Token | ich |
Token ID | 488 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Reviewed | +1.096 |
itaire | +0.891 |
ippery | +0.788 |
Discuss | +0.773 |
Split | +0.761 |
Neg logit contributions | |
expectations | -1.140 |
Wonderland | -1.099 |
Pepe | -1.081 |
UTERS | -1.059 |
gest | -1.033 |
Token | gets |
Token ID | 3011 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
expectations | +0.684 |
Wonderland | +0.645 |
Pepe | +0.637 |
gest | +0.612 |
UTERS | +0.608 |
Neg logit contributions | |
Reviewed | -0.895 |
itaire | -0.747 |
ippery | -0.665 |
Split | -0.652 |
Discuss | -0.647 |
Token | down |
Token ID | 866 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Reviewed | +3.733 |
itaire | +3.066 |
ippery | +2.730 |
Discuss | +2.679 |
Split | +2.667 |
Neg logit contributions | |
expectations | -3.259 |
Wonderland | -3.128 |
Pepe | -3.066 |
UTERS | -3.017 |
gest | -2.964 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
expectations | +0.174 |
Wonderland | +0.166 |
Pepe | +0.164 |
gest | +0.162 |
UTERS | +0.160 |
Neg logit contributions | |
Reviewed | -0.160 |
itaire | -0.126 |
ippery | -0.109 |
Discuss | -0.107 |
Split | -0.107 |
Token | the |
Token ID | 262 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
Reviewed | +1.593 |
itaire | +1.333 |
ippery | +1.216 |
Split | +1.191 |
Discuss | +1.190 |
Neg logit contributions | |
expectations | -1.039 |
Wonderland | -0.986 |
Pepe | -0.966 |
gest | -0.926 |
UTERS | -0.923 |
Token | n |
Token ID | 299 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Reviewed | +5.771 |
itaire | +4.838 |
ippery | +4.379 |
Discuss | +4.295 |
Gray | +4.280 |
Neg logit contributions | |
expectations | -4.306 |
Wonderland | -4.119 |
UTERS | -4.067 |
Pepe | -4.038 |
gest | -3.874 |
Token | itty |
Token ID | 9760 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Reviewed | +6.617 |
itaire | +4.919 |
ippery | +4.583 |
ancy | +4.154 |
ippy | +3.967 |
Neg logit contributions | |
expectations | -13.564 |
Wonderland | -13.251 |
UTERS | -13.147 |
Pepe | -12.985 |
Carbuncle | -12.813 |
Token | - |
Token ID | 12 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
expectations | +2.224 |
Wonderland | +2.066 |
Pepe | +2.028 |
gest | +1.995 |
UTERS | +1.966 |
Neg logit contributions | |
Reviewed | -2.982 |
itaire | -2.428 |
ippery | -2.221 |
Discuss | -2.143 |
Split | -2.134 |
Token | gr |
Token ID | 2164 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Reviewed | +1.944 |
itaire | +1.661 |
ippery | +1.522 |
Split | +1.485 |
Discuss | +1.481 |
Neg logit contributions | |
expectations | -1.182 |
Wonderland | -1.142 |
Pepe | -1.100 |
UTERS | -1.066 |
gest | -1.014 |
Token | itty |
Token ID | 9760 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Reviewed | +2.616 |
itaire | +2.068 |
ippery | +1.771 |
Split | +1.670 |
Gray | +1.633 |
Neg logit contributions | |
expectations | -4.415 |
Wonderland | -4.334 |
Pepe | -4.232 |
UTERS | -4.152 |
Carbuncle | -4.033 |
Token | of |
Token ID | 286 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Reviewed | +5.264 |
itaire | +4.420 |
ippery | +3.977 |
Discuss | +3.974 |
Split | +3.906 |
Neg logit contributions | |
expectations | -3.649 |
Wonderland | -3.516 |
Pepe | -3.419 |
UTERS | -3.402 |
gest | -3.309 |
Token | 3 |
Token ID | 18 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Reviewed | +3.061 |
itaire | +2.283 |
Split | +2.174 |
Gray | +2.161 |
Discuss | +2.158 |
Neg logit contributions | |
expectations | -3.773 |
Wonderland | -3.670 |
UTERS | -3.561 |
Pepe | -3.511 |
Carbuncle | -3.447 |
Token | Ga |
Token ID | 12822 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
Reviewed | +4.029 |
itaire | +3.075 |
Gray | +2.921 |
Split | +2.790 |
ippery | +2.736 |
Neg logit contributions | |
expectations | -5.172 |
UTERS | -4.920 |
Wonderland | -4.861 |
Pepe | -4.801 |
QUEST | -4.742 |
Token | ussian |
Token ID | 31562 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Reviewed | +4.454 |
itaire | +3.512 |
Discuss | +3.119 |
ippery | +3.094 |
Gray | +3.057 |
Neg logit contributions | |
expectations | -6.745 |
Wonderland | -6.484 |
Pepe | -6.452 |
Carbuncle | -6.432 |
Kardashian | -6.199 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Reviewed | +3.463 |
itaire | +2.866 |
Gray | +2.692 |
Split | +2.623 |
Discuss | +2.613 |
Neg logit contributions | |
expectations | -2.533 |
UTERS | -2.446 |
Wonderland | -2.407 |
Pepe | -2.323 |
gest | -2.314 |
Token | then |
Token ID | 788 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Reviewed | +2.387 |
itaire | +1.557 |
Gray | +1.216 |
ippery | +1.160 |
Split | +1.135 |
Neg logit contributions | |
expectations | -6.612 |
Wonderland | -6.566 |
Pepe | -6.482 |
UTERS | -6.481 |
aspberry | -6.316 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Reviewed | +2.802 |
itaire | +2.108 |
Gray | +1.923 |
ippery | +1.890 |
Discuss | +1.876 |
Neg logit contributions | |
expectations | -3.928 |
Wonderland | -3.908 |
UTERS | -3.805 |
Pepe | -3.740 |
aspberry | -3.688 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Reviewed | +6.631 |
itaire | +4.949 |
Gray | +4.938 |
Split | +4.617 |
Discuss | +4.457 |
Neg logit contributions | |
eleph | -11.674 |
pione | -11.627 |
UTERS | -11.306 |
aspberry | -11.281 |
Carbuncle | -11.281 |
Token | black |
Token ID | 2042 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
Reviewed | +3.180 |
itaire | +2.623 |
Gray | +2.363 |
ippery | +2.332 |
Discuss | +2.269 |
Neg logit contributions | |
expectations | -3.072 |
Wonderland | -3.003 |
UTERS | -2.977 |
Pepe | -2.928 |
gest | -2.842 |
Token | hat |
Token ID | 5183 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
expectations | +0.165 |
Wonderland | +0.148 |
Pepe | +0.140 |
UTERS | +0.135 |
gest | +0.126 |
Neg logit contributions | |
Reviewed | -0.707 |
itaire | -0.625 |
ippery | -0.583 |
Discuss | -0.577 |
Split | -0.575 |
Token | # |
Token ID | 1303 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Reviewed | +3.455 |
itaire | +2.940 |
ippery | +2.684 |
Discuss | +2.649 |
Split | +2.630 |
Neg logit contributions | |
expectations | -1.885 |
Wonderland | -1.775 |
Pepe | -1.734 |
UTERS | -1.686 |
gest | -1.655 |
Token | morph |
Token ID | 17488 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
Reviewed | +3.475 |
itaire | +3.002 |
ippery | +2.801 |
Split | +2.768 |
Discuss | +2.751 |
Neg logit contributions | |
expectations | -1.448 |
Wonderland | -1.369 |
UTERS | -1.332 |
Pepe | -1.322 |
gest | -1.253 |
Token | Dirk |
Token ID | 42761 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Reviewed | +3.098 |
itaire | +2.559 |
ippery | +2.297 |
Discuss | +2.256 |
Split | +2.247 |
Neg logit contributions | |
expectations | -2.434 |
Wonderland | -2.339 |
Pepe | -2.267 |
UTERS | -2.257 |
gest | -2.214 |
Token | K |
Token ID | 509 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
Reviewed | +1.911 |
itaire | +1.597 |
ippery | +1.440 |
Discuss | +1.420 |
Split | +1.408 |
Neg logit contributions | |
expectations | -1.374 |
Wonderland | -1.307 |
Pepe | -1.277 |
UTERS | -1.259 |
gest | -1.234 |
Token | uy |
Token ID | 4669 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
expectations | +0.461 |
Wonderland | +0.433 |
Pepe | +0.431 |
UTERS | +0.420 |
gest | +0.417 |
Neg logit contributions | |
Reviewed | -0.741 |
itaire | -0.617 |
ippery | -0.562 |
Split | -0.552 |
Discuss | -0.552 |
Token | t |
Token ID | 83 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
expectations | +1.398 |
Wonderland | +1.297 |
Pepe | +1.288 |
gest | +1.241 |
UTERS | +1.233 |
Neg logit contributions | |
Reviewed | -2.215 |
itaire | -1.870 |
ippery | -1.682 |
Gray | -1.654 |
Discuss | -1.653 |
Token | switching |
Token ID | 15430 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Reviewed | +3.102 |
itaire | +2.572 |
ippery | +2.305 |
Discuss | +2.262 |
Split | +2.259 |
Neg logit contributions | |
expectations | -2.470 |
Wonderland | -2.368 |
Pepe | -2.305 |
UTERS | -2.285 |
gest | -2.232 |
Token | fl |
Token ID | 781 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Reviewed | +4.977 |
itaire | +4.101 |
ippery | +3.649 |
Split | +3.649 |
Discuss | +3.588 |
Neg logit contributions | |
expectations | -4.264 |
Wonderland | -4.161 |
UTERS | -4.086 |
Pepe | -4.000 |
gest | -3.980 |
Token | anks |
Token ID | 2283 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Reviewed | +7.204 |
itaire | +6.110 |
ippery | +5.421 |
agy | +4.833 |
ippy | +4.769 |
Neg logit contributions | |
expectations | -11.879 |
Wonderland | -11.745 |
Pepe | -11.242 |
UTERS | -11.047 |
complicity | -11.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Reviewed | +2.898 |
itaire | +2.399 |
ippery | +2.149 |
Discuss | +2.113 |
Split | +2.103 |
Neg logit contributions | |
expectations | -2.343 |
Wonderland | -2.242 |
Pepe | -2.196 |
UTERS | -2.160 |
gest | -2.118 |
Token | Holland |
Token ID | 16070 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Reviewed | +2.566 |
itaire | +2.103 |
ippery | +1.870 |
Discuss | +1.848 |
Split | +1.836 |
Neg logit contributions | |
expectations | -2.211 |
Wonderland | -2.113 |
Pepe | -2.062 |
UTERS | -2.042 |
gest | -2.003 |
Token | were |
Token ID | 547 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Reviewed | +2.974 |
itaire | +2.430 |
ippery | +2.164 |
Discuss | +2.125 |
Split | +2.122 |
Neg logit contributions | |
expectations | -2.637 |
Wonderland | -2.532 |
Pepe | -2.476 |
UTERS | -2.457 |
gest | -2.406 |
Token | now |
Token ID | 783 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Reviewed | +4.924 |
itaire | +4.030 |
ippery | +3.675 |
Split | +3.579 |
Discuss | +3.561 |
Neg logit contributions | |
expectations | -3.850 |
Wonderland | -3.707 |
UTERS | -3.647 |
Pepe | -3.581 |
gest | -3.507 |
Token | IN |
Token ID | 1268 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
expectations | +1.745 |
UTERS | +1.724 |
Wonderland | +1.688 |
Pepe | +1.669 |
QUEST | +1.634 |
Neg logit contributions | |
Reviewed | -2.264 |
itaire | -1.943 |
ippery | -1.767 |
Discuss | -1.650 |
Split | -1.641 |
Token | IK |
Token ID | 18694 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
Reviewed | +2.372 |
itaire | +1.971 |
ippery | +1.767 |
Discuss | +1.730 |
Split | +1.721 |
Neg logit contributions | |
expectations | -1.887 |
Wonderland | -1.804 |
Pepe | -1.769 |
UTERS | -1.740 |
gest | -1.707 |
Token | AIN |
Token ID | 29833 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Reviewed | +0.533 |
itaire | +0.438 |
ippery | +0.386 |
Discuss | +0.373 |
Split | +0.372 |
Neg logit contributions | |
expectations | -0.518 |
Wonderland | -0.494 |
Pepe | -0.488 |
UTERS | -0.482 |
gest | -0.469 |
Token | EN |
Token ID | 1677 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
expectations | +1.265 |
Wonderland | +1.193 |
Pepe | +1.185 |
UTERS | +1.175 |
gest | +1.132 |
Neg logit contributions | |
Reviewed | -1.492 |
itaire | -1.255 |
ippery | -1.111 |
Split | -1.064 |
Discuss | -1.056 |
Token | p |
Token ID | 79 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
Reviewed | +0.999 |
itaire | +0.833 |
ippery | +0.745 |
Discuss | +0.725 |
Split | +0.724 |
Neg logit contributions | |
expectations | -0.807 |
Wonderland | -0.770 |
Pepe | -0.757 |
UTERS | -0.744 |
gest | -0.729 |
Token | aul |
Token ID | 2518 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
expectations | +0.105 |
Wonderland | +0.100 |
Pepe | +0.098 |
UTERS | +0.097 |
gest | +0.094 |
Neg logit contributions | |
Reviewed | -0.139 |
itaire | -0.116 |
ippery | -0.104 |
Split | -0.102 |
Discuss | -0.102 |
Token | i |
Token ID | 72 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Reviewed | +9.879 |
itaire | +8.499 |
ippery | +7.508 |
Gray | +7.167 |
orum | +7.039 |
Neg logit contributions | |
expectations | -9.109 |
Wonderland | -9.075 |
Pepe | -8.738 |
UTERS | -8.542 |
gest | -8.344 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Reviewed | +3.419 |
itaire | +2.816 |
ippery | +2.518 |
Discuss | +2.474 |
Split | +2.460 |
Neg logit contributions | |
expectations | -2.804 |
Wonderland | -2.692 |
Pepe | -2.640 |
UTERS | -2.591 |
gest | -2.552 |
Token | re |
Token ID | 260 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Reviewed | +2.311 |
itaire | +1.909 |
ippery | +1.706 |
Discuss | +1.677 |
Split | +1.667 |
Neg logit contributions | |
expectations | -1.911 |
Wonderland | -1.824 |
Pepe | -1.791 |
UTERS | -1.758 |
gest | -1.729 |
Token | in |
Token ID | 259 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Reviewed | +2.108 |
itaire | +1.686 |
ippery | +1.474 |
Discuss | +1.449 |
Split | +1.437 |
Neg logit contributions | |
expectations | -2.290 |
Wonderland | -2.199 |
Pepe | -2.166 |
UTERS | -2.136 |
gest | -2.104 |
Token | ik |
Token ID | 1134 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Reviewed | +5.148 |
itaire | +4.308 |
ippery | +3.814 |
Discuss | +3.696 |
Gray | +3.637 |
Neg logit contributions | |
expectations | -4.611 |
Wonderland | -4.438 |
Pepe | -4.392 |
UTERS | -4.231 |
gest | -4.150 |
Token | , |
Token ID | 11 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
Reviewed | +1.498 |
itaire | +1.251 |
ippery | +1.128 |
Discuss | +1.112 |
Split | +1.105 |
Neg logit contributions | |
expectations | -1.063 |
Wonderland | -1.010 |
Pepe | -0.989 |
UTERS | -0.965 |
gest | -0.950 |
Token | who |
Token ID | 508 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
expectations | +0.371 |
Wonderland | +0.351 |
Pepe | +0.343 |
UTERS | +0.332 |
gest | +0.328 |
Neg logit contributions | |
Reviewed | -0.523 |
itaire | -0.440 |
ippery | -0.393 |
Discuss | -0.388 |
Split | -0.386 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
expectations | +0.167 |
Wonderland | +0.158 |
Pepe | +0.155 |
UTERS | +0.151 |
gest | +0.149 |
Neg logit contributions | |
Reviewed | -0.205 |
itaire | -0.169 |
ippery | -0.151 |
Discuss | -0.149 |
Split | -0.148 |
Token | almost |
Token ID | 2048 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Reviewed | +0.149 |
itaire | +0.125 |
ippery | +0.112 |
Discuss | +0.111 |
Gray | +0.110 |
Neg logit contributions | |
expectations | -0.108 |
Wonderland | -0.102 |
Pepe | -0.100 |
UTERS | -0.097 |
gest | -0.096 |
Token | all |
Token ID | 477 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Reviewed | +1.628 |
itaire | +1.356 |
ippery | +1.224 |
Discuss | +1.201 |
Split | +1.197 |
Neg logit contributions | |
expectations | -1.205 |
Wonderland | -1.151 |
Pepe | -1.130 |
UTERS | -1.111 |
gest | -1.089 |
Token | their |
Token ID | 511 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Reviewed | +3.521 |
itaire | +2.954 |
ippery | +2.668 |
Split | +2.624 |
Discuss | +2.622 |
Neg logit contributions | |
expectations | -2.386 |
Wonderland | -2.300 |
Pepe | -2.261 |
UTERS | -2.216 |
gest | -2.169 |
Token | put |
Token ID | 1234 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
Reviewed | +11.101 |
itaire | +9.133 |
Split | +8.415 |
ippery | +8.388 |
Discuss | +8.211 |
Neg logit contributions | |
aspberry | -6.915 |
UTERS | -6.709 |
Pepe | -6.669 |
expectations | -6.662 |
Wonderland | -6.658 |
Token | ts |
Token ID | 912 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Reviewed | +3.227 |
itaire | +2.633 |
ippery | +2.327 |
Split | +2.285 |
Discuss | +2.278 |
Neg logit contributions | |
expectations | -3.073 |
Wonderland | -2.973 |
Pepe | -2.926 |
UTERS | -2.853 |
gest | -2.811 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Reviewed | +4.968 |
itaire | +4.125 |
ippery | +3.718 |
Split | +3.658 |
Discuss | +3.651 |
Neg logit contributions | |
expectations | -3.918 |
Wonderland | -3.813 |
Pepe | -3.737 |
UTERS | -3.708 |
gest | -3.629 |
Token | The |
Token ID | 383 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
Reviewed | +0.878 |
itaire | +0.717 |
ippery | +0.636 |
Discuss | +0.621 |
Split | +0.617 |
Neg logit contributions | |
expectations | -0.824 |
Wonderland | -0.791 |
Pepe | -0.777 |
UTERS | -0.761 |
gest | -0.751 |
Token | increase |
Token ID | 2620 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
expectations | +0.127 |
Wonderland | +0.121 |
Pepe | +0.118 |
UTERS | +0.115 |
gest | +0.113 |
Neg logit contributions | |
Reviewed | -0.185 |
itaire | -0.155 |
ippery | -0.140 |
Discuss | -0.138 |
Split | -0.137 |
Token | would |
Token ID | 561 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Reviewed | +2.419 |
itaire | +1.997 |
ippery | +1.794 |
Discuss | +1.767 |
Split | +1.761 |
Neg logit contributions | |
expectations | -1.925 |
Wonderland | -1.853 |
Pepe | -1.814 |
UTERS | -1.797 |
gest | -1.756 |
Token | prefer |
Token ID | 4702 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
expectations | +0.726 |
Wonderland | +0.683 |
Pepe | +0.674 |
UTERS | +0.652 |
gest | +0.651 |
Neg logit contributions | |
Reviewed | -0.938 |
itaire | -0.778 |
ippery | -0.701 |
Discuss | -0.683 |
Split | -0.682 |
Token | to |
Token ID | 284 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Reviewed | +4.961 |
itaire | +4.046 |
ippery | +3.617 |
Split | +3.549 |
Discuss | +3.529 |
Neg logit contributions | |
expectations | -4.581 |
Wonderland | -4.408 |
Pepe | -4.339 |
UTERS | -4.286 |
gest | -4.190 |
Token | follow |
Token ID | 1061 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Reviewed | +4.443 |
itaire | +3.686 |
ippery | +3.273 |
Split | +3.223 |
Discuss | +3.213 |
Neg logit contributions | |
expectations | -4.055 |
Wonderland | -3.917 |
Pepe | -3.842 |
UTERS | -3.824 |
gest | -3.686 |
Token | a |
Token ID | 257 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Reviewed | +1.869 |
itaire | +1.558 |
ippery | +1.400 |
Discuss | +1.378 |
Split | +1.369 |
Neg logit contributions | |
expectations | -1.400 |
Wonderland | -1.334 |
Pepe | -1.307 |
UTERS | -1.279 |
gest | -1.257 |
Token | fl |
Token ID | 781 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
expectations | +1.036 |
Wonderland | +0.998 |
Pepe | +0.967 |
gest | +0.934 |
UTERS | +0.931 |
Neg logit contributions | |
Reviewed | -1.289 |
itaire | -1.064 |
ippery | -0.944 |
Discuss | -0.937 |
Gray | -0.917 |
Token | atter |
Token ID | 1436 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Reviewed | +5.972 |
itaire | +4.598 |
ippery | +4.088 |
adier | +3.610 |
Gray | +3.557 |
Neg logit contributions | |
expectations | -12.692 |
Wonderland | -12.489 |
Pepe | -12.427 |
UTERS | -11.987 |
complicity | -11.883 |
Token | route |
Token ID | 6339 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
expectations | +0.648 |
Wonderland | +0.616 |
Pepe | +0.599 |
gest | +0.576 |
UTERS | +0.575 |
Neg logit contributions | |
Reviewed | -0.995 |
itaire | -0.838 |
ippery | -0.754 |
Discuss | -0.744 |
Split | -0.737 |
Token | under |
Token ID | 739 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
Reviewed | +0.912 |
itaire | +0.755 |
ippery | +0.674 |
Discuss | +0.662 |
Split | +0.656 |
Neg logit contributions | |
expectations | -0.751 |
Wonderland | -0.715 |
Pepe | -0.701 |
UTERS | -0.684 |
gest | -0.675 |
Token | the |
Token ID | 262 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
expectations | +0.336 |
Wonderland | +0.319 |
Pepe | +0.309 |
UTERS | +0.299 |
gest | +0.297 |
Neg logit contributions | |
Reviewed | -0.462 |
itaire | -0.387 |
ippery | -0.346 |
Discuss | -0.342 |
Gray | -0.337 |
Token | bridge |
Token ID | 7696 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
expectations | +0.272 |
Wonderland | +0.258 |
Pepe | +0.251 |
gest | +0.239 |
UTERS | +0.238 |
Neg logit contributions | |
Reviewed | -0.418 |
itaire | -0.356 |
ippery | -0.317 |
Discuss | -0.314 |
Split | -0.310 |
Token | las |
Token ID | 21921 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Reviewed | +2.336 |
itaire | +1.941 |
ippery | +1.744 |
Discuss | +1.720 |
Split | +1.704 |
Neg logit contributions | |
expectations | -1.706 |
Wonderland | -1.622 |
Pepe | -1.594 |
UTERS | -1.553 |
gest | -1.531 |
Token | Back |
Token ID | 5157 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Reviewed | +0.189 |
itaire | +0.153 |
ippery | +0.134 |
Discuss | +0.132 |
Split | +0.131 |
Neg logit contributions | |
expectations | -0.171 |
Wonderland | -0.163 |
Pepe | -0.161 |
UTERS | -0.156 |
gest | -0.156 |
Token | strom |
Token ID | 20282 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
Reviewed | +3.667 |
itaire | +2.953 |
ippery | +2.545 |
Discuss | +2.544 |
Split | +2.535 |
Neg logit contributions | |
expectations | -4.278 |
Wonderland | -4.161 |
Pepe | -4.083 |
UTERS | -4.033 |
Carbuncle | -3.901 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Reviewed | +0.502 |
itaire | +0.410 |
ippery | +0.365 |
Discuss | +0.354 |
Gray | +0.352 |
Neg logit contributions | |
expectations | -0.444 |
Wonderland | -0.423 |
Pepe | -0.416 |
UTERS | -0.407 |
gest | -0.402 |
Token |
|
Token ID | 198 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Reviewed | +1.227 |
itaire | +0.920 |
Discuss | +0.828 |
Split | +0.811 |
Gray | +0.799 |
Neg logit contributions | |
expectations | -1.605 |
Wonderland | -1.555 |
Pepe | -1.518 |
UTERS | -1.506 |
Carbuncle | -1.466 |
Token | Jason |
Token ID | 26497 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
expectations | +0.279 |
Wonderland | +0.266 |
Pepe | +0.263 |
UTERS | +0.262 |
gest | +0.258 |
Neg logit contributions | |
Reviewed | -0.276 |
itaire | -0.225 |
ippery | -0.200 |
Discuss | -0.189 |
Split | -0.186 |
Token | Chimera |
Token ID | 38399 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Reviewed | +8.545 |
itaire | +6.455 |
Gray | +6.365 |
orum | +6.312 |
ippery | +6.279 |
Neg logit contributions | |
sbm | -9.356 |
UTERS | -9.295 |
expectations | -9.052 |
aspberry | -8.935 |
minist | -8.766 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Reviewed | +4.441 |
itaire | +3.627 |
ippery | +3.220 |
Discuss | +3.164 |
Split | +3.145 |
Neg logit contributions | |
expectations | -4.070 |
Wonderland | -3.903 |
Pepe | -3.832 |
UTERS | -3.765 |
gest | -3.704 |
Token |
|
Token ID | 198 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
Reviewed | +2.048 |
itaire | +1.494 |
Discuss | +1.370 |
Split | +1.330 |
Gray | +1.312 |
Neg logit contributions | |
expectations | -2.863 |
Wonderland | -2.784 |
Pepe | -2.708 |
UTERS | -2.697 |
Carbuncle | -2.643 |
Token | Present |
Token ID | 34695 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Reviewed | +0.494 |
itaire | +0.402 |
ippery | +0.356 |
Discuss | +0.339 |
Split | +0.336 |
Neg logit contributions | |
expectations | -0.509 |
Wonderland | -0.487 |
Pepe | -0.480 |
UTERS | -0.476 |
gest | -0.470 |
Token | ed |
Token ID | 276 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Reviewed | +4.157 |
itaire | +3.418 |
ippery | +3.033 |
Discuss | +2.995 |
Split | +2.980 |
Neg logit contributions | |
expectations | -3.653 |
Wonderland | -3.528 |
Pepe | -3.471 |
UTERS | -3.416 |
gest | -3.346 |
Token | blockbuster |
Token ID | 32034 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
expectations | +2.989 |
Wonderland | +2.850 |
Pepe | +2.785 |
gest | +2.720 |
UTERS | +2.700 |
Neg logit contributions | |
Reviewed | -2.984 |
itaire | -2.394 |
ippery | -2.137 |
Discuss | -2.118 |
Gray | -2.036 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
expectations | +0.488 |
Wonderland | +0.461 |
Pepe | +0.455 |
UTERS | +0.446 |
gest | +0.444 |
Neg logit contributions | |
Reviewed | -0.491 |
itaire | -0.395 |
ippery | -0.352 |
Discuss | -0.345 |
Gray | -0.338 |
Token | also |
Token ID | 635 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
expectations | +0.671 |
Wonderland | +0.634 |
Pepe | +0.626 |
UTERS | +0.598 |
gest | +0.597 |
Neg logit contributions | |
Reviewed | -0.793 |
itaire | -0.660 |
ippery | -0.589 |
Discuss | -0.577 |
Gray | -0.563 |
Token | brought |
Token ID | 3181 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
expectations | +1.710 |
Wonderland | +1.577 |
Pepe | +1.553 |
gest | +1.477 |
Kardashian | +1.475 |
Neg logit contributions | |
Reviewed | -2.751 |
itaire | -2.335 |
ippery | -2.123 |
Discuss | -2.093 |
Split | -2.044 |
Token | Joe |
Token ID | 5689 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Reviewed | +0.727 |
itaire | +0.606 |
ippery | +0.543 |
Discuss | +0.535 |
Split | +0.530 |
Neg logit contributions | |
expectations | -0.568 |
Wonderland | -0.538 |
Pepe | -0.529 |
UTERS | -0.515 |
gest | -0.507 |
Token | N |
Token ID | 399 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
expectations | +1.679 |
Wonderland | +1.615 |
Pepe | +1.613 |
UTERS | +1.551 |
gest | +1.540 |
Neg logit contributions | |
Reviewed | -1.533 |
itaire | -1.192 |
ippery | -1.028 |
Discuss | -1.022 |
Split | -1.013 |
Token | ieu |
Token ID | 22304 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Reviewed | +6.406 |
itaire | +5.510 |
ippery | +4.527 |
Gray | +4.360 |
orum | +4.349 |
Neg logit contributions | |
Wonderland | -11.779 |
expectations | -11.684 |
Pepe | -11.624 |
Carbuncle | -11.092 |
complicity | -11.004 |
Token | w |
Token ID | 86 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
expectations | +1.809 |
Pepe | +1.651 |
Wonderland | +1.641 |
gest | +1.574 |
Kardashian | +1.536 |
Neg logit contributions | |
Reviewed | -4.528 |
itaire | -3.832 |
ippery | -3.516 |
Split | -3.507 |
Discuss | -3.502 |
Token | end |
Token ID | 437 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Reviewed | +0.317 |
itaire | +0.265 |
ippery | +0.238 |
Split | +0.233 |
Discuss | +0.233 |
Neg logit contributions | |
expectations | -0.232 |
Wonderland | -0.220 |
Pepe | -0.217 |
UTERS | -0.212 |
gest | -0.210 |
Token | yk |
Token ID | 48361 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
expectations | +1.836 |
Pepe | +1.705 |
Wonderland | +1.700 |
gest | +1.661 |
Kardashian | +1.631 |
Neg logit contributions | |
Reviewed | -2.118 |
itaire | -1.691 |
ippery | -1.507 |
Discuss | -1.487 |
Split | -1.467 |
Token | to |
Token ID | 284 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
expectations | +2.791 |
Wonderland | +2.551 |
Pepe | +2.531 |
UTERS | +2.474 |
gest | +2.456 |
Neg logit contributions | |
Reviewed | -3.439 |
itaire | -2.807 |
ippery | -2.551 |
Discuss | -2.542 |
Gray | -2.494 |
Token | Allow |
Token ID | 35265 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
expectations | +1.717 |
Wonderland | +1.628 |
UTERS | +1.622 |
Pepe | +1.620 |
gest | +1.600 |
Neg logit contributions | |
Reviewed | -1.685 |
itaire | -1.408 |
ippery | -1.239 |
Split | -1.159 |
Discuss | -1.155 |
Token | ay |
Token ID | 323 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Reviewed | +1.417 |
itaire | +1.141 |
ippery | +1.005 |
Discuss | +0.998 |
Split | +0.980 |
Neg logit contributions | |
expectations | -1.532 |
Wonderland | -1.490 |
Pepe | -1.454 |
UTERS | -1.432 |
gest | -1.398 |
Token | is |
Token ID | 318 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
expectations | +1.649 |
Wonderland | +1.539 |
Pepe | +1.523 |
gest | +1.464 |
Kardashian | +1.445 |
Neg logit contributions | |
Reviewed | -2.077 |
itaire | -1.768 |
ippery | -1.546 |
Discuss | -1.515 |
Gray | -1.506 |
Token | a |
Token ID | 257 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
expectations | +0.832 |
Wonderland | +0.781 |
Pepe | +0.775 |
gest | +0.747 |
UTERS | +0.728 |
Neg logit contributions | |
Reviewed | -1.047 |
itaire | -0.881 |
ippery | -0.775 |
Discuss | -0.771 |
Split | -0.759 |
Token | quick |
Token ID | 2068 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
Reviewed | +0.574 |
itaire | +0.479 |
Discuss | +0.427 |
ippery | +0.427 |
Split | +0.418 |
Neg logit contributions | |
expectations | -0.433 |
Wonderland | -0.413 |
Pepe | -0.403 |
gest | -0.389 |
UTERS | -0.388 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Reviewed | +0.054 |
itaire | +0.045 |
ippery | +0.042 |
Discuss | +0.041 |
Split | +0.041 |
Neg logit contributions | |
expectations | -0.033 |
Wonderland | -0.031 |
Pepe | -0.030 |
gest | -0.030 |
UTERS | -0.029 |
Token | fast |
Token ID | 3049 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
Reviewed | +9.687 |
itaire | +7.834 |
ippery | +7.097 |
Split | +6.996 |
threaded | +6.879 |
Neg logit contributions | |
expectations | -8.571 |
Wonderland | -8.539 |
UTERS | -8.520 |
Pepe | -8.310 |
sbm | -8.209 |
Token | slot |
Token ID | 10852 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Reviewed | +0.358 |
itaire | +0.302 |
ippery | +0.274 |
Discuss | +0.270 |
Split | +0.268 |
Neg logit contributions | |
expectations | -0.228 |
Wonderland | -0.214 |
Pepe | -0.211 |
UTERS | -0.203 |
gest | -0.203 |
Token | receiver |
Token ID | 9733 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Reviewed | +3.346 |
itaire | +2.691 |
ippery | +2.354 |
Split | +2.319 |
Discuss | +2.313 |
Neg logit contributions | |
expectations | -3.569 |
Wonderland | -3.463 |
Pepe | -3.378 |
UTERS | -3.369 |
gest | -3.267 |
Token | who |
Token ID | 508 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Reviewed | +2.925 |
itaire | +2.443 |
ippery | +2.202 |
Discuss | +2.166 |
Split | +2.159 |
Neg logit contributions | |
expectations | -2.102 |
Wonderland | -2.009 |
Pepe | -1.964 |
UTERS | -1.934 |
gest | -1.890 |
Token | was |
Token ID | 373 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Reviewed | +0.907 |
itaire | +0.754 |
ippery | +0.674 |
Discuss | +0.660 |
Split | +0.652 |
Neg logit contributions | |
expectations | -0.743 |
Wonderland | -0.702 |
Pepe | -0.695 |
UTERS | -0.671 |
gest | -0.665 |
Token | ) |
Token ID | 8 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
expectations | +1.343 |
Wonderland | +1.267 |
Pepe | +1.227 |
UTERS | +1.225 |
gest | +1.192 |
Neg logit contributions | |
Reviewed | -1.884 |
itaire | -1.578 |
ippery | -1.427 |
Discuss | -1.403 |
Gray | -1.369 |
Token |
|
Token ID | 198 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
Reviewed | +2.964 |
itaire | +2.444 |
ippery | +2.183 |
Discuss | +2.147 |
Split | +2.134 |
Neg logit contributions | |
expectations | -2.474 |
Wonderland | -2.365 |
Pepe | -2.321 |
UTERS | -2.278 |
gest | -2.239 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
expectations | +0.657 |
Wonderland | +0.633 |
Pepe | +0.622 |
UTERS | +0.613 |
gest | +0.600 |
Neg logit contributions | |
Reviewed | -0.569 |
itaire | -0.447 |
Discuss | -0.388 |
ippery | -0.388 |
Split | -0.384 |
Token | 27 |
Token ID | 1983 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
expectations | +2.411 |
gest | +2.291 |
UTERS | +2.288 |
Wonderland | +2.265 |
Pepe | +2.240 |
Neg logit contributions | |
Reviewed | -2.492 |
itaire | -2.124 |
ippery | -1.897 |
oun | -1.770 |
agy | -1.732 |
Token | " |
Token ID | 366 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Reviewed | +3.222 |
itaire | +2.664 |
ippery | +2.387 |
Discuss | +2.347 |
Split | +2.336 |
Neg logit contributions | |
expectations | -2.600 |
Wonderland | -2.484 |
Pepe | -2.439 |
UTERS | -2.390 |
gest | -2.348 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Reviewed | +4.625 |
itaire | +3.785 |
ippery | +3.407 |
Discuss | +3.362 |
Split | +3.359 |
Neg logit contributions | |
expectations | -3.826 |
Wonderland | -3.644 |
Pepe | -3.589 |
UTERS | -3.534 |
gest | -3.433 |
Token | ms |
Token ID | 907 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Reviewed | +8.444 |
itaire | +6.492 |
Split | +5.932 |
ippery | +5.782 |
Gray | +5.762 |
Neg logit contributions | |
expectations | -9.768 |
Pepe | -9.650 |
Wonderland | -9.555 |
Carbuncle | -9.171 |
UTERS | -9.156 |
Token | G |
Token ID | 402 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Reviewed | +0.871 |
itaire | +0.722 |
ippery | +0.649 |
Discuss | +0.639 |
Split | +0.627 |
Neg logit contributions | |
expectations | -0.689 |
Wonderland | -0.659 |
Pepe | -0.638 |
UTERS | -0.627 |
gest | -0.620 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Reviewed | +7.528 |
itaire | +5.825 |
Split | +5.318 |
Discuss | +5.103 |
Gray | +5.075 |
Neg logit contributions | |
expectations | -9.465 |
Wonderland | -9.251 |
Pepe | -9.236 |
UTERS | -8.912 |
Carbuncle | -8.761 |
Token | G |
Token ID | 38 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Reviewed | +5.084 |
Gray | +3.720 |
Discuss | +3.515 |
Split | +3.485 |
itaire | +3.227 |
Neg logit contributions | |
expectations | -9.041 |
eleph | -8.940 |
Wonderland | -8.741 |
Pepe | -8.579 |
geries | -8.562 |
Token | AU |
Token ID | 27548 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Reviewed | +3.153 |
itaire | +2.577 |
ippery | +2.285 |
Discuss | +2.237 |
Split | +2.224 |
Neg logit contributions | |
expectations | -2.952 |
Wonderland | -2.834 |
Pepe | -2.777 |
UTERS | -2.733 |
gest | -2.683 |
Token | nit |
Token ID | 13759 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Reviewed | +1.708 |
itaire | +1.423 |
ippery | +1.281 |
Discuss | +1.261 |
Split | +1.253 |
Neg logit contributions | |
expectations | -1.275 |
Wonderland | -1.216 |
Pepe | -1.192 |
UTERS | -1.169 |
gest | -1.147 |
Token | rous |
Token ID | 7596 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Reviewed | +2.385 |
itaire | +1.916 |
ippery | +1.673 |
Discuss | +1.643 |
Gray | +1.627 |
Neg logit contributions | |
expectations | -2.508 |
Wonderland | -2.442 |
Pepe | -2.392 |
UTERS | -2.350 |
gest | -2.305 |
Token | oxide |
Token ID | 30788 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
Reviewed | +2.703 |
itaire | +2.308 |
ippery | +2.112 |
Discuss | +2.087 |
Split | +2.068 |
Neg logit contributions | |
expectations | -1.437 |
Wonderland | -1.366 |
Pepe | -1.327 |
UTERS | -1.299 |
gest | -1.263 |
Token | emissions |
Token ID | 8971 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
Reviewed | +4.592 |
itaire | +3.864 |
ippery | +3.501 |
Discuss | +3.466 |
Gray | +3.435 |
Neg logit contributions | |
expectations | -3.005 |
Wonderland | -2.902 |
Pepe | -2.837 |
UTERS | -2.817 |
gest | -2.734 |
Token | and |
Token ID | 290 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Reviewed | +4.442 |
itaire | +3.688 |
ippery | +3.346 |
Discuss | +3.311 |
Gray | +3.259 |
Neg logit contributions | |
expectations | -3.252 |
Wonderland | -3.171 |
Pepe | -3.092 |
UTERS | -3.071 |
gest | -2.962 |
Token | fl |
Token ID | 781 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Reviewed | +5.052 |
itaire | +4.211 |
ippery | +3.816 |
Discuss | +3.726 |
Split | +3.722 |
Neg logit contributions | |
expectations | -3.787 |
Wonderland | -3.690 |
Pepe | -3.598 |
UTERS | -3.567 |
gest | -3.487 |
Token | ue |
Token ID | 518 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Reviewed | +7.770 |
itaire | +6.205 |
ippery | +5.651 |
Gray | +5.242 |
Discuss | +5.156 |
Neg logit contributions | |
expectations | -10.601 |
Wonderland | -10.567 |
Pepe | -10.300 |
UTERS | -10.041 |
Carbuncle | -9.923 |
Token | gas |
Token ID | 3623 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Reviewed | +5.307 |
itaire | +4.592 |
ippery | +4.230 |
Gray | +4.169 |
Split | +4.168 |
Neg logit contributions | |
expectations | -2.248 |
Wonderland | -2.166 |
Pepe | -2.091 |
UTERS | -2.034 |
gest | -1.944 |
Token | des |
Token ID | 748 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Reviewed | +3.928 |
itaire | +3.287 |
ippery | +2.961 |
Discuss | +2.927 |
Split | +2.909 |
Neg logit contributions | |
expectations | -2.781 |
Wonderland | -2.685 |
Pepe | -2.627 |
UTERS | -2.592 |
gest | -2.528 |
Token | ulf |
Token ID | 4754 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
Reviewed | +2.454 |
itaire | +2.052 |
ippery | +1.855 |
Discuss | +1.821 |
Split | +1.806 |
Neg logit contributions | |
expectations | -1.766 |
Wonderland | -1.694 |
Pepe | -1.654 |
UTERS | -1.609 |
gest | -1.564 |
Token | ur |
Token ID | 333 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
expectations | +0.520 |
Wonderland | +0.492 |
Pepe | +0.484 |
UTERS | +0.471 |
gest | +0.471 |
Neg logit contributions | |
Reviewed | -0.743 |
itaire | -0.606 |
Discuss | -0.550 |
ippery | -0.547 |
Split | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
expectations | +1.962 |
Wonderland | +1.799 |
Pepe | +1.749 |
gest | +1.709 |
UTERS | +1.705 |
Neg logit contributions | |
Reviewed | -3.182 |
itaire | -2.698 |
ippery | -2.441 |
Discuss | -2.406 |
Split | -2.383 |
Token | with |
Token ID | 351 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
Reviewed | +1.859 |
itaire | +1.556 |
ippery | +1.403 |
Discuss | +1.383 |
Split | +1.372 |
Neg logit contributions | |
expectations | -1.330 |
Wonderland | -1.258 |
Pepe | -1.233 |
UTERS | -1.205 |
gest | -1.188 |
Token | a |
Token ID | 257 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
expectations | +0.256 |
Wonderland | +0.239 |
Pepe | +0.235 |
gest | +0.227 |
UTERS | +0.227 |
Neg logit contributions | |
Reviewed | -0.321 |
itaire | -0.269 |
ippery | -0.239 |
Discuss | -0.236 |
Split | -0.233 |
Token | few |
Token ID | 1178 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
expectations | +0.319 |
Wonderland | +0.302 |
Pepe | +0.296 |
UTERS | +0.286 |
gest | +0.286 |
Neg logit contributions | |
Reviewed | -0.431 |
itaire | -0.358 |
ippery | -0.322 |
Discuss | -0.318 |
Split | -0.315 |
Token | small |
Token ID | 1402 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
expectations | +0.181 |
Wonderland | +0.169 |
Pepe | +0.166 |
UTERS | +0.162 |
gest | +0.160 |
Neg logit contributions | |
Reviewed | -0.253 |
itaire | -0.211 |
ippery | -0.190 |
Discuss | -0.188 |
Split | -0.185 |
Token | fl |
Token ID | 781 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
expectations | +0.951 |
Wonderland | +0.875 |
Pepe | +0.862 |
UTERS | +0.838 |
gest | +0.833 |
Neg logit contributions | |
Reviewed | -1.619 |
itaire | -1.372 |
ippery | -1.253 |
Discuss | -1.232 |
Split | -1.216 |
Token | aps |
Token ID | 1686 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Reviewed | +7.447 |
itaire | +5.989 |
ippery | +5.510 |
ippy | +4.945 |
agy | +4.927 |
Neg logit contributions | |
Wonderland | -10.576 |
expectations | -10.564 |
Pepe | -10.396 |
Carbuncle | -9.923 |
Kardashian | -9.910 |
Token | and |
Token ID | 290 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Reviewed | +4.010 |
itaire | +3.332 |
ippery | +2.987 |
Discuss | +2.948 |
Split | +2.947 |
Neg logit contributions | |
expectations | -3.055 |
Wonderland | -2.937 |
Pepe | -2.884 |
UTERS | -2.824 |
gest | -2.767 |
Token | a |
Token ID | 257 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
Reviewed | +2.093 |
itaire | +1.743 |
ippery | +1.562 |
Discuss | +1.540 |
Split | +1.524 |
Neg logit contributions | |
expectations | -1.619 |
Wonderland | -1.536 |
Pepe | -1.509 |
UTERS | -1.475 |
gest | -1.452 |
Token | fuel |
Token ID | 5252 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
expectations | +0.537 |
Wonderland | +0.509 |
Pepe | +0.500 |
UTERS | +0.484 |
gest | +0.483 |
Neg logit contributions | |
Reviewed | -0.733 |
itaire | -0.610 |
ippery | -0.549 |
Discuss | -0.543 |
Split | -0.535 |
Token | jet |
Token ID | 12644 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Reviewed | +0.720 |
itaire | +0.607 |
ippery | +0.552 |
Discuss | +0.542 |
Split | +0.539 |
Neg logit contributions | |
expectations | -0.479 |
Wonderland | -0.449 |
Pepe | -0.444 |
UTERS | -0.431 |
gest | -0.427 |
Token | ner |
Token ID | 1008 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
Reviewed | +2.980 |
itaire | +2.405 |
ippery | +2.137 |
Discuss | +2.105 |
Split | +2.033 |
Neg logit contributions | |
expectations | -3.178 |
Wonderland | -3.101 |
UTERS | -3.084 |
Pepe | -3.003 |
gest | -2.900 |
Token | gave |
Token ID | 2921 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Reviewed | +0.647 |
itaire | +0.533 |
ippery | +0.477 |
Discuss | +0.469 |
Split | +0.465 |
Neg logit contributions | |
expectations | -0.530 |
Wonderland | -0.506 |
Pepe | -0.497 |
UTERS | -0.487 |
gest | -0.478 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Reviewed | +3.246 |
itaire | +2.704 |
ippery | +2.432 |
Discuss | +2.393 |
Split | +2.381 |
Neg logit contributions | |
expectations | -2.438 |
Wonderland | -2.326 |
Pepe | -2.281 |
UTERS | -2.238 |
gest | -2.197 |
Token | Flyers |
Token ID | 30652 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Reviewed | +2.225 |
itaire | +1.856 |
ippery | +1.667 |
Discuss | +1.645 |
Split | +1.636 |
Neg logit contributions | |
expectations | -1.600 |
Wonderland | -1.520 |
Pepe | -1.485 |
UTERS | -1.447 |
gest | -1.429 |
Token | two |
Token ID | 734 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Reviewed | +1.079 |
itaire | +0.887 |
ippery | +0.788 |
Discuss | +0.774 |
Split | +0.767 |
Neg logit contributions | |
expectations | -0.922 |
Wonderland | -0.876 |
Pepe | -0.859 |
UTERS | -0.838 |
gest | -0.826 |
Token | very |
Token ID | 845 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Reviewed | +1.307 |
itaire | +1.093 |
ippery | +0.983 |
Discuss | +0.970 |
Split | +0.962 |
Neg logit contributions | |
expectations | -0.912 |
Wonderland | -0.864 |
Pepe | -0.845 |
UTERS | -0.821 |
gest | -0.810 |
Token | valuable |
Token ID | 8119 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Reviewed | +8.988 |
itaire | +7.416 |
ippery | +6.831 |
Split | +6.626 |
Discuss | +6.564 |
Neg logit contributions | |
UTERS | -8.560 |
expectations | -8.462 |
Wonderland | -8.248 |
sbm | -8.196 |
Pepe | -8.152 |
Token | standings |
Token ID | 33864 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Reviewed | +5.094 |
itaire | +4.337 |
ippery | +3.963 |
Split | +3.885 |
Discuss | +3.864 |
Neg logit contributions | |
expectations | -3.426 |
Wonderland | -3.312 |
UTERS | -3.273 |
Pepe | -3.244 |
gest | -3.138 |
Token | points |
Token ID | 2173 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
expectations | +0.236 |
Wonderland | +0.217 |
Pepe | +0.213 |
UTERS | +0.207 |
gest | +0.202 |
Neg logit contributions | |
Reviewed | -0.360 |
itaire | -0.302 |
ippery | -0.273 |
Discuss | -0.270 |
Gray | -0.268 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Reviewed | +1.089 |
itaire | +0.912 |
ippery | +0.822 |
Discuss | +0.809 |
Split | +0.803 |
Neg logit contributions | |
expectations | -0.763 |
Wonderland | -0.718 |
Pepe | -0.704 |
UTERS | -0.691 |
gest | -0.676 |
Token | perhaps |
Token ID | 3737 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
Reviewed | +2.269 |
itaire | +1.874 |
ippery | +1.682 |
Discuss | +1.651 |
Split | +1.646 |
Neg logit contributions | |
expectations | -1.845 |
Wonderland | -1.769 |
Pepe | -1.735 |
UTERS | -1.710 |
gest | -1.680 |
Token | We |
Token ID | 1135 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Reviewed | +4.070 |
itaire | +3.119 |
Discuss | +2.820 |
Split | +2.800 |
Gray | +2.757 |
Neg logit contributions | |
expectations | -4.855 |
Wonderland | -4.688 |
Pepe | -4.528 |
UTERS | -4.496 |
Kardashian | -4.405 |
Token | had |
Token ID | 550 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
Reviewed | +1.161 |
itaire | +0.954 |
ippery | +0.850 |
Discuss | +0.836 |
Split | +0.830 |
Neg logit contributions | |
expectations | -1.003 |
Wonderland | -0.960 |
Pepe | -0.942 |
UTERS | -0.925 |
gest | -0.910 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
Reviewed | +0.540 |
itaire | +0.446 |
ippery | +0.391 |
Discuss | +0.386 |
Split | +0.381 |
Neg logit contributions | |
expectations | -0.483 |
Wonderland | -0.452 |
Pepe | -0.450 |
gest | -0.427 |
UTERS | -0.426 |
Token | couple |
Token ID | 3155 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Reviewed | +0.128 |
itaire | +0.105 |
ippery | +0.094 |
Discuss | +0.092 |
Split | +0.092 |
Neg logit contributions | |
expectations | -0.105 |
Wonderland | -0.100 |
Pepe | -0.099 |
gest | -0.095 |
UTERS | -0.094 |
Token | of |
Token ID | 286 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Reviewed | +2.798 |
itaire | +2.355 |
ippery | +2.134 |
Discuss | +2.102 |
Split | +2.091 |
Neg logit contributions | |
expectations | -1.843 |
Wonderland | -1.754 |
Pepe | -1.713 |
UTERS | -1.682 |
gest | -1.646 |
Token | very |
Token ID | 845 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Reviewed | +3.497 |
itaire | +2.904 |
ippery | +2.624 |
Discuss | +2.576 |
Split | +2.560 |
Neg logit contributions | |
expectations | -2.706 |
Wonderland | -2.623 |
UTERS | -2.556 |
Pepe | -2.541 |
gest | -2.479 |
Token | good |
Token ID | 922 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Reviewed | +8.239 |
itaire | +6.475 |
ippery | +5.806 |
Gray | +5.782 |
threaded | +5.745 |
Neg logit contributions | |
UTERS | -9.346 |
expectations | -9.136 |
Wonderland | -9.095 |
aspberry | -8.973 |
sbm | -8.889 |
Token | chances |
Token ID | 8395 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Reviewed | +4.390 |
itaire | +3.698 |
ippery | +3.376 |
Split | +3.319 |
Discuss | +3.312 |
Neg logit contributions | |
expectations | -2.762 |
Wonderland | -2.688 |
UTERS | -2.609 |
Pepe | -2.561 |
gest | -2.515 |
Token | and |
Token ID | 290 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Reviewed | +4.630 |
itaire | +3.826 |
ippery | +3.473 |
Discuss | +3.430 |
Split | +3.403 |
Neg logit contributions | |
expectations | -3.692 |
Wonderland | -3.578 |
UTERS | -3.489 |
Pepe | -3.465 |
gest | -3.380 |
Token | in |
Token ID | 287 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Reviewed | +0.936 |
itaire | +0.772 |
ippery | +0.686 |
Discuss | +0.677 |
Split | +0.670 |
Neg logit contributions | |
expectations | -0.792 |
Wonderland | -0.754 |
Pepe | -0.744 |
UTERS | -0.724 |
gest | -0.714 |
Token | international |
Token ID | 3230 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Reviewed | +2.940 |
itaire | +2.442 |
ippery | +2.193 |
Discuss | +2.156 |
Split | +2.148 |
Neg logit contributions | |
expectations | -2.281 |
Wonderland | -2.179 |
Pepe | -2.133 |
UTERS | -2.104 |
gest | -2.056 |
Token | version |
Token ID | 2196 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Reviewed | +3.122 |
itaire | +2.608 |
ippery | +2.353 |
Discuss | +2.313 |
Split | +2.301 |
Neg logit contributions | |
expectations | -2.236 |
Wonderland | -2.130 |
Pepe | -2.092 |
UTERS | -2.057 |
gest | -1.998 |
Token | of |
Token ID | 286 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Reviewed | +3.957 |
itaire | +3.338 |
ippery | +3.024 |
Discuss | +2.974 |
Split | +2.965 |
Neg logit contributions | |
expectations | -2.525 |
Wonderland | -2.395 |
Pepe | -2.347 |
UTERS | -2.302 |
gest | -2.255 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Reviewed | +2.864 |
itaire | +2.385 |
ippery | +2.145 |
Discuss | +2.110 |
Split | +2.098 |
Neg logit contributions | |
expectations | -2.154 |
Wonderland | -2.054 |
Pepe | -2.014 |
UTERS | -1.976 |
gest | -1.939 |
Token | H |
Token ID | 367 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Reviewed | +1.919 |
itaire | +1.595 |
ippery | +1.430 |
Discuss | +1.411 |
Split | +1.402 |
Neg logit contributions | |
expectations | -1.464 |
Wonderland | -1.397 |
Pepe | -1.365 |
UTERS | -1.332 |
gest | -1.315 |
Token | 1 |
Token ID | 16 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
expectations | +1.387 |
Wonderland | +1.306 |
Pepe | +1.285 |
gest | +1.255 |
UTERS | +1.238 |
Neg logit contributions | |
Reviewed | -1.884 |
itaire | -1.539 |
ippery | -1.364 |
Discuss | -1.364 |
Split | -1.357 |
Token | N |
Token ID | 45 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Reviewed | +3.384 |
itaire | +2.771 |
ippery | +2.456 |
Split | +2.412 |
Discuss | +2.405 |
Neg logit contributions | |
expectations | -3.122 |
Wonderland | -3.005 |
Pepe | -2.944 |
UTERS | -2.900 |
gest | -2.832 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Reviewed | +6.466 |
itaire | +5.157 |
ippery | +4.257 |
Discuss | +4.076 |
orum | +4.045 |
Neg logit contributions | |
Wonderland | -10.984 |
Pepe | -10.929 |
expectations | -10.618 |
enegger | -10.359 |
UTERS | -10.323 |
Token | strain |
Token ID | 14022 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Reviewed | +2.892 |
itaire | +2.438 |
ippery | +2.206 |
Discuss | +2.171 |
Split | +2.164 |
Neg logit contributions | |
expectations | -1.895 |
Wonderland | -1.802 |
Pepe | -1.765 |
UTERS | -1.730 |
gest | -1.689 |
Token | which |
Token ID | 543 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Reviewed | +1.165 |
itaire | +0.974 |
ippery | +0.879 |
Discuss | +0.866 |
Split | +0.861 |
Neg logit contributions | |
expectations | -0.827 |
Wonderland | -0.788 |
Pepe | -0.772 |
UTERS | -0.755 |
gest | -0.741 |
Token | caused |
Token ID | 4073 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Reviewed | +1.925 |
itaire | +1.582 |
ippery | +1.410 |
Discuss | +1.386 |
Split | +1.376 |
Neg logit contributions | |
expectations | -1.665 |
Wonderland | -1.594 |
Pepe | -1.565 |
UTERS | -1.535 |
gest | -1.510 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Reviewed | +2.338 |
itaire | +1.928 |
ippery | +1.722 |
Discuss | +1.695 |
Split | +1.684 |
Neg logit contributions | |
expectations | -1.943 |
Wonderland | -1.859 |
Pepe | -1.825 |
UTERS | -1.794 |
gest | -1.761 |
Token | ball |
Token ID | 1894 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
expectations | +1.829 |
Wonderland | +1.711 |
Pepe | +1.699 |
gest | +1.630 |
UTERS | +1.579 |
Neg logit contributions | |
Reviewed | -3.897 |
itaire | -3.306 |
ippery | -3.054 |
Discuss | -3.042 |
Split | -3.024 |
Token | field |
Token ID | 2214 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Reviewed | +0.037 |
itaire | +0.031 |
ippery | +0.027 |
Discuss | +0.027 |
Split | +0.027 |
Neg logit contributions | |
expectations | -0.030 |
Wonderland | -0.029 |
Pepe | -0.028 |
gest | -0.027 |
UTERS | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Reviewed | +6.292 |
itaire | +5.298 |
ippery | +4.702 |
Split | +4.636 |
Gray | +4.599 |
Neg logit contributions | |
expectations | -4.837 |
Wonderland | -4.650 |
Pepe | -4.573 |
UTERS | -4.508 |
Carbuncle | -4.369 |
Token | where |
Token ID | 810 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Reviewed | +1.389 |
itaire | +1.167 |
ippery | +1.054 |
Discuss | +1.041 |
Split | +1.032 |
Neg logit contributions | |
expectations | -0.942 |
Wonderland | -0.893 |
Pepe | -0.876 |
UTERS | -0.852 |
gest | -0.841 |
Token | four |
Token ID | 1440 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
Reviewed | +5.014 |
itaire | +4.175 |
ippery | +3.735 |
Discuss | +3.674 |
Split | +3.672 |
Neg logit contributions | |
expectations | -3.925 |
Wonderland | -3.799 |
UTERS | -3.714 |
Pepe | -3.706 |
gest | -3.589 |
Token | t |
Token ID | 256 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Reviewed | +0.682 |
itaire | +0.572 |
ippery | +0.516 |
Discuss | +0.511 |
Split | +0.506 |
Neg logit contributions | |
expectations | -0.468 |
Wonderland | -0.441 |
Pepe | -0.432 |
UTERS | -0.418 |
gest | -0.415 |
Token | attered |
Token ID | 10228 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
Reviewed | +9.252 |
itaire | +7.518 |
ippery | +7.067 |
Split | +6.742 |
ippy | +6.622 |
Neg logit contributions | |
expectations | -8.687 |
Wonderland | -8.546 |
Pepe | -8.164 |
UTERS | -8.057 |
Kardashian | -7.899 |
Token | white |
Token ID | 2330 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
expectations | +0.263 |
Wonderland | +0.245 |
Pepe | +0.242 |
UTERS | +0.231 |
gest | +0.229 |
Neg logit contributions | |
Reviewed | -0.450 |
itaire | -0.381 |
ippery | -0.347 |
Discuss | -0.344 |
Split | -0.339 |
Token | bases |
Token ID | 12536 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
expectations | +0.783 |
Wonderland | +0.730 |
Pepe | +0.721 |
UTERS | +0.690 |
gest | +0.682 |
Neg logit contributions | |
Reviewed | -1.367 |
itaire | -1.153 |
ippery | -1.055 |
Discuss | -1.046 |
Split | -1.029 |
Token | mark |
Token ID | 1317 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
Reviewed | +2.155 |
itaire | +1.800 |
ippery | +1.608 |
Discuss | +1.584 |
Split | +1.576 |
Neg logit contributions | |
expectations | -1.667 |
Wonderland | -1.595 |
Pepe | -1.562 |
UTERS | -1.533 |
gest | -1.503 |
Token | the |
Token ID | 262 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
Reviewed | +0.528 |
itaire | +0.440 |
ippery | +0.394 |
Discuss | +0.390 |
Split | +0.384 |
Neg logit contributions | |
expectations | -0.383 |
Wonderland | -0.363 |
Pepe | -0.355 |
UTERS | -0.343 |
gest | -0.340 |
Token | people |
Token ID | 661 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Reviewed | +2.261 |
itaire | +1.870 |
ippery | +1.674 |
Discuss | +1.646 |
Split | +1.636 |
Neg logit contributions | |
expectations | -1.831 |
Wonderland | -1.749 |
Pepe | -1.716 |
UTERS | -1.685 |
gest | -1.655 |
Token | with |
Token ID | 351 |
Feature activation | -8.18e-03 |
Pos logit contributions | |
Reviewed | +1.437 |
itaire | +1.199 |
ippery | +1.080 |
Discuss | +1.064 |
Split | +1.058 |
Neg logit contributions | |
expectations | -1.047 |
Wonderland | -0.998 |
Pepe | -0.978 |
UTERS | -0.961 |
gest | -0.942 |
Token | bad |
Token ID | 2089 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
expectations | +0.046 |
Wonderland | +0.043 |
Pepe | +0.043 |
UTERS | +0.041 |
gest | +0.041 |
Neg logit contributions | |
Reviewed | -0.060 |
itaire | -0.050 |
ippery | -0.045 |
Split | -0.044 |
Discuss | -0.044 |
Token | manners |
Token ID | 33558 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
expectations | +0.205 |
Wonderland | +0.189 |
Pepe | +0.186 |
UTERS | +0.180 |
gest | +0.177 |
Neg logit contributions | |
Reviewed | -0.354 |
itaire | -0.304 |
ippery | -0.276 |
Split | -0.272 |
Discuss | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
expectations | +2.107 |
Wonderland | +1.926 |
Pepe | +1.890 |
UTERS | +1.825 |
gest | +1.823 |
Neg logit contributions | |
Reviewed | -3.124 |
itaire | -2.638 |
ippery | -2.411 |
Split | -2.364 |
Gray | -2.326 |
Token | - |
Token ID | 532 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Reviewed | +2.038 |
itaire | +1.680 |
ippery | +1.502 |
Discuss | +1.479 |
Split | +1.470 |
Neg logit contributions | |
expectations | -1.682 |
Wonderland | -1.607 |
Pepe | -1.576 |
UTERS | -1.551 |
gest | -1.522 |
Token | January |
Token ID | 3269 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Reviewed | +6.525 |
itaire | +4.559 |
Discuss | +4.281 |
ippery | +4.137 |
ancy | +3.899 |
Neg logit contributions | |
Wonderland | -10.364 |
geries | -10.336 |
expectations | -10.242 |
Pepe | -10.236 |
UTERS | -10.197 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Reviewed | +3.505 |
itaire | +2.590 |
Discuss | +2.477 |
Split | +2.376 |
ippery | +2.349 |
Neg logit contributions | |
expectations | -4.246 |
Wonderland | -4.160 |
Pepe | -4.100 |
UTERS | -4.062 |
rants | -4.016 |
Token | , |
Token ID | 11 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Reviewed | +5.869 |
itaire | +4.368 |
Discuss | +4.350 |
Gray | +4.268 |
Split | +4.250 |
Neg logit contributions | |
eleph | -5.310 |
expectations | -5.273 |
Wonderland | -5.122 |
pione | -5.036 |
Pepe | -4.893 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Reviewed | +3.235 |
itaire | +2.140 |
Discuss | +1.945 |
ippery | +1.918 |
Gray | +1.895 |
Neg logit contributions | |
expectations | -5.628 |
Wonderland | -5.486 |
Pepe | -5.432 |
UTERS | -5.432 |
sbm | -5.375 |
Token | User |
Token ID | 12982 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Reviewed | +2.021 |
itaire | +1.595 |
ippery | +1.379 |
Discuss | +1.345 |
Split | +1.335 |
Neg logit contributions | |
expectations | -2.478 |
Wonderland | -2.387 |
Pepe | -2.351 |
UTERS | -2.316 |
gest | -2.286 |
Token | cigarette |
Token ID | 17779 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
expectations | +1.432 |
Wonderland | +1.349 |
Pepe | +1.328 |
gest | +1.292 |
UTERS | +1.283 |
Neg logit contributions | |
Reviewed | -1.855 |
itaire | -1.547 |
ippery | -1.373 |
Discuss | -1.362 |
Split | -1.340 |
Token | lighter |
Token ID | 14871 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Reviewed | +1.817 |
itaire | +1.458 |
ippery | +1.278 |
Discuss | +1.251 |
Split | +1.243 |
Neg logit contributions | |
expectations | -1.942 |
Wonderland | -1.868 |
Pepe | -1.837 |
UTERS | -1.808 |
gest | -1.780 |
Token | , |
Token ID | 11 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Reviewed | +1.799 |
itaire | +1.515 |
ippery | +1.372 |
Discuss | +1.353 |
Split | +1.343 |
Neg logit contributions | |
expectations | -1.175 |
Wonderland | -1.113 |
Pepe | -1.090 |
UTERS | -1.064 |
gest | -1.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
expectations | +1.096 |
Wonderland | +1.022 |
Pepe | +1.004 |
UTERS | +0.972 |
gest | +0.972 |
Neg logit contributions | |
Reviewed | -1.799 |
itaire | -1.512 |
ippery | -1.372 |
Discuss | -1.366 |
Split | -1.347 |
Token | the |
Token ID | 262 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
expectations | +0.179 |
Wonderland | +0.169 |
Pepe | +0.166 |
UTERS | +0.162 |
gest | +0.160 |
Neg logit contributions | |
Reviewed | -0.252 |
itaire | -0.210 |
ippery | -0.189 |
Discuss | -0.188 |
Split | -0.185 |
Token | fl |
Token ID | 781 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
expectations | +1.930 |
Wonderland | +1.822 |
Pepe | +1.794 |
gest | +1.731 |
UTERS | +1.719 |
Neg logit contributions | |
Reviewed | -2.495 |
itaire | -2.073 |
Discuss | -1.842 |
ippery | -1.838 |
Split | -1.795 |
Token | asher |
Token ID | 31218 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Reviewed | +8.445 |
itaire | +7.052 |
ippery | +6.512 |
adier | +6.074 |
orum | +5.909 |
Neg logit contributions | |
expectations | -9.074 |
Wonderland | -8.984 |
Pepe | -8.840 |
UTERS | -8.489 |
Carbuncle | -8.388 |
Token | button |
Token ID | 4936 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Reviewed | +1.175 |
itaire | +0.981 |
ippery | +0.883 |
Discuss | +0.871 |
Split | +0.862 |
Neg logit contributions | |
expectations | -0.847 |
Wonderland | -0.803 |
Pepe | -0.788 |
UTERS | -0.773 |
gest | -0.760 |
Token | between |
Token ID | 1022 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Reviewed | +1.076 |
itaire | +0.901 |
ippery | +0.813 |
Discuss | +0.796 |
Split | +0.790 |
Neg logit contributions | |
expectations | -0.767 |
Wonderland | -0.727 |
Pepe | -0.712 |
UTERS | -0.701 |
gest | -0.690 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
expectations | +0.865 |
Wonderland | +0.821 |
Pepe | +0.802 |
UTERS | +0.776 |
gest | +0.767 |
Neg logit contributions | |
Reviewed | -1.282 |
itaire | -1.070 |
ippery | -0.967 |
Discuss | -0.959 |
Split | -0.945 |
Token | air |
Token ID | 1633 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
expectations | +2.513 |
Wonderland | +2.351 |
Pepe | +2.318 |
gest | +2.232 |
UTERS | +2.208 |
Neg logit contributions | |
Reviewed | -3.334 |
itaire | -2.785 |
Discuss | -2.493 |
ippery | -2.462 |
Split | -2.403 |
Token | thr |
Token ID | 5636 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Reviewed | +0.922 |
itaire | +0.712 |
ippery | +0.608 |
Discuss | +0.599 |
Split | +0.589 |
Neg logit contributions | |
expectations | -1.259 |
Wonderland | -1.225 |
Pepe | -1.212 |
UTERS | -1.195 |
gest | -1.173 |
Token | : |
Token ID | 25 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Reviewed | +5.845 |
itaire | +4.134 |
Discuss | +4.104 |
Split | +3.972 |
Gray | +3.742 |
Neg logit contributions | |
eleph | -9.220 |
expectations | -9.005 |
Wonderland | -8.945 |
pione | -8.880 |
Pepe | -8.653 |
Token | off |
Token ID | 2364 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Reviewed | +0.976 |
itaire | +0.700 |
ippery | +0.568 |
Discuss | +0.559 |
Split | +0.548 |
Neg logit contributions | |
expectations | -1.873 |
Wonderland | -1.832 |
Pepe | -1.798 |
UTERS | -1.783 |
Kardashian | -1.739 |
Token | Frag |
Token ID | 24229 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Reviewed | +0.862 |
itaire | +0.736 |
ippery | +0.676 |
Discuss | +0.665 |
Gray | +0.660 |
Neg logit contributions | |
expectations | -0.433 |
Wonderland | -0.404 |
Pepe | -0.394 |
UTERS | -0.380 |
gest | -0.379 |
Token | ment |
Token ID | 434 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Reviewed | +0.987 |
itaire | +0.807 |
ippery | +0.719 |
Discuss | +0.717 |
Split | +0.715 |
Neg logit contributions | |
expectations | -0.895 |
Wonderland | -0.870 |
Pepe | -0.851 |
UTERS | -0.836 |
Carbuncle | -0.803 |
Token | thr |
Token ID | 5636 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Reviewed | +1.530 |
itaire | +1.165 |
ippery | +0.979 |
Discuss | +0.965 |
Split | +0.937 |
Neg logit contributions | |
expectations | -2.358 |
Wonderland | -2.328 |
Pepe | -2.319 |
UTERS | -2.279 |
gest | -2.221 |
Token | : |
Token ID | 25 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
Reviewed | +6.405 |
Discuss | +4.528 |
Split | +4.352 |
itaire | +4.243 |
Gray | +4.095 |
Neg logit contributions | |
eleph | -11.865 |
pione | -11.423 |
expectations | -10.761 |
reluct | -10.748 |
Wonderland | -10.689 |
Token | off |
Token ID | 2364 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Reviewed | +0.422 |
itaire | +0.301 |
ippery | +0.242 |
Discuss | +0.241 |
Gray | +0.235 |
Neg logit contributions | |
expectations | -0.823 |
Wonderland | -0.809 |
Pepe | -0.793 |
UTERS | -0.784 |
Carbuncle | -0.766 |
Token | Power |
Token ID | 4333 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Reviewed | +3.186 |
itaire | +2.568 |
ippery | +2.254 |
Discuss | +2.210 |
Split | +2.192 |
Neg logit contributions | |
expectations | -3.305 |
Wonderland | -3.175 |
Pepe | -3.121 |
UTERS | -3.068 |
gest | -3.025 |
Token | Management |
Token ID | 8549 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Reviewed | +3.238 |
itaire | +2.559 |
Discuss | +2.250 |
Split | +2.239 |
ippery | +2.218 |
Neg logit contributions | |
expectations | -3.565 |
Wonderland | -3.480 |
Pepe | -3.434 |
UTERS | -3.392 |
aspberry | -3.290 |
Token | : |
Token ID | 25 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Reviewed | +4.548 |
itaire | +3.345 |
Discuss | +3.139 |
Split | +3.069 |
Gray | +2.928 |
Neg logit contributions | |
expectations | -6.289 |
Wonderland | -6.131 |
eleph | -6.069 |
Pepe | -6.006 |
UTERS | -5.978 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
expectations | +1.270 |
Wonderland | +1.189 |
Pepe | +1.148 |
UTERS | +1.115 |
gest | +1.106 |
Neg logit contributions | |
Reviewed | -1.994 |
itaire | -1.710 |
ippery | -1.535 |
Discuss | -1.515 |
Split | -1.495 |
Token | years |
Token ID | 812 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
expectations | +2.366 |
Wonderland | +2.214 |
UTERS | +2.168 |
Pepe | +2.137 |
gest | +2.092 |
Neg logit contributions | |
Reviewed | -2.575 |
itaire | -2.152 |
ippery | -1.895 |
Discuss | -1.843 |
Gray | -1.839 |
Token | to |
Token ID | 284 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
expectations | +1.336 |
Wonderland | +1.213 |
Pepe | +1.191 |
UTERS | +1.191 |
gest | +1.149 |
Neg logit contributions | |
Reviewed | -2.210 |
itaire | -1.890 |
ippery | -1.716 |
Discuss | -1.677 |
Gray | -1.657 |
Token | 700 |
Token ID | 13037 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
expectations | +2.368 |
Wonderland | +2.225 |
Pepe | +2.177 |
UTERS | +2.089 |
gest | +2.086 |
Neg logit contributions | |
Reviewed | -3.170 |
itaire | -2.609 |
ippery | -2.356 |
Discuss | -2.286 |
Split | -2.277 |
Token | million |
Token ID | 1510 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
expectations | +1.944 |
Wonderland | +1.797 |
Pepe | +1.715 |
UTERS | +1.701 |
gest | +1.606 |
Neg logit contributions | |
Reviewed | -4.199 |
itaire | -3.600 |
ippery | -3.317 |
Discuss | -3.237 |
Split | -3.216 |
Token | fl |
Token ID | 781 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Reviewed | +1.846 |
itaire | +1.546 |
ippery | +1.398 |
Discuss | +1.374 |
Split | +1.363 |
Neg logit contributions | |
expectations | -1.308 |
Wonderland | -1.242 |
Pepe | -1.217 |
UTERS | -1.187 |
gest | -1.165 |
Token | iers |
Token ID | 3183 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
Reviewed | +8.620 |
itaire | +6.941 |
Gray | +6.238 |
ippery | +6.200 |
orum | +6.098 |
Neg logit contributions | |
expectations | -9.003 |
Wonderland | -8.947 |
Pepe | -8.853 |
Carbuncle | -8.633 |
UTERS | -8.460 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
expectations | +0.024 |
Wonderland | +0.022 |
Pepe | +0.022 |
UTERS | +0.021 |
gest | +0.021 |
Neg logit contributions | |
Reviewed | -0.031 |
itaire | -0.026 |
ippery | -0.023 |
Discuss | -0.023 |
Split | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
Reviewed | +1.015 |
itaire | +0.835 |
ippery | +0.746 |
Discuss | +0.722 |
Split | +0.716 |
Neg logit contributions | |
expectations | -0.915 |
Wonderland | -0.881 |
Pepe | -0.866 |
UTERS | -0.844 |
gest | -0.837 |
Token |
|
Token ID | 198 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
Reviewed | +0.251 |
itaire | +0.194 |
Discuss | +0.170 |
ippery | +0.168 |
Split | +0.168 |
Neg logit contributions | |
expectations | -0.302 |
Wonderland | -0.292 |
Pepe | -0.285 |
UTERS | -0.282 |
gest | -0.275 |
Token | Last |
Token ID | 5956 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Reviewed | +0.317 |
itaire | +0.259 |
ippery | +0.231 |
Discuss | +0.220 |
Split | +0.219 |
Neg logit contributions | |
expectations | -0.317 |
Wonderland | -0.304 |
Pepe | -0.299 |
UTERS | -0.298 |
gest | -0.293 |
Token | This |
Token ID | 1212 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
expectations | +1.484 |
Wonderland | +1.418 |
UTERS | +1.396 |
Pepe | +1.388 |
gest | +1.378 |
Neg logit contributions | |
Reviewed | -1.469 |
itaire | -1.202 |
ippery | -1.079 |
Discuss | -1.004 |
Split | -1.004 |
Token | monumental |
Token ID | 36364 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
expectations | +0.521 |
Wonderland | +0.496 |
Pepe | +0.482 |
UTERS | +0.468 |
gest | +0.468 |
Neg logit contributions | |
Reviewed | -0.632 |
itaire | -0.522 |
ippery | -0.467 |
Split | -0.456 |
Discuss | -0.456 |
Token | feat |
Token ID | 2218 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
expectations | +3.263 |
Wonderland | +3.069 |
Pepe | +2.976 |
gest | +2.947 |
UTERS | +2.850 |
Neg logit contributions | |
Reviewed | -3.727 |
itaire | -3.004 |
ippery | -2.692 |
Discuss | -2.631 |
Split | -2.625 |
Token | could |
Token ID | 714 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
expectations | +4.894 |
Wonderland | +4.380 |
Pepe | +4.340 |
gest | +4.245 |
UTERS | +4.139 |
Neg logit contributions | |
Reviewed | -6.482 |
itaire | -5.342 |
ippery | -4.766 |
Split | -4.701 |
Gray | -4.685 |
Token | not |
Token ID | 407 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
expectations | +3.882 |
Wonderland | +3.529 |
gest | +3.457 |
Pepe | +3.427 |
UTERS | +3.370 |
Neg logit contributions | |
Reviewed | -5.618 |
itaire | -4.721 |
ippery | -4.199 |
Gray | -4.198 |
Split | -4.090 |
Token | have |
Token ID | 423 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
expectations | +6.485 |
Wonderland | +5.615 |
gest | +5.425 |
Pepe | +5.421 |
harbor | +5.235 |
Neg logit contributions | |
Reviewed | -11.354 |
itaire | -9.635 |
Gray | -8.895 |
ippery | -8.854 |
Split | -8.513 |
Token | been |
Token ID | 587 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
expectations | +8.395 |
Pepe | +7.091 |
gest | +7.012 |
Wonderland | +6.998 |
lent | +6.686 |
Neg logit contributions | |
Reviewed | -11.910 |
itaire | -10.586 |
Gray | -9.190 |
Discuss | -8.972 |
ippery | -8.906 |
Token | accomplished |
Token ID | 13013 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
expectations | +6.608 |
Wonderland | +5.829 |
gest | +5.729 |
Pepe | +5.713 |
Kardashian | +5.650 |
Neg logit contributions | |
Reviewed | -9.271 |
itaire | -7.975 |
ippery | -7.138 |
Gray | -7.089 |
Discuss | -7.057 |
Token | without |
Token ID | 1231 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
expectations | +3.910 |
Wonderland | +3.381 |
gest | +3.275 |
Pepe | +3.260 |
Kardashian | +3.132 |
Neg logit contributions | |
Reviewed | -8.637 |
itaire | -7.333 |
ippery | -6.739 |
Split | -6.614 |
Gray | -6.557 |
Token | our |
Token ID | 674 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
expectations | +2.593 |
Wonderland | +2.393 |
Pepe | +2.296 |
UTERS | +2.206 |
gest | +2.194 |
Neg logit contributions | |
Reviewed | -4.345 |
itaire | -3.593 |
ippery | -3.313 |
Gray | -3.232 |
Discuss | -3.211 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
expectations | +3.878 |
Wonderland | +3.594 |
Pepe | +3.482 |
gest | +3.384 |
UTERS | +3.315 |
Neg logit contributions | |
Reviewed | -5.089 |
itaire | -4.117 |
ippery | -3.717 |
Gray | -3.637 |
Discuss | -3.610 |
Token | true |
Token ID | 2081 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Reviewed | +3.508 |
itaire | +3.002 |
ippery | +2.755 |
Discuss | +2.720 |
Split | +2.708 |
Neg logit contributions | |
expectations | -1.805 |
Wonderland | -1.730 |
Pepe | -1.677 |
UTERS | -1.660 |
gest | -1.599 |
Token | priorities |
Token ID | 15369 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Reviewed | +8.162 |
itaire | +7.025 |
ippery | +6.540 |
Split | +6.530 |
Discuss | +6.519 |
Neg logit contributions | |
Wonderland | -3.834 |
UTERS | -3.726 |
expectations | -3.651 |
Pepe | -3.601 |
aspberry | -3.507 |
Token | — |
Token ID | 851 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Reviewed | +2.368 |
itaire | +1.951 |
ippery | +1.739 |
Discuss | +1.720 |
Split | +1.698 |
Neg logit contributions | |
expectations | -2.058 |
Wonderland | -2.000 |
Pepe | -1.950 |
UTERS | -1.923 |
gest | -1.880 |
Token | and |
Token ID | 290 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
expectations | +0.812 |
Wonderland | +0.750 |
Pepe | +0.742 |
UTERS | +0.721 |
gest | +0.713 |
Neg logit contributions | |
Reviewed | -1.179 |
itaire | -0.990 |
ippery | -0.893 |
Split | -0.875 |
Discuss | -0.875 |
Token | his |
Token ID | 465 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
expectations | +0.478 |
Wonderland | +0.443 |
Pepe | +0.440 |
UTERS | +0.427 |
gest | +0.421 |
Neg logit contributions | |
Reviewed | -0.570 |
itaire | -0.468 |
ippery | -0.416 |
Discuss | -0.409 |
Gray | -0.406 |
Token | or |
Token ID | 393 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Reviewed | +0.395 |
itaire | +0.332 |
ippery | +0.299 |
Discuss | +0.294 |
Split | +0.293 |
Neg logit contributions | |
expectations | -0.273 |
Wonderland | -0.256 |
Pepe | -0.252 |
UTERS | -0.245 |
gest | -0.241 |
Token | her |
Token ID | 607 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
expectations | +5.959 |
Wonderland | +5.386 |
Pepe | +5.321 |
Kardashian | +5.030 |
gest | +4.984 |
Neg logit contributions | |
Reviewed | -14.528 |
itaire | -12.292 |
ippery | -11.518 |
Gray | -11.170 |
oun | -11.168 |
Token | character |
Token ID | 2095 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Reviewed | +1.307 |
itaire | +1.103 |
ippery | +1.001 |
Discuss | +0.986 |
Split | +0.981 |
Neg logit contributions | |
expectations | -0.829 |
Wonderland | -0.785 |
Pepe | -0.768 |
UTERS | -0.750 |
gest | -0.736 |
Token | — |
Token ID | 851 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
expectations | +2.705 |
Pepe | +2.360 |
Wonderland | +2.348 |
UTERS | +2.271 |
gest | +2.248 |
Neg logit contributions | |
Reviewed | -4.482 |
itaire | -3.854 |
ippery | -3.521 |
Split | -3.458 |
Gray | -3.439 |
Token | is |
Token ID | 318 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
expectations | +0.623 |
Wonderland | +0.585 |
Pepe | +0.582 |
UTERS | +0.566 |
gest | +0.562 |
Neg logit contributions | |
Reviewed | -0.759 |
itaire | -0.625 |
ippery | -0.559 |
Split | -0.548 |
Discuss | -0.547 |
Token | to |
Token ID | 284 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Reviewed | +2.882 |
itaire | +2.276 |
ippery | +1.973 |
Discuss | +1.930 |
Split | +1.915 |
Neg logit contributions | |
expectations | -3.455 |
Wonderland | -3.329 |
Pepe | -3.277 |
UTERS | -3.227 |
gest | -3.182 |
Token | for |
Token ID | 329 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Reviewed | +1.576 |
itaire | +1.316 |
ippery | +1.183 |
Discuss | +1.164 |
Split | +1.157 |
Neg logit contributions | |
expectations | -1.165 |
Wonderland | -1.110 |
Pepe | -1.089 |
UTERS | -1.061 |
gest | -1.045 |
Token | he |
Token ID | 339 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
expectations | +4.424 |
Wonderland | +4.179 |
Pepe | +4.114 |
gest | +3.954 |
UTERS | +3.876 |
Neg logit contributions | |
Reviewed | -4.923 |
itaire | -4.041 |
ippery | -3.624 |
Discuss | -3.505 |
Split | -3.492 |
Token | has |
Token ID | 468 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
expectations | +1.609 |
Wonderland | +1.512 |
Pepe | +1.491 |
gest | +1.426 |
Kardashian | +1.409 |
Neg logit contributions | |
Reviewed | -1.943 |
itaire | -1.616 |
ippery | -1.424 |
Split | -1.401 |
Discuss | -1.395 |
Token | taken |
Token ID | 2077 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
expectations | +0.059 |
Wonderland | +0.056 |
Pepe | +0.055 |
UTERS | +0.053 |
gest | +0.053 |
Neg logit contributions | |
Reviewed | -0.072 |
itaire | -0.060 |
ippery | -0.053 |
Discuss | -0.052 |
Split | -0.051 |
Token | Sar |
Token ID | 6866 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
expectations | +2.277 |
Wonderland | +2.149 |
Pepe | +2.113 |
gest | +1.974 |
UTERS | +1.972 |
Neg logit contributions | |
Reviewed | -3.122 |
itaire | -2.621 |
ippery | -2.325 |
Discuss | -2.283 |
Split | -2.276 |
Token | uman |
Token ID | 3778 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
expectations | +1.554 |
Wonderland | +1.426 |
Pepe | +1.381 |
UTERS | +1.325 |
gest | +1.322 |
Neg logit contributions | |
Reviewed | -4.594 |
itaire | -3.968 |
ippery | -3.672 |
Discuss | -3.643 |
Split | -3.640 |
Token | 's |
Token ID | 338 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
expectations | +8.207 |
Wonderland | +7.670 |
Pepe | +7.444 |
persona | +7.324 |
Carbuncle | +7.116 |
Neg logit contributions | |
Reviewed | -11.904 |
itaire | -9.848 |
Split | -8.682 |
ippery | -8.642 |
Discuss | -8.596 |
Token | place |
Token ID | 1295 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
expectations | +6.484 |
Wonderland | +5.947 |
Pepe | +5.720 |
persona | +5.584 |
Carbuncle | +5.526 |
Neg logit contributions | |
Reviewed | -9.655 |
itaire | -7.813 |
ippery | -7.160 |
Discuss | -6.950 |
Split | -6.840 |
Token | as |
Token ID | 355 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
expectations | +1.590 |
Wonderland | +1.471 |
Pepe | +1.445 |
UTERS | +1.400 |
gest | +1.393 |
Neg logit contributions | |
Reviewed | -2.692 |
itaire | -2.264 |
ippery | -2.059 |
Discuss | -2.027 |
Split | -1.999 |
Token | the |
Token ID | 262 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
expectations | +0.781 |
Wonderland | +0.745 |
Pepe | +0.726 |
gest | +0.696 |
UTERS | +0.696 |
Neg logit contributions | |
Reviewed | -1.028 |
itaire | -0.851 |
ippery | -0.763 |
Discuss | -0.750 |
Split | -0.745 |
Token | chief |
Token ID | 4039 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
expectations | +0.546 |
Wonderland | +0.520 |
Pepe | +0.507 |
UTERS | +0.490 |
gest | +0.488 |
Neg logit contributions | |
Reviewed | -0.708 |
itaire | -0.586 |
ippery | -0.525 |
Discuss | -0.517 |
Split | -0.512 |
Token | Oklahoma |
Token ID | 10433 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
expectations | +0.743 |
Wonderland | +0.715 |
Pepe | +0.700 |
UTERS | +0.683 |
gest | +0.676 |
Neg logit contributions | |
Reviewed | -0.762 |
itaire | -0.618 |
ippery | -0.544 |
Discuss | -0.536 |
Split | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Reviewed | +0.331 |
itaire | +0.278 |
ippery | +0.254 |
Split | +0.249 |
Discuss | +0.248 |
Neg logit contributions | |
expectations | -0.222 |
Wonderland | -0.208 |
Pepe | -0.205 |
UTERS | -0.202 |
gest | -0.198 |
Token | March |
Token ID | 2805 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
expectations | +4.755 |
Pepe | +4.338 |
Wonderland | +4.327 |
UTERS | +4.166 |
gest | +4.160 |
Neg logit contributions | |
Reviewed | -7.341 |
itaire | -6.326 |
ippery | -5.733 |
Split | -5.648 |
Gray | -5.543 |
Token | 24 |
Token ID | 1987 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
expectations | +1.936 |
Wonderland | +1.859 |
Pepe | +1.816 |
UTERS | +1.759 |
gest | +1.751 |
Neg logit contributions | |
Reviewed | -2.658 |
itaire | -2.237 |
ippery | -2.008 |
Discuss | -1.957 |
Split | -1.950 |
Token | , |
Token ID | 11 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
expectations | +2.527 |
Wonderland | +2.375 |
Pepe | +2.337 |
UTERS | +2.271 |
gest | +2.236 |
Neg logit contributions | |
Reviewed | -4.926 |
itaire | -4.244 |
ippery | -3.875 |
Discuss | -3.777 |
Split | -3.767 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
expectations | +3.428 |
Wonderland | +3.219 |
Pepe | +3.143 |
gest | +3.058 |
UTERS | +3.009 |
Neg logit contributions | |
Reviewed | -5.444 |
itaire | -4.678 |
ippery | -4.188 |
Split | -4.071 |
Discuss | -4.062 |
Token | . |
Token ID | 13 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
expectations | +5.360 |
UTERS | +5.084 |
Pepe | +4.982 |
Wonderland | +4.664 |
Kardashian | +4.618 |
Neg logit contributions | |
Reviewed | -12.684 |
itaire | -11.427 |
ippery | -10.404 |
Gray | -10.141 |
agy | -10.036 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
expectations | +2.045 |
Wonderland | +1.992 |
UTERS | +1.978 |
Pepe | +1.959 |
gest | +1.779 |
Neg logit contributions | |
Reviewed | -4.728 |
itaire | -4.229 |
ippery | -3.851 |
Discuss | -3.733 |
Gray | -3.678 |
Token | / |
Token ID | 14 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Reviewed | +3.233 |
itaire | +2.499 |
Split | +2.265 |
Discuss | +2.262 |
Gray | +2.222 |
Neg logit contributions | |
expectations | -3.170 |
Wonderland | -3.029 |
Pepe | -2.957 |
gest | -2.856 |
Carbuncle | -2.848 |
Token | Nick |
Token ID | 23609 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
Reviewed | +1.796 |
itaire | +1.406 |
ippery | +1.219 |
Discuss | +1.203 |
Split | +1.196 |
Neg logit contributions | |
expectations | -2.169 |
Wonderland | -2.090 |
Pepe | -2.053 |
UTERS | -2.019 |
gest | -1.992 |
Token | Oxford |
Token ID | 13643 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
expectations | +0.466 |
Wonderland | +0.449 |
Pepe | +0.443 |
UTERS | +0.423 |
gest | +0.422 |
Neg logit contributions | |
Reviewed | -0.585 |
itaire | -0.484 |
ippery | -0.428 |
Discuss | -0.426 |
Split | -0.420 |
Token | which |
Token ID | 543 |
Feature activation | +4.57e-04 |
Pos logit contributions | |
Reviewed | +5.141 |
itaire | +4.315 |
ippery | +3.903 |
Discuss | +3.775 |
Split | +3.745 |
Neg logit contributions | |
expectations | -3.977 |
Pepe | -3.771 |
Wonderland | -3.764 |
UTERS | -3.762 |
aspberry | -3.578 |
Token | the |
Token ID | 262 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
Reviewed | +0.003 |
itaire | +0.003 |
ippery | +0.002 |
Discuss | +0.002 |
Split | +0.002 |
Neg logit contributions | |
expectations | -0.003 |
Wonderland | -0.002 |
Pepe | -0.002 |
UTERS | -0.002 |
gest | -0.002 |
Token | perpetrator |
Token ID | 33599 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
expectations | +0.206 |
Wonderland | +0.192 |
Pepe | +0.187 |
UTERS | +0.181 |
gest | +0.181 |
Neg logit contributions | |
Reviewed | -0.304 |
itaire | -0.253 |
ippery | -0.229 |
Discuss | -0.227 |
Split | -0.225 |
Token | presents |
Token ID | 10969 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
expectations | +0.751 |
Wonderland | +0.707 |
Pepe | +0.697 |
gest | +0.670 |
UTERS | +0.670 |
Neg logit contributions | |
Reviewed | -1.021 |
itaire | -0.847 |
ippery | -0.765 |
Discuss | -0.751 |
Split | -0.748 |
Token | him |
Token ID | 683 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
expectations | +2.119 |
Wonderland | +1.955 |
Pepe | +1.939 |
gest | +1.833 |
Kardashian | +1.829 |
Neg logit contributions | |
Reviewed | -2.619 |
itaire | -2.131 |
ippery | -1.931 |
Discuss | -1.893 |
Gray | -1.880 |
Token | / |
Token ID | 14 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
expectations | +3.370 |
Wonderland | +3.103 |
Pepe | +3.034 |
gest | +2.996 |
UTERS | +2.899 |
Neg logit contributions | |
Reviewed | -5.450 |
itaire | -4.448 |
Split | -4.038 |
Discuss | -4.011 |
ippery | -4.002 |
Token | her |
Token ID | 372 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
expectations | +8.744 |
gest | +8.692 |
Wonderland | +8.304 |
Pepe | +8.044 |
arent | +7.972 |
Neg logit contributions | |
Reviewed | -10.355 |
itaire | -8.051 |
ippery | -7.724 |
oun | -7.440 |
Discuss | -7.119 |
Token | self |
Token ID | 944 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Reviewed | +0.033 |
itaire | +0.026 |
ippery | +0.024 |
Discuss | +0.023 |
Split | +0.023 |
Neg logit contributions | |
expectations | -0.032 |
Wonderland | -0.030 |
Pepe | -0.030 |
UTERS | -0.029 |
gest | -0.029 |
Token | as |
Token ID | 355 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
expectations | +2.658 |
Wonderland | +2.433 |
Pepe | +2.414 |
gest | +2.298 |
UTERS | +2.275 |
Neg logit contributions | |
Reviewed | -4.570 |
itaire | -3.789 |
ippery | -3.465 |
Discuss | -3.460 |
Split | -3.407 |
Token | someone |
Token ID | 2130 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
expectations | +1.592 |
Wonderland | +1.513 |
Pepe | +1.497 |
gest | +1.422 |
Kardashian | +1.410 |
Neg logit contributions | |
Reviewed | -2.058 |
itaire | -1.684 |
ippery | -1.508 |
Discuss | -1.488 |
Split | -1.477 |
Token | he |
Token ID | 339 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
expectations | +0.255 |
Wonderland | +0.242 |
Pepe | +0.237 |
UTERS | +0.227 |
gest | +0.226 |
Neg logit contributions | |
Reviewed | -0.370 |
itaire | -0.307 |
ippery | -0.279 |
Discuss | -0.275 |
Split | -0.273 |
Token | R |
Token ID | 49 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
expectations | +1.497 |
Wonderland | +1.435 |
UTERS | +1.432 |
Pepe | +1.428 |
gest | +1.407 |
Neg logit contributions | |
Reviewed | -1.605 |
itaire | -1.365 |
ippery | -1.213 |
oun | -1.125 |
Split | -1.107 |
Token | obby |
Token ID | 11369 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
expectations | +2.079 |
UTERS | +1.932 |
Pepe | +1.926 |
Wonderland | +1.921 |
gest | +1.908 |
Neg logit contributions | |
Reviewed | -2.169 |
itaire | -1.805 |
ippery | -1.544 |
Discuss | -1.539 |
Split | -1.531 |
Token | M |
Token ID | 337 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Reviewed | +3.081 |
itaire | +2.546 |
ippery | +2.293 |
Discuss | +2.259 |
Split | +2.241 |
Neg logit contributions | |
expectations | -2.416 |
Wonderland | -2.308 |
Pepe | -2.256 |
UTERS | -2.226 |
gest | -2.178 |
Token | ook |
Token ID | 566 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
expectations | +0.958 |
Wonderland | +0.924 |
Pepe | +0.909 |
UTERS | +0.893 |
gest | +0.881 |
Neg logit contributions | |
Reviewed | -0.791 |
itaire | -0.628 |
ippery | -0.546 |
Discuss | -0.532 |
Split | -0.527 |
Token | ( |
Token ID | 357 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
expectations | +3.127 |
Pepe | +2.957 |
Wonderland | +2.944 |
gest | +2.833 |
Kardashian | +2.774 |
Neg logit contributions | |
Reviewed | -4.571 |
itaire | -3.879 |
Split | -3.400 |
ippery | -3.389 |
Gray | -3.286 |
Token | left |
Token ID | 9464 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
expectations | +5.923 |
Pepe | +5.721 |
gest | +5.707 |
Wonderland | +5.576 |
UTERS | +5.511 |
Neg logit contributions | |
Reviewed | -7.669 |
itaire | -6.604 |
ippery | -5.920 |
oun | -5.612 |
Discuss | -5.533 |
Token | ) |
Token ID | 8 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
expectations | +5.088 |
Pepe | +4.806 |
Wonderland | +4.384 |
gest | +4.354 |
UTERS | +4.239 |
Neg logit contributions | |
Reviewed | -13.725 |
itaire | -11.599 |
Discuss | -10.825 |
ippery | -10.793 |
Gray | -10.357 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
expectations | +2.925 |
Pepe | +2.772 |
Wonderland | +2.741 |
gest | +2.635 |
Kardashian | +2.590 |
Neg logit contributions | |
Reviewed | -4.027 |
itaire | -3.420 |
ippery | -3.012 |
Split | -2.995 |
Discuss | -2.889 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
expectations | +2.166 |
Pepe | +2.057 |
Wonderland | +2.035 |
gest | +1.952 |
UTERS | +1.941 |
Neg logit contributions | |
Reviewed | -2.709 |
itaire | -2.259 |
ippery | -1.997 |
Split | -1.948 |
Discuss | -1.938 |
Token | by |
Token ID | 416 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
expectations | +2.796 |
Pepe | +2.623 |
Wonderland | +2.612 |
Kardashian | +2.448 |
gest | +2.439 |
Neg logit contributions | |
Reviewed | -3.982 |
itaire | -3.347 |
ippery | -2.954 |
Split | -2.913 |
Gray | -2.892 |
Token | NBC |
Token ID | 9716 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Reviewed | +3.037 |
itaire | +2.546 |
ippery | +2.308 |
Discuss | +2.281 |
Split | +2.260 |
Neg logit contributions | |
expectations | -2.119 |
Wonderland | -2.013 |
Pepe | -1.971 |
UTERS | -1.938 |
gest | -1.898 |
Token | , |
Token ID | 11 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
expectations | +1.257 |
Wonderland | +1.172 |
Pepe | +1.153 |
gest | +1.081 |
UTERS | +1.075 |
Neg logit contributions | |
Reviewed | -2.632 |
itaire | -2.236 |
ippery | -2.049 |
Discuss | -2.027 |
Split | -2.008 |
Token | Qu |
Token ID | 2264 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
expectations | +2.427 |
Wonderland | +2.288 |
Pepe | +2.267 |
Kardashian | +2.114 |
UTERS | +2.098 |
Neg logit contributions | |
Reviewed | -3.330 |
itaire | -2.761 |
ippery | -2.453 |
Discuss | -2.442 |
Split | -2.412 |
Token | antic |
Token ID | 5109 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
expectations | +0.412 |
Wonderland | +0.393 |
Pepe | +0.389 |
UTERS | +0.383 |
gest | +0.379 |
Neg logit contributions | |
Reviewed | -0.387 |
itaire | -0.309 |
ippery | -0.268 |
Discuss | -0.265 |
Split | -0.263 |
Token | were |
Token ID | 547 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
expectations | +1.547 |
Wonderland | +1.469 |
Pepe | +1.440 |
UTERS | +1.408 |
gest | +1.367 |
Neg logit contributions | |
Reviewed | -1.869 |
itaire | -1.553 |
ippery | -1.383 |
Discuss | -1.360 |
Gray | -1.323 |
Token | also |
Token ID | 635 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
expectations | +0.150 |
Wonderland | +0.142 |
Pepe | +0.140 |
UTERS | +0.137 |
gest | +0.135 |
Neg logit contributions | |
Reviewed | -0.184 |
itaire | -0.152 |
ippery | -0.136 |
Discuss | -0.134 |
Split | -0.132 |
Token | late |
Token ID | 2739 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
expectations | +3.740 |
Wonderland | +3.465 |
Pepe | +3.414 |
gest | +3.265 |
UTERS | +3.252 |
Neg logit contributions | |
Reviewed | -5.083 |
itaire | -4.238 |
ippery | -3.810 |
Discuss | -3.756 |
Gray | -3.669 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
expectations | +8.903 |
Wonderland | +8.326 |
gest | +7.991 |
Pepe | +7.968 |
UTERS | +7.739 |
Neg logit contributions | |
Reviewed | -9.741 |
itaire | -8.019 |
Gray | -6.873 |
Discuss | -6.866 |
ippery | -6.825 |
Token | so |
Token ID | 523 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Reviewed | +1.096 |
itaire | +0.901 |
ippery | +0.801 |
Discuss | +0.789 |
Split | +0.780 |
Neg logit contributions | |
expectations | -0.952 |
Wonderland | -0.911 |
Pepe | -0.894 |
UTERS | -0.873 |
gest | -0.860 |
Token | I |
Token ID | 314 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Reviewed | +1.579 |
itaire | +1.307 |
ippery | +1.170 |
Discuss | +1.151 |
Split | +1.144 |
Neg logit contributions | |
expectations | -1.272 |
Wonderland | -1.216 |
Pepe | -1.192 |
UTERS | -1.170 |
gest | -1.150 |
Token | told |
Token ID | 1297 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
expectations | +0.242 |
Wonderland | +0.231 |
Pepe | +0.228 |
UTERS | +0.222 |
gest | +0.220 |
Neg logit contributions | |
Reviewed | -0.256 |
itaire | -0.208 |
ippery | -0.185 |
Discuss | -0.181 |
Split | -0.180 |
Token | them |
Token ID | 606 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Reviewed | +1.264 |
itaire | +1.062 |
ippery | +0.959 |
Discuss | +0.943 |
Split | +0.938 |
Neg logit contributions | |
expectations | -0.852 |
Wonderland | -0.808 |
Pepe | -0.793 |
UTERS | -0.768 |
gest | -0.755 |
Token | on |
Token ID | 261 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
expectations | +0.911 |
Wonderland | +0.873 |
Pepe | +0.863 |
gest | +0.831 |
UTERS | +0.825 |
Neg logit contributions | |
Reviewed | -0.894 |
itaire | -0.715 |
ippery | -0.646 |
Split | -0.626 |
Discuss | -0.625 |
Token | . |
Token ID | 13 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Reviewed | +2.399 |
itaire | +2.009 |
ippery | +1.813 |
Discuss | +1.784 |
Split | +1.777 |
Neg logit contributions | |
expectations | -1.707 |
Wonderland | -1.622 |
Pepe | -1.593 |
UTERS | -1.551 |
gest | -1.525 |
Token | The |
Token ID | 383 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
expectations | +0.356 |
Wonderland | +0.342 |
Pepe | +0.338 |
UTERS | +0.327 |
gest | +0.322 |
Neg logit contributions | |
Reviewed | -0.445 |
itaire | -0.369 |
ippery | -0.333 |
Discuss | -0.324 |
Split | -0.322 |
Token | deal |
Token ID | 1730 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
expectations | +1.137 |
Wonderland | +1.068 |
Pepe | +1.048 |
gest | +1.004 |
UTERS | +1.003 |
Neg logit contributions | |
Reviewed | -1.669 |
itaire | -1.398 |
ippery | -1.267 |
Discuss | -1.246 |
Split | -1.245 |
Token | behind |
Token ID | 2157 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
expectations | +1.331 |
Wonderland | +1.243 |
Pepe | +1.241 |
gest | +1.194 |
UTERS | +1.190 |
Neg logit contributions | |
Reviewed | -1.547 |
itaire | -1.270 |
ippery | -1.138 |
Discuss | -1.112 |
Split | -1.099 |
Token | Bour |
Token ID | 20576 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
expectations | +0.742 |
Wonderland | +0.704 |
Pepe | +0.694 |
UTERS | +0.672 |
gest | +0.664 |
Neg logit contributions | |
Reviewed | -0.933 |
itaire | -0.770 |
ippery | -0.695 |
Discuss | -0.680 |
Split | -0.675 |
Token | dain |
Token ID | 27162 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
expectations | +2.942 |
gest | +2.635 |
Pepe | +2.529 |
Wonderland | +2.432 |
Kardashian | +2.404 |
Neg logit contributions | |
Reviewed | -15.575 |
itaire | -13.691 |
oun | -13.083 |
ippery | -13.007 |
Split | -12.833 |
Token | Market |
Token ID | 5991 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
expectations | +6.088 |
Wonderland | +5.957 |
Pepe | +5.702 |
Kardashian | +5.372 |
gest | +5.195 |
Neg logit contributions | |
Reviewed | -9.239 |
itaire | -7.753 |
ippery | -7.118 |
Discuss | -6.817 |
Split | -6.772 |
Token | is |
Token ID | 318 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
expectations | +0.999 |
Wonderland | +0.941 |
Pepe | +0.928 |
UTERS | +0.897 |
gest | +0.891 |
Neg logit contributions | |
Reviewed | -1.270 |
itaire | -1.049 |
ippery | -0.952 |
Discuss | -0.924 |
Split | -0.914 |
Token | complicated |
Token ID | 8253 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Reviewed | +1.272 |
itaire | +1.047 |
ippery | +0.936 |
Discuss | +0.926 |
Split | +0.913 |
Neg logit contributions | |
expectations | -1.057 |
Wonderland | -1.006 |
Pepe | -0.991 |
UTERS | -0.964 |
gest | -0.956 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
expectations | +1.173 |
Wonderland | +1.098 |
Pepe | +1.078 |
UTERS | +1.034 |
gest | +1.032 |
Neg logit contributions | |
Reviewed | -1.924 |
itaire | -1.618 |
ippery | -1.480 |
Split | -1.452 |
Discuss | -1.451 |
Token | 's |
Token ID | 338 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
expectations | +2.240 |
Wonderland | +2.098 |
Pepe | +2.040 |
UTERS | +1.961 |
gest | +1.951 |
Neg logit contributions | |
Reviewed | -3.922 |
itaire | -3.366 |
ippery | -3.069 |
Gray | -2.982 |
Split | -2.952 |
Token | GU |
Token ID | 19348 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
expectations | +5.033 |
Wonderland | +4.663 |
Pepe | +4.444 |
gest | +4.348 |
Kardashian | +4.183 |
Neg logit contributions | |
Reviewed | -7.476 |
itaire | -6.511 |
ippery | -5.640 |
Registered | -5.543 |
Gray | -5.520 |
Token | ARD |
Token ID | 9795 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
expectations | +4.960 |
UTERS | +4.710 |
Wonderland | +4.697 |
Pepe | +4.664 |
gest | +4.577 |
Neg logit contributions | |
Reviewed | -3.927 |
itaire | -3.141 |
ippery | -2.596 |
Discuss | -2.446 |
Registered | -2.386 |
Token | I |
Token ID | 40 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
expectations | +2.562 |
Wonderland | +2.439 |
UTERS | +2.396 |
Pepe | +2.380 |
gest | +2.341 |
Neg logit contributions | |
Reviewed | -2.993 |
itaire | -2.414 |
ippery | -2.186 |
Discuss | -2.072 |
Gray | -2.036 |
Token | ANS |
Token ID | 15037 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Reviewed | +2.181 |
itaire | +1.854 |
ippery | +1.689 |
Discuss | +1.665 |
Split | +1.655 |
Neg logit contributions | |
expectations | -1.265 |
Wonderland | -1.196 |
Pepe | -1.168 |
UTERS | -1.142 |
gest | -1.113 |
Token | OF |
Token ID | 3963 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
expectations | +0.837 |
Wonderland | +0.780 |
Pepe | +0.734 |
UTERS | +0.731 |
QUEST | +0.703 |
Neg logit contributions | |
Reviewed | -1.601 |
itaire | -1.361 |
ippery | -1.250 |
Discuss | -1.218 |
Gray | -1.194 |
Token | THE |
Token ID | 3336 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Wonderland | +5.132 |
Pepe | +4.933 |
expectations | +4.790 |
UTERS | +4.694 |
QUEST | +4.458 |
Neg logit contributions | |
Reviewed | -14.159 |
itaire | -11.944 |
Discuss | -11.279 |
Registered | -11.183 |
ippery | -11.040 |
Token | G |
Token ID | 402 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
expectations | +4.433 |
Wonderland | +4.333 |
Pepe | +4.131 |
UTERS | +4.003 |
gest | +3.964 |
Neg logit contributions | |
Reviewed | -7.184 |
itaire | -6.011 |
Discuss | -5.508 |
ippery | -5.349 |
agy | -5.296 |
Token | AL |
Token ID | 1847 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Reviewed | +1.135 |
itaire | +0.906 |
ippery | +0.793 |
Split | +0.791 |
Discuss | +0.788 |
Neg logit contributions | |
expectations | -1.404 |
Pepe | -1.348 |
Wonderland | -1.346 |
gest | -1.287 |
Carbuncle | -1.285 |
Token | AX |
Token ID | 25922 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Reviewed | +0.730 |
itaire | +0.587 |
ippery | +0.515 |
Discuss | +0.511 |
Split | +0.507 |
Neg logit contributions | |
expectations | -0.764 |
Wonderland | -0.733 |
Pepe | -0.723 |
UTERS | -0.709 |
gest | -0.703 |
Token | Y |
Token ID | 56 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
expectations | +0.115 |
Wonderland | +0.110 |
Pepe | +0.108 |
UTERS | +0.106 |
gest | +0.105 |
Neg logit contributions | |
Reviewed | -0.121 |
itaire | -0.099 |
ippery | -0.087 |
Discuss | -0.086 |
Split | -0.086 |
Token | crowd |
Token ID | 4315 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
expectations | +3.409 |
Pepe | +3.177 |
gest | +3.127 |
Wonderland | +3.108 |
UTERS | +3.088 |
Neg logit contributions | |
Reviewed | -4.556 |
itaire | -3.747 |
ippery | -3.379 |
Discuss | -3.339 |
Gray | -3.266 |
Token | the |
Token ID | 262 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
expectations | +1.831 |
Wonderland | +1.684 |
Pepe | +1.663 |
UTERS | +1.619 |
gest | +1.585 |
Neg logit contributions | |
Reviewed | -2.770 |
itaire | -2.331 |
ippery | -2.122 |
Discuss | -2.116 |
Split | -2.088 |
Token | pan |
Token ID | 3425 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
expectations | +2.723 |
Pepe | +2.532 |
Wonderland | +2.475 |
UTERS | +2.373 |
gest | +2.372 |
Neg logit contributions | |
Reviewed | -4.167 |
itaire | -3.556 |
Discuss | -3.251 |
ippery | -3.230 |
Gray | -3.163 |
Token | ; |
Token ID | 26 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
expectations | +1.089 |
Wonderland | +1.003 |
Pepe | +0.983 |
UTERS | +0.964 |
gest | +0.946 |
Neg logit contributions | |
Reviewed | -1.907 |
itaire | -1.615 |
ippery | -1.474 |
Discuss | -1.466 |
Split | -1.453 |
Token | only |
Token ID | 691 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
expectations | +2.009 |
Pepe | +1.874 |
Wonderland | +1.874 |
gest | +1.808 |
UTERS | +1.805 |
Neg logit contributions | |
Reviewed | -2.528 |
itaire | -2.080 |
ippery | -1.872 |
Discuss | -1.857 |
Gray | -1.828 |
Token | cook |
Token ID | 4255 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
expectations | +1.720 |
Pepe | +1.606 |
Wonderland | +1.601 |
UTERS | +1.544 |
gest | +1.538 |
Neg logit contributions | |
Reviewed | -2.378 |
itaire | -1.960 |
ippery | -1.774 |
Discuss | -1.749 |
Split | -1.718 |
Token | about |
Token ID | 546 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
expectations | +7.257 |
Pepe | +6.773 |
Wonderland | +6.606 |
gest | +6.550 |
UTERS | +6.517 |
Neg logit contributions | |
Reviewed | -11.278 |
itaire | -9.226 |
Discuss | -8.563 |
ippery | -8.492 |
Gray | -8.445 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
expectations | +2.718 |
Wonderland | +2.516 |
Pepe | +2.496 |
gest | +2.431 |
UTERS | +2.360 |
Neg logit contributions | |
Reviewed | -3.829 |
itaire | -3.217 |
Discuss | -2.869 |
ippery | -2.831 |
Split | -2.811 |
Token | f |
Token ID | 277 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
expectations | +3.655 |
UTERS | +3.390 |
Pepe | +3.368 |
Wonderland | +3.363 |
gest | +3.250 |
Neg logit contributions | |
Reviewed | -5.474 |
itaire | -4.700 |
ippery | -4.167 |
Discuss | -4.166 |
Registered | -4.116 |
Token | rit |
Token ID | 799 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
expectations | +0.979 |
Pepe | +0.922 |
Wonderland | +0.920 |
UTERS | +0.907 |
gest | +0.895 |
Neg logit contributions | |
Reviewed | -1.226 |
itaire | -1.009 |
ippery | -0.907 |
Discuss | -0.891 |
Split | -0.883 |
Token | ters |
Token ID | 1010 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Reviewed | +1.428 |
itaire | +1.120 |
ippery | +0.926 |
Split | +0.915 |
Discuss | +0.888 |
Neg logit contributions | |
expectations | -2.139 |
Wonderland | -2.089 |
Pepe | -2.046 |
UTERS | -1.986 |
Carbuncle | -1.978 |
Token | so |
Token ID | 523 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
expectations | +0.996 |
Wonderland | +0.940 |
Pepe | +0.936 |
gest | +0.890 |
UTERS | +0.889 |
Neg logit contributions | |
Reviewed | -1.350 |
itaire | -1.122 |
ippery | -1.007 |
Discuss | -0.992 |
Split | -0.982 |
Token | vastly |
Token ID | 22056 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Reviewed | +1.722 |
itaire | +1.434 |
ippery | +1.289 |
Discuss | +1.268 |
Split | +1.262 |
Neg logit contributions | |
expectations | -1.295 |
Wonderland | -1.237 |
Pepe | -1.210 |
UTERS | -1.191 |
gest | -1.168 |
Token | different |
Token ID | 1180 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
expectations | +1.401 |
Wonderland | +1.304 |
Pepe | +1.286 |
UTERS | +1.241 |
gest | +1.237 |
Neg logit contributions | |
Reviewed | -2.089 |
itaire | -1.759 |
ippery | -1.590 |
Discuss | -1.553 |
Split | -1.541 |
Token | from |
Token ID | 422 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Reviewed | +2.720 |
itaire | +2.244 |
ippery | +2.022 |
Discuss | +1.985 |
Split | +1.978 |
Neg logit contributions | |
expectations | -2.166 |
Wonderland | -2.050 |
Pepe | -2.019 |
UTERS | -1.968 |
gest | -1.942 |
Token | his |
Token ID | 465 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
expectations | +0.452 |
Wonderland | +0.421 |
Pepe | +0.419 |
UTERS | +0.401 |
gest | +0.397 |
Neg logit contributions | |
Reviewed | -0.622 |
itaire | -0.516 |
ippery | -0.468 |
Split | -0.459 |
Discuss | -0.458 |
Token | or |
Token ID | 393 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Reviewed | +0.796 |
itaire | +0.661 |
ippery | +0.596 |
Discuss | +0.583 |
Split | +0.581 |
Neg logit contributions | |
expectations | -0.619 |
Wonderland | -0.581 |
Pepe | -0.574 |
UTERS | -0.557 |
gest | -0.550 |
Token | her |
Token ID | 607 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
expectations | +5.572 |
Wonderland | +5.257 |
Pepe | +5.170 |
Kardashian | +4.852 |
gest | +4.626 |
Neg logit contributions | |
Reviewed | -13.608 |
itaire | -11.461 |
ippery | -10.716 |
Discuss | -10.402 |
Split | -10.376 |
Token | offline |
Token ID | 18043 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Reviewed | +0.488 |
itaire | +0.407 |
ippery | +0.368 |
Discuss | +0.361 |
Split | +0.360 |
Neg logit contributions | |
expectations | -0.347 |
Wonderland | -0.326 |
Pepe | -0.321 |
UTERS | -0.312 |
gest | -0.308 |
Token | persona |
Token ID | 27822 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
expectations | +0.671 |
Wonderland | +0.532 |
Pepe | +0.527 |
persona | +0.456 |
UTERS | +0.455 |
Neg logit contributions | |
Reviewed | -3.603 |
itaire | -3.192 |
ippery | -3.010 |
Split | -2.946 |
Discuss | -2.940 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
expectations | +0.528 |
Wonderland | +0.477 |
Pepe | +0.473 |
UTERS | +0.453 |
gest | +0.448 |
Neg logit contributions | |
Reviewed | -1.015 |
itaire | -0.856 |
ippery | -0.796 |
Split | -0.779 |
Gray | -0.773 |
Token | it |
Token ID | 340 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
expectations | +0.619 |
Wonderland | +0.580 |
Pepe | +0.574 |
UTERS | +0.551 |
gest | +0.545 |
Neg logit contributions | |
Reviewed | -0.770 |
itaire | -0.637 |
ippery | -0.572 |
Discuss | -0.562 |
Split | -0.558 |
Token | failed |
Token ID | 4054 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
expectations | +3.264 |
Wonderland | +3.042 |
Pepe | +3.002 |
gest | +2.924 |
Kardashian | +2.852 |
Neg logit contributions | |
Reviewed | -4.175 |
itaire | -3.510 |
ippery | -3.084 |
Split | -3.022 |
Discuss | -3.018 |
Token | ! |
Token ID | 0 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
expectations | +4.923 |
Wonderland | +4.637 |
Pepe | +4.550 |
UTERS | +4.444 |
gest | +4.435 |
Neg logit contributions | |
Reviewed | -4.241 |
itaire | -3.348 |
ippery | -2.904 |
Gray | -2.868 |
Split | -2.847 |
Token | That |
Token ID | 1320 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
expectations | +1.604 |
Wonderland | +1.519 |
Pepe | +1.475 |
UTERS | +1.443 |
gest | +1.423 |
Neg logit contributions | |
Reviewed | -2.314 |
itaire | -1.947 |
ippery | -1.751 |
Split | -1.715 |
Discuss | -1.702 |
Token | should |
Token ID | 815 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
expectations | +1.763 |
Wonderland | +1.647 |
Pepe | +1.612 |
gest | +1.567 |
UTERS | +1.544 |
Neg logit contributions | |
Reviewed | -2.303 |
itaire | -1.936 |
ippery | -1.730 |
Discuss | -1.688 |
Split | -1.686 |
Token | NEVER |
Token ID | 33602 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
expectations | +1.673 |
Wonderland | +1.544 |
Pepe | +1.536 |
UTERS | +1.499 |
gest | +1.491 |
Neg logit contributions | |
Reviewed | -2.588 |
itaire | -2.180 |
ippery | -1.977 |
Gray | -1.911 |
Split | -1.908 |
Token | have |
Token ID | 423 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
expectations | +4.558 |
Wonderland | +4.253 |
Pepe | +4.242 |
UTERS | +4.085 |
gest | +4.053 |
Neg logit contributions | |
Reviewed | -6.821 |
itaire | -5.703 |
ippery | -5.137 |
Split | -5.000 |
Gray | -4.856 |
Token | happened |
Token ID | 3022 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
expectations | +8.055 |
gest | +7.287 |
Pepe | +7.209 |
Wonderland | +7.045 |
UTERS | +6.925 |
Neg logit contributions | |
Reviewed | -9.950 |
itaire | -8.718 |
ippery | -7.375 |
Split | -7.236 |
Gray | -7.234 |
Token | ! |
Token ID | 0 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
expectations | +3.282 |
Wonderland | +3.074 |
Pepe | +2.959 |
UTERS | +2.906 |
gest | +2.879 |
Neg logit contributions | |
Reviewed | -5.674 |
itaire | -4.810 |
ippery | -4.333 |
Split | -4.277 |
Gray | -4.234 |
Token | � |
Token ID | 447 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
expectations | +1.676 |
Wonderland | +1.588 |
Pepe | +1.543 |
UTERS | +1.509 |
gest | +1.475 |
Neg logit contributions | |
Reviewed | -2.669 |
itaire | -2.260 |
ippery | -2.050 |
Split | -2.001 |
Discuss | -1.985 |
Token | � |
Token ID | 251 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
expectations | +0.646 |
Wonderland | +0.612 |
Pepe | +0.607 |
UTERS | +0.593 |
gest | +0.579 |
Neg logit contributions | |
Reviewed | -0.877 |
itaire | -0.739 |
ippery | -0.665 |
Discuss | -0.647 |
Split | -0.646 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
expectations | +0.721 |
Wonderland | +0.673 |
Pepe | +0.660 |
UTERS | +0.651 |
gest | +0.630 |
Neg logit contributions | |
Reviewed | -1.315 |
itaire | -1.128 |
ippery | -1.030 |
Split | -1.006 |
Gray | -1.000 |
Token | a |
Token ID | 257 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
expectations | +4.747 |
Wonderland | +4.430 |
Pepe | +4.358 |
gest | +4.063 |
UTERS | +4.031 |
Neg logit contributions | |
Reviewed | -7.821 |
itaire | -6.711 |
Discuss | -5.994 |
ippery | -5.983 |
Split | -5.885 |
Token | tablespoon |
Token ID | 33107 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
expectations | +4.076 |
Pepe | +3.929 |
Wonderland | +3.859 |
gest | +3.653 |
cher | +3.629 |
Neg logit contributions | |
Reviewed | -7.664 |
itaire | -6.616 |
ippery | -6.004 |
Discuss | -5.956 |
Split | -5.846 |
Token | coconut |
Token ID | 20132 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
expectations | +2.541 |
Pepe | +2.356 |
Wonderland | +2.329 |
UTERS | +2.204 |
Kardashian | +2.190 |
Neg logit contributions | |
Reviewed | -5.200 |
itaire | -4.473 |
Discuss | -4.045 |
ippery | -4.040 |
Gray | -3.955 |
Token | oil |
Token ID | 3056 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
expectations | +1.717 |
Wonderland | +1.605 |
Pepe | +1.578 |
UTERS | +1.480 |
gest | +1.479 |
Neg logit contributions | |
Reviewed | -3.417 |
itaire | -2.920 |
ippery | -2.679 |
Discuss | -2.663 |
Gray | -2.648 |
Token | and |
Token ID | 290 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
expectations | +1.355 |
Wonderland | +1.255 |
Pepe | +1.233 |
UTERS | +1.190 |
gest | +1.190 |
Neg logit contributions | |
Reviewed | -2.508 |
itaire | -2.140 |
ippery | -1.954 |
Discuss | -1.952 |
Gray | -1.924 |
Token | fry |
Token ID | 32959 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
expectations | +2.471 |
Wonderland | +2.303 |
Pepe | +2.291 |
gest | +2.191 |
UTERS | +2.143 |
Neg logit contributions | |
Reviewed | -3.828 |
itaire | -3.204 |
Discuss | -2.867 |
ippery | -2.856 |
Gray | -2.815 |
Token | until |
Token ID | 1566 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
expectations | +7.635 |
Wonderland | +7.012 |
Pepe | +6.998 |
cher | +6.686 |
UTERS | +6.579 |
Neg logit contributions | |
Reviewed | -10.353 |
itaire | -8.176 |
Discuss | -7.740 |
ippery | -7.643 |
Registered | -7.623 |
Token | carrots |
Token ID | 34397 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
expectations | +4.884 |
Pepe | +4.600 |
Wonderland | +4.596 |
cher | +4.318 |
lent | +4.289 |
Neg logit contributions | |
Reviewed | -6.695 |
itaire | -5.611 |
Discuss | -5.166 |
ippery | -5.082 |
Split | -5.012 |
Token | are |
Token ID | 389 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
expectations | +0.342 |
Wonderland | +0.320 |
Pepe | +0.316 |
UTERS | +0.304 |
gest | +0.304 |
Neg logit contributions | |
Reviewed | -0.544 |
itaire | -0.459 |
ippery | -0.415 |
Discuss | -0.409 |
Split | -0.404 |
Token | soft |
Token ID | 2705 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Reviewed | +1.265 |
itaire | +1.057 |
ippery | +0.943 |
Discuss | +0.934 |
Split | +0.924 |
Neg logit contributions | |
expectations | -0.964 |
Wonderland | -0.920 |
Pepe | -0.904 |
UTERS | -0.877 |
gest | -0.869 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
expectations | +2.319 |
Pepe | +2.151 |
Wonderland | +2.138 |
gest | +2.098 |
UTERS | +2.039 |
Neg logit contributions | |
Reviewed | -4.469 |
itaire | -3.844 |
Discuss | -3.481 |
ippery | -3.470 |
Split | -3.449 |
Token | Wooden |
Token ID | 40143 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Reviewed | +0.198 |
itaire | +0.165 |
ippery | +0.149 |
Discuss | +0.147 |
Split | +0.146 |
Neg logit contributions | |
expectations | -0.145 |
Wonderland | -0.138 |
Pepe | -0.135 |
UTERS | -0.133 |
gest | -0.130 |
Token | Award |
Token ID | 11289 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
expectations | +2.162 |
Wonderland | +1.994 |
Pepe | +1.968 |
gest | +1.894 |
UTERS | +1.867 |
Neg logit contributions | |
Reviewed | -3.971 |
itaire | -3.416 |
ippery | -3.114 |
Discuss | -3.070 |
Gray | -3.049 |
Token | voting |
Token ID | 6709 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Reviewed | +2.772 |
itaire | +2.306 |
ippery | +2.081 |
Split | +2.052 |
Discuss | +2.047 |
Neg logit contributions | |
expectations | -2.024 |
Wonderland | -1.946 |
Pepe | -1.915 |
UTERS | -1.878 |
gest | -1.834 |
Token | ( |
Token ID | 357 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
Reviewed | +0.417 |
itaire | +0.353 |
ippery | +0.319 |
Discuss | +0.314 |
Split | +0.310 |
Neg logit contributions | |
expectations | -0.274 |
Wonderland | -0.258 |
Pepe | -0.252 |
UTERS | -0.247 |
gest | -0.243 |
Token | 33 |
Token ID | 2091 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
Reviewed | +0.500 |
itaire | +0.411 |
ippery | +0.365 |
Discuss | +0.356 |
Split | +0.352 |
Neg logit contributions | |
expectations | -0.456 |
Wonderland | -0.435 |
Pepe | -0.427 |
UTERS | -0.421 |
gest | -0.417 |
Token | 85 |
Token ID | 5332 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
expectations | +4.420 |
Wonderland | +3.977 |
UTERS | +3.928 |
Pepe | +3.862 |
gest | +3.829 |
Neg logit contributions | |
Reviewed | -6.502 |
itaire | -5.511 |
ippery | -5.000 |
Discuss | -4.922 |
Gray | -4.851 |
Token | – |
Token ID | 1906 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
expectations | +7.023 |
Wonderland | +6.183 |
UTERS | +6.145 |
Pepe | +6.128 |
gest | +5.962 |
Neg logit contributions | |
Reviewed | -10.718 |
itaire | -9.334 |
ippery | -8.639 |
Discuss | -8.410 |
Gray | -8.199 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
expectations | +2.177 |
Wonderland | +2.062 |
Pepe | +2.033 |
gest | +2.007 |
UTERS | +1.985 |
Neg logit contributions | |
Reviewed | -2.836 |
itaire | -2.393 |
ippery | -2.162 |
Discuss | -2.060 |
Split | -2.036 |
Token | 60 |
Token ID | 1899 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
expectations | +1.391 |
Wonderland | +1.322 |
Pepe | +1.299 |
UTERS | +1.269 |
gest | +1.253 |
Neg logit contributions | |
Reviewed | -1.761 |
itaire | -1.461 |
ippery | -1.315 |
Discuss | -1.285 |
Split | -1.271 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
expectations | +1.540 |
Wonderland | +1.361 |
Pepe | +1.343 |
UTERS | +1.320 |
gest | +1.262 |
Neg logit contributions | |
Reviewed | -3.560 |
itaire | -3.078 |
ippery | -2.865 |
Discuss | -2.794 |
Gray | -2.764 |
Token | 126 |
Token ID | 19420 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Reviewed | +1.136 |
itaire | +0.970 |
ippery | +0.883 |
Discuss | +0.858 |
Gray | +0.850 |
Neg logit contributions | |
expectations | -0.709 |
Wonderland | -0.658 |
Pepe | -0.649 |
UTERS | -0.646 |
gest | -0.635 |
Token | J |
Token ID | 449 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Reviewed | +0.138 |
itaire | +0.118 |
ippery | +0.107 |
Discuss | +0.105 |
Split | +0.105 |
Neg logit contributions | |
expectations | -0.080 |
Wonderland | -0.074 |
Pepe | -0.073 |
UTERS | -0.070 |
gest | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
Reviewed | +0.209 |
itaire | +0.173 |
ippery | +0.156 |
Discuss | +0.154 |
Split | +0.153 |
Neg logit contributions | |
expectations | -0.167 |
Wonderland | -0.160 |
Pepe | -0.156 |
UTERS | -0.154 |
gest | -0.151 |
Token | R |
Token ID | 49 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Reviewed | +0.073 |
itaire | +0.060 |
Discuss | +0.053 |
Split | +0.053 |
ippery | +0.053 |
Neg logit contributions | |
expectations | -0.064 |
Wonderland | -0.061 |
Pepe | -0.060 |
UTERS | -0.059 |
gest | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Reviewed | +2.124 |
itaire | +1.726 |
Discuss | +1.560 |
Split | +1.543 |
Gray | +1.542 |
Neg logit contributions | |
expectations | -1.920 |
Wonderland | -1.835 |
UTERS | -1.783 |
Pepe | -1.783 |
gest | -1.729 |
Token | Smith |
Token ID | 4176 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Reviewed | +1.982 |
itaire | +1.425 |
Split | +1.210 |
Discuss | +1.200 |
Gray | +1.200 |
Neg logit contributions | |
expectations | -3.646 |
Wonderland | -3.552 |
UTERS | -3.480 |
Pepe | -3.458 |
gest | -3.423 |
Token | ( |
Token ID | 357 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
expectations | +1.016 |
Pepe | +0.936 |
Wonderland | +0.934 |
UTERS | +0.917 |
gest | +0.893 |
Neg logit contributions | |
Reviewed | -1.521 |
itaire | -1.273 |
ippery | -1.143 |
Split | -1.125 |
Discuss | -1.117 |
Token | 5 |
Token ID | 20 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
expectations | +7.264 |
gest | +6.857 |
UTERS | +6.816 |
Pepe | +6.711 |
Wonderland | +6.550 |
Neg logit contributions | |
Reviewed | -10.219 |
itaire | -9.009 |
ippery | -8.271 |
oun | -8.009 |
paio | -7.487 |
Token | ) |
Token ID | 8 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
expectations | +2.559 |
Wonderland | +2.267 |
UTERS | +2.251 |
Pepe | +2.245 |
gest | +2.127 |
Neg logit contributions | |
Reviewed | -6.055 |
itaire | -5.292 |
ippery | -4.906 |
Discuss | -4.797 |
Split | -4.722 |
Token | after |
Token ID | 706 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
expectations | +2.527 |
Pepe | +2.315 |
Wonderland | +2.275 |
UTERS | +2.252 |
Kardashian | +2.195 |
Neg logit contributions | |
Reviewed | -3.703 |
itaire | -3.109 |
ippery | -2.782 |
Split | -2.724 |
Discuss | -2.702 |
Token | Smith |
Token ID | 4176 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Reviewed | +1.369 |
itaire | +1.125 |
ippery | +0.992 |
Discuss | +0.968 |
Split | +0.961 |
Neg logit contributions | |
expectations | -1.287 |
Wonderland | -1.220 |
Pepe | -1.209 |
UTERS | -1.173 |
gest | -1.162 |
Token | 's |
Token ID | 338 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
expectations | +2.426 |
Pepe | +2.275 |
Wonderland | +2.260 |
UTERS | +2.169 |
gest | +2.169 |
Neg logit contributions | |
Reviewed | -2.872 |
itaire | -2.420 |
ippery | -2.132 |
Discuss | -2.082 |
Split | -2.028 |
Token | CLASS |
Token ID | 31631 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
expectations | +0.462 |
Wonderland | +0.437 |
Pepe | +0.430 |
UTERS | +0.426 |
gest | +0.419 |
Neg logit contributions | |
Reviewed | -0.643 |
itaire | -0.545 |
ippery | -0.490 |
Discuss | -0.476 |
Split | -0.469 |
Token | _ |
Token ID | 62 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Reviewed | +0.427 |
itaire | +0.353 |
ippery | +0.314 |
Discuss | +0.309 |
Split | +0.305 |
Neg logit contributions | |
expectations | -0.359 |
Wonderland | -0.342 |
Pepe | -0.335 |
UTERS | -0.330 |
gest | -0.324 |
Token | ST |
Token ID | 2257 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
expectations | +0.614 |
Wonderland | +0.578 |
Pepe | +0.570 |
UTERS | +0.567 |
gest | +0.554 |
Neg logit contributions | |
Reviewed | -0.859 |
itaire | -0.729 |
ippery | -0.658 |
Discuss | -0.636 |
Split | -0.626 |
Token | ART |
Token ID | 7227 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
Reviewed | +0.747 |
itaire | +0.626 |
ippery | +0.566 |
Discuss | +0.554 |
Split | +0.550 |
Neg logit contributions | |
expectations | -0.531 |
Wonderland | -0.505 |
Pepe | -0.495 |
UTERS | -0.487 |
gest | -0.475 |
Token | ( |
Token ID | 7 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
expectations | +0.379 |
Wonderland | +0.363 |
Pepe | +0.355 |
UTERS | +0.350 |
gest | +0.342 |
Neg logit contributions | |
Reviewed | -0.457 |
itaire | -0.380 |
ippery | -0.338 |
Discuss | -0.332 |
Split | -0.326 |
Token | mem |
Token ID | 11883 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
expectations | +2.828 |
Wonderland | +2.665 |
Pepe | +2.635 |
gest | +2.623 |
UTERS | +2.590 |
Neg logit contributions | |
Reviewed | -3.802 |
itaire | -3.243 |
ippery | -2.890 |
Discuss | -2.829 |
Gray | -2.739 |
Token | c |
Token ID | 66 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
expectations | +6.131 |
gest | +5.832 |
Pepe | +5.674 |
UTERS | +5.347 |
Wonderland | +5.285 |
Neg logit contributions | |
Reviewed | -11.256 |
itaire | -9.701 |
ippery | -8.808 |
Discuss | -8.795 |
Gray | -8.595 |
Token | py |
Token ID | 9078 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
expectations | +1.752 |
Wonderland | +1.652 |
Pepe | +1.618 |
UTERS | +1.577 |
gest | +1.547 |
Neg logit contributions | |
Reviewed | -3.146 |
itaire | -2.673 |
ippery | -2.438 |
Discuss | -2.407 |
Split | -2.393 |
Token | _ |
Token ID | 62 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
expectations | +3.013 |
Wonderland | +2.768 |
gest | +2.765 |
Pepe | +2.763 |
UTERS | +2.745 |
Neg logit contributions | |
Reviewed | -3.861 |
itaire | -3.327 |
ippery | -2.933 |
Discuss | -2.844 |
Gray | -2.774 |
Token | speed |
Token ID | 12287 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
expectations | +2.252 |
gest | +2.128 |
Pepe | +2.103 |
Wonderland | +2.086 |
UTERS | +2.042 |
Neg logit contributions | |
Reviewed | -2.782 |
itaire | -2.347 |
ippery | -2.070 |
Discuss | -2.030 |
Gray | -1.997 |
Token | _ |
Token ID | 62 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
expectations | +2.050 |
Wonderland | +1.877 |
Pepe | +1.870 |
gest | +1.858 |
UTERS | +1.821 |
Neg logit contributions | |
Reviewed | -3.184 |
itaire | -2.706 |
ippery | -2.453 |
Discuss | -2.406 |
Gray | -2.348 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Reviewed | +3.644 |
itaire | +3.048 |
ippery | +2.738 |
Discuss | +2.699 |
Split | +2.683 |
Neg logit contributions | |
expectations | -2.720 |
Wonderland | -2.624 |
Pepe | -2.575 |
UTERS | -2.536 |
gest | -2.482 |
Token | relationship |
Token ID | 2776 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Reviewed | +2.908 |
itaire | +2.415 |
ippery | +2.166 |
Discuss | +2.131 |
Split | +2.118 |
Neg logit contributions | |
expectations | -2.294 |
Wonderland | -2.200 |
Pepe | -2.160 |
UTERS | -2.127 |
gest | -2.081 |
Token | in |
Token ID | 287 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Reviewed | +4.460 |
itaire | +3.625 |
ippery | +3.224 |
Discuss | +3.179 |
Split | +3.170 |
Neg logit contributions | |
expectations | -4.158 |
Wonderland | -4.068 |
Pepe | -3.977 |
UTERS | -3.972 |
gest | -3.877 |
Token | light |
Token ID | 1657 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Reviewed | +3.138 |
itaire | +2.621 |
ippery | +2.362 |
Discuss | +2.325 |
Split | +2.312 |
Neg logit contributions | |
expectations | -2.274 |
Wonderland | -2.167 |
Pepe | -2.123 |
UTERS | -2.081 |
gest | -2.042 |
Token | of |
Token ID | 286 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Reviewed | +3.597 |
itaire | +2.908 |
Discuss | +2.717 |
Split | +2.684 |
Gray | +2.655 |
Neg logit contributions | |
expectations | -3.029 |
Wonderland | -2.978 |
UTERS | -2.909 |
Pepe | -2.897 |
geries | -2.837 |
Token | moves |
Token ID | 6100 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
expectations | +1.144 |
Wonderland | +1.036 |
Pepe | +1.030 |
UTERS | +0.969 |
gest | +0.960 |
Neg logit contributions | |
Reviewed | -1.616 |
itaire | -1.355 |
ippery | -1.203 |
Split | -1.181 |
Discuss | -1.179 |
Token | towards |
Token ID | 3371 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
expectations | +8.257 |
Wonderland | +7.302 |
Pepe | +7.234 |
Kardashian | +6.949 |
UTERS | +6.902 |
Neg logit contributions | |
Reviewed | -9.993 |
itaire | -8.446 |
ippery | -7.534 |
Registered | -7.391 |
Gray | -7.372 |
Token | further |
Token ID | 2252 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
expectations | +1.322 |
Wonderland | +1.209 |
Pepe | +1.196 |
UTERS | +1.168 |
gest | +1.138 |
Neg logit contributions | |
Reviewed | -1.752 |
itaire | -1.425 |
ippery | -1.282 |
Discuss | -1.255 |
Gray | -1.249 |
Token | integration |
Token ID | 11812 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
expectations | +1.994 |
Wonderland | +1.793 |
UTERS | +1.747 |
Pepe | +1.746 |
Kardashian | +1.671 |
Neg logit contributions | |
Reviewed | -2.993 |
itaire | -2.502 |
ippery | -2.269 |
Gray | -2.222 |
Discuss | -2.203 |
Token | by |
Token ID | 416 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
expectations | +0.351 |
Wonderland | +0.327 |
Pepe | +0.320 |
UTERS | +0.313 |
gest | +0.304 |
Neg logit contributions | |
Reviewed | -0.519 |
itaire | -0.437 |
ippery | -0.399 |
Discuss | -0.389 |
Split | -0.387 |
Token | countries |
Token ID | 2678 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Reviewed | +0.586 |
itaire | +0.490 |
ippery | +0.442 |
Discuss | +0.435 |
Split | +0.433 |
Neg logit contributions | |
expectations | -0.379 |
Wonderland | -0.352 |
Pepe | -0.347 |
UTERS | -0.336 |
gest | -0.330 |
Token | pic |
Token ID | 8301 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
expectations | +3.355 |
Pepe | +3.119 |
Wonderland | +3.103 |
UTERS | +3.002 |
gest | +2.976 |
Neg logit contributions | |
Reviewed | -5.675 |
itaire | -4.798 |
ippery | -4.369 |
Split | -4.194 |
Gray | -4.180 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
expectations | +3.758 |
Pepe | +3.580 |
Wonderland | +3.575 |
UTERS | +3.436 |
gest | +3.417 |
Neg logit contributions | |
Reviewed | -6.298 |
itaire | -5.464 |
ippery | -4.971 |
oun | -4.971 |
Split | -4.702 |
Token | twitter |
Token ID | 6956 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
expectations | +1.066 |
Wonderland | +1.013 |
Pepe | +0.981 |
UTERS | +0.959 |
gest | +0.933 |
Neg logit contributions | |
Reviewed | -1.739 |
itaire | -1.464 |
ippery | -1.334 |
Discuss | -1.323 |
Split | -1.314 |
Token | . |
Token ID | 13 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
expectations | +1.358 |
Wonderland | +1.297 |
Pepe | +1.268 |
UTERS | +1.244 |
gest | +1.219 |
Neg logit contributions | |
Reviewed | -1.760 |
itaire | -1.459 |
ippery | -1.309 |
Discuss | -1.296 |
Split | -1.287 |
Token | com |
Token ID | 785 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
expectations | +1.746 |
Wonderland | +1.601 |
Pepe | +1.576 |
UTERS | +1.514 |
gest | +1.488 |
Neg logit contributions | |
Reviewed | -4.940 |
itaire | -4.313 |
ippery | -3.990 |
Discuss | -3.917 |
Split | -3.904 |
Token | / |
Token ID | 14 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
expectations | +2.875 |
Wonderland | +2.733 |
Pepe | +2.716 |
UTERS | +2.656 |
gest | +2.620 |
Neg logit contributions | |
Reviewed | -4.391 |
itaire | -3.763 |
ippery | -3.394 |
oun | -3.321 |
Discuss | -3.251 |
Token | W |
Token ID | 54 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
expectations | +7.246 |
gest | +7.132 |
UTERS | +6.978 |
Pepe | +6.797 |
sbm | +6.793 |
Neg logit contributions | |
Reviewed | -9.788 |
itaire | -8.113 |
ippery | -7.129 |
oun | -7.043 |
Discuss | -6.968 |
Token | 8 |
Token ID | 23 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
expectations | +1.261 |
Wonderland | +1.195 |
Pepe | +1.181 |
UTERS | +1.170 |
gest | +1.161 |
Neg logit contributions | |
Reviewed | -1.605 |
itaire | -1.330 |
ippery | -1.187 |
Discuss | -1.166 |
Split | -1.153 |
Token | v |
Token ID | 85 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
expectations | +3.108 |
Wonderland | +2.938 |
UTERS | +2.916 |
Pepe | +2.910 |
gest | +2.900 |
Neg logit contributions | |
Reviewed | -3.964 |
itaire | -3.296 |
ippery | -2.907 |
Discuss | -2.848 |
Split | -2.814 |
Token | X |
Token ID | 55 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
expectations | +2.335 |
Wonderland | +2.219 |
Pepe | +2.197 |
UTERS | +2.187 |
gest | +2.173 |
Neg logit contributions | |
Reviewed | -2.896 |
itaire | -2.394 |
ippery | -2.123 |
Discuss | -2.085 |
Split | -2.053 |
Token | Ds |
Token ID | 30832 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
expectations | +2.658 |
Wonderland | +2.513 |
Pepe | +2.489 |
UTERS | +2.482 |
gest | +2.477 |
Neg logit contributions | |
Reviewed | -3.413 |
itaire | -2.835 |
ippery | -2.511 |
Discuss | -2.462 |
Split | -2.430 |
Token | hin |
Token ID | 20079 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
expectations | +1.547 |
Wonderland | +1.461 |
Pepe | +1.428 |
gest | +1.411 |
UTERS | +1.365 |
Neg logit contributions | |
Reviewed | -2.160 |
itaire | -1.803 |
ippery | -1.610 |
Split | -1.589 |
Discuss | -1.589 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
expectations | +3.707 |
Wonderland | +3.484 |
Pepe | +3.469 |
Kardashian | +3.289 |
gest | +3.212 |
Neg logit contributions | |
Reviewed | -6.963 |
itaire | -5.966 |
ippery | -5.364 |
Discuss | -5.248 |
Split | -5.233 |
Token | Sean |
Token ID | 11465 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
expectations | +2.470 |
Wonderland | +2.345 |
Pepe | +2.339 |
UTERS | +2.173 |
Kardashian | +2.149 |
Neg logit contributions | |
Reviewed | -3.143 |
itaire | -2.669 |
ippery | -2.309 |
Discuss | -2.303 |
Split | -2.269 |
Token | F |
Token ID | 376 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Reviewed | +0.974 |
itaire | +0.802 |
ippery | +0.712 |
Discuss | +0.701 |
Split | +0.697 |
Neg logit contributions | |
expectations | -0.804 |
Wonderland | -0.771 |
Pepe | -0.761 |
UTERS | -0.735 |
gest | -0.727 |
Token | agan |
Token ID | 7329 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
expectations | +1.250 |
Wonderland | +1.199 |
Pepe | +1.182 |
UTERS | +1.150 |
gest | +1.143 |
Neg logit contributions | |
Reviewed | -1.456 |
itaire | -1.175 |
ippery | -1.039 |
Discuss | -1.037 |
Split | -1.033 |
Token | for |
Token ID | 329 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Reviewed | +0.036 |
itaire | +0.030 |
ippery | +0.027 |
Discuss | +0.027 |
Split | +0.027 |
Neg logit contributions | |
expectations | -0.022 |
Wonderland | -0.021 |
Pepe | -0.021 |
UTERS | -0.020 |
gest | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
expectations | +7.069 |
Wonderland | +6.655 |
Pepe | +6.368 |
modeling | +6.027 |
complicity | +6.021 |
Neg logit contributions | |
Reviewed | -10.712 |
itaire | -9.437 |
ippery | -8.297 |
Gray | -8.094 |
Split | -8.041 |
Token | support |
Token ID | 1104 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
expectations | +5.197 |
Wonderland | +4.803 |
Pepe | +4.581 |
complicity | +4.413 |
gest | +4.405 |
Neg logit contributions | |
Reviewed | -7.695 |
itaire | -6.492 |
ippery | -5.787 |
Split | -5.666 |
Gray | -5.666 |
Token | of |
Token ID | 286 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
expectations | +0.818 |
Wonderland | +0.762 |
Pepe | +0.748 |
UTERS | +0.725 |
gest | +0.718 |
Neg logit contributions | |
Reviewed | -1.342 |
itaire | -1.138 |
ippery | -1.036 |
Discuss | -1.014 |
Split | -1.010 |
Token | 8 |
Token ID | 807 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Reviewed | +0.129 |
itaire | +0.109 |
ippery | +0.097 |
Discuss | +0.095 |
Split | +0.094 |
Neg logit contributions | |
expectations | -0.089 |
Wonderland | -0.084 |
Pepe | -0.083 |
UTERS | -0.079 |
gest | -0.079 |
Token | lim |
Token ID | 2475 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
expectations | +1.245 |
Wonderland | +1.189 |
Pepe | +1.161 |
UTERS | +1.124 |
gest | +1.123 |
Neg logit contributions | |
Reviewed | -1.539 |
itaire | -1.300 |
ippery | -1.145 |
Discuss | -1.122 |
Gray | -1.104 |
Token | 23 |
Token ID | 1954 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
expectations | +1.271 |
Wonderland | +1.215 |
Pepe | +1.192 |
UTERS | +1.177 |
gest | +1.163 |
Neg logit contributions | |
Reviewed | -1.598 |
itaire | -1.331 |
ippery | -1.198 |
Discuss | -1.161 |
Split | -1.150 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
expectations | +1.444 |
Wonderland | +1.375 |
Pepe | +1.350 |
UTERS | +1.332 |
gest | +1.324 |
Neg logit contributions | |
Reviewed | -1.845 |
itaire | -1.543 |
ippery | -1.390 |
Discuss | -1.342 |
Split | -1.340 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Reviewed | +1.321 |
itaire | +1.056 |
Discuss | +0.955 |
Split | +0.940 |
ippery | +0.937 |
Neg logit contributions | |
expectations | -1.228 |
Wonderland | -1.172 |
Pepe | -1.146 |
UTERS | -1.127 |
gest | -1.100 |
Token | e |
Token ID | 68 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
expectations | +0.337 |
Wonderland | +0.324 |
Pepe | +0.315 |
UTERS | +0.310 |
gest | +0.302 |
Neg logit contributions | |
Reviewed | -0.414 |
itaire | -0.340 |
ippery | -0.306 |
Discuss | -0.300 |
Gray | -0.299 |
Token | ce |
Token ID | 344 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
expectations | +0.549 |
Wonderland | +0.518 |
Pepe | +0.504 |
UTERS | +0.491 |
gest | +0.478 |
Neg logit contributions | |
Reviewed | -1.057 |
itaire | -0.906 |
ippery | -0.829 |
Discuss | -0.817 |
Split | -0.817 |
Token | / |
Token ID | 14 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
expectations | +0.611 |
Wonderland | +0.581 |
Pepe | +0.568 |
UTERS | +0.560 |
gest | +0.547 |
Neg logit contributions | |
Reviewed | -0.834 |
itaire | -0.699 |
ippery | -0.628 |
Discuss | -0.617 |
Split | -0.612 |
Token | edd |
Token ID | 6048 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
expectations | +6.908 |
gest | +6.676 |
arent | +6.401 |
sbm | +6.355 |
aspberry | +6.293 |
Neg logit contributions | |
Reviewed | -10.512 |
itaire | -8.705 |
oun | -7.839 |
Discuss | -7.740 |
ippery | -7.665 |
Token | 75 |
Token ID | 2425 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Reviewed | +1.128 |
itaire | +0.934 |
ippery | +0.838 |
Discuss | +0.821 |
Split | +0.817 |
Neg logit contributions | |
expectations | -0.924 |
Wonderland | -0.884 |
Pepe | -0.867 |
UTERS | -0.850 |
gest | -0.831 |
Token | / |
Token ID | 14 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
expectations | +0.821 |
Wonderland | +0.777 |
Pepe | +0.761 |
UTERS | +0.751 |
gest | +0.742 |
Neg logit contributions | |
Reviewed | -1.158 |
itaire | -0.973 |
ippery | -0.871 |
Discuss | -0.861 |
Split | -0.854 |
Token | AUT |
Token ID | 39371 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
expectations | +3.693 |
Wonderland | +3.317 |
UTERS | +3.140 |
Pepe | +3.018 |
FIG | +2.984 |
Neg logit contributions | |
Reviewed | -11.874 |
itaire | -10.917 |
oun | -10.047 |
paio | -10.007 |
ippery | -9.714 |
Token | OC |
Token ID | 4503 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Reviewed | +0.081 |
itaire | +0.065 |
ippery | +0.057 |
Discuss | +0.056 |
Split | +0.055 |
Neg logit contributions | |
expectations | -0.089 |
Wonderland | -0.086 |
Pepe | -0.084 |
UTERS | -0.083 |
gest | -0.082 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
expectations | +2.057 |
Wonderland | +1.891 |
Pepe | +1.884 |
gest | +1.804 |
UTERS | +1.774 |
Neg logit contributions | |
Reviewed | -2.973 |
itaire | -2.502 |
ippery | -2.229 |
Discuss | -2.204 |
Gray | -2.169 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
expectations | +0.626 |
Wonderland | +0.582 |
Pepe | +0.568 |
UTERS | +0.557 |
gest | +0.547 |
Neg logit contributions | |
Reviewed | -1.016 |
itaire | -0.867 |
ippery | -0.786 |
Discuss | -0.773 |
Gray | -0.764 |
Token | Kelley |
Token ID | 34560 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Reviewed | +0.729 |
itaire | +0.597 |
ippery | +0.530 |
Discuss | +0.516 |
Split | +0.511 |
Neg logit contributions | |
expectations | -0.676 |
Wonderland | -0.648 |
Pepe | -0.641 |
UTERS | -0.624 |
gest | -0.617 |
Token | had |
Token ID | 550 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Reviewed | +0.893 |
itaire | +0.744 |
ippery | +0.664 |
Discuss | +0.650 |
Split | +0.645 |
Neg logit contributions | |
expectations | -0.718 |
Wonderland | -0.676 |
Pepe | -0.668 |
UTERS | -0.646 |
gest | -0.644 |
Token | a |
Token ID | 257 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Reviewed | +2.108 |
itaire | +1.741 |
ippery | +1.542 |
Discuss | +1.523 |
Gray | +1.493 |
Neg logit contributions | |
expectations | -1.861 |
Wonderland | -1.748 |
Pepe | -1.725 |
gest | -1.662 |
UTERS | -1.660 |
Token | 4 |
Token ID | 604 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Reviewed | +2.157 |
itaire | +1.777 |
ippery | +1.586 |
Discuss | +1.560 |
Split | +1.549 |
Neg logit contributions | |
expectations | -1.813 |
Wonderland | -1.733 |
Pepe | -1.701 |
UTERS | -1.665 |
gest | -1.641 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Reviewed | +6.593 |
itaire | +5.398 |
ippery | +4.853 |
Split | +4.837 |
Discuss | +4.729 |
Neg logit contributions | |
expectations | -5.765 |
Wonderland | -5.577 |
Pepe | -5.502 |
UTERS | -5.376 |
gest | -5.293 |
Token | 53 |
Token ID | 4310 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Reviewed | +1.743 |
itaire | +1.416 |
Discuss | +1.258 |
Split | +1.256 |
ippery | +1.250 |
Neg logit contributions | |
expectations | -1.571 |
Wonderland | -1.505 |
Pepe | -1.471 |
UTERS | -1.447 |
gest | -1.408 |
Token | ERA |
Token ID | 18802 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
Reviewed | +2.536 |
itaire | +2.024 |
ippery | +1.765 |
Discuss | +1.722 |
Split | +1.720 |
Neg logit contributions | |
expectations | -2.875 |
Wonderland | -2.780 |
Pepe | -2.731 |
UTERS | -2.692 |
gest | -2.654 |
Token | for |
Token ID | 329 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Reviewed | +0.636 |
itaire | +0.540 |
ippery | +0.491 |
Discuss | +0.484 |
Gray | +0.478 |
Neg logit contributions | |
expectations | -0.381 |
Wonderland | -0.354 |
Pepe | -0.347 |
UTERS | -0.338 |
gest | -0.333 |
Token | the |
Token ID | 262 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
expectations | +3.603 |
Wonderland | +3.384 |
Pepe | +3.296 |
gest | +3.159 |
UTERS | +3.062 |
Neg logit contributions | |
Reviewed | -5.042 |
itaire | -4.186 |
Discuss | -3.711 |
ippery | -3.686 |
Gray | -3.566 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Reviewed | +1.375 |
itaire | +1.096 |
ippery | +0.947 |
Gray | +0.925 |
Discuss | +0.923 |
Neg logit contributions | |
expectations | -1.551 |
Wonderland | -1.482 |
Pepe | -1.452 |
UTERS | -1.421 |
gest | -1.417 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Reviewed | +1.210 |
itaire | +0.908 |
Discuss | +0.814 |
Split | +0.798 |
Gray | +0.790 |
Neg logit contributions | |
expectations | -1.610 |
Wonderland | -1.562 |
Pepe | -1.522 |
UTERS | -1.515 |
Carbuncle | -1.477 |
Token | making |
Token ID | 8601 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Reviewed | +1.619 |
itaire | +1.327 |
ippery | +1.178 |
Discuss | +1.152 |
Split | +1.145 |
Neg logit contributions | |
expectations | -1.468 |
Wonderland | -1.403 |
Pepe | -1.378 |
UTERS | -1.354 |
gest | -1.343 |
Token | a |
Token ID | 257 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Reviewed | +4.228 |
itaire | +3.552 |
ippery | +3.220 |
Discuss | +3.167 |
Split | +3.149 |
Neg logit contributions | |
expectations | -2.815 |
Wonderland | -2.688 |
Pepe | -2.628 |
UTERS | -2.597 |
gest | -2.531 |
Token | lot |
Token ID | 1256 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Reviewed | +4.843 |
itaire | +4.016 |
ippery | +3.603 |
Discuss | +3.533 |
Split | +3.509 |
Neg logit contributions | |
expectations | -3.858 |
Wonderland | -3.671 |
Pepe | -3.619 |
UTERS | -3.599 |
gest | -3.486 |
Token | of |
Token ID | 286 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Reviewed | +5.106 |
itaire | +4.306 |
ippery | +3.911 |
Discuss | +3.850 |
Split | +3.822 |
Neg logit contributions | |
expectations | -3.264 |
Wonderland | -3.112 |
Pepe | -3.044 |
UTERS | -2.970 |
gest | -2.916 |
Token | sense |
Token ID | 2565 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
Reviewed | +7.657 |
itaire | +6.469 |
ippery | +6.027 |
Discuss | +5.864 |
Split | +5.823 |
Neg logit contributions | |
expectations | -4.076 |
Wonderland | -3.983 |
UTERS | -3.933 |
Pepe | -3.851 |
gest | -3.740 |
Token | . |
Token ID | 13 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
expectations | +0.405 |
Wonderland | +0.379 |
Pepe | +0.368 |
UTERS | +0.360 |
gest | +0.357 |
Neg logit contributions | |
Reviewed | -0.599 |
itaire | -0.502 |
ippery | -0.450 |
Split | -0.444 |
Discuss | -0.442 |
Token | Its |
Token ID | 6363 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Reviewed | +0.586 |
itaire | +0.483 |
ippery | +0.430 |
Discuss | +0.419 |
Split | +0.417 |
Neg logit contributions | |
expectations | -0.515 |
Wonderland | -0.495 |
Pepe | -0.486 |
UTERS | -0.474 |
gest | -0.468 |
Token | admittedly |
Token ID | 33603 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Reviewed | +4.556 |
itaire | +3.790 |
ippery | +3.440 |
Discuss | +3.394 |
Split | +3.361 |
Neg logit contributions | |
expectations | -3.251 |
Wonderland | -3.137 |
Pepe | -3.078 |
UTERS | -3.040 |
gest | -2.947 |
Token | high |
Token ID | 1029 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Reviewed | +5.187 |
itaire | +4.249 |
ippery | +3.814 |
Discuss | +3.761 |
Split | +3.704 |
Neg logit contributions | |
expectations | -4.397 |
Wonderland | -4.235 |
Pepe | -4.178 |
UTERS | -4.136 |
gest | -4.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
expectations | +1.238 |
Wonderland | +1.194 |
Pepe | +1.151 |
gest | +1.104 |
UTERS | +1.103 |
Neg logit contributions | |
Reviewed | -1.831 |
itaire | -1.554 |
ippery | -1.413 |
Discuss | -1.356 |
Split | -1.352 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
expectations | +1.084 |
Pepe | +1.038 |
Wonderland | +1.034 |
gest | +0.993 |
UTERS | +0.988 |
Neg logit contributions | |
Reviewed | -1.259 |
itaire | -1.058 |
ippery | -0.937 |
Split | -0.898 |
Gray | -0.884 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
expectations | +0.780 |
Wonderland | +0.751 |
Pepe | +0.737 |
UTERS | +0.727 |
gest | +0.714 |
Neg logit contributions | |
Reviewed | -0.694 |
itaire | -0.550 |
ippery | -0.480 |
Discuss | -0.475 |
Split | -0.470 |
Token | � |
Token ID | 447 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
expectations | +0.684 |
Wonderland | +0.650 |
Pepe | +0.646 |
UTERS | +0.637 |
gest | +0.632 |
Neg logit contributions | |
Reviewed | -0.817 |
itaire | -0.690 |
ippery | -0.619 |
Split | -0.582 |
Discuss | -0.578 |
Token | � |
Token ID | 250 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
Reviewed | +0.889 |
itaire | +0.747 |
ippery | +0.674 |
Discuss | +0.654 |
Split | +0.651 |
Neg logit contributions | |
expectations | -0.660 |
Wonderland | -0.628 |
Pepe | -0.622 |
UTERS | -0.609 |
gest | -0.592 |
Token | N |
Token ID | 45 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
expectations | +0.206 |
Wonderland | +0.197 |
Pepe | +0.195 |
UTERS | +0.192 |
gest | +0.189 |
Neg logit contributions | |
Reviewed | -0.204 |
itaire | -0.166 |
ippery | -0.146 |
Discuss | -0.142 |
Split | -0.141 |
Token | athan |
Token ID | 6696 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Reviewed | +5.945 |
itaire | +4.683 |
ippery | +4.186 |
Gray | +4.020 |
Discuss | +4.016 |
Neg logit contributions | |
expectations | -7.106 |
Wonderland | -7.080 |
Pepe | -6.875 |
UTERS | -6.677 |
Carbuncle | -6.630 |
Token | ( |
Token ID | 357 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
Reviewed | +1.912 |
itaire | +1.558 |
ippery | +1.377 |
Discuss | +1.353 |
Split | +1.344 |
Neg logit contributions | |
expectations | -1.811 |
Wonderland | -1.736 |
Pepe | -1.707 |
UTERS | -1.676 |
gest | -1.650 |
Token | N |
Token ID | 45 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
Reviewed | +0.363 |
itaire | +0.300 |
ippery | +0.265 |
Discuss | +0.257 |
Split | +0.255 |
Neg logit contributions | |
expectations | -0.333 |
Wonderland | -0.318 |
Pepe | -0.313 |
UTERS | -0.307 |
gest | -0.306 |
Token | ate |
Token ID | 378 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Reviewed | +4.894 |
itaire | +3.953 |
ippery | +3.535 |
Gray | +3.419 |
Split | +3.415 |
Neg logit contributions | |
expectations | -5.109 |
Wonderland | -5.050 |
Pepe | -4.873 |
UTERS | -4.753 |
Carbuncle | -4.632 |
Token | Diaz |
Token ID | 26899 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Reviewed | +1.557 |
itaire | +1.309 |
ippery | +1.180 |
Discuss | +1.163 |
Split | +1.150 |
Neg logit contributions | |
expectations | -1.042 |
Wonderland | -0.989 |
Pepe | -0.973 |
UTERS | -0.945 |
gest | -0.926 |
Token | Ric |
Token ID | 15868 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
Reviewed | +4.490 |
orum | +2.640 |
Discuss | +2.611 |
ippery | +2.610 |
Gray | +2.529 |
Neg logit contributions | |
expectations | -8.362 |
sbm | -7.953 |
Wonderland | -7.902 |
arent | -7.867 |
UTERS | -7.859 |
Token | her |
Token ID | 372 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
Reviewed | +0.221 |
itaire | +0.173 |
ippery | +0.146 |
Split | +0.146 |
Discuss | +0.145 |
Neg logit contributions | |
expectations | -0.293 |
Wonderland | -0.282 |
Pepe | -0.279 |
gest | -0.273 |
UTERS | -0.272 |
Token | t |
Token ID | 83 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
Reviewed | +4.645 |
itaire | +3.800 |
ippery | +3.359 |
Discuss | +3.356 |
orum | +3.243 |
Neg logit contributions | |
expectations | -3.922 |
Wonderland | -3.862 |
Pepe | -3.742 |
UTERS | -3.714 |
aspberry | -3.551 |
Token | and |
Token ID | 290 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Reviewed | +0.231 |
itaire | +0.197 |
ippery | +0.181 |
Discuss | +0.175 |
Split | +0.175 |
Neg logit contributions | |
expectations | -0.118 |
Wonderland | -0.112 |
Pepe | -0.109 |
UTERS | -0.106 |
gest | -0.104 |
Token | David |
Token ID | 3271 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
Reviewed | +4.256 |
itaire | +3.162 |
ippery | +2.722 |
Discuss | +2.683 |
Gray | +2.601 |
Neg logit contributions | |
expectations | -6.171 |
Wonderland | -5.997 |
UTERS | -5.918 |
Pepe | -5.816 |
gest | -5.793 |
Token | Gordon |
Token ID | 11646 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
Reviewed | +4.266 |
itaire | +3.079 |
Gray | +2.870 |
ippery | +2.759 |
Discuss | +2.742 |
Neg logit contributions | |
expectations | -7.958 |
Wonderland | -7.608 |
UTERS | -7.493 |
sbm | -7.460 |
enegger | -7.349 |
Token | ( |
Token ID | 357 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
Reviewed | +5.552 |
itaire | +4.467 |
Discuss | +4.245 |
Gray | +4.138 |
ippery | +4.093 |
Neg logit contributions | |
expectations | -5.502 |
UTERS | -5.338 |
Wonderland | -5.275 |
Pepe | -5.267 |
gest | -5.112 |
Token | IS |
Token ID | 1797 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Reviewed | +2.947 |
itaire | +2.001 |
Gray | +1.669 |
Discuss | +1.615 |
ippery | +1.588 |
Neg logit contributions | |
expectations | -5.953 |
Wonderland | -5.863 |
Pepe | -5.789 |
UTERS | -5.703 |
Kardashian | -5.540 |
Token | I |
Token ID | 40 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
expectations | +1.730 |
Wonderland | +1.660 |
Pepe | +1.636 |
UTERS | +1.605 |
gest | +1.559 |
Neg logit contributions | |
Reviewed | -1.749 |
itaire | -1.442 |
ippery | -1.278 |
Discuss | -1.237 |
Split | -1.221 |
Token | Books |
Token ID | 13661 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
expectations | +1.930 |
Wonderland | +1.798 |
Pepe | +1.767 |
UTERS | +1.658 |
gest | +1.633 |
Neg logit contributions | |
Reviewed | -4.480 |
itaire | -3.904 |
ippery | -3.591 |
Discuss | -3.515 |
Split | -3.508 |
Token | , |
Token ID | 11 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
expectations | +1.046 |
Wonderland | +0.968 |
Pepe | +0.962 |
UTERS | +0.920 |
gest | +0.920 |
Neg logit contributions | |
Reviewed | -1.935 |
itaire | -1.639 |
ippery | -1.515 |
Split | -1.481 |
Discuss | -1.475 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
expectations | +0.233 |
Wonderland | +0.225 |
Pepe | +0.221 |
UTERS | +0.218 |
gest | +0.213 |
Neg logit contributions | |
Reviewed | -0.199 |
itaire | -0.156 |
ippery | -0.136 |
Discuss | -0.136 |
Split | -0.134 |
Token | Carter |
Token ID | 49958 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Reviewed | +0.718 |
itaire | +0.581 |
ippery | +0.514 |
Discuss | +0.498 |
Split | +0.497 |
Neg logit contributions | |
expectations | -0.728 |
Wonderland | -0.699 |
Pepe | -0.686 |
UTERS | -0.678 |
gest | -0.669 |
Token | , |
Token ID | 11 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
Reviewed | +1.142 |
itaire | +0.946 |
ippery | +0.849 |
Discuss | +0.835 |
Split | +0.829 |
Neg logit contributions | |
expectations | -0.904 |
Wonderland | -0.864 |
Pepe | -0.847 |
UTERS | -0.832 |
gest | -0.817 |
Token | an |
Token ID | 281 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
expectations | +0.507 |
Wonderland | +0.481 |
Pepe | +0.470 |
UTERS | +0.447 |
gest | +0.444 |
Neg logit contributions | |
Reviewed | -0.734 |
itaire | -0.613 |
ippery | -0.551 |
Split | -0.546 |
Discuss | -0.543 |
Token | occupational |
Token ID | 34266 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Reviewed | +1.412 |
itaire | +1.162 |
ippery | +1.034 |
Discuss | +1.021 |
Split | +1.014 |
Neg logit contributions | |
expectations | -1.204 |
Wonderland | -1.151 |
Pepe | -1.126 |
UTERS | -1.101 |
gest | -1.086 |
Token | therapist |
Token ID | 24636 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Reviewed | +2.890 |
itaire | +2.423 |
ippery | +2.187 |
Discuss | +2.132 |
Split | +2.123 |
Neg logit contributions | |
expectations | -2.128 |
Wonderland | -2.049 |
Pepe | -2.020 |
UTERS | -1.993 |
gest | -1.929 |
Token | by |
Token ID | 416 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Reviewed | +7.895 |
itaire | +6.597 |
ippery | +5.869 |
Split | +5.844 |
Registered | +5.796 |
Neg logit contributions | |
expectations | -5.834 |
Wonderland | -5.782 |
UTERS | -5.676 |
Pepe | -5.612 |
gest | -5.388 |
Token | day |
Token ID | 1110 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
Reviewed | +5.349 |
itaire | +4.550 |
ippery | +4.163 |
Discuss | +4.137 |
Split | +4.098 |
Neg logit contributions | |
expectations | -2.921 |
Wonderland | -2.778 |
Pepe | -2.755 |
UTERS | -2.702 |
gest | -2.615 |
Token | , |
Token ID | 11 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
Reviewed | +4.857 |
itaire | +4.127 |
ippery | +3.735 |
Discuss | +3.686 |
Split | +3.672 |
Neg logit contributions | |
expectations | -2.963 |
Wonderland | -2.827 |
Pepe | -2.770 |
UTERS | -2.718 |
gest | -2.639 |
Token | believes |
Token ID | 5804 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
expectations | +0.409 |
Wonderland | +0.387 |
Pepe | +0.381 |
UTERS | +0.367 |
gest | +0.366 |
Neg logit contributions | |
Reviewed | -0.494 |
itaire | -0.409 |
ippery | -0.363 |
Split | -0.357 |
Discuss | -0.356 |
Token | it |
Token ID | 340 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Reviewed | +1.542 |
itaire | +1.280 |
ippery | +1.146 |
Discuss | +1.127 |
Split | +1.120 |
Neg logit contributions | |
expectations | -1.231 |
Wonderland | -1.176 |
Pepe | -1.158 |
UTERS | -1.136 |
gest | -1.114 |
Token | real |
Token ID | 1103 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
Reviewed | +3.714 |
itaire | +3.086 |
ippery | +2.810 |
Discuss | +2.767 |
Gray | +2.762 |
Neg logit contributions | |
expectations | -2.801 |
Wonderland | -2.643 |
UTERS | -2.602 |
Pepe | -2.595 |
gest | -2.517 |
Token | estate |
Token ID | 7964 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Reviewed | +3.904 |
itaire | +3.173 |
ippery | +2.794 |
Discuss | +2.743 |
Split | +2.719 |
Neg logit contributions | |
expectations | -3.926 |
Wonderland | -3.769 |
Pepe | -3.710 |
UTERS | -3.657 |
gest | -3.584 |
Token | agent |
Token ID | 5797 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Reviewed | +0.982 |
itaire | +0.822 |
ippery | +0.743 |
Discuss | +0.731 |
Split | +0.727 |
Neg logit contributions | |
expectations | -0.685 |
Wonderland | -0.651 |
Pepe | -0.639 |
UTERS | -0.624 |
gest | -0.614 |
Token | murdered |
Token ID | 12864 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Reviewed | +2.003 |
itaire | +1.656 |
ippery | +1.482 |
Discuss | +1.461 |
Split | +1.453 |
Neg logit contributions | |
expectations | -1.616 |
Wonderland | -1.549 |
Pepe | -1.511 |
UTERS | -1.497 |
gest | -1.463 |
Token | by |
Token ID | 416 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Reviewed | +1.086 |
itaire | +0.915 |
ippery | +0.826 |
Discuss | +0.814 |
Split | +0.809 |
Neg logit contributions | |
expectations | -0.718 |
Wonderland | -0.681 |
Pepe | -0.667 |
UTERS | -0.649 |
gest | -0.638 |
Token | members |
Token ID | 1866 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Reviewed | +3.433 |
itaire | +2.835 |
ippery | +2.550 |
Discuss | +2.498 |
Split | +2.493 |
Neg logit contributions | |
expectations | -2.872 |
Wonderland | -2.764 |
Pepe | -2.705 |
UTERS | -2.679 |
gest | -2.623 |
Token | of |
Token ID | 286 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
Reviewed | +1.222 |
itaire | +1.040 |
ippery | +0.950 |
Discuss | +0.934 |
Split | +0.925 |
Neg logit contributions | |
expectations | -0.693 |
Wonderland | -0.648 |
Pepe | -0.637 |
UTERS | -0.621 |
gest | -0.605 |
Token | his |
Token ID | 465 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Reviewed | +0.355 |
itaire | +0.293 |
ippery | +0.261 |
Discuss | +0.258 |
Split | +0.255 |
Neg logit contributions | |
expectations | -0.282 |
Wonderland | -0.268 |
Pepe | -0.263 |
UTERS | -0.255 |
gest | -0.252 |
Token | gang |
Token ID | 7706 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
Reviewed | +1.303 |
itaire | +1.093 |
ippery | +0.988 |
Discuss | +0.974 |
Split | +0.968 |
Neg logit contributions | |
expectations | -0.863 |
Wonderland | -0.819 |
Pepe | -0.802 |
UTERS | -0.782 |
gest | -0.769 |
Token | in |
Token ID | 287 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
expectations | +0.393 |
Wonderland | +0.371 |
Pepe | +0.364 |
UTERS | +0.355 |
gest | +0.350 |
Neg logit contributions | |
Reviewed | -0.605 |
itaire | -0.509 |
ippery | -0.461 |
Discuss | -0.452 |
Split | -0.449 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Reviewed | +2.196 |
itaire | +1.775 |
ippery | +1.575 |
Discuss | +1.545 |
Split | +1.538 |
Neg logit contributions | |
expectations | -2.160 |
Wonderland | -2.073 |
Pepe | -2.039 |
UTERS | -2.016 |
gest | -1.976 |
Token | research |
Token ID | 2267 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
expectations | +0.667 |
Wonderland | +0.608 |
Pepe | +0.597 |
UTERS | +0.575 |
gest | +0.572 |
Neg logit contributions | |
Reviewed | -1.175 |
itaire | -1.011 |
ippery | -0.929 |
Split | -0.901 |
Discuss | -0.897 |
Token | and |
Token ID | 290 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
expectations | +0.414 |
Wonderland | +0.378 |
Pepe | +0.375 |
UTERS | +0.363 |
gest | +0.358 |
Neg logit contributions | |
Reviewed | -0.758 |
itaire | -0.647 |
ippery | -0.598 |
Split | -0.582 |
Discuss | -0.581 |
Token | communication |
Token ID | 6946 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Reviewed | +3.201 |
itaire | +2.685 |
ippery | +2.415 |
Discuss | +2.383 |
Split | +2.364 |
Neg logit contributions | |
expectations | -2.268 |
Wonderland | -2.180 |
Pepe | -2.131 |
UTERS | -2.107 |
gest | -2.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Reviewed | +3.199 |
itaire | +2.678 |
ippery | +2.402 |
Discuss | +2.382 |
Split | +2.374 |
Neg logit contributions | |
expectations | -2.266 |
Wonderland | -2.181 |
Pepe | -2.128 |
UTERS | -2.093 |
gest | -2.048 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Reviewed | +0.916 |
itaire | +0.769 |
ippery | +0.702 |
Discuss | +0.689 |
Split | +0.688 |
Neg logit contributions | |
expectations | -0.577 |
Wonderland | -0.539 |
Pepe | -0.530 |
UTERS | -0.510 |
gest | -0.507 |
Token | international |
Token ID | 3230 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Reviewed | +2.360 |
itaire | +1.968 |
ippery | +1.769 |
Discuss | +1.742 |
Split | +1.730 |
Neg logit contributions | |
expectations | -1.765 |
Wonderland | -1.688 |
Pepe | -1.653 |
UTERS | -1.625 |
gest | -1.593 |
Token | development |
Token ID | 2478 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Reviewed | +1.926 |
itaire | +1.623 |
ippery | +1.473 |
Discuss | +1.451 |
Split | +1.443 |
Neg logit contributions | |
expectations | -1.236 |
Wonderland | -1.172 |
Pepe | -1.146 |
UTERS | -1.121 |
gest | -1.099 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
expectations | +1.008 |
Wonderland | +0.916 |
Pepe | +0.911 |
UTERS | +0.880 |
gest | +0.865 |
Neg logit contributions | |
Reviewed | -1.646 |
itaire | -1.382 |
ippery | -1.280 |
Discuss | -1.243 |
Split | -1.235 |
Token | We |
Token ID | 775 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Reviewed | +0.187 |
itaire | +0.156 |
ippery | +0.141 |
Discuss | +0.138 |
Split | +0.137 |
Neg logit contributions | |
expectations | -0.142 |
Wonderland | -0.136 |
Pepe | -0.133 |
UTERS | -0.130 |
gest | -0.128 |
Token | have |
Token ID | 423 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
expectations | +0.206 |
Wonderland | +0.194 |
Pepe | +0.192 |
UTERS | +0.186 |
gest | +0.185 |
Neg logit contributions | |
Reviewed | -0.265 |
itaire | -0.220 |
ippery | -0.198 |
Discuss | -0.194 |
Split | -0.193 |
Token | supported |
Token ID | 4855 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Reviewed | +2.314 |
itaire | +1.909 |
ippery | +1.707 |
Discuss | +1.677 |
Split | +1.669 |
Neg logit contributions | |
expectations | -1.912 |
Wonderland | -1.832 |
Pepe | -1.797 |
UTERS | -1.767 |
gest | -1.735 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
expectations | +0.072 |
Wonderland | +0.068 |
Pepe | +0.067 |
UTERS | +0.066 |
gest | +0.064 |
Neg logit contributions | |
Reviewed | -0.115 |
itaire | -0.097 |
ippery | -0.088 |
Discuss | -0.087 |
Split | -0.086 |
Token | customers |
Token ID | 4297 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Reviewed | +0.942 |
itaire | +0.791 |
ippery | +0.712 |
Discuss | +0.700 |
Split | +0.697 |
Neg logit contributions | |
expectations | -0.676 |
Wonderland | -0.641 |
Pepe | -0.632 |
UTERS | -0.611 |
gest | -0.601 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
expectations | +1.644 |
Wonderland | +1.532 |
Pepe | +1.512 |
UTERS | +1.451 |
gest | +1.433 |
Neg logit contributions | |
Reviewed | -2.512 |
itaire | -2.129 |
ippery | -1.945 |
Split | -1.897 |
Discuss | -1.887 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Reviewed | +0.730 |
itaire | +0.606 |
ippery | +0.534 |
Discuss | +0.509 |
Split | +0.509 |
Neg logit contributions | |
expectations | -0.678 |
Wonderland | -0.658 |
Pepe | -0.653 |
UTERS | -0.628 |
gest | -0.619 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
expectations | +0.904 |
Wonderland | +0.870 |
Pepe | +0.855 |
UTERS | +0.843 |
gest | +0.828 |
Neg logit contributions | |
Reviewed | -0.807 |
itaire | -0.640 |
ippery | -0.559 |
Discuss | -0.552 |
Split | -0.547 |
Token | T |
Token ID | 51 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
expectations | +1.387 |
UTERS | +1.335 |
Pepe | +1.333 |
Wonderland | +1.330 |
gest | +1.307 |
Neg logit contributions | |
Reviewed | -1.468 |
itaire | -1.258 |
ippery | -1.118 |
oun | -1.056 |
agy | -1.013 |
Token | ori |
Token ID | 10145 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Reviewed | +4.395 |
itaire | +3.544 |
ippery | +3.167 |
Split | +3.092 |
Discuss | +3.074 |
Neg logit contributions | |
expectations | -4.495 |
Wonderland | -4.332 |
Pepe | -4.259 |
UTERS | -4.130 |
gest | -4.108 |
Token | had |
Token ID | 550 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Reviewed | +2.209 |
itaire | +1.830 |
ippery | +1.643 |
Discuss | +1.616 |
Split | +1.607 |
Neg logit contributions | |
expectations | -1.740 |
Wonderland | -1.661 |
Pepe | -1.628 |
UTERS | -1.599 |
gest | -1.571 |
Token | been |
Token ID | 587 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Reviewed | +1.228 |
itaire | +1.006 |
ippery | +0.889 |
Discuss | +0.874 |
Split | +0.862 |
Neg logit contributions | |
expectations | -1.139 |
Wonderland | -1.089 |
Pepe | -1.068 |
UTERS | -1.039 |
gest | -1.032 |
Token | laughing |
Token ID | 14376 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
expectations | +1.262 |
Wonderland | +1.195 |
Pepe | +1.177 |
gest | +1.132 |
UTERS | +1.132 |
Neg logit contributions | |
Reviewed | -1.688 |
itaire | -1.411 |
ippery | -1.271 |
Discuss | -1.244 |
Split | -1.236 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Reviewed | +3.761 |
itaire | +3.150 |
ippery | +2.827 |
Discuss | +2.825 |
Split | +2.789 |
Neg logit contributions | |
expectations | -2.791 |
Wonderland | -2.673 |
Pepe | -2.608 |
UTERS | -2.607 |
gest | -2.538 |
Token | - |
Token ID | 12 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
expectations | +1.282 |
Wonderland | +1.187 |
Pepe | +1.157 |
UTERS | +1.146 |
gest | +1.136 |
Neg logit contributions | |
Reviewed | -2.281 |
itaire | -1.972 |
ippery | -1.770 |
Gray | -1.759 |
Split | -1.745 |
Token | spons |
Token ID | 20587 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
expectations | +3.732 |
gest | +3.432 |
UTERS | +3.395 |
Wonderland | +3.389 |
Pepe | +3.380 |
Neg logit contributions | |
Reviewed | -5.672 |
itaire | -5.012 |
ippery | -4.403 |
Split | -4.293 |
Gray | -4.217 |
Token | or |
Token ID | 273 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
Reviewed | +0.030 |
itaire | +0.024 |
ippery | +0.020 |
Split | +0.020 |
Discuss | +0.019 |
Neg logit contributions | |
expectations | -0.037 |
Wonderland | -0.036 |
Pepe | -0.036 |
gest | -0.035 |
UTERS | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
expectations | +0.026 |
Wonderland | +0.025 |
Pepe | +0.024 |
UTERS | +0.024 |
gest | +0.023 |
Neg logit contributions | |
Reviewed | -0.035 |
itaire | -0.029 |
ippery | -0.026 |
Discuss | -0.026 |
Split | -0.026 |
Token | Retro |
Token ID | 29884 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
expectations | +0.561 |
Wonderland | +0.533 |
Pepe | +0.523 |
UTERS | +0.507 |
gest | +0.503 |
Neg logit contributions | |
Reviewed | -0.719 |
itaire | -0.597 |
ippery | -0.531 |
Discuss | -0.528 |
Split | -0.523 |
Token | active |
Token ID | 5275 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Reviewed | +0.846 |
itaire | +0.698 |
ippery | +0.626 |
Discuss | +0.615 |
Split | +0.609 |
Neg logit contributions | |
expectations | -0.709 |
Wonderland | -0.676 |
Pepe | -0.664 |
UTERS | -0.652 |
gest | -0.645 |
Token | Immunity |
Token ID | 46824 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
Reviewed | +3.563 |
itaire | +2.957 |
ippery | +2.654 |
Discuss | +2.616 |
Split | +2.606 |
Neg logit contributions | |
expectations | -2.695 |
Wonderland | -2.562 |
Pepe | -2.519 |
UTERS | -2.474 |
gest | -2.423 |
Token | Repe |
Token ID | 30558 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
expectations | +0.375 |
Wonderland | +0.356 |
Pepe | +0.349 |
UTERS | +0.336 |
gest | +0.333 |
Neg logit contributions | |
Reviewed | -0.551 |
itaire | -0.461 |
ippery | -0.420 |
Discuss | -0.413 |
Split | -0.409 |
Token | al |
Token ID | 282 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
expectations | +1.343 |
Pepe | +1.232 |
Wonderland | +1.220 |
gest | +1.210 |
UTERS | +1.195 |
Neg logit contributions | |
Reviewed | -2.323 |
itaire | -1.941 |
ippery | -1.789 |
Gray | -1.750 |
Split | -1.748 |
Token | Act |
Token ID | 2191 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
Reviewed | +1.532 |
itaire | +1.297 |
ippery | +1.177 |
Discuss | +1.161 |
Split | +1.155 |
Neg logit contributions | |
expectations | -0.943 |
Wonderland | -0.894 |
Pepe | -0.874 |
UTERS | -0.855 |
gest | -0.837 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
expectations | +0.036 |
Wonderland | +0.034 |
Pepe | +0.033 |
UTERS | +0.032 |
gest | +0.032 |
Neg logit contributions | |
Reviewed | -0.054 |
itaire | -0.046 |
ippery | -0.042 |
Discuss | -0.041 |
Split | -0.041 |
Token | 19 |
Token ID | 678 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
Reviewed | +2.311 |
itaire | +1.925 |
ippery | +1.732 |
Discuss | +1.705 |
Split | +1.695 |
Neg logit contributions | |
expectations | -1.725 |
Wonderland | -1.645 |
Pepe | -1.613 |
UTERS | -1.583 |
gest | -1.553 |
Token | - |
Token ID | 12 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
expectations | +0.491 |
Wonderland | +0.475 |
Pepe | +0.460 |
UTERS | +0.456 |
gest | +0.443 |
Neg logit contributions | |
Reviewed | -0.527 |
itaire | -0.432 |
ippery | -0.382 |
Discuss | -0.376 |
Split | -0.374 |
Token | feet |
Token ID | 39690 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
expectations | +0.646 |
Wonderland | +0.624 |
Pepe | +0.610 |
gest | +0.606 |
UTERS | +0.603 |
Neg logit contributions | |
Reviewed | -0.531 |
itaire | -0.423 |
ippery | -0.359 |
Discuss | -0.354 |
Split | -0.353 |
Token | tall |
Token ID | 7331 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
expectations | +0.160 |
Wonderland | +0.155 |
Pepe | +0.150 |
UTERS | +0.146 |
gest | +0.145 |
Neg logit contributions | |
Reviewed | -0.164 |
itaire | -0.133 |
ippery | -0.118 |
Discuss | -0.116 |
Split | -0.114 |
Token | from |
Token ID | 422 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Reviewed | +2.500 |
itaire | +2.101 |
ippery | +1.901 |
Discuss | +1.873 |
Split | +1.861 |
Neg logit contributions | |
expectations | -1.682 |
Wonderland | -1.599 |
Pepe | -1.565 |
UTERS | -1.528 |
gest | -1.501 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Reviewed | +2.339 |
itaire | +1.940 |
ippery | +1.740 |
Discuss | +1.712 |
Split | +1.702 |
Neg logit contributions | |
expectations | -1.834 |
Wonderland | -1.750 |
Pepe | -1.716 |
UTERS | -1.685 |
gest | -1.655 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Reviewed | +2.839 |
itaire | +2.374 |
ippery | +2.140 |
Discuss | +2.109 |
Split | +2.094 |
Neg logit contributions | |
expectations | -2.041 |
Wonderland | -1.945 |
Pepe | -1.904 |
UTERS | -1.861 |
gest | -1.829 |
Token | Seven |
Token ID | 13723 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
expectations | +1.982 |
Wonderland | +1.933 |
Pepe | +1.906 |
UTERS | +1.825 |
gest | +1.794 |
Neg logit contributions | |
Reviewed | -2.598 |
itaire | -2.179 |
ippery | -1.982 |
Discuss | -1.890 |
Split | -1.872 |
Token | of |
Token ID | 286 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
expectations | +5.357 |
Wonderland | +5.133 |
Pepe | +4.833 |
Kardashian | +4.613 |
cher | +4.569 |
Neg logit contributions | |
Reviewed | -9.396 |
itaire | -7.974 |
ippery | -7.212 |
Discuss | -7.102 |
Split | -6.929 |
Token | the |
Token ID | 262 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
expectations | +2.821 |
Wonderland | +2.716 |
Pepe | +2.601 |
UTERS | +2.462 |
gest | +2.435 |
Neg logit contributions | |
Reviewed | -4.759 |
itaire | -4.021 |
ippery | -3.627 |
Discuss | -3.579 |
Split | -3.578 |
Token | three |
Token ID | 1115 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
expectations | +2.865 |
Wonderland | +2.726 |
Pepe | +2.630 |
Kardashian | +2.441 |
gest | +2.435 |
Neg logit contributions | |
Reviewed | -4.944 |
itaire | -4.253 |
ippery | -3.799 |
Discuss | -3.778 |
Split | -3.722 |
Token | not |
Token ID | 407 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Reviewed | +1.566 |
itaire | +1.276 |
ippery | +1.131 |
Discuss | +1.111 |
Split | +1.103 |
Neg logit contributions | |
expectations | -1.463 |
Wonderland | -1.403 |
Pepe | -1.378 |
UTERS | -1.354 |
gest | -1.332 |
Token | make |
Token ID | 787 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
expectations | +1.083 |
Wonderland | +1.022 |
Pepe | +1.013 |
gest | +0.984 |
UTERS | +0.983 |
Neg logit contributions | |
Reviewed | -1.156 |
itaire | -0.941 |
ippery | -0.842 |
Discuss | -0.818 |
Split | -0.818 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Reviewed | +2.822 |
itaire | +2.355 |
ippery | +2.122 |
Discuss | +2.093 |
Split | +2.072 |
Neg logit contributions | |
expectations | -2.045 |
Wonderland | -1.970 |
Pepe | -1.911 |
UTERS | -1.891 |
gest | -1.844 |
Token | In |
Token ID | 554 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
expectations | +1.919 |
Wonderland | +1.859 |
Pepe | +1.842 |
UTERS | +1.749 |
gest | +1.743 |
Neg logit contributions | |
Reviewed | -2.660 |
itaire | -2.282 |
ippery | -2.066 |
Discuss | -1.977 |
Split | -1.969 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Reviewed | +1.684 |
itaire | +1.385 |
ippery | +1.237 |
Discuss | +1.216 |
Split | +1.209 |
Neg logit contributions | |
expectations | -1.425 |
Wonderland | -1.364 |
Pepe | -1.339 |
UTERS | -1.317 |
gest | -1.290 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
expectations | +0.680 |
Wonderland | +0.637 |
Pepe | +0.627 |
UTERS | +0.603 |
gest | +0.590 |
Neg logit contributions | |
Reviewed | -1.144 |
itaire | -0.990 |
ippery | -0.897 |
Discuss | -0.881 |
Split | -0.877 |
Token | a |
Token ID | 257 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Reviewed | +0.160 |
itaire | +0.135 |
ippery | +0.120 |
Discuss | +0.119 |
Split | +0.118 |
Neg logit contributions | |
expectations | -0.120 |
Wonderland | -0.113 |
Pepe | -0.112 |
UTERS | -0.108 |
gest | -0.106 |
Token | Swedish |
Token ID | 14023 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Reviewed | +2.173 |
itaire | +1.837 |
ippery | +1.670 |
Discuss | +1.644 |
Split | +1.637 |
Neg logit contributions | |
expectations | -1.323 |
Wonderland | -1.253 |
Pepe | -1.223 |
UTERS | -1.203 |
gest | -1.173 |
Token | team |
Token ID | 1074 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
expectations | +1.453 |
Wonderland | +1.358 |
Pepe | +1.328 |
gest | +1.268 |
UTERS | +1.258 |
Neg logit contributions | |
Reviewed | -2.708 |
itaire | -2.331 |
ippery | -2.124 |
Discuss | -2.108 |
Split | -2.079 |
Token | found |
Token ID | 1043 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Reviewed | +2.440 |
itaire | +2.029 |
ippery | +1.829 |
Discuss | +1.807 |
Split | +1.802 |
Neg logit contributions | |
expectations | -1.731 |
Wonderland | -1.656 |
Pepe | -1.611 |
UTERS | -1.599 |
gest | -1.551 |
Token | soft |
Token ID | 2705 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
Reviewed | +1.281 |
itaire | +1.073 |
ippery | +0.965 |
Discuss | +0.952 |
Split | +0.946 |
Neg logit contributions | |
expectations | -0.920 |
Wonderland | -0.872 |
Pepe | -0.858 |
UTERS | -0.833 |
gest | -0.821 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Reviewed | +0.303 |
itaire | +0.253 |
ippery | +0.229 |
Discuss | +0.225 |
Split | +0.225 |
Neg logit contributions | |
expectations | -0.203 |
Wonderland | -0.192 |
Pepe | -0.189 |
UTERS | -0.184 |
gest | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
expectations | +2.030 |
Wonderland | +1.969 |
Pepe | +1.936 |
UTERS | +1.857 |
gest | +1.851 |
Neg logit contributions | |
Reviewed | -2.477 |
itaire | -2.086 |
ippery | -1.880 |
Split | -1.783 |
Discuss | -1.780 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
expectations | +1.648 |
Wonderland | +1.584 |
Pepe | +1.560 |
UTERS | +1.533 |
gest | +1.515 |
Neg logit contributions | |
Reviewed | -1.544 |
itaire | -1.245 |
ippery | -1.092 |
Discuss | -1.061 |
Split | -1.055 |
Token | The |
Token ID | 464 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
expectations | +1.216 |
Wonderland | +1.160 |
UTERS | +1.147 |
Pepe | +1.142 |
gest | +1.133 |
Neg logit contributions | |
Reviewed | -1.204 |
itaire | -1.000 |
ippery | -0.897 |
Split | -0.832 |
Discuss | -0.830 |
Token | film |
Token ID | 2646 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
expectations | +1.325 |
Wonderland | +1.242 |
Pepe | +1.195 |
gest | +1.156 |
UTERS | +1.152 |
Neg logit contributions | |
Reviewed | -2.051 |
itaire | -1.731 |
ippery | -1.565 |
Discuss | -1.540 |
Split | -1.535 |
Token | runs |
Token ID | 4539 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Reviewed | +0.476 |
itaire | +0.391 |
ippery | +0.348 |
Discuss | +0.338 |
Split | +0.338 |
Neg logit contributions | |
expectations | -0.432 |
Wonderland | -0.411 |
Pepe | -0.405 |
UTERS | -0.392 |
gest | -0.389 |
Token | just |
Token ID | 655 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
expectations | +0.638 |
Wonderland | +0.598 |
Pepe | +0.587 |
UTERS | +0.566 |
gest | +0.564 |
Neg logit contributions | |
Reviewed | -0.920 |
itaire | -0.772 |
ippery | -0.700 |
Split | -0.688 |
Discuss | -0.682 |
Token | over |
Token ID | 625 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
expectations | +1.206 |
Wonderland | +1.133 |
Pepe | +1.112 |
UTERS | +1.073 |
gest | +1.067 |
Neg logit contributions | |
Reviewed | -1.637 |
itaire | -1.372 |
ippery | -1.231 |
Split | -1.201 |
Discuss | -1.196 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
expectations | +1.056 |
Wonderland | +0.999 |
Pepe | +0.973 |
UTERS | +0.934 |
gest | +0.933 |
Neg logit contributions | |
Reviewed | -1.524 |
itaire | -1.281 |
ippery | -1.153 |
Discuss | -1.131 |
Split | -1.128 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
expectations | +0.015 |
Wonderland | +0.014 |
Pepe | +0.014 |
UTERS | +0.013 |
gest | +0.013 |
Neg logit contributions | |
Reviewed | -0.021 |
itaire | -0.017 |
ippery | -0.016 |
Discuss | -0.015 |
Split | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Reviewed | +1.974 |
itaire | +1.663 |
ippery | +1.508 |
Discuss | +1.485 |
Split | +1.477 |
Neg logit contributions | |
expectations | -1.272 |
Wonderland | -1.205 |
Pepe | -1.178 |
UTERS | -1.152 |
gest | -1.130 |
Token | of |
Token ID | 286 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Reviewed | +1.104 |
itaire | +0.933 |
ippery | +0.858 |
Discuss | +0.843 |
Split | +0.834 |
Neg logit contributions | |
expectations | -0.640 |
Wonderland | -0.599 |
Pepe | -0.587 |
UTERS | -0.575 |
gest | -0.559 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Reviewed | +2.227 |
itaire | +1.852 |
ippery | +1.663 |
Discuss | +1.637 |
Split | +1.628 |
Neg logit contributions | |
expectations | -1.698 |
Wonderland | -1.618 |
Pepe | -1.588 |
UTERS | -1.552 |
gest | -1.525 |
Token | Currency |
Token ID | 20113 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Reviewed | +0.781 |
itaire | +0.649 |
ippery | +0.585 |
Discuss | +0.577 |
Split | +0.571 |
Neg logit contributions | |
expectations | -0.576 |
Wonderland | -0.549 |
Pepe | -0.537 |
UTERS | -0.517 |
gest | -0.515 |
Token | Inter |
Token ID | 4225 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Reviewed | +1.254 |
itaire | +1.054 |
ippery | +0.956 |
Discuss | +0.941 |
Split | +0.932 |
Neg logit contributions | |
expectations | -0.846 |
Wonderland | -0.808 |
Pepe | -0.790 |
UTERS | -0.767 |
gest | -0.756 |
Token | change |
Token ID | 3803 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
expectations | +2.895 |
Wonderland | +2.822 |
gest | +2.725 |
Pepe | +2.675 |
rants | +2.588 |
Neg logit contributions | |
Reviewed | -4.605 |
itaire | -3.778 |
ippery | -3.556 |
Discuss | -3.514 |
Gray | -3.410 |
Token | ability |
Token ID | 1799 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
expectations | +1.099 |
Wonderland | +1.054 |
Pepe | +1.015 |
UTERS | +0.983 |
gest | +0.968 |
Neg logit contributions | |
Reviewed | -1.767 |
itaire | -1.482 |
ippery | -1.371 |
Discuss | -1.347 |
Split | -1.326 |
Token | Agreement |
Token ID | 12729 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
expectations | +1.554 |
Wonderland | +1.463 |
Pepe | +1.416 |
UTERS | +1.347 |
gest | +1.346 |
Neg logit contributions | |
Reviewed | -2.739 |
itaire | -2.294 |
ippery | -2.154 |
Discuss | -2.106 |
Split | -2.083 |
Token | ( |
Token ID | 357 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Reviewed | +0.419 |
itaire | +0.349 |
ippery | +0.316 |
Discuss | +0.310 |
Split | +0.307 |
Neg logit contributions | |
expectations | -0.316 |
Wonderland | -0.300 |
Pepe | -0.295 |
UTERS | -0.288 |
gest | -0.283 |
Token | since |
Token ID | 20777 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Reviewed | +0.167 |
itaire | +0.140 |
ippery | +0.128 |
Discuss | +0.124 |
Split | +0.123 |
Neg logit contributions | |
expectations | -0.119 |
Wonderland | -0.112 |
Pepe | -0.110 |
UTERS | -0.108 |
gest | -0.107 |
Token | 12 |
Token ID | 1105 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
Reviewed | +1.857 |
itaire | +1.523 |
ippery | +1.355 |
Discuss | +1.331 |
Split | +1.323 |
Neg logit contributions | |
expectations | -1.641 |
Wonderland | -1.571 |
Pepe | -1.542 |
UTERS | -1.515 |
gest | -1.490 |
Token | June |
Token ID | 2795 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Reviewed | +0.475 |
itaire | +0.393 |
ippery | +0.354 |
Discuss | +0.347 |
Split | +0.344 |
Neg logit contributions | |
expectations | -0.387 |
Wonderland | -0.370 |
Pepe | -0.362 |
UTERS | -0.356 |
gest | -0.350 |
Token | a |
Token ID | 257 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
expectations | +0.289 |
Wonderland | +0.277 |
Pepe | +0.273 |
UTERS | +0.260 |
gest | +0.259 |
Neg logit contributions | |
Reviewed | -0.345 |
itaire | -0.286 |
ippery | -0.254 |
Discuss | -0.250 |
Split | -0.250 |
Token | guy |
Token ID | 3516 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
expectations | +1.981 |
Wonderland | +1.895 |
Pepe | +1.845 |
gest | +1.749 |
Kardashian | +1.745 |
Neg logit contributions | |
Reviewed | -3.253 |
itaire | -2.754 |
ippery | -2.505 |
Discuss | -2.473 |
Split | -2.472 |
Token | who |
Token ID | 508 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
expectations | +0.776 |
Wonderland | +0.734 |
Pepe | +0.723 |
UTERS | +0.692 |
gest | +0.690 |
Neg logit contributions | |
Reviewed | -1.097 |
itaire | -0.919 |
ippery | -0.824 |
Discuss | -0.814 |
Split | -0.811 |
Token | developed |
Token ID | 4166 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
expectations | +0.866 |
Wonderland | +0.816 |
Pepe | +0.807 |
UTERS | +0.772 |
gest | +0.770 |
Neg logit contributions | |
Reviewed | -1.107 |
itaire | -0.920 |
ippery | -0.824 |
Discuss | -0.810 |
Split | -0.806 |
Token | games |
Token ID | 1830 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Reviewed | +3.149 |
itaire | +2.610 |
ippery | +2.341 |
Discuss | +2.300 |
Split | +2.294 |
Neg logit contributions | |
expectations | -2.465 |
Wonderland | -2.376 |
Pepe | -2.313 |
UTERS | -2.303 |
gest | -2.244 |
Token | for |
Token ID | 329 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
expectations | +1.064 |
Wonderland | +0.995 |
Pepe | +0.985 |
UTERS | +0.948 |
gest | +0.933 |
Neg logit contributions | |
Reviewed | -1.558 |
itaire | -1.301 |
ippery | -1.184 |
Discuss | -1.172 |
Split | -1.165 |
Token | Play |
Token ID | 3811 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Reviewed | +0.097 |
itaire | +0.082 |
ippery | +0.074 |
Discuss | +0.073 |
Split | +0.073 |
Neg logit contributions | |
expectations | -0.064 |
Wonderland | -0.061 |
Pepe | -0.060 |
UTERS | -0.057 |
gest | -0.057 |
Token | St |
Token ID | 1273 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
expectations | +1.172 |
Wonderland | +1.123 |
Pepe | +1.090 |
gest | +1.073 |
UTERS | +1.055 |
Neg logit contributions | |
Reviewed | -1.490 |
itaire | -1.232 |
ippery | -1.116 |
Discuss | -1.092 |
Split | -1.061 |
Token | ations |
Token ID | 602 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Reviewed | +1.072 |
itaire | +0.871 |
ippery | +0.783 |
Discuss | +0.767 |
Split | +0.764 |
Neg logit contributions | |
expectations | -0.956 |
Wonderland | -0.912 |
Pepe | -0.900 |
UTERS | -0.881 |
gest | -0.866 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Reviewed | +1.243 |
itaire | +1.040 |
ippery | +0.939 |
Discuss | +0.925 |
Split | +0.920 |
Neg logit contributions | |
expectations | -0.876 |
Wonderland | -0.833 |
Pepe | -0.816 |
UTERS | -0.799 |
gest | -0.784 |
Token | has |
Token ID | 468 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Reviewed | +0.970 |
itaire | +0.804 |
ippery | +0.721 |
Discuss | +0.709 |
Split | +0.703 |
Neg logit contributions | |
expectations | -0.781 |
Wonderland | -0.745 |
Pepe | -0.732 |
UTERS | -0.711 |
gest | -0.701 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Reviewed | +1.284 |
itaire | +1.074 |
ippery | +0.968 |
Discuss | +0.953 |
Split | +0.948 |
Neg logit contributions | |
expectations | -0.919 |
Wonderland | -0.874 |
Pepe | -0.857 |
UTERS | -0.839 |
gest | -0.823 |
Token | she |
Token ID | 673 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
expectations | +1.352 |
Wonderland | +1.295 |
Pepe | +1.264 |
Kardashian | +1.206 |
UTERS | +1.200 |
Neg logit contributions | |
Reviewed | -1.835 |
itaire | -1.535 |
ippery | -1.362 |
Discuss | -1.338 |
Split | -1.337 |
Token | said |
Token ID | 531 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
expectations | +1.718 |
Wonderland | +1.621 |
Pepe | +1.590 |
gest | +1.528 |
Kardashian | +1.519 |
Neg logit contributions | |
Reviewed | -2.366 |
itaire | -1.993 |
ippery | -1.755 |
Split | -1.743 |
Discuss | -1.721 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
expectations | +1.328 |
Wonderland | +1.241 |
Pepe | +1.206 |
UTERS | +1.188 |
gest | +1.178 |
Neg logit contributions | |
Reviewed | -2.082 |
itaire | -1.758 |
ippery | -1.595 |
Split | -1.565 |
Gray | -1.548 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
expectations | +0.050 |
Wonderland | +0.049 |
Pepe | +0.048 |
UTERS | +0.046 |
gest | +0.046 |
Neg logit contributions | |
Reviewed | -0.055 |
itaire | -0.045 |
ippery | -0.040 |
Discuss | -0.039 |
Split | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
expectations | +1.306 |
Wonderland | +1.256 |
Pepe | +1.236 |
UTERS | +1.216 |
gest | +1.200 |
Neg logit contributions | |
Reviewed | -1.207 |
itaire | -0.969 |
ippery | -0.848 |
Discuss | -0.828 |
Split | -0.823 |
Token | " |
Token ID | 1 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
expectations | +0.778 |
Wonderland | +0.746 |
UTERS | +0.737 |
Pepe | +0.735 |
gest | +0.732 |
Neg logit contributions | |
Reviewed | -0.825 |
itaire | -0.686 |
ippery | -0.617 |
Split | -0.576 |
Discuss | -0.575 |
Token | Now |
Token ID | 3844 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Reviewed | +1.523 |
itaire | +1.203 |
Discuss | +1.044 |
Split | +1.037 |
ippery | +1.033 |
Neg logit contributions | |
expectations | -1.763 |
Wonderland | -1.693 |
Pepe | -1.665 |
UTERS | -1.634 |
gest | -1.606 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
Reviewed | +2.174 |
itaire | +1.819 |
ippery | +1.628 |
Discuss | +1.599 |
Split | +1.598 |
Neg logit contributions | |
expectations | -1.703 |
Wonderland | -1.635 |
Pepe | -1.599 |
UTERS | -1.582 |
gest | -1.548 |
Token | it |
Token ID | 340 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Reviewed | +0.118 |
itaire | +0.098 |
ippery | +0.088 |
Discuss | +0.087 |
Split | +0.086 |
Neg logit contributions | |
expectations | -0.088 |
Wonderland | -0.084 |
Pepe | -0.082 |
UTERS | -0.080 |
gest | -0.079 |
Token | seems |
Token ID | 2331 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
expectations | +1.539 |
Wonderland | +1.411 |
Pepe | +1.410 |
gest | +1.330 |
Kardashian | +1.303 |
Neg logit contributions | |
Reviewed | -2.643 |
itaire | -2.235 |
ippery | -2.005 |
Discuss | -1.987 |
Split | -1.974 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
expectations | +0.178 |
Wonderland | +0.169 |
Pepe | +0.166 |
UTERS | +0.162 |
gest | +0.161 |
Neg logit contributions | |
Reviewed | -0.226 |
itaire | -0.188 |
ippery | -0.168 |
Discuss | -0.164 |
Split | -0.164 |
Token | second |
Token ID | 1218 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
expectations | +0.700 |
Wonderland | +0.656 |
Pepe | +0.639 |
UTERS | +0.622 |
gest | +0.617 |
Neg logit contributions | |
Reviewed | -1.056 |
itaire | -0.887 |
ippery | -0.797 |
Discuss | -0.787 |
Split | -0.784 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
expectations | +1.785 |
Wonderland | +1.655 |
Pepe | +1.627 |
gest | +1.577 |
UTERS | +1.575 |
Neg logit contributions | |
Reviewed | -2.500 |
itaire | -2.097 |
ippery | -1.885 |
Split | -1.857 |
Discuss | -1.854 |
Token | they |
Token ID | 484 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
Reviewed | +1.727 |
itaire | +1.424 |
ippery | +1.270 |
Discuss | +1.249 |
Split | +1.242 |
Neg logit contributions | |
expectations | -1.449 |
Wonderland | -1.382 |
Pepe | -1.357 |
UTERS | -1.331 |
gest | -1.309 |
Token | were |
Token ID | 547 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
Reviewed | +0.049 |
itaire | +0.041 |
ippery | +0.037 |
Discuss | +0.036 |
Split | +0.036 |
Neg logit contributions | |
expectations | -0.039 |
Wonderland | -0.036 |
Pepe | -0.036 |
UTERS | -0.035 |
gest | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
expectations | +0.553 |
Wonderland | +0.520 |
Pepe | +0.515 |
UTERS | +0.497 |
gest | +0.493 |
Neg logit contributions | |
Reviewed | -0.720 |
itaire | -0.602 |
ippery | -0.539 |
Discuss | -0.528 |
Gray | -0.523 |
Token | diapers |
Token ID | 45162 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
expectations | +4.570 |
Wonderland | +4.442 |
Pepe | +4.149 |
gest | +4.009 |
Kardashian | +3.943 |
Neg logit contributions | |
Reviewed | -6.564 |
itaire | -5.260 |
ippery | -4.820 |
Discuss | -4.758 |
Gray | -4.704 |
Token | and |
Token ID | 290 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
expectations | +1.862 |
Wonderland | +1.721 |
Pepe | +1.692 |
UTERS | +1.632 |
gest | +1.629 |
Neg logit contributions | |
Reviewed | -2.989 |
itaire | -2.517 |
ippery | -2.291 |
Split | -2.253 |
Discuss | -2.236 |
Token | sand |
Token ID | 6450 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Reviewed | +0.546 |
itaire | +0.456 |
ippery | +0.411 |
Discuss | +0.405 |
Split | +0.402 |
Neg logit contributions | |
expectations | -0.406 |
Wonderland | -0.385 |
Pepe | -0.378 |
UTERS | -0.367 |
gest | -0.362 |
Token | boxes |
Token ID | 29305 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
expectations | +0.516 |
Wonderland | +0.478 |
Pepe | +0.472 |
UTERS | +0.457 |
gest | +0.456 |
Neg logit contributions | |
Reviewed | -0.850 |
itaire | -0.714 |
ippery | -0.660 |
Gray | -0.649 |
Discuss | -0.647 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Reviewed | +1.321 |
itaire | +1.108 |
ippery | +1.002 |
Discuss | +0.984 |
Split | +0.981 |
Neg logit contributions | |
expectations | -0.907 |
Wonderland | -0.861 |
Pepe | -0.844 |
UTERS | -0.824 |
gest | -0.810 |
Token | BN |
Token ID | 15766 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Reviewed | +0.255 |
itaire | +0.212 |
ippery | +0.190 |
Discuss | +0.186 |
Split | +0.184 |
Neg logit contributions | |
expectations | -0.202 |
Wonderland | -0.192 |
Pepe | -0.189 |
UTERS | -0.185 |
gest | -0.183 |
Token | / |
Token ID | 14 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
expectations | +1.444 |
Wonderland | +1.333 |
Pepe | +1.314 |
UTERS | +1.286 |
gest | +1.264 |
Neg logit contributions | |
Reviewed | -2.725 |
itaire | -2.338 |
ippery | -2.150 |
Discuss | -2.087 |
Split | -2.080 |
Token | SS |
Token ID | 5432 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Reviewed | +0.454 |
itaire | +0.369 |
ippery | +0.325 |
Discuss | +0.316 |
Split | +0.314 |
Neg logit contributions | |
expectations | -0.457 |
Wonderland | -0.439 |
Pepe | -0.431 |
UTERS | -0.425 |
gest | -0.421 |
Token | GN |
Token ID | 16630 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
expectations | +0.463 |
Wonderland | +0.444 |
Pepe | +0.436 |
UTERS | +0.427 |
gest | +0.422 |
Neg logit contributions | |
Reviewed | -0.485 |
itaire | -0.395 |
ippery | -0.350 |
Discuss | -0.340 |
Split | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Reviewed | +0.424 |
itaire | +0.360 |
ippery | +0.329 |
Discuss | +0.324 |
Split | +0.322 |
Neg logit contributions | |
expectations | -0.239 |
Wonderland | -0.225 |
Pepe | -0.220 |
UTERS | -0.215 |
gest | -0.210 |
Token | 52 |
Token ID | 6740 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
expectations | +0.555 |
Wonderland | +0.528 |
Pepe | +0.517 |
UTERS | +0.503 |
gest | +0.498 |
Neg logit contributions | |
Reviewed | -0.748 |
itaire | -0.624 |
ippery | -0.561 |
Discuss | -0.552 |
Split | -0.549 |
Token | SS |
Token ID | 6723 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
expectations | +4.630 |
Wonderland | +4.339 |
Pepe | +4.278 |
gest | +4.139 |
UTERS | +4.083 |
Neg logit contributions | |
Reviewed | -6.525 |
itaire | -5.472 |
ippery | -4.967 |
Discuss | -4.850 |
Split | -4.819 |
Token | N |
Token ID | 45 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Reviewed | +0.405 |
itaire | +0.329 |
ippery | +0.290 |
Discuss | +0.281 |
Split | +0.277 |
Neg logit contributions | |
expectations | -0.415 |
Wonderland | -0.399 |
Pepe | -0.391 |
UTERS | -0.385 |
gest | -0.381 |
Token | ) |
Token ID | 8 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Reviewed | +1.192 |
itaire | +1.006 |
ippery | +0.915 |
Discuss | +0.898 |
Split | +0.894 |
Neg logit contributions | |
expectations | -0.758 |
Wonderland | -0.717 |
Pepe | -0.702 |
UTERS | -0.688 |
gest | -0.674 |
Token | with |
Token ID | 351 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
Reviewed | +1.550 |
itaire | +1.295 |
ippery | +1.172 |
Discuss | +1.151 |
Split | +1.147 |
Neg logit contributions | |
expectations | -1.074 |
Wonderland | -1.012 |
Pepe | -0.994 |
UTERS | -0.971 |
gest | -0.960 |
Token | 92 |
Token ID | 10190 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Reviewed | +0.356 |
itaire | +0.295 |
ippery | +0.265 |
Discuss | +0.260 |
Split | +0.259 |
Neg logit contributions | |
expectations | -0.281 |
Wonderland | -0.266 |
Pepe | -0.261 |
UTERS | -0.255 |
gest | -0.252 |
Token | camera |
Token ID | 4676 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
expectations | +2.276 |
Wonderland | +2.134 |
Pepe | +2.087 |
gest | +2.003 |
Kardashian | +1.960 |
Neg logit contributions | |
Reviewed | -3.511 |
itaire | -2.965 |
ippery | -2.659 |
Discuss | -2.622 |
Split | -2.612 |
Token | will |
Token ID | 481 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Reviewed | +0.154 |
itaire | +0.128 |
ippery | +0.114 |
Discuss | +0.113 |
Split | +0.112 |
Neg logit contributions | |
expectations | -0.123 |
Wonderland | -0.116 |
Pepe | -0.114 |
UTERS | -0.111 |
gest | -0.110 |
Token | pan |
Token ID | 3425 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Reviewed | +2.015 |
itaire | +1.676 |
ippery | +1.505 |
Discuss | +1.484 |
Split | +1.477 |
Neg logit contributions | |
expectations | -1.555 |
Wonderland | -1.486 |
Pepe | -1.455 |
UTERS | -1.435 |
gest | -1.396 |
Token | over |
Token ID | 625 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
Reviewed | +0.870 |
itaire | +0.721 |
ippery | +0.644 |
Discuss | +0.635 |
Split | +0.629 |
Neg logit contributions | |
expectations | -0.689 |
Wonderland | -0.656 |
Pepe | -0.647 |
UTERS | -0.626 |
gest | -0.621 |
Token | or |
Token ID | 393 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Reviewed | +0.270 |
itaire | +0.223 |
ippery | +0.199 |
Discuss | +0.195 |
Split | +0.194 |
Neg logit contributions | |
expectations | -0.225 |
Wonderland | -0.215 |
Pepe | -0.212 |
UTERS | -0.202 |
gest | -0.202 |
Token | Lem |
Token ID | 20607 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
expectations | +1.071 |
Pepe | +1.012 |
Wonderland | +1.011 |
gest | +0.970 |
UTERS | +0.958 |
Neg logit contributions | |
Reviewed | -1.373 |
itaire | -1.132 |
ippery | -1.014 |
Discuss | -1.000 |
Gray | -0.988 |
Token | ony |
Token ID | 1647 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
expectations | +6.750 |
Wonderland | +6.380 |
Pepe | +6.362 |
gest | +6.196 |
Kardashian | +6.130 |
Neg logit contributions | |
Reviewed | -5.889 |
itaire | -4.478 |
Discuss | -3.873 |
Split | -3.829 |
ippery | -3.734 |
Token | will |
Token ID | 481 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
expectations | +1.151 |
Wonderland | +1.090 |
Pepe | +1.063 |
gest | +1.026 |
UTERS | +1.009 |
Neg logit contributions | |
Reviewed | -1.724 |
itaire | -1.450 |
ippery | -1.303 |
Discuss | -1.273 |
Split | -1.267 |
Token | walk |
Token ID | 2513 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
expectations | +0.067 |
Wonderland | +0.064 |
Pepe | +0.063 |
gest | +0.061 |
UTERS | +0.060 |
Neg logit contributions | |
Reviewed | -0.088 |
itaire | -0.073 |
ippery | -0.065 |
Discuss | -0.064 |
Split | -0.064 |
Token | into |
Token ID | 656 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
expectations | +3.653 |
Pepe | +3.404 |
Wonderland | +3.393 |
gest | +3.251 |
Kardashian | +3.193 |
Neg logit contributions | |
Reviewed | -4.960 |
itaire | -4.162 |
ippery | -3.754 |
Discuss | -3.689 |
Gray | -3.678 |
Token | a |
Token ID | 257 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
expectations | +1.683 |
Wonderland | +1.608 |
Pepe | +1.580 |
gest | +1.503 |
UTERS | +1.468 |
Neg logit contributions | |
Reviewed | -2.301 |
itaire | -1.926 |
ippery | -1.727 |
Discuss | -1.711 |
Split | -1.677 |
Token | - |
Token ID | 12 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
expectations | +1.713 |
Wonderland | +1.618 |
Pepe | +1.562 |
gest | +1.545 |
UTERS | +1.520 |
Neg logit contributions | |
Reviewed | -2.242 |
itaire | -1.883 |
ippery | -1.674 |
Discuss | -1.631 |
Split | -1.625 |
Token | effect |
Token ID | 10760 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
expectations | +0.394 |
Wonderland | +0.372 |
gest | +0.369 |
Pepe | +0.367 |
UTERS | +0.358 |
Neg logit contributions | |
Reviewed | -0.433 |
itaire | -0.359 |
ippery | -0.315 |
Split | -0.306 |
Discuss | -0.305 |
Token | as |
Token ID | 355 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Reviewed | +1.933 |
itaire | +1.626 |
ippery | +1.471 |
Discuss | +1.448 |
Split | +1.441 |
Neg logit contributions | |
expectations | -1.289 |
Wonderland | -1.224 |
Pepe | -1.197 |
UTERS | -1.171 |
gest | -1.150 |
Token | you |
Token ID | 345 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Reviewed | +4.814 |
itaire | +3.914 |
ippery | +3.534 |
Discuss | +3.500 |
Split | +3.480 |
Neg logit contributions | |
expectations | -4.014 |
Wonderland | -3.890 |
Pepe | -3.832 |
UTERS | -3.792 |
gest | -3.703 |
Token | can |
Token ID | 460 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Reviewed | +0.281 |
itaire | +0.237 |
ippery | +0.213 |
Discuss | +0.209 |
Split | +0.209 |
Neg logit contributions | |
expectations | -0.194 |
Wonderland | -0.184 |
Pepe | -0.179 |
UTERS | -0.174 |
gest | -0.174 |
Token | see |
Token ID | 766 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
expectations | +1.904 |
Wonderland | +1.808 |
Pepe | +1.783 |
gest | +1.742 |
UTERS | +1.732 |
Neg logit contributions | |
Reviewed | -1.727 |
itaire | -1.389 |
ippery | -1.212 |
Split | -1.186 |
Discuss | -1.177 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
expectations | +4.088 |
Wonderland | +3.672 |
Pepe | +3.646 |
gest | +3.516 |
Kardashian | +3.406 |
Neg logit contributions | |
Reviewed | -6.983 |
itaire | -6.022 |
ippery | -5.450 |
Split | -5.235 |
Gray | -5.210 |
Token | This |
Token ID | 770 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
expectations | +1.183 |
Wonderland | +1.145 |
Pepe | +1.123 |
gest | +1.079 |
UTERS | +1.078 |
Neg logit contributions | |
Reviewed | -1.524 |
itaire | -1.284 |
ippery | -1.160 |
Discuss | -1.110 |
Split | -1.098 |
Token | screen |
Token ID | 3159 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
expectations | +1.392 |
Wonderland | +1.303 |
Pepe | +1.285 |
gest | +1.244 |
UTERS | +1.224 |
Neg logit contributions | |
Reviewed | -1.636 |
itaire | -1.387 |
ippery | -1.225 |
Discuss | -1.190 |
Split | -1.182 |
Token | also |
Token ID | 635 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
Reviewed | +0.217 |
itaire | +0.176 |
ippery | +0.156 |
Discuss | +0.152 |
Split | +0.151 |
Neg logit contributions | |
expectations | -0.214 |
Wonderland | -0.202 |
Pepe | -0.199 |
UTERS | -0.194 |
gest | -0.193 |
Token | includes |
Token ID | 3407 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
Reviewed | +0.333 |
itaire | +0.285 |
ippery | +0.261 |
Discuss | +0.257 |
Split | +0.255 |
Neg logit contributions | |
expectations | -0.170 |
Wonderland | -0.158 |
Pepe | -0.154 |
UTERS | -0.148 |
gest | -0.146 |
Token | mentioned |
Token ID | 17181 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
expectations | +1.126 |
Wonderland | +1.063 |
Pepe | +1.039 |
gest | +1.023 |
UTERS | +1.013 |
Neg logit contributions | |
Reviewed | -1.588 |
itaire | -1.329 |
ippery | -1.206 |
Discuss | -1.181 |
Split | -1.179 |
Token | until |
Token ID | 1566 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
expectations | +1.627 |
Wonderland | +1.505 |
Pepe | +1.483 |
gest | +1.420 |
UTERS | +1.413 |
Neg logit contributions | |
Reviewed | -2.522 |
itaire | -2.141 |
ippery | -1.925 |
Split | -1.880 |
Gray | -1.871 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
expectations | +0.344 |
Wonderland | +0.326 |
Pepe | +0.320 |
UTERS | +0.307 |
gest | +0.304 |
Neg logit contributions | |
Reviewed | -0.475 |
itaire | -0.401 |
ippery | -0.360 |
Split | -0.352 |
Discuss | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
expectations | +1.676 |
Wonderland | +1.581 |
Pepe | +1.551 |
UTERS | +1.507 |
gest | +1.478 |
Neg logit contributions | |
Reviewed | -2.501 |
itaire | -2.130 |
ippery | -1.916 |
Discuss | -1.866 |
Split | -1.854 |
Token | when |
Token ID | 618 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
expectations | +1.743 |
Wonderland | +1.644 |
Pepe | +1.638 |
gest | +1.557 |
UTERS | +1.542 |
Neg logit contributions | |
Reviewed | -2.416 |
itaire | -2.044 |
ippery | -1.793 |
Split | -1.761 |
Discuss | -1.757 |
Token | Cue |
Token ID | 40568 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
expectations | +0.440 |
Wonderland | +0.416 |
Pepe | +0.411 |
UTERS | +0.393 |
gest | +0.389 |
Neg logit contributions | |
Reviewed | -0.578 |
itaire | -0.481 |
ippery | -0.433 |
Split | -0.423 |
Discuss | -0.420 |
Token | ll |
Token ID | 297 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
expectations | +3.068 |
Pepe | +2.838 |
Wonderland | +2.828 |
gest | +2.771 |
UTERS | +2.679 |
Neg logit contributions | |
Reviewed | -7.256 |
itaire | -6.258 |
ippery | -5.724 |
oun | -5.619 |
Split | -5.585 |
Token | ar |
Token ID | 283 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
expectations | +0.923 |
Wonderland | +0.874 |
Pepe | +0.852 |
UTERS | +0.835 |
gest | +0.813 |
Neg logit contributions | |
Reviewed | -1.583 |
itaire | -1.342 |
ippery | -1.223 |
Discuss | -1.209 |
Split | -1.202 |
Token | and |
Token ID | 290 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
expectations | +0.826 |
Wonderland | +0.780 |
Pepe | +0.765 |
gest | +0.731 |
UTERS | +0.730 |
Neg logit contributions | |
Reviewed | -1.244 |
itaire | -1.058 |
ippery | -0.953 |
Split | -0.928 |
Discuss | -0.927 |
Token | Julio |
Token ID | 48273 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
expectations | +1.760 |
Wonderland | +1.653 |
Pepe | +1.623 |
UTERS | +1.537 |
gest | +1.511 |
Neg logit contributions | |
Reviewed | -3.032 |
itaire | -2.557 |
ippery | -2.326 |
Split | -2.290 |
Discuss | -2.271 |
Token | announced |
Token ID | 3414 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
expectations | +2.031 |
Wonderland | +1.917 |
Pepe | +1.897 |
UTERS | +1.813 |
gest | +1.806 |
Neg logit contributions | |
Reviewed | -2.787 |
itaire | -2.359 |
ippery | -2.119 |
Discuss | -2.043 |
Split | -2.035 |