Token | those |
Token ID | 883 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
bered | +0.095 |
tons | +0.089 |
tto | +0.087 |
ean | +0.086 |
CHAT | +0.084 |
Neg logit contributions | |
incial | -0.122 |
ISION | -0.120 |
netflix | -0.109 |
andom | -0.108 |
iple | -0.106 |
Token | that |
Token ID | 326 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
bered | +0.806 |
tons | +0.751 |
tto | +0.737 |
ean | +0.725 |
CHAT | +0.714 |
Neg logit contributions | |
incial | -1.033 |
ISION | -1.014 |
netflix | -0.918 |
andom | -0.916 |
iple | -0.896 |
Token | are |
Token ID | 389 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
incial | +0.851 |
ISION | +0.838 |
netflix | +0.764 |
andom | +0.763 |
iple | +0.747 |
Neg logit contributions | |
bered | -0.560 |
tons | -0.516 |
tto | -0.507 |
ean | -0.499 |
CHAT | -0.495 |
Token | in |
Token ID | 287 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
incial | +0.495 |
ISION | +0.486 |
netflix | +0.438 |
andom | +0.437 |
iple | +0.427 |
Neg logit contributions | |
bered | -0.414 |
tons | -0.386 |
tto | -0.381 |
ean | -0.374 |
CHAT | -0.370 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
incial | +0.292 |
ISION | +0.286 |
netflix | +0.258 |
andom | +0.258 |
iple | +0.252 |
Neg logit contributions | |
bered | -0.239 |
tons | -0.223 |
tto | -0.219 |
ean | -0.215 |
CHAT | -0.212 |
Token | thro |
Token ID | 9244 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
incial | +0.540 |
ISION | +0.530 |
netflix | +0.481 |
andom | +0.480 |
iple | +0.470 |
Neg logit contributions | |
bered | -0.401 |
tons | -0.372 |
tto | -0.365 |
ean | -0.359 |
CHAT | -0.354 |
Token | es |
Token ID | 274 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
bered | +1.117 |
tto | +0.784 |
tons | +0.776 |
ean | +0.758 |
ber | +0.542 |
Neg logit contributions | |
incial | -12.232 |
ISION | -12.078 |
netflix | -11.429 |
iple | -11.081 |
andom | -11.050 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
bered | +0.076 |
tons | +0.070 |
tto | +0.069 |
CHAT | +0.067 |
ean | +0.067 |
Neg logit contributions | |
incial | -0.114 |
ISION | -0.113 |
netflix | -0.102 |
andom | -0.102 |
iple | -0.100 |
Token | making |
Token ID | 1642 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
incial | +0.352 |
ISION | +0.346 |
netflix | +0.311 |
andom | +0.311 |
iple | +0.304 |
Neg logit contributions | |
bered | -0.298 |
tons | -0.278 |
tto | -0.275 |
ean | -0.270 |
CHAT | -0.267 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
incial | +0.024 |
ISION | +0.023 |
netflix | +0.021 |
andom | +0.021 |
iple | +0.021 |
Neg logit contributions | |
bered | -0.019 |
tons | -0.018 |
tto | -0.017 |
ean | -0.017 |
CHAT | -0.017 |
Token | decision |
Token ID | 2551 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
bered | +0.166 |
tons | +0.154 |
tto | +0.152 |
ean | +0.149 |
CHAT | +0.147 |
Neg logit contributions | |
incial | -0.211 |
ISION | -0.207 |
netflix | -0.188 |
andom | -0.187 |
iple | -0.183 |
Token | Today |
Token ID | 6288 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
bered | +2.459 |
tons | +2.319 |
tto | +2.301 |
ean | +2.245 |
odus | +2.171 |
Neg logit contributions | |
incial | -2.958 |
ISION | -2.926 |
netflix | -2.641 |
andom | -2.619 |
iple | -2.540 |
Token | : |
Token ID | 25 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
bered | +1.328 |
tons | +1.247 |
tto | +1.229 |
ean | +1.205 |
CHAT | +1.165 |
Neg logit contributions | |
incial | -2.168 |
ISION | -2.127 |
andom | -1.945 |
netflix | -1.935 |
iple | -1.903 |
Token | Tor |
Token ID | 4022 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
bered | +0.129 |
tons | +0.121 |
tto | +0.119 |
ean | +0.117 |
CHAT | +0.115 |
Neg logit contributions | |
incial | -0.151 |
ISION | -0.148 |
netflix | -0.134 |
andom | -0.133 |
iple | -0.130 |
Token | chy |
Token ID | 29658 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
bered | +0.899 |
tons | +0.842 |
tto | +0.832 |
ean | +0.816 |
CHAT | +0.796 |
Neg logit contributions | |
incial | -0.957 |
ISION | -0.943 |
netflix | -0.841 |
andom | -0.831 |
iple | -0.813 |
Token | 's |
Token ID | 338 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
bered | +0.019 |
tons | +0.018 |
tto | +0.018 |
ean | +0.017 |
CHAT | +0.017 |
Neg logit contributions | |
incial | -0.024 |
ISION | -0.024 |
netflix | -0.022 |
andom | -0.022 |
iple | -0.021 |
Token | Tac |
Token ID | 26075 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
incial | +0.472 |
ISION | +0.463 |
netflix | +0.419 |
andom | +0.417 |
iple | +0.409 |
Neg logit contributions | |
bered | -0.373 |
tons | -0.348 |
tto | -0.341 |
ean | -0.336 |
CHAT | -0.332 |
Token | os |
Token ID | 418 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
bered | +3.760 |
tto | +3.456 |
tons | +3.308 |
ean | +3.265 |
ness | +3.208 |
Neg logit contributions | |
incial | -8.039 |
ISION | -8.003 |
andom | -7.227 |
netflix | -7.197 |
sqor | -7.079 |
Token | Previously |
Token ID | 29875 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
bered | +0.290 |
tons | +0.269 |
tto | +0.264 |
ean | +0.259 |
CHAT | +0.256 |
Neg logit contributions | |
incial | -0.397 |
ISION | -0.390 |
netflix | -0.354 |
andom | -0.353 |
iple | -0.346 |
Token | : |
Token ID | 25 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
bered | +0.462 |
tons | +0.430 |
tto | +0.424 |
ean | +0.416 |
CHAT | +0.406 |
Neg logit contributions | |
incial | -0.699 |
ISION | -0.688 |
andom | -0.625 |
netflix | -0.625 |
iple | -0.614 |
Token | Great |
Token ID | 3878 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
incial | +0.055 |
ISION | +0.054 |
netflix | +0.049 |
andom | +0.049 |
iple | +0.047 |
Neg logit contributions | |
bered | -0.047 |
tons | -0.044 |
tto | -0.043 |
ean | -0.042 |
CHAT | -0.042 |
Token | full |
Token ID | 12853 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
incial | +0.369 |
ISION | +0.361 |
netflix | +0.324 |
andom | +0.323 |
iple | +0.316 |
Neg logit contributions | |
bered | -0.344 |
tons | -0.322 |
tto | -0.317 |
ean | -0.312 |
CHAT | -0.309 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
incial | +0.002 |
ISION | +0.002 |
netflix | +0.002 |
andom | +0.002 |
iple | +0.002 |
Neg logit contributions | |
bered | -0.002 |
tons | -0.002 |
tto | -0.002 |
ean | -0.002 |
CHAT | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
bered | +0.510 |
tons | +0.483 |
tto | +0.474 |
ean | +0.465 |
CHAT | +0.456 |
Neg logit contributions | |
incial | -0.709 |
ISION | -0.696 |
andom | -0.633 |
netflix | -0.632 |
iple | -0.620 |
Token | As |
Token ID | 1722 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
bered | +0.097 |
tons | +0.090 |
tto | +0.088 |
ean | +0.087 |
CHAT | +0.085 |
Neg logit contributions | |
incial | -0.124 |
ISION | -0.122 |
netflix | -0.110 |
andom | -0.110 |
iple | -0.107 |
Token | for |
Token ID | 329 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
incial | +0.663 |
ISION | +0.651 |
netflix | +0.593 |
andom | +0.592 |
iple | +0.580 |
Neg logit contributions | |
bered | -0.449 |
tons | -0.415 |
tto | -0.407 |
ean | -0.400 |
CHAT | -0.393 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
incial | +0.288 |
ISION | +0.282 |
netflix | +0.254 |
andom | +0.254 |
iple | +0.248 |
Neg logit contributions | |
bered | -0.239 |
tons | -0.223 |
tto | -0.220 |
ean | -0.216 |
CHAT | -0.213 |
Token | logistics |
Token ID | 26355 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
incial | +0.033 |
ISION | +0.033 |
netflix | +0.029 |
andom | +0.029 |
iple | +0.029 |
Neg logit contributions | |
bered | -0.028 |
tons | -0.027 |
tto | -0.026 |
ean | -0.026 |
CHAT | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
bered | +3.931 |
tons | +3.746 |
tto | +3.561 |
ean | +3.468 |
ness | +3.407 |
Neg logit contributions | |
incial | -7.716 |
ISION | -7.473 |
netflix | -6.957 |
andom | -6.885 |
iple | -6.703 |
Token | one |
Token ID | 530 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
bered | +0.251 |
tons | +0.239 |
tto | +0.235 |
ean | +0.231 |
CHAT | +0.229 |
Neg logit contributions | |
incial | -0.206 |
ISION | -0.200 |
netflix | -0.177 |
andom | -0.176 |
iple | -0.171 |
Token | member |
Token ID | 2888 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
incial | +0.543 |
ISION | +0.534 |
netflix | +0.487 |
andom | +0.485 |
iple | +0.475 |
Neg logit contributions | |
bered | -0.368 |
tons | -0.341 |
tto | -0.334 |
ean | -0.328 |
CHAT | -0.322 |
Token | remaining |
Token ID | 5637 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
bered | +0.711 |
tons | +0.669 |
tto | +0.658 |
ean | +0.647 |
CHAT | +0.638 |
Neg logit contributions | |
incial | -0.710 |
ISION | -0.695 |
netflix | -0.620 |
andom | -0.617 |
iple | -0.600 |
Token | a |
Token ID | 257 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
bered | +1.114 |
tons | +1.020 |
tto | +1.000 |
ean | +0.977 |
CHAT | +0.957 |
Neg logit contributions | |
incial | -1.806 |
ISION | -1.779 |
netflix | -1.624 |
andom | -1.620 |
iple | -1.586 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
bered | +0.322 |
tons | +0.298 |
tto | +0.292 |
ean | +0.287 |
CHAT | +0.280 |
Neg logit contributions | |
incial | -0.464 |
ISION | -0.456 |
netflix | -0.415 |
andom | -0.413 |
iple | -0.404 |
Token |
|
Token ID | 198 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
incial | +0.262 |
ISION | +0.256 |
netflix | +0.231 |
andom | +0.231 |
iple | +0.226 |
Neg logit contributions | |
bered | -0.220 |
tons | -0.206 |
tto | -0.203 |
ean | -0.200 |
CHAT | -0.197 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
incial | +0.160 |
ISION | +0.157 |
andom | +0.143 |
netflix | +0.143 |
iple | +0.140 |
Neg logit contributions | |
bered | -0.122 |
tons | -0.114 |
tto | -0.112 |
ean | -0.110 |
CHAT | -0.109 |
Token | Speaking |
Token ID | 13887 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
incial | +0.495 |
ISION | +0.488 |
netflix | +0.439 |
andom | +0.439 |
iple | +0.429 |
Neg logit contributions | |
bered | -0.406 |
tons | -0.377 |
tto | -0.371 |
ean | -0.364 |
CHAT | -0.358 |
Token | of |
Token ID | 286 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
bered | +1.669 |
tons | +1.539 |
tto | +1.512 |
ean | +1.487 |
CHAT | +1.456 |
Neg logit contributions | |
incial | -2.826 |
ISION | -2.787 |
netflix | -2.556 |
andom | -2.545 |
iple | -2.482 |
Token | Mou |
Token ID | 49902 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
incial | +0.311 |
ISION | +0.305 |
netflix | +0.273 |
andom | +0.271 |
iple | +0.266 |
Neg logit contributions | |
bered | -0.279 |
tons | -0.263 |
tto | -0.258 |
ean | -0.255 |
CHAT | -0.251 |
Token | z |
Token ID | 89 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
bered | +4.410 |
tons | +4.175 |
tto | +4.108 |
ean | +3.966 |
xy | +3.957 |
Neg logit contributions | |
incial | -6.665 |
ISION | -6.584 |
andom | -5.852 |
netflix | -5.848 |
sqor | -5.693 |
Token | Black |
Token ID | 2619 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
bered | +1.128 |
tons | +1.049 |
tto | +1.020 |
ean | +1.009 |
CHAT | +0.986 |
Neg logit contributions | |
incial | -1.652 |
ISION | -1.617 |
netflix | -1.476 |
andom | -1.463 |
iple | -1.434 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
bered | +1.001 |
tons | +0.931 |
tto | +0.907 |
ean | +0.892 |
CHAT | +0.875 |
Neg logit contributions | |
incial | -1.508 |
ISION | -1.478 |
netflix | -1.346 |
andom | -1.339 |
iple | -1.309 |
Token | who |
Token ID | 508 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
bered | +0.309 |
tons | +0.289 |
tto | +0.283 |
ean | +0.279 |
CHAT | +0.274 |
Neg logit contributions | |
incial | -0.396 |
ISION | -0.388 |
netflix | -0.351 |
andom | -0.351 |
iple | -0.343 |
Token | had |
Token ID | 550 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
bered | +0.560 |
tons | +0.521 |
tto | +0.510 |
ean | +0.503 |
CHAT | +0.495 |
Neg logit contributions | |
incial | -0.740 |
ISION | -0.727 |
netflix | -0.658 |
andom | -0.656 |
iple | -0.640 |
Token | Romney |
Token ID | 8431 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
bered | +0.208 |
tons | +0.194 |
tto | +0.190 |
ean | +0.187 |
CHAT | +0.184 |
Neg logit contributions | |
incial | -0.271 |
ISION | -0.266 |
netflix | -0.241 |
andom | -0.240 |
iple | -0.235 |
Token | tax |
Token ID | 1687 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
bered | +1.395 |
tons | +1.293 |
tto | +1.267 |
ean | +1.244 |
CHAT | +1.223 |
Neg logit contributions | |
incial | -2.099 |
ISION | -2.063 |
netflix | -1.881 |
andom | -1.874 |
iple | -1.837 |
Token | returns |
Token ID | 5860 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
incial | +0.685 |
ISION | +0.673 |
andom | +0.605 |
netflix | +0.603 |
iple | +0.591 |
Neg logit contributions | |
bered | -0.588 |
tons | -0.550 |
tto | -0.541 |
ean | -0.532 |
CHAT | -0.524 |
Token | would |
Token ID | 561 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
incial | +0.148 |
ISION | +0.145 |
netflix | +0.131 |
andom | +0.131 |
iple | +0.128 |
Neg logit contributions | |
bered | -0.118 |
tons | -0.110 |
tto | -0.108 |
ean | -0.106 |
CHAT | -0.105 |
Token | lay |
Token ID | 3830 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
bered | +1.381 |
tons | +1.294 |
tto | +1.266 |
ean | +1.252 |
CHAT | +1.220 |
Neg logit contributions | |
incial | -1.757 |
ISION | -1.734 |
netflix | -1.568 |
andom | -1.561 |
iple | -1.525 |
Token | bare |
Token ID | 6247 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
bered | +0.824 |
tons | +0.758 |
tto | +0.741 |
ean | +0.725 |
CHAT | +0.709 |
Neg logit contributions | |
incial | -1.461 |
ISION | -1.436 |
netflix | -1.319 |
andom | -1.316 |
iple | -1.291 |
Token | is |
Token ID | 318 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
bered | +4.287 |
tons | +4.037 |
tto | +3.972 |
ean | +3.878 |
ness | +3.778 |
Neg logit contributions | |
incial | -6.345 |
ISION | -6.220 |
andom | -5.691 |
netflix | -5.683 |
iple | -5.522 |
Token | the |
Token ID | 262 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
bered | +0.585 |
tons | +0.545 |
tto | +0.535 |
ean | +0.526 |
CHAT | +0.519 |
Neg logit contributions | |
incial | -0.759 |
ISION | -0.746 |
netflix | -0.675 |
andom | -0.673 |
iple | -0.659 |
Token | extent |
Token ID | 6287 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
bered | +0.532 |
tons | +0.495 |
tto | +0.486 |
ean | +0.477 |
CHAT | +0.470 |
Neg logit contributions | |
incial | -0.718 |
ISION | -0.705 |
netflix | -0.640 |
andom | -0.638 |
iple | -0.625 |
Token | of |
Token ID | 286 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
bered | +1.517 |
tons | +1.393 |
tto | +1.374 |
ean | +1.349 |
CHAT | +1.319 |
Neg logit contributions | |
incial | -2.383 |
ISION | -2.339 |
netflix | -2.135 |
andom | -2.132 |
iple | -2.093 |
Token | his |
Token ID | 465 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
bered | +0.283 |
tons | +0.264 |
tto | +0.260 |
ean | +0.255 |
CHAT | +0.251 |
Neg logit contributions | |
incial | -0.346 |
ISION | -0.340 |
netflix | -0.307 |
andom | -0.306 |
iple | -0.300 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
bered | +0.569 |
tons | +0.539 |
tto | +0.530 |
ean | +0.520 |
CHAT | +0.510 |
Neg logit contributions | |
incial | -0.793 |
ISION | -0.777 |
andom | -0.708 |
netflix | -0.708 |
iple | -0.695 |
Token | � |
Token ID | 447 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
bered | +0.244 |
tons | +0.225 |
tto | +0.221 |
ean | +0.217 |
CHAT | +0.213 |
Neg logit contributions | |
incial | -0.332 |
ISION | -0.327 |
netflix | -0.296 |
andom | -0.295 |
iple | -0.290 |
Token | � |
Token ID | 250 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
incial | +0.508 |
ISION | +0.498 |
netflix | +0.443 |
andom | +0.441 |
iple | +0.431 |
Neg logit contributions | |
bered | -0.527 |
tons | -0.496 |
tto | -0.488 |
ean | -0.482 |
CHAT | -0.475 |
Token | Pat |
Token ID | 12130 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
incial | +0.638 |
ISION | +0.629 |
netflix | +0.569 |
andom | +0.567 |
iple | +0.557 |
Neg logit contributions | |
bered | -0.460 |
tons | -0.421 |
tto | -0.414 |
ean | -0.407 |
odus | -0.398 |
Token | will |
Token ID | 481 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
bered | +1.522 |
tons | +1.424 |
tto | +1.401 |
ean | +1.376 |
CHAT | +1.350 |
Neg logit contributions | |
incial | -1.886 |
ISION | -1.855 |
andom | -1.681 |
netflix | -1.679 |
iple | -1.611 |
Token | undergo |
Token ID | 17777 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
bered | +1.150 |
tons | +1.068 |
tto | +1.049 |
ean | +1.031 |
CHAT | +1.016 |
Neg logit contributions | |
incial | -1.561 |
ISION | -1.533 |
netflix | -1.391 |
andom | -1.388 |
iple | -1.359 |
Token | surgery |
Token ID | 8185 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
bered | +4.414 |
tons | +4.178 |
tto | +4.124 |
ean | +3.994 |
CHAT | +3.926 |
Neg logit contributions | |
incial | -6.212 |
ISION | -6.122 |
netflix | -5.593 |
andom | -5.578 |
sqor | -5.306 |
Token | this |
Token ID | 428 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
bered | +1.807 |
tons | +1.666 |
tto | +1.644 |
ean | +1.600 |
CHAT | +1.571 |
Neg logit contributions | |
incial | -2.832 |
ISION | -2.776 |
netflix | -2.542 |
andom | -2.540 |
iple | -2.477 |
Token | week |
Token ID | 1285 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
bered | +0.043 |
tons | +0.040 |
tto | +0.039 |
ean | +0.038 |
CHAT | +0.038 |
Neg logit contributions | |
incial | -0.075 |
ISION | -0.074 |
netflix | -0.068 |
andom | -0.068 |
iple | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
incial | +0.915 |
ISION | +0.900 |
netflix | +0.816 |
andom | +0.814 |
iple | +0.801 |
Neg logit contributions | |
bered | -0.647 |
tons | -0.600 |
tto | -0.587 |
ean | -0.578 |
CHAT | -0.569 |
Token | we |
Token ID | 356 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
incial | +0.320 |
ISION | +0.314 |
netflix | +0.283 |
andom | +0.282 |
iple | +0.278 |
Neg logit contributions | |
bered | -0.261 |
tons | -0.243 |
tto | -0.238 |
ean | -0.234 |
CHAT | -0.232 |
Token | year |
Token ID | 1941 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
bered | +0.675 |
tons | +0.633 |
tto | +0.620 |
ean | +0.612 |
CHAT | +0.602 |
Neg logit contributions | |
incial | -0.786 |
ISION | -0.772 |
netflix | -0.693 |
andom | -0.692 |
iple | -0.675 |
Token | - |
Token ID | 12 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
bered | +0.611 |
tons | +0.564 |
tto | +0.550 |
ean | +0.539 |
CHAT | +0.523 |
Neg logit contributions | |
incial | -1.045 |
ISION | -1.027 |
andom | -0.939 |
netflix | -0.939 |
iple | -0.918 |
Token | old |
Token ID | 727 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
bered | +0.402 |
tons | +0.370 |
tto | +0.359 |
ean | +0.351 |
CHAT | +0.342 |
Neg logit contributions | |
incial | -0.798 |
ISION | -0.786 |
andom | -0.721 |
netflix | -0.720 |
iple | -0.707 |
Token | N |
Token ID | 399 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
bered | +2.091 |
tons | +1.963 |
tto | +1.925 |
ean | +1.899 |
CHAT | +1.852 |
Neg logit contributions | |
incial | -2.367 |
ISION | -2.329 |
netflix | -2.101 |
andom | -2.098 |
iple | -2.032 |
Token | eng |
Token ID | 1516 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
bered | +1.851 |
tons | +1.750 |
tto | +1.720 |
ean | +1.711 |
odus | +1.672 |
Neg logit contributions | |
incial | -1.854 |
ISION | -1.836 |
netflix | -1.656 |
andom | -1.622 |
iple | -1.568 |
Token | Mou |
Token ID | 49902 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
incial | +1.358 |
ISION | +1.325 |
andom | +1.197 |
netflix | +1.196 |
iple | +1.172 |
Neg logit contributions | |
bered | -1.145 |
tons | -1.066 |
tto | -1.052 |
ean | -1.030 |
CHAT | -1.023 |
Token | a |
Token ID | 64 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
bered | +4.790 |
tons | +4.513 |
tto | +4.463 |
ean | +4.382 |
CHAT | +4.270 |
Neg logit contributions | |
ISION | -5.904 |
incial | -5.834 |
andom | -5.205 |
netflix | -5.154 |
iple | -5.009 |
Token | shot |
Token ID | 2823 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
bered | +0.317 |
tons | +0.295 |
tto | +0.290 |
ean | +0.285 |
CHAT | +0.280 |
Neg logit contributions | |
incial | -0.424 |
ISION | -0.417 |
netflix | -0.378 |
andom | -0.377 |
iple | -0.369 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
incial | +1.300 |
ISION | +1.272 |
netflix | +1.153 |
andom | +1.147 |
iple | +1.126 |
Neg logit contributions | |
bered | -1.001 |
tons | -0.934 |
tto | -0.911 |
ean | -0.900 |
CHAT | -0.892 |
Token | killed |
Token ID | 2923 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
bered | +0.209 |
tons | +0.191 |
tto | +0.188 |
ean | +0.184 |
CHAT | +0.180 |
Neg logit contributions | |
incial | -0.362 |
ISION | -0.356 |
netflix | -0.326 |
andom | -0.325 |
iple | -0.319 |
Token | his |
Token ID | 465 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
bered | +0.640 |
tons | +0.597 |
tto | +0.587 |
ean | +0.578 |
CHAT | +0.568 |
Neg logit contributions | |
incial | -0.783 |
ISION | -0.769 |
netflix | -0.695 |
andom | -0.694 |
iple | -0.678 |
Token | this |
Token ID | 428 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
incial | +1.455 |
ISION | +1.428 |
netflix | +1.284 |
andom | +1.282 |
iple | +1.253 |
Neg logit contributions | |
bered | -1.279 |
tons | -1.195 |
tto | -1.178 |
ean | -1.158 |
CHAT | -1.143 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
incial | +0.229 |
ISION | +0.225 |
netflix | +0.205 |
andom | +0.204 |
iple | +0.199 |
Neg logit contributions | |
bered | -0.167 |
tons | -0.155 |
tto | -0.152 |
ean | -0.150 |
CHAT | -0.148 |
Token | thinking |
Token ID | 3612 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
incial | +0.246 |
ISION | +0.242 |
netflix | +0.218 |
andom | +0.218 |
iple | +0.213 |
Neg logit contributions | |
bered | -0.192 |
tons | -0.179 |
tto | -0.176 |
ean | -0.173 |
CHAT | -0.171 |
Token | it |
Token ID | 340 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
bered | +0.133 |
tons | +0.124 |
tto | +0.122 |
ean | +0.119 |
CHAT | +0.118 |
Neg logit contributions | |
incial | -0.175 |
ISION | -0.172 |
netflix | -0.156 |
andom | -0.155 |
iple | -0.152 |
Token | was |
Token ID | 373 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
incial | +0.802 |
ISION | +0.788 |
netflix | +0.712 |
andom | +0.711 |
iple | +0.694 |
Neg logit contributions | |
bered | -0.647 |
tons | -0.603 |
tto | -0.593 |
ean | -0.583 |
CHAT | -0.574 |
Token | Mou |
Token ID | 49902 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
incial | +0.133 |
ISION | +0.130 |
netflix | +0.118 |
andom | +0.117 |
iple | +0.115 |
Neg logit contributions | |
bered | -0.108 |
tons | -0.101 |
tto | -0.099 |
ean | -0.098 |
CHAT | -0.096 |
Token | z |
Token ID | 89 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
bered | +4.577 |
tons | +4.226 |
tto | +4.199 |
ean | +4.096 |
CHAT | +4.067 |
Neg logit contributions | |
incial | -6.235 |
ISION | -6.146 |
netflix | -5.498 |
andom | -5.493 |
iple | -5.326 |
Token | Black |
Token ID | 2619 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
bered | +1.118 |
tons | +1.044 |
tto | +1.020 |
ean | +1.016 |
CHAT | +0.990 |
Neg logit contributions | |
incial | -1.418 |
ISION | -1.396 |
netflix | -1.263 |
andom | -1.251 |
iple | -1.219 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
bered | +0.722 |
tons | +0.675 |
tto | +0.658 |
ean | +0.651 |
CHAT | +0.640 |
Neg logit contributions | |
incial | -0.937 |
ISION | -0.921 |
netflix | -0.835 |
andom | -0.828 |
iple | -0.808 |
Token | who |
Token ID | 508 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
incial | +0.357 |
ISION | +0.351 |
netflix | +0.319 |
andom | +0.318 |
iple | +0.312 |
Neg logit contributions | |
bered | -0.251 |
tons | -0.232 |
tto | -0.228 |
ean | -0.224 |
CHAT | -0.221 |
Token | had |
Token ID | 550 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
bered | +0.402 |
tons | +0.374 |
tto | +0.366 |
ean | +0.361 |
CHAT | +0.355 |
Neg logit contributions | |
incial | -0.533 |
ISION | -0.523 |
netflix | -0.474 |
andom | -0.472 |
iple | -0.461 |
Token | In |
Token ID | 818 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
incial | +0.306 |
ISION | +0.302 |
netflix | +0.272 |
andom | +0.271 |
iple | +0.265 |
Neg logit contributions | |
bered | -0.239 |
tons | -0.222 |
tto | -0.217 |
ean | -0.215 |
CHAT | -0.210 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
bered | +0.136 |
tons | +0.127 |
tto | +0.125 |
ean | +0.122 |
CHAT | +0.121 |
Neg logit contributions | |
incial | -0.177 |
ISION | -0.174 |
netflix | -0.158 |
andom | -0.157 |
iple | -0.154 |
Token | Lord |
Token ID | 4453 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
bered | +0.701 |
tons | +0.653 |
tto | +0.644 |
ean | +0.631 |
CHAT | +0.618 |
Neg logit contributions | |
incial | -0.920 |
ISION | -0.904 |
netflix | -0.822 |
andom | -0.821 |
iple | -0.803 |
Token | Williams |
Token ID | 6484 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
incial | +0.639 |
ISION | +0.627 |
netflix | +0.564 |
andom | +0.563 |
iple | +0.550 |
Neg logit contributions | |
bered | -0.557 |
tons | -0.519 |
tto | -0.510 |
ean | -0.502 |
CHAT | -0.497 |
Token | of |
Token ID | 286 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
bered | +1.099 |
tons | +1.021 |
tto | +0.997 |
ean | +0.984 |
CHAT | +0.958 |
Neg logit contributions | |
incial | -1.683 |
ISION | -1.655 |
netflix | -1.518 |
andom | -1.507 |
iple | -1.471 |
Token | Oy |
Token ID | 39447 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
incial | +0.472 |
ISION | +0.463 |
netflix | +0.417 |
andom | +0.416 |
iple | +0.407 |
Neg logit contributions | |
bered | -0.403 |
tons | -0.377 |
tto | -0.371 |
ean | -0.365 |
CHAT | -0.360 |
Token | ster |
Token ID | 1706 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
bered | +3.331 |
tons | +2.984 |
tto | +2.940 |
ber | +2.846 |
ean | +2.824 |
Neg logit contributions | |
incial | -7.476 |
ISION | -7.465 |
netflix | -6.729 |
andom | -6.703 |
iple | -6.605 |
Token | mouth |
Token ID | 14775 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
incial | +0.554 |
ISION | +0.543 |
netflix | +0.491 |
andom | +0.490 |
iple | +0.479 |
Neg logit contributions | |
bered | -0.459 |
tons | -0.428 |
tto | -0.421 |
ean | -0.415 |
CHAT | -0.408 |
Token | , |
Token ID | 11 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
incial | +0.069 |
ISION | +0.068 |
netflix | +0.062 |
andom | +0.061 |
iple | +0.060 |
Neg logit contributions | |
bered | -0.049 |
tons | -0.046 |
tto | -0.045 |
ean | -0.044 |
CHAT | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
bered | +0.094 |
tons | +0.087 |
tto | +0.086 |
ean | +0.084 |
CHAT | +0.083 |
Neg logit contributions | |
incial | -0.118 |
ISION | -0.116 |
netflix | -0.105 |
andom | -0.105 |
iple | -0.102 |
Token | then |
Token ID | 788 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
bered | +0.244 |
tons | +0.227 |
tto | +0.224 |
ean | +0.220 |
CHAT | +0.216 |
Neg logit contributions | |
incial | -0.309 |
ISION | -0.303 |
netflix | -0.275 |
andom | -0.274 |
iple | -0.267 |
Token | Hem |
Token ID | 15617 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
bered | +0.815 |
tons | +0.758 |
tto | +0.744 |
ean | +0.731 |
CHAT | +0.718 |
Neg logit contributions | |
incial | -1.154 |
ISION | -1.132 |
netflix | -1.028 |
andom | -1.028 |
iple | -1.008 |
Token | isp |
Token ID | 8802 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
bered | +1.271 |
tons | +1.190 |
tto | +1.166 |
ean | +1.155 |
CHAT | +1.129 |
Neg logit contributions | |
incial | -1.438 |
ISION | -1.416 |
andom | -1.263 |
netflix | -1.263 |
iple | -1.230 |
Token | heres |
Token ID | 19079 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
incial | +0.845 |
ISION | +0.826 |
netflix | +0.729 |
andom | +0.725 |
iple | +0.705 |
Neg logit contributions | |
bered | -1.019 |
tons | -0.961 |
tto | -0.950 |
ean | -0.938 |
CHAT | -0.926 |
Token | magazine |
Token ID | 7093 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
incial | +0.512 |
ISION | +0.503 |
netflix | +0.457 |
andom | +0.456 |
iple | +0.447 |
Neg logit contributions | |
bered | -0.368 |
tons | -0.341 |
tto | -0.335 |
ean | -0.329 |
CHAT | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
incial | +0.770 |
ISION | +0.757 |
netflix | +0.689 |
andom | +0.686 |
iple | +0.673 |
Neg logit contributions | |
bered | -0.538 |
tons | -0.499 |
tto | -0.490 |
ean | -0.480 |
CHAT | -0.474 |
Token | Lux |
Token ID | 17145 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
incial | +0.142 |
ISION | +0.140 |
netflix | +0.126 |
andom | +0.126 |
iple | +0.123 |
Neg logit contributions | |
bered | -0.114 |
tons | -0.106 |
tto | -0.104 |
ean | -0.103 |
CHAT | -0.101 |
Token | x |
Token ID | 87 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
bered | +4.469 |
tons | +4.145 |
tto | +4.119 |
ean | +4.108 |
CHAT | +3.959 |
Neg logit contributions | |
incial | -6.057 |
ISION | -5.932 |
netflix | -5.392 |
andom | -5.384 |
iple | -5.219 |
Token | Living |
Token ID | 13728 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
bered | +2.679 |
tons | +2.506 |
tto | +2.465 |
ean | +2.431 |
CHAT | +2.368 |
Neg logit contributions | |
incial | -3.429 |
ISION | -3.366 |
andom | -3.044 |
netflix | -3.043 |
iple | -2.968 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
bered | +0.604 |
tons | +0.560 |
tto | +0.551 |
ean | +0.541 |
CHAT | +0.534 |
Neg logit contributions | |
incial | -0.802 |
ISION | -0.787 |
netflix | -0.713 |
andom | -0.712 |
iple | -0.697 |
Token | THR |
Token ID | 35383 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
bered | +0.004 |
tons | +0.004 |
tto | +0.004 |
ean | +0.004 |
CHAT | +0.004 |
Neg logit contributions | |
incial | -0.005 |
ISION | -0.005 |
netflix | -0.004 |
andom | -0.004 |
iple | -0.004 |
Token | IVE |
Token ID | 9306 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
incial | +0.654 |
ISION | +0.644 |
netflix | +0.582 |
andom | +0.581 |
iple | +0.570 |
Neg logit contributions | |
bered | -0.494 |
tons | -0.460 |
tto | -0.451 |
ean | -0.443 |
CHAT | -0.437 |
Token | Bell |
Token ID | 7459 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
bered | +0.151 |
tons | +0.142 |
tto | +0.139 |
ean | +0.137 |
CHAT | +0.135 |
Neg logit contributions | |
incial | -0.179 |
ISION | -0.175 |
netflix | -0.158 |
andom | -0.158 |
iple | -0.154 |
Token | said |
Token ID | 531 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
incial | +2.449 |
ISION | +2.400 |
andom | +2.174 |
netflix | +2.171 |
iple | +2.140 |
Neg logit contributions | |
bered | -1.873 |
tons | -1.730 |
tto | -1.705 |
ean | -1.668 |
CHAT | -1.652 |
Token | Lip |
Token ID | 24701 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
bered | +0.729 |
tons | +0.682 |
tto | +0.672 |
ean | +0.661 |
CHAT | +0.651 |
Neg logit contributions | |
incial | -0.846 |
ISION | -0.830 |
netflix | -0.750 |
andom | -0.746 |
iple | -0.727 |
Token | inski |
Token ID | 21141 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
bered | +0.091 |
tons | +0.087 |
tto | +0.085 |
ean | +0.084 |
CHAT | +0.083 |
Neg logit contributions | |
incial | -0.065 |
ISION | -0.064 |
netflix | -0.056 |
andom | -0.056 |
iple | -0.054 |
Token | would |
Token ID | 561 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
bered | +0.660 |
tons | +0.613 |
tto | +0.602 |
ean | +0.590 |
CHAT | +0.580 |
Neg logit contributions | |
incial | -0.914 |
ISION | -0.898 |
netflix | -0.815 |
andom | -0.814 |
iple | -0.796 |
Token | undergo |
Token ID | 17777 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
bered | +1.232 |
tons | +1.144 |
tto | +1.124 |
ean | +1.104 |
CHAT | +1.084 |
Neg logit contributions | |
incial | -1.695 |
ISION | -1.667 |
netflix | -1.511 |
andom | -1.509 |
iple | -1.477 |
Token | surgery |
Token ID | 8185 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
bered | +4.295 |
tons | +4.021 |
tto | +3.996 |
ean | +3.865 |
xy | +3.758 |
Neg logit contributions | |
incial | -5.967 |
ISION | -5.904 |
netflix | -5.376 |
andom | -5.371 |
sqor | -5.140 |
Token | this |
Token ID | 428 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
bered | +1.789 |
tons | +1.639 |
tto | +1.625 |
ean | +1.570 |
CHAT | +1.529 |
Neg logit contributions | |
incial | -2.902 |
ISION | -2.851 |
netflix | -2.622 |
andom | -2.619 |
iple | -2.556 |
Token | week |
Token ID | 1285 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
bered | +0.103 |
tons | +0.095 |
tto | +0.093 |
ean | +0.092 |
CHAT | +0.090 |
Neg logit contributions | |
incial | -0.151 |
ISION | -0.148 |
netflix | -0.135 |
andom | -0.135 |
iple | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
incial | +1.065 |
ISION | +1.044 |
netflix | +0.945 |
andom | +0.943 |
iple | +0.927 |
Neg logit contributions | |
bered | -0.763 |
tons | -0.712 |
tto | -0.693 |
ean | -0.685 |
CHAT | -0.677 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
bered | +0.183 |
tons | +0.171 |
tto | +0.169 |
ean | +0.166 |
CHAT | +0.164 |
Neg logit contributions | |
incial | -0.234 |
ISION | -0.230 |
netflix | -0.208 |
andom | -0.208 |
iple | -0.203 |
Token | have |
Token ID | 423 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
incial | +0.083 |
ISION | +0.081 |
netflix | +0.073 |
andom | +0.073 |
iple | +0.072 |
Neg logit contributions | |
bered | -0.066 |
tons | -0.062 |
tto | -0.061 |
ean | -0.060 |
CHAT | -0.059 |
Token | them |
Token ID | 606 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
incial | +0.417 |
ISION | +0.409 |
netflix | +0.369 |
andom | +0.368 |
iple | +0.360 |
Neg logit contributions | |
bered | -0.347 |
tons | -0.323 |
tto | -0.318 |
ean | -0.313 |
CHAT | -0.309 |
Token | once |
Token ID | 1752 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
incial | +0.065 |
ISION | +0.064 |
netflix | +0.058 |
andom | +0.058 |
iple | +0.057 |
Neg logit contributions | |
bered | -0.050 |
tons | -0.046 |
tto | -0.045 |
ean | -0.045 |
CHAT | -0.044 |
Token | more |
Token ID | 517 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
incial | +0.708 |
ISION | +0.692 |
netflix | +0.617 |
andom | +0.614 |
iple | +0.599 |
Neg logit contributions | |
bered | -0.747 |
tons | -0.703 |
tto | -0.693 |
ean | -0.683 |
CHAT | -0.676 |
Token | laid |
Token ID | 8104 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
bered | +0.466 |
tons | +0.433 |
tto | +0.426 |
ean | +0.418 |
CHAT | +0.411 |
Neg logit contributions | |
incial | -0.617 |
ISION | -0.606 |
netflix | -0.549 |
andom | -0.548 |
iple | -0.537 |
Token | bare |
Token ID | 6247 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
bered | +0.243 |
tons | +0.226 |
tto | +0.221 |
ean | +0.217 |
CHAT | +0.215 |
Neg logit contributions | |
incial | -0.348 |
ISION | -0.341 |
netflix | -0.310 |
andom | -0.310 |
iple | -0.303 |
Token | to |
Token ID | 284 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
bered | +3.911 |
tons | +3.627 |
tto | +3.571 |
ean | +3.433 |
ness | +3.327 |
Neg logit contributions | |
incial | -6.346 |
ISION | -6.208 |
netflix | -5.716 |
andom | -5.709 |
iple | -5.599 |
Token | each |
Token ID | 1123 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
incial | +0.083 |
ISION | +0.081 |
netflix | +0.073 |
andom | +0.073 |
iple | +0.072 |
Neg logit contributions | |
bered | -0.069 |
tons | -0.064 |
tto | -0.063 |
ean | -0.062 |
CHAT | -0.062 |
Token | other |
Token ID | 584 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
incial | +0.369 |
ISION | +0.360 |
andom | +0.318 |
netflix | +0.318 |
iple | +0.308 |
Neg logit contributions | |
bered | -0.450 |
tons | -0.426 |
tto | -0.419 |
ean | -0.412 |
CHAT | -0.411 |
Token | and |
Token ID | 290 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
incial | +0.617 |
ISION | +0.606 |
netflix | +0.550 |
andom | +0.550 |
iple | +0.538 |
Neg logit contributions | |
bered | -0.449 |
tons | -0.417 |
tto | -0.410 |
ean | -0.403 |
CHAT | -0.398 |
Token | be |
Token ID | 307 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
bered | +0.091 |
tons | +0.085 |
tto | +0.083 |
ean | +0.082 |
CHAT | +0.081 |
Neg logit contributions | |
incial | -0.120 |
ISION | -0.118 |
netflix | -0.107 |
andom | -0.107 |
iple | -0.105 |
Token | ays |
Token ID | 592 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
incial | +1.077 |
ISION | +1.047 |
netflix | +0.911 |
andom | +0.910 |
iple | +0.882 |
Neg logit contributions | |
bered | -1.559 |
tons | -1.476 |
tto | -1.457 |
ean | -1.439 |
CHAT | -1.429 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bered | +0.396 |
tons | +0.369 |
tto | +0.360 |
ean | +0.351 |
CHAT | +0.338 |
Neg logit contributions | |
incial | -0.609 |
ISION | -0.597 |
andom | -0.545 |
netflix | -0.544 |
iple | -0.534 |
Token | There |
Token ID | 1318 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
incial | +0.023 |
ISION | +0.022 |
netflix | +0.020 |
andom | +0.020 |
iple | +0.020 |
Neg logit contributions | |
bered | -0.021 |
tons | -0.019 |
tto | -0.019 |
ean | -0.019 |
CHAT | -0.019 |
Token | are |
Token ID | 389 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
bered | +0.297 |
tons | +0.277 |
tto | +0.273 |
ean | +0.267 |
CHAT | +0.262 |
Neg logit contributions | |
incial | -0.378 |
ISION | -0.372 |
netflix | -0.337 |
andom | -0.335 |
iple | -0.328 |
Token | t |
Token ID | 256 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
incial | +0.397 |
ISION | +0.389 |
netflix | +0.353 |
andom | +0.352 |
iple | +0.344 |
Neg logit contributions | |
bered | -0.304 |
tons | -0.283 |
tto | -0.278 |
ean | -0.273 |
CHAT | -0.269 |
Token | inct |
Token ID | 4612 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
bered | +0.405 |
tons | +0.326 |
tto | +0.307 |
ean | +0.290 |
CHAT | +0.270 |
Neg logit contributions | |
incial | -2.231 |
ISION | -2.210 |
netflix | -2.067 |
andom | -2.060 |
iple | -2.032 |
Token | ures |
Token ID | 942 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
bered | +3.601 |
tons | +3.392 |
ean | +3.304 |
tto | +3.239 |
odus | +3.060 |
Neg logit contributions | |
incial | -6.536 |
ISION | -6.533 |
andom | -5.937 |
netflix | -5.839 |
sqor | -5.694 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
bered | +1.288 |
tons | +1.192 |
tto | +1.171 |
ean | +1.146 |
ber | +1.087 |
Neg logit contributions | |
incial | -1.966 |
ISION | -1.937 |
netflix | -1.764 |
andom | -1.761 |
iple | -1.723 |
Token | You |
Token ID | 921 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
bered | +0.027 |
tons | +0.026 |
tto | +0.025 |
ean | +0.025 |
CHAT | +0.025 |
Neg logit contributions | |
incial | -0.030 |
ISION | -0.030 |
netflix | -0.027 |
andom | -0.027 |
iple | -0.026 |
Token | can |
Token ID | 460 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
bered | +1.189 |
tons | +1.101 |
tto | +1.083 |
ean | +1.059 |
CHAT | +1.030 |
Neg logit contributions | |
incial | -1.722 |
ISION | -1.694 |
netflix | -1.544 |
andom | -1.538 |
iple | -1.501 |
Token | put |
Token ID | 1234 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
bered | +0.860 |
tons | +0.804 |
tto | +0.793 |
ean | +0.779 |
CHAT | +0.763 |
Neg logit contributions | |
incial | -1.015 |
ISION | -0.993 |
netflix | -0.898 |
andom | -0.894 |
iple | -0.870 |
Token | has |
Token ID | 468 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
bered | +0.914 |
tons | +0.854 |
tto | +0.834 |
ean | +0.827 |
CHAT | +0.811 |
Neg logit contributions | |
incial | -1.158 |
ISION | -1.136 |
netflix | -1.028 |
andom | -1.024 |
iple | -1.003 |
Token | also |
Token ID | 635 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
incial | +0.240 |
ISION | +0.235 |
netflix | +0.213 |
andom | +0.212 |
iple | +0.207 |
Neg logit contributions | |
bered | -0.195 |
tons | -0.182 |
tto | -0.179 |
ean | -0.176 |
CHAT | -0.174 |
Token | upset |
Token ID | 9247 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
incial | +0.049 |
ISION | +0.048 |
netflix | +0.043 |
andom | +0.043 |
iple | +0.042 |
Neg logit contributions | |
bered | -0.038 |
tons | -0.035 |
tto | -0.035 |
ean | -0.034 |
CHAT | -0.034 |
Token | defenders |
Token ID | 16355 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
bered | +0.301 |
tons | +0.281 |
tto | +0.276 |
ean | +0.271 |
CHAT | +0.268 |
Neg logit contributions | |
incial | -0.376 |
ISION | -0.369 |
netflix | -0.334 |
andom | -0.333 |
iple | -0.326 |
Token | of |
Token ID | 286 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
incial | +0.077 |
ISION | +0.076 |
netflix | +0.069 |
andom | +0.069 |
iple | +0.068 |
Neg logit contributions | |
bered | -0.050 |
tons | -0.046 |
tto | -0.045 |
ean | -0.044 |
CHAT | -0.044 |
Token | wom |
Token ID | 1116 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
incial | +0.690 |
ISION | +0.678 |
netflix | +0.612 |
andom | +0.611 |
iple | +0.601 |
Neg logit contributions | |
bered | -0.536 |
tons | -0.500 |
tto | -0.489 |
ean | -0.483 |
CHAT | -0.477 |
Token | ens |
Token ID | 641 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
bered | +3.993 |
tons | +3.686 |
tto | +3.605 |
ean | +3.535 |
phys | +3.426 |
Neg logit contributions | |
incial | -6.183 |
ISION | -6.177 |
netflix | -5.744 |
andom | -5.479 |
sqor | -5.408 |
Token | � |
Token ID | 447 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
incial | +0.040 |
ISION | +0.040 |
andom | +0.036 |
netflix | +0.036 |
iple | +0.036 |
Neg logit contributions | |
bered | -0.025 |
tons | -0.023 |
tto | -0.023 |
ean | -0.022 |
CHAT | -0.022 |
Token | � |
Token ID | 247 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
incial | +0.317 |
ISION | +0.309 |
netflix | +0.272 |
andom | +0.270 |
iple | +0.261 |
Neg logit contributions | |
bered | -0.415 |
tons | -0.392 |
tto | -0.389 |
ean | -0.382 |
CHAT | -0.378 |
Token | rights |
Token ID | 2489 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
incial | +0.268 |
ISION | +0.264 |
andom | +0.241 |
netflix | +0.238 |
iple | +0.235 |
Neg logit contributions | |
bered | -0.184 |
tons | -0.170 |
tto | -0.167 |
ean | -0.164 |
CHAT | -0.162 |
Token | in |
Token ID | 287 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
bered | +1.637 |
tons | +1.507 |
tto | +1.472 |
ean | +1.442 |
CHAT | +1.393 |
Neg logit contributions | |
incial | -2.801 |
ISION | -2.745 |
netflix | -2.518 |
andom | -2.514 |
iple | -2.464 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
incial | +1.077 |
ISION | +1.057 |
andom | +0.958 |
netflix | +0.956 |
iple | +0.940 |
Neg logit contributions | |
bered | -0.782 |
tons | -0.725 |
tto | -0.713 |
ean | -0.702 |
CHAT | -0.691 |
Token | 000 |
Token ID | 830 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
bered | +0.066 |
tons | +0.061 |
tto | +0.060 |
ean | +0.058 |
CHAT | +0.057 |
Neg logit contributions | |
incial | -0.111 |
ISION | -0.109 |
netflix | -0.100 |
andom | -0.100 |
iple | -0.098 |
Token | worsh |
Token ID | 26511 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
bered | +1.155 |
tons | +1.074 |
tto | +1.051 |
ean | +1.031 |
CHAT | +1.015 |
Neg logit contributions | |
incial | -1.609 |
ISION | -1.581 |
netflix | -1.441 |
andom | -1.433 |
iple | -1.399 |
Token | ippers |
Token ID | 16415 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
bered | +0.319 |
tons | +0.298 |
tto | +0.293 |
ean | +0.288 |
CHAT | +0.284 |
Neg logit contributions | |
incial | -0.366 |
ISION | -0.359 |
netflix | -0.323 |
andom | -0.322 |
iple | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
bered | +0.450 |
tons | +0.417 |
tto | +0.409 |
ean | +0.401 |
CHAT | +0.393 |
Neg logit contributions | |
incial | -0.653 |
ISION | -0.643 |
netflix | -0.585 |
andom | -0.583 |
iple | -0.571 |
Token | ooz |
Token ID | 49564 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
bered | +0.232 |
tons | +0.217 |
tto | +0.213 |
ean | +0.210 |
CHAT | +0.206 |
Neg logit contributions | |
incial | -0.276 |
ISION | -0.270 |
netflix | -0.244 |
andom | -0.243 |
iple | -0.238 |
Token | es |
Token ID | 274 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
bered | +1.095 |
tons | +0.877 |
ean | +0.779 |
tto | +0.754 |
odus | +0.527 |
Neg logit contributions | |
ISION | -8.931 |
incial | -8.927 |
andom | -8.363 |
netflix | -8.308 |
iple | -8.206 |
Token | confidence |
Token ID | 6628 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
incial | +0.914 |
ISION | +0.898 |
netflix | +0.814 |
andom | +0.813 |
iple | +0.797 |
Neg logit contributions | |
bered | -0.664 |
tons | -0.613 |
tto | -0.605 |
ean | -0.593 |
CHAT | -0.587 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
incial | +1.277 |
ISION | +1.254 |
netflix | +1.138 |
andom | +1.137 |
iple | +1.115 |
Neg logit contributions | |
bered | -0.930 |
tons | -0.862 |
tto | -0.847 |
ean | -0.833 |
CHAT | -0.823 |
Token | rising |
Token ID | 7396 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
bered | +0.155 |
tons | +0.145 |
tto | +0.143 |
ean | +0.140 |
CHAT | +0.138 |
Neg logit contributions | |
incial | -0.198 |
ISION | -0.194 |
netflix | -0.175 |
andom | -0.175 |
iple | -0.172 |
Token | 50 |
Token ID | 2026 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
incial | +0.781 |
ISION | +0.767 |
netflix | +0.696 |
andom | +0.694 |
iple | +0.680 |
Neg logit contributions | |
bered | -0.576 |
tons | -0.535 |
tto | -0.526 |
ean | -0.516 |
CHAT | -0.510 |
Token |
|
Token ID | 198 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
bered | +0.112 |
tons | +0.106 |
tto | +0.104 |
ean | +0.102 |
CHAT | +0.100 |
Neg logit contributions | |
incial | -0.151 |
ISION | -0.148 |
andom | -0.134 |
netflix | -0.134 |
iple | -0.132 |
Token | William |
Token ID | 17121 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
incial | +0.182 |
ISION | +0.179 |
netflix | +0.162 |
andom | +0.161 |
iple | +0.158 |
Neg logit contributions | |
bered | -0.141 |
tons | -0.131 |
tto | -0.129 |
ean | -0.127 |
CHAT | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
bered | +0.024 |
tons | +0.023 |
tto | +0.022 |
ean | +0.022 |
CHAT | +0.022 |
Neg logit contributions | |
incial | -0.028 |
ISION | -0.028 |
netflix | -0.025 |
andom | -0.025 |
iple | -0.024 |
Token | Flor |
Token ID | 4432 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
bered | +0.209 |
tons | +0.196 |
tto | +0.193 |
ean | +0.190 |
CHAT | +0.188 |
Neg logit contributions | |
incial | -0.226 |
ISION | -0.221 |
netflix | -0.198 |
andom | -0.198 |
iple | -0.193 |
Token | a |
Token ID | 64 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
bered | +2.680 |
tons | +2.502 |
tto | +2.494 |
ean | +2.448 |
CHAT | +2.370 |
Neg logit contributions | |
incial | -3.423 |
ISION | -3.388 |
netflix | -3.054 |
andom | -3.004 |
iple | -2.969 |
Token | Hew |
Token ID | 30446 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
bered | +0.620 |
tons | +0.581 |
tto | +0.573 |
ean | +0.563 |
CHAT | +0.554 |
Neg logit contributions | |
incial | -0.723 |
ISION | -0.709 |
netflix | -0.637 |
andom | -0.635 |
iple | -0.623 |
Token | lett |
Token ID | 15503 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
bered | +3.485 |
tons | +3.355 |
ean | +3.185 |
tto | +3.155 |
ness | +3.034 |
Neg logit contributions | |
incial | -6.601 |
ISION | -6.525 |
netflix | -5.903 |
andom | -5.824 |
iple | -5.793 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
incial | +0.046 |
ISION | +0.046 |
andom | +0.041 |
netflix | +0.041 |
iple | +0.040 |
Neg logit contributions | |
bered | -0.034 |
tons | -0.031 |
tto | -0.031 |
ean | -0.030 |
CHAT | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
bered | +1.563 |
tons | +1.451 |
tto | +1.423 |
ean | +1.396 |
CHAT | +1.377 |
Neg logit contributions | |
incial | -2.183 |
ISION | -2.137 |
netflix | -1.944 |
andom | -1.933 |
iple | -1.905 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
incial | +0.108 |
ISION | +0.106 |
andom | +0.096 |
netflix | +0.096 |
iple | +0.094 |
Neg logit contributions | |
bered | -0.082 |
tons | -0.077 |
tto | -0.075 |
ean | -0.074 |
CHAT | -0.073 |
Token | F |
Token ID | 37 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
incial | +0.301 |
ISION | +0.296 |
netflix | +0.269 |
andom | +0.267 |
iple | +0.261 |
Neg logit contributions | |
bered | -0.239 |
tons | -0.221 |
tto | -0.218 |
ean | -0.214 |
CHAT | -0.210 |
Token | , |
Token ID | 11 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
incial | +1.621 |
ISION | +1.590 |
netflix | +1.443 |
andom | +1.434 |
iple | +1.402 |
Neg logit contributions | |
bered | -1.201 |
tons | -1.119 |
tto | -1.102 |
CHAT | -1.082 |
ean | -1.078 |
Token | the |
Token ID | 262 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
bered | +0.097 |
tons | +0.091 |
tto | +0.089 |
ean | +0.088 |
CHAT | +0.087 |
Neg logit contributions | |
incial | -0.115 |
ISION | -0.113 |
netflix | -0.102 |
andom | -0.102 |
iple | -0.099 |
Token | authorities |
Token ID | 4773 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
bered | +0.131 |
tons | +0.122 |
tto | +0.120 |
ean | +0.118 |
CHAT | +0.116 |
Neg logit contributions | |
incial | -0.168 |
ISION | -0.165 |
netflix | -0.150 |
andom | -0.149 |
iple | -0.146 |
Token | must |
Token ID | 1276 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
incial | +0.473 |
ISION | +0.462 |
netflix | +0.421 |
andom | +0.418 |
iple | +0.412 |
Neg logit contributions | |
bered | -0.322 |
tons | -0.298 |
tto | -0.293 |
ean | -0.287 |
CHAT | -0.284 |
Token | look |
Token ID | 804 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
bered | +1.080 |
tons | +1.004 |
tto | +0.988 |
ean | +0.969 |
CHAT | +0.944 |
Neg logit contributions | |
incial | -1.432 |
ISION | -1.410 |
netflix | -1.281 |
andom | -1.275 |
iple | -1.246 |
Token | urgently |
Token ID | 37788 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
bered | +0.031 |
tons | +0.029 |
tto | +0.028 |
ean | +0.028 |
CHAT | +0.027 |
Neg logit contributions | |
incial | -0.049 |
ISION | -0.048 |
netflix | -0.044 |
andom | -0.044 |
iple | -0.043 |
Token | at |
Token ID | 379 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
bered | +3.551 |
tons | +3.193 |
tto | +3.148 |
ness | +3.081 |
ean | +3.075 |
Neg logit contributions | |
incial | -6.198 |
ISION | -6.109 |
andom | -5.616 |
netflix | -5.532 |
iple | -5.488 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
bered | +0.383 |
tons | +0.359 |
tto | +0.353 |
ean | +0.347 |
CHAT | +0.341 |
Neg logit contributions | |
incial | -0.454 |
ISION | -0.446 |
andom | -0.402 |
netflix | -0.401 |
iple | -0.392 |
Token | construction |
Token ID | 5103 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
bered | +0.248 |
tons | +0.231 |
tto | +0.227 |
ean | +0.223 |
CHAT | +0.220 |
Neg logit contributions | |
incial | -0.311 |
ISION | -0.305 |
netflix | -0.276 |
andom | -0.276 |
iple | -0.269 |
Token | of |
Token ID | 286 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
bered | +1.012 |
tons | +0.938 |
tto | +0.912 |
ean | +0.898 |
CHAT | +0.881 |
Neg logit contributions | |
incial | -1.705 |
ISION | -1.680 |
netflix | -1.543 |
andom | -1.530 |
iple | -1.499 |
Token | dams |
Token ID | 40907 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
bered | +0.080 |
tons | +0.075 |
tto | +0.074 |
ean | +0.073 |
CHAT | +0.072 |
Neg logit contributions | |
incial | -0.095 |
ISION | -0.094 |
netflix | -0.084 |
andom | -0.084 |
iple | -0.082 |
Token | narrow |
Token ID | 7135 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
bered | +0.114 |
tons | +0.106 |
tto | +0.104 |
ean | +0.103 |
CHAT | +0.101 |
Neg logit contributions | |
incial | -0.133 |
ISION | -0.131 |
netflix | -0.118 |
andom | -0.117 |
iple | -0.115 |
Token | passage |
Token ID | 10066 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
bered | +1.078 |
tons | +1.006 |
tto | +0.990 |
ean | +0.973 |
CHAT | +0.958 |
Neg logit contributions | |
incial | -1.322 |
ISION | -1.297 |
netflix | -1.172 |
andom | -1.170 |
iple | -1.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
bered | +0.315 |
tons | +0.292 |
tto | +0.287 |
ean | +0.282 |
CHAT | +0.275 |
Neg logit contributions | |
incial | -0.456 |
ISION | -0.448 |
netflix | -0.408 |
andom | -0.407 |
iple | -0.399 |
Token | According |
Token ID | 4784 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
bered | +0.175 |
tons | +0.164 |
tto | +0.162 |
ean | +0.159 |
CHAT | +0.157 |
Neg logit contributions | |
incial | -0.196 |
ISION | -0.192 |
netflix | -0.173 |
andom | -0.173 |
iple | -0.169 |
Token | to |
Token ID | 284 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
bered | +0.924 |
tons | +0.858 |
tto | +0.847 |
ean | +0.830 |
CHAT | +0.810 |
Neg logit contributions | |
incial | -1.507 |
ISION | -1.484 |
netflix | -1.353 |
andom | -1.352 |
iple | -1.327 |
Token | Herod |
Token ID | 48084 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
bered | +0.074 |
tons | +0.069 |
tto | +0.068 |
ean | +0.067 |
CHAT | +0.066 |
Neg logit contributions | |
incial | -0.095 |
ISION | -0.093 |
netflix | -0.084 |
andom | -0.084 |
iple | -0.083 |
Token | ot |
Token ID | 313 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
bered | +3.573 |
tons | +3.409 |
tto | +3.377 |
ean | +3.346 |
odus | +3.296 |
Neg logit contributions | |
ISION | -6.007 |
incial | -5.943 |
netflix | -5.444 |
andom | -5.218 |
iple | -5.182 |
Token | us |
Token ID | 385 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
bered | +0.215 |
tons | +0.199 |
tto | +0.196 |
ean | +0.194 |
odus | +0.187 |
Neg logit contributions | |
incial | -0.334 |
ISION | -0.331 |
netflix | -0.300 |
andom | -0.299 |
iple | -0.292 |
Token | , |
Token ID | 11 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
bered | +0.325 |
tons | +0.301 |
tto | +0.296 |
ean | +0.291 |
CHAT | +0.286 |
Neg logit contributions | |
incial | -0.465 |
ISION | -0.457 |
netflix | -0.415 |
andom | -0.414 |
iple | -0.406 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
bered | +0.878 |
tons | +0.821 |
tto | +0.806 |
ean | +0.794 |
CHAT | +0.778 |
Neg logit contributions | |
incial | -1.111 |
ISION | -1.091 |
netflix | -0.986 |
andom | -0.984 |
iple | -0.962 |
Token | squ |
Token ID | 2809 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
bered | +0.240 |
tons | +0.223 |
tto | +0.219 |
ean | +0.215 |
CHAT | +0.212 |
Neg logit contributions | |
incial | -0.319 |
ISION | -0.313 |
netflix | -0.284 |
andom | -0.283 |
iple | -0.277 |
Token | couple |
Token ID | 3155 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bered | +0.329 |
tons | +0.305 |
tto | +0.300 |
ean | +0.294 |
CHAT | +0.289 |
Neg logit contributions | |
incial | -0.460 |
ISION | -0.451 |
netflix | -0.409 |
andom | -0.409 |
iple | -0.401 |
Token | of |
Token ID | 286 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
incial | +0.289 |
ISION | +0.283 |
netflix | +0.259 |
andom | +0.258 |
iple | +0.253 |
Neg logit contributions | |
bered | -0.187 |
tons | -0.172 |
tto | -0.169 |
ean | -0.166 |
CHAT | -0.164 |
Token | drops |
Token ID | 10532 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
bered | +0.223 |
tons | +0.207 |
tto | +0.203 |
ean | +0.200 |
CHAT | +0.197 |
Neg logit contributions | |
incial | -0.306 |
ISION | -0.301 |
netflix | -0.273 |
andom | -0.273 |
iple | -0.267 |
Token | of |
Token ID | 286 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
bered | +0.700 |
tons | +0.644 |
tto | +0.632 |
ean | +0.618 |
CHAT | +0.601 |
Neg logit contributions | |
incial | -1.138 |
ISION | -1.120 |
andom | -1.022 |
netflix | -1.021 |
iple | -1.000 |
Token | t |
Token ID | 256 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
bered | +0.095 |
tons | +0.088 |
tto | +0.087 |
ean | +0.085 |
CHAT | +0.084 |
Neg logit contributions | |
incial | -0.114 |
ISION | -0.112 |
netflix | -0.101 |
andom | -0.101 |
iple | -0.099 |
Token | inct |
Token ID | 4612 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
bered | +0.316 |
tons | +0.228 |
tto | +0.210 |
ean | +0.190 |
CHAT | +0.172 |
Neg logit contributions | |
incial | -2.550 |
ISION | -2.524 |
netflix | -2.373 |
andom | -2.366 |
iple | -2.334 |
Token | ure |
Token ID | 495 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
bered | +2.917 |
ean | +2.636 |
tons | +2.631 |
tto | +2.614 |
odus | +2.472 |
Neg logit contributions | |
ISION | -6.728 |
incial | -6.694 |
andom | -6.118 |
netflix | -6.044 |
sqor | -5.942 |
Token | or |
Token ID | 393 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
bered | +1.658 |
tons | +1.532 |
tto | +1.528 |
ean | +1.473 |
CHAT | +1.418 |
Neg logit contributions | |
incial | -2.610 |
ISION | -2.575 |
andom | -2.332 |
netflix | -2.327 |
iple | -2.285 |
Token | a |
Token ID | 257 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
incial | +0.328 |
ISION | +0.322 |
netflix | +0.290 |
andom | +0.290 |
iple | +0.284 |
Neg logit contributions | |
bered | -0.268 |
tons | -0.250 |
tto | -0.245 |
ean | -0.241 |
CHAT | -0.239 |
Token | few |
Token ID | 1178 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
bered | +0.225 |
tons | +0.208 |
tto | +0.204 |
ean | +0.200 |
CHAT | +0.197 |
Neg logit contributions | |
incial | -0.337 |
ISION | -0.331 |
netflix | -0.302 |
andom | -0.301 |
iple | -0.295 |
Token | dro |
Token ID | 3102 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
incial | +0.533 |
ISION | +0.522 |
netflix | +0.471 |
andom | +0.470 |
iple | +0.461 |
Neg logit contributions | |
bered | -0.442 |
tons | -0.411 |
tto | -0.404 |
ean | -0.399 |
CHAT | -0.395 |
Token | and |
Token ID | 290 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
bered | +0.106 |
tons | +0.098 |
tto | +0.096 |
ean | +0.094 |
CHAT | +0.093 |
Neg logit contributions | |
incial | -0.150 |
ISION | -0.148 |
netflix | -0.134 |
andom | -0.134 |
iple | -0.131 |
Token | other |
Token ID | 584 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
incial | +0.086 |
ISION | +0.085 |
netflix | +0.076 |
andom | +0.076 |
iple | +0.075 |
Neg logit contributions | |
bered | -0.071 |
tons | -0.066 |
tto | -0.065 |
ean | -0.064 |
CHAT | -0.063 |
Token | related |
Token ID | 3519 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
incial | +0.415 |
ISION | +0.408 |
netflix | +0.369 |
andom | +0.368 |
iple | +0.361 |
Neg logit contributions | |
bered | -0.309 |
tons | -0.287 |
tto | -0.282 |
ean | -0.276 |
CHAT | -0.273 |
Token | elements |
Token ID | 4847 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
bered | +0.741 |
tons | +0.688 |
tto | +0.675 |
ean | +0.664 |
CHAT | +0.652 |
Neg logit contributions | |
incial | -1.056 |
ISION | -1.036 |
netflix | -0.943 |
andom | -0.942 |
iple | -0.922 |
Token | of |
Token ID | 286 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
incial | +0.509 |
ISION | +0.500 |
netflix | +0.454 |
andom | +0.453 |
iple | +0.444 |
Neg logit contributions | |
bered | -0.364 |
tons | -0.338 |
tto | -0.332 |
ean | -0.326 |
CHAT | -0.321 |
Token | logistics |
Token ID | 26355 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
incial | +0.431 |
ISION | +0.422 |
netflix | +0.380 |
andom | +0.379 |
iple | +0.370 |
Neg logit contributions | |
bered | -0.388 |
tons | -0.363 |
tto | -0.357 |
ean | -0.352 |
CHAT | -0.347 |
Token | and |
Token ID | 290 |
Feature activation | +5.48e-04 |
Pos logit contributions | |
bered | +3.560 |
tons | +3.290 |
tto | +3.220 |
ean | +3.190 |
ness | +3.117 |
Neg logit contributions | |
incial | -6.070 |
ISION | -5.894 |
netflix | -5.527 |
andom | -5.467 |
iple | -5.382 |
Token | program |
Token ID | 1430 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
bered | +0.001 |
tons | +0.001 |
tto | +0.001 |
ean | +0.001 |
CHAT | +0.001 |
Neg logit contributions | |
incial | -0.001 |
ISION | -0.001 |
netflix | -0.001 |
andom | -0.001 |
iple | -0.001 |
Token | support |
Token ID | 1104 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
incial | +0.296 |
ISION | +0.291 |
netflix | +0.263 |
andom | +0.263 |
iple | +0.258 |
Neg logit contributions | |
bered | -0.223 |
tons | -0.207 |
tto | -0.203 |
ean | -0.199 |
CHAT | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
bered | +0.384 |
tons | +0.356 |
tto | +0.350 |
ean | +0.343 |
CHAT | +0.337 |
Neg logit contributions | |
incial | -0.554 |
ISION | -0.544 |
netflix | -0.497 |
andom | -0.495 |
iple | -0.485 |
Token | The |
Token ID | 383 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
bered | +0.172 |
tons | +0.161 |
tto | +0.159 |
ean | +0.156 |
CHAT | +0.153 |
Neg logit contributions | |
incial | -0.217 |
ISION | -0.214 |
netflix | -0.193 |
andom | -0.193 |
iple | -0.189 |
Token | was |
Token ID | 373 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
incial | +0.545 |
ISION | +0.535 |
netflix | +0.483 |
andom | +0.482 |
iple | +0.471 |
Neg logit contributions | |
bered | -0.439 |
tons | -0.410 |
tto | -0.403 |
ean | -0.396 |
CHAT | -0.390 |
Token | about |
Token ID | 546 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
incial | +0.503 |
ISION | +0.493 |
netflix | +0.446 |
andom | +0.445 |
iple | +0.436 |
Neg logit contributions | |
bered | -0.401 |
tons | -0.374 |
tto | -0.368 |
ean | -0.361 |
CHAT | -0.356 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
incial | +1.009 |
ISION | +0.991 |
netflix | +0.894 |
andom | +0.892 |
iple | +0.871 |
Neg logit contributions | |
bered | -0.846 |
tons | -0.789 |
tto | -0.776 |
ean | -0.763 |
CHAT | -0.755 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
incial | +0.735 |
ISION | +0.722 |
netflix | +0.657 |
andom | +0.655 |
iple | +0.641 |
Neg logit contributions | |
bered | -0.525 |
tons | -0.487 |
tto | -0.478 |
ean | -0.470 |
CHAT | -0.463 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
incial | +0.098 |
ISION | +0.096 |
netflix | +0.087 |
andom | +0.087 |
iple | +0.085 |
Neg logit contributions | |
bered | -0.078 |
tons | -0.073 |
tto | -0.071 |
ean | -0.070 |
CHAT | -0.069 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
incial | +0.430 |
ISION | +0.423 |
netflix | +0.383 |
andom | +0.382 |
iple | +0.372 |
Neg logit contributions | |
bered | -0.358 |
tons | -0.333 |
tto | -0.328 |
ean | -0.322 |
CHAT | -0.318 |
Token | : |
Token ID | 25 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
incial | +6.580 |
ISION | +6.498 |
iple | +5.892 |
andom | +5.889 |
netflix | +5.829 |
Neg logit contributions | |
bered | -6.306 |
tons | -5.717 |
cellence | -5.708 |
tto | -5.679 |
odus | -5.586 |
Token | k |
Token ID | 479 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
incial | +0.493 |
ISION | +0.484 |
netflix | +0.436 |
andom | +0.435 |
iple | +0.426 |
Neg logit contributions | |
bered | -0.415 |
tons | -0.388 |
tto | -0.382 |
ean | -0.375 |
CHAT | -0.370 |
Token | imp |
Token ID | 11011 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
bered | +0.511 |
tons | +0.478 |
tto | +0.472 |
ean | +0.465 |
CHAT | +0.455 |
Neg logit contributions | |
incial | -0.595 |
ISION | -0.585 |
netflix | -0.524 |
andom | -0.521 |
iple | -0.510 |
Token | unk |
Token ID | 2954 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
bered | +0.357 |
tons | +0.333 |
tto | +0.327 |
ean | +0.322 |
CHAT | +0.316 |
Neg logit contributions | |
incial | -0.450 |
ISION | -0.442 |
netflix | -0.399 |
andom | -0.397 |
iple | -0.389 |
Token | rock |
Token ID | 10823 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
incial | +0.192 |
ISION | +0.189 |
netflix | +0.170 |
andom | +0.170 |
iple | +0.166 |
Neg logit contributions | |
bered | -0.162 |
tons | -0.151 |
tto | -0.149 |
ean | -0.146 |
CHAT | -0.144 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
bered | +1.087 |
tons | +1.032 |
tto | +1.011 |
ean | +0.990 |
CHAT | +0.970 |
Neg logit contributions | |
incial | -1.841 |
ISION | -1.792 |
andom | -1.647 |
netflix | -1.635 |
iple | -1.617 |
Token | I |
Token ID | 314 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
bered | +0.167 |
tons | +0.156 |
tto | +0.154 |
ean | +0.151 |
CHAT | +0.149 |
Neg logit contributions | |
incial | -0.207 |
ISION | -0.203 |
netflix | -0.183 |
andom | -0.183 |
iple | -0.179 |
Token | think |
Token ID | 892 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
bered | +0.506 |
tons | +0.468 |
tto | +0.462 |
ean | +0.448 |
CHAT | +0.440 |
Neg logit contributions | |
incial | -0.810 |
ISION | -0.797 |
netflix | -0.726 |
andom | -0.725 |
iple | -0.710 |
Token |
|
Token ID | 198 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
bered | +1.107 |
tons | +1.031 |
tto | +1.018 |
ean | +1.003 |
CHAT | +0.978 |
Neg logit contributions | |
incial | -1.475 |
ISION | -1.442 |
andom | -1.307 |
netflix | -1.304 |
iple | -1.275 |
Token |
|
Token ID | 198 |
Feature activation | +6.38e-04 |
Pos logit contributions | |
bered | +0.401 |
tons | +0.378 |
tto | +0.372 |
ean | +0.364 |
CHAT | +0.357 |
Neg logit contributions | |
incial | -0.555 |
ISION | -0.543 |
andom | -0.493 |
netflix | -0.492 |
iple | -0.484 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
bered | +0.001 |
tons | +0.001 |
tto | +0.001 |
ean | +0.001 |
CHAT | +0.001 |
Neg logit contributions | |
incial | -0.001 |
ISION | -0.001 |
netflix | -0.001 |
andom | -0.001 |
iple | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
incial | +6.379 |
ISION | +6.305 |
netflix | +5.654 |
andom | +5.612 |
iple | +5.492 |
Neg logit contributions | |
bered | -6.306 |
cellence | -5.784 |
tons | -5.662 |
odus | -5.595 |
tto | -5.574 |
Token | B |
Token ID | 347 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
incial | +0.491 |
ISION | +0.482 |
netflix | +0.434 |
andom | +0.433 |
iple | +0.423 |
Neg logit contributions | |
bered | -0.417 |
tons | -0.390 |
tto | -0.383 |
ean | -0.377 |
CHAT | -0.372 |
Token | iz |
Token ID | 528 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
incial | +0.472 |
ISION | +0.462 |
netflix | +0.416 |
andom | +0.414 |
iple | +0.405 |
Neg logit contributions | |
bered | -0.417 |
tons | -0.391 |
tto | -0.385 |
ean | -0.378 |
CHAT | -0.373 |
Token | r |
Token ID | 81 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
bered | +0.182 |
tons | +0.170 |
tto | +0.167 |
ean | +0.164 |
CHAT | +0.162 |
Neg logit contributions | |
incial | -0.230 |
ISION | -0.226 |
netflix | -0.204 |
andom | -0.204 |
iple | -0.200 |
Token | Pix |
Token ID | 21642 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
bered | +1.239 |
tons | +1.161 |
tto | +1.147 |
ean | +1.125 |
CHAT | +1.107 |
Neg logit contributions | |
incial | -1.449 |
ISION | -1.422 |
netflix | -1.277 |
andom | -1.261 |
iple | -1.240 |
Token | iff |
Token ID | 733 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
bered | +0.989 |
tons | +0.939 |
tto | +0.932 |
ean | +0.919 |
CHAT | +0.898 |
Neg logit contributions | |
incial | -0.900 |
ISION | -0.886 |
netflix | -0.788 |
andom | -0.775 |
iple | -0.748 |
Token | Tra |
Token ID | 15721 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
incial | +0.553 |
ISION | +0.543 |
netflix | +0.494 |
andom | +0.493 |
iple | +0.483 |
Neg logit contributions | |
bered | -0.372 |
tons | -0.345 |
tto | -0.339 |
ean | -0.332 |
CHAT | -0.327 |
Token | x |
Token ID | 87 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
incial | +2.986 |
ISION | +2.929 |
netflix | +2.743 |
andom | +2.742 |
iple | +2.704 |
Neg logit contributions | |
bered | -0.840 |
tons | -0.710 |
tto | -0.674 |
CHAT | -0.654 |
ean | -0.645 |
Token |
|
Token ID | 198 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
bered | +2.229 |
tons | +2.066 |
tto | +2.065 |
ean | +2.007 |
CHAT | +1.959 |
Neg logit contributions | |
incial | -3.119 |
ISION | -3.043 |
andom | -2.766 |
netflix | -2.746 |
iple | -2.727 |
Token |
|
Token ID | 198 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
bered | +0.117 |
tons | +0.110 |
tto | +0.108 |
ean | +0.106 |
CHAT | +0.104 |
Neg logit contributions | |
incial | -0.157 |
ISION | -0.154 |
andom | -0.139 |
netflix | -0.139 |
iple | -0.137 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
incial | +0.068 |
ISION | +0.066 |
netflix | +0.055 |
andom | +0.055 |
iple | +0.053 |
Neg logit contributions | |
bered | -0.144 |
tons | -0.137 |
tto | -0.136 |
ean | -0.134 |
CHAT | -0.133 |
Token | : |
Token ID | 25 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
incial | +6.366 |
ISION | +6.281 |
netflix | +5.637 |
andom | +5.606 |
iple | +5.483 |
Neg logit contributions | |
bered | -6.256 |
cellence | -5.745 |
tons | -5.631 |
odus | -5.557 |
tto | -5.541 |
Token | V |
Token ID | 569 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
incial | +0.640 |
ISION | +0.628 |
netflix | +0.566 |
andom | +0.565 |
iple | +0.552 |
Neg logit contributions | |
bered | -0.542 |
tons | -0.506 |
tto | -0.498 |
ean | -0.490 |
CHAT | -0.483 |
Token | the |
Token ID | 1169 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bered | +0.231 |
tons | +0.216 |
tto | +0.213 |
ean | +0.210 |
CHAT | +0.206 |
Neg logit contributions | |
incial | -0.264 |
ISION | -0.258 |
netflix | -0.233 |
andom | -0.231 |
iple | -0.226 |
Token | Happy |
Token ID | 25082 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
bered | +0.166 |
tons | +0.154 |
tto | +0.152 |
ean | +0.149 |
CHAT | +0.147 |
Neg logit contributions | |
incial | -0.222 |
ISION | -0.218 |
netflix | -0.198 |
andom | -0.198 |
iple | -0.193 |
Token | L |
Token ID | 43 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
incial | +1.489 |
ISION | +1.464 |
netflix | +1.328 |
andom | +1.327 |
iple | +1.299 |
Neg logit contributions | |
bered | -1.130 |
tons | -1.043 |
tto | -1.029 |
ean | -1.012 |
CHAT | -0.999 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
incial | +0.122 |
ISION | +0.120 |
netflix | +0.110 |
andom | +0.110 |
iple | +0.108 |
Neg logit contributions | |
bered | -0.073 |
tons | -0.068 |
tto | -0.066 |
ean | -0.065 |
CHAT | -0.063 |
Token | boys |
Token ID | 13202 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
bered | +0.919 |
tons | +0.887 |
tto | +0.864 |
ean | +0.858 |
CHAT | +0.849 |
Neg logit contributions | |
incial | -0.438 |
ISION | -0.418 |
andom | -0.337 |
netflix | -0.336 |
iple | -0.325 |
Token | beware |
Token ID | 40600 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
incial | +1.211 |
ISION | +1.186 |
netflix | +1.064 |
andom | +1.060 |
iple | +1.037 |
Neg logit contributions | |
bered | -1.117 |
tons | -1.046 |
tto | -1.030 |
ean | -1.014 |
CHAT | -0.999 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
incial | +0.809 |
ISION | +0.794 |
netflix | +0.717 |
andom | +0.716 |
iple | +0.701 |
Neg logit contributions | |
bered | -0.650 |
tons | -0.607 |
tto | -0.596 |
ean | -0.586 |
CHAT | -0.578 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
bered | +0.238 |
tons | +0.224 |
tto | +0.220 |
ean | +0.216 |
CHAT | +0.212 |
Neg logit contributions | |
incial | -0.324 |
ISION | -0.317 |
andom | -0.287 |
netflix | -0.287 |
iple | -0.282 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
incial | +0.075 |
ISION | +0.073 |
netflix | +0.061 |
andom | +0.061 |
iple | +0.058 |
Neg logit contributions | |
bered | -0.162 |
tons | -0.154 |
tto | -0.153 |
ean | -0.151 |
CHAT | -0.150 |
Token | : |
Token ID | 25 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
incial | +6.336 |
ISION | +6.244 |
netflix | +5.613 |
andom | +5.583 |
iple | +5.466 |
Neg logit contributions | |
bered | -6.159 |
cellence | -5.650 |
tons | -5.555 |
tto | -5.465 |
odus | -5.460 |
Token | j |
Token ID | 474 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
incial | +0.489 |
ISION | +0.479 |
netflix | +0.432 |
andom | +0.431 |
iple | +0.422 |
Neg logit contributions | |
bered | -0.413 |
tons | -0.386 |
tto | -0.380 |
ean | -0.373 |
CHAT | -0.368 |
Token | wt |
Token ID | 46569 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
bered | +0.743 |
tons | +0.692 |
tto | +0.681 |
ean | +0.671 |
CHAT | +0.658 |
Neg logit contributions | |
incial | -0.953 |
ISION | -0.937 |
netflix | -0.846 |
andom | -0.844 |
iple | -0.826 |
Token | 0001 |
Token ID | 18005 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
incial | +1.749 |
ISION | +1.712 |
andom | +1.568 |
netflix | +1.564 |
iple | +1.533 |
Neg logit contributions | |
bered | -1.297 |
tons | -1.201 |
tto | -1.178 |
ean | -1.161 |
CHAT | -1.151 |
Token | - |
Token ID | 532 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
bered | +0.597 |
tons | +0.559 |
tto | +0.550 |
ean | +0.542 |
CHAT | +0.533 |
Neg logit contributions | |
incial | -0.682 |
ISION | -0.668 |
netflix | -0.601 |
andom | -0.600 |
iple | -0.587 |
Token | er |
Token ID | 263 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
bered | +1.414 |
ean | +1.207 |
tto | +1.195 |
tons | +1.179 |
ber | +1.152 |
Neg logit contributions | |
ISION | -6.956 |
incial | -6.914 |
netflix | -6.428 |
andom | -6.413 |
sqor | -6.358 |
Token | magnet |
Token ID | 19972 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
bered | +0.063 |
tons | +0.061 |
tto | +0.059 |
ean | +0.059 |
CHAT | +0.058 |
Neg logit contributions | |
incial | -0.046 |
ISION | -0.045 |
netflix | -0.039 |
andom | -0.039 |
iple | -0.037 |
Token | ? |
Token ID | 30 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
incial | +1.673 |
ISION | +1.645 |
andom | +1.483 |
netflix | +1.479 |
iple | +1.447 |
Neg logit contributions | |
bered | -1.444 |
tons | -1.359 |
tto | -1.332 |
ean | -1.306 |
CHAT | -1.294 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
incial | +0.565 |
ISION | +0.554 |
netflix | +0.501 |
andom | +0.500 |
iple | +0.489 |
Neg logit contributions | |
bered | -0.460 |
tons | -0.429 |
tto | -0.422 |
ean | -0.415 |
CHAT | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
bered | +0.198 |
tons | +0.186 |
tto | +0.183 |
ean | +0.179 |
CHAT | +0.176 |
Neg logit contributions | |
incial | -0.269 |
ISION | -0.263 |
andom | -0.239 |
netflix | -0.238 |
iple | -0.234 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
incial | +0.087 |
ISION | +0.085 |
netflix | +0.071 |
andom | +0.070 |
iple | +0.068 |
Neg logit contributions | |
bered | -0.187 |
tons | -0.178 |
tto | -0.176 |
ean | -0.174 |
CHAT | -0.173 |
Token | : |
Token ID | 25 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
incial | +6.286 |
ISION | +6.187 |
netflix | +5.557 |
andom | +5.522 |
iple | +5.404 |
Neg logit contributions | |
bered | -6.105 |
cellence | -5.594 |
tons | -5.490 |
odus | -5.413 |
tto | -5.404 |
Token | hey |
Token ID | 17207 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
incial | +0.707 |
ISION | +0.693 |
netflix | +0.625 |
andom | +0.623 |
iple | +0.610 |
Neg logit contributions | |
bered | -0.601 |
tons | -0.561 |
tto | -0.552 |
ean | -0.543 |
CHAT | -0.536 |
Token | _ |
Token ID | 62 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
bered | +0.094 |
tons | +0.088 |
tto | +0.087 |
ean | +0.085 |
CHAT | +0.083 |
Neg logit contributions | |
incial | -0.119 |
ISION | -0.117 |
netflix | -0.105 |
andom | -0.105 |
iple | -0.103 |
Token | ler |
Token ID | 1754 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
bered | +0.031 |
tons | +0.029 |
tto | +0.028 |
ean | +0.028 |
CHAT | +0.027 |
Neg logit contributions | |
incial | -0.039 |
ISION | -0.038 |
netflix | -0.034 |
andom | -0.034 |
iple | -0.034 |
Token | oy |
Token ID | 726 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
incial | +0.432 |
ISION | +0.425 |
netflix | +0.382 |
andom | +0.380 |
iple | +0.371 |
Neg logit contributions | |
bered | -0.363 |
tons | -0.340 |
tto | -0.335 |
ean | -0.329 |
CHAT | -0.322 |
Token | are |
Token ID | 389 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
incial | +0.377 |
ISION | +0.370 |
netflix | +0.334 |
andom | +0.334 |
iple | +0.326 |
Neg logit contributions | |
bered | -0.306 |
tons | -0.286 |
tto | -0.281 |
ean | -0.276 |
CHAT | -0.272 |
Token | Here |
Token ID | 3423 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
incial | +0.164 |
ISION | +0.161 |
netflix | +0.147 |
andom | +0.146 |
iple | +0.143 |
Neg logit contributions | |
bered | -0.111 |
tons | -0.102 |
tto | -0.101 |
ean | -0.099 |
CHAT | -0.097 |
Token | .... |
Token ID | 1106 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
bered | +0.175 |
tons | +0.161 |
tto | +0.158 |
ean | +0.155 |
CHAT | +0.152 |
Neg logit contributions | |
incial | -0.298 |
ISION | -0.293 |
netflix | -0.268 |
andom | -0.268 |
iple | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
bered | +0.379 |
tons | +0.353 |
tto | +0.347 |
ean | +0.342 |
CHAT | +0.336 |
Neg logit contributions | |
incial | -0.473 |
ISION | -0.462 |
andom | -0.418 |
netflix | -0.418 |
iple | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
bered | +0.211 |
tons | +0.199 |
tto | +0.195 |
ean | +0.191 |
CHAT | +0.188 |
Neg logit contributions | |
incial | -0.286 |
ISION | -0.280 |
andom | -0.254 |
netflix | -0.253 |
iple | -0.249 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
incial | +0.084 |
ISION | +0.081 |
netflix | +0.068 |
andom | +0.067 |
iple | +0.065 |
Neg logit contributions | |
bered | -0.173 |
tons | -0.165 |
tto | -0.164 |
ean | -0.162 |
CHAT | -0.160 |
Token | : |
Token ID | 25 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
incial | +6.119 |
ISION | +6.032 |
netflix | +5.425 |
andom | +5.383 |
iple | +5.281 |
Neg logit contributions | |
bered | -5.850 |
cellence | -5.337 |
tons | -5.268 |
tto | -5.186 |
odus | -5.177 |
Token | SAS |
Token ID | 35516 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
incial | +0.276 |
ISION | +0.271 |
netflix | +0.244 |
andom | +0.243 |
iple | +0.238 |
Neg logit contributions | |
bered | -0.237 |
tons | -0.222 |
tto | -0.218 |
ean | -0.215 |
CHAT | -0.212 |
Token | K |
Token ID | 42 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
bered | +1.131 |
tons | +1.058 |
tto | +1.046 |
ean | +1.026 |
CHAT | +1.014 |
Neg logit contributions | |
incial | -1.361 |
ISION | -1.334 |
netflix | -1.205 |
andom | -1.195 |
iple | -1.170 |
Token | ATCH |
Token ID | 11417 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
bered | +0.800 |
tons | +0.749 |
tto | +0.738 |
ean | +0.727 |
CHAT | +0.720 |
Neg logit contributions | |
incial | -0.923 |
ISION | -0.901 |
netflix | -0.812 |
andom | -0.809 |
iple | -0.792 |
Token | EW |
Token ID | 6217 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
bered | +1.433 |
tons | +1.355 |
tto | +1.335 |
ean | +1.318 |
CHAT | +1.306 |
Neg logit contributions | |
incial | -1.604 |
ISION | -1.556 |
netflix | -1.414 |
andom | -1.405 |
iple | -1.378 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
bered | +0.028 |
tons | +0.027 |
tto | +0.026 |
ean | +0.026 |
CHAT | +0.026 |
Neg logit contributions | |
incial | -0.026 |
ISION | -0.025 |
netflix | -0.022 |
andom | -0.022 |
iple | -0.022 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
incial | +2.144 |
ISION | +2.097 |
netflix | +1.862 |
andom | +1.857 |
iple | +1.810 |
Neg logit contributions | |
bered | -2.341 |
tons | -2.206 |
tto | -2.175 |
ean | -2.144 |
CHAT | -2.119 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
incial | +0.606 |
ISION | +0.593 |
netflix | +0.540 |
andom | +0.540 |
iple | +0.529 |
Neg logit contributions | |
bered | -0.423 |
tons | -0.395 |
tto | -0.389 |
ean | -0.382 |
CHAT | -0.374 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
incial | +0.078 |
ISION | +0.077 |
netflix | +0.069 |
andom | +0.069 |
iple | +0.068 |
Neg logit contributions | |
bered | -0.060 |
tons | -0.056 |
tto | -0.055 |
ean | -0.054 |
CHAT | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
bered | +0.289 |
tons | +0.272 |
tto | +0.267 |
ean | +0.261 |
CHAT | +0.256 |
Neg logit contributions | |
incial | -0.394 |
ISION | -0.385 |
andom | -0.350 |
netflix | -0.349 |
iple | -0.343 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
incial | +0.008 |
ISION | +0.008 |
netflix | +0.007 |
andom | +0.007 |
iple | +0.007 |
Neg logit contributions | |
bered | -0.017 |
tons | -0.016 |
tto | -0.016 |
ean | -0.016 |
CHAT | -0.016 |
Token | : |
Token ID | 25 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
incial | +6.017 |
ISION | +5.921 |
netflix | +5.327 |
andom | +5.304 |
iple | +5.206 |
Neg logit contributions | |
bered | -5.627 |
cellence | -5.129 |
tons | -5.077 |
tto | -5.003 |
odus | -4.990 |
Token | Mike |
Token ID | 4995 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
incial | +0.403 |
ISION | +0.395 |
netflix | +0.356 |
andom | +0.355 |
iple | +0.347 |
Neg logit contributions | |
bered | -0.343 |
tons | -0.320 |
tto | -0.315 |
ean | -0.310 |
CHAT | -0.306 |
Token | M |
Token ID | 44 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
incial | +0.139 |
ISION | +0.136 |
netflix | +0.123 |
andom | +0.122 |
iple | +0.120 |
Neg logit contributions | |
bered | -0.118 |
tons | -0.110 |
tto | -0.108 |
ean | -0.106 |
CHAT | -0.105 |
Token | anners |
Token ID | 15672 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
bered | +0.723 |
tons | +0.688 |
tto | +0.675 |
ean | +0.670 |
CHAT | +0.662 |
Neg logit contributions | |
incial | -0.532 |
ISION | -0.520 |
netflix | -0.454 |
andom | -0.449 |
iple | -0.438 |
Token | - |
Token ID | 532 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
incial | +1.209 |
ISION | +1.188 |
netflix | +1.072 |
andom | +1.069 |
iple | +1.043 |
Neg logit contributions | |
bered | -1.045 |
tons | -0.974 |
tto | -0.959 |
ean | -0.942 |
CHAT | -0.930 |
Token | prohibited |
Token ID | 12244 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
incial | +1.544 |
ISION | +1.523 |
netflix | +1.381 |
andom | +1.366 |
iple | +1.353 |
Neg logit contributions | |
bered | -1.191 |
tons | -1.101 |
tto | -1.090 |
ean | -1.073 |
CHAT | -1.059 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
incial | +1.071 |
ISION | +1.055 |
netflix | +0.957 |
andom | +0.954 |
iple | +0.935 |
Neg logit contributions | |
bered | -0.771 |
tons | -0.715 |
tto | -0.701 |
ean | -0.690 |
CHAT | -0.679 |
Token | as |
Token ID | 355 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
incial | +0.282 |
ISION | +0.276 |
netflix | +0.250 |
andom | +0.250 |
iple | +0.244 |
Neg logit contributions | |
bered | -0.213 |
tons | -0.199 |
tto | -0.195 |
ean | -0.192 |
CHAT | -0.189 |
Token | are |
Token ID | 389 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
incial | +1.113 |
ISION | +1.090 |
netflix | +0.981 |
andom | +0.979 |
iple | +0.957 |
Neg logit contributions | |
bered | -0.972 |
tons | -0.910 |
tto | -0.894 |
ean | -0.880 |
CHAT | -0.869 |
Token | portable |
Token ID | 17726 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
incial | +0.832 |
ISION | +0.816 |
netflix | +0.734 |
andom | +0.733 |
iple | +0.718 |
Neg logit contributions | |
bered | -0.737 |
tons | -0.687 |
tto | -0.677 |
ean | -0.668 |
CHAT | -0.657 |
Token | Wi |
Token ID | 11759 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
incial | +0.977 |
ISION | +0.958 |
netflix | +0.854 |
andom | +0.848 |
iple | +0.832 |
Neg logit contributions | |
bered | -1.062 |
tons | -0.994 |
tto | -0.986 |
ean | -0.974 |
odus | -0.957 |
Token | - |
Token ID | 12 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
incial | +6.463 |
ISION | +6.401 |
netflix | +5.935 |
andom | +5.837 |
iple | +5.747 |
Neg logit contributions | |
bered | -5.116 |
tons | -4.711 |
tto | -4.595 |
ean | -4.526 |
odus | -4.400 |
Token | Fi |
Token ID | 10547 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
incial | +0.517 |
ISION | +0.503 |
andom | +0.431 |
netflix | +0.430 |
iple | +0.417 |
Neg logit contributions | |
bered | -0.773 |
tons | -0.736 |
tto | -0.727 |
ean | -0.718 |
CHAT | -0.713 |
Token | hots |
Token ID | 33915 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
incial | +4.867 |
ISION | +4.805 |
netflix | +4.398 |
andom | +4.329 |
iple | +4.224 |
Neg logit contributions | |
bered | -5.038 |
tons | -4.727 |
tto | -4.666 |
ean | -4.610 |
odus | -4.557 |
Token | pot |
Token ID | 13059 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
bered | +0.270 |
tons | +0.248 |
tto | +0.241 |
ean | +0.235 |
CHAT | +0.231 |
Neg logit contributions | |
incial | -0.508 |
ISION | -0.502 |
andom | -0.458 |
netflix | -0.457 |
iple | -0.450 |
Token | devices |
Token ID | 4410 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
incial | +1.770 |
ISION | +1.741 |
netflix | +1.581 |
andom | +1.573 |
iple | +1.544 |
Neg logit contributions | |
bered | -1.406 |
tons | -1.306 |
tto | -1.289 |
ean | -1.272 |
CHAT | -1.251 |
Token | carbon |
Token ID | 6588 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
bered | +0.579 |
tons | +0.541 |
tto | +0.535 |
ean | +0.528 |
CHAT | +0.515 |
Neg logit contributions | |
incial | -0.652 |
ISION | -0.639 |
andom | -0.573 |
netflix | -0.571 |
iple | -0.560 |
Token | dioxide |
Token ID | 17556 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
bered | +1.167 |
tto | +1.083 |
tons | +1.082 |
ean | +1.073 |
CHAT | +1.041 |
Neg logit contributions | |
incial | -1.339 |
ISION | -1.324 |
andom | -1.179 |
netflix | -1.178 |
iple | -1.157 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
bered | +0.147 |
tons | +0.135 |
tto | +0.134 |
ean | +0.131 |
CHAT | +0.128 |
Neg logit contributions | |
incial | -0.213 |
ISION | -0.209 |
andom | -0.189 |
netflix | -0.189 |
iple | -0.186 |
Token | A |
Token ID | 317 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
incial | +0.002 |
ISION | +0.002 |
netflix | +0.002 |
andom | +0.002 |
iple | +0.002 |
Neg logit contributions | |
bered | -0.002 |
tons | -0.002 |
tto | -0.002 |
ean | -0.002 |
CHAT | -0.002 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
bered | +0.641 |
tons | +0.597 |
tto | +0.589 |
ean | +0.578 |
CHAT | +0.569 |
Neg logit contributions | |
incial | -0.777 |
ISION | -0.760 |
netflix | -0.687 |
andom | -0.686 |
iple | -0.671 |
Token | Cornell |
Token ID | 27119 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
bered | +0.251 |
tons | +0.234 |
tto | +0.230 |
ean | +0.226 |
CHAT | +0.223 |
Neg logit contributions | |
incial | -0.322 |
ISION | -0.316 |
netflix | -0.287 |
andom | -0.286 |
iple | -0.280 |
Token | University |
Token ID | 2059 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
incial | +6.064 |
ISION | +5.996 |
andom | +5.280 |
netflix | +5.200 |
iple | +5.139 |
Neg logit contributions | |
bered | -5.342 |
tons | -4.953 |
tto | -4.950 |
CHAT | -4.763 |
odus | -4.731 |
Token | analysis |
Token ID | 3781 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
incial | +1.470 |
ISION | +1.445 |
andom | +1.294 |
netflix | +1.290 |
iple | +1.265 |
Neg logit contributions | |
bered | -1.271 |
tons | -1.190 |
tto | -1.171 |
ean | -1.145 |
CHAT | -1.138 |
Token | found |
Token ID | 1043 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
bered | +0.243 |
tons | +0.226 |
tto | +0.221 |
ean | +0.219 |
CHAT | +0.214 |
Neg logit contributions | |
incial | -0.343 |
ISION | -0.337 |
netflix | -0.307 |
andom | -0.306 |
iple | -0.300 |
Token | that |
Token ID | 326 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
incial | +0.744 |
ISION | +0.731 |
netflix | +0.664 |
andom | +0.662 |
iple | +0.648 |
Neg logit contributions | |
bered | -0.543 |
tons | -0.504 |
tto | -0.495 |
ean | -0.486 |
CHAT | -0.479 |
Token | unless |
Token ID | 4556 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
bered | +0.484 |
tons | +0.455 |
tto | +0.446 |
ean | +0.439 |
CHAT | +0.429 |
Neg logit contributions | |
incial | -0.600 |
ISION | -0.588 |
andom | -0.530 |
netflix | -0.529 |
iple | -0.518 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
bered | +0.023 |
tons | +0.021 |
tto | +0.021 |
ean | +0.020 |
CHAT | +0.020 |
Neg logit contributions | |
incial | -0.029 |
ISION | -0.029 |
netflix | -0.026 |
andom | -0.026 |
iple | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
incial | +1.354 |
ISION | +1.331 |
netflix | +1.210 |
andom | +1.208 |
iple | +1.183 |
Neg logit contributions | |
bered | -0.943 |
tons | -0.873 |
tto | -0.857 |
ean | -0.842 |
CHAT | -0.830 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
bered | +0.192 |
tons | +0.178 |
tto | +0.175 |
ean | +0.172 |
CHAT | +0.169 |
Neg logit contributions | |
incial | -0.279 |
ISION | -0.274 |
netflix | -0.249 |
andom | -0.248 |
iple | -0.244 |
Token | levels |
Token ID | 2974 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
bered | +0.046 |
tons | +0.043 |
tto | +0.043 |
ean | +0.042 |
CHAT | +0.041 |
Neg logit contributions | |
incial | -0.052 |
ISION | -0.051 |
netflix | -0.046 |
andom | -0.046 |
iple | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
incial | +2.123 |
ISION | +2.081 |
netflix | +1.903 |
andom | +1.887 |
iple | +1.857 |
Neg logit contributions | |
bered | -1.464 |
tons | -1.355 |
tto | -1.325 |
ean | -1.299 |
CHAT | -1.292 |
Token | radioactive |
Token ID | 25521 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
incial | +0.195 |
ISION | +0.190 |
netflix | +0.167 |
andom | +0.166 |
iple | +0.162 |
Neg logit contributions | |
bered | -0.243 |
tons | -0.230 |
tto | -0.227 |
ean | -0.224 |
CHAT | -0.221 |
Token | iodine |
Token ID | 50047 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
incial | +5.643 |
ISION | +5.455 |
andom | +4.973 |
netflix | +4.911 |
iple | +4.865 |
Neg logit contributions | |
bered | -5.559 |
tons | -5.258 |
CHAT | -5.163 |
tto | -5.152 |
odus | -5.055 |
Token | will |
Token ID | 481 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
incial | +2.851 |
ISION | +2.794 |
netflix | +2.541 |
andom | +2.540 |
iple | +2.489 |
Neg logit contributions | |
bered | -2.097 |
tons | -1.948 |
tto | -1.911 |
ean | -1.883 |
CHAT | -1.865 |
Token | only |
Token ID | 691 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
bered | +0.923 |
tons | +0.853 |
tto | +0.839 |
ean | +0.824 |
CHAT | +0.804 |
Neg logit contributions | |
incial | -1.310 |
ISION | -1.290 |
andom | -1.168 |
netflix | -1.168 |
iple | -1.141 |
Token | be |
Token ID | 307 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
bered | +0.360 |
tons | +0.335 |
tto | +0.330 |
ean | +0.325 |
CHAT | +0.319 |
Neg logit contributions | |
incial | -0.442 |
ISION | -0.434 |
netflix | -0.392 |
andom | -0.391 |
iple | -0.382 |
Token | about |
Token ID | 546 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
bered | +0.172 |
tons | +0.161 |
tto | +0.158 |
ean | +0.156 |
CHAT | +0.153 |
Neg logit contributions | |
incial | -0.201 |
ISION | -0.197 |
netflix | -0.178 |
andom | -0.177 |
iple | -0.173 |
Token | had |
Token ID | 550 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
incial | +1.714 |
ISION | +1.684 |
netflix | +1.527 |
andom | +1.526 |
iple | +1.491 |
Neg logit contributions | |
bered | -1.312 |
tons | -1.219 |
tto | -1.202 |
ean | -1.175 |
CHAT | -1.159 |
Token | been |
Token ID | 587 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
incial | +0.463 |
ISION | +0.454 |
andom | +0.408 |
netflix | +0.408 |
iple | +0.398 |
Neg logit contributions | |
bered | -0.411 |
tons | -0.384 |
tto | -0.379 |
ean | -0.371 |
CHAT | -0.369 |
Token | supers |
Token ID | 22754 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
incial | +1.230 |
ISION | +1.207 |
andom | +1.088 |
netflix | +1.088 |
iple | +1.063 |
Neg logit contributions | |
bered | -1.041 |
tons | -0.973 |
tto | -0.957 |
ean | -0.938 |
CHAT | -0.931 |
Token | eded |
Token ID | 15395 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
bered | +1.735 |
tons | +1.610 |
ean | +1.590 |
tto | +1.583 |
odus | +1.535 |
Neg logit contributions | |
incial | -1.866 |
ISION | -1.851 |
netflix | -1.656 |
andom | -1.631 |
iple | -1.610 |
Token | by |
Token ID | 416 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
bered | +0.221 |
tons | +0.203 |
tto | +0.199 |
ean | +0.195 |
CHAT | +0.191 |
Neg logit contributions | |
incial | -0.375 |
ISION | -0.369 |
netflix | -0.338 |
andom | -0.337 |
iple | -0.331 |
Token | Wi |
Token ID | 11759 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
incial | +0.199 |
ISION | +0.194 |
netflix | +0.175 |
andom | +0.174 |
iple | +0.170 |
Neg logit contributions | |
bered | -0.180 |
tons | -0.170 |
tto | -0.167 |
ean | -0.164 |
CHAT | -0.162 |
Token | - |
Token ID | 12 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
incial | +6.276 |
ISION | +6.264 |
netflix | +5.697 |
andom | +5.643 |
iple | +5.593 |
Neg logit contributions | |
bered | -5.160 |
tons | -4.684 |
tto | -4.586 |
ean | -4.485 |
odus | -4.369 |
Token | Fi |
Token ID | 10547 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
incial | +0.382 |
ISION | +0.371 |
netflix | +0.321 |
andom | +0.321 |
iple | +0.310 |
Neg logit contributions | |
bered | -0.553 |
tons | -0.526 |
tto | -0.519 |
ean | -0.513 |
CHAT | -0.508 |
Token | Prot |
Token ID | 5038 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
incial | +4.834 |
ISION | +4.767 |
andom | +4.335 |
netflix | +4.299 |
iple | +4.193 |
Neg logit contributions | |
bered | -4.250 |
tons | -3.929 |
tto | -3.877 |
ean | -3.764 |
CHAT | -3.731 |
Token | ected |
Token ID | 11197 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
bered | +0.524 |
tons | +0.499 |
tto | +0.492 |
ean | +0.489 |
CHAT | +0.482 |
Neg logit contributions | |
incial | -0.302 |
ISION | -0.294 |
netflix | -0.250 |
andom | -0.248 |
iple | -0.239 |
Token | Access |
Token ID | 8798 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
incial | +1.528 |
ISION | +1.501 |
andom | +1.345 |
netflix | +1.342 |
iple | +1.314 |
Neg logit contributions | |
bered | -1.433 |
tons | -1.341 |
tto | -1.326 |
ean | -1.297 |
CHAT | -1.285 |
Token |
|
Token ID | 198 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
incial | +0.287 |
ISION | +0.281 |
netflix | +0.254 |
andom | +0.253 |
iple | +0.247 |
Neg logit contributions | |
bered | -0.246 |
tons | -0.231 |
tto | -0.228 |
ean | -0.224 |
CHAT | -0.221 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
bered | +0.699 |
tons | +0.665 |
tto | +0.652 |
ean | +0.638 |
CHAT | +0.630 |
Neg logit contributions | |
incial | -0.987 |
ISION | -0.965 |
andom | -0.880 |
netflix | -0.878 |
iple | -0.862 |
Token | In |
Token ID | 818 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
bered | +0.334 |
tons | +0.312 |
tto | +0.306 |
ean | +0.300 |
CHAT | +0.297 |
Neg logit contributions | |
incial | -0.457 |
ISION | -0.448 |
netflix | -0.407 |
andom | -0.406 |
iple | -0.397 |
Token | 2003 |
Token ID | 5816 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
bered | +0.093 |
tons | +0.086 |
tto | +0.085 |
ean | +0.083 |
CHAT | +0.082 |
Neg logit contributions | |
incial | -0.125 |
ISION | -0.122 |
netflix | -0.111 |
andom | -0.111 |
iple | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
incial | +0.710 |
ISION | +0.697 |
netflix | +0.632 |
andom | +0.630 |
iple | +0.617 |
Neg logit contributions | |
bered | -0.535 |
tons | -0.498 |
tto | -0.489 |
ean | -0.480 |
CHAT | -0.473 |
Token | Wi |
Token ID | 11759 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
incial | +0.918 |
ISION | +0.905 |
andom | +0.811 |
netflix | +0.811 |
iple | +0.796 |
Neg logit contributions | |
bered | -0.813 |
tons | -0.758 |
tto | -0.746 |
ean | -0.735 |
CHAT | -0.726 |
Token | - |
Token ID | 12 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
incial | +6.154 |
ISION | +6.121 |
andom | +5.545 |
netflix | +5.516 |
iple | +5.482 |
Neg logit contributions | |
bered | -5.151 |
tons | -4.684 |
tto | -4.587 |
ean | -4.495 |
CHAT | -4.405 |
Token | Fi |
Token ID | 10547 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
incial | +0.372 |
ISION | +0.361 |
netflix | +0.312 |
andom | +0.310 |
iple | +0.299 |
Neg logit contributions | |
bered | -0.560 |
tons | -0.533 |
tto | -0.527 |
ean | -0.521 |
CHAT | -0.516 |
Token | Alliance |
Token ID | 10302 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
incial | +4.997 |
ISION | +4.988 |
andom | +4.550 |
netflix | +4.463 |
iple | +4.396 |
Neg logit contributions | |
bered | -3.993 |
tons | -3.629 |
tto | -3.595 |
CHAT | -3.495 |
ean | -3.489 |
Token | announced |
Token ID | 3414 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
bered | +0.128 |
tons | +0.120 |
tto | +0.118 |
ean | +0.116 |
CHAT | +0.114 |
Neg logit contributions | |
incial | -0.154 |
ISION | -0.151 |
netflix | -0.137 |
andom | -0.136 |
iple | -0.133 |
Token | that |
Token ID | 326 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
bered | +0.417 |
tons | +0.389 |
tto | +0.382 |
ean | +0.376 |
CHAT | +0.370 |
Neg logit contributions | |
incial | -0.523 |
ISION | -0.511 |
netflix | -0.462 |
andom | -0.461 |
iple | -0.450 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
incial | +0.128 |
ISION | +0.126 |
netflix | +0.114 |
andom | +0.113 |
iple | +0.111 |
Neg logit contributions | |
bered | -0.096 |
tons | -0.090 |
tto | -0.088 |
ean | -0.087 |
CHAT | -0.085 |
Token | worst |
Token ID | 5290 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
incial | +0.567 |
ISION | +0.556 |
netflix | +0.502 |
andom | +0.501 |
iple | +0.490 |
Neg logit contributions | |
bered | -0.467 |
tons | -0.436 |
tto | -0.430 |
ean | -0.422 |
CHAT | -0.416 |
Token | case |
Token ID | 1339 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
incial | +1.243 |
ISION | +1.218 |
netflix | +1.090 |
andom | +1.088 |
iple | +1.063 |
Neg logit contributions | |
bered | -1.191 |
tons | -1.117 |
tto | -1.100 |
ean | -1.082 |
CHAT | -1.073 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
bered | +0.134 |
tons | +0.124 |
tto | +0.122 |
ean | +0.119 |
CHAT | +0.117 |
Neg logit contributions | |
incial | -0.207 |
ISION | -0.204 |
netflix | -0.186 |
andom | -0.185 |
iple | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
bered | +0.353 |
tons | +0.332 |
tto | +0.327 |
ean | +0.321 |
CHAT | +0.314 |
Neg logit contributions | |
incial | -0.422 |
ISION | -0.413 |
netflix | -0.373 |
andom | -0.371 |
iple | -0.362 |
Token | radioactive |
Token ID | 25521 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
incial | +0.174 |
ISION | +0.170 |
netflix | +0.153 |
andom | +0.153 |
iple | +0.150 |
Neg logit contributions | |
bered | -0.147 |
tons | -0.137 |
tto | -0.135 |
ean | -0.133 |
CHAT | -0.131 |
Token | cloud |
Token ID | 6279 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
incial | +5.677 |
ISION | +5.610 |
netflix | +4.999 |
andom | +4.995 |
iple | +4.973 |
Neg logit contributions | |
bered | -5.389 |
tons | -5.144 |
CHAT | -5.026 |
tto | -4.956 |
cellence | -4.932 |
Token | would |
Token ID | 561 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
incial | +2.041 |
ISION | +2.007 |
netflix | +1.819 |
andom | +1.815 |
iple | +1.782 |
Neg logit contributions | |
bered | -1.518 |
tons | -1.413 |
tto | -1.384 |
ean | -1.361 |
CHAT | -1.348 |
Token | not |
Token ID | 407 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
bered | +0.676 |
tons | +0.627 |
tto | +0.620 |
ean | +0.611 |
CHAT | +0.586 |
Neg logit contributions | |
incial | -0.867 |
ISION | -0.857 |
netflix | -0.770 |
andom | -0.768 |
iple | -0.751 |
Token | go |
Token ID | 467 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
bered | +0.218 |
tons | +0.201 |
tto | +0.199 |
ean | +0.196 |
CHAT | +0.190 |
Neg logit contributions | |
incial | -0.289 |
ISION | -0.284 |
netflix | -0.256 |
andom | -0.255 |
iple | -0.250 |
Token | that |
Token ID | 326 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
incial | +0.208 |
ISION | +0.204 |
andom | +0.184 |
netflix | +0.183 |
iple | +0.180 |
Neg logit contributions | |
bered | -0.164 |
tons | -0.151 |
tto | -0.150 |
ean | -0.148 |
CHAT | -0.144 |
Token | when |
Token ID | 618 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
incial | +1.175 |
ISION | +1.156 |
netflix | +1.050 |
andom | +1.048 |
iple | +1.028 |
Neg logit contributions | |
bered | -0.841 |
tons | -0.778 |
tto | -0.764 |
ean | -0.751 |
CHAT | -0.741 |
Token | compared |
Token ID | 3688 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
incial | +1.702 |
ISION | +1.669 |
netflix | +1.506 |
andom | +1.503 |
iple | +1.470 |
Neg logit contributions | |
bered | -1.402 |
tons | -1.308 |
tto | -1.286 |
ean | -1.265 |
CHAT | -1.248 |
Token | to |
Token ID | 284 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
incial | +1.339 |
ISION | +1.320 |
netflix | +1.204 |
andom | +1.193 |
iple | +1.171 |
Neg logit contributions | |
bered | -0.907 |
tons | -0.843 |
tto | -0.822 |
ean | -0.807 |
CHAT | -0.798 |
Token | their |
Token ID | 511 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
incial | +0.690 |
ISION | +0.672 |
andom | +0.602 |
netflix | +0.601 |
iple | +0.585 |
Neg logit contributions | |
bered | -0.668 |
tons | -0.626 |
tto | -0.616 |
ean | -0.608 |
CHAT | -0.600 |
Token | low |
Token ID | 1877 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
incial | +1.118 |
ISION | +1.095 |
netflix | +0.988 |
andom | +0.987 |
iple | +0.963 |
Neg logit contributions | |
bered | -0.921 |
tons | -0.859 |
tto | -0.844 |
ean | -0.829 |
CHAT | -0.819 |
Token | viewership |
Token ID | 48347 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
incial | +2.073 |
ISION | +2.036 |
netflix | +1.831 |
andom | +1.822 |
iple | +1.786 |
Neg logit contributions | |
bered | -1.863 |
tons | -1.745 |
tto | -1.717 |
ean | -1.690 |
CHAT | -1.670 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
incial | +5.812 |
ISION | +5.780 |
netflix | +5.230 |
andom | +5.173 |
iple | +5.093 |
Neg logit contributions | |
bered | -5.231 |
tons | -4.888 |
tto | -4.839 |
ean | -4.766 |
CHAT | -4.711 |
Token | Dish |
Token ID | 33275 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
incial | +0.603 |
ISION | +0.587 |
andom | +0.529 |
netflix | +0.528 |
iple | +0.516 |
Neg logit contributions | |
bered | -0.549 |
tons | -0.517 |
tto | -0.510 |
ean | -0.501 |
CHAT | -0.496 |
Token | will |
Token ID | 481 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
incial | +3.202 |
ISION | +3.170 |
netflix | +2.852 |
andom | +2.846 |
iple | +2.793 |
Neg logit contributions | |
bered | -2.632 |
tons | -2.433 |
tto | -2.408 |
ean | -2.366 |
CHAT | -2.321 |
Token | make |
Token ID | 787 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
bered | +0.804 |
tons | +0.748 |
tto | +0.735 |
ean | +0.722 |
CHAT | +0.708 |
Neg logit contributions | |
incial | -1.081 |
ISION | -1.059 |
netflix | -0.961 |
andom | -0.958 |
iple | -0.937 |
Token | alternative |
Token ID | 5559 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
bered | +0.393 |
tons | +0.366 |
tto | +0.360 |
ean | +0.353 |
CHAT | +0.348 |
Neg logit contributions | |
incial | -0.511 |
ISION | -0.498 |
andom | -0.453 |
netflix | -0.449 |
iple | -0.439 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
incial | +0.048 |
ISION | +0.048 |
andom | +0.043 |
netflix | +0.043 |
iple | +0.042 |
Neg logit contributions | |
bered | -0.032 |
tons | -0.030 |
tto | -0.029 |
ean | -0.029 |
CHAT | -0.028 |
Token | you |
Token ID | 345 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
bered | +0.046 |
tons | +0.043 |
tto | +0.042 |
ean | +0.041 |
CHAT | +0.041 |
Neg logit contributions | |
incial | -0.057 |
ISION | -0.056 |
netflix | -0.050 |
andom | -0.050 |
iple | -0.049 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
bered | +0.695 |
tons | +0.643 |
tto | +0.631 |
ean | +0.619 |
CHAT | +0.609 |
Neg logit contributions | |
incial | -1.022 |
ISION | -1.004 |
netflix | -0.914 |
andom | -0.912 |
iple | -0.894 |
Token | notice |
Token ID | 4003 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
bered | +0.262 |
tons | +0.242 |
tto | +0.238 |
ean | +0.233 |
CHAT | +0.230 |
Neg logit contributions | |
incial | -0.383 |
ISION | -0.376 |
netflix | -0.342 |
andom | -0.342 |
iple | -0.335 |
Token | that |
Token ID | 326 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
incial | +1.192 |
ISION | +1.175 |
netflix | +1.062 |
andom | +1.060 |
iple | +1.038 |
Neg logit contributions | |
bered | -0.945 |
tons | -0.878 |
tto | -0.865 |
ean | -0.850 |
CHAT | -0.840 |
Token | Gunn |
Token ID | 40837 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
bered | +0.248 |
tons | +0.233 |
tto | +0.228 |
ean | +0.224 |
CHAT | +0.221 |
Neg logit contributions | |
incial | -0.291 |
ISION | -0.284 |
netflix | -0.256 |
andom | -0.255 |
iple | -0.250 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
incial | +5.717 |
ISION | +5.635 |
andom | +5.130 |
netflix | +5.103 |
iple | +5.027 |
Neg logit contributions | |
bered | -5.096 |
tons | -4.732 |
tto | -4.692 |
CHAT | -4.588 |
odus | -4.571 |
Token | 't |
Token ID | 470 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
bered | +0.231 |
tons | +0.216 |
tto | +0.211 |
ean | +0.207 |
CHAT | +0.202 |
Neg logit contributions | |
incial | -0.407 |
ISION | -0.401 |
netflix | -0.367 |
andom | -0.367 |
iple | -0.360 |
Token | give |
Token ID | 1577 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
bered | +0.092 |
tons | +0.086 |
tto | +0.085 |
ean | +0.083 |
CHAT | +0.082 |
Neg logit contributions | |
incial | -0.110 |
ISION | -0.108 |
netflix | -0.097 |
andom | -0.097 |
iple | -0.095 |
Token | us |
Token ID | 514 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
incial | +0.132 |
ISION | +0.130 |
netflix | +0.117 |
andom | +0.117 |
iple | +0.115 |
Neg logit contributions | |
bered | -0.101 |
tons | -0.094 |
tto | -0.092 |
ean | -0.091 |
CHAT | -0.089 |
Token | an |
Token ID | 281 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
bered | +0.374 |
tons | +0.351 |
tto | +0.344 |
ean | +0.339 |
CHAT | +0.333 |
Neg logit contributions | |
incial | -0.448 |
ISION | -0.438 |
netflix | -0.396 |
andom | -0.395 |
iple | -0.386 |
Token | seeking |
Token ID | 6095 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
incial | +0.430 |
ISION | +0.421 |
netflix | +0.377 |
andom | +0.376 |
iple | +0.367 |
Neg logit contributions | |
bered | -0.417 |
tons | -0.392 |
tto | -0.386 |
ean | -0.380 |
CHAT | -0.375 |
Token | out |
Token ID | 503 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
bered | +0.959 |
tons | +0.895 |
tto | +0.877 |
ean | +0.861 |
CHAT | +0.852 |
Neg logit contributions | |
incial | -1.299 |
ISION | -1.277 |
netflix | -1.156 |
andom | -1.154 |
iple | -1.130 |
Token | un |
Token ID | 555 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
bered | +0.503 |
tons | +0.472 |
tto | +0.463 |
ean | +0.455 |
CHAT | +0.450 |
Neg logit contributions | |
incial | -0.584 |
ISION | -0.573 |
netflix | -0.514 |
andom | -0.514 |
iple | -0.501 |
Token | author |
Token ID | 9800 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
incial | +0.512 |
ISION | +0.499 |
netflix | +0.443 |
andom | +0.442 |
iple | +0.430 |
Neg logit contributions | |
bered | -0.600 |
tons | -0.567 |
tto | -0.559 |
ean | -0.551 |
CHAT | -0.544 |
Token | ised |
Token ID | 1417 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
incial | +1.256 |
ISION | +1.219 |
andom | +1.073 |
netflix | +1.063 |
iple | +1.032 |
Neg logit contributions | |
bered | -1.754 |
tons | -1.672 |
tto | -1.659 |
ean | -1.623 |
CHAT | -1.618 |
Token | Wi |
Token ID | 11759 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
incial | +2.333 |
ISION | +2.292 |
netflix | +2.060 |
andom | +2.045 |
iple | +2.027 |
Neg logit contributions | |
bered | -2.277 |
tons | -2.132 |
tto | -2.112 |
ean | -2.095 |
CHAT | -2.050 |
Token | - |
Token ID | 12 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
incial | +6.261 |
ISION | +6.156 |
netflix | +5.669 |
andom | +5.611 |
iple | +5.498 |
Neg logit contributions | |
bered | -4.757 |
tons | -4.335 |
tto | -4.271 |
ean | -4.180 |
cellence | -4.084 |
Token | Fi |
Token ID | 10547 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
incial | +0.225 |
ISION | +0.219 |
andom | +0.187 |
netflix | +0.187 |
iple | +0.182 |
Neg logit contributions | |
bered | -0.330 |
tons | -0.316 |
tto | -0.311 |
ean | -0.308 |
CHAT | -0.306 |
Token | hots |
Token ID | 33915 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
incial | +4.169 |
ISION | +4.086 |
netflix | +3.715 |
andom | +3.679 |
iple | +3.595 |
Neg logit contributions | |
bered | -4.485 |
tons | -4.208 |
tto | -4.160 |
ean | -4.140 |
odus | -4.000 |
Token | pots |
Token ID | 40793 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
bered | +0.473 |
tons | +0.434 |
tto | +0.423 |
ean | +0.411 |
CHAT | +0.405 |
Neg logit contributions | |
incial | -0.872 |
ISION | -0.861 |
andom | -0.785 |
netflix | -0.785 |
iple | -0.771 |
Token | with |
Token ID | 351 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
incial | +1.772 |
ISION | +1.739 |
netflix | +1.586 |
andom | +1.577 |
iple | +1.545 |
Neg logit contributions | |
bered | -1.261 |
tons | -1.169 |
tto | -1.146 |
ean | -1.130 |
CHAT | -1.115 |
Token | are |
Token ID | 389 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
bered | +0.472 |
tons | +0.439 |
tto | +0.431 |
ean | +0.423 |
CHAT | +0.416 |
Neg logit contributions | |
incial | -0.604 |
ISION | -0.593 |
andom | -0.535 |
netflix | -0.534 |
iple | -0.523 |
Token | cutting |
Token ID | 7720 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
incial | +0.412 |
ISION | +0.405 |
netflix | +0.366 |
andom | +0.363 |
iple | +0.356 |
Neg logit contributions | |
bered | -0.361 |
tons | -0.339 |
tto | -0.334 |
ean | -0.329 |
CHAT | -0.324 |
Token | the |
Token ID | 262 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
incial | +1.748 |
ISION | +1.712 |
netflix | +1.532 |
andom | +1.531 |
iple | +1.493 |
Neg logit contributions | |
bered | -1.656 |
tons | -1.554 |
tto | -1.529 |
ean | -1.505 |
CHAT | -1.486 |
Token | cable |
Token ID | 7862 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
incial | +0.045 |
ISION | +0.044 |
andom | +0.039 |
netflix | +0.039 |
iple | +0.038 |
Neg logit contributions | |
bered | -0.047 |
tons | -0.045 |
tto | -0.044 |
ean | -0.043 |
CHAT | -0.043 |
Token | TV |
Token ID | 3195 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
incial | +3.989 |
ISION | +3.937 |
netflix | +3.562 |
andom | +3.486 |
iple | +3.439 |
Neg logit contributions | |
bered | -3.376 |
tons | -3.152 |
ean | -3.147 |
tto | -3.134 |
CHAT | -3.051 |
Token | cord |
Token ID | 15050 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
incial | +3.420 |
ISION | +3.382 |
netflix | +3.056 |
andom | +3.000 |
iple | +2.963 |
Neg logit contributions | |
bered | -2.925 |
tons | -2.725 |
tto | -2.716 |
ean | -2.689 |
CHAT | -2.627 |
Token | and |
Token ID | 290 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
incial | +5.965 |
ISION | +5.870 |
netflix | +5.272 |
andom | +5.179 |
iple | +5.126 |
Neg logit contributions | |
bered | -4.729 |
tons | -4.471 |
tto | -4.384 |
CHAT | -4.382 |
ean | -4.371 |
Token | switching |
Token ID | 15430 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
incial | +0.165 |
ISION | +0.162 |
netflix | +0.146 |
andom | +0.146 |
iple | +0.142 |
Neg logit contributions | |
bered | -0.139 |
tons | -0.130 |
tto | -0.128 |
ean | -0.126 |
CHAT | -0.124 |
Token | to |
Token ID | 284 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
incial | +0.650 |
ISION | +0.638 |
netflix | +0.580 |
andom | +0.579 |
iple | +0.567 |
Neg logit contributions | |
bered | -0.457 |
tons | -0.423 |
tto | -0.415 |
ean | -0.408 |
CHAT | -0.402 |
Token | streaming |
Token ID | 11305 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
incial | +0.530 |
ISION | +0.518 |
andom | +0.463 |
netflix | +0.461 |
iple | +0.451 |
Neg logit contributions | |
bered | -0.482 |
tons | -0.451 |
tto | -0.443 |
ean | -0.436 |
CHAT | -0.431 |
Token | video |
Token ID | 2008 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
incial | +0.115 |
ISION | +0.113 |
netflix | +0.103 |
andom | +0.103 |
iple | +0.101 |
Neg logit contributions | |
bered | -0.076 |
tons | -0.070 |
tto | -0.069 |
ean | -0.067 |
CHAT | -0.066 |
Token | / |
Token ID | 14 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
bered | +0.249 |
tons | +0.229 |
tto | +0.225 |
ean | +0.221 |
CHAT | +0.215 |
Neg logit contributions | |
incial | -0.408 |
ISION | -0.402 |
netflix | -0.366 |
andom | -0.364 |
iple | -0.357 |
Token | h |
Token ID | 71 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
bered | +0.225 |
tons | +0.211 |
tto | +0.207 |
ean | +0.205 |
CHAT | +0.200 |
Neg logit contributions | |
incial | -0.271 |
ISION | -0.267 |
netflix | -0.240 |
andom | -0.239 |
iple | -0.234 |
Token | ), |
Token ID | 828 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
bered | +0.508 |
tons | +0.475 |
tto | +0.467 |
ean | +0.460 |
CHAT | +0.450 |
Neg logit contributions | |
incial | -0.612 |
ISION | -0.602 |
netflix | -0.543 |
andom | -0.541 |
iple | -0.529 |
Token | according |
Token ID | 1864 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
incial | +0.571 |
ISION | +0.560 |
netflix | +0.506 |
andom | +0.506 |
iple | +0.493 |
Neg logit contributions | |
bered | -0.437 |
tons | -0.408 |
tto | -0.401 |
ean | -0.395 |
CHAT | -0.387 |
Token | to |
Token ID | 284 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
bered | +0.441 |
tons | +0.413 |
tto | +0.408 |
ean | +0.399 |
CHAT | +0.388 |
Neg logit contributions | |
incial | -0.745 |
ISION | -0.732 |
andom | -0.670 |
netflix | -0.668 |
iple | -0.656 |
Token | Cornell |
Token ID | 27119 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
incial | +0.071 |
ISION | +0.069 |
netflix | +0.062 |
andom | +0.062 |
iple | +0.060 |
Neg logit contributions | |
bered | -0.061 |
tons | -0.058 |
tto | -0.057 |
ean | -0.056 |
CHAT | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
incial | +5.852 |
ISION | +5.766 |
andom | +5.218 |
netflix | +5.066 |
iple | +5.031 |
Neg logit contributions | |
bered | -4.942 |
tto | -4.515 |
tons | -4.500 |
CHAT | -4.337 |
ean | -4.331 |
Token | We |
Token ID | 775 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
bered | +0.236 |
tons | +0.223 |
tto | +0.220 |
ean | +0.217 |
CHAT | +0.212 |
Neg logit contributions | |
incial | -0.287 |
ISION | -0.281 |
netflix | -0.255 |
andom | -0.254 |
iple | -0.249 |
Token | can |
Token ID | 460 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
bered | +0.303 |
tons | +0.282 |
tto | +0.277 |
ean | +0.272 |
CHAT | +0.266 |
Neg logit contributions | |
incial | -0.411 |
ISION | -0.404 |
netflix | -0.366 |
andom | -0.365 |
iple | -0.357 |
Token | calculate |
Token ID | 15284 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
bered | +1.195 |
tons | +1.112 |
tto | +1.096 |
ean | +1.083 |
CHAT | +1.051 |
Neg logit contributions | |
incial | -1.506 |
ISION | -1.481 |
netflix | -1.338 |
andom | -1.331 |
iple | -1.296 |
Token | that |
Token ID | 326 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
incial | +1.106 |
ISION | +1.086 |
netflix | +0.980 |
andom | +0.980 |
iple | +0.959 |
Neg logit contributions | |
bered | -0.876 |
tons | -0.814 |
tto | -0.801 |
ean | -0.784 |
CHAT | -0.779 |
Token | of |
Token ID | 286 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
incial | +0.765 |
ISION | +0.751 |
netflix | +0.682 |
andom | +0.680 |
iple | +0.666 |
Neg logit contributions | |
bered | -0.553 |
tons | -0.513 |
tto | -0.505 |
ean | -0.495 |
CHAT | -0.487 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bered | +0.167 |
tons | +0.157 |
tto | +0.154 |
ean | +0.152 |
CHAT | +0.148 |
Neg logit contributions | |
incial | -0.199 |
ISION | -0.195 |
netflix | -0.176 |
andom | -0.176 |
iple | -0.171 |
Token | pools |
Token ID | 20354 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
bered | +0.318 |
tons | +0.300 |
tto | +0.295 |
ean | +0.290 |
CHAT | +0.285 |
Neg logit contributions | |
incial | -0.340 |
ISION | -0.332 |
netflix | -0.299 |
andom | -0.297 |
iple | -0.289 |
Token | containing |
Token ID | 7268 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
bered | +0.115 |
tons | +0.106 |
tto | +0.104 |
ean | +0.102 |
CHAT | +0.100 |
Neg logit contributions | |
incial | -0.159 |
ISION | -0.156 |
netflix | -0.142 |
andom | -0.142 |
iple | -0.139 |
Token | highly |
Token ID | 4047 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
bered | +0.224 |
tons | +0.212 |
tto | +0.210 |
ean | +0.206 |
CHAT | +0.202 |
Neg logit contributions | |
incial | -0.211 |
ISION | -0.207 |
netflix | -0.184 |
andom | -0.183 |
iple | -0.178 |
Token | radioactive |
Token ID | 25521 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
incial | +0.216 |
ISION | +0.211 |
netflix | +0.185 |
andom | +0.184 |
iple | +0.178 |
Neg logit contributions | |
bered | -0.282 |
tons | -0.267 |
tto | -0.263 |
ean | -0.260 |
CHAT | -0.257 |
Token | spent |
Token ID | 3377 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
incial | +5.157 |
ISION | +4.986 |
andom | +4.516 |
netflix | +4.514 |
iple | +4.446 |
Neg logit contributions | |
bered | -5.171 |
tons | -4.825 |
CHAT | -4.752 |
tto | -4.733 |
cellence | -4.708 |
Token | fuel |
Token ID | 5252 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
incial | +1.775 |
ISION | +1.719 |
andom | +1.483 |
netflix | +1.477 |
iple | +1.425 |
Neg logit contributions | |
bered | -2.990 |
tons | -2.845 |
tto | -2.815 |
ean | -2.783 |
CHAT | -2.766 |
Token | rods |
Token ID | 32858 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
incial | +0.954 |
ISION | +0.936 |
netflix | +0.848 |
andom | +0.846 |
iple | +0.828 |
Neg logit contributions | |
bered | -0.731 |
tons | -0.680 |
tto | -0.668 |
ean | -0.657 |
CHAT | -0.648 |
Token | at |
Token ID | 379 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
incial | +4.076 |
ISION | +3.976 |
netflix | +3.625 |
andom | +3.595 |
iple | +3.518 |
Neg logit contributions | |
bered | -3.235 |
tons | -3.014 |
tto | -2.947 |
CHAT | -2.944 |
ean | -2.928 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
incial | +0.360 |
ISION | +0.352 |
netflix | +0.316 |
andom | +0.315 |
iple | +0.308 |
Neg logit contributions | |
bered | -0.335 |
tons | -0.314 |
tto | -0.309 |
ean | -0.304 |
CHAT | -0.300 |
Token | P |
Token ID | 47 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
incial | +0.447 |
ISION | +0.438 |
netflix | +0.398 |
andom | +0.397 |
iple | +0.389 |
Neg logit contributions | |
bered | -0.331 |
tons | -0.309 |
tto | -0.303 |
ean | -0.298 |
CHAT | -0.294 |
Token | was |
Token ID | 373 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
bered | +1.018 |
tons | +0.950 |
tto | +0.932 |
ean | +0.922 |
CHAT | +0.905 |
Neg logit contributions | |
incial | -1.317 |
ISION | -1.288 |
netflix | -1.173 |
andom | -1.155 |
iple | -1.137 |
Token | ratified |
Token ID | 39067 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
incial | +0.199 |
ISION | +0.195 |
netflix | +0.177 |
andom | +0.176 |
iple | +0.172 |
Neg logit contributions | |
bered | -0.160 |
tons | -0.150 |
tto | -0.147 |
ean | -0.145 |
CHAT | -0.142 |
Token | as |
Token ID | 355 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
bered | +0.486 |
tons | +0.447 |
tto | +0.439 |
ean | +0.430 |
CHAT | +0.422 |
Neg logit contributions | |
incial | -0.775 |
ISION | -0.762 |
netflix | -0.695 |
andom | -0.694 |
iple | -0.682 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
incial | +0.619 |
ISION | +0.605 |
netflix | +0.546 |
andom | +0.544 |
iple | +0.531 |
Neg logit contributions | |
bered | -0.529 |
tons | -0.497 |
tto | -0.488 |
ean | -0.481 |
CHAT | -0.474 |
Token | Wi |
Token ID | 11759 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
incial | +0.217 |
ISION | +0.212 |
netflix | +0.192 |
andom | +0.192 |
iple | +0.188 |
Neg logit contributions | |
bered | -0.174 |
tons | -0.162 |
tto | -0.159 |
ean | -0.157 |
CHAT | -0.155 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
incial | +5.991 |
ISION | +5.919 |
andom | +5.366 |
netflix | +5.353 |
iple | +5.281 |
Neg logit contributions | |
bered | -4.551 |
tons | -4.128 |
tto | -4.083 |
ean | -3.960 |
cellence | -3.912 |
Token | Fi |
Token ID | 10547 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
incial | +0.258 |
ISION | +0.250 |
andom | +0.216 |
netflix | +0.215 |
iple | +0.209 |
Neg logit contributions | |
bered | -0.374 |
tons | -0.359 |
tto | -0.353 |
ean | -0.351 |
CHAT | -0.348 |
Token | security |
Token ID | 2324 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
incial | +4.766 |
ISION | +4.731 |
andom | +4.327 |
netflix | +4.243 |
iple | +4.188 |
Neg logit contributions | |
bered | -3.644 |
tto | -3.337 |
tons | -3.330 |
ean | -3.214 |
CHAT | -3.159 |
Token | standard |
Token ID | 3210 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
bered | +0.810 |
tons | +0.754 |
tto | +0.738 |
ean | +0.728 |
CHAT | +0.717 |
Neg logit contributions | |
incial | -1.139 |
ISION | -1.114 |
netflix | -1.016 |
andom | -1.008 |
iple | -0.991 |
Token | in |
Token ID | 287 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
incial | +0.428 |
ISION | +0.420 |
netflix | +0.384 |
andom | +0.383 |
iple | +0.375 |
Neg logit contributions | |
bered | -0.273 |
tons | -0.252 |
tto | -0.247 |
ean | -0.243 |
CHAT | -0.239 |
Token | " |
Token ID | 1 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
bered | +0.075 |
tons | +0.069 |
tto | +0.067 |
ean | +0.066 |
CHAT | +0.064 |
Neg logit contributions | |
incial | -0.100 |
ISION | -0.099 |
netflix | -0.089 |
andom | -0.089 |
iple | -0.086 |
Token | If |
Token ID | 1532 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
incial | +1.732 |
ISION | +1.719 |
netflix | +1.533 |
andom | +1.530 |
iple | +1.491 |
Neg logit contributions | |
bered | -1.502 |
tons | -1.355 |
tto | -1.334 |
ean | -1.315 |
CHAT | -1.292 |
Token | you |
Token ID | 345 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
bered | +0.587 |
tons | +0.548 |
tto | +0.539 |
ean | +0.530 |
CHAT | +0.522 |
Neg logit contributions | |
incial | -0.714 |
ISION | -0.700 |
netflix | -0.632 |
andom | -0.630 |
iple | -0.617 |
Token | look |
Token ID | 804 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
bered | +0.076 |
tons | +0.070 |
tto | +0.069 |
ean | +0.068 |
CHAT | +0.067 |
Neg logit contributions | |
incial | -0.095 |
ISION | -0.093 |
netflix | -0.084 |
andom | -0.084 |
iple | -0.082 |
Token | at |
Token ID | 379 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
incial | +0.278 |
ISION | +0.273 |
netflix | +0.247 |
andom | +0.246 |
iple | +0.242 |
Neg logit contributions | |
bered | -0.209 |
tons | -0.195 |
tto | -0.191 |
ean | -0.188 |
CHAT | -0.186 |
Token | Assy |
Token ID | 39881 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
bered | +0.040 |
tons | +0.037 |
tto | +0.037 |
ean | +0.036 |
CHAT | +0.036 |
Neg logit contributions | |
incial | -0.051 |
ISION | -0.050 |
netflix | -0.045 |
andom | -0.045 |
iple | -0.044 |
Token | rian |
Token ID | 4484 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
bered | +2.141 |
tons | +1.846 |
ean | +1.823 |
tto | +1.795 |
odus | +1.653 |
Neg logit contributions | |
incial | -7.410 |
ISION | -7.380 |
netflix | -6.819 |
andom | -6.753 |
iple | -6.735 |
Token | culture |
Token ID | 3968 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
bered | +1.511 |
tons | +1.382 |
tto | +1.354 |
ean | +1.334 |
CHAT | +1.281 |
Neg logit contributions | |
incial | -2.654 |
ISION | -2.616 |
netflix | -2.407 |
andom | -2.378 |
iple | -2.340 |
Token | or |
Token ID | 393 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
incial | +0.933 |
ISION | +0.914 |
netflix | +0.831 |
andom | +0.829 |
iple | +0.812 |
Neg logit contributions | |
bered | -0.691 |
tons | -0.642 |
tto | -0.631 |
ean | -0.618 |
CHAT | -0.616 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
incial | +1.026 |
ISION | +1.006 |
netflix | +0.912 |
andom | +0.912 |
iple | +0.894 |
Neg logit contributions | |
bered | -0.765 |
tons | -0.708 |
tto | -0.694 |
CHAT | -0.682 |
ean | -0.679 |
Token | Egyptians |
Token ID | 32658 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
incial | +0.038 |
ISION | +0.037 |
netflix | +0.034 |
andom | +0.034 |
iple | +0.033 |
Neg logit contributions | |
bered | -0.026 |
tons | -0.024 |
tto | -0.023 |
ean | -0.023 |
CHAT | -0.023 |
Token | Stevens |
Token ID | 20019 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
bered | +1.954 |
tons | +1.848 |
tto | +1.814 |
ean | +1.789 |
CHAT | +1.738 |
Neg logit contributions | |
incial | -2.341 |
ISION | -2.299 |
netflix | -2.082 |
andom | -2.053 |
iple | -2.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
bered | +1.651 |
tons | +1.542 |
tto | +1.505 |
ean | +1.477 |
CHAT | +1.439 |
Neg logit contributions | |
incial | -2.554 |
ISION | -2.517 |
netflix | -2.305 |
andom | -2.274 |
iple | -2.233 |
Token | who |
Token ID | 508 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
incial | +0.217 |
ISION | +0.214 |
netflix | +0.194 |
andom | +0.193 |
iple | +0.190 |
Neg logit contributions | |
bered | -0.157 |
tons | -0.146 |
tto | -0.143 |
ean | -0.140 |
CHAT | -0.138 |
Token | represented |
Token ID | 7997 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
bered | +0.367 |
tons | +0.340 |
tto | +0.333 |
ean | +0.328 |
CHAT | +0.322 |
Neg logit contributions | |
incial | -0.520 |
ISION | -0.511 |
netflix | -0.464 |
andom | -0.463 |
iple | -0.454 |
Token | the |
Token ID | 262 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
bered | +0.419 |
tons | +0.391 |
tto | +0.385 |
ean | +0.379 |
CHAT | +0.374 |
Neg logit contributions | |
incial | -0.492 |
ISION | -0.482 |
netflix | -0.435 |
andom | -0.434 |
iple | -0.424 |
Token | mining |
Token ID | 9691 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
bered | +0.106 |
tons | +0.100 |
tto | +0.098 |
ean | +0.096 |
CHAT | +0.095 |
Neg logit contributions | |
incial | -0.119 |
ISION | -0.117 |
netflix | -0.105 |
andom | -0.105 |
iple | -0.102 |
Token | area |
Token ID | 1989 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
bered | +3.630 |
tons | +3.374 |
ean | +3.254 |
tto | +3.233 |
CHAT | +3.088 |
Neg logit contributions | |
incial | -4.672 |
ISION | -4.651 |
netflix | -4.224 |
andom | -4.151 |
iple | -4.106 |
Token | from |
Token ID | 422 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bered | +0.563 |
tons | +0.519 |
tto | +0.510 |
ean | +0.501 |
CHAT | +0.490 |
Neg logit contributions | |
incial | -0.831 |
ISION | -0.818 |
netflix | -0.743 |
andom | -0.743 |
iple | -0.728 |
Token | which |
Token ID | 543 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
bered | +1.511 |
tons | +1.403 |
tto | +1.386 |
ean | +1.365 |
CHAT | +1.332 |
Neg logit contributions | |
incial | -1.853 |
ISION | -1.814 |
netflix | -1.647 |
andom | -1.640 |
iple | -1.608 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
incial | +1.070 |
ISION | +1.049 |
andom | +0.941 |
netflix | +0.939 |
iple | +0.920 |
Neg logit contributions | |
bered | -0.973 |
tons | -0.907 |
tto | -0.894 |
ean | -0.881 |
CHAT | -0.874 |
Token | arton |
Token ID | 41328 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
incial | +0.706 |
ISION | +0.686 |
netflix | +0.569 |
andom | +0.565 |
iple | +0.542 |
Neg logit contributions | |
bered | -1.494 |
tons | -1.429 |
tto | -1.413 |
ean | -1.399 |
CHAT | -1.385 |
Token | For |
Token ID | 1114 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
incial | +0.252 |
ISION | +0.248 |
netflix | +0.223 |
andom | +0.222 |
iple | +0.218 |
Neg logit contributions | |
bered | -0.216 |
tons | -0.202 |
tto | -0.199 |
ean | -0.196 |
CHAT | -0.193 |
Token | the |
Token ID | 262 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
bered | +0.566 |
tons | +0.525 |
tto | +0.515 |
ean | +0.505 |
CHAT | +0.496 |
Neg logit contributions | |
incial | -0.821 |
ISION | -0.806 |
netflix | -0.733 |
andom | -0.732 |
iple | -0.717 |
Token | sake |
Token ID | 11060 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
incial | +0.125 |
ISION | +0.123 |
netflix | +0.110 |
andom | +0.110 |
iple | +0.107 |
Neg logit contributions | |
bered | -0.117 |
tons | -0.110 |
tto | -0.108 |
ean | -0.106 |
CHAT | -0.105 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bered | +0.437 |
tons | +0.404 |
tto | +0.395 |
ean | +0.389 |
CHAT | +0.379 |
Neg logit contributions | |
incial | -0.755 |
ISION | -0.741 |
netflix | -0.678 |
andom | -0.675 |
iple | -0.662 |
Token | comple |
Token ID | 1224 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
incial | +0.269 |
ISION | +0.264 |
netflix | +0.239 |
andom | +0.238 |
iple | +0.233 |
Neg logit contributions | |
bered | -0.207 |
tons | -0.193 |
tto | -0.189 |
ean | -0.186 |
CHAT | -0.183 |
Token | teness |
Token ID | 43205 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
bered | +2.353 |
tons | +2.184 |
tto | +2.167 |
ean | +2.107 |
CHAT | +2.033 |
Neg logit contributions | |
incial | -3.669 |
ISION | -3.610 |
netflix | -3.317 |
andom | -3.270 |
iple | -3.216 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
bered | +3.231 |
tons | +3.049 |
tto | +2.970 |
ean | +2.940 |
ness | +2.851 |
Neg logit contributions | |
incial | -5.061 |
ISION | -4.915 |
netflix | -4.521 |
andom | -4.472 |
iple | -4.356 |
Token | here |
Token ID | 994 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
bered | +0.438 |
tons | +0.411 |
tto | +0.403 |
ean | +0.397 |
CHAT | +0.391 |
Neg logit contributions | |
incial | -0.527 |
ISION | -0.516 |
netflix | -0.465 |
andom | -0.464 |
iple | -0.454 |
Token | is |
Token ID | 318 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
bered | +0.282 |
tons | +0.265 |
tto | +0.261 |
ean | +0.256 |
CHAT | +0.250 |
Neg logit contributions | |
incial | -0.355 |
ISION | -0.349 |
netflix | -0.316 |
andom | -0.314 |
iple | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
bered | +0.315 |
tons | +0.295 |
tto | +0.290 |
ean | +0.286 |
CHAT | +0.281 |
Neg logit contributions | |
incial | -0.378 |
ISION | -0.371 |
netflix | -0.334 |
andom | -0.334 |
iple | -0.326 |
Token | real |
Token ID | 1103 |
Feature activation | +4.76e-03 |
Pos logit contributions | |
incial | +0.019 |
ISION | +0.019 |
netflix | +0.017 |
andom | +0.017 |
iple | +0.017 |
Neg logit contributions | |
bered | -0.014 |
tons | -0.013 |
tto | -0.013 |
ean | -0.013 |
CHAT | -0.013 |
Token | tools |
Token ID | 4899 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
incial | +0.434 |
ISION | +0.427 |
netflix | +0.392 |
andom | +0.391 |
iple | +0.384 |
Neg logit contributions | |
bered | -0.244 |
tons | -0.224 |
tto | -0.219 |
ean | -0.214 |
CHAT | -0.210 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
bered | +1.230 |
tons | +1.149 |
tto | +1.118 |
ean | +1.101 |
CHAT | +1.070 |
Neg logit contributions | |
incial | -1.904 |
ISION | -1.867 |
andom | -1.701 |
netflix | -1.699 |
iple | -1.660 |
Token | shop |
Token ID | 6128 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
bered | +0.696 |
tons | +0.648 |
tto | +0.632 |
ean | +0.623 |
CHAT | +0.613 |
Neg logit contributions | |
incial | -1.030 |
ISION | -1.012 |
netflix | -0.920 |
andom | -0.919 |
iple | -0.899 |
Token | my |
Token ID | 616 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
bered | +1.000 |
tons | +0.929 |
tto | +0.911 |
ean | +0.893 |
CHAT | +0.878 |
Neg logit contributions | |
incial | -1.415 |
ISION | -1.392 |
andom | -1.263 |
netflix | -1.259 |
iple | -1.234 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
bered | +0.840 |
tons | +0.779 |
tto | +0.766 |
ean | +0.753 |
CHAT | +0.741 |
Neg logit contributions | |
incial | -1.091 |
ISION | -1.070 |
andom | -0.969 |
netflix | -0.968 |
iple | -0.946 |
Token | essentials |
Token ID | 41954 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
bered | +0.855 |
tons | +0.797 |
tto | +0.780 |
ean | +0.760 |
CHAT | +0.745 |
Neg logit contributions | |
incial | -1.248 |
ISION | -1.225 |
andom | -1.113 |
netflix | -1.108 |
iple | -1.090 |
Token | ! |
Token ID | 0 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
bered | +3.108 |
tons | +2.909 |
tto | +2.810 |
ean | +2.781 |
ber | +2.703 |
Neg logit contributions | |
incial | -4.061 |
ISION | -3.943 |
andom | -3.593 |
netflix | -3.565 |
iple | -3.523 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
bered | +0.605 |
tons | +0.568 |
tto | +0.559 |
ean | +0.549 |
CHAT | +0.540 |
Neg logit contributions | |
incial | -0.727 |
ISION | -0.712 |
andom | -0.642 |
netflix | -0.642 |
iple | -0.628 |
Token | Posted |
Token ID | 14231 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
bered | +2.305 |
tons | +2.182 |
tto | +2.129 |
CHAT | +2.096 |
ean | +2.090 |
Neg logit contributions | |
incial | -3.009 |
ISION | -2.934 |
andom | -2.663 |
netflix | -2.639 |
iple | -2.602 |
Token | on |
Token ID | 319 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
incial | +1.499 |
ISION | +1.471 |
netflix | +1.334 |
andom | +1.330 |
iple | +1.303 |
Neg logit contributions | |
bered | -1.125 |
tons | -1.045 |
tto | -1.019 |
ean | -1.005 |
CHAT | -0.993 |
Token | by |
Token ID | 416 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bered | +0.149 |
tons | +0.138 |
tto | +0.136 |
ean | +0.133 |
CHAT | +0.131 |
Neg logit contributions | |
incial | -0.215 |
ISION | -0.211 |
netflix | -0.192 |
andom | -0.191 |
iple | -0.187 |
Token | box |
Token ID | 3091 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
incial | +1.134 |
ISION | +1.120 |
netflix | +1.035 |
andom | +1.033 |
iple | +1.017 |
Neg logit contributions | |
bered | -0.503 |
tons | -0.449 |
tto | -0.436 |
ean | -0.426 |
CHAT | -0.420 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
bered | +0.730 |
tons | +0.675 |
tto | +0.663 |
ean | +0.650 |
CHAT | +0.640 |
Neg logit contributions | |
incial | -1.086 |
ISION | -1.067 |
netflix | -0.972 |
andom | -0.970 |
iple | -0.951 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
bered | +0.023 |
tons | +0.022 |
tto | +0.021 |
ean | +0.021 |
CHAT | +0.021 |
Neg logit contributions | |
incial | -0.030 |
ISION | -0.030 |
netflix | -0.027 |
andom | -0.027 |
iple | -0.026 |
Token | now |
Token ID | 783 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
incial | +0.207 |
ISION | +0.204 |
netflix | +0.185 |
andom | +0.185 |
iple | +0.181 |
Neg logit contributions | |
bered | -0.153 |
tons | -0.142 |
tto | -0.140 |
ean | -0.137 |
CHAT | -0.136 |
Token | global |
Token ID | 3298 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
bered | +0.389 |
tons | +0.362 |
tto | +0.356 |
ean | +0.350 |
CHAT | +0.345 |
Neg logit contributions | |
incial | -0.486 |
ISION | -0.477 |
netflix | -0.431 |
andom | -0.430 |
iple | -0.421 |
Token | fragmentation |
Token ID | 42965 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
bered | +0.904 |
tons | +0.844 |
tto | +0.822 |
ean | +0.811 |
CHAT | +0.799 |
Neg logit contributions | |
incial | -1.095 |
ISION | -1.070 |
netflix | -0.968 |
andom | -0.960 |
iple | -0.946 |
Token | leading |
Token ID | 3756 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
bered | +3.219 |
tons | +2.980 |
tto | +2.948 |
ean | +2.824 |
ness | +2.783 |
Neg logit contributions | |
incial | -4.136 |
ISION | -4.021 |
netflix | -3.666 |
andom | -3.643 |
iple | -3.537 |
Token | to |
Token ID | 284 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
bered | +0.450 |
tons | +0.417 |
tto | +0.409 |
ean | +0.401 |
CHAT | +0.398 |
Neg logit contributions | |
incial | -0.634 |
ISION | -0.622 |
netflix | -0.566 |
andom | -0.565 |
iple | -0.552 |
Token | annihilation |
Token ID | 49972 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
incial | +0.171 |
ISION | +0.168 |
netflix | +0.151 |
andom | +0.151 |
iple | +0.148 |
Neg logit contributions | |
bered | -0.147 |
tons | -0.137 |
tto | -0.135 |
ean | -0.133 |
CHAT | -0.131 |
Token | of |
Token ID | 286 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
bered | +0.243 |
tons | +0.226 |
tto | +0.222 |
ean | +0.218 |
CHAT | +0.215 |
Neg logit contributions | |
incial | -0.342 |
ISION | -0.336 |
netflix | -0.306 |
andom | -0.305 |
iple | -0.299 |
Token | life |
Token ID | 1204 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
incial | +0.056 |
ISION | +0.055 |
netflix | +0.050 |
andom | +0.050 |
iple | +0.049 |
Neg logit contributions | |
bered | -0.048 |
tons | -0.045 |
tto | -0.044 |
ean | -0.043 |
CHAT | -0.043 |
Token | rated |
Token ID | 4111 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
incial | +0.198 |
ISION | +0.195 |
andom | +0.180 |
netflix | +0.178 |
iple | +0.176 |
Neg logit contributions | |
bered | -0.119 |
tons | -0.109 |
tto | -0.107 |
ean | -0.105 |
CHAT | -0.102 |
Token | movies |
Token ID | 6918 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
incial | +1.613 |
ISION | +1.586 |
netflix | +1.446 |
andom | +1.444 |
iple | +1.412 |
Neg logit contributions | |
bered | -1.178 |
tons | -1.096 |
tto | -1.074 |
ean | -1.055 |
CHAT | -1.048 |
Token | and |
Token ID | 290 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
incial | +0.820 |
ISION | +0.807 |
netflix | +0.733 |
andom | +0.733 |
iple | +0.719 |
Neg logit contributions | |
bered | -0.551 |
tons | -0.509 |
tto | -0.500 |
ean | -0.491 |
CHAT | -0.482 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
incial | +0.067 |
ISION | +0.066 |
netflix | +0.060 |
andom | +0.059 |
iple | +0.058 |
Neg logit contributions | |
bered | -0.055 |
tons | -0.051 |
tto | -0.051 |
ean | -0.050 |
CHAT | -0.049 |
Token | like |
Token ID | 588 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
bered | +0.229 |
tons | +0.213 |
tto | +0.210 |
ean | +0.206 |
CHAT | +0.203 |
Neg logit contributions | |
incial | -0.295 |
ISION | -0.290 |
netflix | -0.262 |
andom | -0.262 |
iple | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
bered | +0.177 |
tons | +0.163 |
tto | +0.161 |
ean | +0.158 |
CHAT | +0.154 |
Neg logit contributions | |
incial | -0.255 |
ISION | -0.250 |
netflix | -0.227 |
andom | -0.227 |
iple | -0.223 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
bered | +0.069 |
tons | +0.064 |
tto | +0.063 |
ean | +0.062 |
CHAT | +0.061 |
Neg logit contributions | |
incial | -0.095 |
ISION | -0.094 |
netflix | -0.085 |
andom | -0.085 |
iple | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
incial | +0.359 |
ISION | +0.353 |
netflix | +0.320 |
andom | +0.320 |
iple | +0.312 |
Neg logit contributions | |
bered | -0.276 |
tons | -0.258 |
tto | -0.253 |
ean | -0.248 |
CHAT | -0.246 |
Token | continue |
Token ID | 2555 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
incial | +0.306 |
ISION | +0.301 |
netflix | +0.272 |
andom | +0.271 |
iple | +0.265 |
Neg logit contributions | |
bered | -0.241 |
tons | -0.225 |
tto | -0.221 |
ean | -0.217 |
CHAT | -0.214 |
Token | paying |
Token ID | 5989 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
bered | +0.362 |
tons | +0.337 |
tto | +0.332 |
ean | +0.326 |
CHAT | +0.320 |
Neg logit contributions | |
incial | -0.463 |
ISION | -0.454 |
netflix | -0.411 |
andom | -0.410 |
iple | -0.402 |
Token | my |
Token ID | 616 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
bered | +0.979 |
tons | +0.913 |
tto | +0.897 |
ean | +0.884 |
CHAT | +0.866 |
Neg logit contributions | |
incial | -1.224 |
ISION | -1.201 |
netflix | -1.086 |
andom | -1.080 |
iple | -1.059 |
Token | ) |
Token ID | 8 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
bered | +0.319 |
tons | +0.296 |
tto | +0.291 |
ean | +0.286 |
CHAT | +0.282 |
Neg logit contributions | |
incial | -0.423 |
ISION | -0.416 |
netflix | -0.377 |
andom | -0.376 |
iple | -0.368 |
Token | on |
Token ID | 319 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
incial | +1.243 |
ISION | +1.221 |
netflix | +1.120 |
andom | +1.116 |
iple | +1.097 |
Neg logit contributions | |
bered | -0.737 |
tons | -0.674 |
tto | -0.660 |
ean | -0.646 |
CHAT | -0.638 |
Token | Jan |
Token ID | 2365 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
incial | +0.203 |
ISION | +0.199 |
netflix | +0.179 |
andom | +0.179 |
iple | +0.175 |
Neg logit contributions | |
bered | -0.173 |
tons | -0.162 |
tto | -0.159 |
ean | -0.157 |
CHAT | -0.154 |
Token | 16 |
Token ID | 1467 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
incial | +0.659 |
ISION | +0.646 |
netflix | +0.577 |
andom | +0.575 |
iple | +0.561 |
Neg logit contributions | |
bered | -0.654 |
tons | -0.613 |
tto | -0.604 |
ean | -0.595 |
CHAT | -0.588 |
Token | , |
Token ID | 11 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
incial | +1.362 |
ISION | +1.339 |
netflix | +1.216 |
andom | +1.212 |
iple | +1.187 |
Neg logit contributions | |
bered | -0.977 |
tons | -0.900 |
tto | -0.884 |
ean | -0.869 |
CHAT | -0.858 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
bered | +0.062 |
tons | +0.057 |
tto | +0.056 |
ean | +0.055 |
CHAT | +0.054 |
Neg logit contributions | |
incial | -0.097 |
ISION | -0.096 |
netflix | -0.087 |
andom | -0.087 |
iple | -0.085 |
Token | at |
Token ID | 379 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
bered | +0.227 |
tons | +0.211 |
tto | +0.208 |
ean | +0.204 |
CHAT | +0.198 |
Neg logit contributions | |
incial | -0.326 |
ISION | -0.321 |
netflix | -0.290 |
andom | -0.290 |
iple | -0.284 |
Token | 9 |
Token ID | 860 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
incial | +0.365 |
ISION | +0.357 |
netflix | +0.320 |
andom | +0.319 |
iple | +0.311 |
Neg logit contributions | |
bered | -0.352 |
tons | -0.331 |
tto | -0.326 |
ean | -0.321 |
CHAT | -0.316 |
Token | : |
Token ID | 25 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
incial | +0.014 |
ISION | +0.014 |
netflix | +0.012 |
andom | +0.012 |
iple | +0.012 |
Neg logit contributions | |
bered | -0.009 |
tons | -0.009 |
tto | -0.009 |
ean | -0.008 |
CHAT | -0.008 |
Token | 28 |
Token ID | 2078 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
bered | +0.275 |
tons | +0.253 |
tto | +0.248 |
ean | +0.243 |
CHAT | +0.239 |
Neg logit contributions | |
incial | -0.454 |
ISION | -0.447 |
netflix | -0.408 |
andom | -0.408 |
iple | -0.400 |
Token | am |
Token ID | 321 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
bered | +1.690 |
tons | +1.585 |
tto | +1.560 |
ean | +1.530 |
CHAT | +1.501 |
Neg logit contributions | |
incial | -2.010 |
ISION | -1.982 |
netflix | -1.774 |
andom | -1.770 |
iple | -1.732 |
Token | man |
Token ID | 805 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
bered | +0.390 |
tons | +0.361 |
tto | +0.354 |
ean | +0.347 |
CHAT | +0.342 |
Neg logit contributions | |
incial | -0.572 |
ISION | -0.562 |
netflix | -0.512 |
andom | -0.511 |
iple | -0.501 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
bered | +1.688 |
tons | +1.574 |
tto | +1.543 |
ean | +1.515 |
CHAT | +1.477 |
Neg logit contributions | |
incial | -2.583 |
ISION | -2.543 |
netflix | -2.328 |
andom | -2.300 |
iple | -2.261 |
Token | ed |
Token ID | 1225 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
bered | +0.437 |
tons | +0.408 |
tto | +0.401 |
ean | +0.395 |
CHAT | +0.389 |
Neg logit contributions | |
incial | -0.537 |
ISION | -0.527 |
netflix | -0.476 |
andom | -0.475 |
iple | -0.464 |
Token | s |
Token ID | 82 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
incial | +1.011 |
ISION | +0.991 |
netflix | +0.897 |
andom | +0.895 |
iple | +0.880 |
Neg logit contributions | |
bered | -0.719 |
tons | -0.664 |
tto | -0.653 |
ean | -0.637 |
CHAT | -0.635 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
bered | +0.892 |
tons | +0.834 |
tto | +0.821 |
ean | +0.808 |
CHAT | +0.795 |
Neg logit contributions | |
incial | -1.041 |
ISION | -1.021 |
netflix | -0.921 |
andom | -0.918 |
iple | -0.897 |
Token | Outside |
Token ID | 22151 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
bered | +0.306 |
tons | +0.286 |
tto | +0.281 |
ean | +0.277 |
CHAT | +0.273 |
Neg logit contributions | |
incial | -0.361 |
ISION | -0.354 |
netflix | -0.319 |
andom | -0.318 |
iple | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
bered | +1.740 |
tons | +1.630 |
tto | +1.600 |
ean | +1.588 |
CHAT | +1.552 |
Neg logit contributions | |
incial | -2.104 |
ISION | -2.073 |
netflix | -1.893 |
andom | -1.854 |
iple | -1.822 |
Token | Bible |
Token ID | 9111 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
bered | +0.590 |
tons | +0.551 |
tto | +0.540 |
ean | +0.532 |
CHAT | +0.524 |
Neg logit contributions | |
incial | -0.741 |
ISION | -0.727 |
netflix | -0.660 |
andom | -0.656 |
iple | -0.641 |
Token | : |
Token ID | 25 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
incial | +0.929 |
ISION | +0.909 |
andom | +0.827 |
netflix | +0.824 |
iple | +0.809 |
Neg logit contributions | |
bered | -0.677 |
tons | -0.626 |
tto | -0.615 |
ean | -0.603 |
CHAT | -0.596 |
Token | Ancient |
Token ID | 13406 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
bered | +0.905 |
tons | +0.851 |
tto | +0.836 |
ean | +0.825 |
CHAT | +0.813 |
Neg logit contributions | |
incial | -1.073 |
ISION | -1.051 |
netflix | -0.956 |
andom | -0.947 |
iple | -0.927 |
Token | Jewish |
Token ID | 5582 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
bered | +1.457 |
tons | +1.373 |
tto | +1.339 |
ean | +1.330 |
CHAT | +1.294 |
Neg logit contributions | |
incial | -1.975 |
ISION | -1.946 |
netflix | -1.785 |
andom | -1.753 |
iple | -1.718 |
Token | know |
Token ID | 760 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
bered | +0.498 |
tons | +0.454 |
tto | +0.449 |
ean | +0.439 |
CHAT | +0.427 |
Neg logit contributions | |
incial | -0.786 |
ISION | -0.777 |
netflix | -0.710 |
andom | -0.706 |
iple | -0.690 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
bered | +0.479 |
tons | +0.443 |
tto | +0.435 |
ean | +0.428 |
CHAT | +0.414 |
Neg logit contributions | |
incial | -0.711 |
ISION | -0.698 |
netflix | -0.639 |
andom | -0.636 |
iple | -0.623 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bered | +0.273 |
tons | +0.261 |
tto | +0.257 |
ean | +0.253 |
CHAT | +0.246 |
Neg logit contributions | |
incial | -0.323 |
ISION | -0.316 |
netflix | -0.285 |
andom | -0.285 |
iple | -0.279 |
Token | like |
Token ID | 588 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
bered | +2.002 |
tons | +1.914 |
tto | +1.841 |
ean | +1.825 |
CHAT | +1.752 |
Neg logit contributions | |
incial | -2.591 |
ISION | -2.532 |
netflix | -2.315 |
andom | -2.289 |
iple | -2.254 |
Token | looking |
Token ID | 2045 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
bered | +0.246 |
tons | +0.232 |
tto | +0.226 |
ean | +0.222 |
CHAT | +0.216 |
Neg logit contributions | |
incial | -0.321 |
ISION | -0.314 |
netflix | -0.284 |
andom | -0.283 |
iple | -0.278 |
Token | at |
Token ID | 379 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
bered | +0.597 |
tons | +0.555 |
tto | +0.546 |
ean | +0.535 |
CHAT | +0.518 |
Neg logit contributions | |
incial | -0.757 |
ISION | -0.743 |
andom | -0.673 |
netflix | -0.672 |
iple | -0.657 |
Token | someone |
Token ID | 2130 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
bered | +0.377 |
tons | +0.354 |
tto | +0.346 |
ean | +0.342 |
CHAT | +0.333 |
Neg logit contributions | |
incial | -0.468 |
ISION | -0.458 |
netflix | -0.413 |
andom | -0.412 |
iple | -0.403 |
Token | � |
Token ID | 447 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
bered | +0.995 |
tons | +0.925 |
tto | +0.903 |
ean | +0.880 |
CHAT | +0.853 |
Neg logit contributions | |
incial | -1.376 |
ISION | -1.355 |
netflix | -1.231 |
andom | -1.225 |
iple | -1.195 |
Token | � |
Token ID | 247 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
bered | +0.037 |
tons | +0.035 |
tto | +0.035 |
ean | +0.034 |
CHAT | +0.034 |
Neg logit contributions | |
incial | -0.029 |
ISION | -0.028 |
netflix | -0.025 |
andom | -0.025 |
iple | -0.024 |
Token | s |
Token ID | 82 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
bered | +0.034 |
tons | +0.032 |
tto | +0.031 |
ean | +0.030 |
CHAT | +0.030 |
Neg logit contributions | |
incial | -0.054 |
ISION | -0.053 |
netflix | -0.048 |
andom | -0.048 |
iple | -0.047 |
Token | work |
Token ID | 670 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
bered | +0.192 |
tons | +0.178 |
tto | +0.175 |
ean | +0.172 |
CHAT | +0.168 |
Neg logit contributions | |
incial | -0.275 |
ISION | -0.270 |
netflix | -0.245 |
andom | -0.245 |
iple | -0.240 |
Token | Row |
Token ID | 11314 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
incial | +0.037 |
ISION | +0.036 |
netflix | +0.032 |
andom | +0.032 |
iple | +0.031 |
Neg logit contributions | |
bered | -0.033 |
tons | -0.030 |
tto | -0.030 |
ean | -0.029 |
CHAT | -0.029 |
Token | lf |
Token ID | 1652 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
bered | +0.024 |
tons | +0.022 |
tto | +0.021 |
ean | +0.021 |
CHAT | +0.020 |
Neg logit contributions | |
incial | -0.063 |
ISION | -0.062 |
andom | -0.057 |
netflix | -0.057 |
iple | -0.056 |
Token | uttered |
Token ID | 36144 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
bered | +0.661 |
tons | +0.615 |
tto | +0.604 |
ean | +0.595 |
CHAT | +0.585 |
Neg logit contributions | |
incial | -0.857 |
ISION | -0.841 |
netflix | -0.761 |
andom | -0.758 |
iple | -0.743 |
Token | his |
Token ID | 465 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
bered | +0.403 |
tons | +0.377 |
tto | +0.370 |
ean | +0.363 |
CHAT | +0.357 |
Neg logit contributions | |
incial | -0.500 |
ISION | -0.491 |
netflix | -0.442 |
andom | -0.442 |
iple | -0.432 |
Token | first |
Token ID | 717 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
bered | +0.193 |
tons | +0.179 |
tto | +0.176 |
ean | +0.173 |
CHAT | +0.171 |
Neg logit contributions | |
incial | -0.246 |
ISION | -0.242 |
netflix | -0.219 |
andom | -0.218 |
iple | -0.213 |
Token | word |
Token ID | 1573 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
incial | +0.735 |
ISION | +0.721 |
netflix | +0.651 |
andom | +0.649 |
iple | +0.635 |
Neg logit contributions | |
bered | -0.605 |
tons | -0.565 |
tto | -0.555 |
ean | -0.546 |
CHAT | -0.539 |
Token | since |
Token ID | 1201 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
bered | +0.079 |
tons | +0.073 |
tto | +0.072 |
ean | +0.070 |
CHAT | +0.069 |
Neg logit contributions | |
incial | -0.117 |
ISION | -0.115 |
netflix | -0.104 |
andom | -0.104 |
iple | -0.102 |
Token | H |
Token ID | 367 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
bered | +1.561 |
tons | +1.462 |
tto | +1.432 |
ean | +1.410 |
CHAT | +1.380 |
Neg logit contributions | |
incial | -1.924 |
ISION | -1.876 |
netflix | -1.689 |
andom | -1.684 |
iple | -1.657 |
Token | enson |
Token ID | 19069 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
bered | +0.527 |
tons | +0.495 |
tto | +0.488 |
ean | +0.481 |
CHAT | +0.469 |
Neg logit contributions | |
incial | -0.643 |
ISION | -0.630 |
netflix | -0.568 |
andom | -0.562 |
iple | -0.553 |
Token | 's |
Token ID | 338 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
bered | +0.330 |
tons | +0.306 |
tto | +0.301 |
ean | +0.296 |
CHAT | +0.291 |
Neg logit contributions | |
incial | -0.441 |
ISION | -0.433 |
netflix | -0.392 |
andom | -0.391 |
iple | -0.383 |
Token | death |
Token ID | 1918 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
incial | +1.175 |
ISION | +1.161 |
andom | +1.065 |
netflix | +1.061 |
iple | +1.037 |
Neg logit contributions | |
bered | -0.690 |
tons | -0.637 |
tto | -0.622 |
ean | -0.612 |
CHAT | -0.606 |
Token | laun |
Token ID | 38722 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
bered | +0.196 |
tons | +0.184 |
tto | +0.180 |
ean | +0.178 |
CHAT | +0.175 |
Neg logit contributions | |
incial | -0.210 |
ISION | -0.208 |
andom | -0.184 |
netflix | -0.184 |
iple | -0.179 |
Token | ched |
Token ID | 1740 |
Feature activation | -3.99e-04 |
Pos logit contributions | |
bered | +1.028 |
tons | +0.967 |
tto | +0.950 |
ean | +0.938 |
CHAT | +0.919 |
Neg logit contributions | |
incial | -0.830 |
ISION | -0.827 |
netflix | -0.724 |
andom | -0.716 |
iple | -0.696 |
Token | their |
Token ID | 511 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
incial | +0.001 |
ISION | +0.001 |
netflix | +0.001 |
andom | +0.001 |
iple | +0.001 |
Neg logit contributions | |
bered | -0.001 |
tons | -0.001 |
tto | -0.001 |
ean | -0.001 |
CHAT | -0.001 |
Token | careers |
Token ID | 16179 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
incial | +0.783 |
ISION | +0.770 |
netflix | +0.706 |
andom | +0.702 |
iple | +0.688 |
Neg logit contributions | |
bered | -0.520 |
tons | -0.481 |
tto | -0.474 |
ean | -0.463 |
CHAT | -0.455 |
Token | with |
Token ID | 351 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
incial | +0.577 |
ISION | +0.567 |
netflix | +0.516 |
andom | +0.515 |
iple | +0.505 |
Neg logit contributions | |
bered | -0.394 |
tons | -0.364 |
tto | -0.358 |
ean | -0.351 |
CHAT | -0.345 |
Token | MLS |
Token ID | 13981 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
incial | +0.145 |
ISION | +0.142 |
netflix | +0.129 |
andom | +0.128 |
iple | +0.125 |
Neg logit contributions | |
bered | -0.126 |
tons | -0.118 |
tto | -0.116 |
ean | -0.114 |
CHAT | -0.112 |
Token | in |
Token ID | 287 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
incial | +0.717 |
ISION | +0.704 |
netflix | +0.638 |
andom | +0.637 |
iple | +0.624 |
Neg logit contributions | |
bered | -0.521 |
tons | -0.484 |
tto | -0.476 |
ean | -0.467 |
CHAT | -0.460 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
incial | +0.382 |
ISION | +0.374 |
netflix | +0.339 |
andom | +0.337 |
iple | +0.330 |
Neg logit contributions | |
bered | -0.311 |
tons | -0.290 |
tto | -0.285 |
ean | -0.281 |
CHAT | -0.276 |
Token | past |
Token ID | 1613 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
incial | +0.620 |
ISION | +0.607 |
netflix | +0.549 |
andom | +0.547 |
iple | +0.534 |
Neg logit contributions | |
bered | -0.531 |
tons | -0.496 |
tto | -0.489 |
ean | -0.481 |
CHAT | -0.472 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
incial | +0.754 |
ISION | +0.742 |
netflix | +0.673 |
andom | +0.671 |
iple | +0.660 |
Neg logit contributions | |
bered | -0.523 |
tons | -0.485 |
tto | -0.476 |
ean | -0.466 |
CHAT | -0.462 |
Token | it |
Token ID | 340 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
incial | +0.281 |
ISION | +0.276 |
netflix | +0.249 |
andom | +0.249 |
iple | +0.244 |
Neg logit contributions | |
bered | -0.210 |
tons | -0.195 |
tto | -0.192 |
ean | -0.188 |
CHAT | -0.186 |
Token | lots |
Token ID | 6041 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
incial | +1.292 |
ISION | +1.273 |
andom | +1.149 |
netflix | +1.143 |
iple | +1.133 |
Neg logit contributions | |
bered | -0.975 |
tons | -0.897 |
tto | -0.885 |
ean | -0.873 |
CHAT | -0.860 |
Token | of |
Token ID | 286 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
bered | +0.540 |
tons | +0.497 |
tto | +0.487 |
ean | +0.478 |
CHAT | +0.470 |
Neg logit contributions | |
incial | -0.873 |
ISION | -0.858 |
netflix | -0.784 |
andom | -0.782 |
iple | -0.768 |
Token | people |
Token ID | 661 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
incial | +0.873 |
ISION | +0.859 |
andom | +0.783 |
netflix | +0.781 |
iple | +0.769 |
Neg logit contributions | |
bered | -0.563 |
tons | -0.517 |
tto | -0.509 |
ean | -0.501 |
CHAT | -0.492 |
Token | on |
Token ID | 319 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
bered | +0.312 |
tons | +0.290 |
tto | +0.284 |
ean | +0.279 |
CHAT | +0.274 |
Neg logit contributions | |
incial | -0.433 |
ISION | -0.425 |
netflix | -0.387 |
andom | -0.386 |
iple | -0.377 |
Token | the |
Token ID | 262 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
incial | +0.545 |
ISION | +0.535 |
netflix | +0.482 |
andom | +0.481 |
iple | +0.471 |
Neg logit contributions | |
bered | -0.462 |
tons | -0.432 |
tto | -0.425 |
ean | -0.418 |
CHAT | -0.412 |
Token | other |
Token ID | 584 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
incial | +0.574 |
ISION | +0.564 |
netflix | +0.514 |
andom | +0.513 |
iple | +0.503 |
Neg logit contributions | |
bered | -0.384 |
tons | -0.355 |
tto | -0.348 |
ean | -0.342 |
CHAT | -0.336 |
Token | end |
Token ID | 886 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
incial | +0.725 |
ISION | +0.707 |
netflix | +0.620 |
andom | +0.619 |
iple | +0.602 |
Neg logit contributions | |
bered | -0.931 |
tons | -0.880 |
tto | -0.869 |
ean | -0.858 |
CHAT | -0.848 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
incial | +2.106 |
ISION | +2.072 |
netflix | +1.881 |
andom | +1.879 |
iple | +1.854 |
Neg logit contributions | |
bered | -1.464 |
tons | -1.348 |
tto | -1.327 |
ean | -1.304 |
CHAT | -1.293 |
Token | I |
Token ID | 314 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
incial | +0.266 |
ISION | +0.261 |
netflix | +0.235 |
andom | +0.235 |
iple | +0.230 |
Neg logit contributions | |
bered | -0.220 |
tons | -0.204 |
tto | -0.201 |
ean | -0.198 |
CHAT | -0.195 |
Token | don |
Token ID | 836 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
incial | +0.102 |
ISION | +0.101 |
netflix | +0.092 |
andom | +0.091 |
iple | +0.089 |
Neg logit contributions | |
bered | -0.070 |
tons | -0.065 |
tto | -0.064 |
ean | -0.063 |
CHAT | -0.062 |
Token | � |
Token ID | 447 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
bered | +0.330 |
tons | +0.310 |
tto | +0.302 |
ean | +0.297 |
CHAT | +0.288 |
Neg logit contributions | |
incial | -0.604 |
ISION | -0.594 |
netflix | -0.546 |
andom | -0.546 |
iple | -0.535 |
Token | ists |
Token ID | 1023 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
incial | +0.050 |
ISION | +0.049 |
netflix | +0.044 |
andom | +0.044 |
iple | +0.044 |
Neg logit contributions | |
bered | -0.031 |
tons | -0.029 |
tto | -0.028 |
ean | -0.028 |
CHAT | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
incial | +0.804 |
ISION | +0.789 |
netflix | +0.719 |
andom | +0.717 |
iple | +0.704 |
Neg logit contributions | |
bered | -0.555 |
tons | -0.515 |
tto | -0.505 |
ean | -0.494 |
CHAT | -0.492 |
Token | yet |
Token ID | 1865 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
bered | +0.042 |
tons | +0.039 |
tto | +0.038 |
ean | +0.038 |
CHAT | +0.037 |
Neg logit contributions | |
incial | -0.057 |
ISION | -0.056 |
netflix | -0.051 |
andom | -0.051 |
iple | -0.050 |
Token | when |
Token ID | 618 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
bered | +0.820 |
tons | +0.766 |
tto | +0.749 |
ean | +0.737 |
CHAT | +0.724 |
Neg logit contributions | |
incial | -1.063 |
ISION | -1.042 |
netflix | -0.944 |
andom | -0.941 |
iple | -0.922 |
Token | it |
Token ID | 340 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
incial | +1.618 |
ISION | +1.589 |
andom | +1.438 |
netflix | +1.438 |
iple | +1.402 |
Neg logit contributions | |
bered | -1.268 |
tons | -1.179 |
tto | -1.165 |
ean | -1.142 |
CHAT | -1.139 |
Token | was |
Token ID | 373 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
incial | +0.811 |
ISION | +0.792 |
netflix | +0.695 |
andom | +0.693 |
iple | +0.674 |
Neg logit contributions | |
bered | -1.037 |
tons | -0.981 |
tto | -0.968 |
ean | -0.956 |
CHAT | -0.946 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
incial | +0.677 |
ISION | +0.664 |
netflix | +0.601 |
andom | +0.600 |
iple | +0.587 |
Neg logit contributions | |
bered | -0.523 |
tons | -0.487 |
tto | -0.479 |
ean | -0.470 |
CHAT | -0.464 |
Token | question |
Token ID | 1808 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
incial | +0.403 |
ISION | +0.396 |
netflix | +0.360 |
andom | +0.359 |
iple | +0.351 |
Neg logit contributions | |
bered | -0.290 |
tons | -0.269 |
tto | -0.264 |
ean | -0.260 |
CHAT | -0.256 |
Token | of |
Token ID | 286 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
bered | +0.902 |
tons | +0.831 |
tto | +0.814 |
ean | +0.799 |
CHAT | +0.783 |
Neg logit contributions | |
incial | -1.473 |
ISION | -1.447 |
netflix | -1.324 |
andom | -1.321 |
iple | -1.296 |
Token | vote |
Token ID | 3015 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
incial | +0.763 |
ISION | +0.751 |
andom | +0.675 |
netflix | +0.674 |
iple | +0.660 |
Neg logit contributions | |
bered | -0.620 |
tons | -0.575 |
tto | -0.568 |
ean | -0.559 |
CHAT | -0.552 |
Token | on |
Token ID | 319 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
incial | +1.727 |
ISION | +1.704 |
netflix | +1.545 |
andom | +1.539 |
iple | +1.507 |
Neg logit contributions | |
bered | -1.297 |
tons | -1.204 |
tto | -1.181 |
ean | -1.167 |
CHAT | -1.152 |
Token | lack |
Token ID | 3092 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
bered | +0.292 |
tons | +0.274 |
tto | +0.270 |
ean | +0.265 |
CHAT | +0.260 |
Neg logit contributions | |
incial | -0.349 |
ISION | -0.342 |
netflix | -0.308 |
andom | -0.307 |
iple | -0.301 |
Token | of |
Token ID | 286 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
bered | +1.321 |
tons | +1.243 |
tto | +1.220 |
ean | +1.202 |
CHAT | +1.173 |
Neg logit contributions | |
incial | -1.632 |
ISION | -1.588 |
netflix | -1.444 |
andom | -1.433 |
iple | -1.405 |
Token | comedic |
Token ID | 42047 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
bered | +0.277 |
tons | +0.258 |
tto | +0.255 |
ean | +0.250 |
CHAT | +0.245 |
Neg logit contributions | |
incial | -0.340 |
ISION | -0.332 |
netflix | -0.301 |
andom | -0.300 |
iple | -0.295 |
Token | flour |
Token ID | 10601 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
incial | +0.834 |
ISION | +0.819 |
netflix | +0.741 |
andom | +0.741 |
iple | +0.726 |
Neg logit contributions | |
bered | -0.631 |
tons | -0.587 |
tto | -0.577 |
ean | -0.567 |
CHAT | -0.557 |
Token | ishes |
Token ID | 5614 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
incial | +0.650 |
ISION | +0.636 |
netflix | +0.567 |
andom | +0.565 |
iple | +0.551 |
Neg logit contributions | |
bered | -0.676 |
tons | -0.636 |
tto | -0.627 |
ean | -0.618 |
CHAT | -0.610 |
Token | , |
Token ID | 11 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
bered | +0.468 |
tons | +0.433 |
tto | +0.426 |
ean | +0.416 |
CHAT | +0.407 |
Neg logit contributions | |
incial | -0.683 |
ISION | -0.669 |
netflix | -0.610 |
andom | -0.609 |
iple | -0.596 |
Token | them |
Token ID | 606 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
incial | +0.070 |
ISION | +0.068 |
netflix | +0.062 |
andom | +0.062 |
iple | +0.061 |
Neg logit contributions | |
bered | -0.050 |
tons | -0.047 |
tto | -0.046 |
ean | -0.045 |
CHAT | -0.044 |
Token | atic |
Token ID | 1512 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
bered | +0.101 |
tons | +0.095 |
tto | +0.093 |
ean | +0.092 |
CHAT | +0.090 |
Neg logit contributions | |
incial | -0.113 |
ISION | -0.110 |
netflix | -0.099 |
andom | -0.099 |
iple | -0.096 |
Token | solemn |
Token ID | 26322 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
bered | +0.014 |
tons | +0.013 |
tto | +0.013 |
ean | +0.013 |
CHAT | +0.012 |
Neg logit contributions | |
incial | -0.018 |
ISION | -0.017 |
netflix | -0.016 |
andom | -0.016 |
iple | -0.015 |
Token | ity |
Token ID | 414 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
bered | +0.665 |
tons | +0.596 |
tto | +0.564 |
ean | +0.560 |
CHAT | +0.523 |
Neg logit contributions | |
incial | -2.184 |
ISION | -2.153 |
netflix | -2.008 |
andom | -1.993 |
iple | -1.966 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
bered | +0.614 |
tons | +0.569 |
tto | +0.558 |
ean | +0.545 |
CHAT | +0.534 |
Neg logit contributions | |
incial | -0.915 |
ISION | -0.898 |
netflix | -0.819 |
andom | -0.817 |
iple | -0.799 |
Token | failure |
Token ID | 5287 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
incial | +1.738 |
ISION | +1.708 |
netflix | +1.538 |
andom | +1.537 |
iple | +1.506 |
Neg logit contributions | |
bered | -1.432 |
tons | -1.339 |
tto | -1.313 |
ean | -1.292 |
CHAT | -1.280 |
Token | to |
Token ID | 284 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
incial | +2.054 |
ISION | +2.026 |
netflix | +1.832 |
andom | +1.827 |
iple | +1.778 |
Neg logit contributions | |
bered | -1.489 |
tons | -1.389 |
tto | -1.345 |
ean | -1.327 |
CHAT | -1.322 |
Token | pass |
Token ID | 1208 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
incial | +0.726 |
ISION | +0.711 |
netflix | +0.637 |
andom | +0.636 |
iple | +0.620 |
Neg logit contributions | |
bered | -0.676 |
tons | -0.634 |
tto | -0.625 |
ean | -0.615 |
CHAT | -0.604 |
Token | a |
Token ID | 257 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
incial | +0.778 |
ISION | +0.763 |
netflix | +0.688 |
andom | +0.685 |
iple | +0.671 |
Neg logit contributions | |
bered | -0.678 |
tons | -0.634 |
tto | -0.623 |
ean | -0.613 |
CHAT | -0.608 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
incial | +0.106 |
ISION | +0.104 |
netflix | +0.094 |
andom | +0.094 |
iple | +0.092 |
Neg logit contributions | |
bered | -0.087 |
tons | -0.081 |
tto | -0.080 |
ean | -0.078 |
CHAT | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
incial | +3.044 |
ISION | +2.999 |
netflix | +2.733 |
andom | +2.697 |
iple | +2.646 |
Neg logit contributions | |
bered | -2.308 |
tons | -2.162 |
tto | -2.113 |
CHAT | -2.097 |
ean | -2.067 |
Token | replace |
Token ID | 6330 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
incial | +0.984 |
ISION | +0.965 |
netflix | +0.867 |
andom | +0.865 |
iple | +0.845 |
Neg logit contributions | |
bered | -0.882 |
tons | -0.826 |
tto | -0.813 |
ean | -0.800 |
CHAT | -0.789 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
bered | +1.726 |
tons | +1.622 |
tto | +1.611 |
ean | +1.576 |
odus | +1.537 |
Neg logit contributions | |
incial | -1.827 |
ISION | -1.792 |
andom | -1.611 |
netflix | -1.604 |
iple | -1.577 |
Token | former |
Token ID | 1966 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
bered | +2.367 |
tons | +2.226 |
tto | +2.185 |
ean | +2.163 |
CHAT | +2.103 |
Neg logit contributions | |
incial | -2.537 |
ISION | -2.501 |
netflix | -2.248 |
andom | -2.226 |
iple | -2.191 |
Token | President |
Token ID | 1992 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
bered | +1.216 |
tons | +1.146 |
tto | +1.130 |
ean | +1.113 |
CHAT | +1.093 |
Neg logit contributions | |
incial | -1.256 |
ISION | -1.230 |
netflix | -1.103 |
andom | -1.102 |
iple | -1.071 |
Token | Barack |
Token ID | 8732 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
incial | +0.570 |
ISION | +0.553 |
netflix | +0.463 |
andom | +0.462 |
iple | +0.444 |
Neg logit contributions | |
bered | -1.127 |
tons | -1.076 |
tto | -1.064 |
ean | -1.053 |
CHAT | -1.043 |
Token | think |
Token ID | 892 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
incial | +0.063 |
ISION | +0.062 |
netflix | +0.057 |
andom | +0.057 |
iple | +0.055 |
Neg logit contributions | |
bered | -0.042 |
tons | -0.039 |
tto | -0.038 |
ean | -0.037 |
CHAT | -0.037 |
Token | we |
Token ID | 356 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
bered | +0.763 |
tons | +0.708 |
tto | +0.695 |
ean | +0.683 |
CHAT | +0.669 |
Neg logit contributions | |
incial | -1.052 |
ISION | -1.032 |
netflix | -0.938 |
andom | -0.936 |
iple | -0.915 |
Token | � |
Token ID | 447 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
incial | +0.463 |
ISION | +0.454 |
netflix | +0.412 |
andom | +0.411 |
iple | +0.402 |
Neg logit contributions | |
bered | -0.349 |
tons | -0.324 |
tto | -0.319 |
ean | -0.313 |
CHAT | -0.309 |
Token | � |
Token ID | 247 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
incial | +0.195 |
ISION | +0.190 |
netflix | +0.167 |
andom | +0.166 |
iple | +0.160 |
Neg logit contributions | |
bered | -0.259 |
tons | -0.245 |
tto | -0.244 |
ean | -0.239 |
CHAT | -0.236 |
Token | re |
Token ID | 260 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
incial | +0.120 |
ISION | +0.118 |
netflix | +0.108 |
andom | +0.107 |
iple | +0.105 |
Neg logit contributions | |
bered | -0.085 |
tons | -0.078 |
tto | -0.077 |
ean | -0.076 |
CHAT | -0.074 |
Token | learning |
Token ID | 4673 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
incial | +0.940 |
ISION | +0.923 |
netflix | +0.832 |
andom | +0.829 |
iple | +0.817 |
Neg logit contributions | |
bered | -0.750 |
tons | -0.703 |
tto | -0.692 |
ean | -0.680 |
CHAT | -0.674 |
Token | . |
Token ID | 13 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
incial | +3.947 |
ISION | +3.888 |
andom | +3.460 |
netflix | +3.458 |
iple | +3.446 |
Neg logit contributions | |
bered | -3.284 |
tons | -3.050 |
tto | -3.036 |
ean | -2.970 |
CHAT | -2.945 |
Token | We |
Token ID | 775 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
bered | +0.084 |
tons | +0.079 |
tto | +0.078 |
ean | +0.076 |
CHAT | +0.075 |
Neg logit contributions | |
incial | -0.111 |
ISION | -0.109 |
netflix | -0.099 |
andom | -0.099 |
iple | -0.097 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
bered | +0.142 |
tons | +0.131 |
tto | +0.128 |
ean | +0.126 |
CHAT | +0.124 |
Neg logit contributions | |
incial | -0.208 |
ISION | -0.204 |
netflix | -0.186 |
andom | -0.186 |
iple | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
incial | +3.774 |
ISION | +3.739 |
netflix | +3.315 |
andom | +3.305 |
iple | +3.297 |
Neg logit contributions | |
bered | -3.287 |
tons | -3.052 |
tto | -3.013 |
CHAT | -2.955 |
ean | -2.942 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
bered | +0.348 |
tons | +0.323 |
tto | +0.315 |
ean | +0.309 |
CHAT | +0.305 |
Neg logit contributions | |
incial | -0.504 |
ISION | -0.495 |
netflix | -0.452 |
andom | -0.450 |
iple | -0.441 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
incial | +2.889 |
ISION | +2.839 |
netflix | +2.576 |
andom | +2.564 |
iple | +2.519 |
Neg logit contributions | |
bered | -2.109 |
tons | -1.963 |
tto | -1.941 |
CHAT | -1.913 |
ean | -1.900 |
Token | budget |
Token ID | 4466 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
incial | +0.382 |
ISION | +0.375 |
netflix | +0.339 |
andom | +0.338 |
iple | +0.331 |
Neg logit contributions | |
bered | -0.305 |
tons | -0.284 |
tto | -0.279 |
ean | -0.274 |
CHAT | -0.270 |
Token | integrated |
Token ID | 11521 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
incial | +0.675 |
ISION | +0.663 |
netflix | +0.604 |
andom | +0.602 |
iple | +0.591 |
Neg logit contributions | |
bered | -0.464 |
tons | -0.429 |
tto | -0.422 |
ean | -0.414 |
CHAT | -0.408 |
Token | amps |
Token ID | 45796 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
bered | +0.417 |
tons | +0.387 |
tto | +0.380 |
ean | +0.373 |
CHAT | +0.367 |
Neg logit contributions | |
incial | -0.575 |
ISION | -0.565 |
netflix | -0.513 |
andom | -0.512 |
iple | -0.501 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
incial | +1.790 |
ISION | +1.757 |
netflix | +1.599 |
andom | +1.594 |
iple | +1.569 |
Neg logit contributions | |
bered | -1.247 |
tons | -1.157 |
tto | -1.139 |
ean | -1.116 |
CHAT | -1.106 |
Token | DAC |
Token ID | 45793 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
bered | +0.162 |
tons | +0.151 |
tto | +0.148 |
ean | +0.146 |
CHAT | +0.143 |
Neg logit contributions | |
incial | -0.204 |
ISION | -0.200 |
netflix | -0.181 |
andom | -0.181 |
iple | -0.177 |
Token | s |
Token ID | 82 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
incial | +4.452 |
ISION | +4.404 |
andom | +3.965 |
netflix | +3.922 |
iple | +3.915 |
Neg logit contributions | |
bered | -3.376 |
tons | -3.114 |
tto | -3.102 |
ean | -3.037 |
CHAT | -3.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
bered | +0.083 |
tons | +0.077 |
tto | +0.075 |
ean | +0.074 |
CHAT | +0.072 |
Neg logit contributions | |
incial | -0.119 |
ISION | -0.117 |
netflix | -0.107 |
andom | -0.107 |
iple | -0.104 |
Token | It |
Token ID | 632 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
bered | +0.552 |
tons | +0.522 |
tto | +0.514 |
ean | +0.504 |
CHAT | +0.497 |
Neg logit contributions | |
incial | -0.646 |
ISION | -0.631 |
netflix | -0.570 |
andom | -0.569 |
iple | -0.558 |
Token | would |
Token ID | 561 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
bered | +0.112 |
tons | +0.105 |
tto | +0.102 |
ean | +0.101 |
CHAT | +0.099 |
Neg logit contributions | |
incial | -0.141 |
ISION | -0.138 |
netflix | -0.125 |
andom | -0.125 |
iple | -0.122 |
Token | be |
Token ID | 307 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
bered | +0.952 |
tons | +0.879 |
tto | +0.860 |
ean | +0.851 |
CHAT | +0.827 |
Neg logit contributions | |
incial | -1.443 |
ISION | -1.424 |
netflix | -1.300 |
andom | -1.293 |
iple | -1.269 |
Token | " |
Token ID | 366 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
incial | +0.247 |
ISION | +0.242 |
netflix | +0.218 |
andom | +0.217 |
iple | +0.213 |
Neg logit contributions | |
bered | -0.213 |
tons | -0.199 |
tto | -0.196 |
ean | -0.193 |
CHAT | -0.190 |
Token | Due |
Token ID | 22229 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
incial | +1.342 |
ISION | +1.326 |
netflix | +1.186 |
andom | +1.183 |
iple | +1.157 |
Neg logit contributions | |
bered | -1.142 |
tons | -1.054 |
tto | -1.039 |
ean | -1.023 |
CHAT | -0.999 |
Token | to |
Token ID | 284 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
bered | +0.977 |
tons | +0.897 |
tto | +0.893 |
ean | +0.878 |
CHAT | +0.850 |
Neg logit contributions | |
incial | -1.603 |
ISION | -1.576 |
netflix | -1.437 |
andom | -1.429 |
iple | -1.410 |
Token | this |
Token ID | 428 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
bered | +0.038 |
tons | +0.035 |
tto | +0.035 |
ean | +0.034 |
CHAT | +0.034 |
Neg logit contributions | |
incial | -0.045 |
ISION | -0.044 |
netflix | -0.040 |
andom | -0.040 |
iple | -0.039 |
Token | fl |
Token ID | 781 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
bered | +0.208 |
tons | +0.195 |
tto | +0.191 |
ean | +0.188 |
CHAT | +0.186 |
Neg logit contributions | |
incial | -0.264 |
ISION | -0.259 |
netflix | -0.234 |
andom | -0.234 |
iple | -0.228 |
Token | attery |
Token ID | 16296 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
incial | +0.683 |
ISION | +0.668 |
netflix | +0.595 |
andom | +0.595 |
iple | +0.581 |
Neg logit contributions | |
bered | -0.700 |
tons | -0.659 |
tto | -0.649 |
ean | -0.638 |
CHAT | -0.631 |
Token | the |
Token ID | 262 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
incial | +3.856 |
ISION | +3.776 |
netflix | +3.433 |
andom | +3.414 |
iple | +3.359 |
Neg logit contributions | |
bered | -3.222 |
tons | -2.981 |
tto | -2.939 |
ean | -2.889 |
CHAT | -2.860 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
incial | +0.067 |
ISION | +0.066 |
netflix | +0.059 |
andom | +0.059 |
iple | +0.058 |
Neg logit contributions | |
bered | -0.057 |
tons | -0.054 |
tto | -0.053 |
ean | -0.052 |
CHAT | -0.051 |
Token | began |
Token ID | 2540 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
bered | +0.036 |
tons | +0.033 |
tto | +0.033 |
ean | +0.032 |
CHAT | +0.032 |
Neg logit contributions | |
incial | -0.048 |
ISION | -0.047 |
netflix | -0.043 |
andom | -0.042 |
iple | -0.042 |
Token | communicating |
Token ID | 22889 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
incial | +1.236 |
ISION | +1.215 |
netflix | +1.101 |
andom | +1.100 |
iple | +1.075 |
Neg logit contributions | |
bered | -0.924 |
tons | -0.859 |
tto | -0.843 |
ean | -0.829 |
CHAT | -0.816 |
Token | with |
Token ID | 351 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
incial | +1.355 |
ISION | +1.330 |
netflix | +1.224 |
andom | +1.215 |
iple | +1.191 |
Neg logit contributions | |
bered | -0.833 |
tons | -0.764 |
tto | -0.750 |
ean | -0.734 |
CHAT | -0.722 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
bered | +0.101 |
tons | +0.095 |
tto | +0.093 |
ean | +0.091 |
CHAT | +0.090 |
Neg logit contributions | |
incial | -0.135 |
ISION | -0.132 |
andom | -0.120 |
netflix | -0.120 |
iple | -0.118 |
Token | China |
Token ID | 14581 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
incial | +0.250 |
ISION | +0.246 |
netflix | +0.222 |
andom | +0.222 |
iple | +0.217 |
Neg logit contributions | |
bered | -0.202 |
tons | -0.188 |
tto | -0.185 |
ean | -0.182 |
CHAT | -0.179 |
Token | has |
Token ID | 468 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
incial | +1.567 |
ISION | +1.541 |
netflix | +1.384 |
andom | +1.384 |
iple | +1.352 |
Neg logit contributions | |
bered | -1.325 |
tons | -1.236 |
tto | -1.217 |
ean | -1.199 |
CHAT | -1.184 |
Token | about |
Token ID | 546 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
incial | +0.834 |
ISION | +0.819 |
netflix | +0.737 |
andom | +0.737 |
iple | +0.720 |
Neg logit contributions | |
bered | -0.704 |
tons | -0.658 |
tto | -0.647 |
ean | -0.636 |
CHAT | -0.630 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
incial | +1.319 |
ISION | +1.296 |
netflix | +1.159 |
andom | +1.153 |
iple | +1.128 |
Neg logit contributions | |
bered | -1.258 |
tons | -1.175 |
tto | -1.156 |
ean | -1.141 |
CHAT | -1.134 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
incial | +0.484 |
ISION | +0.475 |
netflix | +0.428 |
andom | +0.427 |
iple | +0.418 |
Neg logit contributions | |
bered | -0.406 |
tons | -0.379 |
tto | -0.373 |
ean | -0.366 |
CHAT | -0.362 |
Token | - |
Token ID | 12 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
incial | +3.561 |
ISION | +3.497 |
andom | +3.160 |
netflix | +3.113 |
iple | +3.055 |
Neg logit contributions | |
bered | -3.106 |
tons | -2.918 |
tto | -2.882 |
CHAT | -2.840 |
ean | -2.836 |
Token | powered |
Token ID | 12293 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
incial | +0.100 |
ISION | +0.098 |
netflix | +0.086 |
andom | +0.086 |
iple | +0.084 |
Neg logit contributions | |
bered | -0.117 |
tons | -0.111 |
tto | -0.109 |
ean | -0.108 |
CHAT | -0.106 |
Token | submarines |
Token ID | 34031 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
incial | +2.370 |
ISION | +2.341 |
andom | +2.085 |
netflix | +2.068 |
iple | +2.031 |
Neg logit contributions | |
bered | -2.272 |
tons | -2.123 |
tto | -2.085 |
ean | -2.060 |
CHAT | -2.058 |
Token | ( |
Token ID | 357 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
incial | +2.504 |
ISION | +2.455 |
netflix | +2.218 |
andom | +2.216 |
iple | +2.176 |
Neg logit contributions | |
bered | -1.906 |
tons | -1.770 |
tto | -1.743 |
CHAT | -1.727 |
ean | -1.716 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
incial | +0.109 |
ISION | +0.107 |
netflix | +0.098 |
andom | +0.097 |
iple | +0.095 |
Neg logit contributions | |
bered | -0.073 |
tons | -0.067 |
tto | -0.066 |
ean | -0.065 |
CHAT | -0.064 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
incial | +0.469 |
ISION | +0.459 |
netflix | +0.410 |
andom | +0.409 |
iple | +0.399 |
Neg logit contributions | |
bered | -0.465 |
tons | -0.436 |
tto | -0.429 |
ean | -0.423 |
CHAT | -0.418 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
incial | +0.072 |
ISION | +0.071 |
andom | +0.064 |
netflix | +0.064 |
iple | +0.063 |
Neg logit contributions | |
bered | -0.046 |
tons | -0.044 |
tto | -0.043 |
ean | -0.042 |
CHAT | -0.041 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
bered | +0.222 |
tons | +0.203 |
tto | +0.201 |
ean | +0.198 |
CHAT | +0.194 |
Neg logit contributions | |
incial | -0.360 |
ISION | -0.354 |
netflix | -0.324 |
andom | -0.323 |
iple | -0.316 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
bered | +0.805 |
tons | +0.771 |
tto | +0.754 |
ean | +0.735 |
CHAT | +0.722 |
Neg logit contributions | |
incial | -1.198 |
ISION | -1.171 |
andom | -1.065 |
netflix | -1.064 |
iple | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
bered | +0.461 |
tons | +0.436 |
tto | +0.428 |
ean | +0.418 |
CHAT | +0.410 |
Neg logit contributions | |
incial | -0.637 |
ISION | -0.624 |
andom | -0.567 |
netflix | -0.566 |
iple | -0.556 |
Token | Subject |
Token ID | 19776 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
bered | +0.279 |
tons | +0.264 |
tto | +0.261 |
ean | +0.256 |
CHAT | +0.252 |
Neg logit contributions | |
incial | -0.262 |
ISION | -0.254 |
andom | -0.226 |
netflix | -0.226 |
iple | -0.219 |
Token | : |
Token ID | 25 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
incial | +4.675 |
ISION | +4.621 |
netflix | +4.198 |
andom | +4.136 |
iple | +4.051 |
Neg logit contributions | |
bered | -4.278 |
tons | -3.867 |
tto | -3.823 |
cellence | -3.804 |
CHAT | -3.766 |
Token | R |
Token ID | 371 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
incial | +0.087 |
ISION | +0.085 |
netflix | +0.077 |
andom | +0.077 |
iple | +0.075 |
Neg logit contributions | |
bered | -0.072 |
tons | -0.068 |
tto | -0.067 |
ean | -0.066 |
CHAT | -0.065 |
Token | iff |
Token ID | 733 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
bered | +0.729 |
tons | +0.686 |
tto | +0.677 |
ean | +0.666 |
CHAT | +0.656 |
Neg logit contributions | |
incial | -0.732 |
ISION | -0.714 |
netflix | -0.642 |
andom | -0.635 |
iple | -0.619 |
Token | Tra |
Token ID | 15721 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
incial | +0.442 |
ISION | +0.434 |
netflix | +0.396 |
andom | +0.395 |
iple | +0.388 |
Neg logit contributions | |
bered | -0.284 |
tons | -0.262 |
tto | -0.257 |
ean | -0.251 |
CHAT | -0.248 |
Token | x |
Token ID | 87 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
incial | +2.648 |
ISION | +2.604 |
andom | +2.434 |
netflix | +2.421 |
iple | +2.405 |
Neg logit contributions | |
bered | -0.776 |
tons | -0.674 |
tto | -0.636 |
CHAT | -0.612 |
ean | -0.604 |