Token | vi |
Token ID | 8903 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
ipop | +1.523 |
EQU | +1.517 |
atche | +1.451 |
aspers | +1.375 |
Tiff | +1.370 |
Neg logit contributions | |
Frazier | -1.093 |
�� | -1.006 |
VC | -0.987 |
mt | -0.986 |
bnb | -0.974 |
Token | : |
Token ID | 25 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
EQU | +3.190 |
ipop | +3.173 |
atche | +2.950 |
Tiff | +2.754 |
Expend | +2.707 |
Neg logit contributions | |
Frazier | -4.584 |
�� | -4.433 |
bnb | -4.229 |
VC | -4.214 |
Kh | -4.209 |
Token | ", |
Token ID | 1600 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ipop | +2.181 |
EQU | +2.171 |
atche | +2.085 |
Tiff | +1.967 |
aspers | +1.966 |
Neg logit contributions | |
Frazier | -1.446 |
�� | -1.319 |
VC | -1.286 |
mt | -1.278 |
bnb | -1.269 |
Token | " |
Token ID | 366 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
EQU | +3.263 |
ipop | +3.215 |
atche | +3.013 |
Tiff | +2.875 |
Expend | +2.819 |
Neg logit contributions | |
Frazier | -3.483 |
�� | -3.425 |
bnb | -3.204 |
Kh | -3.179 |
han | -3.177 |
Token | vim |
Token ID | 31124 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
ipop | +2.776 |
EQU | +2.755 |
atche | +2.633 |
aspers | +2.500 |
Tiff | +2.485 |
Neg logit contributions | |
Frazier | -2.007 |
�� | -1.865 |
mt | -1.812 |
VC | -1.811 |
bnb | -1.780 |
Token | :" |
Token ID | 11097 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
EQU | +5.106 |
ipop | +5.100 |
atche | +4.609 |
Tiff | +4.407 |
aspers | +4.317 |
Neg logit contributions | |
Frazier | -6.891 |
�� | -6.619 |
mt | -6.290 |
bnb | -6.278 |
VC | -6.278 |
Token | or |
Token ID | 393 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
EQU | +5.537 |
ipop | +5.331 |
atche | +4.713 |
Tiff | +4.475 |
Expend | +4.412 |
Neg logit contributions | |
�� | -10.126 |
Frazier | -9.866 |
�� | -9.398 |
�� | -9.311 |
�� | -9.291 |
Token | " |
Token ID | 366 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
EQU | +3.465 |
ipop | +3.368 |
atche | +3.148 |
Tiff | +3.019 |
Expend | +2.976 |
Neg logit contributions | |
Frazier | -3.797 |
�� | -3.795 |
bnb | -3.535 |
Kh | -3.468 |
�� | -3.456 |
Token | ex |
Token ID | 1069 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ipop | +4.365 |
EQU | +4.295 |
atche | +4.057 |
effective | +3.791 |
aspers | +3.657 |
Neg logit contributions | |
Frazier | -10.590 |
�� | -10.429 |
�� | -9.845 |
Hound | -9.804 |
�� | -9.795 |
Token | :" |
Token ID | 11097 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ipop | +3.288 |
EQU | +3.266 |
atche | +3.046 |
Tiff | +2.879 |
aspers | +2.870 |
Neg logit contributions | |
Frazier | -3.558 |
�� | -3.378 |
mt | -3.260 |
VC | -3.259 |
Kh | -3.228 |
Token | [ |
Token ID | 685 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
EQU | +2.964 |
ipop | +2.894 |
atche | +2.704 |
Tiff | +2.553 |
Expend | +2.498 |
Neg logit contributions | |
Frazier | -3.942 |
�� | -3.734 |
bnb | -3.663 |
han | -3.641 |
Kh | -3.614 |
Token | ", |
Token ID | 1600 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ipop | +2.181 |
EQU | +2.171 |
atche | +2.085 |
Tiff | +1.967 |
aspers | +1.966 |
Neg logit contributions | |
Frazier | -1.446 |
�� | -1.319 |
VC | -1.286 |
mt | -1.278 |
bnb | -1.269 |
Token | " |
Token ID | 366 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
EQU | +3.263 |
ipop | +3.215 |
atche | +3.013 |
Tiff | +2.875 |
Expend | +2.819 |
Neg logit contributions | |
Frazier | -3.483 |
�� | -3.425 |
bnb | -3.204 |
Kh | -3.179 |
han | -3.177 |
Token | vim |
Token ID | 31124 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
ipop | +2.776 |
EQU | +2.755 |
atche | +2.633 |
aspers | +2.500 |
Tiff | +2.485 |
Neg logit contributions | |
Frazier | -2.007 |
�� | -1.865 |
mt | -1.812 |
VC | -1.811 |
bnb | -1.780 |
Token | :" |
Token ID | 11097 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
EQU | +5.106 |
ipop | +5.100 |
atche | +4.609 |
Tiff | +4.407 |
aspers | +4.317 |
Neg logit contributions | |
Frazier | -6.891 |
�� | -6.619 |
mt | -6.290 |
bnb | -6.278 |
VC | -6.278 |
Token | or |
Token ID | 393 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
EQU | +5.537 |
ipop | +5.331 |
atche | +4.713 |
Tiff | +4.475 |
Expend | +4.412 |
Neg logit contributions | |
�� | -10.126 |
Frazier | -9.866 |
�� | -9.398 |
�� | -9.311 |
�� | -9.291 |
Token | " |
Token ID | 366 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
EQU | +3.465 |
ipop | +3.368 |
atche | +3.148 |
Tiff | +3.019 |
Expend | +2.976 |
Neg logit contributions | |
Frazier | -3.797 |
�� | -3.795 |
bnb | -3.535 |
Kh | -3.468 |
�� | -3.456 |
Token | ex |
Token ID | 1069 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ipop | +4.365 |
EQU | +4.295 |
atche | +4.057 |
effective | +3.791 |
aspers | +3.657 |
Neg logit contributions | |
Frazier | -10.590 |
�� | -10.429 |
�� | -9.845 |
Hound | -9.804 |
�� | -9.795 |
Token | :" |
Token ID | 11097 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ipop | +3.288 |
EQU | +3.266 |
atche | +3.046 |
Tiff | +2.879 |
aspers | +2.870 |
Neg logit contributions | |
Frazier | -3.558 |
�� | -3.378 |
mt | -3.260 |
VC | -3.259 |
Kh | -3.228 |
Token | [ |
Token ID | 685 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
EQU | +2.964 |
ipop | +2.894 |
atche | +2.704 |
Tiff | +2.553 |
Expend | +2.498 |
Neg logit contributions | |
Frazier | -3.942 |
�� | -3.734 |
bnb | -3.663 |
han | -3.641 |
Kh | -3.614 |
Token | white |
Token ID | 11186 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
Frazier | +0.307 |
�� | +0.285 |
VC | +0.282 |
mt | +0.281 |
han | +0.279 |
Neg logit contributions | |
ipop | -0.446 |
EQU | -0.444 |
atche | -0.423 |
Tiff | -0.402 |
aspers | -0.402 |
Token | ] |
Token ID | 60 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Frazier | +0.341 |
�� | +0.321 |
VC | +0.319 |
mt | +0.317 |
han | +0.315 |
Neg logit contributions | |
ipop | -0.288 |
EQU | -0.287 |
atche | -0.270 |
Tiff | -0.252 |
aspers | -0.252 |
Token | one |
Token ID | 530 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Frazier | +2.380 |
VC | +2.249 |
mt | +2.240 |
�� | +2.223 |
han | +2.216 |
Neg logit contributions | |
ipop | -2.219 |
EQU | -2.194 |
atche | -2.122 |
aspers | -1.957 |
Expend | -1.955 |
Token | blank |
Token ID | 9178 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Frazier | +0.205 |
�� | +0.181 |
VC | +0.180 |
mt | +0.178 |
han | +0.175 |
Neg logit contributions | |
ipop | -0.548 |
EQU | -0.546 |
atche | -0.526 |
aspers | -0.504 |
Tiff | -0.504 |
Token | character |
Token ID | 2095 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ipop | +0.708 |
EQU | +0.706 |
atche | +0.668 |
Tiff | +0.629 |
aspers | +0.626 |
Neg logit contributions | |
Frazier | -0.685 |
�� | -0.642 |
VC | -0.633 |
mt | -0.631 |
han | -0.627 |
Token | (< |
Token ID | 38155 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
EQU | +1.715 |
ipop | +1.712 |
atche | +1.599 |
Tiff | +1.495 |
aspers | +1.485 |
Neg logit contributions | |
Frazier | -2.107 |
�� | -1.988 |
VC | -1.955 |
mt | -1.950 |
han | -1.947 |
Token | Space |
Token ID | 14106 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
Frazier | +0.083 |
�� | +0.078 |
VC | +0.078 |
mt | +0.077 |
han | +0.077 |
Neg logit contributions | |
ipop | -0.059 |
EQU | -0.059 |
atche | -0.055 |
Tiff | -0.051 |
aspers | -0.051 |
Token | > |
Token ID | 29 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ipop | +0.606 |
EQU | +0.600 |
atche | +0.576 |
aspers | +0.546 |
Tiff | +0.542 |
Neg logit contributions | |
Frazier | -0.427 |
VC | -0.397 |
mt | -0.394 |
han | -0.389 |
Kh | -0.384 |
Token | or |
Token ID | 393 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
EQU | +5.128 |
ipop | +4.918 |
atche | +4.517 |
Tiff | +4.300 |
aspers | +4.199 |
Neg logit contributions | |
Frazier | -9.255 |
�� | -9.055 |
bnb | -8.725 |
�� | -8.673 |
han | -8.660 |
Token | < |
Token ID | 1279 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
EQU | +1.623 |
ipop | +1.619 |
atche | +1.517 |
Tiff | +1.424 |
aspers | +1.413 |
Neg logit contributions | |
Frazier | -1.934 |
�� | -1.833 |
VC | -1.802 |
mt | -1.796 |
han | -1.789 |
Token | Tab |
Token ID | 33349 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
EQU | +1.488 |
ipop | +1.471 |
atche | +1.382 |
Tiff | +1.292 |
aspers | +1.274 |
Neg logit contributions | |
Frazier | -2.096 |
�� | -2.005 |
mt | -1.960 |
VC | -1.958 |
bnb | -1.947 |
Token | >) |
Token ID | 43734 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ipop | +0.407 |
EQU | +0.404 |
atche | +0.378 |
Tiff | +0.348 |
aspers | +0.347 |
Neg logit contributions | |
Frazier | -0.596 |
VC | -0.564 |
�� | -0.562 |
mt | -0.561 |
han | -0.558 |
Token | { |
Token ID | 1391 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ipop | +1.107 |
EQU | +1.106 |
atche | +1.051 |
Tiff | +0.997 |
aspers | +0.994 |
Neg logit contributions | |
Frazier | -0.838 |
�� | -0.776 |
VC | -0.766 |
mt | -0.763 |
han | -0.758 |
Token | mates |
Token ID | 27973 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
Frazier | +1.154 |
VC | +1.044 |
mt | +1.035 |
han | +1.018 |
�� | +1.005 |
Neg logit contributions | |
ipop | -2.719 |
EQU | -2.670 |
atche | -2.587 |
Tiff | -2.475 |
aspers | -2.469 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ipop | +0.236 |
EQU | +0.235 |
atche | +0.223 |
aspers | +0.210 |
Tiff | +0.210 |
Neg logit contributions | |
Frazier | -0.212 |
�� | -0.197 |
VC | -0.196 |
mt | -0.195 |
han | -0.194 |
Token | V |
Token ID | 569 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
Frazier | +1.747 |
VC | +1.626 |
mt | +1.601 |
han | +1.590 |
�� | +1.589 |
Neg logit contributions | |
ipop | -1.969 |
EQU | -1.928 |
atche | -1.859 |
aspers | -1.735 |
Tiff | -1.720 |
Token | Ps |
Token ID | 12016 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Frazier | +0.059 |
VC | +0.055 |
han | +0.055 |
�� | +0.055 |
mt | +0.055 |
Neg logit contributions | |
ipop | -0.058 |
EQU | -0.058 |
atche | -0.055 |
Tiff | -0.052 |
aspers | -0.052 |
Token | See |
Token ID | 4091 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ipop | +0.700 |
EQU | +0.698 |
atche | +0.659 |
Tiff | +0.620 |
aspers | +0.618 |
Neg logit contributions | |
Frazier | -0.708 |
�� | -0.664 |
VC | -0.658 |
mt | -0.656 |
han | -0.651 |
Token | Gallery |
Token ID | 12917 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Frazier | +1.390 |
VC | +1.264 |
�� | +1.261 |
mt | +1.256 |
han | +1.246 |
Neg logit contributions | |
ipop | -2.136 |
EQU | -2.116 |
atche | -2.036 |
aspers | -1.933 |
Tiff | -1.920 |
Token | Donald |
Token ID | 3759 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
EQU | +5.519 |
ipop | +5.109 |
atche | +4.798 |
Expend | +4.772 |
Tiff | +4.761 |
Neg logit contributions | |
�� | -8.559 |
Frazier | -8.219 |
bnb | -8.034 |
�� | -7.968 |
mt | -7.961 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Frazier | +0.191 |
VC | +0.177 |
han | +0.175 |
mt | +0.174 |
Kh | +0.172 |
Neg logit contributions | |
ipop | -0.188 |
EQU | -0.185 |
atche | -0.178 |
aspers | -0.168 |
Tiff | -0.165 |
Token | passes |
Token ID | 8318 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
ipop | +1.586 |
EQU | +1.583 |
atche | +1.496 |
Tiff | +1.408 |
aspers | +1.404 |
Neg logit contributions | |
Frazier | -1.535 |
�� | -1.447 |
VC | -1.421 |
mt | -1.417 |
han | -1.406 |
Token | on |
Token ID | 319 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Frazier | +0.304 |
�� | +0.287 |
VC | +0.285 |
mt | +0.284 |
han | +0.282 |
Neg logit contributions | |
ipop | -0.246 |
EQU | -0.245 |
atche | -0.230 |
Tiff | -0.215 |
aspers | -0.214 |
Token | ' |
Token ID | 705 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Frazier | +1.016 |
�� | +0.939 |
VC | +0.932 |
mt | +0.927 |
han | +0.919 |
Neg logit contributions | |
ipop | -1.375 |
EQU | -1.370 |
atche | -1.304 |
Tiff | -1.236 |
aspers | -1.235 |
Token | ulse |
Token ID | 9615 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ipop | +1.539 |
EQU | +1.526 |
atche | +1.451 |
aspers | +1.358 |
Tiff | +1.354 |
Neg logit contributions | |
Frazier | -1.516 |
�� | -1.432 |
VC | -1.406 |
mt | -1.401 |
bnb | -1.387 |
Token | period |
Token ID | 2278 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ipop | +1.107 |
EQU | +1.103 |
atche | +1.035 |
Tiff | +0.964 |
aspers | +0.963 |
Neg logit contributions | |
Frazier | -1.387 |
�� | -1.304 |
VC | -1.299 |
mt | -1.294 |
han | -1.285 |
Token | " |
Token ID | 1 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
Frazier | +1.002 |
VC | +0.942 |
mt | +0.942 |
han | +0.935 |
Kh | +0.922 |
Neg logit contributions | |
ipop | -0.865 |
EQU | -0.857 |
atche | -0.807 |
aspers | -0.763 |
Tiff | -0.756 |
Token | , |
Token ID | 837 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ipop | +0.029 |
EQU | +0.028 |
atche | +0.027 |
aspers | +0.025 |
Tiff | +0.025 |
Neg logit contributions | |
Frazier | -0.025 |
VC | -0.024 |
mt | -0.023 |
han | -0.023 |
�� | -0.023 |
Token | Float |
Token ID | 48436 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
EQU | +1.353 |
ipop | +1.333 |
atche | +1.217 |
Tiff | +1.109 |
Expend | +1.093 |
Neg logit contributions | |
Frazier | -3.040 |
�� | -2.947 |
bnb | -2.871 |
VC | -2.869 |
han | -2.866 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ipop | +1.409 |
EQU | +1.404 |
atche | +1.314 |
Tiff | +1.220 |
aspers | +1.217 |
Neg logit contributions | |
Frazier | -1.880 |
�� | -1.778 |
VC | -1.763 |
mt | -1.757 |
han | -1.746 |
Token | = |
Token ID | 796 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
EQU | +4.223 |
ipop | +3.708 |
atche | +3.470 |
Tiff | +3.285 |
Expend | +3.258 |
Neg logit contributions | |
�� | -10.716 |
Frazier | -9.707 |
�� | -9.624 |
�� | -9.614 |
�� | -9.525 |
Token | 1 |
Token ID | 352 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ipop | +1.039 |
EQU | +1.035 |
atche | +0.988 |
Tiff | +0.937 |
aspers | +0.936 |
Neg logit contributions | |
Frazier | -0.744 |
VC | -0.683 |
�� | -0.679 |
mt | -0.679 |
han | -0.673 |
Token | // |
Token ID | 3373 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
Frazier | +1.443 |
VC | +1.357 |
mt | +1.356 |
han | +1.298 |
Kh | +1.283 |
Neg logit contributions | |
ipop | -3.265 |
EQU | -3.115 |
atche | -3.079 |
aspers | -2.987 |
Tiff | -2.873 |
Token | seconds |
Token ID | 4201 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Frazier | +0.547 |
VC | +0.508 |
mt | +0.504 |
�� | +0.502 |
han | +0.498 |
Neg logit contributions | |
ipop | -0.784 |
EQU | -0.772 |
atche | -0.742 |
Tiff | -0.706 |
aspers | -0.701 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
Frazier | +1.058 |
VC | +0.987 |
mt | +0.985 |
han | +0.973 |
�� | +0.970 |
Neg logit contributions | |
ipop | -1.128 |
EQU | -1.119 |
atche | -1.068 |
aspers | -1.009 |
Tiff | -1.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Frazier | +0.615 |
VC | +0.579 |
mt | +0.571 |
han | +0.563 |
Kh | +0.555 |
Neg logit contributions | |
ipop | -0.729 |
EQU | -0.717 |
atche | -0.689 |
aspers | -0.652 |
Tiff | -0.642 |
Token | streets |
Token ID | 6483 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Frazier | +0.935 |
VC | +0.879 |
mt | +0.869 |
han | +0.859 |
�� | +0.855 |
Neg logit contributions | |
ipop | -1.119 |
EQU | -1.110 |
atche | -1.056 |
Tiff | -0.995 |
aspers | -0.993 |
Token | of |
Token ID | 286 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ipop | +0.986 |
EQU | +0.983 |
atche | +0.932 |
Tiff | +0.878 |
aspers | +0.878 |
Neg logit contributions | |
Frazier | -0.884 |
�� | -0.822 |
VC | -0.819 |
mt | -0.815 |
han | -0.808 |
Token | the |
Token ID | 262 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
ipop | +0.150 |
EQU | +0.148 |
atche | +0.142 |
aspers | +0.134 |
Tiff | +0.132 |
Neg logit contributions | |
Frazier | -0.135 |
VC | -0.126 |
mt | -0.125 |
han | -0.124 |
Kh | -0.123 |
Token | city |
Token ID | 1748 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ipop | +0.762 |
EQU | +0.760 |
atche | +0.724 |
Tiff | +0.687 |
aspers | +0.686 |
Neg logit contributions | |
Frazier | -0.550 |
�� | -0.507 |
VC | -0.504 |
mt | -0.501 |
han | -0.497 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ipop | +1.036 |
EQU | +1.033 |
atche | +0.978 |
Tiff | +0.921 |
aspers | +0.919 |
Neg logit contributions | |
Frazier | -0.971 |
�� | -0.908 |
VC | -0.899 |
mt | -0.895 |
han | -0.889 |
Token | or |
Token ID | 393 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
EQU | +4.852 |
ipop | +4.737 |
atche | +4.181 |
Tiff | +4.079 |
Expend | +3.970 |
Neg logit contributions | |
�� | -9.410 |
Frazier | -8.708 |
�� | -8.594 |
�� | -8.589 |
�� | -8.527 |
Token | parked |
Token ID | 19584 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Frazier | +0.688 |
�� | +0.642 |
VC | +0.634 |
mt | +0.631 |
han | +0.627 |
Neg logit contributions | |
ipop | -0.808 |
EQU | -0.805 |
atche | -0.763 |
Tiff | -0.721 |
aspers | -0.720 |
Token | in |
Token ID | 287 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ipop | +0.925 |
EQU | +0.923 |
atche | +0.876 |
Tiff | +0.828 |
aspers | +0.824 |
Neg logit contributions | |
Frazier | -0.784 |
�� | -0.738 |
VC | -0.722 |
mt | -0.718 |
han | -0.714 |
Token | front |
Token ID | 2166 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Frazier | +0.069 |
�� | +0.065 |
VC | +0.064 |
mt | +0.064 |
han | +0.063 |
Neg logit contributions | |
ipop | -0.079 |
EQU | -0.079 |
atche | -0.075 |
Tiff | -0.071 |
aspers | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Frazier | +0.734 |
VC | +0.681 |
mt | +0.674 |
han | +0.670 |
Kh | +0.665 |
Neg logit contributions | |
ipop | -0.945 |
EQU | -0.931 |
atche | -0.889 |
aspers | -0.850 |
Tiff | -0.839 |
Token | vi |
Token ID | 8903 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
EQU | +4.282 |
ipop | +4.271 |
atche | +4.053 |
aspers | +3.873 |
Tiff | +3.828 |
Neg logit contributions | |
Frazier | -3.437 |
�� | -3.144 |
mt | -3.047 |
han | -3.044 |
bnb | -3.041 |
Token | : |
Token ID | 25 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ipop | +1.733 |
EQU | +1.728 |
atche | +1.625 |
Tiff | +1.519 |
aspers | +1.516 |
Neg logit contributions | |
Frazier | -1.988 |
�� | -1.874 |
VC | -1.855 |
mt | -1.848 |
han | -1.836 |
Token | | |
Token ID | 91 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
EQU | +4.875 |
ipop | +4.873 |
atche | +4.650 |
Tiff | +4.407 |
aspers | +4.387 |
Neg logit contributions | |
Frazier | -3.557 |
�� | -3.345 |
mt | -3.173 |
VC | -3.161 |
han | -3.146 |
Token | vim |
Token ID | 31124 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ipop | +2.800 |
EQU | +2.786 |
atche | +2.656 |
aspers | +2.523 |
Tiff | +2.516 |
Neg logit contributions | |
Frazier | -1.981 |
�� | -1.840 |
VC | -1.796 |
mt | -1.792 |
han | -1.769 |
Token | : |
Token ID | 25 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ipop | +1.904 |
EQU | +1.903 |
atche | +1.783 |
Tiff | +1.668 |
aspers | +1.661 |
Neg logit contributions | |
Frazier | -2.250 |
�� | -2.146 |
VC | -2.095 |
mt | -2.090 |
han | -2.074 |
Token | | |
Token ID | 91 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
EQU | +3.864 |
ipop | +3.839 |
atche | +3.678 |
Tiff | +3.499 |
aspers | +3.471 |
Neg logit contributions | |
Frazier | -2.618 |
�� | -2.514 |
mt | -2.356 |
VC | -2.350 |
bnb | -2.334 |
Token | ex |
Token ID | 1069 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ipop | +4.717 |
EQU | +4.694 |
atche | +4.349 |
effective | +4.132 |
aspers | +4.052 |
Neg logit contributions | |
Frazier | -8.777 |
�� | -8.308 |
Hound | -8.131 |
�� | -8.017 |
Kh | -8.006 |
Token | : |
Token ID | 25 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
ipop | +1.126 |
EQU | +1.122 |
atche | +1.058 |
Tiff | +0.989 |
aspers | +0.988 |
Neg logit contributions | |
Frazier | -1.257 |
VC | -1.176 |
�� | -1.173 |
mt | -1.170 |
han | -1.163 |
Token | } |
Token ID | 92 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ipop | +0.448 |
EQU | +0.446 |
atche | +0.421 |
Tiff | +0.397 |
aspers | +0.396 |
Neg logit contributions | |
Frazier | -0.441 |
�� | -0.410 |
VC | -0.406 |
mt | -0.405 |
han | -0.403 |
Token | the |
Token ID | 262 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
EQU | +3.700 |
ipop | +3.626 |
atche | +3.428 |
Tiff | +3.250 |
aspers | +3.234 |
Neg logit contributions | |
Frazier | -4.094 |
�� | -3.799 |
VC | -3.701 |
han | -3.695 |
bnb | -3.691 |
Token | string |
Token ID | 4731 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
EQU | +1.523 |
ipop | +1.496 |
atche | +1.405 |
Tiff | +1.332 |
aspers | +1.309 |
Neg logit contributions | |
Frazier | -1.852 |
�� | -1.744 |
han | -1.706 |
bnb | -1.702 |
Kh | -1.701 |
Token | they |
Token ID | 484 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
EQU | +4.336 |
ipop | +4.248 |
atche | +4.044 |
Tiff | +3.824 |
Expend | +3.736 |
Neg logit contributions | |
�� | -4.906 |
Frazier | -4.704 |
�� | -4.431 |
bnb | -4.417 |
�� | -4.371 |
Token | are |
Token ID | 389 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
EQU | +2.748 |
ipop | +2.727 |
atche | +2.583 |
Tiff | +2.421 |
aspers | +2.403 |
Neg logit contributions | |
Frazier | -2.831 |
�� | -2.808 |
bnb | -2.614 |
VC | -2.582 |
mt | -2.581 |
Token | not |
Token ID | 407 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
EQU | +3.133 |
ipop | +3.058 |
atche | +2.849 |
Tiff | +2.742 |
Expend | +2.674 |
Neg logit contributions | |
Frazier | -3.891 |
�� | -3.874 |
bnb | -3.600 |
iven | -3.562 |
VC | -3.558 |
Token | too |
Token ID | 1165 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
EQU | +3.684 |
ipop | +3.668 |
atche | +3.460 |
Tiff | +3.340 |
effective | +3.245 |
Neg logit contributions | |
Frazier | -2.905 |
�� | -2.881 |
bnb | -2.608 |
mt | -2.596 |
VC | -2.592 |
Token | obvious |
Token ID | 3489 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
ipop | +1.963 |
EQU | +1.959 |
atche | +1.864 |
Tiff | +1.771 |
aspers | +1.761 |
Neg logit contributions | |
Frazier | -1.426 |
�� | -1.321 |
VC | -1.296 |
mt | -1.292 |
bnb | -1.280 |
Token | ( |
Token ID | 357 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ipop | +0.162 |
EQU | +0.161 |
atche | +0.154 |
aspers | +0.145 |
Tiff | +0.143 |
Neg logit contributions | |
Frazier | -0.152 |
VC | -0.142 |
mt | -0.142 |
han | -0.140 |
Kh | -0.139 |
Token | as |
Token ID | 292 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ipop | +3.778 |
EQU | +3.678 |
atche | +3.480 |
effective | +3.254 |
aspers | +3.201 |
Neg logit contributions | |
�� | -9.988 |
Frazier | -9.837 |
�� | -9.223 |
�� | -9.155 |
mt | -9.152 |
Token | opposed |
Token ID | 6886 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
EQU | +4.229 |
ipop | +4.043 |
atche | +3.652 |
Tiff | +3.634 |
aspers | +3.478 |
Neg logit contributions | |
Frazier | -5.618 |
�� | -5.568 |
�� | -5.198 |
VC | -5.175 |
mt | -5.157 |
Token | to |
Token ID | 284 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ipop | +0.569 |
EQU | +0.566 |
atche | +0.536 |
aspers | +0.504 |
Tiff | +0.503 |
Neg logit contributions | |
Frazier | -0.551 |
VC | -0.513 |
mt | -0.511 |
�� | -0.508 |
han | -0.508 |
Token | back |
Token ID | 736 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Frazier | +1.155 |
VC | +1.073 |
mt | +1.069 |
�� | +1.068 |
han | +1.060 |
Neg logit contributions | |
ipop | -1.279 |
EQU | -1.277 |
atche | -1.215 |
aspers | -1.143 |
Tiff | -1.137 |
Token | in |
Token ID | 287 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ipop | +0.984 |
EQU | +0.983 |
atche | +0.931 |
Tiff | +0.878 |
aspers | +0.875 |
Neg logit contributions | |
Frazier | -0.860 |
�� | -0.821 |
VC | -0.789 |
mt | -0.785 |
bnb | -0.783 |
Token | supported |
Token ID | 4855 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Frazier | +1.251 |
VC | +1.159 |
mt | +1.150 |
han | +1.138 |
�� | +1.125 |
Neg logit contributions | |
ipop | -1.574 |
EQU | -1.566 |
atche | -1.501 |
aspers | -1.424 |
Tiff | -1.412 |
Token | : |
Token ID | 25 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
EQU | +2.571 |
ipop | +2.538 |
atche | +2.366 |
Expend | +2.216 |
Tiff | +2.212 |
Neg logit contributions | |
�� | -3.689 |
Frazier | -3.595 |
bnb | -3.365 |
mt | -3.342 |
VC | -3.325 |
Token | Chip |
Token ID | 17869 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ipop | +1.910 |
EQU | +1.896 |
atche | +1.732 |
Tiff | +1.603 |
Expend | +1.571 |
Neg logit contributions | |
Frazier | -3.856 |
�� | -3.741 |
mt | -3.642 |
VC | -3.637 |
han | -3.635 |
Token | in |
Token ID | 287 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
EQU | +2.732 |
ipop | +2.725 |
atche | +2.570 |
Tiff | +2.428 |
Expend | +2.417 |
Neg logit contributions | |
�� | -2.763 |
Frazier | -2.720 |
bnb | -2.508 |
Kh | -2.490 |
VC | -2.484 |
Token | $ |
Token ID | 720 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ipop | +0.518 |
EQU | +0.516 |
atche | +0.489 |
aspers | +0.460 |
Tiff | +0.460 |
Neg logit contributions | |
Frazier | -0.477 |
VC | -0.442 |
�� | -0.442 |
mt | -0.440 |
han | -0.436 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Frazier | +0.806 |
VC | +0.735 |
mt | +0.732 |
han | +0.726 |
Kh | +0.721 |
Neg logit contributions | |
ipop | -1.278 |
EQU | -1.267 |
atche | -1.213 |
aspers | -1.158 |
Tiff | -1.154 |
Token | or |
Token ID | 393 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
EQU | +4.606 |
ipop | +4.485 |
atche | +4.001 |
Tiff | +3.858 |
Expend | +3.815 |
Neg logit contributions | |
�� | -9.221 |
Frazier | -8.451 |
�� | -8.349 |
�� | -8.278 |
�� | -8.182 |
Token | more |
Token ID | 517 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
EQU | +3.731 |
ipop | +3.657 |
atche | +3.433 |
Tiff | +3.271 |
Expend | +3.265 |
Neg logit contributions | |
�� | -3.773 |
Frazier | -3.604 |
bnb | -3.372 |
iven | -3.354 |
Kh | -3.349 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ipop | +0.716 |
EQU | +0.712 |
atche | +0.675 |
aspers | +0.635 |
Tiff | +0.633 |
Neg logit contributions | |
Frazier | -0.696 |
VC | -0.647 |
mt | -0.644 |
�� | -0.640 |
han | -0.639 |
Token | help |
Token ID | 1037 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
EQU | +0.940 |
ipop | +0.937 |
atche | +0.881 |
Tiff | +0.826 |
aspers | +0.821 |
Neg logit contributions | |
Frazier | -1.005 |
�� | -0.981 |
VC | -0.936 |
mt | -0.933 |
bnb | -0.932 |
Token | us |
Token ID | 514 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ipop | +1.431 |
EQU | +1.427 |
atche | +1.361 |
Tiff | +1.294 |
aspers | +1.292 |
Neg logit contributions | |
Frazier | -0.949 |
�� | -0.877 |
VC | -0.864 |
mt | -0.860 |
han | -0.852 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
EQU | +3.028 |
ipop | +3.008 |
atche | +2.845 |
Tiff | +2.688 |
Expend | +2.660 |
Neg logit contributions | |
Frazier | -3.342 |
�� | -3.279 |
bnb | -3.171 |
mt | -3.168 |
VC | -3.129 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
EQU | +1.110 |
ipop | +1.101 |
atche | +1.043 |
Tiff | +1.000 |
Expend | +0.991 |
Neg logit contributions | |
Frazier | -0.900 |
�� | -0.861 |
mt | -0.831 |
VC | -0.830 |
bnb | -0.828 |
Token | Caption |
Token ID | 11260 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Frazier | +0.721 |
VC | +0.662 |
mt | +0.647 |
han | +0.641 |
Kh | +0.637 |
Neg logit contributions | |
ipop | -1.246 |
EQU | -1.219 |
atche | -1.188 |
aspers | -1.134 |
Tiff | -1.107 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
EQU | +5.238 |
ipop | +4.890 |
atche | +4.613 |
Tiff | +4.570 |
Expend | +4.504 |
Neg logit contributions | |
�� | -5.912 |
Frazier | -5.708 |
�� | -5.461 |
bnb | -5.382 |
�� | -5.306 |
Token | of |
Token ID | 286 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
EQU | +1.736 |
ipop | +1.736 |
atche | +1.639 |
Tiff | +1.548 |
aspers | +1.539 |
Neg logit contributions | |
Frazier | -1.627 |
�� | -1.550 |
VC | -1.502 |
mt | -1.498 |
bnb | -1.488 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
EQU | +4.999 |
ipop | +4.591 |
atche | +4.391 |
Expend | +4.299 |
Tiff | +4.282 |
Neg logit contributions | |
�� | -6.860 |
Frazier | -6.580 |
�� | -6.254 |
bnb | -6.211 |
�� | -6.168 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
EQU | +5.821 |
ipop | +5.379 |
Expend | +5.157 |
atche | +5.094 |
Tiff | +5.074 |
Neg logit contributions | |
�� | -7.950 |
Frazier | -7.293 |
�� | -7.216 |
�� | -7.165 |
�� | -7.114 |
Token | : |
Token ID | 25 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
EQU | +4.017 |
ipop | +3.807 |
atche | +3.567 |
Tiff | +3.468 |
Expend | +3.392 |
Neg logit contributions | |
�� | -6.612 |
Frazier | -6.152 |
�� | -5.941 |
�� | -5.921 |
bnb | -5.912 |
Token | Carly |
Token ID | 35982 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
EQU | +2.711 |
ipop | +2.658 |
atche | +2.479 |
Tiff | +2.389 |
Expend | +2.353 |
Neg logit contributions | |
Frazier | -3.787 |
�� | -3.759 |
bnb | -3.561 |
mt | -3.534 |
han | -3.526 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
ipop | +1.242 |
EQU | +1.238 |
atche | +1.130 |
Tiff | +1.036 |
aspers | +1.026 |
Neg logit contributions | |
Frazier | -2.413 |
�� | -2.326 |
VC | -2.283 |
mt | -2.283 |
bnb | -2.268 |
Token | 's |
Token ID | 338 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Frazier | +0.418 |
VC | +0.391 |
mt | +0.386 |
han | +0.384 |
Kh | +0.379 |
Neg logit contributions | |
ipop | -0.478 |
EQU | -0.473 |
atche | -0.452 |
aspers | -0.426 |
Tiff | -0.424 |
Token | + |
Token ID | 1343 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
EQU | +2.316 |
ipop | +2.298 |
atche | +2.167 |
Tiff | +2.053 |
aspers | +2.033 |
Neg logit contributions | |
Frazier | -2.141 |
�� | -2.015 |
VC | -1.969 |
bnb | -1.955 |
han | -1.953 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ipop | +0.585 |
EQU | +0.575 |
atche | +0.530 |
Tiff | +0.481 |
aspers | +0.475 |
Neg logit contributions | |
Frazier | -1.163 |
VC | -1.103 |
han | -1.099 |
mt | -1.098 |
�� | -1.094 |
Token | --+ |
Token ID | 44785 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ipop | +1.758 |
EQU | +1.741 |
atche | +1.585 |
Tiff | +1.437 |
aspers | +1.427 |
Neg logit contributions | |
Frazier | -3.808 |
VC | -3.617 |
�� | -3.615 |
mt | -3.607 |
han | -3.595 |
Token | | |
Token ID | 930 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
EQU | +1.492 |
ipop | +1.484 |
atche | +1.385 |
Tiff | +1.299 |
aspers | +1.293 |
Neg logit contributions | |
Frazier | -1.774 |
�� | -1.675 |
VC | -1.649 |
bnb | -1.639 |
mt | -1.638 |
Token | ... |
Token ID | 2644 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
EQU | +1.172 |
ipop | +1.165 |
atche | +1.067 |
Tiff | +0.994 |
Expend | +0.978 |
Neg logit contributions | |
Frazier | -1.944 |
�� | -1.845 |
VC | -1.821 |
bnb | -1.814 |
han | -1.812 |
Token | | |
Token ID | 930 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
EQU | +3.517 |
ipop | +3.446 |
atche | +3.254 |
Tiff | +3.098 |
Expend | +3.070 |
Neg logit contributions | |
Frazier | -3.377 |
�� | -3.311 |
bnb | -3.116 |
VC | -3.103 |
mt | -3.090 |
Token | + |
Token ID | 1343 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
EQU | +6.183 |
ipop | +5.841 |
atche | +5.467 |
Tiff | +5.209 |
Expend | +5.109 |
Neg logit contributions | |
Frazier | -7.226 |
�� | -6.858 |
Kh | -6.632 |
bnb | -6.615 |
iven | -6.578 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ipop | +1.083 |
EQU | +1.071 |
atche | +0.982 |
Tiff | +0.888 |
aspers | +0.879 |
Neg logit contributions | |
Frazier | -2.254 |
VC | -2.138 |
�� | -2.133 |
mt | -2.129 |
han | -2.128 |
Token | --+ |
Token ID | 44785 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ipop | +2.216 |
EQU | +2.211 |
atche | +2.006 |
Tiff | +1.788 |
aspers | +1.786 |
Neg logit contributions | |
Frazier | -5.255 |
�� | -5.031 |
VC | -4.984 |
mt | -4.970 |
han | -4.939 |
Token |
|
Token ID | 198 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
EQU | +2.000 |
ipop | +1.986 |
atche | +1.861 |
Tiff | +1.742 |
aspers | +1.730 |
Neg logit contributions | |
Frazier | -2.342 |
�� | -2.204 |
VC | -2.167 |
bnb | -2.159 |
mt | -2.152 |
Token |
|
Token ID | 198 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
ipop | +0.342 |
EQU | +0.338 |
atche | +0.321 |
aspers | +0.300 |
Tiff | +0.299 |
Neg logit contributions | |
Frazier | -0.373 |
VC | -0.350 |
mt | -0.347 |
han | -0.346 |
Kh | -0.343 |
Token | + |
Token ID | 1343 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
EQU | +3.153 |
ipop | +3.098 |
atche | +2.935 |
Tiff | +2.796 |
Expend | +2.763 |
Neg logit contributions | |
Frazier | -2.874 |
�� | -2.796 |
bnb | -2.643 |
VC | -2.637 |
mt | -2.627 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ipop | +0.408 |
EQU | +0.399 |
atche | +0.369 |
Tiff | +0.337 |
aspers | +0.331 |
Neg logit contributions | |
Frazier | -0.781 |
VC | -0.742 |
han | -0.740 |
mt | -0.738 |
Kh | -0.736 |
Token | --+ |
Token ID | 44785 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ipop | +1.868 |
EQU | +1.852 |
atche | +1.686 |
Tiff | +1.523 |
aspers | +1.512 |
Neg logit contributions | |
Frazier | -4.142 |
�� | -3.942 |
VC | -3.933 |
mt | -3.921 |
han | -3.907 |
Token | | |
Token ID | 930 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
EQU | +1.961 |
ipop | +1.944 |
atche | +1.819 |
Tiff | +1.720 |
aspers | +1.705 |
Neg logit contributions | |
Frazier | -2.089 |
�� | -1.974 |
VC | -1.929 |
bnb | -1.926 |
han | -1.914 |
Token | ... |
Token ID | 2644 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
EQU | +0.786 |
ipop | +0.786 |
atche | +0.719 |
Tiff | +0.664 |
aspers | +0.654 |
Neg logit contributions | |
Frazier | -1.377 |
�� | -1.309 |
VC | -1.294 |
mt | -1.286 |
han | -1.286 |
Token | | |
Token ID | 930 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
EQU | +3.345 |
ipop | +3.286 |
atche | +3.103 |
Tiff | +2.953 |
Expend | +2.923 |
Neg logit contributions | |
Frazier | -3.178 |
�� | -3.097 |
bnb | -2.925 |
VC | -2.918 |
mt | -2.907 |
Token | + |
Token ID | 1343 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
EQU | +6.315 |
ipop | +5.782 |
atche | +5.505 |
Tiff | +5.395 |
Expend | +5.304 |
Neg logit contributions | |
�� | -7.325 |
Frazier | -6.963 |
�� | -6.724 |
�� | -6.621 |
�� | -6.526 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ipop | +0.913 |
EQU | +0.899 |
atche | +0.828 |
Tiff | +0.750 |
aspers | +0.741 |
Neg logit contributions | |
Frazier | -1.842 |
VC | -1.748 |
han | -1.742 |
mt | -1.739 |
�� | -1.736 |
Token | --+ |
Token ID | 44785 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ipop | +2.266 |
EQU | +2.266 |
atche | +2.054 |
Tiff | +1.824 |
aspers | +1.824 |
Neg logit contributions | |
Frazier | -5.465 |
�� | -5.237 |
VC | -5.180 |
mt | -5.168 |
han | -5.131 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
EQU | +1.839 |
ipop | +1.835 |
atche | +1.708 |
Tiff | +1.597 |
aspers | +1.579 |
Neg logit contributions | |
Frazier | -2.266 |
�� | -2.137 |
VC | -2.095 |
bnb | -2.094 |
mt | -2.083 |
Token |
|
Token ID | 198 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
ipop | +1.103 |
EQU | +1.098 |
atche | +1.033 |
Tiff | +0.965 |
aspers | +0.963 |
Neg logit contributions | |
Frazier | -1.288 |
�� | -1.209 |
VC | -1.203 |
mt | -1.198 |
han | -1.191 |
Token | . |
Token ID | 13 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
ipop | +1.495 |
EQU | +1.488 |
atche | +1.407 |
Tiff | +1.324 |
Expend | +1.307 |
Neg logit contributions | |
Frazier | -1.501 |
�� | -1.434 |
mt | -1.406 |
VC | -1.396 |
bnb | -1.395 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Frazier | +0.045 |
VC | +0.041 |
�� | +0.041 |
mt | +0.041 |
han | +0.041 |
Neg logit contributions | |
ipop | -0.056 |
EQU | -0.055 |
atche | -0.053 |
aspers | -0.050 |
Tiff | -0.049 |
Token | Caption |
Token ID | 11260 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Frazier | +0.760 |
VC | +0.698 |
mt | +0.681 |
han | +0.673 |
Kh | +0.668 |
Neg logit contributions | |
ipop | -1.344 |
EQU | -1.305 |
atche | -1.281 |
aspers | -1.222 |
Tiff | -1.186 |
Token | 14 |
Token ID | 1478 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
EQU | +3.774 |
ipop | +3.612 |
atche | +3.401 |
Tiff | +3.268 |
Expend | +3.144 |
Neg logit contributions | |
�� | -6.095 |
Frazier | -6.030 |
bnb | -5.738 |
�� | -5.661 |
VC | -5.646 |
Token | of |
Token ID | 286 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
EQU | +2.321 |
ipop | +2.312 |
atche | +2.183 |
Tiff | +2.066 |
aspers | +2.044 |
Neg logit contributions | |
Frazier | -2.243 |
�� | -2.176 |
mt | -2.067 |
VC | -2.066 |
bnb | -2.061 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
EQU | +5.169 |
ipop | +4.798 |
atche | +4.577 |
Expend | +4.436 |
Tiff | +4.428 |
Neg logit contributions | |
�� | -7.102 |
Frazier | -6.792 |
�� | -6.452 |
bnb | -6.391 |
�� | -6.334 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
EQU | +5.757 |
ipop | +5.309 |
Expend | +5.075 |
Tiff | +5.040 |
atche | +4.992 |
Neg logit contributions | |
�� | -7.763 |
Frazier | -7.098 |
�� | -7.028 |
�� | -7.002 |
bnb | -6.954 |
Token | : |
Token ID | 25 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
EQU | +4.014 |
ipop | +3.809 |
atche | +3.555 |
Tiff | +3.474 |
Expend | +3.394 |
Neg logit contributions | |
�� | -6.634 |
Frazier | -6.141 |
�� | -5.954 |
�� | -5.950 |
bnb | -5.921 |
Token | Carly |
Token ID | 35982 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
EQU | +2.849 |
ipop | +2.788 |
atche | +2.597 |
Tiff | +2.513 |
Expend | +2.472 |
Neg logit contributions | |
Frazier | -4.015 |
�� | -4.008 |
bnb | -3.786 |
han | -3.745 |
mt | -3.743 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ipop | +1.601 |
EQU | +1.597 |
atche | +1.438 |
Tiff | +1.337 |
Expend | +1.320 |
Neg logit contributions | |
Frazier | -3.252 |
�� | -3.200 |
mt | -3.091 |
bnb | -3.082 |
VC | -3.077 |
Token | 's |
Token ID | 338 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ipop | +0.174 |
EQU | +0.173 |
atche | +0.165 |
aspers | +0.155 |
Tiff | +0.155 |
Neg logit contributions | |
Frazier | -0.156 |
VC | -0.146 |
mt | -0.144 |
han | -0.143 |
Kh | -0.142 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
EQU | +2.600 |
ipop | +2.596 |
atche | +2.402 |
Tiff | +2.343 |
Expend | +2.279 |
Neg logit contributions | |
Frazier | -2.968 |
�� | -2.922 |
bnb | -2.849 |
mt | -2.821 |
Kh | -2.786 |
Token | , |
Token ID | 11 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ipop | +4.578 |
EQU | +4.538 |
atche | +4.263 |
Tiff | +4.036 |
Expend | +3.970 |
Neg logit contributions | |
�� | -5.741 |
Frazier | -5.689 |
mt | -5.486 |
bnb | -5.444 |
Kh | -5.420 |
Token | California |
Token ID | 3442 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
EQU | +3.521 |
ipop | +3.462 |
atche | +3.232 |
Tiff | +3.093 |
Expend | +3.013 |
Neg logit contributions | |
�� | -4.097 |
Frazier | -4.048 |
�� | -3.823 |
bnb | -3.808 |
han | -3.744 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ipop | +4.032 |
EQU | +4.000 |
atche | +3.786 |
Tiff | +3.493 |
Expend | +3.473 |
Neg logit contributions | |
Frazier | -4.632 |
�� | -4.459 |
mt | -4.406 |
bnb | -4.374 |
VC | -4.310 |
Token | Hide |
Token ID | 10415 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
EQU | +1.442 |
ipop | +1.438 |
atche | +1.357 |
Tiff | +1.289 |
Expend | +1.278 |
Neg logit contributions | |
Frazier | -1.311 |
�� | -1.242 |
VC | -1.213 |
mt | -1.212 |
bnb | -1.205 |
Token | Caption |
Token ID | 11260 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Frazier | +0.478 |
VC | +0.438 |
mt | +0.430 |
han | +0.427 |
Kh | +0.424 |
Neg logit contributions | |
ipop | -0.809 |
EQU | -0.793 |
atche | -0.771 |
aspers | -0.735 |
Tiff | -0.721 |
Token | 9 |
Token ID | 860 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
EQU | +6.233 |
ipop | +5.908 |
atche | +5.536 |
Tiff | +5.492 |
Expend | +5.306 |
Neg logit contributions | |
�� | -7.293 |
Frazier | -6.799 |
bnb | -6.495 |
�� | -6.462 |
�� | -6.435 |
Token | of |
Token ID | 286 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
EQU | +1.597 |
ipop | +1.596 |
atche | +1.508 |
Tiff | +1.424 |
aspers | +1.415 |
Neg logit contributions | |
Frazier | -1.498 |
�� | -1.428 |
VC | -1.383 |
mt | -1.380 |
bnb | -1.371 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
EQU | +4.715 |
ipop | +4.395 |
atche | +4.168 |
Expend | +4.059 |
Tiff | +4.050 |
Neg logit contributions | |
�� | -6.367 |
Frazier | -6.112 |
�� | -5.793 |
bnb | -5.773 |
�� | -5.711 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
EQU | +5.583 |
ipop | +5.204 |
Expend | +4.946 |
atche | +4.901 |
Tiff | +4.880 |
Neg logit contributions | |
�� | -7.423 |
Frazier | -6.838 |
�� | -6.715 |
�� | -6.670 |
bnb | -6.647 |
Token | : |
Token ID | 25 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
EQU | +4.033 |
ipop | +3.823 |
atche | +3.571 |
Tiff | +3.476 |
Expend | +3.400 |
Neg logit contributions | |
�� | -6.704 |
Frazier | -6.210 |
�� | -6.018 |
�� | -6.008 |
bnb | -5.982 |
Token | \ |
Token ID | 59 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ipop | +1.407 |
EQU | +1.403 |
atche | +1.332 |
Tiff | +1.260 |
aspers | +1.259 |
Neg logit contributions | |
Frazier | -1.135 |
�� | -1.055 |
VC | -1.043 |
mt | -1.038 |
han | -1.031 |
Token | S |
Token ID | 50 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
ipop | +0.281 |
EQU | +0.280 |
atche | +0.264 |
Tiff | +0.248 |
aspers | +0.247 |
Neg logit contributions | |
Frazier | -0.295 |
�� | -0.276 |
VC | -0.275 |
mt | -0.273 |
han | -0.272 |
Token | +) |
Token ID | 28988 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
EQU | +3.578 |
ipop | +3.527 |
atche | +3.275 |
Tiff | +2.895 |
aspers | +2.879 |
Neg logit contributions | |
Frazier | -7.369 |
�� | -7.055 |
han | -6.909 |
mt | -6.897 |
VC | -6.887 |
Token | "] |
Token ID | 8973 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ipop | +0.074 |
EQU | +0.073 |
atche | +0.070 |
Tiff | +0.065 |
aspers | +0.065 |
Neg logit contributions | |
Frazier | -0.070 |
�� | -0.065 |
VC | -0.065 |
mt | -0.065 |
han | -0.065 |
Token | ' |
Token ID | 6 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
EQU | +1.921 |
ipop | +1.905 |
atche | +1.806 |
Tiff | +1.707 |
aspers | +1.698 |
Neg logit contributions | |
Frazier | -1.661 |
�� | -1.561 |
VC | -1.526 |
mt | -1.512 |
han | -1.504 |
Token | ) |
Token ID | 1267 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Frazier | +0.883 |
�� | +0.833 |
VC | +0.831 |
mt | +0.829 |
han | +0.820 |
Neg logit contributions | |
ipop | -0.704 |
EQU | -0.696 |
atche | -0.657 |
Tiff | -0.612 |
aspers | -0.611 |
Token | AS |
Token ID | 7054 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
EQU | +4.115 |
ipop | +3.502 |
atche | +3.322 |
Tiff | +3.087 |
ASC | +3.038 |
Neg logit contributions | |
Frazier | -9.177 |
�� | -9.079 |
bnb | -8.611 |
iven | -8.573 |
Kh | -8.556 |
Token | version |
Token ID | 2196 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
Frazier | +1.041 |
VC | +0.977 |
mt | +0.972 |
�� | +0.950 |
han | +0.949 |
Neg logit contributions | |
ipop | -1.263 |
EQU | -1.242 |
atche | -1.197 |
aspers | -1.127 |
Tiff | -1.116 |
Token | , |
Token ID | 837 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Frazier | +0.455 |
VC | +0.427 |
mt | +0.425 |
�� | +0.424 |
han | +0.422 |
Neg logit contributions | |
ipop | -0.472 |
EQU | -0.464 |
atche | -0.442 |
Tiff | -0.417 |
aspers | -0.416 |
Token | C |
Token ID | 327 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
EQU | +0.706 |
ipop | +0.705 |
atche | +0.659 |
Tiff | +0.615 |
aspers | +0.613 |
Neg logit contributions | |
Frazier | -0.889 |
�� | -0.840 |
VC | -0.829 |
mt | -0.827 |
han | -0.824 |
Token | OUNT |
Token ID | 28270 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Frazier | +0.719 |
VC | +0.683 |
mt | +0.680 |
han | +0.674 |
�� | +0.671 |
Neg logit contributions | |
ipop | -0.517 |
EQU | -0.506 |
atche | -0.479 |
Tiff | -0.442 |
Expend | -0.437 |
Token | vi |
Token ID | 8903 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
ipop | +2.674 |
EQU | +2.662 |
atche | +2.530 |
aspers | +2.399 |
Tiff | +2.392 |
Neg logit contributions | |
Frazier | -2.047 |
�� | -1.883 |
VC | -1.844 |
mt | -1.842 |
han | -1.828 |
Token | : |
Token ID | 25 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ipop | +0.618 |
EQU | +0.616 |
atche | +0.579 |
Tiff | +0.541 |
aspers | +0.540 |
Neg logit contributions | |
Frazier | -0.720 |
�� | -0.679 |
VC | -0.671 |
mt | -0.668 |
han | -0.665 |
Token | | |
Token ID | 91 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ipop | +2.740 |
EQU | +2.739 |
atche | +2.609 |
Tiff | +2.476 |
aspers | +2.472 |
Neg logit contributions | |
Frazier | -1.873 |
�� | -1.722 |
VC | -1.680 |
mt | -1.677 |
han | -1.667 |
Token | vim |
Token ID | 31124 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ipop | +2.082 |
EQU | +2.074 |
atche | +1.973 |
aspers | +1.872 |
Tiff | +1.867 |
Neg logit contributions | |
Frazier | -1.520 |
�� | -1.398 |
VC | -1.373 |
mt | -1.369 |
han | -1.357 |
Token | : |
Token ID | 25 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ipop | +1.202 |
EQU | +1.194 |
atche | +1.128 |
aspers | +1.055 |
Tiff | +1.055 |
Neg logit contributions | |
Frazier | -1.324 |
VC | -1.240 |
mt | -1.233 |
�� | -1.228 |
han | -1.226 |
Token | | |
Token ID | 91 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
EQU | +2.202 |
ipop | +2.202 |
atche | +2.103 |
Tiff | +1.996 |
aspers | +1.990 |
Neg logit contributions | |
Frazier | -1.478 |
�� | -1.353 |
mt | -1.327 |
VC | -1.325 |
han | -1.312 |
Token | ex |
Token ID | 1069 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ipop | +5.106 |
EQU | +5.104 |
atche | +4.709 |
effective | +4.438 |
aspers | +4.419 |
Neg logit contributions | |
Frazier | -7.789 |
�� | -7.218 |
Hound | -7.089 |
han | -7.034 |
Kh | -7.030 |
Token | : |
Token ID | 25 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ipop | +0.258 |
EQU | +0.257 |
atche | +0.241 |
Tiff | +0.225 |
aspers | +0.225 |
Neg logit contributions | |
Frazier | -0.301 |
�� | -0.283 |
VC | -0.280 |
mt | -0.279 |
han | -0.277 |
Token | } |
Token ID | 92 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Frazier | +1.906 |
�� | +1.800 |
VC | +1.800 |
mt | +1.787 |
han | +1.761 |
Neg logit contributions | |
ipop | -2.257 |
EQU | -2.247 |
atche | -2.140 |
aspers | -2.017 |
Tiff | -2.008 |
Token | [ |
Token ID | 58 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
EQU | +2.156 |
ipop | +2.129 |
atche | +1.995 |
Tiff | +1.861 |
aspers | +1.842 |
Neg logit contributions | |
Frazier | -2.980 |
�� | -2.813 |
VC | -2.759 |
han | -2.756 |
mt | -2.749 |
Token | white |
Token ID | 11186 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Frazier | +4.461 |
�� | +4.282 |
han | +4.268 |
mt | +4.263 |
VC | +4.248 |
Neg logit contributions | |
ipop | -5.641 |
EQU | -5.574 |
atche | -5.306 |
Expend | -5.149 |
Tiff | -5.063 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
EQU | +1.760 |
ipop | +1.760 |
atche | +1.666 |
Tiff | +1.564 |
Expend | +1.539 |
Neg logit contributions | |
Frazier | -1.785 |
�� | -1.697 |
mt | -1.670 |
VC | -1.657 |
bnb | -1.657 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ipop | +0.232 |
EQU | +0.231 |
atche | +0.220 |
aspers | +0.208 |
Tiff | +0.207 |
Neg logit contributions | |
Frazier | -0.193 |
�� | -0.179 |
VC | -0.178 |
mt | -0.177 |
han | -0.175 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Frazier | +0.526 |
VC | +0.482 |
mt | +0.473 |
han | +0.467 |
Kh | +0.465 |
Neg logit contributions | |
ipop | -0.902 |
EQU | -0.881 |
atche | -0.859 |
aspers | -0.819 |
Tiff | -0.801 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
EQU | +1.166 |
ipop | +1.163 |
atche | +1.102 |
Tiff | +1.042 |
aspers | +1.033 |
Neg logit contributions | |
Frazier | -1.038 |
�� | -0.981 |
VC | -0.960 |
mt | -0.956 |
bnb | -0.951 |
Token | of |
Token ID | 286 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
ipop | +1.631 |
EQU | +1.628 |
atche | +1.541 |
Tiff | +1.453 |
aspers | +1.448 |
Neg logit contributions | |
Frazier | -1.494 |
�� | -1.406 |
VC | -1.381 |
mt | -1.376 |
han | -1.366 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
EQU | +4.424 |
ipop | +4.149 |
atche | +3.953 |
Tiff | +3.810 |
Expend | +3.810 |
Neg logit contributions | |
�� | -5.738 |
Frazier | -5.564 |
bnb | -5.233 |
�� | -5.221 |
�� | -5.144 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
EQU | +5.683 |
ipop | +5.295 |
Expend | +5.014 |
atche | +4.984 |
Tiff | +4.967 |
Neg logit contributions | |
�� | -7.641 |
Frazier | -7.029 |
�� | -6.918 |
�� | -6.862 |
�� | -6.838 |
Token | : |
Token ID | 25 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
EQU | +3.943 |
ipop | +3.752 |
atche | +3.506 |
Tiff | +3.409 |
Expend | +3.331 |
Neg logit contributions | |
�� | -6.469 |
Frazier | -6.003 |
�� | -5.804 |
�� | -5.802 |
bnb | -5.782 |
Token | Carly |
Token ID | 35982 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
EQU | +2.668 |
ipop | +2.620 |
atche | +2.441 |
Tiff | +2.352 |
Expend | +2.316 |
Neg logit contributions | |
Frazier | -3.715 |
�� | -3.686 |
bnb | -3.492 |
mt | -3.462 |
han | -3.457 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
ipop | +1.206 |
EQU | +1.201 |
atche | +1.098 |
Tiff | +1.006 |
aspers | +0.997 |
Neg logit contributions | |
Frazier | -2.333 |
�� | -2.247 |
VC | -2.207 |
mt | -2.206 |
bnb | -2.191 |
Token | 's |
Token ID | 338 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Frazier | +0.241 |
VC | +0.225 |
mt | +0.222 |
han | +0.221 |
Kh | +0.218 |
Neg logit contributions | |
ipop | -0.276 |
EQU | -0.274 |
atche | -0.262 |
aspers | -0.246 |
Tiff | -0.245 |
Token | + |
Token ID | 1343 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
EQU | +2.658 |
ipop | +2.638 |
atche | +2.497 |
Tiff | +2.369 |
aspers | +2.348 |
Neg logit contributions | |
Frazier | -2.355 |
�� | -2.246 |
VC | -2.166 |
mt | -2.156 |
bnb | -2.151 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ipop | +0.333 |
EQU | +0.326 |
atche | +0.302 |
Tiff | +0.276 |
Expend | +0.271 |
Neg logit contributions | |
Frazier | -0.632 |
VC | -0.600 |
han | -0.600 |
mt | -0.597 |
Kh | -0.596 |
Token | --+ |
Token ID | 44785 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ipop | +1.935 |
EQU | +1.919 |
atche | +1.747 |
Tiff | +1.578 |
aspers | +1.567 |
Neg logit contributions | |
Frazier | -4.294 |
�� | -4.087 |
VC | -4.077 |
mt | -4.064 |
han | -4.050 |
Token | | |
Token ID | 930 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
EQU | +1.996 |
ipop | +1.995 |
atche | +1.884 |
Tiff | +1.779 |
aspers | +1.772 |
Neg logit contributions | |
Frazier | -1.826 |
�� | -1.716 |
VC | -1.686 |
mt | -1.678 |
han | -1.668 |
Token | ... |
Token ID | 2644 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
EQU | +0.866 |
ipop | +0.866 |
atche | +0.789 |
Tiff | +0.728 |
aspers | +0.718 |
Neg logit contributions | |
Frazier | -1.547 |
�� | -1.470 |
VC | -1.453 |
mt | -1.445 |
bnb | -1.445 |
Token | | |
Token ID | 930 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
EQU | +3.208 |
ipop | +3.168 |
atche | +2.993 |
Tiff | +2.843 |
aspers | +2.823 |
Neg logit contributions | |
Frazier | -2.992 |
�� | -2.886 |
VC | -2.751 |
bnb | -2.745 |
mt | -2.740 |
Token | + |
Token ID | 1343 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
EQU | +6.005 |
ipop | +5.736 |
atche | +5.348 |
Tiff | +5.090 |
Expend | +4.964 |
Neg logit contributions | |
Frazier | -7.028 |
�� | -6.759 |
Kh | -6.451 |
bnb | -6.406 |
iven | -6.406 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
ipop | +0.904 |
EQU | +0.892 |
atche | +0.820 |
Tiff | +0.746 |
Expend | +0.734 |
Neg logit contributions | |
Frazier | -1.808 |
VC | -1.715 |
han | -1.712 |
mt | -1.707 |
�� | -1.701 |
Token | --+ |
Token ID | 44785 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ipop | +2.338 |
EQU | +2.337 |
atche | +2.120 |
aspers | +1.882 |
Tiff | +1.881 |
Neg logit contributions | |
Frazier | -5.638 |
�� | -5.404 |
VC | -5.345 |
mt | -5.333 |
han | -5.293 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
EQU | +1.747 |
ipop | +1.746 |
atche | +1.628 |
Tiff | +1.517 |
aspers | +1.507 |
Neg logit contributions | |
Frazier | -2.171 |
�� | -2.046 |
VC | -2.012 |
bnb | -2.003 |
mt | -2.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ipop | +0.885 |
EQU | +0.880 |
atche | +0.829 |
aspers | +0.774 |
Tiff | +0.774 |
Neg logit contributions | |
Frazier | -1.016 |
VC | -0.951 |
�� | -0.947 |
mt | -0.946 |
han | -0.940 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
EQU | +1.361 |
ipop | +1.360 |
atche | +1.282 |
Tiff | +1.214 |
aspers | +1.204 |
Neg logit contributions | |
Frazier | -1.302 |
�� | -1.237 |
VC | -1.209 |
mt | -1.208 |
bnb | -1.198 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
EQU | +1.708 |
ipop | +1.683 |
atche | +1.591 |
Tiff | +1.539 |
Expend | +1.526 |
Neg logit contributions | |
Frazier | -1.420 |
�� | -1.387 |
bnb | -1.322 |
mt | -1.322 |
VC | -1.309 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Frazier | +0.537 |
VC | +0.491 |
mt | +0.482 |
han | +0.478 |
Kh | +0.475 |
Neg logit contributions | |
ipop | -0.906 |
EQU | -0.889 |
atche | -0.864 |
aspers | -0.824 |
Tiff | -0.808 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
EQU | +3.672 |
ipop | +3.577 |
atche | +3.347 |
Tiff | +3.191 |
Expend | +3.145 |
Neg logit contributions | |
Frazier | -4.305 |
�� | -4.278 |
bnb | -4.039 |
mt | -4.008 |
VC | -3.992 |
Token | of |
Token ID | 286 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
EQU | +1.785 |
ipop | +1.785 |
atche | +1.685 |
Tiff | +1.592 |
aspers | +1.581 |
Neg logit contributions | |
Frazier | -1.682 |
�� | -1.605 |
VC | -1.552 |
mt | -1.549 |
bnb | -1.538 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
EQU | +4.889 |
ipop | +4.492 |
atche | +4.293 |
Expend | +4.210 |
Tiff | +4.178 |
Neg logit contributions | |
�� | -6.600 |
Frazier | -6.357 |
�� | -6.027 |
bnb | -6.006 |
�� | -5.950 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
EQU | +5.679 |
ipop | +5.248 |
Expend | +5.025 |
atche | +4.981 |
Tiff | +4.935 |
Neg logit contributions | |
�� | -7.611 |
Frazier | -7.009 |
�� | -6.894 |
�� | -6.862 |
�� | -6.806 |
Token | : |
Token ID | 25 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
EQU | +4.039 |
ipop | +3.821 |
atche | +3.580 |
Tiff | +3.486 |
Expend | +3.410 |
Neg logit contributions | |
�� | -6.700 |
Frazier | -6.216 |
�� | -6.021 |
�� | -5.994 |
bnb | -5.984 |
Token | Carly |
Token ID | 35982 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
EQU | +3.071 |
ipop | +2.982 |
atche | +2.777 |
Tiff | +2.709 |
Expend | +2.668 |
Neg logit contributions | |
�� | -4.480 |
Frazier | -4.443 |
bnb | -4.208 |
mt | -4.157 |
han | -4.147 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ipop | +1.435 |
EQU | +1.434 |
atche | +1.299 |
Tiff | +1.198 |
Expend | +1.185 |
Neg logit contributions | |
Frazier | -2.855 |
�� | -2.778 |
mt | -2.709 |
VC | -2.703 |
bnb | -2.694 |
Token | 's |
Token ID | 338 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Frazier | +0.101 |
VC | +0.094 |
mt | +0.093 |
han | +0.092 |
�� | +0.091 |
Neg logit contributions | |
ipop | -0.112 |
EQU | -0.111 |
atche | -0.106 |
aspers | -0.099 |
Tiff | -0.099 |
Token | [ |
Token ID | 58 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
EQU | +1.472 |
ipop | +1.452 |
atche | +1.352 |
Tiff | +1.237 |
aspers | +1.232 |
Neg logit contributions | |
Frazier | -2.451 |
�� | -2.397 |
mt | -2.297 |
VC | -2.294 |
bnb | -2.288 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Frazier | +0.583 |
VC | +0.536 |
han | +0.533 |
mt | +0.532 |
Kh | +0.531 |
Neg logit contributions | |
ipop | -0.874 |
EQU | -0.863 |
atche | -0.828 |
Tiff | -0.789 |
aspers | -0.786 |
Token | ]) |
Token ID | 12962 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ipop | +1.039 |
EQU | +1.039 |
atche | +0.963 |
aspers | +0.895 |
Tiff | +0.894 |
Neg logit contributions | |
Frazier | -1.406 |
�� | -1.328 |
VC | -1.317 |
mt | -1.310 |
han | -1.303 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
EQU | +2.338 |
ipop | +2.235 |
atche | +2.054 |
Tiff | +1.955 |
aspers | +1.895 |
Neg logit contributions | |
Frazier | -3.661 |
�� | -3.586 |
han | -3.405 |
bnb | -3.402 |
VC | -3.391 |
Token | $ |
Token ID | 720 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
EQU | +2.779 |
ipop | +2.717 |
atche | +2.538 |
Tiff | +2.460 |
Expend | +2.438 |
Neg logit contributions | |
Frazier | -2.732 |
�� | -2.550 |
han | -2.527 |
Kh | -2.515 |
bnb | -2.509 |
Token | s |
Token ID | 82 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ipop | +2.195 |
EQU | +2.186 |
atche | +2.061 |
aspers | +1.945 |
Tiff | +1.937 |
Neg logit contributions | |
Frazier | -2.545 |
�� | -2.366 |
mt | -2.351 |
VC | -2.348 |
bnb | -2.315 |
Token | z |
Token ID | 89 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ipop | +6.382 |
EQU | +6.036 |
atche | +6.035 |
aspers | +5.639 |
Tiff | +5.513 |
Neg logit contributions | |
Frazier | -6.409 |
�� | -6.208 |
VC | -6.021 |
mt | -5.824 |
lyn | -5.814 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Frazier | +1.022 |
�� | +0.944 |
mt | +0.943 |
VC | +0.937 |
han | +0.935 |
Neg logit contributions | |
EQU | -1.340 |
ipop | -1.338 |
atche | -1.271 |
Tiff | -1.204 |
aspers | -1.196 |
Token | = |
Token ID | 796 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
EQU | +2.030 |
ipop | +2.024 |
atche | +1.879 |
Tiff | +1.739 |
aspers | +1.731 |
Neg logit contributions | |
Frazier | -3.176 |
�� | -3.054 |
VC | -2.980 |
mt | -2.971 |
bnb | -2.950 |
Token | [ |
Token ID | 685 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
EQU | +1.931 |
ipop | +1.886 |
atche | +1.732 |
Expend | +1.660 |
Tiff | +1.638 |
Neg logit contributions | |
Frazier | -2.922 |
bnb | -2.758 |
�� | -2.752 |
han | -2.738 |
Kh | -2.721 |
Token | system |
Token ID | 10057 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Frazier | +0.443 |
VC | +0.421 |
han | +0.419 |
mt | +0.417 |
Kh | +0.415 |
Neg logit contributions | |
EQU | -0.356 |
ipop | -0.355 |
atche | -0.334 |
Tiff | -0.313 |
Expend | -0.310 |
Token | again |
Token ID | 757 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Frazier | +3.016 |
VC | +2.840 |
mt | +2.818 |
han | +2.804 |
bnb | +2.766 |
Neg logit contributions | |
ipop | -3.616 |
EQU | -3.585 |
atche | -3.443 |
aspers | -3.269 |
Tiff | -3.247 |
Token | that |
Token ID | 326 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
Frazier | +2.293 |
VC | +2.159 |
mt | +2.144 |
han | +2.132 |
bnb | +2.076 |
Neg logit contributions | |
ipop | -2.819 |
EQU | -2.810 |
atche | -2.676 |
aspers | -2.562 |
Tiff | -2.516 |
Token | the |
Token ID | 262 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
ipop | +0.198 |
EQU | +0.197 |
atche | +0.188 |
aspers | +0.177 |
Tiff | +0.175 |
Neg logit contributions | |
Frazier | -0.180 |
VC | -0.169 |
mt | -0.168 |
han | -0.166 |
bnb | -0.165 |
Token | old |
Token ID | 1468 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ipop | +0.444 |
EQU | +0.443 |
atche | +0.420 |
aspers | +0.396 |
Tiff | +0.396 |
Neg logit contributions | |
Frazier | -0.389 |
�� | -0.361 |
VC | -0.361 |
mt | -0.360 |
han | -0.355 |
Token | address |
Token ID | 2209 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ipop | +2.392 |
EQU | +2.385 |
atche | +2.231 |
Tiff | +2.049 |
Expend | +2.030 |
Neg logit contributions | |
Frazier | -3.399 |
�� | -3.279 |
han | -3.144 |
Kh | -3.139 |
VC | -3.136 |
Token | https |
Token ID | 3740 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Frazier | +5.134 |
mt | +4.901 |
VC | +4.847 |
han | +4.737 |
bnb | +4.670 |
Neg logit contributions | |
EQU | -5.271 |
ipop | -5.248 |
atche | -5.080 |
aspers | -4.876 |
Tiff | -4.698 |
Token | :// |
Token ID | 1378 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Frazier | +4.547 |
VC | +4.287 |
han | +4.229 |
mt | +4.227 |
Kh | +4.171 |
Neg logit contributions | |
ipop | -9.552 |
EQU | -9.403 |
atche | -9.131 |
aspers | -8.946 |
therap | -8.811 |
Token | . |
Token ID | 764 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Frazier | +4.959 |
mt | +4.796 |
VC | +4.771 |
bnb | +4.672 |
han | +4.622 |
Neg logit contributions | |
EQU | -6.050 |
ipop | -6.009 |
atche | -5.789 |
aspers | -5.574 |
Tiff | -5.446 |
Token | nice |
Token ID | 44460 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ipop | +1.825 |
EQU | +1.795 |
atche | +1.680 |
Tiff | +1.531 |
aspers | +1.528 |
Neg logit contributions | |
Frazier | -2.838 |
�� | -2.709 |
VC | -2.672 |
mt | -2.646 |
Kh | -2.644 |
Token | hash |
Token ID | 17831 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
EQU | +0.806 |
ipop | +0.800 |
atche | +0.749 |
Tiff | +0.709 |
Expend | +0.707 |
Neg logit contributions | |
Frazier | -0.884 |
han | -0.836 |
mt | -0.832 |
VC | -0.827 |
bnb | -0.825 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ipop | +0.440 |
EQU | +0.438 |
atche | +0.417 |
aspers | +0.394 |
Tiff | +0.393 |
Neg logit contributions | |
Frazier | -0.368 |
VC | -0.341 |
mt | -0.340 |
han | -0.336 |
Kh | -0.333 |
Token | for |
Token ID | 329 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
ipop | +0.496 |
EQU | +0.494 |
atche | +0.467 |
Tiff | +0.438 |
aspers | +0.438 |
Neg logit contributions | |
Frazier | -0.499 |
�� | -0.467 |
VC | -0.463 |
mt | -0.461 |
han | -0.458 |
Token | virtual |
Token ID | 7166 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ipop | +0.586 |
EQU | +0.585 |
atche | +0.550 |
Tiff | +0.519 |
aspers | +0.516 |
Neg logit contributions | |
Frazier | -0.601 |
�� | -0.568 |
VC | -0.559 |
mt | -0.556 |
han | -0.553 |
Token | creatures |
Token ID | 8109 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Frazier | +0.873 |
VC | +0.816 |
mt | +0.812 |
�� | +0.812 |
han | +0.804 |
Neg logit contributions | |
ipop | -0.773 |
EQU | -0.767 |
atche | -0.726 |
aspers | -0.675 |
Tiff | -0.675 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ipop | +0.953 |
EQU | +0.949 |
atche | +0.899 |
Tiff | +0.846 |
aspers | +0.845 |
Neg logit contributions | |
Frazier | -0.894 |
�� | -0.834 |
VC | -0.828 |
mt | -0.824 |
han | -0.819 |
Token | ( |
Token ID | 357 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Frazier | +0.831 |
VC | +0.773 |
mt | +0.765 |
�� | +0.758 |
han | +0.756 |
Neg logit contributions | |
ipop | -0.843 |
EQU | -0.832 |
atche | -0.793 |
aspers | -0.743 |
Tiff | -0.739 |
Token | Photo |
Token ID | 6191 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Frazier | +2.875 |
Kh | +2.798 |
VC | +2.747 |
han | +2.668 |
mt | +2.645 |
Neg logit contributions | |
ipop | -4.694 |
atche | -4.480 |
EQU | -4.339 |
aspers | -4.110 |
Tiff | -4.025 |
Token | : |
Token ID | 25 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Frazier | +5.643 |
VC | +5.404 |
mt | +5.195 |
han | +4.993 |
Kh | +4.888 |
Neg logit contributions | |
ipop | -9.180 |
atche | -8.873 |
therap | -8.358 |
aspers | -8.310 |
EQU | -8.296 |
Token | KY |
Token ID | 33668 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Frazier | +4.194 |
VC | +3.957 |
mt | +3.869 |
Kh | +3.767 |
han | +3.747 |
Neg logit contributions | |
ipop | -3.969 |
atche | -3.763 |
EQU | -3.706 |
aspers | -3.473 |
effective | -3.353 |
Token | LE |
Token ID | 2538 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Frazier | +2.414 |
VC | +2.255 |
mt | +2.223 |
Kh | +2.212 |
�� | +2.207 |
Neg logit contributions | |
ipop | -2.337 |
EQU | -2.237 |
atche | -2.155 |
Tiff | -2.031 |
Expend | -2.015 |
Token | GR |
Token ID | 10863 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
EQU | +1.118 |
ipop | +1.088 |
atche | +1.029 |
Tiff | +0.975 |
aspers | +0.959 |
Neg logit contributions | |
Frazier | -1.205 |
�� | -1.164 |
bnb | -1.126 |
mt | -1.122 |
han | -1.121 |
Token | AN |
Token ID | 1565 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Frazier | +0.355 |
VC | +0.330 |
�� | +0.329 |
mt | +0.327 |
han | +0.326 |
Neg logit contributions | |
ipop | -0.361 |
EQU | -0.355 |
atche | -0.336 |
Tiff | -0.317 |
aspers | -0.316 |
Token | failed |
Token ID | 4054 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ipop | +0.206 |
EQU | +0.206 |
atche | +0.195 |
Tiff | +0.184 |
aspers | +0.184 |
Neg logit contributions | |
Frazier | -0.169 |
�� | -0.156 |
VC | -0.156 |
mt | -0.156 |
han | -0.154 |
Token | will |
Token ID | 481 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Frazier | +0.777 |
VC | +0.730 |
mt | +0.727 |
han | +0.714 |
Kh | +0.713 |
Neg logit contributions | |
ipop | -0.771 |
EQU | -0.770 |
atche | -0.729 |
aspers | -0.691 |
Tiff | -0.686 |
Token | save |
Token ID | 3613 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Frazier | +3.744 |
VC | +3.734 |
mt | +3.613 |
lyn | +3.575 |
mono | +3.460 |
Neg logit contributions | |
ipop | -4.495 |
EQU | -4.439 |
aspers | -4.064 |
Tiff | -4.027 |
atche | -4.019 |
Token | , |
Token ID | 11 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Frazier | +3.188 |
VC | +2.999 |
han | +2.951 |
mt | +2.935 |
Kh | +2.911 |
Neg logit contributions | |
ipop | -4.926 |
EQU | -4.810 |
atche | -4.645 |
aspers | -4.516 |
therap | -4.485 |
Token | your |
Token ID | 534 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Frazier | +2.540 |
VC | +2.368 |
mt | +2.331 |
han | +2.253 |
Kh | +2.221 |
Neg logit contributions | |
ipop | -5.644 |
EQU | -5.605 |
atche | -5.419 |
aspers | -5.268 |
Tiff | -5.107 |
Token | character |
Token ID | 2095 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Frazier | +2.852 |
VC | +2.764 |
mt | +2.731 |
han | +2.666 |
lyn | +2.625 |
Neg logit contributions | |
EQU | -4.013 |
ipop | -4.002 |
atche | -3.770 |
aspers | -3.708 |
Tiff | -3.602 |
Token | now |
Token ID | 783 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
VC | +3.334 |
mt | +3.262 |
Frazier | +3.259 |
han | +3.215 |
lyn | +2.944 |
Neg logit contributions | |
EQU | -10.655 |
ipop | -10.609 |
atche | -10.450 |
ECA | -10.103 |
Tiff | -10.005 |
Token | receives |
Token ID | 11583 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
Frazier | +3.189 |
mt | +3.067 |
VC | +3.020 |
lyn | +2.942 |
Kh | +2.881 |
Neg logit contributions | |
ipop | -3.159 |
EQU | -3.094 |
atche | -2.954 |
aspers | -2.892 |
Tiff | -2.763 |
Token | secret |
Token ID | 3200 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ipop | +0.568 |
EQU | +0.565 |
atche | +0.536 |
aspers | +0.507 |
Tiff | +0.507 |
Neg logit contributions | |
Frazier | -0.494 |
VC | -0.460 |
�� | -0.458 |
mt | -0.457 |
han | -0.453 |
Token | voices |
Token ID | 10839 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Frazier | +2.775 |
VC | +2.711 |
mt | +2.655 |
han | +2.621 |
Kh | +2.596 |
Neg logit contributions | |
ipop | -2.323 |
EQU | -2.270 |
atche | -2.184 |
Tiff | -2.039 |
aspers | -2.001 |
Token | in |
Token ID | 287 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Frazier | +1.185 |
VC | +1.103 |
mt | +1.096 |
han | +1.089 |
Kh | +1.068 |
Neg logit contributions | |
ipop | -1.654 |
EQU | -1.635 |
atche | -1.566 |
aspers | -1.498 |
Tiff | -1.483 |
Token | ent |
Token ID | 298 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Frazier | +0.459 |
han | +0.436 |
VC | +0.433 |
mt | +0.430 |
Kh | +0.427 |
Neg logit contributions | |
EQU | -0.376 |
ipop | -0.374 |
atche | -0.348 |
Tiff | -0.329 |
aspers | -0.328 |
Token | Sh |
Token ID | 911 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Frazier | +1.340 |
�� | +1.253 |
VC | +1.248 |
mt | +1.240 |
han | +1.234 |
Neg logit contributions | |
ipop | -1.265 |
EQU | -1.264 |
atche | -1.187 |
aspers | -1.117 |
Tiff | -1.106 |
Token | river |
Token ID | 38291 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Frazier | +0.366 |
VC | +0.326 |
�� | +0.325 |
han | +0.324 |
mt | +0.324 |
Neg logit contributions | |
EQU | -0.800 |
ipop | -0.797 |
atche | -0.762 |
Tiff | -0.733 |
Expend | -0.731 |
Token | Award |
Token ID | 11289 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
EQU | +0.734 |
ipop | +0.734 |
atche | +0.671 |
Tiff | +0.614 |
Expend | +0.610 |
Neg logit contributions | |
Frazier | -1.426 |
�� | -1.367 |
mt | -1.352 |
bnb | -1.352 |
VC | -1.349 |
Token | for |
Token ID | 329 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Frazier | +3.670 |
VC | +3.402 |
�� | +3.363 |
mt | +3.348 |
han | +3.334 |
Neg logit contributions | |
ipop | -4.101 |
EQU | -4.094 |
atche | -3.851 |
aspers | -3.699 |
Tiff | -3.631 |
Token | Dist |
Token ID | 4307 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Frazier | +2.519 |
VC | +2.289 |
�� | +2.269 |
mt | +2.252 |
han | +2.214 |
Neg logit contributions | |
ipop | -4.323 |
EQU | -4.232 |
atche | -4.104 |
aspers | -3.950 |
Tiff | -3.849 |
Token | inguished |
Token ID | 46709 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
iven | +3.166 |
VC | +3.103 |
Frazier | +3.089 |
arter | +2.973 |
han | +2.906 |
Neg logit contributions | |
EQU | -10.525 |
ipop | -10.326 |
therap | -10.029 |
Expend | -9.781 |
atche | -9.700 |
Token | Human |
Token ID | 5524 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Frazier | +1.603 |
VC | +1.442 |
mt | +1.396 |
han | +1.382 |
Kh | +1.351 |
Neg logit contributions | |
ipop | -3.620 |
EQU | -3.521 |
atche | -3.463 |
aspers | -3.351 |
Tiff | -3.250 |
Token | itarian |
Token ID | 8353 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Frazier | +0.671 |
VC | +0.620 |
han | +0.614 |
mt | +0.609 |
Kh | +0.606 |
Neg logit contributions | |
EQU | -0.867 |
ipop | -0.864 |
atche | -0.820 |
aspers | -0.783 |
Tiff | -0.778 |
Token | Service |
Token ID | 4809 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
Frazier | +0.425 |
VC | +0.394 |
mt | +0.385 |
han | +0.381 |
Kh | +0.376 |
Neg logit contributions | |
ipop | -0.569 |
EQU | -0.558 |
atche | -0.541 |
aspers | -0.515 |
Tiff | -0.504 |
Token | winner |
Token ID | 8464 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Frazier | +0.210 |
�� | +0.199 |
VC | +0.197 |
mt | +0.196 |
bnb | +0.196 |
Neg logit contributions | |
ipop | -0.176 |
EQU | -0.175 |
atche | -0.165 |
Tiff | -0.154 |
aspers | -0.152 |
Token | Clemson |
Token ID | 27801 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Frazier | +0.042 |
VC | +0.039 |
�� | +0.039 |
mt | +0.039 |
han | +0.039 |
Neg logit contributions | |
ipop | -0.048 |
EQU | -0.047 |
atche | -0.045 |
aspers | -0.042 |
Tiff | -0.042 |
Token | Game |
Token ID | 3776 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Frazier | +1.623 |
VC | +1.500 |
mt | +1.463 |
han | +1.456 |
lyn | +1.447 |
Neg logit contributions | |
ipop | -2.063 |
EQU | -2.042 |
atche | -1.970 |
aspers | -1.847 |
Tiff | -1.815 |
Token | in |
Token ID | 287 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
Frazier | +1.685 |
VC | +1.568 |
�� | +1.544 |
mt | +1.543 |
han | +1.541 |
Neg logit contributions | |
ipop | -1.807 |
EQU | -1.789 |
atche | -1.709 |
aspers | -1.604 |
Tiff | -1.595 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
Frazier | +0.013 |
�� | +0.012 |
VC | +0.012 |
mt | +0.012 |
han | +0.012 |
Neg logit contributions | |
ipop | -0.015 |
EQU | -0.015 |
atche | -0.014 |
aspers | -0.014 |
Tiff | -0.014 |
Token | ( |
Token ID | 357 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ipop | +0.422 |
EQU | +0.421 |
atche | +0.398 |
Tiff | +0.376 |
aspers | +0.374 |
Neg logit contributions | |
Frazier | -0.392 |
�� | -0.367 |
VC | -0.363 |
mt | -0.362 |
han | -0.359 |
Token | Photo |
Token ID | 6191 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Frazier | +1.625 |
VC | +1.508 |
han | +1.501 |
Kh | +1.497 |
mt | +1.494 |
Neg logit contributions | |
ipop | -1.907 |
EQU | -1.887 |
atche | -1.799 |
Tiff | -1.696 |
aspers | -1.685 |
Token | : |
Token ID | 25 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
Frazier | +5.545 |
VC | +5.276 |
mt | +5.063 |
han | +4.955 |
Kh | +4.813 |
Neg logit contributions | |
ipop | -8.504 |
atche | -8.180 |
EQU | -7.916 |
therap | -7.828 |
aspers | -7.710 |
Token | Wayne |
Token ID | 13329 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Frazier | +4.556 |
VC | +4.303 |
mt | +4.201 |
Kh | +4.074 |
han | +4.050 |
Neg logit contributions | |
ipop | -4.287 |
atche | -4.057 |
EQU | -3.972 |
aspers | -3.737 |
effective | -3.611 |
Token | McG |
Token ID | 11130 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Frazier | +1.749 |
VC | +1.607 |
han | +1.583 |
mt | +1.575 |
Kh | +1.569 |
Neg logit contributions | |
ipop | -1.728 |
EQU | -1.691 |
atche | -1.608 |
aspers | -1.520 |
Tiff | -1.489 |
Token | a |
Token ID | 64 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Frazier | +2.127 |
han | +2.023 |
iven | +1.974 |
bnb | +1.934 |
mt | +1.904 |
Neg logit contributions | |
ipop | -2.750 |
EQU | -2.739 |
atche | -2.550 |
Tiff | -2.500 |
Expend | -2.459 |
Token | hee |
Token ID | 21067 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Frazier | +1.696 |
han | +1.586 |
VC | +1.576 |
mt | +1.570 |
iven | +1.565 |
Neg logit contributions | |
EQU | -1.527 |
ipop | -1.497 |
atche | -1.407 |
Tiff | -1.333 |
Expend | -1.328 |
Token | | |
Token ID | 930 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Frazier | +2.520 |
VC | +2.381 |
mt | +2.367 |
han | +2.364 |
Kh | +2.363 |
Neg logit contributions | |
ipop | -4.084 |
EQU | -3.919 |
atche | -3.876 |
aspers | -3.650 |
therap | -3.642 |
Token | org |
Token ID | 8745 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ipop | +0.256 |
EQU | +0.255 |
atche | +0.239 |
Tiff | +0.226 |
aspers | +0.225 |
Neg logit contributions | |
Frazier | -0.271 |
�� | -0.254 |
VC | -0.250 |
han | -0.249 |
mt | -0.249 |
Token | . |
Token ID | 764 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Frazier | +2.872 |
VC | +2.720 |
mt | +2.703 |
han | +2.686 |
Kh | +2.599 |
Neg logit contributions | |
ipop | -3.972 |
EQU | -3.899 |
atche | -3.765 |
aspers | -3.578 |
Expend | -3.533 |
Token | cl |
Token ID | 537 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
Frazier | +2.000 |
mt | +1.910 |
lyn | +1.886 |
VC | +1.883 |
mono | +1.822 |
Neg logit contributions | |
ipop | -4.039 |
EQU | -4.010 |
atche | -3.888 |
aspers | -3.753 |
Tiff | -3.680 |
Token | ojure |
Token ID | 32511 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Frazier | +0.171 |
han | +0.162 |
bnb | +0.160 |
VC | +0.160 |
mt | +0.160 |
Neg logit contributions | |
EQU | -0.137 |
ipop | -0.135 |
atche | -0.127 |
Expend | -0.119 |
Tiff | -0.119 |
Token | / |
Token ID | 1220 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Frazier | +3.437 |
mt | +3.298 |
VC | +3.296 |
han | +3.234 |
Kh | +3.156 |
Neg logit contributions | |
ipop | -3.359 |
EQU | -3.268 |
atche | -3.229 |
aspers | -3.014 |
Tiff | -2.935 |
Token | tools |
Token ID | 4899 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Frazier | +5.715 |
mt | +5.662 |
lyn | +5.612 |
VC | +5.585 |
mono | +5.496 |
Neg logit contributions | |
ipop | -7.654 |
EQU | -7.531 |
atche | -7.435 |
aspers | -7.039 |
effective | -6.867 |
Token | . |
Token ID | 764 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Frazier | +3.205 |
VC | +3.041 |
mt | +3.010 |
han | +3.002 |
lyn | +2.946 |
Neg logit contributions | |
ipop | -3.740 |
EQU | -3.669 |
atche | -3.520 |
Expend | -3.372 |
aspers | -3.315 |
Token | logging |
Token ID | 18931 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Frazier | +2.293 |
mt | +2.160 |
VC | +2.154 |
lyn | +2.106 |
han | +2.102 |
Neg logit contributions | |
ipop | -3.064 |
EQU | -3.011 |
atche | -2.916 |
aspers | -2.760 |
Tiff | -2.729 |
Token | | |
Token ID | 930 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Frazier | +4.313 |
mt | +4.085 |
VC | +4.077 |
lyn | +4.015 |
han | +3.991 |
Neg logit contributions | |
ipop | -6.406 |
EQU | -6.354 |
atche | -6.146 |
Expend | -5.965 |
aspers | -5.867 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Frazier | +2.259 |
VC | +2.116 |
mt | +2.078 |
han | +2.022 |
Kh | +2.015 |
Neg logit contributions | |
ipop | -2.927 |
EQU | -2.818 |
atche | -2.758 |
aspers | -2.623 |
Tiff | -2.548 |
Token | org |
Token ID | 8745 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
EQU | +0.389 |
ipop | +0.388 |
atche | +0.363 |
Tiff | +0.343 |
aspers | +0.340 |
Neg logit contributions | |
Frazier | -0.414 |
�� | -0.388 |
VC | -0.382 |
han | -0.381 |
mt | -0.381 |
Token | . |
Token ID | 764 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Frazier | +2.943 |
VC | +2.790 |
han | +2.777 |
mt | +2.774 |
Kh | +2.679 |
Neg logit contributions | |
ipop | -4.189 |
EQU | -4.086 |
atche | -3.959 |
aspers | -3.764 |
therap | -3.740 |
Token | cl |
Token ID | 537 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Frazier | +1.867 |
mt | +1.783 |
VC | +1.769 |
lyn | +1.765 |
mono | +1.699 |
Neg logit contributions | |
ipop | -3.848 |
EQU | -3.799 |
atche | -3.698 |
aspers | -3.581 |
Expend | -3.496 |
Token | ojure |
Token ID | 32511 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Frazier | +1.213 |
han | +1.159 |
bnb | +1.147 |
iven | +1.134 |
VC | +1.129 |
Neg logit contributions | |
EQU | -1.049 |
ipop | -1.018 |
atche | -0.955 |
Expend | -0.922 |
Tiff | -0.909 |
Token | / |
Token ID | 1220 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Frazier | +3.335 |
mt | +3.194 |
VC | +3.192 |
han | +3.137 |
Kh | +3.058 |
Neg logit contributions | |
ipop | -3.271 |
EQU | -3.171 |
atche | -3.129 |
aspers | -2.934 |
Tiff | -2.852 |
Token | core |
Token ID | 4755 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Frazier | +3.059 |
mt | +2.908 |
VC | +2.898 |
lyn | +2.845 |
�� | +2.844 |
Neg logit contributions | |
ipop | -3.616 |
EQU | -3.546 |
atche | -3.444 |
aspers | -3.232 |
Expend | -3.203 |
Token | . |
Token ID | 764 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Frazier | +5.583 |
VC | +5.350 |
mt | +5.299 |
�� | +5.292 |
han | +5.176 |
Neg logit contributions | |
ipop | -7.505 |
EQU | -7.430 |
atche | -7.198 |
Expend | -6.896 |
aspers | -6.765 |
Token | match |
Token ID | 2872 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Frazier | +3.643 |
mt | +3.483 |
VC | +3.475 |
lyn | +3.425 |
�� | +3.371 |
Neg logit contributions | |
ipop | -4.996 |
EQU | -4.900 |
atche | -4.752 |
aspers | -4.526 |
Tiff | -4.464 |
Token | | |
Token ID | 930 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
Frazier | +4.265 |
mt | +4.136 |
han | +4.101 |
VC | +4.093 |
�� | +4.062 |
Neg logit contributions | |
ipop | -5.058 |
EQU | -5.029 |
atche | -4.760 |
Expend | -4.634 |
aspers | -4.538 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ipop | +0.340 |
EQU | +0.340 |
atche | +0.323 |
Tiff | +0.306 |
aspers | +0.305 |
Neg logit contributions | |
Frazier | -0.259 |
�� | -0.242 |
VC | -0.237 |
mt | -0.237 |
han | -0.235 |
Token | 78 |
Token ID | 3695 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
Frazier | +1.722 |
VC | +1.593 |
mt | +1.592 |
han | +1.567 |
Kh | +1.564 |
Neg logit contributions | |
ipop | -2.287 |
EQU | -2.231 |
atche | -2.153 |
aspers | -2.039 |
Tiff | -2.030 |
Token | Paul |
Token ID | 3362 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Frazier | +1.715 |
VC | +1.580 |
mt | +1.569 |
�� | +1.545 |
han | +1.542 |
Neg logit contributions | |
ipop | -2.138 |
EQU | -2.128 |
atche | -2.030 |
aspers | -1.922 |
Tiff | -1.897 |
Token | Newman |
Token ID | 27698 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Frazier | +1.093 |
VC | +1.013 |
han | +1.000 |
�� | +0.992 |
mt | +0.988 |
Neg logit contributions | |
ipop | -1.131 |
EQU | -1.126 |
atche | -1.047 |
aspers | -0.987 |
Tiff | -0.976 |
Token | about |
Token ID | 546 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Frazier | +2.316 |
VC | +2.124 |
mt | +2.115 |
han | +2.109 |
�� | +2.096 |
Neg logit contributions | |
EQU | -2.760 |
ipop | -2.750 |
atche | -2.598 |
aspers | -2.489 |
Tiff | -2.479 |
Token | him |
Token ID | 683 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Frazier | +1.509 |
VC | +1.379 |
mt | +1.373 |
�� | +1.370 |
han | +1.364 |
Neg logit contributions | |
ipop | -2.065 |
EQU | -2.063 |
atche | -1.959 |
aspers | -1.863 |
Tiff | -1.859 |
Token | '. |
Token ID | 4458 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
Frazier | +0.555 |
�� | +0.504 |
VC | +0.504 |
mt | +0.500 |
han | +0.499 |
Neg logit contributions | |
ipop | -0.905 |
EQU | -0.903 |
atche | -0.861 |
aspers | -0.821 |
Tiff | -0.821 |
Token | Photograph |
Token ID | 18903 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ipop | +0.399 |
EQU | +0.396 |
atche | +0.378 |
aspers | +0.358 |
Tiff | +0.357 |
Neg logit contributions | |
Frazier | -0.306 |
�� | -0.281 |
VC | -0.281 |
mt | -0.279 |
han | -0.277 |
Token | : |
Token ID | 25 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
Frazier | +5.563 |
VC | +5.186 |
han | +5.031 |
Kh | +4.931 |
mt | +4.800 |
Neg logit contributions | |
ipop | -7.930 |
EQU | -7.751 |
atche | -7.648 |
therap | -7.607 |
contrace | -7.453 |
Token | Joe |
Token ID | 5689 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Frazier | +0.008 |
�� | +0.007 |
VC | +0.007 |
mt | +0.007 |
han | +0.007 |
Neg logit contributions | |
ipop | -0.008 |
EQU | -0.008 |
atche | -0.007 |
Tiff | -0.007 |
aspers | -0.007 |
Token | Castro |
Token ID | 21193 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ipop | +1.176 |
EQU | +1.175 |
atche | +1.111 |
Tiff | +1.050 |
aspers | +1.041 |
Neg logit contributions | |
Frazier | -1.136 |
�� | -1.078 |
VC | -1.058 |
mt | -1.058 |
bnb | -1.052 |
Token |
|
Token ID | 198 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
ipop | +0.183 |
EQU | +0.182 |
atche | +0.170 |
aspers | +0.157 |
Tiff | +0.157 |
Neg logit contributions | |
Frazier | -0.262 |
�� | -0.247 |
VC | -0.246 |
mt | -0.245 |
han | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
Frazier | +0.606 |
VC | +0.570 |
mt | +0.564 |
han | +0.562 |
Kh | +0.560 |
Neg logit contributions | |
ipop | -0.593 |
EQU | -0.580 |
atche | -0.557 |
aspers | -0.522 |
Tiff | -0.517 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Frazier | +0.747 |
VC | +0.687 |
�� | +0.683 |
mt | +0.678 |
han | +0.672 |
Neg logit contributions | |
ipop | -1.143 |
EQU | -1.138 |
atche | -1.094 |
aspers | -1.035 |
Tiff | -1.032 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
ipop | +0.763 |
EQU | +0.761 |
atche | +0.718 |
Tiff | +0.678 |
aspers | +0.674 |
Neg logit contributions | |
Frazier | -0.747 |
�� | -0.702 |
VC | -0.692 |
mt | -0.690 |
han | -0.686 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ipop | +0.396 |
EQU | +0.395 |
atche | +0.372 |
Tiff | +0.351 |
aspers | +0.350 |
Neg logit contributions | |
Frazier | -0.398 |
�� | -0.374 |
VC | -0.368 |
mt | -0.367 |
bnb | -0.365 |
Token | 35 |
Token ID | 2327 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
Frazier | +0.810 |
VC | +0.743 |
�� | +0.739 |
mt | +0.733 |
han | +0.733 |
Neg logit contributions | |
ipop | -1.247 |
EQU | -1.243 |
atche | -1.189 |
aspers | -1.129 |
Tiff | -1.125 |
Token | f |
Token ID | 277 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ipop | +0.315 |
EQU | +0.315 |
atche | +0.299 |
Tiff | +0.285 |
aspers | +0.284 |
Neg logit contributions | |
Frazier | -0.216 |
�� | -0.201 |
mt | -0.196 |
VC | -0.196 |
bnb | -0.194 |
Token | / |
Token ID | 14 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Frazier | +2.611 |
VC | +2.524 |
han | +2.485 |
mt | +2.462 |
Kh | +2.438 |
Neg logit contributions | |
ipop | -1.966 |
EQU | -1.936 |
atche | -1.829 |
aspers | -1.694 |
Tiff | -1.688 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
Frazier | +4.440 |
VC | +4.297 |
han | +4.253 |
mt | +4.006 |
iven | +3.989 |
Neg logit contributions | |
EQU | -8.632 |
ipop | -8.593 |
atche | -8.281 |
aspers | -7.985 |
Expend | -7.927 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Frazier | +0.170 |
�� | +0.159 |
VC | +0.157 |
mt | +0.156 |
han | +0.155 |
Neg logit contributions | |
ipop | -0.185 |
EQU | -0.184 |
atche | -0.174 |
Tiff | -0.164 |
aspers | -0.164 |
Token | 8 |
Token ID | 23 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Frazier | +1.686 |
�� | +1.570 |
VC | +1.569 |
mt | +1.553 |
han | +1.539 |
Neg logit contributions | |
ipop | -2.116 |
EQU | -2.108 |
atche | -2.014 |
aspers | -1.905 |
Tiff | -1.893 |
Token | II |
Token ID | 2873 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
Frazier | +1.230 |
VC | +1.169 |
mt | +1.144 |
�� | +1.127 |
han | +1.124 |
Neg logit contributions | |
ipop | -1.469 |
EQU | -1.449 |
atche | -1.413 |
aspers | -1.323 |
Tiff | -1.306 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ipop | +0.443 |
EQU | +0.441 |
atche | +0.420 |
aspers | +0.396 |
Tiff | +0.396 |
Neg logit contributions | |
Frazier | -0.362 |
�� | -0.336 |
VC | -0.334 |
mt | -0.332 |
han | -0.329 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Frazier | +0.838 |
VC | +0.780 |
mt | +0.770 |
�� | +0.769 |
han | +0.761 |
Neg logit contributions | |
ipop | -1.130 |
EQU | -1.123 |
atche | -1.079 |
aspers | -1.018 |
Tiff | -1.013 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
ipop | +0.912 |
EQU | +0.911 |
atche | +0.860 |
Tiff | +0.813 |
aspers | +0.809 |
Neg logit contributions | |
Frazier | -0.848 |
�� | -0.794 |
VC | -0.781 |
mt | -0.780 |
han | -0.775 |
Token | - |
Token ID | 12 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ipop | +0.391 |
EQU | +0.388 |
atche | +0.370 |
aspers | +0.348 |
Tiff | +0.346 |
Neg logit contributions | |
Frazier | -0.362 |
VC | -0.339 |
mt | -0.335 |
han | -0.334 |
Kh | -0.330 |
Token | 35 |
Token ID | 2327 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Frazier | +0.097 |
han | +0.089 |
VC | +0.089 |
Kh | +0.087 |
mt | +0.087 |
Neg logit contributions | |
ipop | -0.164 |
EQU | -0.163 |
atche | -0.157 |
aspers | -0.149 |
Tiff | -0.149 |
Token | f |
Token ID | 277 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
EQU | +1.446 |
ipop | +1.445 |
atche | +1.362 |
Tiff | +1.303 |
aspers | +1.291 |
Neg logit contributions | |
Frazier | -1.143 |
�� | -1.074 |
bnb | -1.044 |
mt | -1.043 |
VC | -1.038 |
Token | / |
Token ID | 14 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Frazier | +2.806 |
VC | +2.718 |
han | +2.681 |
mt | +2.648 |
Kh | +2.618 |
Neg logit contributions | |
ipop | -2.148 |
EQU | -2.122 |
atche | -2.004 |
Tiff | -1.860 |
aspers | -1.822 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Frazier | +4.420 |
VC | +4.282 |
han | +4.164 |
mt | +4.062 |
Kh | +3.966 |
Neg logit contributions | |
ipop | -8.567 |
EQU | -8.564 |
atche | -8.247 |
aspers | -7.858 |
Expend | -7.821 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Frazier | +0.345 |
�� | +0.322 |
VC | +0.319 |
mt | +0.318 |
han | +0.315 |
Neg logit contributions | |
ipop | -0.388 |
EQU | -0.387 |
atche | -0.367 |
Tiff | -0.346 |
aspers | -0.346 |
Token | 8 |
Token ID | 23 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
Frazier | +0.847 |
VC | +0.807 |
mt | +0.793 |
han | +0.781 |
Kh | +0.778 |
Neg logit contributions | |
ipop | -1.192 |
EQU | -1.172 |
atche | -1.134 |
aspers | -1.079 |
Tiff | -1.061 |
Token | II |
Token ID | 2873 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Frazier | +0.657 |
VC | +0.619 |
�� | +0.613 |
mt | +0.612 |
han | +0.604 |
Neg logit contributions | |
ipop | -0.670 |
EQU | -0.664 |
atche | -0.637 |
aspers | -0.596 |
Tiff | -0.591 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
EQU | +1.772 |
ipop | +1.769 |
atche | +1.665 |
Tiff | +1.585 |
aspers | +1.572 |
Neg logit contributions | |
Frazier | -1.570 |
�� | -1.483 |
mt | -1.438 |
VC | -1.438 |
bnb | -1.438 |
Token | org |
Token ID | 8745 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
EQU | +0.834 |
ipop | +0.831 |
atche | +0.777 |
Tiff | +0.735 |
aspers | +0.727 |
Neg logit contributions | |
Frazier | -0.919 |
�� | -0.862 |
han | -0.847 |
VC | -0.845 |
Kh | -0.842 |
Token | . |
Token ID | 764 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Frazier | +3.334 |
VC | +3.177 |
mt | +3.161 |
han | +3.149 |
Kh | +3.038 |
Neg logit contributions | |
ipop | -4.995 |
EQU | -4.860 |
atche | -4.704 |
therap | -4.548 |
aspers | -4.498 |
Token | cl |
Token ID | 537 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Frazier | +1.607 |
mt | +1.527 |
VC | +1.517 |
lyn | +1.500 |
mono | +1.451 |
Neg logit contributions | |
ipop | -3.228 |
EQU | -3.190 |
atche | -3.096 |
aspers | -2.997 |
Expend | -2.931 |
Token | ojure |
Token ID | 32511 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Frazier | +1.067 |
han | +1.017 |
bnb | +1.008 |
iven | +0.996 |
VC | +0.994 |
Neg logit contributions | |
EQU | -0.919 |
ipop | -0.895 |
atche | -0.838 |
Expend | -0.809 |
Tiff | -0.797 |
Token | / |
Token ID | 1220 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Frazier | +3.673 |
mt | +3.523 |
VC | +3.517 |
han | +3.463 |
Kh | +3.366 |
Neg logit contributions | |
ipop | -3.781 |
EQU | -3.633 |
atche | -3.603 |
aspers | -3.395 |
Tiff | -3.292 |
Token | tools |
Token ID | 4899 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
Frazier | +3.241 |
mt | +3.110 |
VC | +3.079 |
lyn | +3.022 |
mono | +2.991 |
Neg logit contributions | |
ipop | -3.335 |
EQU | -3.234 |
atche | -3.149 |
aspers | -2.945 |
Expend | -2.913 |
Token | . |
Token ID | 764 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Frazier | +5.084 |
VC | +4.932 |
mt | +4.930 |
lyn | +4.782 |
han | +4.753 |
Neg logit contributions | |
ipop | -7.775 |
EQU | -7.551 |
atche | -7.365 |
Expend | -7.089 |
aspers | -7.039 |
Token | reader |
Token ID | 9173 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Frazier | +4.460 |
mt | +4.339 |
VC | +4.287 |
lyn | +4.215 |
mono | +4.140 |
Neg logit contributions | |
ipop | -5.107 |
EQU | -4.920 |
atche | -4.814 |
aspers | -4.530 |
Expend | -4.473 |
Token | | |
Token ID | 930 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Frazier | +2.839 |
mt | +2.700 |
VC | +2.683 |
han | +2.663 |
bnb | +2.640 |
Neg logit contributions | |
ipop | -3.385 |
EQU | -3.325 |
atche | -3.181 |
Expend | -3.044 |
aspers | -3.038 |
Token | 368 |
Token ID | 43019 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
Frazier | +3.340 |
VC | +3.131 |
mt | +3.074 |
han | +2.999 |
Kh | +2.959 |
Neg logit contributions | |
ipop | -4.318 |
EQU | -4.193 |
atche | -4.151 |
aspers | -3.936 |
Tiff | -3.786 |
Token | | |
Token ID | 930 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ipop | +0.523 |
EQU | +0.513 |
atche | +0.493 |
aspers | +0.466 |
Tiff | +0.464 |
Neg logit contributions | |
Frazier | -0.422 |
VC | -0.392 |
mt | -0.390 |
han | -0.386 |
Kh | -0.383 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Frazier | +2.722 |
mt | +2.580 |
VC | +2.509 |
�� | +2.498 |
han | +2.469 |
Neg logit contributions | |
ipop | -4.391 |
EQU | -4.337 |
atche | -4.224 |
aspers | -4.018 |
Tiff | -3.972 |
Token | undo |
Token ID | 23981 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Frazier | +1.363 |
mt | +1.293 |
VC | +1.288 |
�� | +1.282 |
han | +1.271 |
Neg logit contributions | |
ipop | -0.904 |
EQU | -0.888 |
atche | -0.838 |
aspers | -0.776 |
Tiff | -0.773 |
Token | _ |
Token ID | 62 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
Frazier | +1.129 |
VC | +1.078 |
mt | +1.073 |
han | +1.072 |
Kh | +1.056 |
Neg logit contributions | |
EQU | -0.979 |
ipop | -0.970 |
atche | -0.920 |
aspers | -0.864 |
Tiff | -0.862 |
Token | move |
Token ID | 21084 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
EQU | +0.315 |
ipop | +0.313 |
atche | +0.292 |
Tiff | +0.280 |
Expend | +0.274 |
Neg logit contributions | |
Frazier | -0.383 |
VC | -0.362 |
han | -0.361 |
mt | -0.361 |
Kh | -0.358 |
Token | ( |
Token ID | 357 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Frazier | +2.108 |
mt | +1.979 |
�� | +1.973 |
VC | +1.967 |
han | +1.957 |
Neg logit contributions | |
EQU | -2.291 |
ipop | -2.287 |
atche | -2.167 |
aspers | -2.055 |
Tiff | -2.053 |
Token | & |
Token ID | 1222 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Frazier | +1.392 |
�� | +1.287 |
mt | +1.283 |
VC | +1.281 |
han | +1.253 |
Neg logit contributions | |
ipop | -2.153 |
EQU | -2.138 |
atche | -2.050 |
aspers | -1.947 |
Tiff | -1.946 |
Token | mut |
Token ID | 4517 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Frazier | +2.507 |
mt | +2.425 |
VC | +2.289 |
lyn | +2.085 |
han | +2.083 |
Neg logit contributions | |
ipop | -10.369 |
EQU | -10.288 |
atche | -10.186 |
Tiff | -9.633 |
aspers | -9.626 |
Token | self |
Token ID | 2116 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
mt | +3.013 |
Frazier | +3.004 |
VC | +2.915 |
pt | +2.760 |
mono | +2.754 |
Neg logit contributions | |
ipop | -5.318 |
EQU | -5.246 |
atche | -5.181 |
aspers | -4.944 |
ECA | -4.855 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Frazier | +2.938 |
�� | +2.780 |
mt | +2.774 |
VC | +2.767 |
han | +2.755 |
Neg logit contributions | |
ipop | -2.546 |
EQU | -2.538 |
atche | -2.392 |
Tiff | -2.243 |
aspers | -2.243 |
Token | { |
Token ID | 1391 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ipop | +1.238 |
EQU | +1.232 |
atche | +1.182 |
aspers | +1.127 |
Tiff | +1.127 |
Neg logit contributions | |
Frazier | -0.655 |
VC | -0.590 |
�� | -0.590 |
mt | -0.587 |
han | -0.579 |
Token | let |
Token ID | 1309 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Frazier | +2.125 |
mt | +2.011 |
VC | +2.010 |
lyn | +1.910 |
han | +1.903 |
Neg logit contributions | |
ipop | -4.040 |
EQU | -3.925 |
atche | -3.848 |
aspers | -3.663 |
Tiff | -3.610 |
Token | org |
Token ID | 8745 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
ipop | +0.129 |
EQU | +0.129 |
atche | +0.121 |
Tiff | +0.114 |
aspers | +0.113 |
Neg logit contributions | |
Frazier | -0.136 |
�� | -0.128 |
VC | -0.126 |
mt | -0.125 |
han | -0.125 |
Token | . |
Token ID | 764 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Frazier | +3.563 |
VC | +3.398 |
mt | +3.385 |
han | +3.372 |
Kh | +3.235 |
Neg logit contributions | |
ipop | -5.459 |
EQU | -5.317 |
atche | -5.157 |
therap | -5.015 |
aspers | -4.935 |
Token | cl |
Token ID | 537 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Frazier | +1.766 |
mt | +1.684 |
VC | +1.671 |
lyn | +1.660 |
mono | +1.603 |
Neg logit contributions | |
ipop | -3.599 |
EQU | -3.558 |
atche | -3.455 |
aspers | -3.347 |
Expend | -3.271 |
Token | ojure |
Token ID | 32511 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Frazier | +1.265 |
han | +1.209 |
bnb | +1.197 |
iven | +1.184 |
VC | +1.177 |
Neg logit contributions | |
EQU | -1.104 |
ipop | -1.071 |
atche | -1.004 |
Expend | -0.972 |
Tiff | -0.957 |
Token | / |
Token ID | 1220 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Frazier | +3.595 |
mt | +3.448 |
VC | +3.440 |
han | +3.386 |
Kh | +3.294 |
Neg logit contributions | |
ipop | -3.643 |
EQU | -3.519 |
atche | -3.477 |
aspers | -3.276 |
Tiff | -3.176 |
Token | data |
Token ID | 1366 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
Frazier | +3.601 |
mt | +3.470 |
VC | +3.428 |
lyn | +3.376 |
mono | +3.334 |
Neg logit contributions | |
ipop | -3.953 |
EQU | -3.842 |
atche | -3.755 |
aspers | -3.518 |
Expend | -3.470 |
Token | . |
Token ID | 764 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Frazier | +5.353 |
mt | +5.110 |
VC | +5.066 |
han | +5.061 |
iven | +5.023 |
Neg logit contributions | |
EQU | -7.249 |
ipop | -7.247 |
atche | -6.869 |
Expend | -6.506 |
aspers | -6.477 |
Token | c |
Token ID | 269 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Frazier | +1.767 |
mt | +1.679 |
VC | +1.658 |
lyn | +1.621 |
han | +1.620 |
Neg logit contributions | |
ipop | -2.259 |
EQU | -2.226 |
atche | -2.147 |
aspers | -2.022 |
Tiff | -2.008 |
Token | sv |
Token ID | 21370 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Frazier | +2.587 |
han | +2.508 |
bnb | +2.479 |
mt | +2.471 |
VC | +2.440 |
Neg logit contributions | |
EQU | -2.243 |
ipop | -2.228 |
atche | -2.061 |
Expend | -1.960 |
Tiff | -1.954 |
Token | | |
Token ID | 930 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Frazier | +1.975 |
mt | +1.848 |
VC | +1.847 |
�� | +1.836 |
han | +1.833 |
Neg logit contributions | |
ipop | -2.489 |
EQU | -2.464 |
atche | -2.340 |
Expend | -2.227 |
aspers | -2.227 |
Token | 38 |
Token ID | 4353 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Frazier | +1.731 |
VC | +1.611 |
mt | +1.589 |
han | +1.555 |
�� | +1.541 |
Neg logit contributions | |
ipop | -2.289 |
EQU | -2.261 |
atche | -2.182 |
aspers | -2.076 |
Tiff | -2.035 |
Token | February |
Token ID | 3945 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
Frazier | +1.720 |
VC | +1.612 |
mt | +1.577 |
bnb | +1.507 |
mono | +1.482 |
Neg logit contributions | |
ipop | -3.918 |
EQU | -3.813 |
atche | -3.755 |
aspers | -3.591 |
ICES | -3.528 |
Token | 9 |
Token ID | 860 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Frazier | +0.337 |
VC | +0.307 |
mt | +0.304 |
han | +0.299 |
bnb | +0.294 |
Neg logit contributions | |
ipop | -0.471 |
EQU | -0.467 |
atche | -0.450 |
aspers | -0.429 |
Expend | -0.421 |
Token | , |
Token ID | 11 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Frazier | +1.652 |
VC | +1.545 |
han | +1.528 |
mt | +1.528 |
Kh | +1.522 |
Neg logit contributions | |
ipop | -2.179 |
EQU | -2.124 |
atche | -2.046 |
aspers | -1.966 |
Tiff | -1.929 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Frazier | +2.290 |
mt | +2.134 |
VC | +2.134 |
han | +2.041 |
Kh | +2.020 |
Neg logit contributions | |
ipop | -2.937 |
EQU | -2.849 |
atche | -2.821 |
aspers | -2.699 |
Tiff | -2.565 |
Token | R |
Token ID | 49 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
Frazier | +1.821 |
Kh | +1.782 |
VC | +1.698 |
han | +1.697 |
mt | +1.632 |
Neg logit contributions | |
ipop | -4.441 |
EQU | -4.367 |
atche | -4.174 |
Tiff | -4.037 |
aspers | -4.011 |
Token | ipe |
Token ID | 3757 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Frazier | +3.794 |
iven | +3.724 |
han | +3.707 |
bnb | +3.636 |
Kh | +3.586 |
Neg logit contributions | |
EQU | -2.428 |
ipop | -2.066 |
Expend | -1.977 |
Tiff | -1.951 |
atche | -1.892 |
Token | for |
Token ID | 329 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Frazier | +5.689 |
mt | +5.247 |
VC | +5.232 |
han | +5.156 |
lyn | +5.092 |
Neg logit contributions | |
ipop | -6.963 |
EQU | -6.923 |
atche | -6.530 |
aspers | -6.381 |
Tiff | -6.139 |
Token | M |
Token ID | 337 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Frazier | +3.928 |
VC | +3.738 |
mt | +3.732 |
han | +3.584 |
mono | +3.570 |
Neg logit contributions | |
ipop | -3.976 |
EQU | -3.864 |
atche | -3.695 |
aspers | -3.512 |
Tiff | -3.428 |
Token | ST |
Token ID | 2257 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Frazier | +2.649 |
VC | +2.613 |
Kh | +2.577 |
han | +2.566 |
mt | +2.556 |
Neg logit contributions | |
ipop | -3.065 |
EQU | -2.992 |
atche | -2.817 |
Tiff | -2.733 |
Expend | -2.684 |
Token | 3 |
Token ID | 18 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Frazier | +1.413 |
Kh | +1.318 |
VC | +1.308 |
han | +1.292 |
mt | +1.280 |
Neg logit contributions | |
ipop | -2.241 |
EQU | -2.232 |
atche | -2.144 |
Tiff | -2.051 |
aspers | -2.027 |
Token | K |
Token ID | 42 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Kh | +2.114 |
Frazier | +2.084 |
VC | +1.955 |
han | +1.875 |
mt | +1.832 |
Neg logit contributions | |
ipop | -6.076 |
EQU | -5.812 |
atche | -5.773 |
aspers | -5.518 |
Tiff | -5.491 |
Token | Que |
Token ID | 15681 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Frazier | +0.469 |
VC | +0.430 |
Kh | +0.428 |
mt | +0.426 |
han | +0.426 |
Neg logit contributions | |
ipop | -0.709 |
EQU | -0.702 |
atche | -0.671 |
Tiff | -0.641 |
aspers | -0.638 |
Token | er |
Token ID | 263 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Frazier | +2.484 |
han | +2.352 |
VC | +2.338 |
Kh | +2.296 |
mt | +2.276 |
Neg logit contributions | |
EQU | -2.475 |
ipop | -2.447 |
atche | -2.316 |
aspers | -2.217 |
Tiff | -2.211 |
Token | magnet |
Token ID | 19972 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
Frazier | +1.490 |
mt | +1.397 |
VC | +1.391 |
han | +1.353 |
lyn | +1.335 |
Neg logit contributions | |
ipop | -2.356 |
EQU | -2.332 |
atche | -2.280 |
aspers | -2.185 |
Tiff | -2.143 |
Token | ? |
Token ID | 30 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Frazier | +5.435 |
VC | +5.121 |
mt | +5.046 |
han | +5.039 |
lyn | +4.980 |
Neg logit contributions | |
EQU | -5.875 |
ipop | -5.828 |
atche | -5.625 |
aspers | -5.372 |
Tiff | -5.279 |
Token |
|
Token ID | 198 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Frazier | +2.005 |
VC | +1.873 |
mt | +1.867 |
�� | +1.865 |
han | +1.845 |
Neg logit contributions | |
ipop | -1.783 |
EQU | -1.780 |
atche | -1.688 |
aspers | -1.584 |
Tiff | -1.566 |
Token |
|
Token ID | 198 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
Frazier | +3.694 |
VC | +3.522 |
mt | +3.461 |
han | +3.420 |
Kh | +3.385 |
Neg logit contributions | |
ipop | -4.969 |
EQU | -4.794 |
atche | -4.693 |
therap | -4.575 |
aspers | -4.520 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Frazier | +0.856 |
Kh | +0.648 |
han | +0.637 |
VC | +0.461 |
mt | +0.414 |
Neg logit contributions | |
EQU | -11.659 |
ipop | -11.474 |
atche | -11.012 |
Tiff | -10.862 |
Expend | -10.851 |
Token | : |
Token ID | 25 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Frazier | +2.855 |
VC | +2.734 |
han | +2.692 |
Kh | +2.666 |
mt | +2.653 |
Neg logit contributions | |
ipop | -3.649 |
EQU | -3.535 |
atche | -3.441 |
aspers | -3.287 |
therap | -3.258 |
Token | hey |
Token ID | 17207 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
Frazier | +1.134 |
mt | +1.054 |
VC | +1.053 |
�� | +1.046 |
han | +1.035 |
Neg logit contributions | |
ipop | -1.232 |
EQU | -1.219 |
atche | -1.162 |
aspers | -1.093 |
Tiff | -1.083 |
Token | _ |
Token ID | 62 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Frazier | +0.303 |
�� | +0.283 |
VC | +0.282 |
mt | +0.281 |
han | +0.280 |
Neg logit contributions | |
EQU | -0.299 |
ipop | -0.299 |
atche | -0.281 |
Tiff | -0.265 |
aspers | -0.264 |
Token | ler |
Token ID | 1754 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Frazier | +0.340 |
�� | +0.318 |
VC | +0.317 |
mt | +0.316 |
han | +0.315 |
Neg logit contributions | |
EQU | -0.321 |
ipop | -0.320 |
atche | -0.301 |
Tiff | -0.284 |
aspers | -0.282 |
Token | Come |
Token ID | 7911 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ipop | +0.791 |
EQU | +0.791 |
atche | +0.746 |
Tiff | +0.703 |
aspers | +0.700 |
Neg logit contributions | |
Frazier | -0.770 |
�� | -0.724 |
VC | -0.715 |
mt | -0.712 |
han | -0.707 |
Token | again |
Token ID | 757 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Frazier | +0.924 |
VC | +0.861 |
mt | +0.858 |
han | +0.857 |
�� | +0.855 |
Neg logit contributions | |
ipop | -0.817 |
EQU | -0.810 |
atche | -0.764 |
aspers | -0.721 |
Tiff | -0.713 |
Token | ? |
Token ID | 30 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Frazier | +1.143 |
VC | +1.058 |
han | +1.055 |
mt | +1.053 |
�� | +1.044 |
Neg logit contributions | |
EQU | -1.214 |
ipop | -1.213 |
atche | -1.148 |
aspers | -1.084 |
Tiff | -1.075 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
Frazier | +0.875 |
VC | +0.812 |
mt | +0.806 |
han | +0.801 |
�� | +0.795 |
Neg logit contributions | |
ipop | -0.927 |
EQU | -0.915 |
atche | -0.879 |
aspers | -0.827 |
Tiff | -0.810 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Frazier | +0.498 |
VC | +0.468 |
mt | +0.464 |
han | +0.463 |
Kh | +0.459 |
Neg logit contributions | |
ipop | -0.490 |
EQU | -0.481 |
atche | -0.460 |
aspers | -0.434 |
Tiff | -0.428 |
Token | Come |
Token ID | 16773 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
Frazier | +2.538 |
Kh | +2.437 |
han | +2.423 |
VC | +2.366 |
�� | +2.350 |
Neg logit contributions | |
EQU | -2.764 |
ipop | -2.729 |
atche | -2.601 |
Tiff | -2.476 |
aspers | -2.459 |
Token | again |
Token ID | 757 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Frazier | +5.200 |
han | +4.767 |
mt | +4.738 |
bnb | +4.729 |
VC | +4.714 |
Neg logit contributions | |
ipop | -7.249 |
EQU | -7.244 |
atche | -6.937 |
aspers | -6.764 |
effective | -6.550 |
Token | ? |
Token ID | 30 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Frazier | +1.094 |
�� | +1.020 |
VC | +1.019 |
mt | +1.015 |
han | +1.010 |
Neg logit contributions | |
ipop | -0.945 |
EQU | -0.945 |
atche | -0.889 |
aspers | -0.832 |
Tiff | -0.830 |
Token | Y |
Token ID | 575 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Frazier | +1.343 |
VC | +1.234 |
mt | +1.229 |
han | +1.217 |
�� | +1.200 |
Neg logit contributions | |
ipop | -1.732 |
EQU | -1.712 |
atche | -1.655 |
aspers | -1.568 |
Tiff | -1.528 |
Token | una |
Token ID | 9613 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
ipop | +2.614 |
EQU | +2.549 |
atche | +2.423 |
aspers | +2.204 |
Tiff | +2.156 |
Neg logit contributions | |
Frazier | -4.392 |
�� | -4.193 |
VC | -4.104 |
mt | -4.091 |
bnb | -4.018 |
Token | : |
Token ID | 25 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
ipop | +2.518 |
EQU | +2.465 |
atche | +2.311 |
Tiff | +2.172 |
Expend | +2.119 |
Neg logit contributions | |
Frazier | -3.321 |
�� | -3.183 |
VC | -3.113 |
mt | -3.102 |
bnb | -3.099 |
Token | R |
Token ID | 49 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Frazier | +1.772 |
Kh | +1.668 |
VC | +1.624 |
han | +1.606 |
mt | +1.585 |
Neg logit contributions | |
ipop | -4.063 |
EQU | -3.988 |
atche | -3.797 |
aspers | -3.660 |
Tiff | -3.646 |
Token | iff |
Token ID | 733 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Frazier | +2.643 |
han | +2.491 |
iven | +2.474 |
bnb | +2.445 |
VC | +2.401 |
Neg logit contributions | |
EQU | -3.037 |
ipop | -2.883 |
atche | -2.693 |
Expend | -2.674 |
aspers | -2.659 |
Token | Tra |
Token ID | 15721 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Frazier | +1.709 |
Kh | +1.595 |
VC | +1.564 |
mt | +1.552 |
han | +1.542 |
Neg logit contributions | |
ipop | -2.483 |
EQU | -2.454 |
atche | -2.319 |
aspers | -2.241 |
Expend | -2.218 |
Token | x |
Token ID | 87 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Frazier | +2.387 |
han | +2.326 |
VC | +2.269 |
Kh | +2.229 |
mt | +2.193 |
Neg logit contributions | |
EQU | -3.287 |
ipop | -3.217 |
atche | -3.064 |
Tiff | -3.010 |
Expend | -2.929 |
Token |
|
Token ID | 198 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Frazier | +4.976 |
VC | +4.794 |
mt | +4.761 |
han | +4.676 |
lyn | +4.614 |
Neg logit contributions | |
ipop | -5.444 |
EQU | -5.440 |
atche | -5.179 |
aspers | -4.963 |
Tiff | -4.824 |
Token |
|
Token ID | 198 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
Frazier | +4.462 |
VC | +4.316 |
mt | +4.200 |
han | +4.183 |
Kh | +4.121 |
Neg logit contributions | |
ipop | -6.795 |
therap | -6.524 |
EQU | -6.502 |
atche | -6.402 |
aspers | -6.189 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Frazier | +0.849 |
han | +0.842 |
Kh | +0.773 |
VC | +0.596 |
mt | +0.511 |
Neg logit contributions | |
EQU | -11.347 |
ipop | -11.164 |
atche | -10.745 |
Tiff | -10.572 |
Expend | -10.471 |
Token | : |
Token ID | 25 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Frazier | +2.842 |
VC | +2.725 |
han | +2.700 |
Kh | +2.666 |
mt | +2.643 |
Neg logit contributions | |
ipop | -3.653 |
EQU | -3.561 |
atche | -3.449 |
aspers | -3.302 |
therap | -3.270 |
Token | V |
Token ID | 569 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
Frazier | +1.054 |
mt | +0.979 |
VC | +0.978 |
�� | +0.972 |
han | +0.962 |
Neg logit contributions | |
ipop | -1.176 |
EQU | -1.166 |
atche | -1.110 |
aspers | -1.046 |
Tiff | -1.037 |
Token | the |
Token ID | 1169 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Frazier | +0.028 |
�� | +0.026 |
VC | +0.026 |
mt | +0.026 |
han | +0.026 |
Neg logit contributions | |
ipop | -0.028 |
EQU | -0.028 |
atche | -0.026 |
Tiff | -0.025 |
aspers | -0.025 |
Token | Happy |
Token ID | 25082 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ipop | +0.772 |
EQU | +0.768 |
atche | +0.730 |
Tiff | +0.687 |
aspers | +0.686 |
Neg logit contributions | |
Frazier | -0.698 |
�� | -0.651 |
VC | -0.645 |
mt | -0.642 |
han | -0.634 |
Token | three |
Token ID | 1115 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Frazier | +0.562 |
�� | +0.520 |
VC | +0.518 |
mt | +0.514 |
han | +0.511 |
Neg logit contributions | |
ipop | -0.673 |
EQU | -0.671 |
atche | -0.638 |
aspers | -0.602 |
Tiff | -0.601 |
Token | quarterbacks |
Token ID | 23643 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
EQU | +0.965 |
ipop | +0.963 |
atche | +0.905 |
Tiff | +0.854 |
aspers | +0.845 |
Neg logit contributions | |
Frazier | -1.032 |
�� | -0.978 |
mt | -0.964 |
VC | -0.958 |
bnb | -0.954 |
Token | have |
Token ID | 423 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Frazier | +0.152 |
�� | +0.144 |
VC | +0.141 |
mt | +0.141 |
han | +0.140 |
Neg logit contributions | |
ipop | -0.152 |
EQU | -0.152 |
atche | -0.143 |
Tiff | -0.135 |
aspers | -0.134 |
Token | scored |
Token ID | 7781 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
EQU | +0.138 |
ipop | +0.138 |
atche | +0.130 |
Tiff | +0.122 |
aspers | +0.121 |
Neg logit contributions | |
Frazier | -0.147 |
�� | -0.140 |
VC | -0.137 |
mt | -0.137 |
han | -0.136 |
Token | at |
Token ID | 379 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Frazier | +1.440 |
VC | +1.331 |
mt | +1.310 |
han | +1.299 |
�� | +1.299 |
Neg logit contributions | |
ipop | -1.798 |
EQU | -1.767 |
atche | -1.697 |
aspers | -1.609 |
Tiff | -1.592 |
Token | least |
Token ID | 1551 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
Frazier | +2.313 |
VC | +2.157 |
mt | +2.121 |
�� | +2.118 |
han | +2.117 |
Neg logit contributions | |
ipop | -2.669 |
EQU | -2.624 |
atche | -2.513 |
aspers | -2.364 |
Expend | -2.343 |
Token | 20 |
Token ID | 1160 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Frazier | +4.592 |
VC | +4.245 |
han | +4.028 |
mt | +3.993 |
Kh | +3.960 |
Neg logit contributions | |
ipop | -7.891 |
atche | -7.528 |
EQU | -7.503 |
aspers | -7.201 |
ICES | -7.035 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Frazier | +2.674 |
VC | +2.456 |
�� | +2.426 |
mt | +2.418 |
han | +2.406 |
Neg logit contributions | |
ipop | -3.774 |
EQU | -3.740 |
atche | -3.611 |
aspers | -3.425 |
Tiff | -3.396 |
Token | points |
Token ID | 2173 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Frazier | +1.876 |
VC | +1.729 |
mt | +1.695 |
han | +1.672 |
Kh | +1.661 |
Neg logit contributions | |
ipop | -3.148 |
EQU | -3.092 |
atche | -2.991 |
aspers | -2.854 |
Tiff | -2.842 |
Token | against |
Token ID | 1028 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Frazier | +1.944 |
VC | +1.793 |
mt | +1.752 |
bnb | +1.751 |
han | +1.747 |
Neg logit contributions | |
ipop | -2.553 |
EQU | -2.518 |
atche | -2.435 |
aspers | -2.306 |
Expend | -2.279 |
Token | Carolina |
Token ID | 5913 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Frazier | +1.303 |
VC | +1.210 |
�� | +1.194 |
mt | +1.185 |
han | +1.181 |
Neg logit contributions | |
ipop | -1.484 |
EQU | -1.473 |
atche | -1.411 |
aspers | -1.335 |
Tiff | -1.314 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
ipop | +0.570 |
EQU | +0.568 |
atche | +0.537 |
Tiff | +0.506 |
aspers | +0.505 |
Neg logit contributions | |
Frazier | -0.543 |
�� | -0.510 |
VC | -0.503 |
mt | -0.501 |
han | -0.496 |
Token |
|
Token ID | 198 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
Frazier | +0.234 |
VC | +0.218 |
mt | +0.218 |
�� | +0.215 |
han | +0.214 |
Neg logit contributions | |
ipop | -0.229 |
EQU | -0.227 |
atche | -0.217 |
aspers | -0.203 |
Tiff | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
Frazier | +0.041 |
VC | +0.038 |
mt | +0.038 |
han | +0.038 |
Kh | +0.037 |
Neg logit contributions | |
ipop | -0.038 |
EQU | -0.038 |
atche | -0.036 |
aspers | -0.034 |
Tiff | -0.033 |
Token | on |
Token ID | 261 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Frazier | +0.572 |
�� | +0.537 |
VC | +0.536 |
han | +0.534 |
mt | +0.534 |
Neg logit contributions | |
EQU | -0.574 |
ipop | -0.573 |
atche | -0.542 |
Tiff | -0.510 |
aspers | -0.505 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
Frazier | +1.017 |
�� | +0.951 |
VC | +0.945 |
mt | +0.943 |
han | +0.934 |
Neg logit contributions | |
ipop | -1.060 |
EQU | -1.058 |
atche | -1.002 |
Tiff | -0.942 |
aspers | -0.941 |
Token | address |
Token ID | 2209 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
ipop | +0.175 |
EQU | +0.173 |
atche | +0.163 |
Tiff | +0.150 |
Expend | +0.149 |
Neg logit contributions | |
Frazier | -0.227 |
�� | -0.214 |
VC | -0.211 |
han | -0.211 |
mt | -0.210 |
Token | https |
Token ID | 3740 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
Frazier | +5.054 |
mt | +4.822 |
VC | +4.758 |
bnb | +4.675 |
han | +4.631 |
Neg logit contributions | |
EQU | -6.994 |
ipop | -6.925 |
atche | -6.730 |
aspers | -6.522 |
Tiff | -6.313 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Frazier | +3.521 |
VC | +3.299 |
han | +3.273 |
Kh | +3.252 |
mt | +3.232 |
Neg logit contributions | |
ipop | -6.858 |
EQU | -6.810 |
atche | -6.559 |
aspers | -6.413 |
therap | -6.356 |
Token | old |
Token ID | 727 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Frazier | +1.358 |
bnb | +1.289 |
mt | +1.282 |
VC | +1.277 |
han | +1.265 |
Neg logit contributions | |
EQU | -2.480 |
ipop | -2.428 |
atche | -2.338 |
Tiff | -2.261 |
Expend | -2.255 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
EQU | +3.220 |
ipop | +3.195 |
atche | +3.006 |
Tiff | +2.843 |
Expend | +2.818 |
Neg logit contributions | |
�� | -3.390 |
Frazier | -3.337 |
bnb | -3.091 |
�� | -3.064 |
VC | -3.058 |
Token | nice |
Token ID | 44460 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ipop | +2.001 |
EQU | +1.962 |
atche | +1.838 |
aspers | +1.673 |
Tiff | +1.660 |
Neg logit contributions | |
Frazier | -3.361 |
�� | -3.222 |
VC | -3.173 |
mt | -3.154 |
han | -3.128 |
Token | , |
Token ID | 11 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Frazier | +1.155 |
VC | +1.077 |
mt | +1.067 |
han | +1.064 |
Kh | +1.057 |
Neg logit contributions | |
ipop | -1.484 |
EQU | -1.448 |
atche | -1.394 |
aspers | -1.334 |
Tiff | -1.313 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Frazier | +3.141 |
mt | +2.955 |
VC | +2.928 |
han | +2.790 |
Kh | +2.749 |
Neg logit contributions | |
ipop | -4.257 |
EQU | -4.111 |
atche | -4.082 |
aspers | -3.927 |
Tiff | -3.708 |
Token | boys |
Token ID | 13202 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Frazier | +1.307 |
han | +1.271 |
Kh | +1.248 |
VC | +1.242 |
bnb | +1.241 |
Neg logit contributions | |
ipop | -0.893 |
EQU | -0.892 |
atche | -0.805 |
Tiff | -0.777 |
Expend | -0.763 |
Token | beware |
Token ID | 40600 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Frazier | +2.824 |
VC | +2.638 |
mt | +2.602 |
han | +2.591 |
�� | +2.583 |
Neg logit contributions | |
ipop | -3.784 |
EQU | -3.737 |
atche | -3.615 |
Tiff | -3.413 |
aspers | -3.392 |
Token |
|
Token ID | 198 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Frazier | +4.897 |
VC | +4.542 |
mt | +4.525 |
han | +4.517 |
lyn | +4.428 |
Neg logit contributions | |
ipop | -5.219 |
EQU | -5.180 |
atche | -4.917 |
aspers | -4.766 |
Tiff | -4.613 |
Token |
|
Token ID | 198 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
Frazier | +4.574 |
VC | +4.381 |
mt | +4.306 |
han | +4.266 |
Kh | +4.229 |
Neg logit contributions | |
ipop | -7.008 |
therap | -6.746 |
EQU | -6.706 |
atche | -6.589 |
contrace | -6.471 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Frazier | +0.661 |
han | +0.568 |
Kh | +0.540 |
VC | +0.332 |
chin | +0.304 |
Neg logit contributions | |
EQU | -11.399 |
ipop | -11.273 |
atche | -10.759 |
Tiff | -10.695 |
Expend | -10.588 |
Token | : |
Token ID | 25 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Frazier | +2.903 |
VC | +2.789 |
han | +2.758 |
Kh | +2.733 |
mt | +2.698 |
Neg logit contributions | |
ipop | -3.737 |
EQU | -3.641 |
atche | -3.523 |
aspers | -3.370 |
therap | -3.362 |
Token | j |
Token ID | 474 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
Frazier | +1.188 |
mt | +1.104 |
VC | +1.102 |
�� | +1.094 |
han | +1.084 |
Neg logit contributions | |
ipop | -1.311 |
EQU | -1.299 |
atche | -1.236 |
aspers | -1.165 |
Tiff | -1.153 |
Token | wt |
Token ID | 46569 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Frazier | +0.552 |
�� | +0.515 |
VC | +0.513 |
mt | +0.512 |
han | +0.512 |
Neg logit contributions | |
EQU | -0.514 |
ipop | -0.513 |
atche | -0.481 |
Tiff | -0.454 |
Expend | -0.449 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Frazier | +1.204 |
mt | +1.116 |
VC | +1.114 |
�� | +1.114 |
han | +1.111 |
Neg logit contributions | |
EQU | -1.281 |
ipop | -1.273 |
atche | -1.199 |
Tiff | -1.137 |
aspers | -1.132 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
EQU | +1.932 |
ipop | +1.916 |
atche | +1.796 |
Tiff | +1.681 |
aspers | +1.663 |
Neg logit contributions | |
Frazier | -2.483 |
�� | -2.444 |
bnb | -2.318 |
VC | -2.309 |
mt | -2.308 |
Token | EC |
Token ID | 2943 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
EQU | +1.598 |
ipop | +1.595 |
atche | +1.509 |
aspers | +1.425 |
Tiff | +1.408 |
Neg logit contributions | |
Frazier | -1.652 |
�� | -1.566 |
VC | -1.528 |
mt | -1.522 |
bnb | -1.517 |
Token | ON |
Token ID | 1340 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ipop | +0.641 |
EQU | +0.632 |
atche | +0.586 |
Tiff | +0.537 |
aspers | +0.535 |
Neg logit contributions | |
Frazier | -1.139 |
�� | -1.078 |
VC | -1.077 |
mt | -1.072 |
han | -1.065 |
Token | OM |
Token ID | 2662 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
EQU | +1.285 |
ipop | +1.272 |
atche | +1.195 |
Tiff | +1.122 |
aspers | +1.120 |
Neg logit contributions | |
Frazier | -1.448 |
�� | -1.370 |
VC | -1.345 |
mt | -1.344 |
bnb | -1.338 |
Token | ICS |
Token ID | 19505 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
EQU | +0.990 |
ipop | +0.967 |
atche | +0.887 |
Tiff | +0.833 |
Expend | +0.833 |
Neg logit contributions | |
Frazier | -1.342 |
�� | -1.288 |
mt | -1.257 |
han | -1.256 |
bnb | -1.254 |
Token | AND |
Token ID | 5357 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
EQU | +2.957 |
ipop | +2.758 |
atche | +2.611 |
Tiff | +2.505 |
Expend | +2.484 |
Neg logit contributions | |
Frazier | -3.491 |
�� | -3.403 |
bnb | -3.268 |
han | -3.258 |
iven | -3.240 |
Token | TR |
Token ID | 7579 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
EQU | +4.147 |
ipop | +3.706 |
atche | +3.497 |
Expend | +3.437 |
Tiff | +3.436 |
Neg logit contributions | |
Frazier | -4.447 |
�� | -4.387 |
bnb | -4.245 |
han | -4.216 |
iven | -4.173 |
Token | ADE |
Token ID | 19266 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ipop | +0.966 |
EQU | +0.965 |
atche | +0.884 |
Tiff | +0.801 |
aspers | +0.799 |
Neg logit contributions | |
Frazier | -1.906 |
�� | -1.821 |
VC | -1.803 |
mt | -1.797 |
han | -1.790 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
EQU | +1.678 |
ipop | +1.621 |
atche | +1.524 |
Tiff | +1.444 |
Expend | +1.435 |
Neg logit contributions | |
Frazier | -2.047 |
�� | -1.974 |
bnb | -1.915 |
han | -1.910 |
mt | -1.904 |
Token |
|
Token ID | 198 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
EQU | +3.219 |
ipop | +3.081 |
atche | +2.889 |
Tiff | +2.727 |
Expend | +2.685 |
Neg logit contributions | |
�� | -5.059 |
Frazier | -4.829 |
bnb | -4.604 |
�� | -4.600 |
�� | -4.554 |
Token | The |
Token ID | 464 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
EQU | +2.834 |
ipop | +2.802 |
atche | +2.663 |
aspers | +2.531 |
effective | +2.490 |
Neg logit contributions | |
Frazier | -2.977 |
�� | -2.853 |
bnb | -2.744 |
VC | -2.744 |
mt | -2.729 |
Token | The |
Token ID | 383 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
ipop | +0.365 |
EQU | +0.362 |
atche | +0.343 |
aspers | +0.320 |
Tiff | +0.319 |
Neg logit contributions | |
Frazier | -0.397 |
VC | -0.370 |
�� | -0.369 |
mt | -0.368 |
han | -0.365 |
Token | book |
Token ID | 1492 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Frazier | +0.599 |
VC | +0.557 |
mt | +0.551 |
�� | +0.551 |
han | +0.544 |
Neg logit contributions | |
ipop | -0.712 |
EQU | -0.704 |
atche | -0.672 |
aspers | -0.635 |
Tiff | -0.632 |
Token | The |
Token ID | 383 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Frazier | +0.655 |
VC | +0.603 |
�� | +0.601 |
mt | +0.596 |
han | +0.592 |
Neg logit contributions | |
ipop | -0.920 |
EQU | -0.917 |
atche | -0.873 |
aspers | -0.827 |
Tiff | -0.827 |
Token | Rise |
Token ID | 15648 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
EQU | +2.540 |
ipop | +2.518 |
atche | +2.385 |
Expend | +2.259 |
Tiff | +2.256 |
Neg logit contributions | |
Frazier | -2.549 |
�� | -2.412 |
mt | -2.363 |
han | -2.336 |
VC | -2.333 |
Token | of |
Token ID | 286 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
EQU | +2.207 |
ipop | +2.200 |
atche | +2.098 |
Expend | +1.965 |
Tiff | +1.954 |
Neg logit contributions | |
Frazier | -2.428 |
�� | -2.305 |
mt | -2.263 |
bnb | -2.237 |
VC | -2.227 |
Token | the |
Token ID | 262 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
EQU | +3.482 |
ipop | +3.408 |
atche | +3.184 |
Tiff | +3.179 |
Expend | +3.144 |
Neg logit contributions | |
�� | -3.457 |
Frazier | -3.446 |
bnb | -3.237 |
mt | -3.231 |
iven | -3.230 |
Token | Robots |
Token ID | 39096 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
EQU | +4.628 |
ipop | +4.536 |
atche | +4.254 |
Tiff | +4.224 |
Expend | +4.223 |
Neg logit contributions | |
Frazier | -4.516 |
�� | -4.410 |
bnb | -4.243 |
iven | -4.217 |
Kh | -4.215 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ipop | +0.110 |
EQU | +0.110 |
atche | +0.104 |
Tiff | +0.097 |
aspers | +0.097 |
Neg logit contributions | |
Frazier | -0.119 |
�� | -0.112 |
VC | -0.111 |
mt | -0.111 |
han | -0.110 |
Token | this |
Token ID | 428 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ipop | +0.805 |
EQU | +0.804 |
atche | +0.761 |
Tiff | +0.721 |
aspers | +0.718 |
Neg logit contributions | |
Frazier | -0.680 |
�� | -0.638 |
VC | -0.624 |
mt | -0.624 |
han | -0.619 |
Token | issue |
Token ID | 2071 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
Frazier | +1.067 |
VC | +0.988 |
mt | +0.982 |
�� | +0.981 |
han | +0.973 |
Neg logit contributions | |
ipop | -1.243 |
EQU | -1.235 |
atche | -1.176 |
aspers | -1.110 |
Tiff | -1.108 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Frazier | +0.486 |
�� | +0.454 |
VC | +0.450 |
mt | +0.448 |
han | +0.444 |
Neg logit contributions | |
ipop | -0.547 |
EQU | -0.545 |
atche | -0.517 |
Tiff | -0.488 |
aspers | -0.487 |
Token | 79 |
Token ID | 3720 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ipop | +0.696 |
EQU | +0.694 |
atche | +0.662 |
Tiff | +0.630 |
aspers | +0.627 |
Neg logit contributions | |
Frazier | -0.463 |
�� | -0.430 |
VC | -0.421 |
mt | -0.419 |
han | -0.416 |
Token | - |
Token ID | 12 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
EQU | +1.510 |
ipop | +1.509 |
atche | +1.412 |
Tiff | +1.343 |
Expend | +1.332 |
Neg logit contributions | |
Frazier | -1.578 |
�� | -1.496 |
bnb | -1.465 |
han | -1.458 |
VC | -1.456 |
Token | 488 |
Token ID | 33646 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
EQU | +1.153 |
ipop | +1.150 |
atche | +1.091 |
Tiff | +1.034 |
aspers | +1.032 |
Neg logit contributions | |
Frazier | -0.904 |
�� | -0.847 |
VC | -0.829 |
mt | -0.828 |
han | -0.820 |
Token | - |
Token ID | 12 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
EQU | +1.805 |
ipop | +1.804 |
atche | +1.698 |
Tiff | +1.600 |
aspers | +1.590 |
Neg logit contributions | |
Frazier | -1.883 |
�� | -1.803 |
VC | -1.742 |
mt | -1.740 |
bnb | -1.733 |
Token | 46 |
Token ID | 3510 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ipop | +0.302 |
EQU | +0.301 |
atche | +0.287 |
Tiff | +0.273 |
aspers | +0.272 |
Neg logit contributions | |
Frazier | -0.209 |
�� | -0.193 |
VC | -0.191 |
mt | -0.190 |
han | -0.188 |
Token | 99 |
Token ID | 2079 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
EQU | +3.019 |
ipop | +2.964 |
atche | +2.832 |
Tiff | +2.715 |
Expend | +2.678 |
Neg logit contributions | |
Frazier | -2.221 |
�� | -2.189 |
bnb | -2.052 |
mt | -2.015 |
VC | -2.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ipop | +4.359 |
EQU | +4.304 |
atche | +3.996 |
Tiff | +3.841 |
Expend | +3.794 |
Neg logit contributions | |
Frazier | -4.908 |
�� | -4.835 |
bnb | -4.679 |
han | -4.622 |
Kh | -4.599 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
EQU | +3.084 |
ipop | +3.023 |
atche | +2.808 |
Expend | +2.703 |
Tiff | +2.690 |
Neg logit contributions | |
Frazier | -3.513 |
�� | -3.469 |
bnb | -3.324 |
han | -3.299 |
VC | -3.290 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Frazier | +1.087 |
VC | +1.027 |
mt | +1.016 |
han | +1.010 |
Kh | +1.001 |
Neg logit contributions | |
ipop | -1.140 |
EQU | -1.109 |
atche | -1.070 |
aspers | -1.014 |
Tiff | -0.996 |
Token | References |
Token ID | 19927 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Frazier | +0.149 |
�� | +0.139 |
VC | +0.138 |
mt | +0.138 |
han | +0.137 |
Neg logit contributions | |
ipop | -0.153 |
EQU | -0.152 |
atche | -0.144 |
Tiff | -0.136 |
aspers | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
EQU | +1.465 |
ipop | +1.454 |
atche | +1.358 |
Tiff | +1.273 |
Expend | +1.263 |
Neg logit contributions | |
Frazier | -1.834 |
�� | -1.764 |
bnb | -1.719 |
mt | -1.713 |
VC | -1.713 |
Token | cipher |
Token ID | 38012 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Frazier | +1.710 |
mt | +1.624 |
VC | +1.623 |
han | +1.599 |
�� | +1.594 |
Neg logit contributions | |
ipop | -1.631 |
EQU | -1.616 |
atche | -1.534 |
aspers | -1.460 |
Expend | -1.432 |
Token | RC |
Token ID | 13987 |
Feature activation | +1.83e-04 |
Pos logit contributions | |
Frazier | +1.676 |
VC | +1.579 |
mt | +1.569 |
han | +1.552 |
�� | +1.534 |
Neg logit contributions | |
ipop | -1.770 |
EQU | -1.753 |
atche | -1.671 |
aspers | -1.597 |
Tiff | -1.573 |
Token | 4 |
Token ID | 19 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ipop | +0.002 |
EQU | +0.002 |
atche | +0.001 |
Tiff | +0.001 |
aspers | +0.001 |
Neg logit contributions | |
Frazier | -0.001 |
�� | -0.001 |
VC | -0.001 |
mt | -0.001 |
han | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ipop | +0.196 |
EQU | +0.196 |
atche | +0.185 |
Tiff | +0.174 |
aspers | +0.173 |
Neg logit contributions | |
Frazier | -0.195 |
�� | -0.183 |
VC | -0.181 |
mt | -0.180 |
han | -0.179 |
Token | confidentiality |
Token ID | 32554 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
EQU | +1.309 |
ipop | +1.305 |
atche | +1.228 |
Tiff | +1.161 |
aspers | +1.154 |
Neg logit contributions | |
Frazier | -1.259 |
�� | -1.186 |
VC | -1.157 |
bnb | -1.156 |
mt | -1.151 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
ipop | +0.579 |
EQU | +0.578 |
atche | +0.545 |
Tiff | +0.514 |
aspers | +0.510 |
Neg logit contributions | |
Frazier | -0.565 |
�� | -0.535 |
VC | -0.523 |
mt | -0.520 |
han | -0.518 |
Token | 9 |
Token ID | 24 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ipop | +4.405 |
EQU | +4.312 |
atche | +4.130 |
aspers | +3.820 |
effective | +3.778 |
Neg logit contributions | |
Frazier | -5.623 |
�� | -5.368 |
mt | -5.252 |
VC | -5.249 |
lyn | -5.144 |
Token | ] |
Token ID | 60 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Frazier | +0.988 |
�� | +0.929 |
VC | +0.923 |
mt | +0.920 |
han | +0.913 |
Neg logit contributions | |
ipop | -0.851 |
EQU | -0.847 |
atche | -0.797 |
Tiff | -0.745 |
aspers | -0.743 |
Token | and |
Token ID | 290 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
EQU | +1.990 |
ipop | +1.979 |
atche | +1.870 |
Tiff | +1.768 |
aspers | +1.746 |
Neg logit contributions | |
Frazier | -1.844 |
�� | -1.753 |
bnb | -1.689 |
han | -1.688 |
VC | -1.685 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
EQU | +1.884 |
ipop | +1.871 |
atche | +1.755 |
Tiff | +1.659 |
aspers | +1.645 |
Neg logit contributions | |
Frazier | -1.979 |
�� | -1.884 |
bnb | -1.826 |
han | -1.825 |
VC | -1.822 |
Token | CRC |
Token ID | 45623 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ipop | +0.305 |
EQU | +0.304 |
atche | +0.289 |
Tiff | +0.273 |
aspers | +0.272 |
Neg logit contributions | |
Frazier | -0.264 |
�� | -0.246 |
VC | -0.243 |
mt | -0.242 |
han | -0.240 |
Token | s |
Token ID | 82 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
ipop | +0.079 |
EQU | +0.079 |
atche | +0.074 |
Tiff | +0.070 |
aspers | +0.070 |
Neg logit contributions | |
Frazier | -0.082 |
�� | -0.077 |
VC | -0.076 |
mt | -0.076 |
han | -0.075 |
Token | School |
Token ID | 3961 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
Frazier | +0.267 |
VC | +0.248 |
�� | +0.246 |
mt | +0.244 |
han | +0.244 |
Neg logit contributions | |
ipop | -0.320 |
EQU | -0.317 |
atche | -0.303 |
aspers | -0.285 |
Expend | -0.283 |
Token | of |
Token ID | 286 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ipop | +0.178 |
EQU | +0.176 |
atche | +0.168 |
aspers | +0.159 |
Tiff | +0.158 |
Neg logit contributions | |
Frazier | -0.152 |
VC | -0.141 |
mt | -0.139 |
han | -0.139 |
�� | -0.138 |
Token | Marine |
Token ID | 11000 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
EQU | +3.605 |
ipop | +3.559 |
atche | +3.371 |
Tiff | +3.228 |
Expend | +3.219 |
Neg logit contributions | |
Frazier | -3.115 |
�� | -3.017 |
mt | -2.871 |
bnb | -2.870 |
Kh | -2.828 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ipop | +1.725 |
EQU | +1.723 |
atche | +1.620 |
Tiff | +1.521 |
aspers | +1.514 |
Neg logit contributions | |
Frazier | -1.866 |
�� | -1.756 |
VC | -1.735 |
mt | -1.728 |
han | -1.716 |
Token | Atmospheric |
Token ID | 41516 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
EQU | +2.966 |
ipop | +2.922 |
atche | +2.689 |
Expend | +2.509 |
Tiff | +2.501 |
Neg logit contributions | |
Frazier | -4.279 |
�� | -4.069 |
bnb | -3.982 |
mt | -3.957 |
VC | -3.949 |
Token | Sciences |
Token ID | 13473 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
EQU | +2.770 |
ipop | +2.620 |
Expend | +2.321 |
Tiff | +2.241 |
atche | +2.225 |
Neg logit contributions | |
Frazier | -5.641 |
�� | -5.621 |
bnb | -5.350 |
�� | -5.278 |
iven | -5.265 |
Token | ( |
Token ID | 357 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
ipop | +1.696 |
EQU | +1.682 |
atche | +1.589 |
Tiff | +1.507 |
aspers | +1.488 |
Neg logit contributions | |
Frazier | -1.658 |
�� | -1.587 |
mt | -1.535 |
bnb | -1.531 |
VC | -1.530 |
Token | So |
Token ID | 2396 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ipop | +0.027 |
EQU | +0.027 |
atche | +0.025 |
Tiff | +0.024 |
aspers | +0.023 |
Neg logit contributions | |
Frazier | -0.027 |
�� | -0.026 |
VC | -0.025 |
mt | -0.025 |
han | -0.025 |
Token | MAS |
Token ID | 31180 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ipop | +1.143 |
EQU | +1.137 |
atche | +1.076 |
aspers | +1.029 |
Tiff | +1.009 |
Neg logit contributions | |
Frazier | -1.116 |
�� | -1.065 |
mt | -1.051 |
VC | -1.034 |
bnb | -1.028 |
Token | ). |
Token ID | 737 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Frazier | +1.909 |
VC | +1.781 |
�� | +1.778 |
han | +1.760 |
mt | +1.758 |
Neg logit contributions | |
ipop | -2.059 |
EQU | -2.048 |
atche | -1.945 |
Tiff | -1.841 |
aspers | -1.825 |
Token | breaks |
Token ID | 9457 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
Frazier | +1.602 |
VC | +1.507 |
mt | +1.497 |
han | +1.494 |
bnb | +1.486 |
Neg logit contributions | |
ipop | -1.561 |
EQU | -1.545 |
atche | -1.471 |
Tiff | -1.365 |
aspers | -1.362 |
Token | all |
Token ID | 477 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
ipop | +0.032 |
EQU | +0.031 |
atche | +0.030 |
Tiff | +0.028 |
aspers | +0.028 |
Neg logit contributions | |
Frazier | -0.029 |
�� | -0.027 |
VC | -0.027 |
mt | -0.027 |
han | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ipop | +0.485 |
EQU | +0.483 |
atche | +0.457 |
Tiff | +0.430 |
aspers | +0.429 |
Neg logit contributions | |
Frazier | -0.468 |
�� | -0.438 |
VC | -0.434 |
mt | -0.432 |
han | -0.429 |
Token | time |
Token ID | 640 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Frazier | +0.191 |
�� | +0.179 |
VC | +0.177 |
mt | +0.176 |
han | +0.175 |
Neg logit contributions | |
ipop | -0.215 |
EQU | -0.214 |
atche | -0.203 |
Tiff | -0.192 |
aspers | -0.191 |
Token | time |
Token ID | 640 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
Frazier | +1.334 |
VC | +1.235 |
mt | +1.234 |
han | +1.219 |
�� | +1.219 |
Neg logit contributions | |
ipop | -1.525 |
EQU | -1.521 |
atche | -1.449 |
Tiff | -1.365 |
aspers | -1.365 |
Token | but |
Token ID | 475 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ipop | +0.449 |
EQU | +0.448 |
atche | +0.423 |
Tiff | +0.398 |
aspers | +0.398 |
Neg logit contributions | |
Frazier | -0.424 |
�� | -0.399 |
VC | -0.393 |
mt | -0.391 |
han | -0.388 |
Token | you |
Token ID | 345 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ipop | +1.015 |
EQU | +1.013 |
atche | +0.958 |
Tiff | +0.904 |
aspers | +0.900 |
Neg logit contributions | |
Frazier | -0.953 |
�� | -0.895 |
VC | -0.882 |
mt | -0.878 |
han | -0.874 |
Token | know |
Token ID | 760 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Frazier | +0.853 |
VC | +0.787 |
mt | +0.786 |
han | +0.781 |
�� | +0.777 |
Neg logit contributions | |
ipop | -1.015 |
EQU | -1.006 |
atche | -0.958 |
Tiff | -0.905 |
Expend | -0.899 |
Token | when |
Token ID | 618 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
ipop | +0.873 |
EQU | +0.870 |
atche | +0.826 |
Tiff | +0.780 |
aspers | +0.779 |
Neg logit contributions | |
Frazier | -0.740 |
�� | -0.689 |
VC | -0.683 |
mt | -0.680 |
han | -0.674 |
Token | it |
Token ID | 340 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Frazier | +0.589 |
VC | +0.548 |
mt | +0.547 |
�� | +0.540 |
han | +0.538 |
Neg logit contributions | |
ipop | -0.678 |
EQU | -0.673 |
atche | -0.644 |
aspers | -0.603 |
Tiff | -0.600 |
Token | happens |
Token ID | 4325 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Frazier | +0.859 |
VC | +0.802 |
mt | +0.801 |
han | +0.797 |
�� | +0.795 |
Neg logit contributions | |
ipop | -0.760 |
EQU | -0.758 |
atche | -0.714 |
Expend | -0.668 |
aspers | -0.666 |
Token | come |
Token ID | 1282 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
EQU | +0.599 |
ipop | +0.598 |
atche | +0.567 |
Tiff | +0.534 |
aspers | +0.534 |
Neg logit contributions | |
Frazier | -0.531 |
�� | -0.497 |
VC | -0.491 |
mt | -0.487 |
han | -0.484 |
Token | down |
Token ID | 866 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
Frazier | +0.138 |
�� | +0.130 |
VC | +0.129 |
mt | +0.129 |
han | +0.128 |
Neg logit contributions | |
ipop | -0.112 |
EQU | -0.111 |
atche | -0.105 |
aspers | -0.098 |
Tiff | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Frazier | +0.015 |
�� | +0.014 |
VC | +0.014 |
bnb | +0.014 |
mt | +0.014 |
Neg logit contributions | |
EQU | -0.014 |
ipop | -0.014 |
atche | -0.013 |
Tiff | -0.012 |
aspers | -0.012 |
Token | an |
Token ID | 281 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
EQU | +0.742 |
ipop | +0.742 |
atche | +0.701 |
Tiff | +0.663 |
aspers | +0.660 |
Neg logit contributions | |
Frazier | -0.657 |
�� | -0.618 |
VC | -0.610 |
mt | -0.604 |
bnb | -0.601 |
Token | alleg |
Token ID | 2868 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ipop | +1.061 |
EQU | +1.051 |
atche | +1.002 |
Tiff | +0.943 |
aspers | +0.938 |
Neg logit contributions | |
Frazier | -0.983 |
�� | -0.921 |
mt | -0.915 |
VC | -0.914 |
han | -0.906 |
Token | oric |
Token ID | 8146 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ipop | +0.255 |
EQU | +0.254 |
atche | +0.245 |
Tiff | +0.234 |
aspers | +0.234 |
Neg logit contributions | |
Frazier | -0.101 |
�� | -0.091 |
VC | -0.089 |
mt | -0.087 |
han | -0.086 |
Token | interpretation |
Token ID | 10794 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ipop | +0.763 |
EQU | +0.760 |
atche | +0.722 |
Tiff | +0.683 |
aspers | +0.681 |
Neg logit contributions | |
Frazier | -0.628 |
�� | -0.584 |
VC | -0.579 |
mt | -0.576 |
han | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Frazier | +0.762 |
�� | +0.705 |
VC | +0.704 |
mt | +0.702 |
han | +0.698 |
Neg logit contributions | |
ipop | -0.848 |
EQU | -0.843 |
atche | -0.802 |
aspers | -0.757 |
Tiff | -0.754 |
Token | Myth |
Token ID | 18900 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ipop | +0.801 |
EQU | +0.795 |
atche | +0.753 |
aspers | +0.706 |
Tiff | +0.704 |
Neg logit contributions | |
Frazier | -0.814 |
�� | -0.757 |
VC | -0.756 |
mt | -0.753 |
han | -0.748 |
Token | � |
Token ID | 447 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ipop | +1.440 |
EQU | +1.435 |
atche | +1.362 |
aspers | +1.281 |
Tiff | +1.279 |
Neg logit contributions | |
Frazier | -1.333 |
�� | -1.249 |
VC | -1.234 |
mt | -1.227 |
han | -1.213 |
Token | � |
Token ID | 247 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
ipop | +0.232 |
EQU | +0.232 |
atche | +0.224 |
Tiff | +0.217 |
aspers | +0.217 |
Neg logit contributions | |
Frazier | -0.044 |
VC | -0.034 |
mt | -0.033 |
�� | -0.033 |
bnb | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ipop | +0.200 |
EQU | +0.200 |
atche | +0.188 |
aspers | +0.177 |
Tiff | +0.176 |
Neg logit contributions | |
Frazier | -0.213 |
�� | -0.199 |
VC | -0.198 |
mt | -0.198 |
han | -0.196 |
Token | how |
Token ID | 703 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
Frazier | +1.153 |
VC | +1.059 |
mt | +1.052 |
han | +1.051 |
�� | +1.038 |
Neg logit contributions | |
ipop | -1.384 |
EQU | -1.363 |
atche | -1.310 |
aspers | -1.243 |
Tiff | -1.229 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Frazier | +0.429 |
VC | +0.396 |
�� | +0.394 |
mt | +0.393 |
han | +0.391 |
Neg logit contributions | |
ipop | -0.501 |
EQU | -0.497 |
atche | -0.474 |
aspers | -0.448 |
Tiff | -0.444 |
Token | were |
Token ID | 547 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
Frazier | +0.827 |
VC | +0.765 |
mt | +0.761 |
han | +0.753 |
�� | +0.752 |
Neg logit contributions | |
ipop | -0.933 |
EQU | -0.929 |
atche | -0.878 |
aspers | -0.833 |
Tiff | -0.830 |
Token | really |
Token ID | 1107 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Frazier | +0.012 |
VC | +0.011 |
mt | +0.011 |
�� | +0.011 |
han | +0.011 |
Neg logit contributions | |
ipop | -0.014 |
EQU | -0.014 |
atche | -0.013 |
aspers | -0.012 |
Tiff | -0.012 |
Token | tricky |
Token ID | 17198 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
ipop | +0.539 |
EQU | +0.535 |
atche | +0.509 |
aspers | +0.483 |
Tiff | +0.477 |
Neg logit contributions | |
Frazier | -0.473 |
VC | -0.438 |
�� | -0.435 |
mt | -0.435 |
han | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ipop | +0.381 |
EQU | +0.379 |
atche | +0.360 |
aspers | +0.339 |
Tiff | +0.339 |
Neg logit contributions | |
Frazier | -0.346 |
VC | -0.320 |
�� | -0.320 |
mt | -0.319 |
han | -0.316 |
Token | If |
Token ID | 1002 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
EQU | +1.457 |
ipop | +1.447 |
atche | +1.362 |
Tiff | +1.295 |
Expend | +1.280 |
Neg logit contributions | |
Frazier | -1.505 |
�� | -1.440 |
VC | -1.400 |
mt | -1.399 |
bnb | -1.391 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Frazier | +0.095 |
�� | +0.088 |
VC | +0.088 |
mt | +0.088 |
han | +0.087 |
Neg logit contributions | |
ipop | -0.100 |
EQU | -0.100 |
atche | -0.094 |
aspers | -0.089 |
Tiff | -0.088 |
Token | go |
Token ID | 467 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ipop | +1.633 |
EQU | +1.630 |
atche | +1.545 |
Tiff | +1.457 |
aspers | +1.453 |
Neg logit contributions | |
Frazier | -1.428 |
�� | -1.360 |
VC | -1.322 |
mt | -1.317 |
han | -1.308 |
Token | back |
Token ID | 736 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
ipop | +0.979 |
EQU | +0.975 |
atche | +0.923 |
Tiff | +0.867 |
aspers | +0.862 |
Neg logit contributions | |
Frazier | -0.958 |
�� | -0.904 |
VC | -0.890 |
mt | -0.886 |
han | -0.880 |
Token | , |
Token ID | 11 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
ipop | +0.568 |
EQU | +0.567 |
atche | +0.532 |
Expend | +0.502 |
Tiff | +0.502 |
Neg logit contributions | |
Frazier | -0.601 |
�� | -0.565 |
bnb | -0.558 |
VC | -0.555 |
mt | -0.550 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Frazier | +0.455 |
�� | +0.414 |
VC | +0.411 |
mt | +0.409 |
han | +0.405 |
Neg logit contributions | |
ipop | -0.790 |
EQU | -0.787 |
atche | -0.753 |
Tiff | -0.718 |
aspers | -0.717 |
Token | fighters |
Token ID | 8486 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
EQU | +1.455 |
ipop | +1.450 |
atche | +1.366 |
Tiff | +1.306 |
aspers | +1.299 |
Neg logit contributions | |
Frazier | -1.197 |
�� | -1.130 |
bnb | -1.105 |
VC | -1.091 |
mt | -1.088 |
Token | to |
Token ID | 284 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Frazier | +0.486 |
VC | +0.450 |
mt | +0.449 |
han | +0.447 |
�� | +0.447 |
Neg logit contributions | |
ipop | -0.512 |
EQU | -0.510 |
atche | -0.484 |
aspers | -0.456 |
Tiff | -0.455 |
Token | southern |
Token ID | 8372 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Frazier | +0.073 |
�� | +0.067 |
VC | +0.067 |
mt | +0.066 |
han | +0.066 |
Neg logit contributions | |
ipop | -0.089 |
EQU | -0.089 |
atche | -0.085 |
aspers | -0.080 |
Tiff | -0.079 |
Token | Aleppo |
Token ID | 18593 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
ipop | +1.108 |
EQU | +1.105 |
atche | +1.047 |
Tiff | +0.990 |
aspers | +0.986 |
Neg logit contributions | |
Frazier | -0.959 |
�� | -0.896 |
VC | -0.886 |
mt | -0.882 |
han | -0.875 |
Token | to |
Token ID | 284 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
ipop | +0.458 |
EQU | +0.457 |
atche | +0.432 |
Tiff | +0.406 |
aspers | +0.405 |
Neg logit contributions | |
Frazier | -0.441 |
�� | -0.415 |
VC | -0.409 |
mt | -0.407 |
han | -0.403 |
Token | reinforce |
Token ID | 19594 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Frazier | +0.556 |
VC | +0.512 |
�� | +0.512 |
mt | +0.509 |
han | +0.504 |
Neg logit contributions | |
ipop | -0.722 |
EQU | -0.718 |
atche | -0.687 |
Tiff | -0.647 |
aspers | -0.647 |
Token | positions |
Token ID | 6116 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ipop | +0.848 |
EQU | +0.847 |
atche | +0.797 |
Tiff | +0.756 |
aspers | +0.752 |
Neg logit contributions | |
Frazier | -0.799 |
�� | -0.752 |
VC | -0.740 |
mt | -0.738 |
bnb | -0.737 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Frazier | +1.181 |
VC | +1.089 |
mt | +1.075 |
�� | +1.073 |
han | +1.068 |
Neg logit contributions | |
ipop | -1.507 |
EQU | -1.499 |
atche | -1.436 |
Tiff | -1.354 |
aspers | -1.349 |
Token | army |
Token ID | 5428 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Frazier | +1.330 |
VC | +1.217 |
�� | +1.200 |
mt | +1.200 |
Kh | +1.183 |
Neg logit contributions | |
ipop | -2.269 |
EQU | -2.253 |
atche | -2.172 |
aspers | -2.067 |
Tiff | -2.061 |
Token | . |
Token ID | 13 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
EQU | +2.514 |
ipop | +2.490 |
atche | +2.371 |
Tiff | +2.247 |
Expend | +2.224 |
Neg logit contributions | |
Frazier | -2.430 |
�� | -2.316 |
bnb | -2.261 |
VC | -2.249 |
mt | -2.246 |
Token | It |
Token ID | 632 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ipop | +0.444 |
EQU | +0.438 |
atche | +0.416 |
aspers | +0.390 |
Tiff | +0.387 |
Neg logit contributions | |
Frazier | -0.460 |
VC | -0.428 |
�� | -0.426 |
mt | -0.425 |
han | -0.421 |
Token | stood |
Token ID | 6204 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
Frazier | +1.991 |
mt | +1.846 |
VC | +1.839 |
han | +1.824 |
lyn | +1.823 |
Neg logit contributions | |
ipop | -2.092 |
EQU | -2.050 |
atche | -1.941 |
aspers | -1.841 |
Tiff | -1.825 |
Token | on |
Token ID | 319 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Frazier | +0.288 |
�� | +0.268 |
VC | +0.266 |
mt | +0.265 |
han | +0.263 |
Neg logit contributions | |
ipop | -0.317 |
EQU | -0.315 |
atche | -0.299 |
aspers | -0.282 |
Tiff | -0.282 |
Token | four |
Token ID | 1440 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
EQU | +1.081 |
ipop | +1.080 |
atche | +1.022 |
Tiff | +0.967 |
aspers | +0.958 |
Neg logit contributions | |
Frazier | -0.996 |
�� | -0.937 |
VC | -0.922 |
mt | -0.917 |
han | -0.914 |
Token | legs |
Token ID | 7405 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Frazier | +0.767 |
VC | +0.714 |
mt | +0.713 |
�� | +0.710 |
han | +0.698 |
Neg logit contributions | |
ipop | -0.922 |
EQU | -0.907 |
atche | -0.866 |
aspers | -0.820 |
Tiff | -0.816 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ipop | +1.101 |
EQU | +1.099 |
atche | +1.038 |
Tiff | +0.978 |
aspers | +0.971 |
Neg logit contributions | |
Frazier | -1.068 |
�� | -1.008 |
VC | -0.991 |
mt | -0.987 |
han | -0.980 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
EQU | +0.979 |
ipop | +0.977 |
atche | +0.926 |
Tiff | +0.878 |
aspers | +0.871 |
Neg logit contributions | |
Frazier | -0.872 |
�� | -0.824 |
VC | -0.808 |
mt | -0.803 |
bnb | -0.802 |
Token | had |
Token ID | 550 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ipop | +0.151 |
EQU | +0.151 |
atche | +0.143 |
Tiff | +0.135 |
aspers | +0.135 |
Neg logit contributions | |
Frazier | -0.135 |
�� | -0.126 |
VC | -0.124 |
mt | -0.124 |
han | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
Frazier | +0.843 |
�� | +0.777 |
VC | +0.775 |
mt | +0.772 |
han | +0.763 |
Neg logit contributions | |
ipop | -1.062 |
EQU | -1.054 |
atche | -1.005 |
Tiff | -0.947 |
aspers | -0.947 |
Token | figure |
Token ID | 3785 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Frazier | +0.438 |
�� | +0.406 |
VC | +0.405 |
mt | +0.403 |
han | +0.398 |
Neg logit contributions | |
ipop | -0.513 |
EQU | -0.509 |
atche | -0.484 |
aspers | -0.457 |
Tiff | -0.456 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
EQU | +1.770 |
ipop | +1.769 |
atche | +1.664 |
Tiff | +1.585 |
aspers | +1.555 |
Neg logit contributions | |
Frazier | -1.880 |
�� | -1.793 |
VC | -1.751 |
mt | -1.745 |
han | -1.742 |
Token | 199 |
Token ID | 1594 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
EQU | +1.129 |
ipop | +1.129 |
atche | +1.065 |
Tiff | +1.006 |
aspers | +1.000 |
Neg logit contributions | |
Frazier | -1.083 |
�� | -1.019 |
VC | -1.001 |
mt | -0.997 |
han | -0.993 |
Token | buildings |
Token ID | 6832 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
EQU | +2.355 |
ipop | +2.338 |
atche | +2.204 |
Tiff | +2.090 |
Expend | +2.066 |
Neg logit contributions | |
Frazier | -2.313 |
�� | -2.180 |
VC | -2.124 |
mt | -2.115 |
bnb | -2.105 |
Token | that |
Token ID | 326 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
EQU | +1.314 |
ipop | +1.313 |
atche | +1.241 |
Tiff | +1.174 |
aspers | +1.165 |
Neg logit contributions | |
Frazier | -1.215 |
�� | -1.151 |
VC | -1.124 |
mt | -1.118 |
bnb | -1.113 |
Token | have |
Token ID | 423 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
EQU | +0.290 |
ipop | +0.290 |
atche | +0.274 |
Tiff | +0.259 |
aspers | +0.258 |
Neg logit contributions | |
Frazier | -0.272 |
�� | -0.256 |
VC | -0.252 |
mt | -0.251 |
han | -0.250 |
Token | failed |
Token ID | 4054 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
EQU | +0.782 |
ipop | +0.780 |
atche | +0.739 |
Tiff | +0.702 |
aspers | +0.695 |
Neg logit contributions | |
Frazier | -0.682 |
�� | -0.643 |
VC | -0.628 |
han | -0.625 |
mt | -0.625 |
Token | fire |
Token ID | 2046 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Frazier | +1.176 |
VC | +1.093 |
mt | +1.089 |
�� | +1.085 |
han | +1.071 |
Neg logit contributions | |
ipop | -1.464 |
EQU | -1.449 |
atche | -1.385 |
aspers | -1.313 |
Tiff | -1.303 |
Token | safety |
Token ID | 3747 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Frazier | +1.925 |
VC | +1.788 |
mt | +1.782 |
�� | +1.778 |
han | +1.747 |
Neg logit contributions | |
ipop | -2.999 |
EQU | -2.989 |
atche | -2.863 |
Tiff | -2.710 |
aspers | -2.706 |
Token | testing |
Token ID | 4856 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Frazier | +0.800 |
VC | +0.740 |
mt | +0.737 |
�� | +0.728 |
han | +0.723 |
Neg logit contributions | |
ipop | -1.157 |
EQU | -1.146 |
atche | -1.103 |
aspers | -1.043 |
Tiff | -1.041 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Frazier | +2.985 |
mt | +2.761 |
VC | +2.755 |
han | +2.734 |
bnb | +2.696 |
Neg logit contributions | |
ipop | -3.710 |
EQU | -3.641 |
atche | -3.529 |
Tiff | -3.324 |
aspers | -3.324 |
Token | But |
Token ID | 887 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Frazier | +0.453 |
VC | +0.422 |
mt | +0.419 |
�� | +0.416 |
han | +0.415 |
Neg logit contributions | |
ipop | -0.427 |
EQU | -0.419 |
atche | -0.399 |
aspers | -0.373 |
Tiff | -0.369 |
Token | 't |
Token ID | 470 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ipop | +0.779 |
EQU | +0.775 |
atche | +0.740 |
Tiff | +0.703 |
aspers | +0.702 |
Neg logit contributions | |
Frazier | -0.535 |
VC | -0.489 |
�� | -0.487 |
mt | -0.486 |
han | -0.482 |
Token | normally |
Token ID | 7685 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
EQU | +0.758 |
ipop | +0.757 |
atche | +0.712 |
aspers | +0.675 |
Tiff | +0.674 |
Neg logit contributions | |
Frazier | -0.640 |
�� | -0.606 |
VC | -0.587 |
mt | -0.585 |
bnb | -0.584 |
Token | see |
Token ID | 766 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ipop | +0.117 |
EQU | +0.117 |
atche | +0.111 |
Tiff | +0.105 |
aspers | +0.105 |
Neg logit contributions | |
Frazier | -0.096 |
�� | -0.089 |
VC | -0.088 |
mt | -0.088 |
han | -0.087 |
Token | in |
Token ID | 287 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
Frazier | +0.478 |
�� | +0.446 |
VC | +0.443 |
mt | +0.441 |
han | +0.438 |
Neg logit contributions | |
ipop | -0.513 |
EQU | -0.511 |
atche | -0.484 |
Tiff | -0.456 |
aspers | -0.455 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Frazier | +0.355 |
�� | +0.333 |
VC | +0.329 |
mt | +0.328 |
han | +0.326 |
Neg logit contributions | |
ipop | -0.375 |
EQU | -0.374 |
atche | -0.353 |
Tiff | -0.333 |
aspers | -0.332 |
Token | youngster |
Token ID | 40944 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Frazier | +0.742 |
�� | +0.693 |
VC | +0.688 |
mt | +0.685 |
han | +0.679 |
Neg logit contributions | |
ipop | -0.779 |
EQU | -0.777 |
atche | -0.735 |
Tiff | -0.692 |
aspers | -0.691 |
Token | ," |
Token ID | 553 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Frazier | +1.692 |
VC | +1.574 |
mt | +1.562 |
�� | +1.549 |
han | +1.547 |
Neg logit contributions | |
ipop | -1.966 |
EQU | -1.962 |
atche | -1.877 |
aspers | -1.764 |
Tiff | -1.755 |
Token | says |
Token ID | 1139 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
Frazier | +1.354 |
VC | +1.264 |
mt | +1.256 |
�� | +1.250 |
han | +1.250 |
Neg logit contributions | |
ipop | -1.167 |
EQU | -1.156 |
atche | -1.093 |
aspers | -1.020 |
Tiff | -1.013 |
Token | Kevin |
Token ID | 7939 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
Frazier | +0.339 |
�� | +0.316 |
VC | +0.310 |
mt | +0.309 |
bnb | +0.306 |
Neg logit contributions | |
ipop | -0.484 |
EQU | -0.483 |
atche | -0.460 |
Tiff | -0.438 |
aspers | -0.435 |
Token | O |
Token ID | 440 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ipop | +0.243 |
EQU | +0.242 |
atche | +0.229 |
Tiff | +0.216 |
aspers | +0.216 |
Neg logit contributions | |
Frazier | -0.225 |
�� | -0.211 |
VC | -0.209 |
mt | -0.208 |
han | -0.206 |
Token | ' |
Token ID | 6 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Frazier | +1.250 |
han | +1.148 |
VC | +1.143 |
mt | +1.139 |
�� | +1.138 |
Neg logit contributions | |
EQU | -1.550 |
ipop | -1.547 |
atche | -1.470 |
Tiff | -1.392 |
aspers | -1.378 |
Token | Watts |
Token ID | 27555 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
Frazier | +0.813 |
VC | +0.752 |
�� | +0.748 |
mt | +0.745 |
han | +0.744 |
Neg logit contributions | |
ipop | -0.832 |
EQU | -0.825 |
atche | -0.778 |
aspers | -0.735 |
Tiff | -0.727 |
Token | , |
Token ID | 11 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
Frazier | +0.375 |
VC | +0.346 |
�� | +0.344 |
mt | +0.344 |
han | +0.343 |
Neg logit contributions | |
ipop | -0.414 |
EQU | -0.413 |
atche | -0.390 |
aspers | -0.370 |
Tiff | -0.368 |
Token | is |
Token ID | 318 |
Feature activation | +7.16e-03 |
Pos logit contributions | |
Frazier | +0.466 |
VC | +0.432 |
�� | +0.431 |
mt | +0.430 |
han | +0.426 |
Neg logit contributions | |
ipop | -0.510 |
EQU | -0.506 |
atche | -0.481 |
aspers | -0.453 |
Tiff | -0.451 |
Token | being |
Token ID | 852 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ipop | +0.051 |
EQU | +0.051 |
atche | +0.049 |
aspers | +0.046 |
Tiff | +0.045 |
Neg logit contributions | |
Frazier | -0.046 |
VC | -0.043 |
mt | -0.043 |
�� | -0.042 |
han | -0.042 |
Token | called |
Token ID | 1444 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
EQU | +1.257 |
ipop | +1.251 |
atche | +1.187 |
Tiff | +1.123 |
aspers | +1.116 |
Neg logit contributions | |
Frazier | -1.101 |
�� | -1.040 |
VC | -1.013 |
mt | -1.012 |
han | -1.003 |
Token | absurd |
Token ID | 12986 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
EQU | +1.572 |
ipop | +1.570 |
atche | +1.485 |
Tiff | +1.400 |
aspers | +1.396 |
Neg logit contributions | |
Frazier | -1.457 |
�� | -1.370 |
VC | -1.349 |
mt | -1.343 |
han | -1.332 |
Token | and |
Token ID | 290 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Frazier | +1.388 |
VC | +1.281 |
�� | +1.278 |
mt | +1.275 |
han | +1.268 |
Neg logit contributions | |
ipop | -1.668 |
EQU | -1.658 |
atche | -1.577 |
aspers | -1.489 |
Tiff | -1.485 |
Token | fear |
Token ID | 3252 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
ipop | +0.210 |
EQU | +0.208 |
atche | +0.197 |
aspers | +0.185 |
Tiff | +0.184 |
Neg logit contributions | |
Frazier | -0.210 |
VC | -0.196 |
�� | -0.195 |
mt | -0.195 |
han | -0.193 |
Token | m |
Token ID | 285 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
EQU | +0.371 |
ipop | +0.370 |
atche | +0.354 |
aspers | +0.336 |
Tiff | +0.336 |
Neg logit contributions | |
Frazier | -0.237 |
�� | -0.220 |
VC | -0.216 |
mt | -0.214 |
han | -0.211 |
Token | ong |
Token ID | 506 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Frazier | +0.282 |
�� | +0.258 |
VC | +0.258 |
mt | +0.256 |
han | +0.255 |
Neg logit contributions | |
ipop | -0.421 |
EQU | -0.419 |
atche | -0.399 |
Tiff | -0.381 |
aspers | -0.378 |
Token | ering |
Token ID | 1586 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Frazier | +0.671 |
VC | +0.580 |
�� | +0.579 |
mt | +0.575 |
han | +0.574 |
Neg logit contributions | |
ipop | -1.885 |
EQU | -1.876 |
atche | -1.800 |
Tiff | -1.732 |
aspers | -1.731 |
Token | - |
Token ID | 12 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ipop | +0.605 |
EQU | +0.602 |
atche | +0.571 |
Tiff | +0.531 |
aspers | +0.527 |
Neg logit contributions | |
Frazier | -0.661 |
�� | -0.622 |
VC | -0.608 |
mt | -0.607 |
bnb | -0.606 |
Token | 10 |
Token ID | 940 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ipop | +1.594 |
EQU | +1.580 |
atche | +1.511 |
Tiff | +1.419 |
aspers | +1.418 |
Neg logit contributions | |
Frazier | -1.321 |
�� | -1.243 |
VC | -1.204 |
mt | -1.203 |
han | -1.184 |
Token | start |
Token ID | 923 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ipop | +3.967 |
EQU | +3.911 |
atche | +3.716 |
Tiff | +3.492 |
aspers | +3.441 |
Neg logit contributions | |
Frazier | -3.617 |
�� | -3.466 |
bnb | -3.354 |
han | -3.353 |
iven | -3.327 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
ipop | +1.422 |
EQU | +1.413 |
atche | +1.333 |
Tiff | +1.258 |
aspers | +1.244 |
Neg logit contributions | |
Frazier | -1.353 |
�� | -1.287 |
VC | -1.257 |
mt | -1.251 |
han | -1.246 |
Token |
|
Token ID | 198 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
Frazier | +0.026 |
VC | +0.024 |
�� | +0.024 |
mt | +0.024 |
han | +0.023 |
Neg logit contributions | |
ipop | -0.025 |
EQU | -0.025 |
atche | -0.024 |
aspers | -0.022 |
Tiff | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Frazier | +0.574 |
VC | +0.540 |
mt | +0.534 |
han | +0.532 |
Kh | +0.530 |
Neg logit contributions | |
ipop | -0.585 |
EQU | -0.575 |
atche | -0.549 |
aspers | -0.520 |
Tiff | -0.513 |
Token | " |
Token ID | 1 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Frazier | +1.286 |
Kh | +1.202 |
�� | +1.196 |
VC | +1.195 |
han | +1.193 |
Neg logit contributions | |
ipop | -1.240 |
EQU | -1.238 |
atche | -1.156 |
Tiff | -1.100 |
Expend | -1.089 |
Token | Luckily |
Token ID | 42332 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
EQU | +0.487 |
ipop | +0.487 |
atche | +0.458 |
Tiff | +0.431 |
aspers | +0.429 |
Neg logit contributions | |
Frazier | -0.527 |
�� | -0.500 |
mt | -0.493 |
VC | -0.492 |
bnb | -0.488 |
Token | nothing |
Token ID | 2147 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
Frazier | +0.988 |
VC | +0.914 |
�� | +0.913 |
mt | +0.906 |
han | +0.901 |
Neg logit contributions | |
ipop | -1.083 |
EQU | -1.079 |
atche | -1.024 |
aspers | -0.966 |
Tiff | -0.960 |
Token | happened |
Token ID | 3022 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Frazier | +0.406 |
VC | +0.378 |
mt | +0.373 |
�� | +0.370 |
han | +0.367 |
Neg logit contributions | |
ipop | -0.438 |
EQU | -0.436 |
atche | -0.413 |
aspers | -0.394 |
Expend | -0.389 |
Token | [ |
Token ID | 685 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
ipop | +0.381 |
EQU | +0.380 |
atche | +0.360 |
aspers | +0.340 |
Tiff | +0.339 |
Neg logit contributions | |
Frazier | -0.346 |
�� | -0.321 |
VC | -0.320 |
mt | -0.319 |
han | -0.316 |
Token | at |
Token ID | 379 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ipop | +0.212 |
EQU | +0.212 |
atche | +0.200 |
Tiff | +0.188 |
aspers | +0.187 |
Neg logit contributions | |
Frazier | -0.207 |
�� | -0.195 |
VC | -0.192 |
mt | -0.192 |
han | -0.190 |
Token | everyone |
Token ID | 2506 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
ipop | +0.576 |
EQU | +0.575 |
atche | +0.544 |
Tiff | +0.512 |
aspers | +0.511 |
Neg logit contributions | |
Frazier | -0.544 |
�� | -0.509 |
VC | -0.504 |
mt | -0.502 |
han | -0.498 |
Token | ! |
Token ID | 0 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Frazier | +0.308 |
VC | +0.285 |
�� | +0.285 |
mt | +0.283 |
han | +0.282 |
Neg logit contributions | |
ipop | -0.345 |
EQU | -0.342 |
atche | -0.326 |
aspers | -0.309 |
Tiff | -0.306 |
Token | H |
Token ID | 367 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Frazier | +0.717 |
VC | +0.667 |
mt | +0.661 |
�� | +0.659 |
han | +0.656 |
Neg logit contributions | |
ipop | -0.708 |
EQU | -0.695 |
atche | -0.664 |
aspers | -0.626 |
Tiff | -0.616 |
Token | ah |
Token ID | 993 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Frazier | +0.134 |
�� | +0.125 |
VC | +0.124 |
mt | +0.124 |
han | +0.123 |
Neg logit contributions | |
ipop | -0.134 |
EQU | -0.134 |
atche | -0.126 |
Tiff | -0.119 |
aspers | -0.118 |
Token | aha |
Token ID | 12236 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
Frazier | +0.283 |
�� | +0.266 |
VC | +0.263 |
mt | +0.261 |
bnb | +0.259 |
Neg logit contributions | |
ipop | -0.273 |
EQU | -0.271 |
atche | -0.257 |
Tiff | -0.241 |
aspers | -0.240 |
Token | ! |
Token ID | 0 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Frazier | +0.266 |
�� | +0.248 |
VC | +0.246 |
mt | +0.245 |
han | +0.244 |
Neg logit contributions | |
ipop | -0.295 |
EQU | -0.294 |
atche | -0.278 |
aspers | -0.262 |
Tiff | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
Frazier | +1.596 |
VC | +1.483 |
mt | +1.466 |
han | +1.450 |
�� | +1.443 |
Neg logit contributions | |
ipop | -1.602 |
EQU | -1.558 |
atche | -1.507 |
aspers | -1.424 |
Tiff | -1.381 |
Token |
|
Token ID | 198 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
Frazier | +0.408 |
VC | +0.383 |
mt | +0.380 |
han | +0.378 |
Kh | +0.377 |
Neg logit contributions | |
ipop | -0.396 |
EQU | -0.389 |
atche | -0.372 |
aspers | -0.350 |
Tiff | -0.346 |
Token | With |
Token ID | 3152 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
ipop | +0.653 |
EQU | +0.651 |
atche | +0.615 |
Tiff | +0.577 |
aspers | +0.576 |
Neg logit contributions | |
Frazier | -0.671 |
�� | -0.630 |
VC | -0.624 |
mt | -0.621 |
han | -0.616 |
Token | all |
Token ID | 477 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
EQU | +0.668 |
ipop | +0.668 |
atche | +0.632 |
Tiff | +0.596 |
aspers | +0.594 |
Neg logit contributions | |
Frazier | -0.623 |
�� | -0.584 |
VC | -0.577 |
mt | -0.575 |
han | -0.571 |
Token | oub |
Token ID | 12944 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Frazier | +1.316 |
han | +1.255 |
bnb | +1.236 |
VC | +1.204 |
Kh | +1.202 |
Neg logit contributions | |
EQU | -1.386 |
ipop | -1.330 |
atche | -1.237 |
Tiff | -1.210 |
Expend | -1.199 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Frazier | +1.608 |
�� | +1.502 |
VC | +1.500 |
mt | +1.498 |
han | +1.485 |
Neg logit contributions | |
ipop | -1.430 |
EQU | -1.427 |
atche | -1.342 |
aspers | -1.264 |
Tiff | -1.255 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Frazier | +2.243 |
VC | +2.102 |
mt | +2.070 |
han | +2.037 |
Kh | +2.022 |
Neg logit contributions | |
ipop | -2.311 |
EQU | -2.276 |
atche | -2.186 |
aspers | -2.073 |
Expend | -1.999 |
Token | Parsons |
Token ID | 35925 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ipop | +0.692 |
EQU | +0.688 |
atche | +0.636 |
aspers | +0.579 |
Tiff | +0.576 |
Neg logit contributions | |
Frazier | -1.231 |
VC | -1.161 |
mt | -1.155 |
�� | -1.153 |
han | -1.150 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
EQU | +1.723 |
ipop | +1.715 |
atche | +1.606 |
Tiff | +1.509 |
Expend | +1.489 |
Neg logit contributions | |
Frazier | -2.133 |
�� | -2.068 |
VC | -1.987 |
mt | -1.986 |
bnb | -1.985 |
Token |
|
Token ID | 198 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ipop | +0.876 |
EQU | +0.870 |
atche | +0.821 |
aspers | +0.767 |
Tiff | +0.766 |
Neg logit contributions | |
Frazier | -0.998 |
VC | -0.933 |
mt | -0.929 |
�� | -0.925 |
han | -0.923 |
Token | 2011 |
Token ID | 9804 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
Frazier | +2.857 |
han | +2.717 |
Kh | +2.700 |
VC | +2.634 |
mt | +2.595 |
Neg logit contributions | |
EQU | -5.108 |
ipop | -5.099 |
atche | -4.872 |
Tiff | -4.691 |
aspers | -4.630 |
Token | Alec |
Token ID | 38285 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Frazier | +0.635 |
VC | +0.591 |
mt | +0.584 |
han | +0.578 |
�� | +0.575 |
Neg logit contributions | |
ipop | -0.664 |
EQU | -0.659 |
atche | -0.628 |
aspers | -0.593 |
Expend | -0.578 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ipop | +0.823 |
EQU | +0.820 |
atche | +0.770 |
Tiff | +0.721 |
aspers | +0.718 |
Neg logit contributions | |
Frazier | -0.975 |
�� | -0.922 |
VC | -0.911 |
mt | -0.909 |
han | -0.902 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
ipop | +1.035 |
EQU | +1.031 |
atche | +0.969 |
Tiff | +0.906 |
aspers | +0.903 |
Neg logit contributions | |
Frazier | -1.218 |
�� | -1.148 |
VC | -1.138 |
mt | -1.134 |
han | -1.126 |
Token |
|
Token ID | 198 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Frazier | +0.572 |
VC | +0.538 |
mt | +0.533 |
han | +0.530 |
Kh | +0.527 |
Neg logit contributions | |
ipop | -0.572 |
EQU | -0.561 |
atche | -0.538 |
aspers | -0.507 |
Tiff | -0.499 |
Token | lot |
Token ID | 1256 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
ipop | +0.614 |
EQU | +0.612 |
atche | +0.582 |
Tiff | +0.552 |
aspers | +0.550 |
Neg logit contributions | |
Frazier | -0.463 |
�� | -0.429 |
VC | -0.423 |
mt | -0.422 |
han | -0.418 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ipop | +0.218 |
EQU | +0.218 |
atche | +0.206 |
Tiff | +0.194 |
aspers | +0.193 |
Neg logit contributions | |
Frazier | -0.205 |
�� | -0.192 |
VC | -0.190 |
mt | -0.189 |
han | -0.188 |
Token | issues |
Token ID | 2428 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Frazier | +0.979 |
VC | +0.919 |
mt | +0.900 |
han | +0.888 |
�� | +0.887 |
Neg logit contributions | |
ipop | -1.143 |
EQU | -1.129 |
atche | -1.086 |
aspers | -1.027 |
Tiff | -1.016 |
Token | fall |
Token ID | 2121 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Frazier | +0.939 |
VC | +0.875 |
mt | +0.863 |
�� | +0.862 |
han | +0.857 |
Neg logit contributions | |
ipop | -1.063 |
EQU | -1.056 |
atche | -1.003 |
aspers | -0.946 |
Tiff | -0.942 |
Token | into |
Token ID | 656 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Frazier | +2.402 |
VC | +2.229 |
mt | +2.224 |
han | +2.194 |
�� | +2.188 |
Neg logit contributions | |
ipop | -2.889 |
EQU | -2.876 |
atche | -2.741 |
aspers | -2.634 |
Expend | -2.597 |
Token | HR |
Token ID | 15172 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Frazier | +2.277 |
VC | +2.138 |
mt | +2.098 |
han | +2.087 |
�� | +2.087 |
Neg logit contributions | |
ipop | -2.812 |
EQU | -2.770 |
atche | -2.669 |
aspers | -2.542 |
Tiff | -2.510 |
Token | � |
Token ID | 447 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Frazier | +3.441 |
VC | +3.212 |
han | +3.210 |
bnb | +3.181 |
mt | +3.171 |
Neg logit contributions | |
ipop | -3.999 |
EQU | -3.955 |
atche | -3.762 |
aspers | -3.580 |
Tiff | -3.575 |
Token | � |
Token ID | 247 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Frazier | +0.274 |
�� | +0.220 |
VC | +0.193 |
han | +0.186 |
mt | +0.178 |
Neg logit contributions | |
ipop | -2.548 |
EQU | -2.535 |
atche | -2.459 |
Tiff | -2.378 |
aspers | -2.372 |
Token | s |
Token ID | 82 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Frazier | +0.878 |
�� | +0.824 |
VC | +0.819 |
mt | +0.816 |
han | +0.813 |
Neg logit contributions | |
ipop | -0.837 |
EQU | -0.833 |
atche | -0.787 |
Tiff | -0.738 |
aspers | -0.737 |
Token | lap |
Token ID | 14779 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Frazier | +2.900 |
VC | +2.760 |
mt | +2.741 |
han | +2.710 |
�� | +2.705 |
Neg logit contributions | |
ipop | -3.415 |
EQU | -3.345 |
atche | -3.225 |
aspers | -3.115 |
Tiff | -3.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Frazier | +1.520 |
VC | +1.406 |
�� | +1.400 |
bnb | +1.395 |
han | +1.393 |
Neg logit contributions | |
EQU | -1.771 |
ipop | -1.760 |
atche | -1.663 |
Expend | -1.589 |
aspers | -1.586 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Frazier | +2.272 |
VC | +2.147 |
han | +2.076 |
mt | +2.066 |
Kh | +2.052 |
Neg logit contributions | |
EQU | -2.867 |
ipop | -2.847 |
atche | -2.701 |
aspers | -2.642 |
Tiff | -2.571 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Frazier | +1.100 |
�� | +1.036 |
VC | +1.026 |
mt | +1.023 |
han | +1.016 |
Neg logit contributions | |
ipop | -0.937 |
EQU | -0.934 |
atche | -0.878 |
Tiff | -0.821 |
aspers | -0.816 |
Token | ). |
Token ID | 737 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Frazier | +0.654 |
�� | +0.613 |
mt | +0.604 |
VC | +0.601 |
han | +0.596 |
Neg logit contributions | |
ipop | -0.717 |
EQU | -0.716 |
atche | -0.677 |
Tiff | -0.642 |
aspers | -0.635 |
Token |
|
Token ID | 198 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Frazier | +2.000 |
VC | +1.873 |
mt | +1.851 |
�� | +1.845 |
han | +1.839 |
Neg logit contributions | |
ipop | -1.848 |
EQU | -1.825 |
atche | -1.727 |
aspers | -1.654 |
Tiff | -1.610 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Frazier | +2.932 |
VC | +2.801 |
han | +2.779 |
Kh | +2.740 |
mt | +2.732 |
Neg logit contributions | |
ipop | -3.671 |
EQU | -3.613 |
atche | -3.471 |
aspers | -3.346 |
therap | -3.292 |
Token | You |
Token ID | 1639 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Frazier | +3.540 |
Kh | +3.457 |
han | +3.429 |
VC | +3.231 |
lyn | +3.229 |
Neg logit contributions | |
EQU | -4.322 |
ipop | -4.183 |
atche | -4.100 |
Tiff | -3.962 |
aspers | -3.885 |
Token | can |
Token ID | 460 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Frazier | +2.796 |
han | +2.593 |
lyn | +2.581 |
VC | +2.577 |
mt | +2.540 |
Neg logit contributions | |
EQU | -4.649 |
ipop | -4.362 |
atche | -4.358 |
Tiff | -4.165 |
aspers | -4.104 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Frazier | +3.227 |
VC | +2.982 |
lyn | +2.917 |
Warren | +2.894 |
mt | +2.865 |
Neg logit contributions | |
ipop | -4.908 |
EQU | -4.767 |
aspers | -4.698 |
atche | -4.670 |
soever | -4.550 |
Token | An |
Token ID | 1052 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Frazier | +2.124 |
VC | +2.047 |
han | +2.036 |
mt | +1.983 |
bnb | +1.968 |
Neg logit contributions | |
ipop | -1.141 |
EQU | -1.086 |
atche | -1.019 |
aspers | -0.955 |
Tiff | -0.892 |
Token | Enemy |
Token ID | 21785 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Frazier | +2.283 |
VC | +2.164 |
han | +2.162 |
iven | +2.137 |
Kh | +2.128 |
Neg logit contributions | |
ipop | -1.642 |
EQU | -1.602 |
atche | -1.517 |
aspers | -1.394 |
Tiff | -1.394 |
Token | of |
Token ID | 286 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
Frazier | +1.656 |
VC | +1.529 |
han | +1.499 |
mt | +1.499 |
bnb | +1.497 |
Neg logit contributions | |
ipop | -2.058 |
EQU | -2.026 |
atche | -1.963 |
Tiff | -1.847 |
aspers | -1.818 |
Token | M |
Token ID | 337 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Frazier | +0.602 |
�� | +0.560 |
VC | +0.559 |
mt | +0.558 |
han | +0.550 |
Neg logit contributions | |
ipop | -0.681 |
EQU | -0.676 |
atche | -0.645 |
aspers | -0.608 |
Tiff | -0.605 |
Token | - |
Token ID | 12 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ipop | +1.153 |
EQU | +1.150 |
atche | +1.086 |
aspers | +1.021 |
Tiff | +1.019 |
Neg logit contributions | |
Frazier | -1.117 |
�� | -1.041 |
VC | -1.034 |
mt | -1.028 |
han | -1.021 |
Token | Sport |
Token ID | 42576 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Frazier | +0.035 |
�� | +0.030 |
VC | +0.029 |
mt | +0.029 |
han | +0.029 |
Neg logit contributions | |
ipop | -0.114 |
EQU | -0.114 |
atche | -0.110 |
Tiff | -0.106 |
aspers | -0.106 |
Token | Ford |
Token ID | 8092 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Frazier | +0.152 |
�� | +0.142 |
VC | +0.140 |
mt | +0.140 |
han | +0.139 |
Neg logit contributions | |
ipop | -0.169 |
EQU | -0.169 |
atche | -0.160 |
Tiff | -0.151 |
aspers | -0.151 |
Token | Fiesta |
Token ID | 49839 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
Frazier | +0.778 |
VC | +0.730 |
mt | +0.727 |
�� | +0.726 |
han | +0.718 |
Neg logit contributions | |
ipop | -0.712 |
EQU | -0.705 |
atche | -0.667 |
aspers | -0.628 |
Tiff | -0.620 |
Token | R |
Token ID | 371 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Frazier | +0.296 |
�� | +0.277 |
VC | +0.275 |
mt | +0.274 |
han | +0.272 |
Neg logit contributions | |
ipop | -0.300 |
EQU | -0.299 |
atche | -0.283 |
Tiff | -0.265 |
aspers | -0.265 |
Token | 5 |
Token ID | 20 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Frazier | +3.467 |
VC | +3.329 |
�� | +3.292 |
mt | +3.266 |
han | +3.250 |
Neg logit contributions | |
ipop | -3.827 |
EQU | -3.773 |
atche | -3.599 |
aspers | -3.405 |
Tiff | -3.382 |
Token | , |
Token ID | 11 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
Frazier | +2.646 |
VC | +2.502 |
mt | +2.496 |
�� | +2.468 |
han | +2.454 |
Neg logit contributions | |
ipop | -2.819 |
EQU | -2.785 |
atche | -2.664 |
aspers | -2.524 |
Tiff | -2.489 |
Token | he |
Token ID | 339 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Frazier | +0.461 |
�� | +0.429 |
VC | +0.425 |
mt | +0.423 |
han | +0.420 |
Neg logit contributions | |
ipop | -0.554 |
EQU | -0.553 |
atche | -0.524 |
Tiff | -0.496 |
aspers | -0.495 |
Token | will |
Token ID | 481 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Frazier | +1.360 |
VC | +1.273 |
mt | +1.268 |
han | +1.263 |
�� | +1.243 |
Neg logit contributions | |
ipop | -1.249 |
EQU | -1.234 |
atche | -1.170 |
aspers | -1.092 |
Expend | -1.087 |
Token | also |
Token ID | 635 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Frazier | +0.707 |
�� | +0.658 |
VC | +0.653 |
mt | +0.650 |
han | +0.644 |
Neg logit contributions | |
ipop | -0.835 |
EQU | -0.832 |
atche | -0.791 |
Tiff | -0.746 |
aspers | -0.745 |
Token | hat |
Token ID | 6877 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
ipop | +0.374 |
EQU | +0.374 |
atche | +0.355 |
Tiff | +0.342 |
aspers | +0.337 |
Neg logit contributions | |
Frazier | -0.250 |
�� | -0.237 |
bnb | -0.229 |
VC | -0.228 |
mt | -0.227 |
Token | chet |
Token ID | 20043 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Frazier | +0.476 |
VC | +0.448 |
mt | +0.446 |
�� | +0.445 |
han | +0.444 |
Neg logit contributions | |
ipop | -0.306 |
EQU | -0.306 |
atche | -0.282 |
aspers | -0.261 |
Tiff | -0.260 |
Token | at |
Token ID | 379 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ipop | +0.964 |
EQU | +0.962 |
atche | +0.907 |
Tiff | +0.855 |
aspers | +0.849 |
Neg logit contributions | |
Frazier | -0.948 |
�� | -0.908 |
VC | -0.882 |
mt | -0.878 |
han | -0.873 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ipop | +0.136 |
EQU | +0.136 |
atche | +0.129 |
aspers | +0.121 |
Tiff | +0.121 |
Neg logit contributions | |
Frazier | -0.125 |
�� | -0.116 |
VC | -0.116 |
mt | -0.115 |
han | -0.114 |
Token | same |
Token ID | 976 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ipop | +1.476 |
EQU | +1.473 |
atche | +1.392 |
Tiff | +1.323 |
aspers | +1.309 |
Neg logit contributions | |
Frazier | -1.319 |
�� | -1.249 |
VC | -1.222 |
mt | -1.218 |
bnb | -1.214 |
Token | Fred |
Token ID | 8559 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Frazier | +1.616 |
VC | +1.456 |
mt | +1.436 |
han | +1.397 |
Kh | +1.378 |
Neg logit contributions | |
ipop | -2.518 |
EQU | -2.514 |
atche | -2.425 |
aspers | -2.309 |
Expend | -2.268 |
Token | Meyer |
Token ID | 23975 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Frazier | +3.451 |
han | +3.085 |
mt | +3.051 |
VC | +3.047 |
iven | +2.935 |
Neg logit contributions | |
EQU | -5.133 |
ipop | -5.121 |
atche | -4.990 |
aspers | -4.712 |
effective | -4.590 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Frazier | +0.544 |
VC | +0.494 |
mt | +0.491 |
�� | +0.490 |
han | +0.485 |
Neg logit contributions | |
ipop | -0.861 |
EQU | -0.857 |
atche | -0.821 |
aspers | -0.779 |
Tiff | -0.777 |
Token | Long |
Token ID | 5882 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
ipop | +0.699 |
EQU | +0.697 |
atche | +0.656 |
Tiff | +0.614 |
aspers | +0.612 |
Neg logit contributions | |
Frazier | -0.790 |
�� | -0.745 |
VC | -0.737 |
mt | -0.735 |
han | -0.730 |
Token | view |
Token ID | 1177 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
Frazier | +0.611 |
�� | +0.573 |
VC | +0.570 |
mt | +0.567 |
han | +0.564 |
Neg logit contributions | |
ipop | -0.541 |
EQU | -0.540 |
atche | -0.508 |
Tiff | -0.476 |
aspers | -0.475 |
Token | resident |
Token ID | 6623 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ipop | +0.267 |
EQU | +0.267 |
atche | +0.253 |
Tiff | +0.239 |
aspers | +0.239 |
Neg logit contributions | |
Frazier | -0.217 |
�� | -0.202 |
VC | -0.200 |
mt | -0.199 |
han | -0.198 |