Token | fr |
Token ID | 1216 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
DIT | +0.097 |
RNA | +0.095 |
VOL | +0.088 |
EH | +0.088 |
CONT | +0.086 |
Neg logit contributions | |
abl | -0.089 |
osexual | -0.086 |
xual | -0.081 |
wolves | -0.079 |
erer | -0.078 |
Token | atern |
Token ID | 9205 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
DIT | +0.964 |
RNA | +0.951 |
VOL | +0.887 |
EH | +0.882 |
CONT | +0.868 |
Neg logit contributions | |
abl | -0.764 |
osexual | -0.737 |
xual | -0.688 |
wolves | -0.672 |
erer | -0.667 |
Token | ities |
Token ID | 871 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
DIT | +0.292 |
RNA | +0.288 |
VOL | +0.255 |
EH | +0.254 |
CONT | +0.245 |
Neg logit contributions | |
abl | -0.599 |
osexual | -0.586 |
xual | -0.554 |
wolves | -0.553 |
awn | -0.545 |
Token | or |
Token ID | 393 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
DIT | +1.146 |
RNA | +1.131 |
VOL | +1.045 |
EH | +1.036 |
CONT | +1.017 |
Neg logit contributions | |
abl | -1.193 |
osexual | -1.161 |
xual | -1.097 |
wolves | -1.070 |
erer | -1.066 |
Token | just |
Token ID | 655 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
abl | +0.456 |
osexual | +0.445 |
xual | +0.425 |
wolves | +0.419 |
erer | +0.415 |
Neg logit contributions | |
DIT | -0.282 |
RNA | -0.277 |
VOL | -0.249 |
EH | -0.248 |
CONT | -0.241 |
Token | sor |
Token ID | 25655 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
DIT | +0.680 |
RNA | +0.672 |
VOL | +0.627 |
EH | +0.622 |
CONT | +0.613 |
Neg logit contributions | |
abl | -0.560 |
osexual | -0.542 |
xual | -0.508 |
wolves | -0.495 |
erer | -0.492 |
Token | or |
Token ID | 273 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
DIT | +3.339 |
RNA | +3.336 |
VOL | +3.045 |
EH | +3.018 |
Chatt | +2.969 |
Neg logit contributions | |
abl | -3.396 |
osexual | -3.296 |
xual | -3.271 |
erer | -3.058 |
wolves | -3.024 |
Token | ities |
Token ID | 871 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
DIT | +1.005 |
RNA | +0.988 |
VOL | +0.856 |
EH | +0.845 |
CONT | +0.816 |
Neg logit contributions | |
abl | -2.391 |
osexual | -2.344 |
xual | -2.276 |
erer | -2.221 |
wolves | -2.207 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
DIT | +1.351 |
RNA | +1.333 |
VOL | +1.236 |
EH | +1.226 |
CONT | +1.203 |
Neg logit contributions | |
abl | -1.322 |
osexual | -1.285 |
xual | -1.211 |
wolves | -1.182 |
erer | -1.175 |
Token | This |
Token ID | 770 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
DIT | +0.124 |
RNA | +0.123 |
VOL | +0.114 |
EH | +0.113 |
CONT | +0.111 |
Neg logit contributions | |
abl | -0.121 |
osexual | -0.117 |
xual | -0.110 |
wolves | -0.108 |
erer | -0.107 |
Token | goes |
Token ID | 2925 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
DIT | +0.534 |
RNA | +0.528 |
VOL | +0.487 |
EH | +0.483 |
CONT | +0.475 |
Neg logit contributions | |
abl | -0.543 |
osexual | -0.527 |
xual | -0.498 |
wolves | -0.486 |
erer | -0.483 |
Token | ization |
Token ID | 1634 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
DIT | +0.347 |
RNA | +0.341 |
VOL | +0.310 |
EH | +0.307 |
CONT | +0.300 |
Neg logit contributions | |
abl | -0.519 |
osexual | -0.504 |
xual | -0.480 |
wolves | -0.471 |
erer | -0.470 |
Token | . |
Token ID | 13 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
DIT | +1.021 |
RNA | +1.008 |
VOL | +0.937 |
EH | +0.929 |
CONT | +0.913 |
Neg logit contributions | |
abl | -0.928 |
osexual | -0.900 |
xual | -0.847 |
wolves | -0.826 |
erer | -0.820 |
Token | CL |
Token ID | 7852 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
DIT | +0.016 |
RNA | +0.016 |
VOL | +0.015 |
EH | +0.015 |
CONT | +0.014 |
Neg logit contributions | |
abl | -0.015 |
osexual | -0.015 |
xual | -0.014 |
wolves | -0.014 |
erer | -0.013 |
Token | TV |
Token ID | 6849 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
abl | +0.205 |
osexual | +0.199 |
xual | +0.187 |
wolves | +0.183 |
erer | +0.183 |
Neg logit contributions | |
DIT | -0.203 |
RNA | -0.200 |
VOL | -0.185 |
EH | -0.184 |
CONT | -0.181 |
Token | ( |
Token ID | 357 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
DIT | +0.998 |
RNA | +0.985 |
VOL | +0.911 |
EH | +0.903 |
CONT | +0.887 |
Neg logit contributions | |
abl | -1.010 |
osexual | -0.980 |
xual | -0.926 |
wolves | -0.905 |
erer | -0.899 |
Token | BIP |
Token ID | 47772 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
abl | +0.105 |
osexual | +0.101 |
xual | +0.096 |
wolves | +0.095 |
erer | +0.094 |
Neg logit contributions | |
DIT | -0.088 |
RNA | -0.087 |
VOL | -0.080 |
EH | -0.079 |
CONT | -0.077 |
Token | 65 |
Token ID | 2996 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
DIT | +3.391 |
RNA | +3.338 |
VOL | +3.103 |
EH | +3.076 |
CONT | +3.055 |
Neg logit contributions | |
abl | -3.314 |
osexual | -3.251 |
xual | -3.043 |
wolves | -2.992 |
erer | -2.963 |
Token | ), |
Token ID | 828 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
DIT | +0.364 |
RNA | +0.360 |
VOL | +0.333 |
EH | +0.330 |
CONT | +0.324 |
Neg logit contributions | |
abl | -0.364 |
osexual | -0.351 |
xual | -0.332 |
wolves | -0.324 |
erer | -0.324 |
Token | deployed |
Token ID | 12380 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
abl | +0.254 |
osexual | +0.245 |
xual | +0.230 |
wolves | +0.226 |
erer | +0.224 |
Neg logit contributions | |
DIT | -0.294 |
RNA | -0.291 |
VOL | -0.271 |
EH | -0.268 |
CONT | -0.264 |
Token | a |
Token ID | 257 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
DIT | +0.932 |
RNA | +0.920 |
VOL | +0.861 |
EH | +0.854 |
CONT | +0.842 |
Neg logit contributions | |
abl | -0.707 |
osexual | -0.686 |
xual | -0.643 |
wolves | -0.622 |
erer | -0.618 |
Token | month |
Token ID | 1227 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
DIT | +0.062 |
RNA | +0.061 |
VOL | +0.057 |
EH | +0.056 |
CONT | +0.055 |
Neg logit contributions | |
abl | -0.060 |
osexual | -0.058 |
xual | -0.054 |
wolves | -0.053 |
erer | -0.053 |
Token | refunds |
Token ID | 36903 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
DIT | +0.908 |
RNA | +0.898 |
VOL | +0.834 |
EH | +0.827 |
CONT | +0.814 |
Neg logit contributions | |
abl | -0.807 |
osexual | -0.784 |
xual | -0.738 |
wolves | -0.718 |
erer | -0.713 |
Token | work |
Token ID | 670 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
abl | +0.355 |
osexual | +0.341 |
xual | +0.321 |
wolves | +0.314 |
erer | +0.312 |
Neg logit contributions | |
DIT | -0.402 |
RNA | -0.397 |
VOL | -0.369 |
EH | -0.366 |
CONT | -0.360 |
Token | ); |
Token ID | 1776 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
DIT | +0.802 |
RNA | +0.790 |
VOL | +0.732 |
EH | +0.727 |
CONT | +0.714 |
Neg logit contributions | |
abl | -0.781 |
osexual | -0.762 |
xual | -0.721 |
wolves | -0.700 |
erer | -0.695 |
Token | CSV |
Token ID | 44189 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
abl | +0.187 |
osexual | +0.179 |
xual | +0.169 |
wolves | +0.166 |
erer | +0.164 |
Neg logit contributions | |
DIT | -0.210 |
RNA | -0.208 |
VOL | -0.193 |
EH | -0.191 |
CONT | -0.188 |
Token | ( |
Token ID | 357 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
DIT | +0.521 |
RNA | +0.514 |
VOL | +0.477 |
EH | +0.474 |
CONT | +0.466 |
Neg logit contributions | |
abl | -0.478 |
osexual | -0.461 |
xual | -0.434 |
wolves | -0.425 |
erer | -0.422 |
Token | BIP |
Token ID | 47772 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
DIT | +0.071 |
RNA | +0.070 |
VOL | +0.064 |
EH | +0.063 |
CONT | +0.062 |
Neg logit contributions | |
abl | -0.093 |
osexual | -0.090 |
xual | -0.085 |
wolves | -0.084 |
erer | -0.083 |
Token | 68 |
Token ID | 3104 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
DIT | +3.148 |
RNA | +3.109 |
VOL | +2.866 |
EH | +2.845 |
CONT | +2.794 |
Neg logit contributions | |
abl | -3.383 |
osexual | -3.328 |
xual | -3.152 |
wolves | -3.075 |
erer | -3.044 |
Token | / |
Token ID | 1220 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
DIT | +0.954 |
RNA | +0.941 |
VOL | +0.869 |
EH | +0.862 |
CONT | +0.847 |
Neg logit contributions | |
abl | -0.992 |
osexual | -0.964 |
xual | -0.911 |
wolves | -0.891 |
erer | -0.884 |
Token | B |
Token ID | 347 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
DIT | +0.190 |
RNA | +0.188 |
VOL | +0.174 |
EH | +0.172 |
CONT | +0.169 |
Neg logit contributions | |
abl | -0.197 |
osexual | -0.191 |
xual | -0.180 |
wolves | -0.177 |
erer | -0.175 |
Token | IP |
Token ID | 4061 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
DIT | +0.380 |
RNA | +0.376 |
VOL | +0.350 |
EH | +0.348 |
CONT | +0.342 |
Neg logit contributions | |
abl | -0.319 |
osexual | -0.309 |
xual | -0.289 |
wolves | -0.282 |
erer | -0.281 |
Token | 112 |
Token ID | 14686 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
DIT | +1.524 |
RNA | +1.501 |
VOL | +1.394 |
EH | +1.377 |
CONT | +1.356 |
Neg logit contributions | |
abl | -1.517 |
osexual | -1.485 |
xual | -1.406 |
wolves | -1.366 |
erer | -1.359 |
Token | of |
Token ID | 286 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
DIT | +1.017 |
RNA | +1.005 |
VOL | +0.937 |
EH | +0.930 |
CONT | +0.915 |
Neg logit contributions | |
abl | -0.841 |
osexual | -0.814 |
xual | -0.764 |
wolves | -0.745 |
erer | -0.739 |
Token | fr |
Token ID | 1216 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
DIT | +0.283 |
RNA | +0.280 |
VOL | +0.260 |
EH | +0.258 |
CONT | +0.254 |
Neg logit contributions | |
abl | -0.248 |
osexual | -0.240 |
xual | -0.226 |
wolves | -0.220 |
erer | -0.218 |
Token | atern |
Token ID | 9205 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
DIT | +0.585 |
RNA | +0.574 |
VOL | +0.539 |
EH | +0.536 |
CONT | +0.528 |
Neg logit contributions | |
abl | -0.445 |
osexual | -0.429 |
xual | -0.396 |
wolves | -0.390 |
erer | -0.386 |
Token | ities |
Token ID | 871 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
DIT | +0.182 |
RNA | +0.180 |
EH | +0.161 |
VOL | +0.160 |
CONT | +0.154 |
Neg logit contributions | |
abl | -0.356 |
osexual | -0.349 |
wolves | -0.327 |
xual | -0.326 |
awn | -0.323 |
Token | and |
Token ID | 290 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
DIT | +1.107 |
RNA | +1.093 |
VOL | +1.010 |
EH | +1.001 |
CONT | +0.984 |
Neg logit contributions | |
abl | -1.138 |
osexual | -1.106 |
xual | -1.045 |
wolves | -1.022 |
erer | -1.015 |
Token | sor |
Token ID | 25655 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
DIT | +0.003 |
RNA | +0.003 |
VOL | +0.002 |
EH | +0.002 |
CONT | +0.002 |
Neg logit contributions | |
abl | -0.005 |
osexual | -0.005 |
xual | -0.005 |
wolves | -0.004 |
erer | -0.004 |
Token | or |
Token ID | 273 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
DIT | +3.318 |
RNA | +3.288 |
VOL | +3.023 |
EH | +3.012 |
Chatt | +2.940 |
Neg logit contributions | |
abl | -3.220 |
osexual | -3.119 |
xual | -3.048 |
wolves | -2.861 |
erer | -2.850 |
Token | ities |
Token ID | 871 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
DIT | +0.911 |
RNA | +0.891 |
VOL | +0.762 |
EH | +0.759 |
Chatt | +0.733 |
Neg logit contributions | |
abl | -2.280 |
osexual | -2.234 |
xual | -2.189 |
erer | -2.134 |
wolves | -2.107 |
Token | on |
Token ID | 319 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
DIT | +1.231 |
RNA | +1.214 |
VOL | +1.119 |
EH | +1.111 |
CONT | +1.090 |
Neg logit contributions | |
abl | -1.326 |
osexual | -1.293 |
xual | -1.221 |
wolves | -1.197 |
erer | -1.189 |
Token | campus |
Token ID | 7611 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
DIT | +0.029 |
RNA | +0.029 |
VOL | +0.027 |
EH | +0.027 |
CONT | +0.026 |
Neg logit contributions | |
abl | -0.026 |
osexual | -0.025 |
xual | -0.024 |
wolves | -0.023 |
erer | -0.023 |
Token | ), |
Token ID | 828 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
abl | +0.369 |
osexual | +0.356 |
xual | +0.338 |
wolves | +0.327 |
erer | +0.326 |
Neg logit contributions | |
DIT | -0.365 |
RNA | -0.360 |
VOL | -0.333 |
EH | -0.329 |
CONT | -0.324 |
Token | in |
Token ID | 259 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
DIT | +0.089 |
RNA | +0.088 |
VOL | +0.082 |
EH | +0.081 |
CONT | +0.080 |
Neg logit contributions | |
abl | -0.076 |
osexual | -0.073 |
xual | -0.069 |
wolves | -0.067 |
erer | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
abl | +0.564 |
osexual | +0.542 |
xual | +0.510 |
wolves | +0.502 |
erer | +0.497 |
Neg logit contributions | |
DIT | -0.580 |
RNA | -0.567 |
VOL | -0.526 |
EH | -0.521 |
CONT | -0.516 |
Token | um |
Token ID | 388 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
abl | +0.545 |
osexual | +0.528 |
xual | +0.498 |
wolves | +0.492 |
erer | +0.486 |
Neg logit contributions | |
DIT | -0.473 |
RNA | -0.467 |
VOL | -0.428 |
EH | -0.423 |
CONT | -0.417 |
Token | ich |
Token ID | 488 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
DIT | +0.706 |
RNA | +0.701 |
VOL | +0.659 |
EH | +0.657 |
CONT | +0.646 |
Neg logit contributions | |
abl | -0.373 |
osexual | -0.359 |
xual | -0.331 |
wolves | -0.319 |
erer | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
DIT | +0.911 |
RNA | +0.905 |
VOL | +0.839 |
EH | +0.835 |
CONT | +0.818 |
Neg logit contributions | |
abl | -0.862 |
osexual | -0.837 |
xual | -0.793 |
wolves | -0.775 |
erer | -0.765 |
Token | edu |
Token ID | 15532 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
abl | +0.304 |
osexual | +0.295 |
xual | +0.280 |
wolves | +0.275 |
erer | +0.273 |
Neg logit contributions | |
DIT | -0.251 |
RNA | -0.248 |
VOL | -0.227 |
EH | -0.224 |
CONT | -0.221 |
Token | /. |
Token ID | 11757 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
DIT | +2.966 |
RNA | +2.937 |
VOL | +2.717 |
EH | +2.696 |
CONT | +2.653 |
Neg logit contributions | |
abl | -3.238 |
osexual | -3.164 |
xual | -3.013 |
wolves | -2.914 |
erer | -2.895 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
DIT | +0.111 |
RNA | +0.109 |
VOL | +0.100 |
EH | +0.100 |
thumbnails | +0.097 |
Neg logit contributions | |
abl | -0.121 |
osexual | -0.117 |
xual | -0.111 |
wolves | -0.109 |
erer | -0.108 |
Token | I |
Token ID | 40 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
DIT | +0.593 |
RNA | +0.585 |
VOL | +0.536 |
EH | +0.532 |
CONT | +0.521 |
Neg logit contributions | |
abl | -0.697 |
osexual | -0.677 |
xual | -0.639 |
wolves | -0.629 |
erer | -0.625 |
Token | remember |
Token ID | 3505 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
abl | +0.140 |
osexual | +0.136 |
xual | +0.128 |
wolves | +0.126 |
erer | +0.125 |
Neg logit contributions | |
DIT | -0.124 |
RNA | -0.122 |
VOL | -0.113 |
EH | -0.111 |
CONT | -0.110 |
Token | about |
Token ID | 546 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
DIT | +0.121 |
RNA | +0.120 |
VOL | +0.112 |
EH | +0.111 |
CONT | +0.109 |
Neg logit contributions | |
abl | -0.100 |
osexual | -0.096 |
xual | -0.090 |
wolves | -0.088 |
erer | -0.087 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
abl | +0.682 |
osexual | +0.661 |
xual | +0.620 |
wolves | +0.605 |
erer | +0.601 |
Neg logit contributions | |
DIT | -0.778 |
RNA | -0.769 |
VOL | -0.715 |
EH | -0.709 |
CONT | -0.697 |
Token | Delta |
Token ID | 16978 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
abl | +0.351 |
osexual | +0.340 |
xual | +0.317 |
wolves | +0.309 |
erer | +0.308 |
Neg logit contributions | |
DIT | -0.419 |
RNA | -0.415 |
VOL | -0.385 |
EH | -0.383 |
CONT | -0.377 |
Token | Sigma |
Token ID | 31669 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
abl | +0.720 |
osexual | +0.701 |
xual | +0.651 |
wolves | +0.643 |
awn | +0.634 |
Neg logit contributions | |
DIT | -0.786 |
RNA | -0.771 |
EH | -0.715 |
VOL | -0.711 |
TEXT | -0.702 |
Token | The |
Token ID | 383 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
abl | +0.423 |
osexual | +0.411 |
xual | +0.382 |
wolves | +0.371 |
awn | +0.369 |
Neg logit contributions | |
DIT | -0.478 |
RNA | -0.470 |
EH | -0.437 |
VOL | -0.434 |
CONT | -0.428 |
Token | ta |
Token ID | 8326 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
DIT | +0.361 |
RNA | +0.355 |
VOL | +0.324 |
EH | +0.322 |
CONT | +0.315 |
Neg logit contributions | |
abl | -0.479 |
osexual | -0.467 |
xual | -0.443 |
wolves | -0.435 |
erer | -0.432 |
Token | sor |
Token ID | 25655 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
abl | +0.551 |
osexual | +0.533 |
xual | +0.500 |
wolves | +0.487 |
erer | +0.485 |
Neg logit contributions | |
DIT | -0.608 |
RNA | -0.597 |
VOL | -0.553 |
EH | -0.552 |
CONT | -0.543 |
Token | ority |
Token ID | 29134 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
DIT | +2.638 |
RNA | +2.611 |
VOL | +2.360 |
EH | +2.338 |
Chatt | +2.274 |
Neg logit contributions | |
abl | -3.455 |
osexual | -3.362 |
xual | -3.293 |
wolves | -3.137 |
erer | -3.118 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
DIT | +1.542 |
RNA | +1.526 |
VOL | +1.416 |
EH | +1.399 |
CONT | +1.373 |
Neg logit contributions | |
abl | -1.561 |
osexual | -1.512 |
xual | -1.435 |
wolves | -1.400 |
erer | -1.390 |
Token | 48 |
Token ID | 2780 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
abl | +0.204 |
osexual | +0.199 |
xual | +0.186 |
wolves | +0.181 |
erer | +0.180 |
Neg logit contributions | |
DIT | -0.222 |
RNA | -0.219 |
VOL | -0.203 |
EH | -0.201 |
CONT | -0.200 |
Token | ] |
Token ID | 60 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
DIT | +0.179 |
RNA | +0.175 |
VOL | +0.156 |
EH | +0.154 |
CONT | +0.151 |
Neg logit contributions | |
abl | -0.348 |
osexual | -0.340 |
xual | -0.327 |
wolves | -0.322 |
erer | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | -4.28e-04 |
Pos logit contributions | |
abl | +0.033 |
osexual | +0.032 |
xual | +0.030 |
wolves | +0.030 |
erer | +0.029 |
Neg logit contributions | |
DIT | -0.029 |
RNA | -0.029 |
VOL | -0.027 |
EH | -0.026 |
CONT | -0.026 |
Token | vital |
Token ID | 9204 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
DIT | +0.264 |
RNA | +0.261 |
VOL | +0.243 |
EH | +0.240 |
CONT | +0.236 |
Neg logit contributions | |
abl | -0.233 |
osexual | -0.226 |
xual | -0.212 |
wolves | -0.207 |
erer | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
DIT | +0.316 |
RNA | +0.313 |
VOL | +0.293 |
EH | +0.290 |
CONT | +0.286 |
Neg logit contributions | |
abl | -0.235 |
osexual | -0.227 |
xual | -0.212 |
wolves | -0.206 |
erer | -0.205 |
Token | And |
Token ID | 843 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
DIT | +0.244 |
RNA | +0.242 |
VOL | +0.224 |
EH | +0.222 |
CONT | +0.217 |
Neg logit contributions | |
abl | -0.236 |
osexual | -0.228 |
xual | -0.214 |
wolves | -0.211 |
erer | -0.210 |
Token | while |
Token ID | 981 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
DIT | +0.155 |
RNA | +0.153 |
VOL | +0.142 |
EH | +0.141 |
CONT | +0.138 |
Neg logit contributions | |
abl | -0.136 |
osexual | -0.131 |
xual | -0.123 |
wolves | -0.120 |
erer | -0.120 |
Token | your |
Token ID | 534 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
abl | +0.026 |
osexual | +0.025 |
xual | +0.023 |
wolves | +0.023 |
erer | +0.023 |
Neg logit contributions | |
DIT | -0.027 |
RNA | -0.027 |
VOL | -0.025 |
EH | -0.024 |
CONT | -0.024 |
Token | Inner |
Token ID | 24877 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
DIT | +0.683 |
RNA | +0.674 |
VOL | +0.625 |
EH | +0.620 |
CONT | +0.609 |
Neg logit contributions | |
abl | -0.648 |
osexual | -0.628 |
xual | -0.592 |
wolves | -0.578 |
erer | -0.574 |
Token | Ass |
Token ID | 2195 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
DIT | +3.729 |
RNA | +3.715 |
EH | +3.457 |
VOL | +3.452 |
Chatt | +3.443 |
Neg logit contributions | |
abl | -2.230 |
osexual | -2.172 |
xual | -2.059 |
wolves | -1.989 |
erer | -1.908 |
Token | hole |
Token ID | 13207 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
DIT | +0.199 |
RNA | +0.193 |
VOL | +0.158 |
EH | +0.154 |
CONT | +0.146 |
Neg logit contributions | |
abl | -0.781 |
osexual | -0.766 |
xual | -0.738 |
erer | -0.728 |
wolves | -0.727 |
Token | is |
Token ID | 318 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
DIT | +1.155 |
RNA | +1.140 |
VOL | +1.053 |
EH | +1.045 |
CONT | +1.027 |
Neg logit contributions | |
abl | -1.173 |
osexual | -1.140 |
xual | -1.078 |
wolves | -1.052 |
erer | -1.044 |
Token | confused |
Token ID | 10416 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
DIT | +0.304 |
RNA | +0.301 |
VOL | +0.280 |
EH | +0.278 |
CONT | +0.274 |
Neg logit contributions | |
abl | -0.251 |
osexual | -0.243 |
xual | -0.228 |
wolves | -0.222 |
erer | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
DIT | +0.336 |
RNA | +0.332 |
VOL | +0.309 |
EH | +0.307 |
CONT | +0.302 |
Neg logit contributions | |
abl | -0.273 |
osexual | -0.264 |
xual | -0.248 |
wolves | -0.241 |
erer | -0.239 |
Token | right |
Token ID | 826 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
DIT | +0.169 |
RNA | +0.167 |
VOL | +0.155 |
EH | +0.154 |
CONT | +0.151 |
Neg logit contributions | |
abl | -0.148 |
osexual | -0.143 |
xual | -0.134 |
wolves | -0.131 |
erer | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
DIT | +0.717 |
RNA | +0.708 |
VOL | +0.663 |
EH | +0.655 |
CONT | +0.641 |
Neg logit contributions | |
abl | -0.545 |
osexual | -0.535 |
xual | -0.502 |
wolves | -0.489 |
erer | -0.481 |
Token | protect |
Token ID | 1805 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
DIT | +0.491 |
RNA | +0.486 |
VOL | +0.454 |
EH | +0.451 |
CONT | +0.444 |
Neg logit contributions | |
abl | -0.367 |
osexual | -0.356 |
xual | -0.334 |
wolves | -0.324 |
erer | -0.320 |
Token | Russian |
Token ID | 3394 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
DIT | +1.446 |
RNA | +1.426 |
VOL | +1.320 |
EH | +1.310 |
CONT | +1.286 |
Neg logit contributions | |
abl | -1.440 |
osexual | -1.400 |
xual | -1.328 |
wolves | -1.294 |
erer | -1.282 |
Token | - |
Token ID | 12 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
abl | +0.122 |
osexual | +0.118 |
xual | +0.108 |
wolves | +0.106 |
erer | +0.106 |
Neg logit contributions | |
DIT | -0.145 |
RNA | -0.143 |
VOL | -0.132 |
EH | -0.132 |
CONT | -0.130 |
Token | spe |
Token ID | 4125 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
DIT | +0.370 |
RNA | +0.364 |
VOL | +0.335 |
EH | +0.333 |
CONT | +0.326 |
Neg logit contributions | |
abl | -0.407 |
osexual | -0.393 |
xual | -0.371 |
wolves | -0.365 |
erer | -0.362 |
Token | akers |
Token ID | 3979 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
RNA | +2.265 |
DIT | +2.258 |
VOL | +2.024 |
EH | +1.993 |
CONT | +1.942 |
Neg logit contributions | |
abl | -3.720 |
osexual | -3.676 |
xual | -3.489 |
wolves | -3.458 |
erer | -3.380 |
Token | in |
Token ID | 287 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
abl | +0.090 |
osexual | +0.086 |
xual | +0.081 |
wolves | +0.079 |
erer | +0.078 |
Neg logit contributions | |
DIT | -0.110 |
RNA | -0.109 |
VOL | -0.101 |
EH | -0.100 |
CONT | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
abl | +0.096 |
osexual | +0.092 |
xual | +0.086 |
wolves | +0.084 |
erer | +0.084 |
Neg logit contributions | |
DIT | -0.116 |
RNA | -0.115 |
VOL | -0.106 |
EH | -0.106 |
CONT | -0.104 |
Token | region |
Token ID | 3814 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
abl | +0.132 |
osexual | +0.128 |
xual | +0.120 |
wolves | +0.117 |
erer | +0.116 |
Neg logit contributions | |
DIT | -0.156 |
RNA | -0.155 |
VOL | -0.144 |
EH | -0.143 |
CONT | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
DIT | +0.587 |
RNA | +0.581 |
VOL | +0.539 |
EH | +0.535 |
CONT | +0.526 |
Neg logit contributions | |
abl | -0.519 |
osexual | -0.501 |
xual | -0.472 |
wolves | -0.460 |
erer | -0.457 |
Token | you |
Token ID | 345 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
abl | +0.300 |
osexual | +0.288 |
xual | +0.270 |
wolves | +0.264 |
erer | +0.263 |
Neg logit contributions | |
DIT | -0.343 |
RNA | -0.339 |
VOL | -0.314 |
EH | -0.312 |
CONT | -0.308 |
Token | connect |
Token ID | 2018 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
abl | +0.102 |
osexual | +0.098 |
xual | +0.092 |
wolves | +0.091 |
erer | +0.091 |
Neg logit contributions | |
DIT | -0.102 |
RNA | -0.101 |
VOL | -0.093 |
EH | -0.092 |
CONT | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
DIT | +1.553 |
RNA | +1.533 |
VOL | +1.426 |
EH | +1.413 |
CONT | +1.390 |
Neg logit contributions | |
abl | -1.400 |
osexual | -1.360 |
xual | -1.281 |
wolves | -1.249 |
erer | -1.239 |
Token | dock |
Token ID | 23423 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
DIT | +0.058 |
RNA | +0.057 |
VOL | +0.053 |
EH | +0.052 |
CONT | +0.052 |
Neg logit contributions | |
abl | -0.055 |
osexual | -0.053 |
xual | -0.050 |
wolves | -0.049 |
erer | -0.049 |
Token | / |
Token ID | 14 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
DIT | +0.516 |
RNA | +0.510 |
VOL | +0.475 |
EH | +0.472 |
CONT | +0.464 |
Neg logit contributions | |
abl | -0.419 |
osexual | -0.405 |
xual | -0.380 |
wolves | -0.370 |
erer | -0.367 |
Token | charg |
Token ID | 11121 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
abl | +0.498 |
osexual | +0.480 |
xual | +0.453 |
wolves | +0.450 |
erer | +0.443 |
Neg logit contributions | |
DIT | -0.439 |
RNA | -0.433 |
VOL | -0.396 |
EH | -0.393 |
Chatt | -0.387 |
Token | er |
Token ID | 263 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
DIT | +2.600 |
RNA | +2.576 |
VOL | +2.355 |
EH | +2.331 |
CONT | +2.259 |
Neg logit contributions | |
abl | -3.360 |
osexual | -3.295 |
xual | -3.156 |
wolves | -3.085 |
awn | -3.020 |
Token | and |
Token ID | 290 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
abl | +0.079 |
osexual | +0.076 |
xual | +0.072 |
wolves | +0.070 |
erer | +0.070 |
Neg logit contributions | |
DIT | -0.095 |
RNA | -0.094 |
VOL | -0.087 |
EH | -0.087 |
CONT | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
abl | +0.071 |
osexual | +0.069 |
xual | +0.065 |
wolves | +0.063 |
erer | +0.063 |
Neg logit contributions | |
DIT | -0.084 |
RNA | -0.083 |
VOL | -0.077 |
EH | -0.077 |
CONT | -0.075 |
Token | moment |
Token ID | 2589 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
abl | +0.056 |
osexual | +0.054 |
xual | +0.050 |
wolves | +0.049 |
erer | +0.049 |
Neg logit contributions | |
DIT | -0.068 |
RNA | -0.067 |
VOL | -0.062 |
EH | -0.062 |
CONT | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
abl | +0.379 |
osexual | +0.365 |
xual | +0.343 |
wolves | +0.337 |
erer | +0.334 |
Neg logit contributions | |
DIT | -0.411 |
RNA | -0.407 |
VOL | -0.375 |
EH | -0.372 |
CONT | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
abl | +0.086 |
osexual | +0.082 |
erer | +0.077 |
wolves | +0.076 |
awn | +0.076 |
Neg logit contributions | |
DIT | -0.079 |
RNA | -0.078 |
VOL | -0.073 |
EH | -0.072 |
thumbnails | -0.071 |
Token | E |
Token ID | 36 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
abl | +0.085 |
osexual | +0.082 |
xual | +0.077 |
wolves | +0.076 |
erer | +0.075 |
Neg logit contributions | |
DIT | -0.089 |
RNA | -0.088 |
VOL | -0.082 |
EH | -0.081 |
CONT | -0.080 |
Token | t |
Token ID | 83 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
abl | +0.537 |
osexual | +0.522 |
xual | +0.497 |
wolves | +0.487 |
erer | +0.483 |
Neg logit contributions | |
DIT | -0.442 |
RNA | -0.435 |
VOL | -0.399 |
EH | -0.395 |
CONT | -0.388 |
Token | iquette |
Token ID | 40387 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
abl | +0.111 |
osexual | +0.106 |
xual | +0.094 |
erer | +0.091 |
wolves | +0.090 |
Neg logit contributions | |
DIT | -0.266 |
RNA | -0.264 |
VOL | -0.250 |
EH | -0.248 |
CONT | -0.246 |
Token | for |
Token ID | 329 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
abl | +0.544 |
osexual | +0.523 |
xual | +0.487 |
wolves | +0.472 |
erer | +0.469 |
Neg logit contributions | |
DIT | -0.780 |
RNA | -0.771 |
VOL | -0.723 |
EH | -0.717 |
CONT | -0.706 |
Token | Gentle |
Token ID | 25066 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
abl | +0.444 |
osexual | +0.434 |
xual | +0.412 |
wolves | +0.402 |
erer | +0.401 |
Neg logit contributions | |
DIT | -0.366 |
RNA | -0.362 |
VOL | -0.331 |
EH | -0.329 |
CONT | -0.321 |
Token | men |
Token ID | 3653 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
RNA | +2.874 |
DIT | +2.868 |
VOL | +2.631 |
EH | +2.603 |
Chatt | +2.575 |
Neg logit contributions | |
abl | -3.066 |
osexual | -2.971 |
xual | -2.816 |
wolves | -2.747 |
erer | -2.704 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
DIT | +0.914 |
RNA | +0.894 |
VOL | +0.830 |
EH | +0.826 |
CONT | +0.807 |
Neg logit contributions | |
abl | -0.971 |
osexual | -0.940 |
xual | -0.893 |
wolves | -0.875 |
erer | -0.860 |
Token | 18 |
Token ID | 1248 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
abl | +0.204 |
osexual | +0.197 |
xual | +0.186 |
wolves | +0.181 |
erer | +0.180 |
Neg logit contributions | |
DIT | -0.238 |
RNA | -0.236 |
VOL | -0.218 |
EH | -0.217 |
CONT | -0.213 |
Token | 57 |
Token ID | 3553 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
DIT | +0.661 |
RNA | +0.654 |
VOL | +0.607 |
EH | +0.602 |
CONT | +0.591 |
Neg logit contributions | |
abl | -0.609 |
osexual | -0.589 |
xual | -0.554 |
wolves | -0.543 |
erer | -0.539 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
abl | +0.209 |
osexual | +0.203 |
xual | +0.191 |
wolves | +0.186 |
erer | +0.185 |
Neg logit contributions | |
DIT | -0.230 |
RNA | -0.227 |
VOL | -0.211 |
EH | -0.209 |
CONT | -0.206 |
Token | :// |
Token ID | 1378 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
abl | +1.036 |
osexual | +0.953 |
erer | +0.893 |
awn | +0.879 |
wolves | +0.876 |
Neg logit contributions | |
DIT | -1.541 |
RNA | -1.519 |
VOL | -1.435 |
Chatt | -1.422 |
EH | -1.404 |
Token | www |
Token ID | 2503 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
abl | +1.165 |
osexual | +1.115 |
xual | +1.039 |
wolves | +1.012 |
awn | +0.996 |
Neg logit contributions | |
DIT | -1.646 |
RNA | -1.630 |
VOL | -1.530 |
EH | -1.510 |
Chatt | -1.489 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
abl | +0.517 |
osexual | +0.487 |
erer | +0.452 |
xual | +0.452 |
wolves | +0.450 |
Neg logit contributions | |
DIT | -0.652 |
RNA | -0.643 |
VOL | -0.604 |
EH | -0.596 |
Chatt | -0.588 |
Token | eff |
Token ID | 14822 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
DIT | +0.429 |
RNA | +0.423 |
VOL | +0.392 |
EH | +0.389 |
CONT | +0.382 |
Neg logit contributions | |
abl | -0.415 |
osexual | -0.403 |
xual | -0.380 |
wolves | -0.371 |
erer | -0.368 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
DIT | +1.728 |
RNA | +1.709 |
VOL | +1.584 |
EH | +1.571 |
CONT | +1.546 |
Neg logit contributions | |
abl | -1.595 |
osexual | -1.551 |
xual | -1.467 |
wolves | -1.423 |
erer | -1.410 |
Token | org |
Token ID | 2398 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
DIT | +0.284 |
RNA | +0.279 |
VOL | +0.262 |
EH | +0.259 |
CONT | +0.256 |
Neg logit contributions | |
abl | -0.221 |
osexual | -0.211 |
xual | -0.195 |
wolves | -0.193 |
erer | -0.192 |
Token | / |
Token ID | 14 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
DIT | +2.918 |
RNA | +2.884 |
VOL | +2.651 |
EH | +2.636 |
CONT | +2.603 |
Neg logit contributions | |
abl | -3.057 |
osexual | -3.005 |
xual | -2.871 |
wolves | -2.750 |
erer | -2.724 |
Token | d |
Token ID | 67 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
DIT | +0.466 |
RNA | +0.461 |
VOL | +0.425 |
EH | +0.422 |
Chatt | +0.413 |
Neg logit contributions | |
abl | -0.486 |
osexual | -0.471 |
xual | -0.445 |
wolves | -0.437 |
erer | -0.432 |
Token | ee |
Token ID | 1453 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
DIT | +1.209 |
RNA | +1.197 |
VOL | +1.130 |
EH | +1.128 |
CONT | +1.111 |
Neg logit contributions | |
abl | -0.536 |
osexual | -0.515 |
xual | -0.475 |
wolves | -0.455 |
erer | -0.443 |
Token | pl |
Token ID | 489 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
abl | +0.145 |
osexual | +0.140 |
xual | +0.132 |
wolves | +0.130 |
erer | +0.129 |
Neg logit contributions | |
DIT | -0.118 |
RNA | -0.116 |
EH | -0.107 |
VOL | -0.107 |
Chatt | -0.104 |
Token | inks |
Token ID | 2973 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
DIT | +0.241 |
RNA | +0.238 |
VOL | +0.222 |
EH | +0.221 |
CONT | +0.218 |
Neg logit contributions | |
abl | -0.217 |
osexual | -0.209 |
xual | -0.195 |
wolves | -0.192 |
awn | -0.190 |
Token | emergency |
Token ID | 6334 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
DIT | +0.567 |
RNA | +0.561 |
VOL | +0.521 |
EH | +0.517 |
CONT | +0.508 |
Neg logit contributions | |
abl | -0.498 |
osexual | -0.482 |
xual | -0.453 |
wolves | -0.442 |
erer | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
DIT | +0.618 |
RNA | +0.611 |
VOL | +0.570 |
EH | +0.566 |
CONT | +0.558 |
Neg logit contributions | |
abl | -0.484 |
osexual | -0.469 |
xual | -0.439 |
wolves | -0.427 |
erer | -0.424 |
Token | tt |
Token ID | 926 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
abl | +0.012 |
osexual | +0.011 |
xual | +0.011 |
wolves | +0.010 |
erer | +0.010 |
Neg logit contributions | |
DIT | -0.011 |
RNA | -0.011 |
VOL | -0.010 |
EH | -0.010 |
CONT | -0.010 |
Token | u |
Token ID | 84 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
DIT | +0.153 |
RNA | +0.151 |
VOL | +0.140 |
EH | +0.138 |
CONT | +0.136 |
Neg logit contributions | |
abl | -0.173 |
osexual | -0.168 |
xual | -0.159 |
wolves | -0.156 |
erer | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
DIT | +0.118 |
RNA | +0.117 |
VOL | +0.108 |
EH | +0.108 |
CONT | +0.106 |
Neg logit contributions | |
abl | -0.106 |
osexual | -0.103 |
xual | -0.097 |
wolves | -0.095 |
erer | -0.094 |
Token | edu |
Token ID | 15532 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
abl | +0.220 |
osexual | +0.214 |
xual | +0.203 |
wolves | +0.199 |
erer | +0.198 |
Neg logit contributions | |
DIT | -0.181 |
RNA | -0.179 |
VOL | -0.164 |
EH | -0.162 |
CONT | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
DIT | +2.907 |
RNA | +2.871 |
VOL | +2.654 |
EH | +2.634 |
CONT | +2.606 |
Neg logit contributions | |
abl | -3.038 |
osexual | -2.972 |
xual | -2.804 |
erer | -2.721 |
wolves | -2.720 |
Token | � |
Token ID | 447 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
abl | +0.260 |
osexual | +0.251 |
xual | +0.238 |
wolves | +0.233 |
erer | +0.231 |
Neg logit contributions | |
DIT | -0.257 |
RNA | -0.254 |
VOL | -0.235 |
EH | -0.232 |
CONT | -0.228 |
Token | � |
Token ID | 251 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
abl | +0.335 |
osexual | +0.321 |
xual | +0.297 |
wolves | +0.287 |
erer | +0.285 |
Neg logit contributions | |
DIT | -0.543 |
RNA | -0.537 |
VOL | -0.504 |
EH | -0.502 |
CONT | -0.493 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
DIT | +0.365 |
RNA | +0.360 |
VOL | +0.331 |
EH | +0.328 |
CONT | +0.321 |
Neg logit contributions | |
abl | -0.416 |
osexual | -0.404 |
xual | -0.383 |
wolves | -0.375 |
erer | -0.373 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
DIT | +0.057 |
RNA | +0.056 |
VOL | +0.052 |
EH | +0.051 |
thumbnails | +0.050 |
Neg logit contributions | |
abl | -0.063 |
osexual | -0.060 |
erer | -0.056 |
xual | -0.056 |
wolves | -0.056 |
Token | Game |
Token ID | 3776 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
DIT | +0.232 |
RNA | +0.229 |
VOL | +0.213 |
EH | +0.211 |
CONT | +0.208 |
Neg logit contributions | |
abl | -0.209 |
osexual | -0.202 |
xual | -0.189 |
wolves | -0.185 |
erer | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
DIT | +0.279 |
RNA | +0.274 |
VOL | +0.255 |
EH | +0.251 |
CONT | +0.248 |
Neg logit contributions | |
abl | -0.270 |
osexual | -0.260 |
xual | -0.245 |
erer | -0.239 |
wolves | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
abl | +0.010 |
osexual | +0.010 |
xual | +0.010 |
wolves | +0.009 |
erer | +0.009 |
Neg logit contributions | |
DIT | -0.009 |
RNA | -0.009 |
VOL | -0.008 |
EH | -0.008 |
CONT | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
DIT | +0.128 |
RNA | +0.126 |
VOL | +0.117 |
EH | +0.115 |
Chatt | +0.114 |
Neg logit contributions | |
abl | -0.141 |
osexual | -0.135 |
erer | -0.126 |
wolves | -0.126 |
xual | -0.125 |
Token | Your |
Token ID | 7120 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
DIT | +0.139 |
RNA | +0.137 |
VOL | +0.125 |
EH | +0.124 |
Chatt | +0.123 |
Neg logit contributions | |
abl | -0.163 |
osexual | -0.158 |
xual | -0.148 |
wolves | -0.147 |
erer | -0.147 |
Token | Inner |
Token ID | 24877 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
DIT | +0.501 |
RNA | +0.495 |
VOL | +0.459 |
EH | +0.455 |
CONT | +0.448 |
Neg logit contributions | |
abl | -0.474 |
osexual | -0.459 |
xual | -0.433 |
wolves | -0.423 |
erer | -0.420 |
Token | Ass |
Token ID | 2195 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
DIT | +3.566 |
RNA | +3.538 |
EH | +3.295 |
VOL | +3.290 |
Chatt | +3.272 |
Neg logit contributions | |
abl | -2.298 |
osexual | -2.227 |
xual | -2.101 |
wolves | -2.034 |
erer | -1.973 |
Token | hole |
Token ID | 13207 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
DIT | +0.031 |
RNA | +0.030 |
VOL | +0.024 |
EH | +0.024 |
CONT | +0.022 |
Neg logit contributions | |
abl | -0.128 |
osexual | -0.125 |
xual | -0.121 |
wolves | -0.119 |
erer | -0.119 |
Token | never |
Token ID | 1239 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
DIT | +1.181 |
RNA | +1.166 |
VOL | +1.081 |
EH | +1.073 |
CONT | +1.055 |
Neg logit contributions | |
abl | -1.117 |
osexual | -1.083 |
xual | -1.021 |
wolves | -0.997 |
erer | -0.989 |
Token | gets |
Token ID | 3011 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
DIT | +0.379 |
RNA | +0.374 |
VOL | +0.346 |
EH | +0.343 |
CONT | +0.337 |
Neg logit contributions | |
abl | -0.400 |
osexual | -0.389 |
xual | -0.369 |
wolves | -0.359 |
erer | -0.357 |
Token | enough |
Token ID | 1576 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
abl | +0.030 |
osexual | +0.029 |
xual | +0.027 |
wolves | +0.026 |
erer | +0.026 |
Neg logit contributions | |
DIT | -0.041 |
RNA | -0.041 |
VOL | -0.038 |
EH | -0.038 |
CONT | -0.037 |
Token | ote |
Token ID | 1258 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
DIT | +0.796 |
RNA | +0.777 |
VOL | +0.711 |
EH | +0.705 |
CONT | +0.699 |
Neg logit contributions | |
abl | -0.984 |
osexual | -0.957 |
xual | -0.900 |
erer | -0.887 |
wolves | -0.884 |
Token | will |
Token ID | 481 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
abl | +0.009 |
osexual | +0.008 |
xual | +0.008 |
wolves | +0.008 |
erer | +0.008 |
Neg logit contributions | |
DIT | -0.008 |
RNA | -0.008 |
VOL | -0.008 |
EH | -0.008 |
CONT | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
abl | +0.634 |
osexual | +0.611 |
xual | +0.573 |
wolves | +0.558 |
erer | +0.556 |
Neg logit contributions | |
DIT | -0.779 |
RNA | -0.770 |
VOL | -0.717 |
EH | -0.712 |
CONT | -0.702 |
Token | receiving |
Token ID | 6464 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
DIT | +0.025 |
RNA | +0.025 |
VOL | +0.023 |
EH | +0.023 |
CONT | +0.023 |
Neg logit contributions | |
abl | -0.023 |
osexual | -0.022 |
xual | -0.021 |
wolves | -0.020 |
erer | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
DIT | +0.065 |
RNA | +0.064 |
VOL | +0.060 |
EH | +0.059 |
CONT | +0.058 |
Neg logit contributions | |
abl | -0.059 |
osexual | -0.057 |
xual | -0.054 |
wolves | -0.052 |
erer | -0.052 |
Token | improve |
Token ID | 49453 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
DIT | +0.018 |
RNA | +0.018 |
VOL | +0.016 |
EH | +0.016 |
CONT | +0.016 |
Neg logit contributions | |
abl | -0.014 |
osexual | -0.013 |
xual | -0.013 |
wolves | -0.012 |
erer | -0.012 |
Token | ments |
Token ID | 902 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
DIT | +1.756 |
RNA | +1.726 |
VOL | +1.502 |
EH | +1.474 |
CONT | +1.439 |
Neg logit contributions | |
abl | -4.125 |
osexual | -4.067 |
xual | -3.907 |
wolves | -3.864 |
erer | -3.832 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
DIT | +0.798 |
RNA | +0.787 |
VOL | +0.720 |
EH | +0.713 |
CONT | +0.700 |
Neg logit contributions | |
abl | -1.002 |
osexual | -0.976 |
xual | -0.927 |
wolves | -0.909 |
erer | -0.904 |
Token | Apple |
Token ID | 4196 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
abl | +0.065 |
osexual | +0.063 |
xual | +0.059 |
wolves | +0.058 |
erer | +0.057 |
Neg logit contributions | |
DIT | -0.069 |
RNA | -0.069 |
VOL | -0.064 |
EH | -0.063 |
CONT | -0.062 |
Token | Script |
Token ID | 7391 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
abl | +0.813 |
osexual | +0.792 |
xual | +0.745 |
erer | +0.730 |
wolves | +0.730 |
Neg logit contributions | |
DIT | -0.684 |
RNA | -0.673 |
VOL | -0.621 |
EH | -0.615 |
CONT | -0.600 |
Token | support |
Token ID | 1104 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
abl | +0.422 |
osexual | +0.408 |
xual | +0.386 |
wolves | +0.377 |
erer | +0.375 |
Neg logit contributions | |
DIT | -0.391 |
RNA | -0.385 |
VOL | -0.356 |
EH | -0.353 |
CONT | -0.345 |
Token | story |
Token ID | 1621 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
DIT | +0.127 |
RNA | +0.126 |
VOL | +0.117 |
EH | +0.116 |
CONT | +0.114 |
Neg logit contributions | |
abl | -0.110 |
osexual | -0.106 |
xual | -0.099 |
erer | -0.097 |
wolves | -0.097 |
Token | ! |
Token ID | 0 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
abl | +0.099 |
osexual | +0.096 |
xual | +0.091 |
wolves | +0.089 |
erer | +0.088 |
Neg logit contributions | |
DIT | -0.107 |
RNA | -0.106 |
VOL | -0.098 |
EH | -0.097 |
CONT | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
abl | +0.572 |
osexual | +0.555 |
xual | +0.521 |
wolves | +0.514 |
erer | +0.514 |
Neg logit contributions | |
DIT | -0.526 |
RNA | -0.519 |
VOL | -0.477 |
EH | -0.472 |
CONT | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
DIT | +0.039 |
RNA | +0.039 |
VOL | +0.036 |
EH | +0.035 |
thumbnails | +0.035 |
Neg logit contributions | |
abl | -0.043 |
osexual | -0.041 |
erer | -0.039 |
wolves | -0.038 |
xual | -0.038 |
Token | Your |
Token ID | 7120 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
DIT | +0.071 |
RNA | +0.070 |
VOL | +0.064 |
EH | +0.064 |
Chatt | +0.063 |
Neg logit contributions | |
abl | -0.086 |
osexual | -0.084 |
xual | -0.079 |
wolves | -0.078 |
erer | -0.078 |
Token | Inner |
Token ID | 24877 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
DIT | +0.475 |
RNA | +0.469 |
VOL | +0.432 |
EH | +0.429 |
CONT | +0.421 |
Neg logit contributions | |
abl | -0.504 |
osexual | -0.490 |
xual | -0.463 |
wolves | -0.453 |
erer | -0.450 |
Token | Ass |
Token ID | 2195 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
DIT | +3.587 |
RNA | +3.583 |
Chatt | +3.336 |
EH | +3.325 |
VOL | +3.321 |
Neg logit contributions | |
abl | -2.187 |
osexual | -2.115 |
xual | -2.020 |
wolves | -1.959 |
erer | -1.872 |
Token | hole |
Token ID | 13207 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
DIT | +0.115 |
RNA | +0.111 |
VOL | +0.092 |
EH | +0.090 |
CONT | +0.086 |
Neg logit contributions | |
abl | -0.438 |
osexual | -0.429 |
xual | -0.413 |
erer | -0.408 |
wolves | -0.407 |
Token | is |
Token ID | 318 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
DIT | +1.338 |
RNA | +1.320 |
VOL | +1.222 |
EH | +1.213 |
CONT | +1.193 |
Neg logit contributions | |
abl | -1.298 |
osexual | -1.262 |
xual | -1.189 |
wolves | -1.162 |
erer | -1.152 |
Token | never |
Token ID | 1239 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
DIT | +0.508 |
RNA | +0.502 |
VOL | +0.468 |
EH | +0.464 |
CONT | +0.457 |
Neg logit contributions | |
abl | -0.419 |
osexual | -0.406 |
xual | -0.381 |
wolves | -0.370 |
erer | -0.368 |
Token | off |
Token ID | 572 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
DIT | +0.357 |
RNA | +0.354 |
VOL | +0.331 |
EH | +0.329 |
CONT | +0.324 |
Neg logit contributions | |
abl | -0.269 |
osexual | -0.261 |
xual | -0.245 |
wolves | -0.235 |
erer | -0.234 |
Token | - |
Token ID | 12 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
DIT | +0.290 |
RNA | +0.286 |
VOL | +0.262 |
EH | +0.258 |
CONT | +0.253 |
Neg logit contributions | |
abl | -0.369 |
osexual | -0.359 |
xual | -0.341 |
wolves | -0.335 |
erer | -0.333 |
Token | cent |
Token ID | 1087 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
DIT | +0.367 |
RNA | +0.360 |
VOL | +0.323 |
EH | +0.319 |
CONT | +0.311 |
Neg logit contributions | |
abl | -0.648 |
osexual | -0.632 |
xual | -0.604 |
wolves | -0.595 |
erer | -0.592 |
Token | piece |
Token ID | 3704 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
DIT | +0.343 |
RNA | +0.337 |
VOL | +0.303 |
EH | +0.300 |
CONT | +0.293 |
Neg logit contributions | |
abl | -0.560 |
osexual | -0.547 |
xual | -0.522 |
wolves | -0.513 |
erer | -0.510 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
DIT | +0.198 |
RNA | +0.195 |
VOL | +0.182 |
EH | +0.180 |
CONT | +0.178 |
Neg logit contributions | |
abl | -0.170 |
osexual | -0.165 |
xual | -0.155 |
wolves | -0.151 |
erer | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
DIT | +0.471 |
RNA | +0.464 |
VOL | +0.430 |
EH | +0.426 |
CONT | +0.418 |
Neg logit contributions | |
abl | -0.448 |
osexual | -0.433 |
xual | -0.408 |
wolves | -0.399 |
erer | -0.397 |
Token | encl |
Token ID | 13507 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
DIT | +0.234 |
RNA | +0.231 |
VOL | +0.215 |
EH | +0.213 |
CONT | +0.209 |
Neg logit contributions | |
abl | -0.206 |
osexual | -0.200 |
xual | -0.187 |
wolves | -0.183 |
erer | -0.183 |
Token | osing |
Token ID | 2752 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
DIT | +3.589 |
RNA | +3.581 |
VOL | +3.318 |
EH | +3.311 |
CONT | +3.265 |
Neg logit contributions | |
abl | -2.244 |
osexual | -2.151 |
xual | -2.032 |
wolves | -1.982 |
erer | -1.931 |
Token | pattern |
Token ID | 3912 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
DIT | +1.629 |
RNA | +1.607 |
VOL | +1.480 |
EH | +1.468 |
CONT | +1.442 |
Neg logit contributions | |
abl | -1.754 |
osexual | -1.705 |
xual | -1.615 |
wolves | -1.578 |
erer | -1.567 |
Token | coins |
Token ID | 10796 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
DIT | +0.838 |
RNA | +0.829 |
VOL | +0.772 |
EH | +0.766 |
CONT | +0.754 |
Neg logit contributions | |
abl | -0.685 |
osexual | -0.662 |
xual | -0.621 |
wolves | -0.605 |
erer | -0.600 |
Token | of |
Token ID | 286 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
abl | +0.293 |
osexual | +0.281 |
xual | +0.263 |
wolves | +0.258 |
erer | +0.256 |
Neg logit contributions | |
DIT | -0.335 |
RNA | -0.330 |
VOL | -0.309 |
EH | -0.304 |
CONT | -0.300 |
Token | the |
Token ID | 262 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
DIT | +0.198 |
RNA | +0.195 |
VOL | +0.181 |
EH | +0.180 |
CONT | +0.177 |
Neg logit contributions | |
abl | -0.184 |
osexual | -0.179 |
xual | -0.168 |
wolves | -0.164 |
erer | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
abl | +0.217 |
osexual | +0.208 |
xual | +0.196 |
erer | +0.191 |
wolves | +0.190 |
Neg logit contributions | |
DIT | -0.247 |
RNA | -0.245 |
VOL | -0.228 |
EH | -0.225 |
CONT | -0.223 |
Token | seemingly |
Token ID | 9775 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
DIT | +0.060 |
RNA | +0.059 |
VOL | +0.054 |
EH | +0.054 |
CONT | +0.053 |
Neg logit contributions | |
abl | -0.058 |
osexual | -0.056 |
xual | -0.053 |
wolves | -0.052 |
erer | -0.052 |
Token | making |
Token ID | 1642 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
abl | +1.103 |
osexual | +1.047 |
xual | +0.978 |
wolves | +0.965 |
erer | +0.962 |
Neg logit contributions | |
DIT | -1.230 |
RNA | -1.214 |
VOL | -1.124 |
EH | -1.107 |
thumbnails | -1.098 |
Token | it |
Token ID | 340 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
abl | +0.991 |
osexual | +0.941 |
xual | +0.886 |
wolves | +0.873 |
erer | +0.870 |
Neg logit contributions | |
DIT | -1.060 |
RNA | -1.048 |
VOL | -0.975 |
EH | -0.958 |
CONT | -0.947 |
Token | unsu |
Token ID | 48092 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
abl | +0.149 |
osexual | +0.143 |
xual | +0.134 |
wolves | +0.131 |
erer | +0.131 |
Neg logit contributions | |
DIT | -0.164 |
RNA | -0.162 |
VOL | -0.151 |
EH | -0.149 |
CONT | -0.147 |
Token | itable |
Token ID | 4674 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
DIT | +1.095 |
RNA | +1.082 |
VOL | +1.005 |
EH | +0.997 |
CONT | +0.981 |
Neg logit contributions | |
abl | -0.973 |
osexual | -0.943 |
xual | -0.887 |
wolves | -0.865 |
erer | -0.859 |
Token | for |
Token ID | 329 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
DIT | +3.224 |
RNA | +3.188 |
VOL | +2.965 |
EH | +2.957 |
CONT | +2.906 |
Neg logit contributions | |
abl | -2.545 |
osexual | -2.505 |
xual | -2.342 |
wolves | -2.279 |
erer | -2.266 |
Token | low |
Token ID | 1877 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
abl | +0.163 |
osexual | +0.157 |
xual | +0.149 |
wolves | +0.145 |
erer | +0.145 |
Neg logit contributions | |
DIT | -0.162 |
RNA | -0.160 |
VOL | -0.147 |
EH | -0.146 |
CONT | -0.144 |
Token | - |
Token ID | 12 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
abl | +0.322 |
osexual | +0.310 |
xual | +0.293 |
erer | +0.287 |
wolves | +0.286 |
Neg logit contributions | |
DIT | -0.308 |
RNA | -0.305 |
VOL | -0.280 |
EH | -0.277 |
CONT | -0.272 |
Token | speed |
Token ID | 12287 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
DIT | +0.008 |
RNA | +0.008 |
VOL | +0.007 |
EH | +0.007 |
CONT | +0.007 |
Neg logit contributions | |
abl | -0.009 |
osexual | -0.008 |
xual | -0.008 |
wolves | -0.008 |
erer | -0.008 |
Token | devices |
Token ID | 4410 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
DIT | +1.194 |
RNA | +1.180 |
VOL | +1.092 |
EH | +1.081 |
CONT | +1.063 |
Neg logit contributions | |
abl | -1.181 |
osexual | -1.142 |
xual | -1.079 |
wolves | -1.054 |
erer | -1.050 |
Token | ans |
Token ID | 504 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
abl | +1.270 |
osexual | +1.174 |
erer | +1.156 |
awn | +1.152 |
ier | +1.116 |
Neg logit contributions | |
DIT | -1.056 |
RNA | -0.985 |
VOL | -0.954 |
TEXT | -0.941 |
EH | -0.935 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
DIT | +0.176 |
RNA | +0.174 |
VOL | +0.162 |
EH | +0.160 |
CONT | +0.157 |
Neg logit contributions | |
abl | -0.156 |
osexual | -0.150 |
xual | -0.141 |
erer | -0.137 |
wolves | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
DIT | +0.279 |
RNA | +0.275 |
VOL | +0.256 |
EH | +0.252 |
CONT | +0.249 |
Neg logit contributions | |
abl | -0.246 |
osexual | -0.238 |
xual | -0.223 |
erer | -0.220 |
wolves | -0.219 |
Token | largest |
Token ID | 4387 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
DIT | +0.195 |
RNA | +0.194 |
VOL | +0.180 |
EH | +0.178 |
CONT | +0.175 |
Neg logit contributions | |
abl | -0.183 |
osexual | -0.176 |
xual | -0.164 |
erer | -0.162 |
wolves | -0.162 |
Token | contiguous |
Token ID | 48627 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
DIT | +0.370 |
RNA | +0.364 |
VOL | +0.336 |
EH | +0.331 |
CONT | +0.326 |
Neg logit contributions | |
abl | -0.419 |
osexual | -0.403 |
xual | -0.382 |
wolves | -0.375 |
erer | -0.375 |
Token | tidal |
Token ID | 40738 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
DIT | +1.636 |
RNA | +1.615 |
VOL | +1.493 |
EH | +1.479 |
CONT | +1.453 |
Neg logit contributions | |
abl | -1.666 |
osexual | -1.614 |
xual | -1.525 |
wolves | -1.491 |
erer | -1.482 |
Token | man |
Token ID | 582 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
DIT | +2.761 |
RNA | +2.718 |
VOL | +2.509 |
EH | +2.490 |
CONT | +2.442 |
Neg logit contributions | |
abl | -3.050 |
osexual | -2.979 |
xual | -2.852 |
wolves | -2.756 |
erer | -2.722 |
Token | gro |
Token ID | 27333 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
abl | +0.279 |
osexual | +0.268 |
erer | +0.254 |
xual | +0.253 |
awn | +0.252 |
Neg logit contributions | |
DIT | -0.202 |
RNA | -0.194 |
VOL | -0.180 |
CONT | -0.176 |
EH | -0.176 |
Token | ve |
Token ID | 303 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
DIT | +0.480 |
RNA | +0.462 |
VOL | +0.419 |
EH | +0.411 |
thumbnails | +0.405 |
Neg logit contributions | |
abl | -0.807 |
osexual | -0.792 |
xual | -0.752 |
erer | -0.739 |
wolves | -0.735 |
Token | forest |
Token ID | 8222 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
abl | +0.871 |
osexual | +0.823 |
xual | +0.773 |
erer | +0.769 |
wolves | +0.762 |
Neg logit contributions | |
DIT | -0.976 |
RNA | -0.966 |
VOL | -0.899 |
EH | -0.886 |
thumbnails | -0.877 |
Token | in |
Token ID | 287 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
DIT | +0.727 |
RNA | +0.718 |
VOL | +0.669 |
EH | +0.663 |
CONT | +0.651 |
Neg logit contributions | |
abl | -0.632 |
osexual | -0.608 |
xual | -0.571 |
wolves | -0.559 |
erer | -0.557 |
Token | is |
Token ID | 318 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
DIT | +0.088 |
RNA | +0.087 |
VOL | +0.080 |
EH | +0.080 |
CONT | +0.078 |
Neg logit contributions | |
abl | -0.086 |
osexual | -0.083 |
xual | -0.079 |
wolves | -0.077 |
erer | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
DIT | +0.096 |
RNA | +0.095 |
VOL | +0.089 |
EH | +0.088 |
CONT | +0.086 |
Neg logit contributions | |
abl | -0.084 |
osexual | -0.081 |
xual | -0.076 |
wolves | -0.075 |
erer | -0.074 |
Token | same |
Token ID | 976 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
DIT | +0.057 |
RNA | +0.056 |
VOL | +0.052 |
EH | +0.052 |
CONT | +0.051 |
Neg logit contributions | |
abl | -0.052 |
osexual | -0.051 |
xual | -0.048 |
wolves | -0.046 |
erer | -0.046 |
Token | instant |
Token ID | 9113 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
abl | +0.715 |
osexual | +0.691 |
xual | +0.648 |
wolves | +0.633 |
erer | +0.630 |
Neg logit contributions | |
DIT | -0.808 |
RNA | -0.800 |
VOL | -0.741 |
EH | -0.733 |
CONT | -0.722 |
Token | your |
Token ID | 534 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
abl | +0.578 |
osexual | +0.558 |
xual | +0.522 |
wolves | +0.510 |
erer | +0.509 |
Neg logit contributions | |
DIT | -0.641 |
RNA | -0.634 |
VOL | -0.589 |
EH | -0.581 |
CONT | -0.573 |
Token | Inner |
Token ID | 24877 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
DIT | +0.545 |
RNA | +0.539 |
VOL | +0.498 |
EH | +0.495 |
CONT | +0.485 |
Neg logit contributions | |
abl | -0.543 |
osexual | -0.527 |
xual | -0.498 |
wolves | -0.486 |
erer | -0.482 |
Token | Ass |
Token ID | 2195 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
DIT | +3.495 |
RNA | +3.491 |
Chatt | +3.244 |
EH | +3.239 |
VOL | +3.234 |
Neg logit contributions | |
abl | -2.129 |
osexual | -2.070 |
xual | -1.988 |
wolves | -1.923 |
erer | -1.833 |
Token | hole |
Token ID | 13207 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
abl | +0.112 |
osexual | +0.109 |
xual | +0.105 |
erer | +0.104 |
wolves | +0.104 |
Neg logit contributions | |
DIT | -0.030 |
RNA | -0.029 |
VOL | -0.024 |
EH | -0.024 |
CONT | -0.022 |
Token | grabs |
Token ID | 22378 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
DIT | +1.209 |
RNA | +1.192 |
VOL | +1.106 |
EH | +1.098 |
CONT | +1.083 |
Neg logit contributions | |
abl | -1.123 |
osexual | -1.094 |
xual | -1.033 |
wolves | -1.002 |
erer | -0.995 |
Token | his |
Token ID | 465 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
DIT | +0.264 |
RNA | +0.260 |
VOL | +0.241 |
EH | +0.239 |
CONT | +0.234 |
Neg logit contributions | |
abl | -0.251 |
osexual | -0.243 |
xual | -0.228 |
wolves | -0.225 |
erer | -0.223 |
Token | Ass |
Token ID | 2195 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
DIT | +0.268 |
RNA | +0.264 |
VOL | +0.245 |
EH | +0.242 |
CONT | +0.238 |
Neg logit contributions | |
abl | -0.263 |
osexual | -0.255 |
xual | -0.239 |
wolves | -0.235 |
erer | -0.234 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
DIT | +0.073 |
RNA | +0.073 |
VOL | +0.067 |
EH | +0.066 |
CONT | +0.065 |
Neg logit contributions | |
abl | -0.080 |
osexual | -0.078 |
xual | -0.073 |
wolves | -0.072 |
erer | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
DIT | +0.298 |
RNA | +0.295 |
VOL | +0.273 |
EH | +0.271 |
CONT | +0.268 |
Neg logit contributions | |
abl | -0.265 |
osexual | -0.257 |
xual | -0.242 |
wolves | -0.236 |
erer | -0.235 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
DIT | +0.205 |
RNA | +0.202 |
VOL | +0.188 |
EH | +0.186 |
CONT | +0.183 |
Neg logit contributions | |
abl | -0.185 |
osexual | -0.179 |
xual | -0.169 |
wolves | -0.165 |
erer | -0.163 |
Token | meaningless |
Token ID | 24513 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
DIT | +0.273 |
RNA | +0.271 |
VOL | +0.250 |
EH | +0.248 |
CONT | +0.243 |
Neg logit contributions | |
abl | -0.279 |
osexual | -0.271 |
xual | -0.255 |
wolves | -0.250 |
erer | -0.250 |
Token | graduate |
Token ID | 10428 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
DIT | +0.354 |
RNA | +0.350 |
VOL | +0.324 |
EH | +0.322 |
CONT | +0.316 |
Neg logit contributions | |
abl | -0.336 |
osexual | -0.326 |
xual | -0.305 |
wolves | -0.299 |
erer | -0.299 |
Token | degree |
Token ID | 4922 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
DIT | +0.745 |
RNA | +0.735 |
VOL | +0.684 |
EH | +0.680 |
CONT | +0.668 |
Neg logit contributions | |
abl | -0.630 |
osexual | -0.610 |
xual | -0.571 |
erer | -0.556 |
wolves | -0.554 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
DIT | +2.966 |
RNA | +2.922 |
VOL | +2.698 |
EH | +2.697 |
CONT | +2.649 |
Neg logit contributions | |
abl | -2.741 |
osexual | -2.686 |
xual | -2.507 |
wolves | -2.495 |
awn | -2.418 |
Token | I |
Token ID | 314 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
DIT | +0.310 |
RNA | +0.307 |
VOL | +0.284 |
EH | +0.282 |
CONT | +0.277 |
Neg logit contributions | |
abl | -0.295 |
osexual | -0.286 |
xual | -0.269 |
wolves | -0.264 |
erer | -0.262 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
DIT | +0.025 |
RNA | +0.025 |
VOL | +0.023 |
EH | +0.022 |
CONT | +0.022 |
Neg logit contributions | |
abl | -0.029 |
osexual | -0.028 |
xual | -0.027 |
wolves | -0.026 |
erer | -0.026 |
Token | grinding |
Token ID | 28436 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
DIT | +0.270 |
RNA | +0.267 |
VOL | +0.248 |
EH | +0.246 |
CONT | +0.242 |
Neg logit contributions | |
abl | -0.239 |
osexual | -0.231 |
xual | -0.217 |
wolves | -0.212 |
erer | -0.211 |
Token | out |
Token ID | 503 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
abl | +0.479 |
osexual | +0.462 |
xual | +0.432 |
erer | +0.424 |
wolves | +0.424 |
Neg logit contributions | |
DIT | -0.549 |
RNA | -0.544 |
VOL | -0.504 |
EH | -0.500 |
CONT | -0.493 |
Token | He |
Token ID | 679 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
abl | +0.284 |
osexual | +0.274 |
xual | +0.256 |
wolves | +0.250 |
erer | +0.248 |
Neg logit contributions | |
DIT | -0.359 |
RNA | -0.355 |
VOL | -0.331 |
EH | -0.329 |
CONT | -0.323 |
Token | also |
Token ID | 635 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
DIT | +0.061 |
RNA | +0.060 |
VOL | +0.056 |
EH | +0.055 |
CONT | +0.054 |
Neg logit contributions | |
abl | -0.058 |
osexual | -0.056 |
xual | -0.053 |
wolves | -0.052 |
erer | -0.051 |
Token | performs |
Token ID | 17706 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
abl | +0.175 |
osexual | +0.169 |
xual | +0.159 |
wolves | +0.156 |
erer | +0.155 |
Neg logit contributions | |
DIT | -0.187 |
RNA | -0.184 |
VOL | -0.171 |
EH | -0.169 |
CONT | -0.166 |
Token | " |
Token ID | 366 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
DIT | +1.073 |
RNA | +1.060 |
VOL | +0.986 |
EH | +0.977 |
CONT | +0.962 |
Neg logit contributions | |
abl | -0.969 |
osexual | -0.939 |
xual | -0.885 |
wolves | -0.861 |
erer | -0.856 |
Token | Sm |
Token ID | 7556 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
abl | +0.363 |
osexual | +0.351 |
xual | +0.330 |
wolves | +0.328 |
erer | +0.324 |
Neg logit contributions | |
DIT | -0.322 |
RNA | -0.317 |
VOL | -0.291 |
EH | -0.289 |
CONT | -0.283 |
Token | ells |
Token ID | 19187 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
abl | +0.665 |
osexual | +0.635 |
xual | +0.578 |
wolves | +0.572 |
erer | +0.572 |
Neg logit contributions | |
DIT | -0.924 |
RNA | -0.902 |
VOL | -0.857 |
EH | -0.847 |
CONT | -0.839 |
Token | Like |
Token ID | 4525 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
abl | +3.112 |
osexual | +3.001 |
wolves | +2.787 |
erer | +2.781 |
awn | +2.759 |
Neg logit contributions | |
DIT | -3.205 |
RNA | -3.115 |
VOL | -2.931 |
EH | -2.893 |
TEXT | -2.858 |
Token | Teen |
Token ID | 21432 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
DIT | +0.728 |
RNA | +0.720 |
VOL | +0.668 |
EH | +0.663 |
CONT | +0.652 |
Neg logit contributions | |
abl | -0.650 |
osexual | -0.630 |
xual | -0.594 |
wolves | -0.578 |
erer | -0.574 |
Token | Spirit |
Token ID | 7710 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
abl | +1.628 |
osexual | +1.596 |
erer | +1.457 |
wolves | +1.433 |
awn | +1.424 |
Neg logit contributions | |
DIT | -1.585 |
RNA | -1.503 |
thumbnails | -1.416 |
VOL | -1.401 |
EH | -1.392 |
Token | " |
Token ID | 1 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
DIT | +0.355 |
RNA | +0.348 |
VOL | +0.314 |
EH | +0.311 |
CONT | +0.305 |
Neg logit contributions | |
abl | -0.558 |
osexual | -0.544 |
xual | -0.517 |
wolves | -0.508 |
erer | -0.506 |
Token | in |
Token ID | 287 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
abl | +0.198 |
osexual | +0.191 |
xual | +0.179 |
wolves | +0.175 |
erer | +0.174 |
Neg logit contributions | |
DIT | -0.231 |
RNA | -0.228 |
VOL | -0.212 |
EH | -0.210 |
CONT | -0.207 |
Token | newly |
Token ID | 8308 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
abl | +0.233 |
osexual | +0.226 |
xual | +0.212 |
wolves | +0.208 |
erer | +0.207 |
Neg logit contributions | |
DIT | -0.256 |
RNA | -0.253 |
VOL | -0.235 |
EH | -0.233 |
CONT | -0.228 |
Token | implemented |
Token ID | 9177 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
DIT | +0.803 |
RNA | +0.792 |
VOL | +0.734 |
EH | +0.727 |
CONT | +0.715 |
Neg logit contributions | |
abl | -0.769 |
osexual | -0.745 |
xual | -0.702 |
wolves | -0.686 |
erer | -0.681 |
Token | features |
Token ID | 3033 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
abl | +0.415 |
osexual | +0.402 |
xual | +0.376 |
wolves | +0.371 |
erer | +0.368 |
Neg logit contributions | |
DIT | -0.456 |
RNA | -0.450 |
VOL | -0.419 |
EH | -0.413 |
CONT | -0.407 |
Token | such |
Token ID | 884 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
abl | +0.029 |
osexual | +0.028 |
xual | +0.026 |
wolves | +0.025 |
erer | +0.025 |
Neg logit contributions | |
DIT | -0.033 |
RNA | -0.033 |
VOL | -0.031 |
EH | -0.030 |
CONT | -0.030 |
Token | as |
Token ID | 355 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
DIT | +0.416 |
RNA | +0.411 |
VOL | +0.383 |
EH | +0.378 |
CONT | +0.369 |
Neg logit contributions | |
abl | -0.381 |
osexual | -0.367 |
xual | -0.344 |
wolves | -0.340 |
erer | -0.338 |
Token | climbing |
Token ID | 14281 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
DIT | +0.403 |
RNA | +0.398 |
VOL | +0.370 |
EH | +0.367 |
CONT | +0.361 |
Neg logit contributions | |
abl | -0.364 |
osexual | -0.352 |
xual | -0.332 |
wolves | -0.323 |
erer | -0.321 |
Token | and |
Token ID | 290 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
abl | +2.834 |
osexual | +2.692 |
wolves | +2.535 |
xual | +2.489 |
erer | +2.469 |
Neg logit contributions | |
DIT | -3.332 |
RNA | -3.303 |
VOL | -3.045 |
EH | -3.030 |
CONT | -2.969 |
Token | weather |
Token ID | 6193 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
DIT | +0.059 |
RNA | +0.058 |
VOL | +0.054 |
EH | +0.054 |
CONT | +0.053 |
Neg logit contributions | |
abl | -0.056 |
osexual | -0.054 |
xual | -0.051 |
wolves | -0.050 |
erer | -0.050 |
Token | on |
Token ID | 319 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
abl | +1.175 |
osexual | +1.123 |
xual | +1.048 |
wolves | +1.046 |
erer | +1.035 |
Neg logit contributions | |
DIT | -1.276 |
RNA | -1.265 |
VOL | -1.169 |
EH | -1.154 |
CONT | -1.138 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
abl | +0.006 |
osexual | +0.005 |
xual | +0.005 |
wolves | +0.005 |
erer | +0.005 |
Neg logit contributions | |
DIT | -0.006 |
RNA | -0.006 |
VOL | -0.005 |
EH | -0.005 |
CONT | -0.005 |
Token | game |
Token ID | 983 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
abl | +0.010 |
osexual | +0.009 |
xual | +0.009 |
wolves | +0.009 |
erer | +0.009 |
Neg logit contributions | |
DIT | -0.011 |
RNA | -0.011 |
VOL | -0.010 |
EH | -0.010 |
CONT | -0.010 |
Token | edit |
Token ID | 4370 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
DIT | +0.556 |
RNA | +0.548 |
VOL | +0.506 |
EH | +0.503 |
CONT | +0.492 |
Neg logit contributions | |
abl | -0.563 |
osexual | -0.546 |
xual | -0.514 |
wolves | -0.504 |
erer | -0.501 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
DIT | +0.405 |
RNA | +0.399 |
VOL | +0.360 |
EH | +0.356 |
CONT | +0.347 |
Neg logit contributions | |
abl | -0.622 |
osexual | -0.606 |
xual | -0.578 |
wolves | -0.567 |
erer | -0.565 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
DIT | +0.279 |
RNA | +0.276 |
VOL | +0.254 |
EH | +0.251 |
CONT | +0.246 |
Neg logit contributions | |
abl | -0.321 |
osexual | -0.311 |
xual | -0.292 |
wolves | -0.289 |
erer | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
DIT | +0.297 |
RNA | +0.292 |
VOL | +0.270 |
EH | +0.266 |
Chatt | +0.261 |
Neg logit contributions | |
abl | -0.338 |
osexual | -0.325 |
xual | -0.304 |
erer | -0.303 |
wolves | -0.303 |
Token | O |
Token ID | 46 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
DIT | +0.301 |
RNA | +0.297 |
VOL | +0.273 |
EH | +0.270 |
CONT | +0.265 |
Neg logit contributions | |
abl | -0.342 |
osexual | -0.333 |
xual | -0.313 |
wolves | -0.309 |
erer | -0.306 |
Token | ka |
Token ID | 4914 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
abl | +1.036 |
osexual | +1.010 |
xual | +0.949 |
wolves | +0.930 |
erer | +0.929 |
Neg logit contributions | |
DIT | -1.020 |
RNA | -0.999 |
VOL | -0.924 |
EH | -0.913 |
CONT | -0.909 |
Token | for |
Token ID | 1640 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
abl | +2.953 |
osexual | +2.845 |
awn | +2.651 |
xual | +2.603 |
erer | +2.582 |
Neg logit contributions | |
DIT | -3.159 |
RNA | -3.028 |
VOL | -2.861 |
EH | -2.811 |
TEXT | -2.804 |
Token | played |
Token ID | 2826 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
abl | +1.014 |
osexual | +0.983 |
xual | +0.923 |
awn | +0.912 |
erer | +0.906 |
Neg logit contributions | |
DIT | -1.062 |
RNA | -1.046 |
VOL | -0.958 |
EH | -0.953 |
CONT | -0.937 |
Token | one |
Token ID | 530 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
abl | +0.339 |
osexual | +0.329 |
xual | +0.306 |
erer | +0.300 |
wolves | +0.298 |
Neg logit contributions | |
DIT | -0.395 |
RNA | -0.391 |
VOL | -0.360 |
EH | -0.358 |
CONT | -0.352 |
Token | season |
Token ID | 1622 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
abl | +0.178 |
osexual | +0.174 |
xual | +0.161 |
erer | +0.157 |
wolves | +0.157 |
Neg logit contributions | |
DIT | -0.230 |
RNA | -0.226 |
VOL | -0.210 |
EH | -0.210 |
CONT | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
DIT | +0.084 |
RNA | +0.083 |
VOL | +0.078 |
EH | +0.077 |
thumbnails | +0.076 |
Neg logit contributions | |
abl | -0.067 |
osexual | -0.065 |
xual | -0.060 |
erer | -0.058 |
wolves | -0.058 |
Token | Angular |
Token ID | 28147 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
abl | +0.413 |
osexual | +0.400 |
xual | +0.375 |
wolves | +0.367 |
erer | +0.366 |
Neg logit contributions | |
DIT | -0.453 |
RNA | -0.447 |
VOL | -0.416 |
EH | -0.412 |
CONT | -0.405 |
Token | tutorial |
Token ID | 11808 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
abl | +0.475 |
osexual | +0.461 |
xual | +0.435 |
erer | +0.426 |
wolves | +0.426 |
Neg logit contributions | |
DIT | -0.435 |
RNA | -0.430 |
VOL | -0.397 |
EH | -0.392 |
CONT | -0.385 |
Token | : |
Token ID | 25 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
DIT | +0.086 |
RNA | +0.085 |
VOL | +0.079 |
EH | +0.078 |
CONT | +0.077 |
Neg logit contributions | |
abl | -0.075 |
osexual | -0.072 |
xual | -0.068 |
wolves | -0.066 |
erer | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
abl | +0.244 |
osexual | +0.237 |
xual | +0.225 |
wolves | +0.220 |
erer | +0.219 |
Neg logit contributions | |
DIT | -0.212 |
RNA | -0.209 |
VOL | -0.192 |
EH | -0.190 |
CONT | -0.186 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
abl | +0.720 |
osexual | +0.684 |
erer | +0.644 |
wolves | +0.637 |
awn | +0.634 |
Neg logit contributions | |
DIT | -0.685 |
RNA | -0.672 |
VOL | -0.627 |
EH | -0.616 |
Chatt | -0.610 |
Token | < |
Token ID | 27 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
abl | +0.523 |
osexual | +0.505 |
xual | +0.475 |
wolves | +0.470 |
erer | +0.468 |
Neg logit contributions | |
DIT | -0.458 |
RNA | -0.451 |
VOL | -0.415 |
EH | -0.411 |
Chatt | -0.406 |
Token | body |
Token ID | 2618 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
abl | +2.808 |
osexual | +2.719 |
xual | +2.510 |
erer | +2.504 |
wolves | +2.458 |
Neg logit contributions | |
DIT | -3.232 |
RNA | -3.150 |
EH | -2.950 |
VOL | -2.942 |
Chatt | -2.920 |
Token | ng |
Token ID | 23370 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
DIT | +0.207 |
RNA | +0.204 |
VOL | +0.192 |
EH | +0.191 |
CONT | +0.187 |
Neg logit contributions | |
abl | -0.142 |
osexual | -0.136 |
xual | -0.126 |
wolves | -0.123 |
erer | -0.123 |
Token | - |
Token ID | 12 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
abl | +1.250 |
osexual | +1.207 |
xual | +1.117 |
wolves | +1.110 |
erer | +1.104 |
Neg logit contributions | |
DIT | -1.346 |
RNA | -1.318 |
VOL | -1.231 |
EH | -1.214 |
Chatt | -1.199 |
Token | controller |
Token ID | 36500 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
DIT | +0.094 |
RNA | +0.093 |
VOL | +0.087 |
EH | +0.086 |
CONT | +0.085 |
Neg logit contributions | |
abl | -0.086 |
osexual | -0.083 |
xual | -0.078 |
wolves | -0.076 |
erer | -0.076 |
Token | =" |
Token ID | 2625 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
abl | +0.265 |
osexual | +0.255 |
xual | +0.235 |
wolves | +0.228 |
erer | +0.226 |
Neg logit contributions | |
DIT | -0.445 |
RNA | -0.441 |
VOL | -0.414 |
EH | -0.412 |
CONT | -0.406 |
Token | Trent |
Token ID | 24269 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
abl | +1.102 |
osexual | +1.069 |
wolves | +1.011 |
xual | +1.008 |
awn | +1.007 |
Neg logit contributions | |
DIT | -0.559 |
RNA | -0.543 |
VOL | -0.496 |
EH | -0.495 |
CONT | -0.469 |
Token | in |
Token ID | 259 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
abl | +1.731 |
osexual | +1.669 |
xual | +1.565 |
wolves | +1.527 |
erer | +1.525 |
Neg logit contributions | |
DIT | -1.806 |
RNA | -1.787 |
VOL | -1.656 |
EH | -1.648 |
CONT | -1.606 |
Token | ( |
Token ID | 357 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
abl | +0.347 |
osexual | +0.331 |
xual | +0.301 |
erer | +0.298 |
wolves | +0.297 |
Neg logit contributions | |
DIT | -0.556 |
RNA | -0.549 |
VOL | -0.518 |
EH | -0.512 |
CONT | -0.508 |
Token | O |
Token ID | 46 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
abl | +0.540 |
osexual | +0.520 |
wolves | +0.484 |
erer | +0.483 |
xual | +0.480 |
Neg logit contributions | |
DIT | -0.445 |
RNA | -0.440 |
EH | -0.400 |
VOL | -0.400 |
Chatt | -0.395 |
Token | mega |
Token ID | 13731 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
abl | +1.001 |
osexual | +0.969 |
xual | +0.909 |
wolves | +0.899 |
erer | +0.895 |
Neg logit contributions | |
DIT | -0.941 |
RNA | -0.930 |
VOL | -0.851 |
EH | -0.846 |
TEXT | -0.837 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
abl | +0.551 |
osexual | +0.531 |
xual | +0.496 |
wolves | +0.481 |
erer | +0.477 |
Neg logit contributions | |
DIT | -0.782 |
RNA | -0.773 |
VOL | -0.724 |
EH | -0.719 |
CONT | -0.708 |
Token | - |
Token ID | 532 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
abl | +2.845 |
osexual | +2.718 |
xual | +2.552 |
erer | +2.524 |
wolves | +2.486 |
Neg logit contributions | |
DIT | -3.158 |
RNA | -3.116 |
VOL | -2.864 |
EH | -2.839 |
thumbnails | -2.802 |
Token | Quick |
Token ID | 12029 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
abl | +0.266 |
osexual | +0.258 |
xual | +0.240 |
wolves | +0.240 |
erer | +0.239 |
Neg logit contributions | |
DIT | -0.218 |
RNA | -0.216 |
VOL | -0.198 |
EH | -0.198 |
TEXT | -0.193 |
Token | step |
Token ID | 9662 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
abl | +0.228 |
osexual | +0.220 |
erer | +0.205 |
wolves | +0.205 |
xual | +0.203 |
Neg logit contributions | |
DIT | -0.248 |
RNA | -0.243 |
VOL | -0.226 |
EH | -0.224 |
CONT | -0.220 |
Token | ) |
Token ID | 8 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
abl | +0.831 |
osexual | +0.796 |
xual | +0.752 |
wolves | +0.737 |
erer | +0.736 |
Neg logit contributions | |
DIT | -0.824 |
RNA | -0.818 |
VOL | -0.757 |
EH | -0.753 |
CONT | -0.737 |
Token | s |
Token ID | 264 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
abl | +0.312 |
osexual | +0.304 |
xual | +0.290 |
wolves | +0.285 |
erer | +0.284 |
Neg logit contributions | |
DIT | -0.191 |
RNA | -0.188 |
VOL | -0.169 |
EH | -0.167 |
CONT | -0.163 |
Token | all |
Token ID | 477 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
DIT | +0.873 |
RNA | +0.861 |
VOL | +0.795 |
EH | +0.784 |
CONT | +0.777 |
Neg logit contributions | |
abl | -0.896 |
osexual | -0.870 |
xual | -0.831 |
wolves | -0.810 |
erer | -0.800 |
Token | materials |
Token ID | 5696 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
DIT | +0.650 |
RNA | +0.643 |
VOL | +0.594 |
EH | +0.589 |
CONT | +0.580 |
Neg logit contributions | |
abl | -0.635 |
osexual | -0.615 |
xual | -0.581 |
wolves | -0.568 |
erer | -0.562 |
Token | to |
Token ID | 284 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
abl | +0.320 |
osexual | +0.308 |
xual | +0.291 |
wolves | +0.281 |
erer | +0.277 |
Neg logit contributions | |
DIT | -0.447 |
RNA | -0.443 |
VOL | -0.413 |
EH | -0.409 |
CONT | -0.406 |
Token | v |
Token ID | 410 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
DIT | +0.011 |
RNA | +0.011 |
VOL | +0.010 |
EH | +0.010 |
CONT | +0.010 |
Neg logit contributions | |
abl | -0.016 |
osexual | -0.016 |
xual | -0.015 |
wolves | -0.015 |
erer | -0.015 |
Token | p |
Token ID | 79 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
abl | +1.005 |
osexual | +0.968 |
xual | +0.908 |
awn | +0.890 |
wolves | +0.889 |
Neg logit contributions | |
DIT | -1.022 |
RNA | -0.998 |
VOL | -0.931 |
EH | -0.917 |
CONT | -0.909 |
Token | @ |
Token ID | 31 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
DIT | +0.035 |
RNA | +0.034 |
VOL | +0.032 |
EH | +0.032 |
CONT | +0.031 |
Neg logit contributions | |
abl | -0.032 |
osexual | -0.031 |
xual | -0.029 |
wolves | -0.028 |
erer | -0.028 |
Token | peace |
Token ID | 22988 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
abl | +2.680 |
osexual | +2.540 |
awn | +2.366 |
xual | +2.351 |
wolves | +2.344 |
Neg logit contributions | |
DIT | -3.165 |
RNA | -3.124 |
VOL | -2.886 |
EH | -2.877 |
Chatt | -2.870 |
Token | cor |
Token ID | 10215 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
DIT | +0.549 |
RNA | +0.542 |
VOL | +0.503 |
EH | +0.500 |
CONT | +0.491 |
Neg logit contributions | |
abl | -0.495 |
osexual | -0.479 |
xual | -0.451 |
wolves | -0.440 |
erer | -0.437 |
Token | ps |
Token ID | 862 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
DIT | +1.015 |
RNA | +0.996 |
VOL | +0.899 |
EH | +0.895 |
CONT | +0.873 |
Neg logit contributions | |
abl | -1.576 |
osexual | -1.533 |
xual | -1.458 |
wolves | -1.441 |
erer | -1.427 |
Token | connect |
Token ID | 8443 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
DIT | +0.815 |
RNA | +0.802 |
VOL | +0.727 |
EH | +0.720 |
CONT | +0.704 |
Neg logit contributions | |
abl | -1.187 |
osexual | -1.157 |
xual | -1.103 |
wolves | -1.081 |
erer | -1.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
DIT | +1.505 |
RNA | +1.488 |
VOL | +1.379 |
EH | +1.369 |
CONT | +1.347 |
Neg logit contributions | |
abl | -1.365 |
osexual | -1.325 |
xual | -1.250 |
wolves | -1.217 |
erer | -1.206 |
Token | my |
Token ID | 616 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
abl | +0.425 |
osexual | +0.408 |
xual | +0.381 |
wolves | +0.371 |
erer | +0.369 |
Neg logit contributions | |
DIT | -0.549 |
RNA | -0.545 |
VOL | -0.507 |
EH | -0.505 |
CONT | -0.495 |
Token | comparison |
Token ID | 7208 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
abl | +0.218 |
osexual | +0.210 |
xual | +0.194 |
wolves | +0.188 |
erer | +0.187 |
Neg logit contributions | |
DIT | -0.347 |
RNA | -0.343 |
VOL | -0.322 |
EH | -0.320 |
CONT | -0.315 |
Token | data |
Token ID | 1366 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
DIT | +0.694 |
RNA | +0.685 |
VOL | +0.637 |
EH | +0.632 |
CONT | +0.622 |
Neg logit contributions | |
abl | -0.609 |
osexual | -0.590 |
xual | -0.555 |
wolves | -0.541 |
erer | -0.537 |
Token | above |
Token ID | 2029 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
abl | +0.480 |
osexual | +0.460 |
xual | +0.433 |
erer | +0.424 |
wolves | +0.424 |
Neg logit contributions | |
DIT | -0.534 |
RNA | -0.530 |
VOL | -0.491 |
EH | -0.486 |
CONT | -0.480 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
abl | +0.699 |
osexual | +0.672 |
xual | +0.633 |
wolves | +0.616 |
erer | +0.616 |
Neg logit contributions | |
DIT | -0.805 |
RNA | -0.798 |
VOL | -0.741 |
EH | -0.734 |
CONT | -0.724 |
Token | vec |
Token ID | 43030 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
abl | +0.433 |
osexual | +0.419 |
xual | +0.394 |
wolves | +0.387 |
erer | +0.385 |
Neg logit contributions | |
DIT | -0.450 |
RNA | -0.445 |
VOL | -0.413 |
EH | -0.409 |
CONT | -0.401 |
Token | 4 |
Token ID | 19 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
abl | +2.698 |
osexual | +2.545 |
xual | +2.405 |
wolves | +2.361 |
erer | +2.357 |
Neg logit contributions | |
DIT | -3.165 |
RNA | -3.079 |
VOL | -2.889 |
EH | -2.867 |
thumbnails | -2.816 |
Token | has |
Token ID | 468 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
abl | +0.139 |
osexual | +0.134 |
xual | +0.127 |
wolves | +0.124 |
erer | +0.123 |
Neg logit contributions | |
DIT | -0.143 |
RNA | -0.141 |
VOL | -0.131 |
EH | -0.129 |
CONT | -0.127 |
Token | all |
Token ID | 477 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
DIT | +0.159 |
RNA | +0.157 |
VOL | +0.146 |
EH | +0.145 |
CONT | +0.143 |
Neg logit contributions | |
abl | -0.145 |
osexual | -0.141 |
xual | -0.132 |
wolves | -0.129 |
erer | -0.128 |
Token | default |
Token ID | 4277 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
DIT | +0.080 |
RNA | +0.079 |
VOL | +0.073 |
EH | +0.073 |
CONT | +0.072 |
Neg logit contributions | |
abl | -0.072 |
osexual | -0.070 |
xual | -0.066 |
wolves | -0.064 |
erer | -0.064 |
Token | values |
Token ID | 3815 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
abl | +1.040 |
osexual | +0.999 |
xual | +0.934 |
wolves | +0.919 |
erer | +0.915 |
Neg logit contributions | |
DIT | -1.160 |
RNA | -1.152 |
VOL | -1.068 |
EH | -1.059 |
CONT | -1.037 |
Token |
|
Token ID | 198 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
abl | +0.105 |
osexual | +0.100 |
erer | +0.094 |
wolves | +0.094 |
xual | +0.093 |
Neg logit contributions | |
DIT | -0.094 |
RNA | -0.093 |
VOL | -0.086 |
EH | -0.085 |
Chatt | -0.083 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
abl | +0.053 |
osexual | +0.052 |
xual | +0.049 |
wolves | +0.048 |
erer | +0.048 |
Neg logit contributions | |
DIT | -0.048 |
RNA | -0.047 |
VOL | -0.043 |
EH | -0.043 |
CONT | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
abl | +0.355 |
osexual | +0.343 |
xual | +0.324 |
wolves | +0.317 |
erer | +0.313 |
Neg logit contributions | |
DIT | -0.399 |
RNA | -0.394 |
VOL | -0.364 |
EH | -0.362 |
CONT | -0.355 |
Token | 000 |
Token ID | 830 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
abl | +0.408 |
osexual | +0.395 |
xual | +0.375 |
wolves | +0.366 |
erer | +0.364 |
Neg logit contributions | |
DIT | -0.387 |
RNA | -0.383 |
VOL | -0.352 |
EH | -0.349 |
CONT | -0.343 |
Token | App |
Token ID | 2034 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
DIT | +0.048 |
RNA | +0.048 |
VOL | +0.044 |
EH | +0.044 |
CONT | +0.043 |
Neg logit contributions | |
abl | -0.040 |
osexual | -0.039 |
xual | -0.037 |
wolves | -0.036 |
erer | -0.035 |
Token | rox |
Token ID | 13907 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
abl | +1.853 |
osexual | +1.788 |
xual | +1.639 |
wolves | +1.634 |
erer | +1.612 |
Neg logit contributions | |
DIT | -2.356 |
RNA | -2.332 |
VOL | -2.175 |
EH | -2.162 |
CONT | -2.133 |
Token | imate |
Token ID | 1920 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
abl | +2.733 |
osexual | +2.630 |
xual | +2.482 |
wolves | +2.403 |
erer | +2.395 |
Neg logit contributions | |
DIT | -3.110 |
RNA | -3.057 |
VOL | -2.845 |
EH | -2.822 |
CONT | -2.793 |
Token | number |
Token ID | 1271 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
abl | +0.430 |
osexual | +0.417 |
xual | +0.396 |
wolves | +0.388 |
erer | +0.384 |
Neg logit contributions | |
DIT | -0.385 |
RNA | -0.379 |
VOL | -0.348 |
EH | -0.345 |
CONT | -0.340 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
DIT | +1.085 |
RNA | +1.075 |
VOL | +1.000 |
EH | +0.990 |
CONT | +0.973 |
Neg logit contributions | |
abl | -1.030 |
osexual | -1.004 |
xual | -0.941 |
wolves | -0.925 |
erer | -0.920 |
Token | adult |
Token ID | 4044 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
DIT | +0.024 |
RNA | +0.023 |
VOL | +0.022 |
EH | +0.022 |
CONT | +0.021 |
Neg logit contributions | |
abl | -0.018 |
osexual | -0.017 |
xual | -0.016 |
wolves | -0.015 |
erer | -0.015 |
Token | Buddh |
Token ID | 20921 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
abl | +0.521 |
osexual | +0.504 |
xual | +0.468 |
wolves | +0.457 |
erer | +0.454 |
Neg logit contributions | |
DIT | -0.735 |
RNA | -0.726 |
VOL | -0.678 |
EH | -0.675 |
CONT | -0.665 |
Token | m |
Token ID | 76 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
abl | +0.200 |
osexual | +0.192 |
wolves | +0.182 |
xual | +0.181 |
erer | +0.180 |
Neg logit contributions | |
DIT | -0.149 |
RNA | -0.147 |
EH | -0.134 |
VOL | -0.134 |
CONT | -0.131 |
Token | ote |
Token ID | 1258 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
abl | +0.204 |
osexual | +0.198 |
xual | +0.185 |
erer | +0.184 |
wolves | +0.183 |
Neg logit contributions | |
DIT | -0.168 |
RNA | -0.164 |
VOL | -0.152 |
EH | -0.150 |
CONT | -0.148 |
Token | ( |
Token ID | 357 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
DIT | +0.479 |
RNA | +0.473 |
VOL | +0.441 |
EH | +0.438 |
Chatt | +0.431 |
Neg logit contributions | |
abl | -0.362 |
osexual | -0.350 |
xual | -0.330 |
wolves | -0.322 |
erer | -0.312 |
Token | O |
Token ID | 46 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
abl | +0.962 |
osexual | +0.921 |
wolves | +0.860 |
erer | +0.858 |
xual | +0.851 |
Neg logit contributions | |
DIT | -0.820 |
RNA | -0.813 |
VOL | -0.739 |
Chatt | -0.737 |
EH | -0.735 |
Token | mega |
Token ID | 13731 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
abl | +1.194 |
osexual | +1.162 |
xual | +1.102 |
wolves | +1.087 |
erer | +1.082 |
Neg logit contributions | |
DIT | -0.791 |
RNA | -0.780 |
VOL | -0.698 |
EH | -0.698 |
%] | -0.684 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
abl | +0.685 |
osexual | +0.656 |
xual | +0.601 |
erer | +0.585 |
wolves | +0.584 |
Neg logit contributions | |
DIT | -1.149 |
RNA | -1.130 |
VOL | -1.080 |
EH | -1.071 |
CONT | -1.055 |
Token | - |
Token ID | 532 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
abl | +2.620 |
osexual | +2.443 |
erer | +2.330 |
xual | +2.284 |
wolves | +2.266 |
Neg logit contributions | |
DIT | -3.038 |
RNA | -3.030 |
VOL | -2.799 |
EH | -2.777 |
thumbnails | -2.757 |
Token | Quick |
Token ID | 12029 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
abl | +0.234 |
osexual | +0.225 |
xual | +0.212 |
erer | +0.210 |
wolves | +0.209 |
Neg logit contributions | |
DIT | -0.195 |
RNA | -0.190 |
VOL | -0.176 |
EH | -0.175 |
CONT | -0.171 |
Token | step |
Token ID | 9662 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
abl | +0.172 |
osexual | +0.160 |
wolves | +0.150 |
erer | +0.149 |
xual | +0.149 |
Neg logit contributions | |
DIT | -0.263 |
RNA | -0.258 |
EH | -0.243 |
VOL | -0.243 |
Chatt | -0.240 |
Token | ) |
Token ID | 8 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
abl | +0.903 |
osexual | +0.850 |
erer | +0.802 |
wolves | +0.793 |
xual | +0.787 |
Neg logit contributions | |
DIT | -0.991 |
RNA | -0.978 |
VOL | -0.919 |
EH | -0.904 |
thumbnails | -0.896 |
Token | s |
Token ID | 264 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
abl | +0.306 |
osexual | +0.298 |
xual | +0.285 |
wolves | +0.280 |
erer | +0.278 |
Neg logit contributions | |
DIT | -0.184 |
RNA | -0.180 |
VOL | -0.162 |
EH | -0.161 |
CONT | -0.157 |
Token | full |
Token ID | 1336 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
abl | +0.199 |
osexual | +0.193 |
xual | +0.182 |
wolves | +0.179 |
erer | +0.178 |
Neg logit contributions | |
DIT | -0.174 |
RNA | -0.171 |
VOL | -0.156 |
EH | -0.156 |
thumbnails | -0.152 |
Token | : |
Token ID | 25 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
abl | +1.349 |
osexual | +1.300 |
xual | +1.211 |
wolves | +1.183 |
erer | +1.180 |
Neg logit contributions | |
DIT | -1.692 |
RNA | -1.677 |
VOL | -1.564 |
EH | -1.548 |
thumbnails | -1.517 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
abl | +0.430 |
osexual | +0.418 |
xual | +0.397 |
wolves | +0.389 |
erer | +0.386 |
Neg logit contributions | |
DIT | -0.359 |
RNA | -0.354 |
VOL | -0.325 |
EH | -0.322 |
CONT | -0.316 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
abl | +0.748 |
osexual | +0.709 |
erer | +0.665 |
wolves | +0.658 |
awn | +0.652 |
Neg logit contributions | |
DIT | -0.731 |
RNA | -0.722 |
VOL | -0.667 |
EH | -0.663 |
thumbnails | -0.659 |
Token | Full |
Token ID | 13295 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
abl | +0.642 |
osexual | +0.620 |
xual | +0.574 |
wolves | +0.574 |
erer | +0.573 |
Neg logit contributions | |
DIT | -0.510 |
RNA | -0.502 |
EH | -0.454 |
VOL | -0.451 |
Chatt | -0.451 |
Token | Faith |
Token ID | 16463 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
abl | +1.778 |
osexual | +1.695 |
erer | +1.586 |
awn | +1.568 |
wolves | +1.566 |
Neg logit contributions | |
DIT | -1.717 |
RNA | -1.700 |
VOL | -1.572 |
EH | -1.557 |
CONT | -1.553 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
abl | +2.821 |
osexual | +2.631 |
xual | +2.401 |
awn | +2.398 |
erer | +2.382 |
Neg logit contributions | |
DIT | -2.930 |
RNA | -2.878 |
VOL | -2.717 |
EH | -2.621 |
thumbnails | -2.607 |
Token | Credit |
Token ID | 10504 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
abl | +0.602 |
osexual | +0.564 |
erer | +0.526 |
xual | +0.523 |
awn | +0.516 |
Neg logit contributions | |
DIT | -0.579 |
RNA | -0.560 |
VOL | -0.523 |
devices | -0.523 |
EH | -0.520 |
Token | shall |
Token ID | 2236 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
DIT | +0.062 |
RNA | +0.062 |
VOL | +0.058 |
EH | +0.057 |
CONT | +0.056 |
Neg logit contributions | |
abl | -0.048 |
osexual | -0.046 |
xual | -0.043 |
wolves | -0.042 |
erer | -0.041 |
Token | be |
Token ID | 307 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
abl | +0.888 |
osexual | +0.837 |
xual | +0.748 |
awn | +0.740 |
wolves | +0.734 |
Neg logit contributions | |
DIT | -1.429 |
RNA | -1.425 |
VOL | -1.330 |
EH | -1.329 |
TEXT | -1.307 |
Token | given |
Token ID | 1813 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
DIT | +0.153 |
RNA | +0.151 |
VOL | +0.143 |
EH | +0.142 |
CONT | +0.140 |
Neg logit contributions | |
abl | -0.077 |
osexual | -0.073 |
xual | -0.066 |
wolves | -0.064 |
erer | -0.064 |
Token | contact |
Token ID | 2800 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
DIT | +0.457 |
RNA | +0.451 |
VOL | +0.418 |
EH | +0.414 |
CONT | +0.407 |
Neg logit contributions | |
abl | -0.447 |
osexual | -0.434 |
xual | -0.410 |
wolves | -0.400 |
erer | -0.397 |
Token | us |
Token ID | 514 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
DIT | +0.692 |
RNA | +0.684 |
VOL | +0.628 |
EH | +0.623 |
CONT | +0.610 |
Neg logit contributions | |
abl | -0.786 |
osexual | -0.763 |
xual | -0.722 |
wolves | -0.708 |
erer | -0.704 |
Token | at |
Token ID | 379 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
abl | +0.147 |
osexual | +0.142 |
xual | +0.133 |
wolves | +0.130 |
erer | +0.129 |
Neg logit contributions | |
DIT | -0.183 |
RNA | -0.181 |
VOL | -0.168 |
EH | -0.167 |
CONT | -0.164 |
Token | yog |
Token ID | 27423 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
abl | +0.144 |
osexual | +0.139 |
xual | +0.131 |
wolves | +0.128 |
erer | +0.128 |
Neg logit contributions | |
DIT | -0.147 |
RNA | -0.145 |
VOL | -0.134 |
EH | -0.133 |
CONT | -0.131 |
Token | ventures |
Token ID | 10065 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
DIT | +0.991 |
RNA | +0.975 |
VOL | +0.888 |
EH | +0.878 |
CONT | +0.861 |
Neg logit contributions | |
abl | -1.358 |
osexual | -1.323 |
xual | -1.261 |
wolves | -1.234 |
erer | -1.227 |
Token | @ |
Token ID | 31 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
abl | +0.055 |
osexual | +0.052 |
xual | +0.048 |
wolves | +0.046 |
erer | +0.046 |
Neg logit contributions | |
DIT | -0.110 |
RNA | -0.109 |
VOL | -0.102 |
EH | -0.102 |
CONT | -0.100 |
Token | y |
Token ID | 88 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
abl | +2.982 |
osexual | +2.828 |
wolves | +2.697 |
xual | +2.661 |
awn | +2.654 |
Neg logit contributions | |
DIT | -2.608 |
RNA | -2.594 |
EH | -2.381 |
VOL | -2.374 |
Chatt | -2.329 |
Token | og |
Token ID | 519 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
DIT | +0.453 |
RNA | +0.447 |
VOL | +0.418 |
EH | +0.414 |
CONT | +0.408 |
Neg logit contributions | |
abl | -0.358 |
osexual | -0.344 |
xual | -0.322 |
wolves | -0.314 |
erer | -0.312 |
Token | sc |
Token ID | 1416 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
DIT | +0.682 |
RNA | +0.672 |
VOL | +0.614 |
EH | +0.609 |
CONT | +0.596 |
Neg logit contributions | |
abl | -0.880 |
osexual | -0.856 |
xual | -0.814 |
wolves | -0.798 |
erer | -0.793 |
Token | ast |
Token ID | 459 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
abl | +0.548 |
osexual | +0.525 |
xual | +0.491 |
wolves | +0.486 |
awn | +0.482 |
Neg logit contributions | |
DIT | -0.578 |
RNA | -0.567 |
VOL | -0.531 |
EH | -0.525 |
CONT | -0.517 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
DIT | +1.006 |
RNA | +0.995 |
VOL | +0.923 |
EH | +0.917 |
CONT | +0.902 |
Neg logit contributions | |
abl | -0.897 |
osexual | -0.872 |
xual | -0.820 |
wolves | -0.799 |
erer | -0.792 |
Token | le |
Token ID | 293 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
abl | +0.191 |
osexual | +0.185 |
xual | +0.173 |
wolves | +0.170 |
erer | +0.169 |
Neg logit contributions | |
DIT | -0.196 |
RNA | -0.193 |
VOL | -0.180 |
EH | -0.178 |
CONT | -0.175 |
Token | k |
Token ID | 74 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
abl | +0.723 |
osexual | +0.706 |
xual | +0.671 |
wolves | +0.660 |
awn | +0.652 |
Neg logit contributions | |
DIT | -0.552 |
RNA | -0.544 |
EH | -0.496 |
VOL | -0.496 |
CONT | -0.484 |
Token | ( |
Token ID | 357 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
abl | +0.599 |
osexual | +0.576 |
xual | +0.533 |
erer | +0.518 |
wolves | +0.517 |
Neg logit contributions | |
DIT | -0.895 |
RNA | -0.887 |
VOL | -0.832 |
EH | -0.825 |
CONT | -0.815 |
Token | O |
Token ID | 46 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
abl | +0.671 |
osexual | +0.640 |
wolves | +0.601 |
erer | +0.598 |
xual | +0.592 |
Neg logit contributions | |
DIT | -0.600 |
RNA | -0.592 |
VOL | -0.542 |
EH | -0.538 |
Chatt | -0.534 |
Token | mega |
Token ID | 13731 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
abl | +1.145 |
osexual | +1.112 |
xual | +1.051 |
wolves | +1.038 |
erer | +1.033 |
Neg logit contributions | |
DIT | -0.857 |
RNA | -0.844 |
VOL | -0.764 |
EH | -0.761 |
TEXT | -0.749 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
abl | +0.573 |
osexual | +0.553 |
xual | +0.510 |
wolves | +0.495 |
erer | +0.494 |
Neg logit contributions | |
DIT | -0.892 |
RNA | -0.877 |
VOL | -0.832 |
EH | -0.824 |
CONT | -0.813 |
Token | - |
Token ID | 532 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
abl | +2.719 |
osexual | +2.610 |
xual | +2.456 |
erer | +2.424 |
wolves | +2.388 |
Neg logit contributions | |
DIT | -2.824 |
RNA | -2.811 |
VOL | -2.588 |
EH | -2.569 |
CONT | -2.519 |
Token | Quick |
Token ID | 12029 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
abl | +0.388 |
osexual | +0.375 |
xual | +0.354 |
erer | +0.348 |
wolves | +0.348 |
Neg logit contributions | |
DIT | -0.312 |
RNA | -0.305 |
VOL | -0.282 |
EH | -0.280 |
CONT | -0.274 |
Token | step |
Token ID | 9662 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
abl | +0.171 |
osexual | +0.160 |
wolves | +0.150 |
erer | +0.149 |
xual | +0.148 |
Neg logit contributions | |
DIT | -0.261 |
RNA | -0.256 |
EH | -0.241 |
VOL | -0.241 |
Chatt | -0.238 |
Token | ) |
Token ID | 8 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
abl | +0.922 |
osexual | +0.869 |
erer | +0.819 |
wolves | +0.811 |
xual | +0.806 |
Neg logit contributions | |
DIT | -1.006 |
RNA | -0.993 |
VOL | -0.932 |
EH | -0.918 |
thumbnails | -0.910 |
Token | s |
Token ID | 264 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
abl | +0.435 |
osexual | +0.424 |
xual | +0.405 |
wolves | +0.398 |
erer | +0.396 |
Neg logit contributions | |
DIT | -0.266 |
RNA | -0.262 |
VOL | -0.235 |
EH | -0.233 |
CONT | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
DIT | +0.698 |
RNA | +0.689 |
VOL | +0.640 |
EH | +0.635 |
CONT | +0.624 |
Neg logit contributions | |
abl | -0.637 |
osexual | -0.618 |
xual | -0.582 |
wolves | -0.568 |
erer | -0.563 |
Token | We |
Token ID | 775 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
abl | +0.221 |
osexual | +0.214 |
xual | +0.201 |
wolves | +0.197 |
erer | +0.196 |
Neg logit contributions | |
DIT | -0.236 |
RNA | -0.233 |
VOL | -0.216 |
EH | -0.214 |
CONT | -0.211 |
Token | now |
Token ID | 783 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
DIT | +0.019 |
RNA | +0.019 |
VOL | +0.018 |
EH | +0.017 |
CONT | +0.017 |
Neg logit contributions | |
abl | -0.021 |
osexual | -0.020 |
xual | -0.019 |
wolves | -0.019 |
erer | -0.019 |
Token | have |
Token ID | 423 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
DIT | +0.190 |
RNA | +0.188 |
VOL | +0.173 |
EH | +0.172 |
CONT | +0.169 |
Neg logit contributions | |
abl | -0.192 |
osexual | -0.186 |
xual | -0.176 |
wolves | -0.172 |
erer | -0.171 |
Token | a |
Token ID | 257 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
abl | +0.373 |
osexual | +0.361 |
xual | +0.339 |
wolves | +0.331 |
erer | +0.329 |
Neg logit contributions | |
DIT | -0.423 |
RNA | -0.419 |
VOL | -0.388 |
EH | -0.385 |
CONT | -0.379 |
Token | crunch |
Token ID | 23527 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
abl | +0.011 |
osexual | +0.011 |
xual | +0.010 |
wolves | +0.010 |
erer | +0.010 |
Neg logit contributions | |
DIT | -0.012 |
RNA | -0.012 |
VOL | -0.011 |
EH | -0.011 |
CONT | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
abl | +2.455 |
osexual | +2.340 |
xual | +2.178 |
erer | +2.165 |
wolves | +2.158 |
Neg logit contributions | |
DIT | -3.083 |
RNA | -3.061 |
VOL | -2.860 |
CONT | -2.809 |
EH | -2.796 |
Token | gran |
Token ID | 19468 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
DIT | +0.211 |
RNA | +0.208 |
VOL | +0.193 |
EH | +0.191 |
CONT | +0.188 |
Neg logit contributions | |
abl | -0.211 |
osexual | -0.205 |
xual | -0.193 |
wolves | -0.189 |
erer | -0.188 |
Token | ola |
Token ID | 5708 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
DIT | +0.855 |
RNA | +0.846 |
VOL | +0.794 |
EH | +0.789 |
CONT | +0.778 |
Neg logit contributions | |
abl | -0.536 |
osexual | -0.516 |
xual | -0.479 |
wolves | -0.464 |
erer | -0.459 |
Token | mentality |
Token ID | 21332 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
DIT | +0.160 |
RNA | +0.158 |
VOL | +0.147 |
EH | +0.145 |
CONT | +0.143 |
Neg logit contributions | |
abl | -0.149 |
osexual | -0.144 |
xual | -0.135 |
erer | -0.133 |
wolves | -0.132 |
Token | running |
Token ID | 2491 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
abl | +0.150 |
osexual | +0.145 |
xual | +0.136 |
wolves | +0.132 |
erer | +0.132 |
Neg logit contributions | |
DIT | -0.172 |
RNA | -0.170 |
VOL | -0.158 |
EH | -0.156 |
CONT | -0.154 |
Token | rooting |
Token ID | 40105 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
abl | +0.321 |
osexual | +0.311 |
xual | +0.291 |
wolves | +0.284 |
erer | +0.281 |
Neg logit contributions | |
DIT | -0.404 |
RNA | -0.399 |
VOL | -0.372 |
EH | -0.370 |
CONT | -0.364 |
Token | for |
Token ID | 329 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
abl | +0.004 |
osexual | +0.004 |
xual | +0.004 |
wolves | +0.004 |
erer | +0.003 |
Neg logit contributions | |
DIT | -0.006 |
RNA | -0.006 |
VOL | -0.005 |
EH | -0.005 |
CONT | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
DIT | +0.082 |
RNA | +0.080 |
VOL | +0.074 |
EH | +0.073 |
CONT | +0.072 |
Neg logit contributions | |
abl | -0.091 |
osexual | -0.088 |
xual | -0.083 |
wolves | -0.082 |
erer | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
DIT | +0.577 |
RNA | +0.570 |
VOL | +0.530 |
EH | +0.526 |
CONT | +0.517 |
Neg logit contributions | |
abl | -0.506 |
osexual | -0.490 |
xual | -0.460 |
wolves | -0.449 |
erer | -0.446 |
Token | O |
Token ID | 440 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
DIT | +0.268 |
RNA | +0.265 |
VOL | +0.245 |
EH | +0.243 |
CONT | +0.239 |
Neg logit contributions | |
abl | -0.252 |
osexual | -0.244 |
xual | -0.230 |
wolves | -0.224 |
erer | -0.223 |
Token | lic |
Token ID | 677 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
abl | +1.013 |
osexual | +0.986 |
xual | +0.939 |
wolves | +0.915 |
erer | +0.911 |
Neg logit contributions | |
DIT | -0.756 |
RNA | -0.745 |
VOL | -0.676 |
EH | -0.674 |
Chatt | -0.659 |
Token | ity |
Token ID | 414 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
abl | +3.509 |
osexual | +3.415 |
xual | +3.185 |
erer | +3.170 |
awn | +3.163 |
Neg logit contributions | |
DIT | -2.020 |
RNA | -1.977 |
VOL | -1.820 |
EH | -1.786 |
Chatt | -1.743 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
abl | +0.035 |
osexual | +0.033 |
xual | +0.032 |
wolves | +0.031 |
erer | +0.031 |
Neg logit contributions | |
DIT | -0.038 |
RNA | -0.037 |
VOL | -0.034 |
EH | -0.034 |
CONT | -0.034 |
Token | You |
Token ID | 921 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
DIT | +0.040 |
RNA | +0.039 |
VOL | +0.036 |
EH | +0.036 |
CONT | +0.035 |
Neg logit contributions | |
abl | -0.040 |
osexual | -0.039 |
xual | -0.037 |
wolves | -0.036 |
erer | -0.036 |
Token | are |
Token ID | 389 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
DIT | +0.459 |
RNA | +0.453 |
VOL | +0.418 |
EH | +0.415 |
CONT | +0.408 |
Neg logit contributions | |
abl | -0.476 |
osexual | -0.461 |
xual | -0.436 |
wolves | -0.427 |
erer | -0.424 |
Token | now |
Token ID | 783 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
abl | +0.313 |
osexual | +0.303 |
xual | +0.284 |
wolves | +0.278 |
erer | +0.275 |
Neg logit contributions | |
DIT | -0.362 |
RNA | -0.357 |
VOL | -0.332 |
EH | -0.330 |
CONT | -0.324 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
abl | +1.124 |
osexual | +1.065 |
xual | +0.980 |
wolves | +0.960 |
erer | +0.956 |
Neg logit contributions | |
DIT | -1.849 |
RNA | -1.823 |
VOL | -1.714 |
EH | -1.700 |
thumbnails | -1.673 |
Token | , |
Token ID | 11 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
abl | +0.242 |
osexual | +0.234 |
xual | +0.220 |
wolves | +0.215 |
erer | +0.213 |
Neg logit contributions | |
DIT | -0.279 |
RNA | -0.275 |
VOL | -0.256 |
EH | -0.254 |
CONT | -0.250 |
Token | as |
Token ID | 355 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
DIT | +0.128 |
RNA | +0.127 |
VOL | +0.117 |
EH | +0.117 |
CONT | +0.114 |
Neg logit contributions | |
abl | -0.121 |
osexual | -0.116 |
xual | -0.110 |
wolves | -0.108 |
erer | -0.108 |
Token | well |
Token ID | 880 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
DIT | +0.461 |
RNA | +0.457 |
VOL | +0.429 |
EH | +0.427 |
CONT | +0.421 |
Neg logit contributions | |
abl | -0.261 |
osexual | -0.250 |
xual | -0.229 |
wolves | -0.223 |
erer | -0.221 |
Token | as |
Token ID | 355 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
abl | +0.029 |
osexual | +0.027 |
xual | +0.026 |
erer | +0.026 |
wolves | +0.026 |
Neg logit contributions | |
DIT | -0.033 |
RNA | -0.032 |
VOL | -0.030 |
EH | -0.030 |
CONT | -0.029 |
Token | TNT |
Token ID | 42490 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
abl | +0.434 |
osexual | +0.419 |
xual | +0.394 |
wolves | +0.387 |
erer | +0.386 |
Neg logit contributions | |
DIT | -0.473 |
RNA | -0.466 |
VOL | -0.432 |
EH | -0.429 |
CONT | -0.421 |
Token | , |
Token ID | 11 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
abl | +2.553 |
osexual | +2.455 |
xual | +2.284 |
wolves | +2.265 |
erer | +2.255 |
Neg logit contributions | |
DIT | -2.945 |
RNA | -2.891 |
VOL | -2.673 |
EH | -2.658 |
%] | -2.630 |
Token | T |
Token ID | 309 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
DIT | +0.090 |
RNA | +0.088 |
VOL | +0.082 |
EH | +0.081 |
CONT | +0.080 |
Neg logit contributions | |
abl | -0.082 |
osexual | -0.078 |
xual | -0.074 |
wolves | -0.073 |
erer | -0.072 |
Token | BS |
Token ID | 4462 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
abl | +1.150 |
osexual | +1.113 |
xual | +1.053 |
wolves | +1.044 |
erer | +1.041 |
Neg logit contributions | |
DIT | -0.765 |
RNA | -0.746 |
VOL | -0.677 |
EH | -0.668 |
thumbnails | -0.656 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
abl | +0.541 |
osexual | +0.524 |
xual | +0.493 |
wolves | +0.482 |
erer | +0.478 |
Neg logit contributions | |
DIT | -0.579 |
RNA | -0.572 |
VOL | -0.530 |
EH | -0.526 |
CONT | -0.517 |
Token | Food |
Token ID | 7318 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
DIT | +0.322 |
RNA | +0.317 |
VOL | +0.294 |
EH | +0.292 |
CONT | +0.286 |
Neg logit contributions | |
abl | -0.307 |
osexual | -0.295 |
xual | -0.278 |
wolves | -0.274 |
erer | -0.272 |
Token | that |
Token ID | 326 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
abl | +0.684 |
osexual | +0.661 |
xual | +0.620 |
wolves | +0.602 |
erer | +0.598 |
Neg logit contributions | |
DIT | -0.876 |
RNA | -0.867 |
VOL | -0.809 |
EH | -0.803 |
CONT | -0.791 |
Token | he |
Token ID | 339 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
abl | +0.349 |
osexual | +0.337 |
xual | +0.316 |
wolves | +0.307 |
erer | +0.305 |
Neg logit contributions | |
DIT | -0.447 |
RNA | -0.442 |
VOL | -0.412 |
EH | -0.409 |
CONT | -0.403 |
Token | had |
Token ID | 550 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
DIT | +0.081 |
RNA | +0.080 |
VOL | +0.073 |
EH | +0.073 |
CONT | +0.071 |
Neg logit contributions | |
abl | -0.093 |
osexual | -0.091 |
xual | -0.086 |
wolves | -0.084 |
erer | -0.084 |
Token | been |
Token ID | 587 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
abl | +0.154 |
osexual | +0.149 |
xual | +0.140 |
wolves | +0.137 |
erer | +0.136 |
Neg logit contributions | |
DIT | -0.181 |
RNA | -0.179 |
VOL | -0.166 |
EH | -0.165 |
CONT | -0.162 |
Token | an |
Token ID | 281 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
abl | +0.148 |
osexual | +0.143 |
xual | +0.134 |
wolves | +0.131 |
erer | +0.130 |
Neg logit contributions | |
DIT | -0.179 |
RNA | -0.177 |
VOL | -0.165 |
EH | -0.164 |
CONT | -0.161 |
Token | inst |
Token ID | 916 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
abl | +0.286 |
osexual | +0.276 |
xual | +0.259 |
wolves | +0.252 |
erer | +0.250 |
Neg logit contributions | |
DIT | -0.369 |
RNA | -0.365 |
VOL | -0.341 |
EH | -0.338 |
CONT | -0.333 |
Token | igator |
Token ID | 23823 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
abl | +2.644 |
osexual | +2.480 |
erer | +2.336 |
xual | +2.245 |
ier | +2.221 |
Neg logit contributions | |
DIT | -3.024 |
RNA | -2.829 |
VOL | -2.784 |
INGTON | -2.736 |
TEXT | -2.716 |
Token | of |
Token ID | 286 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
abl | +0.159 |
osexual | +0.154 |
xual | +0.144 |
wolves | +0.140 |
erer | +0.140 |
Neg logit contributions | |
DIT | -0.188 |
RNA | -0.186 |
VOL | -0.172 |
EH | -0.171 |
CONT | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
abl | +0.308 |
osexual | +0.298 |
xual | +0.278 |
wolves | +0.271 |
erer | +0.268 |
Neg logit contributions | |
DIT | -0.392 |
RNA | -0.388 |
VOL | -0.361 |
EH | -0.358 |
CONT | -0.352 |
Token | Mau |
Token ID | 28931 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
abl | +0.076 |
osexual | +0.073 |
xual | +0.068 |
wolves | +0.067 |
erer | +0.066 |
Neg logit contributions | |
DIT | -0.094 |
RNA | -0.093 |
VOL | -0.086 |
EH | -0.086 |
CONT | -0.085 |
Token | Mau |
Token ID | 28931 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
abl | +0.726 |
osexual | +0.699 |
xual | +0.643 |
wolves | +0.632 |
erer | +0.620 |
Neg logit contributions | |
DIT | -1.188 |
RNA | -1.170 |
EH | -1.097 |
VOL | -1.096 |
CONT | -1.074 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
abl | +0.422 |
osexual | +0.405 |
xual | +0.382 |
wolves | +0.373 |
erer | +0.369 |
Neg logit contributions | |
DIT | -0.500 |
RNA | -0.498 |
VOL | -0.464 |
EH | -0.459 |
CONT | -0.448 |
Token | omn |
Token ID | 22284 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
abl | +0.739 |
osexual | +0.715 |
xual | +0.673 |
wolves | +0.656 |
erer | +0.653 |
Neg logit contributions | |
DIT | -0.766 |
RNA | -0.760 |
VOL | -0.705 |
EH | -0.700 |
CONT | -0.683 |
Token | is |
Token ID | 271 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
abl | +0.634 |
osexual | +0.610 |
xual | +0.562 |
erer | +0.550 |
wolves | +0.548 |
Neg logit contributions | |
DIT | -0.868 |
RNA | -0.858 |
VOL | -0.807 |
EH | -0.798 |
CONT | -0.785 |
Token | cient |
Token ID | 3456 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
abl | +0.268 |
osexual | +0.258 |
xual | +0.239 |
wolves | +0.232 |
erer | +0.231 |
Neg logit contributions | |
DIT | -0.379 |
RNA | -0.373 |
VOL | -0.351 |
EH | -0.349 |
CONT | -0.342 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
abl | +0.496 |
osexual | +0.477 |
xual | +0.445 |
wolves | +0.443 |
erer | +0.440 |
Neg logit contributions | |
DIT | -0.524 |
RNA | -0.520 |
VOL | -0.484 |
EH | -0.480 |
thumbnails | -0.469 |
Token | infall |
Token ID | 48124 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
abl | +0.335 |
osexual | +0.322 |
xual | +0.303 |
wolves | +0.296 |
erer | +0.294 |
Neg logit contributions | |
DIT | -0.393 |
RNA | -0.389 |
VOL | -0.361 |
EH | -0.358 |
CONT | -0.351 |
Token | ible |
Token ID | 856 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
abl | +2.911 |
osexual | +2.768 |
erer | +2.590 |
xual | +2.587 |
awn | +2.571 |
Neg logit contributions | |
DIT | -2.587 |
RNA | -2.554 |
VOL | -2.352 |
EH | -2.323 |
CONT | -2.275 |
Token | knowledge |
Token ID | 3725 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
abl | +0.086 |
osexual | +0.083 |
xual | +0.078 |
wolves | +0.077 |
erer | +0.077 |
Neg logit contributions | |
DIT | -0.086 |
RNA | -0.085 |
VOL | -0.079 |
EH | -0.078 |
CONT | -0.076 |
Token | database |
Token ID | 6831 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
abl | +0.723 |
osexual | +0.692 |
xual | +0.652 |
wolves | +0.636 |
erer | +0.633 |
Neg logit contributions | |
DIT | -0.865 |
RNA | -0.859 |
VOL | -0.801 |
EH | -0.789 |
CONT | -0.778 |
Token | that |
Token ID | 326 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
abl | +0.465 |
osexual | +0.448 |
xual | +0.424 |
wolves | +0.414 |
erer | +0.412 |
Neg logit contributions | |
DIT | -0.488 |
RNA | -0.482 |
VOL | -0.448 |
EH | -0.442 |
CONT | -0.435 |
Token | is |
Token ID | 318 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
abl | +0.024 |
osexual | +0.023 |
xual | +0.022 |
wolves | +0.021 |
erer | +0.021 |
Neg logit contributions | |
DIT | -0.024 |
RNA | -0.023 |
VOL | -0.022 |
EH | -0.021 |
CONT | -0.021 |
Token | 105 |
Token ID | 13348 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
DIT | +0.188 |
RNA | +0.185 |
VOL | +0.171 |
EH | +0.170 |
CONT | +0.168 |
Neg logit contributions | |
abl | -0.179 |
osexual | -0.174 |
xual | -0.164 |
wolves | -0.160 |
erer | -0.159 |
Token | ] |
Token ID | 60 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
DIT | +0.153 |
RNA | +0.150 |
VOL | +0.133 |
EH | +0.132 |
CONT | +0.129 |
Neg logit contributions | |
abl | -0.300 |
osexual | -0.294 |
xual | -0.283 |
wolves | -0.278 |
erer | -0.276 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
DIT | +0.169 |
RNA | +0.167 |
VOL | +0.155 |
EH | +0.154 |
CONT | +0.152 |
Neg logit contributions | |
abl | -0.140 |
osexual | -0.136 |
xual | -0.127 |
wolves | -0.124 |
erer | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
DIT | +0.443 |
RNA | +0.436 |
VOL | +0.402 |
EH | +0.398 |
Chatt | +0.389 |
Neg logit contributions | |
abl | -0.505 |
osexual | -0.486 |
xual | -0.454 |
wolves | -0.453 |
erer | -0.452 |
Token | O |
Token ID | 46 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
DIT | +0.440 |
RNA | +0.434 |
VOL | +0.400 |
EH | +0.397 |
CONT | +0.389 |
Neg logit contributions | |
abl | -0.475 |
osexual | -0.461 |
xual | -0.435 |
wolves | -0.427 |
erer | -0.424 |
Token | ka |
Token ID | 4914 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
abl | +0.669 |
osexual | +0.650 |
xual | +0.601 |
wolves | +0.587 |
awn | +0.585 |
Neg logit contributions | |
DIT | -0.902 |
RNA | -0.880 |
VOL | -0.825 |
EH | -0.823 |
Chatt | -0.817 |
Token | for |
Token ID | 1640 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
abl | +2.655 |
osexual | +2.525 |
erer | +2.317 |
awn | +2.309 |
xual | +2.296 |
Neg logit contributions | |
DIT | -2.855 |
RNA | -2.737 |
VOL | -2.597 |
EH | -2.574 |
Chatt | -2.555 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
abl | +0.782 |
osexual | +0.759 |
xual | +0.709 |
erer | +0.698 |
awn | +0.697 |
Neg logit contributions | |
DIT | -0.836 |
RNA | -0.824 |
VOL | -0.755 |
EH | -0.751 |
CONT | -0.740 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
abl | +0.238 |
osexual | +0.230 |
xual | +0.213 |
wolves | +0.209 |
erer | +0.208 |
Neg logit contributions | |
DIT | -0.322 |
RNA | -0.319 |
VOL | -0.297 |
EH | -0.297 |
CONT | -0.291 |
Token | season |
Token ID | 1622 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
abl | +0.301 |
osexual | +0.294 |
xual | +0.274 |
wolves | +0.270 |
erer | +0.269 |
Neg logit contributions | |
DIT | -0.296 |
RNA | -0.292 |
VOL | -0.270 |
EH | -0.268 |
CONT | -0.263 |
Token | as |
Token ID | 355 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
abl | +0.947 |
osexual | +0.915 |
xual | +0.840 |
wolves | +0.838 |
erer | +0.836 |
Neg logit contributions | |
DIT | -1.152 |
RNA | -1.150 |
VOL | -1.053 |
EH | -1.045 |
CONT | -1.035 |
Token | performance |
Token ID | 2854 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
abl | +0.645 |
osexual | +0.625 |
xual | +0.579 |
wolves | +0.569 |
erer | +0.569 |
Neg logit contributions | |
DIT | -0.813 |
RNA | -0.800 |
VOL | -0.747 |
EH | -0.738 |
CONT | -0.732 |
Token | against |
Token ID | 1028 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
DIT | +0.456 |
RNA | +0.451 |
VOL | +0.417 |
EH | +0.414 |
CONT | +0.407 |
Neg logit contributions | |
abl | -0.447 |
osexual | -0.434 |
xual | -0.411 |
wolves | -0.400 |
erer | -0.397 |
Token | Elon |
Token ID | 32451 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
abl | +0.675 |
osexual | +0.650 |
xual | +0.614 |
wolves | +0.606 |
erer | +0.603 |
Neg logit contributions | |
DIT | -0.660 |
RNA | -0.651 |
VOL | -0.601 |
EH | -0.596 |
CONT | -0.588 |
Token | , |
Token ID | 11 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
DIT | +1.153 |
RNA | +1.141 |
VOL | +1.063 |
EH | +1.053 |
CONT | +1.035 |
Neg logit contributions | |
abl | -0.969 |
osexual | -0.939 |
xual | -0.885 |
wolves | -0.858 |
erer | -0.852 |
Token | O |
Token ID | 440 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
DIT | +0.170 |
RNA | +0.168 |
VOL | +0.158 |
EH | +0.157 |
CONT | +0.154 |
Neg logit contributions | |
abl | -0.113 |
osexual | -0.109 |
xual | -0.101 |
wolves | -0.098 |
erer | -0.097 |
Token | ka |
Token ID | 4914 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
abl | +0.877 |
osexual | +0.834 |
xual | +0.772 |
awn | +0.758 |
erer | +0.757 |
Neg logit contributions | |
DIT | -1.229 |
RNA | -1.200 |
VOL | -1.132 |
Chatt | -1.125 |
EH | -1.123 |
Token | for |
Token ID | 1640 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
abl | +2.636 |
osexual | +2.486 |
erer | +2.301 |
awn | +2.284 |
wolves | +2.264 |
Neg logit contributions | |
DIT | -2.816 |
RNA | -2.706 |
VOL | -2.572 |
EH | -2.546 |
Chatt | -2.537 |
Token | became |
Token ID | 2627 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
abl | +0.420 |
osexual | +0.404 |
xual | +0.381 |
wolves | +0.376 |
erer | +0.375 |
Neg logit contributions | |
DIT | -0.410 |
RNA | -0.407 |
VOL | -0.372 |
EH | -0.370 |
CONT | -0.364 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
DIT | +0.368 |
RNA | +0.363 |
VOL | +0.336 |
EH | +0.334 |
CONT | +0.329 |
Neg logit contributions | |
abl | -0.351 |
osexual | -0.339 |
xual | -0.321 |
wolves | -0.312 |
erer | -0.310 |
Token | first |
Token ID | 717 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
DIT | +0.199 |
RNA | +0.197 |
VOL | +0.181 |
EH | +0.179 |
CONT | +0.175 |
Neg logit contributions | |
abl | -0.238 |
osexual | -0.231 |
xual | -0.219 |
wolves | -0.215 |
erer | -0.214 |
Token | Duke |
Token ID | 11083 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
abl | +0.416 |
osexual | +0.403 |
xual | +0.376 |
wolves | +0.367 |
erer | +0.364 |
Neg logit contributions | |
DIT | -0.556 |
RNA | -0.550 |
VOL | -0.512 |
EH | -0.510 |
CONT | -0.501 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
DIT | +0.080 |
RNA | +0.079 |
VOL | +0.074 |
EH | +0.073 |
CONT | +0.072 |
Neg logit contributions | |
abl | -0.061 |
osexual | -0.059 |
xual | -0.055 |
wolves | -0.053 |
erer | -0.053 |
Token | find |
Token ID | 1064 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
abl | +0.207 |
osexual | +0.201 |
xual | +0.190 |
wolves | +0.185 |
erer | +0.184 |
Neg logit contributions | |
DIT | -0.223 |
RNA | -0.221 |
VOL | -0.205 |
EH | -0.203 |
CONT | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
DIT | +0.343 |
RNA | +0.339 |
VOL | +0.314 |
EH | +0.311 |
CONT | +0.306 |
Neg logit contributions | |
abl | -0.325 |
osexual | -0.315 |
xual | -0.297 |
wolves | -0.290 |
erer | -0.288 |
Token | books |
Token ID | 3835 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
abl | +0.074 |
osexual | +0.072 |
xual | +0.067 |
wolves | +0.066 |
erer | +0.065 |
Neg logit contributions | |
DIT | -0.090 |
RNA | -0.089 |
VOL | -0.083 |
EH | -0.082 |
CONT | -0.081 |
Token | enjoyable |
Token ID | 20050 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
abl | +0.906 |
osexual | +0.872 |
xual | +0.814 |
wolves | +0.801 |
erer | +0.792 |
Neg logit contributions | |
DIT | -1.134 |
RNA | -1.122 |
VOL | -1.043 |
EH | -1.031 |
CONT | -1.014 |
Token | nonetheless |
Token ID | 19018 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
abl | +0.441 |
osexual | +0.427 |
xual | +0.402 |
wolves | +0.392 |
erer | +0.389 |
Neg logit contributions | |
DIT | -0.498 |
RNA | -0.492 |
VOL | -0.457 |
EH | -0.453 |
CONT | -0.446 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
abl | +2.369 |
osexual | +2.289 |
xual | +2.117 |
wolves | +2.082 |
erer | +2.066 |
Neg logit contributions | |
DIT | -2.992 |
RNA | -2.985 |
VOL | -2.768 |
EH | -2.720 |
thumbnails | -2.717 |
Token | Readers |
Token ID | 41969 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
abl | +0.530 |
osexual | +0.514 |
xual | +0.481 |
wolves | +0.477 |
erer | +0.470 |
Neg logit contributions | |
DIT | -0.550 |
RNA | -0.544 |
VOL | -0.502 |
EH | -0.498 |
CONT | -0.488 |
Token | will |
Token ID | 481 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
abl | +0.520 |
osexual | +0.503 |
xual | +0.473 |
wolves | +0.464 |
erer | +0.459 |
Neg logit contributions | |
DIT | -0.565 |
RNA | -0.559 |
VOL | -0.518 |
EH | -0.514 |
CONT | -0.505 |
Token | likely |
Token ID | 1884 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
abl | +1.307 |
osexual | +1.257 |
xual | +1.182 |
wolves | +1.153 |
erer | +1.146 |
Neg logit contributions | |
DIT | -1.544 |
RNA | -1.532 |
VOL | -1.424 |
EH | -1.412 |
CONT | -1.387 |
Token | finish |
Token ID | 5461 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
abl | +0.674 |
osexual | +0.650 |
xual | +0.612 |
wolves | +0.597 |
erer | +0.593 |
Neg logit contributions | |
DIT | -0.771 |
RNA | -0.764 |
VOL | -0.708 |
EH | -0.703 |
CONT | -0.690 |
Token | " |
Token ID | 1 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
abl | +0.282 |
osexual | +0.268 |
xual | +0.248 |
erer | +0.241 |
wolves | +0.240 |
Neg logit contributions | |
DIT | -0.424 |
RNA | -0.418 |
VOL | -0.394 |
EH | -0.387 |
CONT | -0.387 |
Token | - |
Token ID | 532 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
DIT | +0.503 |
RNA | +0.496 |
VOL | +0.457 |
EH | +0.453 |
CONT | +0.445 |
Neg logit contributions | |
abl | -0.537 |
osexual | -0.520 |
xual | -0.493 |
wolves | -0.481 |
erer | -0.479 |
Token | but |
Token ID | 475 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
DIT | +0.794 |
RNA | +0.785 |
VOL | +0.727 |
EH | +0.722 |
CONT | +0.709 |
Neg logit contributions | |
abl | -0.759 |
osexual | -0.737 |
xual | -0.694 |
wolves | -0.678 |
erer | -0.673 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
DIT | +0.698 |
RNA | +0.689 |
VOL | +0.640 |
EH | +0.635 |
CONT | +0.624 |
Neg logit contributions | |
abl | -0.638 |
osexual | -0.619 |
xual | -0.582 |
wolves | -0.568 |
erer | -0.564 |
Token | what |
Token ID | 644 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
DIT | +0.215 |
RNA | +0.213 |
VOL | +0.198 |
EH | +0.196 |
CONT | +0.193 |
Neg logit contributions | |
abl | -0.194 |
osexual | -0.188 |
xual | -0.177 |
wolves | -0.173 |
erer | -0.171 |
Token | degree |
Token ID | 4922 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
abl | +0.127 |
osexual | +0.122 |
xual | +0.115 |
wolves | +0.112 |
erer | +0.112 |
Neg logit contributions | |
DIT | -0.142 |
RNA | -0.140 |
VOL | -0.130 |
EH | -0.129 |
CONT | -0.127 |
Token | has |
Token ID | 468 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
DIT | +2.314 |
RNA | +2.288 |
VOL | +2.113 |
EH | +2.089 |
CONT | +2.053 |
Neg logit contributions | |
abl | -2.771 |
osexual | -2.721 |
xual | -2.576 |
wolves | -2.528 |
erer | -2.508 |
Token | the |
Token ID | 262 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
DIT | +0.806 |
RNA | +0.795 |
VOL | +0.737 |
EH | +0.730 |
CONT | +0.717 |
Neg logit contributions | |
abl | -0.819 |
osexual | -0.797 |
xual | -0.753 |
wolves | -0.736 |
erer | -0.730 |
Token | city |
Token ID | 1748 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
DIT | +0.395 |
RNA | +0.389 |
VOL | +0.362 |
EH | +0.359 |
CONT | +0.353 |
Neg logit contributions | |
abl | -0.345 |
osexual | -0.332 |
xual | -0.313 |
wolves | -0.304 |
erer | -0.303 |
Token | really |
Token ID | 1107 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
DIT | +0.101 |
RNA | +0.099 |
VOL | +0.092 |
EH | +0.091 |
CONT | +0.089 |
Neg logit contributions | |
abl | -0.090 |
osexual | -0.087 |
xual | -0.081 |
wolves | -0.080 |
erer | -0.080 |
Token | reckoned |
Token ID | 46630 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
DIT | +1.536 |
RNA | +1.524 |
VOL | +1.421 |
EH | +1.412 |
CONT | +1.387 |
Neg logit contributions | |
abl | -1.314 |
osexual | -1.275 |
xual | -1.203 |
wolves | -1.166 |
erer | -1.156 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
DIT | +0.294 |
RNA | +0.289 |
VOL | +0.268 |
EH | +0.265 |
Chatt | +0.259 |
Neg logit contributions | |
abl | -0.331 |
osexual | -0.318 |
erer | -0.297 |
xual | -0.297 |
wolves | -0.296 |
Token | And |
Token ID | 1870 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
DIT | +0.211 |
RNA | +0.209 |
VOL | +0.192 |
EH | +0.190 |
CONT | +0.186 |
Neg logit contributions | |
abl | -0.239 |
osexual | -0.232 |
xual | -0.219 |
wolves | -0.216 |
erer | -0.214 |
Token | so |
Token ID | 523 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
abl | +0.073 |
osexual | +0.071 |
xual | +0.067 |
wolves | +0.066 |
erer | +0.065 |
Neg logit contributions | |
DIT | -0.078 |
RNA | -0.077 |
VOL | -0.071 |
EH | -0.071 |
CONT | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
abl | +0.651 |
osexual | +0.630 |
xual | +0.591 |
wolves | +0.579 |
erer | +0.573 |
Neg logit contributions | |
DIT | -0.759 |
RNA | -0.754 |
VOL | -0.699 |
EH | -0.693 |
CONT | -0.682 |
Token | teams |
Token ID | 3466 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
DIT | +0.030 |
RNA | +0.030 |
VOL | +0.027 |
EH | +0.027 |
CONT | +0.027 |
Neg logit contributions | |
abl | -0.027 |
osexual | -0.026 |
xual | -0.025 |
wolves | -0.024 |
erer | -0.024 |
Token | line |
Token ID | 1627 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
abl | +0.109 |
osexual | +0.105 |
xual | +0.099 |
wolves | +0.097 |
erer | +0.096 |
Neg logit contributions | |
DIT | -0.124 |
RNA | -0.122 |
VOL | -0.114 |
EH | -0.113 |
CONT | -0.111 |
Token | upon |
Token ID | 2402 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
DIT | +2.516 |
RNA | +2.481 |
VOL | +2.305 |
EH | +2.299 |
CONT | +2.261 |
Neg logit contributions | |
abl | -2.066 |
osexual | -2.002 |
xual | -1.890 |
wolves | -1.819 |
erer | -1.810 |
Token | one |
Token ID | 530 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
abl | +0.177 |
osexual | +0.172 |
xual | +0.162 |
wolves | +0.159 |
erer | +0.158 |
Neg logit contributions | |
DIT | -0.163 |
RNA | -0.161 |
VOL | -0.149 |
EH | -0.147 |
CONT | -0.144 |
Token | another |
Token ID | 1194 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
DIT | +0.419 |
RNA | +0.414 |
VOL | +0.385 |
EH | +0.382 |
CONT | +0.376 |
Neg logit contributions | |
abl | -0.362 |
osexual | -0.350 |
xual | -0.329 |
wolves | -0.321 |
erer | -0.319 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
abl | +0.434 |
osexual | +0.419 |
xual | +0.391 |
wolves | +0.387 |
erer | +0.384 |
Neg logit contributions | |
DIT | -0.501 |
RNA | -0.500 |
VOL | -0.464 |
EH | -0.457 |
CONT | -0.450 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
DIT | +0.227 |
RNA | +0.225 |
VOL | +0.208 |
EH | +0.206 |
CONT | +0.202 |
Neg logit contributions | |
abl | -0.219 |
osexual | -0.212 |
xual | -0.200 |
wolves | -0.197 |
erer | -0.194 |
Token | right |
Token ID | 826 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
DIT | +0.169 |
RNA | +0.167 |
VOL | +0.155 |
EH | +0.154 |
CONT | +0.151 |
Neg logit contributions | |
abl | -0.148 |
osexual | -0.143 |
xual | -0.134 |
wolves | -0.131 |
erer | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
DIT | +0.717 |
RNA | +0.708 |
VOL | +0.663 |
EH | +0.655 |
CONT | +0.641 |
Neg logit contributions | |
abl | -0.545 |
osexual | -0.535 |
xual | -0.502 |
wolves | -0.489 |
erer | -0.481 |
Token | protect |
Token ID | 1805 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
DIT | +0.491 |
RNA | +0.486 |
VOL | +0.454 |
EH | +0.451 |
CONT | +0.444 |
Neg logit contributions | |
abl | -0.367 |
osexual | -0.356 |
xual | -0.334 |
wolves | -0.324 |
erer | -0.320 |
Token | Russian |
Token ID | 3394 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
DIT | +1.446 |
RNA | +1.426 |
VOL | +1.320 |
EH | +1.310 |
CONT | +1.286 |
Neg logit contributions | |
abl | -1.440 |
osexual | -1.400 |
xual | -1.328 |
wolves | -1.294 |
erer | -1.282 |
Token | - |
Token ID | 12 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
abl | +0.122 |
osexual | +0.118 |
xual | +0.108 |
wolves | +0.106 |
erer | +0.106 |
Neg logit contributions | |
DIT | -0.145 |
RNA | -0.143 |
VOL | -0.132 |
EH | -0.132 |
CONT | -0.130 |
Token | spe |
Token ID | 4125 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
DIT | +0.370 |
RNA | +0.364 |
VOL | +0.335 |
EH | +0.333 |
CONT | +0.326 |
Neg logit contributions | |
abl | -0.407 |
osexual | -0.393 |
xual | -0.371 |
wolves | -0.365 |
erer | -0.362 |
Token | akers |
Token ID | 3979 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
RNA | +2.265 |
DIT | +2.258 |
VOL | +2.024 |
EH | +1.993 |
CONT | +1.942 |
Neg logit contributions | |
abl | -3.720 |
osexual | -3.676 |
xual | -3.489 |
wolves | -3.458 |
erer | -3.380 |
Token | in |
Token ID | 287 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
abl | +0.090 |
osexual | +0.086 |
xual | +0.081 |
wolves | +0.079 |
erer | +0.078 |
Neg logit contributions | |
DIT | -0.110 |
RNA | -0.109 |
VOL | -0.101 |
EH | -0.100 |
CONT | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
abl | +0.096 |
osexual | +0.092 |
xual | +0.086 |
wolves | +0.084 |
erer | +0.084 |
Neg logit contributions | |
DIT | -0.116 |
RNA | -0.115 |
VOL | -0.106 |
EH | -0.106 |
CONT | -0.104 |
Token | region |
Token ID | 3814 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
abl | +0.132 |
osexual | +0.128 |
xual | +0.120 |
wolves | +0.117 |
erer | +0.116 |
Neg logit contributions | |
DIT | -0.156 |
RNA | -0.155 |
VOL | -0.144 |
EH | -0.143 |
CONT | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
DIT | +0.587 |
RNA | +0.581 |
VOL | +0.539 |
EH | +0.535 |
CONT | +0.526 |
Neg logit contributions | |
abl | -0.519 |
osexual | -0.501 |
xual | -0.472 |
wolves | -0.460 |
erer | -0.457 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
DIT | +0.073 |
RNA | +0.073 |
VOL | +0.067 |
EH | +0.066 |
CONT | +0.065 |
Neg logit contributions | |
abl | -0.080 |
osexual | -0.078 |
xual | -0.073 |
wolves | -0.072 |
erer | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
DIT | +0.298 |
RNA | +0.295 |
VOL | +0.273 |
EH | +0.271 |
CONT | +0.268 |
Neg logit contributions | |
abl | -0.265 |
osexual | -0.257 |
xual | -0.242 |
wolves | -0.236 |
erer | -0.235 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
DIT | +0.205 |
RNA | +0.202 |
VOL | +0.188 |
EH | +0.186 |
CONT | +0.183 |
Neg logit contributions | |
abl | -0.185 |
osexual | -0.179 |
xual | -0.169 |
wolves | -0.165 |
erer | -0.163 |
Token | meaningless |
Token ID | 24513 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
DIT | +0.273 |
RNA | +0.271 |
VOL | +0.250 |
EH | +0.248 |
CONT | +0.243 |
Neg logit contributions | |
abl | -0.279 |
osexual | -0.271 |
xual | -0.255 |
wolves | -0.250 |
erer | -0.250 |
Token | graduate |
Token ID | 10428 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
DIT | +0.354 |
RNA | +0.350 |
VOL | +0.324 |
EH | +0.322 |
CONT | +0.316 |
Neg logit contributions | |
abl | -0.336 |
osexual | -0.326 |
xual | -0.305 |
wolves | -0.299 |
erer | -0.299 |
Token | degree |
Token ID | 4922 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
DIT | +0.745 |
RNA | +0.735 |
VOL | +0.684 |
EH | +0.680 |
CONT | +0.668 |
Neg logit contributions | |
abl | -0.630 |
osexual | -0.610 |
xual | -0.571 |
erer | -0.556 |
wolves | -0.554 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
DIT | +2.966 |
RNA | +2.922 |
VOL | +2.698 |
EH | +2.697 |
CONT | +2.649 |
Neg logit contributions | |
abl | -2.741 |
osexual | -2.686 |
xual | -2.507 |
wolves | -2.495 |
awn | -2.418 |
Token | I |
Token ID | 314 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
DIT | +0.310 |
RNA | +0.307 |
VOL | +0.284 |
EH | +0.282 |
CONT | +0.277 |
Neg logit contributions | |
abl | -0.295 |
osexual | -0.286 |
xual | -0.269 |
wolves | -0.264 |
erer | -0.262 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
DIT | +0.025 |
RNA | +0.025 |
VOL | +0.023 |
EH | +0.022 |
CONT | +0.022 |
Neg logit contributions | |
abl | -0.029 |
osexual | -0.028 |
xual | -0.027 |
wolves | -0.026 |
erer | -0.026 |
Token | grinding |
Token ID | 28436 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
DIT | +0.270 |
RNA | +0.267 |
VOL | +0.248 |
EH | +0.246 |
CONT | +0.242 |
Neg logit contributions | |
abl | -0.239 |
osexual | -0.231 |
xual | -0.217 |
wolves | -0.212 |
erer | -0.211 |
Token | out |
Token ID | 503 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
abl | +0.479 |
osexual | +0.462 |
xual | +0.432 |
erer | +0.424 |
wolves | +0.424 |
Neg logit contributions | |
DIT | -0.549 |
RNA | -0.544 |
VOL | -0.504 |
EH | -0.500 |
CONT | -0.493 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
abl | +0.231 |
osexual | +0.223 |
xual | +0.210 |
wolves | +0.205 |
erer | +0.204 |
Neg logit contributions | |
DIT | -0.259 |
RNA | -0.256 |
VOL | -0.237 |
EH | -0.236 |
CONT | -0.231 |
Token | female |
Token ID | 4048 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
DIT | +0.023 |
RNA | +0.023 |
VOL | +0.021 |
EH | +0.021 |
CONT | +0.020 |
Neg logit contributions | |
abl | -0.020 |
osexual | -0.020 |
xual | -0.019 |
wolves | -0.018 |
erer | -0.018 |
Token | anatomy |
Token ID | 33449 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
abl | +0.236 |
osexual | +0.228 |
xual | +0.212 |
wolves | +0.206 |
erer | +0.205 |
Neg logit contributions | |
DIT | -0.331 |
RNA | -0.327 |
VOL | -0.306 |
EH | -0.304 |
CONT | -0.299 |
Token | on |
Token ID | 319 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
DIT | +0.035 |
RNA | +0.034 |
VOL | +0.031 |
EH | +0.031 |
CONT | +0.031 |
Neg logit contributions | |
abl | -0.040 |
osexual | -0.039 |
xual | -0.037 |
wolves | -0.036 |
erer | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
DIT | +0.210 |
RNA | +0.208 |
VOL | +0.193 |
EH | +0.192 |
CONT | +0.188 |
Neg logit contributions | |
abl | -0.185 |
osexual | -0.179 |
xual | -0.168 |
wolves | -0.164 |
erer | -0.163 |
Token | Heart |
Token ID | 28541 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
abl | +0.063 |
osexual | +0.061 |
xual | +0.057 |
wolves | +0.057 |
erer | +0.056 |
Neg logit contributions | |
DIT | -0.053 |
RNA | -0.052 |
VOL | -0.048 |
EH | -0.047 |
CONT | -0.046 |
Token | - |
Token ID | 12 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
DIT | +2.230 |
RNA | +2.222 |
VOL | +2.046 |
EH | +2.031 |
CONT | +2.000 |
Neg logit contributions | |
abl | -2.374 |
osexual | -2.310 |
xual | -2.184 |
wolves | -2.126 |
erer | -2.109 |
Token | Sh |
Token ID | 2484 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
DIT | +0.506 |
RNA | +0.497 |
VOL | +0.458 |
EH | +0.452 |
CONT | +0.444 |
Neg logit contributions | |
abl | -0.572 |
osexual | -0.555 |
xual | -0.525 |
wolves | -0.518 |
erer | -0.514 |
Token | aped |
Token ID | 5813 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
abl | +0.285 |
osexual | +0.274 |
xual | +0.257 |
awn | +0.255 |
erer | +0.253 |
Neg logit contributions | |
DIT | -0.271 |
RNA | -0.261 |
VOL | -0.245 |
EH | -0.244 |
CONT | -0.240 |
Token | Box |
Token ID | 8315 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
abl | +0.662 |
osexual | +0.644 |
xual | +0.607 |
wolves | +0.595 |
erer | +0.594 |
Neg logit contributions | |
DIT | -0.630 |
RNA | -0.620 |
VOL | -0.575 |
EH | -0.570 |
CONT | -0.557 |
Token | ." |
Token ID | 526 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
DIT | +0.025 |
RNA | +0.025 |
VOL | +0.023 |
EH | +0.022 |
CONT | +0.022 |
Neg logit contributions | |
abl | -0.032 |
osexual | -0.031 |
xual | -0.030 |
wolves | -0.029 |
erer | -0.029 |
Token | Israeli |
Token ID | 6085 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
DIT | +0.240 |
RNA | +0.237 |
VOL | +0.221 |
EH | +0.220 |
CONT | +0.216 |
Neg logit contributions | |
abl | -0.185 |
osexual | -0.178 |
xual | -0.167 |
wolves | -0.162 |
erer | -0.161 |
Token | Zion |
Token ID | 16899 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
DIT | +0.305 |
RNA | +0.302 |
VOL | +0.282 |
EH | +0.280 |
CONT | +0.275 |
Neg logit contributions | |
abl | -0.221 |
osexual | -0.212 |
xual | -0.196 |
wolves | -0.192 |
erer | -0.191 |
Token | ists |
Token ID | 1023 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
DIT | +0.819 |
RNA | +0.810 |
VOL | +0.757 |
EH | +0.752 |
CONT | +0.741 |
Neg logit contributions | |
abl | -0.609 |
osexual | -0.587 |
xual | -0.549 |
wolves | -0.534 |
erer | -0.529 |
Token | have |
Token ID | 423 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
DIT | +1.008 |
RNA | +0.995 |
VOL | +0.918 |
EH | +0.911 |
CONT | +0.894 |
Neg logit contributions | |
abl | -1.054 |
osexual | -1.023 |
xual | -0.968 |
wolves | -0.945 |
erer | -0.939 |
Token | occupied |
Token ID | 12030 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
abl | +0.113 |
osexual | +0.109 |
xual | +0.103 |
wolves | +0.101 |
erer | +0.100 |
Neg logit contributions | |
DIT | -0.121 |
RNA | -0.119 |
VOL | -0.110 |
EH | -0.109 |
CONT | -0.107 |
Token | Arab |
Token ID | 4498 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
DIT | +1.405 |
RNA | +1.389 |
VOL | +1.289 |
EH | +1.280 |
CONT | +1.259 |
Neg logit contributions | |
abl | -1.285 |
osexual | -1.248 |
xual | -1.178 |
wolves | -1.147 |
erer | -1.137 |
Token | lands |
Token ID | 8604 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
DIT | +0.589 |
RNA | +0.580 |
VOL | +0.530 |
EH | +0.525 |
CONT | +0.513 |
Neg logit contributions | |
abl | -0.735 |
osexual | -0.715 |
xual | -0.674 |
erer | -0.662 |
wolves | -0.661 |
Token | … |
Token ID | 1399 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
DIT | +0.232 |
RNA | +0.229 |
VOL | +0.213 |
EH | +0.211 |
CONT | +0.208 |
Neg logit contributions | |
abl | -0.211 |
osexual | -0.203 |
xual | -0.191 |
wolves | -0.187 |
erer | -0.186 |
Token | without |
Token ID | 19419 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
abl | +0.386 |
osexual | +0.374 |
xual | +0.353 |
wolves | +0.347 |
erer | +0.344 |
Neg logit contributions | |
DIT | -0.348 |
RNA | -0.343 |
VOL | -0.316 |
EH | -0.313 |
CONT | -0.306 |
Token | putting |
Token ID | 5137 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
DIT | +0.854 |
RNA | +0.846 |
VOL | +0.784 |
EH | +0.783 |
CONT | +0.772 |
Neg logit contributions | |
abl | -0.736 |
osexual | -0.717 |
xual | -0.673 |
wolves | -0.654 |
erer | -0.650 |
Token | an |
Token ID | 281 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
DIT | +1.376 |
RNA | +1.357 |
VOL | +1.258 |
EH | +1.253 |
CONT | +1.235 |
Neg logit contributions | |
abl | -1.268 |
osexual | -1.233 |
xual | -1.163 |
wolves | -1.133 |
erer | -1.125 |
Token | power |
Token ID | 1176 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
abl | +0.046 |
osexual | +0.044 |
xual | +0.042 |
wolves | +0.041 |
erer | +0.040 |
Neg logit contributions | |
DIT | -0.054 |
RNA | -0.054 |
VOL | -0.050 |
EH | -0.049 |
CONT | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
abl | +0.095 |
osexual | +0.091 |
xual | +0.086 |
wolves | +0.084 |
erer | +0.083 |
Neg logit contributions | |
DIT | -0.118 |
RNA | -0.117 |
VOL | -0.109 |
EH | -0.108 |
CONT | -0.106 |
Token | naming |
Token ID | 19264 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
abl | +0.086 |
osexual | +0.083 |
xual | +0.078 |
wolves | +0.076 |
erer | +0.075 |
Neg logit contributions | |
DIT | -0.100 |
RNA | -0.099 |
VOL | -0.092 |
EH | -0.092 |
CONT | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
DIT | +0.498 |
RNA | +0.492 |
VOL | +0.456 |
EH | +0.453 |
CONT | +0.445 |
Neg logit contributions | |
abl | -0.454 |
osexual | -0.440 |
xual | -0.414 |
wolves | -0.404 |
erer | -0.401 |
Token | The |
Token ID | 383 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
abl | +0.009 |
osexual | +0.009 |
xual | +0.009 |
wolves | +0.008 |
erer | +0.008 |
Neg logit contributions | |
DIT | -0.009 |
RNA | -0.009 |
VOL | -0.009 |
EH | -0.008 |
CONT | -0.008 |
Token | original |
Token ID | 2656 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
DIT | +0.138 |
RNA | +0.137 |
VOL | +0.127 |
EH | +0.126 |
CONT | +0.124 |
Neg logit contributions | |
abl | -0.123 |
osexual | -0.119 |
xual | -0.112 |
wolves | -0.110 |
erer | -0.109 |
Token | power |
Token ID | 1176 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
DIT | +0.755 |
RNA | +0.746 |
VOL | +0.692 |
EH | +0.687 |
CONT | +0.675 |
Neg logit contributions | |
abl | -0.703 |
osexual | -0.681 |
xual | -0.642 |
wolves | -0.626 |
erer | -0.622 |
Token | of |
Token ID | 286 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
abl | +0.087 |
osexual | +0.084 |
xual | +0.079 |
wolves | +0.077 |
erer | +0.076 |
Neg logit contributions | |
DIT | -0.100 |
RNA | -0.099 |
VOL | -0.092 |
EH | -0.091 |
CONT | -0.090 |
Token | language |
Token ID | 3303 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
abl | +0.173 |
osexual | +0.168 |
xual | +0.158 |
wolves | +0.155 |
erer | +0.153 |
Neg logit contributions | |
DIT | -0.177 |
RNA | -0.174 |
VOL | -0.162 |
EH | -0.160 |
CONT | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
DIT | +0.906 |
RNA | +0.894 |
VOL | +0.826 |
EH | +0.820 |
CONT | +0.807 |
Neg logit contributions | |
abl | -0.918 |
osexual | -0.893 |
xual | -0.843 |
wolves | -0.823 |
erer | -0.818 |
Token | Nietzsche |
Token ID | 40258 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
abl | +0.280 |
osexual | +0.271 |
xual | +0.256 |
wolves | +0.250 |
erer | +0.249 |
Neg logit contributions | |
DIT | -0.281 |
RNA | -0.277 |
VOL | -0.257 |
EH | -0.254 |
CONT | -0.249 |
Token | ь |
Token ID | 45367 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
abl | +0.108 |
osexual | +0.105 |
xual | +0.099 |
wolves | +0.097 |
erer | +0.097 |
Neg logit contributions | |
DIT | -0.099 |
RNA | -0.098 |
VOL | -0.090 |
EH | -0.089 |
CONT | -0.087 |
Token | м |
Token ID | 43108 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
DIT | +0.261 |
RNA | +0.259 |
VOL | +0.240 |
EH | +0.239 |
CONT | +0.234 |
Neg logit contributions | |
abl | -0.236 |
osexual | -0.227 |
xual | -0.214 |
wolves | -0.208 |
erer | -0.207 |
Token | а |
Token ID | 16142 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
abl | +0.647 |
osexual | +0.623 |
xual | +0.588 |
erer | +0.574 |
wolves | +0.572 |
Neg logit contributions | |
DIT | -0.616 |
RNA | -0.611 |
VOL | -0.563 |
EH | -0.559 |
thumbnails | -0.547 |
Token | � |
Token ID | 12466 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
DIT | +0.049 |
RNA | +0.048 |
VOL | +0.045 |
EH | +0.044 |
CONT | +0.043 |
Neg logit contributions | |
abl | -0.048 |
osexual | -0.046 |
xual | -0.044 |
wolves | -0.043 |
erer | -0.042 |
Token | � |
Token ID | 123 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
abl | +0.507 |
osexual | +0.487 |
xual | +0.458 |
wolves | +0.445 |
erer | +0.441 |
Neg logit contributions | |
DIT | -0.609 |
RNA | -0.601 |
VOL | -0.558 |
EH | -0.557 |
CONT | -0.546 |
Token | о� |
Token ID | 25443 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
abl | +0.179 |
osexual | +0.174 |
xual | +0.165 |
wolves | +0.161 |
erer | +0.161 |
Neg logit contributions | |
DIT | -0.145 |
RNA | -0.143 |
VOL | -0.131 |
EH | -0.130 |
CONT | -0.127 |
Token | � |
Token ID | 115 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
DIT | +1.019 |
RNA | +1.006 |
VOL | +0.931 |
EH | +0.923 |
CONT | +0.907 |
Neg logit contributions | |
abl | -1.009 |
osexual | -0.979 |
xual | -0.924 |
wolves | -0.903 |
erer | -0.896 |
Token | д |
Token ID | 43666 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
abl | +0.050 |
osexual | +0.048 |
xual | +0.046 |
erer | +0.044 |
wolves | +0.044 |
Neg logit contributions | |
DIT | -0.052 |
RNA | -0.051 |
VOL | -0.047 |
EH | -0.047 |
CONT | -0.046 |
Token | н |
Token ID | 22177 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
DIT | +1.001 |
RNA | +0.987 |
VOL | +0.908 |
EH | +0.900 |
CONT | +0.883 |
Neg logit contributions | |
abl | -1.114 |
osexual | -1.083 |
xual | -1.027 |
wolves | -1.005 |
erer | -0.997 |
Token | и |
Token ID | 18849 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
abl | +0.324 |
osexual | +0.311 |
xual | +0.293 |
wolves | +0.286 |
erer | +0.286 |
Neg logit contributions | |
DIT | -0.339 |
RNA | -0.335 |
EH | -0.309 |
VOL | -0.309 |
CONT | -0.303 |
Token | м |
Token ID | 43108 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
DIT | +0.171 |
RNA | +0.170 |
VOL | +0.157 |
EH | +0.156 |
CONT | +0.153 |
Neg logit contributions | |
abl | -0.165 |
osexual | -0.159 |
xual | -0.150 |
wolves | -0.146 |
erer | -0.145 |
Token | into |
Token ID | 656 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
DIT | +0.583 |
RNA | +0.574 |
VOL | +0.538 |
EH | +0.534 |
CONT | +0.524 |
Neg logit contributions | |
abl | -0.416 |
osexual | -0.403 |
xual | -0.371 |
wolves | -0.366 |
erer | -0.362 |
Token | existence |
Token ID | 6224 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
abl | +0.054 |
osexual | +0.051 |
xual | +0.047 |
wolves | +0.045 |
erer | +0.045 |
Neg logit contributions | |
DIT | -0.108 |
RNA | -0.107 |
VOL | -0.101 |
EH | -0.100 |
CONT | -0.099 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
DIT | +0.683 |
RNA | +0.674 |
VOL | +0.628 |
EH | +0.623 |
CONT | +0.613 |
Neg logit contributions | |
abl | -0.603 |
osexual | -0.585 |
xual | -0.551 |
wolves | -0.537 |
erer | -0.532 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
DIT | +0.309 |
RNA | +0.305 |
VOL | +0.284 |
EH | +0.282 |
CONT | +0.277 |
Neg logit contributions | |
abl | -0.256 |
osexual | -0.246 |
xual | -0.231 |
wolves | -0.225 |
erer | -0.224 |
Token | early |
Token ID | 1903 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
DIT | +0.050 |
RNA | +0.049 |
VOL | +0.046 |
EH | +0.045 |
CONT | +0.044 |
Neg logit contributions | |
abl | -0.043 |
osexual | -0.042 |
xual | -0.039 |
wolves | -0.038 |
erer | -0.038 |
Token | part |
Token ID | 636 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
DIT | +0.296 |
RNA | +0.293 |
VOL | +0.273 |
EH | +0.272 |
CONT | +0.267 |
Neg logit contributions | |
abl | -0.226 |
osexual | -0.218 |
xual | -0.204 |
wolves | -0.199 |
erer | -0.197 |
Token | of |
Token ID | 286 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
DIT | +1.360 |
RNA | +1.343 |
VOL | +1.251 |
EH | +1.240 |
CONT | +1.220 |
Neg logit contributions | |
abl | -1.166 |
osexual | -1.127 |
xual | -1.058 |
wolves | -1.032 |
erer | -1.028 |
Token | the |
Token ID | 262 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
DIT | +0.043 |
RNA | +0.043 |
VOL | +0.040 |
EH | +0.039 |
CONT | +0.039 |
Neg logit contributions | |
abl | -0.036 |
osexual | -0.035 |
xual | -0.033 |
wolves | -0.032 |
erer | -0.032 |
Token | 20 |
Token ID | 1160 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
abl | +0.101 |
osexual | +0.098 |
xual | +0.092 |
wolves | +0.090 |
erer | +0.089 |
Neg logit contributions | |
DIT | -0.114 |
RNA | -0.113 |
VOL | -0.105 |
EH | -0.104 |
CONT | -0.103 |
Token | th |
Token ID | 400 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
abl | +0.172 |
osexual | +0.169 |
xual | +0.161 |
wolves | +0.160 |
awn | +0.160 |
Neg logit contributions | |
DIT | -0.079 |
RNA | -0.078 |
VOL | -0.068 |
EH | -0.067 |
TEXT | -0.064 |
Token | century |
Token ID | 4289 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
abl | +0.297 |
osexual | +0.285 |
xual | +0.264 |
wolves | +0.256 |
erer | +0.252 |
Neg logit contributions | |
DIT | -0.512 |
RNA | -0.506 |
VOL | -0.476 |
EH | -0.473 |
CONT | -0.467 |
Token | Sexual |
Token ID | 19536 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
DIT | +0.152 |
RNA | +0.150 |
VOL | +0.140 |
EH | +0.138 |
CONT | +0.136 |
Neg logit contributions | |
abl | -0.137 |
osexual | -0.132 |
xual | -0.124 |
wolves | -0.121 |
erer | -0.120 |
Token | orientation |
Token ID | 12852 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
DIT | +0.705 |
RNA | +0.697 |
VOL | +0.656 |
EH | +0.652 |
CONT | +0.644 |
Neg logit contributions | |
abl | -0.400 |
osexual | -0.380 |
xual | -0.353 |
wolves | -0.342 |
erer | -0.337 |
Token | has |
Token ID | 468 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
DIT | +0.250 |
RNA | +0.246 |
VOL | +0.227 |
EH | +0.225 |
CONT | +0.222 |
Neg logit contributions | |
abl | -0.264 |
osexual | -0.256 |
xual | -0.242 |
wolves | -0.237 |
erer | -0.235 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
DIT | +0.445 |
RNA | +0.439 |
VOL | +0.408 |
EH | +0.405 |
CONT | +0.399 |
Neg logit contributions | |
abl | -0.403 |
osexual | -0.389 |
xual | -0.367 |
wolves | -0.358 |
erer | -0.355 |
Token | to |
Token ID | 284 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
DIT | +0.241 |
RNA | +0.237 |
VOL | +0.223 |
EH | +0.221 |
CONT | +0.219 |
Neg logit contributions | |
abl | -0.173 |
osexual | -0.165 |
xual | -0.155 |
wolves | -0.152 |
erer | -0.149 |
Token | do |
Token ID | 466 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
DIT | +0.394 |
RNA | +0.390 |
VOL | +0.357 |
EH | +0.354 |
CONT | +0.347 |
Neg logit contributions | |
abl | -0.454 |
osexual | -0.442 |
xual | -0.418 |
wolves | -0.408 |
erer | -0.407 |
Token | with |
Token ID | 351 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
DIT | +0.803 |
RNA | +0.795 |
VOL | +0.733 |
EH | +0.725 |
CONT | +0.711 |
Neg logit contributions | |
abl | -0.814 |
osexual | -0.787 |
xual | -0.742 |
erer | -0.725 |
wolves | -0.724 |
Token | gender |
Token ID | 5279 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
DIT | +0.963 |
RNA | +0.949 |
VOL | +0.887 |
EH | +0.881 |
CONT | +0.869 |
Neg logit contributions | |
abl | -0.759 |
osexual | -0.731 |
xual | -0.684 |
wolves | -0.669 |
erer | -0.663 |
Token | identity |
Token ID | 5369 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
abl | +1.510 |
osexual | +1.465 |
xual | +1.361 |
erer | +1.311 |
wolves | +1.310 |
Neg logit contributions | |
DIT | -1.952 |
RNA | -1.931 |
VOL | -1.798 |
EH | -1.792 |
CONT | -1.756 |
Token | or |
Token ID | 393 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
abl | +0.535 |
osexual | +0.520 |
xual | +0.489 |
wolves | +0.477 |
erer | +0.474 |
Neg logit contributions | |
DIT | -0.564 |
RNA | -0.558 |
VOL | -0.517 |
EH | -0.513 |
CONT | -0.504 |
Token | gender |
Token ID | 5279 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
abl | +0.508 |
osexual | +0.491 |
xual | +0.458 |
wolves | +0.444 |
erer | +0.441 |
Neg logit contributions | |
DIT | -0.712 |
RNA | -0.704 |
VOL | -0.659 |
EH | -0.654 |
CONT | -0.644 |
Token | of |
Token ID | 286 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
abl | +0.312 |
osexual | +0.300 |
xual | +0.282 |
wolves | +0.275 |
erer | +0.272 |
Neg logit contributions | |
DIT | -0.379 |
RNA | -0.375 |
VOL | -0.349 |
EH | -0.346 |
CONT | -0.341 |
Token | possible |
Token ID | 1744 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
abl | +0.078 |
osexual | +0.075 |
xual | +0.070 |
wolves | +0.069 |
erer | +0.068 |
Neg logit contributions | |
DIT | -0.091 |
RNA | -0.090 |
VOL | -0.083 |
EH | -0.083 |
CONT | -0.081 |
Token | impaired |
Token ID | 22753 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
DIT | +0.308 |
RNA | +0.304 |
VOL | +0.282 |
EH | +0.279 |
CONT | +0.275 |
Neg logit contributions | |
abl | -0.279 |
osexual | -0.270 |
xual | -0.253 |
wolves | -0.248 |
erer | -0.246 |
Token | driving |
Token ID | 5059 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
abl | +1.505 |
osexual | +1.443 |
xual | +1.365 |
wolves | +1.345 |
erer | +1.344 |
Neg logit contributions | |
DIT | -1.341 |
RNA | -1.321 |
VOL | -1.209 |
EH | -1.191 |
CONT | -1.173 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
DIT | +0.618 |
RNA | +0.610 |
VOL | +0.566 |
EH | +0.563 |
CONT | +0.552 |
Neg logit contributions | |
abl | -0.573 |
osexual | -0.558 |
xual | -0.526 |
wolves | -0.512 |
erer | -0.508 |
Token | Further |
Token ID | 7735 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
abl | +0.286 |
osexual | +0.276 |
xual | +0.257 |
wolves | +0.253 |
erer | +0.250 |
Neg logit contributions | |
DIT | -0.350 |
RNA | -0.346 |
VOL | -0.323 |
EH | -0.320 |
CONT | -0.315 |
Token | investigation |
Token ID | 3645 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
abl | +0.183 |
osexual | +0.177 |
xual | +0.166 |
wolves | +0.162 |
erer | +0.161 |
Neg logit contributions | |
DIT | -0.210 |
RNA | -0.208 |
VOL | -0.193 |
EH | -0.191 |
CONT | -0.188 |
Token | revealed |
Token ID | 4602 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
DIT | +0.107 |
RNA | +0.106 |
VOL | +0.098 |
EH | +0.097 |
CONT | +0.096 |
Neg logit contributions | |
abl | -0.089 |
osexual | -0.086 |
xual | -0.080 |
wolves | -0.079 |
erer | -0.078 |
Token | he |
Token ID | 339 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
abl | +0.164 |
osexual | +0.158 |
xual | +0.148 |
wolves | +0.145 |
erer | +0.144 |
Neg logit contributions | |
DIT | -0.208 |
RNA | -0.205 |
VOL | -0.192 |
EH | -0.190 |
CONT | -0.187 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
DIT | +0.083 |
RNA | +0.082 |
VOL | +0.074 |
EH | +0.074 |
CONT | +0.072 |
Neg logit contributions | |
abl | -0.105 |
osexual | -0.102 |
xual | -0.097 |
wolves | -0.095 |
erer | -0.095 |
Token | driving |
Token ID | 5059 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
DIT | +0.290 |
RNA | +0.286 |
VOL | +0.266 |
EH | +0.263 |
CONT | +0.259 |
Neg logit contributions | |
abl | -0.252 |
osexual | -0.244 |
xual | -0.229 |
wolves | -0.224 |
erer | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
DIT | +0.746 |
RNA | +0.736 |
VOL | +0.684 |
EH | +0.679 |
CONT | +0.668 |
Neg logit contributions | |
abl | -0.676 |
osexual | -0.656 |
xual | -0.617 |
wolves | -0.601 |
erer | -0.597 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
abl | +0.182 |
osexual | +0.176 |
xual | +0.169 |
wolves | +0.165 |
erer | +0.163 |
Neg logit contributions | |
DIT | -0.140 |
RNA | -0.138 |
VOL | -0.125 |
EH | -0.124 |
CONT | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
abl | +0.073 |
osexual | +0.070 |
erer | +0.066 |
wolves | +0.065 |
xual | +0.065 |
Neg logit contributions | |
DIT | -0.068 |
RNA | -0.067 |
VOL | -0.062 |
EH | -0.061 |
thumbnails | -0.061 |
Token | Dr |
Token ID | 6187 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
abl | +0.057 |
osexual | +0.055 |
xual | +0.052 |
wolves | +0.051 |
erer | +0.051 |
Neg logit contributions | |
DIT | -0.046 |
RNA | -0.046 |
VOL | -0.042 |
EH | -0.041 |
Chatt | -0.041 |
Token | Ian |
Token ID | 12930 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
DIT | +0.911 |
RNA | +0.901 |
EH | +0.820 |
VOL | +0.819 |
CONT | +0.800 |
Neg logit contributions | |
abl | -1.044 |
osexual | -1.013 |
xual | -0.966 |
wolves | -0.942 |
erer | -0.933 |
Token | Jenkins |
Token ID | 21835 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
DIT | +0.115 |
RNA | +0.113 |
VOL | +0.103 |
EH | +0.102 |
CONT | +0.100 |
Neg logit contributions | |
abl | -0.166 |
osexual | -0.162 |
xual | -0.154 |
wolves | -0.151 |
erer | -0.150 |
Token | is |
Token ID | 318 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
abl | +0.523 |
osexual | +0.509 |
xual | +0.475 |
erer | +0.466 |
wolves | +0.461 |
Neg logit contributions | |
DIT | -0.604 |
RNA | -0.594 |
VOL | -0.554 |
EH | -0.547 |
CONT | -0.538 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
DIT | +0.224 |
RNA | +0.221 |
VOL | +0.205 |
EH | +0.204 |
CONT | +0.200 |
Neg logit contributions | |
abl | -0.209 |
osexual | -0.203 |
xual | -0.191 |
wolves | -0.187 |
erer | -0.185 |
Token | British |
Token ID | 3517 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
abl | +0.039 |
osexual | +0.038 |
xual | +0.036 |
erer | +0.035 |
wolves | +0.035 |
Neg logit contributions | |
DIT | -0.030 |
RNA | -0.030 |
VOL | -0.027 |
EH | -0.027 |
CONT | -0.026 |
Token | Museum |
Token ID | 9594 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
DIT | +0.153 |
RNA | +0.151 |
VOL | +0.137 |
EH | +0.136 |
CONT | +0.132 |
Neg logit contributions | |
abl | -0.212 |
osexual | -0.207 |
xual | -0.196 |
erer | -0.194 |
wolves | -0.192 |
Token | 's |
Token ID | 338 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
abl | +0.744 |
osexual | +0.726 |
xual | +0.683 |
erer | +0.672 |
wolves | +0.663 |
Neg logit contributions | |
DIT | -0.718 |
RNA | -0.708 |
VOL | -0.652 |
EH | -0.644 |
CONT | -0.631 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
DIT | +0.226 |
RNA | +0.224 |
VOL | +0.208 |
EH | +0.206 |
CONT | +0.203 |
Neg logit contributions | |
abl | -0.196 |
osexual | -0.189 |
xual | -0.178 |
wolves | -0.173 |
erer | -0.172 |
Token | or |
Token ID | 393 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
abl | +0.060 |
osexual | +0.058 |
xual | +0.055 |
wolves | +0.053 |
erer | +0.053 |
Neg logit contributions | |
DIT | -0.059 |
RNA | -0.058 |
VOL | -0.054 |
EH | -0.054 |
CONT | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
abl | +0.483 |
osexual | +0.466 |
xual | +0.438 |
wolves | +0.426 |
erer | +0.424 |
Neg logit contributions | |
DIT | -0.583 |
RNA | -0.578 |
VOL | -0.537 |
EH | -0.533 |
CONT | -0.523 |
Token | holiday |
Token ID | 9912 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
abl | +0.177 |
osexual | +0.171 |
xual | +0.160 |
wolves | +0.156 |
erer | +0.155 |
Neg logit contributions | |
DIT | -0.215 |
RNA | -0.213 |
VOL | -0.198 |
EH | -0.197 |
CONT | -0.194 |
Token | tradition |
Token ID | 6761 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
abl | +0.461 |
osexual | +0.445 |
xual | +0.419 |
wolves | +0.409 |
erer | +0.406 |
Neg logit contributions | |
DIT | -0.533 |
RNA | -0.528 |
VOL | -0.490 |
EH | -0.487 |
CONT | -0.478 |
Token | that |
Token ID | 326 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
DIT | +0.266 |
RNA | +0.263 |
VOL | +0.245 |
EH | +0.243 |
CONT | +0.239 |
Neg logit contributions | |
abl | -0.224 |
osexual | -0.217 |
xual | -0.204 |
wolves | -0.199 |
erer | -0.197 |
Token | dates |
Token ID | 9667 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
DIT | +0.043 |
RNA | +0.042 |
VOL | +0.039 |
EH | +0.039 |
CONT | +0.038 |
Neg logit contributions | |
abl | -0.042 |
osexual | -0.041 |
xual | -0.039 |
wolves | -0.038 |
erer | -0.038 |
Token | back |
Token ID | 736 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
abl | +0.039 |
osexual | +0.038 |
xual | +0.035 |
wolves | +0.034 |
erer | +0.034 |
Neg logit contributions | |
DIT | -0.057 |
RNA | -0.056 |
VOL | -0.053 |
EH | -0.052 |
CONT | -0.052 |
Token | generations |
Token ID | 10439 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
DIT | +0.081 |
RNA | +0.080 |
VOL | +0.075 |
EH | +0.075 |
CONT | +0.074 |
Neg logit contributions | |
abl | -0.057 |
osexual | -0.055 |
xual | -0.051 |
wolves | -0.050 |
erer | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
DIT | +1.213 |
RNA | +1.196 |
VOL | +1.109 |
EH | +1.102 |
CONT | +1.084 |
Neg logit contributions | |
abl | -1.117 |
osexual | -1.083 |
xual | -1.022 |
wolves | -0.995 |
erer | -0.986 |
Token | � |
Token ID | 447 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
DIT | +0.230 |
RNA | +0.226 |
VOL | +0.209 |
EH | +0.208 |
CONT | +0.204 |
Neg logit contributions | |
abl | -0.231 |
osexual | -0.225 |
xual | -0.212 |
wolves | -0.207 |
erer | -0.206 |
Token | in |
Token ID | 287 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
DIT | +0.363 |
RNA | +0.358 |
VOL | +0.330 |
EH | +0.328 |
CONT | +0.322 |
Neg logit contributions | |
abl | -0.380 |
osexual | -0.368 |
xual | -0.346 |
wolves | -0.340 |
erer | -0.336 |
Token | Japan |
Token ID | 2869 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
abl | +0.175 |
osexual | +0.169 |
xual | +0.158 |
wolves | +0.154 |
erer | +0.154 |
Neg logit contributions | |
DIT | -0.192 |
RNA | -0.191 |
VOL | -0.176 |
EH | -0.175 |
CONT | -0.171 |
Token | � |
Token ID | 447 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
abl | +0.099 |
osexual | +0.096 |
xual | +0.091 |
wolves | +0.089 |
erer | +0.088 |
Neg logit contributions | |
DIT | -0.104 |
RNA | -0.103 |
VOL | -0.095 |
EH | -0.094 |
CONT | -0.092 |
Token | � |
Token ID | 251 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
abl | +0.356 |
osexual | +0.343 |
xual | +0.320 |
erer | +0.311 |
wolves | +0.310 |
Neg logit contributions | |
DIT | -0.472 |
RNA | -0.467 |
VOL | -0.436 |
EH | -0.436 |
Chatt | -0.428 |
Token | report |
Token ID | 989 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
DIT | +0.379 |
RNA | +0.375 |
VOL | +0.347 |
EH | +0.344 |
CONT | +0.339 |
Neg logit contributions | |
abl | -0.361 |
osexual | -0.349 |
xual | -0.330 |
wolves | -0.322 |
erer | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
DIT | +0.207 |
RNA | +0.205 |
VOL | +0.190 |
EH | +0.188 |
CONT | +0.185 |
Neg logit contributions | |
abl | -0.181 |
osexual | -0.175 |
xual | -0.165 |
wolves | -0.161 |
erer | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
abl | +0.403 |
osexual | +0.390 |
xual | +0.369 |
wolves | +0.362 |
erer | +0.359 |
Neg logit contributions | |
DIT | -0.380 |
RNA | -0.376 |
VOL | -0.346 |
EH | -0.343 |
CONT | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
abl | +0.288 |
osexual | +0.274 |
erer | +0.258 |
wolves | +0.256 |
xual | +0.254 |
Neg logit contributions | |
DIT | -0.269 |
RNA | -0.264 |
VOL | -0.246 |
EH | -0.242 |
Chatt | -0.239 |
Token | Last |
Token ID | 5956 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
abl | +0.169 |
osexual | +0.164 |
xual | +0.154 |
wolves | +0.152 |
erer | +0.151 |
Neg logit contributions | |
DIT | -0.151 |
RNA | -0.149 |
VOL | -0.136 |
EH | -0.135 |
Chatt | -0.133 |
Token | month |
Token ID | 1227 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
DIT | +0.265 |
RNA | +0.261 |
VOL | +0.242 |
EH | +0.241 |
CONT | +0.237 |
Neg logit contributions | |
abl | -0.243 |
osexual | -0.235 |
xual | -0.221 |
wolves | -0.216 |
erer | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
abl | +0.309 |
osexual | +0.300 |
xual | +0.282 |
wolves | +0.276 |
erer | +0.274 |
Neg logit contributions | |
DIT | -0.340 |
RNA | -0.336 |
VOL | -0.312 |
EH | -0.310 |
CONT | -0.304 |
Token | only |
Token ID | 691 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
abl | +0.078 |
osexual | +0.075 |
xual | +0.071 |
wolves | +0.070 |
erer | +0.069 |
Neg logit contributions | |
DIT | -0.084 |
RNA | -0.083 |
VOL | -0.077 |
EH | -0.077 |
CONT | -0.075 |
Token | one |
Token ID | 530 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
abl | +1.031 |
osexual | +0.998 |
xual | +0.938 |
wolves | +0.934 |
erer | +0.913 |
Neg logit contributions | |
DIT | -1.012 |
RNA | -1.005 |
VOL | -0.925 |
EH | -0.915 |
CONT | -0.899 |
Token | enemy |
Token ID | 4472 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
abl | +0.611 |
osexual | +0.591 |
xual | +0.556 |
wolves | +0.548 |
erer | +0.543 |
Neg logit contributions | |
DIT | -0.615 |
RNA | -0.610 |
VOL | -0.564 |
EH | -0.556 |
CONT | -0.547 |
Token | minion |
Token ID | 28365 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
DIT | +0.144 |
RNA | +0.142 |
VOL | +0.131 |
EH | +0.129 |
CONT | +0.127 |
Neg logit contributions | |
abl | -0.158 |
osexual | -0.153 |
xual | -0.145 |
wolves | -0.143 |
erer | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
DIT | +1.214 |
RNA | +1.200 |
VOL | +1.116 |
EH | +1.108 |
CONT | +1.090 |
Neg logit contributions | |
abl | -1.044 |
osexual | -1.011 |
xual | -0.950 |
wolves | -0.924 |
erer | -0.918 |
Token | it |
Token ID | 340 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
DIT | +0.046 |
RNA | +0.046 |
VOL | +0.043 |
EH | +0.042 |
CONT | +0.041 |
Neg logit contributions | |
abl | -0.043 |
osexual | -0.041 |
xual | -0.039 |
wolves | -0.038 |
erer | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
DIT | +0.034 |
RNA | +0.034 |
VOL | +0.031 |
EH | +0.030 |
CONT | +0.030 |
Neg logit contributions | |
abl | -0.042 |
osexual | -0.040 |
xual | -0.038 |
wolves | -0.038 |
erer | -0.037 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
abl | +0.130 |
osexual | +0.125 |
xual | +0.118 |
wolves | +0.116 |
erer | +0.114 |
Neg logit contributions | |
DIT | -0.147 |
RNA | -0.146 |
VOL | -0.135 |
EH | -0.134 |
CONT | -0.132 |
Token | os |
Token ID | 418 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
DIT | +0.932 |
RNA | +0.923 |
VOL | +0.862 |
EH | +0.855 |
CONT | +0.842 |
Neg logit contributions | |
abl | -0.724 |
osexual | -0.696 |
xual | -0.645 |
wolves | -0.637 |
awn | -0.628 |
Token | , |
Token ID | 11 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
DIT | +0.319 |
RNA | +0.317 |
VOL | +0.295 |
EH | +0.291 |
CONT | +0.288 |
Neg logit contributions | |
abl | -0.277 |
osexual | -0.265 |
xual | -0.250 |
wolves | -0.245 |
erer | -0.243 |
Token | and |
Token ID | 290 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
abl | +0.098 |
osexual | +0.094 |
xual | +0.089 |
wolves | +0.088 |
erer | +0.087 |
Neg logit contributions | |
RNA | -0.111 |
DIT | -0.110 |
VOL | -0.103 |
EH | -0.101 |
CONT | -0.099 |
Token | Stanley |
Token ID | 14167 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
abl | +0.081 |
osexual | +0.079 |
xual | +0.074 |
wolves | +0.073 |
erer | +0.073 |
Neg logit contributions | |
DIT | -0.081 |
RNA | -0.080 |
VOL | -0.074 |
EH | -0.074 |
thumbnails | -0.072 |
Token | Cup |
Token ID | 5454 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
abl | +1.093 |
osexual | +1.050 |
erer | +0.995 |
awn | +0.967 |
xual | +0.962 |
Neg logit contributions | |
DIT | -1.064 |
RNA | -1.034 |
VOL | -0.962 |
EH | -0.954 |
thumbnails | -0.952 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
abl | +0.412 |
osexual | +0.396 |
xual | +0.369 |
erer | +0.367 |
awn | +0.362 |
Neg logit contributions | |
DIT | -0.447 |
RNA | -0.443 |
VOL | -0.410 |
EH | -0.407 |
thumbnails | -0.398 |
Token | Alex |
Token ID | 4422 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
DIT | +0.014 |
RNA | +0.014 |
VOL | +0.013 |
EH | +0.013 |
CONT | +0.012 |
Neg logit contributions | |
abl | -0.014 |
osexual | -0.013 |
xual | -0.012 |
wolves | -0.012 |
erer | -0.012 |
Token | O |
Token ID | 440 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
abl | +0.065 |
osexual | +0.062 |
xual | +0.057 |
wolves | +0.057 |
erer | +0.057 |
Neg logit contributions | |
DIT | -0.086 |
RNA | -0.085 |
VOL | -0.079 |
EH | -0.079 |
thumbnails | -0.077 |
Token | ve |
Token ID | 303 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
abl | +0.908 |
osexual | +0.885 |
erer | +0.834 |
xual | +0.834 |
wolves | +0.825 |
Neg logit contributions | |
RNA | -0.529 |
DIT | -0.528 |
VOL | -0.472 |
EH | -0.464 |
thumbnails | -0.463 |
Token | ch |
Token ID | 354 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
abl | +1.968 |
osexual | +1.929 |
xual | +1.805 |
wolves | +1.788 |
erer | +1.776 |
Neg logit contributions | |
DIT | -1.246 |
RNA | -1.244 |
VOL | -1.145 |
EH | -1.132 |
TEXT | -1.084 |
Token | kin |
Token ID | 5116 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
abl | +1.124 |
osexual | +1.094 |
xual | +1.003 |
wolves | +1.000 |
erer | +0.995 |
Neg logit contributions | |
DIT | -1.208 |
RNA | -1.189 |
VOL | -1.098 |
EH | -1.096 |
thumbnails | -1.067 |
Token | hasn |
Token ID | 5818 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
abl | +1.249 |
osexual | +1.200 |
xual | +1.129 |
erer | +1.115 |
wolves | +1.112 |
Neg logit contributions | |
DIT | -1.238 |
RNA | -1.229 |
VOL | -1.130 |
EH | -1.116 |
CONT | -1.095 |
Token | � |
Token ID | 447 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
DIT | +0.661 |
RNA | +0.654 |
VOL | +0.603 |
EH | +0.598 |
Chatt | +0.585 |
Neg logit contributions | |
abl | -0.709 |
osexual | -0.681 |
xual | -0.641 |
wolves | -0.633 |
erer | -0.630 |
Token | � |
Token ID | 247 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
abl | +0.173 |
osexual | +0.162 |
xual | +0.147 |
erer | +0.140 |
awn | +0.137 |
Neg logit contributions | |
DIT | -0.481 |
RNA | -0.475 |
EH | -0.451 |
VOL | -0.450 |
Chatt | -0.445 |
Token | construct |
Token ID | 5678 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
DIT | +0.137 |
RNA | +0.135 |
VOL | +0.125 |
EH | +0.123 |
CONT | +0.121 |
Neg logit contributions | |
abl | -0.140 |
osexual | -0.135 |
xual | -0.128 |
wolves | -0.125 |
erer | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | -7.81e-04 |
Pos logit contributions | |
abl | +0.300 |
osexual | +0.291 |
xual | +0.271 |
wolves | +0.267 |
erer | +0.265 |
Neg logit contributions | |
DIT | -0.336 |
RNA | -0.333 |
VOL | -0.309 |
EH | -0.303 |
CONT | -0.300 |
Token | pont |
Token ID | 45443 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
abl | +0.002 |
osexual | +0.002 |
xual | +0.001 |
erer | +0.001 |
wolves | +0.001 |
Neg logit contributions | |
DIT | -0.002 |
RNA | -0.002 |
VOL | -0.001 |
EH | -0.001 |
thumbnails | -0.001 |
Token | oon |
Token ID | 2049 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
DIT | +1.202 |
RNA | +1.178 |
VOL | +1.062 |
EH | +1.050 |
CONT | +1.027 |
Neg logit contributions | |
abl | -1.968 |
osexual | -1.922 |
xual | -1.827 |
wolves | -1.798 |
erer | -1.793 |
Token | bridge |
Token ID | 7696 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
abl | +0.065 |
osexual | +0.062 |
xual | +0.058 |
erer | +0.057 |
wolves | +0.057 |
Neg logit contributions | |
DIT | -0.090 |
RNA | -0.089 |
VOL | -0.083 |
EH | -0.081 |
CONT | -0.081 |
Token | across |
Token ID | 1973 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
DIT | +0.403 |
RNA | +0.399 |
VOL | +0.374 |
EH | +0.370 |
CONT | +0.366 |
Neg logit contributions | |
abl | -0.271 |
osexual | -0.260 |
xual | -0.241 |
wolves | -0.235 |
erer | -0.233 |
Token | the |
Token ID | 262 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
abl | +1.691 |
osexual | +1.613 |
xual | +1.493 |
erer | +1.470 |
wolves | +1.467 |
Neg logit contributions | |
DIT | -2.190 |
RNA | -2.174 |
VOL | -2.023 |
EH | -2.003 |
TEXT | -1.973 |
Token | narrow |
Token ID | 7135 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
abl | +0.096 |
osexual | +0.092 |
xual | +0.087 |
wolves | +0.086 |
erer | +0.085 |
Neg logit contributions | |
DIT | -0.087 |
RNA | -0.086 |
VOL | -0.079 |
EH | -0.078 |
CONT | -0.076 |
Token | passage |
Token ID | 10066 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
DIT | +0.304 |
RNA | +0.301 |
VOL | +0.277 |
EH | +0.274 |
CONT | +0.268 |
Neg logit contributions | |
abl | -0.347 |
osexual | -0.335 |
xual | -0.316 |
wolves | -0.311 |
erer | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
DIT | +0.230 |
RNA | +0.227 |
VOL | +0.212 |
EH | +0.209 |
CONT | +0.206 |
Neg logit contributions | |
abl | -0.196 |
osexual | -0.189 |
xual | -0.177 |
wolves | -0.173 |
erer | -0.172 |
Token | According |
Token ID | 4784 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
DIT | +0.281 |
RNA | +0.278 |
VOL | +0.259 |
EH | +0.256 |
CONT | +0.251 |
Neg logit contributions | |
abl | -0.251 |
osexual | -0.243 |
xual | -0.228 |
wolves | -0.224 |
erer | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
DIT | +0.391 |
RNA | +0.386 |
VOL | +0.357 |
EH | +0.354 |
CONT | +0.348 |
Neg logit contributions | |
abl | -0.387 |
osexual | -0.375 |
xual | -0.355 |
wolves | -0.346 |
erer | -0.343 |
Token | Obama |
Token ID | 2486 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
DIT | +0.071 |
RNA | +0.070 |
VOL | +0.065 |
EH | +0.065 |
CONT | +0.064 |
Neg logit contributions | |
abl | -0.062 |
osexual | -0.060 |
xual | -0.056 |
wolves | -0.055 |
erer | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
DIT | +0.116 |
RNA | +0.115 |
VOL | +0.106 |
EH | +0.105 |
CONT | +0.103 |
Neg logit contributions | |
abl | -0.114 |
osexual | -0.110 |
xual | -0.103 |
wolves | -0.101 |
erer | -0.101 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
DIT | +0.244 |
RNA | +0.241 |
VOL | +0.224 |
EH | +0.223 |
CONT | +0.219 |
Neg logit contributions | |
abl | -0.205 |
osexual | -0.198 |
xual | -0.187 |
wolves | -0.181 |
erer | -0.180 |
Token | by |
Token ID | 416 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
abl | +0.588 |
osexual | +0.567 |
xual | +0.527 |
wolves | +0.513 |
erer | +0.510 |
Neg logit contributions | |
DIT | -0.829 |
RNA | -0.821 |
VOL | -0.768 |
EH | -0.762 |
CONT | -0.750 |
Token | Mark |
Token ID | 2940 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
DIT | +0.231 |
RNA | +0.228 |
VOL | +0.211 |
EH | +0.209 |
CONT | +0.206 |
Neg logit contributions | |
abl | -0.225 |
osexual | -0.219 |
xual | -0.208 |
wolves | -0.202 |
erer | -0.200 |
Token | Kn |
Token ID | 6102 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
abl | +1.604 |
osexual | +1.516 |
awn | +1.432 |
erer | +1.412 |
xual | +1.396 |
Neg logit contributions | |
DIT | -1.579 |
RNA | -1.577 |
EH | -1.464 |
VOL | -1.456 |
CONT | -1.422 |
Token | oller |
Token ID | 49252 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
abl | +1.176 |
osexual | +1.126 |
xual | +1.040 |
erer | +1.039 |
awn | +1.031 |
Neg logit contributions | |
DIT | -1.176 |
RNA | -1.143 |
VOL | -1.075 |
EH | -1.057 |
CONT | -1.050 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
abl | +0.437 |
osexual | +0.422 |
xual | +0.395 |
wolves | +0.386 |
erer | +0.385 |
Neg logit contributions | |
DIT | -0.526 |
RNA | -0.520 |
VOL | -0.485 |
EH | -0.482 |
CONT | -0.473 |
Token | CBS |
Token ID | 11133 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
abl | +0.665 |
osexual | +0.642 |
xual | +0.602 |
wolves | +0.593 |
erer | +0.591 |
Neg logit contributions | |
DIT | -0.685 |
RNA | -0.675 |
VOL | -0.626 |
EH | -0.619 |
CONT | -0.608 |
Token | if |
Token ID | 611 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
abl | +0.901 |
osexual | +0.874 |
xual | +0.824 |
wolves | +0.811 |
erer | +0.804 |
Neg logit contributions | |
DIT | -0.794 |
RNA | -0.781 |
VOL | -0.719 |
EH | -0.710 |
CONT | -0.697 |
Token | tex |
Token ID | 16886 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
DIT | +0.280 |
RNA | +0.277 |
VOL | +0.256 |
EH | +0.254 |
CONT | +0.250 |
Neg logit contributions | |
abl | -0.272 |
osexual | -0.263 |
xual | -0.248 |
wolves | -0.242 |
erer | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
abl | +0.540 |
osexual | +0.515 |
xual | +0.477 |
erer | +0.467 |
wolves | +0.465 |
Neg logit contributions | |
DIT | -0.774 |
RNA | -0.767 |
VOL | -0.717 |
EH | -0.712 |
CONT | -0.701 |
Token | xy |
Token ID | 5431 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
abl | +0.218 |
osexual | +0.211 |
xual | +0.199 |
wolves | +0.194 |
erer | +0.193 |
Neg logit contributions | |
DIT | -0.221 |
RNA | -0.218 |
VOL | -0.201 |
EH | -0.200 |
CONT | -0.196 |
Token | z |
Token ID | 89 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
DIT | +0.119 |
RNA | +0.118 |
VOL | +0.110 |
EH | +0.109 |
CONT | +0.108 |
Neg logit contributions | |
abl | -0.086 |
osexual | -0.082 |
xual | -0.076 |
wolves | -0.075 |
erer | -0.074 |
Token | += |
Token ID | 15853 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
abl | +0.240 |
osexual | +0.228 |
xual | +0.208 |
wolves | +0.202 |
erer | +0.201 |
Neg logit contributions | |
DIT | -0.466 |
RNA | -0.461 |
VOL | -0.435 |
EH | -0.432 |
CONT | -0.426 |
Token | v |
Token ID | 410 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
abl | +1.066 |
osexual | +1.020 |
xual | +0.959 |
wolves | +0.940 |
erer | +0.939 |
Neg logit contributions | |
DIT | -1.197 |
RNA | -1.190 |
VOL | -1.096 |
EH | -1.091 |
CONT | -1.066 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
abl | +1.404 |
osexual | +1.356 |
xual | +1.273 |
wolves | +1.242 |
erer | +1.242 |
Neg logit contributions | |
DIT | -1.592 |
RNA | -1.578 |
VOL | -1.461 |
EH | -1.448 |
CONT | -1.424 |
Token | normal |
Token ID | 11265 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
abl | +0.469 |
osexual | +0.453 |
xual | +0.427 |
wolves | +0.418 |
erer | +0.415 |
Neg logit contributions | |
DIT | -0.483 |
RNA | -0.477 |
VOL | -0.441 |
EH | -0.439 |
CONT | -0.430 |
Token | * |
Token ID | 1635 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
DIT | +0.222 |
RNA | +0.219 |
VOL | +0.203 |
EH | +0.202 |
CONT | +0.198 |
Neg logit contributions | |
abl | -0.209 |
osexual | -0.202 |
xual | -0.190 |
erer | -0.186 |
wolves | -0.185 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
DIT | +0.211 |
RNA | +0.208 |
VOL | +0.194 |
EH | +0.192 |
CONT | +0.189 |
Neg logit contributions | |
abl | -0.195 |
osexual | -0.190 |
xual | -0.179 |
wolves | -0.174 |
erer | -0.173 |
Token | ; |
Token ID | 26 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
abl | +0.419 |
osexual | +0.406 |
xual | +0.384 |
wolves | +0.376 |
erer | +0.375 |
Neg logit contributions | |
DIT | -0.386 |
RNA | -0.382 |
VOL | -0.351 |
EH | -0.347 |
CONT | -0.341 |
Token | bit |
Token ID | 1643 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
DIT | +0.177 |
RNA | +0.175 |
VOL | +0.160 |
EH | +0.159 |
CONT | +0.155 |
Neg logit contributions | |
abl | -0.209 |
osexual | -0.204 |
xual | -0.193 |
wolves | -0.189 |
erer | -0.188 |
Token | of |
Token ID | 286 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
DIT | +1.472 |
RNA | +1.455 |
VOL | +1.354 |
EH | +1.346 |
CONT | +1.326 |
Neg logit contributions | |
abl | -1.246 |
osexual | -1.208 |
xual | -1.137 |
wolves | -1.103 |
erer | -1.089 |
Token | a |
Token ID | 257 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
abl | +0.168 |
osexual | +0.163 |
xual | +0.154 |
erer | +0.150 |
wolves | +0.150 |
Neg logit contributions | |
DIT | -0.184 |
RNA | -0.182 |
VOL | -0.170 |
EH | -0.168 |
CONT | -0.164 |
Token | fac |
Token ID | 1777 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
abl | +0.055 |
osexual | +0.053 |
xual | +0.050 |
wolves | +0.049 |
erer | +0.049 |
Neg logit contributions | |
DIT | -0.054 |
RNA | -0.053 |
VOL | -0.049 |
EH | -0.049 |
CONT | -0.048 |
Token | el |
Token ID | 417 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
abl | +0.722 |
osexual | +0.670 |
xual | +0.581 |
erer | +0.569 |
wolves | +0.562 |
Neg logit contributions | |
DIT | -2.015 |
RNA | -1.978 |
VOL | -1.886 |
EH | -1.878 |
CONT | -1.859 |
Token | ift |
Token ID | 2135 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
abl | +1.053 |
osexual | +0.989 |
awn | +0.921 |
erer | +0.917 |
xual | +0.916 |
Neg logit contributions | |
DIT | -1.296 |
RNA | -1.250 |
VOL | -1.193 |
EH | -1.172 |
CONT | -1.167 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
abl | +1.261 |
osexual | +1.215 |
xual | +1.135 |
erer | +1.110 |
wolves | +1.106 |
Neg logit contributions | |
DIT | -1.563 |
RNA | -1.549 |
VOL | -1.441 |
EH | -1.420 |
CONT | -1.403 |
Token |
|
Token ID | 198 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
abl | +0.420 |
osexual | +0.408 |
xual | +0.384 |
wolves | +0.379 |
erer | +0.376 |
Neg logit contributions | |
DIT | -0.399 |
RNA | -0.395 |
VOL | -0.364 |
EH | -0.361 |
CONT | -0.354 |
Token |
|
Token ID | 198 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
abl | +0.182 |
osexual | +0.173 |
erer | +0.163 |
wolves | +0.161 |
xual | +0.161 |
Neg logit contributions | |
DIT | -0.167 |
RNA | -0.165 |
VOL | -0.153 |
EH | -0.151 |
Chatt | -0.149 |
Token | Beyond |
Token ID | 24102 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
abl | +0.161 |
osexual | +0.156 |
xual | +0.146 |
wolves | +0.145 |
erer | +0.144 |
Neg logit contributions | |
DIT | -0.137 |
RNA | -0.135 |
VOL | -0.124 |
EH | -0.122 |
Chatt | -0.121 |
Token | that |
Token ID | 326 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
DIT | +0.447 |
RNA | +0.442 |
VOL | +0.412 |
EH | +0.409 |
CONT | +0.402 |
Neg logit contributions | |
abl | -0.376 |
osexual | -0.364 |
xual | -0.342 |
wolves | -0.333 |
erer | -0.331 |