Token | to |
Token ID | 284 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Duo | +0.524 |
enf | +0.493 |
Phi | +0.486 |
agra | +0.480 |
eny | +0.470 |
Neg logit contributions | |
gement | -0.567 |
llah | -0.547 |
gment | -0.522 |
Brit | -0.516 |
Asset | -0.500 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
gement | +1.194 |
llah | +1.146 |
gment | +1.099 |
Brit | +1.079 |
Asset | +1.046 |
Neg logit contributions | |
Duo | -1.040 |
enf | -0.992 |
agra | -0.968 |
Phi | -0.963 |
eny | -0.940 |
Token | this |
Token ID | 428 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
gement | +2.584 |
llah | +2.423 |
gment | +2.351 |
Brit | +2.304 |
Asset | +2.252 |
Neg logit contributions | |
Duo | -2.676 |
enf | -2.613 |
agra | -2.543 |
Phi | -2.470 |
eny | -2.465 |
Token | contest |
Token ID | 8414 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
gement | +6.327 |
llah | +5.810 |
gment | +5.759 |
Brit | +5.535 |
Asset | +5.469 |
Neg logit contributions | |
Duo | -6.206 |
enf | -6.204 |
agra | -6.037 |
eny | -5.830 |
eless | -5.762 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
gement | +3.435 |
llah | +3.291 |
gment | +3.162 |
Brit | +3.059 |
Asset | +2.989 |
Neg logit contributions | |
Duo | -3.639 |
enf | -3.546 |
agra | -3.449 |
Phi | -3.384 |
eny | -3.365 |
Token | - |
Token ID | 12 |
Feature activation | +2.34e+01 |
Pos logit contributions | |
gement | +8.373 |
llah | +7.865 |
gment | +7.564 |
Asset | +7.350 |
Brit | +7.246 |
Neg logit contributions | |
agra | -8.109 |
enf | -8.064 |
Duo | -7.945 |
eny | -7.667 |
eless | -7.416 |
Token | un |
Token ID | 403 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
gement | +14.323 |
Asset | +13.496 |
llah | +13.375 |
Brit | +13.370 |
priv | +13.003 |
Neg logit contributions | |
Duo | -12.536 |
agra | -12.515 |
Phi | -12.178 |
enf | -12.045 |
eny | -11.756 |
Token | iverse |
Token ID | 3997 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
gement | +5.535 |
llah | +5.425 |
gment | +5.179 |
Brit | +5.138 |
Asset | +4.902 |
Neg logit contributions | |
Duo | -4.787 |
agra | -4.399 |
enf | -4.388 |
Phi | -4.371 |
eny | -4.079 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
gement | +1.336 |
llah | +1.283 |
gment | +1.223 |
Brit | +1.213 |
Asset | +1.172 |
Neg logit contributions | |
Duo | -1.290 |
enf | -1.227 |
Phi | -1.196 |
agra | -1.193 |
eny | -1.168 |
Token | If |
Token ID | 1532 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
gement | +1.965 |
llah | +1.885 |
Brit | +1.809 |
gment | +1.791 |
Asset | +1.753 |
Neg logit contributions | |
Duo | -2.013 |
enf | -1.939 |
agra | -1.897 |
Phi | -1.867 |
eny | -1.850 |
Token | you |
Token ID | 345 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Duo | +3.482 |
Phi | +3.231 |
enf | +3.223 |
agra | +3.116 |
eny | +3.104 |
Neg logit contributions | |
gement | -3.657 |
llah | -3.568 |
gment | -3.379 |
Brit | -3.347 |
Asset | -3.211 |
Token | = |
Token ID | 796 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
gement | +4.490 |
llah | +4.306 |
Brit | +4.255 |
gment | +4.105 |
Asset | +4.053 |
Neg logit contributions | |
Duo | -7.252 |
enf | -7.036 |
agra | -6.796 |
eny | -6.711 |
conduc | -6.574 |
Token | c |
Token ID | 269 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
gement | +5.498 |
llah | +5.244 |
gment | +5.163 |
Brit | +4.938 |
Asset | +4.723 |
Neg logit contributions | |
Duo | -5.236 |
enf | -5.154 |
agra | -4.987 |
eny | -4.984 |
Phi | -4.763 |
Token | v |
Token ID | 85 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
gement | +3.841 |
gment | +3.604 |
llah | +3.425 |
Brit | +3.268 |
Asset | +2.987 |
Neg logit contributions | |
Duo | -8.274 |
Phi | -7.860 |
conduc | -7.748 |
enf | -7.732 |
agra | -7.691 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Duo | +0.345 |
enf | +0.323 |
Phi | +0.315 |
agra | +0.313 |
eny | +0.305 |
Neg logit contributions | |
gement | -0.491 |
llah | -0.474 |
gment | -0.454 |
Brit | -0.449 |
Asset | -0.437 |
Token | . |
Token ID | 13 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Duo | +0.808 |
enf | +0.764 |
Phi | +0.750 |
agra | +0.742 |
eny | +0.728 |
Neg logit contributions | |
gement | -0.886 |
llah | -0.849 |
gment | -0.811 |
Brit | -0.800 |
Asset | -0.774 |
Token | get |
Token ID | 1136 |
Feature activation | +2.33e+01 |
Pos logit contributions | |
gement | +0.797 |
llah | +0.773 |
gment | +0.751 |
Brit | +0.745 |
Asset | +0.727 |
Neg logit contributions | |
Duo | -0.325 |
enf | -0.293 |
Phi | -0.285 |
agra | -0.280 |
eny | -0.269 |
Token | Struct |
Token ID | 44909 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
Struct | +9.305 |
Asset | +7.406 |
Brit | +6.078 |
struct | +5.193 |
gment | +5.126 |
Neg logit contributions | |
conduc | -21.425 |
awa | -21.269 |
unbeliev | -21.167 |
Duo | -20.817 |
skelet | -20.229 |
Token | uring |
Token ID | 870 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
gement | +2.904 |
llah | +2.700 |
gment | +2.683 |
Asset | +2.538 |
Brit | +2.536 |
Neg logit contributions | |
Duo | -3.059 |
enf | -2.830 |
Phi | -2.797 |
agra | -2.748 |
cf | -2.700 |
Token | Element |
Token ID | 20180 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
Asset | +6.341 |
gement | +6.210 |
gment | +5.821 |
llah | +5.739 |
Brit | +5.658 |
Neg logit contributions | |
conduc | -14.084 |
Duo | -14.081 |
agra | -13.854 |
enf | -13.560 |
awa | -13.219 |
Token | ( |
Token ID | 7 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
gement | +2.902 |
llah | +2.810 |
Brit | +2.698 |
gment | +2.669 |
Asset | +2.600 |
Neg logit contributions | |
Duo | -2.909 |
enf | -2.763 |
agra | -2.715 |
Phi | -2.700 |
eny | -2.656 |
Token | cv |
Token ID | 33967 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Duo | +0.221 |
enf | +0.208 |
Phi | +0.203 |
agra | +0.202 |
eny | +0.197 |
Neg logit contributions | |
gement | -0.299 |
llah | -0.289 |
gment | -0.277 |
Brit | -0.274 |
Asset | -0.267 |
Token | sum |
Token ID | 2160 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Duo | +2.326 |
Phi | +2.155 |
enf | +2.153 |
agra | +2.115 |
eny | +2.096 |
Neg logit contributions | |
gement | -2.838 |
llah | -2.772 |
Brit | -2.642 |
gment | -2.627 |
Asset | -2.543 |
Token | of |
Token ID | 286 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
Duo | +1.145 |
enf | +1.080 |
Phi | +1.058 |
agra | +1.052 |
eny | +1.039 |
Neg logit contributions | |
gement | -1.226 |
llah | -1.177 |
gment | -1.123 |
Brit | -1.120 |
Asset | -1.082 |
Token | money |
Token ID | 1637 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
Duo | +2.147 |
enf | +1.998 |
Phi | +1.973 |
agra | +1.966 |
eny | +1.924 |
Neg logit contributions | |
gement | -2.534 |
llah | -2.461 |
gment | -2.360 |
Brit | -2.340 |
Asset | -2.262 |
Token | ," |
Token ID | 553 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Duo | +0.641 |
enf | +0.604 |
Phi | +0.593 |
agra | +0.589 |
eny | +0.578 |
Neg logit contributions | |
gement | -0.678 |
llah | -0.652 |
gment | -0.622 |
Brit | -0.617 |
Asset | -0.596 |
Token | the |
Token ID | 262 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
gement | +8.595 |
llah | +7.857 |
gment | +7.522 |
Asset | +7.024 |
Brit | +6.949 |
Neg logit contributions | |
enf | -10.429 |
Duo | -10.352 |
agra | -10.162 |
eny | -10.060 |
Phi | -9.820 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.29e+01 |
Pos logit contributions | |
gement | +4.361 |
llah | +3.951 |
gment | +3.815 |
Brit | +3.594 |
Asset | +3.361 |
Neg logit contributions | |
Duo | -7.566 |
enf | -7.525 |
eny | -7.246 |
agra | -7.205 |
Phi | -7.193 |
Token | said |
Token ID | 531 |
Feature activation | +9.55e+00 |
Pos logit contributions | |
gement | +10.165 |
gment | +8.889 |
llah | +7.983 |
Roy | +7.634 |
warranty | +7.496 |
Neg logit contributions | |
enf | -17.510 |
Duo | -16.432 |
eno | -16.037 |
Phi | -15.916 |
Pros | -15.745 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
gement | +5.795 |
llah | +5.441 |
gment | +5.290 |
Brit | +5.018 |
Asset | +4.862 |
Neg logit contributions | |
Duo | -7.366 |
enf | -7.312 |
Phi | -6.956 |
agra | -6.859 |
eny | -6.760 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
gement | +3.580 |
llah | +3.422 |
gment | +3.212 |
Brit | +3.201 |
Asset | +3.099 |
Neg logit contributions | |
Duo | -4.245 |
enf | -4.036 |
Phi | -3.971 |
agra | -3.948 |
eny | -3.915 |
Token |
|
Token ID | 198 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Duo | +0.338 |
enf | +0.320 |
Phi | +0.315 |
agra | +0.312 |
eny | +0.306 |
Neg logit contributions | |
gement | -0.337 |
llah | -0.323 |
gment | -0.308 |
Brit | -0.303 |
Asset | -0.293 |
Token | " |
Token ID | 1 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
gement | +4.035 |
llah | +3.830 |
Brit | +3.756 |
gment | +3.656 |
Asset | +3.646 |
Neg logit contributions | |
Duo | -4.167 |
Phi | -3.875 |
enf | -3.830 |
agra | -3.769 |
eny | -3.726 |
Token | [ |
Token ID | 685 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
gement | +4.675 |
gment | +4.180 |
llah | +3.984 |
Asset | +3.686 |
�� | +3.241 |
Neg logit contributions | |
enf | -10.444 |
Duo | -10.422 |
agra | -10.198 |
eny | -9.705 |
cum | -9.687 |
Token | return |
Token ID | 7783 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
gement | +5.612 |
llah | +5.247 |
gment | +5.181 |
Asset | +4.983 |
Brit | +4.889 |
Neg logit contributions | |
Duo | -6.034 |
Phi | -5.565 |
agra | -5.554 |
enf | -5.538 |
Solo | -5.222 |
Token | address |
Token ID | 2209 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
gement | +7.381 |
llah | +6.934 |
gment | +6.787 |
Asset | +6.283 |
warranty | +6.211 |
Neg logit contributions | |
Duo | -8.432 |
agra | -8.333 |
enf | -8.234 |
glers | -7.802 |
cum | -7.781 |
Token | ] |
Token ID | 60 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
gement | +4.033 |
llah | +3.754 |
gment | +3.613 |
Brit | +3.431 |
Asset | +3.358 |
Neg logit contributions | |
Duo | -7.727 |
enf | -7.596 |
agra | -7.560 |
eny | -7.265 |
Phi | -7.210 |
Token | | |
Token ID | 930 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
gement | +3.921 |
llah | +3.714 |
Brit | +3.442 |
gment | +3.383 |
Asset | +3.333 |
Neg logit contributions | |
Duo | -8.696 |
enf | -8.592 |
agra | -8.437 |
Phi | -8.279 |
eny | -8.225 |
Token | + |
Token ID | 1343 |
Feature activation | +2.28e+01 |
Pos logit contributions | |
gement | +5.311 |
llah | +4.990 |
gment | +4.761 |
Brit | +4.740 |
Asset | +4.703 |
Neg logit contributions | |
enf | -6.017 |
Duo | -5.948 |
agra | -5.796 |
eny | -5.683 |
Phi | -5.541 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
gement | +6.768 |
llah | +6.096 |
Brit | +5.734 |
Asset | +5.617 |
gment | +5.288 |
Neg logit contributions | |
Duo | -21.371 |
conduc | -20.687 |
unbeliev | -20.167 |
skelet | -19.633 |
Phi | -19.479 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
gement | +5.090 |
llah | +4.869 |
Brit | +4.628 |
gment | +4.615 |
Asset | +4.506 |
Neg logit contributions | |
Duo | -7.157 |
enf | -6.698 |
Phi | -6.515 |
Solo | -6.430 |
agra | -6.406 |
Token | + |
Token ID | 1343 |
Feature activation | +1.82e+01 |
Pos logit contributions | |
gement | +3.554 |
llah | +3.407 |
Brit | +3.243 |
gment | +3.232 |
Asset | +3.142 |
Neg logit contributions | |
Duo | -3.523 |
enf | -3.477 |
agra | -3.364 |
eny | -3.311 |
Phi | -3.258 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +7.54e+00 |
Pos logit contributions | |
gement | +6.315 |
llah | +5.832 |
Brit | +5.492 |
Asset | +5.352 |
gment | +5.110 |
Neg logit contributions | |
Duo | -17.413 |
conduc | -16.468 |
Phi | -15.909 |
unbeliev | -15.879 |
Solo | -15.586 |
Token | --+ |
Token ID | 44785 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
gement | +4.592 |
llah | +4.379 |
gment | +4.191 |
Brit | +4.141 |
Asset | +4.038 |
Neg logit contributions | |
Duo | -6.036 |
enf | -5.627 |
Phi | -5.487 |
Solo | -5.398 |
agra | -5.388 |
Token | # |
Token ID | 1303 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
gement | +7.634 |
gment | +7.099 |
llah | +7.006 |
Brit | +6.330 |
warranty | +6.260 |
Neg logit contributions | |
Duo | -10.021 |
enf | -9.782 |
eny | -9.373 |
agra | -9.099 |
Phi | -8.960 |
Token | initialize |
Token ID | 41216 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
gement | +2.769 |
llah | +2.669 |
gment | +2.517 |
Brit | +2.355 |
Asset | +2.317 |
Neg logit contributions | |
Duo | -4.162 |
enf | -3.988 |
agra | -3.939 |
Phi | -3.878 |
eny | -3.771 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
gement | +5.156 |
llah | +4.944 |
gment | +4.616 |
Brit | +4.510 |
Asset | +4.471 |
Neg logit contributions | |
Duo | -8.436 |
enf | -8.191 |
agra | -8.102 |
eny | -7.842 |
Phi | -7.814 |
Token | rectangular |
Token ID | 36954 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
gement | +6.805 |
gment | +6.338 |
llah | +6.202 |
Brit | +5.460 |
warranty | +5.284 |
Neg logit contributions | |
enf | -10.681 |
Duo | -10.238 |
agra | -10.059 |
eny | -10.046 |
glers | -9.858 |
Token | and |
Token ID | 290 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
gement | +6.143 |
llah | +5.894 |
gment | +5.620 |
Asset | +5.145 |
Brit | +5.077 |
Neg logit contributions | |
Duo | -9.512 |
enf | -9.378 |
agra | -9.169 |
eny | -8.949 |
Phi | -8.672 |
Token | square |
Token ID | 6616 |
Feature activation | +2.28e+01 |
Pos logit contributions | |
gement | +4.887 |
llah | +4.576 |
gment | +4.434 |
Brit | +4.314 |
Asset | +4.116 |
Neg logit contributions | |
Duo | -6.199 |
enf | -6.056 |
agra | -5.682 |
eny | -5.667 |
Phi | -5.652 |
Token | struct |
Token ID | 2878 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Struct | +3.812 |
gement | +3.654 |
warranty | +3.538 |
gment | +3.201 |
llah | +3.065 |
Neg logit contributions | |
Duo | -21.874 |
enf | -21.548 |
agra | -21.264 |
eny | -21.248 |
glers | -21.205 |
Token | uring |
Token ID | 870 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
gement | +2.679 |
llah | +2.506 |
gment | +2.482 |
Brit | +2.369 |
Asset | +2.316 |
Neg logit contributions | |
Duo | -2.787 |
enf | -2.613 |
Phi | -2.557 |
agra | -2.547 |
eny | -2.485 |
Token | kernel |
Token ID | 9720 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
gement | +3.964 |
llah | +3.914 |
gment | +3.509 |
warranty | +3.157 |
GPU | +2.703 |
Neg logit contributions | |
agra | -13.649 |
Duo | -13.629 |
enf | -13.539 |
Cosponsors | -13.080 |
eny | -13.031 |
Token | rect |
Token ID | 13621 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
gement | +6.052 |
gment | +5.311 |
llah | +5.174 |
rect | +4.584 |
warranty | +4.554 |
Neg logit contributions | |
Duo | -14.643 |
enf | -14.532 |
agra | -14.055 |
eny | -13.801 |
glers | -13.785 |
Token | K |
Token ID | 42 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
gement | +1.609 |
llah | +1.551 |
Brit | +1.500 |
gment | +1.494 |
Asset | +1.454 |
Neg logit contributions | |
Duo | -1.312 |
enf | -1.243 |
agra | -1.202 |
Phi | -1.194 |
eny | -1.177 |
Token | - |
Token ID | 12 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
gement | +0.286 |
llah | +0.274 |
gment | +0.262 |
Brit | +0.260 |
Asset | +0.251 |
Neg logit contributions | |
Duo | -0.263 |
enf | -0.249 |
Phi | -0.243 |
agra | -0.243 |
eny | -0.237 |
Token | Cook |
Token ID | 28937 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
gement | +0.670 |
llah | +0.645 |
gment | +0.617 |
Brit | +0.614 |
Asset | +0.594 |
Neg logit contributions | |
Duo | -0.573 |
enf | -0.538 |
Phi | -0.528 |
agra | -0.525 |
eny | -0.512 |
Token | man |
Token ID | 805 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Duo | +4.100 |
Phi | +3.853 |
enf | +3.835 |
agra | +3.708 |
eny | +3.648 |
Neg logit contributions | |
gement | -4.046 |
llah | -3.872 |
gment | -3.673 |
Brit | -3.652 |
Asset | -3.471 |
Token | University |
Token ID | 2059 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
Duo | +1.087 |
enf | +1.024 |
Phi | +1.013 |
agra | +0.994 |
eny | +0.977 |
Neg logit contributions | |
gement | -1.100 |
llah | -1.053 |
gment | -1.006 |
Brit | -0.995 |
Asset | -0.959 |
Token | celebrated |
Token ID | 13943 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
Duo | +0.672 |
enf | +0.635 |
Phi | +0.628 |
agra | +0.617 |
eny | +0.608 |
Neg logit contributions | |
gement | -0.662 |
llah | -0.636 |
gment | -0.605 |
Brit | -0.598 |
Asset | -0.577 |
Token | its |
Token ID | 663 |
Feature activation | +2.21e+01 |
Pos logit contributions | |
gement | +5.056 |
llah | +4.788 |
Brit | +4.592 |
gment | +4.513 |
Asset | +4.338 |
Neg logit contributions | |
Duo | -5.778 |
enf | -5.749 |
agra | -5.601 |
eny | -5.367 |
cum | -5.305 |
Token | hundred |
Token ID | 3470 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
gement | +11.500 |
llah | +10.185 |
Brit | +10.148 |
Roy | +9.804 |
gment | +9.732 |
Neg logit contributions | |
enf | -13.996 |
agra | -13.920 |
eless | -13.437 |
Duo | -13.370 |
cum | -13.318 |
Token | th |
Token ID | 400 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
gement | +4.702 |
llah | +4.431 |
gment | +4.197 |
Brit | +4.063 |
Asset | +3.896 |
Neg logit contributions | |
Duo | -6.419 |
enf | -6.081 |
agra | -6.018 |
Phi | -5.880 |
eny | -5.779 |
Token | anniversary |
Token ID | 11162 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
gement | +5.602 |
llah | +5.010 |
gment | +4.842 |
Brit | +4.749 |
Asset | +4.565 |
Neg logit contributions | |
Duo | -9.775 |
enf | -9.760 |
agra | -9.758 |
eny | -9.278 |
eless | -9.077 |
Token | from |
Token ID | 422 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
gement | +5.563 |
llah | +5.224 |
gment | +5.069 |
Brit | +5.003 |
Asset | +4.624 |
Neg logit contributions | |
Duo | -6.147 |
enf | -6.028 |
agra | -5.901 |
eless | -5.571 |
eny | -5.551 |
Token | its |
Token ID | 663 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
gement | +2.818 |
llah | +2.680 |
gment | +2.574 |
Brit | +2.542 |
Asset | +2.437 |
Neg logit contributions | |
Duo | -2.631 |
enf | -2.578 |
agra | -2.481 |
eny | -2.419 |
eless | -2.381 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Duo | +0.707 |
enf | +0.668 |
Phi | +0.654 |
agra | +0.651 |
eny | +0.638 |
Neg logit contributions | |
gement | -0.712 |
llah | -0.685 |
gment | -0.652 |
Brit | -0.648 |
Asset | -0.624 |
Token | the |
Token ID | 262 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
Duo | +0.072 |
enf | +0.068 |
Phi | +0.067 |
agra | +0.067 |
eny | +0.065 |
Neg logit contributions | |
gement | -0.078 |
llah | -0.075 |
gment | -0.072 |
Brit | -0.071 |
Asset | -0.069 |
Token | state |
Token ID | 1181 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
gement | +5.473 |
llah | +5.218 |
gment | +4.952 |
Brit | +4.880 |
Asset | +4.692 |
Neg logit contributions | |
Duo | -5.444 |
enf | -5.232 |
Phi | -5.065 |
agra | -5.014 |
eny | -4.961 |
Token | ," |
Token ID | 553 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Duo | +1.745 |
enf | +1.647 |
Phi | +1.612 |
agra | +1.609 |
eny | +1.580 |
Neg logit contributions | |
gement | -1.767 |
llah | -1.696 |
gment | -1.616 |
Brit | -1.609 |
Asset | -1.548 |
Token | the |
Token ID | 262 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
gement | +8.077 |
llah | +7.271 |
gment | +7.110 |
Asset | +6.641 |
Brit | +6.633 |
Neg logit contributions | |
enf | -9.438 |
Duo | -9.265 |
agra | -9.146 |
eny | -9.042 |
Phi | -8.842 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
gement | +4.697 |
llah | +4.258 |
gment | +4.132 |
Brit | +3.928 |
Asset | +3.636 |
Neg logit contributions | |
enf | -7.309 |
Duo | -7.252 |
eny | -6.997 |
Phi | -6.938 |
agra | -6.924 |
Token | said |
Token ID | 531 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
gement | +10.429 |
gment | +9.254 |
llah | +8.221 |
Roy | +7.979 |
Brit | +7.740 |
Neg logit contributions | |
enf | -16.618 |
Duo | -15.376 |
eno | -15.200 |
Phi | -14.938 |
eny | -14.845 |
Token | . |
Token ID | 13 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
gement | +6.316 |
llah | +5.869 |
gment | +5.761 |
Brit | +5.412 |
Asset | +5.263 |
Neg logit contributions | |
enf | -7.720 |
Duo | -7.654 |
Phi | -7.220 |
agra | -7.188 |
eny | -7.128 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
gement | +4.842 |
llah | +4.613 |
Brit | +4.349 |
gment | +4.309 |
Asset | +4.186 |
Neg logit contributions | |
Duo | -5.984 |
enf | -5.770 |
eny | -5.650 |
agra | -5.649 |
Phi | -5.647 |
Token |
|
Token ID | 198 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
gement | +1.317 |
llah | +1.269 |
Brit | +1.203 |
gment | +1.200 |
Asset | +1.155 |
Neg logit contributions | |
Duo | -1.515 |
enf | -1.447 |
agra | -1.418 |
Phi | -1.411 |
eny | -1.389 |
Token | The |
Token ID | 464 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
gement | +4.730 |
llah | +4.459 |
Brit | +4.444 |
Asset | +4.289 |
gment | +4.272 |
Neg logit contributions | |
Duo | -5.002 |
Phi | -4.663 |
enf | -4.582 |
agra | -4.523 |
eny | -4.484 |
Token | from |
Token ID | 422 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Duo | +3.057 |
Phi | +2.849 |
enf | +2.807 |
agra | +2.739 |
cum | +2.682 |
Neg logit contributions | |
gement | -4.731 |
llah | -4.623 |
Brit | -4.427 |
gment | -4.420 |
Asset | -4.316 |
Token | an |
Token ID | 281 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Duo | +1.480 |
enf | +1.372 |
Phi | +1.372 |
agra | +1.360 |
eny | +1.320 |
Neg logit contributions | |
gement | -1.675 |
llah | -1.615 |
gment | -1.538 |
Brit | -1.525 |
Asset | -1.483 |
Token | out |
Token ID | 503 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Duo | +0.235 |
enf | +0.222 |
Phi | +0.219 |
agra | +0.217 |
eny | +0.213 |
Neg logit contributions | |
gement | -0.234 |
llah | -0.224 |
gment | -0.214 |
Brit | -0.212 |
Asset | -0.204 |
Token | - |
Token ID | 12 |
Feature activation | +9.57e+00 |
Pos logit contributions | |
gement | +1.905 |
llah | +1.808 |
gment | +1.741 |
Brit | +1.713 |
Asset | +1.640 |
Neg logit contributions | |
Duo | -2.105 |
enf | -1.999 |
Phi | -1.964 |
agra | -1.944 |
eny | -1.916 |
Token | of |
Token ID | 1659 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
gement | +5.855 |
Brit | +5.601 |
gment | +5.471 |
llah | +5.412 |
Asset | +5.206 |
Neg logit contributions | |
Duo | -7.620 |
Phi | -7.106 |
enf | -6.906 |
agra | -6.833 |
eny | -6.726 |
Token | - |
Token ID | 12 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
gement | +7.283 |
llah | +6.842 |
gment | +6.667 |
warranty | +6.331 |
Brit | +6.313 |
Neg logit contributions | |
Duo | -15.748 |
enf | -15.181 |
eny | -14.723 |
conduc | -14.577 |
Cosponsors | -14.373 |
Token | comp |
Token ID | 5589 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Brit | +11.043 |
gement | +10.515 |
priv | +10.220 |
home | +10.148 |
gment | +10.112 |
Neg logit contributions | |
Duo | -16.155 |
Phi | -14.669 |
Cosponsors | -14.272 |
eny | -14.187 |
Solo | -13.939 |
Token | etition |
Token ID | 15620 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
gement | +2.383 |
llah | +2.244 |
gment | +2.202 |
Brit | +2.140 |
Asset | +2.068 |
Neg logit contributions | |
Duo | -2.388 |
enf | -2.269 |
Phi | -2.257 |
agra | -2.208 |
eny | -2.140 |
Token | test |
Token ID | 1332 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
gement | +1.079 |
llah | +1.031 |
gment | +0.990 |
Brit | +0.974 |
Asset | +0.936 |
Neg logit contributions | |
Duo | -1.065 |
enf | -1.020 |
agra | -0.988 |
Phi | -0.988 |
eny | -0.971 |
Token | conducted |
Token ID | 5952 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
gement | +1.534 |
llah | +1.465 |
gment | +1.407 |
Brit | +1.389 |
Asset | +1.327 |
Neg logit contributions | |
Duo | -1.465 |
enf | -1.399 |
Phi | -1.361 |
agra | -1.359 |
eny | -1.329 |
Token | on |
Token ID | 319 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Duo | +3.989 |
Phi | +3.654 |
agra | +3.595 |
enf | +3.563 |
eny | +3.475 |
Neg logit contributions | |
gement | -5.433 |
llah | -5.295 |
gment | -5.021 |
Asset | -4.985 |
Brit | -4.968 |
Token | can |
Token ID | 460 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
gement | +4.464 |
llah | +4.236 |
gment | +4.089 |
Brit | +4.014 |
Asset | +3.872 |
Neg logit contributions | |
Duo | -5.069 |
enf | -4.772 |
Phi | -4.710 |
agra | -4.698 |
eny | -4.573 |
Token | be |
Token ID | 307 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
gement | +2.789 |
llah | +2.664 |
gment | +2.577 |
Brit | +2.510 |
Asset | +2.412 |
Neg logit contributions | |
Duo | -2.575 |
enf | -2.443 |
Phi | -2.407 |
agra | -2.396 |
eny | -2.327 |
Token | strengthened |
Token ID | 27324 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
gement | +5.698 |
gment | +5.355 |
llah | +5.247 |
Brit | +4.974 |
Asset | +4.903 |
Neg logit contributions | |
Duo | -5.884 |
enf | -5.564 |
agra | -5.465 |
Phi | -5.391 |
eny | -5.363 |
Token | over |
Token ID | 625 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
gement | +3.707 |
llah | +3.553 |
gment | +3.416 |
Brit | +3.327 |
Asset | +3.218 |
Neg logit contributions | |
Duo | -3.552 |
enf | -3.358 |
Phi | -3.303 |
agra | -3.293 |
eny | -3.186 |
Token | time |
Token ID | 640 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Duo | +0.813 |
enf | +0.761 |
Phi | +0.750 |
agra | +0.743 |
eny | +0.726 |
Neg logit contributions | |
gement | -1.019 |
llah | -0.983 |
gment | -0.941 |
Brit | -0.936 |
Asset | -0.906 |
Token | with |
Token ID | 351 |
Feature activation | +2.18e+01 |
Pos logit contributions | |
gement | +2.754 |
llah | +2.623 |
gment | +2.539 |
Brit | +2.471 |
Asset | +2.398 |
Neg logit contributions | |
Duo | -2.703 |
enf | -2.556 |
Phi | -2.512 |
agra | -2.508 |
eny | -2.428 |
Token | practice |
Token ID | 3357 |
Feature activation | +8.03e+00 |
Pos logit contributions | |
gement | +12.421 |
gment | +12.112 |
llah | +11.854 |
Asset | +10.669 |
attendance | +10.597 |
Neg logit contributions | |
enf | -13.136 |
Duo | -12.806 |
agra | -12.515 |
eny | -12.139 |
eless | -11.734 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
gement | +5.273 |
llah | +4.953 |
gment | +4.842 |
Brit | +4.597 |
Asset | +4.485 |
Neg logit contributions | |
Duo | -6.012 |
enf | -5.724 |
agra | -5.679 |
Phi | -5.584 |
eny | -5.404 |
Token | But |
Token ID | 887 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
gement | +7.029 |
Brit | +6.871 |
llah | +6.787 |
Asset | +6.508 |
Classes | +6.507 |
Neg logit contributions | |
enf | -9.578 |
agra | -9.529 |
eny | -9.343 |
Duo | -9.130 |
eless | -8.864 |
Token | this |
Token ID | 428 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
gement | +7.865 |
llah | +7.484 |
gment | +7.219 |
Brit | +6.966 |
Asset | +6.630 |
Neg logit contributions | |
Duo | -8.740 |
enf | -8.706 |
agra | -8.529 |
eless | -8.196 |
eny | -8.156 |
Token | ability |
Token ID | 2694 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
gement | +4.708 |
llah | +4.380 |
gment | +4.312 |
Brit | +4.143 |
Asset | +4.031 |
Neg logit contributions | |
Duo | -5.087 |
enf | -4.864 |
agra | -4.814 |
Phi | -4.664 |
eny | -4.651 |
Token | from |
Token ID | 422 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
Duo | +4.202 |
Phi | +3.913 |
enf | +3.815 |
agra | +3.718 |
eny | +3.665 |
Neg logit contributions | |
gement | -4.919 |
llah | -4.712 |
gment | -4.541 |
Asset | -4.462 |
Brit | -4.455 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
gement | +3.462 |
llah | +3.386 |
gment | +3.150 |
Brit | +3.146 |
Asset | +2.992 |
Neg logit contributions | |
Duo | -3.569 |
enf | -3.474 |
agra | -3.366 |
Phi | -3.272 |
eny | -3.254 |
Token | 1980 |
Token ID | 7169 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
llah | +6.309 |
gement | +6.307 |
Brit | +5.745 |
gment | +5.623 |
Asset | +5.222 |
Neg logit contributions | |
Duo | -7.832 |
enf | -7.772 |
agra | -7.449 |
cum | -7.260 |
Phi | -7.255 |
Token | s |
Token ID | 82 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
gement | +0.873 |
llah | +0.828 |
gment | +0.771 |
Brit | +0.763 |
Asset | +0.724 |
Neg logit contributions | |
Duo | -1.459 |
enf | -1.401 |
Phi | -1.377 |
agra | -1.374 |
eny | -1.348 |
Token | to |
Token ID | 284 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
Duo | +4.633 |
Phi | +4.307 |
enf | +4.254 |
agra | +4.186 |
eny | +4.161 |
Neg logit contributions | |
gement | -5.102 |
llah | -4.775 |
gment | -4.658 |
Brit | -4.507 |
Asset | -4.481 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e+01 |
Pos logit contributions | |
gement | +5.478 |
llah | +5.437 |
gment | +4.853 |
Brit | +4.837 |
Asset | +4.506 |
Neg logit contributions | |
Duo | -6.958 |
enf | -6.768 |
agra | -6.661 |
eless | -6.478 |
Phi | -6.404 |
Token | 1990 |
Token ID | 6303 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
llah | +10.166 |
gement | +9.963 |
Brit | +8.370 |
gment | +8.317 |
warranty | +7.459 |
Neg logit contributions | |
Duo | -15.692 |
enf | -15.659 |
agra | -15.231 |
eless | -14.931 |
cum | -14.283 |
Token | s |
Token ID | 82 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
gement | +2.694 |
llah | +2.493 |
gment | +2.308 |
Brit | +2.298 |
Asset | +2.124 |
Neg logit contributions | |
Duo | -5.635 |
Phi | -5.353 |
enf | -5.351 |
agra | -5.303 |
eny | -5.156 |
Token | , |
Token ID | 11 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Duo | +5.767 |
Phi | +5.306 |
enf | +5.132 |
Cambodia | +5.054 |
eny | +5.032 |
Neg logit contributions | |
gement | -7.885 |
llah | -7.473 |
gment | -7.174 |
Asset | -7.071 |
Brit | -7.066 |
Token | his |
Token ID | 465 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Duo | +4.086 |
Phi | +3.774 |
enf | +3.690 |
agra | +3.646 |
eny | +3.573 |
Neg logit contributions | |
gement | -4.937 |
llah | -4.738 |
gment | -4.527 |
Asset | -4.459 |
Brit | -4.458 |
Token | family |
Token ID | 1641 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Duo | +4.386 |
Phi | +4.092 |
enf | +4.020 |
eny | +3.921 |
agra | +3.913 |
Neg logit contributions | |
gement | -4.442 |
llah | -4.250 |
gment | -4.035 |
Brit | -4.002 |
Asset | -3.999 |
Token | refusal |
Token ID | 17387 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
gement | +1.335 |
llah | +1.273 |
gment | +1.224 |
Brit | +1.205 |
Asset | +1.164 |
Neg logit contributions | |
Duo | -1.328 |
enf | -1.265 |
Phi | -1.230 |
agra | -1.230 |
eny | -1.208 |
Token | to |
Token ID | 284 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
gement | +7.329 |
llah | +6.564 |
gment | +6.446 |
Brit | +6.292 |
Asset | +5.762 |
Neg logit contributions | |
Duo | -8.616 |
agra | -8.258 |
enf | -8.182 |
Phi | -7.903 |
eny | -7.782 |
Token | attend |
Token ID | 5262 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
gement | +3.132 |
llah | +3.023 |
gment | +2.870 |
Brit | +2.828 |
Asset | +2.680 |
Neg logit contributions | |
Duo | -3.040 |
enf | -2.936 |
agra | -2.860 |
Phi | -2.819 |
eny | -2.777 |
Token | a |
Token ID | 257 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
gement | +8.028 |
llah | +7.135 |
Brit | +6.959 |
gment | +6.940 |
Asset | +6.556 |
Neg logit contributions | |
Duo | -9.397 |
enf | -9.315 |
eny | -8.889 |
agra | -8.844 |
eless | -8.820 |
Token | meeting |
Token ID | 3249 |
Feature activation | +9.99e+00 |
Pos logit contributions | |
gement | +4.143 |
llah | +3.857 |
gment | +3.734 |
Brit | +3.688 |
Asset | +3.493 |
Neg logit contributions | |
Duo | -4.536 |
enf | -4.451 |
eny | -4.278 |
agra | -4.269 |
eless | -4.171 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e+01 |
Pos logit contributions | |
gement | +6.402 |
llah | +5.906 |
gment | +5.762 |
Brit | +5.707 |
Asset | +5.166 |
Neg logit contributions | |
Duo | -7.375 |
enf | -7.171 |
agra | -7.036 |
eny | -6.768 |
Phi | -6.760 |
Token | Pu |
Token ID | 11634 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
gement | +13.113 |
Roy | +12.464 |
llah | +11.976 |
gment | +11.834 |
Brit | +11.535 |
Neg logit contributions | |
Duo | -11.799 |
enf | -11.742 |
eny | -11.336 |
agra | -11.278 |
eless | -10.933 |
Token | ig |
Token ID | 328 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
gement | +1.255 |
llah | +1.217 |
gment | +1.173 |
Brit | +1.157 |
Asset | +1.129 |
Neg logit contributions | |
Duo | -0.725 |
enf | -0.666 |
Phi | -0.650 |
agra | -0.642 |
eny | -0.622 |
Token | dem |
Token ID | 9536 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
gement | +3.326 |
llah | +3.124 |
gment | +2.989 |
Brit | +2.858 |
Asset | +2.669 |
Neg logit contributions | |
Duo | -5.038 |
Phi | -4.776 |
agra | -4.737 |
enf | -4.693 |
eny | -4.575 |
Token | ont |
Token ID | 756 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
gement | +6.428 |
llah | +6.020 |
gment | +5.857 |
Brit | +5.583 |
Asset | +5.198 |
Neg logit contributions | |
Duo | -7.382 |
agra | -6.748 |
Phi | -6.747 |
enf | -6.476 |
Solo | -6.442 |
Token | said |
Token ID | 531 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
gement | +6.406 |
llah | +6.184 |
gment | +5.562 |
Brit | +5.507 |
Asset | +5.176 |
Neg logit contributions | |
Duo | -9.071 |
agra | -8.845 |
enf | -8.619 |
Phi | -8.604 |
cum | -8.321 |
Token | bank |
Token ID | 3331 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Duo | +2.882 |
Phi | +2.666 |
enf | +2.663 |
agra | +2.582 |
eny | +2.548 |
Neg logit contributions | |
gement | -3.063 |
llah | -2.979 |
Brit | -2.827 |
gment | -2.803 |
Asset | -2.677 |
Token | operates |
Token ID | 14051 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
Duo | +1.577 |
enf | +1.480 |
Phi | +1.461 |
agra | +1.433 |
eny | +1.416 |
Neg logit contributions | |
gement | -1.578 |
llah | -1.524 |
Brit | -1.438 |
gment | -1.433 |
Asset | -1.378 |
Token | ," |
Token ID | 553 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Duo | +5.966 |
Phi | +5.548 |
enf | +5.532 |
cf | +5.308 |
eny | +5.252 |
Neg logit contributions | |
gement | -6.883 |
llah | -6.649 |
Brit | -6.318 |
gment | -6.271 |
Asset | -5.909 |
Token | Z |
Token ID | 1168 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
gement | +9.513 |
llah | +9.181 |
gment | +8.435 |
Brit | +8.307 |
Asset | +8.304 |
Neg logit contributions | |
enf | -9.874 |
Duo | -9.481 |
agra | -9.436 |
eny | -8.796 |
Phi | -8.756 |
Token | et |
Token ID | 316 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Duo | +0.444 |
enf | +0.416 |
Phi | +0.404 |
agra | +0.403 |
eny | +0.394 |
Neg logit contributions | |
gement | -0.696 |
llah | -0.672 |
gment | -0.645 |
Brit | -0.641 |
Asset | -0.623 |
Token | i |
Token ID | 72 |
Feature activation | +2.15e+01 |
Pos logit contributions | |
gement | +0.921 |
llah | +0.887 |
gment | +0.847 |
Brit | +0.836 |
Asset | +0.808 |
Neg logit contributions | |
Duo | -0.860 |
enf | -0.808 |
Phi | -0.793 |
agra | -0.786 |
eny | -0.769 |
Token | said |
Token ID | 531 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
gement | +11.146 |
llah | +10.812 |
gment | +9.740 |
Brit | +9.652 |
Asset | +9.248 |
Neg logit contributions | |
enf | -14.355 |
Duo | -14.076 |
agra | -13.497 |
Phi | -13.278 |
ilton | -12.905 |
Token | at |
Token ID | 379 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Duo | +0.836 |
enf | +0.785 |
Phi | +0.772 |
agra | +0.764 |
eny | +0.750 |
Neg logit contributions | |
gement | -0.981 |
llah | -0.944 |
gment | -0.904 |
Brit | -0.894 |
Asset | -0.867 |
Token | a |
Token ID | 257 |
Feature activation | +9.43e+00 |
Pos logit contributions | |
gement | +3.467 |
llah | +3.327 |
gment | +3.101 |
Brit | +3.074 |
Asset | +3.060 |
Neg logit contributions | |
Duo | -3.896 |
enf | -3.835 |
agra | -3.653 |
Phi | -3.607 |
eny | -3.595 |
Token | media |
Token ID | 2056 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
gement | +6.279 |
llah | +5.947 |
gment | +5.670 |
Asset | +5.551 |
Brit | +5.454 |
Neg logit contributions | |
enf | -6.838 |
Duo | -6.618 |
agra | -6.252 |
eny | -6.226 |
Phi | -6.132 |
Token | briefing |
Token ID | 17719 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
gement | +0.564 |
llah | +0.540 |
gment | +0.514 |
Brit | +0.507 |
Asset | +0.490 |
Neg logit contributions | |
Duo | -0.599 |
enf | -0.570 |
Phi | -0.558 |
agra | -0.556 |
eny | -0.545 |
Token | : |
Token ID | 25 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
gement | +4.365 |
llah | +4.215 |
Brit | +4.021 |
gment | +3.970 |
Asset | +3.810 |
Neg logit contributions | |
Duo | -4.779 |
enf | -4.574 |
agra | -4.572 |
Phi | -4.411 |
eny | -4.351 |
Token | Frank |
Token ID | 5278 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
gement | +5.754 |
llah | +5.500 |
Brit | +5.306 |
gment | +5.258 |
Asset | +5.013 |
Neg logit contributions | |
Duo | -6.030 |
enf | -5.875 |
agra | -5.838 |
Phi | -5.555 |
eny | -5.552 |
Token | Miller |
Token ID | 7920 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
gement | +2.930 |
llah | +2.851 |
gment | +2.645 |
Brit | +2.571 |
Asset | +2.467 |
Neg logit contributions | |
Duo | -4.887 |
agra | -4.736 |
enf | -4.698 |
eny | -4.593 |
Phi | -4.552 |
Token | . |
Token ID | 13 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
gement | +1.319 |
llah | +1.267 |
gment | +1.206 |
Brit | +1.193 |
Asset | +1.153 |
Neg logit contributions | |
Duo | -1.285 |
enf | -1.220 |
agra | -1.198 |
Phi | -1.197 |
eny | -1.165 |
Token | How |
Token ID | 1374 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
gement | +5.327 |
llah | +5.203 |
Brit | +5.078 |
Asset | +4.832 |
gment | +4.736 |
Neg logit contributions | |
enf | -7.067 |
Duo | -6.986 |
agra | -6.972 |
eny | -6.858 |
Phi | -6.624 |
Token | could |
Token ID | 714 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
gement | +10.129 |
llah | +9.493 |
gment | +8.987 |
Brit | +8.908 |
Roy | +8.666 |
Neg logit contributions | |
Duo | -10.924 |
enf | -10.845 |
agra | -10.534 |
Phi | -10.053 |
cum | -9.934 |
Token | this |
Token ID | 428 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
gement | +11.087 |
llah | +10.390 |
Roy | +10.387 |
Brit | +10.211 |
Asset | +9.974 |
Neg logit contributions | |
enf | -13.537 |
agra | -13.500 |
Duo | -12.838 |
eny | -12.787 |
Phi | -12.453 |
Token | go |
Token ID | 467 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
gement | +10.071 |
llah | +9.482 |
Brit | +9.024 |
gment | +8.789 |
Asset | +8.630 |
Neg logit contributions | |
agra | -10.548 |
Duo | -10.373 |
enf | -10.354 |
Phi | -10.019 |
eny | -9.793 |
Token | wrong |
Token ID | 2642 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
Duo | +2.416 |
enf | +2.260 |
Phi | +2.224 |
agra | +2.204 |
eny | +2.175 |
Neg logit contributions | |
gement | -2.883 |
llah | -2.772 |
gment | -2.649 |
Brit | -2.641 |
Asset | -2.578 |
Token | ?! |
Token ID | 12248 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
gement | +3.015 |
llah | +2.872 |
gment | +2.715 |
Brit | +2.679 |
Asset | +2.554 |
Neg logit contributions | |
Duo | -3.938 |
enf | -3.790 |
agra | -3.733 |
Phi | -3.718 |
eny | -3.631 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
gement | +5.692 |
llah | +5.642 |
Brit | +5.475 |
Asset | +5.205 |
gment | +5.054 |
Neg logit contributions | |
enf | -7.297 |
agra | -7.254 |
Duo | -7.191 |
eny | -7.020 |
Phi | -6.815 |
Token | v |
Token ID | 85 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
gement | +4.941 |
gment | +4.698 |
llah | +4.308 |
Brit | +3.980 |
Asset | +3.630 |
Neg logit contributions | |
Duo | -11.790 |
conduc | -11.620 |
Phi | -11.223 |
enf | -11.118 |
agra | -11.076 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
gement | +0.871 |
llah | +0.839 |
gment | +0.808 |
Brit | +0.803 |
Asset | +0.779 |
Neg logit contributions | |
Duo | -0.667 |
enf | -0.631 |
Phi | -0.614 |
agra | -0.612 |
eny | -0.599 |
Token | . |
Token ID | 764 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
gement | +2.530 |
llah | +2.440 |
gment | +2.299 |
Brit | +2.293 |
Asset | +2.209 |
Neg logit contributions | |
Duo | -3.554 |
enf | -3.440 |
agra | -3.397 |
eny | -3.312 |
Phi | -3.297 |
Token | im |
Token ID | 545 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
gement | +3.889 |
llah | +3.663 |
gment | +3.618 |
Brit | +3.459 |
Asset | +3.372 |
Neg logit contributions | |
Duo | -3.582 |
enf | -3.491 |
agra | -3.403 |
eny | -3.360 |
Phi | -3.295 |
Token | read |
Token ID | 961 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
gement | +1.020 |
llah | +0.959 |
gment | +0.912 |
Brit | +0.889 |
Asset | +0.839 |
Neg logit contributions | |
Duo | -1.582 |
enf | -1.497 |
Phi | -1.484 |
agra | -1.478 |
eny | -1.437 |
Token | ( |
Token ID | 357 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
gement | +4.107 |
llah | +3.838 |
Brit | +3.734 |
gment | +3.685 |
Asset | +3.539 |
Neg logit contributions | |
Duo | -5.174 |
agra | -4.994 |
enf | -4.990 |
eny | -4.878 |
Phi | -4.786 |
Token | image |
Token ID | 2939 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
gement | +5.277 |
gment | +4.220 |
llah | +3.950 |
pal | +3.219 |
ox | +3.016 |
Neg logit contributions | |
enf | -20.941 |
agra | -20.592 |
Duo | -20.572 |
Pros | -20.446 |
glers | -20.397 |
Token | Path |
Token ID | 15235 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
Brit | +4.533 |
gement | +4.518 |
Asset | +4.358 |
llah | +4.136 |
gment | +3.813 |
Neg logit contributions | |
Duo | -15.512 |
agra | -15.411 |
enf | -15.228 |
conduc | -14.813 |
eny | -14.789 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
gement | +2.256 |
llah | +2.149 |
Brit | +1.944 |
gment | +1.553 |
Asset | +1.536 |
Neg logit contributions | |
Duo | -16.328 |
enf | -16.284 |
agra | -16.239 |
conduc | -16.156 |
eny | -15.771 |
Token | image |
Token ID | 2939 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
gement | +5.242 |
gment | +4.401 |
llah | +3.707 |
warranty | +3.508 |
pal | +3.502 |
Neg logit contributions | |
enf | -18.328 |
Duo | -17.727 |
glers | -17.641 |
agra | -17.520 |
eny | -17.372 |
Token | = |
Token ID | 796 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
gement | +5.138 |
Brit | +5.032 |
llah | +4.912 |
Asset | +4.756 |
gment | +4.633 |
Neg logit contributions | |
Duo | -9.964 |
enf | -9.936 |
agra | -9.835 |
eny | -9.592 |
conduc | -9.476 |
Token | | |
Token ID | 930 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
gement | +2.992 |
llah | +2.793 |
gment | +2.631 |
Brit | +2.597 |
Asset | +2.543 |
Neg logit contributions | |
Duo | -5.338 |
enf | -5.257 |
agra | -5.124 |
Phi | -5.024 |
eny | -5.020 |
Token | void |
Token ID | 7951 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
gement | +5.607 |
gment | +5.321 |
llah | +5.253 |
Asset | +5.028 |
Brit | +4.954 |
Neg logit contributions | |
Duo | -4.057 |
enf | -3.995 |
agra | -3.846 |
eny | -3.706 |
Phi | -3.678 |
Token | * |
Token ID | 1635 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
gement | +7.172 |
llah | +6.919 |
gment | +6.776 |
Brit | +6.689 |
Asset | +6.566 |
Neg logit contributions | |
enf | -4.504 |
agra | -4.464 |
Duo | -4.430 |
eny | -4.169 |
eless | -3.966 |
Token | arg |
Token ID | 853 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
gement | +7.539 |
gment | +7.042 |
llah | +6.815 |
Brit | +6.439 |
Asset | +6.274 |
Neg logit contributions | |
Duo | -10.790 |
Phi | -10.250 |
conduc | -9.894 |
enf | -9.739 |
Solo | -9.662 |
Token | | |
Token ID | 930 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
gement | +4.329 |
llah | +3.996 |
gment | +3.795 |
Brit | +3.666 |
Asset | +3.535 |
Neg logit contributions | |
Duo | -10.004 |
enf | -9.964 |
agra | -9.851 |
Phi | -9.595 |
conduc | -9.552 |
Token | + |
Token ID | 1343 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
gement | +7.665 |
gment | +6.903 |
llah | +6.787 |
Asset | +6.401 |
Brit | +6.223 |
Neg logit contributions | |
enf | -8.999 |
Duo | -8.894 |
agra | -8.413 |
Phi | -8.383 |
eny | -8.323 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
gement | +6.741 |
llah | +6.036 |
Brit | +5.491 |
Asset | +5.334 |
gment | +5.327 |
Neg logit contributions | |
Duo | -20.096 |
conduc | -19.148 |
unbeliev | -18.623 |
Phi | -18.482 |
Solo | -18.181 |
Token | --+ |
Token ID | 44785 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
gement | +4.754 |
llah | +4.535 |
gment | +4.340 |
Brit | +4.288 |
Asset | +4.158 |
Neg logit contributions | |
Duo | -6.177 |
enf | -5.768 |
Phi | -5.644 |
agra | -5.541 |
Solo | -5.532 |
Token | | |
Token ID | 930 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
gement | +3.489 |
llah | +3.291 |
Brit | +3.073 |
gment | +3.050 |
Asset | +2.956 |
Neg logit contributions | |
Duo | -6.895 |
enf | -6.757 |
agra | -6.717 |
Phi | -6.516 |
eny | -6.497 |
Token | [ |
Token ID | 685 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
gement | +4.675 |
gment | +4.180 |
llah | +3.984 |
Asset | +3.686 |
�� | +3.241 |
Neg logit contributions | |
enf | -10.444 |
Duo | -10.422 |
agra | -10.198 |
eny | -9.705 |
cum | -9.687 |
Token | return |
Token ID | 7783 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
gement | +5.612 |
llah | +5.247 |
gment | +5.181 |
Asset | +4.983 |
Brit | +4.889 |
Neg logit contributions | |
Duo | -6.034 |
Phi | -5.565 |
agra | -5.554 |
enf | -5.538 |
Solo | -5.222 |
Token | We |
Token ID | 1135 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
gement | +4.404 |
llah | +4.297 |
Brit | +4.191 |
Asset | +4.100 |
gment | +4.068 |
Neg logit contributions | |
Duo | -4.634 |
enf | -4.390 |
agra | -4.320 |
Phi | -4.311 |
eny | -4.204 |
Token | built |
Token ID | 3170 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Duo | +0.416 |
enf | +0.394 |
Phi | +0.386 |
agra | +0.385 |
eny | +0.378 |
Neg logit contributions | |
gement | -0.388 |
llah | -0.371 |
gment | -0.353 |
Brit | -0.350 |
Asset | -0.338 |
Token | it |
Token ID | 340 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
gement | +1.016 |
llah | +0.976 |
gment | +0.934 |
Brit | +0.917 |
Asset | +0.890 |
Neg logit contributions | |
Duo | -0.993 |
enf | -0.947 |
Phi | -0.922 |
agra | -0.921 |
eny | -0.902 |
Token | entirely |
Token ID | 5000 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Duo | +3.926 |
Phi | +3.596 |
enf | +3.591 |
agra | +3.503 |
eny | +3.464 |
Neg logit contributions | |
gement | -5.301 |
llah | -5.054 |
Brit | -4.877 |
gment | -4.843 |
Asset | -4.762 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
Duo | +0.912 |
enf | +0.850 |
Phi | +0.837 |
agra | +0.825 |
eny | +0.811 |
Neg logit contributions | |
gement | -1.099 |
llah | -1.058 |
gment | -1.010 |
Brit | -1.004 |
Asset | -0.974 |
Token | - |
Token ID | 12 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
gement | +7.476 |
llah | +7.359 |
gment | +6.987 |
Asset | +6.596 |
Brit | +6.591 |
Neg logit contributions | |
enf | -7.276 |
agra | -7.168 |
Duo | -7.001 |
eless | -6.795 |
eny | -6.785 |
Token | house |
Token ID | 4803 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
gement | +10.670 |
llah | +10.645 |
Brit | +10.475 |
Asset | +10.439 |
home | +10.180 |
Neg logit contributions | |
Duo | -13.917 |
agra | -13.906 |
Phi | -13.765 |
enf | -13.435 |
eny | -13.113 |
Token | ? |
Token ID | 30 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
gement | +1.078 |
llah | +1.041 |
gment | +0.996 |
Brit | +0.983 |
Asset | +0.951 |
Neg logit contributions | |
Duo | -0.928 |
enf | -0.880 |
Phi | -0.859 |
agra | -0.856 |
eny | -0.835 |
Token | the |
Token ID | 1169 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
gement | +2.666 |
llah | +2.585 |
gment | +2.455 |
Brit | +2.442 |
Asset | +2.378 |
Neg logit contributions | |
Duo | -2.489 |
enf | -2.381 |
agra | -2.347 |
Phi | -2.311 |
eny | -2.267 |
Token | hardware |
Token ID | 6890 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
gement | +2.199 |
llah | +2.126 |
gment | +2.024 |
Brit | +1.991 |
Asset | +1.929 |
Neg logit contributions | |
Duo | -2.190 |
enf | -2.096 |
agra | -2.040 |
Phi | -2.034 |
eny | -1.991 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
Duo | +3.353 |
enf | +3.109 |
Phi | +3.051 |
eny | +2.991 |
agra | +2.990 |
Neg logit contributions | |
gement | -3.894 |
llah | -3.728 |
Brit | -3.576 |
gment | -3.566 |
Asset | -3.411 |
Token | work |
Token ID | 670 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
gement | +0.160 |
llah | +0.153 |
gment | +0.147 |
Brit | +0.145 |
Asset | +0.140 |
Neg logit contributions | |
Duo | -0.151 |
enf | -0.143 |
Phi | -0.140 |
agra | -0.139 |
eny | -0.136 |
Token | with |
Token ID | 351 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
gement | +4.068 |
llah | +3.861 |
gment | +3.750 |
Brit | +3.621 |
Asset | +3.457 |
Neg logit contributions | |
Duo | -4.299 |
enf | -4.125 |
Phi | -3.991 |
agra | -3.972 |
eny | -3.938 |
Token | our |
Token ID | 674 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
gement | +3.277 |
llah | +3.077 |
gment | +2.999 |
Brit | +2.919 |
Asset | +2.820 |
Neg logit contributions | |
Duo | -3.262 |
enf | -3.127 |
agra | -3.100 |
eny | -3.020 |
Phi | -3.007 |
Token | civil |
Token ID | 3026 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
Duo | +0.995 |
enf | +0.938 |
Phi | +0.927 |
agra | +0.911 |
eny | +0.896 |
Neg logit contributions | |
gement | -0.963 |
llah | -0.926 |
gment | -0.879 |
Brit | -0.870 |
Asset | -0.842 |
Token | servants |
Token ID | 17523 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Duo | +5.096 |
enf | +4.837 |
Phi | +4.745 |
agra | +4.636 |
eny | +4.590 |
Neg logit contributions | |
gement | -4.750 |
llah | -4.576 |
gment | -4.292 |
Brit | -4.241 |
Asset | -4.213 |
Token | ," |
Token ID | 553 |
Feature activation | +2.13e+01 |
Pos logit contributions | |
Duo | +1.583 |
enf | +1.495 |
Phi | +1.466 |
agra | +1.446 |
eny | +1.426 |
Neg logit contributions | |
gement | -1.829 |
llah | -1.752 |
gment | -1.681 |
Brit | -1.660 |
Asset | -1.623 |
Token | he |
Token ID | 339 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
gement | +11.055 |
llah | +10.439 |
Asset | +9.471 |
Brit | +9.323 |
gment | +9.254 |
Neg logit contributions | |
enf | -13.748 |
Duo | -13.724 |
agra | -13.458 |
Phi | -12.787 |
eny | -12.724 |
Token | said |
Token ID | 531 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
gement | +3.041 |
llah | +2.871 |
gment | +2.725 |
Brit | +2.644 |
Asset | +2.502 |
Neg logit contributions | |
Duo | -4.648 |
enf | -4.440 |
Phi | -4.410 |
agra | -4.379 |
eny | -4.271 |
Token | . |
Token ID | 13 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
Duo | +1.904 |
enf | +1.795 |
Phi | +1.752 |
agra | +1.737 |
eny | +1.723 |
Neg logit contributions | |
gement | -2.189 |
llah | -2.112 |
gment | -2.009 |
Brit | -1.992 |
Asset | -1.934 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
gement | +4.237 |
llah | +4.075 |
gment | +3.818 |
Brit | +3.795 |
Asset | +3.643 |
Neg logit contributions | |
Duo | -5.075 |
enf | -4.806 |
Phi | -4.707 |
agra | -4.688 |
eny | -4.642 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
gement | +1.699 |
llah | +1.629 |
Brit | +1.553 |
gment | +1.547 |
Asset | +1.485 |
Neg logit contributions | |
Duo | -2.033 |
enf | -1.941 |
agra | -1.909 |
Phi | -1.897 |
eny | -1.868 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
gement | +1.859 |
llah | +1.792 |
Brit | +1.717 |
gment | +1.693 |
Asset | +1.646 |
Neg logit contributions | |
Duo | -2.255 |
enf | -2.163 |
agra | -2.117 |
Phi | -2.102 |
eny | -2.084 |
Token | With |
Token ID | 3152 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
Brit | +8.796 |
llah | +8.444 |
gement | +8.440 |
Asset | +8.376 |
Article | +7.746 |
Neg logit contributions | |
Duo | -10.889 |
Phi | -10.481 |
enf | -10.197 |
agra | -9.879 |
dynam | -9.676 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
gement | +9.032 |
llah | +8.572 |
gment | +8.154 |
Brit | +7.784 |
attendance | +7.495 |
Neg logit contributions | |
enf | -9.407 |
Duo | -9.126 |
Phi | -8.769 |
eny | -8.703 |
agra | -8.635 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
gement | +10.131 |
llah | +9.580 |
gment | +9.081 |
attendance | +8.826 |
Brit | +8.808 |
Neg logit contributions | |
enf | -9.963 |
eless | -9.244 |
Duo | -9.137 |
agra | -9.115 |
eny | -9.104 |
Token | being |
Token ID | 852 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
gement | +7.487 |
llah | +7.046 |
gment | +6.868 |
Brit | +6.478 |
Asset | +6.443 |
Neg logit contributions | |
Duo | -7.449 |
enf | -7.328 |
Phi | -7.037 |
agra | -7.005 |
eny | -6.850 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e+01 |
Pos logit contributions | |
gement | +6.767 |
llah | +6.294 |
gment | +6.101 |
Brit | +5.798 |
Asset | +5.695 |
Neg logit contributions | |
enf | -7.319 |
Duo | -7.319 |
agra | -6.911 |
eny | -6.897 |
Phi | -6.758 |
Token | session |
Token ID | 6246 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
gement | +11.307 |
llah | +10.692 |
attendance | +10.615 |
gment | +9.913 |
Roy | +9.571 |
Neg logit contributions | |
enf | -13.854 |
Duo | -13.059 |
eless | -12.879 |
eny | -12.876 |
agra | -12.601 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
gement | +7.996 |
llah | +7.617 |
gment | +7.127 |
Brit | +6.984 |
Asset | +6.492 |
Neg logit contributions | |
enf | -10.422 |
Duo | -10.182 |
agra | -9.756 |
eny | -9.544 |
Phi | -9.501 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
gement | +8.799 |
llah | +8.553 |
gment | +7.753 |
Brit | +7.695 |
attendance | +7.467 |
Neg logit contributions | |
enf | -10.670 |
Duo | -10.204 |
agra | -10.079 |
Phi | -9.879 |
eny | -9.703 |
Token | cant |
Token ID | 18548 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
gement | +6.833 |
llah | +6.441 |
gment | +6.096 |
Brit | +5.804 |
attendance | +5.476 |
Neg logit contributions | |
enf | -8.507 |
Duo | -8.155 |
agra | -8.078 |
Phi | -8.061 |
eless | -8.025 |
Token | een |
Token ID | 6429 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Duo | +1.731 |
enf | +1.659 |
Phi | +1.617 |
agra | +1.610 |
eny | +1.600 |
Neg logit contributions | |
gement | -1.655 |
llah | -1.590 |
Brit | -1.514 |
gment | -1.510 |
Asset | -1.459 |
Token | [ |
Token ID | 685 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
gement | +4.594 |
gment | +4.134 |
llah | +4.078 |
Asset | +3.767 |
Brit | +3.572 |
Neg logit contributions | |
Duo | -8.010 |
enf | -7.896 |
agra | -7.755 |
eny | -7.430 |
Phi | -7.414 |
Token | return |
Token ID | 7783 |
Feature activation | +9.66e+00 |
Pos logit contributions | |
gement | +5.309 |
llah | +5.001 |
gment | +4.918 |
Asset | +4.726 |
Brit | +4.671 |
Neg logit contributions | |
Duo | -5.243 |
agra | -4.858 |
enf | -4.857 |
Phi | -4.818 |
eny | -4.603 |
Token | address |
Token ID | 2209 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
gement | +6.580 |
llah | +6.154 |
gment | +6.024 |
Asset | +5.631 |
warranty | +5.433 |
Neg logit contributions | |
Duo | -6.682 |
agra | -6.545 |
enf | -6.501 |
cum | -6.104 |
eny | -6.029 |
Token | ] |
Token ID | 60 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
gement | +3.314 |
llah | +3.087 |
gment | +2.970 |
Brit | +2.855 |
Asset | +2.784 |
Neg logit contributions | |
Duo | -5.687 |
enf | -5.548 |
agra | -5.517 |
eny | -5.328 |
Phi | -5.324 |
Token | | |
Token ID | 930 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
gement | +3.575 |
llah | +3.354 |
Brit | +3.121 |
gment | +3.117 |
Asset | +3.030 |
Neg logit contributions | |
Duo | -6.923 |
enf | -6.834 |
agra | -6.706 |
Phi | -6.576 |
eny | -6.538 |
Token | + |
Token ID | 1343 |
Feature activation | +2.11e+01 |
Pos logit contributions | |
gement | +7.282 |
llah | +6.556 |
gment | +6.550 |
Asset | +6.206 |
Brit | +6.102 |
Neg logit contributions | |
Duo | -8.050 |
enf | -7.873 |
agra | -7.557 |
Phi | -7.464 |
eny | -7.409 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
gement | +6.368 |
llah | +5.703 |
Brit | +5.349 |
Asset | +5.307 |
gment | +5.029 |
Neg logit contributions | |
Duo | -20.255 |
conduc | -19.345 |
unbeliev | -18.800 |
Phi | -18.529 |
skelet | -18.371 |
Token | --+ |
Token ID | 44785 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
gement | +4.375 |
llah | +4.183 |
gment | +3.988 |
Brit | +3.964 |
Asset | +3.855 |
Neg logit contributions | |
Duo | -5.568 |
enf | -5.218 |
Phi | -5.089 |
agra | -5.009 |
Solo | -4.975 |
Token | + |
Token ID | 1343 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
gement | +3.086 |
llah | +2.946 |
gment | +2.810 |
Brit | +2.800 |
Asset | +2.719 |
Neg logit contributions | |
Duo | -2.948 |
enf | -2.876 |
agra | -2.796 |
eny | -2.735 |
Phi | -2.720 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
gement | +5.985 |
llah | +5.463 |
Brit | +5.206 |
Asset | +5.092 |
gment | +4.866 |
Neg logit contributions | |
Duo | -16.759 |
conduc | -15.754 |
Phi | -15.414 |
unbeliev | -15.147 |
Solo | -15.066 |
Token | --+ |
Token ID | 44785 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
gement | +4.074 |
llah | +3.887 |
gment | +3.726 |
Brit | +3.678 |
Asset | +3.572 |
Neg logit contributions | |
Duo | -5.031 |
enf | -4.696 |
Phi | -4.591 |
agra | -4.520 |
Solo | -4.482 |
Token | | |
Token ID | 930 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
gement | +2.897 |
llah | +2.716 |
gment | +2.552 |
Brit | +2.532 |
Asset | +2.474 |
Neg logit contributions | |
Duo | -5.147 |
enf | -5.074 |
agra | -4.942 |
eny | -4.846 |
Phi | -4.844 |
Token | void |
Token ID | 7951 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
gement | +4.265 |
gment | +4.015 |
llah | +4.012 |
Asset | +3.800 |
Brit | +3.771 |
Neg logit contributions | |
Duo | -3.397 |
enf | -3.324 |
agra | -3.213 |
Phi | -3.107 |
eny | -3.106 |
Token | * |
Token ID | 1635 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
gement | +7.195 |
llah | +6.957 |
gment | +6.801 |
Brit | +6.726 |
Asset | +6.597 |
Neg logit contributions | |
enf | -4.545 |
agra | -4.502 |
Duo | -4.457 |
eny | -4.220 |
eless | -3.996 |
Token | arg |
Token ID | 853 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
gement | +7.396 |
gment | +6.915 |
llah | +6.662 |
Brit | +6.334 |
Asset | +6.161 |
Neg logit contributions | |
Duo | -10.514 |
Phi | -9.963 |
conduc | -9.599 |
enf | -9.486 |
Solo | -9.387 |
Token | | |
Token ID | 930 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
gement | +4.225 |
llah | +3.922 |
gment | +3.699 |
Brit | +3.613 |
Asset | +3.468 |
Neg logit contributions | |
Duo | -9.990 |
enf | -9.972 |
agra | -9.850 |
conduc | -9.608 |
Phi | -9.578 |
Token | + |
Token ID | 1343 |
Feature activation | +2.10e+01 |
Pos logit contributions | |
gement | +7.550 |
gment | +6.784 |
llah | +6.716 |
Asset | +6.317 |
Brit | +6.114 |
Neg logit contributions | |
enf | -8.827 |
Duo | -8.718 |
Phi | -8.220 |
agra | -8.196 |
eny | -8.164 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
gement | +6.592 |
llah | +5.887 |
Brit | +5.345 |
Asset | +5.169 |
gment | +5.154 |
Neg logit contributions | |
Duo | -19.992 |
conduc | -19.011 |
unbeliev | -18.531 |
Phi | -18.390 |
Solo | -18.131 |
Token | --+ |
Token ID | 44785 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
gement | +4.445 |
llah | +4.241 |
gment | +4.059 |
Brit | +4.006 |
Asset | +3.884 |
Neg logit contributions | |
Duo | -5.613 |
enf | -5.250 |
Phi | -5.131 |
agra | -5.036 |
Solo | -5.016 |
Token | | |
Token ID | 930 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
gement | +3.450 |
llah | +3.251 |
Brit | +3.028 |
gment | +3.015 |
Asset | +2.918 |
Neg logit contributions | |
Duo | -6.805 |
enf | -6.674 |
agra | -6.619 |
Phi | -6.433 |
eny | -6.410 |
Token | [ |
Token ID | 685 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
gement | +4.056 |
gment | +3.615 |
llah | +3.576 |
Asset | +3.241 |
Brit | +3.036 |
Neg logit contributions | |
Duo | -8.102 |
enf | -8.013 |
agra | -7.818 |
eny | -7.540 |
Phi | -7.539 |
Token | return |
Token ID | 7783 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
gement | +5.136 |
llah | +4.812 |
gment | +4.729 |
Asset | +4.525 |
Brit | +4.475 |
Neg logit contributions | |
Duo | -5.378 |
Phi | -4.953 |
enf | -4.911 |
agra | -4.906 |
Solo | -4.642 |
Token | vibration |
Token ID | 30999 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
gement | +3.880 |
llah | +3.740 |
gment | +3.571 |
Brit | +3.510 |
Asset | +3.405 |
Neg logit contributions | |
Duo | -3.703 |
enf | -3.517 |
agra | -3.463 |
Phi | -3.409 |
eny | -3.358 |
Token | need |
Token ID | 761 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
gement | +3.539 |
llah | +3.350 |
gment | +3.192 |
Brit | +3.147 |
Asset | +3.023 |
Neg logit contributions | |
Duo | -3.746 |
enf | -3.571 |
agra | -3.512 |
Phi | -3.494 |
eny | -3.407 |
Token | not |
Token ID | 407 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
Duo | +0.445 |
enf | +0.421 |
Phi | +0.412 |
agra | +0.410 |
eny | +0.401 |
Neg logit contributions | |
gement | -0.477 |
llah | -0.458 |
gment | -0.438 |
Brit | -0.433 |
Asset | -0.419 |
Token | be |
Token ID | 307 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
Duo | +2.189 |
enf | +2.043 |
Phi | +2.001 |
agra | +1.995 |
eny | +1.970 |
Neg logit contributions | |
gement | -2.632 |
llah | -2.541 |
gment | -2.420 |
Brit | -2.418 |
Asset | -2.364 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
Duo | +4.301 |
enf | +4.033 |
Phi | +3.927 |
agra | +3.922 |
eny | +3.859 |
Neg logit contributions | |
gement | -4.722 |
llah | -4.619 |
Brit | -4.400 |
gment | -4.307 |
Asset | -4.157 |
Token | major |
Token ID | 1688 |
Feature activation | -2.49e+01 |
Pos logit contributions | |
Duo | +7.138 |
enf | +6.560 |
agra | +6.425 |
Phi | +6.365 |
eny | +6.162 |
Neg logit contributions | |
gement | -9.583 |
llah | -9.351 |
Brit | -9.122 |
Asset | -8.888 |
gment | -8.737 |
Token |
|
Token ID | 198 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
Duo | +12.363 |
cf | +11.642 |
enf | +11.266 |
agra | +10.954 |
hur | +10.858 |
Neg logit contributions | |
llah | -15.941 |
gement | -14.904 |
Brit | -14.881 |
Asset | -14.363 |
vironment | -14.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
Duo | +3.595 |
enf | +3.349 |
Phi | +3.329 |
agra | +3.214 |
cum | +3.189 |
Neg logit contributions | |
gement | -4.920 |
llah | -4.724 |
gment | -4.503 |
�� | -4.480 |
Brit | -4.373 |
Token | import |
Token ID | 11748 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
enf | +11.873 |
cum | +11.229 |
if | +10.831 |
eny | +10.831 |
agra | +10.663 |
Neg logit contributions | |
llah | -11.093 |
gement | -10.280 |
�� | -9.742 |
Brit | -9.499 |
vironment | -9.224 |
Token | ance |
Token ID | 590 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
Duo | +0.697 |
enf | +0.656 |
Phi | +0.637 |
agra | +0.634 |
eny | +0.620 |
Neg logit contributions | |
gement | -0.959 |
llah | -0.929 |
gment | -0.889 |
Brit | -0.884 |
Asset | -0.859 |
Token | for |
Token ID | 329 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
Duo | +4.512 |
enf | +4.234 |
Phi | +4.123 |
agra | +4.057 |
eny | +3.995 |
Neg logit contributions | |
gement | -5.897 |
llah | -5.706 |
Brit | -5.482 |
gment | -5.464 |
Asset | -5.330 |
Token | of |
Token ID | 286 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
gement | +1.388 |
llah | +1.332 |
gment | +1.263 |
Brit | +1.249 |
Asset | +1.202 |
Neg logit contributions | |
Duo | -1.443 |
enf | -1.363 |
Phi | -1.347 |
agra | -1.341 |
eny | -1.305 |
Token | sleep |
Token ID | 3993 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
gement | +5.758 |
llah | +5.444 |
Brit | +5.181 |
gment | +5.148 |
Asset | +4.900 |
Neg logit contributions | |
Duo | -6.170 |
agra | -6.028 |
enf | -6.021 |
Phi | -5.823 |
eny | -5.761 |
Token | is |
Token ID | 318 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
gement | +1.831 |
llah | +1.738 |
gment | +1.669 |
Brit | +1.648 |
Asset | +1.580 |
Neg logit contributions | |
Duo | -1.856 |
enf | -1.746 |
Phi | -1.720 |
agra | -1.699 |
eny | -1.669 |
Token | having |
Token ID | 1719 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
gement | +0.136 |
llah | +0.131 |
gment | +0.125 |
Brit | +0.123 |
Asset | +0.119 |
Neg logit contributions | |
Duo | -0.132 |
enf | -0.125 |
Phi | -0.123 |
agra | -0.122 |
eny | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
Duo | +7.577 |
Phi | +6.888 |
agra | +6.827 |
enf | +6.821 |
hur | +6.801 |
Neg logit contributions | |
gement | -11.509 |
llah | -11.229 |
Asset | -10.754 |
gment | -10.715 |
�� | -10.694 |
Token | major |
Token ID | 1688 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
Duo | +9.480 |
hur | +8.705 |
Phi | +8.687 |
cf | +8.292 |
dynam | +8.291 |
Neg logit contributions | |
gement | -13.819 |
llah | -13.772 |
Asset | -13.443 |
ighting | -13.066 |
Brit | -13.051 |
Token | impact |
Token ID | 2928 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
Duo | +10.070 |
hur | +9.316 |
cf | +8.982 |
Phi | +8.973 |
bearing | +8.803 |
Neg logit contributions | |
llah | -17.527 |
gement | -16.528 |
Asset | -16.520 |
Brit | -16.511 |
ighting | -16.158 |
Token | on |
Token ID | 319 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Duo | +3.491 |
enf | +3.265 |
agra | +3.197 |
Phi | +3.187 |
eny | +3.144 |
Neg logit contributions | |
gement | -4.564 |
llah | -4.435 |
gment | -4.246 |
Asset | -4.130 |
Brit | -4.108 |
Token | workers |
Token ID | 3259 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Duo | +0.337 |
enf | +0.318 |
Phi | +0.312 |
agra | +0.310 |
eny | +0.303 |
Neg logit contributions | |
gement | -0.372 |
llah | -0.359 |
gment | -0.343 |
Brit | -0.338 |
Asset | -0.328 |
Token | with |
Token ID | 351 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Duo | +0.791 |
enf | +0.748 |
Phi | +0.731 |
agra | +0.725 |
eny | +0.714 |
Neg logit contributions | |
gement | -0.855 |
llah | -0.824 |
gment | -0.788 |
Brit | -0.776 |
Asset | -0.755 |
Token | over |
Token ID | 625 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
Duo | +1.491 |
enf | +1.408 |
Phi | +1.384 |
agra | +1.375 |
eny | +1.344 |
Neg logit contributions | |
gement | -1.479 |
llah | -1.421 |
gment | -1.353 |
Brit | -1.342 |
Asset | -1.301 |
Token | unemployment |
Token ID | 10681 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
gement | +4.158 |
llah | +3.970 |
gment | +3.778 |
Brit | +3.714 |
Asset | +3.673 |
Neg logit contributions | |
Duo | -4.253 |
enf | -4.050 |
agra | -3.951 |
Phi | -3.937 |
eny | -3.857 |
Token | and |
Token ID | 290 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
gement | +3.120 |
llah | +2.930 |
gment | +2.804 |
Brit | +2.756 |
Asset | +2.655 |
Neg logit contributions | |
Duo | -3.225 |
enf | -3.013 |
agra | -3.003 |
Phi | -2.981 |
eny | -2.898 |
Token | wages |
Token ID | 9400 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
gement | +2.988 |
llah | +2.851 |
gment | +2.724 |
Brit | +2.674 |
Asset | +2.629 |
Neg logit contributions | |
Duo | -2.995 |
enf | -2.834 |
agra | -2.781 |
Phi | -2.774 |
eny | -2.696 |
Token | will |
Token ID | 481 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
gement | +2.793 |
llah | +2.609 |
gment | +2.524 |
Brit | +2.462 |
Asset | +2.372 |
Neg logit contributions | |
Duo | -3.381 |
enf | -3.230 |
Phi | -3.139 |
agra | -3.136 |
eny | -3.037 |
Token | have |
Token ID | 423 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
Duo | +0.201 |
enf | +0.189 |
Phi | +0.185 |
agra | +0.184 |
eny | +0.180 |
Neg logit contributions | |
gement | -0.228 |
llah | -0.219 |
gment | -0.210 |
Brit | -0.208 |
Asset | -0.201 |
Token | an |
Token ID | 281 |
Feature activation | -2.40e+01 |
Pos logit contributions | |
Duo | +4.552 |
enf | +4.281 |
Phi | +4.228 |
agra | +4.174 |
eny | +4.087 |
Neg logit contributions | |
gement | -5.958 |
llah | -5.884 |
gment | -5.505 |
Brit | -5.500 |
Asset | -5.296 |
Token | influence |
Token ID | 4588 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Duo | +10.092 |
eny | +9.856 |
enf | +9.754 |
eless | +9.735 |
cf | +9.246 |
Neg logit contributions | |
Brit | -16.902 |
gement | -16.703 |
llah | -16.647 |
�� | -15.943 |
gment | -15.750 |
Token | on |
Token ID | 319 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
gement | +0.824 |
llah | +0.790 |
gment | +0.754 |
Brit | +0.746 |
Asset | +0.719 |
Neg logit contributions | |
Duo | -0.814 |
enf | -0.771 |
Phi | -0.755 |
agra | -0.750 |
eny | -0.732 |
Token | prices |
Token ID | 4536 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Duo | +1.275 |
enf | +1.204 |
Phi | +1.187 |
agra | +1.174 |
eny | +1.155 |
Neg logit contributions | |
gement | -1.266 |
llah | -1.218 |
gment | -1.161 |
Brit | -1.149 |
Asset | -1.102 |
Token | over |
Token ID | 625 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
gement | +2.031 |
llah | +1.939 |
gment | +1.856 |
Brit | +1.823 |
Asset | +1.762 |
Neg logit contributions | |
Duo | -2.145 |
enf | -2.017 |
Phi | -1.983 |
agra | -1.981 |
eny | -1.921 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Duo | +3.744 |
Phi | +3.470 |
agra | +3.435 |
enf | +3.434 |
eny | +3.375 |
Neg logit contributions | |
gement | -5.238 |
llah | -5.146 |
gment | -4.931 |
Brit | -4.888 |
Asset | -4.657 |
Token | Ichigo |
Token ID | 44547 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Duo | +5.718 |
Phi | +5.427 |
enf | +5.287 |
eny | +5.018 |
Solo | +4.967 |
Neg logit contributions | |
gement | -6.141 |
llah | -5.784 |
gment | -5.693 |
Brit | -5.450 |
Asset | -5.412 |
Token | m |
Token ID | 285 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
Duo | +1.529 |
enf | +1.435 |
Phi | +1.416 |
agra | +1.389 |
eny | +1.378 |
Neg logit contributions | |
gement | -1.600 |
llah | -1.538 |
gment | -1.468 |
Brit | -1.453 |
Asset | -1.420 |
Token | umbled |
Token ID | 11137 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
gement | +2.909 |
llah | +2.652 |
gment | +2.536 |
Brit | +2.433 |
Asset | +2.302 |
Neg logit contributions | |
Duo | -4.830 |
enf | -4.569 |
Phi | -4.560 |
agra | -4.508 |
eny | -4.389 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
gement | +0.991 |
llah | +0.949 |
gment | +0.907 |
Brit | +0.899 |
Asset | +0.865 |
Neg logit contributions | |
Duo | -0.977 |
enf | -0.933 |
agra | -0.912 |
Phi | -0.905 |
eny | -0.887 |
Token | himself |
Token ID | 2241 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
Duo | +10.515 |
Phi | +10.317 |
eless | +9.290 |
eny | +9.272 |
enf | +9.266 |
Neg logit contributions | |
gement | -13.188 |
gment | -12.335 |
llah | -12.258 |
Brit | -12.086 |
Asset | -12.023 |
Token | as |
Token ID | 355 |
Feature activation | -2.36e+01 |
Pos logit contributions | |
gement | +2.970 |
llah | +2.845 |
gment | +2.718 |
Brit | +2.680 |
Asset | +2.556 |
Neg logit contributions | |
Duo | -3.246 |
enf | -3.101 |
agra | -3.055 |
Phi | -3.024 |
eny | -2.943 |
Token | he |
Token ID | 339 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
Duo | +11.554 |
Phi | +11.552 |
if | +10.372 |
eless | +10.279 |
enf | +10.107 |
Neg logit contributions | |
gement | -16.474 |
llah | -15.742 |
gment | -15.273 |
Brit | -14.890 |
Asset | -14.827 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Duo | +5.871 |
Phi | +5.371 |
enf | +5.343 |
eless | +5.272 |
eny | +5.246 |
Neg logit contributions | |
gement | -6.375 |
llah | -6.289 |
Asset | -5.964 |
Brit | -5.860 |
gment | -5.833 |
Token | his |
Token ID | 465 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Duo | +7.574 |
Phi | +7.312 |
enf | +6.762 |
eless | +6.665 |
Solo | +6.626 |
Neg logit contributions | |
gement | -10.709 |
llah | -10.352 |
gment | -9.900 |
Asset | -9.639 |
Brit | -9.635 |
Token | good |
Token ID | 922 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
gement | +0.435 |
llah | +0.417 |
gment | +0.396 |
Brit | +0.391 |
Asset | +0.377 |
Neg logit contributions | |
Duo | -0.476 |
enf | -0.453 |
Phi | -0.443 |
agra | -0.443 |
eny | -0.433 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
gement | +2.192 |
llah | +2.066 |
gment | +1.932 |
Brit | +1.894 |
Asset | +1.764 |
Neg logit contributions | |
Duo | -4.182 |
enf | -4.026 |
agra | -3.971 |
Phi | -3.951 |
eless | -3.836 |
Token | are |
Token ID | 389 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
Duo | +6.449 |
Phi | +5.943 |
enf | +5.807 |
cf | +5.768 |
Solo | +5.696 |
Neg logit contributions | |
gement | -7.292 |
llah | -7.253 |
Asset | -6.796 |
Brit | -6.781 |
gment | -6.724 |
Token | appropriate |
Token ID | 5035 |
Feature activation | -9.02e+00 |
Pos logit contributions | |
Duo | +6.763 |
enf | +6.396 |
Phi | +6.240 |
cf | +6.204 |
agra | +5.933 |
Neg logit contributions | |
gement | -7.877 |
llah | -7.703 |
Brit | -7.325 |
gment | -7.201 |
Asset | -7.146 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Duo | +5.190 |
enf | +4.909 |
cf | +4.821 |
Phi | +4.781 |
agra | +4.712 |
Neg logit contributions | |
gement | -7.175 |
llah | -6.930 |
Brit | -6.689 |
gment | -6.616 |
Asset | -6.481 |
Token | make |
Token ID | 787 |
Feature activation | -8.99e+00 |
Pos logit contributions | |
Duo | +7.007 |
Phi | +6.474 |
enf | +6.444 |
cf | +6.258 |
agra | +6.221 |
Neg logit contributions | |
gement | -7.803 |
llah | -7.654 |
Brit | -7.386 |
Asset | -7.184 |
gment | -7.118 |
Token | in |
Token ID | 287 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
Duo | +5.005 |
enf | +4.642 |
cf | +4.475 |
Phi | +4.465 |
agra | +4.419 |
Neg logit contributions | |
gement | -7.310 |
llah | -7.131 |
Brit | -6.915 |
gment | -6.804 |
Asset | -6.789 |
Token | an |
Token ID | 281 |
Feature activation | -2.34e+01 |
Pos logit contributions | |
Duo | +10.560 |
Solo | +9.720 |
Phi | +9.617 |
enf | +9.167 |
cf | +9.029 |
Neg logit contributions | |
llah | -12.002 |
gement | -11.715 |
Brit | -11.235 |
gment | -10.860 |
Asset | -10.852 |
Token | interview |
Token ID | 2720 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Duo | +13.313 |
enf | +12.230 |
Solo | +12.162 |
Phi | +11.832 |
if | +11.450 |
Neg logit contributions | |
Brit | -14.105 |
gement | -13.931 |
llah | -13.718 |
gment | -13.052 |
Asset | -12.574 |
Token | about |
Token ID | 546 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Duo | +6.601 |
enf | +6.080 |
Phi | +5.885 |
eny | +5.838 |
eless | +5.737 |
Neg logit contributions | |
gement | -8.775 |
llah | -8.622 |
Brit | -8.422 |
Asset | -8.126 |
gment | -7.957 |
Token | improvis |
Token ID | 47833 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
Duo | +6.899 |
Phi | +6.385 |
Solo | +6.120 |
enf | +6.049 |
cf | +5.913 |
Neg logit contributions | |
gement | -7.489 |
llah | -7.472 |
Brit | -7.116 |
Asset | -6.925 |
gment | -6.892 |
Token | ation |
Token ID | 341 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
Duo | +6.413 |
enf | +6.072 |
Phi | +6.030 |
agra | +5.978 |
eny | +5.977 |
Neg logit contributions | |
gement | -2.666 |
llah | -2.615 |
Brit | -2.366 |
gment | -2.256 |
Asset | -2.243 |
Token | . |
Token ID | 13 |
Feature activation | -9.15e+00 |
Pos logit contributions | |
Duo | +5.557 |
Phi | +5.045 |
enf | +5.043 |
eny | +4.852 |
Solo | +4.816 |
Neg logit contributions | |
gement | -7.263 |
llah | -7.073 |
Brit | -6.855 |
gment | -6.672 |
Asset | -6.559 |
Token | — |
Token ID | 960 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
gement | +2.148 |
llah | +2.081 |
gment | +1.971 |
Brit | +1.948 |
Asset | +1.877 |
Neg logit contributions | |
Duo | -2.266 |
enf | -2.145 |
Phi | -2.109 |
agra | -2.103 |
eny | -2.038 |
Token | all |
Token ID | 439 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Duo | +3.047 |
enf | +2.871 |
Phi | +2.789 |
agra | +2.759 |
eny | +2.725 |
Neg logit contributions | |
gement | -4.641 |
llah | -4.485 |
gment | -4.287 |
Brit | -4.156 |
Asset | -4.078 |
Token | that |
Token ID | 326 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Duo | +0.159 |
enf | +0.150 |
Phi | +0.147 |
agra | +0.146 |
eny | +0.143 |
Neg logit contributions | |
gement | -0.172 |
llah | -0.166 |
gment | -0.158 |
Brit | -0.157 |
Asset | -0.152 |
Token | stuff |
Token ID | 3404 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
Duo | +1.834 |
enf | +1.721 |
Phi | +1.701 |
agra | +1.681 |
eny | +1.655 |
Neg logit contributions | |
gement | -1.982 |
llah | -1.905 |
gment | -1.811 |
Brit | -1.795 |
Asset | -1.735 |
Token | has |
Token ID | 468 |
Feature activation | -8.97e+00 |
Pos logit contributions | |
Duo | +1.923 |
enf | +1.807 |
Phi | +1.776 |
agra | +1.762 |
eny | +1.745 |
Neg logit contributions | |
gement | -2.127 |
llah | -2.022 |
gment | -1.942 |
Brit | -1.919 |
Asset | -1.867 |
Token | an |
Token ID | 281 |
Feature activation | -2.33e+01 |
Pos logit contributions | |
Duo | +5.463 |
Phi | +5.110 |
enf | +5.049 |
eny | +4.899 |
agra | +4.892 |
Neg logit contributions | |
gement | -6.955 |
llah | -6.749 |
Brit | -6.424 |
gment | -6.300 |
Asset | -6.247 |
Token | impact |
Token ID | 2928 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
Duo | +11.948 |
Phi | +11.827 |
eless | +11.807 |
enf | +11.627 |
eny | +11.403 |
Neg logit contributions | |
gement | -14.880 |
Brit | -14.652 |
llah | -13.950 |
gment | -13.578 |
�� | -13.032 |
Token | on |
Token ID | 319 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Duo | +4.976 |
enf | +4.623 |
eless | +4.611 |
Phi | +4.609 |
agra | +4.597 |
Neg logit contributions | |
gement | -7.089 |
llah | -6.689 |
gment | -6.437 |
Brit | -6.388 |
Asset | -6.293 |
Token | our |
Token ID | 674 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Duo | +0.118 |
enf | +0.112 |
Phi | +0.110 |
agra | +0.109 |
eny | +0.107 |
Neg logit contributions | |
gement | -0.125 |
llah | -0.120 |
gment | -0.115 |
Brit | -0.113 |
Asset | -0.110 |
Token | long |
Token ID | 890 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
gement | +1.704 |
llah | +1.628 |
gment | +1.572 |
Brit | +1.544 |
Asset | +1.491 |
Neg logit contributions | |
Duo | -1.636 |
enf | -1.563 |
agra | -1.520 |
Phi | -1.509 |
eny | -1.481 |
Token | - |
Token ID | 12 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
gement | +2.546 |
llah | +2.417 |
gment | +2.344 |
Brit | +2.306 |
Asset | +2.239 |
Neg logit contributions | |
Duo | -2.387 |
enf | -2.241 |
Phi | -2.206 |
agra | -2.180 |
eny | -2.125 |
Token | itability |
Token ID | 34147 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
Duo | +3.862 |
enf | +3.664 |
Phi | +3.609 |
eny | +3.607 |
eless | +3.549 |
Neg logit contributions | |
gement | -2.875 |
llah | -2.784 |
Brit | -2.602 |
gment | -2.596 |
Asset | -2.546 |
Token | about |
Token ID | 546 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Duo | +3.474 |
enf | +3.217 |
Phi | +3.182 |
agra | +3.105 |
eny | +3.102 |
Neg logit contributions | |
gement | -4.299 |
llah | -4.175 |
Brit | -3.993 |
gment | -3.961 |
Asset | -3.904 |
Token | what |
Token ID | 644 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
Duo | +9.403 |
Phi | +8.818 |
Solo | +8.457 |
cf | +8.207 |
enf | +8.058 |
Neg logit contributions | |
llah | -10.100 |
gement | -10.027 |
Brit | -9.687 |
Asset | -9.629 |
gment | -9.472 |
Token | happens |
Token ID | 4325 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
Duo | +7.838 |
Phi | +7.308 |
Solo | +7.021 |
cf | +6.754 |
enf | +6.719 |
Neg logit contributions | |
llah | -9.269 |
gement | -9.036 |
Brit | -8.537 |
Asset | -8.504 |
gment | -8.482 |
Token | in |
Token ID | 287 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
Duo | +5.191 |
Phi | +4.775 |
enf | +4.769 |
Solo | +4.598 |
eny | +4.591 |
Neg logit contributions | |
gement | -7.738 |
llah | -7.517 |
gment | -7.174 |
Brit | -7.147 |
Asset | -7.147 |
Token | an |
Token ID | 281 |
Feature activation | -2.32e+01 |
Pos logit contributions | |
Duo | +8.752 |
Phi | +8.020 |
Solo | +7.840 |
cf | +7.351 |
enf | +7.329 |
Neg logit contributions | |
gement | -10.794 |
llah | -10.766 |
Brit | -10.191 |
Asset | -10.045 |
gment | -9.942 |
Token | improvis |
Token ID | 47833 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
Duo | +11.939 |
Phi | +10.725 |
Solo | +10.695 |
enf | +10.656 |
� | +10.371 |
Neg logit contributions | |
Brit | -15.078 |
gement | -15.027 |
llah | -14.648 |
gment | -13.991 |
Asset | -13.750 |
Token | ation |
Token ID | 341 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Duo | +8.007 |
enf | +7.533 |
eless | +7.437 |
eny | +7.412 |
Phi | +7.382 |
Neg logit contributions | |
gement | -3.490 |
llah | -3.476 |
Brit | -3.248 |
Asset | -3.091 |
gment | -2.876 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Duo | +5.975 |
enf | +5.410 |
Phi | +5.381 |
Solo | +5.262 |
eny | +5.209 |
Neg logit contributions | |
gement | -7.894 |
llah | -7.724 |
Brit | -7.512 |
Asset | -7.256 |
gment | -7.246 |
Token | while |
Token ID | 981 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
Duo | +1.505 |
enf | +1.406 |
Phi | +1.393 |
agra | +1.376 |
eny | +1.346 |
Neg logit contributions | |
gement | -1.661 |
llah | -1.605 |
gment | -1.528 |
Brit | -1.519 |
Asset | -1.475 |
Token | the |
Token ID | 262 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
Duo | +4.774 |
Phi | +4.441 |
enf | +4.396 |
cf | +4.221 |
agra | +4.220 |
Neg logit contributions | |
gement | -5.895 |
llah | -5.671 |
gment | -5.452 |
Brit | -5.300 |
Asset | -5.266 |
Token | hasn |
Token ID | 5818 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
Duo | +2.971 |
enf | +2.770 |
Phi | +2.736 |
agra | +2.707 |
eny | +2.655 |
Neg logit contributions | |
gement | -3.412 |
llah | -3.319 |
gment | -3.112 |
Brit | -3.096 |
Asset | -3.030 |
Token | 't |
Token ID | 470 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
Duo | +2.569 |
enf | +2.435 |
Phi | +2.353 |
agra | +2.317 |
eny | +2.308 |
Neg logit contributions | |
gement | -4.201 |
llah | -4.033 |
gment | -3.880 |
Brit | -3.810 |
�� | -3.791 |
Token | had |
Token ID | 550 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
Duo | +4.752 |
enf | +4.414 |
Phi | +4.349 |
agra | +4.280 |
eless | +4.269 |
Neg logit contributions | |
gement | -5.452 |
llah | -5.342 |
Asset | -5.051 |
Brit | -5.049 |
gment | -4.924 |
Token | more |
Token ID | 517 |
Feature activation | -1.82e+01 |
Pos logit contributions | |
Duo | +7.124 |
Phi | +6.693 |
enf | +6.549 |
agra | +6.316 |
eny | +6.213 |
Neg logit contributions | |
gement | -10.370 |
llah | -10.106 |
Brit | -9.536 |
gment | -9.410 |
�� | -9.263 |
Token | of |
Token ID | 286 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
Duo | +9.450 |
Phi | +8.903 |
hur | +8.702 |
dynam | +8.650 |
cf | +8.636 |
Neg logit contributions | |
gement | -13.395 |
llah | -13.170 |
Brit | -12.144 |
gment | -12.120 |
Asset | -11.879 |
Token | an |
Token ID | 281 |
Feature activation | -2.31e+01 |
Pos logit contributions | |
Duo | +5.193 |
Phi | +4.775 |
enf | +4.763 |
agra | +4.701 |
eny | +4.600 |
Neg logit contributions | |
gement | -6.790 |
llah | -6.639 |
Brit | -6.241 |
gment | -6.115 |
Asset | -5.986 |
Token | impact |
Token ID | 2928 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
Duo | +8.722 |
Phi | +8.226 |
hur | +8.191 |
enf | +8.146 |
eny | +7.930 |
Neg logit contributions | |
llah | -17.785 |
Brit | -17.753 |
gement | -17.589 |
gment | -16.580 |
ighting | -16.373 |
Token | on |
Token ID | 319 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Duo | +4.423 |
enf | +4.129 |
Phi | +4.061 |
agra | +4.023 |
eny | +4.018 |
Neg logit contributions | |
gement | -6.143 |
llah | -5.988 |
gment | -5.640 |
Brit | -5.557 |
Asset | -5.518 |
Token | prices |
Token ID | 4536 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
gement | +0.030 |
llah | +0.029 |
gment | +0.027 |
Brit | +0.027 |
Asset | +0.026 |
Neg logit contributions | |
Duo | -0.031 |
enf | -0.029 |
Phi | -0.028 |
agra | -0.028 |
eny | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
Duo | +1.237 |
enf | +1.168 |
Phi | +1.142 |
agra | +1.131 |
eny | +1.114 |
Neg logit contributions | |
gement | -1.494 |
llah | -1.442 |
gment | -1.374 |
Brit | -1.359 |
Asset | -1.321 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Duo | +5.207 |
Phi | +4.820 |
enf | +4.706 |
Solo | +4.607 |
cf | +4.567 |
Neg logit contributions | |
gement | -6.560 |
llah | -6.204 |
gment | -6.041 |
�� | -5.660 |
Brit | -5.597 |
Token |
|
Token ID | 198 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
Duo | +0.577 |
enf | +0.546 |
Phi | +0.536 |
agra | +0.531 |
eny | +0.521 |
Neg logit contributions | |
gement | -0.587 |
llah | -0.562 |
gment | -0.537 |
Brit | -0.528 |
Asset | -0.511 |
Token | Manchester |
Token ID | 40744 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Duo | +4.310 |
enf | +4.222 |
Phi | +4.096 |
agra | +4.093 |
eny | +4.048 |
Neg logit contributions | |
gement | -3.149 |
llah | -3.044 |
gment | -2.861 |
Brit | -2.635 |
Asset | -2.559 |
Token | United |
Token ID | 1578 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
gement | +1.979 |
llah | +1.846 |
gment | +1.771 |
Brit | +1.767 |
Asset | +1.680 |
Neg logit contributions | |
Duo | -2.305 |
enf | -2.229 |
agra | -2.173 |
Phi | -2.167 |
eny | -2.139 |
Token | [ |
Token ID | 58 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
gement | +0.747 |
llah | +0.716 |
gment | +0.682 |
Brit | +0.678 |
Asset | +0.652 |
Neg logit contributions | |
Duo | -0.727 |
enf | -0.691 |
agra | -0.675 |
Phi | -0.675 |
eny | -0.659 |
Token | 95 |
Token ID | 3865 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
enf | +5.300 |
Duo | +5.096 |
cum | +4.824 |
Phi | +4.776 |
cf | +4.732 |
Neg logit contributions | |
gement | -10.867 |
llah | -10.638 |
gment | -10.030 |
Asset | -9.471 |
Brit | -9.381 |
Token | ][ |
Token ID | 7131 |
Feature activation | -2.28e+01 |
Pos logit contributions | |
gement | +1.293 |
llah | +1.228 |
gment | +1.159 |
Brit | +1.143 |
Asset | +1.097 |
Neg logit contributions | |
Duo | -1.799 |
enf | -1.717 |
agra | -1.689 |
Phi | -1.688 |
eny | -1.655 |
Token | 96 |
Token ID | 4846 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
enf | +8.290 |
cum | +8.227 |
Duo | +8.210 |
if | +8.174 |
cf | +7.706 |
Neg logit contributions | |
gement | -18.059 |
llah | -17.149 |
gment | -16.534 |
�� | -16.372 |
Asset | -16.352 |
Token | ] |
Token ID | 60 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
gement | +0.615 |
llah | +0.585 |
gment | +0.553 |
Brit | +0.545 |
Asset | +0.523 |
Neg logit contributions | |
Duo | -0.820 |
enf | -0.783 |
Phi | -0.769 |
agra | -0.768 |
eny | -0.753 |
Token |
|
Token ID | 198 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
Duo | +1.728 |
enf | +1.628 |
Phi | +1.606 |
agra | +1.580 |
eny | +1.555 |
Neg logit contributions | |
gement | -1.793 |
llah | -1.734 |
gment | -1.651 |
Brit | -1.619 |
Asset | -1.577 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Duo | +0.607 |
enf | +0.573 |
Phi | +0.564 |
agra | +0.558 |
eny | +0.548 |
Neg logit contributions | |
gement | -0.619 |
llah | -0.593 |
gment | -0.566 |
Brit | -0.556 |
Asset | -0.539 |
Token | International |
Token ID | 24274 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Duo | +1.816 |
enf | +1.747 |
Phi | +1.707 |
agra | +1.700 |
eny | +1.673 |
Neg logit contributions | |
gement | -1.670 |
llah | -1.607 |
gment | -1.528 |
Brit | -1.464 |
Asset | -1.421 |
Token | said |
Token ID | 531 |
Feature activation | -8.93e+00 |
Pos logit contributions | |
Duo | +0.685 |
enf | +0.650 |
Phi | +0.638 |
agra | +0.634 |
eny | +0.622 |
Neg logit contributions | |
gement | -0.582 |
llah | -0.555 |
gment | -0.529 |
Brit | -0.521 |
Asset | -0.502 |
Token | these |
Token ID | 777 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Duo | +5.516 |
Phi | +5.025 |
agra | +4.877 |
enf | +4.864 |
Solo | +4.799 |
Neg logit contributions | |
gement | -7.007 |
llah | -6.852 |
gment | -6.655 |
Brit | -6.406 |
Asset | -6.261 |
Token | would |
Token ID | 561 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
Duo | +2.963 |
enf | +2.753 |
Phi | +2.701 |
agra | +2.682 |
eny | +2.633 |
Neg logit contributions | |
gement | -3.068 |
llah | -2.905 |
gment | -2.826 |
Brit | -2.746 |
Asset | -2.713 |
Token | have |
Token ID | 423 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Duo | +4.590 |
enf | +4.348 |
eless | +4.124 |
Phi | +4.093 |
agra | +4.084 |
Neg logit contributions | |
gement | -6.106 |
llah | -5.932 |
Brit | -5.726 |
Asset | -5.620 |
gment | -5.608 |
Token | a |
Token ID | 257 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
Duo | +6.916 |
enf | +6.602 |
eless | +6.276 |
cf | +6.269 |
Phi | +6.223 |
Neg logit contributions | |
gement | -10.607 |
llah | -10.511 |
gment | -9.785 |
Brit | -9.776 |
Asset | -9.669 |
Token | negative |
Token ID | 4633 |
Feature activation | -2.24e+01 |
Pos logit contributions | |
Duo | +9.068 |
Phi | +8.239 |
hur | +8.070 |
enf | +8.051 |
deaf | +8.025 |
Neg logit contributions | |
gement | -14.444 |
llah | -14.089 |
Brit | -13.910 |
Asset | -13.855 |
ighting | -13.635 |
Token | impact |
Token ID | 2928 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Duo | +8.728 |
Phi | +7.664 |
cf | +7.471 |
Cambodia | +7.395 |
hur | +7.380 |
Neg logit contributions | |
llah | -17.702 |
gement | -17.383 |
Brit | -17.366 |
Asset | -17.047 |
�� | -16.691 |
Token | on |
Token ID | 319 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
Duo | +2.717 |
enf | +2.566 |
Phi | +2.505 |
agra | +2.501 |
eny | +2.454 |
Neg logit contributions | |
gement | -3.441 |
llah | -3.287 |
gment | -3.171 |
Brit | -3.108 |
Asset | -3.068 |
Token | current |
Token ID | 1459 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Duo | +4.409 |
Phi | +4.165 |
enf | +4.085 |
agra | +4.060 |
Solo | +3.954 |
Neg logit contributions | |
gement | -4.697 |
llah | -4.481 |
gment | -4.347 |
Brit | -4.296 |
Asset | -4.154 |
Token | peace |
Token ID | 4167 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Duo | +2.406 |
enf | +2.289 |
Phi | +2.270 |
agra | +2.239 |
eny | +2.189 |
Neg logit contributions | |
gement | -1.761 |
llah | -1.669 |
gment | -1.592 |
Brit | -1.574 |
Asset | -1.506 |
Token | talks |
Token ID | 6130 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
Duo | +0.442 |
enf | +0.420 |
Phi | +0.412 |
agra | +0.410 |
eny | +0.401 |
Neg logit contributions | |
gement | -0.407 |
llah | -0.390 |
gment | -0.370 |
Brit | -0.367 |
Asset | -0.354 |
Token | hand |
Token ID | 1021 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Duo | +4.868 |
enf | +4.614 |
Phi | +4.535 |
agra | +4.528 |
eny | +4.480 |
Neg logit contributions | |
gement | -3.396 |
llah | -3.371 |
Brit | -3.089 |
gment | -3.054 |
Asset | -2.990 |
Token | in |
Token ID | 287 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
gement | +0.674 |
llah | +0.647 |
gment | +0.618 |
Brit | +0.610 |
Asset | +0.591 |
Neg logit contributions | |
Duo | -0.642 |
enf | -0.608 |
Phi | -0.596 |
agra | -0.592 |
eny | -0.579 |
Token | today |
Token ID | 1909 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Duo | +4.549 |
Phi | +4.172 |
enf | +4.113 |
agra | +4.021 |
Solo | +3.941 |
Neg logit contributions | |
gement | -5.041 |
llah | -4.972 |
Brit | -4.765 |
gment | -4.611 |
Asset | -4.444 |
Token | � |
Token ID | 447 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Duo | +6.854 |
enf | +6.270 |
cum | +6.014 |
Phi | +6.004 |
� | +5.933 |
Neg logit contributions | |
gement | -10.276 |
llah | -10.233 |
Brit | -9.947 |
gment | -9.605 |
Asset | -9.358 |
Token | � |
Token ID | 247 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
Duo | +2.026 |
enf | +1.875 |
Phi | +1.861 |
agra | +1.834 |
eny | +1.803 |
Neg logit contributions | |
gement | -2.325 |
llah | -2.245 |
Brit | -2.150 |
gment | -2.144 |
Asset | -2.090 |
Token | s |
Token ID | 82 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
Duo | +4.732 |
enf | +4.472 |
Phi | +4.368 |
eny | +4.300 |
agra | +4.288 |
Neg logit contributions | |
gement | -3.449 |
llah | -3.359 |
Brit | -3.181 |
gment | -3.122 |
Asset | -2.986 |
Token | time |
Token ID | 640 |
Feature activation | -9.57e+00 |
Pos logit contributions | |
Duo | +13.007 |
Phi | +11.963 |
Solo | +11.529 |
enf | +11.160 |
dynam | +11.112 |
Neg logit contributions | |
Brit | -13.929 |
gement | -13.555 |
llah | -13.541 |
gment | -12.211 |
Asset | -12.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Duo | +5.824 |
enf | +5.319 |
Phi | +5.150 |
cf | +5.083 |
cum | +5.038 |
Neg logit contributions | |
gement | -7.443 |
llah | -7.137 |
Brit | -7.050 |
gment | -6.792 |
Asset | -6.626 |
Token | The |
Token ID | 383 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
Duo | +3.197 |
Phi | +2.958 |
enf | +2.922 |
agra | +2.843 |
eny | +2.800 |
Neg logit contributions | |
gement | -3.223 |
llah | -3.083 |
gment | -2.947 |
Brit | -2.896 |
Asset | -2.732 |
Token | ultimate |
Token ID | 8713 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
Duo | +3.833 |
Phi | +3.563 |
enf | +3.504 |
agra | +3.451 |
eny | +3.392 |
Neg logit contributions | |
gement | -3.502 |
llah | -3.418 |
Brit | -3.266 |
gment | -3.188 |
Asset | -3.075 |
Token | objective |
Token ID | 9432 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
Duo | +5.459 |
Phi | +5.003 |
enf | +4.840 |
agra | +4.710 |
eny | +4.677 |
Neg logit contributions | |
gement | -5.886 |
llah | -5.885 |
Brit | -5.679 |
gment | -5.438 |
Asset | -5.263 |
Token | � |
Token ID | 250 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Duo | +2.163 |
enf | +2.044 |
Phi | +2.021 |
agra | +1.973 |
eny | +1.956 |
Neg logit contributions | |
gement | -2.151 |
llah | -2.065 |
gment | -1.961 |
Brit | -1.938 |
Asset | -1.908 |
Token | This |
Token ID | 1212 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
Duo | +6.421 |
enf | +6.116 |
cum | +5.888 |
Phi | +5.873 |
eny | +5.761 |
Neg logit contributions | |
gement | -7.929 |
llah | -7.758 |
gment | -7.277 |
Asset | -7.075 |
Brit | -7.068 |
Token | version |
Token ID | 2196 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
Duo | +6.209 |
Phi | +5.721 |
enf | +5.614 |
agra | +5.507 |
Solo | +5.478 |
Neg logit contributions | |
gement | -6.807 |
llah | -6.736 |
Brit | -6.265 |
gment | -6.237 |
Asset | -6.184 |
Token | had |
Token ID | 550 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
Duo | +5.157 |
enf | +4.773 |
Phi | +4.709 |
eny | +4.588 |
cf | +4.582 |
Neg logit contributions | |
gement | -6.422 |
llah | -6.268 |
gment | -5.921 |
Brit | -5.875 |
Asset | -5.783 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
Duo | +7.172 |
Phi | +6.703 |
enf | +6.613 |
Solo | +6.390 |
eny | +6.384 |
Neg logit contributions | |
llah | -7.976 |
gement | -7.974 |
Brit | -7.474 |
Asset | -7.463 |
gment | -7.401 |
Token | most |
Token ID | 749 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
Duo | +8.378 |
Phi | +7.786 |
enf | +7.583 |
Solo | +7.313 |
eny | +7.218 |
Neg logit contributions | |
gement | -8.780 |
llah | -8.597 |
Brit | -8.140 |
Asset | -8.124 |
gment | -7.941 |
Token | motion |
Token ID | 6268 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
Duo | +12.685 |
Phi | +12.563 |
dynam | +11.857 |
cf | +11.698 |
enf | +11.654 |
Neg logit contributions | |
llah | -13.467 |
gement | -13.299 |
Asset | -12.486 |
gment | -12.159 |
Brit | -12.044 |
Token | � |
Token ID | 447 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Duo | +3.753 |
enf | +3.495 |
eless | +3.404 |
Phi | +3.402 |
eny | +3.379 |
Neg logit contributions | |
gement | -4.436 |
llah | -4.374 |
Brit | -4.139 |
gment | -4.113 |
Asset | -4.016 |
Token | � |
Token ID | 251 |
Feature activation | -8.80e+00 |
Pos logit contributions | |
Duo | +1.380 |
enf | +1.310 |
Phi | +1.294 |
agra | +1.276 |
eny | +1.259 |
Neg logit contributions | |
gement | -1.158 |
llah | -1.107 |
gment | -1.049 |
Brit | -1.045 |
Asset | -1.013 |
Token | stems |
Token ID | 21552 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
Duo | +5.540 |
enf | +5.144 |
Phi | +5.134 |
cf | +4.993 |
eny | +4.975 |
Neg logit contributions | |
gement | -6.637 |
llah | -6.558 |
Brit | -6.118 |
gment | -6.105 |
Asset | -6.034 |
Token | from |
Token ID | 422 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Duo | +2.768 |
enf | +2.613 |
Phi | +2.558 |
agra | +2.504 |
eny | +2.475 |
Neg logit contributions | |
gement | -3.872 |
llah | -3.787 |
Brit | -3.598 |
gment | -3.593 |
Asset | -3.520 |
Token | 000 |
Token ID | 830 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
gement | +1.166 |
llah | +1.122 |
gment | +1.062 |
Brit | +1.051 |
Asset | +1.012 |
Neg logit contributions | |
Duo | -1.310 |
enf | -1.252 |
Phi | -1.223 |
agra | -1.216 |
eny | -1.196 |
Token | each |
Token ID | 1123 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
Duo | +2.589 |
enf | +2.439 |
Phi | +2.411 |
agra | +2.374 |
eny | +2.349 |
Neg logit contributions | |
gement | -2.508 |
llah | -2.396 |
gment | -2.272 |
Brit | -2.236 |
Asset | -2.180 |
Token | — |
Token ID | 851 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
Duo | +4.355 |
Phi | +4.041 |
enf | +4.039 |
agra | +3.934 |
eny | +3.923 |
Neg logit contributions | |
gement | -4.149 |
llah | -3.918 |
gment | -3.724 |
Brit | -3.695 |
Asset | -3.614 |
Token | are |
Token ID | 389 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Duo | +2.699 |
enf | +2.571 |
agra | +2.514 |
Phi | +2.505 |
eny | +2.482 |
Neg logit contributions | |
gement | -2.639 |
llah | -2.539 |
gment | -2.399 |
Brit | -2.392 |
Asset | -2.331 |
Token | having |
Token ID | 1719 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
Duo | +2.462 |
enf | +2.330 |
Phi | +2.291 |
agra | +2.276 |
eny | +2.233 |
Neg logit contributions | |
gement | -2.618 |
llah | -2.526 |
gment | -2.393 |
Brit | -2.389 |
Asset | -2.295 |
Token | an |
Token ID | 281 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
Duo | +8.090 |
Phi | +7.687 |
agra | +7.387 |
eny | +7.376 |
Solo | +7.350 |
Neg logit contributions | |
gement | -10.619 |
llah | -10.060 |
Brit | -9.781 |
gment | -9.527 |
Asset | -9.498 |
Token | effect |
Token ID | 1245 |
Feature activation | -8.04e+00 |
Pos logit contributions | |
Duo | +9.330 |
eless | +9.276 |
eny | +9.014 |
enf | +8.969 |
Phi | +8.558 |
Neg logit contributions | |
gement | -16.613 |
Brit | -16.337 |
llah | -15.905 |
gment | -15.249 |
ighting | -15.078 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Duo | +4.831 |
enf | +4.496 |
Phi | +4.466 |
agra | +4.446 |
eny | +4.393 |
Neg logit contributions | |
gement | -6.537 |
llah | -6.141 |
gment | -5.976 |
Asset | -5.774 |
Brit | -5.770 |
Token | Many |
Token ID | 4650 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
Duo | +1.782 |
enf | +1.659 |
Phi | +1.652 |
agra | +1.617 |
eny | +1.573 |
Neg logit contributions | |
gement | -1.870 |
llah | -1.764 |
gment | -1.715 |
Brit | -1.650 |
Asset | -1.599 |
Token | who |
Token ID | 508 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Duo | +4.340 |
Phi | +4.005 |
enf | +3.982 |
agra | +3.924 |
eless | +3.872 |
Neg logit contributions | |
gement | -4.601 |
llah | -4.308 |
gment | -4.199 |
Brit | -4.110 |
Asset | -4.005 |
Token | are |
Token ID | 389 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
Duo | +6.938 |
enf | +6.473 |
eny | +6.419 |
eless | +6.328 |
agra | +6.303 |
Neg logit contributions | |
gement | -7.560 |
llah | -6.962 |
Asset | -6.958 |
Brit | -6.954 |
gment | -6.866 |
Token | the |
Token ID | 262 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Duo | +2.303 |
enf | +2.140 |
Phi | +2.130 |
agra | +2.084 |
eny | +2.062 |
Neg logit contributions | |
gement | -2.474 |
llah | -2.379 |
gment | -2.282 |
Brit | -2.239 |
Asset | -2.185 |
Token | D |
Token ID | 360 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Duo | +3.651 |
Phi | +3.377 |
enf | +3.355 |
agra | +3.268 |
eny | +3.238 |
Neg logit contributions | |
gement | -3.661 |
llah | -3.541 |
gment | -3.373 |
Brit | -3.331 |
Asset | -3.257 |
Token | NR |
Token ID | 24723 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Duo | +3.627 |
enf | +3.541 |
agra | +3.381 |
Phi | +3.380 |
eny | +3.311 |
Neg logit contributions | |
gement | -5.028 |
llah | -4.830 |
Brit | -4.651 |
gment | -4.613 |
Asset | -4.466 |
Token | commissioner |
Token ID | 16248 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
Duo | +6.877 |
Phi | +6.241 |
enf | +6.205 |
eny | +5.953 |
cf | +5.952 |
Neg logit contributions | |
gement | -7.379 |
llah | -7.192 |
Brit | -6.845 |
gment | -6.838 |
Asset | -6.526 |
Token | who |
Token ID | 508 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
Duo | +2.012 |
enf | +1.890 |
Phi | +1.859 |
agra | +1.831 |
eny | +1.812 |
Neg logit contributions | |
gement | -2.246 |
llah | -2.176 |
gment | -2.068 |
Brit | -2.059 |
Asset | -1.989 |
Token | set |
Token ID | 900 |
Feature activation | -2.18e+01 |
Pos logit contributions | |
Duo | +4.259 |
enf | +3.978 |
Phi | +3.917 |
eny | +3.840 |
agra | +3.840 |
Neg logit contributions | |
gement | -4.472 |
llah | -4.354 |
Brit | -4.142 |
gment | -4.119 |
Asset | -4.050 |
Token | our |
Token ID | 674 |
Feature activation | -9.59e+00 |
Pos logit contributions | |
Duo | +12.039 |
Phi | +10.897 |
Solo | +10.421 |
Boone | +10.270 |
cf | +10.075 |
Neg logit contributions | |
llah | -14.551 |
gement | -14.494 |
Brit | -14.387 |
gment | -13.736 |
Asset | -12.997 |
Token | research |
Token ID | 2267 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
Duo | +6.873 |
Phi | +6.239 |
enf | +6.150 |
eny | +6.005 |
agra | +5.977 |
Neg logit contributions | |
gement | -6.667 |
llah | -6.541 |
Brit | -6.207 |
gment | -6.134 |
Asset | -5.972 |
Token | on |
Token ID | 319 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
Duo | +5.287 |
enf | +4.908 |
Phi | +4.884 |
agra | +4.720 |
eny | +4.656 |
Neg logit contributions | |
gement | -5.871 |
llah | -5.662 |
Brit | -5.386 |
gment | -5.359 |
Asset | -5.175 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
Duo | +9.442 |
Phi | +8.779 |
enf | +8.326 |
Solo | +8.180 |
eny | +8.173 |
Neg logit contributions | |
gement | -10.026 |
llah | -9.825 |
Brit | -9.484 |
gment | -9.338 |
Asset | -9.107 |
Token | road |
Token ID | 2975 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Duo | +8.180 |
Phi | +7.433 |
enf | +7.195 |
cf | +7.072 |
Solo | +7.008 |
Neg logit contributions | |
gement | -8.439 |
llah | -8.437 |
Brit | -7.996 |
gment | -7.871 |
Asset | -7.843 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
gement | +2.611 |
llah | +2.496 |
gment | +2.388 |
Brit | +2.355 |
Asset | +2.287 |
Neg logit contributions | |
Duo | -2.537 |
enf | -2.414 |
agra | -2.360 |
Phi | -2.329 |
eny | -2.307 |
Token | weapons |
Token ID | 3777 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
Duo | +3.559 |
enf | +3.390 |
Phi | +3.347 |
agra | +3.253 |
eny | +3.239 |
Neg logit contributions | |
gement | -3.716 |
llah | -3.615 |
gment | -3.410 |
Brit | -3.351 |
Asset | -3.255 |
Token | viewed |
Token ID | 9569 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
gement | +2.292 |
llah | +2.186 |
gment | +2.087 |
Brit | +2.050 |
Asset | +1.986 |
Neg logit contributions | |
Duo | -2.312 |
enf | -2.192 |
agra | -2.171 |
Phi | -2.160 |
eny | -2.088 |
Token | in |
Token ID | 287 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
Duo | +0.876 |
enf | +0.828 |
Phi | +0.810 |
agra | +0.807 |
eny | +0.787 |
Neg logit contributions | |
gement | -0.985 |
llah | -0.951 |
gment | -0.905 |
Brit | -0.897 |
Asset | -0.873 |
Token | exactly |
Token ID | 3446 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Duo | +4.382 |
enf | +4.123 |
Phi | +4.059 |
agra | +3.979 |
eny | +3.887 |
Neg logit contributions | |
gement | -5.460 |
llah | -5.382 |
gment | -5.075 |
Brit | -4.985 |
Asset | -4.891 |
Token | this |
Token ID | 428 |
Feature activation | -2.17e+01 |
Pos logit contributions | |
Duo | +2.849 |
Phi | +2.633 |
enf | +2.624 |
agra | +2.563 |
eny | +2.519 |
Neg logit contributions | |
gement | -3.606 |
llah | -3.480 |
gment | -3.344 |
Brit | -3.296 |
Asset | -3.230 |
Token | light |
Token ID | 1657 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Duo | +10.640 |
enf | +9.860 |
Phi | +9.709 |
Solo | +9.320 |
cf | +9.203 |
Neg logit contributions | |
gement | -14.776 |
llah | -14.525 |
Asset | -14.007 |
Brit | -13.872 |
gment | -13.812 |
Token | before |
Token ID | 878 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
gement | +1.514 |
llah | +1.450 |
gment | +1.385 |
Brit | +1.369 |
Asset | +1.317 |
Neg logit contributions | |
Duo | -1.547 |
enf | -1.469 |
Phi | -1.440 |
agra | -1.436 |
eny | -1.397 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Duo | +0.803 |
enf | +0.757 |
Phi | +0.743 |
agra | +0.737 |
eny | +0.723 |
Neg logit contributions | |
gement | -0.857 |
llah | -0.824 |
gment | -0.787 |
Brit | -0.777 |
Asset | -0.752 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
gement | +0.848 |
llah | +0.816 |
Brit | +0.772 |
gment | +0.772 |
Asset | +0.746 |
Neg logit contributions | |
Duo | -0.915 |
enf | -0.875 |
agra | -0.856 |
Phi | -0.852 |
eny | -0.840 |
Token | The |
Token ID | 464 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
gement | +2.892 |
llah | +2.779 |
Brit | +2.719 |
gment | +2.669 |
Asset | +2.629 |
Neg logit contributions | |
Duo | -2.669 |
enf | -2.469 |
Phi | -2.460 |
agra | -2.412 |
eny | -2.349 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
gement | +0.260 |
llah | +0.250 |
gment | +0.239 |
Brit | +0.236 |
Asset | +0.228 |
Neg logit contributions | |
Duo | -0.243 |
enf | -0.230 |
Phi | -0.225 |
agra | -0.224 |
eny | -0.219 |
Token | On |
Token ID | 1550 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
Duo | +8.260 |
Phi | +7.585 |
Solo | +7.505 |
enf | +6.894 |
agra | +6.888 |
Neg logit contributions | |
gement | -9.512 |
llah | -9.184 |
gment | -8.869 |
Asset | -8.420 |
�� | -8.277 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Duo | +4.894 |
Phi | +4.647 |
agra | +4.513 |
enf | +4.406 |
eny | +4.383 |
Neg logit contributions | |
llah | -5.980 |
gement | -5.933 |
Brit | -5.666 |
Asset | -5.503 |
gment | -5.472 |
Token | way |
Token ID | 835 |
Feature activation | -9.21e+00 |
Pos logit contributions | |
Duo | +0.936 |
enf | +0.853 |
Phi | +0.844 |
agra | +0.831 |
eny | +0.795 |
Neg logit contributions | |
gement | -1.795 |
llah | -1.754 |
gment | -1.679 |
Brit | -1.676 |
Asset | -1.640 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
Duo | +5.354 |
Phi | +4.983 |
Solo | +4.813 |
enf | +4.789 |
agra | +4.724 |
Neg logit contributions | |
gement | -7.370 |
llah | -7.250 |
Asset | -6.919 |
Brit | -6.887 |
gment | -6.868 |
Token | they |
Token ID | 484 |
Feature activation | -2.16e+01 |
Pos logit contributions | |
Duo | +6.420 |
Phi | +5.805 |
Solo | +5.699 |
agra | +5.593 |
enf | +5.501 |
Neg logit contributions | |
gement | -9.526 |
llah | -9.452 |
Asset | -9.000 |
Brit | -8.920 |
gment | -8.915 |
Token | encounter |
Token ID | 8791 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
Duo | +10.592 |
cf | +9.321 |
eless | +9.204 |
agra | +9.170 |
Solo | +8.982 |
Neg logit contributions | |
Asset | -16.417 |
gement | -15.591 |
llah | -15.583 |
Brit | -15.168 |
�� | -14.653 |
Token | Far |
Token ID | 6755 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Duo | +5.130 |
Phi | +4.697 |
agra | +4.625 |
enf | +4.564 |
Solo | +4.471 |
Neg logit contributions | |
gement | -5.734 |
llah | -5.595 |
Brit | -5.266 |
gment | -5.248 |
Asset | -5.174 |
Token | am |
Token ID | 321 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
Duo | +7.391 |
agra | +7.027 |
enf | +6.860 |
eless | +6.859 |
Solo | +6.517 |
Neg logit contributions | |
gement | -7.792 |
llah | -7.593 |
Asset | -7.306 |
Brit | -7.136 |
gment | -6.986 |
Token | ir |
Token ID | 343 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Duo | +2.256 |
enf | +2.142 |
Phi | +2.106 |
agra | +2.105 |
eny | +2.062 |
Neg logit contributions | |
gement | -2.021 |
llah | -1.935 |
Brit | -1.831 |
gment | -1.824 |
Asset | -1.775 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
gement | +0.622 |
llah | +0.599 |
gment | +0.571 |
Brit | +0.563 |
Asset | +0.543 |
Neg logit contributions | |
Duo | -0.596 |
enf | -0.565 |
Phi | -0.553 |
agra | -0.550 |
eny | -0.538 |
Token | ! |
Token ID | 0 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Duo | +7.130 |
Phi | +6.645 |
enf | +6.528 |
eny | +6.416 |
cum | +6.211 |
Neg logit contributions | |
gement | -8.367 |
llah | -7.789 |
gment | -7.624 |
Brit | -7.447 |
Asset | -7.440 |
Token | � |
Token ID | 447 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
Duo | +8.636 |
Phi | +8.094 |
enf | +7.767 |
� | +7.718 |
eny | +7.502 |
Neg logit contributions | |
gement | -9.687 |
gment | -8.930 |
llah | -8.825 |
Brit | -8.401 |
Asset | -8.239 |
Token | � |
Token ID | 251 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
gement | +2.783 |
llah | +2.629 |
gment | +2.497 |
Brit | +2.413 |
Asset | +2.264 |
Neg logit contributions | |
Duo | -4.047 |
enf | -3.888 |
agra | -3.864 |
Phi | -3.791 |
eny | -3.740 |
Token | Ichigo |
Token ID | 44547 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Duo | +7.399 |
Phi | +7.059 |
enf | +6.778 |
Solo | +6.497 |
eny | +6.456 |
Neg logit contributions | |
gement | -7.397 |
llah | -6.892 |
gment | -6.860 |
Asset | -6.448 |
Brit | -6.437 |
Token | yelled |
Token ID | 22760 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
Duo | +3.418 |
Phi | +3.162 |
enf | +3.139 |
eny | +3.035 |
agra | +3.008 |
Neg logit contributions | |
gement | -3.831 |
llah | -3.685 |
gment | -3.517 |
Brit | -3.480 |
Asset | -3.435 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e+01 |
Pos logit contributions | |
gement | +0.059 |
llah | +0.057 |
gment | +0.054 |
Brit | +0.054 |
Asset | +0.052 |
Neg logit contributions | |
Duo | -0.052 |
enf | -0.049 |
Phi | -0.048 |
agra | -0.048 |
eny | -0.047 |
Token | Chad |
Token ID | 19800 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
Duo | +12.147 |
Phi | +11.990 |
Solo | +10.566 |
enf | +10.493 |
eless | +10.440 |
Neg logit contributions | |
gement | -14.528 |
gment | -13.463 |
llah | -13.305 |
Asset | -13.118 |
Brit | -12.978 |
Token | � |
Token ID | 447 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Duo | +2.076 |
enf | +1.945 |
Phi | +1.919 |
agra | +1.878 |
eny | +1.855 |
Neg logit contributions | |
gement | -2.378 |
llah | -2.280 |
gment | -2.181 |
Brit | -2.155 |
Asset | -2.111 |
Token | � |
Token ID | 247 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Duo | +1.264 |
enf | +1.195 |
Phi | +1.175 |
agra | +1.158 |
eny | +1.142 |
Neg logit contributions | |
gement | -1.239 |
llah | -1.184 |
gment | -1.131 |
Brit | -1.125 |
Asset | -1.092 |
Token | s |
Token ID | 82 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
gement | +0.418 |
llah | +0.402 |
gment | +0.383 |
Brit | +0.378 |
Asset | +0.365 |
Neg logit contributions | |
Duo | -0.417 |
enf | -0.395 |
Phi | -0.387 |
agra | -0.386 |
eny | -0.377 |
Token | far |
Token ID | 1290 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Duo | +5.329 |
Phi | +5.004 |
enf | +4.946 |
eny | +4.790 |
Solo | +4.724 |
Neg logit contributions | |
gement | -5.119 |
llah | -4.924 |
gment | -4.625 |
Brit | -4.575 |
Asset | -4.542 |
Token | 8 |
Token ID | 23 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Duo | +2.956 |
enf | +2.851 |
agra | +2.779 |
eny | +2.743 |
Phi | +2.730 |
Neg logit contributions | |
gement | -3.474 |
llah | -3.406 |
Brit | -3.234 |
gment | -3.195 |
Asset | -3.114 |
Token | { |
Token ID | 1391 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
Duo | +3.044 |
Phi | +2.840 |
enf | +2.827 |
agra | +2.787 |
eny | +2.750 |
Neg logit contributions | |
gement | -2.608 |
llah | -2.508 |
Brit | -2.382 |
gment | -2.368 |
Asset | -2.286 |
Token | ( |
Token ID | 7 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
Duo | +4.912 |
cum | +4.623 |
enf | +4.612 |
if | +4.603 |
� | +4.434 |
Neg logit contributions | |
gement | -11.055 |
llah | -10.672 |
�� | -10.475 |
gment | -10.357 |
vironment | -9.649 |
Token | 113 |
Token ID | 16616 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Duo | +3.133 |
enf | +2.943 |
Phi | +2.876 |
agra | +2.848 |
eny | +2.782 |
Neg logit contributions | |
gement | -3.847 |
llah | -3.676 |
gment | -3.549 |
Brit | -3.439 |
Asset | -3.341 |
Token | s |
Token ID | 82 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
Duo | +4.158 |
enf | +3.990 |
agra | +3.885 |
Phi | +3.882 |
eny | +3.879 |
Neg logit contributions | |
gement | -3.223 |
llah | -3.042 |
gment | -2.901 |
Brit | -2.831 |
�� | -2.755 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
Duo | +4.356 |
enf | +3.857 |
Phi | +3.834 |
cf | +3.540 |
eless | +3.441 |
Neg logit contributions | |
gement | -12.405 |
llah | -11.935 |
�� | -11.863 |
gment | -11.681 |
Asset | -11.401 |
Token | 56 |
Token ID | 7265 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
Duo | +10.969 |
cf | +9.714 |
Phi | +9.634 |
Solo | +9.234 |
if | +8.789 |
Neg logit contributions | |
gement | -15.530 |
Brit | -15.205 |
Asset | -14.904 |
llah | -14.802 |
gment | -14.488 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
Duo | +3.681 |
Phi | +3.446 |
enf | +3.350 |
agra | +3.271 |
eny | +3.243 |
Neg logit contributions | |
gement | -4.808 |
llah | -4.613 |
gment | -4.425 |
Brit | -4.363 |
�� | -4.257 |
Token | f |
Token ID | 277 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
Duo | +7.492 |
Phi | +6.829 |
cf | +6.712 |
Solo | +6.219 |
agra | +6.181 |
Neg logit contributions | |
gement | -10.001 |
llah | -9.956 |
Brit | -9.624 |
gment | -9.387 |
�� | -9.241 |
Token | 5 |
Token ID | 20 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
Duo | +5.174 |
enf | +5.038 |
eny | +4.825 |
agra | +4.783 |
Phi | +4.687 |
Neg logit contributions | |
llah | -7.810 |
gement | -7.646 |
Brit | -7.491 |
�� | -7.307 |
Asset | -7.189 |
Token | { |
Token ID | 1391 |
Feature activation | -8.71e+00 |
Pos logit contributions | |
Duo | +5.479 |
Phi | +5.084 |
enf | +4.981 |
agra | +4.974 |
cf | +4.884 |
Neg logit contributions | |
gement | -5.252 |
llah | -5.168 |
Brit | -4.967 |
gment | -4.863 |
Asset | -4.679 |
Token | that |
Token ID | 326 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Duo | +0.963 |
enf | +0.907 |
Phi | +0.891 |
agra | +0.883 |
eny | +0.867 |
Neg logit contributions | |
gement | -1.057 |
llah | -1.022 |
gment | -0.969 |
Brit | -0.962 |
Asset | -0.934 |
Token | is |
Token ID | 318 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
Duo | +1.372 |
enf | +1.293 |
Phi | +1.273 |
agra | +1.260 |
eny | +1.234 |
Neg logit contributions | |
gement | -1.408 |
llah | -1.360 |
gment | -1.289 |
Brit | -1.270 |
Asset | -1.235 |
Token | going |
Token ID | 1016 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
Duo | +3.454 |
enf | +3.245 |
Phi | +3.198 |
agra | +3.129 |
eny | +3.081 |
Neg logit contributions | |
gement | -3.979 |
llah | -3.933 |
gment | -3.644 |
Brit | -3.635 |
Asset | -3.554 |
Token | to |
Token ID | 284 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Duo | +7.828 |
enf | +7.560 |
eless | +7.387 |
Solo | +7.307 |
agra | +7.222 |
Neg logit contributions | |
gement | -13.808 |
llah | -13.772 |
Asset | -12.847 |
gment | -12.692 |
Brit | -12.420 |
Token | have |
Token ID | 423 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Duo | +3.108 |
enf | +2.922 |
Phi | +2.865 |
agra | +2.805 |
eny | +2.762 |
Neg logit contributions | |
gement | -3.668 |
llah | -3.576 |
gment | -3.349 |
Brit | -3.347 |
Asset | -3.301 |
Token | significant |
Token ID | 2383 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
Duo | +7.768 |
Phi | +7.245 |
enf | +7.123 |
cf | +7.004 |
hur | +6.950 |
Neg logit contributions | |
llah | -11.449 |
gement | -11.264 |
Asset | -10.415 |
gment | -10.365 |
�� | -10.346 |
Token | implications |
Token ID | 10939 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
Duo | +10.485 |
dynam | +9.851 |
cf | +9.707 |
hur | +9.685 |
Phi | +9.619 |
Neg logit contributions | |
llah | -14.900 |
gement | -14.684 |
�� | -13.812 |
Brit | -13.800 |
Asset | -13.733 |
Token | for |
Token ID | 329 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Duo | +4.658 |
enf | +4.344 |
Phi | +4.302 |
agra | +4.225 |
eny | +4.197 |
Neg logit contributions | |
gement | -6.488 |
llah | -6.310 |
gment | -5.994 |
Asset | -5.970 |
Brit | -5.908 |
Token | things |
Token ID | 1243 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Duo | +1.104 |
enf | +1.032 |
Phi | +1.023 |
agra | +1.009 |
eny | +0.988 |
Neg logit contributions | |
gement | -1.222 |
llah | -1.185 |
gment | -1.125 |
Brit | -1.112 |
Asset | -1.081 |
Token | like |
Token ID | 588 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
Duo | +1.078 |
enf | +1.008 |
Phi | +0.996 |
agra | +0.982 |
eny | +0.966 |
Neg logit contributions | |
gement | -1.289 |
llah | -1.246 |
gment | -1.187 |
Brit | -1.171 |
Asset | -1.142 |
Token | trade |
Token ID | 3292 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
gement | +3.016 |
llah | +2.841 |
gment | +2.752 |
Brit | +2.724 |
Asset | +2.622 |
Neg logit contributions | |
Duo | -3.007 |
enf | -2.889 |
agra | -2.806 |
Phi | -2.781 |
eny | -2.759 |
Token | conversion |
Token ID | 11315 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Duo | +2.823 |
Phi | +2.613 |
enf | +2.589 |
agra | +2.502 |
eny | +2.487 |
Neg logit contributions | |
gement | -3.221 |
llah | -3.132 |
Brit | -2.962 |
gment | -2.958 |
Asset | -2.816 |
Token | to |
Token ID | 284 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
gement | +2.283 |
llah | +2.151 |
gment | +2.083 |
Brit | +2.038 |
Asset | +1.979 |
Neg logit contributions | |
Duo | -2.416 |
enf | -2.300 |
agra | -2.263 |
Phi | -2.249 |
eny | -2.185 |
Token | L |
Token ID | 406 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
gement | +0.309 |
llah | +0.296 |
gment | +0.282 |
Brit | +0.279 |
Asset | +0.269 |
Neg logit contributions | |
Duo | -0.324 |
enf | -0.307 |
Phi | -0.301 |
agra | -0.300 |
eny | -0.294 |
Token | NG |
Token ID | 10503 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
gement | +4.880 |
llah | +4.627 |
gment | +4.470 |
Brit | +4.284 |
Asset | +4.267 |
Neg logit contributions | |
Duo | -5.853 |
Phi | -5.361 |
enf | -5.344 |
agra | -5.301 |
Solo | -5.049 |
Token | has |
Token ID | 468 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
gement | +0.886 |
llah | +0.846 |
gment | +0.812 |
Brit | +0.801 |
Asset | +0.777 |
Neg logit contributions | |
Duo | -0.870 |
enf | -0.823 |
Phi | -0.805 |
agra | -0.804 |
eny | -0.784 |
Token | major |
Token ID | 1688 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
Duo | +7.139 |
Phi | +6.748 |
enf | +6.643 |
Solo | +6.367 |
agra | +6.310 |
Neg logit contributions | |
gement | -9.083 |
llah | -9.016 |
Brit | -8.496 |
gment | -8.333 |
Asset | -7.981 |
Token | drawbacks |
Token ID | 42763 |
Feature activation | -8.67e+00 |
Pos logit contributions | |
Duo | +11.354 |
cf | +10.696 |
Phi | +10.594 |
enf | +10.416 |
dynam | +10.315 |
Neg logit contributions | |
gement | -14.238 |
llah | -13.731 |
Brit | -13.457 |
gment | -12.680 |
Asset | -12.436 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Duo | +5.127 |
enf | +4.839 |
eny | +4.660 |
Phi | +4.658 |
cf | +4.585 |
Neg logit contributions | |
gement | -6.924 |
llah | -6.554 |
Brit | -6.406 |
gment | -6.343 |
Asset | -6.211 |
Token | Firstly |
Token ID | 41039 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
gement | +1.802 |
llah | +1.749 |
gment | +1.649 |
Brit | +1.645 |
Asset | +1.598 |
Neg logit contributions | |
Duo | -1.942 |
enf | -1.877 |
agra | -1.847 |
Phi | -1.808 |
eny | -1.798 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
gement | +0.030 |
llah | +0.029 |
gment | +0.028 |
Brit | +0.028 |
Asset | +0.027 |
Neg logit contributions | |
Duo | -0.029 |
enf | -0.028 |
Phi | -0.027 |
agra | -0.027 |
eny | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
gement | +1.692 |
llah | +1.621 |
gment | +1.551 |
Brit | +1.523 |
Asset | +1.480 |
Neg logit contributions | |
Duo | -1.703 |
enf | -1.633 |
agra | -1.594 |
Phi | -1.578 |
eny | -1.545 |
Token | is |
Token ID | 271 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
gement | +6.654 |
llah | +6.229 |
gment | +6.137 |
Brit | +5.889 |
Asset | +5.672 |
Neg logit contributions | |
Duo | -5.205 |
Phi | -4.760 |
enf | -4.531 |
Solo | -4.286 |
eny | -4.273 |
Token | q |
Token ID | 80 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
gement | +4.895 |
llah | +4.565 |
gment | +4.529 |
Brit | +4.170 |
Asset | +4.037 |
Neg logit contributions | |
Duo | -6.595 |
Phi | -6.221 |
enf | -6.137 |
eny | -5.926 |
agra | -5.880 |
Token | ars |
Token ID | 945 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
gement | +4.961 |
llah | +4.633 |
gment | +4.524 |
Brit | +4.104 |
Asset | +4.028 |
Neg logit contributions | |
Duo | -7.701 |
Phi | -7.241 |
enf | -7.040 |
Solo | -6.745 |
cf | -6.735 |
Token | / |
Token ID | 14 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
gement | +4.607 |
llah | +4.376 |
gment | +4.296 |
Brit | +4.128 |
Asset | +4.072 |
Neg logit contributions | |
Duo | -4.994 |
enf | -4.733 |
Phi | -4.708 |
agra | -4.630 |
eless | -4.556 |
Token | f |
Token ID | 69 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
gement | +5.942 |
llah | +5.735 |
gment | +5.515 |
Brit | +5.484 |
Asset | +5.364 |
Neg logit contributions | |
Duo | -5.375 |
Phi | -5.016 |
enf | -4.919 |
agra | -4.876 |
eless | -4.769 |
Token | atal |
Token ID | 10254 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
gement | +7.175 |
llah | +6.830 |
gment | +6.719 |
Brit | +6.450 |
Asset | +6.188 |
Neg logit contributions | |
Duo | -5.718 |
Phi | -5.271 |
enf | -5.099 |
Solo | -4.863 |
agra | -4.844 |
Token | . |
Token ID | 13 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
gement | +9.654 |
gment | +8.887 |
llah | +8.853 |
Brit | +8.460 |
Asset | +8.298 |
Neg logit contributions | |
Duo | -10.898 |
Phi | -10.492 |
agra | -9.723 |
Cambodia | -9.304 |
cf | -9.282 |
Token | html |
Token ID | 6494 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
gement | +5.540 |
llah | +5.383 |
gment | +5.139 |
Brit | +5.071 |
Asset | +4.867 |
Neg logit contributions | |
Duo | -4.928 |
enf | -4.665 |
Phi | -4.573 |
agra | -4.549 |
eny | -4.442 |
Token | . |
Token ID | 13 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
gement | +7.709 |
llah | +7.535 |
Brit | +7.186 |
gment | +7.130 |
Asset | +6.847 |
Neg logit contributions | |
Duo | -8.455 |
enf | -8.225 |
agra | -8.111 |
eny | -7.981 |
Phi | -7.856 |
Token | CDC |
Token ID | 20434 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
gement | +4.049 |
llah | +3.957 |
Brit | +3.806 |
gment | +3.712 |
Asset | +3.605 |
Neg logit contributions | |
Duo | -4.071 |
enf | -3.940 |
agra | -3.866 |
eny | -3.798 |
Phi | -3.754 |
Token | . |
Token ID | 13 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
gement | +1.975 |
llah | +1.909 |
gment | +1.809 |
Brit | +1.795 |
Asset | +1.744 |
Neg logit contributions | |
Duo | -2.069 |
enf | -1.969 |
agra | -1.944 |
Phi | -1.926 |
eny | -1.884 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
gement | +0.874 |
llah | +0.840 |
gment | +0.800 |
Brit | +0.794 |
Asset | +0.767 |
Neg logit contributions | |
Duo | -0.848 |
enf | -0.805 |
Phi | -0.788 |
agra | -0.783 |
eny | -0.765 |
Token | Urban |
Token ID | 14665 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
gement | +3.855 |
llah | +3.766 |
Brit | +3.676 |
Asset | +3.545 |
gment | +3.453 |
Neg logit contributions | |
Duo | -4.826 |
enf | -4.823 |
agra | -4.699 |
eny | -4.622 |
Phi | -4.519 |
Token | India |
Token ID | 3794 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Duo | +0.620 |
enf | +0.587 |
Phi | +0.577 |
agra | +0.574 |
eny | +0.564 |
Neg logit contributions | |
gement | -0.550 |
llah | -0.526 |
gment | -0.501 |
Brit | -0.493 |
Asset | -0.476 |
Token | is |
Token ID | 318 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
gement | +2.591 |
llah | +2.486 |
gment | +2.373 |
Brit | +2.358 |
Asset | +2.274 |
Neg logit contributions | |
Duo | -2.560 |
enf | -2.459 |
Phi | -2.395 |
agra | -2.376 |
eny | -2.325 |
Token | slightly |
Token ID | 4622 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
gement | +4.018 |
llah | +3.763 |
gment | +3.646 |
Brit | +3.602 |
Asset | +3.485 |
Neg logit contributions | |
Duo | -4.190 |
enf | -4.054 |
agra | -3.900 |
Phi | -3.850 |
eny | -3.813 |
Token | more |
Token ID | 517 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
gement | +6.126 |
llah | +5.670 |
Brit | +5.493 |
gment | +5.489 |
Asset | +5.127 |
Neg logit contributions | |
Duo | -6.800 |
enf | -6.635 |
agra | -6.394 |
Phi | -6.235 |
eny | -6.188 |
Token | egalitarian |
Token ID | 41469 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
gement | +8.200 |
llah | +7.897 |
Brit | +7.432 |
gment | +7.395 |
Asset | +7.327 |
Neg logit contributions | |
Duo | -9.093 |
agra | -8.962 |
enf | -8.946 |
eny | -8.319 |
eless | -8.268 |
Token | , |
Token ID | 11 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
gement | +0.178 |
llah | +0.171 |
gment | +0.164 |
Brit | +0.162 |
Asset | +0.157 |
Neg logit contributions | |
Duo | -0.154 |
enf | -0.145 |
Phi | -0.142 |
agra | -0.141 |
eny | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
gement | +4.804 |
llah | +4.564 |
Brit | +4.388 |
gment | +4.316 |
Asset | +4.130 |
Neg logit contributions | |
Duo | -4.791 |
enf | -4.781 |
agra | -4.548 |
eny | -4.429 |
Phi | -4.407 |
Token | figure |
Token ID | 3785 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
gement | +5.602 |
llah | +5.300 |
Brit | +5.107 |
gment | +5.027 |
Asset | +4.836 |
Neg logit contributions | |
Duo | -5.704 |
enf | -5.624 |
agra | -5.446 |
eny | -5.276 |
Phi | -5.254 |
Token | being |
Token ID | 852 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
gement | +1.961 |
llah | +1.873 |
gment | +1.793 |
Brit | +1.773 |
Asset | +1.699 |
Neg logit contributions | |
Duo | -1.953 |
enf | -1.859 |
agra | -1.819 |
Phi | -1.798 |
eny | -1.763 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Duo | +1.552 |
enf | +1.451 |
Phi | +1.426 |
agra | +1.409 |
eny | +1.381 |
Neg logit contributions | |
gement | -1.916 |
llah | -1.838 |
gment | -1.766 |
Brit | -1.712 |
Asset | -1.671 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Duo | +1.069 |
enf | +1.004 |
Phi | +0.987 |
agra | +0.979 |
eny | +0.960 |
Neg logit contributions | |
gement | -1.158 |
llah | -1.117 |
gment | -1.065 |
Brit | -1.046 |
Asset | -1.021 |
Token | 59 |
Token ID | 3270 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
Duo | +3.149 |
enf | +2.912 |
Phi | +2.884 |
agra | +2.844 |
eny | +2.784 |
Neg logit contributions | |
gement | -3.038 |
llah | -2.964 |
gment | -2.806 |
Brit | -2.672 |
Asset | -2.659 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Duo | +4.672 |
Phi | +4.223 |
enf | +4.218 |
agra | +4.212 |
Solo | +4.080 |
Neg logit contributions | |
gement | -5.953 |
llah | -5.779 |
gment | -5.572 |
Asset | -5.373 |
Brit | -5.346 |
Token | go |
Token ID | 467 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Duo | +1.858 |
enf | +1.706 |
Phi | +1.682 |
agra | +1.674 |
eny | +1.629 |
Neg logit contributions | |
gement | -2.303 |
llah | -2.237 |
gment | -2.145 |
Brit | -2.096 |
Asset | -2.068 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
Duo | +1.313 |
enf | +1.234 |
Phi | +1.209 |
agra | +1.202 |
eny | +1.173 |
Neg logit contributions | |
gement | -1.504 |
llah | -1.447 |
gment | -1.388 |
Brit | -1.361 |
Asset | -1.339 |
Token | book |
Token ID | 1492 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
gement | +8.697 |
llah | +7.809 |
Brit | +7.730 |
gment | +7.612 |
priv | +6.855 |
Neg logit contributions | |
Duo | -8.589 |
enf | -8.252 |
Phi | -7.899 |
eny | -7.853 |
cum | -7.755 |
Token | shop |
Token ID | 24643 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
gement | +2.706 |
llah | +2.520 |
gment | +2.461 |
Brit | +2.432 |
Asset | +2.304 |
Neg logit contributions | |
Duo | -2.658 |
Phi | -2.492 |
enf | -2.452 |
agra | -2.395 |
eny | -2.385 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
gement | +2.028 |
llah | +1.919 |
gment | +1.857 |
Brit | +1.840 |
Asset | +1.765 |
Neg logit contributions | |
Duo | -2.178 |
enf | -2.068 |
Phi | -2.031 |
agra | -2.013 |
eny | -1.977 |
Token | the |
Token ID | 1169 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
gement | +1.266 |
llah | +1.214 |
gment | +1.169 |
Brit | +1.161 |
Asset | +1.117 |
Neg logit contributions | |
Duo | -0.962 |
enf | -0.899 |
Phi | -0.894 |
agra | -0.880 |
eny | -0.851 |
Token | guard |
Token ID | 14864 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
gement | +4.837 |
gment | +4.242 |
llah | +3.689 |
Brit | +3.655 |
priv | +3.168 |
Neg logit contributions | |
Duo | -11.598 |
Phi | -11.392 |
enf | -10.875 |
eless | -10.605 |
Solo | -10.534 |
Token | a |
Token ID | 257 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
gement | +6.450 |
gment | +6.082 |
llah | +5.945 |
Brit | +5.754 |
Asset | +5.574 |
Neg logit contributions | |
enf | -6.120 |
Duo | -6.107 |
agra | -5.926 |
eny | -5.845 |
eless | -5.591 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
gement | +2.808 |
llah | +2.637 |
gment | +2.610 |
Brit | +2.536 |
Asset | +2.437 |
Neg logit contributions | |
Duo | -2.650 |
enf | -2.564 |
agra | -2.493 |
eny | -2.448 |
Phi | -2.437 |
Token | x |
Token ID | 87 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Duo | +3.283 |
enf | +3.079 |
Phi | +2.905 |
eny | +2.878 |
agra | +2.784 |
Neg logit contributions | |
gement | -6.141 |
llah | -6.013 |
Brit | -5.813 |
gment | -5.677 |
Asset | -5.621 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
gement | +2.220 |
llah | +2.082 |
gment | +2.049 |
Brit | +2.004 |
Asset | +1.950 |
Neg logit contributions | |
Duo | -2.120 |
enf | -2.003 |
agra | -1.964 |
Phi | -1.943 |
eny | -1.927 |
Token | Ga |
Token ID | 12822 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
Duo | +0.116 |
enf | +0.110 |
Phi | +0.108 |
agra | +0.107 |
eny | +0.105 |
Neg logit contributions | |
gement | -0.114 |
llah | -0.109 |
gment | -0.104 |
Brit | -0.103 |
Asset | -0.100 |
Token | ussian |
Token ID | 31562 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
gement | +2.502 |
gment | +2.268 |
Brit | +2.265 |
llah | +2.260 |
Asset | +2.199 |
Neg logit contributions | |
Duo | -4.449 |
enf | -4.333 |
agra | -4.184 |
Phi | -4.169 |
eny | -4.083 |
Token | , |
Token ID | 11 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
gement | +7.786 |
gment | +7.443 |
Brit | +6.912 |
llah | +6.900 |
Asset | +6.684 |
Neg logit contributions | |
enf | -9.423 |
agra | -9.275 |
Duo | -9.057 |
eny | -8.854 |
cum | -8.763 |
Token | then |
Token ID | 788 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
gement | +5.128 |
gment | +4.824 |
llah | +4.749 |
Brit | +4.607 |
Asset | +4.466 |
Neg logit contributions | |
Duo | -4.585 |
enf | -4.490 |
agra | -4.374 |
eny | -4.238 |
Phi | -4.110 |
Token | apply |
Token ID | 4174 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
Duo | +0.181 |
enf | +0.171 |
Phi | +0.167 |
agra | +0.166 |
eny | +0.163 |
Neg logit contributions | |
gement | -0.200 |
llah | -0.193 |
gment | -0.184 |
Brit | -0.182 |
Asset | -0.176 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
gement | +5.836 |
gment | +5.435 |
llah | +5.262 |
Brit | +5.145 |
Asset | +4.930 |
Neg logit contributions | |
Duo | -5.986 |
enf | -5.958 |
agra | -5.694 |
eny | -5.592 |
cum | -5.448 |
Token | black |
Token ID | 2042 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
gement | +1.585 |
llah | +1.501 |
gment | +1.460 |
Brit | +1.426 |
Asset | +1.378 |
Neg logit contributions | |
Duo | -1.517 |
enf | -1.451 |
agra | -1.407 |
Phi | -1.396 |
eny | -1.377 |
Token | stack |
Token ID | 8931 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Duo | +0.231 |
enf | +0.217 |
Phi | +0.213 |
agra | +0.211 |
eny | +0.206 |
Neg logit contributions | |
gement | -0.284 |
llah | -0.274 |
gment | -0.262 |
Brit | -0.260 |
Asset | -0.252 |
Token | pointer |
Token ID | 17562 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
gement | +1.037 |
llah | +0.930 |
gment | +0.861 |
Brit | +0.788 |
Asset | +0.757 |
Neg logit contributions | |
Duo | -3.228 |
enf | -3.130 |
agra | -3.094 |
Phi | -3.064 |
eny | -3.029 |
Token | + |
Token ID | 1343 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
gement | +4.852 |
llah | +4.465 |
gment | +4.355 |
Asset | +4.204 |
Brit | +4.161 |
Neg logit contributions | |
Duo | -5.023 |
enf | -4.941 |
agra | -4.783 |
eny | -4.693 |
Phi | -4.656 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
gement | +6.000 |
llah | +5.481 |
Asset | +5.013 |
Brit | +4.946 |
gment | +4.813 |
Neg logit contributions | |
Duo | -16.444 |
Phi | -15.107 |
conduc | -14.977 |
Solo | -14.891 |
unbeliev | -14.759 |
Token | --+ |
Token ID | 44785 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
gement | +5.038 |
llah | +4.802 |
gment | +4.604 |
Brit | +4.490 |
Asset | +4.396 |
Neg logit contributions | |
Duo | -6.880 |
enf | -6.435 |
Phi | -6.296 |
Solo | -6.189 |
agra | -6.119 |
Token | + |
Token ID | 1343 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
gement | +4.241 |
llah | +4.022 |
gment | +3.760 |
Brit | +3.750 |
Asset | +3.695 |
Neg logit contributions | |
enf | -6.217 |
Duo | -6.203 |
agra | -6.041 |
eny | -5.932 |
Phi | -5.822 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
gement | +6.138 |
llah | +5.537 |
Asset | +5.056 |
Brit | +5.028 |
gment | +4.950 |
Neg logit contributions | |
Duo | -16.109 |
Phi | -14.787 |
conduc | -14.707 |
Solo | -14.571 |
enf | -14.339 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
gement | +3.758 |
llah | +3.582 |
gment | +3.445 |
Brit | +3.384 |
Asset | +3.291 |
Neg logit contributions | |
Duo | -4.442 |
enf | -4.153 |
Phi | -4.068 |
agra | -3.996 |
Solo | -3.944 |
Token | < |
Token ID | 1279 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
gement | +5.000 |
llah | +4.638 |
gment | +4.407 |
Asset | +4.292 |
Brit | +4.229 |
Neg logit contributions | |
enf | -9.288 |
Duo | -9.269 |
agra | -9.200 |
eny | -8.772 |
eless | -8.693 |
Token | -- |
Token ID | 438 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
gement | +1.866 |
llah | +1.762 |
gment | +1.692 |
Brit | +1.689 |
Asset | +1.629 |
Neg logit contributions | |
Duo | -2.699 |
enf | -2.560 |
Phi | -2.529 |
agra | -2.524 |
eny | -2.458 |
Token | pop |
Token ID | 1461 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Duo | +1.484 |
enf | +1.369 |
Phi | +1.363 |
agra | +1.326 |
eny | +1.314 |
Neg logit contributions | |
gement | -1.836 |
llah | -1.790 |
Brit | -1.695 |
gment | -1.692 |
Asset | -1.632 |
Token | The |
Token ID | 464 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
gement | +3.504 |
Brit | +3.365 |
llah | +3.338 |
Asset | +3.220 |
gment | +3.206 |
Neg logit contributions | |
Duo | -3.408 |
Phi | -3.159 |
enf | -3.159 |
agra | -3.096 |
eny | -3.038 |
Token | deal |
Token ID | 1730 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
gement | +0.092 |
llah | +0.088 |
gment | +0.084 |
Brit | +0.083 |
Asset | +0.080 |
Neg logit contributions | |
Duo | -0.090 |
enf | -0.085 |
Phi | -0.083 |
agra | -0.083 |
eny | -0.081 |
Token | is |
Token ID | 318 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Duo | +0.554 |
enf | +0.523 |
Phi | +0.514 |
agra | +0.510 |
eny | +0.499 |
Neg logit contributions | |
gement | -0.596 |
llah | -0.574 |
gment | -0.547 |
Brit | -0.542 |
Asset | -0.525 |
Token | being |
Token ID | 852 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Duo | +2.497 |
enf | +2.331 |
Phi | +2.305 |
agra | +2.288 |
eny | +2.224 |
Neg logit contributions | |
gement | -2.601 |
llah | -2.542 |
gment | -2.397 |
Brit | -2.387 |
Asset | -2.285 |
Token | handled |
Token ID | 12118 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Duo | +2.825 |
enf | +2.644 |
Phi | +2.614 |
agra | +2.598 |
eny | +2.513 |
Neg logit contributions | |
gement | -2.910 |
llah | -2.824 |
Brit | -2.696 |
gment | -2.670 |
Asset | -2.582 |
Token | by |
Token ID | 416 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
gement | +1.077 |
llah | +1.032 |
gment | +0.991 |
Brit | +0.980 |
Asset | +0.946 |
Neg logit contributions | |
Duo | -0.949 |
enf | -0.897 |
Phi | -0.880 |
agra | -0.873 |
eny | -0.855 |
Token | Google |
Token ID | 3012 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
gement | +1.263 |
llah | +1.204 |
gment | +1.152 |
Brit | +1.141 |
Asset | +1.107 |
Neg logit contributions | |
Duo | -1.221 |
enf | -1.173 |
Phi | -1.140 |
agra | -1.140 |
eny | -1.119 |
Token | � |
Token ID | 447 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Duo | +0.532 |
enf | +0.501 |
Phi | +0.492 |
agra | +0.488 |
eny | +0.478 |
Neg logit contributions | |
gement | -0.561 |
llah | -0.540 |
gment | -0.515 |
Brit | -0.509 |
Asset | -0.492 |
Token | � |
Token ID | 247 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
gement | +0.294 |
llah | +0.282 |
gment | +0.269 |
Brit | +0.266 |
Asset | +0.257 |
Neg logit contributions | |
Duo | -0.294 |
enf | -0.278 |
Phi | -0.273 |
agra | -0.272 |
eny | -0.266 |
Token | s |
Token ID | 82 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
Duo | +1.942 |
enf | +1.842 |
Phi | +1.798 |
agra | +1.779 |
eny | +1.761 |
Neg logit contributions | |
gement | -1.635 |
llah | -1.578 |
gment | -1.486 |
Brit | -1.460 |
Asset | -1.403 |
Token | YouTube |
Token ID | 7444 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
gement | +0.714 |
llah | +0.682 |
gment | +0.654 |
Brit | +0.645 |
Asset | +0.626 |
Neg logit contributions | |
Duo | -0.672 |
enf | -0.639 |
Phi | -0.624 |
agra | -0.623 |
eny | -0.610 |
Token | " |
Token ID | 366 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Duo | +0.921 |
enf | +0.867 |
Phi | +0.855 |
agra | +0.845 |
eny | +0.828 |
Neg logit contributions | |
gement | -1.058 |
llah | -1.019 |
gment | -0.972 |
Brit | -0.958 |
Asset | -0.936 |
Token | You |
Token ID | 1639 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Duo | +1.635 |
enf | +1.541 |
Phi | +1.508 |
agra | +1.487 |
eny | +1.457 |
Neg logit contributions | |
gement | -2.042 |
llah | -1.975 |
gment | -1.882 |
Brit | -1.848 |
Asset | -1.803 |
Token | have |
Token ID | 423 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
gement | +1.431 |
llah | +1.365 |
gment | +1.296 |
Brit | +1.282 |
Asset | +1.217 |
Neg logit contributions | |
Duo | -1.667 |
enf | -1.590 |
Phi | -1.562 |
agra | -1.559 |
eny | -1.517 |
Token | to |
Token ID | 284 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Duo | +0.156 |
enf | +0.147 |
Phi | +0.144 |
agra | +0.143 |
eny | +0.140 |
Neg logit contributions | |
gement | -0.169 |
llah | -0.163 |
gment | -0.155 |
Brit | -0.154 |
Asset | -0.149 |
Token | come |
Token ID | 1282 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
gement | +1.440 |
llah | +1.381 |
gment | +1.319 |
Brit | +1.297 |
Asset | +1.239 |
Neg logit contributions | |
Duo | -1.493 |
enf | -1.420 |
agra | -1.395 |
Phi | -1.394 |
eny | -1.355 |
Token | off |
Token ID | 572 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
gement | +0.392 |
llah | +0.377 |
gment | +0.362 |
Brit | +0.358 |
Asset | +0.347 |
Neg logit contributions | |
Duo | -0.315 |
enf | -0.296 |
Phi | -0.289 |
agra | -0.288 |
eny | -0.281 |
Token | the |
Token ID | 262 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
gement | +2.268 |
llah | +2.166 |
gment | +2.075 |
Brit | +2.042 |
Asset | +1.977 |
Neg logit contributions | |
Duo | -2.263 |
enf | -2.148 |
agra | -2.081 |
Phi | -2.078 |
eny | -2.048 |
Token | racing |
Token ID | 11717 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
gement | +5.483 |
llah | +5.174 |
gment | +4.990 |
Brit | +4.921 |
Asset | +4.669 |
Neg logit contributions | |
Duo | -5.964 |
enf | -5.703 |
agra | -5.483 |
eny | -5.436 |
Phi | -5.401 |
Token | line |
Token ID | 1627 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
gement | +1.881 |
llah | +1.789 |
gment | +1.692 |
Brit | +1.672 |
Asset | +1.579 |
Neg logit contributions | |
Duo | -2.498 |
enf | -2.382 |
agra | -2.339 |
Phi | -2.330 |
eny | -2.298 |
Token | and |
Token ID | 290 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Duo | +2.001 |
enf | +1.883 |
Phi | +1.865 |
agra | +1.844 |
eny | +1.804 |
Neg logit contributions | |
gement | -2.354 |
llah | -2.280 |
gment | -2.169 |
Brit | -2.153 |
Asset | -2.113 |
Token | overtake |
Token ID | 48155 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
Duo | +0.311 |
enf | +0.294 |
Phi | +0.289 |
agra | +0.286 |
eny | +0.281 |
Neg logit contributions | |
gement | -0.310 |
llah | -0.297 |
gment | -0.283 |
Brit | -0.280 |
Asset | -0.271 |
Token | who |
Token ID | 508 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Duo | +0.632 |
enf | +0.597 |
Phi | +0.586 |
agra | +0.581 |
eny | +0.570 |
Neg logit contributions | |
gement | -0.686 |
llah | -0.660 |
gment | -0.630 |
Brit | -0.624 |
Asset | -0.604 |
Token | know |
Token ID | 760 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
gement | +1.843 |
llah | +1.738 |
gment | +1.664 |
Brit | +1.630 |
Asset | +1.542 |
Neg logit contributions | |
Duo | -2.321 |
enf | -2.228 |
Phi | -2.179 |
agra | -2.172 |
eny | -2.127 |
Token | its |
Token ID | 663 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
Duo | +1.391 |
enf | +1.297 |
Phi | +1.294 |
agra | +1.270 |
eny | +1.240 |
Neg logit contributions | |
gement | -1.631 |
llah | -1.575 |
gment | -1.498 |
Brit | -1.490 |
Asset | -1.438 |
Token | importance |
Token ID | 6817 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Duo | +5.203 |
Phi | +4.933 |
enf | +4.854 |
agra | +4.712 |
eny | +4.616 |
Neg logit contributions | |
gement | -5.778 |
llah | -5.670 |
Brit | -5.355 |
gment | -5.313 |
Asset | -5.119 |
Token | ." |
Token ID | 526 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Duo | +1.888 |
enf | +1.785 |
Phi | +1.750 |
agra | +1.729 |
eny | +1.702 |
Neg logit contributions | |
gement | -2.190 |
llah | -2.099 |
gment | -2.018 |
Brit | -1.998 |
Asset | -1.938 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Duo | +1.345 |
enf | +1.262 |
Phi | +1.249 |
agra | +1.233 |
eny | +1.203 |
Neg logit contributions | |
gement | -1.380 |
llah | -1.318 |
gment | -1.266 |
Brit | -1.232 |
Asset | -1.195 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
gement | +0.958 |
llah | +0.917 |
gment | +0.873 |
Brit | +0.871 |
Asset | +0.836 |
Neg logit contributions | |
Duo | -1.072 |
enf | -1.020 |
agra | -0.999 |
Phi | -0.998 |
eny | -0.977 |
Token | The |
Token ID | 464 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Duo | +2.467 |
enf | +2.369 |
agra | +2.323 |
Phi | +2.293 |
eny | +2.267 |
Neg logit contributions | |
gement | -2.892 |
llah | -2.779 |
gment | -2.657 |
Brit | -2.487 |
�� | -2.439 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Duo | +1.597 |
enf | +1.502 |
Phi | +1.486 |
agra | +1.474 |
eny | +1.441 |
Neg logit contributions | |
gement | -1.608 |
llah | -1.555 |
gment | -1.473 |
Brit | -1.455 |
Asset | -1.420 |
Token | ascent |
Token ID | 37137 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Duo | +2.157 |
enf | +2.023 |
Phi | +1.962 |
agra | +1.961 |
eny | +1.914 |
Neg logit contributions | |
gement | -2.789 |
llah | -2.714 |
gment | -2.579 |
Brit | -2.549 |
Asset | -2.497 |
Token | is |
Token ID | 318 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
gement | +1.171 |
llah | +1.117 |
gment | +1.069 |
Brit | +1.059 |
Asset | +1.013 |
Neg logit contributions | |
Duo | -1.187 |
enf | -1.121 |
Phi | -1.100 |
agra | -1.094 |
eny | -1.070 |
Token | have |
Token ID | 423 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
Duo | +1.194 |
enf | +1.122 |
Phi | +1.104 |
agra | +1.094 |
eny | +1.082 |
Neg logit contributions | |
gement | -1.126 |
llah | -1.078 |
gment | -1.027 |
Brit | -1.010 |
Asset | -0.990 |
Token | a |
Token ID | 257 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Duo | +3.199 |
enf | +2.981 |
Phi | +2.980 |
agra | +2.868 |
eny | +2.843 |
Neg logit contributions | |
gement | -3.532 |
llah | -3.475 |
gment | -3.242 |
Brit | -3.204 |
Asset | -3.191 |
Token | hot |
Token ID | 3024 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
Duo | +2.749 |
Phi | +2.572 |
enf | +2.550 |
agra | +2.487 |
eny | +2.436 |
Neg logit contributions | |
gement | -2.888 |
llah | -2.810 |
gment | -2.628 |
Brit | -2.605 |
Asset | -2.588 |
Token | bod |
Token ID | 16429 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
gement | +4.452 |
llah | +4.255 |
Brit | +4.199 |
gment | +4.082 |
Asset | +3.902 |
Neg logit contributions | |
Duo | -4.515 |
enf | -4.377 |
agra | -4.318 |
Phi | -4.183 |
eny | -4.154 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
gement | +0.268 |
llah | +0.256 |
gment | +0.244 |
Brit | +0.240 |
Asset | +0.231 |
Neg logit contributions | |
Duo | -0.307 |
enf | -0.292 |
Phi | -0.287 |
agra | -0.285 |
eny | -0.280 |
Token | Let |
Token ID | 3914 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Duo | +4.146 |
Phi | +3.836 |
enf | +3.730 |
Solo | +3.631 |
agra | +3.584 |
Neg logit contributions | |
gement | -4.522 |
llah | -4.329 |
gment | -4.154 |
Brit | -3.956 |
Asset | -3.892 |
Token | 's |
Token ID | 338 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
gement | +1.770 |
llah | +1.686 |
gment | +1.618 |
Brit | +1.603 |
Asset | +1.532 |
Neg logit contributions | |
Duo | -1.711 |
enf | -1.634 |
agra | -1.603 |
Phi | -1.596 |
eny | -1.566 |
Token | not |
Token ID | 407 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
gement | +0.026 |
llah | +0.025 |
gment | +0.023 |
Brit | +0.023 |
Asset | +0.022 |
Neg logit contributions | |
Duo | -0.024 |
enf | -0.022 |
Phi | -0.022 |
agra | -0.022 |
eny | -0.021 |
Token | pretend |
Token ID | 16614 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
gement | +0.729 |
llah | +0.700 |
gment | +0.670 |
Brit | +0.662 |
Asset | +0.638 |
Neg logit contributions | |
Duo | -0.665 |
enf | -0.633 |
Phi | -0.618 |
agra | -0.617 |
eny | -0.601 |
Token | we |
Token ID | 356 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Duo | +1.477 |
enf | +1.373 |
Phi | +1.367 |
agra | +1.329 |
eny | +1.311 |
Neg logit contributions | |
gement | -1.678 |
llah | -1.627 |
gment | -1.544 |
Brit | -1.519 |
Asset | -1.489 |
Token | 're |
Token ID | 821 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
gement | +0.217 |
llah | +0.208 |
gment | +0.198 |
Brit | +0.196 |
Asset | +0.188 |
Neg logit contributions | |
Duo | -0.232 |
enf | -0.220 |
Phi | -0.216 |
agra | -0.215 |
eny | -0.210 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Duo | +4.604 |
Phi | +4.296 |
enf | +4.156 |
agra | +4.118 |
cf | +4.068 |
Neg logit contributions | |
gement | -4.931 |
llah | -4.695 |
gment | -4.499 |
Brit | -4.378 |
Asset | -4.365 |
Token | short |
Token ID | 1790 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Duo | +1.526 |
enf | +1.434 |
Phi | +1.421 |
agra | +1.400 |
eny | +1.374 |
Neg logit contributions | |
gement | -1.587 |
llah | -1.522 |
gment | -1.450 |
Brit | -1.433 |
Asset | -1.399 |
Token | - |
Token ID | 12 |
Feature activation | -2.33e-04 |
Pos logit contributions | |
Duo | +1.727 |
enf | +1.637 |
agra | +1.606 |
Phi | +1.605 |
eny | +1.566 |
Neg logit contributions | |
gement | -1.800 |
llah | -1.734 |
gment | -1.646 |
Brit | -1.633 |
Asset | -1.588 |
Token | eared |
Token ID | 3380 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Duo | +0.000 |
enf | +0.000 |
Phi | +0.000 |
agra | +0.000 |
eny | +0.000 |
Neg logit contributions | |
gement | -0.000 |
llah | -0.000 |
gment | -0.000 |
Brit | -0.000 |
Asset | -0.000 |
Token | rock |
Token ID | 3881 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
gement | +1.035 |
llah | +0.995 |
gment | +0.952 |
Brit | +0.942 |
Asset | +0.905 |
Neg logit contributions | |
Duo | -0.963 |
enf | -0.914 |
Phi | -0.890 |
agra | -0.887 |
eny | -0.869 |
Token | - |
Token ID | 12 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
gement | +0.274 |
llah | +0.263 |
gment | +0.251 |
Brit | +0.248 |
Asset | +0.239 |
Neg logit contributions | |
Duo | -0.275 |
enf | -0.260 |
Phi | -0.255 |
agra | -0.254 |
eny | -0.249 |
Token | wall |
Token ID | 11930 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
gement | +0.354 |
llah | +0.340 |
gment | +0.325 |
Brit | +0.322 |
Asset | +0.311 |
Neg logit contributions | |
Duo | -0.329 |
enf | -0.310 |
Phi | -0.305 |
agra | -0.302 |
eny | -0.296 |
Token | aby |
Token ID | 3930 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Duo | +2.057 |
enf | +1.966 |
agra | +1.920 |
Phi | +1.917 |
eny | +1.884 |
Neg logit contributions | |
gement | -1.772 |
llah | -1.697 |
gment | -1.604 |
Brit | -1.590 |
Asset | -1.551 |
Token | ( |
Token ID | 357 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
gement | +0.765 |
llah | +0.736 |
gment | +0.703 |
Brit | +0.696 |
Asset | +0.671 |
Neg logit contributions | |
Duo | -0.733 |
enf | -0.696 |
Phi | -0.679 |
agra | -0.678 |
eny | -0.663 |
Token | Pet |
Token ID | 25803 |
Feature activation | -8.05e+00 |
Pos logit contributions | |
Duo | +2.561 |
enf | +2.419 |
Phi | +2.367 |
agra | +2.341 |
eny | +2.299 |
Neg logit contributions | |
gement | -3.060 |
llah | -2.948 |
gment | -2.809 |
Brit | -2.724 |
Asset | -2.680 |
Token | rog |
Token ID | 3828 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
Duo | +5.055 |
agra | +4.931 |
enf | +4.818 |
eny | +4.707 |
Phi | +4.699 |
Neg logit contributions | |
gement | -6.119 |
llah | -5.856 |
Asset | -5.602 |
Brit | -5.574 |
gment | -5.510 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Duo | +1.192 |
enf | +1.112 |
Phi | +1.101 |
agra | +1.084 |
eny | +1.066 |
Neg logit contributions | |
gement | -1.331 |
llah | -1.294 |
gment | -1.225 |
Brit | -1.216 |
Asset | -1.179 |
Token | out |
Token ID | 503 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
Duo | +3.892 |
enf | +3.597 |
Phi | +3.552 |
eny | +3.517 |
agra | +3.484 |
Neg logit contributions | |
gement | -5.038 |
llah | -4.919 |
Brit | -4.662 |
gment | -4.652 |
Asset | -4.549 |
Token | of |
Token ID | 286 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Duo | +3.302 |
enf | +3.101 |
Phi | +3.030 |
agra | +2.997 |
eny | +2.980 |
Neg logit contributions | |
gement | -3.989 |
llah | -3.873 |
Brit | -3.676 |
gment | -3.663 |
Asset | -3.579 |
Token | the |
Token ID | 262 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
gement | +2.147 |
llah | +2.020 |
gment | +1.968 |
Brit | +1.924 |
Asset | +1.862 |
Neg logit contributions | |
Duo | -2.049 |
enf | -1.980 |
agra | -1.923 |
Phi | -1.910 |
eny | -1.869 |
Token | full |
Token ID | 1336 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
gement | +0.558 |
llah | +0.533 |
gment | +0.510 |
Brit | +0.503 |
Asset | +0.486 |
Neg logit contributions | |
Duo | -0.575 |
enf | -0.549 |
Phi | -0.536 |
agra | -0.535 |
eny | -0.523 |
Token | sensor |
Token ID | 12694 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
Duo | +5.347 |
enf | +4.940 |
Phi | +4.919 |
eny | +4.772 |
agra | +4.769 |
Neg logit contributions | |
llah | -5.459 |
gement | -5.421 |
Brit | -5.017 |
gment | -4.945 |
Asset | -4.879 |
Token | area |
Token ID | 1989 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
Duo | +3.060 |
enf | +2.839 |
Phi | +2.819 |
agra | +2.778 |
eny | +2.736 |
Neg logit contributions | |
gement | -3.297 |
llah | -3.228 |
Brit | -3.031 |
gment | -3.015 |
Asset | -2.935 |
Token | with |
Token ID | 351 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Duo | +0.598 |
enf | +0.564 |
Phi | +0.553 |
agra | +0.549 |
eny | +0.539 |
Neg logit contributions | |
gement | -0.638 |
llah | -0.614 |
gment | -0.585 |
Brit | -0.581 |
Asset | -0.563 |
Token | v |
Token ID | 410 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
gement | +1.100 |
llah | +1.045 |
gment | +1.008 |
Brit | +0.991 |
Asset | +0.960 |
Neg logit contributions | |
Duo | -1.072 |
enf | -1.023 |
Phi | -0.998 |
agra | -0.995 |
eny | -0.974 |
Token | ign |
Token ID | 570 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
gement | +4.666 |
gment | +4.329 |
llah | +4.217 |
Brit | +4.152 |
Asset | +4.044 |
Neg logit contributions | |
Duo | -5.145 |
enf | -4.797 |
Phi | -4.769 |
agra | -4.673 |
eny | -4.672 |
Token | etting |
Token ID | 35463 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
gement | +1.311 |
llah | +1.256 |
gment | +1.207 |
Brit | +1.190 |
Asset | +1.156 |
Neg logit contributions | |
Duo | -1.065 |
enf | -0.992 |
Phi | -0.978 |
agra | -0.968 |
eny | -0.943 |
Token | Powell |
Token ID | 19675 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Duo | +2.164 |
enf | +2.011 |
Phi | +1.994 |
agra | +1.959 |
eny | +1.917 |
Neg logit contributions | |
gement | -2.362 |
llah | -2.281 |
gment | -2.178 |
Brit | -2.142 |
Asset | -2.072 |
Token | said |
Token ID | 531 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
gement | +1.982 |
llah | +1.880 |
gment | +1.783 |
Brit | +1.737 |
Asset | +1.665 |
Neg logit contributions | |
Duo | -2.752 |
enf | -2.628 |
Phi | -2.587 |
agra | -2.575 |
eny | -2.532 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Duo | +0.793 |
enf | +0.750 |
Phi | +0.733 |
agra | +0.728 |
eny | +0.716 |
Neg logit contributions | |
gement | -0.845 |
llah | -0.813 |
gment | -0.775 |
Brit | -0.768 |
Asset | -0.739 |
Token | adding |
Token ID | 4375 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
gement | +1.260 |
llah | +1.203 |
gment | +1.151 |
Brit | +1.141 |
Asset | +1.102 |
Neg logit contributions | |
Duo | -1.271 |
enf | -1.211 |
Phi | -1.182 |
agra | -1.178 |
eny | -1.154 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
Duo | +2.736 |
enf | +2.531 |
Phi | +2.517 |
agra | +2.463 |
eny | +2.434 |
Neg logit contributions | |
gement | -3.163 |
llah | -3.073 |
gment | -2.927 |
Brit | -2.895 |
Asset | -2.772 |
Token | company |
Token ID | 1664 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
Duo | +3.587 |
Phi | +3.342 |
enf | +3.338 |
agra | +3.281 |
eny | +3.202 |
Neg logit contributions | |
gement | -3.618 |
llah | -3.534 |
Brit | -3.327 |
gment | -3.326 |
Asset | -3.191 |
Token | looks |
Token ID | 3073 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Duo | +3.926 |
enf | +3.705 |
Phi | +3.655 |
agra | +3.586 |
eny | +3.479 |
Neg logit contributions | |
gement | -4.640 |
llah | -4.539 |
Brit | -4.255 |
gment | -4.229 |
Asset | -4.119 |
Token | closely |
Token ID | 7173 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Duo | +1.299 |
enf | +1.223 |
Phi | +1.198 |
agra | +1.185 |
eny | +1.158 |
Neg logit contributions | |
gement | -1.706 |
llah | -1.647 |
gment | -1.573 |
Brit | -1.567 |
Asset | -1.528 |
Token | at |
Token ID | 379 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
gement | +0.326 |
llah | +0.314 |
gment | +0.302 |
Brit | +0.298 |
Asset | +0.289 |
Neg logit contributions | |
Duo | -0.257 |
enf | -0.242 |
Phi | -0.237 |
agra | -0.235 |
eny | -0.230 |
Token | overtime |
Token ID | 17820 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Duo | +1.100 |
enf | +1.036 |
Phi | +1.022 |
agra | +1.009 |
eny | +0.987 |
Neg logit contributions | |
gement | -1.175 |
llah | -1.133 |
gment | -1.079 |
Brit | -1.073 |
Asset | -1.030 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
gement | +0.981 |
llah | +0.936 |
gment | +0.897 |
Brit | +0.885 |
Asset | +0.854 |
Neg logit contributions | |
Duo | -0.982 |
enf | -0.931 |
agra | -0.911 |
Phi | -0.910 |
eny | -0.888 |
Token | electronic |
Token ID | 7914 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Duo | +2.431 |
Phi | +2.261 |
enf | +2.245 |
agra | +2.182 |
eny | +2.153 |
Neg logit contributions | |
gement | -2.684 |
llah | -2.579 |
gment | -2.464 |
Brit | -2.451 |
Asset | -2.371 |
Token | text |
Token ID | 2420 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
Duo | +0.192 |
enf | +0.178 |
Phi | +0.174 |
agra | +0.172 |
eny | +0.167 |
Neg logit contributions | |
gement | -0.318 |
llah | -0.308 |
gment | -0.296 |
Brit | -0.294 |
Asset | -0.286 |
Token | uality |
Token ID | 25775 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Duo | +3.102 |
enf | +2.948 |
Phi | +2.890 |
agra | +2.867 |
eny | +2.824 |
Neg logit contributions | |
gement | -3.428 |
llah | -3.346 |
Brit | -3.153 |
gment | -3.133 |
Asset | -3.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
gement | +0.159 |
llah | +0.152 |
gment | +0.146 |
Brit | +0.144 |
Asset | +0.139 |
Neg logit contributions | |
Duo | -0.146 |
enf | -0.138 |
Phi | -0.136 |
agra | -0.135 |
eny | -0.132 |
Token | Matthew |
Token ID | 9308 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
gement | +2.013 |
llah | +1.932 |
gment | +1.848 |
Brit | +1.828 |
Asset | +1.761 |
Neg logit contributions | |
Duo | -1.908 |
enf | -1.831 |
agra | -1.778 |
Phi | -1.772 |
eny | -1.739 |
Token | Kir |
Token ID | 7385 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
gement | +0.944 |
llah | +0.909 |
gment | +0.867 |
Brit | +0.860 |
Asset | +0.830 |
Neg logit contributions | |
Duo | -0.854 |
enf | -0.811 |
agra | -0.791 |
Phi | -0.789 |
eny | -0.771 |
Token | sc |
Token ID | 1416 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
Duo | +2.266 |
enf | +2.181 |
agra | +2.117 |
eny | +2.111 |
Phi | +2.107 |
Neg logit contributions | |
gement | -2.567 |
llah | -2.472 |
Brit | -2.380 |
gment | -2.358 |
Asset | -2.311 |
Token | hen |
Token ID | 831 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Duo | +1.933 |
enf | +1.796 |
eny | +1.704 |
Phi | +1.682 |
agra | +1.647 |
Neg logit contributions | |
gement | -5.354 |
llah | -5.112 |
gment | -5.019 |
Asset | -5.012 |
Brit | -4.990 |
Token | baum |
Token ID | 24738 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
gement | +0.809 |
llah | +0.763 |
gment | +0.714 |
Brit | +0.697 |
Asset | +0.659 |
Neg logit contributions | |
Duo | -1.442 |
enf | -1.378 |
Phi | -1.363 |
agra | -1.357 |
eny | -1.327 |
Token | proposes |
Token ID | 26017 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
gement | +0.632 |
llah | +0.608 |
gment | +0.582 |
Brit | +0.574 |
Asset | +0.555 |
Neg logit contributions | |
Duo | -0.573 |
enf | -0.541 |
Phi | -0.531 |
agra | -0.528 |
eny | -0.515 |
Token | a |
Token ID | 257 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
gement | +0.141 |
llah | +0.136 |
gment | +0.129 |
Brit | +0.128 |
Asset | +0.124 |
Neg logit contributions | |
Duo | -0.136 |
enf | -0.129 |
Phi | -0.126 |
agra | -0.126 |
eny | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
Duo | +0.824 |
enf | +0.775 |
Phi | +0.762 |
agra | +0.752 |
eny | +0.737 |
Neg logit contributions | |
gement | -0.938 |
llah | -0.899 |
gment | -0.862 |
Brit | -0.853 |
Asset | -0.823 |
Token | file |
Token ID | 2393 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Duo | +3.121 |
enf | +2.879 |
Phi | +2.799 |
cf | +2.753 |
agra | +2.741 |
Neg logit contributions | |
gement | -4.743 |
llah | -4.711 |
Brit | -4.535 |
gment | -4.442 |
Asset | -4.241 |
Token | . |
Token ID | 13 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Duo | +2.023 |
enf | +1.898 |
Phi | +1.879 |
agra | +1.829 |
eny | +1.807 |
Neg logit contributions | |
gement | -2.450 |
llah | -2.336 |
gment | -2.238 |
Brit | -2.206 |
�� | -2.133 |
Token | The |
Token ID | 383 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
gement | +2.525 |
llah | +2.359 |
gment | +2.261 |
Brit | +2.184 |
Asset | +2.178 |
Neg logit contributions | |
Duo | -3.094 |
enf | -3.038 |
agra | -2.966 |
Phi | -2.933 |
eny | -2.914 |
Token | template |
Token ID | 11055 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
Duo | +3.269 |
enf | +3.009 |
Phi | +2.975 |
agra | +2.942 |
cf | +2.877 |
Neg logit contributions | |
gement | -3.186 |
llah | -3.165 |
Brit | -2.982 |
gment | -2.938 |
Asset | -2.786 |
Token | created |
Token ID | 2727 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
Duo | +3.897 |
enf | +3.600 |
Phi | +3.570 |
agra | +3.518 |
cf | +3.449 |
Neg logit contributions | |
gement | -4.231 |
llah | -4.153 |
gment | -3.907 |
Brit | -3.900 |
Asset | -3.689 |
Token | is |
Token ID | 318 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
Duo | +4.676 |
enf | +4.233 |
Phi | +4.196 |
agra | +4.180 |
cf | +4.062 |
Neg logit contributions | |
gement | -6.340 |
llah | -6.331 |
Brit | -6.034 |
gment | -5.893 |
Asset | -5.795 |
Token | pushed |
Token ID | 7121 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Duo | +2.702 |
enf | +2.528 |
agra | +2.472 |
Phi | +2.461 |
eny | +2.418 |
Neg logit contributions | |
gement | -2.774 |
llah | -2.720 |
Brit | -2.589 |
gment | -2.550 |
Asset | -2.437 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Duo | +1.081 |
enf | +1.011 |
Phi | +0.993 |
agra | +0.984 |
eny | +0.966 |
Neg logit contributions | |
gement | -1.242 |
llah | -1.198 |
gment | -1.145 |
Brit | -1.139 |
Asset | -1.098 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Duo | +1.098 |
enf | +1.025 |
Phi | +1.014 |
agra | +1.002 |
eny | +0.980 |
Neg logit contributions | |
gement | -1.139 |
llah | -1.104 |
gment | -1.048 |
Brit | -1.046 |
Asset | -1.000 |
Token | S |
Token ID | 311 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
Duo | +2.288 |
enf | +2.120 |
Phi | +2.107 |
agra | +2.071 |
eny | +2.032 |
Neg logit contributions | |
gement | -2.121 |
llah | -2.082 |
Brit | -1.967 |
gment | -1.948 |
Asset | -1.851 |
Token | experiences |
Token ID | 6461 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Duo | +0.562 |
enf | +0.508 |
Phi | +0.494 |
agra | +0.483 |
eny | +0.469 |
Neg logit contributions | |
gement | -1.408 |
llah | -1.374 |
Brit | -1.323 |
gment | -1.323 |
Asset | -1.289 |
Token | will |
Token ID | 481 |
Feature activation | -8.04e+00 |
Pos logit contributions | |
Duo | +0.600 |
enf | +0.568 |
Phi | +0.559 |
agra | +0.555 |
eny | +0.545 |
Neg logit contributions | |
gement | -0.565 |
llah | -0.543 |
gment | -0.515 |
Brit | -0.511 |
Asset | -0.494 |
Token | long |
Token ID | 890 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Duo | +4.699 |
Phi | +4.252 |
enf | +4.202 |
eless | +4.122 |
eny | +4.093 |
Neg logit contributions | |
gement | -6.549 |
llah | -6.388 |
Brit | -6.196 |
Asset | -6.074 |
gment | -6.035 |
Token | - |
Token ID | 12 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Duo | +1.484 |
enf | +1.393 |
Phi | +1.365 |
agra | +1.357 |
eny | +1.308 |
Neg logit contributions | |
gement | -2.253 |
llah | -2.188 |
Brit | -2.094 |
gment | -2.093 |
Asset | -2.033 |
Token | term |
Token ID | 4354 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
Duo | +2.342 |
enf | +2.240 |
agra | +2.166 |
Phi | +2.122 |
cum | +2.110 |
Neg logit contributions | |
gement | -3.493 |
llah | -3.452 |
Brit | -3.243 |
gment | -3.229 |
Asset | -3.162 |
Token | be |
Token ID | 307 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
Duo | +4.584 |
enf | +4.322 |
Phi | +4.306 |
agra | +4.224 |
eny | +4.157 |
Neg logit contributions | |
gement | -5.324 |
llah | -5.145 |
Brit | -4.983 |
gment | -4.849 |
Asset | -4.802 |
Token | forgotten |
Token ID | 11564 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Duo | +3.860 |
enf | +3.609 |
Phi | +3.590 |
agra | +3.515 |
eny | +3.430 |
Neg logit contributions | |
gement | -3.924 |
llah | -3.863 |
Brit | -3.678 |
gment | -3.555 |
Asset | -3.482 |
Token | . |
Token ID | 13 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Duo | +1.853 |
enf | +1.741 |
Phi | +1.706 |
agra | +1.691 |
eny | +1.661 |
Neg logit contributions | |
gement | -2.099 |
llah | -2.022 |
gment | -1.924 |
Brit | -1.924 |
Asset | -1.867 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Duo | +0.592 |
enf | +0.556 |
Phi | +0.551 |
agra | +0.543 |
eny | +0.532 |
Neg logit contributions | |
gement | -0.577 |
llah | -0.552 |
gment | -0.527 |
Brit | -0.519 |
Asset | -0.500 |
Token |
|
Token ID | 198 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
gement | +0.216 |
llah | +0.207 |
gment | +0.197 |
Brit | +0.195 |
Asset | +0.189 |
Neg logit contributions | |
Duo | -0.227 |
enf | -0.216 |
Phi | -0.211 |
agra | -0.210 |
eny | -0.206 |
Token | On |
Token ID | 2202 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
gement | +0.523 |
llah | +0.503 |
gment | +0.481 |
Brit | +0.478 |
Asset | +0.464 |
Neg logit contributions | |
Duo | -0.472 |
enf | -0.445 |
Phi | -0.436 |
agra | -0.434 |
eny | -0.424 |
Token | in |
Token ID | 287 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
Duo | +3.841 |
enf | +3.661 |
agra | +3.610 |
Phi | +3.566 |
eny | +3.512 |
Neg logit contributions | |
gement | -4.743 |
llah | -4.518 |
gment | -4.367 |
Brit | -4.304 |
Asset | -4.227 |
Token | parallel |
Token ID | 10730 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Duo | +5.041 |
agra | +4.788 |
enf | +4.781 |
Phi | +4.696 |
eny | +4.641 |
Neg logit contributions | |
gement | -5.709 |
llah | -5.519 |
gment | -5.301 |
Brit | -5.205 |
Asset | -5.138 |
Token | fashion |
Token ID | 6977 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Duo | +2.886 |
enf | +2.718 |
agra | +2.689 |
Phi | +2.667 |
eny | +2.623 |
Neg logit contributions | |
gement | -3.099 |
llah | -2.952 |
gment | -2.844 |
Brit | -2.791 |
Asset | -2.742 |
Token | , |
Token ID | 11 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
Duo | +2.775 |
enf | +2.636 |
Phi | +2.559 |
agra | +2.558 |
eny | +2.534 |
Neg logit contributions | |
gement | -3.177 |
llah | -3.054 |
gment | -2.926 |
Brit | -2.874 |
Asset | -2.819 |
Token | in |
Token ID | 259 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
Duo | +3.070 |
enf | +2.923 |
agra | +2.864 |
Phi | +2.847 |
eny | +2.808 |
Neg logit contributions | |
gement | -3.484 |
llah | -3.359 |
gment | -3.208 |
Brit | -3.158 |
Asset | -3.092 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
Duo | +5.480 |
agra | +5.214 |
enf | +5.182 |
Phi | +5.143 |
eny | +5.043 |
Neg logit contributions | |
gement | -5.997 |
llah | -5.837 |
gment | -5.533 |
Brit | -5.532 |
Asset | -5.410 |
Token | kind |
Token ID | 1611 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
Duo | +9.205 |
Phi | +8.635 |
agra | +8.635 |
enf | +8.593 |
cum | +8.337 |
Neg logit contributions | |
gement | -9.495 |
llah | -9.020 |
Asset | -8.628 |
gment | -8.565 |
Brit | -8.472 |
Token | of |
Token ID | 286 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
Duo | +2.575 |
enf | +2.433 |
agra | +2.377 |
Phi | +2.368 |
eny | +2.325 |
Neg logit contributions | |
gement | -2.948 |
llah | -2.838 |
gment | -2.708 |
Brit | -2.681 |
Asset | -2.618 |
Token | horizontal |
Token ID | 16021 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
Duo | +6.317 |
enf | +6.009 |
Phi | +5.914 |
agra | +5.911 |
eny | +5.770 |
Neg logit contributions | |
gement | -6.214 |
llah | -5.931 |
gment | -5.632 |
Brit | -5.512 |
Asset | -5.442 |
Token | storm |
Token ID | 6388 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
Duo | +5.576 |
Phi | +5.203 |
enf | +5.185 |
agra | +5.145 |
eny | +5.084 |
Neg logit contributions | |
gement | -5.494 |
llah | -5.204 |
gment | -4.981 |
Brit | -4.915 |
Asset | -4.826 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
gement | +3.511 |
llah | +3.376 |
gment | +3.218 |
Brit | +3.199 |
Asset | +3.045 |
Neg logit contributions | |
Duo | -3.650 |
enf | -3.442 |
Phi | -3.407 |
agra | -3.397 |
eny | -3.292 |
Token | now |
Token ID | 783 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Duo | +2.787 |
Phi | +2.594 |
enf | +2.571 |
agra | +2.506 |
eny | +2.490 |
Neg logit contributions | |
gement | -3.308 |
llah | -3.198 |
gment | -3.073 |
Brit | -3.027 |
Asset | -2.957 |
Token | that |
Token ID | 326 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
gement | +0.251 |
llah | +0.241 |
gment | +0.230 |
Brit | +0.228 |
Asset | +0.220 |
Neg logit contributions | |
Duo | -0.232 |
enf | -0.220 |
Phi | -0.215 |
agra | -0.214 |
eny | -0.209 |
Token | the |
Token ID | 262 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
gement | +0.275 |
llah | +0.265 |
gment | +0.253 |
Brit | +0.250 |
Asset | +0.242 |
Neg logit contributions | |
Duo | -0.255 |
enf | -0.241 |
Phi | -0.236 |
agra | -0.235 |
eny | -0.230 |
Token | Jets |
Token ID | 14728 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
gement | +4.055 |
llah | +3.886 |
gment | +3.657 |
Brit | +3.652 |
Asset | +3.447 |
Neg logit contributions | |
Duo | -4.587 |
enf | -4.473 |
agra | -4.381 |
Phi | -4.263 |
eny | -4.232 |
Token | have |
Token ID | 423 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
gement | +2.107 |
llah | +2.014 |
gment | +1.908 |
Brit | +1.888 |
Asset | +1.809 |
Neg logit contributions | |
Duo | -2.525 |
enf | -2.428 |
agra | -2.385 |
Phi | -2.378 |
eny | -2.308 |
Token | set |
Token ID | 900 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
gement | +3.638 |
llah | +3.424 |
gment | +3.310 |
Brit | +3.263 |
Asset | +3.130 |
Neg logit contributions | |
Duo | -3.704 |
enf | -3.574 |
agra | -3.510 |
Phi | -3.434 |
eny | -3.391 |
Token | a |
Token ID | 257 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
Duo | +7.557 |
Phi | +7.006 |
Solo | +6.654 |
enf | +6.610 |
eless | +6.602 |
Neg logit contributions | |
gement | -9.840 |
llah | -9.696 |
Brit | -9.414 |
gment | -9.265 |
Asset | -8.904 |
Token | modest |
Token ID | 12949 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Duo | +5.448 |
Phi | +5.056 |
enf | +4.926 |
agra | +4.783 |
Solo | +4.773 |
Neg logit contributions | |
gement | -5.897 |
llah | -5.713 |
Brit | -5.443 |
gment | -5.428 |
Asset | -5.343 |
Token | team |
Token ID | 1074 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Duo | +1.947 |
enf | +1.821 |
Phi | +1.810 |
agra | +1.770 |
eny | +1.742 |
Neg logit contributions | |
gement | -2.024 |
llah | -1.954 |
gment | -1.859 |
Brit | -1.849 |
Asset | -1.785 |
Token | record |
Token ID | 1700 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
Duo | +1.693 |
enf | +1.587 |
Phi | +1.553 |
agra | +1.528 |
eny | +1.499 |
Neg logit contributions | |
gement | -2.270 |
llah | -2.210 |
gment | -2.112 |
Brit | -2.095 |
Asset | -2.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Duo | +0.587 |
enf | +0.553 |
Phi | +0.542 |
agra | +0.538 |
eny | +0.528 |
Neg logit contributions | |
gement | -0.655 |
llah | -0.632 |
gment | -0.603 |
Brit | -0.597 |
Asset | -0.579 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
gement | +2.916 |
llah | +2.817 |
gment | +2.683 |
Brit | +2.632 |
Asset | +2.539 |
Neg logit contributions | |
Duo | -2.968 |
enf | -2.801 |
Phi | -2.773 |
agra | -2.757 |
eny | -2.681 |
Token | Story |
Token ID | 11605 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
gement | +4.594 |
llah | +4.423 |
Brit | +4.411 |
Asset | +4.263 |
gment | +4.255 |
Neg logit contributions | |
Duo | -4.312 |
Phi | -3.969 |
enf | -3.946 |
agra | -3.863 |
eny | -3.748 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
Duo | +0.305 |
enf | +0.287 |
Phi | +0.281 |
agra | +0.279 |
eny | +0.273 |
Neg logit contributions | |
gement | -0.361 |
llah | -0.348 |
gment | -0.332 |
Brit | -0.329 |
Asset | -0.319 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
llah | +8.953 |
Brit | +8.866 |
gement | +8.833 |
Asset | +8.245 |
Roy | +8.214 |
Neg logit contributions | |
agra | -8.274 |
enf | -8.160 |
eny | -8.007 |
Duo | -7.822 |
cum | -7.587 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Duo | +0.792 |
enf | +0.746 |
Phi | +0.733 |
agra | +0.725 |
eny | +0.711 |
Neg logit contributions | |
gement | -0.840 |
llah | -0.805 |
gment | -0.771 |
Brit | -0.762 |
Asset | -0.737 |
Token | Defense |
Token ID | 5947 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
gement | +0.175 |
llah | +0.169 |
gment | +0.163 |
Brit | +0.161 |
Asset | +0.157 |
Neg logit contributions | |
Duo | -0.115 |
enf | -0.107 |
Phi | -0.104 |
agra | -0.104 |
eny | -0.101 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
Duo | +8.581 |
Phi | +7.718 |
enf | +7.591 |
Solo | +7.540 |
cf | +7.406 |
Neg logit contributions | |
gement | -10.280 |
llah | -9.822 |
gment | -9.433 |
Brit | -9.255 |
Asset | -9.036 |
Token | Hag |
Token ID | 21375 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Duo | +2.960 |
enf | +2.660 |
Phi | +2.613 |
eny | +2.534 |
Solo | +2.485 |
Neg logit contributions | |
gement | -4.810 |
llah | -4.580 |
gment | -4.431 |
Brit | -4.410 |
Asset | -4.226 |
Token | el |
Token ID | 417 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
enf | +4.478 |
Duo | +4.400 |
eless | +4.030 |
eny | +4.010 |
eno | +3.738 |
Neg logit contributions | |
Brit | -10.078 |
gement | -9.917 |
Asset | -9.762 |
llah | -9.674 |
�� | -9.363 |
Token | will |
Token ID | 481 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
Duo | +3.376 |
enf | +3.143 |
Phi | +3.093 |
agra | +3.008 |
eny | +2.997 |
Neg logit contributions | |
gement | -3.850 |
llah | -3.702 |
gment | -3.532 |
Brit | -3.522 |
Asset | -3.443 |
Token | step |
Token ID | 2239 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Duo | +2.605 |
enf | +2.379 |
Phi | +2.376 |
eny | +2.290 |
agra | +2.285 |
Neg logit contributions | |
gement | -3.275 |
llah | -3.144 |
Brit | -3.038 |
gment | -3.016 |
Asset | -2.938 |
Token | go |
Token ID | 467 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
Duo | +2.014 |
enf | +1.894 |
Phi | +1.861 |
agra | +1.843 |
eny | +1.827 |
Neg logit contributions | |
gement | -2.022 |
llah | -1.961 |
Brit | -1.850 |
gment | -1.845 |
Asset | -1.782 |
Token | hand |
Token ID | 1021 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
Duo | +5.758 |
enf | +5.422 |
agra | +5.404 |
Phi | +5.365 |
eny | +5.302 |
Neg logit contributions | |
gement | -4.858 |
llah | -4.720 |
Brit | -4.512 |
gment | -4.367 |
Asset | -4.273 |
Token | in |
Token ID | 287 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
Duo | +2.625 |
Phi | +2.437 |
enf | +2.425 |
agra | +2.424 |
eless | +2.377 |
Neg logit contributions | |
gement | -3.260 |
llah | -3.182 |
gment | -3.040 |
Brit | -3.022 |
Asset | -2.924 |
Token | hand |
Token ID | 1021 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Duo | +4.868 |
enf | +4.614 |
Phi | +4.535 |
agra | +4.528 |
eny | +4.480 |
Neg logit contributions | |
gement | -3.396 |
llah | -3.371 |
Brit | -3.089 |
gment | -3.054 |
Asset | -2.990 |
Token | in |
Token ID | 287 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
gement | +0.674 |
llah | +0.647 |
gment | +0.618 |
Brit | +0.610 |
Asset | +0.591 |
Neg logit contributions | |
Duo | -0.642 |
enf | -0.608 |
Phi | -0.596 |
agra | -0.592 |
eny | -0.579 |
Token | today |
Token ID | 1909 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Duo | +4.549 |
Phi | +4.172 |
enf | +4.113 |
agra | +4.021 |
Solo | +3.941 |
Neg logit contributions | |
gement | -5.041 |
llah | -4.972 |
Brit | -4.765 |
gment | -4.611 |
Asset | -4.444 |
Token | � |
Token ID | 447 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Duo | +6.854 |
enf | +6.270 |
cum | +6.014 |
Phi | +6.004 |
� | +5.933 |
Neg logit contributions | |
gement | -10.276 |
llah | -10.233 |
Brit | -9.947 |
gment | -9.605 |
Asset | -9.358 |
Token | � |
Token ID | 247 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
Duo | +2.026 |
enf | +1.875 |
Phi | +1.861 |
agra | +1.834 |
eny | +1.803 |
Neg logit contributions | |
gement | -2.325 |
llah | -2.245 |
Brit | -2.150 |
gment | -2.144 |
Asset | -2.090 |
Token | s |
Token ID | 82 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
Duo | +4.732 |
enf | +4.472 |
Phi | +4.368 |
eny | +4.300 |
agra | +4.288 |
Neg logit contributions | |
gement | -3.449 |
llah | -3.359 |
Brit | -3.181 |
gment | -3.122 |
Asset | -2.986 |
Token | time |
Token ID | 640 |
Feature activation | -9.57e+00 |
Pos logit contributions | |
Duo | +13.007 |
Phi | +11.963 |
Solo | +11.529 |
enf | +11.160 |
dynam | +11.112 |
Neg logit contributions | |
Brit | -13.929 |
gement | -13.555 |
llah | -13.541 |
gment | -12.211 |
Asset | -12.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Duo | +5.824 |
enf | +5.319 |
Phi | +5.150 |
cf | +5.083 |
cum | +5.038 |
Neg logit contributions | |
gement | -7.443 |
llah | -7.137 |
Brit | -7.050 |
gment | -6.792 |
Asset | -6.626 |
Token | , |
Token ID | 11 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
Duo | +2.244 |
enf | +2.110 |
agra | +2.053 |
Phi | +2.052 |
eny | +2.023 |
Neg logit contributions | |
gement | -2.621 |
llah | -2.512 |
gment | -2.403 |
Brit | -2.386 |
Asset | -2.340 |
Token | 2000 |
Token ID | 4751 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
Duo | +3.679 |
enf | +3.449 |
Phi | +3.406 |
agra | +3.375 |
cf | +3.274 |
Neg logit contributions | |
gement | -3.814 |
llah | -3.661 |
gment | -3.495 |
Brit | -3.374 |
Asset | -3.349 |
Token | spears |
Token ID | 46842 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Duo | +7.969 |
enf | +7.617 |
agra | +7.520 |
cf | +7.490 |
cum | +7.365 |
Neg logit contributions | |
gement | -7.942 |
llah | -7.455 |
gment | -7.213 |
Asset | -7.142 |
�� | -6.956 |
Token | , |
Token ID | 11 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
Duo | +2.876 |
enf | +2.716 |
agra | +2.661 |
Phi | +2.653 |
eny | +2.594 |
Neg logit contributions | |
gement | -3.581 |
llah | -3.426 |
gment | -3.285 |
Brit | -3.244 |
Asset | -3.201 |
Token | 300 |
Token ID | 5867 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
Duo | +2.638 |
enf | +2.460 |
Phi | +2.444 |
agra | +2.419 |
eny | +2.332 |
Neg logit contributions | |
gement | -2.916 |
llah | -2.795 |
gment | -2.687 |
Brit | -2.632 |
Asset | -2.579 |
Token | arm |
Token ID | 3211 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
Duo | +6.135 |
enf | +5.826 |
agra | +5.784 |
cf | +5.678 |
Phi | +5.587 |
Neg logit contributions | |
gement | -6.261 |
llah | -5.918 |
gment | -5.682 |
Asset | -5.660 |
Brit | -5.515 |
Token | ours |
Token ID | 4662 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
agra | +9.216 |
enf | +9.054 |
Duo | +8.984 |
eless | +8.943 |
cum | +8.654 |
Neg logit contributions | |
gement | -9.979 |
llah | -9.488 |
�� | -9.214 |
gment | -9.205 |
Asset | -9.148 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Duo | +2.706 |
enf | +2.556 |
agra | +2.491 |
Phi | +2.484 |
eny | +2.429 |
Neg logit contributions | |
gement | -3.285 |
llah | -3.137 |
gment | -3.013 |
Brit | -2.973 |
Asset | -2.932 |
Token | 500 |
Token ID | 5323 |
Feature activation | -8.08e+00 |
Pos logit contributions | |
Duo | +2.217 |
enf | +2.086 |
Phi | +2.056 |
agra | +2.038 |
eny | +1.974 |
Neg logit contributions | |
gement | -2.349 |
llah | -2.258 |
gment | -2.163 |
Brit | -2.111 |
Asset | -2.069 |
Token | shields |
Token ID | 21132 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Duo | +5.591 |
enf | +5.312 |
agra | +5.226 |
Phi | +5.128 |
cf | +5.111 |
Neg logit contributions | |
gement | -5.678 |
llah | -5.374 |
gment | -5.147 |
Asset | -5.103 |
Brit | -5.003 |
Token | , |
Token ID | 11 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Duo | +1.122 |
enf | +1.058 |
Phi | +1.035 |
agra | +1.031 |
eny | +1.011 |
Neg logit contributions | |
gement | -1.251 |
llah | -1.199 |
gment | -1.147 |
Brit | -1.134 |
Asset | -1.106 |