Token | of |
Token ID | 286 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
ting | +8.092 |
rend | +7.542 |
lisher | +7.225 |
◼ | +6.993 |
ITNESS | +6.868 |
Neg logit contributions | |
ioxide | -10.164 |
uve | -9.966 |
ourgeois | -9.959 |
PF | -9.845 |
uses | -9.772 |
Token | Queen |
Token ID | 7542 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ting | +5.573 |
rend | +5.155 |
◼ | +4.716 |
ITNESS | +4.642 |
lisher | +4.547 |
Neg logit contributions | |
ioxide | -9.464 |
anguage | -9.200 |
ourgeois | -9.181 |
uve | -9.179 |
orescent | -8.980 |
Token | � |
Token ID | 447 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ting | +1.191 |
◼ | +1.118 |
lisher | +1.105 |
rend | +1.099 |
ITNESS | +1.049 |
Neg logit contributions | |
ioxide | -1.123 |
uve | -1.118 |
ourgeois | -1.102 |
PF | -1.077 |
uum | -1.074 |
Token | � |
Token ID | 247 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ting | +2.537 |
◼ | +2.363 |
rend | +2.314 |
lisher | +2.311 |
tto | +2.220 |
Neg logit contributions | |
ioxide | -2.694 |
uve | -2.658 |
ourgeois | -2.656 |
ophobia | -2.601 |
PF | -2.580 |
Token | s |
Token ID | 82 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
ting | +4.958 |
rend | +4.474 |
◼ | +4.437 |
lisher | +4.432 |
ted | +4.230 |
Neg logit contributions | |
ioxide | -6.258 |
ourgeois | -6.124 |
uve | -6.119 |
PF | -6.010 |
ophobia | -5.950 |
Token | Bench |
Token ID | 25187 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ting | +4.158 |
rend | +3.749 |
◼ | +3.727 |
lisher | +3.557 |
ITNESS | +3.369 |
Neg logit contributions | |
ioxide | -7.985 |
uve | -7.966 |
ourgeois | -7.872 |
PF | -7.743 |
ophobia | -7.702 |
Token | judge |
Token ID | 5052 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ting | +15.921 |
rend | +14.217 |
ted | +13.514 |
lisher | +12.945 |
overr | +12.891 |
Neg logit contributions | |
ioxide | -14.580 |
uve | -14.083 |
ourgeois | -13.687 |
PF | -13.461 |
uses | -13.456 |
Token | sided |
Token ID | 34384 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ting | +10.407 |
rend | +9.337 |
ted | +8.983 |
overr | +8.949 |
◼ | +8.943 |
Neg logit contributions | |
ioxide | -10.872 |
ourgeois | -10.324 |
PF | -10.202 |
uve | -10.139 |
itement | -9.733 |
Token | with |
Token ID | 351 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ting | +0.760 |
◼ | +0.725 |
lisher | +0.715 |
rend | +0.708 |
ITNESS | +0.688 |
Neg logit contributions | |
ioxide | -0.438 |
uve | -0.433 |
ourgeois | -0.423 |
ophobia | -0.414 |
PF | -0.413 |
Token | Ottawa |
Token ID | 14074 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
uve | +3.042 |
ourgeois | +3.008 |
iv | +2.999 |
ioxide | +2.995 |
ophobia | +2.939 |
Neg logit contributions | |
ting | -3.841 |
◼ | -3.798 |
lisher | -3.702 |
rend | -3.589 |
tto | -3.500 |
Token | . |
Token ID | 13 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ting | +0.955 |
◼ | +0.902 |
lisher | +0.888 |
rend | +0.878 |
ITNESS | +0.847 |
Neg logit contributions | |
ioxide | -0.833 |
uve | -0.826 |
ourgeois | -0.811 |
ophobia | -0.797 |
PF | -0.795 |
Token | better |
Token ID | 1365 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ting | +1.028 |
◼ | +0.986 |
lisher | +0.970 |
rend | +0.964 |
ITNESS | +0.937 |
Neg logit contributions | |
uve | -0.667 |
ioxide | -0.667 |
ourgeois | -0.652 |
iv | -0.645 |
uses | -0.643 |
Token | . |
Token ID | 13 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ting | +4.459 |
◼ | +4.044 |
lisher | +4.014 |
rend | +3.991 |
tto | +3.894 |
Neg logit contributions | |
ioxide | -4.178 |
uve | -4.051 |
ourgeois | -4.007 |
PF | -3.957 |
uum | -3.917 |
Token | Today |
Token ID | 6288 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ting | +6.414 |
◼ | +5.801 |
rend | +5.759 |
tto | +5.676 |
lisher | +5.584 |
Neg logit contributions | |
ioxide | -5.719 |
uve | -5.583 |
ourgeois | -5.476 |
uum | -5.396 |
anguage | -5.347 |
Token | 's |
Token ID | 338 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ting | +4.235 |
◼ | +3.845 |
rend | +3.807 |
lisher | +3.798 |
tto | +3.681 |
Neg logit contributions | |
ioxide | -4.134 |
uve | -4.046 |
ourgeois | -3.939 |
PF | -3.914 |
uum | -3.872 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ting | +6.011 |
◼ | +5.443 |
rend | +5.377 |
lisher | +5.296 |
ted | +5.225 |
Neg logit contributions | |
ioxide | -5.454 |
uve | -5.369 |
PF | -5.192 |
ourgeois | -5.174 |
uum | -5.139 |
Token | Court |
Token ID | 3078 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ting | +7.433 |
rend | +6.447 |
tto | +6.055 |
ted | +5.950 |
◼ | +5.870 |
Neg logit contributions | |
uve | -13.987 |
anguage | -13.980 |
uum | -13.734 |
ourgeois | -13.489 |
PF | -13.435 |
Token | rulings |
Token ID | 31532 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ting | +14.606 |
overr | +12.375 |
rend | +12.224 |
ted | +12.129 |
tto | +11.803 |
Neg logit contributions | |
ioxide | -14.960 |
uve | -14.367 |
uum | -14.198 |
oglu | -13.976 |
ourgeois | -13.913 |
Token | are |
Token ID | 389 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
ting | +11.970 |
tto | +10.081 |
ted | +10.079 |
rend | +10.058 |
tering | +9.935 |
Neg logit contributions | |
ioxide | -11.630 |
uum | -11.057 |
uve | -11.034 |
PF | -10.944 |
ourgeois | -10.658 |
Token | a |
Token ID | 257 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
ting | +7.775 |
◼ | +7.022 |
rend | +7.003 |
lisher | +6.870 |
tto | +6.718 |
Neg logit contributions | |
uve | -7.054 |
ioxide | -6.982 |
uum | -6.959 |
ourgeois | -6.858 |
PF | -6.795 |
Token | giant |
Token ID | 6175 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
ting | +7.681 |
lisher | +6.960 |
◼ | +6.934 |
rend | +6.898 |
tto | +6.685 |
Neg logit contributions | |
ioxide | -6.138 |
uve | -6.104 |
ourgeois | -5.917 |
uum | -5.854 |
PF | -5.751 |
Token | leap |
Token ID | 16470 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ting | +7.136 |
◼ | +6.636 |
lisher | +6.565 |
rend | +6.502 |
ted | +6.237 |
Neg logit contributions | |
ioxide | -5.279 |
uve | -5.212 |
ourgeois | -4.986 |
PF | -4.917 |
uum | -4.917 |
Token | of |
Token ID | 286 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
ting | +4.197 |
◼ | +3.905 |
lisher | +3.835 |
rend | +3.802 |
ted | +3.654 |
Neg logit contributions | |
ioxide | -3.874 |
uve | -3.846 |
ourgeois | -3.815 |
ivan | -3.716 |
ophobia | -3.682 |
Token | course |
Token ID | 1781 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ting | +8.126 |
◼ | +7.531 |
lisher | +7.501 |
rend | +7.488 |
tto | +7.195 |
Neg logit contributions | |
ioxide | -5.261 |
ourgeois | -5.236 |
uve | -5.205 |
ophobia | -5.006 |
PF | -5.002 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ting | +4.727 |
◼ | +4.362 |
rend | +4.323 |
lisher | +4.280 |
ted | +4.095 |
Neg logit contributions | |
uve | -4.978 |
ioxide | -4.952 |
ourgeois | -4.895 |
PF | -4.836 |
ivan | -4.793 |
Token | is |
Token ID | 318 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
ting | +3.541 |
◼ | +3.254 |
rend | +3.233 |
lisher | +3.218 |
tto | +3.063 |
Neg logit contributions | |
ioxide | -3.637 |
uve | -3.600 |
ourgeois | -3.564 |
PF | -3.528 |
ivan | -3.483 |
Token | not |
Token ID | 407 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ting | +5.716 |
◼ | +5.274 |
lisher | +5.167 |
rend | +5.139 |
ted | +5.026 |
Neg logit contributions | |
uve | -5.486 |
ioxide | -5.480 |
ourgeois | -5.478 |
ivan | -5.310 |
PF | -5.302 |
Token | the |
Token ID | 262 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ting | +9.844 |
◼ | +8.837 |
ted | +8.663 |
rend | +8.621 |
lisher | +8.534 |
Neg logit contributions | |
ourgeois | -10.060 |
ioxide | -9.931 |
uve | -9.896 |
itement | -9.789 |
PF | -9.774 |
Token | only |
Token ID | 691 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
sole | +13.179 |
ting | +13.088 |
exclusive | +11.395 |
ted | +11.380 |
◼ | +11.316 |
Neg logit contributions | |
PF | -15.330 |
ourgeois | -14.945 |
uum | -14.866 |
ioxide | -14.823 |
uve | -14.747 |
Token | motion |
Token ID | 6268 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ting | +7.127 |
◼ | +6.470 |
lisher | +6.356 |
ted | +6.318 |
rend | +6.282 |
Neg logit contributions | |
uve | -6.747 |
ioxide | -6.705 |
ourgeois | -6.619 |
PF | -6.528 |
ivan | -6.466 |
Token | we |
Token ID | 356 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
ting | +8.133 |
◼ | +7.129 |
ted | +7.048 |
lisher | +7.048 |
rend | +7.022 |
Neg logit contributions | |
ioxide | -8.306 |
uve | -7.874 |
ourgeois | -7.818 |
PF | -7.815 |
ivan | -7.670 |
Token | have |
Token ID | 423 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ting | +6.522 |
rend | +5.792 |
tto | +5.690 |
lisher | +5.690 |
◼ | +5.639 |
Neg logit contributions | |
uve | -6.868 |
PF | -6.696 |
ourgeois | -6.610 |
ioxide | -6.501 |
uum | -6.474 |
Token | in |
Token ID | 287 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ting | +3.507 |
◼ | +3.231 |
lisher | +3.195 |
rend | +3.178 |
tto | +3.067 |
Neg logit contributions | |
ioxide | -3.581 |
uve | -3.508 |
ourgeois | -3.466 |
PF | -3.447 |
uum | -3.414 |
Token | but |
Token ID | 475 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
uve | +0.590 |
ioxide | +0.590 |
ourgeois | +0.579 |
iv | +0.576 |
ophobia | +0.575 |
Neg logit contributions | |
ting | -0.772 |
◼ | -0.742 |
lisher | -0.731 |
rend | -0.720 |
ITNESS | -0.702 |
Token | the |
Token ID | 262 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
ting | +2.340 |
◼ | +2.170 |
lisher | +2.141 |
rend | +2.127 |
tto | +2.054 |
Neg logit contributions | |
ioxide | -2.025 |
uve | -2.004 |
ourgeois | -1.961 |
PF | -1.926 |
ophobia | -1.923 |
Token | real |
Token ID | 1103 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ting | +0.413 |
◼ | +0.392 |
lisher | +0.385 |
rend | +0.380 |
ITNESS | +0.368 |
Neg logit contributions | |
ioxide | -0.359 |
uve | -0.356 |
ourgeois | -0.349 |
ophobia | -0.344 |
iv | -0.343 |
Token | ones |
Token ID | 3392 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ting | +3.509 |
lisher | +3.204 |
rend | +3.180 |
◼ | +3.176 |
tto | +3.038 |
Neg logit contributions | |
ioxide | -3.388 |
uve | -3.332 |
ourgeois | -3.266 |
PF | -3.221 |
ophobia | -3.208 |
Token | for |
Token ID | 329 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ting | +8.044 |
rend | +7.020 |
ted | +6.830 |
lisher | +6.712 |
tto | +6.632 |
Neg logit contributions | |
ioxide | -9.944 |
uve | -9.670 |
PF | -9.625 |
ourgeois | -9.346 |
uum | -9.340 |
Token | me |
Token ID | 502 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ting | +1.306 |
◼ | +1.226 |
lisher | +1.206 |
rend | +1.190 |
ITNESS | +1.146 |
Neg logit contributions | |
ioxide | -1.344 |
uve | -1.333 |
ourgeois | -1.310 |
ophobia | -1.290 |
PF | -1.287 |
Token | came |
Token ID | 1625 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
ting | +12.855 |
ted | +10.699 |
rend | +10.546 |
tering | +10.053 |
tto | +9.980 |
Neg logit contributions | |
ioxide | -16.333 |
PF | -15.794 |
uve | -15.533 |
anguage | -15.220 |
uum | -15.131 |
Token | later |
Token ID | 1568 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ting | +7.784 |
ted | +6.723 |
◼ | +6.672 |
rend | +6.612 |
lisher | +6.543 |
Neg logit contributions | |
ioxide | -8.648 |
uve | -8.325 |
ourgeois | -8.248 |
PF | -8.037 |
uum | -7.987 |
Token | in |
Token ID | 287 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
iv | +3.280 |
uve | +3.270 |
uses | +3.265 |
ophobia | +3.224 |
ives | +3.215 |
Neg logit contributions | |
ting | -4.435 |
◼ | -4.396 |
lisher | -4.293 |
rend | -4.169 |
ITNESS | -4.157 |
Token | my |
Token ID | 616 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
uses | +3.963 |
iv | +3.880 |
uve | +3.793 |
ourgeois | +3.770 |
ives | +3.756 |
Neg logit contributions | |
◼ | -8.456 |
lisher | -8.205 |
ting | -8.130 |
ITNESS | -8.033 |
rend | -7.950 |
Token | career |
Token ID | 3451 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
iv | +5.133 |
ives | +5.043 |
uses | +5.029 |
Flames | +4.919 |
PF | +4.890 |
Neg logit contributions | |
◼ | -8.183 |
ting | -8.142 |
lisher | -8.131 |
rend | -7.936 |
ITNESS | -7.836 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ting | +2.379 |
◼ | +2.234 |
lisher | +2.196 |
rend | +2.170 |
ITNESS | +2.080 |
Neg logit contributions | |
ioxide | -2.375 |
uve | -2.357 |
ourgeois | -2.310 |
ophobia | -2.271 |
PF | -2.266 |
Token | calling |
Token ID | 4585 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ting | +8.095 |
◼ | +7.224 |
rend | +7.073 |
lisher | +6.866 |
ted | +6.754 |
Neg logit contributions | |
ioxide | -8.595 |
uve | -8.425 |
ourgeois | -8.334 |
PF | -8.251 |
ophobia | -8.197 |
Token | stores |
Token ID | 7000 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
ting | +9.026 |
◼ | +8.349 |
rend | +8.101 |
ted | +8.091 |
lisher | +8.037 |
Neg logit contributions | |
ioxide | -7.942 |
uve | -7.501 |
ophobia | -7.454 |
PF | -7.378 |
ivan | -7.363 |
Token | and |
Token ID | 290 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ting | +7.198 |
◼ | +6.526 |
rend | +6.446 |
lisher | +6.411 |
ted | +6.276 |
Neg logit contributions | |
ioxide | -7.423 |
uve | -6.989 |
ourgeois | -6.818 |
uum | -6.775 |
ivan | -6.773 |
Token | restaurants |
Token ID | 10808 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ting | +5.073 |
◼ | +4.673 |
lisher | +4.561 |
rend | +4.515 |
ted | +4.357 |
Neg logit contributions | |
ioxide | -4.533 |
uve | -4.464 |
ophobia | -4.353 |
ourgeois | -4.352 |
PF | -4.306 |
Token | for |
Token ID | 329 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ting | +8.749 |
◼ | +7.979 |
rend | +7.782 |
lisher | +7.695 |
ted | +7.605 |
Neg logit contributions | |
ioxide | -9.525 |
uve | -8.839 |
ourgeois | -8.588 |
uum | -8.573 |
ivan | -8.566 |
Token | you |
Token ID | 345 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ting | +14.629 |
◼ | +13.518 |
rend | +13.289 |
sole | +12.916 |
ted | +12.840 |
Neg logit contributions | |
ioxide | -13.366 |
ourgeois | -12.593 |
pour | -12.453 |
uve | -12.429 |
itement | -12.401 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ting | +8.812 |
◼ | +8.104 |
rend | +7.856 |
lisher | +7.840 |
ted | +7.699 |
Neg logit contributions | |
ioxide | -9.258 |
uve | -9.197 |
ourgeois | -8.973 |
PF | -8.754 |
uum | -8.748 |
Token | Talk |
Token ID | 12167 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ting | +1.261 |
◼ | +1.196 |
lisher | +1.178 |
rend | +1.164 |
ITNESS | +1.127 |
Neg logit contributions | |
ioxide | -1.000 |
uve | -0.992 |
ourgeois | -0.972 |
ophobia | -0.955 |
PF | -0.953 |
Token | To |
Token ID | 2514 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ioxide | +1.830 |
uve | +1.801 |
iv | +1.794 |
uses | +1.783 |
PF | +1.779 |
Neg logit contributions | |
ting | -1.861 |
◼ | -1.798 |
lisher | -1.763 |
rend | -1.724 |
ITNESS | -1.692 |
Token | founder |
Token ID | 9119 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
uve | +1.349 |
ioxide | +1.348 |
uses | +1.332 |
iv | +1.330 |
ourgeois | +1.326 |
Neg logit contributions | |
ting | -1.597 |
◼ | -1.523 |
lisher | -1.501 |
rend | -1.476 |
ITNESS | -1.456 |
Token | these |
Token ID | 777 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
iv | +4.373 |
uve | +4.308 |
ourgeois | +4.273 |
uses | +4.213 |
ives | +4.192 |
Neg logit contributions | |
◼ | -5.600 |
lisher | -5.458 |
ting | -5.428 |
rend | -5.254 |
ITNESS | -5.198 |
Token | tasty |
Token ID | 25103 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
uve | +3.140 |
iv | +3.131 |
ourgeois | +3.071 |
ives | +3.061 |
uses | +3.039 |
Neg logit contributions | |
◼ | -4.291 |
ting | -4.287 |
lisher | -4.173 |
rend | -4.123 |
ITNESS | -4.064 |
Token | , |
Token ID | 11 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
uve | +0.939 |
ioxide | +0.933 |
ourgeois | +0.929 |
iv | +0.926 |
uses | +0.914 |
Neg logit contributions | |
ting | -1.347 |
◼ | -1.305 |
lisher | -1.284 |
rend | -1.257 |
ITNESS | -1.239 |
Token | super |
Token ID | 2208 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
uve | +0.269 |
ioxide | +0.268 |
ourgeois | +0.263 |
iv | +0.261 |
ophobia | +0.259 |
Neg logit contributions | |
ting | -0.322 |
◼ | -0.308 |
lisher | -0.303 |
rend | -0.298 |
ITNESS | -0.292 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ting | +0.209 |
◼ | +0.200 |
lisher | +0.196 |
rend | +0.193 |
ITNESS | +0.189 |
Neg logit contributions | |
uve | -0.164 |
ioxide | -0.162 |
ourgeois | -0.159 |
iv | -0.157 |
PF | -0.156 |
Token | nut |
Token ID | 14930 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
uve | +0.854 |
ioxide | +0.830 |
iv | +0.829 |
ourgeois | +0.825 |
PF | +0.817 |
Neg logit contributions | |
ting | -0.898 |
◼ | -0.860 |
lisher | -0.848 |
rend | -0.822 |
ITNESS | -0.822 |
Token | rit |
Token ID | 799 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ting | +13.684 |
rend | +12.601 |
ted | +11.773 |
lisher | +11.380 |
ty | +10.986 |
Neg logit contributions | |
ioxide | -15.523 |
PF | -14.702 |
anguage | -14.610 |
ophobia | -14.374 |
Activate | -14.179 |
Token | ious |
Token ID | 699 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
ting | +6.369 |
lisher | +5.868 |
rend | +5.864 |
◼ | +5.710 |
ted | +5.657 |
Neg logit contributions | |
ioxide | -3.883 |
ourgeois | -3.727 |
pour | -3.711 |
PF | -3.680 |
uve | -3.607 |
Token | wild |
Token ID | 4295 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
uve | +0.453 |
ioxide | +0.452 |
ourgeois | +0.447 |
iv | +0.442 |
ophobia | +0.437 |
Neg logit contributions | |
ting | -0.661 |
◼ | -0.637 |
lisher | -0.626 |
rend | -0.615 |
ITNESS | -0.603 |
Token | plants |
Token ID | 6134 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ting | +2.082 |
◼ | +1.955 |
lisher | +1.934 |
rend | +1.919 |
tto | +1.850 |
Neg logit contributions | |
ioxide | -1.549 |
uve | -1.519 |
ourgeois | -1.486 |
ophobia | -1.457 |
PF | -1.453 |
Token | assuming |
Token ID | 13148 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
uve | +1.898 |
iv | +1.875 |
ophobia | +1.857 |
ioxide | +1.852 |
ourgeois | +1.842 |
Neg logit contributions | |
ting | -2.427 |
◼ | -2.355 |
lisher | -2.338 |
rend | -2.293 |
ITNESS | -2.268 |
Token | 1941 |
Token ID | 23234 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ioxide | +0.644 |
uve | +0.640 |
ourgeois | +0.628 |
iv | +0.624 |
ophobia | +0.616 |
Neg logit contributions | |
ting | -1.060 |
◼ | -1.018 |
lisher | -1.004 |
rend | -0.987 |
ITNESS | -0.967 |
Token | Zh |
Token ID | 10511 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
ting | +1.201 |
◼ | +1.141 |
lisher | +1.126 |
rend | +1.113 |
ITNESS | +1.080 |
Neg logit contributions | |
ioxide | -0.837 |
uve | -0.830 |
ourgeois | -0.812 |
ophobia | -0.796 |
PF | -0.794 |
Token | uk |
Token ID | 2724 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
uve | +2.257 |
ioxide | +2.151 |
iv | +2.144 |
uum | +2.086 |
ivan | +2.073 |
Neg logit contributions | |
◼ | -5.966 |
ting | -5.942 |
lisher | -5.807 |
ITNESS | -5.666 |
rend | -5.640 |
Token | ov |
Token ID | 709 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ioxide | +1.408 |
uve | +1.407 |
iv | +1.393 |
ophobia | +1.313 |
ivan | +1.288 |
Neg logit contributions | |
ting | -5.506 |
◼ | -5.476 |
lisher | -5.327 |
ITNESS | -5.251 |
rend | -5.222 |
Token | was |
Token ID | 373 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ioxide | +1.581 |
uve | +1.579 |
iv | +1.543 |
ourgeois | +1.539 |
ophobia | +1.538 |
Neg logit contributions | |
ting | -1.606 |
◼ | -1.557 |
lisher | -1.515 |
rend | -1.481 |
ITNESS | -1.444 |
Token | made |
Token ID | 925 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ting | +4.442 |
◼ | +4.059 |
lisher | +4.048 |
rend | +4.005 |
ted | +3.874 |
Neg logit contributions | |
ioxide | -4.612 |
uve | -4.489 |
ourgeois | -4.450 |
ophobia | -4.368 |
uum | -4.354 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ting | +13.142 |
sole | +12.570 |
rend | +12.548 |
tto | +12.196 |
lisher | +11.815 |
Neg logit contributions | |
ioxide | -13.383 |
uum | -13.331 |
ourgeois | -12.766 |
pour | -12.655 |
ophobia | -12.638 |
Token | commander |
Token ID | 11561 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ting | +11.955 |
sole | +11.459 |
rend | +11.225 |
lisher | +10.741 |
tto | +10.502 |
Neg logit contributions | |
ioxide | -10.954 |
uum | -10.932 |
ourgeois | -10.730 |
ophobia | -10.544 |
uve | -10.542 |
Token | of |
Token ID | 286 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ting | +2.049 |
◼ | +1.931 |
lisher | +1.903 |
rend | +1.882 |
tto | +1.809 |
Neg logit contributions | |
ioxide | -1.811 |
uve | -1.786 |
ourgeois | -1.768 |
ophobia | -1.738 |
uum | -1.728 |
Token | the |
Token ID | 262 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ting | +4.585 |
◼ | +4.204 |
rend | +4.174 |
lisher | +4.169 |
tto | +3.994 |
Neg logit contributions | |
ioxide | -4.729 |
uve | -4.709 |
ophobia | -4.664 |
ourgeois | -4.654 |
uum | -4.603 |
Token | L |
Token ID | 406 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ting | +5.670 |
rend | +5.269 |
◼ | +5.230 |
lisher | +5.193 |
tto | +5.122 |
Neg logit contributions | |
ioxide | -4.335 |
uve | -4.298 |
ophobia | -4.246 |
ourgeois | -4.208 |
uum | -4.137 |
Token | American |
Token ID | 1605 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ioxide | +1.194 |
uve | +1.189 |
ourgeois | +1.158 |
ophobia | +1.154 |
uses | +1.147 |
Neg logit contributions | |
ting | -1.563 |
◼ | -1.490 |
lisher | -1.484 |
rend | -1.448 |
ITNESS | -1.427 |
Token | economy |
Token ID | 3773 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ting | +5.222 |
◼ | +4.869 |
rend | +4.804 |
lisher | +4.770 |
ted | +4.633 |
Neg logit contributions | |
ioxide | -3.722 |
uve | -3.685 |
ourgeois | -3.553 |
uum | -3.503 |
PF | -3.497 |
Token | and |
Token ID | 290 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
ting | +5.918 |
◼ | +5.449 |
rend | +5.328 |
lisher | +5.262 |
ted | +5.075 |
Neg logit contributions | |
ioxide | -6.262 |
uve | -6.016 |
ourgeois | -5.922 |
PF | -5.853 |
ivan | -5.801 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ioxide | +0.556 |
uve | +0.552 |
ourgeois | +0.544 |
ophobia | +0.537 |
iv | +0.536 |
Neg logit contributions | |
ting | -0.684 |
◼ | -0.656 |
lisher | -0.650 |
rend | -0.637 |
ITNESS | -0.623 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ting | +1.614 |
◼ | +1.528 |
lisher | +1.506 |
rend | +1.489 |
ITNESS | +1.439 |
Neg logit contributions | |
ioxide | -1.288 |
uve | -1.277 |
ourgeois | -1.251 |
ophobia | -1.228 |
PF | -1.226 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ting | +7.285 |
rend | +6.545 |
◼ | +6.317 |
tto | +6.065 |
ted | +5.879 |
Neg logit contributions | |
uve | -13.292 |
ourgeois | -13.163 |
anguage | -13.059 |
PF | -12.871 |
uses | -12.780 |
Token | remotely |
Token ID | 19863 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ting | +14.833 |
rend | +12.886 |
ted | +12.808 |
◼ | +12.432 |
lisher | +12.279 |
Neg logit contributions | |
ioxide | -13.581 |
uve | -12.570 |
ourgeois | -12.438 |
oglu | -12.372 |
uum | -12.122 |
Token | sympathetic |
Token ID | 22335 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ting | +2.467 |
◼ | +2.346 |
lisher | +2.301 |
rend | +2.283 |
ITNESS | +2.211 |
Neg logit contributions | |
ioxide | -1.656 |
uve | -1.626 |
ourgeois | -1.593 |
ophobia | -1.563 |
PF | -1.561 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ting | +2.370 |
◼ | +2.216 |
lisher | +2.160 |
rend | +2.154 |
tto | +2.078 |
Neg logit contributions | |
ioxide | -2.405 |
uve | -2.378 |
ourgeois | -2.330 |
PF | -2.308 |
ophobia | -2.288 |
Token | organized |
Token ID | 8389 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ting | +1.393 |
◼ | +1.319 |
lisher | +1.299 |
rend | +1.284 |
ITNESS | +1.242 |
Neg logit contributions | |
ioxide | -1.142 |
uve | -1.134 |
ourgeois | -1.111 |
ophobia | -1.092 |
PF | -1.090 |
Token | labor |
Token ID | 4827 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ophobia | +2.088 |
iv | +2.078 |
ioxide | +2.075 |
uve | +2.051 |
ourgeois | +2.035 |
Neg logit contributions | |
ting | -3.499 |
◼ | -3.423 |
lisher | -3.372 |
rend | -3.289 |
ITNESS | -3.285 |
Token | iv |
Token ID | 452 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ioxide | +0.324 |
uve | +0.321 |
ourgeois | +0.315 |
iv | +0.311 |
ophobia | +0.311 |
Neg logit contributions | |
ting | -0.411 |
◼ | -0.391 |
lisher | -0.385 |
rend | -0.379 |
ITNESS | -0.368 |
Token | otal |
Token ID | 4997 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
ting | +0.534 |
◼ | +0.511 |
lisher | +0.506 |
rend | +0.502 |
ITNESS | +0.488 |
Neg logit contributions | |
ioxide | -0.226 |
uve | -0.223 |
ourgeois | -0.216 |
PF | -0.210 |
ophobia | -0.210 |
Token | � |
Token ID | 447 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ioxide | +0.652 |
uve | +0.651 |
ourgeois | +0.644 |
uses | +0.635 |
iv | +0.635 |
Neg logit contributions | |
ting | -0.788 |
◼ | -0.747 |
lisher | -0.741 |
rend | -0.722 |
ITNESS | -0.711 |
Token | � |
Token ID | 247 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ioxide | +0.913 |
uve | +0.907 |
ourgeois | +0.886 |
PF | +0.880 |
iv | +0.879 |
Neg logit contributions | |
ting | -0.817 |
◼ | -0.769 |
lisher | -0.758 |
rend | -0.742 |
ITNESS | -0.719 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ting | +2.631 |
◼ | +2.477 |
lisher | +2.434 |
rend | +2.422 |
ted | +2.318 |
Neg logit contributions | |
ioxide | -2.216 |
uve | -2.181 |
ourgeois | -2.125 |
ophobia | -2.099 |
PF | -2.098 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ting | +7.069 |
rend | +6.672 |
◼ | +6.636 |
lisher | +6.137 |
tto | +6.064 |
Neg logit contributions | |
uve | -9.409 |
uum | -9.102 |
ioxide | -9.014 |
PF | -8.858 |
ourgeois | -8.848 |
Token | justices |
Token ID | 27818 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ting | +14.246 |
rend | +13.565 |
ted | +12.506 |
◼ | +12.468 |
tto | +12.217 |
Neg logit contributions | |
uve | -12.861 |
ioxide | -12.854 |
anguage | -12.221 |
uum | -12.164 |
PF | -11.951 |
Token | is |
Token ID | 318 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ting | +8.715 |
rend | +8.119 |
◼ | +7.802 |
ted | +7.683 |
lisher | +7.624 |
Neg logit contributions | |
ioxide | -9.017 |
uve | -8.783 |
ourgeois | -8.570 |
PF | -8.540 |
uum | -8.485 |
Token | four |
Token ID | 1440 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ting | +4.916 |
◼ | +4.620 |
rend | +4.538 |
lisher | +4.517 |
ted | +4.323 |
Neg logit contributions | |
ioxide | -4.234 |
uve | -4.183 |
ourgeois | -4.066 |
uum | -4.049 |
PF | -4.033 |
Token | years |
Token ID | 812 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ting | +3.600 |
◼ | +3.371 |
lisher | +3.317 |
rend | +3.305 |
ted | +3.176 |
Neg logit contributions | |
ioxide | -2.872 |
uve | -2.853 |
ourgeois | -2.772 |
PF | -2.731 |
ophobia | -2.711 |
Token | older |
Token ID | 4697 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
uve | +1.923 |
ourgeois | +1.889 |
ioxide | +1.887 |
iv | +1.868 |
uses | +1.861 |
Neg logit contributions | |
ting | -2.311 |
◼ | -2.236 |
lisher | -2.194 |
rend | -2.164 |
ITNESS | -2.160 |
Token | late |
Token ID | 2739 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ting | +0.635 |
◼ | +0.602 |
lisher | +0.593 |
rend | +0.585 |
ITNESS | +0.566 |
Neg logit contributions | |
ioxide | -0.537 |
uve | -0.533 |
ourgeois | -0.523 |
ophobia | -0.514 |
iv | -0.513 |
Token | January |
Token ID | 3269 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
uve | +2.717 |
ioxide | +2.667 |
iv | +2.646 |
ophobia | +2.626 |
ourgeois | +2.619 |
Neg logit contributions | |
ting | -3.225 |
◼ | -3.120 |
lisher | -3.075 |
rend | -2.995 |
ITNESS | -2.990 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ioxide | +3.323 |
ourgeois | +3.316 |
iv | +3.316 |
uve | +3.309 |
pour | +3.284 |
Neg logit contributions | |
ting | -4.857 |
◼ | -4.782 |
lisher | -4.565 |
rend | -4.497 |
ITNESS | -4.476 |
Token | an |
Token ID | 281 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
uve | +1.008 |
ioxide | +1.004 |
ourgeois | +0.994 |
iv | +0.977 |
ivan | +0.968 |
Neg logit contributions | |
ting | -1.345 |
◼ | -1.289 |
lisher | -1.257 |
rend | -1.242 |
ITNESS | -1.206 |
Token | appeals |
Token ID | 15192 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ting | +2.689 |
◼ | +2.535 |
lisher | +2.518 |
rend | +2.483 |
ted | +2.406 |
Neg logit contributions | |
ioxide | -2.057 |
uve | -2.032 |
ourgeois | -1.987 |
ophobia | -1.970 |
PF | -1.970 |
Token | court |
Token ID | 2184 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ting | +5.670 |
rend | +5.262 |
lisher | +5.127 |
◼ | +5.090 |
tto | +4.987 |
Neg logit contributions | |
uve | -6.316 |
ioxide | -6.265 |
ourgeois | -6.062 |
PF | -6.052 |
ophobia | -5.976 |
Token | ordered |
Token ID | 6149 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ting | +12.431 |
overr | +10.700 |
ted | +10.433 |
rend | +10.349 |
lisher | +10.119 |
Neg logit contributions | |
ioxide | -15.545 |
uve | -14.510 |
PF | -14.456 |
ivan | -14.214 |
ourgeois | -14.183 |
Token | that |
Token ID | 326 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ting | +5.127 |
lisher | +4.738 |
◼ | +4.721 |
rend | +4.701 |
tto | +4.508 |
Neg logit contributions | |
ioxide | -4.576 |
uve | -4.471 |
ophobia | -4.394 |
ourgeois | -4.373 |
PF | -4.366 |
Token | E |
Token ID | 412 |
Feature activation | -2.68e-04 |
Pos logit contributions | |
ting | +0.959 |
◼ | +0.912 |
lisher | +0.899 |
rend | +0.889 |
ITNESS | +0.862 |
Neg logit contributions | |
ioxide | -0.673 |
uve | -0.668 |
ourgeois | -0.654 |
ophobia | -0.641 |
PF | -0.640 |
Token | ch |
Token ID | 354 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ioxide | +0.002 |
uve | +0.002 |
ourgeois | +0.002 |
iv | +0.002 |
PF | +0.002 |
Neg logit contributions | |
ting | -0.002 |
◼ | -0.002 |
lisher | -0.002 |
rend | -0.002 |
ITNESS | -0.002 |
Token | ost |
Token ID | 455 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
ting | +4.235 |
rend | +3.911 |
lisher | +3.894 |
◼ | +3.868 |
ted | +3.749 |
Neg logit contributions | |
ioxide | -2.664 |
uve | -2.602 |
ourgeois | -2.584 |
PF | -2.566 |
uum | -2.482 |
Token | en |
Token ID | 268 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
uve | +1.550 |
iv | +1.525 |
ivan | +1.512 |
uses | +1.476 |
pour | +1.397 |
Neg logit contributions | |
ting | -7.988 |
◼ | -7.926 |
lisher | -7.883 |
ITNESS | -7.866 |
rend | -7.589 |
Token | comp |
Token ID | 5589 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
ioxide | +1.343 |
uve | +1.338 |
ourgeois | +1.305 |
ophobia | +1.296 |
iv | +1.294 |
Neg logit contributions | |
ting | -1.399 |
◼ | -1.324 |
lisher | -1.300 |
rend | -1.277 |
ITNESS | -1.243 |
Token | assing |
Token ID | 19696 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ioxide | +0.596 |
uve | +0.590 |
ourgeois | +0.575 |
ophobia | +0.563 |
iv | +0.562 |
Neg logit contributions | |
ting | -1.066 |
◼ | -1.020 |
lisher | -1.007 |
rend | -0.996 |
ITNESS | -0.969 |
Token | stereotype |
Token ID | 31240 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
ioxide | +1.005 |
uve | +1.002 |
ourgeois | +0.986 |
ophobia | +0.978 |
iv | +0.967 |
Neg logit contributions | |
ting | -1.359 |
◼ | -1.317 |
lisher | -1.291 |
rend | -1.265 |
ITNESS | -1.250 |
Token | of |
Token ID | 286 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
ioxide | +0.700 |
uve | +0.695 |
ourgeois | +0.682 |
ophobia | +0.670 |
PF | +0.669 |
Neg logit contributions | |
ting | -0.835 |
◼ | -0.791 |
lisher | -0.779 |
rend | -0.769 |
ITNESS | -0.744 |
Token | trou |
Token ID | 4057 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ting | +6.550 |
◼ | +6.009 |
rend | +5.989 |
lisher | +5.879 |
ted | +5.596 |
Neg logit contributions | |
ioxide | -8.867 |
uve | -8.682 |
uses | -8.510 |
PF | -8.492 |
ourgeois | -8.461 |
Token | ser |
Token ID | 2655 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ting | +8.254 |
rend | +6.987 |
lisher | +6.815 |
ted | +6.771 |
tering | +6.352 |
Neg logit contributions | |
PF | -18.904 |
ourgeois | -18.565 |
Activate | -18.220 |
ioxide | -18.166 |
Breach | -18.076 |
Token | - |
Token ID | 12 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
uve | +1.881 |
ioxide | +1.823 |
iv | +1.792 |
ophobia | +1.780 |
uses | +1.775 |
Neg logit contributions | |
ting | -2.928 |
◼ | -2.821 |
lisher | -2.802 |
ITNESS | -2.732 |
rend | -2.730 |
Token | w |
Token ID | 86 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
uve | +3.887 |
iv | +3.848 |
pour | +3.778 |
uses | +3.688 |
ophobia | +3.598 |
Neg logit contributions | |
◼ | -9.222 |
ITNESS | -9.144 |
ting | -9.005 |
lisher | -8.925 |
skelet | -8.736 |
Token | earing |
Token ID | 6648 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +4.563 |
rend | +4.024 |
lisher | +3.998 |
◼ | +3.870 |
ITNESS | +3.784 |
Neg logit contributions | |
uve | -5.321 |
PF | -5.310 |
ioxide | -5.282 |
ourgeois | -5.209 |
uum | -5.067 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ting | +0.964 |
◼ | +0.911 |
lisher | +0.895 |
rend | +0.886 |
ITNESS | +0.853 |
Neg logit contributions | |
ioxide | -0.859 |
uve | -0.850 |
ourgeois | -0.834 |
ophobia | -0.820 |
PF | -0.819 |
Token | number |
Token ID | 1271 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
uve | +2.279 |
ioxide | +2.231 |
ourgeois | +2.209 |
iv | +2.202 |
PF | +2.202 |
Neg logit contributions | |
ting | -2.752 |
◼ | -2.677 |
lisher | -2.638 |
rend | -2.549 |
ITNESS | -2.522 |
Token | of |
Token ID | 286 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
uve | +2.248 |
ioxide | +2.239 |
iv | +2.186 |
ourgeois | +2.176 |
uses | +2.173 |
Neg logit contributions | |
ting | -2.979 |
◼ | -2.866 |
lisher | -2.859 |
rend | -2.774 |
ITNESS | -2.724 |
Token | ways |
Token ID | 2842 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
uve | +1.061 |
ioxide | +1.059 |
ourgeois | +1.031 |
iv | +1.026 |
PF | +1.021 |
Neg logit contributions | |
ting | -1.255 |
◼ | -1.205 |
lisher | -1.195 |
rend | -1.162 |
tto | -1.129 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
uve | +0.940 |
ioxide | +0.939 |
ourgeois | +0.925 |
iv | +0.920 |
ophobia | +0.910 |
Neg logit contributions | |
ting | -1.169 |
◼ | -1.121 |
lisher | -1.108 |
rend | -1.080 |
ITNESS | -1.060 |
Token | the |
Token ID | 262 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
ting | +1.478 |
◼ | +1.395 |
lisher | +1.370 |
rend | +1.356 |
ITNESS | +1.310 |
Neg logit contributions | |
ioxide | -1.326 |
uve | -1.309 |
ourgeois | -1.282 |
ophobia | -1.263 |
PF | -1.262 |
Token | court |
Token ID | 2184 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ting | +7.485 |
rend | +6.768 |
◼ | +6.651 |
lisher | +6.607 |
ted | +6.467 |
Neg logit contributions | |
ioxide | -8.403 |
uve | -8.204 |
ourgeois | -8.042 |
pour | -8.016 |
uum | -8.014 |
Token | found |
Token ID | 1043 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ting | +11.841 |
rend | +9.735 |
ted | +9.607 |
lisher | +9.363 |
overr | +9.316 |
Neg logit contributions | |
ioxide | -16.318 |
ourgeois | -15.276 |
uve | -15.160 |
itement | -15.128 |
ivan | -15.078 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ting | +2.702 |
◼ | +2.513 |
lisher | +2.483 |
rend | +2.480 |
tto | +2.370 |
Neg logit contributions | |
ioxide | -2.536 |
uve | -2.492 |
ourgeois | -2.456 |
ophobia | -2.415 |
PF | -2.405 |
Token | overturn |
Token ID | 17586 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ting | +2.303 |
◼ | +2.151 |
lisher | +2.107 |
rend | +2.098 |
tto | +2.005 |
Neg logit contributions | |
ioxide | -2.071 |
uve | -2.029 |
ourgeois | -1.987 |
ophobia | -1.957 |
uum | -1.950 |
Token | ing |
Token ID | 278 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ting | +4.198 |
lisher | +3.277 |
rend | +3.231 |
◼ | +3.085 |
ted | +2.995 |
Neg logit contributions | |
ioxide | -9.838 |
uve | -9.544 |
ophobia | -9.382 |
ourgeois | -9.374 |
uum | -9.334 |
Token | the |
Token ID | 262 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
uve | +2.996 |
ioxide | +2.955 |
iv | +2.947 |
ourgeois | +2.909 |
PF | +2.892 |
Neg logit contributions | |
ting | -4.142 |
◼ | -4.084 |
lisher | -3.966 |
rend | -3.865 |
tto | -3.756 |
Token | not |
Token ID | 407 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
ioxide | +0.352 |
uve | +0.352 |
ourgeois | +0.346 |
iv | +0.342 |
ophobia | +0.341 |
Neg logit contributions | |
ting | -0.439 |
◼ | -0.416 |
lisher | -0.412 |
rend | -0.407 |
ITNESS | -0.395 |
Token | only |
Token ID | 691 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
ting | +4.249 |
◼ | +3.741 |
lisher | +3.705 |
rend | +3.598 |
ITNESS | +3.542 |
Neg logit contributions | |
ioxide | -5.923 |
uve | -5.917 |
ourgeois | -5.757 |
ivan | -5.705 |
PF | -5.702 |
Token | through |
Token ID | 832 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ting | +7.612 |
◼ | +6.865 |
lisher | +6.670 |
rend | +6.616 |
ted | +6.598 |
Neg logit contributions | |
ioxide | -8.290 |
uve | -7.795 |
ivan | -7.570 |
ourgeois | -7.528 |
uum | -7.457 |
Token | numerous |
Token ID | 6409 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ting | +4.504 |
◼ | +4.168 |
lisher | +4.112 |
rend | +4.054 |
tto | +3.961 |
Neg logit contributions | |
ioxide | -3.850 |
uve | -3.752 |
ourgeois | -3.669 |
PF | -3.600 |
uum | -3.591 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ting | +3.216 |
◼ | +3.006 |
lisher | +2.971 |
rend | +2.955 |
tto | +2.855 |
Neg logit contributions | |
ioxide | -2.579 |
uve | -2.540 |
ourgeois | -2.472 |
PF | -2.423 |
ophobia | -2.399 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ting | +7.077 |
rend | +6.557 |
◼ | +6.224 |
ted | +5.934 |
tto | +5.830 |
Neg logit contributions | |
uve | -11.240 |
uum | -10.882 |
ioxide | -10.847 |
anguage | -10.717 |
ourgeois | -10.605 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ting | +11.220 |
rend | +10.240 |
◼ | +9.941 |
overr | +9.413 |
tto | +9.161 |
Neg logit contributions | |
ioxide | -15.485 |
uve | -15.281 |
pour | -14.741 |
uum | -14.719 |
anguage | -14.713 |
Token | other |
Token ID | 584 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ting | +3.766 |
◼ | +3.548 |
lisher | +3.469 |
rend | +3.445 |
tto | +3.372 |
Neg logit contributions | |
ioxide | -2.666 |
uve | -2.624 |
ourgeois | -2.545 |
ophobia | -2.496 |
PF | -2.491 |
Token | court |
Token ID | 2184 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ting | +6.185 |
◼ | +5.619 |
rend | +5.556 |
lisher | +5.501 |
ted | +5.363 |
Neg logit contributions | |
ioxide | -6.341 |
uve | -6.193 |
pour | -6.116 |
ourgeois | -5.955 |
uum | -5.947 |
Token | decisions |
Token ID | 5370 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
ting | +8.346 |
rend | +7.413 |
◼ | +7.163 |
lisher | +6.988 |
ted | +6.852 |
Neg logit contributions | |
ioxide | -12.470 |
uve | -12.082 |
ourgeois | -11.864 |
uum | -11.774 |
pour | -11.716 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ting | +6.523 |
◼ | +6.092 |
rend | +5.938 |
lisher | +5.795 |
ted | +5.640 |
Neg logit contributions | |
ioxide | -6.560 |
uve | -6.233 |
uum | -6.143 |
PF | -6.104 |
ourgeois | -6.092 |
Token | party |
Token ID | 2151 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
uve | +2.592 |
ioxide | +2.570 |
iv | +2.524 |
uses | +2.485 |
ivan | +2.482 |
Neg logit contributions | |
ting | -3.381 |
◼ | -3.355 |
lisher | -3.239 |
rend | -3.115 |
ITNESS | -3.112 |
Token | � |
Token ID | 447 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
uve | +0.430 |
ioxide | +0.427 |
ourgeois | +0.415 |
iv | +0.414 |
ophobia | +0.413 |
Neg logit contributions | |
ting | -0.503 |
◼ | -0.483 |
lisher | -0.473 |
rend | -0.464 |
ITNESS | -0.455 |
Token | � |
Token ID | 247 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
uve | +1.692 |
ioxide | +1.686 |
uum | +1.630 |
iv | +1.625 |
ourgeois | +1.618 |
Neg logit contributions | |
ting | -1.595 |
◼ | -1.510 |
lisher | -1.494 |
rend | -1.452 |
ITNESS | -1.414 |
Token | s |
Token ID | 82 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ting | +1.080 |
◼ | +1.022 |
lisher | +1.005 |
rend | +0.991 |
ITNESS | +0.958 |
Neg logit contributions | |
ioxide | -1.000 |
uve | -0.995 |
ourgeois | -0.975 |
ophobia | -0.960 |
iv | -0.959 |
Token | con |
Token ID | 369 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ting | +1.089 |
◼ | +1.032 |
lisher | +1.018 |
rend | +1.006 |
ITNESS | +0.974 |
Neg logit contributions | |
ioxide | -0.840 |
uve | -0.833 |
ourgeois | -0.816 |
ophobia | -0.801 |
PF | -0.800 |
Token | |
Token ID | 3907 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ting | +3.670 |
lisher | +3.329 |
rend | +3.320 |
◼ | +3.246 |
tto | +3.185 |
Neg logit contributions | |
ioxide | -4.744 |
ourgeois | -4.703 |
PF | -4.618 |
ophobia | -4.590 |
uve | -4.577 |
Token | ven |
Token ID | 574 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ting | +15.074 |
tto | +13.487 |
rend | +13.454 |
lisher | +13.433 |
ted | +13.389 |
Neg logit contributions | |
ioxide | -11.963 |
ourgeois | -11.753 |
ivan | -11.336 |
uve | -11.254 |
PF | -10.995 |
Token | |
Token ID | 3907 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ting | +3.955 |
◼ | +3.576 |
lisher | +3.531 |
rend | +3.472 |
ted | +3.363 |
Neg logit contributions | |
ioxide | -5.068 |
ourgeois | -4.980 |
PF | -4.920 |
uve | -4.909 |
ophobia | -4.871 |
Token | tion |
Token ID | 5378 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ting | +1.580 |
◼ | +1.440 |
lisher | +1.428 |
rend | +1.408 |
ted | +1.345 |
Neg logit contributions | |
ioxide | -1.995 |
uve | -1.969 |
ourgeois | -1.960 |
PF | -1.941 |
ophobia | -1.922 |
Token | in |
Token ID | 287 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ting | +2.017 |
◼ | +1.873 |
lisher | +1.859 |
rend | +1.845 |
tto | +1.774 |
Neg logit contributions | |
ioxide | -1.841 |
uve | -1.810 |
ourgeois | -1.801 |
PF | -1.756 |
ophobia | -1.755 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
ting | +2.807 |
◼ | +2.612 |
lisher | +2.589 |
rend | +2.576 |
tto | +2.476 |
Neg logit contributions | |
ioxide | -2.355 |
uve | -2.309 |
ourgeois | -2.289 |
PF | -2.232 |
ophobia | -2.228 |
Token | � |
Token ID | 247 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ting | +0.116 |
◼ | +0.110 |
lisher | +0.109 |
rend | +0.107 |
ITNESS | +0.104 |
Neg logit contributions | |
ioxide | -0.093 |
uve | -0.092 |
ourgeois | -0.090 |
iv | -0.089 |
PF | -0.089 |
Token | s |
Token ID | 82 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ting | +1.734 |
◼ | +1.640 |
lisher | +1.610 |
rend | +1.596 |
ITNESS | +1.535 |
Neg logit contributions | |
ioxide | -1.454 |
uve | -1.435 |
ourgeois | -1.414 |
ophobia | -1.385 |
PF | -1.380 |
Token | nomination |
Token ID | 11872 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
ting | +9.153 |
rend | +8.326 |
◼ | +8.205 |
ted | +8.142 |
tto | +7.929 |
Neg logit contributions | |
ioxide | -6.583 |
uve | -6.405 |
ourgeois | -6.356 |
pour | -6.318 |
PF | -6.304 |
Token | to |
Token ID | 284 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ting | +0.455 |
◼ | +0.432 |
lisher | +0.425 |
rend | +0.419 |
ITNESS | +0.406 |
Neg logit contributions | |
ioxide | -0.394 |
uve | -0.391 |
ourgeois | -0.384 |
ophobia | -0.378 |
iv | -0.377 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ting | +5.306 |
rend | +4.534 |
ITNESS | +4.528 |
◼ | +4.506 |
lisher | +4.483 |
Neg logit contributions | |
ioxide | -6.502 |
ourgeois | -6.283 |
uve | -6.259 |
uum | -6.238 |
pour | -6.143 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ting | +4.525 |
rend | +3.974 |
◼ | +3.909 |
tto | +3.829 |
ted | +3.812 |
Neg logit contributions | |
ioxide | -5.755 |
ourgeois | -5.589 |
uve | -5.575 |
pour | -5.506 |
PF | -5.431 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ting | +8.305 |
rend | +6.761 |
tto | +6.411 |
ted | +6.327 |
lin | +5.875 |
Neg logit contributions | |
anguage | -18.078 |
ourgeois | -18.051 |
uve | -17.853 |
orescent | -17.516 |
oresc | -17.457 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ting | +10.226 |
rend | +8.888 |
◼ | +8.810 |
tto | +8.707 |
ted | +8.541 |
Neg logit contributions | |
ioxide | -11.259 |
ourgeois | -10.971 |
uve | -10.863 |
uum | -10.501 |
ivan | -10.398 |
Token | In |
Token ID | 554 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ting | +1.662 |
◼ | +1.571 |
lisher | +1.540 |
rend | +1.531 |
ITNESS | +1.478 |
Neg logit contributions | |
ioxide | -1.388 |
uve | -1.372 |
ourgeois | -1.348 |
ophobia | -1.317 |
uum | -1.316 |
Token | brief |
Token ID | 4506 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ioxide | +0.260 |
uve | +0.259 |
ourgeois | +0.254 |
iv | +0.251 |
ophobia | +0.250 |
Neg logit contributions | |
ting | -0.319 |
◼ | -0.306 |
lisher | -0.302 |
rend | -0.296 |
ITNESS | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ting | +1.189 |
◼ | +1.121 |
lisher | +1.103 |
rend | +1.092 |
ITNESS | +1.054 |
Neg logit contributions | |
ioxide | -1.027 |
uve | -1.020 |
ourgeois | -1.000 |
ophobia | -0.982 |
PF | -0.981 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ting | +0.026 |
◼ | +0.025 |
lisher | +0.024 |
rend | +0.024 |
ITNESS | +0.023 |
Neg logit contributions | |
ioxide | -0.022 |
uve | -0.022 |
ourgeois | -0.022 |
iv | -0.021 |
ophobia | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
ting | +2.676 |
◼ | +2.502 |
lisher | +2.446 |
rend | +2.445 |
tto | +2.344 |
Neg logit contributions | |
ioxide | -2.687 |
uve | -2.659 |
ourgeois | -2.610 |
uum | -2.558 |
ophobia | -2.557 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
ting | +0.654 |
◼ | +0.605 |
rend | +0.593 |
lisher | +0.593 |
tto | +0.566 |
Neg logit contributions | |
ioxide | -0.705 |
uve | -0.697 |
ourgeois | -0.692 |
ophobia | -0.673 |
uum | -0.672 |
Token | Perhaps |
Token ID | 13710 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ting | +3.750 |
◼ | +3.543 |
rend | +3.452 |
lisher | +3.414 |
ITNESS | +3.308 |
Neg logit contributions | |
ioxide | -3.304 |
uve | -3.246 |
ourgeois | -3.218 |
ophobia | -3.122 |
uum | -3.098 |
Token | more |
Token ID | 517 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ting | +2.594 |
◼ | +2.411 |
lisher | +2.372 |
rend | +2.354 |
tto | +2.255 |
Neg logit contributions | |
ioxide | -2.507 |
uve | -2.486 |
ourgeois | -2.433 |
PF | -2.392 |
ophobia | -2.390 |
Token | telling |
Token ID | 5149 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ting | +10.225 |
rend | +9.036 |
◼ | +9.010 |
tto | +8.878 |
ted | +8.790 |
Neg logit contributions | |
ioxide | -10.491 |
ourgeois | -10.184 |
uve | -10.155 |
uum | -10.000 |
PF | -9.736 |
Token | are |
Token ID | 389 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
ting | +12.653 |
rend | +11.096 |
◼ | +10.350 |
tto | +10.344 |
ted | +10.298 |
Neg logit contributions | |
ioxide | -14.672 |
uve | -13.845 |
uum | -13.296 |
ourgeois | -13.190 |
ivan | -12.977 |
Token | what |
Token ID | 644 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ting | +6.045 |
◼ | +5.592 |
rend | +5.425 |
lisher | +5.399 |
ted | +5.208 |
Neg logit contributions | |
ioxide | -6.341 |
uve | -6.279 |
ophobia | -6.079 |
ourgeois | -6.063 |
uum | -6.015 |
Token | seem |
Token ID | 1283 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
ting | +5.261 |
◼ | +4.920 |
lisher | +4.818 |
rend | +4.810 |
tto | +4.643 |
Neg logit contributions | |
ioxide | -4.532 |
uve | -4.466 |
ourgeois | -4.300 |
uum | -4.235 |
ophobia | -4.225 |
Token | to |
Token ID | 284 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ting | +6.128 |
◼ | +5.975 |
rend | +5.643 |
lisher | +5.477 |
tto | +5.397 |
Neg logit contributions | |
uve | -7.710 |
ourgeois | -7.394 |
ioxide | -7.332 |
uum | -7.298 |
PF | -7.171 |
Token | be |
Token ID | 307 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
ting | +6.885 |
◼ | +6.263 |
rend | +6.156 |
lisher | +6.037 |
ted | +5.868 |
Neg logit contributions | |
uve | -9.020 |
uum | -8.498 |
ourgeois | -8.497 |
ioxide | -8.488 |
PF | -8.362 |
Token | what |
Token ID | 644 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ting | +4.264 |
◼ | +3.941 |
lisher | +3.870 |
rend | +3.858 |
tto | +3.680 |
Neg logit contributions | |
ioxide | -4.693 |
uve | -4.594 |
ourgeois | -4.492 |
uum | -4.447 |
PF | -4.393 |
Token | would |
Token ID | 561 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ting | +6.947 |
◼ | +6.438 |
rend | +6.339 |
lisher | +6.200 |
ted | +6.130 |
Neg logit contributions | |
ioxide | -6.956 |
uve | -6.692 |
uum | -6.567 |
ourgeois | -6.547 |
pour | -6.344 |
Token | you |
Token ID | 345 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ting | +9.518 |
◼ | +8.785 |
rend | +8.582 |
lisher | +8.451 |
ted | +8.085 |
Neg logit contributions | |
ioxide | -12.354 |
uve | -11.896 |
uum | -11.879 |
ourgeois | -11.534 |
pour | -11.367 |
Token | have |
Token ID | 423 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ting | +8.413 |
ted | +7.266 |
tto | +7.216 |
rend | +6.925 |
lisher | +6.831 |
Neg logit contributions | |
ioxide | -10.333 |
uum | -9.927 |
uve | -9.858 |
ourgeois | -9.854 |
PF | -9.737 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ting | +4.675 |
◼ | +4.256 |
lisher | +4.238 |
rend | +4.150 |
tto | +4.051 |
Neg logit contributions | |
ioxide | -5.404 |
ourgeois | -5.081 |
uve | -5.054 |
uum | -5.021 |
ophobia | -4.961 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ting | +9.350 |
◼ | +8.386 |
rend | +8.137 |
lisher | +8.051 |
ted | +7.977 |
Neg logit contributions | |
ioxide | -11.951 |
uve | -11.288 |
uum | -10.981 |
pour | -10.764 |
anguage | -10.727 |
Token | have |
Token ID | 423 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ting | +11.535 |
ted | +9.558 |
lisher | +9.007 |
rend | +8.916 |
tto | +8.858 |
Neg logit contributions | |
ioxide | -15.852 |
uum | -15.229 |
uve | -15.080 |
anguage | -14.847 |
PF | -14.471 |
Token | done |
Token ID | 1760 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ting | +8.780 |
lisher | +7.820 |
ted | +7.586 |
◼ | +7.507 |
rend | +7.333 |
Neg logit contributions | |
ioxide | -12.401 |
ourgeois | -11.328 |
uum | -11.232 |
anguage | -11.165 |
PF | -11.120 |
Token | differently |
Token ID | 10338 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ting | +4.488 |
◼ | +4.170 |
lisher | +4.047 |
rend | +3.997 |
tto | +3.853 |
Neg logit contributions | |
ioxide | -5.196 |
uve | -4.942 |
uum | -4.889 |
ourgeois | -4.875 |
PF | -4.874 |
Token | ? |
Token ID | 30 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ting | +2.673 |
◼ | +2.487 |
lisher | +2.447 |
rend | +2.421 |
tto | +2.319 |
Neg logit contributions | |
ioxide | -2.718 |
uve | -2.659 |
ourgeois | -2.609 |
PF | -2.586 |
uum | -2.569 |
Token |
|
Token ID | 198 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ting | +7.281 |
rend | +6.672 |
◼ | +6.519 |
lisher | +6.395 |
tto | +6.316 |
Neg logit contributions | |
ioxide | -9.023 |
uve | -9.000 |
uum | -8.694 |
ourgeois | -8.694 |
PF | -8.641 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ting | +1.461 |
◼ | +1.366 |
lisher | +1.350 |
rend | +1.334 |
tto | +1.280 |
Neg logit contributions | |
ioxide | -1.446 |
uve | -1.432 |
ourgeois | -1.405 |
ophobia | -1.385 |
PF | -1.382 |
Token | , |
Token ID | 11 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ting | +1.651 |
◼ | +1.554 |
lisher | +1.534 |
rend | +1.516 |
ITNESS | +1.464 |
Neg logit contributions | |
ioxide | -1.467 |
uve | -1.455 |
ourgeois | -1.426 |
ophobia | -1.403 |
PF | -1.400 |
Token | a |
Token ID | 257 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ting | +3.362 |
◼ | +3.111 |
lisher | +3.109 |
rend | +3.079 |
tto | +2.977 |
Neg logit contributions | |
ioxide | -2.986 |
uve | -2.929 |
ourgeois | -2.852 |
ophobia | -2.823 |
PF | -2.818 |
Token | Swedish |
Token ID | 14023 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ting | +2.458 |
◼ | +2.289 |
lisher | +2.275 |
rend | +2.262 |
tto | +2.175 |
Neg logit contributions | |
ioxide | -2.012 |
uve | -1.987 |
ourgeois | -1.948 |
ophobia | -1.915 |
iv | -1.906 |
Token | appeals |
Token ID | 15192 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ting | +5.987 |
rend | +5.495 |
◼ | +5.460 |
lisher | +5.360 |
tto | +5.262 |
Neg logit contributions | |
ioxide | -5.495 |
uve | -5.457 |
ourgeois | -5.287 |
PF | -5.230 |
uum | -5.198 |
Token | court |
Token ID | 2184 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ting | +4.894 |
rend | +4.601 |
◼ | +4.459 |
lisher | +4.422 |
tto | +4.332 |
Neg logit contributions | |
uve | -5.316 |
ioxide | -5.263 |
uum | -5.115 |
PF | -5.095 |
ourgeois | -5.089 |
Token | upheld |
Token ID | 24816 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ting | +11.888 |
overr | +10.337 |
ted | +9.996 |
rend | +9.975 |
sole | +9.476 |
Neg logit contributions | |
ioxide | -14.826 |
PF | -13.979 |
uve | -13.635 |
ourgeois | -13.541 |
uum | -13.523 |
Token | a |
Token ID | 257 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
ting | +8.016 |
rend | +7.297 |
lisher | +7.131 |
tto | +6.960 |
ted | +6.852 |
Neg logit contributions | |
ioxide | -8.100 |
uum | -7.817 |
uve | -7.739 |
ivan | -7.650 |
pour | -7.641 |
Token | court |
Token ID | 2184 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ting | +5.610 |
rend | +5.073 |
lisher | +4.947 |
◼ | +4.925 |
tto | +4.831 |
Neg logit contributions | |
ioxide | -5.550 |
uve | -5.366 |
ivan | -5.350 |
uses | -5.262 |
uum | -5.258 |
Token | order |
Token ID | 1502 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ting | +9.233 |
rend | +8.053 |
lisher | +7.600 |
◼ | +7.380 |
tto | +7.153 |
Neg logit contributions | |
ioxide | -12.997 |
ivan | -12.711 |
PF | -12.481 |
ourgeois | -12.464 |
uve | -12.459 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ting | +8.359 |
rend | +7.345 |
◼ | +7.209 |
ted | +7.024 |
tto | +7.021 |
Neg logit contributions | |
ioxide | -9.989 |
uum | -9.208 |
ivan | -9.154 |
uve | -9.149 |
PF | -9.072 |
Token | and |
Token ID | 290 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ting | +5.368 |
◼ | +4.981 |
lisher | +4.924 |
rend | +4.843 |
ted | +4.631 |
Neg logit contributions | |
ioxide | -5.493 |
uve | -5.320 |
ourgeois | -5.215 |
PF | -5.184 |
ophobia | -5.174 |
Token | updates |
Token ID | 5992 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ting | +3.946 |
◼ | +3.663 |
lisher | +3.597 |
rend | +3.548 |
tto | +3.373 |
Neg logit contributions | |
ioxide | -4.556 |
uve | -4.473 |
ourgeois | -4.392 |
ophobia | -4.327 |
PF | -4.307 |
Token | we |
Token ID | 356 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ting | +5.149 |
◼ | +4.760 |
lisher | +4.724 |
rend | +4.644 |
ted | +4.449 |
Neg logit contributions | |
ioxide | -5.191 |
uve | -5.029 |
ourgeois | -4.903 |
PF | -4.875 |
ophobia | -4.870 |
Token | � |
Token ID | 447 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ting | +9.364 |
rend | +8.359 |
◼ | +8.212 |
lisher | +8.117 |
tto | +7.880 |
Neg logit contributions | |
ioxide | -10.932 |
ourgeois | -10.677 |
PF | -10.629 |
uve | -10.512 |
uum | -10.223 |
Token | � |
Token ID | 247 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
uve | +2.298 |
ioxide | +2.272 |
uum | +2.212 |
iv | +2.201 |
uses | +2.186 |
Neg logit contributions | |
ting | -3.067 |
◼ | -2.927 |
lisher | -2.906 |
rend | -2.806 |
ITNESS | -2.768 |
Token | ve |
Token ID | 303 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ting | +1.873 |
◼ | +1.783 |
lisher | +1.760 |
rend | +1.747 |
tto | +1.694 |
Neg logit contributions | |
ioxide | -1.091 |
uve | -1.071 |
ourgeois | -1.056 |
ophobia | -1.032 |
PF | -1.028 |
Token | got |
Token ID | 1392 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
ting | +11.988 |
rend | +10.044 |
lisher | +10.019 |
ted | +9.946 |
tering | +9.741 |
Neg logit contributions | |
ioxide | -14.298 |
PF | -13.965 |
ourgeois | -13.774 |
anguage | -13.482 |
itement | -13.456 |
Token | in |
Token ID | 287 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ting | +7.962 |
◼ | +7.060 |
rend | +6.974 |
lisher | +6.902 |
ted | +6.797 |
Neg logit contributions | |
ioxide | -8.141 |
ourgeois | -7.795 |
uve | -7.780 |
PF | -7.681 |
uum | -7.603 |
Token | store |
Token ID | 3650 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ting | +5.086 |
◼ | +4.747 |
lisher | +4.656 |
rend | +4.622 |
ITNESS | +4.467 |
Neg logit contributions | |
ioxide | -5.010 |
uve | -4.901 |
ourgeois | -4.804 |
ophobia | -4.751 |
PF | -4.742 |
Token | for |
Token ID | 329 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ting | +4.450 |
◼ | +4.074 |
lisher | +4.024 |
rend | +4.008 |
ted | +3.849 |
Neg logit contributions | |
ioxide | -4.113 |
uve | -3.985 |
ourgeois | -3.943 |
PF | -3.882 |
ophobia | -3.858 |
Token | … |
Token ID | 1399 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
ting | +2.959 |
◼ | +2.785 |
lisher | +2.753 |
rend | +2.707 |
ITNESS | +2.617 |
Neg logit contributions | |
ioxide | -2.798 |
uve | -2.747 |
ourgeois | -2.704 |
ophobia | -2.670 |
PF | -2.662 |
Token | � |
Token ID | 247 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ting | +2.036 |
◼ | +1.919 |
rend | +1.864 |
lisher | +1.862 |
tto | +1.789 |
Neg logit contributions | |
ourgeois | -2.000 |
ioxide | -2.000 |
uve | -1.970 |
ophobia | -1.925 |
PF | -1.907 |
Token | s |
Token ID | 82 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ting | +3.708 |
◼ | +3.422 |
lisher | +3.348 |
rend | +3.339 |
tto | +3.222 |
Neg logit contributions | |
ioxide | -3.416 |
uve | -3.339 |
ourgeois | -3.320 |
PF | -3.256 |
ophobia | -3.224 |
Token | ballot |
Token ID | 11100 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
ting | +5.466 |
rend | +4.875 |
◼ | +4.841 |
lisher | +4.823 |
ted | +4.770 |
Neg logit contributions | |
ioxide | -4.502 |
uve | -4.417 |
PF | -4.361 |
ourgeois | -4.315 |
uum | -4.180 |
Token | initiative |
Token ID | 10219 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ting | +3.976 |
◼ | +3.683 |
lisher | +3.582 |
rend | +3.531 |
ted | +3.435 |
Neg logit contributions | |
ioxide | -3.781 |
uve | -3.699 |
ourgeois | -3.626 |
PF | -3.611 |
uum | -3.563 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ting | +2.280 |
◼ | +2.111 |
lisher | +2.068 |
rend | +2.050 |
tto | +1.976 |
Neg logit contributions | |
ioxide | -2.296 |
uve | -2.254 |
ourgeois | -2.209 |
PF | -2.184 |
ivan | -2.171 |
Token | would |
Token ID | 561 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ting | +8.138 |
ted | +7.248 |
lisher | +6.938 |
◼ | +6.832 |
rend | +6.801 |
Neg logit contributions | |
ioxide | -9.613 |
PF | -9.138 |
uve | -9.025 |
anguage | -8.914 |
ourgeois | -8.878 |
Token | have |
Token ID | 423 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ting | +10.481 |
ted | +9.100 |
null | +8.565 |
tto | +8.313 |
rend | +8.033 |
Neg logit contributions | |
ioxide | -15.497 |
PF | -15.213 |
uve | -15.046 |
anguage | -14.595 |
ophobia | -14.259 |
Token | made |
Token ID | 925 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ting | +9.668 |
ted | +8.742 |
null | +8.131 |
lisher | +8.102 |
sole | +8.052 |
Neg logit contributions | |
ioxide | -14.109 |
PF | -12.942 |
uve | -12.861 |
itement | -12.823 |
anguage | -12.794 |
Token | medical |
Token ID | 3315 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ting | +10.519 |
ted | +9.029 |
tto | +8.939 |
tering | +8.914 |
sole | +8.772 |
Neg logit contributions | |
ioxide | -10.317 |
PF | -9.594 |
uve | -9.567 |
ourgeois | -9.453 |
anguage | -9.321 |
Token | marijuana |
Token ID | 5727 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ting | +1.289 |
◼ | +1.206 |
lisher | +1.181 |
rend | +1.171 |
tto | +1.126 |
Neg logit contributions | |
ioxide | -1.301 |
uve | -1.293 |
ourgeois | -1.269 |
PF | -1.240 |
uum | -1.237 |
Token | legal |
Token ID | 2742 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ting | +3.983 |
◼ | +3.579 |
lisher | +3.565 |
rend | +3.446 |
tto | +3.399 |
Neg logit contributions | |
uve | -4.573 |
ioxide | -4.562 |
ourgeois | -4.408 |
PF | -4.372 |
uum | -4.359 |
Token | Likewise |
Token ID | 22660 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
iv | +4.054 |
uve | +4.014 |
ophobia | +3.946 |
ioxide | +3.910 |
ourgeois | +3.888 |
Neg logit contributions | |
ting | -5.756 |
◼ | -5.594 |
lisher | -5.468 |
rend | -5.408 |
ITNESS | -5.257 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ioxide | +1.857 |
uve | +1.853 |
ourgeois | +1.829 |
iv | +1.813 |
ophobia | +1.806 |
Neg logit contributions | |
ting | -2.456 |
◼ | -2.376 |
lisher | -2.306 |
rend | -2.299 |
ITNESS | -2.224 |
Token | IGN |
Token ID | 28730 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
uve | +4.221 |
iv | +4.199 |
ourgeois | +4.192 |
ophobia | +4.122 |
ioxide | +4.113 |
Neg logit contributions | |
ting | -5.781 |
◼ | -5.707 |
lisher | -5.454 |
rend | -5.447 |
ITNESS | -5.317 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
iv | +5.717 |
uum | +5.630 |
uve | +5.615 |
ives | +5.559 |
ourgeois | +5.543 |
Neg logit contributions | |
◼ | -6.680 |
ting | -6.670 |
rend | -6.319 |
ITNESS | -6.257 |
lisher | -6.248 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
ioxide | +1.643 |
uve | +1.638 |
ourgeois | +1.591 |
iv | +1.588 |
ophobia | +1.579 |
Neg logit contributions | |
ting | -1.885 |
◼ | -1.821 |
lisher | -1.780 |
rend | -1.750 |
tto | -1.691 |
Token | game |
Token ID | 983 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
uve | +4.420 |
iv | +4.211 |
ophobia | +4.086 |
uses | +3.988 |
ioxide | +3.943 |
Neg logit contributions | |
ting | -10.671 |
◼ | -10.639 |
lisher | -10.175 |
rend | -10.016 |
ITNESS | -9.932 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
iv | +11.120 |
uses | +10.905 |
ives | +10.788 |
uve | +10.495 |
rating | +10.470 |
Neg logit contributions | |
◼ | -17.061 |
ITNESS | -15.991 |
lisher | -15.950 |
tto | -15.877 |
rend | -15.731 |
Token | ' |
Token ID | 705 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rating | +10.557 |
iv | +9.822 |
Poor | +9.640 |
ives | +9.626 |
uses | +9.598 |
Neg logit contributions | |
◼ | -16.523 |
ITNESS | -15.106 |
tto | -14.967 |
ting | -14.897 |
glers | -14.780 |
Token | Pain |
Token ID | 38490 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
iv | +8.975 |
uses | +8.730 |
PF | +8.701 |
uve | +8.565 |
pour | +8.434 |
Neg logit contributions | |
ITNESS | -9.942 |
◼ | -9.756 |
lisher | -9.665 |
ting | -9.491 |
tto | -9.331 |
Token | ful |
Token ID | 913 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ting | +0.149 |
◼ | +0.145 |
lisher | +0.144 |
rend | +0.140 |
ITNESS | +0.138 |
Neg logit contributions | |
uve | -0.131 |
ioxide | -0.130 |
ourgeois | -0.129 |
iv | -0.128 |
ophobia | -0.127 |
Token | ' |
Token ID | 6 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
iv | +2.914 |
uve | +2.901 |
ophobia | +2.898 |
ioxide | +2.861 |
ourgeois | +2.848 |
Neg logit contributions | |
◼ | -4.656 |
ting | -4.647 |
lisher | -4.602 |
ITNESS | -4.460 |
rend | -4.394 |
Token | deep |
Token ID | 2769 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
uve | +4.022 |
iv | +3.836 |
uses | +3.795 |
uum | +3.732 |
ives | +3.699 |
Neg logit contributions | |
◼ | -7.935 |
lisher | -7.821 |
ITNESS | -7.764 |
ting | -7.642 |
rend | -7.389 |
Token | fried |
Token ID | 23018 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ting | +2.998 |
◼ | +2.634 |
rend | +2.579 |
ted | +2.572 |
lisher | +2.558 |
Neg logit contributions | |
ioxide | -4.706 |
ourgeois | -4.586 |
uve | -4.499 |
ivan | -4.487 |
uum | -4.434 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
ioxide | +1.137 |
uve | +1.130 |
ourgeois | +1.100 |
iv | +1.095 |
ophobia | +1.092 |
Neg logit contributions | |
ting | -1.420 |
◼ | -1.367 |
lisher | -1.343 |
rend | -1.316 |
ITNESS | -1.287 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ioxide | +4.322 |
uve | +4.284 |
uses | +4.228 |
pour | +4.202 |
iv | +4.188 |
Neg logit contributions | |
ting | -6.686 |
◼ | -6.555 |
lisher | -6.467 |
rend | -6.226 |
tto | -6.074 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ioxide | +1.123 |
uve | +1.116 |
ourgeois | +1.088 |
iv | +1.081 |
ophobia | +1.078 |
Neg logit contributions | |
ting | -1.377 |
◼ | -1.315 |
lisher | -1.296 |
rend | -1.272 |
ITNESS | -1.240 |
Token | Drain |
Token ID | 36024 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Pour | +6.998 |
Drain | +6.566 |
pour | +5.778 |
Activate | +5.637 |
Flames | +5.386 |
Neg logit contributions | |
skelet | -19.639 |
lisher | -18.751 |
◼ | -18.736 |
ting | -18.703 |
ITNESS | -17.928 |
Token | on |
Token ID | 319 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
iv | +5.289 |
upon | +5.077 |
ives | +4.947 |
pour | +4.561 |
uses | +4.204 |
Neg logit contributions | |
skelet | -25.774 |
lisher | -23.967 |
ITNESS | -23.887 |
◼ | -23.595 |
�� | -22.789 |
Token | a |
Token ID | 257 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
iv | +4.460 |
uve | +4.401 |
ioxide | +4.358 |
ophobia | +4.347 |
uses | +4.342 |
Neg logit contributions | |
◼ | -10.780 |
ting | -10.704 |
lisher | -10.647 |
ITNESS | -10.500 |
rend | -10.408 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ioxide | +1.657 |
uve | +1.645 |
ourgeois | +1.612 |
iv | +1.604 |
ophobia | +1.601 |
Neg logit contributions | |
ting | -1.803 |
◼ | -1.735 |
lisher | -1.697 |
rend | -1.670 |
ITNESS | -1.631 |
Token | towel |
Token ID | 24808 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ioxide | +1.252 |
uve | +1.242 |
ourgeois | +1.208 |
uum | +1.200 |
ophobia | +1.199 |
Neg logit contributions | |
ting | -1.668 |
◼ | -1.598 |
lisher | -1.571 |
rend | -1.552 |
ITNESS | -1.519 |
Token | - |
Token ID | 12 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ting | +2.083 |
◼ | +1.944 |
lisher | +1.904 |
rend | +1.890 |
ted | +1.839 |
Neg logit contributions | |
ioxide | -1.697 |
ourgeois | -1.656 |
uve | -1.652 |
ophobia | -1.603 |
ivan | -1.600 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ioxide | +1.037 |
uve | +1.031 |
ourgeois | +1.007 |
iv | +1.003 |
PF | +1.000 |
Neg logit contributions | |
ting | -1.093 |
◼ | -1.038 |
lisher | -1.024 |
rend | -1.004 |
ITNESS | -0.975 |
Token | The |
Token ID | 464 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ting | +2.458 |
◼ | +2.334 |
lisher | +2.280 |
rend | +2.259 |
ITNESS | +2.174 |
Neg logit contributions | |
ioxide | -2.115 |
uve | -2.089 |
ourgeois | -2.059 |
ophobia | -2.016 |
uum | -1.999 |
Token | city |
Token ID | 1748 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
ioxide | +1.968 |
uve | +1.954 |
ourgeois | +1.923 |
iv | +1.902 |
PF | +1.887 |
Neg logit contributions | |
ting | -2.273 |
◼ | -2.196 |
lisher | -2.109 |
rend | -2.094 |
ITNESS | -2.059 |
Token | is |
Token ID | 318 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
uve | +5.513 |
iv | +5.386 |
uses | +5.360 |
uum | +5.328 |
ophobia | +5.287 |
Neg logit contributions | |
ting | -6.171 |
◼ | -6.170 |
ITNESS | -5.925 |
lisher | -5.921 |
rend | -5.842 |
Token | in |
Token ID | 287 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
uses | +6.176 |
iv | +6.134 |
uve | +6.123 |
ourgeois | +6.079 |
ioxide | +6.005 |
Neg logit contributions | |
◼ | -7.712 |
ITNESS | -7.657 |
lisher | -7.558 |
ting | -7.356 |
rend | -7.257 |
Token | preliminary |
Token ID | 15223 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ives | +7.046 |
uum | +7.025 |
iv | +6.787 |
ophobia | +6.784 |
uses | +6.693 |
Neg logit contributions | |
◼ | -11.753 |
ting | -11.304 |
lisher | -11.292 |
rend | -11.244 |
ITNESS | -11.042 |
Token | talks |
Token ID | 6130 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
occupancy | +8.303 |
ives | +7.938 |
envelope | +7.689 |
odor | +7.476 |
appro | +7.370 |
Neg logit contributions | |
ITNESS | -19.718 |
lisher | -19.553 |
◼ | -19.541 |
rend | -19.136 |
ithing | -18.687 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iv | +6.235 |
ives | +6.111 |
ourgeois | +5.822 |
uve | +5.766 |
ophobia | +5.718 |
Neg logit contributions | |
◼ | -13.532 |
lisher | -13.357 |
ITNESS | -13.056 |
rend | -12.764 |
ting | -12.595 |
Token | Hudson |
Token ID | 19995 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ioxide | +7.291 |
uve | +7.272 |
ourgeois | +7.199 |
ives | +7.169 |
iv | +7.104 |
Neg logit contributions | |
◼ | -9.792 |
ting | -9.516 |
lisher | -9.094 |
rend | -9.081 |
ITNESS | -8.948 |
Token | County |
Token ID | 3418 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
iv | +3.643 |
ioxide | +3.630 |
uve | +3.608 |
ourgeois | +3.574 |
ophobia | +3.562 |
Neg logit contributions | |
ting | -5.736 |
◼ | -5.613 |
lisher | -5.338 |
ITNESS | -5.194 |
rend | -5.189 |
Token | officials |
Token ID | 2828 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
iv | +7.562 |
uses | +7.392 |
ivic | +7.375 |
ourgeois | +7.338 |
ivan | +7.316 |
Neg logit contributions | |
◼ | -11.600 |
ting | -10.947 |
ITNESS | -10.880 |
lisher | -10.412 |
rend | -10.131 |
Token | Tony |
Token ID | 8832 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
ioxide | +0.014 |
uve | +0.014 |
ourgeois | +0.013 |
iv | +0.013 |
ophobia | +0.013 |
Neg logit contributions | |
ting | -0.019 |
◼ | -0.018 |
lisher | -0.018 |
rend | -0.018 |
ITNESS | -0.017 |
Token | Shal |
Token ID | 47974 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ioxide | +0.515 |
uve | +0.514 |
ourgeois | +0.505 |
PF | +0.496 |
ophobia | +0.495 |
Neg logit contributions | |
ting | -0.530 |
◼ | -0.496 |
lisher | -0.490 |
rend | -0.485 |
tto | -0.465 |
Token | h |
Token ID | 71 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ioxide | +2.605 |
iv | +2.547 |
uve | +2.543 |
ourgeois | +2.456 |
uum | +2.452 |
Neg logit contributions | |
ting | -6.488 |
◼ | -6.481 |
lisher | -6.362 |
ITNESS | -6.262 |
rend | -6.184 |
Token | oub |
Token ID | 12944 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ioxide | +1.683 |
uve | +1.660 |
ourgeois | +1.607 |
ophobia | +1.585 |
uum | +1.578 |
Neg logit contributions | |
ting | -4.055 |
◼ | -3.957 |
lisher | -3.879 |
rend | -3.813 |
ITNESS | -3.774 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
uve | +3.867 |
ioxide | +3.851 |
iv | +3.838 |
uses | +3.778 |
PF | +3.776 |
Neg logit contributions | |
ting | -4.804 |
◼ | -4.777 |
lisher | -4.661 |
rend | -4.534 |
ITNESS | -4.495 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ioxide | +0.945 |
uve | +0.940 |
ourgeois | +0.917 |
iv | +0.912 |
ophobia | +0.910 |
Neg logit contributions | |
ting | -0.988 |
◼ | -0.940 |
lisher | -0.926 |
rend | -0.908 |
ITNESS | -0.883 |
Token | 2005 |
Token ID | 14315 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
2005 | +7.284 |
pour | +6.903 |
PF | +6.616 |
uses | +6.408 |
iv | +5.994 |
Neg logit contributions | |
skelet | -23.796 |
lisher | -21.326 |
ting | -20.910 |
Somers | -20.429 |
glers | -20.416 |
Token | Jason |
Token ID | 8982 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
uve | +1.237 |
ioxide | +1.229 |
iv | +1.201 |
ophobia | +1.197 |
uum | +1.192 |
Neg logit contributions | |
ting | -1.778 |
◼ | -1.723 |
lisher | -1.695 |
rend | -1.659 |
ITNESS | -1.639 |
Token | Bat |
Token ID | 6577 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
uve | +4.200 |
iv | +4.098 |
ivan | +4.082 |
uum | +4.068 |
ophobia | +4.066 |
Neg logit contributions | |
ting | -5.765 |
◼ | -5.676 |
lisher | -5.508 |
ITNESS | -5.462 |
rend | -5.345 |
Token | eman |
Token ID | 8463 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ting | +8.403 |
rend | +7.428 |
tto | +7.410 |
tering | +7.157 |
zel | +7.070 |
Neg logit contributions | |
ioxide | -5.937 |
PF | -5.827 |
� | -5.596 |
ophobia | -5.540 |
ourgeois | -5.536 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
uve | +5.243 |
uses | +5.161 |
ophobia | +5.127 |
iv | +5.123 |
pour | +5.107 |
Neg logit contributions | |
ting | -7.350 |
◼ | -7.255 |
lisher | -7.211 |
rend | -7.149 |
ITNESS | -6.850 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ioxide | +1.857 |
uve | +1.853 |
ourgeois | +1.829 |
iv | +1.813 |
ophobia | +1.806 |
Neg logit contributions | |
ting | -2.456 |
◼ | -2.376 |
lisher | -2.306 |
rend | -2.299 |
ITNESS | -2.224 |
Token | IGN |
Token ID | 28730 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
uve | +4.221 |
iv | +4.199 |
ourgeois | +4.192 |
ophobia | +4.122 |
ioxide | +4.113 |
Neg logit contributions | |
ting | -5.781 |
◼ | -5.707 |
lisher | -5.454 |
rend | -5.447 |
ITNESS | -5.317 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
iv | +5.717 |
uum | +5.630 |
uve | +5.615 |
ives | +5.559 |
ourgeois | +5.543 |
Neg logit contributions | |
◼ | -6.680 |
ting | -6.670 |
rend | -6.319 |
ITNESS | -6.257 |
lisher | -6.248 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
ioxide | +1.643 |
uve | +1.638 |
ourgeois | +1.591 |
iv | +1.588 |
ophobia | +1.579 |
Neg logit contributions | |
ting | -1.885 |
◼ | -1.821 |
lisher | -1.780 |
rend | -1.750 |
tto | -1.691 |
Token | game |
Token ID | 983 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
uve | +4.420 |
iv | +4.211 |
ophobia | +4.086 |
uses | +3.988 |
ioxide | +3.943 |
Neg logit contributions | |
ting | -10.671 |
◼ | -10.639 |
lisher | -10.175 |
rend | -10.016 |
ITNESS | -9.932 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
iv | +11.120 |
uses | +10.905 |
ives | +10.788 |
uve | +10.495 |
rating | +10.470 |
Neg logit contributions | |
◼ | -17.061 |
ITNESS | -15.991 |
lisher | -15.950 |
tto | -15.877 |
rend | -15.731 |
Token | ' |
Token ID | 705 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rating | +10.557 |
iv | +9.822 |
Poor | +9.640 |
ives | +9.626 |
uses | +9.598 |
Neg logit contributions | |
◼ | -16.523 |
ITNESS | -15.106 |
tto | -14.967 |
ting | -14.897 |
glers | -14.780 |
Token | Pain |
Token ID | 38490 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
iv | +8.975 |
uses | +8.730 |
PF | +8.701 |
uve | +8.565 |
pour | +8.434 |
Neg logit contributions | |
ITNESS | -9.942 |
◼ | -9.756 |
lisher | -9.665 |
ting | -9.491 |
tto | -9.331 |
Token | ful |
Token ID | 913 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ting | +0.149 |
◼ | +0.145 |
lisher | +0.144 |
rend | +0.140 |
ITNESS | +0.138 |
Neg logit contributions | |
uve | -0.131 |
ioxide | -0.130 |
ourgeois | -0.129 |
iv | -0.128 |
ophobia | -0.127 |
Token | ' |
Token ID | 6 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
iv | +2.914 |
uve | +2.901 |
ophobia | +2.898 |
ioxide | +2.861 |
ourgeois | +2.848 |
Neg logit contributions | |
◼ | -4.656 |
ting | -4.647 |
lisher | -4.602 |
ITNESS | -4.460 |
rend | -4.394 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
rating | +10.508 |
score | +10.214 |
iv | +10.182 |
pour | +9.529 |
ophobia | +9.517 |
Neg logit contributions | |
◼ | -15.573 |
ITNESS | -15.002 |
lisher | -14.884 |
ting | -14.589 |
tto | -14.539 |
Token | moves |
Token ID | 6100 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ting | +1.051 |
◼ | +0.983 |
lisher | +0.968 |
rend | +0.957 |
tto | +0.915 |
Neg logit contributions | |
ioxide | -1.149 |
uve | -1.139 |
ourgeois | -1.117 |
ophobia | -1.102 |
PF | -1.100 |
Token | now |
Token ID | 783 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ting | +6.667 |
rend | +5.894 |
◼ | +5.834 |
lisher | +5.791 |
ted | +5.783 |
Neg logit contributions | |
ioxide | -6.933 |
uve | -6.586 |
ourgeois | -6.562 |
PF | -6.546 |
uum | -6.427 |
Token | place |
Token ID | 1295 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ting | +3.399 |
◼ | +3.135 |
lisher | +3.106 |
rend | +3.088 |
tto | +2.977 |
Neg logit contributions | |
ioxide | -3.094 |
uve | -3.057 |
ourgeois | -2.992 |
PF | -2.955 |
uum | -2.934 |
Token | the |
Token ID | 262 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ting | +3.047 |
◼ | +2.804 |
lisher | +2.785 |
rend | +2.750 |
tto | +2.645 |
Neg logit contributions | |
ioxide | -3.036 |
uve | -3.008 |
ourgeois | -2.938 |
PF | -2.905 |
ophobia | -2.904 |
Token | high |
Token ID | 1029 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ioxide | +1.627 |
uve | +1.608 |
ourgeois | +1.581 |
ophobia | +1.550 |
iv | +1.548 |
Neg logit contributions | |
ting | -2.528 |
◼ | -2.438 |
lisher | -2.389 |
rend | -2.369 |
ITNESS | -2.314 |
Token | pressure |
Token ID | 3833 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ioxide | +1.810 |
uve | +1.778 |
ourgeois | +1.751 |
uses | +1.723 |
iv | +1.721 |
Neg logit contributions | |
ting | -2.582 |
◼ | -2.468 |
lisher | -2.436 |
rend | -2.387 |
ITNESS | -2.347 |
Token | of |
Token ID | 286 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
iv | +9.884 |
uses | +9.324 |
upon | +9.241 |
envelope | +9.196 |
ives | +9.120 |
Neg logit contributions | |
ITNESS | -17.092 |
◼ | -16.361 |
lisher | -16.141 |
umbnail | -15.765 |
ting | -15.734 |
Token | being |
Token ID | 852 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ioxide | +1.162 |
uve | +1.161 |
ourgeois | +1.139 |
iv | +1.130 |
uses | +1.120 |
Neg logit contributions | |
ting | -1.290 |
◼ | -1.239 |
lisher | -1.212 |
rend | -1.196 |
ITNESS | -1.175 |
Token | a |
Token ID | 257 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
uve | +1.117 |
ioxide | +1.111 |
ourgeois | +1.089 |
iv | +1.085 |
uses | +1.075 |
Neg logit contributions | |
ting | -1.365 |
◼ | -1.305 |
lisher | -1.277 |
rend | -1.268 |
ITNESS | -1.241 |
Token | leader |
Token ID | 3554 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
ioxide | +0.419 |
uve | +0.417 |
ourgeois | +0.409 |
iv | +0.404 |
PF | +0.404 |
Neg logit contributions | |
ting | -0.441 |
◼ | -0.421 |
lisher | -0.409 |
rend | -0.407 |
ITNESS | -0.395 |
Token | in |
Token ID | 287 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
iv | +4.695 |
uve | +4.581 |
ives | +4.495 |
pour | +4.485 |
uses | +4.476 |
Neg logit contributions | |
ITNESS | -8.622 |
◼ | -8.523 |
ting | -8.507 |
lisher | -8.248 |
rend | -8.081 |
Token | existing |
Token ID | 4683 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
uve | +3.680 |
ioxide | +3.671 |
iv | +3.586 |
uses | +3.582 |
ourgeois | +3.553 |
Neg logit contributions | |
ting | -4.105 |
◼ | -4.008 |
rend | -3.861 |
lisher | -3.860 |
ITNESS | -3.822 |
Token | creepy |
Token ID | 23387 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
uve | +6.303 |
ophobia | +6.208 |
PF | +6.174 |
iv | +6.161 |
ives | +6.093 |
Neg logit contributions | |
◼ | -8.169 |
ting | -7.871 |
lisher | -7.626 |
ITNESS | -7.614 |
rend | -7.547 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
uve | +4.614 |
ophobia | +4.591 |
uum | +4.566 |
iv | +4.534 |
ioxide | +4.513 |
Neg logit contributions | |
◼ | -5.636 |
ting | -5.552 |
lisher | -5.339 |
rend | -5.259 |
ITNESS | -5.244 |
Token | and |
Token ID | 290 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
uve | +1.670 |
ioxide | +1.637 |
iv | +1.632 |
ophobia | +1.617 |
uses | +1.610 |
Neg logit contributions | |
ting | -2.091 |
◼ | -2.046 |
lisher | -1.990 |
rend | -1.973 |
ITNESS | -1.941 |
Token | focus |
Token ID | 2962 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
uve | +2.283 |
ioxide | +2.241 |
ourgeois | +2.228 |
iv | +2.222 |
ophobia | +2.205 |
Neg logit contributions | |
ting | -2.684 |
◼ | -2.640 |
lisher | -2.566 |
rend | -2.541 |
ITNESS | -2.460 |
Token | heavily |
Token ID | 7272 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
iv | +7.268 |
uve | +6.901 |
ives | +6.882 |
uum | +6.735 |
ophobia | +6.547 |
Neg logit contributions | |
◼ | -10.469 |
lisher | -10.267 |
ting | -10.025 |
tto | -9.906 |
rend | -9.829 |
Token | on |
Token ID | 319 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
iv | +8.542 |
upon | +8.250 |
ives | +7.962 |
uve | +7.839 |
uum | +7.632 |
Neg logit contributions | |
lisher | -16.968 |
ITNESS | -16.772 |
◼ | -16.599 |
tto | -16.441 |
ting | -16.346 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
uve | +0.542 |
ioxide | +0.537 |
ourgeois | +0.525 |
ophobia | +0.522 |
iv | +0.521 |
Neg logit contributions | |
ting | -0.622 |
◼ | -0.599 |
lisher | -0.587 |
rend | -0.578 |
ITNESS | -0.560 |
Token | design |
Token ID | 1486 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
uve | +2.649 |
ioxide | +2.599 |
ophobia | +2.593 |
PF | +2.541 |
uses | +2.537 |
Neg logit contributions | |
ting | -3.179 |
◼ | -3.116 |
lisher | -3.013 |
rend | -2.983 |
ITNESS | -2.898 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ting | +0.065 |
◼ | +0.062 |
lisher | +0.061 |
rend | +0.060 |
ITNESS | +0.059 |
Neg logit contributions | |
ioxide | -0.053 |
uve | -0.053 |
ourgeois | -0.052 |
iv | -0.052 |
ophobia | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
uve | +0.996 |
ioxide | +0.985 |
ourgeois | +0.966 |
iv | +0.961 |
ophobia | +0.960 |
Neg logit contributions | |
ting | -1.093 |
◼ | -1.065 |
lisher | -1.034 |
rend | -1.017 |
ITNESS | -0.985 |
Token | times |
Token ID | 1661 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ioxide | +1.744 |
uve | +1.734 |
iv | +1.697 |
ourgeois | +1.688 |
ophobia | +1.682 |
Neg logit contributions | |
ting | -2.194 |
◼ | -2.163 |
lisher | -2.118 |
rend | -2.075 |
ITNESS | -2.035 |
Token | for |
Token ID | 329 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ioxide | +1.762 |
uve | +1.752 |
iv | +1.721 |
ourgeois | +1.709 |
ophobia | +1.702 |
Neg logit contributions | |
ting | -2.179 |
◼ | -2.137 |
lisher | -2.076 |
rend | -2.042 |
ITNESS | -2.036 |
Token | Monk |
Token ID | 28854 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ioxide | +3.430 |
uve | +3.410 |
ophobia | +3.322 |
ourgeois | +3.321 |
ivan | +3.289 |
Neg logit contributions | |
ting | -4.353 |
◼ | -4.334 |
lisher | -4.218 |
ITNESS | -4.078 |
rend | -4.068 |
Token | ), |
Token ID | 828 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ioxide | +3.328 |
uve | +3.280 |
ophobia | +3.255 |
iv | +3.255 |
ourgeois | +3.234 |
Neg logit contributions | |
ting | -4.003 |
◼ | -4.001 |
lisher | -3.822 |
rend | -3.798 |
ITNESS | -3.783 |
Token | Gu |
Token ID | 1962 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
uve | +1.251 |
ioxide | +1.244 |
ourgeois | +1.221 |
iv | +1.208 |
PF | +1.198 |
Neg logit contributions | |
ting | -1.657 |
◼ | -1.594 |
lisher | -1.572 |
rend | -1.543 |
ITNESS | -1.514 |
Token | illa |
Token ID | 5049 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
uve | +2.740 |
ioxide | +2.710 |
ivan | +2.589 |
iv | +2.555 |
ourgeois | +2.488 |
Neg logit contributions | |
ting | -9.585 |
◼ | -9.404 |
lisher | -9.182 |
ITNESS | -9.084 |
rend | -9.039 |
Token | ume |
Token ID | 2454 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
uve | +7.658 |
uum | +7.400 |
ioxide | +7.085 |
uses | +7.035 |
iv | +6.765 |
Neg logit contributions | |
◼ | -22.084 |
skelet | -21.762 |
ting | -20.399 |
lisher | -20.147 |
ITNESS | -20.108 |
Token | ( |
Token ID | 357 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
ioxide | +2.232 |
uve | +2.212 |
iv | +2.160 |
ourgeois | +2.155 |
ophobia | +2.154 |
Neg logit contributions | |
ting | -3.137 |
◼ | -3.053 |
lisher | -2.999 |
rend | -2.915 |
ITNESS | -2.907 |
Token | nom |
Token ID | 26601 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
iv | +6.000 |
uses | +5.681 |
PF | +5.607 |
uve | +5.570 |
pour | +5.555 |
Neg logit contributions | |
ITNESS | -8.403 |
ting | -8.379 |
lisher | -8.331 |
◼ | -8.231 |
tto | -7.874 |
Token | inated |
Token ID | 3898 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ting | +2.717 |
◼ | +2.550 |
lisher | +2.544 |
rend | +2.511 |
tto | +2.433 |
Neg logit contributions | |
ioxide | -1.675 |
uve | -1.651 |
ourgeois | -1.604 |
PF | -1.583 |
ophobia | -1.564 |
Token | five |
Token ID | 1936 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ioxide | +2.498 |
uve | +2.493 |
iv | +2.470 |
ourgeois | +2.452 |
uses | +2.431 |
Neg logit contributions | |
ting | -4.132 |
◼ | -4.101 |
lisher | -4.015 |
ITNESS | -3.955 |
rend | -3.944 |
Token | the |
Token ID | 262 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
uve | +2.095 |
ioxide | +2.070 |
ophobia | +2.042 |
ourgeois | +2.038 |
PF | +2.032 |
Neg logit contributions | |
ting | -2.378 |
◼ | -2.316 |
lisher | -2.283 |
rend | -2.201 |
ITNESS | -2.151 |
Token | Organization |
Token ID | 12275 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
uve | +3.709 |
ioxide | +3.676 |
ophobia | +3.645 |
ourgeois | +3.600 |
ives | +3.574 |
Neg logit contributions | |
ting | -5.558 |
◼ | -5.511 |
lisher | -5.385 |
rend | -5.120 |
ITNESS | -5.107 |
Token | of |
Token ID | 286 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
uve | +2.376 |
ourgeois | +2.306 |
ioxide | +2.296 |
PF | +2.284 |
ophobia | +2.279 |
Neg logit contributions | |
ting | -3.474 |
◼ | -3.428 |
lisher | -3.380 |
rend | -3.299 |
ITNESS | -3.226 |
Token | American |
Token ID | 1605 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
ourgeois | +1.316 |
uve | +1.308 |
ioxide | +1.305 |
ophobia | +1.279 |
iv | +1.277 |
Neg logit contributions | |
ting | -3.280 |
◼ | -3.168 |
lisher | -3.129 |
rend | -3.084 |
ITNESS | -3.002 |
Token | States |
Token ID | 1829 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ting | +7.598 |
rend | +7.164 |
lisher | +6.947 |
◼ | +6.860 |
tto | +6.570 |
Neg logit contributions | |
ioxide | -7.113 |
uve | -7.039 |
PF | -6.732 |
uum | -6.718 |
pour | -6.700 |
Token | ( |
Token ID | 357 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
uve | +1.708 |
ioxide | +1.708 |
ophobia | +1.669 |
ourgeois | +1.668 |
iv | +1.662 |
Neg logit contributions | |
ting | -2.270 |
◼ | -2.212 |
lisher | -2.153 |
rend | -2.095 |
ITNESS | -2.063 |
Token | O |
Token ID | 46 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
PF | +7.121 |
OH | +6.645 |
IV | +6.486 |
ophobia | +6.481 |
iv | +6.182 |
Neg logit contributions | |
ting | -19.822 |
◼ | -19.799 |
rend | -19.296 |
lisher | -18.940 |
ted | -18.453 |
Token | AS |
Token ID | 1921 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
uses | +5.321 |
uve | +5.308 |
ivan | +5.274 |
ives | +5.208 |
ourgeois | +5.191 |
Neg logit contributions | |
ting | -5.584 |
◼ | -5.544 |
lisher | -5.323 |
rend | -5.227 |
ITNESS | -5.088 |
Token | ) |
Token ID | 8 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ioxide | +2.599 |
uve | +2.588 |
PF | +2.583 |
iv | +2.556 |
ourgeois | +2.531 |
Neg logit contributions | |
ting | -3.495 |
◼ | -3.432 |
lisher | -3.250 |
rend | -3.202 |
ITNESS | -3.195 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
uve | +3.303 |
iv | +3.226 |
ioxide | +3.223 |
ourgeois | +3.194 |
uum | +3.186 |
Neg logit contributions | |
ting | -4.220 |
◼ | -4.168 |
lisher | -4.014 |
ITNESS | -3.917 |
rend | -3.900 |
Token | the |
Token ID | 262 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
uve | +1.558 |
ioxide | +1.549 |
ourgeois | +1.536 |
ophobia | +1.517 |
iv | +1.511 |
Neg logit contributions | |
ting | -1.866 |
◼ | -1.809 |
lisher | -1.781 |
rend | -1.737 |
ITNESS | -1.688 |
Token | game |
Token ID | 983 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
uve | +4.420 |
iv | +4.211 |
ophobia | +4.086 |
uses | +3.988 |
ioxide | +3.943 |
Neg logit contributions | |
ting | -10.671 |
◼ | -10.639 |
lisher | -10.175 |
rend | -10.016 |
ITNESS | -9.932 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
iv | +11.120 |
uses | +10.905 |
ives | +10.788 |
uve | +10.495 |
rating | +10.470 |
Neg logit contributions | |
◼ | -17.061 |
ITNESS | -15.991 |
lisher | -15.950 |
tto | -15.877 |
rend | -15.731 |
Token | ' |
Token ID | 705 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rating | +10.557 |
iv | +9.822 |
Poor | +9.640 |
ives | +9.626 |
uses | +9.598 |
Neg logit contributions | |
◼ | -16.523 |
ITNESS | -15.106 |
tto | -14.967 |
ting | -14.897 |
glers | -14.780 |
Token | Pain |
Token ID | 38490 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
iv | +8.975 |
uses | +8.730 |
PF | +8.701 |
uve | +8.565 |
pour | +8.434 |
Neg logit contributions | |
ITNESS | -9.942 |
◼ | -9.756 |
lisher | -9.665 |
ting | -9.491 |
tto | -9.331 |
Token | ful |
Token ID | 913 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ting | +0.149 |
◼ | +0.145 |
lisher | +0.144 |
rend | +0.140 |
ITNESS | +0.138 |
Neg logit contributions | |
uve | -0.131 |
ioxide | -0.130 |
ourgeois | -0.129 |
iv | -0.128 |
ophobia | -0.127 |
Token | ' |
Token ID | 6 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
iv | +2.914 |
uve | +2.901 |
ophobia | +2.898 |
ioxide | +2.861 |
ourgeois | +2.848 |
Neg logit contributions | |
◼ | -4.656 |
ting | -4.647 |
lisher | -4.602 |
ITNESS | -4.460 |
rend | -4.394 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
rating | +10.508 |
score | +10.214 |
iv | +10.182 |
pour | +9.529 |
ophobia | +9.517 |
Neg logit contributions | |
◼ | -15.573 |
ITNESS | -15.002 |
lisher | -14.884 |
ting | -14.589 |
tto | -14.539 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
iv | +6.109 |
uve | +6.061 |
uses | +5.893 |
uum | +5.835 |
ourgeois | +5.832 |
Neg logit contributions | |
◼ | -9.232 |
ting | -9.185 |
lisher | -8.957 |
ITNESS | -8.907 |
tto | -8.843 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
iv | +5.458 |
ioxide | +4.851 |
uve | +4.769 |
ophobia | +4.764 |
PF | +4.694 |
Neg logit contributions | |
◼ | -16.067 |
ting | -15.890 |
lisher | -15.674 |
ITNESS | -15.302 |
tto | -15.046 |
Token | out |
Token ID | 503 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
iv | +8.908 |
uve | +8.863 |
pour | +8.753 |
PF | +8.678 |
uum | +8.665 |
Neg logit contributions | |
◼ | -9.203 |
ITNESS | -9.028 |
ting | -8.923 |
lisher | -8.730 |
tto | -8.692 |
Token | of |
Token ID | 286 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
uve | +3.653 |
ioxide | +3.647 |
iv | +3.582 |
pour | +3.570 |
uses | +3.540 |
Neg logit contributions | |
ting | -5.543 |
◼ | -5.468 |
lisher | -5.409 |
rend | -5.213 |
ITNESS | -5.204 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
uve | +7.603 |
iv | +7.575 |
ives | +7.326 |
pour | +7.247 |
ophobia | +6.925 |
Neg logit contributions | |
lisher | -11.450 |
ting | -11.376 |
ITNESS | -11.356 |
◼ | -11.309 |
tto | -11.126 |
Token | a |
Token ID | 257 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
uve | +9.896 |
Pour | +9.714 |
uses | +9.623 |
iv | +9.623 |
pour | +9.528 |
Neg logit contributions | |
lisher | -12.759 |
ting | -12.744 |
◼ | -12.743 |
ITNESS | -12.586 |
tto | -12.234 |
Token | 0 |
Token ID | 657 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
uve | +4.857 |
iv | +4.586 |
pour | +4.552 |
PF | +4.464 |
ourgeois | +4.458 |
Neg logit contributions | |
◼ | -9.275 |
ting | -9.068 |
lisher | -8.813 |
ITNESS | -8.736 |
tto | -8.613 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
uve | +5.068 |
iv | +5.036 |
uses | +4.797 |
ivan | +4.779 |
pour | +4.765 |
Neg logit contributions | |
ting | -8.618 |
◼ | -8.613 |
lisher | -8.382 |
ITNESS | -8.314 |
tto | -8.155 |
Token | 8 |
Token ID | 23 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
iv | +4.270 |
uve | +4.023 |
ioxide | +3.930 |
ivan | +3.741 |
ives | +3.662 |
Neg logit contributions | |
◼ | -12.690 |
ting | -12.662 |
lisher | -12.412 |
ITNESS | -12.016 |
tto | -11.876 |
Token | rating |
Token ID | 7955 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
uve | +6.270 |
iv | +6.063 |
pour | +5.867 |
PF | +5.790 |
ives | +5.773 |
Neg logit contributions | |
ting | -9.073 |
◼ | -8.766 |
ITNESS | -8.656 |
lisher | -8.643 |
tto | -8.528 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
iv | +10.587 |
uve | +10.557 |
pour | +10.210 |
rating | +10.056 |
uum | +9.948 |
Neg logit contributions | |
◼ | -14.589 |
ITNESS | -14.476 |
lisher | -14.259 |
ting | -14.246 |
tto | -13.717 |
Token | The |
Token ID | 383 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
uve | +10.244 |
Pour | +10.236 |
iv | +10.176 |
uum | +10.172 |
ourgeois | +10.138 |
Neg logit contributions | |
ITNESS | -11.439 |
◼ | -11.415 |
lisher | -11.400 |
ting | -11.324 |
rend | -10.999 |
Token | Bastard |
Token ID | 47209 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ioxide | +2.983 |
uve | +2.943 |
iv | +2.940 |
ophobia | +2.930 |
ives | +2.877 |
Neg logit contributions | |
ting | -4.523 |
◼ | -4.411 |
lisher | -4.283 |
rend | -4.154 |
ITNESS | -4.120 |
Token | Execution |
Token ID | 37497 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
ioxide | +1.382 |
uve | +1.367 |
ourgeois | +1.358 |
iv | +1.354 |
uses | +1.346 |
Neg logit contributions | |
ting | -1.133 |
◼ | -1.089 |
lisher | -1.053 |
rend | -1.028 |
ITNESS | -1.003 |
Token | er |
Token ID | 263 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uve | +0.540 |
ioxide | +0.538 |
ourgeois | +0.528 |
iv | +0.527 |
uses | +0.525 |
Neg logit contributions | |
ting | -0.712 |
◼ | -0.684 |
lisher | -0.675 |
rend | -0.665 |
ITNESS | -0.649 |
Token | violation |
Token ID | 8747 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ioxide | +0.289 |
uve | +0.288 |
ourgeois | +0.281 |
ophobia | +0.278 |
iv | +0.277 |
Neg logit contributions | |
ting | -0.399 |
◼ | -0.384 |
lisher | -0.378 |
rend | -0.371 |
ITNESS | -0.363 |
Token | will |
Token ID | 481 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ting | +1.210 |
◼ | +1.138 |
lisher | +1.121 |
rend | +1.107 |
ITNESS | +1.065 |
Neg logit contributions | |
ioxide | -1.123 |
uve | -1.112 |
ourgeois | -1.093 |
ophobia | -1.074 |
PF | -1.073 |
Token | certainly |
Token ID | 3729 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ting | +2.702 |
◼ | +2.476 |
lisher | +2.454 |
rend | +2.443 |
tto | +2.347 |
Neg logit contributions | |
ioxide | -2.568 |
uve | -2.557 |
ourgeois | -2.508 |
PF | -2.462 |
ophobia | -2.460 |
Token | put |
Token ID | 1234 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ioxide | +0.904 |
uve | +0.901 |
iv | +0.883 |
ourgeois | +0.883 |
ophobia | +0.879 |
Neg logit contributions | |
ting | -1.056 |
◼ | -1.038 |
lisher | -1.018 |
rend | -0.990 |
ITNESS | -0.987 |
Token | additional |
Token ID | 3224 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
uve | +2.899 |
iv | +2.871 |
ioxide | +2.853 |
ourgeois | +2.817 |
uses | +2.786 |
Neg logit contributions | |
◼ | -4.491 |
ting | -4.382 |
lisher | -4.283 |
rend | -4.249 |
ITNESS | -4.159 |
Token | pressure |
Token ID | 3833 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ioxide | +3.330 |
iv | +3.319 |
uve | +3.317 |
ophobia | +3.264 |
uum | +3.262 |
Neg logit contributions | |
ting | -3.576 |
◼ | -3.555 |
lisher | -3.402 |
rend | -3.344 |
ITNESS | -3.272 |
Token | on |
Token ID | 319 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
iv | +8.944 |
upon | +7.960 |
ives | +7.867 |
uve | +7.778 |
uum | +7.615 |
Neg logit contributions | |
ITNESS | -16.878 |
lisher | -16.370 |
◼ | -16.241 |
ting | -15.874 |
exclusive | -15.521 |
Token | WWE |
Token ID | 15247 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
uve | +0.328 |
ioxide | +0.328 |
ourgeois | +0.321 |
iv | +0.317 |
uses | +0.313 |
Neg logit contributions | |
ting | -0.458 |
◼ | -0.444 |
lisher | -0.433 |
rend | -0.429 |
ITNESS | -0.418 |
Token | to |
Token ID | 284 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ting | +3.521 |
◼ | +3.259 |
lisher | +3.235 |
rend | +3.194 |
tto | +3.075 |
Neg logit contributions | |
ioxide | -3.400 |
uve | -3.304 |
ourgeois | -3.272 |
PF | -3.224 |
ophobia | -3.208 |
Token | re |
Token ID | 302 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
ting | +2.065 |
◼ | +1.916 |
lisher | +1.904 |
rend | +1.882 |
tto | +1.815 |
Neg logit contributions | |
ioxide | -1.896 |
uve | -1.885 |
ourgeois | -1.846 |
ophobia | -1.814 |
PF | -1.811 |
Token | evaluate |
Token ID | 49786 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
uve | +4.523 |
uses | +4.367 |
iv | +4.331 |
uum | +4.305 |
pour | +4.290 |
Neg logit contributions | |
ting | -7.739 |
◼ | -7.637 |
lisher | -7.337 |
ITNESS | -7.255 |
rend | -7.080 |
Token | be |
Token ID | 307 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
iv | +4.550 |
ioxide | +4.499 |
ivan | +4.436 |
pour | +4.401 |
ourgeois | +4.399 |
Neg logit contributions | |
◼ | -4.866 |
lisher | -4.831 |
ting | -4.750 |
ITNESS | -4.678 |
rend | -4.549 |
Token | � |
Token ID | 564 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
iv | +4.148 |
uve | +4.141 |
ioxide | +4.138 |
ophobia | +4.115 |
ourgeois | +4.092 |
Neg logit contributions | |
ting | -5.108 |
◼ | -5.063 |
lisher | -5.040 |
rend | -4.855 |
ITNESS | -4.835 |
Token | � |
Token ID | 250 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ioxide | +0.771 |
uve | +0.770 |
ourgeois | +0.754 |
iv | +0.746 |
ophobia | +0.746 |
Neg logit contributions | |
ting | -0.601 |
◼ | -0.563 |
lisher | -0.555 |
rend | -0.541 |
ITNESS | -0.523 |
Token | at |
Token ID | 265 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
ioxide | +1.021 |
uve | +1.020 |
ourgeois | +1.000 |
iv | +0.997 |
uses | +0.989 |
Neg logit contributions | |
ting | -1.155 |
◼ | -1.110 |
lisher | -1.096 |
rend | -1.068 |
ITNESS | -1.053 |
Token | an |
Token ID | 281 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
ioxide | +0.338 |
uve | +0.337 |
ourgeois | +0.329 |
iv | +0.328 |
ivan | +0.326 |
Neg logit contributions | |
ting | -0.371 |
◼ | -0.354 |
lisher | -0.352 |
rend | -0.340 |
ITNESS | -0.335 |
Token | early |
Token ID | 1903 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
iv | +5.732 |
ives | +5.672 |
uses | +5.639 |
uve | +5.614 |
uum | +5.586 |
Neg logit contributions | |
ting | -8.751 |
lisher | -8.721 |
ITNESS | -8.498 |
◼ | -8.416 |
rend | -8.099 |
Token | stage |
Token ID | 3800 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
iv | +5.787 |
envelope | +5.638 |
izational | +5.285 |
occupancy | +5.183 |
Stage | +5.138 |
Neg logit contributions | |
lisher | -19.370 |
ITNESS | -19.042 |
◼ | -18.483 |
ting | -18.349 |
ithing | -18.333 |
Token | � |
Token ID | 447 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
uve | +1.508 |
ioxide | +1.493 |
iv | +1.476 |
ourgeois | +1.467 |
ivan | +1.456 |
Neg logit contributions | |
ting | -1.626 |
◼ | -1.568 |
lisher | -1.553 |
rend | -1.494 |
ITNESS | -1.484 |
Token | � |
Token ID | 251 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ioxide | +0.489 |
uve | +0.486 |
ourgeois | +0.479 |
ophobia | +0.472 |
PF | +0.471 |
Neg logit contributions | |
ting | -0.379 |
◼ | -0.354 |
lisher | -0.347 |
rend | -0.342 |
ITNESS | -0.328 |
Token | by |
Token ID | 416 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ting | +1.396 |
◼ | +1.320 |
lisher | +1.301 |
rend | +1.286 |
ITNESS | +1.241 |
Neg logit contributions | |
ioxide | -1.112 |
uve | -1.102 |
ourgeois | -1.080 |
ophobia | -1.061 |
PF | -1.058 |
Token | the |
Token ID | 262 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
uve | +2.596 |
ioxide | +2.576 |
ourgeois | +2.564 |
iv | +2.558 |
uses | +2.532 |
Neg logit contributions | |
ting | -3.499 |
◼ | -3.406 |
lisher | -3.322 |
rend | -3.281 |
ITNESS | -3.232 |
Token | v |
Token ID | 85 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
iv | +4.177 |
uve | +3.856 |
uses | +3.667 |
pour | +3.622 |
ivan | +3.569 |
Neg logit contributions | |
◼ | -9.760 |
lisher | -9.368 |
ITNESS | -9.360 |
skelet | -9.286 |
ting | -9.262 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ioxide | +0.192 |
uve | +0.190 |
ourgeois | +0.186 |
ophobia | +0.178 |
PF | +0.177 |
Neg logit contributions | |
ting | -0.536 |
◼ | -0.512 |
lisher | -0.506 |
rend | -0.504 |
tto | -0.490 |
Token | . |
Token ID | 764 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ioxide | +1.068 |
uve | +1.059 |
ourgeois | +1.028 |
iv | +1.023 |
ophobia | +1.020 |
Neg logit contributions | |
ting | -1.413 |
◼ | -1.355 |
lisher | -1.331 |
rend | -1.311 |
ITNESS | -1.275 |
Token | Ga |
Token ID | 12822 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
ioxide | +4.226 |
uve | +4.220 |
iv | +4.058 |
uum | +4.050 |
envelope | +4.036 |
Neg logit contributions | |
ting | -6.270 |
◼ | -6.182 |
lisher | -6.040 |
ITNESS | -5.889 |
rend | -5.879 |
Token | ussian |
Token ID | 31562 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
uve | +2.063 |
iv | +1.904 |
uum | +1.873 |
uses | +1.809 |
ioxide | +1.801 |
Neg logit contributions | |
◼ | -12.260 |
ting | -12.242 |
lisher | -11.959 |
ITNESS | -11.875 |
rend | -11.681 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
PF | +4.571 |
iv | +4.287 |
ophobia | +4.193 |
ioxide | +4.112 |
Activate | +3.888 |
Neg logit contributions | |
◼ | -14.158 |
ting | -13.997 |
skelet | -13.977 |
lisher | -13.775 |
tering | -13.344 |
Token | ur |
Token ID | 333 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
iv | +6.463 |
uum | +5.869 |
uve | +5.670 |
uses | +5.435 |
ives | +5.310 |
Neg logit contributions | |
skelet | -22.756 |
◼ | -22.213 |
ITNESS | -20.326 |
lisher | -20.002 |
JO | -19.974 |
Token | ( |
Token ID | 357 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
ting | +1.296 |
◼ | +1.189 |
lisher | +1.180 |
rend | +1.172 |
ITNESS | +1.132 |
Neg logit contributions | |
uve | -1.151 |
ioxide | -1.145 |
ourgeois | -1.138 |
uum | -1.104 |
ivan | -1.100 |
Token | gray |
Token ID | 12768 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ioxide | +0.633 |
uve | +0.628 |
ourgeois | +0.613 |
ophobia | +0.601 |
PF | +0.600 |
Neg logit contributions | |
ting | -0.984 |
◼ | -0.938 |
lisher | -0.925 |
rend | -0.915 |
ITNESS | -0.888 |
Token | , |
Token ID | 837 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ioxide | +2.350 |
uve | +2.320 |
iv | +2.276 |
ophobia | +2.258 |
PF | +2.256 |
Neg logit contributions | |
ting | -2.685 |
◼ | -2.621 |
lisher | -2.557 |
rend | -2.515 |
ITNESS | -2.446 |
Token | ( |
Token ID | 357 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ting | +1.578 |
◼ | +1.452 |
rend | +1.441 |
lisher | +1.438 |
tto | +1.383 |
Neg logit contributions | |
uve | -1.434 |
ioxide | -1.426 |
ourgeois | -1.409 |
ophobia | -1.383 |
uum | -1.378 |
Token | to |
Token ID | 284 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
ophobia | +5.929 |
iv | +5.925 |
uses | +5.712 |
ives | +5.699 |
pour | +5.669 |
Neg logit contributions | |
◼ | -8.903 |
lisher | -8.868 |
ITNESS | -8.844 |
ting | -8.819 |
rend | -8.360 |
Token | a |
Token ID | 257 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ioxide | +0.033 |
uve | +0.033 |
ourgeois | +0.032 |
ophobia | +0.032 |
iv | +0.032 |
Neg logit contributions | |
ting | -0.046 |
◼ | -0.044 |
lisher | -0.043 |
rend | -0.042 |
ITNESS | -0.041 |
Token | state |
Token ID | 1181 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
uve | +2.429 |
ophobia | +2.396 |
ourgeois | +2.395 |
ioxide | +2.375 |
uses | +2.370 |
Neg logit contributions | |
◼ | -3.177 |
ting | -3.175 |
lisher | -3.076 |
ITNESS | -2.995 |
rend | -2.979 |
Token | that |
Token ID | 326 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
uve | +0.019 |
ioxide | +0.019 |
ourgeois | +0.019 |
ophobia | +0.019 |
PF | +0.019 |
Neg logit contributions | |
ting | -0.023 |
◼ | -0.022 |
lisher | -0.021 |
rend | -0.021 |
ITNESS | -0.021 |
Token | shows |
Token ID | 2523 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ioxide | +1.094 |
uve | +1.088 |
ophobia | +1.075 |
uses | +1.072 |
ourgeois | +1.070 |
Neg logit contributions | |
ting | -1.246 |
◼ | -1.205 |
lisher | -1.187 |
rend | -1.143 |
ITNESS | -1.130 |
Token | little |
Token ID | 1310 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ioxide | +1.408 |
uve | +1.400 |
ophobia | +1.389 |
ourgeois | +1.371 |
uses | +1.366 |
Neg logit contributions | |
ting | -2.101 |
◼ | -2.071 |
lisher | -2.043 |
rend | -1.946 |
ITNESS | -1.933 |
Token | comp |
Token ID | 552 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ophobia | +9.341 |
civ | +9.064 |
odor | +8.741 |
envelope | +8.740 |
eth | +8.613 |
Neg logit contributions | |
lisher | -16.734 |
◼ | -16.172 |
sts | -15.033 |
ITNESS | -14.875 |
exclusive | -14.873 |
Token | unction |
Token ID | 4575 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
iv | +4.513 |
uve | +4.499 |
ophobia | +4.435 |
ourgeois | +4.410 |
ivan | +4.406 |
Neg logit contributions | |
ting | -4.654 |
◼ | -4.574 |
lisher | -4.383 |
tto | -4.140 |
ITNESS | -4.121 |
Token | about |
Token ID | 546 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ophobia | +5.761 |
iv | +5.706 |
uve | +5.655 |
ourgeois | +5.614 |
pour | +5.511 |
Neg logit contributions | |
◼ | -6.378 |
lisher | -6.315 |
ting | -6.148 |
ITNESS | -6.026 |
rend | -5.911 |
Token | tort |
Token ID | 7619 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
uses | +4.491 |
uve | +4.482 |
ourgeois | +4.370 |
ioxide | +4.352 |
ophobia | +4.335 |
Neg logit contributions | |
◼ | -5.024 |
lisher | -4.954 |
ting | -4.906 |
ITNESS | -4.697 |
rend | -4.677 |
Token | uring |
Token ID | 870 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
iv | +2.795 |
uve | +2.787 |
uses | +2.738 |
ioxide | +2.714 |
uum | +2.713 |
Neg logit contributions | |
◼ | -4.055 |
ting | -3.979 |
lisher | -3.934 |
ITNESS | -3.845 |
rend | -3.793 |
Token | is |
Token ID | 318 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
uses | +5.647 |
uve | +5.585 |
iv | +5.520 |
ourgeois | +5.452 |
ophobia | +5.448 |
Neg logit contributions | |
◼ | -7.089 |
lisher | -6.871 |
ting | -6.824 |
rend | -6.582 |
ITNESS | -6.544 |
Token | made |
Token ID | 925 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
uses | +6.312 |
uve | +6.279 |
iv | +6.231 |
PF | +6.199 |
pour | +6.159 |
Neg logit contributions | |
◼ | -7.968 |
ting | -7.910 |
lisher | -7.751 |
rend | -7.561 |
ITNESS | -7.546 |
Token | available |
Token ID | 1695 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ting | +0.988 |
◼ | +0.914 |
lisher | +0.897 |
rend | +0.886 |
tto | +0.847 |
Neg logit contributions | |
ioxide | -1.242 |
uve | -1.232 |
ourgeois | -1.213 |
ophobia | -1.198 |
PF | -1.191 |
Token | to |
Token ID | 284 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ioxide | +0.886 |
uve | +0.882 |
ourgeois | +0.866 |
iv | +0.858 |
ophobia | +0.854 |
Neg logit contributions | |
ting | -0.906 |
◼ | -0.864 |
lisher | -0.849 |
rend | -0.834 |
ITNESS | -0.811 |
Token | low |
Token ID | 1877 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
uve | +3.204 |
ioxide | +3.148 |
ourgeois | +3.124 |
iv | +3.114 |
PF | +3.072 |
Neg logit contributions | |
ting | -4.971 |
◼ | -4.957 |
rend | -4.859 |
lisher | -4.813 |
ITNESS | -4.642 |
Token | - |
Token ID | 12 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
occupancy | +6.835 |
ioxide | +6.600 |
iv | +6.165 |
uve | +6.156 |
uses | +6.029 |
Neg logit contributions | |
lisher | -15.134 |
ITNESS | -14.936 |
ting | -14.612 |
tto | -14.442 |
◼ | -14.396 |
Token | income |
Token ID | 12519 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
iv | +8.848 |
pour | +8.822 |
PF | +8.463 |
ioxide | +8.329 |
uses | +8.306 |
Neg logit contributions | |
ITNESS | -16.290 |
lisher | -16.164 |
◼ | -16.135 |
ting | -15.327 |
tto | -15.232 |
Token | residents |
Token ID | 5085 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
iv | +4.504 |
uve | +4.465 |
ives | +4.417 |
ourgeois | +4.409 |
uses | +4.365 |
Neg logit contributions | |
◼ | -10.936 |
ting | -10.842 |
lisher | -10.765 |
ITNESS | -10.749 |
rend | -10.632 |
Token | and |
Token ID | 290 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
uve | +3.649 |
iv | +3.628 |
ioxide | +3.537 |
ourgeois | +3.532 |
pour | +3.522 |
Neg logit contributions | |
ting | -5.050 |
◼ | -4.992 |
lisher | -4.919 |
ITNESS | -4.870 |
rend | -4.806 |
Token | other |
Token ID | 584 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
uve | +2.817 |
ourgeois | +2.783 |
ioxide | +2.764 |
iv | +2.747 |
PF | +2.732 |
Neg logit contributions | |
ting | -3.657 |
◼ | -3.603 |
rend | -3.505 |
lisher | -3.502 |
ITNESS | -3.404 |
Token | eligible |
Token ID | 8867 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
uve | +3.446 |
ourgeois | +3.385 |
ioxide | +3.328 |
iv | +3.315 |
PF | +3.286 |
Neg logit contributions | |
ting | -5.103 |
◼ | -5.012 |
rend | -4.975 |
lisher | -4.908 |
ITNESS | -4.811 |
Token | ( |
Token ID | 357 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ioxide | +0.076 |
uve | +0.076 |
ourgeois | +0.074 |
iv | +0.073 |
ophobia | +0.073 |
Neg logit contributions | |
ting | -0.095 |
◼ | -0.090 |
lisher | -0.089 |
rend | -0.087 |
ITNESS | -0.085 |
Token | Fun |
Token ID | 24629 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
uve | +2.180 |
PF | +2.179 |
ioxide | +2.177 |
iv | +2.167 |
uses | +2.122 |
Neg logit contributions | |
ting | -2.701 |
lisher | -2.586 |
◼ | -2.563 |
rend | -2.502 |
ITNESS | -2.448 |
Token | fact |
Token ID | 1109 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
uum | +4.617 |
iv | +4.603 |
ivan | +4.565 |
pour | +4.507 |
ourgeois | +4.501 |
Neg logit contributions | |
◼ | -5.062 |
ting | -4.910 |
lisher | -4.791 |
rend | -4.701 |
ITNESS | -4.641 |
Token | : |
Token ID | 25 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ioxide | +3.007 |
iv | +2.975 |
uve | +2.932 |
ourgeois | +2.925 |
uses | +2.900 |
Neg logit contributions | |
◼ | -5.701 |
ting | -5.646 |
lisher | -5.513 |
rend | -5.431 |
ITNESS | -5.349 |
Token | Gu |
Token ID | 1962 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ioxide | +1.607 |
uve | +1.589 |
ourgeois | +1.565 |
iv | +1.548 |
uum | +1.539 |
Neg logit contributions | |
ting | -2.097 |
◼ | -2.043 |
lisher | -2.004 |
rend | -1.965 |
ITNESS | -1.930 |
Token | illa |
Token ID | 5049 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
uve | +3.350 |
ioxide | +3.314 |
iv | +3.159 |
ivan | +3.118 |
ourgeois | +3.035 |
Neg logit contributions | |
ting | -10.104 |
◼ | -9.966 |
lisher | -9.742 |
ITNESS | -9.619 |
rend | -9.551 |
Token | ume |
Token ID | 2454 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
uve | +7.872 |
uum | +7.768 |
uses | +7.528 |
ioxide | +7.527 |
iv | +7.166 |
Neg logit contributions | |
◼ | -20.058 |
skelet | -19.630 |
ting | -18.556 |
lisher | -18.397 |
ITNESS | -18.261 |
Token | is |
Token ID | 318 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
uve | +5.458 |
iv | +5.453 |
ophobia | +5.322 |
uses | +5.259 |
ivan | +5.215 |
Neg logit contributions | |
◼ | -8.028 |
ITNESS | -7.901 |
lisher | -7.828 |
ting | -7.805 |
rend | -7.562 |
Token | also |
Token ID | 635 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
ioxide | +3.107 |
uve | +3.070 |
iv | +3.047 |
ourgeois | +3.036 |
uses | +3.026 |
Neg logit contributions | |
ting | -3.976 |
◼ | -3.849 |
lisher | -3.769 |
rend | -3.726 |
ITNESS | -3.688 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
iv | +4.523 |
ioxide | +4.500 |
uses | +4.475 |
uve | +4.461 |
PF | +4.423 |
Neg logit contributions | |
ting | -5.818 |
◼ | -5.657 |
lisher | -5.502 |
ITNESS | -5.435 |
rend | -5.427 |
Token | only |
Token ID | 691 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
ting | +4.265 |
lisher | +3.953 |
◼ | +3.921 |
rend | +3.886 |
tto | +3.704 |
Neg logit contributions | |
ioxide | -4.037 |
uve | -4.002 |
ourgeois | -3.950 |
ophobia | -3.877 |
PF | -3.861 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
iv | +8.368 |
uve | +8.126 |
pour | +8.084 |
ives | +8.057 |
uses | +7.851 |
Neg logit contributions | |
ting | -11.098 |
◼ | -11.006 |
ITNESS | -10.919 |
tto | -10.784 |
lisher | -10.722 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
uve | +7.611 |
iv | +7.414 |
uses | +7.276 |
pour | +7.125 |
Pour | +7.113 |
Neg logit contributions | |
lisher | -11.745 |
ting | -11.706 |
◼ | -11.504 |
ITNESS | -11.454 |
tto | -11.328 |
Token | 1 |
Token ID | 352 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
uve | +5.298 |
iv | +5.036 |
pour | +4.967 |
PF | +4.882 |
uses | +4.838 |
Neg logit contributions | |
◼ | -10.511 |
ting | -10.332 |
lisher | -10.043 |
ITNESS | -9.948 |
tto | -9.944 |
Token | . |
Token ID | 13 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
uve | +4.169 |
iv | +4.022 |
ourgeois | +3.955 |
uses | +3.928 |
ioxide | +3.918 |
Neg logit contributions | |
ting | -6.778 |
◼ | -6.427 |
lisher | -6.400 |
tto | -6.286 |
ITNESS | -6.275 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
iv | +3.396 |
ioxide | +3.206 |
uve | +3.187 |
PF | +2.993 |
ivan | +2.938 |
Neg logit contributions | |
◼ | -11.377 |
ting | -11.357 |
lisher | -11.074 |
ITNESS | -10.807 |
tto | -10.635 |
Token | rating |
Token ID | 7955 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
uve | +7.013 |
iv | +6.678 |
pour | +6.515 |
uum | +6.481 |
PF | +6.415 |
Neg logit contributions | |
ting | -9.450 |
◼ | -9.117 |
ITNESS | -9.056 |
lisher | -9.019 |
tto | -8.894 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
uve | +11.299 |
iv | +10.780 |
rating | +10.587 |
pour | +10.454 |
uum | +10.262 |
Neg logit contributions | |
ting | -13.649 |
◼ | -13.610 |
ITNESS | -13.581 |
lisher | -13.280 |
tto | -13.059 |
Token | The |
Token ID | 383 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
uve | +9.082 |
ourgeois | +8.889 |
uum | +8.886 |
iv | +8.862 |
uses | +8.755 |
Neg logit contributions | |
ITNESS | -9.082 |
◼ | -8.942 |
ting | -8.820 |
lisher | -8.758 |
rend | -8.581 |
Token | Americans |
Token ID | 3399 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ioxide | +1.939 |
uve | +1.901 |
iv | +1.889 |
ophobia | +1.874 |
ourgeois | +1.846 |
Neg logit contributions | |
ting | -2.708 |
◼ | -2.614 |
lisher | -2.562 |
rend | -2.493 |
ITNESS | -2.439 |
Token | � |
Token ID | 447 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
uve | +8.028 |
iv | +7.789 |
pour | +7.781 |
uses | +7.718 |
uum | +7.630 |
Neg logit contributions | |
lisher | -8.879 |
ITNESS | -8.869 |
◼ | -8.817 |
ting | -8.802 |
tto | -8.445 |
Token | � |
Token ID | 247 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ioxide | +1.588 |
uve | +1.577 |
ourgeois | +1.525 |
PF | +1.515 |
uum | +1.514 |
Neg logit contributions | |
ting | -2.207 |
◼ | -2.099 |
lisher | -2.074 |
rend | -2.041 |
ITNESS | -1.988 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ting | +2.559 |
rend | +2.190 |
◼ | +2.159 |
lisher | +2.156 |
ted | +2.101 |
Neg logit contributions | |
ioxide | -4.245 |
ourgeois | -4.194 |
uve | -4.142 |
ivan | -4.081 |
ophobia | -4.078 |
Token | on |
Token ID | 319 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
iv | +3.299 |
ives | +3.115 |
uses | +2.709 |
pour | +2.693 |
uve | +2.557 |
Neg logit contributions | |
skelet | -20.655 |
◼ | -19.589 |
ITNESS | -19.216 |
lisher | -19.184 |
ccording | -18.469 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
iv | +4.258 |
PF | +4.076 |
ophobia | +4.025 |
ioxide | +3.958 |
ives | +3.956 |
Neg logit contributions | |
◼ | -11.502 |
ting | -11.433 |
ITNESS | -11.395 |
skelet | -11.339 |
lisher | -11.303 |
Token | Share |
Token ID | 8734 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
uve | +3.396 |
iv | +3.278 |
ioxide | +3.278 |
ophobia | +3.246 |
uses | +3.232 |
Neg logit contributions | |
◼ | -5.822 |
ting | -5.777 |
lisher | -5.729 |
ITNESS | -5.443 |
rend | -5.442 |
Token | this |
Token ID | 428 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
uve | +3.967 |
uses | +3.791 |
PF | +3.747 |
ioxide | +3.746 |
ives | +3.741 |
Neg logit contributions | |
◼ | -10.589 |
lisher | -10.370 |
ITNESS | -10.355 |
skelet | -10.174 |
ting | -10.054 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ting | +2.145 |
rend | +1.852 |
◼ | +1.839 |
lisher | +1.821 |
ted | +1.778 |
Neg logit contributions | |
ioxide | -3.434 |
ourgeois | -3.383 |
uve | -3.357 |
ophobia | -3.292 |
ivan | -3.291 |
Token | on |
Token ID | 319 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
iv | +4.618 |
ives | +4.367 |
uses | +4.136 |
pour | +4.034 |
upon | +3.955 |
Neg logit contributions | |
skelet | -22.401 |
◼ | -20.702 |
ITNESS | -20.538 |
ccording | -20.414 |
lisher | -20.199 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ting | +2.573 |
◼ | +2.364 |
lisher | +2.342 |
rend | +2.339 |
ted | +2.288 |
Neg logit contributions | |
ioxide | -1.901 |
uve | -1.891 |
ourgeois | -1.883 |
ophobia | -1.808 |
PF | -1.797 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ting | +0.326 |
◼ | +0.309 |
lisher | +0.304 |
rend | +0.299 |
ITNESS | +0.288 |
Neg logit contributions | |
ioxide | -0.308 |
uve | -0.306 |
ourgeois | -0.300 |
ophobia | -0.297 |
PF | -0.297 |
Token |
|
Token ID | 198 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ting | +2.187 |
◼ | +1.951 |
rend | +1.946 |
lisher | +1.898 |
tto | +1.861 |
Neg logit contributions | |
ioxide | -2.682 |
ourgeois | -2.662 |
uve | -2.635 |
uum | -2.553 |
anguage | -2.547 |
Token | NY |
Token ID | 12805 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ting | +6.544 |
◼ | +6.182 |
rend | +5.976 |
lisher | +5.873 |
ted | +5.802 |
Neg logit contributions | |
ioxide | -5.831 |
uve | -5.691 |
ourgeois | -5.689 |
ophobia | -5.513 |
uum | -5.418 |
Token | provide |
Token ID | 2148 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ting | +3.726 |
lisher | +3.304 |
rend | +3.259 |
◼ | +3.238 |
ted | +3.192 |
Neg logit contributions | |
uve | -3.742 |
ioxide | -3.736 |
ourgeois | -3.597 |
uum | -3.579 |
PF | -3.547 |
Token | more |
Token ID | 517 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ting | +2.628 |
◼ | +2.439 |
lisher | +2.435 |
rend | +2.372 |
tto | +2.316 |
Neg logit contributions | |
ioxide | -2.221 |
uve | -2.182 |
ourgeois | -2.136 |
ivan | -2.105 |
ophobia | -2.100 |
Token | benefits |
Token ID | 4034 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ting | +2.103 |
◼ | +1.963 |
lisher | +1.945 |
rend | +1.908 |
ITNESS | +1.855 |
Neg logit contributions | |
ioxide | -1.833 |
uve | -1.813 |
ourgeois | -1.775 |
ivan | -1.746 |
PF | -1.744 |
Token | for |
Token ID | 329 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
iv | +2.992 |
uve | +2.980 |
ourgeois | +2.963 |
ioxide | +2.920 |
ophobia | +2.919 |
Neg logit contributions | |
ting | -4.255 |
◼ | -4.156 |
lisher | -4.139 |
rend | -4.043 |
ITNESS | -4.033 |
Token | low |
Token ID | 1877 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uve | +1.242 |
ourgeois | +1.227 |
ioxide | +1.227 |
iv | +1.205 |
ophobia | +1.190 |
Neg logit contributions | |
ting | -1.727 |
◼ | -1.694 |
rend | -1.653 |
lisher | -1.647 |
ITNESS | -1.599 |
Token | - |
Token ID | 12 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
iv | +5.361 |
ioxide | +5.327 |
uses | +5.230 |
ourgeois | +5.202 |
envelope | +5.165 |
Neg logit contributions | |
ITNESS | -13.752 |
◼ | -13.639 |
lisher | -13.498 |
ting | -13.234 |
rend | -13.144 |
Token | income |
Token ID | 12519 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
iv | +8.571 |
uses | +8.447 |
pour | +8.315 |
PF | +8.187 |
eth | +8.059 |
Neg logit contributions | |
◼ | -16.608 |
ITNESS | -16.286 |
lisher | -15.421 |
Somers | -14.815 |
tto | -14.733 |
Token | and |
Token ID | 290 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ourgeois | +3.779 |
iv | +3.647 |
uses | +3.612 |
ives | +3.612 |
uve | +3.610 |
Neg logit contributions | |
◼ | -8.808 |
ting | -8.621 |
ITNESS | -8.613 |
lisher | -8.580 |
rend | -8.575 |
Token | middle |
Token ID | 3504 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
ourgeois | +1.414 |
uve | +1.408 |
ioxide | +1.402 |
iv | +1.385 |
ophobia | +1.372 |
Neg logit contributions | |
ting | -1.936 |
◼ | -1.915 |
lisher | -1.862 |
rend | -1.859 |
ITNESS | -1.805 |
Token | - |
Token ID | 12 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
uve | +4.832 |
iv | +4.626 |
ioxide | +4.542 |
uses | +4.504 |
ourgeois | +4.491 |
Neg logit contributions | |
lisher | -10.033 |
ting | -9.981 |
◼ | -9.780 |
ITNESS | -9.609 |
tto | -9.549 |
Token | class |
Token ID | 4871 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
uses | +4.437 |
uve | +4.310 |
iv | +4.195 |
ourgeois | +4.164 |
pour | +3.977 |
Neg logit contributions | |
◼ | -13.491 |
ITNESS | -13.319 |
lisher | -13.145 |
ting | -12.778 |
tto | -12.629 |
Token | 's |
Token ID | 338 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ting | +2.020 |
◼ | +1.898 |
lisher | +1.868 |
rend | +1.850 |
ITNESS | +1.778 |
Neg logit contributions | |
ioxide | -1.855 |
uve | -1.837 |
ourgeois | -1.806 |
ophobia | -1.772 |
PF | -1.771 |
Token | Counter |
Token ID | 15034 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ting | +3.754 |
◼ | +3.488 |
lisher | +3.452 |
rend | +3.428 |
ITNESS | +3.301 |
Neg logit contributions | |
ioxide | -3.265 |
uve | -3.209 |
ourgeois | -3.167 |
ophobia | -3.089 |
PF | -3.083 |
Token | - |
Token ID | 12 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ting | +3.148 |
◼ | +2.913 |
rend | +2.842 |
lisher | +2.835 |
ted | +2.757 |
Neg logit contributions | |
ioxide | -2.557 |
ourgeois | -2.507 |
uve | -2.475 |
uum | -2.441 |
ophobia | -2.438 |
Token | Strike |
Token ID | 31584 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ting | +2.574 |
◼ | +2.392 |
rend | +2.331 |
lisher | +2.325 |
ted | +2.251 |
Neg logit contributions | |
ioxide | -2.523 |
uve | -2.473 |
ourgeois | -2.472 |
ophobia | -2.422 |
ivan | -2.401 |
Token | are |
Token ID | 389 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ting | +4.665 |
◼ | +4.236 |
lisher | +4.189 |
rend | +4.177 |
tto | +4.054 |
Neg logit contributions | |
ioxide | -3.930 |
uve | -3.842 |
ourgeois | -3.790 |
PF | -3.747 |
uum | -3.704 |
Token | caused |
Token ID | 4073 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ting | +4.258 |
◼ | +3.896 |
lisher | +3.845 |
rend | +3.781 |
ted | +3.707 |
Neg logit contributions | |
ioxide | -4.034 |
uve | -4.014 |
ourgeois | -3.932 |
uum | -3.866 |
iv | -3.832 |
Token | by |
Token ID | 416 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ting | +7.065 |
◼ | +5.712 |
ted | +5.685 |
lisher | +5.513 |
rend | +5.479 |
Neg logit contributions | |
uve | -12.478 |
ioxide | -12.279 |
ourgeois | -12.112 |
uum | -11.942 |
anguage | -11.832 |
Token | two |
Token ID | 734 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
uve | +0.939 |
ioxide | +0.938 |
ourgeois | +0.915 |
ophobia | +0.911 |
uses | +0.906 |
Neg logit contributions | |
ting | -1.184 |
◼ | -1.151 |
lisher | -1.120 |
rend | -1.110 |
ITNESS | -1.075 |
Token | magical |
Token ID | 10883 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ting | +3.215 |
◼ | +2.955 |
lisher | +2.914 |
rend | +2.881 |
ted | +2.779 |
Neg logit contributions | |
ioxide | -3.290 |
uve | -3.262 |
ourgeois | -3.213 |
uum | -3.134 |
ivan | -3.132 |
Token | words |
Token ID | 2456 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ting | +3.257 |
◼ | +3.061 |
lisher | +2.990 |
rend | +2.964 |
ITNESS | +2.856 |
Neg logit contributions | |
ioxide | -2.961 |
uve | -2.943 |
ourgeois | -2.872 |
uum | -2.798 |
PF | -2.793 |
Token | - |
Token ID | 532 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
iv | +2.852 |
ioxide | +2.846 |
ophobia | +2.826 |
uve | +2.818 |
uses | +2.797 |
Neg logit contributions | |
ting | -4.210 |
◼ | -4.147 |
lisher | -4.052 |
rend | -4.003 |
ITNESS | -3.921 |
Token | running |
Token ID | 2491 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
ting | +4.933 |
◼ | +4.400 |
rend | +4.349 |
lisher | +4.346 |
tto | +4.283 |
Neg logit contributions | |
ioxide | -4.462 |
uve | -4.343 |
ourgeois | -4.330 |
PF | -4.186 |
ophobia | -4.169 |
Token | , |
Token ID | 11 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
ting | +7.186 |
ted | +6.243 |
tto | +6.197 |
rend | +6.138 |
lisher | +6.137 |
Neg logit contributions | |
ioxide | -6.998 |
ourgeois | -6.757 |
uve | -6.576 |
ivan | -6.488 |
itement | -6.451 |
Token | pl |
Token ID | 458 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ting | +7.714 |
◼ | +6.606 |
ted | +6.571 |
tering | +6.552 |
tto | +6.535 |
Neg logit contributions | |
ioxide | -6.956 |
ourgeois | -6.655 |
uve | -6.596 |
ivan | -6.447 |
PF | -6.425 |
Token | anking |
Token ID | 15230 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
ting | +1.975 |
◼ | +1.842 |
lisher | +1.834 |
rend | +1.825 |
tto | +1.757 |
Neg logit contributions | |
ioxide | -1.492 |
uve | -1.461 |
ourgeois | -1.436 |
PF | -1.422 |
ophobia | -1.401 |
Token | and |
Token ID | 290 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ting | +4.753 |
lisher | +4.195 |
rend | +4.166 |
◼ | +4.163 |
ted | +4.098 |
Neg logit contributions | |
ioxide | -4.694 |
uve | -4.541 |
ourgeois | -4.452 |
ivan | -4.421 |
ophobia | -4.405 |
Token | lung |
Token ID | 12317 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ting | +4.941 |
◼ | +4.437 |
lisher | +4.390 |
rend | +4.339 |
tto | +4.291 |
Neg logit contributions | |
ioxide | -4.357 |
uve | -4.251 |
ourgeois | -4.205 |
PF | -4.107 |
ivan | -4.096 |
Token | es |
Token ID | 274 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ting | +7.097 |
ted | +5.721 |
tering | +5.389 |
rend | +5.373 |
lisher | +5.338 |
Neg logit contributions | |
ioxide | -10.612 |
ourgeois | -10.392 |
uve | -10.230 |
PF | -10.115 |
anguage | -9.931 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ting | +2.497 |
◼ | +2.309 |
lisher | +2.283 |
rend | +2.262 |
tto | +2.196 |
Neg logit contributions | |
ioxide | -2.221 |
uve | -2.193 |
ourgeois | -2.159 |
PF | -2.112 |
ivan | -2.105 |
Token | ( |
Token ID | 357 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ting | +2.713 |
◼ | +2.515 |
lisher | +2.493 |
rend | +2.480 |
tto | +2.409 |
Neg logit contributions | |
ioxide | -2.382 |
uve | -2.355 |
ourgeois | -2.315 |
PF | -2.270 |
ophobia | -2.262 |
Token | Wa |
Token ID | 33484 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
uve | +1.634 |
ioxide | +1.630 |
iv | +1.622 |
PF | +1.608 |
ivan | +1.589 |
Neg logit contributions | |
ting | -2.563 |
◼ | -2.453 |
lisher | -2.446 |
rend | -2.406 |
ITNESS | -2.335 |
Token | ub |
Token ID | 549 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
uve | +2.633 |
ioxide | +2.632 |
uum | +2.553 |
ourgeois | +2.524 |
iv | +2.524 |
Neg logit contributions | |
ting | -3.919 |
◼ | -3.852 |
lisher | -3.739 |
rend | -3.629 |
ITNESS | -3.594 |
Token | pursue |
Token ID | 10660 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ting | +4.321 |
◼ | +3.955 |
lisher | +3.949 |
rend | +3.922 |
ted | +3.772 |
Neg logit contributions | |
ioxide | -3.587 |
uve | -3.569 |
ourgeois | -3.439 |
PF | -3.390 |
ophobia | -3.377 |
Token | dis |
Token ID | 595 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ting | +6.230 |
◼ | +5.680 |
rend | +5.642 |
lisher | +5.632 |
tto | +5.457 |
Neg logit contributions | |
ioxide | -4.643 |
uve | -4.437 |
ourgeois | -4.292 |
ivan | -4.260 |
PF | -4.213 |
Token | aff |
Token ID | 2001 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
uve | +2.251 |
ioxide | +2.232 |
ourgeois | +2.203 |
iv | +2.202 |
uses | +2.196 |
Neg logit contributions | |
ting | -3.482 |
◼ | -3.397 |
lisher | -3.310 |
rend | -3.237 |
ITNESS | -3.228 |
Token | iliation |
Token ID | 15547 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ting | +1.757 |
lisher | +1.489 |
rend | +1.452 |
◼ | +1.362 |
tto | +1.296 |
Neg logit contributions | |
uve | -4.509 |
ioxide | -4.493 |
PF | -4.484 |
ourgeois | -4.431 |
uum | -4.370 |
Token | was |
Token ID | 373 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ting | +0.901 |
◼ | +0.847 |
lisher | +0.834 |
rend | +0.825 |
tto | +0.793 |
Neg logit contributions | |
ioxide | -0.804 |
uve | -0.795 |
ourgeois | -0.780 |
PF | -0.767 |
ophobia | -0.765 |
Token | mostly |
Token ID | 4632 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ting | +4.265 |
◼ | +3.928 |
lisher | +3.873 |
rend | +3.839 |
ted | +3.742 |
Neg logit contributions | |
ioxide | -4.110 |
uve | -3.989 |
ourgeois | -3.927 |
uum | -3.891 |
PF | -3.885 |
Token | unanimous |
Token ID | 28085 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ting | +9.238 |
◼ | +8.199 |
ted | +8.083 |
lisher | +8.020 |
rend | +8.002 |
Neg logit contributions | |
ioxide | -9.927 |
uum | -9.262 |
PF | -9.196 |
uve | -9.082 |
itement | -9.077 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ting | +1.518 |
◼ | +1.429 |
lisher | +1.408 |
rend | +1.393 |
ITNESS | +1.342 |
Neg logit contributions | |
ioxide | -1.342 |
uve | -1.327 |
ourgeois | -1.301 |
PF | -1.278 |
ophobia | -1.275 |
Token | Brooks |
Token ID | 17704 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ting | +2.411 |
◼ | +2.242 |
lisher | +2.224 |
rend | +2.191 |
ITNESS | +2.123 |
Neg logit contributions | |
ioxide | -2.108 |
uve | -2.085 |
ourgeois | -2.037 |
PF | -2.004 |
ophobia | -2.001 |
Token | Ald |
Token ID | 15586 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
ting | +1.025 |
◼ | +0.965 |
lisher | +0.949 |
rend | +0.937 |
ITNESS | +0.903 |
Neg logit contributions | |
ioxide | -1.022 |
uve | -1.015 |
ourgeois | -0.997 |
ophobia | -0.981 |
PF | -0.980 |
Token | erman |
Token ID | 2224 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ting | +0.701 |
◼ | +0.658 |
lisher | +0.647 |
rend | +0.638 |
ITNESS | +0.613 |
Neg logit contributions | |
ioxide | -0.770 |
uve | -0.765 |
ourgeois | -0.752 |
ophobia | -0.741 |
PF | -0.740 |
Token | , |
Token ID | 11 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ting | +4.544 |
◼ | +4.285 |
rend | +4.164 |
lisher | +4.129 |
ITNESS | +4.039 |
Neg logit contributions | |
ioxide | -4.105 |
uve | -4.049 |
ourgeois | -4.003 |
PF | -3.889 |
uum | -3.851 |
Token | right |
Token ID | 826 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ting | +3.241 |
◼ | +3.049 |
lisher | +2.979 |
rend | +2.977 |
ITNESS | +2.880 |
Neg logit contributions | |
ioxide | -2.706 |
uve | -2.677 |
ourgeois | -2.631 |
PF | -2.566 |
uum | -2.552 |
Token | now |
Token ID | 783 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ting | +5.334 |
◼ | +4.839 |
rend | +4.799 |
lisher | +4.675 |
ted | +4.591 |
Neg logit contributions | |
ioxide | -5.729 |
ourgeois | -5.595 |
uve | -5.535 |
PF | -5.395 |
uum | -5.332 |
Token | in |
Token ID | 287 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
ting | +5.580 |
◼ | +5.134 |
rend | +5.054 |
lisher | +4.921 |
ITNESS | +4.835 |
Neg logit contributions | |
ioxide | -5.568 |
uve | -5.530 |
ourgeois | -5.421 |
PF | -5.309 |
uum | -5.251 |
Token | my |
Token ID | 616 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ioxide | +0.297 |
uve | +0.294 |
ourgeois | +0.286 |
iv | +0.284 |
ophobia | +0.283 |
Neg logit contributions | |
ting | -0.518 |
◼ | -0.497 |
lisher | -0.493 |
rend | -0.483 |
ITNESS | -0.471 |
Token | life |
Token ID | 1204 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ting | +3.876 |
◼ | +3.651 |
lisher | +3.531 |
rend | +3.512 |
ted | +3.390 |
Neg logit contributions | |
ioxide | -3.656 |
uve | -3.594 |
ourgeois | -3.532 |
PF | -3.433 |
ophobia | -3.419 |
Token | , |
Token ID | 11 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
ting | +8.997 |
rend | +8.221 |
◼ | +8.161 |
lisher | +7.723 |
ted | +7.699 |
Neg logit contributions | |
ioxide | -10.040 |
uve | -9.719 |
ourgeois | -9.710 |
PF | -9.559 |
uum | -9.373 |
Token | I |
Token ID | 314 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ting | +4.639 |
◼ | +4.336 |
rend | +4.244 |
lisher | +4.185 |
ITNESS | +4.088 |
Neg logit contributions | |
ioxide | -4.082 |
uve | -4.036 |
ourgeois | -3.975 |
PF | -3.885 |
uum | -3.844 |
Token | don |
Token ID | 836 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ting | +5.019 |
◼ | +4.559 |
rend | +4.540 |
lisher | +4.472 |
tto | +4.415 |
Neg logit contributions | |
ioxide | -4.843 |
uve | -4.776 |
ourgeois | -4.771 |
PF | -4.689 |
uum | -4.567 |
Token | � |
Token ID | 447 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
uve | +2.052 |
ioxide | +2.051 |
iv | +2.025 |
ophobia | +2.002 |
uses | +2.000 |
Neg logit contributions | |
ting | -1.828 |
◼ | -1.746 |
lisher | -1.736 |
rend | -1.666 |
ITNESS | -1.634 |
Token | � |
Token ID | 247 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ioxide | +1.489 |
uve | +1.487 |
ourgeois | +1.445 |
iv | +1.438 |
uum | +1.436 |
Neg logit contributions | |
ting | -1.407 |
◼ | -1.325 |
lisher | -1.308 |
rend | -1.276 |
ITNESS | -1.241 |
Token | � |
Token ID | 251 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ioxide | +2.580 |
uve | +2.544 |
iv | +2.485 |
PF | +2.485 |
uum | +2.475 |
Neg logit contributions | |
ting | -2.564 |
◼ | -2.425 |
lisher | -2.417 |
rend | -2.348 |
ITNESS | -2.262 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ioxide | +0.286 |
uve | +0.285 |
iv | +0.279 |
ourgeois | +0.279 |
ophobia | +0.276 |
Neg logit contributions | |
ting | -0.320 |
◼ | -0.303 |
lisher | -0.300 |
rend | -0.294 |
ITNESS | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ioxide | +1.794 |
uve | +1.790 |
iv | +1.764 |
ophobia | +1.742 |
PF | +1.741 |
Neg logit contributions | |
ting | -2.051 |
◼ | -1.986 |
lisher | -1.958 |
rend | -1.899 |
ITNESS | -1.877 |
Token | And |
Token ID | 1870 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
iv | +2.063 |
PF | +2.052 |
uve | +2.048 |
uses | +2.024 |
ioxide | +2.020 |
Neg logit contributions | |
ting | -2.623 |
lisher | -2.490 |
◼ | -2.461 |
rend | -2.415 |
ITNESS | -2.392 |
Token | then |
Token ID | 788 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
ioxide | +0.738 |
uve | +0.737 |
ourgeois | +0.721 |
iv | +0.715 |
uses | +0.710 |
Neg logit contributions | |
ting | -0.906 |
◼ | -0.869 |
lisher | -0.850 |
rend | -0.838 |
ITNESS | -0.816 |
Token | there |
Token ID | 612 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ioxide | +0.567 |
uve | +0.565 |
ourgeois | +0.554 |
iv | +0.549 |
ophobia | +0.546 |
Neg logit contributions | |
ting | -0.574 |
◼ | -0.547 |
lisher | -0.536 |
rend | -0.526 |
ITNESS | -0.511 |
Token | � |
Token ID | 447 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ting | +7.820 |
rend | +7.021 |
◼ | +6.933 |
lisher | +6.639 |
tto | +6.569 |
Neg logit contributions | |
ioxide | -10.014 |
ourgeois | -9.580 |
uve | -9.503 |
PF | -9.371 |
ivan | -9.303 |
Token | � |
Token ID | 247 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
ting | +0.139 |
◼ | +0.130 |
lisher | +0.128 |
rend | +0.126 |
ITNESS | +0.122 |
Neg logit contributions | |
ioxide | -0.149 |
uve | -0.148 |
ourgeois | -0.147 |
ophobia | -0.144 |
iv | -0.143 |
Token | s |
Token ID | 82 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ioxide | +0.047 |
uve | +0.047 |
ourgeois | +0.046 |
iv | +0.046 |
uses | +0.045 |
Neg logit contributions | |
ting | -0.045 |
◼ | -0.042 |
lisher | -0.042 |
rend | -0.041 |
ITNESS | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
ioxide | +0.243 |
uve | +0.242 |
ourgeois | +0.238 |
iv | +0.235 |
ophobia | +0.234 |
Neg logit contributions | |
ting | -0.278 |
◼ | -0.266 |
lisher | -0.261 |
rend | -0.257 |
ITNESS | -0.250 |
Token | tunnel |
Token ID | 13275 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
ting | +0.829 |
◼ | +0.789 |
lisher | +0.777 |
rend | +0.766 |
ITNESS | +0.743 |
Neg logit contributions | |
ioxide | -0.640 |
uve | -0.635 |
ourgeois | -0.623 |
ophobia | -0.611 |
iv | -0.610 |
Token | ted |
Token ID | 1513 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ting | +1.142 |
ted | +0.523 |
rend | -0.287 |
tto | -0.500 |
lisher | -0.610 |
Neg logit contributions | |
ioxide | -15.313 |
ourgeois | -14.842 |
anguage | -14.759 |
ophobia | -14.755 |
uve | -14.703 |
Token | the |
Token ID | 262 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
iv | +3.403 |
uve | +3.394 |
ourgeois | +3.336 |
uses | +3.316 |
ophobia | +3.306 |
Neg logit contributions | |
◼ | -5.367 |
ting | -5.308 |
lisher | -5.175 |
rend | -5.106 |
ITNESS | -5.059 |
Token | nation |
Token ID | 3277 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
uve | +2.868 |
ioxide | +2.838 |
ourgeois | +2.776 |
iv | +2.775 |
ophobia | +2.765 |
Neg logit contributions | |
ting | -4.459 |
◼ | -4.385 |
lisher | -4.263 |
rend | -4.204 |
ITNESS | -4.188 |
Token | largely |
Token ID | 5688 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ioxide | +0.387 |
uve | +0.387 |
ourgeois | +0.377 |
ophobia | +0.373 |
iv | +0.373 |
Neg logit contributions | |
ting | -0.469 |
◼ | -0.447 |
lisher | -0.440 |
rend | -0.433 |
ITNESS | -0.423 |
Token | because |
Token ID | 780 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
ting | +1.163 |
◼ | +1.105 |
lisher | +1.091 |
rend | +1.081 |
ITNESS | +1.045 |
Neg logit contributions | |
ioxide | -0.720 |
uve | -0.710 |
ourgeois | -0.694 |
PF | -0.678 |
ophobia | -0.676 |
Token | it |
Token ID | 340 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ting | +0.013 |
◼ | +0.013 |
lisher | +0.013 |
rend | +0.012 |
ITNESS | +0.012 |
Neg logit contributions | |
ioxide | -0.011 |
uve | -0.011 |
ourgeois | -0.010 |
ophobia | -0.010 |
iv | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ting | +1.982 |
◼ | +1.846 |
lisher | +1.820 |
rend | +1.810 |
tto | +1.723 |
Neg logit contributions | |
ioxide | -1.955 |
uve | -1.916 |
ourgeois | -1.897 |
PF | -1.860 |
ophobia | -1.850 |
Token | seen |
Token ID | 1775 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
uve | +1.962 |
ioxide | +1.919 |
iv | +1.901 |
uum | +1.891 |
ourgeois | +1.885 |
Neg logit contributions | |
ting | -2.411 |
◼ | -2.327 |
lisher | -2.282 |
rend | -2.238 |
ITNESS | -2.206 |
Token | as |
Token ID | 355 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ting | +2.365 |
◼ | +2.181 |
lisher | +2.134 |
rend | +2.133 |
tto | +2.022 |
Neg logit contributions | |
ioxide | -2.871 |
uve | -2.838 |
ourgeois | -2.798 |
PF | -2.749 |
ophobia | -2.736 |
Token | contributing |
Token ID | 14329 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ting | +3.139 |
◼ | +2.927 |
lisher | +2.882 |
rend | +2.873 |
tto | +2.762 |
Neg logit contributions | |
ioxide | -2.553 |
uve | -2.529 |
ourgeois | -2.476 |
PF | -2.420 |
ophobia | -2.418 |
Token | to |
Token ID | 284 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
ting | +3.387 |
◼ | +3.129 |
rend | +3.074 |
lisher | +3.074 |
ITNESS | +2.965 |
Neg logit contributions | |
uve | -3.484 |
ioxide | -3.415 |
ourgeois | -3.397 |
uum | -3.318 |
ophobia | -3.316 |
Token | par |
Token ID | 1582 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ioxide | +1.030 |
uve | +1.029 |
ourgeois | +1.006 |
iv | +1.002 |
PF | +0.998 |
Neg logit contributions | |
ting | -1.264 |
◼ | -1.226 |
lisher | -1.194 |
rend | -1.170 |
ITNESS | -1.142 |
Token | av |
Token ID | 615 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ting | +1.999 |
◼ | +1.884 |
lisher | +1.872 |
rend | +1.862 |
ITNESS | +1.798 |
Neg logit contributions | |
ioxide | -1.209 |
uve | -1.197 |
ourgeois | -1.179 |
PF | -1.143 |
ophobia | -1.141 |
Token | irt |
Token ID | 2265 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ting | +4.127 |
rend | +3.797 |
lisher | +3.696 |
◼ | +3.561 |
ted | +3.435 |
Neg logit contributions | |
ioxide | -7.089 |
uve | -6.955 |
ophobia | -6.928 |
ourgeois | -6.903 |
pour | -6.874 |
Token | drivers |
Token ID | 6643 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ting | +3.669 |
rend | +3.378 |
lisher | +3.375 |
◼ | +3.339 |
ted | +3.246 |
Neg logit contributions | |
ioxide | -2.872 |
ourgeois | -2.810 |
uve | -2.804 |
ivan | -2.710 |
ophobia | -2.708 |
Token | for |
Token ID | 329 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
uve | +1.965 |
iv | +1.948 |
ioxide | +1.940 |
PF | +1.915 |
ourgeois | +1.914 |
Neg logit contributions | |
ting | -2.576 |
◼ | -2.525 |
lisher | -2.461 |
rend | -2.416 |
ITNESS | -2.383 |
Token | network |
Token ID | 3127 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
ting | +4.902 |
lisher | +4.450 |
◼ | +4.421 |
rend | +4.397 |
ted | +4.271 |
Neg logit contributions | |
ioxide | -4.540 |
uve | -4.426 |
ourgeois | -4.381 |
ophobia | -4.316 |
pour | -4.251 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ting | +6.137 |
lisher | +5.457 |
◼ | +5.430 |
ted | +5.430 |
rend | +5.415 |
Neg logit contributions | |
ioxide | -5.340 |
uve | -5.271 |
ourgeois | -5.153 |
ophobia | -4.964 |
uum | -4.905 |
Token | storage |
Token ID | 6143 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
ting | +3.897 |
◼ | +3.564 |
lisher | +3.555 |
rend | +3.522 |
ITNESS | +3.416 |
Neg logit contributions | |
ioxide | -3.520 |
uve | -3.497 |
ourgeois | -3.437 |
ophobia | -3.354 |
iv | -3.312 |
Token | devices |
Token ID | 4410 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ting | +4.056 |
◼ | +3.689 |
lisher | +3.652 |
rend | +3.650 |
ted | +3.529 |
Neg logit contributions | |
ioxide | -3.821 |
uve | -3.747 |
ourgeois | -3.693 |
ophobia | -3.602 |
ivan | -3.572 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ioxide | +0.075 |
uve | +0.074 |
ourgeois | +0.073 |
iv | +0.072 |
PF | +0.072 |
Neg logit contributions | |
ting | -0.093 |
◼ | -0.089 |
lisher | -0.088 |
rend | -0.087 |
ITNESS | -0.084 |
Token | The |
Token ID | 383 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ioxide | +1.125 |
uve | +1.123 |
ourgeois | +1.105 |
iv | +1.104 |
PF | +1.096 |
Neg logit contributions | |
ting | -1.444 |
◼ | -1.397 |
lisher | -1.367 |
rend | -1.333 |
ITNESS | -1.305 |
Token | Albert |
Token ID | 42590 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ting | +1.419 |
◼ | +1.344 |
lisher | +1.321 |
rend | +1.307 |
ITNESS | +1.262 |
Neg logit contributions | |
ioxide | -1.211 |
uve | -1.200 |
ourgeois | -1.179 |
ophobia | -1.157 |
PF | -1.152 |
Token | Ho |
Token ID | 9544 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
uve | +1.130 |
ioxide | +1.125 |
ourgeois | +1.104 |
iv | +1.090 |
ophobia | +1.089 |
Neg logit contributions | |
ting | -1.438 |
◼ | -1.376 |
lisher | -1.354 |
rend | -1.335 |
ITNESS | -1.296 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
uve | +1.850 |
ioxide | +1.820 |
iv | +1.803 |
ourgeois | +1.797 |
ophobia | +1.783 |
Neg logit contributions | |
ting | -2.239 |
◼ | -2.166 |
lisher | -2.128 |
rend | -2.079 |
ITNESS | -2.044 |
Token | another |
Token ID | 1194 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
uve | +2.039 |
ourgeois | +2.010 |
ioxide | +2.003 |
PF | +1.992 |
uses | +1.972 |
Neg logit contributions | |
ting | -2.679 |
◼ | -2.607 |
lisher | -2.518 |
rend | -2.514 |
ITNESS | -2.440 |
Token | lawmaker |
Token ID | 31340 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
uve | +0.404 |
ioxide | +0.402 |
ourgeois | +0.396 |
PF | +0.391 |
iv | +0.389 |
Neg logit contributions | |
ting | -0.482 |
◼ | -0.463 |
lisher | -0.451 |
rend | -0.447 |
ITNESS | -0.433 |
Token | involved |
Token ID | 2950 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
uve | +0.145 |
ioxide | +0.143 |
ourgeois | +0.142 |
ophobia | +0.140 |
iv | +0.140 |
Neg logit contributions | |
ting | -0.182 |
◼ | -0.174 |
lisher | -0.171 |
rend | -0.169 |
ITNESS | -0.166 |
Token | with |
Token ID | 351 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ting | +1.686 |
◼ | +1.577 |
lisher | +1.552 |
rend | +1.529 |
ITNESS | +1.470 |
Neg logit contributions | |
ioxide | -1.771 |
uve | -1.758 |
ourgeois | -1.722 |
PF | -1.697 |
ophobia | -1.695 |
Token | the |
Token ID | 262 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
ting | +3.116 |
◼ | +2.877 |
lisher | +2.860 |
rend | +2.807 |
ITNESS | +2.717 |
Neg logit contributions | |
ioxide | -3.140 |
uve | -3.069 |
ourgeois | -3.017 |
uum | -2.982 |
iv | -2.976 |
Token | museum |
Token ID | 13257 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
uve | +0.403 |
ioxide | +0.401 |
ourgeois | +0.394 |
ophobia | +0.389 |
PF | +0.387 |
Neg logit contributions | |
ting | -0.516 |
◼ | -0.496 |
lisher | -0.485 |
rend | -0.479 |
ITNESS | -0.465 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ting | +1.299 |
◼ | +1.228 |
lisher | +1.210 |
rend | +1.195 |
ITNESS | +1.155 |
Neg logit contributions | |
ioxide | -1.102 |
uve | -1.092 |
ourgeois | -1.071 |
ophobia | -1.053 |
PF | -1.051 |
Token | said |
Token ID | 531 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
uve | +0.938 |
ioxide | +0.932 |
ourgeois | +0.919 |
ophobia | +0.910 |
iv | +0.908 |
Neg logit contributions | |
ting | -0.950 |
◼ | -0.905 |
lisher | -0.889 |
rend | -0.875 |
ITNESS | -0.849 |
Token | it |
Token ID | 340 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ting | +2.084 |
◼ | +1.955 |
lisher | +1.929 |
rend | +1.915 |
ITNESS | +1.838 |
Neg logit contributions | |
ioxide | -1.783 |
uve | -1.760 |
ourgeois | -1.730 |
PF | -1.703 |
ophobia | -1.696 |
Token | means |
Token ID | 1724 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ting | +2.193 |
◼ | +2.046 |
lisher | +2.011 |
rend | +2.004 |
tto | +1.898 |
Neg logit contributions | |
ioxide | -2.328 |
uve | -2.295 |
ourgeois | -2.276 |
PF | -2.227 |
ophobia | -2.227 |
Token | something |
Token ID | 1223 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ting | +4.418 |
◼ | +4.124 |
lisher | +4.054 |
rend | +4.017 |
ted | +3.848 |
Neg logit contributions | |
ioxide | -3.931 |
uve | -3.900 |
ourgeois | -3.832 |
PF | -3.766 |
ophobia | -3.762 |
Token | different |
Token ID | 1180 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ting | +1.457 |
◼ | +1.373 |
lisher | +1.350 |
rend | +1.335 |
ITNESS | +1.285 |
Neg logit contributions | |
ioxide | -1.317 |
uve | -1.305 |
ourgeois | -1.279 |
ophobia | -1.258 |
PF | -1.258 |
Token | to |
Token ID | 284 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ting | +3.198 |
◼ | +2.928 |
lisher | +2.903 |
rend | +2.883 |
tto | +2.749 |
Neg logit contributions | |
ioxide | -3.360 |
uve | -3.301 |
ourgeois | -3.251 |
PF | -3.213 |
uum | -3.162 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ting | +2.760 |
◼ | +2.595 |
lisher | +2.562 |
rend | +2.524 |
ITNESS | +2.432 |
Neg logit contributions | |
ioxide | -2.253 |
uve | -2.210 |
ourgeois | -2.172 |
ophobia | -2.143 |
PF | -2.137 |
Token | people |
Token ID | 661 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ting | +1.610 |
◼ | +1.530 |
lisher | +1.509 |
rend | +1.491 |
ITNESS | +1.441 |
Neg logit contributions | |
ioxide | -1.161 |
uve | -1.146 |
ourgeois | -1.125 |
PF | -1.104 |
ophobia | -1.103 |
Token | who |
Token ID | 508 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ting | +1.781 |
◼ | +1.685 |
lisher | +1.660 |
rend | +1.644 |
ITNESS | +1.582 |
Neg logit contributions | |
ioxide | -1.419 |
uve | -1.393 |
ourgeois | -1.372 |
PF | -1.351 |
ophobia | -1.346 |
Token | consume |
Token ID | 15000 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ting | +6.081 |
◼ | +5.643 |
lisher | +5.574 |
rend | +5.530 |
ted | +5.306 |
Neg logit contributions | |
ioxide | -5.792 |
PF | -5.636 |
ourgeois | -5.635 |
uve | -5.576 |
ophobia | -5.436 |
Token | it |
Token ID | 340 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ting | +7.963 |
rend | +7.232 |
lisher | +7.097 |
◼ | +7.085 |
ted | +6.966 |
Neg logit contributions | |
ioxide | -8.338 |
PF | -8.077 |
uve | -8.067 |
ourgeois | -7.959 |
ophobia | -7.821 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
ting | +4.001 |
◼ | +3.680 |
rend | +3.651 |
lisher | +3.650 |
ted | +3.459 |
Neg logit contributions | |
ioxide | -3.801 |
uve | -3.733 |
ourgeois | -3.696 |
PF | -3.644 |
uum | -3.614 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
ting | +2.961 |
◼ | +2.731 |
rend | +2.679 |
lisher | +2.673 |
tto | +2.578 |
Neg logit contributions | |
ioxide | -2.987 |
uve | -2.952 |
ourgeois | -2.887 |
uum | -2.848 |
PF | -2.838 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ting | +3.335 |
◼ | +3.079 |
lisher | +3.072 |
rend | +3.047 |
ITNESS | +2.953 |
Neg logit contributions | |
ioxide | -2.767 |
uve | -2.737 |
ourgeois | -2.671 |
uum | -2.648 |
ophobia | -2.639 |
Token | family |
Token ID | 1641 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ting | +1.928 |
◼ | +1.820 |
lisher | +1.799 |
rend | +1.783 |
ITNESS | +1.724 |
Neg logit contributions | |
ioxide | -1.429 |
uve | -1.413 |
ourgeois | -1.382 |
ophobia | -1.358 |
PF | -1.354 |
Token | of |
Token ID | 286 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ting | +1.299 |
◼ | +1.234 |
lisher | +1.216 |
rend | +1.199 |
ITNESS | +1.162 |
Neg logit contributions | |
ioxide | -1.072 |
uve | -1.069 |
ourgeois | -1.046 |
ophobia | -1.029 |
iv | -1.028 |
Token | a |
Token ID | 257 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ting | +2.855 |
◼ | +2.675 |
lisher | +2.649 |
rend | +2.644 |
ITNESS | +2.539 |
Neg logit contributions | |
ioxide | -2.232 |
uve | -2.210 |
ourgeois | -2.157 |
ophobia | -2.126 |
uum | -2.118 |
Token | real |
Token ID | 1103 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
ting | +3.687 |
◼ | +3.388 |
rend | +3.377 |
lisher | +3.362 |
tto | +3.228 |
Neg logit contributions | |
ioxide | -3.451 |
uve | -3.364 |
ourgeois | -3.296 |
ophobia | -3.262 |
uum | -3.249 |
Token | estate |
Token ID | 7964 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ting | +3.497 |
◼ | +3.113 |
rend | +3.086 |
lisher | +3.068 |
ted | +2.948 |
Neg logit contributions | |
ioxide | -5.169 |
uve | -5.134 |
ourgeois | -5.016 |
PF | -4.980 |
ophobia | -4.977 |
Token | agent |
Token ID | 5797 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ioxide | +1.158 |
uve | +1.156 |
ourgeois | +1.143 |
iv | +1.131 |
ivan | +1.116 |
Neg logit contributions | |
ting | -1.555 |
◼ | -1.492 |
lisher | -1.461 |
rend | -1.426 |
ITNESS | -1.409 |
Token | murdered |
Token ID | 12864 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ting | +5.978 |
lisher | +5.411 |
◼ | +5.402 |
rend | +5.353 |
ted | +5.161 |
Neg logit contributions | |
ioxide | -6.144 |
uve | -5.785 |
ourgeois | -5.726 |
PF | -5.717 |
uum | -5.674 |
Token | by |
Token ID | 416 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +5.331 |
◼ | +4.743 |
rend | +4.710 |
lisher | +4.632 |
ted | +4.507 |
Neg logit contributions | |
ioxide | -6.572 |
uve | -6.319 |
ourgeois | -6.241 |
uum | -6.175 |
PF | -6.165 |
Token | members |
Token ID | 1866 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
ting | +1.039 |
◼ | +0.988 |
lisher | +0.973 |
rend | +0.962 |
ITNESS | +0.932 |
Neg logit contributions | |
ioxide | -0.772 |
uve | -0.766 |
ourgeois | -0.751 |
ophobia | -0.737 |
iv | -0.735 |
Token | got |
Token ID | 1392 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
uve | +0.936 |
ioxide | +0.931 |
ourgeois | +0.917 |
iv | +0.907 |
ophobia | +0.906 |
Neg logit contributions | |
ting | -1.181 |
◼ | -1.141 |
lisher | -1.119 |
rend | -1.098 |
ITNESS | -1.077 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
uve | +2.155 |
ioxide | +2.142 |
iv | +2.123 |
ourgeois | +2.117 |
uses | +2.106 |
Neg logit contributions | |
ting | -2.757 |
◼ | -2.710 |
lisher | -2.676 |
rend | -2.590 |
ITNESS | -2.551 |
Token | music |
Token ID | 2647 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ioxide | +1.737 |
iv | +1.714 |
ourgeois | +1.702 |
uve | +1.700 |
ivan | +1.676 |
Neg logit contributions | |
ting | -1.793 |
◼ | -1.762 |
lisher | -1.713 |
rend | -1.664 |
ITNESS | -1.646 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ting | +2.067 |
◼ | +1.940 |
lisher | +1.913 |
rend | +1.893 |
tto | +1.818 |
Neg logit contributions | |
ioxide | -1.820 |
uve | -1.797 |
ourgeois | -1.761 |
PF | -1.732 |
ophobia | -1.724 |
Token | We |
Token ID | 775 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ting | +3.453 |
◼ | +3.232 |
rend | +3.160 |
lisher | +3.137 |
tto | +3.059 |
Neg logit contributions | |
ioxide | -2.982 |
uve | -2.955 |
ourgeois | -2.907 |
uum | -2.837 |
ivan | -2.829 |
Token | 're |
Token ID | 821 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ioxide | +1.114 |
uve | +1.106 |
ourgeois | +1.089 |
iv | +1.079 |
ophobia | +1.076 |
Neg logit contributions | |
ting | -1.039 |
◼ | -0.996 |
lisher | -0.974 |
rend | -0.955 |
ITNESS | -0.930 |
Token | getting |
Token ID | 1972 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ioxide | +0.284 |
uve | +0.283 |
ourgeois | +0.278 |
ophobia | +0.275 |
iv | +0.274 |
Neg logit contributions | |
ting | -0.254 |
◼ | -0.240 |
lisher | -0.238 |
rend | -0.233 |
ITNESS | -0.226 |
Token | a |
Token ID | 257 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
ioxide | +0.852 |
uve | +0.848 |
ourgeois | +0.829 |
ophobia | +0.827 |
iv | +0.826 |
Neg logit contributions | |
ting | -1.078 |
◼ | -1.039 |
lisher | -1.026 |
rend | -1.007 |
ITNESS | -0.980 |
Token | cross |
Token ID | 3272 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ioxide | +0.527 |
uve | +0.527 |
ourgeois | +0.516 |
ophobia | +0.508 |
iv | +0.507 |
Neg logit contributions | |
ting | -0.700 |
◼ | -0.669 |
lisher | -0.661 |
rend | -0.650 |
ITNESS | -0.635 |
Token | - |
Token ID | 12 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uve | +8.000 |
iv | +7.732 |
ourgeois | +7.666 |
pour | +7.614 |
anguage | +7.539 |
Neg logit contributions | |
◼ | -9.882 |
ting | -9.829 |
ITNESS | -9.732 |
lisher | -9.575 |
rend | -8.985 |
Token | f |
Token ID | 69 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
uve | +7.041 |
uses | +6.961 |
iv | +6.934 |
ourgeois | +6.860 |
pour | +6.827 |
Neg logit contributions | |
ting | -8.735 |
◼ | -8.719 |
ITNESS | -8.672 |
lisher | -8.642 |
tto | -8.222 |
Token | so |
Token ID | 523 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ting | +1.797 |
◼ | +1.699 |
lisher | +1.669 |
rend | +1.655 |
ITNESS | +1.591 |
Neg logit contributions | |
ioxide | -1.493 |
uve | -1.479 |
ourgeois | -1.451 |
ophobia | -1.419 |
ivan | -1.417 |
Token | I |
Token ID | 314 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ting | +0.819 |
◼ | +0.775 |
lisher | +0.763 |
rend | +0.753 |
ITNESS | +0.728 |
Neg logit contributions | |
ioxide | -0.730 |
uve | -0.725 |
ourgeois | -0.711 |
ophobia | -0.699 |
PF | -0.698 |
Token | would |
Token ID | 561 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ioxide | +0.520 |
uve | +0.519 |
ourgeois | +0.507 |
iv | +0.502 |
ophobia | +0.501 |
Neg logit contributions | |
ting | -0.570 |
◼ | -0.546 |
lisher | -0.534 |
rend | -0.528 |
ITNESS | -0.513 |
Token | have |
Token ID | 423 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
ting | +0.095 |
◼ | +0.091 |
lisher | +0.089 |
rend | +0.087 |
ITNESS | +0.085 |
Neg logit contributions | |
ioxide | -0.081 |
uve | -0.081 |
ourgeois | -0.079 |
iv | -0.078 |
ophobia | -0.078 |
Token | to |
Token ID | 284 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ting | +0.791 |
◼ | +0.747 |
lisher | +0.735 |
rend | +0.726 |
ITNESS | +0.701 |
Neg logit contributions | |
ioxide | -0.734 |
uve | -0.729 |
ourgeois | -0.716 |
ophobia | -0.704 |
PF | -0.703 |
Token | solve |
Token ID | 8494 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
ting | +3.602 |
lisher | +3.257 |
◼ | +3.236 |
rend | +3.227 |
ted | +3.144 |
Neg logit contributions | |
ioxide | -3.147 |
uve | -3.141 |
ourgeois | -3.051 |
ophobia | -3.002 |
uum | -3.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ioxide | +0.435 |
uve | +0.432 |
ourgeois | +0.424 |
iv | +0.419 |
ophobia | +0.418 |
Neg logit contributions | |
ting | -0.554 |
◼ | -0.531 |
lisher | -0.522 |
rend | -0.513 |
ITNESS | -0.500 |
Token | timed |
Token ID | 28805 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ioxide | +2.107 |
uve | +2.094 |
ourgeois | +2.077 |
PF | +2.076 |
iv | +2.067 |
Neg logit contributions | |
ting | -2.674 |
◼ | -2.600 |
lisher | -2.530 |
rend | -2.477 |
ITNESS | -2.448 |
Token | 45 |
Token ID | 4153 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
ioxide | +1.177 |
uve | +1.156 |
ourgeois | +1.149 |
iv | +1.148 |
PF | +1.142 |
Neg logit contributions | |
ting | -1.357 |
◼ | -1.307 |
lisher | -1.288 |
rend | -1.260 |
ITNESS | -1.232 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ioxide | +0.625 |
uve | +0.619 |
ourgeois | +0.607 |
PF | +0.605 |
iv | +0.602 |
Neg logit contributions | |
ting | -0.667 |
◼ | -0.635 |
lisher | -0.624 |
rend | -0.612 |
ITNESS | -0.596 |
Token | minute |
Token ID | 11374 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ioxide | +1.562 |
uve | +1.552 |
PF | +1.535 |
iv | +1.534 |
uses | +1.522 |
Neg logit contributions | |
ting | -1.620 |
◼ | -1.554 |
lisher | -1.530 |
rend | -1.479 |
ITNESS | -1.468 |
Token | o |
Token ID | 78 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
uve | +3.029 |
ioxide | +2.976 |
iv | +2.966 |
ophobia | +2.939 |
ourgeois | +2.929 |
Neg logit contributions | |
ting | -3.613 |
◼ | -3.559 |
lisher | -3.437 |
ITNESS | -3.370 |
rend | -3.347 |
Token | Po |
Token ID | 7695 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ioxide | +0.600 |
uve | +0.598 |
ourgeois | +0.584 |
iv | +0.583 |
ivan | +0.577 |
Neg logit contributions | |
ting | -0.734 |
◼ | -0.705 |
lisher | -0.693 |
rend | -0.680 |
ITNESS | -0.667 |
Token | ij |
Token ID | 2926 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
iv | +2.467 |
uve | +2.458 |
ioxide | +2.441 |
ivan | +2.396 |
ourgeois | +2.347 |
Neg logit contributions | |
ting | -3.369 |
◼ | -3.312 |
lisher | -3.201 |
ITNESS | -3.165 |
rend | -3.103 |
Token | ä |
Token ID | 11033 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
ting | +0.873 |
◼ | +0.821 |
lisher | +0.811 |
rend | +0.800 |
ITNESS | +0.769 |
Neg logit contributions | |
ioxide | -0.808 |
uve | -0.801 |
ourgeois | -0.786 |
ophobia | -0.774 |
PF | -0.772 |
Token | r |
Token ID | 81 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ting | +0.630 |
◼ | +0.593 |
lisher | +0.581 |
rend | +0.571 |
ITNESS | +0.552 |
Neg logit contributions | |
ioxide | -0.732 |
uve | -0.728 |
ourgeois | -0.716 |
iv | -0.707 |
ophobia | -0.706 |
Token | vi |
Token ID | 8903 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ting | +1.541 |
◼ | +1.470 |
lisher | +1.452 |
rend | +1.439 |
ITNESS | +1.396 |
Neg logit contributions | |
ioxide | -0.824 |
uve | -0.816 |
ourgeois | -0.795 |
ophobia | -0.777 |
PF | -0.775 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
uve | +4.860 |
iv | +4.832 |
uum | +4.761 |
ioxide | +4.748 |
ivan | +4.717 |
Neg logit contributions | |
ting | -7.060 |
◼ | -6.979 |
lisher | -6.846 |
ITNESS | -6.758 |
rend | -6.614 |
Token | Ari |
Token ID | 6069 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
uve | +0.810 |
ioxide | +0.807 |
ourgeois | +0.794 |
iv | +0.786 |
ophobia | +0.780 |
Neg logit contributions | |
ting | -0.993 |
◼ | -0.949 |
lisher | -0.933 |
rend | -0.923 |
ITNESS | -0.900 |
Token | V |
Token ID | 569 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
uve | +1.289 |
ioxide | +1.275 |
ourgeois | +1.257 |
iv | +1.250 |
uum | +1.243 |
Neg logit contributions | |
ting | -1.602 |
◼ | -1.543 |
lisher | -1.513 |
rend | -1.485 |
ITNESS | -1.472 |
Token | ain |
Token ID | 391 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
ting | +2.608 |
◼ | +2.469 |
lisher | +2.446 |
rend | +2.442 |
tto | +2.359 |
Neg logit contributions | |
ioxide | -1.456 |
uve | -1.443 |
ourgeois | -1.401 |
PF | -1.382 |
ophobia | -1.370 |
Token | io |
Token ID | 952 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ting | +0.843 |
◼ | +0.799 |
lisher | +0.790 |
rend | +0.782 |
tto | +0.757 |
Neg logit contributions | |
ioxide | -0.545 |
uve | -0.539 |
ourgeois | -0.528 |
PF | -0.518 |
ophobia | -0.517 |
Token | . |
Token ID | 13 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
iv | +3.343 |
uve | +3.311 |
ioxide | +3.270 |
uses | +3.258 |
ophobia | +3.257 |
Neg logit contributions | |
ting | -4.224 |
lisher | -4.137 |
◼ | -4.129 |
rend | -3.917 |
ITNESS | -3.904 |
Token | � |
Token ID | 447 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ioxide | +3.274 |
uve | +3.267 |
iv | +3.233 |
PF | +3.200 |
ophobia | +3.196 |
Neg logit contributions | |
ting | -3.486 |
lisher | -3.338 |
◼ | -3.270 |
rend | -3.193 |
ITNESS | -3.088 |
Token | � |
Token ID | 251 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ioxide | +1.792 |
uve | +1.786 |
iv | +1.732 |
uses | +1.731 |
uum | +1.730 |
Neg logit contributions | |
ting | -1.662 |
◼ | -1.556 |
lisher | -1.548 |
rend | -1.508 |
ITNESS | -1.453 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
iv | +3.955 |
ioxide | +3.932 |
uve | +3.911 |
PF | +3.847 |
uses | +3.846 |
Neg logit contributions | |
ting | -4.921 |
lisher | -4.720 |
◼ | -4.652 |
rend | -4.620 |
tto | -4.413 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
ioxide | +1.315 |
uve | +1.308 |
iv | +1.279 |
PF | +1.273 |
ourgeois | +1.271 |
Neg logit contributions | |
ting | -1.431 |
◼ | -1.365 |
lisher | -1.352 |
rend | -1.317 |
ITNESS | -1.287 |
Token | When |
Token ID | 2215 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ioxide | +0.009 |
uve | +0.009 |
ourgeois | +0.008 |
PF | +0.008 |
iv | +0.008 |
Neg logit contributions | |
ting | -0.010 |
◼ | -0.009 |
lisher | -0.009 |
rend | -0.009 |
ITNESS | -0.009 |
Token | Mr |
Token ID | 1770 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
uve | +4.101 |
ioxide | +4.042 |
uses | +4.019 |
iv | +4.013 |
ivan | +3.987 |
Neg logit contributions | |
ting | -5.914 |
◼ | -5.736 |
lisher | -5.721 |
rend | -5.569 |
ITNESS | -5.498 |
Token | . |
Token ID | 13 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
uve | +3.653 |
iv | +3.645 |
ioxide | +3.610 |
uses | +3.560 |
ophobia | +3.543 |
Neg logit contributions | |
ting | -5.477 |
◼ | -5.382 |
lisher | -5.341 |
ITNESS | -5.165 |
rend | -5.162 |
Token | Sel |
Token ID | 15300 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
uve | +4.754 |
ioxide | +4.659 |
ophobia | +4.565 |
iv | +4.555 |
ivan | +4.472 |
Neg logit contributions | |
ting | -7.636 |
◼ | -7.347 |
lisher | -7.245 |
ITNESS | -7.144 |
rend | -7.046 |
Token | z |
Token ID | 89 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ting | +1.099 |
rend | +0.980 |
◼ | +0.976 |
lisher | +0.961 |
tto | +0.929 |
Neg logit contributions | |
ioxide | -1.486 |
uve | -1.457 |
ourgeois | -1.457 |
PF | -1.433 |
ophobia | -1.414 |
Token | nick |
Token ID | 17172 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ting | +2.592 |
◼ | +2.312 |
rend | +2.299 |
lisher | +2.274 |
tto | +2.201 |
Neg logit contributions | |
ioxide | -3.076 |
uve | -3.052 |
ourgeois | -3.008 |
PF | -2.951 |
uses | -2.907 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ting | +2.663 |
◼ | +2.498 |
lisher | +2.463 |
rend | +2.434 |
ITNESS | +2.346 |
Neg logit contributions | |
ioxide | -2.323 |
uve | -2.285 |
ourgeois | -2.255 |
ophobia | -2.214 |
uum | -2.208 |
Token | great |
Token ID | 1049 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ting | +8.256 |
lisher | +7.330 |
◼ | +7.238 |
rend | +7.206 |
tto | +7.025 |
Neg logit contributions | |
ioxide | -8.396 |
uum | -8.075 |
ourgeois | -8.073 |
uve | -8.062 |
ophobia | -7.953 |
Token | success |
Token ID | 1943 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ting | +4.476 |
◼ | +3.911 |
lisher | +3.909 |
rend | +3.886 |
ted | +3.636 |
Neg logit contributions | |
ioxide | -7.052 |
ourgeois | -6.793 |
uve | -6.783 |
uum | -6.760 |
ivan | -6.615 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ting | +2.746 |
◼ | +2.550 |
lisher | +2.517 |
rend | +2.493 |
tto | +2.397 |
Neg logit contributions | |
ioxide | -2.533 |
uve | -2.461 |
ourgeois | -2.437 |
PF | -2.385 |
ivan | -2.385 |
Token | returned |
Token ID | 4504 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ting | +1.467 |
◼ | +1.378 |
lisher | +1.352 |
rend | +1.336 |
ITNESS | +1.289 |
Neg logit contributions | |
ioxide | -1.422 |
uve | -1.396 |
ourgeois | -1.378 |
ophobia | -1.357 |
PF | -1.352 |
Token | extremely |
Token ID | 4457 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ting | +3.612 |
◼ | +3.348 |
lisher | +3.307 |
rend | +3.259 |
ITNESS | +3.169 |
Neg logit contributions | |
ioxide | -3.269 |
ourgeois | -3.169 |
uve | -3.164 |
PF | -3.094 |
ophobia | -3.092 |
Token | detailed |
Token ID | 6496 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
uve | +0.489 |
ioxide | +0.486 |
ourgeois | +0.474 |
iv | +0.470 |
ophobia | +0.468 |
Neg logit contributions | |
ting | -0.586 |
◼ | -0.557 |
lisher | -0.550 |
rend | -0.542 |
ITNESS | -0.526 |
Token | images |
Token ID | 4263 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ting | +2.940 |
◼ | +2.730 |
lisher | +2.699 |
rend | +2.682 |
ITNESS | +2.557 |
Neg logit contributions | |
ioxide | -2.807 |
uve | -2.769 |
ourgeois | -2.736 |
PF | -2.688 |
ophobia | -2.679 |
Token | of |
Token ID | 286 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ting | +1.358 |
◼ | +1.279 |
lisher | +1.257 |
rend | +1.244 |
ITNESS | +1.197 |
Neg logit contributions | |
ioxide | -1.167 |
uve | -1.157 |
ourgeois | -1.136 |
ophobia | -1.115 |
PF | -1.113 |
Token | the |
Token ID | 262 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
ting | +5.869 |
◼ | +5.292 |
rend | +5.288 |
lisher | +5.247 |
ted | +5.107 |
Neg logit contributions | |
ioxide | -6.006 |
ourgeois | -5.901 |
PF | -5.861 |
uve | -5.823 |
ophobia | -5.782 |
Token | comet |
Token ID | 31733 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ting | +7.405 |
rend | +6.750 |
◼ | +6.719 |
lisher | +6.595 |
ted | +6.476 |
Neg logit contributions | |
ioxide | -6.884 |
ourgeois | -6.764 |
PF | -6.761 |
ivan | -6.639 |
uve | -6.634 |
Token | people |
Token ID | 661 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
ioxide | +0.845 |
uve | +0.840 |
ourgeois | +0.827 |
iv | +0.819 |
PF | +0.814 |
Neg logit contributions | |
ting | -1.060 |
◼ | -1.019 |
lisher | -0.992 |
rend | -0.980 |
ITNESS | -0.957 |
Token | who |
Token ID | 508 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
uve | +5.811 |
pour | +5.691 |
ourgeois | +5.597 |
uses | +5.590 |
iv | +5.559 |
Neg logit contributions | |
◼ | -7.647 |
ting | -7.517 |
lisher | -7.352 |
rend | -7.217 |
ITNESS | -7.176 |
Token | own |
Token ID | 898 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
uve | +3.855 |
ioxide | +3.847 |
uses | +3.797 |
ivan | +3.787 |
ourgeois | +3.781 |
Neg logit contributions | |
◼ | -4.382 |
ting | -4.362 |
lisher | -4.201 |
rend | -4.172 |
ITNESS | -4.073 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ioxide | +0.160 |
uve | +0.159 |
ourgeois | +0.157 |
iv | +0.155 |
PF | +0.154 |
Neg logit contributions | |
ting | -0.174 |
◼ | -0.167 |
lisher | -0.164 |
rend | -0.161 |
ITNESS | -0.156 |
Token | Kh |
Token ID | 5311 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
uve | +2.931 |
iv | +2.900 |
ourgeois | +2.891 |
ioxide | +2.884 |
PF | +2.840 |
Neg logit contributions | |
ting | -3.993 |
◼ | -3.910 |
lisher | -3.781 |
rend | -3.739 |
ITNESS | -3.672 |
Token | ark |
Token ID | 668 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ioxide | +1.631 |
iv | +1.613 |
uve | +1.611 |
ivan | +1.589 |
ourgeois | +1.587 |
Neg logit contributions | |
ting | -2.497 |
◼ | -2.415 |
lisher | -2.369 |
rend | -2.310 |
ITNESS | -2.295 |
Token | iv |
Token ID | 452 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
iv | +4.657 |
ivan | +3.343 |
ives | +3.126 |
uses | +2.708 |
pour | +2.643 |
Neg logit contributions | |
◼ | -17.771 |
ting | -16.904 |
lisher | -16.587 |
ITNESS | -16.374 |
rend | -16.302 |
Token | firms |
Token ID | 9611 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
uve | +4.244 |
iv | +4.235 |
uses | +4.164 |
ourgeois | +4.137 |
PF | +4.126 |
Neg logit contributions | |
ting | -6.138 |
◼ | -6.045 |
lisher | -5.880 |
ITNESS | -5.809 |
rend | -5.786 |
Token | are |
Token ID | 389 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ioxide | +0.314 |
uve | +0.313 |
ourgeois | +0.308 |
iv | +0.303 |
ophobia | +0.303 |
Neg logit contributions | |
ting | -0.331 |
◼ | -0.316 |
lisher | -0.310 |
rend | -0.306 |
ITNESS | -0.296 |
Token | mostly |
Token ID | 4632 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
uve | +4.059 |
iv | +3.980 |
ourgeois | +3.978 |
ioxide | +3.977 |
uses | +3.960 |
Neg logit contributions | |
ting | -4.743 |
◼ | -4.651 |
lisher | -4.633 |
rend | -4.507 |
ITNESS | -4.456 |
Token | top |
Token ID | 1353 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
uve | +1.939 |
ourgeois | +1.905 |
ioxide | +1.901 |
iv | +1.890 |
PF | +1.872 |
Neg logit contributions | |
ting | -2.676 |
◼ | -2.610 |
lisher | -2.568 |
rend | -2.541 |
ITNESS | -2.495 |
Token | Bulgarian |
Token ID | 42119 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ioxide | +0.750 |
uve | +0.748 |
ophobia | +0.737 |
ourgeois | +0.731 |
iv | +0.730 |
Neg logit contributions | |
ting | -0.874 |
◼ | -0.832 |
lisher | -0.823 |
rend | -0.804 |
ITNESS | -0.784 |
Token | ambassador |
Token ID | 14791 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ioxide | +1.122 |
uve | +1.117 |
ophobia | +1.108 |
iv | +1.102 |
ourgeois | +1.098 |
Neg logit contributions | |
ting | -1.463 |
◼ | -1.400 |
lisher | -1.388 |
rend | -1.358 |
ITNESS | -1.324 |
Token | . |
Token ID | 13 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
uve | +2.506 |
ophobia | +2.489 |
ioxide | +2.467 |
iv | +2.456 |
ivan | +2.414 |
Neg logit contributions | |
ting | -3.079 |
◼ | -2.970 |
lisher | -2.961 |
rend | -2.848 |
ITNESS | -2.844 |
Token |
|
Token ID | 198 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
iv | +4.221 |
uve | +4.176 |
ophobia | +4.164 |
ioxide | +4.076 |
PF | +4.039 |
Neg logit contributions | |
ting | -5.412 |
lisher | -5.242 |
◼ | -5.183 |
rend | -4.999 |
ITNESS | -4.916 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ting | +0.065 |
◼ | +0.061 |
lisher | +0.059 |
rend | +0.059 |
tto | +0.056 |
Neg logit contributions | |
ioxide | -0.067 |
uve | -0.066 |
ourgeois | -0.065 |
ophobia | -0.064 |
PF | -0.064 |
Token | People |
Token ID | 8061 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ting | +1.249 |
◼ | +1.180 |
lisher | +1.156 |
rend | +1.145 |
ITNESS | +1.103 |
Neg logit contributions | |
ioxide | -1.170 |
uve | -1.159 |
ourgeois | -1.140 |
ophobia | -1.118 |
PF | -1.114 |
Token | living |
Token ID | 2877 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ophobia | +7.678 |
iv | +7.446 |
uve | +7.423 |
uses | +7.166 |
pour | +7.131 |
Neg logit contributions | |
◼ | -10.531 |
lisher | -10.478 |
ting | -10.255 |
ITNESS | -10.228 |
rend | -9.937 |
Token | in |
Token ID | 287 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
uve | +2.279 |
ioxide | +2.266 |
ophobia | +2.256 |
iv | +2.252 |
ourgeois | +2.247 |
Neg logit contributions | |
ting | -2.722 |
◼ | -2.633 |
lisher | -2.588 |
rend | -2.523 |
ITNESS | -2.483 |
Token | the |
Token ID | 262 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
ioxide | +1.499 |
uve | +1.496 |
ourgeois | +1.473 |
ophobia | +1.467 |
iv | +1.463 |
Neg logit contributions | |
ting | -1.665 |
◼ | -1.602 |
lisher | -1.565 |
rend | -1.541 |
ITNESS | -1.494 |
Token | UK |
Token ID | 3482 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ioxide | +0.682 |
uve | +0.681 |
ourgeois | +0.668 |
ophobia | +0.659 |
iv | +0.659 |
Neg logit contributions | |
ting | -0.864 |
◼ | -0.820 |
lisher | -0.808 |
rend | -0.798 |
ITNESS | -0.772 |
Token | for |
Token ID | 329 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
uve | +5.107 |
iv | +5.044 |
ophobia | +4.996 |
uses | +4.851 |
ourgeois | +4.832 |
Neg logit contributions | |
ting | -6.662 |
lisher | -6.582 |
◼ | -6.537 |
ITNESS | -6.357 |
rend | -6.343 |
Token | � |
Token ID | 447 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ting | +1.167 |
◼ | +1.097 |
lisher | +1.078 |
rend | +1.070 |
ITNESS | +1.024 |
Neg logit contributions | |
ioxide | -1.080 |
uve | -1.067 |
ourgeois | -1.055 |
uum | -1.030 |
PF | -1.029 |
Token | � |
Token ID | 247 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ioxide | +1.187 |
uve | +1.184 |
ourgeois | +1.141 |
PF | +1.135 |
uum | +1.135 |
Neg logit contributions | |
ting | -1.436 |
◼ | -1.366 |
lisher | -1.349 |
rend | -1.319 |
ITNESS | -1.287 |
Token | s |
Token ID | 82 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
uve | +1.512 |
ioxide | +1.494 |
uses | +1.474 |
iv | +1.471 |
ourgeois | +1.463 |
Neg logit contributions | |
ting | -1.102 |
◼ | -1.064 |
lisher | -1.037 |
ITNESS | -1.008 |
rend | -1.005 |
Token | strict |
Token ID | 7646 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ioxide | +1.281 |
uve | +1.265 |
ourgeois | +1.241 |
ophobia | +1.237 |
iv | +1.233 |
Neg logit contributions | |
ting | -1.142 |
◼ | -1.087 |
lisher | -1.073 |
rend | -1.044 |
ITNESS | -1.019 |
Token | est |
Token ID | 395 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ophobia | +3.559 |
ioxide | +3.480 |
iv | +3.447 |
ives | +3.443 |
PF | +3.388 |
Neg logit contributions | |
◼ | -11.130 |
lisher | -10.995 |
ting | -10.948 |
ITNESS | -10.586 |
tto | -10.335 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Pour | +7.901 |
PF | +7.873 |
envelope | +7.850 |
ioxide | +7.793 |
ives | +7.765 |
Neg logit contributions | |
◼ | -12.357 |
lisher | -12.129 |
ting | -11.642 |
ITNESS | -11.456 |
rend | -11.239 |
Token | for |
Token ID | 329 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
uve | +6.402 |
iv | +6.369 |
ophobia | +6.323 |
pour | +6.180 |
ourgeois | +6.098 |
Neg logit contributions | |
◼ | -10.491 |
lisher | -10.428 |
ting | -10.386 |
ITNESS | -10.381 |
rend | -9.808 |
Token | water |
Token ID | 1660 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
uve | +4.153 |
ioxide | +4.149 |
uses | +4.095 |
iv | +4.074 |
PF | +4.027 |
Neg logit contributions | |
◼ | -5.328 |
ting | -5.309 |
lisher | -5.196 |
rend | -5.141 |
ITNESS | -5.013 |
Token | use |
Token ID | 779 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
iv | +5.309 |
uses | +5.293 |
PF | +5.195 |
uve | +5.136 |
ives | +5.101 |
Neg logit contributions | |
◼ | -8.058 |
lisher | -7.931 |
ITNESS | -7.826 |
ting | -7.774 |
rend | -7.676 |
Token | and |
Token ID | 290 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
uve | +4.271 |
iv | +4.259 |
ioxide | +4.239 |
ophobia | +4.219 |
uses | +4.210 |
Neg logit contributions | |
◼ | -6.132 |
lisher | -6.076 |
ting | -6.057 |
ITNESS | -5.854 |
rend | -5.829 |
Token | protection |
Token ID | 4800 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
ioxide | +4.789 |
uses | +4.709 |
iv | +4.663 |
uum | +4.601 |
pour | +4.598 |
Neg logit contributions | |
lisher | -7.468 |
◼ | -7.465 |
ting | -7.360 |
ITNESS | -7.223 |
rend | -7.209 |
Token | is |
Token ID | 318 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
uve | +4.031 |
ophobia | +4.003 |
uses | +3.960 |
iv | +3.896 |
ives | +3.893 |
Neg logit contributions | |
◼ | -6.486 |
lisher | -6.316 |
ting | -6.315 |
ITNESS | -6.310 |
rend | -6.002 |
Token | best |
Token ID | 1266 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
uve | +3.585 |
ophobia | +3.537 |
uses | +3.521 |
ioxide | +3.506 |
iv | +3.478 |
Neg logit contributions | |
ting | -5.011 |
◼ | -4.971 |
lisher | -4.868 |
ITNESS | -4.757 |
rend | -4.737 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ting | +1.130 |
◼ | +1.073 |
lisher | +1.053 |
rend | +1.039 |
ITNESS | +1.005 |
Neg logit contributions | |
ioxide | -1.032 |
uve | -1.024 |
ourgeois | -1.006 |
ophobia | -0.995 |
iv | -0.992 |
Token | take |
Token ID | 1011 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ioxide | +1.041 |
uve | +1.025 |
ourgeois | +1.015 |
iv | +1.006 |
ivan | +1.000 |
Neg logit contributions | |
ting | -1.157 |
◼ | -1.143 |
lisher | -1.112 |
rend | -1.093 |
ITNESS | -1.060 |
Token | a |
Token ID | 257 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
uve | +3.209 |
ioxide | +3.178 |
uses | +3.168 |
iv | +3.159 |
ophobia | +3.136 |
Neg logit contributions | |
◼ | -3.958 |
ting | -3.946 |
lisher | -3.846 |
rend | -3.710 |
ITNESS | -3.614 |
Token | deep |
Token ID | 2769 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
uve | +3.419 |
ourgeois | +3.406 |
ioxide | +3.403 |
iv | +3.397 |
ophobia | +3.395 |
Neg logit contributions | |
ting | -4.349 |
◼ | -4.309 |
lisher | -4.145 |
rend | -4.057 |
ITNESS | -4.004 |
Token | breath |
Token ID | 8033 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
ophobia | +4.874 |
pour | +4.851 |
iv | +4.793 |
ioxide | +4.780 |
uve | +4.725 |
Neg logit contributions | |
◼ | -14.719 |
ting | -14.041 |
lisher | -13.874 |
ITNESS | -13.714 |
glers | -13.447 |
Token | and |
Token ID | 290 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
ting | +0.923 |
◼ | +0.875 |
lisher | +0.862 |
rend | +0.852 |
ITNESS | +0.825 |
Neg logit contributions | |
ioxide | -0.729 |
uve | -0.724 |
ourgeois | -0.709 |
ophobia | -0.697 |
PF | -0.695 |
Token | not |
Token ID | 407 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
ioxide | +0.013 |
uve | +0.013 |
ourgeois | +0.013 |
iv | +0.012 |
ophobia | +0.012 |
Neg logit contributions | |
ting | -0.016 |
◼ | -0.015 |
lisher | -0.015 |
rend | -0.015 |
ITNESS | -0.014 |
Token | blog |
Token ID | 4130 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
ioxide | +3.627 |
iv | +3.599 |
uve | +3.562 |
pour | +3.556 |
ourgeois | +3.521 |
Neg logit contributions | |
◼ | -4.878 |
ting | -4.685 |
lisher | -4.667 |
rend | -4.566 |
ITNESS | -4.429 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ting | +3.217 |
rend | +2.923 |
lisher | +2.905 |
◼ | +2.899 |
ted | +2.775 |
Neg logit contributions | |
ioxide | -3.311 |
uve | -3.268 |
ourgeois | -3.199 |
uum | -3.140 |
PF | -3.132 |
Token | of |
Token ID | 286 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
uve | +1.535 |
ioxide | +1.534 |
ourgeois | +1.478 |
iv | +1.477 |
pour | +1.465 |
Neg logit contributions | |
ting | -2.090 |
◼ | -2.004 |
lisher | -1.978 |
rend | -1.940 |
ITNESS | -1.906 |
Token | Wright |
Token ID | 12206 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ting | +1.324 |
◼ | +1.253 |
lisher | +1.231 |
rend | +1.212 |
ITNESS | +1.173 |
Neg logit contributions | |
ioxide | -1.288 |
uve | -1.279 |
ourgeois | -1.257 |
ophobia | -1.236 |
iv | -1.235 |
Token | � |
Token ID | 447 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
uve | +3.352 |
ioxide | +3.293 |
iv | +3.262 |
PF | +3.242 |
pour | +3.223 |
Neg logit contributions | |
ting | -3.822 |
lisher | -3.641 |
◼ | -3.597 |
ITNESS | -3.477 |
rend | -3.462 |
Token | � |
Token ID | 247 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ioxide | +1.147 |
uve | +1.139 |
ourgeois | +1.111 |
ophobia | +1.093 |
PF | +1.093 |
Neg logit contributions | |
ting | -1.515 |
◼ | -1.439 |
lisher | -1.420 |
rend | -1.400 |
ITNESS | -1.358 |
Token | s |
Token ID | 82 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ioxide | +1.642 |
uve | +1.638 |
ourgeois | +1.601 |
iv | +1.594 |
uses | +1.591 |
Neg logit contributions | |
ting | -1.149 |
◼ | -1.080 |
lisher | -1.055 |
rend | -1.034 |
ITNESS | -1.004 |
Token | de |
Token ID | 390 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ioxide | +0.978 |
uve | +0.974 |
ourgeois | +0.957 |
iv | +0.956 |
ophobia | +0.944 |
Neg logit contributions | |
ting | -1.099 |
◼ | -1.056 |
lisher | -1.045 |
rend | -1.013 |
ITNESS | -1.003 |
Token | cept |
Token ID | 984 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
iv | +7.955 |
uses | +7.442 |
uve | +7.078 |
ives | +7.056 |
ourgeois | +7.055 |
Neg logit contributions | |
ting | -11.396 |
◼ | -11.216 |
lisher | -11.042 |
ITNESS | -10.868 |
tto | -10.128 |
Token | ively |
Token ID | 2280 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
iv | +0.797 |
uve | +0.777 |
ives | +0.758 |
ourgeois | +0.679 |
ioxide | +0.675 |
Neg logit contributions | |
ting | -7.031 |
◼ | -7.001 |
lisher | -6.867 |
ITNESS | -6.812 |
tto | -6.786 |
Token | simple |
Token ID | 2829 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
uve | +3.858 |
iv | +3.827 |
ourgeois | +3.815 |
uses | +3.745 |
ioxide | +3.728 |
Neg logit contributions | |
ting | -4.288 |
◼ | -4.176 |
lisher | -4.171 |
ITNESS | -4.046 |
rend | -4.003 |
Token | � |
Token ID | 564 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
ives | +7.140 |
iv | +7.135 |
uses | +7.050 |
envelope | +6.883 |
ourgeois | +6.810 |
Neg logit contributions | |
ITNESS | -9.644 |
◼ | -9.548 |
lisher | -9.465 |
ting | -9.412 |
rend | -8.712 |
Token | � |
Token ID | 250 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
ting | +0.405 |
◼ | +0.380 |
lisher | +0.373 |
rend | +0.368 |
ITNESS | +0.353 |
Neg logit contributions | |
ioxide | -0.458 |
uve | -0.455 |
ourgeois | -0.448 |
ophobia | -0.441 |
PF | -0.441 |