +0.169 |
erers | +0.163 |
Pokemon | +0.159 |
Neg logit contributions | |
�� | -0.315 |
apo | -0.294 |
antha | -0.285 |
mosqu | -0.275 |
utenant | -0.272 |
Token | Dan |
Token ID | 6035 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
ni | +0.324 |
Yang | +0.319 |
NES | +0.302 |
erers | +0.296 |
Pokemon | +0.289 |
Neg logit contributions | |
�� | -0.434 |
apo | -0.403 |
antha | -0.387 |
mosqu | -0.371 |
utenant | -0.369 |
Token | Mer |
Token ID | 4638 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ni | +0.776 |
Yang | +0.759 |
NES | +0.726 |
erers | +0.709 |
Num | +0.705 |
Neg logit contributions | |
�� | -0.854 |
apo | -0.751 |
antha | -0.718 |
mosqu | -0.714 |
utenant | -0.686 |
Token | ica |
Token ID | 3970 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
�� | +3.378 |
apo | +3.220 |
antha | +3.106 |
utenant | +2.936 |
aples | +2.918 |
Neg logit contributions | |
Yang | -1.901 |
ni | -1.899 |
NES | -1.774 |
erers | -1.731 |
Pokemon | -1.689 |
Token | (@ |
Token ID | 4275 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
�� | +0.727 |
apo | +0.658 |
antha | +0.630 |
mosqu | +0.618 |
utenant | +0.583 |
Neg logit contributions | |
ni | -0.814 |
Yang | -0.801 |
NES | -0.769 |
erers | -0.755 |
Pokemon | -0.741 |
Token | dan |
Token ID | 25604 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ni | +1.031 |
Yang | +0.998 |
NES | +0.951 |
erers | +0.936 |
DO | +0.916 |
Neg logit contributions | |
�� | -1.206 |
apo | -1.070 |
mosqu | -1.046 |
antha | -1.034 |
utenant | -0.985 |
Token | meric |
Token ID | 946 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ni | +0.456 |
Yang | +0.447 |
NES | +0.428 |
erers | +0.423 |
Pokemon | +0.414 |
Neg logit contributions | |
�� | -0.355 |
apo | -0.310 |
antha | -0.295 |
mosqu | -0.291 |
utenant | -0.275 |
Token | a |
Token ID | 64 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
�� | +0.569 |
apo | +0.520 |
antha | +0.500 |
mosqu | +0.486 |
utenant | +0.473 |
Neg logit contributions | |
ni | -0.516 |
Yang | -0.509 |
NES | -0.483 |
erers | -0.477 |
Pokemon | -0.465 |
Token | a |
Token ID | 257 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
�� | +0.075 |
apo | +0.070 |
antha | +0.067 |
mosqu | +0.064 |
utenant | +0.064 |
Neg logit contributions | |
ni | -0.057 |
Yang | -0.056 |
NES | -0.053 |
erers | -0.052 |
Pokemon | -0.051 |
Token | radio |
Token ID | 5243 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ni | +0.117 |
Yang | +0.115 |
NES | +0.109 |
erers | +0.107 |
Pokemon | +0.104 |
Neg logit contributions | |
�� | -0.152 |
apo | -0.141 |
antha | -0.135 |
mosqu | -0.129 |
utenant | -0.128 |
Token | debate |
Token ID | 4384 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
�� | +0.374 |
apo | +0.350 |
antha | +0.337 |
mosqu | +0.321 |
utenant | +0.319 |
Neg logit contributions | |
ni | -0.279 |
Yang | -0.277 |
NES | -0.261 |
erers | -0.258 |
Pokemon | -0.251 |
Token | hosted |
Token ID | 12007 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ni | +0.351 |
Yang | +0.346 |
NES | +0.325 |
erers | +0.318 |
Pokemon | +0.309 |
Neg logit contributions | |
�� | -0.582 |
apo | -0.543 |
antha | -0.524 |
mosqu | -0.502 |
utenant | -0.499 |
Token | by |
Token ID | 416 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ni | +0.588 |
Yang | +0.580 |
NES | +0.549 |
erers | +0.536 |
Pokemon | +0.523 |
Neg logit contributions | |
�� | -0.853 |
apo | -0.798 |
antha | -0.767 |
mosqu | -0.734 |
utenant | -0.730 |
Token | La |
Token ID | 4689 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
�� | +1.499 |
apo | +1.401 |
antha | +1.345 |
mosqu | +1.277 |
utenant | +1.269 |
Neg logit contributions | |
ni | -1.224 |
Yang | -1.214 |
NES | -1.151 |
erers | -1.133 |
Pokemon | -1.106 |
Token | Opinion |
Token ID | 29525 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
�� | +2.972 |
apo | +2.795 |
antha | +2.676 |
mosqu | +2.553 |
utenant | +2.547 |
Neg logit contributions | |
ni | -2.253 |
Yang | -2.238 |
NES | -2.116 |
erers | -2.082 |
Pokemon | -2.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
�� | +1.300 |
apo | +1.226 |
antha | +1.179 |
mosqu | +1.128 |
utenant | +1.125 |
Neg logit contributions | |
ni | -0.822 |
Yang | -0.815 |
NES | -0.766 |
erers | -0.752 |
Pokemon | -0.731 |
Token | public |
Token ID | 1171 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ni | +0.312 |
Yang | +0.307 |
NES | +0.292 |
erers | +0.286 |
Pokemon | +0.278 |
Neg logit contributions | |
�� | -0.406 |
apo | -0.376 |
antha | -0.362 |
mosqu | -0.345 |
utenant | -0.344 |
Token | radio |
Token ID | 5243 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
ni | +0.406 |
Yang | +0.395 |
NES | +0.375 |
erers | +0.366 |
Pokemon | +0.357 |
Neg logit contributions | |
�� | -0.574 |
apo | -0.537 |
antha | -0.515 |
utenant | -0.489 |
mosqu | -0.488 |
Token | station |
Token ID | 4429 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
�� | +0.069 |
apo | +0.065 |
antha | +0.062 |
mosqu | +0.060 |
utenant | +0.060 |
Neg logit contributions | |
ni | -0.038 |
Yang | -0.037 |
NES | -0.035 |
erers | -0.034 |
Pokemon | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ni | +1.202 |
Yang | +1.181 |
NES | +1.132 |
erers | +1.114 |
Pokemon | +1.087 |
Neg logit contributions | |
�� | -1.441 |
apo | -1.330 |
antha | -1.285 |
mosqu | -1.217 |
utenant | -1.195 |
Token | - |
Token ID | 532 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ni | +0.019 |
Yang | +0.019 |
NES | +0.018 |
erers | +0.018 |
Pokemon | +0.017 |
Neg logit contributions | |
�� | -0.030 |
apo | -0.028 |
antha | -0.027 |
mosqu | -0.026 |
utenant | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
�� | +1.103 |
apo | +1.029 |
antha | +0.990 |
mosqu | +0.948 |
utenant | +0.939 |
Neg logit contributions | |
ni | -0.780 |
Yang | -0.770 |
NES | -0.728 |
erers | -0.717 |
Pokemon | -0.697 |
Token | creates |
Token ID | 8075 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ni | +0.225 |
Yang | +0.221 |
NES | +0.206 |
erers | +0.204 |
Pokemon | +0.197 |
Neg logit contributions | |
�� | -0.356 |
apo | -0.329 |
antha | -0.318 |
mosqu | -0.308 |
utenant | -0.302 |
Token | a |
Token ID | 257 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ni | +0.548 |
Yang | +0.542 |
NES | +0.515 |
erers | +0.508 |
Pokemon | +0.494 |
Neg logit contributions | |
�� | -0.686 |
apo | -0.637 |
antha | -0.612 |
mosqu | -0.582 |
utenant | -0.576 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
ni | +0.756 |
Yang | +0.747 |
NES | +0.703 |
erers | +0.690 |
Num | +0.667 |
Neg logit contributions | |
�� | -1.158 |
apo | -1.084 |
antha | -1.044 |
mosqu | -0.995 |
utenant | -0.987 |
Token | of |
Token ID | 286 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
�� | +0.005 |
apo | +0.005 |
antha | +0.004 |
mosqu | +0.004 |
utenant | +0.004 |
Neg logit contributions | |
ni | -0.003 |
Yang | -0.003 |
NES | -0.003 |
erers | -0.003 |
Pokemon | -0.003 |
Token | entry |
Token ID | 5726 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ni | +0.817 |
Yang | +0.808 |
NES | +0.761 |
erers | +0.751 |
Pokemon | +0.727 |
Neg logit contributions | |
�� | -1.135 |
apo | -1.056 |
antha | -1.015 |
mosqu | -0.967 |
utenant | -0.961 |
Token | points |
Token ID | 2173 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
�� | +0.722 |
apo | +0.678 |
antha | +0.656 |
mosqu | +0.629 |
utenant | +0.627 |
Neg logit contributions | |
ni | -0.410 |
Yang | -0.405 |
NES | -0.379 |
erers | -0.372 |
Pokemon | -0.360 |
Token | where |
Token ID | 810 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
�� | +1.375 |
apo | +1.291 |
antha | +1.243 |
mosqu | +1.186 |
utenant | +1.183 |
Neg logit contributions | |
ni | -0.906 |
Yang | -0.896 |
NES | -0.845 |
erers | -0.828 |
Pokemon | -0.806 |
Token | people |
Token ID | 661 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ni | +0.516 |
Yang | +0.503 |
NES | +0.481 |
erers | +0.476 |
Pokemon | +0.463 |
Neg logit contributions | |
�� | -0.658 |
apo | -0.611 |
antha | -0.586 |
mosqu | -0.563 |
utenant | -0.555 |
Token | than |
Token ID | 621 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ni | +0.210 |
Yang | +0.206 |
NES | +0.195 |
erers | +0.191 |
Pokemon | +0.185 |
Neg logit contributions | |
�� | -0.323 |
apo | -0.300 |
antha | -0.289 |
mosqu | -0.277 |
utenant | -0.275 |
Token | they |
Token ID | 484 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
�� | +0.847 |
apo | +0.786 |
antha | +0.760 |
mosqu | +0.727 |
utenant | +0.722 |
Neg logit contributions | |
ni | -0.587 |
Yang | -0.575 |
NES | -0.543 |
erers | -0.533 |
Pokemon | -0.516 |
Token | initially |
Token ID | 7317 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
�� | +0.612 |
apo | +0.574 |
antha | +0.554 |
mosqu | +0.531 |
utenant | +0.527 |
Neg logit contributions | |
ni | -0.383 |
Yang | -0.378 |
NES | -0.355 |
erers | -0.349 |
Pokemon | -0.338 |
Token | seem |
Token ID | 1283 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ni | +0.205 |
Yang | +0.202 |
NES | +0.191 |
erers | +0.187 |
Pokemon | +0.182 |
Neg logit contributions | |
�� | -0.303 |
apo | -0.284 |
antha | -0.273 |
mosqu | -0.261 |
utenant | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ni | +0.965 |
Yang | +0.943 |
NES | +0.884 |
erers | +0.870 |
Pokemon | +0.837 |
Neg logit contributions | |
�� | -1.677 |
apo | -1.554 |
antha | -1.504 |
mosqu | -1.451 |
utenant | -1.433 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
�� | +0.034 |
apo | +0.032 |
antha | +0.031 |
mosqu | +0.030 |
utenant | +0.029 |
Neg logit contributions | |
ni | -0.022 |
Yang | -0.022 |
NES | -0.020 |
erers | -0.020 |
Pokemon | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
�� | +0.611 |
apo | +0.571 |
antha | +0.552 |
mosqu | +0.532 |
utenant | +0.524 |
Neg logit contributions | |
ni | -0.375 |
Yang | -0.370 |
NES | -0.348 |
erers | -0.340 |
Pokemon | -0.331 |
Token | " |
Token ID | 1 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
�� | +0.210 |
apo | +0.196 |
antha | +0.189 |
mosqu | +0.182 |
utenant | +0.180 |
Neg logit contributions | |
ni | -0.140 |
Yang | -0.138 |
NES | -0.130 |
erers | -0.128 |
Pokemon | -0.124 |
Token | We |
Token ID | 1135 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
�� | +0.195 |
apo | +0.182 |
antha | +0.175 |
mosqu | +0.169 |
utenant | +0.167 |
Neg logit contributions | |
ni | -0.133 |
Yang | -0.131 |
NES | -0.124 |
erers | -0.121 |
Pokemon | -0.118 |
Token | think |
Token ID | 892 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +1.034 |
apo | +0.972 |
antha | +0.938 |
mosqu | +0.898 |
utenant | +0.894 |
Neg logit contributions | |
ni | -0.615 |
Yang | -0.608 |
NES | -0.570 |
erers | -0.559 |
Pokemon | -0.542 |
Token | we |
Token ID | 356 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
�� | +0.384 |
apo | +0.355 |
antha | +0.341 |
mosqu | +0.325 |
utenant | +0.321 |
Neg logit contributions | |
ni | -0.334 |
Yang | -0.328 |
NES | -0.312 |
erers | -0.308 |
Pokemon | -0.299 |
Token | light |
Token ID | 1657 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
�� | +1.173 |
apo | +1.097 |
antha | +1.057 |
mosqu | +1.009 |
utenant | +1.002 |
Neg logit contributions | |
ni | -0.834 |
Yang | -0.823 |
NES | -0.776 |
erers | -0.762 |
Pokemon | -0.741 |
Token | hearted |
Token ID | 20122 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ni | +1.068 |
Yang | +1.040 |
NES | +0.978 |
erers | +0.959 |
Pokemon | +0.919 |
Neg logit contributions | |
�� | -1.882 |
apo | -1.755 |
antha | -1.700 |
mosqu | -1.636 |
utenant | -1.627 |
Token | dis |
Token ID | 595 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ni | +0.966 |
Yang | +0.946 |
NES | +0.881 |
erers | +0.864 |
Pokemon | +0.834 |
Neg logit contributions | |
�� | -1.731 |
apo | -1.624 |
antha | -1.556 |
mosqu | -1.505 |
utenant | -1.496 |
Token | section |
Token ID | 5458 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
�� | +0.336 |
apo | +0.312 |
antha | +0.300 |
mosqu | +0.287 |
utenant | +0.284 |
Neg logit contributions | |
ni | -0.261 |
Yang | -0.257 |
NES | -0.243 |
erers | -0.240 |
Pokemon | -0.233 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ni | +1.444 |
Yang | +1.427 |
NES | +1.331 |
erers | +1.302 |
Pokemon | +1.260 |
Neg logit contributions | |
�� | -2.726 |
apo | -2.569 |
antha | -2.482 |
mosqu | -2.383 |
utenant | -2.372 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ni | +0.246 |
Yang | +0.242 |
NES | +0.230 |
erers | +0.226 |
Pokemon | +0.221 |
Neg logit contributions | |
�� | -0.305 |
apo | -0.283 |
antha | -0.271 |
mosqu | -0.256 |
utenant | -0.255 |
Token | Toronto |
Token ID | 6586 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
�� | +0.098 |
apo | +0.091 |
antha | +0.088 |
mosqu | +0.084 |
utenant | +0.084 |
Neg logit contributions | |
ni | -0.065 |
Yang | -0.064 |
NES | -0.060 |
erers | -0.059 |
Pokemon | -0.057 |
Token | condo |
Token ID | 32119 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
ni | +1.767 |
Yang | +1.691 |
NES | +1.590 |
erers | +1.532 |
Num | +1.488 |
Neg logit contributions | |
�� | -3.627 |
apo | -3.386 |
antha | -3.257 |
utenant | -3.148 |
mosqu | -3.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ni | +1.370 |
Yang | +1.341 |
NES | +1.262 |
erers | +1.238 |
Pokemon | +1.199 |
Neg logit contributions | |
�� | -2.118 |
apo | -1.966 |
antha | -1.892 |
utenant | -1.818 |
mosqu | -1.806 |
Token |
|
Token ID | 198 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
�� | +0.387 |
apo | +0.361 |
antha | +0.348 |
mosqu | +0.333 |
utenant | +0.330 |
Neg logit contributions | |
ni | -0.272 |
Yang | -0.268 |
NES | -0.253 |
erers | -0.249 |
Pokemon | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
�� | +0.199 |
apo | +0.186 |
antha | +0.180 |
mosqu | +0.175 |
utenant | +0.170 |
Neg logit contributions | |
ni | -0.120 |
Yang | -0.118 |
NES | -0.111 |
erers | -0.108 |
Pokemon | -0.105 |
Token | on |
Token ID | 319 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
�� | +0.676 |
apo | +0.633 |
antha | +0.611 |
mosqu | +0.589 |
utenant | +0.583 |
Neg logit contributions | |
ni | -0.398 |
Yang | -0.392 |
NES | -0.368 |
erers | -0.360 |
Pokemon | -0.349 |
Token | IGN |
Token ID | 28730 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ni | +0.268 |
Yang | +0.263 |
NES | +0.251 |
erers | +0.246 |
Pokemon | +0.240 |
Neg logit contributions | |
�� | -0.319 |
apo | -0.295 |
antha | -0.284 |
mosqu | -0.270 |
utenant | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
ni | +0.201 |
Yang | +0.197 |
NES | +0.187 |
erers | +0.180 |
Pokemon | +0.176 |
Neg logit contributions | |
�� | -0.351 |
apo | -0.328 |
antha | -0.319 |
mosqu | -0.307 |
utenant | -0.302 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ni | +0.145 |
Yang | +0.142 |
NES | +0.134 |
erers | +0.131 |
Pokemon | +0.128 |
Neg logit contributions | |
�� | -0.226 |
apo | -0.211 |
antha | -0.204 |
mosqu | -0.197 |
utenant | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ni | +0.230 |
Yang | +0.226 |
NES | +0.212 |
erers | +0.207 |
Pokemon | +0.202 |
Neg logit contributions | |
�� | -0.393 |
apo | -0.365 |
antha | -0.354 |
mosqu | -0.347 |
utenant | -0.335 |
Token | To |
Token ID | 2514 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ni | +0.417 |
Yang | +0.414 |
NES | +0.391 |
erers | +0.379 |
Pokemon | +0.373 |
Neg logit contributions | |
�� | -0.615 |
apo | -0.572 |
antha | -0.554 |
mosqu | -0.536 |
utenant | -0.524 |
Token | celebrate |
Token ID | 10648 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ni | +0.035 |
Yang | +0.035 |
NES | +0.033 |
erers | +0.032 |
Pokemon | +0.031 |
Neg logit contributions | |
�� | -0.049 |
apo | -0.045 |
antha | -0.044 |
mosqu | -0.042 |
utenant | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ni | +0.491 |
Yang | +0.485 |
NES | +0.465 |
erers | +0.453 |
Pokemon | +0.444 |
Neg logit contributions | |
�� | -0.578 |
apo | -0.536 |
antha | -0.512 |
mosqu | -0.491 |
utenant | -0.481 |
Token | upcoming |
Token ID | 7865 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ni | +0.554 |
Yang | +0.545 |
NES | +0.522 |
erers | +0.503 |
Num | +0.496 |
Neg logit contributions | |
�� | -0.765 |
apo | -0.709 |
antha | -0.678 |
mosqu | -0.653 |
utenant | -0.644 |
Token | Halo |
Token ID | 18597 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ni | +0.767 |
Yang | +0.754 |
NES | +0.720 |
erers | +0.697 |
Pokemon | +0.685 |
Neg logit contributions | |
�� | -0.988 |
apo | -0.920 |
antha | -0.879 |
mosqu | -0.844 |
utenant | -0.831 |
Token | : |
Token ID | 25 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ni | +1.079 |
Yang | +1.051 |
NES | +0.994 |
erers | +0.961 |
Pokemon | +0.947 |
Neg logit contributions | |
�� | -1.741 |
apo | -1.639 |
antha | -1.575 |
mosqu | -1.525 |
utenant | -1.506 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ni | +0.611 |
Yang | +0.602 |
NES | +0.565 |
erers | +0.561 |
Pokemon | +0.548 |
Neg logit contributions | |
�� | -0.751 |
apo | -0.697 |
antha | -0.670 |
mosqu | -0.640 |
utenant | -0.635 |
Token | challenge |
Token ID | 4427 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ni | +0.262 |
Yang | +0.258 |
NES | +0.242 |
erers | +0.239 |
Pokemon | +0.232 |
Neg logit contributions | |
�� | -0.387 |
apo | -0.363 |
antha | -0.349 |
mosqu | -0.334 |
utenant | -0.333 |
Token | of |
Token ID | 286 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ni | +0.384 |
Yang | +0.376 |
NES | +0.352 |
erers | +0.345 |
Pokemon | +0.332 |
Neg logit contributions | |
�� | -0.746 |
apo | -0.702 |
antha | -0.680 |
mosqu | -0.652 |
utenant | -0.650 |
Token | advancing |
Token ID | 19988 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
�� | +0.415 |
apo | +0.386 |
antha | +0.370 |
mosqu | +0.352 |
utenant | +0.352 |
Neg logit contributions | |
ni | -0.330 |
Yang | -0.325 |
NES | -0.308 |
erers | -0.303 |
Pokemon | -0.295 |
Token | new |
Token ID | 649 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
�� | +0.711 |
apo | +0.661 |
antha | +0.634 |
mosqu | +0.603 |
utenant | +0.599 |
Neg logit contributions | |
ni | -0.589 |
Yang | -0.581 |
NES | -0.552 |
erers | -0.543 |
Pokemon | -0.530 |
Token | proposals |
Token ID | 11628 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ni | +0.236 |
Yang | +0.232 |
NES | +0.219 |
erers | +0.216 |
Pokemon | +0.208 |
Neg logit contributions | |
�� | -0.320 |
apo | -0.300 |
antha | -0.288 |
mosqu | -0.275 |
utenant | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
�� | +0.259 |
apo | +0.242 |
antha | +0.234 |
mosqu | +0.224 |
utenant | +0.222 |
Neg logit contributions | |
ni | -0.164 |
Yang | -0.162 |
NES | -0.152 |
erers | -0.149 |
Pokemon | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
�� | +0.467 |
apo | +0.435 |
antha | +0.420 |
mosqu | +0.405 |
utenant | +0.399 |
Neg logit contributions | |
ni | -0.310 |
Yang | -0.305 |
NES | -0.287 |
erers | -0.282 |
Pokemon | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
�� | +0.688 |
apo | +0.642 |
antha | +0.621 |
mosqu | +0.599 |
utenant | +0.590 |
Neg logit contributions | |
ni | -0.420 |
Yang | -0.414 |
NES | -0.389 |
erers | -0.381 |
Pokemon | -0.370 |
Token | Please |
Token ID | 5492 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
�� | +0.238 |
apo | +0.223 |
antha | +0.214 |
mosqu | +0.206 |
utenant | +0.204 |
Neg logit contributions | |
ni | -0.155 |
Yang | -0.153 |
NES | -0.144 |
erers | -0.141 |
Pokemon | -0.137 |
Token | read |
Token ID | 1100 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ni | +0.195 |
Yang | +0.191 |
NES | +0.179 |
erers | +0.175 |
Pokemon | +0.169 |
Neg logit contributions | |
�� | -0.363 |
apo | -0.342 |
antha | -0.330 |
mosqu | -0.317 |
utenant | -0.315 |
Token | � |
Token ID | 447 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ni | +0.901 |
Yang | +0.879 |
NES | +0.820 |
erers | +0.814 |
Pokemon | +0.782 |
Neg logit contributions | |
�� | -1.515 |
apo | -1.415 |
antha | -1.372 |
mosqu | -1.319 |
utenant | -1.307 |
Token | � |
Token ID | 247 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
�� | +0.531 |
apo | +0.508 |
antha | +0.492 |
mosqu | +0.480 |
utenant | +0.461 |
Neg logit contributions | |
ni | -0.371 |
Yang | -0.369 |
NES | -0.345 |
erers | -0.340 |
Pokemon | -0.330 |
Token | s |
Token ID | 82 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
�� | +0.045 |
apo | +0.042 |
antha | +0.041 |
mosqu | +0.039 |
utenant | +0.039 |
Neg logit contributions | |
ni | -0.026 |
Yang | -0.025 |
NES | -0.023 |
erers | -0.023 |
Pokemon | -0.022 |
Token | talent |
Token ID | 7401 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ni | +0.183 |
Yang | +0.179 |
NES | +0.169 |
erers | +0.167 |
Pokemon | +0.163 |
Neg logit contributions | |
�� | -0.238 |
apo | -0.221 |
antha | -0.213 |
mosqu | -0.204 |
utenant | -0.203 |
Token | for |
Token ID | 329 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
�� | +0.783 |
apo | +0.737 |
antha | +0.712 |
mosqu | +0.683 |
utenant | +0.678 |
Neg logit contributions | |
ni | -0.445 |
Yang | -0.438 |
NES | -0.409 |
erers | -0.401 |
Pokemon | -0.389 |
Token | disruption |
Token ID | 19911 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
�� | +0.186 |
apo | +0.173 |
antha | +0.167 |
mosqu | +0.159 |
utenant | +0.158 |
Neg logit contributions | |
ni | -0.142 |
Yang | -0.139 |
NES | -0.131 |
erers | -0.129 |
Pokemon | -0.126 |
Token | is |
Token ID | 318 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
ni | +1.058 |
Yang | +1.025 |
NES | +0.951 |
erers | +0.939 |
Pokemon | +0.907 |
Neg logit contributions | |
�� | -1.938 |
apo | -1.815 |
antha | -1.752 |
mosqu | -1.696 |
utenant | -1.677 |
Token | a |
Token ID | 257 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ni | +0.128 |
Yang | +0.126 |
NES | +0.119 |
erers | +0.117 |
Pokemon | +0.114 |
Neg logit contributions | |
�� | -0.179 |
apo | -0.167 |
antha | -0.161 |
mosqu | -0.155 |
utenant | -0.152 |
Token | big |
Token ID | 1263 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ni | +0.382 |
Yang | +0.377 |
NES | +0.348 |
erers | +0.345 |
Pokemon | +0.335 |
Neg logit contributions | |
�� | -0.540 |
apo | -0.502 |
antha | -0.486 |
mosqu | -0.469 |
aples | -0.460 |
Token | part |
Token ID | 636 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ni | +0.358 |
Yang | +0.352 |
NES | +0.330 |
erers | +0.321 |
Pokemon | +0.314 |
Neg logit contributions | |
�� | -0.549 |
apo | -0.510 |
antha | -0.496 |
mosqu | -0.477 |
utenant | -0.471 |
Token | of |
Token ID | 286 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ni | +0.726 |
Yang | +0.719 |
NES | +0.671 |
erers | +0.655 |
Pokemon | +0.636 |
Neg logit contributions | |
�� | -1.352 |
apo | -1.272 |
antha | -1.225 |
mosqu | -1.177 |
utenant | -1.175 |
Token | d |
Token ID | 67 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ni | +0.285 |
Yang | +0.281 |
NES | +0.268 |
erers | +0.262 |
Pokemon | +0.257 |
Neg logit contributions | |
�� | -0.342 |
apo | -0.318 |
antha | -0.306 |
mosqu | -0.291 |
utenant | -0.289 |
Token | owntown |
Token ID | 22748 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
�� | +0.079 |
apo | +0.073 |
antha | +0.070 |
mosqu | +0.067 |
utenant | +0.066 |
Neg logit contributions | |
ni | -0.068 |
Yang | -0.067 |
NES | -0.064 |
erers | -0.062 |
Pokemon | -0.061 |
Token | allowance |
Token ID | 24930 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
�� | +0.049 |
apo | +0.046 |
antha | +0.045 |
mosqu | +0.043 |
utenant | +0.043 |
Neg logit contributions | |
ni | -0.028 |
Yang | -0.028 |
NES | -0.026 |
erers | -0.026 |
Pokemon | -0.025 |
Token | ." |
Token ID | 526 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
�� | +0.102 |
apo | +0.096 |
antha | +0.093 |
mosqu | +0.089 |
utenant | +0.089 |
Neg logit contributions | |
ni | -0.052 |
Yang | -0.051 |
NES | -0.048 |
erers | -0.047 |
Pokemon | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ni | +0.718 |
Yang | +0.706 |
NES | +0.666 |
erers | +0.651 |
Pokemon | +0.630 |
Neg logit contributions | |
�� | -1.072 |
apo | -0.995 |
antha | -0.957 |
mosqu | -0.931 |
utenant | -0.902 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ni | +0.517 |
Yang | +0.506 |
NES | +0.474 |
erers | +0.461 |
Pokemon | +0.448 |
Neg logit contributions | |
�� | -0.931 |
apo | -0.854 |
antha | -0.832 |
mosqu | -0.829 |
utenant | -0.784 |
Token | P |
Token ID | 47 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
ni | +0.659 |
Yang | +0.655 |
NES | +0.615 |
erers | +0.596 |
Pokemon | +0.586 |
Neg logit contributions | |
�� | -1.042 |
apo | -0.969 |
antha | -0.937 |
mosqu | -0.908 |
utenant | -0.889 |
Token | owell |
Token ID | 32829 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
�� | +0.015 |
apo | +0.013 |
antha | +0.012 |
mosqu | +0.012 |
utenant | +0.011 |
Neg logit contributions | |
ni | -0.025 |
Yang | -0.025 |
NES | -0.024 |
erers | -0.024 |
Pokemon | -0.023 |
Token | describes |
Token ID | 8477 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ni | +0.020 |
Yang | +0.020 |
NES | +0.019 |
erers | +0.018 |
Pokemon | +0.018 |
Neg logit contributions | |
�� | -0.035 |
apo | -0.033 |
antha | -0.032 |
mosqu | -0.031 |
utenant | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
�� | +0.825 |
apo | +0.765 |
antha | +0.731 |
mosqu | +0.693 |
utenant | +0.688 |
Neg logit contributions | |
ni | -0.768 |
Yang | -0.761 |
NES | -0.725 |
erers | -0.714 |
Pokemon | -0.697 |
Token | benefit |
Token ID | 4414 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
ni | +0.438 |
Yang | +0.432 |
NES | +0.407 |
erers | +0.399 |
Pokemon | +0.386 |
Neg logit contributions | |
�� | -0.680 |
apo | -0.638 |
antha | -0.613 |
mosqu | -0.589 |
utenant | -0.583 |
Token | is |
Token ID | 318 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ni | +0.542 |
Yang | +0.529 |
NES | +0.494 |
erers | +0.491 |
Pokemon | +0.472 |
Neg logit contributions | |
�� | -0.883 |
apo | -0.816 |
antha | -0.787 |
mosqu | -0.765 |
utenant | -0.750 |
Token | concerned |
Token ID | 5213 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ni | +0.691 |
Yang | +0.678 |
NES | +0.637 |
erers | +0.630 |
Pokemon | +0.609 |
Neg logit contributions | |
�� | -1.021 |
apo | -0.943 |
antha | -0.910 |
mosqu | -0.873 |
utenant | -0.858 |
Token | not |
Token ID | 407 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
ni | +0.895 |
Yang | +0.871 |
NES | +0.827 |
erers | +0.825 |
Pokemon | +0.792 |
Neg logit contributions | |
�� | -1.229 |
apo | -1.141 |
antha | -1.104 |
utenant | -1.046 |
mosqu | -1.043 |
Token | to |
Token ID | 284 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ni | +0.180 |
Yang | +0.177 |
NES | +0.169 |
erers | +0.169 |
Pokemon | +0.164 |
Neg logit contributions | |
�� | -0.177 |
apo | -0.162 |
antha | -0.156 |
utenant | -0.146 |
mosqu | -0.146 |
Token | trigger |
Token ID | 7616 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ni | +1.076 |
Yang | +1.042 |
NES | +0.980 |
erers | +0.975 |
Pokemon | +0.934 |
Neg logit contributions | |
�� | -1.706 |
apo | -1.587 |
antha | -1.535 |
mosqu | -1.476 |
utenant | -1.441 |
Token | panic |
Token ID | 13619 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ni | +0.274 |
Yang | +0.271 |
NES | +0.256 |
erers | +0.252 |
Pokemon | +0.245 |
Neg logit contributions | |
�� | -0.354 |
apo | -0.328 |
antha | -0.315 |
utenant | -0.299 |
mosqu | -0.299 |
Token | measures |
Token ID | 5260 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ni | +0.859 |
Yang | +0.842 |
erers | +0.786 |
NES | +0.785 |
Pokemon | +0.751 |
Neg logit contributions | |
�� | -1.373 |
apo | -1.277 |
antha | -1.238 |
mosqu | -1.177 |
utenant | -1.177 |
Token | such |
Token ID | 884 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
�� | +0.639 |
apo | +0.597 |
antha | +0.577 |
mosqu | +0.553 |
utenant | +0.548 |
Neg logit contributions | |
ni | -0.411 |
Yang | -0.405 |
NES | -0.380 |
erers | -0.374 |
Pokemon | -0.363 |
Token | as |
Token ID | 355 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
ni | +0.098 |
Yang | +0.098 |
NES | +0.091 |
erers | +0.090 |
Pokemon | +0.088 |
Neg logit contributions | |
�� | -0.147 |
apo | -0.136 |
antha | -0.132 |
mosqu | -0.127 |
utenant | -0.125 |
Token | border |
Token ID | 4865 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ni | +0.127 |
Yang | +0.126 |
NES | +0.118 |
erers | +0.117 |
Pokemon | +0.113 |
Neg logit contributions | |
�� | -0.170 |
apo | -0.159 |
antha | -0.153 |
utenant | -0.145 |
mosqu | -0.145 |
Token | closures |
Token ID | 32149 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ni | +0.532 |
Yang | +0.528 |
NES | +0.501 |
erers | +0.490 |
Pokemon | +0.480 |
Neg logit contributions | |
�� | -0.611 |
apo | -0.564 |
antha | -0.544 |
mosqu | -0.516 |
utenant | -0.513 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ni | +0.232 |
Yang | +0.226 |
NES | +0.214 |
erers | +0.210 |
Num | +0.205 |
Neg logit contributions | |
�� | -0.321 |
apo | -0.297 |
antha | -0.285 |
mosqu | -0.273 |
utenant | -0.270 |
Token | side |
Token ID | 1735 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ni | +0.176 |
Yang | +0.172 |
NES | +0.163 |
erers | +0.160 |
Pokemon | +0.154 |
Neg logit contributions | |
�� | -0.259 |
apo | -0.241 |
antha | -0.232 |
mosqu | -0.222 |
utenant | -0.221 |
Token | - |
Token ID | 12 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ni | +0.880 |
Yang | +0.862 |
NES | +0.809 |
erers | +0.800 |
Pokemon | +0.769 |
Neg logit contributions | |
�� | -1.425 |
apo | -1.331 |
antha | -1.281 |
mosqu | -1.236 |
utenant | -1.223 |
Token | by |
Token ID | 1525 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
�� | +0.810 |
apo | +0.755 |
antha | +0.720 |
mosqu | +0.677 |
utenant | +0.676 |
Neg logit contributions | |
ni | -0.791 |
Yang | -0.784 |
NES | -0.748 |
erers | -0.737 |
Pokemon | -0.720 |
Token | - |
Token ID | 12 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
�� | +2.598 |
apo | +2.450 |
antha | +2.355 |
utenant | +2.245 |
mosqu | +2.213 |
Neg logit contributions | |
ni | -1.750 |
Yang | -1.739 |
NES | -1.649 |
erers | -1.608 |
Pokemon | -1.570 |
Token | side |
Token ID | 1589 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ni | +0.117 |
Yang | +0.114 |
NES | +0.106 |
erers | +0.103 |
Pokemon | +0.100 |
Neg logit contributions | |
�� | -0.219 |
apo | -0.203 |
antha | -0.198 |
mosqu | -0.195 |
utenant | -0.190 |
Token | M |
Token ID | 337 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ni | +1.682 |
Yang | +1.653 |
NES | +1.552 |
erers | +1.541 |
CG | +1.500 |
Neg logit contributions | |
�� | -2.378 |
apo | -2.211 |
antha | -2.132 |
mosqu | -2.045 |
utenant | -2.021 |
Token | TF |
Token ID | 10234 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
�� | +0.734 |
apo | +0.688 |
antha | +0.667 |
mosqu | +0.640 |
utenant | +0.635 |
Neg logit contributions | |
ni | -0.415 |
Yang | -0.406 |
NES | -0.383 |
erers | -0.376 |
Pokemon | -0.361 |
Token | charts |
Token ID | 15907 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ni | +0.345 |
Yang | +0.339 |
NES | +0.321 |
erers | +0.316 |
Pokemon | +0.307 |
Neg logit contributions | |
�� | -0.493 |
apo | -0.461 |
antha | -0.444 |
mosqu | -0.425 |
utenant | -0.422 |
Token | of |
Token ID | 286 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
�� | +0.335 |
apo | +0.314 |
antha | +0.302 |
mosqu | +0.291 |
utenant | +0.288 |
Neg logit contributions | |
ni | -0.205 |
Yang | -0.201 |
NES | -0.190 |
erers | -0.186 |
Pokemon | -0.180 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ni | +0.538 |
Yang | +0.521 |
NES | +0.499 |
erers | +0.492 |
Num | +0.483 |
Neg logit contributions | |
�� | -0.661 |
apo | -0.607 |
antha | -0.585 |
mosqu | -0.552 |
utenant | -0.548 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ni | +0.276 |
Yang | +0.272 |
NES | +0.254 |
erers | +0.248 |
Pokemon | +0.241 |
Neg logit contributions | |
�� | -0.483 |
apo | -0.446 |
antha | -0.434 |
mosqu | -0.428 |
utenant | -0.411 |
Token | B |
Token ID | 33 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ni | +0.284 |
Yang | +0.279 |
NES | +0.264 |
erers | +0.259 |
Pokemon | +0.250 |
Neg logit contributions | |
�� | -0.431 |
apo | -0.403 |
antha | -0.388 |
mosqu | -0.369 |
utenant | -0.369 |
Token | earing |
Token ID | 6648 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
�� | +0.418 |
apo | +0.397 |
antha | +0.384 |
mosqu | +0.376 |
utenant | +0.369 |
Neg logit contributions | |
ni | -0.133 |
Yang | -0.128 |
NES | -0.116 |
erers | -0.114 |
Pokemon | -0.105 |
Token | : |
Token ID | 25 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
ni | +1.087 |
Yang | +1.056 |
NES | +0.994 |
erers | +0.977 |
Pokemon | +0.952 |
Neg logit contributions | |
�� | -1.726 |
apo | -1.587 |
mosqu | -1.553 |
antha | -1.542 |
utenant | -1.444 |
Token | Size |
Token ID | 12849 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ni | +0.114 |
Yang | +0.113 |
NES | +0.107 |
erers | +0.105 |
Pokemon | +0.102 |
Neg logit contributions | |
�� | -0.151 |
apo | -0.141 |
antha | -0.135 |
mosqu | -0.128 |
utenant | -0.128 |
Token | C |
Token ID | 327 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ni | +0.032 |
Yang | +0.032 |
NES | +0.029 |
erers | +0.029 |
Pokemon | +0.028 |
Neg logit contributions | |
�� | -0.071 |
apo | -0.067 |
antha | -0.065 |
mosqu | -0.063 |
utenant | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
ni | +0.899 |
Yang | +0.890 |
NES | +0.833 |
erers | +0.825 |
Pokemon | +0.802 |
Neg logit contributions | |
�� | -1.455 |
apo | -1.360 |
antha | -1.313 |
mosqu | -1.258 |
utenant | -1.249 |
Token | Center |
Token ID | 3337 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
�� | +0.241 |
apo | +0.227 |
antha | +0.220 |
mosqu | +0.211 |
utenant | +0.210 |
Neg logit contributions | |
ni | -0.116 |
Yang | -0.114 |
NES | -0.106 |
erers | -0.103 |
Pokemon | -0.100 |
Token | Tr |
Token ID | 833 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ni | +0.499 |
Yang | +0.492 |
NES | +0.463 |
erers | +0.453 |
Pokemon | +0.439 |
Neg logit contributions | |
�� | -0.827 |
apo | -0.777 |
antha | -0.749 |
mosqu | -0.718 |
utenant | -0.714 |
Token | ac |
Token ID | 330 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ni | +0.206 |
Yang | +0.204 |
NES | +0.194 |
erers | +0.192 |
Pokemon | +0.187 |
Neg logit contributions | |
�� | -0.213 |
apo | -0.196 |
antha | -0.188 |
mosqu | -0.178 |
utenant | -0.177 |
Token | cent |
Token ID | 1247 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
�� | +3.385 |
apo | +3.177 |
antha | +3.066 |
utenant | +2.901 |
mosqu | +2.894 |
Neg logit contributions | |
ni | -2.234 |
Yang | -2.221 |
NES | -2.092 |
erers | -2.030 |
Pokemon | -2.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ni | +1.086 |
Yang | +1.066 |
NES | +1.002 |
erers | +1.001 |
CG | +0.965 |
Neg logit contributions | |
�� | -1.532 |
apo | -1.421 |
antha | -1.374 |
mosqu | -1.309 |
utenant | -1.296 |
Token | new |
Token ID | 649 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ni | +0.305 |
Yang | +0.299 |
NES | +0.281 |
erers | +0.280 |
Pokemon | +0.271 |
Neg logit contributions | |
�� | -0.399 |
apo | -0.371 |
antha | -0.357 |
mosqu | -0.339 |
aples | -0.336 |
Token | council |
Token ID | 6745 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ni | +0.626 |
Yang | +0.612 |
NES | +0.573 |
erers | +0.565 |
Pokemon | +0.547 |
Neg logit contributions | |
�� | -0.962 |
apo | -0.898 |
antha | -0.868 |
mosqu | -0.829 |
utenant | -0.819 |
Token | featuring |
Token ID | 9593 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ni | +1.234 |
Yang | +1.201 |
NES | +1.119 |
erers | +1.107 |
Pokemon | +1.061 |
Neg logit contributions | |
�� | -2.221 |
apo | -2.065 |
antha | -2.018 |
mosqu | -1.936 |
aples | -1.912 |
Token | a |
Token ID | 257 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ni | +0.483 |
Yang | +0.475 |
erers | +0.447 |
NES | +0.446 |
Li | +0.429 |
Neg logit contributions | |
�� | -0.656 |
apo | -0.610 |
antha | -0.585 |
mosqu | -0.559 |
utenant | -0.552 |
Token | female |
Token ID | 4048 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ni | +0.425 |
Yang | +0.418 |
NES | +0.391 |
erers | +0.389 |
Pokemon | +0.376 |
Neg logit contributions | |
�� | -0.607 |
apo | -0.566 |
antha | -0.543 |
mosqu | -0.519 |
aples | -0.514 |
Token | representative |
Token ID | 8852 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ni | +2.901 |
Yang | +2.787 |
NES | +2.622 |
erers | +2.593 |
CG | +2.585 |
Neg logit contributions | |
�� | -3.844 |
apo | -3.601 |
antha | -3.473 |
mosqu | -3.298 |
aples | -3.289 |
Token | from |
Token ID | 422 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ni | +0.543 |
Yang | +0.533 |
NES | +0.497 |
erers | +0.486 |
Pokemon | +0.470 |
Neg logit contributions | |
�� | -0.974 |
apo | -0.913 |
antha | -0.885 |
mosqu | -0.849 |
aples | -0.838 |
Token | each |
Token ID | 1123 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
�� | +0.425 |
apo | +0.389 |
antha | +0.372 |
mosqu | +0.352 |
utenant | +0.350 |
Neg logit contributions | |
ni | -0.422 |
Yang | -0.417 |
NES | -0.397 |
erers | -0.393 |
Pokemon | -0.382 |
Token | conf |
Token ID | 1013 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
�� | +0.716 |
apo | +0.671 |
antha | +0.646 |
mosqu | +0.616 |
utenant | +0.613 |
Neg logit contributions | |
ni | -0.486 |
Yang | -0.479 |
NES | -0.452 |
erers | -0.444 |
Pokemon | -0.431 |
Token | ederation |
Token ID | 9748 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
�� | +0.047 |
apo | +0.043 |
antha | +0.042 |
mosqu | +0.040 |
utenant | +0.040 |
Neg logit contributions | |
ni | -0.032 |
Yang | -0.031 |
NES | -0.029 |
erers | -0.029 |
Pokemon | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ni | +0.050 |
Yang | +0.049 |
NES | +0.046 |
erers | +0.045 |
Pokemon | +0.044 |
Neg logit contributions | |
�� | -0.085 |
apo | -0.079 |
antha | -0.076 |
mosqu | -0.075 |
utenant | -0.072 |
Token | He |
Token ID | 1544 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
ni | +0.316 |
Yang | +0.315 |
NES | +0.297 |
erers | +0.287 |
Pokemon | +0.282 |
Neg logit contributions | |
�� | -0.498 |
apo | -0.463 |
antha | -0.449 |
mosqu | -0.436 |
utenant | -0.427 |
Token | has |
Token ID | 468 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
ni | +0.007 |
Yang | +0.007 |
NES | +0.006 |
erers | +0.006 |
Pokemon | +0.006 |
Neg logit contributions | |
�� | -0.011 |
apo | -0.010 |
antha | -0.010 |
mosqu | -0.009 |
utenant | -0.009 |
Token | launched |
Token ID | 5611 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ni | +0.140 |
Yang | +0.137 |
NES | +0.130 |
erers | +0.128 |
Pokemon | +0.124 |
Neg logit contributions | |
�� | -0.193 |
apo | -0.181 |
antha | -0.173 |
mosqu | -0.166 |
utenant | -0.164 |
Token | four |
Token ID | 1440 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ni | +0.681 |
Yang | +0.670 |
NES | +0.636 |
erers | +0.628 |
Pokemon | +0.609 |
Neg logit contributions | |
�� | -0.943 |
apo | -0.874 |
antha | -0.845 |
mosqu | -0.800 |
utenant | -0.796 |
Token | unmanned |
Token ID | 35272 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
�� | +0.323 |
apo | +0.302 |
antha | +0.291 |
mosqu | +0.277 |
utenant | +0.276 |
Neg logit contributions | |
ni | -0.222 |
Yang | -0.219 |
NES | -0.207 |
erers | -0.203 |
Pokemon | -0.197 |
Token | Falcon |
Token ID | 17621 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ni | +2.754 |
Yang | +2.671 |
NES | +2.520 |
erers | +2.493 |
Li | +2.431 |
Neg logit contributions | |
�� | -4.469 |
apo | -4.134 |
antha | -4.050 |
utenant | -3.807 |
mosqu | -3.800 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
�� | +0.780 |
apo | +0.737 |
antha | +0.711 |
mosqu | +0.682 |
utenant | +0.678 |
Neg logit contributions | |
ni | -0.417 |
Yang | -0.412 |
NES | -0.385 |
erers | -0.376 |
Pokemon | -0.364 |
Token | rockets |
Token ID | 20293 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
�� | +0.702 |
apo | +0.655 |
antha | +0.629 |
mosqu | +0.599 |
utenant | +0.595 |
Neg logit contributions | |
ni | -0.558 |
Yang | -0.552 |
NES | -0.524 |
erers | -0.515 |
Pokemon | -0.502 |
Token | into |
Token ID | 656 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
ni | +0.294 |
Yang | +0.290 |
NES | +0.273 |
erers | +0.268 |
Pokemon | +0.261 |
Neg logit contributions | |
�� | -0.449 |
apo | -0.420 |
antha | -0.405 |
mosqu | -0.387 |
utenant | -0.385 |
Token | space |
Token ID | 2272 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
ni | +0.881 |
Yang | +0.863 |
NES | +0.817 |
erers | +0.810 |
Pokemon | +0.784 |
Neg logit contributions | |
�� | -1.121 |
apo | -1.036 |
antha | -0.997 |
mosqu | -0.943 |
utenant | -0.933 |
Token | G |
Token ID | 402 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
�� | +0.541 |
apo | +0.503 |
antha | +0.483 |
mosqu | +0.457 |
utenant | +0.455 |
Neg logit contributions | |
ni | -0.465 |
Yang | -0.463 |
NES | -0.440 |
erers | -0.434 |
Pokemon | -0.424 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
�� | +0.774 |
apo | +0.725 |
antha | +0.702 |
mosqu | +0.680 |
utenant | +0.669 |
Neg logit contributions | |
ni | -0.432 |
Yang | -0.422 |
NES | -0.397 |
erers | -0.389 |
Pokemon | -0.373 |
Token | � |
Token ID | 12520 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Yang | +0.107 |
ni | +0.107 |
NES | +0.102 |
erers | +0.101 |
Pokemon | +0.099 |
Neg logit contributions | |
�� | -0.092 |
apo | -0.085 |
antha | -0.080 |
mosqu | -0.076 |
utenant | -0.076 |
Token | � |
Token ID | 229 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
ni | +3.077 |
Yang | +3.001 |
NES | +2.853 |
erers | +2.793 |
Pokemon | +2.780 |
Neg logit contributions | |
�� | -3.973 |
apo | -3.825 |
antha | -3.712 |
utenant | -3.551 |
mosqu | -3.533 |
Token | � |
Token ID | 118 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ni | +1.097 |
Yang | +1.059 |
NES | +1.004 |
erers | +0.988 |
Pokemon | +0.958 |
Neg logit contributions | |
�� | -1.462 |
apo | -1.387 |
antha | -1.353 |
mosqu | -1.328 |
aples | -1.271 |
Token | � |
Token ID | 8582 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ni | +0.127 |
Yang | +0.124 |
NES | +0.115 |
erers | +0.111 |
Pokemon | +0.109 |
Neg logit contributions | |
�� | -0.286 |
apo | -0.269 |
antha | -0.262 |
mosqu | -0.254 |
utenant | -0.251 |
Token | � |
Token ID | 229 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ni | +2.709 |
Yang | +2.678 |
NES | +2.515 |
erers | +2.459 |
Pokemon | +2.420 |
Neg logit contributions | |
�� | -3.846 |
apo | -3.636 |
mosqu | -3.597 |
antha | -3.544 |
utenant | -3.422 |
Token | � |
Token ID | 116 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
ni | +0.781 |
Yang | +0.753 |
NES | +0.700 |
erers | +0.675 |
Pokemon | +0.662 |
Neg logit contributions | |
�� | -1.331 |
apo | -1.248 |
mosqu | -1.225 |
antha | -1.224 |
utenant | -1.162 |
Token | (@ |
Token ID | 4275 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
�� | +0.154 |
apo | +0.143 |
antha | +0.136 |
mosqu | +0.129 |
utenant | +0.128 |
Neg logit contributions | |
ni | -0.144 |
Yang | -0.143 |
NES | -0.136 |
erers | -0.134 |
Pokemon | -0.130 |
Token | m |
Token ID | 76 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ni | +1.049 |
Yang | +1.032 |
NES | +0.982 |
erers | +0.961 |
Pokemon | +0.949 |
Neg logit contributions | |
�� | -1.079 |
apo | -0.984 |
antha | -0.952 |
mosqu | -0.907 |
utenant | -0.894 |
Token | f |
Token ID | 69 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
�� | +0.684 |
apo | +0.618 |
antha | +0.596 |
mosqu | +0.586 |
utenant | +0.561 |
Neg logit contributions | |
ni | -0.595 |
Yang | -0.576 |
NES | -0.546 |
erers | -0.544 |
Pokemon | -0.527 |
Token | om |
Token ID | 296 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +2.851 |
apo | +2.701 |
antha | +2.597 |
mosqu | +2.469 |
utenant | +2.460 |
Neg logit contributions | |
ni | -1.937 |
Yang | -1.930 |
NES | -1.817 |
erers | -1.784 |
Pokemon | -1.739 |
Token | Hart |
Token ID | 11345 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ni | +0.199 |
Yang | +0.194 |
NES | +0.183 |
erers | +0.180 |
Pokemon | +0.174 |
Neg logit contributions | |
�� | -0.271 |
apo | -0.250 |
antha | -0.244 |
utenant | -0.232 |
mosqu | -0.232 |
Token | man |
Token ID | 805 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
�� | +1.295 |
apo | +1.213 |
antha | +1.159 |
mosqu | +1.104 |
utenant | +1.098 |
Neg logit contributions | |
ni | -1.036 |
Yang | -1.030 |
NES | -0.977 |
erers | -0.960 |
Pokemon | -0.940 |
Token | Institute |
Token ID | 5136 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
�� | +0.989 |
apo | +0.926 |
antha | +0.894 |
mosqu | +0.855 |
utenant | +0.851 |
Neg logit contributions | |
ni | -0.640 |
Yang | -0.631 |
NES | -0.593 |
erers | -0.583 |
Pokemon | -0.565 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
�� | +0.786 |
apo | +0.739 |
antha | +0.710 |
mosqu | +0.683 |
utenant | +0.679 |
Neg logit contributions | |
ni | -0.482 |
Yang | -0.479 |
NES | -0.451 |
erers | -0.443 |
Pokemon | -0.430 |
Token | Amid |
Token ID | 43541 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
�� | +0.724 |
apo | +0.680 |
antha | +0.654 |
mosqu | +0.624 |
utenant | +0.622 |
Neg logit contributions | |
ni | -0.492 |
Yang | -0.486 |
NES | -0.459 |
erers | -0.452 |
Pokemon | -0.438 |
Token | plac |
Token ID | 21957 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
ni | +2.812 |
Yang | +2.686 |
NES | +2.508 |
erers | +2.482 |
Pokemon | +2.429 |
Neg logit contributions | |
�� | -3.979 |
apo | -3.705 |
antha | -3.551 |
mosqu | -3.450 |
utenant | -3.390 |
Token | ards |
Token ID | 1371 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
�� | +1.444 |
apo | +1.320 |
antha | +1.242 |
utenant | +1.136 |
mosqu | +1.122 |
Neg logit contributions | |
ni | -2.352 |
Yang | -2.346 |
NES | -2.262 |
erers | -2.217 |
Pokemon | -2.195 |
Token | including |
Token ID | 1390 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
�� | +0.640 |
apo | +0.603 |
antha | +0.580 |
mosqu | +0.551 |
utenant | +0.550 |
Neg logit contributions | |
ni | -0.422 |
Yang | -0.419 |
NES | -0.397 |
erers | -0.388 |
Pokemon | -0.376 |
Token | � |
Token ID | 564 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ni | +0.451 |
Yang | +0.446 |
NES | +0.419 |
erers | +0.410 |
Pokemon | +0.398 |
Neg logit contributions | |
�� | -0.749 |
apo | -0.703 |
antha | -0.678 |
mosqu | -0.650 |
utenant | -0.646 |
Token | � |
Token ID | 250 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ni | +0.435 |
Yang | +0.431 |
NES | +0.412 |
erers | +0.406 |
Pokemon | +0.398 |
Neg logit contributions | |
�� | -0.409 |
apo | -0.379 |
antha | -0.361 |
mosqu | -0.341 |
utenant | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +0.661 |
apo | +0.619 |
antha | +0.596 |
mosqu | +0.567 |
utenant | +0.565 |
Neg logit contributions | |
ni | -0.484 |
Yang | -0.481 |
NES | -0.455 |
erers | -0.445 |
Pokemon | -0.435 |
Token | death |
Token ID | 1918 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ni | +0.202 |
Yang | +0.199 |
NES | +0.189 |
erers | +0.185 |
Pokemon | +0.181 |
Neg logit contributions | |
�� | -0.276 |
apo | -0.257 |
antha | -0.247 |
mosqu | -0.235 |
utenant | -0.235 |
Token | of |
Token ID | 286 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
�� | +0.631 |
apo | +0.591 |
antha | +0.571 |
mosqu | +0.546 |
utenant | +0.543 |
Neg logit contributions | |
ni | -0.396 |
Yang | -0.390 |
NES | -0.367 |
erers | -0.360 |
Pokemon | -0.350 |
Token | CEO |
Token ID | 6123 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ni | +0.633 |
Yang | +0.626 |
NES | +0.589 |
erers | +0.581 |
Pokemon | +0.568 |
Neg logit contributions | |
�� | -0.804 |
apo | -0.743 |
antha | -0.713 |
mosqu | -0.680 |
utenant | -0.673 |
Token | Karen |
Token ID | 18678 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
�� | +0.077 |
apo | +0.072 |
antha | +0.069 |
mosqu | +0.066 |
utenant | +0.065 |
Neg logit contributions | |
ni | -0.060 |
Yang | -0.059 |
NES | -0.056 |
erers | -0.055 |
Pokemon | -0.054 |
Token | Brick |
Token ID | 28347 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ni | +1.822 |
Yang | +1.792 |
NES | +1.660 |
erers | +1.646 |
Li | +1.611 |
Neg logit contributions | |
�� | -2.581 |
apo | -2.394 |
antha | -2.287 |
mosqu | -2.233 |
utenant | -2.177 |
Token | le |
Token ID | 293 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ni | +4.112 |
Yang | +4.042 |
NES | +3.878 |
erers | +3.846 |
NW | +3.725 |
Neg logit contributions | |
�� | -2.810 |
apo | -2.503 |
antha | -2.389 |
mosqu | -2.299 |
utenant | -2.222 |
Token | my |
Token ID | 1820 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
�� | +0.324 |
apo | +0.304 |
antha | +0.293 |
mosqu | +0.281 |
utenant | +0.279 |
Neg logit contributions | |
ni | -0.211 |
Yang | -0.209 |
NES | -0.196 |
erers | -0.193 |
Pokemon | -0.187 |
Token | er |
Token ID | 263 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ni | +0.478 |
Yang | +0.463 |
NES | +0.435 |
erers | +0.428 |
Pokemon | +0.410 |
Neg logit contributions | |
�� | -0.833 |
apo | -0.780 |
antha | -0.756 |
mosqu | -0.727 |
utenant | -0.718 |
Token | , |
Token ID | 11 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ni | +0.200 |
Yang | +0.197 |
NES | +0.185 |
erers | +0.181 |
Pokemon | +0.176 |
Neg logit contributions | |
�� | -0.309 |
apo | -0.290 |
antha | -0.280 |
mosqu | -0.268 |
utenant | -0.265 |
Token | so |
Token ID | 523 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ni | +0.365 |
Yang | +0.361 |
NES | +0.339 |
erers | +0.334 |
Pokemon | +0.324 |
Neg logit contributions | |
�� | -0.533 |
apo | -0.498 |
antha | -0.479 |
mosqu | -0.458 |
utenant | -0.455 |