Token |
|
Token ID | 198 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
creen | +0.142 |
ovember | +0.138 |
MU | +0.136 |
belie | +0.128 |
hur | +0.126 |
Neg logit contributions | |
Rocks | -0.105 |
arily | -0.097 |
iant | -0.097 |
--> | -0.095 |
iants | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
creen | +2.440 |
MU | +2.382 |
ovember | +2.309 |
hur | +2.165 |
emp | +2.134 |
Neg logit contributions | |
Rocks | -2.263 |
igree | -2.132 |
ogyn | -2.124 |
iant | -2.121 |
iants | -2.118 |
Token | Read |
Token ID | 5569 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
MU | +4.123 |
creen | +3.826 |
ovember | +3.381 |
hur | +3.198 |
emp | +3.125 |
Neg logit contributions | |
Rocks | -9.052 |
igree | -8.964 |
arily | -8.705 |
iants | -8.675 |
iant | -8.620 |
Token | More |
Token ID | 3125 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
creen | +2.202 |
MU | +2.162 |
ovember | +2.118 |
belie | +1.985 |
hur | +1.979 |
Neg logit contributions | |
Rocks | -1.344 |
arily | -1.279 |
iant | -1.271 |
iants | -1.262 |
ogyn | -1.250 |
Token | About |
Token ID | 7994 |
Feature activation | -3.04e-04 |
Pos logit contributions | |
creen | +2.003 |
ovember | +1.943 |
MU | +1.940 |
belie | +1.801 |
hur | +1.788 |
Neg logit contributions | |
Rocks | -1.377 |
arily | -1.300 |
iant | -1.289 |
iants | -1.273 |
bow | -1.266 |
Token | N |
Token ID | 399 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
creen | +0.004 |
ovember | +0.004 |
MU | +0.004 |
belie | +0.003 |
hur | +0.003 |
Neg logit contributions | |
Rocks | -0.002 |
arily | -0.002 |
iant | -0.002 |
iants | -0.002 |
--> | -0.002 |
Token | ages |
Token ID | 1095 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
iant | +6.071 |
iants | +5.876 |
arily | +5.648 |
ians | +5.139 |
awed | +5.028 |
Neg logit contributions | |
captcha | -21.341 |
creen | -21.340 |
MU | -21.334 |
belie | -19.862 |
mixer | -19.720 |
Token | h |
Token ID | 71 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
creen | +3.064 |
ovember | +2.874 |
MU | +2.863 |
hur | +2.775 |
emp | +2.636 |
Neg logit contributions | |
Rocks | -2.729 |
Narc | -2.479 |
iants | -2.470 |
arily | -2.469 |
iant | -2.457 |
Token | war |
Token ID | 5767 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
creen | +1.782 |
ovember | +1.651 |
MU | +1.625 |
hur | +1.461 |
uckle | +1.381 |
Neg logit contributions | |
Rocks | -3.822 |
Narc | -3.584 |
arily | -3.581 |
iant | -3.573 |
iants | -3.569 |
Token | J |
Token ID | 449 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
creen | +0.432 |
ovember | +0.412 |
MU | +0.410 |
belie | +0.374 |
hur | +0.369 |
Neg logit contributions | |
Rocks | -0.575 |
arily | -0.548 |
iant | -0.546 |
iants | -0.543 |
bow | -0.540 |
Token | y |
Token ID | 88 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Rocks | +1.909 |
iant | +1.828 |
bow | +1.816 |
arily | +1.782 |
--> | +1.693 |
Neg logit contributions | |
creen | -7.438 |
ovember | -7.405 |
MU | -7.294 |
captcha | -7.184 |
belie | -7.156 |
Token | and |
Token ID | 290 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
creen | +2.256 |
MU | +2.192 |
ovember | +2.165 |
belie | +2.027 |
hur | +2.002 |
Neg logit contributions | |
Rocks | -2.318 |
iant | -2.182 |
arily | -2.172 |
iants | -2.163 |
ogyn | -2.149 |
Token | girls |
Token ID | 4813 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
creen | +4.084 |
ovember | +4.079 |
MU | +3.983 |
belie | +3.788 |
uckle | +3.616 |
Neg logit contributions | |
Rocks | -4.805 |
arily | -4.557 |
igree | -4.517 |
ogyn | -4.507 |
iant | -4.506 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
creen | +2.687 |
MU | +2.588 |
ovember | +2.562 |
belie | +2.399 |
hur | +2.372 |
Neg logit contributions | |
Rocks | -2.894 |
iant | -2.736 |
arily | -2.732 |
iants | -2.724 |
ogyn | -2.691 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Rocks | +3.727 |
Narc | +3.395 |
Pet | +3.358 |
arily | +3.350 |
iant | +3.334 |
Neg logit contributions | |
creen | -5.011 |
ovember | -4.841 |
MU | -4.608 |
belie | -4.449 |
captcha | -4.407 |
Token |
|
Token ID | 198 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Rocks | +1.279 |
arily | +1.187 |
--> | +1.178 |
bow | +1.176 |
iant | +1.176 |
Neg logit contributions | |
creen | -1.911 |
ovember | -1.870 |
MU | -1.826 |
belie | -1.742 |
captcha | -1.711 |
Token | N |
Token ID | 45 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Rocks | +2.544 |
Pet | +2.453 |
--> | +2.422 |
arily | +2.400 |
iant | +2.400 |
Neg logit contributions | |
creen | -3.635 |
ovember | -3.479 |
MU | -3.367 |
belie | -3.300 |
captcha | -3.237 |
Token | om |
Token ID | 296 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ominated | +12.912 |
iant | +12.779 |
bow | +11.961 |
PG | +11.881 |
Pet | +11.879 |
Neg logit contributions | |
creen | -11.831 |
belie | -10.867 |
captcha | -10.503 |
MU | -10.053 |
hur | -10.041 |
Token | inate |
Token ID | 4559 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Rocks | +1.653 |
iant | +1.546 |
arily | +1.544 |
bow | +1.521 |
iants | +1.519 |
Neg logit contributions | |
creen | -1.992 |
ovember | -1.930 |
MU | -1.915 |
belie | -1.781 |
hur | -1.756 |
Token | an |
Token ID | 281 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Rocks | +1.276 |
arily | +1.186 |
iant | +1.182 |
--> | +1.171 |
iants | +1.167 |
Neg logit contributions | |
creen | -1.448 |
ovember | -1.401 |
MU | -1.384 |
belie | -1.285 |
hur | -1.274 |
Token | exceptional |
Token ID | 15313 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Rocks | +1.629 |
arily | +1.511 |
iant | +1.510 |
iants | +1.488 |
--> | +1.485 |
Neg logit contributions | |
creen | -2.020 |
ovember | -1.946 |
MU | -1.919 |
belie | -1.782 |
hur | -1.767 |
Token | Peace |
Token ID | 12689 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Rocks | +2.471 |
arily | +2.301 |
iant | +2.289 |
--> | +2.273 |
Narc | +2.269 |
Neg logit contributions | |
creen | -2.611 |
ovember | -2.512 |
MU | -2.444 |
hur | -2.261 |
belie | -2.251 |
Token | week |
Token ID | 1285 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Rocks | +0.881 |
arily | +0.828 |
iant | +0.824 |
--> | +0.815 |
iants | +0.814 |
Neg logit contributions | |
creen | -0.951 |
ovember | -0.911 |
MU | -0.909 |
belie | -0.842 |
hur | -0.832 |
Token | after |
Token ID | 706 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
Rocks | +2.238 |
iant | +2.101 |
arily | +2.082 |
bow | +2.079 |
--> | +2.071 |
Neg logit contributions | |
creen | -2.550 |
ovember | -2.476 |
MU | -2.447 |
belie | -2.258 |
hur | -2.241 |
Token | recovering |
Token ID | 20222 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Rocks | +6.240 |
Narc | +5.761 |
bow | +5.678 |
iant | +5.666 |
Hubbard | +5.659 |
Neg logit contributions | |
creen | -6.972 |
ovember | -6.627 |
MU | -6.526 |
veland | -6.040 |
ioxide | -6.000 |
Token | from |
Token ID | 422 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Rocks | +2.626 |
iant | +2.460 |
arily | +2.454 |
bow | +2.431 |
iants | +2.413 |
Neg logit contributions | |
creen | -2.562 |
ovember | -2.475 |
MU | -2.419 |
belie | -2.229 |
hur | -2.216 |
Token | a |
Token ID | 257 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Rocks | +6.357 |
bow | +5.786 |
Narc | +5.748 |
iant | +5.744 |
--> | +5.642 |
Neg logit contributions | |
creen | -8.672 |
ovember | -8.383 |
MU | -8.162 |
veland | -7.671 |
belie | -7.583 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Rocks | +7.380 |
bow | +6.744 |
Narc | +6.675 |
iant | +6.657 |
arily | +6.623 |
Neg logit contributions | |
creen | -8.975 |
ovember | -8.700 |
MU | -8.331 |
ioxide | -8.030 |
veland | -7.789 |
Token | leg |
Token ID | 1232 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Rocks | +9.549 |
bow | +9.409 |
arily | +8.800 |
Narc | +8.717 |
Hubbard | +8.619 |
Neg logit contributions | |
creen | -14.372 |
MU | -13.409 |
ovember | -13.266 |
ioxide | -12.854 |
veland | -12.687 |
Token | in |
Token ID | 287 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Rocks | +2.206 |
iant | +2.071 |
bow | +2.052 |
arily | +2.051 |
iants | +2.047 |
Neg logit contributions | |
creen | -2.330 |
ovember | -2.245 |
MU | -2.229 |
belie | -2.073 |
hur | -2.040 |
Token | round |
Token ID | 2835 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Rocks | +1.267 |
iant | +1.180 |
arily | +1.177 |
iants | +1.171 |
--> | +1.166 |
Neg logit contributions | |
creen | -1.322 |
ovember | -1.271 |
MU | -1.260 |
belie | -1.167 |
hur | -1.154 |
Token | 18 |
Token ID | 1248 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
creen | +1.025 |
ovember | +0.985 |
MU | +0.977 |
belie | +0.888 |
hur | +0.876 |
Neg logit contributions | |
Rocks | -1.291 |
arily | -1.222 |
iant | -1.216 |
iants | -1.206 |
--> | -1.206 |
Token | last |
Token ID | 938 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Rocks | +3.438 |
iant | +3.189 |
bow | +3.126 |
arily | +3.117 |
--> | +3.112 |
Neg logit contributions | |
creen | -3.603 |
ovember | -3.426 |
MU | -3.382 |
belie | -3.155 |
hur | -3.093 |
Token | video |
Token ID | 2008 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
creen | +0.455 |
ovember | +0.438 |
MU | +0.436 |
belie | +0.402 |
hur | +0.396 |
Neg logit contributions | |
Rocks | -0.497 |
iant | -0.467 |
arily | -0.467 |
iants | -0.463 |
--> | -0.461 |
Token | down |
Token ID | 866 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Rocks | +4.158 |
arily | +3.960 |
iant | +3.856 |
bow | +3.840 |
Narc | +3.836 |
Neg logit contributions | |
creen | -5.258 |
ovember | -5.212 |
MU | -4.978 |
veland | -4.659 |
uckle | -4.620 |
Token | as |
Token ID | 355 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
Rocks | +0.954 |
arily | +0.901 |
iant | +0.896 |
bow | +0.884 |
--> | +0.883 |
Neg logit contributions | |
creen | -1.071 |
ovember | -1.048 |
MU | -1.034 |
belie | -0.954 |
hur | -0.943 |
Token | it |
Token ID | 340 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
creen | +0.840 |
MU | +0.809 |
ovember | +0.808 |
belie | +0.753 |
hur | +0.739 |
Neg logit contributions | |
Rocks | -0.826 |
iant | -0.774 |
arily | -0.773 |
iants | -0.768 |
bow | -0.765 |
Token | is |
Token ID | 318 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Rocks | +0.820 |
arily | +0.769 |
iant | +0.765 |
bow | +0.754 |
--> | +0.753 |
Neg logit contributions | |
creen | -0.900 |
ovember | -0.873 |
MU | -0.865 |
belie | -0.794 |
hur | -0.788 |
Token | dem |
Token ID | 1357 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Rocks | +1.448 |
arily | +1.364 |
iant | +1.351 |
--> | +1.330 |
ogyn | +1.328 |
Neg logit contributions | |
creen | -1.563 |
ovember | -1.527 |
MU | -1.501 |
belie | -1.375 |
uckle | -1.374 |
Token | e |
Token ID | 68 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
iant | +7.473 |
Rocks | +6.747 |
arily | +6.744 |
bow | +6.662 |
ogyn | +6.600 |
Neg logit contributions | |
ovember | -16.642 |
creen | -16.389 |
captcha | -15.864 |
belie | -15.718 |
MU | -15.656 |
Token | aning |
Token ID | 7574 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
Rocks | +2.119 |
arily | +1.979 |
iant | +1.856 |
ogyn | +1.768 |
bow | +1.729 |
Neg logit contributions | |
creen | -8.587 |
ovember | -8.393 |
MU | -8.349 |
belie | -7.859 |
iffe | -7.757 |
Token | for |
Token ID | 329 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
Rocks | +0.580 |
arily | +0.545 |
iant | +0.542 |
iants | +0.535 |
bow | +0.535 |
Neg logit contributions | |
creen | -0.646 |
ovember | -0.625 |
MU | -0.618 |
belie | -0.573 |
hur | -0.566 |
Token | women |
Token ID | 1466 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
creen | +0.874 |
ovember | +0.844 |
MU | +0.840 |
belie | +0.782 |
hur | +0.769 |
Neg logit contributions | |
Rocks | -0.837 |
arily | -0.784 |
iant | -0.783 |
iants | -0.775 |
bow | -0.774 |
Token | , |
Token ID | 11 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
creen | +1.358 |
MU | +1.308 |
ovember | +1.306 |
belie | +1.215 |
hur | +1.195 |
Neg logit contributions | |
Rocks | -1.318 |
iant | -1.232 |
arily | -1.231 |
iants | -1.221 |
--> | -1.215 |
Token | raction |
Token ID | 7861 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Rocks | +0.102 |
arily | +0.095 |
iant | +0.095 |
iants | +0.094 |
bow | +0.093 |
Neg logit contributions | |
creen | -0.117 |
ovember | -0.114 |
MU | -0.113 |
belie | -0.105 |
hur | -0.104 |
Token | ( |
Token ID | 357 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Rocks | +2.270 |
arily | +2.133 |
iant | +2.097 |
--> | +2.087 |
bow | +2.070 |
Neg logit contributions | |
creen | -2.064 |
ovember | -1.978 |
MU | -1.961 |
belie | -1.796 |
hur | -1.795 |
Token | b |
Token ID | 65 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
Rocks | +4.083 |
bow | +3.838 |
Pet | +3.822 |
iant | +3.807 |
--> | +3.777 |
Neg logit contributions | |
creen | -4.399 |
ovember | -4.308 |
MU | -4.175 |
belie | -4.046 |
captcha | -3.858 |
Token | , |
Token ID | 11 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Rocks | +0.341 |
arily | +0.317 |
iant | +0.317 |
bow | +0.312 |
--> | +0.311 |
Neg logit contributions | |
creen | -0.439 |
ovember | -0.424 |
MU | -0.422 |
belie | -0.395 |
hur | -0.388 |
Token | c |
Token ID | 66 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Rocks | +3.483 |
iant | +3.198 |
--> | +3.151 |
bow | +3.118 |
iants | +3.117 |
Neg logit contributions | |
creen | -4.777 |
MU | -4.715 |
ovember | -4.711 |
belie | -4.386 |
hur | -4.319 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
creen | +1.444 |
ovember | +1.394 |
MU | +1.381 |
belie | +1.289 |
hur | +1.272 |
Neg logit contributions | |
Rocks | -1.227 |
arily | -1.147 |
iant | -1.145 |
iants | -1.134 |
bow | -1.127 |
Token | d |
Token ID | 67 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Rocks | +8.194 |
bow | +7.809 |
--> | +7.774 |
iant | +7.678 |
iants | +7.551 |
Neg logit contributions | |
MU | -14.256 |
ovember | -14.145 |
creen | -13.951 |
belie | -13.264 |
UGH | -13.094 |
Token | ) |
Token ID | 8 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Rocks | +3.230 |
arily | +2.983 |
iant | +2.970 |
--> | +2.965 |
bow | +2.929 |
Neg logit contributions | |
creen | -4.467 |
MU | -4.378 |
ovember | -4.343 |
belie | -4.030 |
hur | -3.995 |
Token | C |
Token ID | 327 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
creen | +0.141 |
ovember | +0.136 |
MU | +0.135 |
belie | +0.125 |
hur | +0.124 |
Neg logit contributions | |
Rocks | -0.125 |
arily | -0.117 |
iant | -0.117 |
iants | -0.116 |
--> | -0.115 |
Token | - |
Token ID | 12 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
creen | +4.823 |
ovember | +4.687 |
MU | +4.665 |
uckle | +4.227 |
emp | +4.214 |
Neg logit contributions | |
Rocks | -4.991 |
iants | -4.818 |
ogyn | -4.818 |
Narc | -4.776 |
iant | -4.756 |
Token | 14 |
Token ID | 1415 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Rocks | +1.448 |
arily | +1.347 |
iant | +1.339 |
bow | +1.325 |
iants | +1.320 |
Neg logit contributions | |
creen | -2.001 |
ovember | -1.939 |
MU | -1.919 |
belie | -1.816 |
uckle | -1.771 |
Token | our |
Token ID | 674 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Rocks | +5.131 |
arily | +4.994 |
iant | +4.949 |
--> | +4.849 |
Narc | +4.817 |
Neg logit contributions | |
ovember | -11.304 |
creen | -11.167 |
MU | -10.938 |
ioxide | -10.556 |
captcha | -10.264 |
Token | Privacy |
Token ID | 16777 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Rocks | +2.920 |
Narc | +2.723 |
Pet | +2.641 |
iant | +2.618 |
iants | +2.608 |
Neg logit contributions | |
ovember | -7.382 |
creen | -7.313 |
MU | -7.090 |
belie | -6.751 |
ioxide | -6.720 |
Token | Policy |
Token ID | 7820 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Rocks | +2.526 |
Narc | +2.252 |
Pet | +2.244 |
arily | +2.232 |
iant | +2.221 |
Neg logit contributions | |
ovember | -4.744 |
creen | -4.697 |
MU | -4.541 |
belie | -4.431 |
captcha | -4.355 |
Token | here |
Token ID | 994 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
Rocks | +6.303 |
--> | +5.945 |
arily | +5.830 |
Narc | +5.754 |
bow | +5.724 |
Neg logit contributions | |
ovember | -9.790 |
creen | -9.188 |
MU | -9.172 |
ioxide | -8.611 |
belie | -8.476 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Rocks | +5.124 |
bow | +4.775 |
arily | +4.768 |
--> | +4.764 |
iant | +4.688 |
Neg logit contributions | |
ovember | -8.452 |
creen | -8.253 |
MU | -7.832 |
belie | -7.755 |
captcha | -7.632 |
Token | Sign |
Token ID | 5865 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Rocks | +2.140 |
--> | +1.911 |
Pet | +1.843 |
iant | +1.827 |
bow | +1.817 |
Neg logit contributions | |
ovember | -5.260 |
creen | -5.245 |
MU | -5.031 |
belie | -4.876 |
iffe | -4.791 |
Token | up |
Token ID | 510 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
arily | +5.305 |
--> | +4.768 |
bow | +4.690 |
Rocks | +4.430 |
awed | +4.175 |
Neg logit contributions | |
ovember | -18.396 |
creen | -17.359 |
MU | -17.326 |
ioxide | -16.752 |
captcha | -16.481 |
Token | for |
Token ID | 329 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Rocks | +4.646 |
--> | +4.420 |
bow | +4.339 |
Pet | +4.307 |
Narc | +4.297 |
Neg logit contributions | |
ovember | -7.979 |
creen | -7.789 |
MU | -7.494 |
ioxide | -7.237 |
belie | -7.228 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
creen | +2.988 |
MU | +2.849 |
ovember | +2.847 |
belie | +2.686 |
hur | +2.656 |
Neg logit contributions | |
Rocks | -1.930 |
iant | -1.818 |
arily | -1.810 |
iants | -1.800 |
ogyn | -1.788 |
Token | Action |
Token ID | 7561 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
creen | +0.944 |
MU | +0.892 |
ovember | +0.882 |
hur | +0.794 |
belie | +0.788 |
Neg logit contributions | |
Rocks | -1.455 |
iant | -1.408 |
arily | -1.404 |
iants | -1.400 |
ogyn | -1.393 |
Token | Now |
Token ID | 2735 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Rocks | +0.488 |
arily | +0.450 |
iant | +0.448 |
iants | +0.442 |
bow | +0.441 |
Neg logit contributions | |
creen | -0.757 |
ovember | -0.735 |
MU | -0.730 |
belie | -0.685 |
hur | -0.678 |
Token | ARS |
Token ID | 27415 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
Rocks | +1.147 |
arily | +0.923 |
GY | +0.913 |
--> | +0.909 |
Pet | +0.902 |
Neg logit contributions | |
creen | -4.169 |
ovember | -4.077 |
MU | -3.984 |
belie | -3.894 |
hur | -3.873 |
Token | ? |
Token ID | 30 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
creen | +0.762 |
ovember | +0.733 |
MU | +0.729 |
belie | +0.676 |
hur | +0.662 |
Neg logit contributions | |
Rocks | -0.762 |
arily | -0.718 |
iant | -0.717 |
iants | -0.711 |
bow | -0.706 |
Token | N |
Token ID | 399 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
creen | +1.270 |
MU | +1.228 |
ovember | +1.221 |
belie | +1.133 |
hur | +1.119 |
Neg logit contributions | |
Rocks | -1.108 |
arily | -1.050 |
iant | -1.042 |
iants | -1.034 |
bow | -1.025 |
Token | INE |
Token ID | 8881 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
iant | +8.093 |
Rocks | +7.611 |
arily | +7.511 |
iants | +7.442 |
ominated | +7.424 |
Neg logit contributions | |
creen | -10.837 |
captcha | -9.901 |
belie | -9.793 |
ovember | -9.649 |
MU | -9.643 |
Token | DO |
Token ID | 8410 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Rocks | +2.739 |
--> | +2.516 |
arily | +2.513 |
iant | +2.513 |
bow | +2.502 |
Neg logit contributions | |
creen | -2.538 |
ovember | -2.467 |
MU | -2.408 |
belie | -2.232 |
iffe | -2.231 |
Token | LL |
Token ID | 3069 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
creen | +0.148 |
ovember | +0.144 |
MU | +0.143 |
belie | +0.135 |
hur | +0.134 |
Neg logit contributions | |
Rocks | -0.067 |
arily | -0.060 |
iant | -0.060 |
iants | -0.059 |
--> | -0.059 |
Token | ARS |
Token ID | 27415 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Rocks | +2.455 |
NS | +1.916 |
GY | +1.626 |
--> | +1.619 |
Pet | +1.434 |
Neg logit contributions | |
creen | -20.987 |
belie | -20.254 |
ovember | -20.251 |
captcha | -20.191 |
emp | -20.039 |
Token | A |
Token ID | 317 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
creen | +3.438 |
MU | +3.311 |
ovember | +3.285 |
belie | +3.038 |
hur | +2.954 |
Neg logit contributions | |
Rocks | -3.703 |
arily | -3.534 |
iant | -3.523 |
iants | -3.506 |
bow | -3.463 |
Token | BE |
Token ID | 9348 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
creen | +3.124 |
MU | +3.050 |
ovember | +3.033 |
belie | +2.792 |
hur | +2.759 |
Neg logit contributions | |
Rocks | -2.866 |
arily | -2.685 |
iant | -2.674 |
iants | -2.668 |
bow | -2.621 |
Token | ER |
Token ID | 1137 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
creen | +2.631 |
MU | +2.588 |
ovember | +2.546 |
belie | +2.344 |
hur | +2.322 |
Neg logit contributions | |
Rocks | -2.269 |
arily | -2.108 |
iant | -2.103 |
iants | -2.102 |
ogyn | -2.095 |
Token | ! |
Token ID | 0 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
Rocks | +0.171 |
arily | +0.160 |
iant | +0.160 |
iants | +0.158 |
--> | +0.158 |
Neg logit contributions | |
creen | -0.175 |
ovember | -0.169 |
MU | -0.167 |
belie | -0.155 |
hur | -0.153 |
Token | given |
Token ID | 1813 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
creen | +0.256 |
ovember | +0.247 |
MU | +0.245 |
belie | +0.227 |
hur | +0.224 |
Neg logit contributions | |
Rocks | -0.248 |
arily | -0.232 |
iant | -0.232 |
iants | -0.229 |
bow | -0.228 |
Token | � |
Token ID | 564 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
Rocks | +0.860 |
arily | +0.807 |
iant | +0.806 |
--> | +0.795 |
iants | +0.794 |
Neg logit contributions | |
creen | -0.890 |
ovember | -0.863 |
MU | -0.854 |
belie | -0.788 |
hur | -0.778 |
Token | � |
Token ID | 250 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Rocks | +0.915 |
arily | +0.865 |
iant | +0.861 |
--> | +0.854 |
bow | +0.851 |
Neg logit contributions | |
creen | -0.898 |
ovember | -0.860 |
MU | -0.854 |
belie | -0.787 |
hur | -0.773 |
Token | dr |
Token ID | 7109 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Rocks | +1.919 |
iant | +1.834 |
arily | +1.817 |
bow | +1.813 |
--> | +1.804 |
Neg logit contributions | |
creen | -1.976 |
ovember | -1.927 |
MU | -1.863 |
belie | -1.776 |
captcha | -1.714 |
Token | astic |
Token ID | 3477 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Rocks | +3.565 |
iant | +3.444 |
arily | +3.401 |
iants | +3.389 |
Pet | +3.328 |
Neg logit contributions | |
creen | -4.977 |
ovember | -4.794 |
MU | -4.756 |
belie | -4.538 |
hur | -4.429 |
Token | dem |
Token ID | 1357 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
creen | +1.408 |
ovember | +1.354 |
MU | +1.352 |
belie | +1.260 |
hur | +1.245 |
Neg logit contributions | |
Rocks | -1.242 |
arily | -1.152 |
iant | -1.150 |
iants | -1.145 |
bow | -1.138 |
Token | otions |
Token ID | 36083 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
iants | +7.249 |
iant | +7.122 |
bow | +7.037 |
Rocks | +6.824 |
arily | +6.444 |
Neg logit contributions | |
ovember | -15.915 |
creen | -15.667 |
MU | -15.629 |
captcha | -15.137 |
belie | -15.015 |
Token | � |
Token ID | 447 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
Rocks | +0.595 |
arily | +0.555 |
iant | +0.553 |
--> | +0.547 |
bow | +0.545 |
Neg logit contributions | |
creen | -0.772 |
ovember | -0.752 |
MU | -0.746 |
belie | -0.695 |
hur | -0.686 |
Token | � |
Token ID | 251 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
Rocks | +0.522 |
arily | +0.476 |
iant | +0.471 |
--> | +0.468 |
bow | +0.465 |
Neg logit contributions | |
creen | -1.149 |
ovember | -1.117 |
MU | -1.114 |
belie | -1.050 |
hur | -1.036 |
Token | for |
Token ID | 329 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Rocks | +0.632 |
arily | +0.593 |
iant | +0.591 |
--> | +0.584 |
iants | +0.583 |
Neg logit contributions | |
creen | -0.706 |
ovember | -0.686 |
MU | -0.678 |
belie | -0.629 |
hur | -0.620 |
Token | serious |
Token ID | 2726 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
creen | +5.752 |
MU | +5.497 |
ovember | +5.401 |
belie | +5.332 |
hur | +5.139 |
Neg logit contributions | |
Rocks | -6.731 |
arily | -6.318 |
igree | -6.285 |
iant | -6.241 |
iants | -6.234 |
Token | working |
Token ID | 16090 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Rocks | +7.122 |
iant | +6.903 |
bow | +6.807 |
arily | +6.673 |
awed | +6.653 |
Neg logit contributions | |
ovember | -7.799 |
creen | -7.634 |
MU | -7.217 |
captcha | -6.939 |
iffe | -6.803 |
Token | , |
Token ID | 11 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Rocks | +1.259 |
arily | +1.183 |
iant | +1.176 |
iants | +1.160 |
bow | +1.160 |
Neg logit contributions | |
creen | -1.428 |
ovember | -1.391 |
MU | -1.366 |
belie | -1.267 |
hur | -1.256 |
Token | organized |
Token ID | 8389 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Rocks | +5.045 |
iant | +4.837 |
Narc | +4.740 |
arily | +4.720 |
bow | +4.691 |
Neg logit contributions | |
ovember | -5.749 |
creen | -5.728 |
MU | -5.479 |
iffe | -5.187 |
uckle | -5.128 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
creen | +1.086 |
MU | +1.040 |
ovember | +1.039 |
belie | +0.966 |
hur | +0.947 |
Neg logit contributions | |
Rocks | -1.051 |
iant | -0.980 |
arily | -0.980 |
iants | -0.973 |
--> | -0.969 |
Token | self |
Token ID | 2116 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Rocks | +2.737 |
iant | +2.590 |
arily | +2.557 |
bow | +2.534 |
Narc | +2.534 |
Neg logit contributions | |
creen | -3.230 |
ovember | -3.196 |
MU | -3.122 |
iffe | -2.886 |
uckle | -2.875 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
arily | +8.843 |
Rocks | +8.600 |
iant | +8.374 |
Hubbard | +8.137 |
narcissistic | +8.109 |
Neg logit contributions | |
ovember | -13.298 |
creen | -13.194 |
MU | -12.537 |
captcha | -12.113 |
uckle | -12.047 |
Token | mot |
Token ID | 27926 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iant | +9.157 |
bow | +8.867 |
Pet | +8.714 |
arily | +8.714 |
--> | +8.618 |
Neg logit contributions | |
ovember | -14.065 |
creen | -13.193 |
captcha | -12.839 |
MU | -12.674 |
ioxide | -12.448 |
Token | ivated |
Token ID | 30829 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
iant | +5.103 |
arily | +4.981 |
Rocks | +4.981 |
ogyn | +4.859 |
bow | +4.846 |
Neg logit contributions | |
ovember | -7.365 |
creen | -7.349 |
MU | -7.253 |
captcha | -6.775 |
ioxide | -6.654 |
Token | , |
Token ID | 11 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Rocks | +0.326 |
arily | +0.305 |
iant | +0.304 |
iants | +0.301 |
bow | +0.300 |
Neg logit contributions | |
creen | -0.356 |
ovember | -0.344 |
MU | -0.341 |
belie | -0.317 |
hur | -0.313 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Rocks | +3.619 |
iant | +3.446 |
arily | +3.390 |
Narc | +3.377 |
bow | +3.357 |
Neg logit contributions | |
creen | -4.329 |
ovember | -4.303 |
MU | -4.181 |
iffe | -3.867 |
uckle | -3.864 |
Token | dedicated |
Token ID | 7256 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Rocks | +1.912 |
iant | +1.804 |
arily | +1.798 |
bow | +1.766 |
iants | +1.766 |
Neg logit contributions | |
creen | -1.999 |
ovember | -1.953 |
MU | -1.927 |
hur | -1.760 |
iffe | -1.757 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Rocks | +0.806 |
iant | +0.763 |
arily | +0.760 |
bow | +0.751 |
iants | +0.750 |
Neg logit contributions | |
creen | -0.893 |
ovember | -0.869 |
MU | -0.859 |
belie | -0.802 |
captcha | -0.791 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Rocks | +4.563 |
--> | +4.262 |
bow | +4.208 |
Pet | +4.187 |
Narc | +4.177 |
Neg logit contributions | |
creen | -4.497 |
ovember | -4.432 |
MU | -4.244 |
captcha | -4.033 |
belie | -4.007 |
Token | to |
Token ID | 284 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Rocks | +4.908 |
--> | +4.752 |
arily | +4.718 |
iant | +4.563 |
bow | +4.542 |
Neg logit contributions | |
creen | -7.139 |
MU | -7.061 |
ovember | -7.050 |
iffe | -6.442 |
hur | -6.382 |
Token | 21 |
Token ID | 2310 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
creen | +1.704 |
ovember | +1.620 |
MU | +1.609 |
belie | +1.454 |
hur | +1.414 |
Neg logit contributions | |
Rocks | -2.757 |
iant | -2.625 |
iants | -2.624 |
arily | -2.624 |
ogyn | -2.603 |
Token | among |
Token ID | 1871 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Rocks | +3.949 |
arily | +3.734 |
iant | +3.705 |
bow | +3.690 |
Pet | +3.676 |
Neg logit contributions | |
creen | -3.120 |
MU | -3.051 |
ovember | -3.050 |
hur | -2.671 |
ioxide | -2.663 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Rocks | +3.039 |
Narc | +2.830 |
arily | +2.827 |
iant | +2.810 |
iants | +2.799 |
Neg logit contributions | |
creen | -2.453 |
ovember | -2.380 |
MU | -2.360 |
belie | -2.088 |
hur | -2.082 |
Token | , |
Token ID | 11 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Rocks | +6.827 |
Pet | +6.497 |
arily | +6.217 |
bow | +6.090 |
GY | +6.081 |
Neg logit contributions | |
creen | -15.974 |
ovember | -15.262 |
MU | -14.626 |
iffe | -14.552 |
veland | -14.338 |
Token | 488 |
Token ID | 33646 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Rocks | +4.017 |
iant | +3.807 |
arily | +3.733 |
--> | +3.731 |
iants | +3.731 |
Neg logit contributions | |
creen | -4.100 |
ovember | -3.992 |
MU | -3.901 |
iffe | -3.668 |
belie | -3.667 |
Token | voters |
Token ID | 4446 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
creen | +1.530 |
ovember | +1.465 |
MU | +1.455 |
belie | +1.350 |
hur | +1.333 |
Neg logit contributions | |
Rocks | -1.737 |
iant | -1.638 |
arily | -1.631 |
ogyn | -1.620 |
iants | -1.616 |
Token | in |
Token ID | 287 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Rocks | +2.189 |
arily | +2.082 |
iant | +2.040 |
Narc | +2.034 |
bow | +2.025 |
Neg logit contributions | |
creen | -2.047 |
MU | -2.006 |
ovember | -2.002 |
belie | -1.807 |
hur | -1.790 |
Token | Florida |
Token ID | 4744 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
creen | +1.771 |
ovember | +1.697 |
MU | +1.686 |
belie | +1.563 |
captcha | +1.525 |
Neg logit contributions | |
Rocks | -2.191 |
iant | -2.075 |
arily | -2.072 |
--> | -2.067 |
iants | -2.064 |
Token | : |
Token ID | 25 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
creen | +1.735 |
MU | +1.677 |
ovember | +1.673 |
belie | +1.539 |
hur | +1.514 |
Neg logit contributions | |
Rocks | -1.709 |
iant | -1.628 |
arily | -1.621 |
iants | -1.604 |
bow | -1.591 |
Token | Sherman |
Token ID | 23198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Rocks | +2.268 |
iant | +2.070 |
iants | +2.065 |
arily | +2.058 |
Narc | +2.055 |
Neg logit contributions | |
creen | -2.457 |
ovember | -2.383 |
MU | -2.336 |
iffe | -2.183 |
belie | -2.183 |
Token | suffered |
Token ID | 6989 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Rocks | +2.307 |
arily | +2.147 |
iant | +2.133 |
bow | +2.129 |
--> | +2.123 |
Neg logit contributions | |
creen | -2.716 |
ovember | -2.652 |
MU | -2.633 |
belie | -2.395 |
uckle | -2.391 |
Token | a |
Token ID | 257 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
Rocks | +6.482 |
Hubbard | +5.877 |
iant | +5.838 |
arily | +5.779 |
bow | +5.752 |
Neg logit contributions | |
creen | -9.710 |
ovember | -9.460 |
MU | -9.254 |
iffe | -8.658 |
ioxide | -8.647 |
Token | rupt |
Token ID | 31580 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Rocks | +7.725 |
Narc | +7.019 |
iant | +6.999 |
arily | +6.990 |
Hubbard | +6.955 |
Neg logit contributions | |
creen | -9.131 |
ovember | -9.033 |
MU | -8.624 |
ioxide | -8.161 |
iffe | -8.036 |
Token | ured |
Token ID | 1522 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
arily | +3.912 |
iant | +3.771 |
Rocks | +3.717 |
bow | +3.598 |
ogyn | +3.499 |
Neg logit contributions | |
creen | -8.634 |
MU | -8.525 |
ovember | -8.454 |
belie | -8.109 |
captcha | -8.092 |
Token | Achilles |
Token ID | 39561 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Rocks | +9.499 |
Narc | +9.115 |
iant | +8.954 |
narcissistic | +8.749 |
ACS | +8.701 |
Neg logit contributions | |
creen | -13.506 |
ovember | -12.828 |
MU | -12.748 |
ioxide | -12.104 |
UGH | -12.030 |
Token | tendon |
Token ID | 42205 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Rocks | +4.041 |
iant | +3.746 |
bow | +3.742 |
--> | +3.696 |
iants | +3.670 |
Neg logit contributions | |
creen | -6.739 |
ovember | -6.569 |
MU | -6.558 |
iffe | -6.142 |
belie | -6.085 |
Token | in |
Token ID | 287 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Rocks | +2.115 |
arily | +1.988 |
iant | +1.984 |
iants | +1.961 |
bow | +1.961 |
Neg logit contributions | |
creen | -2.105 |
ovember | -2.031 |
MU | -2.023 |
belie | -1.860 |
hur | -1.837 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Rocks | +4.129 |
iant | +3.834 |
iants | +3.821 |
--> | +3.814 |
Narc | +3.803 |
Neg logit contributions | |
creen | -4.686 |
ovember | -4.539 |
MU | -4.520 |
uckle | -4.130 |
iffe | -4.124 |
Token | 's |
Token ID | 338 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Rocks | +1.974 |
arily | +1.840 |
iant | +1.827 |
--> | +1.808 |
bow | +1.805 |
Neg logit contributions | |
creen | -2.721 |
ovember | -2.630 |
MU | -2.596 |
belie | -2.417 |
hur | -2.406 |
Token | and |
Token ID | 290 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
Rocks | +2.108 |
arily | +1.993 |
iant | +1.992 |
bow | +1.962 |
--> | +1.946 |
Neg logit contributions | |
creen | -2.472 |
ovember | -2.412 |
MU | -2.391 |
belie | -2.198 |
hur | -2.193 |
Token | caring |
Token ID | 18088 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Rocks | +0.724 |
arily | +0.679 |
iant | +0.678 |
iants | +0.668 |
--> | +0.667 |
Neg logit contributions | |
creen | -0.767 |
ovember | -0.741 |
MU | -0.736 |
belie | -0.678 |
hur | -0.673 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Rocks | +2.437 |
iant | +2.292 |
arily | +2.285 |
--> | +2.260 |
bow | +2.247 |
Neg logit contributions | |
creen | -2.818 |
ovember | -2.759 |
MU | -2.712 |
belie | -2.498 |
hur | -2.492 |
Token |
|
Token ID | 198 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
Rocks | +2.305 |
Pet | +2.098 |
Narc | +2.078 |
iant | +2.075 |
--> | +2.073 |
Neg logit contributions | |
creen | -2.990 |
ovember | -2.901 |
MU | -2.831 |
belie | -2.698 |
captcha | -2.653 |
Token |
|
Token ID | 198 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Rocks | +0.487 |
arily | +0.453 |
iant | +0.451 |
--> | +0.445 |
bow | +0.445 |
Neg logit contributions | |
creen | -0.662 |
ovember | -0.643 |
MU | -0.637 |
belie | -0.597 |
hur | -0.589 |
Token | T |
Token ID | 51 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Rocks | +2.035 |
Pet | +1.927 |
--> | +1.912 |
iant | +1.903 |
bow | +1.899 |
Neg logit contributions | |
creen | -2.595 |
ovember | -2.506 |
MU | -2.439 |
belie | -2.346 |
captcha | -2.310 |
Token | oys |
Token ID | 19417 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Rocks | +8.434 |
iant | +8.315 |
iants | +8.053 |
NS | +7.868 |
GY | +7.861 |
Neg logit contributions | |
creen | -14.156 |
belie | -13.273 |
MU | -13.144 |
captcha | -13.141 |
ovember | -13.141 |
Token | online |
Token ID | 2691 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Rocks | +1.069 |
arily | +1.001 |
iant | +0.998 |
--> | +0.986 |
iants | +0.985 |
Neg logit contributions | |
creen | -1.100 |
ovember | -1.067 |
MU | -1.056 |
belie | -0.972 |
hur | -0.964 |
Token | in |
Token ID | 287 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Rocks | +2.856 |
arily | +2.651 |
iant | +2.641 |
--> | +2.635 |
bow | +2.596 |
Neg logit contributions | |
creen | -3.626 |
ovember | -3.546 |
MU | -3.508 |
hur | -3.243 |
iffe | -3.240 |
Token | Pakistan |
Token ID | 7648 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
creen | +1.647 |
ovember | +1.585 |
MU | +1.574 |
belie | +1.468 |
hur | +1.435 |
Neg logit contributions | |
Rocks | -1.594 |
arily | -1.506 |
iant | -1.504 |
iants | -1.494 |
ogyn | -1.483 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Rocks | +0.782 |
arily | +0.727 |
iant | +0.726 |
--> | +0.717 |
iants | +0.716 |
Neg logit contributions | |
creen | -0.921 |
ovember | -0.892 |
MU | -0.886 |
belie | -0.820 |
hur | -0.814 |
Token | source |
Token ID | 2723 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
creen | +1.000 |
ovember | +0.963 |
MU | +0.955 |
belie | +0.886 |
hur | +0.874 |
Neg logit contributions | |
Rocks | -0.970 |
arily | -0.916 |
iant | -0.907 |
iants | -0.904 |
ogyn | -0.896 |
Token | of |
Token ID | 286 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
creen | +0.955 |
ovember | +0.920 |
MU | +0.914 |
belie | +0.849 |
hur | +0.831 |
Neg logit contributions | |
Rocks | -1.031 |
arily | -0.973 |
iant | -0.968 |
iants | -0.965 |
--> | -0.959 |
Token | education |
Token ID | 3707 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Rocks | +1.943 |
iant | +1.815 |
arily | +1.796 |
Narc | +1.791 |
--> | +1.790 |
Neg logit contributions | |
creen | -1.990 |
ovember | -1.918 |
MU | -1.910 |
hur | -1.736 |
iffe | -1.735 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Rocks | +0.779 |
arily | +0.727 |
iant | +0.725 |
iants | +0.715 |
--> | +0.715 |
Neg logit contributions | |
creen | -0.940 |
ovember | -0.909 |
MU | -0.902 |
belie | -0.840 |
hur | -0.830 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Rocks | +1.010 |
arily | +0.937 |
iant | +0.931 |
--> | +0.928 |
bow | +0.927 |
Neg logit contributions | |
creen | -1.461 |
ovember | -1.427 |
MU | -1.400 |
belie | -1.328 |
captcha | -1.302 |
Token | T |
Token ID | 51 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Rocks | +2.464 |
Pet | +2.345 |
--> | +2.319 |
bow | +2.307 |
iant | +2.297 |
Neg logit contributions | |
creen | -3.133 |
ovember | -3.023 |
MU | -2.937 |
belie | -2.845 |
captcha | -2.803 |
Token | oys |
Token ID | 19417 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Rocks | +6.714 |
iant | +6.630 |
NS | +6.379 |
oys | +6.312 |
iants | +6.295 |
Neg logit contributions | |
creen | -15.782 |
belie | -14.924 |
captcha | -14.909 |
ovember | -14.803 |
MU | -14.759 |
Token | are |
Token ID | 389 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
Rocks | +2.282 |
arily | +2.130 |
iant | +2.126 |
bow | +2.105 |
--> | +2.105 |
Neg logit contributions | |
creen | -2.409 |
ovember | -2.358 |
MU | -2.324 |
belie | -2.128 |
iffe | -2.125 |
Token | also |
Token ID | 635 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
creen | +0.181 |
ovember | +0.174 |
MU | +0.173 |
belie | +0.161 |
hur | +0.158 |
Neg logit contributions | |
Rocks | -0.174 |
arily | -0.163 |
iant | -0.162 |
iants | -0.161 |
--> | -0.160 |
Token | an |
Token ID | 281 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
creen | +1.024 |
ovember | +0.981 |
MU | +0.978 |
belie | +0.916 |
hur | +0.894 |
Neg logit contributions | |
Rocks | -0.978 |
arily | -0.919 |
iant | -0.915 |
iants | -0.913 |
bow | -0.905 |
Token | educational |
Token ID | 9856 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
creen | +0.727 |
ovember | +0.705 |
MU | +0.702 |
belie | +0.658 |
hur | +0.647 |
Neg logit contributions | |
Rocks | -0.618 |
arily | -0.576 |
iant | -0.573 |
iants | -0.571 |
bow | -0.570 |
Token | Civil |
Token ID | 32610 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
Rocks | +2.346 |
Pet | +2.209 |
iant | +2.207 |
arily | +2.207 |
bow | +2.193 |
Neg logit contributions | |
creen | -2.914 |
ovember | -2.822 |
MU | -2.751 |
belie | -2.632 |
captcha | -2.578 |
Token | Vessel |
Token ID | 44734 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
Rocks | +0.022 |
arily | +0.019 |
iant | +0.019 |
iants | +0.018 |
--> | +0.018 |
Neg logit contributions | |
creen | -0.076 |
ovember | -0.074 |
MU | -0.073 |
belie | -0.070 |
hur | -0.069 |
Token | s |
Token ID | 82 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Rocks | +0.294 |
arily | +0.276 |
iant | +0.275 |
iants | +0.272 |
bow | +0.271 |
Neg logit contributions | |
creen | -0.298 |
ovember | -0.288 |
MU | -0.285 |
belie | -0.264 |
hur | -0.260 |
Token |
|
Token ID | 198 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Rocks | +1.303 |
arily | +1.212 |
iant | +1.209 |
--> | +1.193 |
iants | +1.191 |
Neg logit contributions | |
creen | -1.532 |
ovember | -1.490 |
MU | -1.474 |
belie | -1.367 |
hur | -1.353 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Rocks | +2.642 |
--> | +2.447 |
bow | +2.442 |
arily | +2.437 |
Pet | +2.405 |
Neg logit contributions | |
creen | -4.538 |
ovember | -4.509 |
MU | -4.330 |
belie | -4.211 |
captcha | -4.163 |
Token | N |
Token ID | 45 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Rocks | +3.238 |
Pet | +3.114 |
iant | +3.070 |
arily | +3.067 |
bow | +3.062 |
Neg logit contributions | |
creen | -4.001 |
ovember | -3.877 |
MU | -3.714 |
belie | -3.639 |
captcha | -3.585 |
Token | uclear |
Token ID | 4016 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
iant | +10.898 |
bow | +10.595 |
ominated | +10.556 |
arily | +10.349 |
iants | +10.054 |
Neg logit contributions | |
creen | -11.959 |
belie | -11.139 |
captcha | -10.893 |
MU | -10.606 |
ovember | -10.533 |
Token | propulsion |
Token ID | 38873 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Rocks | +1.905 |
arily | +1.795 |
iant | +1.785 |
bow | +1.756 |
Pet | +1.749 |
Neg logit contributions | |
creen | -2.206 |
ovember | -2.149 |
MU | -2.113 |
belie | -1.962 |
captcha | -1.934 |
Token | has |
Token ID | 468 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Rocks | +2.421 |
arily | +2.286 |
iant | +2.276 |
--> | +2.232 |
bow | +2.229 |
Neg logit contributions | |
creen | -2.723 |
ovember | -2.656 |
MU | -2.609 |
uckle | -2.400 |
belie | -2.390 |
Token | proven |
Token ID | 9157 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
Rocks | +1.206 |
arily | +1.133 |
iant | +1.121 |
iants | +1.104 |
bow | +1.104 |
Neg logit contributions | |
creen | -1.450 |
ovember | -1.409 |
MU | -1.398 |
belie | -1.291 |
hur | -1.281 |
Token | technically |
Token ID | 14497 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Rocks | +0.737 |
arily | +0.698 |
iant | +0.695 |
iants | +0.683 |
bow | +0.682 |
Neg logit contributions | |
creen | -0.814 |
ovember | -0.791 |
MU | -0.779 |
belie | -0.720 |
hur | -0.714 |
Token | . |
Token ID | 13 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
creen | +3.222 |
ovember | +3.076 |
MU | +3.064 |
belie | +2.868 |
emp | +2.788 |
Neg logit contributions | |
Rocks | -3.415 |
iant | -3.199 |
iants | -3.185 |
arily | -3.177 |
ogyn | -3.167 |
Token | All |
Token ID | 1439 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Rocks | +4.024 |
Narc | +3.697 |
Pet | +3.593 |
ACS | +3.564 |
bow | +3.553 |
Neg logit contributions | |
creen | -5.080 |
ovember | -4.916 |
MU | -4.779 |
belie | -4.615 |
veland | -4.541 |
Token | treatments |
Token ID | 13820 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Rocks | +4.233 |
arily | +4.001 |
iant | +3.978 |
iants | +3.948 |
bow | +3.897 |
Neg logit contributions | |
creen | -4.808 |
MU | -4.606 |
ovember | -4.548 |
veland | -4.282 |
belie | -4.279 |
Token | were |
Token ID | 547 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Rocks | +2.168 |
arily | +2.048 |
iant | +2.032 |
--> | +1.999 |
Narc | +1.987 |
Neg logit contributions | |
creen | -2.434 |
ovember | -2.390 |
MU | -2.366 |
hur | -2.171 |
belie | -2.168 |
Token | self |
Token ID | 2116 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Rocks | +2.164 |
arily | +2.058 |
iant | +2.000 |
Narc | +1.990 |
bow | +1.987 |
Neg logit contributions | |
creen | -2.438 |
ovember | -2.370 |
MU | -2.346 |
hur | -2.178 |
belie | -2.173 |
Token | - |
Token ID | 12 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
arily | +7.287 |
Rocks | +6.696 |
GY | +6.491 |
Hubbard | +6.491 |
bow | +6.444 |
Neg logit contributions | |
ovember | -11.098 |
MU | -10.821 |
creen | -10.653 |
ioxide | -10.344 |
veland | -10.162 |
Token | administ |
Token ID | 39081 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
arily | +7.790 |
bow | +7.569 |
ogyn | +7.482 |
GY | +7.353 |
Pet | +7.276 |
Neg logit contributions | |
ovember | -13.941 |
ioxide | -13.235 |
MU | -13.016 |
captcha | -12.986 |
belie | -12.968 |
Token | ered |
Token ID | 1068 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Rocks | +0.653 |
arily | +0.587 |
iant | +0.586 |
iants | +0.560 |
bow | +0.556 |
Neg logit contributions | |
creen | -2.586 |
ovember | -2.530 |
MU | -2.524 |
belie | -2.409 |
captcha | -2.380 |
Token | by |
Token ID | 416 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
Rocks | +3.478 |
arily | +3.283 |
Narc | +3.229 |
iant | +3.185 |
bow | +3.181 |
Neg logit contributions | |
creen | -4.148 |
ovember | -4.082 |
MU | -4.037 |
hur | -3.743 |
veland | -3.740 |
Token | the |
Token ID | 262 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Rocks | +4.892 |
Narc | +4.579 |
arily | +4.550 |
ACS | +4.526 |
iant | +4.444 |
Neg logit contributions | |
creen | -5.816 |
MU | -5.580 |
ovember | -5.515 |
veland | -5.236 |
hur | -5.129 |
Token | patients |
Token ID | 3871 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Rocks | +3.622 |
Narc | +3.376 |
iant | +3.346 |
arily | +3.337 |
bow | +3.316 |
Neg logit contributions | |
creen | -4.206 |
MU | -4.037 |
ovember | -4.001 |
veland | -3.715 |
belie | -3.707 |
Token | - |
Token ID | 12 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Rocks | +1.773 |
iant | +1.664 |
arily | +1.663 |
--> | +1.635 |
iants | +1.632 |
Neg logit contributions | |
creen | -1.789 |
ovember | -1.730 |
MU | -1.705 |
hur | -1.568 |
belie | -1.564 |
Token | working |
Token ID | 16090 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Rocks | +7.122 |
iant | +6.903 |
bow | +6.807 |
arily | +6.673 |
awed | +6.653 |
Neg logit contributions | |
ovember | -7.799 |
creen | -7.634 |
MU | -7.217 |
captcha | -6.939 |
iffe | -6.803 |
Token | , |
Token ID | 11 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Rocks | +1.259 |
arily | +1.183 |
iant | +1.176 |
iants | +1.160 |
bow | +1.160 |
Neg logit contributions | |
creen | -1.428 |
ovember | -1.391 |
MU | -1.366 |
belie | -1.267 |
hur | -1.256 |
Token | organized |
Token ID | 8389 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Rocks | +5.045 |
iant | +4.837 |
Narc | +4.740 |
arily | +4.720 |
bow | +4.691 |
Neg logit contributions | |
ovember | -5.749 |
creen | -5.728 |
MU | -5.479 |
iffe | -5.187 |
uckle | -5.128 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
creen | +1.086 |
MU | +1.040 |
ovember | +1.039 |
belie | +0.966 |
hur | +0.947 |
Neg logit contributions | |
Rocks | -1.051 |
iant | -0.980 |
arily | -0.980 |
iants | -0.973 |
--> | -0.969 |
Token | self |
Token ID | 2116 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Rocks | +2.737 |
iant | +2.590 |
arily | +2.557 |
bow | +2.534 |
Narc | +2.534 |
Neg logit contributions | |
creen | -3.230 |
ovember | -3.196 |
MU | -3.122 |
iffe | -2.886 |
uckle | -2.875 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
arily | +8.843 |
Rocks | +8.600 |
iant | +8.374 |
Hubbard | +8.137 |
narcissistic | +8.109 |
Neg logit contributions | |
ovember | -13.298 |
creen | -13.194 |
MU | -12.537 |
captcha | -12.113 |
uckle | -12.047 |
Token | mot |
Token ID | 27926 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iant | +9.157 |
bow | +8.867 |
Pet | +8.714 |
arily | +8.714 |
--> | +8.618 |
Neg logit contributions | |
ovember | -14.065 |
creen | -13.193 |
captcha | -12.839 |
MU | -12.674 |
ioxide | -12.448 |
Token | ivated |
Token ID | 30829 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
iant | +5.103 |
arily | +4.981 |
Rocks | +4.981 |
ogyn | +4.859 |
bow | +4.846 |
Neg logit contributions | |
ovember | -7.365 |
creen | -7.349 |
MU | -7.253 |
captcha | -6.775 |
ioxide | -6.654 |
Token | , |
Token ID | 11 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Rocks | +0.326 |
arily | +0.305 |
iant | +0.304 |
iants | +0.301 |
bow | +0.300 |
Neg logit contributions | |
creen | -0.356 |
ovember | -0.344 |
MU | -0.341 |
belie | -0.317 |
hur | -0.313 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Rocks | +3.619 |
iant | +3.446 |
arily | +3.390 |
Narc | +3.377 |
bow | +3.357 |
Neg logit contributions | |
creen | -4.329 |
ovember | -4.303 |
MU | -4.181 |
iffe | -3.867 |
uckle | -3.864 |
Token | in |
Token ID | 259 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
bow | +5.153 |
Rocks | +5.081 |
iant | +5.039 |
arily | +4.974 |
--> | +4.964 |
Neg logit contributions | |
creen | -5.725 |
ovember | -5.531 |
MU | -5.437 |
belie | -5.267 |
captcha | -5.183 |
Token | jury |
Token ID | 21871 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Rocks | +1.950 |
iant | +1.874 |
arily | +1.874 |
bow | +1.872 |
iants | +1.861 |
Neg logit contributions | |
creen | -0.984 |
MU | -0.938 |
ovember | -0.933 |
belie | -0.838 |
captcha | -0.811 |
Token | / |
Token ID | 14 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Rocks | +1.970 |
bow | +1.860 |
iant | +1.858 |
arily | +1.855 |
--> | +1.841 |
Neg logit contributions | |
creen | -2.585 |
ovember | -2.517 |
MU | -2.505 |
belie | -2.362 |
captcha | -2.315 |
Token | w |
Token ID | 86 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Rocks | +3.959 |
bow | +3.868 |
iant | +3.787 |
--> | +3.762 |
iants | +3.748 |
Neg logit contributions | |
creen | -4.600 |
ovember | -4.458 |
MU | -4.402 |
belie | -4.174 |
captcha | -4.063 |
Token | is |
Token ID | 271 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
iant | +4.825 |
arily | +4.822 |
Rocks | +4.753 |
iants | +4.742 |
bow | +4.720 |
Neg logit contributions | |
creen | -5.918 |
MU | -5.791 |
ovember | -5.661 |
belie | -5.505 |
captcha | -5.369 |
Token | q |
Token ID | 80 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Rocks | +1.212 |
arily | +1.125 |
iant | +1.125 |
bow | +1.121 |
iants | +1.109 |
Neg logit contributions | |
creen | -1.814 |
MU | -1.766 |
ovember | -1.762 |
belie | -1.668 |
hur | -1.631 |
Token | ars |
Token ID | 945 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Rocks | +7.809 |
arily | +7.732 |
bow | +7.683 |
iants | +7.550 |
iant | +7.439 |
Neg logit contributions | |
MU | -13.520 |
creen | -13.241 |
belie | -12.991 |
captcha | -12.801 |
UGH | -12.730 |
Token | / |
Token ID | 14 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Rocks | +3.730 |
iant | +3.497 |
bow | +3.466 |
arily | +3.458 |
--> | +3.435 |
Neg logit contributions | |
creen | -4.035 |
ovember | -3.952 |
MU | -3.928 |
belie | -3.668 |
captcha | -3.615 |
Token | f |
Token ID | 69 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Rocks | +2.605 |
bow | +2.450 |
iant | +2.440 |
arily | +2.422 |
--> | +2.414 |
Neg logit contributions | |
creen | -2.946 |
ovember | -2.854 |
MU | -2.810 |
belie | -2.641 |
uckle | -2.581 |
Token | atal |
Token ID | 10254 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
Rocks | +1.778 |
iant | +1.690 |
arily | +1.689 |
bow | +1.668 |
iants | +1.666 |
Neg logit contributions | |
creen | -1.952 |
ovember | -1.857 |
MU | -1.853 |
belie | -1.734 |
captcha | -1.690 |
Token | . |
Token ID | 13 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
creen | +0.353 |
ovember | +0.342 |
MU | +0.339 |
belie | +0.316 |
hur | +0.312 |
Neg logit contributions | |
Rocks | -0.298 |
arily | -0.278 |
iant | -0.277 |
iants | -0.274 |
bow | -0.274 |
Token | recovering |
Token ID | 20222 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
creen | +3.970 |
ovember | +3.929 |
MU | +3.843 |
belie | +3.668 |
hur | +3.543 |
Neg logit contributions | |
Rocks | -4.587 |
ogyn | -4.506 |
--> | -4.479 |
iants | -4.468 |
iant | -4.422 |
Token | after |
Token ID | 706 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
creen | +2.222 |
MU | +2.132 |
ovember | +2.125 |
belie | +2.005 |
iffe | +1.949 |
Neg logit contributions | |
Rocks | -2.145 |
iant | -2.024 |
arily | -2.022 |
iants | -2.017 |
--> | -2.014 |
Token | treatment |
Token ID | 3513 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Rocks | +0.051 |
arily | +0.048 |
iant | +0.048 |
iants | +0.047 |
bow | +0.047 |
Neg logit contributions | |
creen | -0.043 |
ovember | -0.042 |
MU | -0.042 |
belie | -0.038 |
hur | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
creen | +1.793 |
ovember | +1.722 |
MU | +1.712 |
belie | +1.594 |
hur | +1.570 |
Neg logit contributions | |
Rocks | -1.669 |
iant | -1.566 |
arily | -1.564 |
iants | -1.553 |
bow | -1.547 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
creen | +0.594 |
ovember | +0.573 |
MU | +0.570 |
belie | +0.532 |
hur | +0.522 |
Neg logit contributions | |
Rocks | -0.553 |
arily | -0.521 |
iant | -0.518 |
iants | -0.515 |
--> | -0.513 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Rocks | +2.184 |
arily | +2.033 |
iant | +2.024 |
bow | +2.017 |
Narc | +1.991 |
Neg logit contributions | |
creen | -2.468 |
ovember | -2.397 |
MU | -2.365 |
belie | -2.179 |
hur | -2.172 |
Token | jaw |
Token ID | 19218 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Rocks | +8.475 |
bow | +8.442 |
Narc | +7.876 |
arily | +7.773 |
Hubbard | +7.656 |
Neg logit contributions | |
creen | -13.477 |
MU | -12.987 |
ovember | -12.742 |
ioxide | -12.221 |
hur | -12.154 |
Token | and |
Token ID | 290 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
creen | +0.191 |
ovember | +0.184 |
MU | +0.183 |
belie | +0.170 |
hur | +0.167 |
Neg logit contributions | |
Rocks | -0.176 |
arily | -0.165 |
iant | -0.165 |
iants | -0.163 |
--> | -0.162 |
Token | rupt |
Token ID | 31580 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Rocks | +0.533 |
arily | +0.498 |
iant | +0.496 |
bow | +0.490 |
iants | +0.490 |
Neg logit contributions | |
creen | -0.601 |
ovember | -0.581 |
MU | -0.577 |
belie | -0.534 |
hur | -0.528 |
Token | ured |
Token ID | 1522 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Rocks | +2.954 |
iant | +2.944 |
arily | +2.927 |
bow | +2.795 |
iants | +2.767 |
Neg logit contributions | |
creen | -5.982 |
MU | -5.956 |
ovember | -5.863 |
belie | -5.630 |
captcha | -5.604 |
Token | eye |
Token ID | 4151 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Rocks | +6.958 |
Narc | +6.441 |
iant | +6.340 |
bow | +6.287 |
narcissistic | +6.176 |
Neg logit contributions | |
creen | -9.273 |
MU | -8.935 |
ovember | -8.916 |
veland | -8.281 |
ioxide | -8.261 |
Token | post |
Token ID | 1281 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Rocks | +1.855 |
arily | +1.747 |
iant | +1.731 |
--> | +1.726 |
Narc | +1.705 |
Neg logit contributions | |
creen | -2.063 |
ovember | -1.999 |
MU | -1.975 |
belie | -1.812 |
hur | -1.810 |
Token | – |
Token ID | 1906 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
creen | +0.502 |
ovember | +0.484 |
MU | +0.481 |
belie | +0.445 |
hur | +0.439 |
Neg logit contributions | |
Rocks | -0.491 |
arily | -0.460 |
iant | -0.459 |
iants | -0.454 |
bow | -0.453 |
Token | absor |
Token ID | 46303 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
creen | +2.565 |
MU | +2.503 |
ovember | +2.471 |
hur | +2.319 |
emp | +2.289 |
Neg logit contributions | |
Rocks | -2.048 |
arily | -1.864 |
iant | -1.854 |
iants | -1.850 |
ogyn | -1.830 |
Token | ptive |
Token ID | 21665 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
creen | +3.187 |
ovember | +2.945 |
MU | +2.907 |
hur | +2.664 |
veland | +2.626 |
Neg logit contributions | |
Rocks | -5.907 |
arily | -5.458 |
GY | -5.418 |
iants | -5.396 |
--> | -5.390 |
Token | state |
Token ID | 1181 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
creen | +1.504 |
MU | +1.431 |
ovember | +1.425 |
belie | +1.309 |
hur | +1.262 |
Neg logit contributions | |
Rocks | -2.337 |
iant | -2.205 |
iants | -2.200 |
arily | -2.198 |
ogyn | -2.190 |
Token | lasts |
Token ID | 20374 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Rocks | +0.627 |
arily | +0.587 |
iant | +0.585 |
--> | +0.579 |
bow | +0.577 |
Neg logit contributions | |
creen | -0.689 |
ovember | -0.667 |
MU | -0.662 |
belie | -0.612 |
hur | -0.604 |
Token | until |
Token ID | 1566 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Rocks | +8.587 |
arily | +8.389 |
--> | +8.283 |
Narc | +7.953 |
Hubbard | +7.795 |
Neg logit contributions | |
ovember | -12.859 |
creen | -12.686 |
MU | -12.467 |
ioxide | -11.971 |
iffe | -11.957 |
Token | 8 |
Token ID | 807 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Rocks | +4.309 |
arily | +4.164 |
--> | +4.124 |
Narc | +4.028 |
iant | +4.021 |
Neg logit contributions | |
creen | -5.464 |
ovember | -5.331 |
MU | -5.239 |
hur | -4.941 |
captcha | -4.835 |
Token | to |
Token ID | 284 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
creen | +2.045 |
ovember | +1.985 |
MU | +1.975 |
hur | +1.790 |
belie | +1.790 |
Neg logit contributions | |
Rocks | -2.259 |
arily | -2.109 |
iants | -2.102 |
iant | -2.101 |
ogyn | -2.098 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
creen | +0.452 |
ovember | +0.433 |
MU | +0.430 |
belie | +0.395 |
hur | +0.386 |
Neg logit contributions | |
Rocks | -0.564 |
arily | -0.532 |
iant | -0.532 |
iants | -0.528 |
bow | -0.525 |
Token | hours |
Token ID | 2250 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
creen | +1.445 |
ovember | +1.390 |
MU | +1.378 |
belie | +1.248 |
hur | +1.243 |
Neg logit contributions | |
Rocks | -1.845 |
arily | -1.733 |
iant | -1.728 |
iants | -1.724 |
ogyn | -1.718 |
Token | ' |
Token ID | 6 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Rocks | +4.187 |
iant | +4.056 |
arily | +3.922 |
bow | +3.880 |
iants | +3.869 |
Neg logit contributions | |
creen | -5.479 |
ovember | -5.385 |
MU | -5.268 |
captcha | -5.033 |
belie | -4.982 |
Token | O |
Token ID | 46 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Rocks | +1.643 |
iant | +1.552 |
arily | +1.548 |
iants | +1.531 |
Pet | +1.526 |
Neg logit contributions | |
creen | -1.913 |
ovember | -1.863 |
MU | -1.816 |
belie | -1.717 |
captcha | -1.681 |
Token | mb |
Token ID | 2022 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
creen | +3.785 |
ovember | +3.672 |
MU | +3.603 |
iffe | +3.324 |
hur | +3.271 |
Neg logit contributions | |
Rocks | -4.337 |
arily | -4.091 |
Narc | -4.004 |
--> | -3.982 |
ogyn | -3.959 |
Token | re |
Token ID | 260 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Rocks | +2.817 |
iant | +2.743 |
bow | +2.675 |
iants | +2.671 |
ogyn | +2.667 |
Neg logit contributions | |
creen | -3.830 |
ovember | -3.692 |
MU | -3.622 |
belie | -3.431 |
captcha | -3.397 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Rocks | +1.302 |
iant | +1.220 |
arily | +1.212 |
iants | +1.199 |
bow | +1.199 |
Neg logit contributions | |
creen | -1.408 |
ovember | -1.365 |
MU | -1.351 |
belie | -1.245 |
hur | -1.234 |
Token | N |
Token ID | 45 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
creen | +1.406 |
MU | +1.369 |
ovember | +1.355 |
belie | +1.254 |
hur | +1.242 |
Neg logit contributions | |
Rocks | -1.281 |
arily | -1.218 |
iant | -1.204 |
ogyn | -1.190 |
iants | -1.188 |
Token | os |
Token ID | 418 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
iant | +9.445 |
ominated | +8.875 |
iants | +8.547 |
Rocks | +8.527 |
Pet | +8.471 |
Neg logit contributions | |
creen | -12.530 |
captcha | -11.830 |
belie | -11.519 |
MU | -11.257 |
Daytona | -10.974 |
Token | relations |
Token ID | 2316 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Rocks | +1.631 |
iant | +1.531 |
arily | +1.524 |
iants | +1.508 |
bow | +1.505 |
Neg logit contributions | |
creen | -1.859 |
ovember | -1.804 |
MU | -1.801 |
hur | -1.649 |
belie | -1.648 |
Token | diplomat |
Token ID | 28278 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
creen | +2.051 |
ovember | +1.980 |
MU | +1.969 |
belie | +1.869 |
hur | +1.809 |
Neg logit contributions | |
Rocks | -1.775 |
arily | -1.669 |
iant | -1.638 |
--> | -1.633 |
bow | -1.629 |
Token | iques |
Token ID | 6368 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
creen | +0.512 |
ovember | +0.496 |
MU | +0.493 |
belie | +0.459 |
hur | +0.453 |
Neg logit contributions | |
Rocks | -0.423 |
arily | -0.394 |
iant | -0.392 |
bow | -0.388 |
--> | -0.388 |
Token | a |
Token ID | 257 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Rocks | +4.285 |
iant | +4.028 |
Narc | +3.996 |
iants | +3.959 |
arily | +3.957 |
Neg logit contributions | |
creen | -5.032 |
ovember | -4.968 |
MU | -4.885 |
uckle | -4.502 |
hur | -4.466 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Rocks | +2.240 |
arily | +2.109 |
iant | +2.084 |
Narc | +2.060 |
bow | +2.051 |
Neg logit contributions | |
creen | -2.747 |
ovember | -2.682 |
MU | -2.618 |
hur | -2.459 |
uckle | -2.429 |
Token | the |
Token ID | 262 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
creen | +1.082 |
ovember | +1.046 |
MU | +1.042 |
belie | +0.970 |
hur | +0.939 |
Neg logit contributions | |
Rocks | -1.085 |
arily | -1.015 |
iant | -1.015 |
iants | -1.010 |
--> | -1.004 |
Token | confidence |
Token ID | 6628 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
creen | +0.738 |
ovember | +0.715 |
MU | +0.709 |
belie | +0.662 |
hur | +0.646 |
Neg logit contributions | |
Rocks | -0.687 |
arily | -0.644 |
iant | -0.643 |
iants | -0.638 |
ogyn | -0.634 |
Token | of |
Token ID | 286 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
creen | +0.928 |
ovember | +0.892 |
MU | +0.887 |
belie | +0.817 |
hur | +0.804 |
Neg logit contributions | |
Rocks | -1.006 |
arily | -0.944 |
iant | -0.942 |
iants | -0.934 |
--> | -0.933 |
Token | Parliament |
Token ID | 8411 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Rocks | +1.566 |
arily | +1.467 |
iant | +1.462 |
bow | +1.446 |
--> | +1.442 |
Neg logit contributions | |
creen | -1.775 |
ovember | -1.710 |
MU | -1.689 |
belie | -1.567 |
hur | -1.564 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
creen | +1.308 |
ovember | +1.254 |
MU | +1.248 |
belie | +1.154 |
hur | +1.135 |
Neg logit contributions | |
Rocks | -1.309 |
iant | -1.223 |
iants | -1.218 |
arily | -1.216 |
--> | -1.211 |
Token | 189 |
Token ID | 23362 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
MU | +8.153 |
creen | +7.591 |
iffe | +7.133 |
hur | +7.083 |
ovember | +6.928 |
Neg logit contributions | |
Rocks | -16.898 |
--> | -15.645 |
igree | -15.611 |
Narc | -15.451 |
iants | -15.445 |
Token | ] |
Token ID | 60 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
creen | +1.913 |
MU | +1.833 |
ovember | +1.810 |
belie | +1.647 |
hur | +1.639 |
Neg logit contributions | |
Rocks | -2.466 |
arily | -2.340 |
iant | -2.326 |
iants | -2.319 |
ogyn | -2.306 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
Rocks | +4.220 |
Narc | +3.868 |
Pet | +3.831 |
bow | +3.782 |
--> | +3.763 |
Neg logit contributions | |
creen | -5.509 |
ovember | -5.346 |
MU | -5.169 |
belie | -4.980 |
hur | -4.902 |
Token |
|
Token ID | 198 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Rocks | +0.300 |
arily | +0.279 |
iant | +0.278 |
iants | +0.274 |
bow | +0.274 |
Neg logit contributions | |
creen | -0.402 |
ovember | -0.390 |
MU | -0.387 |
belie | -0.362 |
hur | -0.357 |
Token | There |
Token ID | 1858 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Pet | +4.337 |
Rocks | +4.227 |
bow | +4.202 |
--> | +4.148 |
iant | +4.111 |
Neg logit contributions | |
creen | -6.048 |
ovember | -5.831 |
belie | -5.547 |
MU | -5.495 |
captcha | -5.429 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
creen | +0.236 |
ovember | +0.227 |
MU | +0.226 |
belie | +0.209 |
hur | +0.206 |
Neg logit contributions | |
Rocks | -0.237 |
arily | -0.223 |
iant | -0.222 |
iants | -0.220 |
bow | -0.219 |
Token | 14 |
Token ID | 1478 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Rocks | +1.461 |
arily | +1.372 |
--> | +1.364 |
iant | +1.361 |
bow | +1.352 |
Neg logit contributions | |
creen | -1.482 |
MU | -1.427 |
ovember | -1.424 |
belie | -1.303 |
hur | -1.297 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
creen | +2.496 |
ovember | +2.417 |
MU | +2.359 |
belie | +2.162 |
hur | +2.126 |
Neg logit contributions | |
Rocks | -3.573 |
iant | -3.412 |
arily | -3.406 |
ogyn | -3.394 |
iants | -3.359 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
creen | +1.365 |
ovember | +1.303 |
MU | +1.287 |
belie | +1.175 |
hur | +1.134 |
Neg logit contributions | |
Rocks | -2.122 |
arily | -2.015 |
iant | -2.013 |
iants | -1.995 |
ogyn | -1.995 |
Token | 17 |
Token ID | 1596 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
creen | +4.266 |
MU | +4.094 |
ovember | +4.058 |
belie | +3.816 |
captcha | +3.644 |
Neg logit contributions | |
Rocks | -6.107 |
ogyn | -5.852 |
iant | -5.774 |
arily | -5.764 |
Pet | -5.736 |
Token | 18 |
Token ID | 1248 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
creen | +7.842 |
ovember | +7.557 |
belie | +7.467 |
MU | +7.439 |
captcha | +7.078 |
Neg logit contributions | |
Rocks | -11.720 |
Sov | -11.458 |
ogyn | -11.435 |
Pet | -11.365 |
iants | -11.121 |
Token | 19 |
Token ID | 678 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
creen | +10.140 |
ovember | +10.030 |
MU | +9.439 |
captcha | +9.415 |
iffe | +9.307 |
Neg logit contributions | |
Rocks | -13.879 |
ogyn | -13.483 |
Pet | -13.199 |
iant | -13.121 |
iants | -13.087 |
Token | 20 |
Token ID | 1160 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
creen | +5.565 |
ovember | +5.432 |
MU | +5.333 |
belie | +4.840 |
captcha | +4.832 |
Neg logit contributions | |
Rocks | -9.720 |
iant | -9.437 |
iants | -9.360 |
ogyn | -9.325 |
arily | -9.268 |
Token | 21 |
Token ID | 2310 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
creen | +4.913 |
ovember | +4.759 |
MU | +4.698 |
belie | +4.208 |
captcha | +4.167 |
Neg logit contributions | |
Rocks | -7.495 |
arily | -7.196 |
ogyn | -7.137 |
iant | -7.130 |
awed | -7.124 |
Token | 22 |
Token ID | 2534 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Rocks | +0.299 |
arily | +0.282 |
iant | +0.280 |
--> | +0.278 |
bow | +0.278 |
Neg logit contributions | |
creen | -0.283 |
ovember | -0.273 |
MU | -0.270 |
belie | -0.249 |
hur | -0.247 |
Token | 23 |
Token ID | 2242 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
creen | +2.753 |
ovember | +2.648 |
MU | +2.622 |
belie | +2.447 |
captcha | +2.400 |
Neg logit contributions | |
Rocks | -2.847 |
iant | -2.691 |
iants | -2.674 |
arily | -2.661 |
ogyn | -2.661 |
Token | 13 |
Token ID | 1511 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
creen | +0.416 |
ovember | +0.401 |
MU | +0.398 |
belie | +0.369 |
hur | +0.363 |
Neg logit contributions | |
Rocks | -0.423 |
arily | -0.397 |
iant | -0.397 |
iants | -0.393 |
bow | -0.392 |
Token | 14 |
Token ID | 1478 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Rocks | +0.586 |
arily | +0.550 |
iant | +0.547 |
--> | +0.544 |
iants | +0.543 |
Neg logit contributions | |
creen | -0.570 |
ovember | -0.549 |
MU | -0.546 |
belie | -0.502 |
hur | -0.497 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
creen | +3.194 |
ovember | +3.088 |
MU | +3.027 |
belie | +2.746 |
captcha | +2.738 |
Neg logit contributions | |
Rocks | -4.890 |
iant | -4.718 |
arily | -4.710 |
ogyn | -4.691 |
iants | -4.641 |
Token | 16 |
Token ID | 1467 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
creen | +1.928 |
ovember | +1.837 |
MU | +1.826 |
belie | +1.655 |
captcha | +1.601 |
Neg logit contributions | |
Rocks | -3.349 |
arily | -3.198 |
iant | -3.196 |
iants | -3.166 |
ogyn | -3.164 |
Token | 17 |
Token ID | 1596 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
creen | +4.340 |
MU | +4.206 |
ovember | +4.076 |
belie | +3.865 |
captcha | +3.650 |
Neg logit contributions | |
Rocks | -7.315 |
ogyn | -7.069 |
Pet | -7.007 |
iant | -6.997 |
bow | -6.970 |
Token | 18 |
Token ID | 1248 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
creen | +7.593 |
MU | +7.445 |
ovember | +7.346 |
belie | +7.235 |
captcha | +6.937 |
Neg logit contributions | |
Rocks | -11.556 |
Pet | -11.353 |
Sov | -11.238 |
ogyn | -11.192 |
iant | -11.117 |
Token | 19 |
Token ID | 678 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
creen | +9.691 |
ovember | +9.574 |
MU | +9.326 |
captcha | +9.007 |
UGH | +8.911 |
Neg logit contributions | |
Rocks | -13.742 |
ogyn | -13.278 |
Pet | -13.222 |
iants | -13.118 |
iant | -13.090 |
Token | 20 |
Token ID | 1160 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
creen | +5.857 |
MU | +5.712 |
ovember | +5.696 |
captcha | +5.066 |
belie | +4.999 |
Neg logit contributions | |
Rocks | -10.954 |
iant | -10.781 |
iants | -10.690 |
arily | -10.599 |
Pet | -10.582 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
creen | +4.116 |
MU | +4.000 |
ovember | +3.948 |
captcha | +3.489 |
belie | +3.477 |
Neg logit contributions | |
Rocks | -6.998 |
arily | -6.686 |
Pet | -6.682 |
iant | -6.676 |
iants | -6.668 |
Token | 22 |
Token ID | 2534 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
creen | +0.880 |
ovember | +0.846 |
MU | +0.842 |
belie | +0.775 |
hur | +0.761 |
Neg logit contributions | |
Rocks | -0.981 |
arily | -0.923 |
iant | -0.923 |
iants | -0.915 |
bow | -0.910 |
Token | 23 |
Token ID | 2242 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
creen | +3.143 |
ovember | +3.020 |
MU | +3.003 |
belie | +2.787 |
captcha | +2.746 |
Neg logit contributions | |
Rocks | -3.302 |
iant | -3.136 |
iants | -3.134 |
ogyn | -3.100 |
arily | -3.092 |
Token | izes |
Token ID | 4340 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
creen | +0.244 |
ovember | +0.231 |
MU | +0.229 |
belie | +0.203 |
hur | +0.198 |
Neg logit contributions | |
Rocks | -0.469 |
arily | -0.449 |
iant | -0.447 |
iants | -0.444 |
--> | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
creen | +3.915 |
MU | +3.764 |
ovember | +3.731 |
belie | +3.545 |
hur | +3.336 |
Neg logit contributions | |
Rocks | -4.215 |
ogyn | -4.004 |
iants | -3.962 |
iant | -3.912 |
bow | -3.911 |
Token | body |
Token ID | 1767 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
creen | +7.758 |
MU | +7.478 |
belie | +7.324 |
ovember | +7.263 |
Daytona | +6.768 |
Neg logit contributions | |
Rocks | -7.560 |
ogyn | -7.368 |
iants | -7.219 |
igree | -7.050 |
iant | -6.973 |
Token | � |
Token ID | 447 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
MU | +6.280 |
creen | +6.269 |
ovember | +6.119 |
belie | +5.789 |
veland | +5.655 |
Neg logit contributions | |
Rocks | -7.092 |
iants | -6.821 |
ogyn | -6.742 |
igree | -6.632 |
bow | -6.615 |
Token | � |
Token ID | 247 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
creen | +2.694 |
MU | +2.650 |
ovember | +2.633 |
belie | +2.463 |
hur | +2.436 |
Neg logit contributions | |
Rocks | -1.976 |
arily | -1.819 |
iant | -1.814 |
iants | -1.808 |
ogyn | -1.800 |
Token | s |
Token ID | 82 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
creen | +5.014 |
MU | +4.910 |
ovember | +4.651 |
hur | +4.405 |
emp | +4.367 |
Neg logit contributions | |
Rocks | -7.289 |
iants | -6.834 |
ogyn | -6.795 |
iant | -6.688 |
Narc | -6.688 |
Token | natural |
Token ID | 3288 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
creen | +10.786 |
MU | +10.536 |
belie | +10.459 |
ovember | +9.787 |
Daytona | +9.603 |
Neg logit contributions | |
Rocks | -12.950 |
iants | -12.909 |
ogyn | -12.521 |
igree | -12.285 |
iant | -11.928 |
Token | shifts |
Token ID | 15381 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
creen | +8.273 |
MU | +7.942 |
ovember | +7.743 |
belie | +7.644 |
Daytona | +7.262 |
Neg logit contributions | |
Rocks | -7.002 |
iants | -6.771 |
igree | -6.681 |
ogyn | -6.651 |
Pet | -6.409 |
Token | between |
Token ID | 1022 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
creen | +2.402 |
MU | +2.270 |
ovember | +2.263 |
belie | +2.107 |
hur | +2.075 |
Neg logit contributions | |
Rocks | -2.466 |
iants | -2.300 |
iant | -2.295 |
Pet | -2.280 |
arily | -2.277 |
Token | sympathetic |
Token ID | 22335 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
creen | +1.589 |
ovember | +1.522 |
MU | +1.517 |
belie | +1.415 |
hur | +1.384 |
Neg logit contributions | |
Rocks | -1.497 |
arily | -1.396 |
iant | -1.391 |
iants | -1.389 |
bow | -1.385 |
Token | ( |
Token ID | 357 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
creen | +0.918 |
ovember | +0.884 |
MU | +0.883 |
belie | +0.823 |
hur | +0.808 |
Neg logit contributions | |
Rocks | -0.838 |
arily | -0.781 |
iant | -0.780 |
iants | -0.773 |
bow | -0.769 |
Token | Opt |
Token ID | 13123 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
creen | +5.500 |
MU | +5.424 |
ovember | +4.961 |
Daytona | +4.728 |
emp | +4.690 |
Neg logit contributions | |
igree | -5.897 |
arily | -5.807 |
iant | -5.797 |
ogyn | -5.748 |
iants | -5.727 |
Token | ronics |
Token ID | 20844 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Rocks | +1.995 |
iant | +1.885 |
iants | +1.858 |
arily | +1.826 |
--> | +1.819 |
Neg logit contributions | |
creen | -3.980 |
ovember | -3.946 |
MU | -3.891 |
belie | -3.738 |
captcha | -3.678 |
Token | TN |
Token ID | 29025 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
creen | +2.244 |
MU | +2.135 |
ovember | +2.108 |
belie | +1.945 |
hur | +1.918 |
Neg logit contributions | |
Rocks | -2.461 |
arily | -2.357 |
iant | -2.339 |
iants | -2.321 |
ogyn | -2.309 |
Token | Film |
Token ID | 13741 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
creen | +3.344 |
MU | +3.134 |
ovember | +3.090 |
belie | +2.797 |
iffe | +2.759 |
Neg logit contributions | |
Rocks | -4.041 |
arily | -3.858 |
iant | -3.830 |
iants | -3.823 |
ogyn | -3.804 |
Token | @ |
Token ID | 2488 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
creen | +4.767 |
MU | +4.485 |
ovember | +4.345 |
belie | +4.037 |
emp | +3.952 |
Neg logit contributions | |
Rocks | -5.376 |
arily | -5.270 |
iant | -5.226 |
iants | -5.146 |
Pet | -5.107 |
Token | 144 |
Token ID | 20224 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
creen | +2.923 |
MU | +2.755 |
ovember | +2.680 |
belie | +2.432 |
captcha | +2.400 |
Neg logit contributions | |
Rocks | -4.561 |
arily | -4.390 |
Pet | -4.358 |
ogyn | -4.350 |
iant | -4.348 |
Token | Hz |
Token ID | 7399 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
MU | +5.684 |
creen | +5.197 |
emp | +3.666 |
hur | +3.446 |
ovember | +3.281 |
Neg logit contributions | |
tremend | -19.594 |
Rocks | -19.403 |
recip | -19.379 |
igree | -18.960 |
quartered | -18.650 |
Token | ( |
Token ID | 357 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
Rocks | +2.263 |
--> | +2.065 |
Narc | +2.050 |
bow | +2.049 |
arily | +2.043 |
Neg logit contributions | |
ovember | -2.424 |
creen | -2.423 |
MU | -2.322 |
belie | -2.195 |
iffe | -2.167 |
Token | AMA |
Token ID | 25087 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Rocks | +6.054 |
Pet | +5.739 |
--> | +5.683 |
bow | +5.641 |
GY | +5.625 |
Neg logit contributions | |
ovember | -8.226 |
creen | -8.034 |
belie | -7.756 |
MU | -7.477 |
captcha | -7.454 |
Token | = |
Token ID | 796 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
creen | +8.409 |
MU | +8.265 |
ovember | +7.789 |
belie | +7.542 |
uckle | +7.480 |
Neg logit contributions | |
Rocks | -5.755 |
arily | -5.408 |
iants | -5.371 |
iant | -5.340 |
ogyn | -5.300 |
Token | High |
Token ID | 3334 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
Rocks | +3.382 |
iant | +3.093 |
--> | +3.086 |
Narc | +3.077 |
arily | +3.068 |
Neg logit contributions | |
ovember | -3.576 |
creen | -3.552 |
MU | -3.391 |
belie | -3.199 |
iffe | -3.172 |
Token | html |
Token ID | 6494 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
creen | +1.741 |
ovember | +1.672 |
MU | +1.667 |
hur | +1.550 |
uckle | +1.548 |
Neg logit contributions | |
Rocks | -1.319 |
Narc | -1.198 |
arily | -1.195 |
ogyn | -1.194 |
iants | -1.183 |
Token | https |
Token ID | 3740 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
creen | +2.237 |
MU | +2.190 |
ovember | +2.139 |
hur | +1.943 |
belie | +1.937 |
Neg logit contributions | |
Rocks | -2.992 |
arily | -2.871 |
iant | -2.833 |
ogyn | -2.807 |
igree | -2.804 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
creen | +0.984 |
MU | +0.954 |
ovember | +0.952 |
belie | +0.880 |
hur | +0.879 |
Neg logit contributions | |
Rocks | -0.711 |
iant | -0.656 |
arily | -0.655 |
iants | -0.649 |
ogyn | -0.646 |
Token | www |
Token ID | 2503 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
creen | +2.653 |
ovember | +2.539 |
MU | +2.535 |
hur | +2.388 |
belie | +2.367 |
Neg logit contributions | |
Rocks | -2.201 |
arily | -2.005 |
Narc | -1.979 |
GY | -1.976 |
ogyn | -1.976 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
creen | +0.611 |
ovember | +0.587 |
MU | +0.585 |
belie | +0.539 |
hur | +0.534 |
Neg logit contributions | |
Rocks | -0.611 |
arily | -0.574 |
iant | -0.572 |
iants | -0.567 |
--> | -0.563 |
Token | bel |
Token ID | 6667 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
creen | +4.398 |
hur | +4.270 |
MU | +3.305 |
emp | +3.276 |
ogie | +3.069 |
Neg logit contributions | |
Rocks | -17.137 |
GY | -16.052 |
Narc | -16.029 |
ACS | -15.999 |
Psychiatric | -15.998 |
Token | fast |
Token ID | 7217 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
creen | +6.019 |
veland | +4.952 |
hur | +4.922 |
ovember | +4.916 |
iffe | +4.772 |
Neg logit contributions | |
Rocks | -18.999 |
Narc | -18.425 |
ACS | -18.003 |
narcissistic | -17.980 |
GY | -17.737 |
Token | te |
Token ID | 660 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
creen | +3.415 |
ovember | +3.048 |
MU | +2.969 |
hur | +2.831 |
veland | +2.716 |
Neg logit contributions | |
Rocks | -7.800 |
Narc | -7.370 |
ACS | -7.247 |
GY | -7.215 |
Hubbard | -7.201 |
Token | legraph |
Token ID | 16606 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
creen | +3.143 |
MU | +2.936 |
ovember | +2.847 |
hur | +2.668 |
emp | +2.599 |
Neg logit contributions | |
Rocks | -8.257 |
ACS | -7.674 |
Pet | -7.665 |
Narc | -7.649 |
narcissistic | -7.601 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
creen | +0.354 |
ovember | +0.340 |
MU | +0.339 |
belie | +0.312 |
hur | +0.309 |
Neg logit contributions | |
Rocks | -0.352 |
arily | -0.330 |
iant | -0.329 |
iants | -0.326 |
--> | -0.324 |
Token | co |
Token ID | 1073 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
creen | +1.646 |
MU | +1.583 |
ovember | +1.572 |
hur | +1.483 |
emp | +1.458 |
Neg logit contributions | |
Rocks | -1.175 |
arily | -1.079 |
iant | -1.071 |
iants | -1.067 |
ogyn | -1.055 |
Token | tested |
Token ID | 6789 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
creen | +2.701 |
ovember | +2.562 |
MU | +2.526 |
belie | +2.400 |
hur | +2.308 |
Neg logit contributions | |
Rocks | -2.752 |
iants | -2.607 |
iant | -2.576 |
ogyn | -2.557 |
bow | -2.551 |
Token | the |
Token ID | 262 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
creen | +4.048 |
MU | +3.723 |
ovember | +3.690 |
belie | +3.536 |
hur | +3.414 |
Neg logit contributions | |
Rocks | -4.338 |
bow | -4.177 |
iants | -4.138 |
iant | -4.134 |
Pet | -4.125 |
Token | single |
Token ID | 2060 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
creen | +5.009 |
MU | +4.700 |
ovember | +4.624 |
belie | +4.485 |
captcha | +4.359 |
Neg logit contributions | |
Rocks | -3.760 |
Pet | -3.575 |
arily | -3.567 |
bow | -3.564 |
iants | -3.537 |
Token | card |
Token ID | 2657 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
creen | +5.494 |
MU | +5.258 |
ovember | +5.033 |
belie | +4.872 |
uckle | +4.686 |
Neg logit contributions | |
Rocks | -5.034 |
iants | -4.828 |
iant | -4.816 |
Pet | -4.773 |
Narc | -4.673 |
Token | in |
Token ID | 287 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
creen | +2.990 |
MU | +2.828 |
ovember | +2.787 |
belie | +2.621 |
hur | +2.572 |
Neg logit contributions | |
Rocks | -2.941 |
iant | -2.767 |
arily | -2.762 |
bow | -2.757 |
Pet | -2.751 |
Token | OC |
Token ID | 24775 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
creen | +2.576 |
MU | +2.437 |
ovember | +2.423 |
belie | +2.297 |
captcha | +2.237 |
Neg logit contributions | |
Rocks | -2.134 |
iant | -2.020 |
iants | -2.007 |
bow | -2.003 |
arily | -1.997 |
Token | mode |
Token ID | 4235 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
creen | +9.539 |
MU | +8.814 |
ovember | +8.179 |
captcha | +7.779 |
belie | +7.730 |
Neg logit contributions | |
Rocks | -13.788 |
Sov | -13.748 |
Pet | -13.615 |
ogyn | -13.570 |
iants | -13.448 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
creen | +0.145 |
ovember | +0.140 |
MU | +0.139 |
belie | +0.129 |
hur | +0.127 |
Neg logit contributions | |
Rocks | -0.139 |
arily | -0.130 |
iant | -0.130 |
iants | -0.128 |
bow | -0.128 |
Token | but |
Token ID | 475 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
Rocks | +1.032 |
arily | +0.960 |
iant | +0.956 |
--> | +0.946 |
iants | +0.942 |
Neg logit contributions | |
creen | -1.195 |
ovember | -1.164 |
MU | -1.152 |
belie | -1.068 |
hur | -1.057 |
Token | we |
Token ID | 356 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
creen | +0.173 |
ovember | +0.166 |
MU | +0.166 |
belie | +0.154 |
hur | +0.151 |
Neg logit contributions | |
Rocks | -0.158 |
arily | -0.148 |
iant | -0.148 |
iants | -0.147 |
bow | -0.146 |
Token | are |
Token ID | 389 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
creen | +2.193 |
ovember | +2.071 |
MU | +2.054 |
belie | +1.960 |
hur | +1.871 |
Neg logit contributions | |
Rocks | -2.264 |
iants | -2.132 |
iant | -2.118 |
ogyn | -2.095 |
bow | -2.094 |
Token | interrupted |
Token ID | 19072 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
creen | +0.676 |
ovember | +0.653 |
MU | +0.648 |
belie | +0.602 |
hur | +0.594 |
Neg logit contributions | |
Rocks | -0.620 |
arily | -0.581 |
iant | -0.579 |
iants | -0.573 |
--> | -0.571 |
Token | by |
Token ID | 416 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Rocks | +1.421 |
arily | +1.340 |
iant | +1.321 |
bow | +1.311 |
--> | +1.310 |
Neg logit contributions | |
creen | -1.530 |
ovember | -1.502 |
MU | -1.489 |
belie | -1.362 |
hur | -1.351 |
Token | a |
Token ID | 257 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
Rocks | +1.639 |
arily | +1.532 |
iant | +1.527 |
bow | +1.510 |
Narc | +1.500 |
Neg logit contributions | |
creen | -1.838 |
ovember | -1.782 |
MU | -1.770 |
belie | -1.629 |
hur | -1.611 |
Token | double |
Token ID | 4274 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Rocks | +0.530 |
arily | +0.498 |
iant | +0.496 |
bow | +0.490 |
--> | +0.489 |
Neg logit contributions | |
creen | -0.543 |
ovember | -0.524 |
MU | -0.520 |
belie | -0.481 |
hur | -0.475 |
Token | dissolution |
Token ID | 37494 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Rocks | +1.543 |
arily | +1.456 |
iant | +1.450 |
bow | +1.440 |
--> | +1.436 |
Neg logit contributions | |
creen | -1.280 |
ovember | -1.236 |
MU | -1.219 |
belie | -1.119 |
hur | -1.100 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
creen | +1.127 |
ovember | +1.083 |
MU | +1.073 |
belie | +0.995 |
hur | +0.980 |
Neg logit contributions | |
Rocks | -1.142 |
iant | -1.068 |
arily | -1.066 |
iants | -1.062 |
--> | -1.054 |
Token | 184 |
Token ID | 22883 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
MU | +8.496 |
creen | +8.169 |
hur | +7.673 |
ovember | +7.504 |
uckle | +6.991 |
Neg logit contributions | |
Rocks | -15.526 |
--> | -14.125 |
iants | -14.125 |
igree | -14.106 |
narcissistic | -13.937 |
Token | ] |
Token ID | 60 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
creen | +2.120 |
ovember | +2.030 |
MU | +2.018 |
belie | +1.847 |
hur | +1.816 |
Neg logit contributions | |
Rocks | -2.639 |
arily | -2.485 |
iant | -2.482 |
iants | -2.469 |
--> | -2.458 |
Token |
|
Token ID | 198 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Rocks | +3.304 |
Narc | +3.017 |
Pet | +2.995 |
iant | +2.975 |
bow | +2.971 |
Neg logit contributions | |
creen | -4.286 |
ovember | -4.168 |
MU | -4.046 |
belie | -3.878 |
hur | -3.819 |
Token |
|
Token ID | 198 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Rocks | +0.678 |
arily | +0.629 |
iant | +0.626 |
bow | +0.620 |
--> | +0.620 |
Neg logit contributions | |
creen | -0.939 |
ovember | -0.912 |
MU | -0.900 |
belie | -0.848 |
hur | -0.834 |
Token | Australia |
Token ID | 27429 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Rocks | +2.837 |
Pet | +2.767 |
bow | +2.726 |
iant | +2.721 |
--> | +2.703 |
Neg logit contributions | |
creen | -3.716 |
ovember | -3.587 |
MU | -3.446 |
belie | -3.376 |
captcha | -3.307 |
Token | 2 |
Token ID | 362 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
creen | +5.231 |
MU | +5.106 |
ovember | +4.800 |
hur | +4.675 |
belie | +4.593 |
Neg logit contributions | |
Rocks | -10.349 |
arily | -10.050 |
ogyn | -9.971 |
igree | -9.893 |
iant | -9.801 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
Rocks | +0.054 |
arily | +0.051 |
iant | +0.051 |
iants | +0.050 |
bow | +0.050 |
Neg logit contributions | |
creen | -0.057 |
ovember | -0.055 |
MU | -0.054 |
belie | -0.051 |
hur | -0.050 |
Token | 34 |
Token ID | 2682 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
MU | +4.861 |
creen | +4.589 |
ovember | +4.332 |
hur | +4.079 |
emp | +4.030 |
Neg logit contributions | |
igree | -7.584 |
Rocks | -7.531 |
ogyn | -7.324 |
arily | -7.272 |
narcissistic | -7.155 |
Token | ERA |
Token ID | 18802 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
creen | +4.911 |
MU | +4.515 |
ovember | +4.241 |
hur | +4.119 |
uckle | +4.056 |
Neg logit contributions | |
Rocks | -12.129 |
ogyn | -11.690 |
arily | -11.569 |
Narc | -11.449 |
iant | -11.401 |
Token | in |
Token ID | 287 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
creen | +5.125 |
ovember | +4.942 |
MU | +4.861 |
belie | +4.499 |
hur | +4.492 |
Neg logit contributions | |
Rocks | -6.362 |
arily | -5.933 |
iant | -5.912 |
ogyn | -5.899 |
Narc | -5.877 |
Token | 65 |
Token ID | 6135 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
creen | +3.737 |
MU | +3.583 |
ovember | +3.463 |
belie | +3.199 |
Daytona | +3.152 |
Neg logit contributions | |
Rocks | -5.850 |
igree | -5.708 |
ogyn | -5.705 |
arily | -5.660 |
iant | -5.631 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
creen | +8.617 |
MU | +8.354 |
ovember | +8.055 |
uckle | +7.872 |
hur | +7.718 |
Neg logit contributions | |
Rocks | -13.979 |
ogyn | -13.630 |
Narc | -13.262 |
awed | -13.214 |
igree | -13.134 |
Token | / |
Token ID | 14 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
creen | +0.959 |
MU | +0.929 |
ovember | +0.926 |
belie | +0.851 |
hur | +0.849 |
Neg logit contributions | |
Rocks | -0.848 |
arily | -0.792 |
iant | -0.791 |
ogyn | -0.781 |
iants | -0.781 |
Token | 3 |
Token ID | 18 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
creen | +1.043 |
ovember | +1.009 |
MU | +1.002 |
belie | +0.923 |
hur | +0.916 |
Neg logit contributions | |
Rocks | -0.977 |
arily | -0.916 |
iant | -0.912 |
iants | -0.902 |
ogyn | -0.899 |
Token | IP |
Token ID | 6101 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
creen | +7.331 |
MU | +7.156 |
ovember | +7.021 |
hur | +6.603 |
uckle | +6.568 |
Neg logit contributions | |
Rocks | -6.651 |
ogyn | -6.386 |
arily | -6.228 |
Narc | -6.212 |
bow | -6.138 |
Token |
|
Token ID | 198 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
creen | +4.269 |
ovember | +4.158 |
MU | +4.059 |
belie | +3.754 |
hur | +3.739 |
Neg logit contributions | |
Rocks | -5.028 |
arily | -4.731 |
iant | -4.715 |
ogyn | -4.673 |
Narc | -4.638 |
Token | reputable |
Token ID | 40300 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
creen | +6.653 |
MU | +6.531 |
belie | +6.485 |
ovember | +6.374 |
captcha | +6.127 |
Neg logit contributions | |
Rocks | -7.451 |
ogyn | -7.320 |
bow | -7.189 |
GY | -7.154 |
arily | -7.062 |
Token | sources |
Token ID | 4237 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
creen | +3.237 |
MU | +3.099 |
ovember | +3.077 |
belie | +2.986 |
captcha | +2.876 |
Neg logit contributions | |
Rocks | -3.829 |
arily | -3.663 |
ogyn | -3.631 |
iants | -3.613 |
iant | -3.610 |
Token | confirm |
Token ID | 6216 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
creen | +3.384 |
ovember | +3.190 |
MU | +3.170 |
belie | +3.118 |
captcha | +2.919 |
Neg logit contributions | |
Rocks | -3.353 |
ogyn | -3.155 |
Pet | -3.116 |
arily | -3.107 |
iants | -3.107 |
Token | or |
Token ID | 393 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
creen | +1.680 |
MU | +1.610 |
ovember | +1.601 |
belie | +1.511 |
hur | +1.473 |
Neg logit contributions | |
Rocks | -1.717 |
iant | -1.606 |
arily | -1.603 |
ogyn | -1.598 |
iants | -1.596 |
Token | shed |
Token ID | 14999 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
creen | +4.915 |
belie | +4.734 |
ovember | +4.656 |
MU | +4.613 |
captcha | +4.148 |
Neg logit contributions | |
Rocks | -6.829 |
ogyn | -6.543 |
arily | -6.374 |
Pet | -6.342 |
iants | -6.340 |
Token | more |
Token ID | 517 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
creen | +3.673 |
ovember | +3.497 |
MU | +3.484 |
belie | +3.364 |
uckle | +3.128 |
Neg logit contributions | |
Rocks | -4.118 |
arily | -3.908 |
--> | -3.898 |
ogyn | -3.891 |
bow | -3.861 |
Token | light |
Token ID | 1657 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
belie | +8.665 |
creen | +8.432 |
ovember | +8.177 |
MU | +8.073 |
captcha | +7.243 |
Neg logit contributions | |
Rocks | -13.719 |
GY | -13.624 |
ogyn | -13.622 |
ominated | -13.487 |
bow | -13.391 |
Token | on |
Token ID | 319 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
creen | +6.400 |
ovember | +6.061 |
MU | +5.777 |
belie | +5.765 |
captcha | +5.360 |
Neg logit contributions | |
Rocks | -8.610 |
iants | -8.106 |
Pet | -7.976 |
arily | -7.974 |
GY | -7.943 |
Token | things |
Token ID | 1243 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
creen | +0.333 |
ovember | +0.321 |
MU | +0.319 |
belie | +0.295 |
hur | +0.291 |
Neg logit contributions | |
Rocks | -0.341 |
arily | -0.320 |
iant | -0.320 |
iants | -0.317 |
bow | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
creen | +4.102 |
MU | +3.873 |
ovember | +3.849 |
belie | +3.672 |
hur | +3.516 |
Neg logit contributions | |
Rocks | -4.374 |
iants | -4.118 |
iant | -4.113 |
arily | -4.063 |
ogyn | -4.059 |
Token | That |
Token ID | 1320 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
creen | +3.942 |
MU | +3.907 |
ovember | +3.749 |
hur | +3.530 |
belie | +3.496 |
Neg logit contributions | |
Rocks | -3.708 |
arily | -3.690 |
ogyn | -3.673 |
iant | -3.610 |
igree | -3.584 |
Token | IPS |
Token ID | 47643 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Rocks | +2.053 |
Pet | +1.908 |
iant | +1.896 |
--> | +1.888 |
bow | +1.864 |
Neg logit contributions | |
creen | -4.768 |
ovember | -4.766 |
belie | -4.522 |
MU | -4.513 |
captcha | -4.400 |
Token | - |
Token ID | 12 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
creen | +2.691 |
MU | +2.580 |
ovember | +2.437 |
belie | +2.247 |
hur | +2.225 |
Neg logit contributions | |
Rocks | -3.258 |
iant | -3.118 |
arily | -3.109 |
igree | -3.104 |
ogyn | -3.099 |
Token | type |
Token ID | 4906 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
creen | +1.763 |
MU | +1.653 |
ovember | +1.612 |
hur | +1.483 |
belie | +1.450 |
Neg logit contributions | |
Rocks | -2.650 |
arily | -2.445 |
Narc | -2.442 |
iants | -2.442 |
iant | -2.440 |
Token | ) |
Token ID | 8 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
creen | +1.722 |
MU | +1.652 |
ovember | +1.632 |
belie | +1.515 |
hur | +1.509 |
Neg logit contributions | |
Rocks | -1.534 |
arily | -1.439 |
iant | -1.437 |
iants | -1.429 |
ogyn | -1.412 |
Token | @ |
Token ID | 2488 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
creen | +0.602 |
ovember | +0.577 |
MU | +0.576 |
belie | +0.532 |
hur | +0.523 |
Neg logit contributions | |
Rocks | -0.594 |
arily | -0.563 |
iant | -0.560 |
iants | -0.555 |
bow | -0.551 |
Token | 144 |
Token ID | 20224 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
creen | +3.800 |
MU | +3.559 |
ovember | +3.419 |
belie | +3.143 |
captcha | +3.085 |
Neg logit contributions | |
Rocks | -6.049 |
arily | -5.849 |
Pet | -5.803 |
iant | -5.778 |
ogyn | -5.768 |
Token | Hz |
Token ID | 7399 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
MU | +4.737 |
creen | +4.432 |
emp | +2.896 |
hur | +2.624 |
ovember | +2.532 |
Neg logit contributions | |
Rocks | -19.175 |
tremend | -18.936 |
recip | -18.895 |
igree | -18.820 |
narcissistic | -18.405 |
Token | ( |
Token ID | 357 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
creen | +0.638 |
ovember | +0.615 |
MU | +0.610 |
belie | +0.563 |
hur | +0.554 |
Neg logit contributions | |
Rocks | -0.678 |
arily | -0.638 |
iant | -0.637 |
iants | -0.630 |
bow | -0.628 |
Token | OD |
Token ID | 3727 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Rocks | +2.613 |
Pet | +2.516 |
--> | +2.488 |
bow | +2.452 |
iant | +2.416 |
Neg logit contributions | |
creen | -4.439 |
ovember | -4.420 |
belie | -4.155 |
MU | -4.131 |
captcha | -4.070 |
Token | = |
Token ID | 796 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
creen | +4.673 |
MU | +4.611 |
ovember | +4.411 |
belie | +4.128 |
veland | +4.060 |
Neg logit contributions | |
Rocks | -4.099 |
arily | -3.896 |
ogyn | -3.811 |
iants | -3.810 |
Narc | -3.802 |
Token | Normal |
Token ID | 14435 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Rocks | +2.114 |
arily | +1.990 |
iant | +1.990 |
bow | +1.979 |
--> | +1.976 |
Neg logit contributions | |
creen | -1.566 |
ovember | -1.538 |
MU | -1.489 |
belie | -1.359 |
iffe | -1.349 |
Token | s |
Token ID | 264 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
creen | +1.197 |
ovember | +1.160 |
MU | +1.153 |
belie | +1.079 |
hur | +1.066 |
Neg logit contributions | |
Rocks | -0.886 |
arily | -0.824 |
iant | -0.820 |
iants | -0.810 |
--> | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
Rocks | +1.275 |
arily | +1.203 |
iant | +1.192 |
bow | +1.188 |
--> | +1.187 |
Neg logit contributions | |
creen | -1.462 |
ovember | -1.434 |
MU | -1.396 |
belie | -1.324 |
captcha | -1.299 |
Token | t |
Token ID | 83 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Rocks | +0.572 |
arily | +0.525 |
iant | +0.523 |
bow | +0.517 |
--> | +0.515 |
Neg logit contributions | |
creen | -1.157 |
ovember | -1.132 |
MU | -1.120 |
belie | -1.067 |
captcha | -1.048 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
creen | +1.986 |
MU | +1.923 |
ovember | +1.879 |
hur | +1.717 |
belie | +1.705 |
Neg logit contributions | |
Rocks | -2.226 |
iant | -2.099 |
iants | -2.097 |
arily | -2.092 |
igree | -2.085 |
Token | F |
Token ID | 376 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
creen | +0.210 |
ovember | +0.203 |
MU | +0.202 |
belie | +0.187 |
hur | +0.184 |
Neg logit contributions | |
Rocks | -0.197 |
arily | -0.185 |
iant | -0.184 |
iants | -0.182 |
bow | -0.182 |
Token | RA |
Token ID | 3861 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
MU | +3.379 |
creen | +3.234 |
ovember | +3.080 |
hur | +2.658 |
iffe | +2.590 |
Neg logit contributions | |
Rocks | -7.627 |
arily | -7.301 |
igree | -7.290 |
iants | -7.236 |
ogyn | -7.195 |
Token | 19 |
Token ID | 678 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
MU | +7.514 |
creen | +7.154 |
UGH | +6.908 |
ovember | +6.628 |
iffe | +6.530 |
Neg logit contributions | |
ogyn | -14.774 |
igree | -14.659 |
arily | -14.642 |
Rocks | -14.618 |
awed | -14.143 |
Token | William |
Token ID | 3977 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Rocks | +0.264 |
arily | +0.246 |
iant | +0.246 |
iants | +0.243 |
bow | +0.242 |
Neg logit contributions | |
creen | -0.275 |
ovember | -0.265 |
MU | -0.262 |
belie | -0.244 |
hur | -0.240 |
Token | Bon |
Token ID | 7979 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
creen | +0.100 |
ovember | +0.096 |
MU | +0.095 |
hur | +0.088 |
belie | +0.088 |
Neg logit contributions | |
Rocks | -0.093 |
arily | -0.089 |
iant | -0.089 |
iants | -0.089 |
ogyn | -0.087 |
Token | net |
Token ID | 3262 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
creen | +6.191 |
ovember | +6.141 |
MU | +5.872 |
iffe | +5.644 |
hur | +5.568 |
Neg logit contributions | |
Rocks | -6.007 |
--> | -5.759 |
iants | -5.725 |
GY | -5.698 |
Narc | -5.615 |
Token | ( |
Token ID | 357 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
creen | +2.171 |
ovember | +2.105 |
MU | +2.078 |
belie | +1.910 |
hur | +1.892 |
Neg logit contributions | |
Rocks | -2.423 |
arily | -2.322 |
iant | -2.281 |
iants | -2.276 |
--> | -2.275 |
Token | IPS |
Token ID | 47643 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Rocks | +2.447 |
iant | +2.285 |
Pet | +2.277 |
--> | +2.256 |
bow | +2.233 |
Neg logit contributions | |
creen | -5.880 |
ovember | -5.878 |
belie | -5.606 |
MU | -5.584 |
captcha | -5.425 |
Token | - |
Token ID | 12 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
creen | +2.830 |
MU | +2.698 |
ovember | +2.548 |
belie | +2.347 |
hur | +2.335 |
Neg logit contributions | |
Rocks | -3.463 |
iant | -3.304 |
igree | -3.300 |
iants | -3.289 |
arily | -3.288 |
Token | type |
Token ID | 4906 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
creen | +0.644 |
MU | +0.609 |
ovember | +0.608 |
belie | +0.548 |
hur | +0.547 |
Neg logit contributions | |
Rocks | -0.892 |
arily | -0.835 |
iant | -0.834 |
iants | -0.830 |
Narc | -0.824 |
Token | ) |
Token ID | 8 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
creen | +4.121 |
MU | +3.924 |
ovember | +3.736 |
hur | +3.528 |
belie | +3.497 |
Neg logit contributions | |
Rocks | -4.263 |
iants | -4.070 |
iant | -4.067 |
igree | -4.052 |
arily | -4.046 |
Token | @ |
Token ID | 2488 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Rocks | +0.739 |
arily | +0.686 |
iant | +0.684 |
--> | +0.679 |
bow | +0.677 |
Neg logit contributions | |
creen | -0.799 |
ovember | -0.779 |
MU | -0.768 |
belie | -0.715 |
hur | -0.707 |
Token | 144 |
Token ID | 20224 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
creen | +3.435 |
MU | +3.212 |
ovember | +3.115 |
belie | +2.850 |
captcha | +2.803 |
Neg logit contributions | |
Rocks | -5.364 |
arily | -5.174 |
ogyn | -5.125 |
Pet | -5.110 |
iant | -5.103 |
Token | Hz |
Token ID | 7399 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
MU | +4.555 |
creen | +4.385 |
emp | +2.774 |
ovember | +2.641 |
hur | +2.610 |
Neg logit contributions | |
Rocks | -19.220 |
recip | -18.940 |
tremend | -18.876 |
igree | -18.757 |
ogyn | -18.346 |
Token | ( |
Token ID | 357 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Rocks | +0.362 |
arily | +0.337 |
iant | +0.337 |
--> | +0.334 |
bow | +0.334 |
Neg logit contributions | |
creen | -0.356 |
ovember | -0.348 |
MU | -0.342 |
belie | -0.317 |
hur | -0.314 |
Token | Tr |
Token ID | 2898 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Rocks | +5.020 |
Pet | +4.848 |
bow | +4.749 |
iant | +4.748 |
--> | +4.707 |
Neg logit contributions | |
ovember | -9.119 |
creen | -9.076 |
belie | -8.634 |
MU | -8.515 |
captcha | -8.360 |
Token | ace |
Token ID | 558 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
creen | +2.006 |
ovember | +1.933 |
MU | +1.897 |
emp | +1.756 |
uckle | +1.749 |
Neg logit contributions | |
Rocks | -2.135 |
Narc | -1.957 |
iants | -1.945 |
arily | -1.942 |
iant | -1.933 |
Token | Free |
Token ID | 3232 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
creen | +3.873 |
MU | +3.687 |
ovember | +3.226 |
Daytona | +3.216 |
iffe | +3.136 |
Neg logit contributions | |
iants | -6.221 |
igree | -6.220 |
iant | -6.210 |
ogyn | -6.198 |
arily | -6.170 |
Token | Tweet |
Token ID | 47845 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
creen | +0.043 |
ovember | +0.042 |
MU | +0.042 |
belie | +0.039 |
hur | +0.038 |
Neg logit contributions | |
Rocks | -0.037 |
arily | -0.035 |
iant | -0.035 |
iants | -0.034 |
bow | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
creen | +2.380 |
MU | +2.300 |
ovember | +2.298 |
belie | +2.147 |
hur | +2.125 |
Neg logit contributions | |
Rocks | -1.900 |
arily | -1.778 |
iant | -1.762 |
iants | -1.753 |
bow | -1.741 |
Token |
|
Token ID | 198 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
creen | +2.273 |
MU | +2.222 |
ovember | +2.154 |
hur | +2.021 |
belie | +1.985 |
Neg logit contributions | |
Rocks | -2.050 |
ogyn | -1.920 |
iant | -1.920 |
arily | -1.920 |
igree | -1.919 |
Token | Pin |
Token ID | 28348 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
MU | +3.561 |
creen | +3.550 |
ovember | +3.407 |
hur | +3.189 |
emp | +3.127 |
Neg logit contributions | |
Rocks | -3.638 |
arily | -3.335 |
Narc | -3.304 |
igree | -3.292 |
ogyn | -3.292 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
creen | +4.468 |
MU | +4.298 |
ovember | +4.258 |
belie | +3.953 |
hur | +3.885 |
Neg logit contributions | |
Rocks | -4.559 |
arily | -4.444 |
--> | -4.322 |
iants | -4.316 |
iant | -4.312 |
Token | shares |
Token ID | 7303 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
MU | +7.661 |
creen | +7.639 |
ovember | +7.091 |
emp | +6.752 |
belie | +6.717 |
Neg logit contributions | |
ogyn | -9.084 |
Rocks | -8.989 |
igree | -8.926 |
iants | -8.862 |
arily | -8.820 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
creen | +10.631 |
MU | +10.012 |
ovember | +9.523 |
captcha | +9.297 |
uckle | +9.155 |
Neg logit contributions | |
arily | -12.076 |
Rocks | -12.046 |
igree | -11.908 |
ogyn | -11.800 |
ominated | -11.696 |
Token |
|
Token ID | 198 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
creen | +2.764 |
MU | +2.700 |
ovember | +2.608 |
hur | +2.455 |
emp | +2.409 |
Neg logit contributions | |
Rocks | -2.629 |
igree | -2.471 |
ogyn | -2.469 |
iants | -2.452 |
iant | -2.449 |
Token | I |
Token ID | 40 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
MU | +5.953 |
creen | +5.855 |
ovember | +5.613 |
hur | +5.333 |
emp | +5.212 |
Neg logit contributions | |
Rocks | -5.609 |
Narc | -5.075 |
arily | -5.073 |
igree | -5.067 |
iants | -5.011 |
Token | was |
Token ID | 373 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
creen | +0.915 |
ovember | +0.882 |
MU | +0.875 |
belie | +0.813 |
hur | +0.796 |
Neg logit contributions | |
Rocks | -0.877 |
iant | -0.820 |
arily | -0.819 |
iants | -0.814 |
--> | -0.811 |
Token | inspired |
Token ID | 7867 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Rocks | +1.066 |
arily | +1.000 |
iant | +0.989 |
bow | +0.978 |
iants | +0.977 |
Neg logit contributions | |
creen | -1.122 |
ovember | -1.086 |
MU | -1.081 |
belie | -0.992 |
hur | -0.984 |
Token | OS |
Token ID | 7294 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Rocks | +0.992 |
arily | +0.922 |
iant | +0.916 |
--> | +0.906 |
iants | +0.905 |
Neg logit contributions | |
creen | -1.121 |
ovember | -1.094 |
MU | -1.079 |
belie | -1.004 |
hur | -0.996 |
Token | X |
Token ID | 55 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
creen | +3.234 |
MU | +3.143 |
ovember | +3.047 |
belie | +2.797 |
emp | +2.791 |
Neg logit contributions | |
Rocks | -2.616 |
iants | -2.492 |
arily | -2.487 |
igree | -2.483 |
iant | -2.476 |
Token | , |
Token ID | 11 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
Rocks | +0.369 |
iant | +0.342 |
arily | +0.342 |
--> | +0.339 |
iants | +0.338 |
Neg logit contributions | |
creen | -0.415 |
ovember | -0.404 |
MU | -0.398 |
belie | -0.371 |
hur | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
Rocks | +0.695 |
arily | +0.643 |
iant | +0.642 |
--> | +0.634 |
iants | +0.632 |
Neg logit contributions | |
creen | -0.764 |
ovember | -0.745 |
MU | -0.729 |
belie | -0.679 |
hur | -0.674 |
Token | AL |
Token ID | 8355 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
creen | +0.632 |
ovember | +0.609 |
MU | +0.607 |
belie | +0.565 |
hur | +0.555 |
Neg logit contributions | |
Rocks | -0.553 |
arily | -0.520 |
iant | -0.517 |
iants | -0.513 |
bow | -0.511 |
Token | SA |
Token ID | 4090 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
MU | +7.688 |
creen | +7.134 |
hur | +6.361 |
ovember | +6.289 |
iffe | +6.089 |
Neg logit contributions | |
Rocks | -8.720 |
arily | -8.625 |
ogyn | -8.600 |
igree | -8.408 |
iant | -8.373 |
Token | on |
Token ID | 319 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
MU | +10.604 |
creen | +10.294 |
mixer | +9.219 |
ovember | +8.961 |
UGH | +8.875 |
Neg logit contributions | |
igree | -11.311 |
ogyn | -11.159 |
awed | -11.142 |
arily | -11.082 |
Narc | -11.013 |
Token | Linux |
Token ID | 7020 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
creen | +1.773 |
MU | +1.686 |
ovember | +1.673 |
belie | +1.552 |
hur | +1.504 |
Neg logit contributions | |
Rocks | -1.981 |
iant | -1.888 |
arily | -1.884 |
bow | -1.879 |
iants | -1.879 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
creen | +2.444 |
MU | +2.345 |
ovember | +2.296 |
belie | +2.149 |
iffe | +2.096 |
Neg logit contributions | |
Rocks | -2.553 |
arily | -2.432 |
iant | -2.411 |
bow | -2.406 |
iants | -2.405 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Rocks | +0.567 |
iant | +0.517 |
arily | +0.517 |
--> | +0.511 |
iants | +0.509 |
Neg logit contributions | |
creen | -0.750 |
ovember | -0.733 |
MU | -0.718 |
belie | -0.676 |
hur | -0.668 |
Token |
|
Token ID | 198 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
creen | +1.371 |
MU | +1.331 |
ovember | +1.309 |
hur | +1.217 |
belie | +1.211 |
Neg logit contributions | |
Rocks | -1.173 |
arily | -1.094 |
iant | -1.093 |
iants | -1.090 |
ogyn | -1.088 |
Token | improves |
Token ID | 19575 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
creen | +1.850 |
MU | +1.775 |
ovember | +1.757 |
belie | +1.639 |
hur | +1.621 |
Neg logit contributions | |
Rocks | -1.841 |
iants | -1.726 |
ogyn | -1.724 |
iant | -1.717 |
arily | -1.713 |
Token | the |
Token ID | 262 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
creen | +3.849 |
MU | +3.764 |
ovember | +3.660 |
belie | +3.491 |
captcha | +3.349 |
Neg logit contributions | |
Rocks | -3.850 |
ogyn | -3.621 |
iants | -3.613 |
iant | -3.580 |
bow | -3.568 |
Token | body |
Token ID | 1767 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
creen | +7.815 |
MU | +7.647 |
belie | +7.385 |
ovember | +7.110 |
captcha | +6.952 |
Neg logit contributions | |
Rocks | -8.084 |
ogyn | -7.957 |
iants | -7.924 |
igree | -7.779 |
iant | -7.706 |
Token | � |
Token ID | 447 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
creen | +5.769 |
MU | +5.733 |
ovember | +5.488 |
belie | +5.306 |
veland | +5.071 |
Neg logit contributions | |
Rocks | -7.019 |
iants | -6.846 |
bow | -6.638 |
igree | -6.633 |
iant | -6.618 |
Token | � |
Token ID | 247 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
creen | +1.399 |
ovember | +1.361 |
MU | +1.361 |
belie | +1.274 |
hur | +1.256 |
Neg logit contributions | |
Rocks | -0.944 |
arily | -0.872 |
iant | -0.872 |
iants | -0.866 |
bow | -0.856 |
Token | s |
Token ID | 82 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
creen | +5.124 |
MU | +5.069 |
ovember | +4.804 |
belie | +4.639 |
emp | +4.561 |
Neg logit contributions | |
Rocks | -4.741 |
iants | -4.333 |
ogyn | -4.269 |
iant | -4.258 |
Narc | -4.250 |
Token | ability |
Token ID | 2694 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
creen | +10.536 |
MU | +10.527 |
belie | +9.854 |
ovember | +9.564 |
abol | +9.546 |
Neg logit contributions | |
Rocks | -11.388 |
iants | -11.233 |
igree | -10.745 |
ogyn | -10.506 |
bow | -10.460 |
Token | to |
Token ID | 284 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
creen | +1.823 |
MU | +1.751 |
ovember | +1.742 |
belie | +1.611 |
hur | +1.591 |
Neg logit contributions | |
Rocks | -1.882 |
iant | -1.749 |
iants | -1.748 |
arily | -1.747 |
ogyn | -1.722 |
Token | utilize |
Token ID | 17624 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
creen | +4.779 |
MU | +4.528 |
ovember | +4.480 |
belie | +4.361 |
veland | +4.082 |
Neg logit contributions | |
Rocks | -5.362 |
iants | -5.080 |
ogyn | -5.056 |
Pet | -5.054 |
bow | -5.020 |
Token | fat |
Token ID | 3735 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
creen | +4.539 |
MU | +4.430 |
ovember | +4.257 |
belie | +4.089 |
emp | +3.943 |
Neg logit contributions | |
Rocks | -4.062 |
iants | -3.860 |
ogyn | -3.831 |
bow | -3.823 |
iant | -3.776 |
Token | for |
Token ID | 329 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
creen | +1.764 |
MU | +1.706 |
ovember | +1.670 |
belie | +1.552 |
iffe | +1.519 |
Neg logit contributions | |
Rocks | -1.922 |
arily | -1.814 |
iants | -1.805 |
iant | -1.802 |
ogyn | -1.789 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Rocks | +1.512 |
iant | +1.421 |
arily | +1.410 |
iants | +1.404 |
bow | +1.399 |
Neg logit contributions | |
creen | -1.635 |
ovember | -1.586 |
MU | -1.557 |
belie | -1.428 |
hur | -1.426 |
Token | supernatural |
Token ID | 22239 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Rocks | +1.541 |
iant | +1.451 |
arily | +1.448 |
iants | +1.431 |
--> | +1.429 |
Neg logit contributions | |
creen | -1.470 |
ovember | -1.421 |
MU | -1.389 |
hur | -1.270 |
belie | -1.269 |
Token | world |
Token ID | 995 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
creen | +2.515 |
MU | +2.438 |
ovember | +2.405 |
belie | +2.275 |
hur | +2.196 |
Neg logit contributions | |
Rocks | -2.607 |
arily | -2.433 |
ogyn | -2.420 |
iant | -2.416 |
iants | -2.411 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Rocks | +3.241 |
arily | +3.087 |
bow | +3.039 |
iant | +3.037 |
--> | +3.022 |
Neg logit contributions | |
creen | -3.848 |
ovember | -3.793 |
MU | -3.644 |
uckle | -3.382 |
iffe | -3.376 |
Token |
|
Token ID | 198 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
creen | +1.439 |
MU | +1.398 |
ovember | +1.374 |
belie | +1.284 |
hur | +1.272 |
Neg logit contributions | |
Rocks | -1.272 |
arily | -1.216 |
iant | -1.204 |
iants | -1.191 |
ogyn | -1.186 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
creen | +2.282 |
MU | +2.228 |
ovember | +2.156 |
hur | +2.024 |
emp | +1.996 |
Neg logit contributions | |
Rocks | -2.111 |
igree | -1.990 |
ogyn | -1.976 |
iants | -1.970 |
arily | -1.968 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
MU | +10.683 |
creen | +9.648 |
ovember | +9.182 |
UGH | +9.020 |
hur | +8.839 |
Neg logit contributions | |
Rocks | -12.532 |
igree | -11.683 |
Narc | -11.447 |
Hubbard | -11.311 |
ACS | -11.304 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Rocks | +1.490 |
arily | +1.380 |
bow | +1.378 |
--> | +1.375 |
iant | +1.373 |
Neg logit contributions | |
creen | -1.701 |
ovember | -1.675 |
MU | -1.610 |
belie | -1.537 |
iffe | -1.510 |
Token | RED |
Token ID | 23848 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
creen | +3.592 |
MU | +3.553 |
ovember | +3.392 |
belie | +3.186 |
hur | +3.130 |
Neg logit contributions | |
Rocks | -3.560 |
arily | -3.453 |
iant | -3.437 |
iants | -3.405 |
igree | -3.397 |
Token | S |
Token ID | 311 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
creen | +0.502 |
ovember | +0.484 |
MU | +0.482 |
belie | +0.444 |
hur | +0.439 |
Neg logit contributions | |
Rocks | -0.494 |
arily | -0.465 |
iant | -0.463 |
iants | -0.459 |
bow | -0.456 |
Token | ON |
Token ID | 1340 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
creen | +3.558 |
MU | +3.481 |
ovember | +3.339 |
uckle | +3.162 |
UGH | +3.070 |
Neg logit contributions | |
Rocks | -3.207 |
iant | -3.030 |
arily | -3.026 |
iants | -3.020 |
igree | -3.019 |
Token | many |
Token ID | 867 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Rocks | +0.723 |
iant | +0.680 |
arily | +0.679 |
iants | +0.672 |
bow | +0.669 |
Neg logit contributions | |
creen | -0.729 |
ovember | -0.708 |
MU | -0.698 |
belie | -0.645 |
hur | -0.640 |
Token | new |
Token ID | 649 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Rocks | +1.161 |
iant | +1.077 |
arily | +1.076 |
iants | +1.063 |
--> | +1.059 |
Neg logit contributions | |
creen | -1.318 |
ovember | -1.282 |
MU | -1.265 |
belie | -1.169 |
hur | -1.162 |
Token | features |
Token ID | 3033 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
creen | +1.542 |
MU | +1.478 |
ovember | +1.474 |
belie | +1.375 |
hur | +1.341 |
Neg logit contributions | |
Rocks | -1.625 |
arily | -1.550 |
iant | -1.535 |
iants | -1.531 |
--> | -1.528 |
Token | in |
Token ID | 287 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
creen | +0.052 |
ovember | +0.050 |
MU | +0.049 |
belie | +0.046 |
hur | +0.045 |
Neg logit contributions | |
Rocks | -0.048 |
arily | -0.045 |
iant | -0.045 |
iants | -0.045 |
bow | -0.045 |
Token | Wii |
Token ID | 16591 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
creen | +0.841 |
ovember | +0.806 |
MU | +0.799 |
belie | +0.734 |
hur | +0.718 |
Neg logit contributions | |
Rocks | -1.048 |
arily | -0.994 |
iant | -0.992 |
iants | -0.985 |
bow | -0.983 |
Token | Sports |
Token ID | 7092 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
creen | +2.099 |
ovember | +2.018 |
MU | +2.008 |
belie | +1.863 |
hur | +1.816 |
Neg logit contributions | |
Rocks | -2.070 |
arily | -1.971 |
iant | -1.961 |
iants | -1.959 |
bow | -1.946 |
Token | Club |
Token ID | 6289 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
creen | +5.672 |
MU | +4.469 |
Daytona | +4.144 |
ovember | +3.912 |
belie | +3.849 |
Neg logit contributions | |
iants | -16.641 |
igree | -16.497 |
Sov | -16.288 |
iant | -16.098 |
arily | -16.053 |
Token | that |
Token ID | 326 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
creen | +7.241 |
MU | +6.997 |
ovember | +6.763 |
belie | +6.411 |
hur | +6.243 |
Neg logit contributions | |
Rocks | -8.966 |
iants | -8.915 |
arily | -8.837 |
bow | -8.737 |
igree | -8.676 |
Token | players |
Token ID | 1938 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
creen | +1.513 |
ovember | +1.447 |
MU | +1.445 |
belie | +1.354 |
hur | +1.323 |
Neg logit contributions | |
Rocks | -1.439 |
arily | -1.354 |
iant | -1.352 |
bow | -1.342 |
iants | -1.341 |
Token | will |
Token ID | 481 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Rocks | +1.203 |
arily | +1.134 |
iant | +1.129 |
--> | +1.113 |
iants | +1.113 |
Neg logit contributions | |
creen | -1.249 |
ovember | -1.211 |
MU | -1.197 |
belie | -1.103 |
hur | -1.092 |
Token | feel |
Token ID | 1254 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Rocks | +1.661 |
arily | +1.566 |
iant | +1.555 |
bow | +1.534 |
--> | +1.533 |
Neg logit contributions | |
creen | -1.761 |
ovember | -1.709 |
MU | -1.696 |
belie | -1.555 |
hur | -1.548 |
Token | partner |
Token ID | 5212 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Rocks | +1.897 |
iant | +1.790 |
arily | +1.789 |
iants | +1.760 |
bow | +1.755 |
Neg logit contributions | |
creen | -2.100 |
ovember | -2.046 |
MU | -2.004 |
belie | -1.868 |
hur | -1.841 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Rocks | +4.049 |
iant | +3.764 |
arily | +3.726 |
iants | +3.693 |
Narc | +3.656 |
Neg logit contributions | |
creen | -5.152 |
ovember | -5.098 |
MU | -4.955 |
belie | -4.658 |
hur | -4.629 |
Token | the |
Token ID | 262 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Rocks | +3.982 |
iant | +3.675 |
arily | +3.624 |
Narc | +3.593 |
bow | +3.560 |
Neg logit contributions | |
creen | -5.103 |
ovember | -5.017 |
MU | -4.893 |
belie | -4.565 |
hur | -4.549 |
Token | National |
Token ID | 2351 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Rocks | +4.537 |
iant | +4.106 |
Narc | +4.067 |
arily | +4.044 |
bow | +3.988 |
Neg logit contributions | |
creen | -6.457 |
ovember | -6.358 |
MU | -6.135 |
hur | -5.762 |
belie | -5.731 |
Token | Party |
Token ID | 3615 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Rocks | +2.017 |
arily | +1.884 |
iant | +1.877 |
bow | +1.841 |
iants | +1.834 |
Neg logit contributions | |
creen | -2.566 |
ovember | -2.473 |
MU | -2.437 |
belie | -2.304 |
hur | -2.281 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Rocks | +2.268 |
iant | +2.113 |
arily | +2.108 |
bow | +2.084 |
iants | +2.076 |
Neg logit contributions | |
creen | -2.612 |
ovember | -2.542 |
MU | -2.494 |
belie | -2.331 |
hur | -2.322 |
Token | 190 |
Token ID | 19782 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
MU | +7.095 |
creen | +6.339 |
ovember | +6.040 |
hur | +5.999 |
veland | +5.824 |
Neg logit contributions | |
Rocks | -15.786 |
iants | -14.362 |
igree | -14.205 |
narcissistic | -14.196 |
ogyn | -14.086 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
creen | +2.171 |
MU | +2.073 |
ovember | +2.060 |
belie | +1.883 |
hur | +1.862 |
Neg logit contributions | |
Rocks | -2.790 |
arily | -2.630 |
iant | -2.623 |
iants | -2.614 |
--> | -2.596 |
Token | 191 |
Token ID | 26492 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
MU | +7.450 |
creen | +6.829 |
ovember | +6.299 |
hur | +6.191 |
veland | +5.891 |
Neg logit contributions | |
Rocks | -15.303 |
ACS | -13.556 |
igree | -13.502 |
arily | -13.425 |
Hubbard | -13.351 |
Token | ] |
Token ID | 60 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
creen | +3.347 |
MU | +3.197 |
ovember | +3.189 |
belie | +2.908 |
hur | +2.863 |
Neg logit contributions | |
Rocks | -4.543 |
arily | -4.285 |
iant | -4.264 |
iants | -4.249 |
ogyn | -4.228 |
Token | Within |
Token ID | 12511 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
Rocks | +4.962 |
Narc | +4.554 |
Pet | +4.426 |
--> | +4.399 |
Hubbard | +4.364 |
Neg logit contributions | |
creen | -6.643 |
ovember | -6.499 |
MU | -6.198 |
belie | -5.995 |
hur | -5.951 |
Token | was |
Token ID | 373 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
creen | +1.304 |
ovember | +1.256 |
MU | +1.238 |
belie | +1.164 |
hur | +1.136 |
Neg logit contributions | |
Rocks | -1.208 |
arily | -1.128 |
iant | -1.128 |
iants | -1.118 |
--> | -1.116 |
Token | not |
Token ID | 407 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Rocks | +2.012 |
arily | +1.877 |
iant | +1.862 |
Narc | +1.856 |
iants | +1.837 |
Neg logit contributions | |
creen | -2.156 |
ovember | -2.091 |
MU | -2.075 |
belie | -1.905 |
hur | -1.901 |
Token | affiliated |
Token ID | 18552 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Rocks | +3.205 |
arily | +3.030 |
iant | +3.007 |
Narc | +2.989 |
iants | +2.967 |
Neg logit contributions | |
creen | -3.256 |
ovember | -3.172 |
MU | -3.160 |
hur | -2.863 |
uckle | -2.833 |
Token | with |
Token ID | 351 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
creen | +1.671 |
ovember | +1.594 |
MU | +1.588 |
belie | +1.457 |
hur | +1.427 |
Neg logit contributions | |
Rocks | -1.973 |
arily | -1.852 |
iant | -1.845 |
bow | -1.832 |
iants | -1.831 |
Token | Sky |
Token ID | 5274 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
creen | +0.820 |
ovember | +0.790 |
MU | +0.786 |
belie | +0.728 |
hur | +0.715 |
Neg logit contributions | |
Rocks | -0.798 |
arily | -0.751 |
iant | -0.747 |
iants | -0.741 |
bow | -0.739 |
Token | High |
Token ID | 3334 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
creen | +3.655 |
MU | +3.482 |
ovember | +3.471 |
belie | +3.202 |
hur | +3.175 |
Neg logit contributions | |
Rocks | -3.443 |
arily | -3.284 |
iant | -3.238 |
iants | -3.238 |
--> | -3.230 |
Token | Hol |
Token ID | 6479 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
creen | +9.566 |
ovember | +8.564 |
MU | +8.465 |
belie | +8.155 |
emp | +8.064 |
Neg logit contributions | |
Rocks | -12.066 |
arily | -11.704 |
igree | -11.614 |
iants | -11.588 |
iant | -11.548 |
Token | istic |
Token ID | 2569 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
creen | +2.605 |
MU | +2.521 |
ovember | +2.484 |
belie | +2.266 |
veland | +2.246 |
Neg logit contributions | |
Rocks | -4.081 |
--> | -3.739 |
iants | -3.722 |
Narc | -3.698 |
Pet | -3.696 |
Token | but |
Token ID | 475 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
creen | +0.152 |
ovember | +0.146 |
MU | +0.145 |
belie | +0.135 |
hur | +0.133 |
Neg logit contributions | |
Rocks | -0.141 |
arily | -0.132 |
iant | -0.132 |
iants | -0.130 |
--> | -0.130 |
Token | lost |
Token ID | 2626 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Rocks | +1.219 |
arily | +1.144 |
iant | +1.138 |
--> | +1.123 |
bow | +1.122 |
Neg logit contributions | |
creen | -1.336 |
ovember | -1.302 |
MU | -1.296 |
belie | -1.188 |
hur | -1.182 |
Token | power |
Token ID | 1176 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
creen | +3.369 |
ovember | +3.244 |
MU | +3.211 |
belie | +3.033 |
uckle | +2.888 |
Neg logit contributions | |
Rocks | -3.612 |
iant | -3.410 |
iants | -3.404 |
ogyn | -3.395 |
bow | -3.390 |
Token | It |
Token ID | 1026 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
creen | +0.152 |
ovember | +0.147 |
MU | +0.147 |
belie | +0.135 |
hur | +0.134 |
Neg logit contributions | |
Rocks | -0.134 |
arily | -0.125 |
iant | -0.124 |
iants | -0.123 |
bow | -0.122 |
Token | was |
Token ID | 373 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
creen | +0.602 |
ovember | +0.581 |
MU | +0.576 |
belie | +0.535 |
hur | +0.529 |
Neg logit contributions | |
Rocks | -0.569 |
arily | -0.532 |
iant | -0.531 |
iants | -0.528 |
--> | -0.525 |
Token | probably |
Token ID | 2192 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Rocks | +4.863 |
arily | +4.573 |
Narc | +4.519 |
--> | +4.475 |
iant | +4.471 |
Neg logit contributions | |
creen | -5.182 |
ovember | -5.004 |
MU | -4.940 |
uckle | -4.546 |
iffe | -4.540 |
Token | the |
Token ID | 262 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Rocks | +3.628 |
arily | +3.434 |
Narc | +3.396 |
--> | +3.369 |
iant | +3.365 |
Neg logit contributions | |
creen | -4.199 |
ovember | -4.099 |
MU | -4.043 |
iffe | -3.696 |
belie | -3.692 |
Token | first |
Token ID | 717 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Rocks | +5.527 |
Narc | +5.164 |
iant | +5.154 |
arily | +5.122 |
--> | +5.112 |
Neg logit contributions | |
creen | -5.816 |
ovember | -5.658 |
MU | -5.546 |
hur | -5.119 |
veland | -5.112 |
Token | time |
Token ID | 640 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Rocks | +6.634 |
Narc | +6.240 |
arily | +6.227 |
--> | +6.191 |
iant | +6.159 |
Neg logit contributions | |
creen | -8.567 |
ovember | -8.336 |
MU | -8.057 |
ioxide | -7.645 |
uckle | -7.580 |
Token | any |
Token ID | 597 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Rocks | +6.638 |
Narc | +6.204 |
--> | +6.159 |
Pet | +6.114 |
arily | +6.104 |
Neg logit contributions | |
creen | -9.387 |
ovember | -9.280 |
MU | -9.029 |
belie | -8.501 |
ioxide | -8.484 |
Token | Prime |
Token ID | 5537 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Rocks | +1.754 |
arily | +1.639 |
iant | +1.637 |
--> | +1.615 |
bow | +1.615 |
Neg logit contributions | |
creen | -2.011 |
ovember | -1.947 |
MU | -1.919 |
belie | -1.787 |
hur | -1.763 |
Token | Minister |
Token ID | 4139 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
creen | +2.730 |
MU | +2.635 |
ovember | +2.615 |
belie | +2.312 |
hur | +2.297 |
Neg logit contributions | |
Rocks | -4.349 |
iants | -4.155 |
iant | -4.144 |
arily | -4.137 |
ogyn | -4.110 |
Token | had |
Token ID | 550 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
Rocks | +0.668 |
arily | +0.624 |
iant | +0.621 |
bow | +0.612 |
--> | +0.612 |
Neg logit contributions | |
creen | -0.793 |
ovember | -0.768 |
MU | -0.763 |
belie | -0.709 |
hur | -0.700 |
Token | lunch |
Token ID | 9965 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
creen | +0.663 |
ovember | +0.637 |
MU | +0.633 |
belie | +0.591 |
hur | +0.580 |
Neg logit contributions | |
Rocks | -0.612 |
iant | -0.572 |
arily | -0.570 |
iants | -0.568 |
--> | -0.563 |
Token | Anti |
Token ID | 12297 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Rocks | +0.278 |
arily | +0.259 |
iant | +0.258 |
iants | +0.255 |
--> | +0.255 |
Neg logit contributions | |
creen | -0.341 |
ovember | -0.330 |
MU | -0.328 |
belie | -0.306 |
hur | -0.302 |
Token | - |
Token ID | 12 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
creen | +4.671 |
MU | +4.555 |
ovember | +4.354 |
hur | +4.132 |
emp | +4.090 |
Neg logit contributions | |
Rocks | -6.416 |
igree | -6.163 |
iant | -6.051 |
arily | -6.050 |
iants | -6.028 |
Token | Author |
Token ID | 13838 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Rocks | +3.203 |
Pet | +3.086 |
iant | +3.003 |
iants | +2.999 |
arily | +2.996 |
Neg logit contributions | |
creen | -5.596 |
ovember | -5.580 |
MU | -5.294 |
belie | -5.177 |
uckle | -5.073 |
Token | itarian |
Token ID | 8353 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
creen | +2.770 |
ovember | +2.684 |
MU | +2.657 |
iffe | +2.530 |
hur | +2.513 |
Neg logit contributions | |
Rocks | -1.951 |
--> | -1.777 |
bow | -1.736 |
arily | -1.733 |
Narc | -1.727 |
Token | Movement |
Token ID | 15477 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
creen | +1.329 |
MU | +1.280 |
ovember | +1.271 |
belie | +1.162 |
hur | +1.144 |
Neg logit contributions | |
Rocks | -1.626 |
arily | -1.543 |
iant | -1.536 |
bow | -1.525 |
iants | -1.519 |
Token | ( |
Token ID | 357 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
Rocks | +3.546 |
arily | +3.290 |
iant | +3.278 |
iants | +3.273 |
--> | +3.257 |
Neg logit contributions | |
creen | -3.895 |
ovember | -3.820 |
MU | -3.657 |
belie | -3.419 |
hur | -3.382 |
Token | AK |
Token ID | 10206 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Rocks | +5.394 |
GY | +5.382 |
arily | +5.339 |
--> | +5.305 |
bow | +5.289 |
Neg logit contributions | |
creen | -11.121 |
ovember | -11.006 |
belie | -10.344 |
uckle | -10.083 |
MU | -10.056 |
Token | ) |
Token ID | 8 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
MU | +5.538 |
creen | +5.502 |
ovember | +5.210 |
belie | +4.888 |
hur | +4.843 |
Neg logit contributions | |
Rocks | -4.907 |
iant | -4.599 |
arily | -4.582 |
igree | -4.556 |
ogyn | -4.544 |
Token | and |
Token ID | 290 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
creen | +0.832 |
ovember | +0.800 |
MU | +0.798 |
belie | +0.736 |
hur | +0.726 |
Neg logit contributions | |
Rocks | -0.872 |
arily | -0.822 |
iant | -0.819 |
bow | -0.809 |
--> | -0.808 |
Token | what |
Token ID | 644 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
creen | +3.294 |
MU | +3.161 |
ovember | +3.126 |
belie | +2.926 |
hur | +2.869 |
Neg logit contributions | |
Rocks | -4.022 |
arily | -3.820 |
bow | -3.805 |
iant | -3.786 |
ogyn | -3.776 |
Token | type |
Token ID | 2099 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
creen | +0.391 |
ovember | +0.377 |
MU | +0.375 |
belie | +0.347 |
hur | +0.342 |
Neg logit contributions | |
Rocks | -0.386 |
arily | -0.362 |
iant | -0.361 |
iants | -0.357 |
bow | -0.357 |
Token | a |
Token ID | 257 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
Rocks | +0.891 |
arily | +0.826 |
iant | +0.822 |
--> | +0.814 |
iants | +0.811 |
Neg logit contributions | |
creen | -1.082 |
ovember | -1.046 |
MU | -1.036 |
belie | -0.963 |
hur | -0.956 |
Token | guest |
Token ID | 8319 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Rocks | +0.567 |
iant | +0.527 |
arily | +0.527 |
--> | +0.521 |
bow | +0.520 |
Neg logit contributions | |
creen | -0.613 |
ovember | -0.592 |
MU | -0.586 |
belie | -0.541 |
hur | -0.539 |
Token | blog |
Token ID | 4130 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Rocks | +1.237 |
arily | +1.144 |
iant | +1.140 |
--> | +1.127 |
bow | +1.124 |
Neg logit contributions | |
creen | -1.550 |
ovember | -1.498 |
MU | -1.486 |
belie | -1.379 |
hur | -1.375 |
Token | ? |
Token ID | 30 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
creen | +1.278 |
ovember | +1.229 |
MU | +1.226 |
belie | +1.137 |
hur | +1.117 |
Neg logit contributions | |
Rocks | -1.255 |
arily | -1.176 |
iant | -1.171 |
iants | -1.168 |
ogyn | -1.156 |
Token | E |
Token ID | 412 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
Rocks | +1.540 |
arily | +1.415 |
iant | +1.415 |
--> | +1.407 |
bow | +1.403 |
Neg logit contributions | |
creen | -1.851 |
ovember | -1.806 |
MU | -1.770 |
belie | -1.663 |
iffe | -1.639 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Rocks | +6.359 |
GY | +6.164 |
bow | +6.062 |
NS | +6.051 |
arily | +6.009 |
Neg logit contributions | |
creen | -8.629 |
ovember | -8.489 |
MU | -8.028 |
belie | -7.803 |
iffe | -7.782 |
Token | mail |
Token ID | 4529 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Pet | +4.608 |
Rocks | +4.579 |
GY | +4.532 |
arily | +4.461 |
bow | +4.368 |
Neg logit contributions | |
creen | -13.098 |
ovember | -12.755 |
ioxide | -12.283 |
belie | -12.250 |
veland | -11.854 |
Token | me |
Token ID | 502 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Rocks | +1.511 |
arily | +1.405 |
iant | +1.393 |
--> | +1.378 |
bow | +1.373 |
Neg logit contributions | |
creen | -1.757 |
ovember | -1.697 |
MU | -1.679 |
iffe | -1.548 |
belie | -1.544 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
creen | +3.165 |
MU | +3.068 |
ovember | +3.048 |
belie | +2.849 |
hur | +2.787 |
Neg logit contributions | |
Rocks | -2.855 |
arily | -2.714 |
iant | -2.684 |
iants | -2.679 |
bow | -2.663 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
creen | +3.707 |
MU | +3.591 |
ovember | +3.535 |
hur | +3.305 |
belie | +3.291 |
Neg logit contributions | |
Rocks | -3.430 |
arily | -3.291 |
iant | -3.244 |
iants | -3.243 |
ogyn | -3.228 |
Token |
|
Token ID | 198 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
creen | +1.695 |
MU | +1.645 |
ovember | +1.616 |
hur | +1.506 |
belie | +1.496 |
Neg logit contributions | |
Rocks | -1.464 |
iant | -1.362 |
arily | -1.361 |
iants | -1.358 |
ogyn | -1.355 |
Token | worrying |
Token ID | 18916 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
creen | +1.161 |
ovember | +1.115 |
MU | +1.110 |
belie | +1.028 |
hur | +1.008 |
Neg logit contributions | |
Rocks | -1.196 |
arily | -1.124 |
iant | -1.123 |
iants | -1.118 |
bow | -1.108 |
Token | interest |
Token ID | 1393 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
creen | +1.618 |
ovember | +1.550 |
MU | +1.548 |
belie | +1.441 |
hur | +1.409 |
Neg logit contributions | |
Rocks | -1.604 |
iant | -1.509 |
iants | -1.506 |
arily | -1.501 |
ogyn | -1.487 |
Token | in |
Token ID | 287 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Rocks | +0.043 |
arily | +0.040 |
iant | +0.040 |
iants | +0.040 |
--> | +0.039 |
Neg logit contributions | |
creen | -0.044 |
ovember | -0.042 |
MU | -0.042 |
belie | -0.039 |
hur | -0.039 |
Token | large |
Token ID | 1588 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
Rocks | +1.969 |
arily | +1.840 |
iant | +1.836 |
--> | +1.810 |
Narc | +1.800 |
Neg logit contributions | |
creen | -2.119 |
ovember | -2.074 |
MU | -2.035 |
belie | -1.866 |
hur | -1.861 |
Token | transmission |
Token ID | 11478 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Rocks | +0.761 |
arily | +0.716 |
iant | +0.708 |
bow | +0.698 |
--> | +0.698 |
Neg logit contributions | |
creen | -0.875 |
ovember | -0.850 |
MU | -0.842 |
belie | -0.782 |
hur | -0.772 |
Token | and |
Token ID | 290 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
creen | +2.060 |
MU | +1.970 |
ovember | +1.964 |
belie | +1.840 |
hur | +1.799 |
Neg logit contributions | |
Rocks | -2.002 |
iant | -1.873 |
iants | -1.861 |
arily | -1.860 |
ogyn | -1.854 |
Token | L |
Token ID | 406 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Rocks | +7.395 |
arily | +7.074 |
iant | +7.028 |
--> | +6.971 |
Pet | +6.883 |
Neg logit contributions | |
ovember | -9.637 |
creen | -9.446 |
MU | -9.313 |
iffe | -8.639 |
uckle | -8.511 |
Token | NG |
Token ID | 10503 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
Rocks | +0.716 |
iant | +0.650 |
arily | +0.622 |
--> | +0.596 |
Pet | +0.582 |
Neg logit contributions | |
creen | -4.419 |
ovember | -4.349 |
MU | -4.263 |
belie | -4.161 |
captcha | -4.117 |
Token | infrastructure |
Token ID | 6884 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
creen | +0.749 |
ovember | +0.718 |
MU | +0.715 |
belie | +0.659 |
hur | +0.649 |
Neg logit contributions | |
Rocks | -0.836 |
arily | -0.785 |
iant | -0.783 |
iants | -0.777 |
--> | -0.775 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
creen | +0.840 |
ovember | +0.811 |
MU | +0.808 |
belie | +0.747 |
hur | +0.734 |
Neg logit contributions | |
Rocks | -0.867 |
iant | -0.813 |
arily | -0.812 |
iants | -0.805 |
bow | -0.803 |
Token | along |
Token ID | 1863 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
creen | +0.158 |
ovember | +0.152 |
MU | +0.151 |
belie | +0.140 |
hur | +0.138 |
Neg logit contributions | |
Rocks | -0.144 |
arily | -0.135 |
iant | -0.135 |
iants | -0.133 |
bow | -0.133 |
Token | ( |
Token ID | 357 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
creen | +0.297 |
ovember | +0.287 |
MU | +0.284 |
belie | +0.262 |
hur | +0.259 |
Neg logit contributions | |
Rocks | -0.316 |
arily | -0.297 |
iant | -0.296 |
iants | -0.293 |
bow | -0.292 |
Token | t |
Token ID | 83 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Rocks | +1.060 |
iant | +0.985 |
arily | +0.978 |
bow | +0.967 |
--> | +0.960 |
Neg logit contributions | |
creen | -2.202 |
ovember | -2.150 |
MU | -2.132 |
belie | -2.034 |
captcha | -1.992 |
Token | � |
Token ID | 447 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
Rocks | +0.889 |
iant | +0.784 |
arily | +0.780 |
--> | +0.775 |
bow | +0.747 |
Neg logit contributions | |
creen | -3.290 |
ovember | -3.212 |
MU | -3.188 |
belie | -3.058 |
hur | -3.011 |
Token | � |
Token ID | 247 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Rocks | +0.456 |
arily | +0.420 |
iant | +0.418 |
iants | +0.412 |
--> | +0.411 |
Neg logit contributions | |
creen | -0.763 |
ovember | -0.741 |
MU | -0.736 |
belie | -0.693 |
hur | -0.684 |
Token | )) |
Token ID | 4008 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
creen | +2.692 |
MU | +2.599 |
ovember | +2.596 |
belie | +2.419 |
hur | +2.416 |
Neg logit contributions | |
Rocks | -2.122 |
arily | -1.967 |
iant | -1.960 |
iants | -1.952 |
ogyn | -1.942 |
Token | exp |
Token ID | 1033 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
creen | +2.013 |
ovember | +1.937 |
MU | +1.932 |
belie | +1.798 |
hur | +1.752 |
Neg logit contributions | |
Rocks | -2.107 |
arily | -2.001 |
iant | -1.992 |
iants | -1.985 |
ogyn | -1.968 |
Token | ( |
Token ID | 7 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Rocks | +4.728 |
iant | +4.656 |
Pet | +4.467 |
--> | +4.467 |
bow | +4.461 |
Neg logit contributions | |
creen | -11.275 |
ovember | -10.849 |
MU | -10.648 |
belie | -10.320 |
captcha | -10.156 |
Token | -( |
Token ID | 30420 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
Rocks | +1.966 |
iant | +1.845 |
arily | +1.831 |
--> | +1.827 |
bow | +1.808 |
Neg logit contributions | |
creen | -3.518 |
ovember | -3.398 |
MU | -3.341 |
belie | -3.216 |
captcha | -3.145 |
Token | t |
Token ID | 83 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
creen | +0.023 |
ovember | +0.022 |
MU | +0.022 |
belie | +0.021 |
hur | +0.021 |
Neg logit contributions | |
Rocks | -0.013 |
arily | -0.012 |
iant | -0.012 |
iants | -0.011 |
--> | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Rocks | +0.608 |
arily | +0.573 |
iant | +0.571 |
--> | +0.566 |
bow | +0.564 |
Neg logit contributions | |
creen | -0.634 |
ovember | -0.613 |
MU | -0.606 |
belie | -0.564 |
hur | -0.554 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Rocks | +1.154 |
iant | +1.082 |
arily | +1.077 |
bow | +1.067 |
--> | +1.058 |
Neg logit contributions | |
creen | -2.522 |
ovember | -2.475 |
MU | -2.451 |
belie | -2.345 |
captcha | -2.306 |
Token | value |
Token ID | 1988 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
creen | +2.196 |
MU | +2.110 |
ovember | +2.098 |
belie | +1.974 |
captcha | +1.940 |
Neg logit contributions | |
Rocks | -2.081 |
arily | -1.974 |
iant | -1.968 |
iants | -1.953 |
ogyn | -1.950 |
Token | inside |
Token ID | 2641 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
Rocks | +0.301 |
arily | +0.282 |
iant | +0.281 |
--> | +0.278 |
iants | +0.278 |
Neg logit contributions | |
creen | -0.319 |
ovember | -0.308 |
MU | -0.305 |
belie | -0.283 |
hur | -0.280 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
creen | +0.843 |
ovember | +0.813 |
MU | +0.808 |
belie | +0.750 |
hur | +0.737 |
Neg logit contributions | |
Rocks | -0.796 |
arily | -0.748 |
iant | -0.747 |
iants | -0.740 |
bow | -0.737 |
Token | tag |
Token ID | 7621 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
creen | +3.276 |
MU | +3.178 |
ovember | +3.150 |
belie | +2.967 |
captcha | +2.937 |
Neg logit contributions | |
Rocks | -2.858 |
arily | -2.701 |
iant | -2.696 |
ogyn | -2.681 |
iants | -2.676 |
Token | is |
Token ID | 318 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
creen | +0.530 |
ovember | +0.512 |
MU | +0.510 |
belie | +0.475 |
hur | +0.468 |
Neg logit contributions | |
Rocks | -0.450 |
arily | -0.420 |
iant | -0.419 |
iants | -0.416 |
ogyn | -0.413 |
Token | shown |
Token ID | 3402 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
creen | +1.044 |
ovember | +1.003 |
MU | +0.999 |
belie | +0.928 |
hur | +0.907 |
Neg logit contributions | |
Rocks | -1.042 |
iant | -0.981 |
arily | -0.979 |
iants | -0.976 |
ogyn | -0.966 |
Token | ( |
Token ID | 357 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
Rocks | +0.615 |
arily | +0.578 |
iant | +0.574 |
--> | +0.569 |
bow | +0.568 |
Neg logit contributions | |
creen | -0.640 |
ovember | -0.621 |
MU | -0.616 |
belie | -0.567 |
hur | -0.562 |
Token | but |
Token ID | 4360 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
creen | +0.716 |
MU | +0.688 |
ovember | +0.688 |
belie | +0.633 |
hur | +0.629 |
Neg logit contributions | |
Rocks | -0.698 |
arily | -0.654 |
iant | -0.652 |
iants | -0.646 |
bow | -0.640 |
Token | you |
Token ID | 345 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Rocks | +0.663 |
arily | +0.621 |
iant | +0.618 |
--> | +0.613 |
bow | +0.610 |
Neg logit contributions | |
creen | -0.714 |
ovember | -0.691 |
MU | -0.686 |
belie | -0.634 |
hur | -0.628 |
Token | can |
Token ID | 460 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
creen | +1.592 |
ovember | +1.501 |
MU | +1.499 |
belie | +1.408 |
captcha | +1.343 |
Neg logit contributions | |
Rocks | -1.943 |
iant | -1.828 |
iants | -1.827 |
ogyn | -1.821 |
bow | -1.817 |
Token | choose |
Token ID | 3853 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
creen | +1.238 |
ovember | +1.181 |
MU | +1.174 |
belie | +1.111 |
captcha | +1.063 |
Neg logit contributions | |
Rocks | -1.278 |
iant | -1.197 |
iants | -1.194 |
arily | -1.193 |
ogyn | -1.185 |
Token | candidate |
Token ID | 4540 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
Rocks | +1.915 |
arily | +1.809 |
iant | +1.806 |
Narc | +1.780 |
bow | +1.773 |
Neg logit contributions | |
creen | -1.785 |
ovember | -1.752 |
MU | -1.704 |
belie | -1.557 |
hur | -1.553 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Rocks | +0.326 |
arily | +0.306 |
iant | +0.306 |
bow | +0.302 |
iants | +0.301 |
Neg logit contributions | |
creen | -0.357 |
ovember | -0.346 |
MU | -0.343 |
belie | -0.317 |
hur | -0.313 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Rocks | +1.796 |
iant | +1.636 |
Narc | +1.634 |
arily | +1.626 |
--> | +1.623 |
Neg logit contributions | |
creen | -2.278 |
ovember | -2.229 |
MU | -2.160 |
belie | -2.048 |
iffe | -2.022 |
Token |
|
Token ID | 198 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
Rocks | +1.466 |
arily | +1.358 |
iant | +1.353 |
--> | +1.349 |
bow | +1.348 |
Neg logit contributions | |
creen | -2.216 |
ovember | -2.173 |
MU | -2.115 |
belie | -2.023 |
captcha | -1.990 |
Token | When |
Token ID | 2215 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Rocks | +0.551 |
arily | +0.514 |
iant | +0.513 |
iants | +0.507 |
bow | +0.505 |
Neg logit contributions | |
creen | -0.648 |
ovember | -0.627 |
MU | -0.622 |
belie | -0.579 |
hur | -0.572 |
Token | you |
Token ID | 345 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Rocks | +2.378 |
arily | +2.202 |
iant | +2.201 |
Narc | +2.178 |
iants | +2.170 |
Neg logit contributions | |
creen | -2.813 |
ovember | -2.749 |
MU | -2.709 |
iffe | -2.490 |
belie | -2.484 |
Token | say |
Token ID | 910 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Rocks | +2.957 |
arily | +2.804 |
iant | +2.772 |
bow | +2.748 |
iants | +2.742 |
Neg logit contributions | |
creen | -3.054 |
MU | -2.976 |
ovember | -2.962 |
hur | -2.717 |
iffe | -2.714 |
Token | this |
Token ID | 428 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Rocks | +2.610 |
arily | +2.441 |
iant | +2.427 |
iants | +2.392 |
ogyn | +2.391 |
Neg logit contributions | |
creen | -2.951 |
ovember | -2.889 |
MU | -2.850 |
iffe | -2.612 |
belie | -2.608 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Rocks | +1.078 |
arily | +1.010 |
iant | +1.002 |
bow | +0.992 |
iants | +0.989 |
Neg logit contributions | |
creen | -1.216 |
ovember | -1.175 |
MU | -1.168 |
belie | -1.076 |
hur | -1.066 |
Token | it |
Token ID | 340 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
creen | +1.011 |
ovember | +0.973 |
MU | +0.969 |
belie | +0.905 |
hur | +0.888 |
Neg logit contributions | |
Rocks | -0.967 |
arily | -0.909 |
iant | -0.905 |
iants | -0.898 |
--> | -0.894 |
Token | tells |
Token ID | 4952 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Rocks | +1.699 |
arily | +1.571 |
iant | +1.559 |
--> | +1.541 |
bow | +1.537 |
Neg logit contributions | |
creen | -2.494 |
ovember | -2.425 |
MU | -2.405 |
iffe | -2.211 |
belie | -2.205 |
Token | way |
Token ID | 835 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
creen | +0.966 |
ovember | +0.927 |
MU | +0.916 |
belie | +0.842 |
hur | +0.821 |
Neg logit contributions | |
Rocks | -1.421 |
iant | -1.347 |
arily | -1.345 |
iants | -1.337 |
--> | -1.334 |
Token | around |
Token ID | 1088 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Rocks | +2.398 |
arily | +2.241 |
Narc | +2.202 |
iant | +2.199 |
--> | +2.188 |
Neg logit contributions | |
creen | -3.026 |
ovember | -2.958 |
MU | -2.879 |
uckle | -2.672 |
hur | -2.668 |
Token | the |
Token ID | 262 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
creen | +1.276 |
ovember | +1.229 |
MU | +1.221 |
belie | +1.132 |
hur | +1.112 |
Neg logit contributions | |
Rocks | -1.345 |
arily | -1.270 |
iant | -1.266 |
bow | -1.255 |
iants | -1.253 |
Token | community |
Token ID | 2055 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
Rocks | +0.726 |
arily | +0.678 |
iant | +0.678 |
iants | +0.669 |
bow | +0.667 |
Neg logit contributions | |
creen | -0.691 |
ovember | -0.665 |
MU | -0.660 |
belie | -0.605 |
hur | -0.598 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Rocks | +0.426 |
arily | +0.400 |
iant | +0.398 |
iants | +0.393 |
bow | +0.392 |
Neg logit contributions | |
creen | -0.456 |
ovember | -0.441 |
MU | -0.436 |
belie | -0.403 |
hur | -0.399 |
Token |
|
Token ID | 198 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
creen | +4.117 |
MU | +4.108 |
ovember | +3.968 |
hur | +3.706 |
Daytona | +3.678 |
Neg logit contributions | |
arily | -3.856 |
Rocks | -3.849 |
igree | -3.822 |
ogyn | -3.763 |
iant | -3.762 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Rocks | +0.516 |
arily | +0.479 |
iant | +0.477 |
bow | +0.472 |
--> | +0.472 |
Neg logit contributions | |
creen | -0.714 |
ovember | -0.694 |
MU | -0.685 |
belie | -0.645 |
hur | -0.634 |
Token | According |
Token ID | 4821 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
MU | +2.753 |
creen | +2.740 |
ovember | +2.673 |
hur | +2.467 |
emp | +2.433 |
Neg logit contributions | |
Rocks | -2.700 |
arily | -2.532 |
igree | -2.517 |
iant | -2.494 |
ogyn | -2.480 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Rocks | +2.655 |
arily | +2.529 |
iant | +2.475 |
Pet | +2.447 |
bow | +2.446 |
Neg logit contributions | |
creen | -3.555 |
ovember | -3.467 |
MU | -3.404 |
belie | -3.205 |
iffe | -3.145 |
Token | the |
Token ID | 262 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
creen | +1.896 |
ovember | +1.825 |
MU | +1.819 |
belie | +1.706 |
hur | +1.676 |
Neg logit contributions | |
Rocks | -1.856 |
arily | -1.760 |
iant | -1.748 |
--> | -1.745 |
bow | -1.744 |
Token | Hills |
Token ID | 14379 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Rocks | +1.763 |
iant | +1.644 |
arily | +1.641 |
Narc | +1.631 |
iants | +1.618 |
Neg logit contributions | |
creen | -1.612 |
ovember | -1.554 |
MU | -1.534 |
belie | -1.396 |
iffe | -1.382 |
Token | The |
Token ID | 383 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
Rocks | +1.588 |
iant | +1.446 |
--> | +1.442 |
arily | +1.441 |
Narc | +1.438 |
Neg logit contributions | |
creen | -1.949 |
ovember | -1.897 |
MU | -1.843 |
belie | -1.754 |
iffe | -1.725 |
Token | profession |
Token ID | 7573 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
creen | +0.370 |
ovember | +0.356 |
MU | +0.354 |
belie | +0.327 |
hur | +0.321 |
Neg logit contributions | |
Rocks | -0.394 |
arily | -0.370 |
iant | -0.370 |
iants | -0.367 |
bow | -0.366 |
Token | has |
Token ID | 468 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
Rocks | +4.507 |
arily | +4.322 |
iant | +4.249 |
--> | +4.198 |
bow | +4.118 |
Neg logit contributions | |
creen | -6.097 |
ovember | -5.852 |
MU | -5.671 |
uckle | -5.329 |
emp | -5.311 |
Token | moved |
Token ID | 3888 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
Rocks | +5.718 |
arily | +5.529 |
Narc | +5.253 |
iant | +5.240 |
--> | +5.205 |
Neg logit contributions | |
creen | -8.192 |
ovember | -8.093 |
MU | -7.842 |
hur | -7.370 |
iffe | -7.345 |
Token | away |
Token ID | 1497 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Rocks | +0.819 |
arily | +0.770 |
iant | +0.764 |
--> | +0.756 |
bow | +0.751 |
Neg logit contributions | |
creen | -0.827 |
ovember | -0.801 |
MU | -0.788 |
belie | -0.722 |
hur | -0.722 |
Token | from |
Token ID | 422 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Rocks | +0.141 |
arily | +0.133 |
iant | +0.133 |
iants | +0.131 |
--> | +0.131 |
Neg logit contributions | |
creen | -0.124 |
ovember | -0.119 |
MU | -0.118 |
belie | -0.109 |
hur | -0.107 |
Token | being |
Token ID | 852 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
Rocks | +1.450 |
arily | +1.369 |
iant | +1.357 |
iants | +1.342 |
--> | +1.338 |
Neg logit contributions | |
creen | -1.358 |
ovember | -1.318 |
MU | -1.302 |
hur | -1.192 |
belie | -1.189 |
Token | primarily |
Token ID | 7525 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
creen | +0.085 |
ovember | +0.082 |
MU | +0.081 |
belie | +0.075 |
hur | +0.074 |
Neg logit contributions | |
Rocks | -0.079 |
arily | -0.074 |
iant | -0.074 |
iants | -0.073 |
bow | -0.073 |
Token | transact |
Token ID | 48878 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Rocks | +3.541 |
arily | +3.381 |
iant | +3.318 |
Narc | +3.242 |
iants | +3.226 |
Neg logit contributions | |
creen | -4.273 |
ovember | -4.266 |
MU | -4.151 |
hur | -3.891 |
veland | -3.853 |
Token | ional |
Token ID | 1538 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
creen | +2.851 |
MU | +2.761 |
ovember | +2.757 |
belie | +2.615 |
hur | +2.547 |
Neg logit contributions | |
Rocks | -1.653 |
arily | -1.486 |
bow | -1.474 |
--> | -1.472 |
Pet | -1.469 |
Token | in |
Token ID | 287 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
creen | +0.158 |
ovember | +0.152 |
MU | +0.151 |
belie | +0.140 |
hur | +0.138 |
Neg logit contributions | |
Rocks | -0.151 |
arily | -0.141 |
iant | -0.141 |
iants | -0.140 |
bow | -0.139 |
Token | Love |
Token ID | 18565 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
creen | +1.818 |
MU | +1.805 |
ovember | +1.760 |
hur | +1.624 |
belie | +1.613 |
Neg logit contributions | |
Rocks | -1.474 |
arily | -1.373 |
iant | -1.357 |
iants | -1.355 |
igree | -1.343 |
Token | in |
Token ID | 287 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Rocks | +0.851 |
arily | +0.790 |
iant | +0.789 |
bow | +0.782 |
iants | +0.779 |
Neg logit contributions | |
creen | -0.951 |
ovember | -0.915 |
MU | -0.913 |
belie | -0.847 |
hur | -0.838 |
Token | Action |
Token ID | 7561 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
creen | +3.509 |
ovember | +3.340 |
MU | +3.295 |
belie | +2.934 |
veland | +2.832 |
Neg logit contributions | |
Rocks | -7.168 |
ogyn | -7.149 |
iant | -7.089 |
iants | -7.076 |
igree | -7.023 |
Token | is |
Token ID | 318 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
creen | +3.845 |
ovember | +3.731 |
MU | +3.674 |
belie | +3.491 |
hur | +3.404 |
Neg logit contributions | |
Rocks | -3.741 |
arily | -3.596 |
iant | -3.560 |
iants | -3.542 |
--> | -3.516 |
Token | the |
Token ID | 262 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
creen | +2.240 |
ovember | +2.146 |
MU | +2.131 |
belie | +1.993 |
hur | +1.954 |
Neg logit contributions | |
Rocks | -2.241 |
iant | -2.102 |
iants | -2.099 |
arily | -2.093 |
--> | -2.091 |
Token | subject |
Token ID | 2426 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Rocks | +4.319 |
arily | +4.079 |
iant | +4.019 |
ogyn | +3.986 |
bow | +3.960 |
Neg logit contributions | |
creen | -4.919 |
ovember | -4.780 |
MU | -4.737 |
hur | -4.384 |
iffe | -4.342 |
Token | of |
Token ID | 286 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
Rocks | +1.781 |
arily | +1.681 |
iant | +1.654 |
bow | +1.645 |
ogyn | +1.637 |
Neg logit contributions | |
creen | -1.896 |
ovember | -1.821 |
MU | -1.810 |
belie | -1.683 |
hur | -1.680 |
Token | a |
Token ID | 257 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
creen | +0.755 |
ovember | +0.729 |
MU | +0.725 |
belie | +0.672 |
hur | +0.661 |
Neg logit contributions | |
Rocks | -0.727 |
arily | -0.684 |
iant | -0.682 |
iants | -0.676 |
--> | -0.673 |
Token | critical |
Token ID | 4688 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
creen | +0.898 |
ovember | +0.865 |
MU | +0.862 |
belie | +0.807 |
hur | +0.793 |
Neg logit contributions | |
Rocks | -0.743 |
iant | -0.696 |
arily | -0.694 |
iants | -0.693 |
bow | -0.682 |
Token | documentary |
Token ID | 11648 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
creen | +1.403 |
MU | +1.346 |
ovember | +1.340 |
belie | +1.256 |
hur | +1.230 |
Neg logit contributions | |
Rocks | -1.273 |
iants | -1.207 |
iant | -1.206 |
arily | -1.197 |
bow | -1.179 |
Token | called |
Token ID | 1444 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Rocks | +1.226 |
arily | +1.151 |
iant | +1.135 |
--> | +1.126 |
bow | +1.124 |
Neg logit contributions | |
creen | -1.362 |
ovember | -1.324 |
MU | -1.314 |
belie | -1.213 |
hur | -1.207 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Rocks | +3.383 |
arily | +3.176 |
iant | +3.174 |
bow | +3.171 |
--> | +3.166 |
Neg logit contributions | |
creen | -4.039 |
ovember | -4.004 |
MU | -3.916 |
captcha | -3.592 |
emp | -3.591 |
Token | if |
Token ID | 611 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Rocks | +1.200 |
arily | +1.117 |
iant | +1.114 |
--> | +1.101 |
bow | +1.099 |
Neg logit contributions | |
creen | -1.409 |
ovember | -1.370 |
MU | -1.351 |
belie | -1.252 |
iffe | -1.240 |
Token | you |
Token ID | 345 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
creen | +0.196 |
ovember | +0.189 |
MU | +0.188 |
belie | +0.174 |
hur | +0.172 |
Neg logit contributions | |
Rocks | -0.180 |
arily | -0.168 |
iant | -0.168 |
iants | -0.166 |
bow | -0.166 |
Token | can |
Token ID | 460 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Rocks | +0.940 |
arily | +0.883 |
iant | +0.881 |
--> | +0.870 |
iants | +0.869 |
Neg logit contributions | |
creen | -0.982 |
ovember | -0.951 |
MU | -0.942 |
belie | -0.869 |
hur | -0.860 |
Token | roll |
Token ID | 4836 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
Rocks | +2.077 |
iant | +1.941 |
arily | +1.937 |
--> | +1.922 |
bow | +1.907 |
Neg logit contributions | |
creen | -2.350 |
ovember | -2.278 |
MU | -2.239 |
belie | -2.067 |
hur | -2.055 |
Token | correctly |
Token ID | 9380 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
creen | +2.840 |
MU | +2.716 |
ovember | +2.700 |
belie | +2.541 |
hur | +2.481 |
Neg logit contributions | |
Rocks | -2.898 |
arily | -2.776 |
iants | -2.756 |
ogyn | -2.741 |
iant | -2.741 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Rocks | +0.463 |
arily | +0.434 |
iant | +0.433 |
--> | +0.429 |
bow | +0.427 |
Neg logit contributions | |
creen | -0.486 |
ovember | -0.471 |
MU | -0.466 |
belie | -0.431 |
hur | -0.426 |
Token | He |
Token ID | 679 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Rocks | +1.280 |
iant | +1.181 |
arily | +1.181 |
Narc | +1.175 |
bow | +1.173 |
Neg logit contributions | |
creen | -1.343 |
ovember | -1.305 |
MU | -1.281 |
belie | -1.195 |
iffe | -1.175 |
Token | also |
Token ID | 635 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
creen | +3.649 |
MU | +3.540 |
ovember | +3.520 |
hur | +3.313 |
belie | +3.281 |
Neg logit contributions | |
Rocks | -3.323 |
iants | -3.122 |
arily | -3.114 |
ogyn | -3.091 |
iant | -3.078 |
Token | self |
Token ID | 2116 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
creen | +3.511 |
ovember | +3.358 |
MU | +3.343 |
belie | +3.174 |
hur | +3.146 |
Neg logit contributions | |
Rocks | -3.399 |
iants | -3.262 |
arily | -3.237 |
ogyn | -3.232 |
iant | -3.224 |
Token | - |
Token ID | 12 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
Rocks | +3.743 |
arily | +3.499 |
bow | +3.422 |
iant | +3.418 |
--> | +3.397 |
Neg logit contributions | |
creen | -4.487 |
ovember | -4.381 |
MU | -4.217 |
captcha | -3.913 |
uckle | -3.898 |
Token | elders |
Token ID | 27495 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
Rocks | +4.345 |
Narc | +4.086 |
iant | +4.045 |
iants | +3.931 |
bow | +3.906 |
Neg logit contributions | |
creen | -5.200 |
ovember | -4.991 |
MU | -4.930 |
emp | -4.570 |
iffe | -4.511 |
Token | in |
Token ID | 287 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Rocks | +5.092 |
iant | +4.834 |
arily | +4.827 |
Narc | +4.749 |
bow | +4.733 |
Neg logit contributions | |
ovember | -6.753 |
creen | -6.652 |
MU | -6.631 |
captcha | -6.156 |
ioxide | -6.138 |
Token | their |
Token ID | 511 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Rocks | +2.869 |
iant | +2.640 |
arily | +2.636 |
Narc | +2.629 |
bow | +2.610 |
Neg logit contributions | |
creen | -3.130 |
ovember | -3.026 |
MU | -2.986 |
belie | -2.730 |
hur | -2.719 |
Token | church |
Token ID | 4928 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Rocks | +2.177 |
iant | +2.035 |
arily | +2.009 |
--> | +1.997 |
Narc | +1.995 |
Neg logit contributions | |
creen | -2.265 |
ovember | -2.173 |
MU | -2.154 |
belie | -1.973 |
hur | -1.956 |
Token | , |
Token ID | 11 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Rocks | +2.377 |
iant | +2.242 |
arily | +2.238 |
bow | +2.191 |
Narc | +2.180 |
Neg logit contributions | |
creen | -2.861 |
ovember | -2.790 |
MU | -2.761 |
belie | -2.553 |
captcha | -2.531 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Rocks | +2.741 |
iant | +2.542 |
arily | +2.537 |
Narc | +2.505 |
iants | +2.505 |
Neg logit contributions | |
creen | -3.248 |
ovember | -3.148 |
MU | -3.089 |
emp | -2.847 |
iffe | -2.842 |
Token | decided |
Token ID | 3066 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
creen | +1.597 |
ovember | +1.541 |
MU | +1.528 |
belie | +1.431 |
hur | +1.400 |
Neg logit contributions | |
Rocks | -1.556 |
iant | -1.460 |
arily | -1.456 |
iants | -1.450 |
--> | -1.443 |
Token | to |
Token ID | 284 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Rocks | +0.327 |
arily | +0.307 |
iant | +0.306 |
iants | +0.302 |
--> | +0.301 |
Neg logit contributions | |
creen | -0.366 |
ovember | -0.354 |
MU | -0.351 |
belie | -0.324 |
hur | -0.320 |
Token | send |
Token ID | 3758 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
Rocks | +4.314 |
arily | +4.127 |
iant | +4.034 |
Narc | +4.009 |
bow | +3.992 |
Neg logit contributions | |
creen | -4.573 |
ovember | -4.516 |
MU | -4.509 |
iffe | -4.102 |
hur | -4.083 |
Token | him |
Token ID | 683 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
creen | +3.905 |
ovember | +3.751 |
MU | +3.730 |
belie | +3.537 |
hur | +3.500 |
Neg logit contributions | |
Rocks | -4.438 |
iants | -4.248 |
iant | -4.247 |
--> | -4.244 |
arily | -4.236 |
Token | away |
Token ID | 1497 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
creen | +2.817 |
ovember | +2.738 |
MU | +2.728 |
belie | +2.597 |
hur | +2.542 |
Neg logit contributions | |
Rocks | -2.725 |
iants | -2.596 |
iant | -2.590 |
arily | -2.571 |
--> | -2.547 |
Token | nut |
Token ID | 14930 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
Rocks | +0.404 |
iant | +0.372 |
arily | +0.371 |
bow | +0.366 |
--> | +0.365 |
Neg logit contributions | |
creen | -0.759 |
ovember | -0.736 |
MU | -0.734 |
belie | -0.693 |
hur | -0.683 |
Token | said |
Token ID | 531 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
creen | +0.347 |
ovember | +0.336 |
MU | +0.334 |
belie | +0.311 |
hur | +0.308 |
Neg logit contributions | |
Rocks | -0.270 |
arily | -0.251 |
iant | -0.251 |
iants | -0.247 |
bow | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Rocks | +1.021 |
arily | +0.952 |
iant | +0.950 |
bow | +0.940 |
ogyn | +0.936 |
Neg logit contributions | |
creen | -1.106 |
MU | -1.069 |
ovember | -1.069 |
belie | -0.980 |
hur | -0.971 |
Token |
|
Token ID | 198 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
Rocks | +0.371 |
arily | +0.341 |
iant | +0.341 |
iants | +0.336 |
--> | +0.335 |
Neg logit contributions | |
creen | -0.568 |
ovember | -0.550 |
MU | -0.546 |
belie | -0.513 |
hur | -0.506 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
Rocks | +0.044 |
arily | +0.041 |
iant | +0.041 |
iants | +0.040 |
bow | +0.040 |
Neg logit contributions | |
creen | -0.057 |
ovember | -0.055 |
MU | -0.055 |
belie | -0.051 |
hur | -0.051 |
Token | In |
Token ID | 818 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
Rocks | +0.197 |
arily | +0.180 |
iant | +0.180 |
iants | +0.177 |
--> | +0.177 |
Neg logit contributions | |
creen | -0.364 |
ovember | -0.353 |
MU | -0.351 |
belie | -0.332 |
hur | -0.327 |
Token | the |
Token ID | 262 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Rocks | +0.309 |
arily | +0.290 |
iant | +0.289 |
iants | +0.286 |
bow | +0.285 |
Neg logit contributions | |
creen | -0.323 |
ovember | -0.312 |
MU | -0.310 |
belie | -0.287 |
hur | -0.283 |
Token | 10 |
Token ID | 838 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
Rocks | +3.143 |
arily | +2.926 |
iant | +2.911 |
Narc | +2.867 |
--> | +2.858 |
Neg logit contributions | |
creen | -3.737 |
ovember | -3.610 |
MU | -3.537 |
hur | -3.243 |
iffe | -3.238 |
Token | - |
Token ID | 12 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
creen | +0.592 |
ovember | +0.571 |
MU | +0.567 |
belie | +0.523 |
hur | +0.516 |
Neg logit contributions | |
Rocks | -0.609 |
arily | -0.572 |
iant | -0.570 |
iants | -0.565 |
bow | -0.563 |
Token | minute |
Token ID | 11374 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Rocks | +1.461 |
arily | +1.379 |
iant | +1.378 |
bow | +1.366 |
Pet | +1.357 |
Neg logit contributions | |
creen | -1.759 |
ovember | -1.704 |
MU | -1.674 |
belie | -1.583 |
uckle | -1.539 |
Token | contest |
Token ID | 8414 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Rocks | +2.769 |
arily | +2.606 |
iant | +2.605 |
--> | +2.577 |
bow | +2.569 |
Neg logit contributions | |
creen | -2.737 |
ovember | -2.700 |
MU | -2.644 |
hur | -2.410 |
belie | -2.406 |
Token | people |
Token ID | 661 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
creen | +0.416 |
ovember | +0.400 |
MU | +0.398 |
belie | +0.370 |
hur | +0.363 |
Neg logit contributions | |
Rocks | -0.403 |
arily | -0.378 |
iant | -0.377 |
iants | -0.374 |
bow | -0.374 |
Token | in |
Token ID | 287 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Rocks | +2.521 |
arily | +2.377 |
iant | +2.352 |
iants | +2.301 |
--> | +2.289 |
Neg logit contributions | |
creen | -2.918 |
ovember | -2.867 |
MU | -2.829 |
hur | -2.599 |
iffe | -2.592 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
creen | +3.244 |
MU | +3.143 |
ovember | +3.141 |
belie | +2.933 |
veland | +2.851 |
Neg logit contributions | |
Rocks | -3.447 |
ogyn | -3.298 |
arily | -3.298 |
iants | -3.293 |
iant | -3.291 |
Token | community |
Token ID | 2055 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
creen | +3.616 |
ovember | +3.516 |
MU | +3.472 |
belie | +3.266 |
veland | +3.114 |
Neg logit contributions | |
Rocks | -4.198 |
arily | -4.042 |
ogyn | -3.993 |
iants | -3.974 |
bow | -3.967 |
Token | embrace |
Token ID | 12553 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Rocks | +1.647 |
arily | +1.555 |
iant | +1.541 |
iants | +1.517 |
--> | +1.514 |
Neg logit contributions | |
creen | -1.784 |
ovember | -1.733 |
MU | -1.717 |
hur | -1.574 |
belie | -1.572 |
Token | me |
Token ID | 502 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
creen | +2.195 |
ovember | +2.107 |
MU | +2.104 |
belie | +1.968 |
hur | +1.909 |
Neg logit contributions | |
Rocks | -2.290 |
arily | -2.164 |
iant | -2.164 |
iants | -2.156 |
bow | -2.144 |
Token | for |
Token ID | 329 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Rocks | +0.286 |
arily | +0.269 |
iant | +0.268 |
iants | +0.264 |
bow | +0.264 |
Neg logit contributions | |
creen | -0.303 |
ovember | -0.294 |
MU | -0.291 |
belie | -0.269 |
hur | -0.266 |
Token | that |
Token ID | 326 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
creen | +3.880 |
MU | +3.714 |
ovember | +3.703 |
belie | +3.523 |
hur | +3.419 |
Neg logit contributions | |
Rocks | -4.555 |
iants | -4.386 |
ogyn | -4.374 |
iant | -4.362 |
--> | -4.344 |
Token | ." |
Token ID | 526 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
creen | +2.484 |
MU | +2.379 |
ovember | +2.373 |
belie | +2.219 |
hur | +2.124 |
Neg logit contributions | |
Rocks | -2.811 |
--> | -2.624 |
iants | -2.621 |
iant | -2.618 |
arily | -2.617 |
Token |
|
Token ID | 198 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
creen | +1.030 |
ovember | +0.994 |
MU | +0.989 |
belie | +0.917 |
hur | +0.905 |
Neg logit contributions | |
Rocks | -0.935 |
arily | -0.876 |
iant | -0.873 |
iants | -0.863 |
--> | -0.860 |
Token |
|
Token ID | 198 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
Rocks | +0.247 |
arily | +0.229 |
iant | +0.229 |
iants | +0.226 |
bow | +0.225 |
Neg logit contributions | |
creen | -0.329 |
ovember | -0.318 |
MU | -0.316 |
belie | -0.296 |
hur | -0.292 |
Token | Friday |
Token ID | 3217 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
creen | +3.846 |
ovember | +3.618 |
MU | +3.588 |
belie | +3.380 |
hur | +3.285 |
Neg logit contributions | |
Rocks | -5.118 |
igree | -4.881 |
arily | -4.871 |
iants | -4.864 |
GY | -4.856 |
Token | in |
Token ID | 287 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
Rocks | +0.523 |
arily | +0.490 |
iant | +0.490 |
bow | +0.483 |
--> | +0.482 |
Neg logit contributions | |
creen | -0.588 |
ovember | -0.571 |
MU | -0.565 |
belie | -0.522 |
hur | -0.516 |
Token | Havana |
Token ID | 40274 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
creen | +0.661 |
ovember | +0.637 |
MU | +0.634 |
belie | +0.590 |
hur | +0.581 |
Neg logit contributions | |
Rocks | -0.616 |
arily | -0.578 |
iant | -0.576 |
iants | -0.571 |
--> | -0.570 |
Token | and |
Token ID | 290 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
creen | +0.014 |
ovember | +0.013 |
MU | +0.013 |
belie | +0.012 |
hur | +0.012 |
Neg logit contributions | |
Rocks | -0.013 |
arily | -0.012 |
iant | -0.012 |
iants | -0.012 |
bow | -0.012 |
Token | released |
Token ID | 2716 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
creen | +0.700 |
ovember | +0.676 |
MU | +0.671 |
belie | +0.623 |
hur | +0.614 |
Neg logit contributions | |
Rocks | -0.691 |
arily | -0.647 |
iant | -0.647 |
iants | -0.641 |
--> | -0.640 |
Token | him |
Token ID | 683 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Rocks | +3.260 |
arily | +3.011 |
iant | +3.011 |
Narc | +3.006 |
Pet | +2.960 |
Neg logit contributions | |
creen | -4.481 |
ovember | -4.367 |
MU | -4.284 |
belie | -3.973 |
uckle | -3.952 |
Token | on |
Token ID | 319 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Rocks | +0.256 |
arily | +0.241 |
iant | +0.240 |
iants | +0.237 |
bow | +0.237 |
Neg logit contributions | |
creen | -0.238 |
ovember | -0.230 |
MU | -0.228 |
belie | -0.210 |
hur | -0.207 |
Token | Sunday |
Token ID | 3502 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
creen | +3.279 |
ovember | +3.083 |
MU | +3.061 |
belie | +2.843 |
captcha | +2.796 |
Neg logit contributions | |
Rocks | -4.189 |
iants | -3.956 |
arily | -3.953 |
iant | -3.924 |
ogyn | -3.918 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Rocks | +0.615 |
arily | +0.578 |
iant | +0.578 |
--> | +0.569 |
bow | +0.569 |
Neg logit contributions | |
creen | -0.676 |
ovember | -0.655 |
MU | -0.649 |
belie | -0.599 |
hur | -0.593 |
Token | his |
Token ID | 465 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
creen | +2.375 |
MU | +2.299 |
ovember | +2.287 |
belie | +2.159 |
hur | +2.125 |
Neg logit contributions | |
Rocks | -2.409 |
arily | -2.279 |
--> | -2.262 |
iant | -2.246 |
iants | -2.241 |
Token | group |
Token ID | 1448 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
creen | +0.929 |
ovember | +0.898 |
MU | +0.897 |
belie | +0.840 |
hur | +0.827 |
Neg logit contributions | |
Rocks | -0.749 |
arily | -0.696 |
iant | -0.695 |
iants | -0.689 |
--> | -0.687 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
creen | +3.352 |
ovember | +3.241 |
MU | +3.234 |
belie | +3.023 |
hur | +2.976 |
Neg logit contributions | |
Rocks | -3.485 |
arily | -3.264 |
iant | -3.256 |
iants | -3.251 |
--> | -3.228 |
Token | I |
Token ID | 314 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
creen | +1.428 |
ovember | +1.378 |
MU | +1.378 |
belie | +1.289 |
hur | +1.260 |
Neg logit contributions | |
Rocks | -1.437 |
arily | -1.354 |
iant | -1.348 |
iants | -1.338 |
bow | -1.336 |
Token | am |
Token ID | 716 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
creen | +0.145 |
ovember | +0.140 |
MU | +0.139 |
belie | +0.130 |
hur | +0.128 |
Neg logit contributions | |
Rocks | -0.132 |
arily | -0.123 |
iant | -0.123 |
iants | -0.122 |
bow | -0.121 |
Token | not |
Token ID | 407 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
creen | +1.684 |
ovember | +1.619 |
MU | +1.618 |
belie | +1.516 |
hur | +1.488 |
Neg logit contributions | |
Rocks | -1.620 |
iant | -1.511 |
arily | -1.504 |
iants | -1.502 |
--> | -1.494 |
Token | in |
Token ID | 287 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
creen | +2.015 |
MU | +1.935 |
ovember | +1.933 |
belie | +1.827 |
hur | +1.789 |
Neg logit contributions | |
Rocks | -2.032 |
iant | -1.902 |
arily | -1.901 |
iants | -1.895 |
ogyn | -1.883 |
Token | the |
Token ID | 262 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
creen | +5.256 |
MU | +5.111 |
ovember | +5.020 |
belie | +4.788 |
emp | +4.655 |
Neg logit contributions | |
Rocks | -6.069 |
igree | -5.736 |
iant | -5.706 |
ogyn | -5.705 |
iants | -5.697 |
Token | business |
Token ID | 1597 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
MU | +6.410 |
creen | +6.404 |
ovember | +6.206 |
belie | +5.970 |
hur | +5.837 |
Neg logit contributions | |
Rocks | -7.760 |
ogyn | -7.433 |
iant | -7.406 |
igree | -7.360 |
--> | -7.313 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
creen | +3.716 |
ovember | +3.553 |
MU | +3.547 |
belie | +3.300 |
hur | +3.196 |
Neg logit contributions | |
Rocks | -4.357 |
iant | -4.065 |
iants | -4.054 |
bow | -4.030 |
ogyn | -4.030 |
Token | ignoring |
Token ID | 15482 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
creen | +1.026 |
ovember | +0.989 |
MU | +0.983 |
belie | +0.920 |
hur | +0.903 |
Neg logit contributions | |
Rocks | -0.977 |
iant | -0.917 |
arily | -0.916 |
iants | -0.908 |
--> | -0.902 |
Token | what |
Token ID | 644 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
creen | +2.461 |
ovember | +2.380 |
MU | +2.376 |
belie | +2.228 |
hur | +2.170 |
Neg logit contributions | |
Rocks | -2.523 |
iant | -2.390 |
iants | -2.365 |
arily | -2.365 |
bow | -2.355 |
Token | The |
Token ID | 383 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
creen | +3.255 |
MU | +3.184 |
ovember | +3.170 |
belie | +2.964 |
hur | +2.883 |
Neg logit contributions | |
Rocks | -3.730 |
iant | -3.560 |
bow | -3.559 |
arily | -3.546 |
iants | -3.542 |
Token | fell |
Token ID | 3214 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
Rocks | +0.172 |
arily | +0.161 |
iant | +0.161 |
iants | +0.159 |
bow | +0.159 |
Neg logit contributions | |
creen | -0.175 |
ovember | -0.168 |
MU | -0.167 |
belie | -0.155 |
hur | -0.152 |
Token | in |
Token ID | 287 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Rocks | +0.071 |
arily | +0.066 |
iant | +0.066 |
iants | +0.065 |
bow | +0.065 |
Neg logit contributions | |
creen | -0.077 |
ovember | -0.074 |
MU | -0.074 |
belie | -0.068 |
hur | -0.067 |
Token | love |
Token ID | 1842 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
creen | +5.203 |
ovember | +5.063 |
MU | +5.018 |
belie | +4.699 |
Daytona | +4.487 |
Neg logit contributions | |
Rocks | -6.561 |
igree | -6.333 |
bow | -6.316 |
iants | -6.283 |
GY | -6.275 |
Token | with |
Token ID | 351 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
creen | +0.278 |
ovember | +0.268 |
MU | +0.266 |
belie | +0.245 |
hur | +0.241 |
Neg logit contributions | |
Rocks | -0.305 |
arily | -0.287 |
iant | -0.287 |
iants | -0.284 |
bow | -0.284 |
Token | Wii |
Token ID | 16591 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
creen | +1.777 |
ovember | +1.698 |
MU | +1.691 |
belie | +1.574 |
hur | +1.541 |
Neg logit contributions | |
Rocks | -1.893 |
arily | -1.805 |
iant | -1.790 |
iants | -1.786 |
--> | -1.783 |
Token | Sports |
Token ID | 7092 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
creen | +3.083 |
MU | +2.927 |
ovember | +2.906 |
belie | +2.755 |
uckle | +2.626 |
Neg logit contributions | |
Rocks | -3.273 |
iants | -3.205 |
arily | -3.186 |
ogyn | -3.166 |
iant | -3.158 |
Token | can |
Token ID | 460 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
creen | +6.535 |
ovember | +5.910 |
MU | +5.874 |
belie | +5.680 |
Daytona | +5.363 |
Neg logit contributions | |
ogyn | -7.432 |
igree | -7.412 |
iants | -7.386 |
arily | -7.342 |
Rocks | -7.340 |
Token | now |
Token ID | 783 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
creen | +0.063 |
ovember | +0.061 |
MU | +0.061 |
belie | +0.057 |
hur | +0.055 |
Neg logit contributions | |
Rocks | -0.059 |
arily | -0.055 |
iant | -0.055 |
iants | -0.054 |
ogyn | -0.054 |
Token | hop |
Token ID | 1725 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Rocks | +1.752 |
arily | +1.637 |
iant | +1.632 |
iants | +1.611 |
bow | +1.609 |
Neg logit contributions | |
creen | -1.914 |
ovember | -1.860 |
MU | -1.844 |
hur | -1.696 |
belie | -1.693 |
Token | off |
Token ID | 572 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
creen | +3.359 |
MU | +3.193 |
ovember | +3.168 |
belie | +2.957 |
hur | +2.896 |
Neg logit contributions | |
Rocks | -3.976 |
arily | -3.810 |
ogyn | -3.779 |
iant | -3.770 |
--> | -3.754 |
Token | their |
Token ID | 511 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
creen | +1.541 |
ovember | +1.471 |
MU | +1.465 |
belie | +1.363 |
hur | +1.334 |
Neg logit contributions | |
Rocks | -1.588 |
arily | -1.502 |
iant | -1.491 |
iants | -1.481 |
ogyn | -1.481 |
Token | school |
Token ID | 1524 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
creen | +3.546 |
MU | +3.427 |
ovember | +3.350 |
belie | +3.169 |
hur | +3.073 |
Neg logit contributions | |
Rocks | -4.070 |
arily | -3.846 |
iant | -3.821 |
iants | -3.812 |
ogyn | -3.799 |
Token | students |
Token ID | 2444 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
creen | +2.376 |
MU | +2.295 |
ovember | +2.282 |
belie | +2.098 |
hur | +2.062 |
Neg logit contributions | |
Rocks | -2.649 |
iant | -2.498 |
arily | -2.482 |
ogyn | -2.473 |
iants | -2.463 |
Token | about |
Token ID | 546 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
creen | +2.401 |
MU | +2.286 |
ovember | +2.284 |
belie | +2.122 |
hur | +2.084 |
Neg logit contributions | |
Rocks | -2.485 |
arily | -2.321 |
iant | -2.316 |
iants | -2.316 |
bow | -2.294 |
Token | careers |
Token ID | 16179 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
creen | +0.445 |
ovember | +0.428 |
MU | +0.425 |
belie | +0.394 |
hur | +0.387 |
Neg logit contributions | |
Rocks | -0.451 |
arily | -0.423 |
iant | -0.423 |
iants | -0.419 |
bow | -0.418 |
Token | in |
Token ID | 287 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
creen | +0.338 |
ovember | +0.326 |
MU | +0.324 |
belie | +0.300 |
hur | +0.296 |
Neg logit contributions | |
Rocks | -0.316 |
arily | -0.296 |
iant | -0.295 |
iants | -0.293 |
bow | -0.292 |
Token | HR |
Token ID | 15172 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
creen | +0.799 |
ovember | +0.768 |
MU | +0.766 |
belie | +0.707 |
hur | +0.691 |
Neg logit contributions | |
Rocks | -0.825 |
arily | -0.779 |
iant | -0.776 |
iants | -0.770 |
bow | -0.770 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
MU | +7.487 |
creen | +7.396 |
ovember | +6.982 |
belie | +6.603 |
iffe | +6.399 |
Neg logit contributions | |
Rocks | -9.517 |
igree | -9.094 |
ogyn | -8.983 |
bow | -8.978 |
iants | -8.921 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
Rocks | +0.170 |
arily | +0.158 |
iant | +0.157 |
iants | +0.156 |
--> | +0.155 |
Neg logit contributions | |
creen | -0.215 |
ovember | -0.208 |
MU | -0.206 |
belie | -0.192 |
hur | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
Rocks | +0.030 |
arily | +0.027 |
iant | +0.027 |
iants | +0.027 |
--> | +0.027 |
Neg logit contributions | |
creen | -0.038 |
ovember | -0.037 |
MU | -0.037 |
belie | -0.034 |
hur | -0.034 |
Token | Q |
Token ID | 48 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Rocks | +0.217 |
arily | +0.203 |
iant | +0.203 |
iants | +0.201 |
--> | +0.200 |
Neg logit contributions | |
creen | -0.247 |
ovember | -0.238 |
MU | -0.236 |
belie | -0.220 |
hur | -0.217 |
Token | : |
Token ID | 25 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Rocks | +0.448 |
arily | +0.420 |
iant | +0.418 |
--> | +0.415 |
bow | +0.414 |
Neg logit contributions | |
creen | -0.505 |
ovember | -0.490 |
MU | -0.482 |
belie | -0.454 |
hur | -0.444 |
Token | other |
Token ID | 584 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Rocks | +0.157 |
arily | +0.147 |
iant | +0.147 |
iants | +0.145 |
--> | +0.145 |
Neg logit contributions | |
creen | -0.169 |
ovember | -0.164 |
MU | -0.162 |
belie | -0.149 |
hur | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
Rocks | +1.072 |
arily | +1.010 |
iant | +1.007 |
--> | +0.993 |
iants | +0.990 |
Neg logit contributions | |
creen | -1.076 |
ovember | -1.050 |
MU | -1.034 |
belie | -0.940 |
hur | -0.940 |
Token | See |
Token ID | 4091 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
creen | +0.409 |
ovember | +0.395 |
MU | +0.394 |
belie | +0.366 |
hur | +0.361 |
Neg logit contributions | |
Rocks | -0.354 |
arily | -0.332 |
iant | -0.330 |
iants | -0.327 |
bow | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
creen | +0.709 |
ovember | +0.684 |
MU | +0.679 |
belie | +0.629 |
hur | +0.620 |
Neg logit contributions | |
Rocks | -0.712 |
arily | -0.669 |
iant | -0.668 |
iants | -0.662 |
bow | -0.659 |
Token | Zak |
Token ID | 32605 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
creen | +1.443 |
ovember | +1.389 |
MU | +1.383 |
belie | +1.288 |
hur | +1.271 |
Neg logit contributions | |
Rocks | -1.430 |
arily | -1.350 |
iant | -1.346 |
iants | -1.335 |
bow | -1.330 |
Token | ov |
Token ID | 709 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
creen | +4.559 |
ovember | +4.323 |
MU | +4.290 |
hur | +4.127 |
emp | +4.017 |
Neg logit contributions | |
Rocks | -4.118 |
Narc | -3.748 |
GY | -3.732 |
iants | -3.698 |
--> | -3.681 |
Token | itch |
Token ID | 2007 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
creen | +3.553 |
ovember | +3.226 |
MU | +2.891 |
hur | +2.858 |
emp | +2.801 |
Neg logit contributions | |
Rocks | -10.627 |
narcissistic | -9.927 |
Narc | -9.918 |
GY | -9.888 |
iants | -9.866 |
Token | , |
Token ID | 11 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
Rocks | +1.200 |
iant | +1.108 |
arily | +1.107 |
bow | +1.099 |
--> | +1.093 |
Neg logit contributions | |
creen | -1.355 |
ovember | -1.310 |
MU | -1.299 |
belie | -1.196 |
hur | -1.183 |
Token | � |
Token ID | 564 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Rocks | +0.776 |
arily | +0.717 |
iant | +0.715 |
--> | +0.708 |
bow | +0.707 |
Neg logit contributions | |
creen | -0.888 |
ovember | -0.861 |
MU | -0.853 |
belie | -0.786 |
hur | -0.776 |
Token | � |
Token ID | 250 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Rocks | +0.215 |
arily | +0.202 |
iant | +0.202 |
--> | +0.200 |
bow | +0.199 |
Neg logit contributions | |
creen | -0.208 |
ovember | -0.200 |
MU | -0.198 |
belie | -0.183 |
hur | -0.180 |
Token | Ass |
Token ID | 8021 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Rocks | +1.021 |
iant | +0.950 |
arily | +0.949 |
--> | +0.944 |
Pet | +0.942 |
Neg logit contributions | |
creen | -1.186 |
ovember | -1.149 |
MU | -1.129 |
belie | -1.057 |
iffe | -1.038 |
Token | Clim |
Token ID | 28573 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Rocks | +1.719 |
arily | +1.580 |
iant | +1.574 |
--> | +1.557 |
bow | +1.556 |
Neg logit contributions | |
creen | -1.790 |
ovember | -1.727 |
MU | -1.710 |
belie | -1.577 |
hur | -1.556 |
Token | atic |
Token ID | 1512 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
creen | +5.302 |
ovember | +5.028 |
MU | +5.006 |
emp | +4.864 |
iffe | +4.695 |
Neg logit contributions | |
Rocks | -4.635 |
--> | -4.477 |
iants | -4.433 |
bow | -4.398 |
ogyn | -4.348 |
Token | Change |
Token ID | 9794 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
creen | +1.645 |
MU | +1.556 |
ovember | +1.511 |
belie | +1.351 |
hur | +1.314 |
Neg logit contributions | |
Rocks | -4.245 |
iants | -4.173 |
iant | -4.165 |
ogyn | -4.143 |
bow | -4.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
creen | +1.377 |
ovember | +1.329 |
MU | +1.322 |
belie | +1.223 |
hur | +1.213 |
Neg logit contributions | |
Rocks | -1.312 |
arily | -1.238 |
iant | -1.232 |
iants | -1.222 |
--> | -1.220 |
Token | provides |
Token ID | 3769 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Rocks | +1.607 |
arily | +1.497 |
iant | +1.484 |
bow | +1.468 |
--> | +1.467 |
Neg logit contributions | |
creen | -1.843 |
ovember | -1.791 |
MU | -1.771 |
belie | -1.616 |
iffe | -1.612 |
Token | policymakers |
Token ID | 29484 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
creen | +0.966 |
ovember | +0.933 |
MU | +0.927 |
belie | +0.864 |
hur | +0.849 |
Neg logit contributions | |
Rocks | -0.919 |
arily | -0.862 |
iant | -0.860 |
iants | -0.853 |
bow | -0.852 |
Token | with |
Token ID | 351 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
creen | +6.236 |
ovember | +5.826 |
MU | +5.824 |
belie | +5.545 |
hur | +5.277 |
Neg logit contributions | |
Rocks | -9.093 |
ogyn | -8.520 |
--> | -8.494 |
iants | -8.430 |
iant | -8.375 |
Token | a |
Token ID | 257 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
creen | +5.067 |
ovember | +4.855 |
MU | +4.834 |
belie | +4.623 |
hur | +4.431 |
Neg logit contributions | |
Rocks | -5.861 |
ogyn | -5.516 |
--> | -5.487 |
bow | -5.466 |
arily | -5.453 |
Token | more |
Token ID | 517 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
creen | +3.667 |
ovember | +3.478 |
MU | +3.461 |
belie | +3.297 |
captcha | +3.175 |
Neg logit contributions | |
Rocks | -3.983 |
iants | -3.751 |
ogyn | -3.737 |
arily | -3.729 |
iant | -3.716 |
Token | accurate |
Token ID | 7187 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
creen | +4.224 |
MU | +4.002 |
ovember | +3.950 |
belie | +3.860 |
hur | +3.678 |
Neg logit contributions | |
Rocks | -4.612 |
ogyn | -4.363 |
iants | -4.357 |
arily | -4.318 |
iant | -4.304 |
Token | framework |
Token ID | 9355 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
creen | +5.709 |
ovember | +5.293 |
MU | +5.211 |
belie | +5.192 |
captcha | +4.852 |
Neg logit contributions | |
Rocks | -7.395 |
iants | -7.019 |
ogyn | -6.979 |
iant | -6.905 |
--> | -6.903 |