Token | by |
Token ID | 416 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
doct | +2.728 |
)=( | +2.636 |
nton | +2.615 |
Doct | +2.585 |
Omaha | +2.558 |
Neg logit contributions | |
imilar | -2.494 |
aiman | -2.467 |
Iro | -2.443 |
200000 | -2.323 |
annis | -2.276 |
Token | Boston |
Token ID | 6182 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
doct | +0.935 |
)=( | +0.908 |
nton | +0.907 |
Doct | +0.890 |
Omaha | +0.882 |
Neg logit contributions | |
imilar | -0.879 |
aiman | -0.869 |
Iro | -0.865 |
200000 | -0.819 |
annis | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
doct | +0.491 |
)=( | +0.476 |
nton | +0.473 |
Doct | +0.465 |
Omaha | +0.461 |
Neg logit contributions | |
imilar | -0.491 |
aiman | -0.487 |
Iro | -0.485 |
200000 | -0.460 |
annis | -0.454 |
Token | com |
Token ID | 785 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
doct | +1.263 |
)=( | +1.218 |
nton | +1.216 |
Doct | +1.193 |
Omaha | +1.179 |
Neg logit contributions | |
imilar | -1.604 |
aiman | -1.587 |
Iro | -1.579 |
200000 | -1.509 |
annis | -1.491 |
Token | The |
Token ID | 383 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
doct | +4.515 |
Doct | +4.331 |
nton | +4.275 |
)=( | +4.263 |
Omaha | +4.254 |
Neg logit contributions | |
imilar | -4.919 |
aiman | -4.873 |
Iro | -4.719 |
200000 | -4.588 |
annis | -4.536 |
Token | old |
Token ID | 1468 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
doct | +5.890 |
Omaha | +5.647 |
Doct | +5.499 |
nton | +5.428 |
)=( | +5.392 |
Neg logit contributions | |
imilar | -8.150 |
aiman | -8.129 |
Iro | -7.855 |
200000 | -7.729 |
arius | -7.683 |
Token | building |
Token ID | 16894 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ey | +15.231 |
Omaha | +14.971 |
Everett | +14.883 |
nton | +14.488 |
doct | +14.417 |
Neg logit contributions | |
imilar | -17.154 |
aiman | -16.659 |
sabotage | -16.111 |
200000 | -15.921 |
henko | -15.916 |
Token | was |
Token ID | 373 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
doct | +2.481 |
)=( | +2.408 |
nton | +2.383 |
Doct | +2.348 |
Omaha | +2.330 |
Neg logit contributions | |
imilar | -2.972 |
aiman | -2.947 |
Iro | -2.891 |
200000 | -2.786 |
annis | -2.746 |
Token | renamed |
Token ID | 25121 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
doct | +1.703 |
nton | +1.637 |
)=( | +1.634 |
Doct | +1.597 |
Omaha | +1.572 |
Neg logit contributions | |
imilar | -2.545 |
aiman | -2.518 |
Iro | -2.496 |
200000 | -2.396 |
annis | -2.375 |
Token | for |
Token ID | 1640 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ey | +12.070 |
Doct | +11.941 |
)=( | +11.929 |
doct | +11.909 |
bringing | +11.637 |
Neg logit contributions | |
imilar | -11.707 |
aiman | -11.300 |
200000 | -10.817 |
Iro | -10.806 |
akov | -10.739 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
doct | +2.659 |
)=( | +2.563 |
nton | +2.552 |
Doct | +2.521 |
Omaha | +2.506 |
Neg logit contributions | |
imilar | -3.126 |
aiman | -3.091 |
Iro | -3.060 |
200000 | -2.945 |
annis | -2.904 |
Token | not |
Token ID | 407 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
doct | +4.907 |
nton | +4.628 |
Doct | +4.548 |
)=( | +4.548 |
Omaha | +4.489 |
Neg logit contributions | |
imilar | -5.789 |
aiman | -5.724 |
Iro | -5.554 |
200000 | -5.457 |
annis | -5.371 |
Token | , |
Token ID | 11 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
doct | +6.975 |
)=( | +6.299 |
Doct | +6.251 |
Omaha | +6.251 |
Hume | +6.167 |
Neg logit contributions | |
aiman | -9.140 |
imilar | -9.014 |
Iro | -8.717 |
annis | -8.698 |
akov | -8.649 |
Token | I |
Token ID | 314 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
doct | +7.771 |
Doct | +7.408 |
Omaha | +7.083 |
Hume | +6.960 |
)=( | +6.955 |
Neg logit contributions | |
aiman | -11.607 |
imilar | -11.153 |
Iro | -10.674 |
akov | -10.659 |
200000 | -10.651 |
Token | think |
Token ID | 892 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
doct | +3.306 |
nton | +3.174 |
)=( | +3.151 |
Doct | +3.085 |
Omaha | +3.060 |
Neg logit contributions | |
imilar | -3.506 |
aiman | -3.427 |
Iro | -3.392 |
200000 | -3.256 |
arius | -3.133 |
Token | , |
Token ID | 11 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
doct | +5.663 |
nton | +5.368 |
)=( | +5.158 |
Omaha | +5.041 |
Doct | +4.963 |
Neg logit contributions | |
imilar | -10.241 |
aiman | -10.025 |
Iro | -9.667 |
insula | -9.435 |
200000 | -9.374 |
Token | what |
Token ID | 644 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
doct | +6.090 |
)=( | +5.541 |
Doct | +5.531 |
Omaha | +5.479 |
nton | +5.479 |
Neg logit contributions | |
aiman | -7.483 |
imilar | -7.327 |
Iro | -7.119 |
200000 | -7.087 |
annis | -6.933 |
Token | He |
Token ID | 679 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Hume | +15.570 |
doct | +15.145 |
Doct | +14.079 |
Omaha | +14.011 |
mater | +13.531 |
Neg logit contributions | |
imilar | -16.387 |
insula | -16.075 |
aiman | -15.948 |
200000 | -15.420 |
akov | -15.351 |
Token | ikes |
Token ID | 7938 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
doct | +4.072 |
nton | +4.019 |
)=( | +3.915 |
ey | +3.806 |
Doct | +3.762 |
Neg logit contributions | |
Iro | -4.889 |
aiman | -4.815 |
imilar | -4.803 |
200000 | -4.581 |
Kara | -4.535 |
Token | intends |
Token ID | 19582 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
doct | +3.503 |
nton | +3.288 |
)=( | +3.256 |
Doct | +3.230 |
Omaha | +3.186 |
Neg logit contributions | |
imilar | -4.002 |
aiman | -3.972 |
Iro | -3.914 |
200000 | -3.811 |
annis | -3.703 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
doct | +2.770 |
)=( | +2.640 |
nton | +2.628 |
Doct | +2.595 |
Omaha | +2.567 |
Neg logit contributions | |
imilar | -3.637 |
aiman | -3.597 |
Iro | -3.541 |
200000 | -3.394 |
akov | -3.372 |
Token | Instead |
Token ID | 5455 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Hume | +9.587 |
Doct | +9.288 |
Omaha | +9.033 |
doct | +8.916 |
)=( | +8.770 |
Neg logit contributions | |
imilar | -13.536 |
aiman | -13.442 |
insula | -12.487 |
sabotage | -12.427 |
akov | -12.414 |
Token | ina |
Token ID | 1437 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
imilar | +2.933 |
aiman | +2.908 |
Iro | +2.806 |
bas | +2.628 |
annis | +2.613 |
Neg logit contributions | |
doct | -5.889 |
Doct | -5.667 |
)=( | -5.637 |
Omaha | -5.612 |
nton | -5.480 |
Token | of |
Token ID | 286 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
doct | +2.276 |
)=( | +2.204 |
nton | +2.169 |
Doct | +2.150 |
Omaha | +2.131 |
Neg logit contributions | |
imilar | -3.695 |
aiman | -3.669 |
Iro | -3.606 |
annis | -3.494 |
200000 | -3.493 |
Token | Time |
Token ID | 3862 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
doct | +3.237 |
nton | +3.154 |
)=( | +3.153 |
Omaha | +3.126 |
Doct | +3.092 |
Neg logit contributions | |
aiman | -4.333 |
imilar | -4.307 |
Iro | -4.121 |
200000 | -4.084 |
annis | -4.079 |
Token | was |
Token ID | 373 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
doct | +4.572 |
)=( | +4.345 |
nton | +4.334 |
Doct | +4.303 |
Omaha | +4.241 |
Neg logit contributions | |
imilar | -5.971 |
aiman | -5.833 |
Iro | -5.760 |
annis | -5.563 |
200000 | -5.512 |
Token | the |
Token ID | 262 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
doct | +3.680 |
nton | +3.515 |
Doct | +3.473 |
)=( | +3.458 |
Omaha | +3.433 |
Neg logit contributions | |
imilar | -4.265 |
aiman | -4.171 |
Iro | -4.111 |
200000 | -3.947 |
annis | -3.936 |
Token | last |
Token ID | 938 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
doct | +7.569 |
Omaha | +7.189 |
Doct | +7.189 |
nton | +7.102 |
)=( | +7.033 |
Neg logit contributions | |
imilar | -8.523 |
aiman | -8.215 |
akov | -7.879 |
Iro | -7.830 |
annis | -7.742 |
Token | Zelda |
Token ID | 22166 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
doct | +15.311 |
Omaha | +14.553 |
Wo | +14.269 |
Doct | +14.066 |
eyeb | +13.942 |
Neg logit contributions | |
imilar | -16.018 |
akov | -15.292 |
henko | -15.240 |
annis | -15.180 |
aiman | -15.121 |
Token | O |
Token ID | 440 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
doct | +7.423 |
nton | +7.030 |
Doct | +6.839 |
Omaha | +6.831 |
mater | +6.716 |
Neg logit contributions | |
imilar | -9.215 |
aiman | -9.007 |
Iro | -8.906 |
200000 | -8.713 |
insula | -8.500 |
Token | ST |
Token ID | 2257 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
doct | +5.747 |
nton | +5.721 |
Doct | +5.374 |
)=( | +5.369 |
ey | +5.333 |
Neg logit contributions | |
imilar | -6.827 |
Iro | -6.789 |
aiman | -6.657 |
200000 | -6.407 |
akov | -6.405 |
Token | that |
Token ID | 326 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
doct | +4.518 |
nton | +4.330 |
Doct | +4.229 |
)=( | +4.187 |
Omaha | +4.175 |
Neg logit contributions | |
imilar | -5.711 |
aiman | -5.538 |
Iro | -5.493 |
200000 | -5.359 |
annis | -5.240 |
Token | Ko |
Token ID | 17634 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
doct | +8.071 |
Doct | +7.579 |
nton | +7.510 |
Omaha | +7.501 |
)=( | +7.413 |
Neg logit contributions | |
imilar | -9.320 |
aiman | -8.995 |
Iro | -8.663 |
200000 | -8.623 |
annis | -8.578 |
Token | at |
Token ID | 379 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
doct | +3.972 |
nton | +3.744 |
Omaha | +3.724 |
Doct | +3.720 |
)=( | +3.708 |
Neg logit contributions | |
imilar | -6.108 |
aiman | -5.954 |
Iro | -5.887 |
200000 | -5.680 |
annis | -5.655 |
Token | 5 |
Token ID | 642 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
doct | +7.088 |
Omaha | +6.834 |
Doct | +6.692 |
nton | +6.436 |
)=( | +6.302 |
Neg logit contributions | |
aiman | -11.540 |
imilar | -11.371 |
insula | -10.912 |
Iro | -10.897 |
200000 | -10.828 |
Token | a |
Token ID | 257 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
doct | +6.608 |
nton | +6.171 |
Omaha | +6.093 |
Doct | +6.048 |
)=( | +5.893 |
Neg logit contributions | |
imilar | -12.270 |
aiman | -12.235 |
Iro | -11.867 |
akov | -11.464 |
200000 | -11.347 |
Token | . |
Token ID | 13 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
doct | +2.244 |
nton | +2.181 |
)=( | +2.159 |
Doct | +2.104 |
Omaha | +2.085 |
Neg logit contributions | |
imilar | -3.006 |
Iro | -2.961 |
aiman | -2.959 |
annis | -2.789 |
200000 | -2.783 |
Token | m |
Token ID | 76 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
nton | +4.367 |
doct | +4.028 |
ey | +3.982 |
noon | +3.910 |
)=( | +3.848 |
Neg logit contributions | |
imilar | -10.162 |
Iro | -10.143 |
aiman | -10.102 |
insula | -9.708 |
sabotage | -9.582 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Omaha | +9.161 |
doct | +9.143 |
Doct | +8.646 |
ey | +8.586 |
nton | +8.496 |
Neg logit contributions | |
aiman | -16.292 |
imilar | -16.170 |
Iro | -16.075 |
200000 | -16.056 |
sabotage | -15.573 |
Token | ET |
Token ID | 12152 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
doct | +14.476 |
Omaha | +14.395 |
Doct | +13.914 |
ET | +13.792 |
noon | +13.638 |
Neg logit contributions | |
aiman | -15.918 |
imilar | -15.839 |
200000 | -14.823 |
arius | -14.777 |
Iro | -14.644 |
Token | for |
Token ID | 329 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
doct | +6.299 |
Omaha | +6.052 |
nton | +6.020 |
)=( | +5.901 |
Doct | +5.875 |
Neg logit contributions | |
imilar | -10.110 |
aiman | -9.814 |
Iro | -9.657 |
200000 | -9.352 |
annis | -9.303 |
Token | an |
Token ID | 281 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
doct | +0.419 |
)=( | +0.408 |
nton | +0.406 |
Doct | +0.398 |
Omaha | +0.393 |
Neg logit contributions | |
imilar | -0.447 |
aiman | -0.442 |
Iro | -0.441 |
200000 | -0.418 |
annis | -0.414 |
Token | additional |
Token ID | 3224 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
doct | +0.062 |
nton | +0.060 |
)=( | +0.060 |
Doct | +0.059 |
Omaha | +0.058 |
Neg logit contributions | |
imilar | -0.075 |
aiman | -0.075 |
Iro | -0.075 |
200000 | -0.071 |
annis | -0.070 |
Token | hour |
Token ID | 1711 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
imilar | +0.589 |
Iro | +0.585 |
aiman | +0.585 |
200000 | +0.557 |
annis | +0.551 |
Neg logit contributions | |
doct | -0.450 |
)=( | -0.442 |
nton | -0.438 |
Doct | -0.425 |
Omaha | -0.419 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
imilar | +1.324 |
Iro | +1.322 |
aiman | +1.301 |
200000 | +1.226 |
annis | +1.210 |
Neg logit contributions | |
doct | -1.836 |
)=( | -1.826 |
nton | -1.794 |
Doct | -1.776 |
Omaha | -1.758 |
Token | that |
Token ID | 326 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
imilar | +2.741 |
Iro | +2.732 |
aiman | +2.703 |
200000 | +2.568 |
Kara | +2.520 |
Neg logit contributions | |
doct | -2.882 |
nton | -2.837 |
)=( | -2.802 |
Doct | -2.751 |
Omaha | -2.701 |
Token | if |
Token ID | 611 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
imilar | +2.281 |
aiman | +2.281 |
Iro | +2.276 |
200000 | +2.122 |
Kara | +2.084 |
Neg logit contributions | |
nton | -3.256 |
doct | -3.254 |
)=( | -3.175 |
Doct | -3.144 |
Omaha | -3.101 |
Token | you |
Token ID | 345 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
doct | +2.433 |
)=( | +2.323 |
nton | +2.290 |
Doct | +2.239 |
Omaha | +2.212 |
Neg logit contributions | |
imilar | -3.746 |
aiman | -3.700 |
Iro | -3.654 |
annis | -3.505 |
200000 | -3.504 |
Token | find |
Token ID | 1064 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
sabotage | +2.775 |
imilar | +2.688 |
bas | +2.641 |
Iro | +2.532 |
aiman | +2.447 |
Neg logit contributions | |
)=( | -13.272 |
nton | -13.229 |
Doct | -13.102 |
doct | -13.031 |
bringing | -12.940 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
doct | +1.150 |
)=( | +1.110 |
nton | +1.102 |
Doct | +1.082 |
Omaha | +1.073 |
Neg logit contributions | |
imilar | -1.418 |
aiman | -1.401 |
Iro | -1.392 |
200000 | -1.331 |
annis | -1.318 |
Token | phantom |
Token ID | 36381 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
doct | +7.035 |
phantom | +7.006 |
UFO | +6.363 |
phant | +5.891 |
mater | +5.647 |
Neg logit contributions | |
Iro | -24.573 |
imilar | -24.271 |
akov | -23.986 |
aiman | -23.833 |
insula | -23.544 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
imilar | +2.097 |
Iro | +2.085 |
aiman | +2.062 |
200000 | +1.985 |
Kara | +1.924 |
Neg logit contributions | |
doct | -2.234 |
)=( | -2.161 |
nton | -2.160 |
Doct | -2.135 |
Omaha | -2.123 |
Token | you |
Token ID | 345 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
doct | +1.399 |
)=( | +1.347 |
nton | +1.337 |
Doct | +1.307 |
Omaha | +1.293 |
Neg logit contributions | |
imilar | -1.944 |
aiman | -1.925 |
Iro | -1.902 |
200000 | -1.824 |
annis | -1.816 |
Token | have |
Token ID | 423 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Iro | +5.775 |
imilar | +5.678 |
aiman | +5.606 |
200000 | +5.433 |
bas | +5.428 |
Neg logit contributions | |
doct | -9.898 |
Doct | -9.866 |
Omaha | -9.847 |
)=( | -9.652 |
nton | -9.595 |
Token | more |
Token ID | 517 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
doct | +4.205 |
nton | +3.608 |
)=( | +3.601 |
Omaha | +3.517 |
Doct | +3.511 |
Neg logit contributions | |
imilar | -10.046 |
aiman | -10.006 |
Iro | -9.847 |
insula | -9.614 |
akov | -9.599 |
Token | y |
Token ID | 88 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
doct | +2.673 |
nton | +2.592 |
)=( | +2.572 |
ey | +2.525 |
Doct | +2.462 |
Neg logit contributions | |
Iro | -4.313 |
imilar | -4.312 |
aiman | -4.290 |
200000 | -4.085 |
annis | -4.033 |
Token | � |
Token ID | 447 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
doct | +3.169 |
nton | +3.056 |
)=( | +3.012 |
Doct | +2.960 |
Omaha | +2.890 |
Neg logit contributions | |
imilar | -4.300 |
aiman | -4.257 |
Iro | -4.229 |
200000 | -4.078 |
annis | -3.993 |
Token | � |
Token ID | 247 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
imilar | +1.421 |
aiman | +1.408 |
Iro | +1.351 |
200000 | +1.299 |
akov | +1.273 |
Neg logit contributions | |
doct | -2.428 |
nton | -2.349 |
Doct | -2.337 |
Omaha | -2.326 |
)=( | -2.319 |
Token | s |
Token ID | 82 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
doct | +1.374 |
nton | +1.337 |
)=( | +1.331 |
Doct | +1.302 |
Omaha | +1.288 |
Neg logit contributions | |
imilar | -1.348 |
aiman | -1.331 |
Iro | -1.323 |
200000 | -1.253 |
annis | -1.236 |
Token | mother |
Token ID | 2802 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
doct | +6.263 |
nton | +5.991 |
Doct | +5.802 |
Omaha | +5.685 |
)=( | +5.653 |
Neg logit contributions | |
imilar | -8.600 |
aiman | -8.444 |
Iro | -8.417 |
200000 | -8.190 |
annis | -8.041 |
Token | first |
Token ID | 717 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
doct | +2.754 |
nton | +2.657 |
)=( | +2.633 |
Doct | +2.594 |
Omaha | +2.569 |
Neg logit contributions | |
imilar | -3.136 |
aiman | -3.120 |
Iro | -3.073 |
200000 | -2.963 |
annis | -2.914 |
Token | brought |
Token ID | 3181 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
doct | +5.823 |
bringing | +5.275 |
mater | +3.560 |
nton | +3.482 |
ey | +3.313 |
Neg logit contributions | |
insula | -27.044 |
aiman | -26.335 |
imilar | -25.717 |
sabotage | -24.851 |
Iro | -24.840 |
Token | her |
Token ID | 607 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
doct | +3.185 |
nton | +2.982 |
)=( | +2.962 |
Omaha | +2.904 |
Doct | +2.789 |
Neg logit contributions | |
imilar | -10.158 |
aiman | -10.115 |
Iro | -9.800 |
annis | -9.620 |
insula | -9.469 |
Token | to |
Token ID | 284 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
doct | +1.045 |
)=( | +1.006 |
nton | +1.005 |
Doct | +0.982 |
Omaha | +0.969 |
Neg logit contributions | |
imilar | -1.430 |
aiman | -1.414 |
Iro | -1.401 |
200000 | -1.344 |
annis | -1.330 |
Token | see |
Token ID | 766 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
doct | +3.593 |
nton | +3.385 |
)=( | +3.352 |
Doct | +3.264 |
Omaha | +3.206 |
Neg logit contributions | |
imilar | -5.488 |
aiman | -5.443 |
Iro | -5.293 |
200000 | -5.177 |
arius | -5.067 |
Token | her |
Token ID | 607 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
doct | +1.495 |
nton | +1.428 |
)=( | +1.427 |
Doct | +1.380 |
Omaha | +1.370 |
Neg logit contributions | |
imilar | -3.160 |
aiman | -3.138 |
Iro | -3.098 |
200000 | -2.984 |
annis | -2.980 |
Token | ton |
Token ID | 1122 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
doct | +0.585 |
nton | +0.562 |
)=( | +0.557 |
Doct | +0.541 |
Omaha | +0.533 |
Neg logit contributions | |
imilar | -1.180 |
Iro | -1.169 |
aiman | -1.169 |
200000 | -1.123 |
annis | -1.112 |
Token | , |
Token ID | 11 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
doct | +0.434 |
)=( | +0.424 |
nton | +0.420 |
Doct | +0.412 |
Omaha | +0.406 |
Neg logit contributions | |
imilar | -0.522 |
aiman | -0.517 |
Iro | -0.517 |
200000 | -0.490 |
annis | -0.486 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
doct | +4.622 |
Omaha | +4.423 |
nton | +4.377 |
Doct | +4.338 |
)=( | +4.305 |
Neg logit contributions | |
imilar | -5.718 |
aiman | -5.633 |
Iro | -5.499 |
200000 | -5.368 |
annis | -5.348 |
Token | World |
Token ID | 2159 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
doct | +10.112 |
Omaha | +10.079 |
Doct | +9.262 |
nton | +9.034 |
Wo | +9.030 |
Neg logit contributions | |
imilar | -11.603 |
aiman | -11.404 |
annis | -11.168 |
insula | -10.872 |
Iro | -10.759 |
Token | War |
Token ID | 1810 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Omaha | +2.253 |
doct | +2.176 |
Doct | +1.858 |
nton | +1.818 |
ey | +1.658 |
Neg logit contributions | |
imilar | -16.782 |
aiman | -16.602 |
insula | -16.330 |
annis | -16.208 |
200000 | -16.107 |
Token | II |
Token ID | 2873 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
doct | +6.338 |
Omaha | +5.925 |
)=( | +5.773 |
nton | +5.700 |
Vietnamese | +5.577 |
Neg logit contributions | |
imilar | -17.148 |
aiman | -17.093 |
insula | -16.358 |
annis | -16.352 |
200000 | -16.329 |
Token | vet |
Token ID | 20202 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
doct | +10.678 |
Omaha | +10.455 |
Vietnamese | +9.553 |
Vietnam | +9.014 |
mater | +8.995 |
Neg logit contributions | |
imilar | -20.144 |
aiman | -19.941 |
200000 | -19.377 |
annis | -19.149 |
insula | -19.088 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
doct | +5.909 |
nton | +5.666 |
Omaha | +5.660 |
Doct | +5.418 |
ey | +5.183 |
Neg logit contributions | |
imilar | -8.803 |
aiman | -8.588 |
200000 | -8.400 |
Iro | -8.379 |
annis | -8.170 |
Token | died |
Token ID | 3724 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
doct | +2.001 |
nton | +1.913 |
)=( | +1.894 |
Doct | +1.875 |
Omaha | +1.866 |
Neg logit contributions | |
imilar | -2.674 |
aiman | -2.640 |
Iro | -2.610 |
200000 | -2.521 |
annis | -2.487 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
doct | +2.148 |
nton | +2.068 |
)=( | +2.058 |
Doct | +2.040 |
Omaha | +2.025 |
Neg logit contributions | |
imilar | -2.414 |
aiman | -2.386 |
Iro | -2.361 |
200000 | -2.265 |
annis | -2.239 |
Token | after |
Token ID | 706 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
doct | +5.483 |
Omaha | +5.261 |
nton | +5.161 |
Doct | +5.133 |
)=( | +4.942 |
Neg logit contributions | |
imilar | -9.011 |
aiman | -8.977 |
Iro | -8.711 |
200000 | -8.502 |
annis | -8.448 |
Token | prime |
Token ID | 6994 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
doct | +5.786 |
Omaha | +5.453 |
nton | +5.355 |
)=( | +5.300 |
Doct | +5.236 |
Neg logit contributions | |
imilar | -8.038 |
aiman | -7.784 |
Iro | -7.740 |
annis | -7.595 |
akov | -7.509 |
Token | - |
Token ID | 12 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
doct | +1.851 |
)=( | +1.774 |
nton | +1.772 |
Doct | +1.735 |
Omaha | +1.729 |
Neg logit contributions | |
imilar | -2.324 |
aiman | -2.305 |
Iro | -2.287 |
200000 | -2.187 |
annis | -2.174 |
Token | age |
Token ID | 496 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
imilar | +3.366 |
aiman | +3.287 |
Iro | +3.223 |
200000 | +3.216 |
bas | +3.133 |
Neg logit contributions | |
doct | -3.837 |
Doct | -3.743 |
)=( | -3.715 |
Omaha | -3.673 |
nton | -3.657 |
Token | public |
Token ID | 1171 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
doct | +5.820 |
Omaha | +5.511 |
nton | +5.434 |
Doct | +5.291 |
)=( | +5.276 |
Neg logit contributions | |
imilar | -8.120 |
aiman | -7.826 |
Iro | -7.774 |
annis | -7.655 |
200000 | -7.561 |
Token | school |
Token ID | 1524 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
doct | +5.094 |
nton | +4.826 |
Omaha | +4.792 |
)=( | +4.718 |
ey | +4.638 |
Neg logit contributions | |
imilar | -7.605 |
aiman | -7.482 |
Iro | -7.401 |
annis | -7.236 |
200000 | -7.221 |
Token | teachers |
Token ID | 7799 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
doct | +6.269 |
nton | +5.774 |
Omaha | +5.724 |
Doct | +5.574 |
)=( | +5.547 |
Neg logit contributions | |
imilar | -11.250 |
aiman | -10.846 |
Iro | -10.791 |
annis | -10.672 |
200000 | -10.548 |
Token | leave |
Token ID | 2666 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
doct | +13.136 |
nton | +12.205 |
)=( | +11.994 |
mater | +11.487 |
ey | +11.446 |
Neg logit contributions | |
imilar | -16.393 |
200000 | -16.201 |
Iro | -15.603 |
aiman | -15.593 |
henko | -15.198 |
Token | the |
Token ID | 262 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
doct | +1.779 |
)=( | +1.715 |
nton | +1.709 |
Doct | +1.682 |
Omaha | +1.675 |
Neg logit contributions | |
imilar | -2.000 |
aiman | -1.978 |
Iro | -1.967 |
200000 | -1.885 |
annis | -1.859 |
Token | profession |
Token ID | 7573 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
imilar | +0.609 |
aiman | +0.601 |
Iro | +0.600 |
200000 | +0.570 |
akov | +0.561 |
Neg logit contributions | |
doct | -0.522 |
)=( | -0.510 |
nton | -0.504 |
Doct | -0.499 |
Omaha | -0.489 |
Token | or |
Token ID | 393 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
doct | +2.430 |
nton | +2.347 |
)=( | +2.346 |
Doct | +2.303 |
Omaha | +2.279 |
Neg logit contributions | |
imilar | -2.773 |
aiman | -2.736 |
Iro | -2.714 |
200000 | -2.598 |
annis | -2.570 |
Token | sector |
Token ID | 6567 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
doct | +6.049 |
nton | +5.680 |
)=( | +5.673 |
Omaha | +5.548 |
Doct | +5.524 |
Neg logit contributions | |
imilar | -7.554 |
aiman | -7.422 |
Iro | -7.375 |
200000 | -7.302 |
annis | -7.203 |
Token | replaced |
Token ID | 6928 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
doct | +9.047 |
nton | +7.843 |
)=( | +7.807 |
Doct | +7.798 |
Omaha | +7.541 |
Neg logit contributions | |
imilar | -11.050 |
aiman | -10.524 |
200000 | -10.370 |
annis | -10.166 |
akov | -10.062 |
Token | with |
Token ID | 351 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
doct | +7.266 |
Doct | +6.401 |
nton | +6.353 |
)=( | +6.247 |
ey | +6.103 |
Neg logit contributions | |
imilar | -12.545 |
aiman | -12.113 |
Iro | -12.065 |
insula | -11.849 |
akov | -11.837 |
Token | better |
Token ID | 1365 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
doct | +10.476 |
)=( | +9.697 |
Doct | +9.332 |
Hume | +9.155 |
Omaha | +9.111 |
Neg logit contributions | |
imilar | -12.307 |
aiman | -11.911 |
akov | -11.783 |
insula | -11.601 |
200000 | -11.554 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
doct | +8.302 |
)=( | +7.467 |
nton | +7.425 |
Doct | +7.260 |
mater | +6.964 |
Neg logit contributions | |
imilar | -11.643 |
akov | -11.093 |
aiman | -10.981 |
insula | -10.735 |
Iro | -10.706 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
doct | +6.816 |
Doct | +6.098 |
)=( | +6.064 |
nton | +6.013 |
Omaha | +5.799 |
Neg logit contributions | |
imilar | -10.354 |
aiman | -10.280 |
200000 | -10.075 |
Iro | -10.035 |
akov | -9.919 |
Token | What |
Token ID | 1867 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Doct | +8.366 |
Hume | +8.153 |
doct | +8.141 |
Omaha | +7.954 |
)=( | +7.926 |
Neg logit contributions | |
imilar | -11.319 |
aiman | -11.118 |
insula | -10.400 |
annis | -10.348 |
sabotage | -10.318 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
doct | +14.038 |
Hume | +13.825 |
Doct | +13.401 |
Omaha | +12.880 |
)=( | +12.728 |
Neg logit contributions | |
imilar | -15.462 |
aiman | -15.360 |
insula | -14.908 |
200000 | -14.350 |
henko | -14.151 |
Token | these |
Token ID | 777 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
doct | +14.468 |
Hume | +13.969 |
Doct | +13.434 |
nton | +12.898 |
Omaha | +12.755 |
Neg logit contributions | |
imilar | -15.307 |
aiman | -14.877 |
200000 | -14.460 |
insula | -14.364 |
akov | -13.930 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
doct | +11.246 |
Doct | +9.974 |
)=( | +9.868 |
nton | +9.793 |
Hume | +9.703 |
Neg logit contributions | |
imilar | -11.132 |
aiman | -11.090 |
200000 | -10.715 |
akov | -10.663 |
arius | -10.655 |
Token | better |
Token ID | 1365 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
doct | +13.674 |
ey | +12.282 |
mater | +12.237 |
)=( | +11.853 |
Hume | +11.782 |
Neg logit contributions | |
200000 | -16.340 |
aiman | -15.969 |
arius | -15.118 |
insula | -15.104 |
imilar | -14.883 |
Token | is |
Token ID | 318 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
doct | +8.148 |
)=( | +7.660 |
nton | +7.524 |
Doct | +7.296 |
ey | +7.107 |
Neg logit contributions | |
imilar | -12.172 |
Iro | -12.030 |
200000 | -11.953 |
aiman | -11.871 |
akov | -11.784 |
Token | with |
Token ID | 351 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
doct | +7.266 |
Doct | +6.401 |
nton | +6.353 |
)=( | +6.247 |
ey | +6.103 |
Neg logit contributions | |
imilar | -12.545 |
aiman | -12.113 |
Iro | -12.065 |
insula | -11.849 |
akov | -11.837 |
Token | better |
Token ID | 1365 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
doct | +10.476 |
)=( | +9.697 |
Doct | +9.332 |
Hume | +9.155 |
Omaha | +9.111 |
Neg logit contributions | |
imilar | -12.307 |
aiman | -11.911 |
akov | -11.783 |
insula | -11.601 |
200000 | -11.554 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
doct | +8.302 |
)=( | +7.467 |
nton | +7.425 |
Doct | +7.260 |
mater | +6.964 |
Neg logit contributions | |
imilar | -11.643 |
akov | -11.093 |
aiman | -10.981 |
insula | -10.735 |
Iro | -10.706 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
doct | +6.816 |
Doct | +6.098 |
)=( | +6.064 |
nton | +6.013 |
Omaha | +5.799 |
Neg logit contributions | |
imilar | -10.354 |
aiman | -10.280 |
200000 | -10.075 |
Iro | -10.035 |
akov | -9.919 |
Token | What |
Token ID | 1867 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Doct | +8.366 |
Hume | +8.153 |
doct | +8.141 |
Omaha | +7.954 |
)=( | +7.926 |
Neg logit contributions | |
imilar | -11.319 |
aiman | -11.118 |
insula | -10.400 |
annis | -10.348 |
sabotage | -10.318 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
doct | +14.038 |
Hume | +13.825 |
Doct | +13.401 |
Omaha | +12.880 |
)=( | +12.728 |
Neg logit contributions | |
imilar | -15.462 |
aiman | -15.360 |
insula | -14.908 |
200000 | -14.350 |
henko | -14.151 |
Token | these |
Token ID | 777 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
doct | +14.468 |
Hume | +13.969 |
Doct | +13.434 |
nton | +12.898 |
Omaha | +12.755 |
Neg logit contributions | |
imilar | -15.307 |
aiman | -14.877 |
200000 | -14.460 |
insula | -14.364 |
akov | -13.930 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
doct | +11.246 |
Doct | +9.974 |
)=( | +9.868 |
nton | +9.793 |
Hume | +9.703 |
Neg logit contributions | |
imilar | -11.132 |
aiman | -11.090 |
200000 | -10.715 |
akov | -10.663 |
arius | -10.655 |
Token | better |
Token ID | 1365 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
doct | +13.674 |
ey | +12.282 |
mater | +12.237 |
)=( | +11.853 |
Hume | +11.782 |
Neg logit contributions | |
200000 | -16.340 |
aiman | -15.969 |
arius | -15.118 |
insula | -15.104 |
imilar | -14.883 |
Token | is |
Token ID | 318 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
doct | +8.148 |
)=( | +7.660 |
nton | +7.524 |
Doct | +7.296 |
ey | +7.107 |
Neg logit contributions | |
imilar | -12.172 |
Iro | -12.030 |
200000 | -11.953 |
aiman | -11.871 |
akov | -11.784 |
Token | that |
Token ID | 326 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
doct | +7.087 |
Doct | +6.596 |
Hume | +6.473 |
)=( | +6.473 |
nton | +6.469 |
Neg logit contributions | |
aiman | -8.830 |
imilar | -8.796 |
Iro | -8.612 |
annis | -8.338 |
200000 | -8.337 |
Token | obvious |
Token ID | 3489 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
doct | +5.113 |
nton | +4.789 |
)=( | +4.761 |
Omaha | +4.731 |
Doct | +4.705 |
Neg logit contributions | |
aiman | -5.304 |
Iro | -5.243 |
imilar | -5.220 |
200000 | -5.068 |
annis | -4.973 |
Token | ( |
Token ID | 357 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
doct | +4.539 |
)=( | +4.362 |
nton | +4.299 |
Doct | +4.236 |
Omaha | +4.203 |
Neg logit contributions | |
imilar | -6.156 |
aiman | -6.090 |
Iro | -6.045 |
200000 | -5.796 |
annis | -5.791 |
Token | as |
Token ID | 292 |
Feature activation | -3.86e-03 |
Pos logit contributions | |
doct | +4.103 |
nton | +4.010 |
)=( | +4.004 |
Doct | +3.897 |
Omaha | +3.849 |
Neg logit contributions | |
imilar | -4.141 |
aiman | -4.100 |
Iro | -4.077 |
200000 | -3.813 |
annis | -3.805 |
Token | opposed |
Token ID | 6886 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
imilar | +0.041 |
aiman | +0.041 |
Iro | +0.041 |
200000 | +0.038 |
annis | +0.038 |
Neg logit contributions | |
doct | -0.038 |
nton | -0.037 |
)=( | -0.037 |
Doct | -0.036 |
Omaha | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
doct | +1.647 |
)=( | +1.593 |
nton | +1.579 |
Doct | +1.546 |
Omaha | +1.519 |
Neg logit contributions | |
imilar | -2.322 |
aiman | -2.303 |
Iro | -2.279 |
200000 | -2.188 |
annis | -2.171 |
Token | back |
Token ID | 736 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
doct | +11.519 |
)=( | +10.988 |
Omaha | +10.769 |
Doct | +10.716 |
eyeb | +10.508 |
Neg logit contributions | |
imilar | -12.478 |
aiman | -12.473 |
insula | -11.733 |
henko | -11.657 |
annis | -11.535 |
Token | in |
Token ID | 287 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
)=( | +15.361 |
doct | +14.259 |
ey | +13.475 |
nton | +12.989 |
eyeb | +12.876 |
Neg logit contributions | |
aiman | -15.518 |
annis | -14.220 |
imilar | -14.165 |
200000 | -13.822 |
Iro | -13.793 |
Token | the |
Token ID | 262 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
doct | +7.181 |
Omaha | +6.808 |
)=( | +6.799 |
Doct | +6.758 |
nton | +6.638 |
Neg logit contributions | |
imilar | -8.978 |
aiman | -8.817 |
annis | -8.433 |
Iro | -8.358 |
200000 | -8.332 |
Token | day |
Token ID | 1110 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
doct | +7.179 |
Doct | +6.723 |
Omaha | +6.618 |
)=( | +6.540 |
ey | +6.337 |
Neg logit contributions | |
imilar | -10.074 |
aiman | -9.844 |
annis | -9.561 |
insula | -9.450 |
200000 | -9.392 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
doct | +10.908 |
)=( | +10.856 |
Omaha | +10.367 |
?). | +10.214 |
Doct | +10.010 |
Neg logit contributions | |
imilar | -13.220 |
aiman | -12.890 |
henko | -12.432 |
annis | -12.311 |
akov | -12.098 |
Token | at |
Token ID | 379 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
doct | +11.939 |
Omaha | +11.229 |
Doct | +11.144 |
)=( | +11.117 |
Wo | +10.622 |
Neg logit contributions | |
aiman | -11.571 |
imilar | -11.537 |
henko | -10.983 |
insula | -10.832 |
annis | -10.738 |
Token | , |
Token ID | 11 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
doct | +1.198 |
)=( | +1.159 |
nton | +1.156 |
Doct | +1.135 |
Omaha | +1.124 |
Neg logit contributions | |
imilar | -1.366 |
aiman | -1.352 |
Iro | -1.344 |
200000 | -1.282 |
annis | -1.266 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
doct | +4.825 |
Omaha | +4.629 |
Doct | +4.602 |
nton | +4.597 |
)=( | +4.528 |
Neg logit contributions | |
imilar | -6.422 |
aiman | -6.345 |
Iro | -6.070 |
200000 | -5.951 |
akov | -5.951 |
Token | p |
Token ID | 279 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
doct | +8.220 |
Omaha | +7.792 |
Doct | +7.661 |
nton | +7.577 |
noon | +7.425 |
Neg logit contributions | |
aiman | -16.157 |
imilar | -15.678 |
Iro | -15.023 |
akov | -14.967 |
200000 | -14.956 |
Token | . |
Token ID | 13 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
doct | +0.941 |
nton | +0.912 |
)=( | +0.912 |
Doct | +0.891 |
Omaha | +0.883 |
Neg logit contributions | |
imilar | -1.124 |
aiman | -1.112 |
Iro | -1.107 |
200000 | -1.049 |
annis | -1.043 |
Token | m |
Token ID | 76 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
nton | +4.116 |
doct | +3.794 |
ey | +3.766 |
noon | +3.691 |
)=( | +3.630 |
Neg logit contributions | |
Iro | -9.508 |
imilar | -9.325 |
aiman | -9.318 |
insula | -8.977 |
sabotage | -8.884 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
doct | +6.124 |
Omaha | +5.998 |
nton | +5.933 |
Doct | +5.883 |
ey | +5.730 |
Neg logit contributions | |
imilar | -14.246 |
aiman | -14.209 |
insula | -13.927 |
Iro | -13.889 |
200000 | -13.440 |
Token | ET |
Token ID | 12152 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ET | +9.917 |
Omaha | +9.753 |
doct | +9.730 |
Doct | +9.536 |
nton | +8.712 |
Neg logit contributions | |
aiman | -19.633 |
imilar | -18.961 |
200000 | -18.285 |
Iro | -18.066 |
akov | -18.051 |
Token | on |
Token ID | 319 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
doct | +4.006 |
Omaha | +3.843 |
Doct | +3.828 |
nton | +3.812 |
)=( | +3.784 |
Neg logit contributions | |
imilar | -6.227 |
aiman | -6.108 |
Iro | -6.042 |
200000 | -5.857 |
annis | -5.742 |
Token | Sunday |
Token ID | 3502 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
doct | +4.497 |
Omaha | +4.381 |
Doct | +4.344 |
nton | +4.272 |
)=( | +4.160 |
Neg logit contributions | |
imilar | -6.579 |
aiman | -6.438 |
Iro | -6.220 |
200000 | -6.133 |
akov | -6.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
doct | +4.734 |
nton | +4.595 |
Omaha | +4.553 |
Doct | +4.526 |
)=( | +4.479 |
Neg logit contributions | |
imilar | -7.000 |
aiman | -6.871 |
Iro | -6.786 |
200000 | -6.511 |
arius | -6.470 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
doct | +2.412 |
nton | +2.312 |
Doct | +2.310 |
)=( | +2.310 |
Omaha | +2.278 |
Neg logit contributions | |
imilar | -3.263 |
aiman | -3.251 |
Iro | -3.207 |
200000 | -3.075 |
annis | -3.034 |
Token | skillet |
Token ID | 41306 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Iro | +3.767 |
aiman | +3.715 |
imilar | +3.702 |
Kara | +3.516 |
200000 | +3.372 |
Neg logit contributions | |
doct | -5.732 |
Doct | -5.660 |
)=( | -5.654 |
nton | -5.500 |
bringing | -5.424 |
Token | ( |
Token ID | 357 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
doct | +1.694 |
)=( | +1.633 |
nton | +1.629 |
Doct | +1.573 |
Omaha | +1.570 |
Neg logit contributions | |
imilar | -2.596 |
aiman | -2.539 |
Iro | -2.526 |
200000 | -2.435 |
annis | -2.409 |
Token | don |
Token ID | 9099 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
doct | +2.970 |
nton | +2.924 |
ey | +2.794 |
)=( | +2.762 |
bringing | +2.592 |
Neg logit contributions | |
Iro | -8.706 |
imilar | -8.689 |
aiman | -8.533 |
insula | -8.223 |
200000 | -8.180 |
Token | � |
Token ID | 447 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
doct | +3.660 |
)=( | +3.551 |
nton | +3.523 |
Doct | +3.269 |
ey | +3.252 |
Neg logit contributions | |
Iro | -7.639 |
imilar | -7.557 |
aiman | -7.535 |
annis | -7.247 |
Kara | -7.210 |
Token | � |
Token ID | 247 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
imilar | +2.344 |
aiman | +2.326 |
Iro | +2.231 |
200000 | +2.150 |
arius | +2.069 |
Neg logit contributions | |
doct | -4.623 |
nton | -4.496 |
Doct | -4.446 |
Omaha | -4.411 |
)=( | -4.322 |
Token | t |
Token ID | 83 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
doct | +2.268 |
nton | +2.223 |
)=( | +2.206 |
Doct | +2.126 |
ey | +2.085 |
Neg logit contributions | |
imilar | -2.771 |
Iro | -2.762 |
aiman | -2.747 |
200000 | -2.588 |
annis | -2.576 |
Token | crowd |
Token ID | 4315 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
doct | +6.687 |
eyeb | +6.031 |
)=( | +5.749 |
canv | +5.163 |
!) | +5.086 |
Neg logit contributions | |
imilar | -23.977 |
Iro | -23.398 |
insula | -22.915 |
bas | -22.740 |
arius | -22.506 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
doct | +2.310 |
)=( | +2.254 |
nton | +2.221 |
Doct | +2.175 |
Omaha | +2.171 |
Neg logit contributions | |
imilar | -2.943 |
aiman | -2.919 |
Iro | -2.885 |
200000 | -2.762 |
annis | -2.750 |
Token | pan |
Token ID | 3425 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
imilar | +0.537 |
aiman | +0.532 |
Iro | +0.531 |
200000 | +0.503 |
annis | +0.497 |
Neg logit contributions | |
doct | -0.515 |
)=( | -0.501 |
nton | -0.499 |
Doct | -0.493 |
Omaha | -0.485 |
Token | ; |
Token ID | 26 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
doct | +4.536 |
)=( | +4.392 |
nton | +4.344 |
ey | +4.170 |
Omaha | +4.118 |
Neg logit contributions | |
aiman | -12.132 |
imilar | -11.813 |
annis | -11.763 |
insula | -11.663 |
Iro | -11.640 |
Token | only |
Token ID | 691 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
imilar | +1.965 |
Iro | +1.951 |
aiman | +1.951 |
200000 | +1.850 |
akov | +1.827 |
Neg logit contributions | |
doct | -1.597 |
)=( | -1.543 |
Doct | -1.540 |
nton | -1.531 |
Omaha | -1.505 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
doct | +1.205 |
)=( | +1.167 |
nton | +1.164 |
Doct | +1.141 |
Omaha | +1.131 |
Neg logit contributions | |
imilar | -1.412 |
aiman | -1.397 |
Iro | -1.390 |
200000 | -1.325 |
annis | -1.310 |
Token | Yet |
Token ID | 6430 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Hume | +8.566 |
Doct | +8.537 |
doct | +8.313 |
Omaha | +8.259 |
)=( | +8.039 |
Neg logit contributions | |
imilar | -11.568 |
aiman | -11.462 |
insula | -10.702 |
sabotage | -10.608 |
annis | -10.601 |
Token | this |
Token ID | 428 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
doct | +8.977 |
Hume | +8.506 |
Doct | +8.473 |
Omaha | +8.268 |
)=( | +8.187 |
Neg logit contributions | |
imilar | -12.144 |
aiman | -11.806 |
Iro | -11.315 |
insula | -11.079 |
200000 | -11.078 |
Token | is |
Token ID | 318 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
doct | +0.855 |
)=( | +0.829 |
nton | +0.827 |
Doct | +0.811 |
Omaha | +0.802 |
Neg logit contributions | |
imilar | -1.004 |
aiman | -0.994 |
Iro | -0.991 |
200000 | -0.943 |
annis | -0.932 |
Token | precisely |
Token ID | 10582 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
doct | +6.163 |
nton | +5.814 |
Doct | +5.749 |
Omaha | +5.716 |
)=( | +5.699 |
Neg logit contributions | |
imilar | -7.211 |
aiman | -7.169 |
Iro | -6.900 |
200000 | -6.748 |
annis | -6.708 |
Token | what |
Token ID | 644 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
doct | +6.556 |
nton | +6.156 |
Doct | +6.124 |
Omaha | +6.027 |
Hume | +5.994 |
Neg logit contributions | |
aiman | -9.918 |
imilar | -9.884 |
Iro | -9.454 |
200000 | -9.286 |
annis | -9.272 |
Token | He |
Token ID | 679 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Hume | +14.407 |
doct | +14.099 |
Doct | +13.667 |
Omaha | +13.100 |
Wah | +12.737 |
Neg logit contributions | |
imilar | -15.166 |
aiman | -14.602 |
insula | -14.267 |
200000 | -13.901 |
henko | -13.863 |
Token | ikes |
Token ID | 7938 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
doct | +4.610 |
nton | +4.559 |
)=( | +4.440 |
ey | +4.337 |
Doct | +4.232 |
Neg logit contributions | |
Iro | -5.812 |
aiman | -5.680 |
imilar | -5.648 |
Kara | -5.406 |
200000 | -5.395 |
Token | claims |
Token ID | 3667 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
doct | +3.983 |
nton | +3.719 |
Doct | +3.672 |
)=( | +3.667 |
Omaha | +3.567 |
Neg logit contributions | |
imilar | -4.944 |
aiman | -4.865 |
Iro | -4.816 |
200000 | -4.718 |
annis | -4.555 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
doct | +5.377 |
Doct | +5.076 |
)=( | +5.071 |
nton | +4.962 |
Omaha | +4.893 |
Neg logit contributions | |
imilar | -8.044 |
aiman | -7.908 |
Iro | -7.656 |
200000 | -7.464 |
akov | -7.412 |
Token | In |
Token ID | 554 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Doct | +8.350 |
Hume | +8.318 |
doct | +8.077 |
Omaha | +8.045 |
)=( | +7.902 |
Neg logit contributions | |
imilar | -11.619 |
aiman | -11.493 |
insula | -10.699 |
akov | -10.606 |
sabotage | -10.599 |
Token | of |
Token ID | 286 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
doct | +2.635 |
)=( | +2.483 |
nton | +2.455 |
Doct | +2.427 |
Omaha | +2.378 |
Neg logit contributions | |
imilar | -4.657 |
aiman | -4.634 |
Iro | -4.563 |
200000 | -4.413 |
annis | -4.405 |
Token | all |
Token ID | 477 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
imilar | +0.198 |
aiman | +0.196 |
Iro | +0.196 |
200000 | +0.186 |
annis | +0.183 |
Neg logit contributions | |
doct | -0.186 |
nton | -0.180 |
)=( | -0.180 |
Doct | -0.177 |
Omaha | -0.175 |
Token | faiths |
Token ID | 43028 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
doct | +2.996 |
)=( | +2.688 |
Doct | +2.665 |
nton | +2.557 |
Omaha | +2.553 |
Neg logit contributions | |
aiman | -6.994 |
imilar | -6.994 |
Iro | -6.863 |
200000 | -6.785 |
annis | -6.727 |
Token | , |
Token ID | 11 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
imilar | +1.591 |
Iro | +1.565 |
aiman | +1.564 |
200000 | +1.469 |
annis | +1.457 |
Neg logit contributions | |
doct | -1.573 |
nton | -1.539 |
)=( | -1.538 |
Doct | -1.503 |
Omaha | -1.492 |
Token | colors |
Token ID | 7577 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
doct | +4.756 |
)=( | +4.561 |
Doct | +4.419 |
nton | +4.401 |
Omaha | +4.359 |
Neg logit contributions | |
imilar | -5.190 |
aiman | -5.147 |
Iro | -4.998 |
akov | -4.912 |
200000 | -4.896 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
doct | +3.375 |
nton | +3.175 |
)=( | +3.151 |
Doct | +3.115 |
Omaha | +3.094 |
Neg logit contributions | |
aiman | -5.118 |
imilar | -5.107 |
Iro | -5.023 |
200000 | -4.864 |
annis | -4.814 |
Token | cre |
Token ID | 1126 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
doct | +6.978 |
eyeb | +5.640 |
cre | +5.386 |
Cre | +5.264 |
canv | +5.118 |
Neg logit contributions | |
insula | -23.592 |
akov | -23.461 |
aiman | -23.335 |
imilar | -22.861 |
BAT | -22.515 |
Token | eds |
Token ID | 5379 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
doct | +7.044 |
nton | +6.952 |
)=( | +6.719 |
ned | +6.619 |
glers | +6.613 |
Neg logit contributions | |
Iro | -12.511 |
200000 | -12.037 |
imilar | -11.854 |
aiman | -11.826 |
Kara | -11.668 |
Token | in |
Token ID | 287 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
Iro | +6.562 |
imilar | +6.465 |
aiman | +6.339 |
Kara | +6.048 |
annis | +5.771 |
Neg logit contributions | |
nton | -7.873 |
)=( | -7.721 |
doct | -7.622 |
Doct | -7.442 |
Omaha | -7.305 |
Token | America |
Token ID | 2253 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Iro | +2.961 |
imilar | +2.904 |
aiman | +2.884 |
Kara | +2.680 |
200000 | +2.622 |
Neg logit contributions | |
doct | -6.175 |
nton | -6.144 |
Doct | -6.064 |
)=( | -6.044 |
glers | -5.975 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
imilar | +3.653 |
Iro | +3.652 |
aiman | +3.572 |
200000 | +3.378 |
Kara | +3.347 |
Neg logit contributions | |
)=( | -4.997 |
doct | -4.988 |
nton | -4.956 |
Doct | -4.775 |
Omaha | -4.697 |
Token | OV |
Token ID | 8874 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
imilar | +0.830 |
aiman | +0.821 |
Iro | +0.817 |
200000 | +0.789 |
annis | +0.777 |
Neg logit contributions | |
doct | -0.457 |
nton | -0.434 |
)=( | -0.434 |
Doct | -0.426 |
Omaha | -0.420 |
Token | even |
Token ID | 772 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
aiman | +2.260 |
imilar | +2.254 |
Iro | +2.250 |
200000 | +2.130 |
Kara | +2.078 |
Neg logit contributions | |
doct | -2.518 |
nton | -2.426 |
)=( | -2.422 |
Doct | -2.419 |
Omaha | -2.330 |
Token | double |
Token ID | 4274 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
doct | +5.626 |
nton | +4.973 |
eyeb | +4.813 |
Omaha | +4.723 |
Doct | +4.145 |
Neg logit contributions | |
imilar | -20.577 |
aiman | -19.938 |
insula | -19.894 |
akov | -19.872 |
annis | -19.483 |
Token | or |
Token ID | 393 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
doct | +3.375 |
)=( | +3.193 |
nton | +3.190 |
Omaha | +3.143 |
Doct | +3.108 |
Neg logit contributions | |
aiman | -4.418 |
imilar | -4.397 |
Iro | -4.278 |
annis | -4.108 |
akov | -4.106 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
doct | +6.523 |
)=( | +6.016 |
Omaha | +5.837 |
eyeb | +5.799 |
nton | +5.763 |
Neg logit contributions | |
aiman | -14.406 |
insula | -14.366 |
imilar | -14.236 |
akov | -13.806 |
Iro | -13.508 |
Token | x |
Token ID | 87 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
)=( | +3.693 |
ey | +3.683 |
nton | +3.620 |
doct | +3.492 |
Ey | +3.340 |
Neg logit contributions | |
aiman | -19.721 |
Iro | -19.535 |
imilar | -19.201 |
insula | -19.141 |
annis | -18.751 |
Token | 1080 |
Token ID | 17729 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
doct | +5.376 |
)=( | +5.040 |
Doct | +4.351 |
nton | +4.208 |
eyeb | +3.998 |
Neg logit contributions | |
insula | -23.749 |
akov | -23.344 |
aiman | -23.228 |
imilar | -23.144 |
arius | -22.997 |
Token | P |
Token ID | 47 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
)=( | +6.523 |
doct | +6.041 |
nton | +5.975 |
Ey | +5.930 |
Omaha | +5.753 |
Neg logit contributions | |
aiman | -17.243 |
Iro | -16.666 |
imilar | -16.560 |
insula | -16.478 |
akov | -16.463 |
Token | resolution |
Token ID | 6323 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
doct | +6.502 |
)=( | +6.333 |
nton | +6.128 |
eyeb | +5.808 |
Omaha | +5.741 |
Neg logit contributions | |
imilar | -17.545 |
aiman | -17.164 |
Iro | -16.588 |
akov | -16.375 |
arius | -16.164 |
Token | you |
Token ID | 345 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
doct | +3.225 |
)=( | +3.068 |
nton | +2.985 |
Doct | +2.914 |
Omaha | +2.872 |
Neg logit contributions | |
imilar | -5.261 |
aiman | -5.183 |
Iro | -5.123 |
annis | -4.994 |
insula | -4.895 |
Token | will |
Token ID | 481 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
doct | +2.030 |
nton | +1.923 |
)=( | +1.921 |
Doct | +1.841 |
Omaha | +1.754 |
Neg logit contributions | |
imilar | -4.463 |
Iro | -4.436 |
aiman | -4.426 |
200000 | -4.240 |
annis | -4.216 |
Token | would |
Token ID | 561 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
doct | +3.660 |
)=( | +3.553 |
nton | +3.487 |
Doct | +3.446 |
Omaha | +3.413 |
Neg logit contributions | |
imilar | -4.347 |
aiman | -4.274 |
Iro | -4.243 |
200000 | -4.092 |
annis | -4.041 |
Token | much |
Token ID | 881 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
doct | +2.920 |
)=( | +2.822 |
nton | +2.796 |
Doct | +2.770 |
Omaha | +2.735 |
Neg logit contributions | |
imilar | -3.043 |
aiman | -3.001 |
Iro | -2.981 |
200000 | -2.854 |
annis | -2.829 |
Token | prefer |
Token ID | 4702 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
doct | +1.341 |
)=( | +1.295 |
nton | +1.292 |
Doct | +1.268 |
Omaha | +1.255 |
Neg logit contributions | |
imilar | -1.629 |
aiman | -1.612 |
Iro | -1.604 |
200000 | -1.531 |
annis | -1.513 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
doct | +6.685 |
)=( | +6.411 |
Doct | +6.299 |
nton | +6.060 |
Omaha | +6.009 |
Neg logit contributions | |
aiman | -8.479 |
imilar | -8.443 |
Iro | -8.179 |
annis | -8.108 |
200000 | -8.045 |
Token | lower |
Token ID | 2793 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
doct | +10.843 |
Doct | +10.110 |
eyeb | +9.777 |
)=( | +9.627 |
Omaha | +9.489 |
Neg logit contributions | |
aiman | -11.391 |
imilar | -11.246 |
henko | -11.001 |
insula | -10.799 |
annis | -10.709 |
Token | res |
Token ID | 581 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
doct | +10.637 |
)=( | +9.358 |
Doct | +9.315 |
mater | +9.190 |
eyeb | +9.180 |
Neg logit contributions | |
aiman | -13.733 |
imilar | -13.592 |
akov | -12.812 |
henko | -12.714 |
annis | -12.682 |
Token | without |
Token ID | 1231 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
doct | +13.307 |
eyeb | +12.113 |
Doct | +12.049 |
)=( | +11.942 |
mater | +11.862 |
Neg logit contributions | |
imilar | -15.162 |
aiman | -14.853 |
arius | -14.716 |
henko | -14.678 |
annis | -14.360 |
Token | screen |
Token ID | 3159 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
doct | +7.125 |
)=( | +6.706 |
Doct | +6.504 |
Omaha | +6.475 |
eyeb | +6.279 |
Neg logit contributions | |
imilar | -8.914 |
aiman | -8.812 |
Iro | -8.405 |
200000 | -8.343 |
henko | -8.338 |
Token | door |
Token ID | 3420 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
doct | +5.890 |
Doct | +5.339 |
)=( | +5.276 |
nton | +5.146 |
eyeb | +5.131 |
Neg logit contributions | |
imilar | -11.558 |
aiman | -11.406 |
200000 | -11.067 |
annis | -11.066 |
Iro | -11.062 |
Token | effect |
Token ID | 1245 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
doct | +3.391 |
)=( | +3.187 |
nton | +3.148 |
Doct | +3.113 |
Omaha | +3.046 |
Neg logit contributions | |
imilar | -5.362 |
aiman | -5.282 |
Iro | -5.224 |
200000 | -5.089 |
annis | -5.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
doct | +4.050 |
)=( | +3.897 |
nton | +3.808 |
Doct | +3.780 |
Omaha | +3.730 |
Neg logit contributions | |
imilar | -5.016 |
aiman | -4.962 |
Iro | -4.886 |
200000 | -4.722 |
annis | -4.695 |
Token | , |
Token ID | 11 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
)=( | +7.500 |
doct | +7.495 |
Omaha | +7.087 |
nton | +7.060 |
Doct | +6.837 |
Neg logit contributions | |
aiman | -11.161 |
imilar | -11.159 |
Iro | -10.856 |
200000 | -10.563 |
annis | -10.396 |
Token | updated |
Token ID | 6153 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
doct | +6.421 |
)=( | +6.064 |
Doct | +6.015 |
Omaha | +5.986 |
nton | +5.967 |
Neg logit contributions | |
imilar | -6.789 |
aiman | -6.705 |
Iro | -6.466 |
200000 | -6.389 |
annis | -6.325 |
Token | at |
Token ID | 379 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
doct | +6.974 |
)=( | +6.664 |
Doct | +6.616 |
nton | +6.588 |
Omaha | +6.569 |
Neg logit contributions | |
imilar | -6.134 |
aiman | -6.035 |
Iro | -5.816 |
annis | -5.696 |
200000 | -5.679 |
Token | 10 |
Token ID | 838 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
doct | +8.060 |
Doct | +7.600 |
Omaha | +7.583 |
nton | +7.469 |
)=( | +7.446 |
Neg logit contributions | |
imilar | -9.262 |
aiman | -9.028 |
Iro | -8.764 |
annis | -8.675 |
insula | -8.666 |
Token | : |
Token ID | 25 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
doct | +5.499 |
)=( | +5.295 |
nton | +5.236 |
Omaha | +5.031 |
Doct | +4.918 |
Neg logit contributions | |
imilar | -11.707 |
aiman | -11.410 |
Iro | -11.382 |
insula | -11.009 |
annis | -10.796 |
Token | 17 |
Token ID | 1558 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
doct | +4.664 |
nton | +4.539 |
)=( | +4.509 |
Doct | +4.420 |
ey | +4.362 |
Neg logit contributions | |
imilar | -5.523 |
aiman | -5.410 |
Iro | -5.259 |
annis | -5.151 |
insula | -5.130 |
Token | UTC |
Token ID | 18119 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
doct | +12.264 |
Omaha | +11.819 |
)=( | +11.693 |
noon | +11.559 |
Doct | +11.522 |
Neg logit contributions | |
aiman | -15.525 |
imilar | -15.457 |
Iro | -14.747 |
insula | -14.469 |
arius | -14.312 |
Token | ): |
Token ID | 2599 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
)=( | +7.732 |
doct | +7.638 |
Omaha | +7.370 |
nton | +7.351 |
Doct | +7.148 |
Neg logit contributions | |
imilar | -10.256 |
aiman | -10.112 |
Iro | -9.798 |
200000 | -9.578 |
annis | -9.557 |
Token | PA |
Token ID | 4537 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
doct | +3.216 |
)=( | +3.107 |
nton | +3.080 |
Doct | +3.043 |
Omaha | +3.010 |
Neg logit contributions | |
imilar | -3.680 |
aiman | -3.650 |
Iro | -3.613 |
200000 | -3.456 |
annis | -3.437 |
Token | UL |
Token ID | 6239 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
doct | +0.489 |
)=( | +0.471 |
nton | +0.469 |
Doct | +0.461 |
Omaha | +0.456 |
Neg logit contributions | |
imilar | -0.605 |
aiman | -0.601 |
Iro | -0.598 |
200000 | -0.570 |
annis | -0.564 |
Token | I |
Token ID | 40 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
doct | +5.481 |
nton | +5.258 |
Doct | +5.223 |
)=( | +5.205 |
Omaha | +5.151 |
Neg logit contributions | |
imilar | -6.173 |
aiman | -5.998 |
Iro | -5.900 |
annis | -5.735 |
200000 | -5.675 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
doct | +8.302 |
)=( | +7.467 |
nton | +7.425 |
Doct | +7.260 |
mater | +6.964 |
Neg logit contributions | |
imilar | -11.643 |
akov | -11.093 |
aiman | -10.981 |
insula | -10.735 |
Iro | -10.706 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
doct | +6.816 |
Doct | +6.098 |
)=( | +6.064 |
nton | +6.013 |
Omaha | +5.799 |
Neg logit contributions | |
imilar | -10.354 |
aiman | -10.280 |
200000 | -10.075 |
Iro | -10.035 |
akov | -9.919 |
Token | What |
Token ID | 1867 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Doct | +8.366 |
Hume | +8.153 |
doct | +8.141 |
Omaha | +7.954 |
)=( | +7.926 |
Neg logit contributions | |
imilar | -11.319 |
aiman | -11.118 |
insula | -10.400 |
annis | -10.348 |
sabotage | -10.318 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
doct | +14.038 |
Hume | +13.825 |
Doct | +13.401 |
Omaha | +12.880 |
)=( | +12.728 |
Neg logit contributions | |
imilar | -15.462 |
aiman | -15.360 |
insula | -14.908 |
200000 | -14.350 |
henko | -14.151 |
Token | these |
Token ID | 777 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
doct | +14.468 |
Hume | +13.969 |
Doct | +13.434 |
nton | +12.898 |
Omaha | +12.755 |
Neg logit contributions | |
imilar | -15.307 |
aiman | -14.877 |
200000 | -14.460 |
insula | -14.364 |
akov | -13.930 |
Token | conceptions |
Token ID | 49849 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
doct | +11.246 |
Doct | +9.974 |
)=( | +9.868 |
nton | +9.793 |
Hume | +9.703 |
Neg logit contributions | |
imilar | -11.132 |
aiman | -11.090 |
200000 | -10.715 |
akov | -10.663 |
arius | -10.655 |
Token | better |
Token ID | 1365 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
doct | +13.674 |
ey | +12.282 |
mater | +12.237 |
)=( | +11.853 |
Hume | +11.782 |
Neg logit contributions | |
200000 | -16.340 |
aiman | -15.969 |
arius | -15.118 |
insula | -15.104 |
imilar | -14.883 |
Token | is |
Token ID | 318 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
doct | +8.148 |
)=( | +7.660 |
nton | +7.524 |
Doct | +7.296 |
ey | +7.107 |
Neg logit contributions | |
imilar | -12.172 |
Iro | -12.030 |
200000 | -11.953 |
aiman | -11.871 |
akov | -11.784 |
Token | that |
Token ID | 326 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
doct | +7.087 |
Doct | +6.596 |
Hume | +6.473 |
)=( | +6.473 |
nton | +6.469 |
Neg logit contributions | |
aiman | -8.830 |
imilar | -8.796 |
Iro | -8.612 |
annis | -8.338 |
200000 | -8.337 |
Token | they |
Token ID | 484 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
doct | +8.215 |
Doct | +7.569 |
Hume | +7.533 |
)=( | +7.412 |
nton | +7.395 |
Neg logit contributions | |
imilar | -10.426 |
aiman | -10.364 |
200000 | -10.049 |
Iro | -9.967 |
annis | -9.806 |
Token | are |
Token ID | 389 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
doct | +4.691 |
)=( | +4.422 |
nton | +4.413 |
Doct | +4.342 |
Omaha | +4.184 |
Neg logit contributions | |
imilar | -5.012 |
aiman | -4.958 |
Iro | -4.885 |
200000 | -4.797 |
akov | -4.624 |
Token | ], |
Token ID | 4357 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
doct | +3.277 |
)=( | +3.133 |
Omaha | +3.106 |
nton | +3.038 |
Doct | +3.026 |
Neg logit contributions | |
imilar | -7.924 |
Iro | -7.917 |
aiman | -7.881 |
annis | -7.599 |
200000 | -7.552 |
Token | � |
Token ID | 447 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
doct | +0.105 |
nton | +0.101 |
)=( | +0.101 |
Doct | +0.098 |
Omaha | +0.097 |
Neg logit contributions | |
imilar | -0.151 |
aiman | -0.149 |
Iro | -0.149 |
200000 | -0.142 |
annis | -0.140 |
Token | � |
Token ID | 251 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
imilar | +4.215 |
aiman | +4.157 |
Iro | +4.131 |
bas | +3.921 |
200000 | +3.872 |
Neg logit contributions | |
doct | -5.200 |
nton | -5.076 |
)=( | -4.927 |
Omaha | -4.918 |
Doct | -4.890 |
Token | D |
Token ID | 360 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
doct | +3.230 |
nton | +3.086 |
Doct | +3.073 |
)=( | +3.062 |
Omaha | +3.011 |
Neg logit contributions | |
imilar | -5.102 |
aiman | -5.084 |
Iro | -5.009 |
200000 | -4.886 |
annis | -4.801 |
Token | ang |
Token ID | 648 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
doct | +5.049 |
nton | +4.957 |
)=( | +4.845 |
Omaha | +4.753 |
Doct | +4.748 |
Neg logit contributions | |
Iro | -6.621 |
imilar | -6.550 |
aiman | -6.284 |
200000 | -6.255 |
Kara | -6.079 |
Token | - |
Token ID | 12 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
doct | +4.737 |
nton | +4.573 |
)=( | +4.546 |
Doct | +4.449 |
Omaha | +4.379 |
Neg logit contributions | |
imilar | -7.094 |
Iro | -6.965 |
aiman | -6.910 |
200000 | -6.824 |
annis | -6.579 |
Token | Hall |
Token ID | 34194 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
ey | +7.910 |
Ey | +7.841 |
)=( | +7.636 |
nton | +7.297 |
meyer | +7.075 |
Neg logit contributions | |
Iro | -20.768 |
imilar | -19.817 |
aiman | -19.484 |
annis | -19.410 |
insula | -19.399 |
Token | er |
Token ID | 263 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
nton | +4.129 |
)=( | +4.038 |
doct | +3.963 |
ey | +3.930 |
meyer | +3.656 |
Neg logit contributions | |
Iro | -9.582 |
imilar | -9.276 |
aiman | -9.214 |
200000 | -9.107 |
annis | -8.883 |
Token | says |
Token ID | 1139 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
imilar | +0.580 |
aiman | +0.576 |
Iro | +0.572 |
200000 | +0.541 |
annis | +0.538 |
Neg logit contributions | |
doct | -0.566 |
)=( | -0.554 |
nton | -0.547 |
Doct | -0.541 |
Omaha | -0.537 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
imilar | +0.045 |
aiman | +0.045 |
Iro | +0.045 |
200000 | +0.043 |
annis | +0.042 |
Neg logit contributions | |
doct | -0.042 |
)=( | -0.041 |
nton | -0.041 |
Doct | -0.040 |
Omaha | -0.039 |
Token | � |
Token ID | 564 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
doct | +3.662 |
Doct | +3.556 |
)=( | +3.540 |
nton | +3.499 |
Omaha | +3.464 |
Neg logit contributions | |
imilar | -4.857 |
aiman | -4.842 |
Iro | -4.673 |
200000 | -4.553 |
annis | -4.547 |
Token | in |
Token ID | 287 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
aiman | +2.645 |
Iro | +2.637 |
imilar | +2.597 |
200000 | +2.484 |
Kara | +2.454 |
Neg logit contributions | |
doct | -2.244 |
)=( | -2.221 |
nton | -2.182 |
Doct | -2.171 |
Omaha | -2.068 |
Token | Chicago |
Token ID | 4842 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
Iro | +1.940 |
aiman | +1.920 |
imilar | +1.911 |
Kara | +1.808 |
200000 | +1.801 |
Neg logit contributions | |
doct | -1.549 |
)=( | -1.527 |
nton | -1.493 |
Doct | -1.487 |
bringing | -1.400 |
Token | hasn |
Token ID | 5818 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
doct | +0.036 |
)=( | +0.035 |
nton | +0.035 |
Doct | +0.035 |
Omaha | +0.034 |
Neg logit contributions | |
aiman | -0.046 |
imilar | -0.046 |
Iro | -0.046 |
200000 | -0.044 |
annis | -0.043 |
Token | 't |
Token ID | 470 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
imilar | +2.416 |
Iro | +2.402 |
aiman | +2.392 |
200000 | +2.325 |
bas | +2.248 |
Neg logit contributions | |
doct | -2.368 |
)=( | -2.285 |
nton | -2.262 |
Doct | -2.257 |
Omaha | -2.246 |
Token | gone |
Token ID | 3750 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
doct | +1.149 |
)=( | +1.115 |
nton | +1.109 |
Doct | +1.086 |
Omaha | +1.073 |
Neg logit contributions | |
imilar | -1.561 |
aiman | -1.545 |
Iro | -1.539 |
200000 | -1.472 |
annis | -1.452 |
Token | as |
Token ID | 355 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
imilar | +6.231 |
aiman | +6.053 |
Iro | +5.983 |
Kara | +5.896 |
bas | +5.715 |
Neg logit contributions | |
)=( | -6.746 |
nton | -6.652 |
doct | -6.410 |
Doct | -6.237 |
Omaha | -6.204 |
Token | planned |
Token ID | 6027 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
imilar | +12.958 |
Kara | +12.744 |
Iro | +12.661 |
bas | +11.508 |
aiman | +11.478 |
Neg logit contributions | |
)=( | -19.149 |
roying | -18.513 |
nton | -18.365 |
clud | -17.804 |
bringing | -17.662 |
Token | so |
Token ID | 523 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
aiman | +6.413 |
imilar | +6.297 |
Iro | +6.203 |
200000 | +5.973 |
Kara | +5.972 |
Neg logit contributions | |
)=( | -8.137 |
doct | -7.988 |
nton | -7.907 |
Doct | -7.651 |
bringing | -7.532 |
Token | far |
Token ID | 1290 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
imilar | +4.844 |
aiman | +4.641 |
Iro | +4.400 |
akov | +4.045 |
Kara | +3.854 |
Neg logit contributions | |
doct | -12.879 |
)=( | -12.600 |
nton | -12.586 |
Doct | -12.435 |
ey | -12.155 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
aiman | +5.168 |
imilar | +5.130 |
Iro | +5.063 |
200000 | +4.774 |
Kara | +4.698 |
Neg logit contributions | |
)=( | -6.250 |
doct | -6.214 |
nton | -6.102 |
Doct | -5.941 |
Omaha | -5.771 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
doct | +1.028 |
)=( | +0.993 |
nton | +0.991 |
Doct | +0.974 |
Omaha | +0.966 |
Neg logit contributions | |
imilar | -1.280 |
aiman | -1.267 |
Iro | -1.255 |
200000 | -1.202 |
annis | -1.190 |
Token | danced |
Token ID | 39480 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Iro | +5.583 |
imilar | +5.378 |
aiman | +5.260 |
Kara | +5.232 |
sabotage | +5.193 |
Neg logit contributions | |
nton | -5.061 |
)=( | -5.027 |
doct | -4.835 |
Doct | -4.758 |
Omaha | -4.752 |
Token | around |
Token ID | 1088 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Iro | +6.563 |
aiman | +6.385 |
Kara | +6.323 |
imilar | +6.267 |
sabotage | +6.041 |
Neg logit contributions | |
nton | -6.679 |
)=( | -6.597 |
doct | -6.364 |
Doct | -6.128 |
bringing | -6.068 |
Token | their |
Token ID | 511 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Iro | +11.242 |
Kara | +10.960 |
aiman | +10.320 |
sabotage | +10.163 |
imilar | +9.951 |
Neg logit contributions | |
nton | -11.403 |
)=( | -10.523 |
doct | -10.393 |
Doct | -9.829 |
glers | -9.671 |
Token | intense |
Token ID | 8157 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Iro | +7.588 |
imilar | +7.297 |
aiman | +7.227 |
Kara | +7.223 |
sabotage | +7.030 |
Neg logit contributions | |
nton | -6.535 |
)=( | -6.372 |
doct | -6.189 |
Doct | -5.940 |
Omaha | -5.859 |
Token | feelings |
Token ID | 7666 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Iro | +10.429 |
Kara | +10.076 |
sabotage | +9.734 |
imilar | +9.553 |
aiman | +9.459 |
Neg logit contributions | |
nton | -9.925 |
doct | -9.500 |
)=( | -9.472 |
Omaha | -8.949 |
Doct | -8.890 |
Token | for |
Token ID | 329 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Iro | +8.243 |
aiman | +8.145 |
imilar | +8.029 |
Kara | +7.876 |
sabotage | +7.671 |
Neg logit contributions | |
nton | -8.710 |
doct | -8.578 |
)=( | -8.390 |
Omaha | -8.387 |
Doct | -8.220 |
Token | one |
Token ID | 530 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Iro | +16.774 |
Kara | +16.590 |
Lena | +15.181 |
Archer | +14.933 |
aiman | +14.566 |
Neg logit contributions | |
nton | -16.797 |
)=( | -15.840 |
doct | -15.520 |
glers | -14.209 |
olphins | -13.839 |
Token | another |
Token ID | 1194 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Iro | +10.768 |
Kara | +10.083 |
imilar | +9.781 |
aiman | +9.651 |
annis | +9.198 |
Neg logit contributions | |
nton | -16.301 |
)=( | -15.979 |
glers | -15.419 |
doct | -14.830 |
Doct | -14.484 |
Token | for |
Token ID | 329 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
aiman | +6.449 |
Iro | +6.368 |
imilar | +6.211 |
Kara | +6.115 |
200000 | +5.954 |
Neg logit contributions | |
doct | -6.743 |
)=( | -6.647 |
nton | -6.635 |
Doct | -6.506 |
Omaha | -6.386 |
Token | almost |
Token ID | 2048 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Iro | +6.070 |
imilar | +5.891 |
aiman | +5.862 |
Kara | +5.774 |
sabotage | +5.634 |
Neg logit contributions | |
nton | -5.960 |
)=( | -5.904 |
doct | -5.790 |
Doct | -5.646 |
glers | -5.567 |
Token | three |
Token ID | 1115 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
Iro | +5.598 |
imilar | +5.423 |
aiman | +5.375 |
200000 | +5.303 |
Kara | +5.256 |
Neg logit contributions | |
)=( | -5.696 |
nton | -5.618 |
doct | -5.518 |
Doct | -5.346 |
glers | -5.317 |
Token | feature |
Token ID | 3895 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
doct | +1.069 |
)=( | +1.030 |
nton | +1.028 |
Doct | +1.009 |
Omaha | +1.000 |
Neg logit contributions | |
imilar | -1.317 |
aiman | -1.303 |
Iro | -1.294 |
200000 | -1.237 |
annis | -1.223 |
Token | of |
Token ID | 286 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
imilar | +1.170 |
aiman | +1.161 |
Iro | +1.158 |
200000 | +1.098 |
annis | +1.095 |
Neg logit contributions | |
doct | -0.909 |
)=( | -0.887 |
nton | -0.878 |
Doct | -0.863 |
Omaha | -0.846 |
Token | politics |
Token ID | 4819 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Iro | +3.855 |
imilar | +3.800 |
aiman | +3.798 |
Kara | +3.655 |
sabotage | +3.573 |
Neg logit contributions | |
doct | -4.199 |
)=( | -4.195 |
nton | -4.111 |
Doct | -4.080 |
Omaha | -3.902 |
Token | , |
Token ID | 11 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
aiman | +5.873 |
Iro | +5.662 |
imilar | +5.653 |
sabotage | +5.550 |
Kara | +5.480 |
Neg logit contributions | |
)=( | -6.866 |
Doct | -6.748 |
doct | -6.731 |
nton | -6.625 |
Omaha | -6.507 |
Token | going |
Token ID | 1016 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
doct | +0.050 |
)=( | +0.049 |
nton | +0.049 |
Doct | +0.048 |
Omaha | +0.047 |
Neg logit contributions | |
imilar | -0.059 |
Iro | -0.058 |
aiman | -0.058 |
200000 | -0.055 |
annis | -0.054 |
Token | as |
Token ID | 355 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Iro | +4.619 |
aiman | +4.596 |
imilar | +4.519 |
sabotage | +4.373 |
Kara | +4.321 |
Neg logit contributions | |
doct | -4.724 |
)=( | -4.723 |
Doct | -4.643 |
nton | -4.604 |
Omaha | -4.442 |
Token | far |
Token ID | 1290 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Iro | +9.833 |
imilar | +9.753 |
aiman | +8.906 |
sabotage | +8.841 |
Kara | +8.693 |
Neg logit contributions | |
)=( | -20.724 |
bringing | -19.899 |
roying | -19.800 |
doct | -19.737 |
Ey | -19.587 |
Token | back |
Token ID | 736 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Iro | +6.472 |
imilar | +6.436 |
aiman | +6.342 |
Kara | +5.924 |
sabotage | +5.867 |
Neg logit contributions | |
doct | -9.410 |
Doct | -9.390 |
)=( | -9.375 |
nton | -9.137 |
glers | -8.959 |
Token | as |
Token ID | 355 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Iro | +4.333 |
imilar | +4.259 |
aiman | +4.209 |
200000 | +4.024 |
Kara | +3.974 |
Neg logit contributions | |
doct | -6.261 |
Doct | -6.205 |
)=( | -6.189 |
nton | -6.189 |
Omaha | -5.951 |
Token | the |
Token ID | 262 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Iro | +1.192 |
imilar | +1.177 |
aiman | +1.165 |
200000 | +1.112 |
Kara | +1.102 |
Neg logit contributions | |
doct | -1.219 |
)=( | -1.211 |
nton | -1.182 |
Doct | -1.169 |
Omaha | -1.141 |
Token | financial |
Token ID | 3176 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
doct | +3.285 |
nton | +3.134 |
Omaha | +3.104 |
)=( | +3.084 |
Doct | +3.078 |
Neg logit contributions | |
imilar | -3.682 |
aiman | -3.640 |
Iro | -3.507 |
200000 | -3.423 |
annis | -3.387 |
Token | Lat |
Token ID | 5476 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
Iro | +2.139 |
imilar | +2.103 |
aiman | +2.102 |
Kara | +1.986 |
200000 | +1.968 |
Neg logit contributions | |
doct | -1.988 |
)=( | -1.971 |
nton | -1.928 |
Doct | -1.878 |
bringing | -1.833 |
Token | robe |
Token ID | 25481 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
aiman | +0.894 |
imilar | +0.888 |
Iro | +0.880 |
annis | +0.826 |
200000 | +0.816 |
Neg logit contributions | |
doct | -1.096 |
)=( | -1.084 |
Doct | -1.044 |
Omaha | -1.041 |
nton | -1.039 |
Token | valley |
Token ID | 19272 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Iro | +3.193 |
aiman | +3.175 |
imilar | +3.148 |
200000 | +3.010 |
Kara | +2.989 |
Neg logit contributions | |
doct | -2.679 |
)=( | -2.657 |
Doct | -2.554 |
nton | -2.547 |
Omaha | -2.507 |
Token | could |
Token ID | 714 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Iro | +4.758 |
aiman | +4.703 |
imilar | +4.567 |
sabotage | +4.441 |
200000 | +4.425 |
Neg logit contributions | |
)=( | -4.655 |
doct | -4.629 |
nton | -4.599 |
Doct | -4.577 |
glers | -4.461 |
Token | close |
Token ID | 1969 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
sabotage | +5.197 |
Iro | +5.093 |
200000 | +4.892 |
imilar | +4.886 |
aiman | +4.881 |
Neg logit contributions | |
)=( | -6.937 |
doct | -6.474 |
bringing | -6.429 |
nton | -6.400 |
Omaha | -6.385 |
Token | as |
Token ID | 355 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Iro | +5.146 |
aiman | +5.061 |
imilar | +4.882 |
sabotage | +4.851 |
Kara | +4.813 |
Neg logit contributions | |
doct | -4.928 |
)=( | -4.913 |
nton | -4.894 |
Doct | -4.739 |
bringing | -4.635 |
Token | early |
Token ID | 1903 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Iro | +14.204 |
imilar | +14.070 |
sabotage | +13.979 |
Renew | +12.993 |
Kara | +12.593 |
Neg logit contributions | |
)=( | -15.145 |
nton | -14.915 |
bringing | -14.522 |
Doct | -14.338 |
doct | -14.328 |
Token | as |
Token ID | 355 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Iro | +5.989 |
aiman | +5.736 |
sabotage | +5.525 |
imilar | +5.452 |
200000 | +5.322 |
Neg logit contributions | |
)=( | -10.500 |
nton | -10.470 |
doct | -10.331 |
Doct | -10.179 |
ey | -9.831 |
Token | next |
Token ID | 1306 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Iro | +2.332 |
imilar | +2.281 |
aiman | +2.278 |
200000 | +2.159 |
Kara | +2.148 |
Neg logit contributions | |
doct | -2.533 |
)=( | -2.516 |
nton | -2.491 |
Doct | -2.414 |
bringing | -2.365 |
Token | April |
Token ID | 3035 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
imilar | +0.864 |
Iro | +0.860 |
aiman | +0.856 |
200000 | +0.802 |
Kara | +0.784 |
Neg logit contributions | |
doct | -1.178 |
)=( | -1.167 |
nton | -1.157 |
Doct | -1.143 |
Omaha | -1.126 |
Token | . |
Token ID | 13 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
aiman | +2.655 |
imilar | +2.648 |
Iro | +2.632 |
200000 | +2.537 |
annis | +2.458 |
Neg logit contributions | |
doct | -2.823 |
)=( | -2.756 |
nton | -2.746 |
Doct | -2.695 |
Omaha | -2.660 |
Token | Some |
Token ID | 4366 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
doct | +0.625 |
)=( | +0.605 |
nton | +0.604 |
Doct | +0.592 |
Omaha | +0.589 |
Neg logit contributions | |
imilar | -0.629 |
aiman | -0.621 |
Iro | -0.619 |
200000 | -0.589 |
annis | -0.579 |
Token | implanted |
Token ID | 40740 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
imilar | +2.721 |
aiman | +2.640 |
Iro | +2.629 |
200000 | +2.482 |
akov | +2.477 |
Neg logit contributions | |
nton | -2.638 |
doct | -2.624 |
)=( | -2.583 |
Omaha | -2.559 |
Doct | -2.526 |
Token | devices |
Token ID | 4410 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
doct | +0.517 |
)=( | +0.505 |
nton | +0.505 |
Doct | +0.494 |
Omaha | +0.492 |
Neg logit contributions | |
imilar | -0.409 |
aiman | -0.404 |
Iro | -0.403 |
200000 | -0.378 |
annis | -0.372 |
Token | can |
Token ID | 460 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
imilar | +0.986 |
Iro | +0.977 |
aiman | +0.971 |
200000 | +0.917 |
sabotage | +0.912 |
Neg logit contributions | |
doct | -0.909 |
nton | -0.898 |
)=( | -0.893 |
Omaha | -0.870 |
Doct | -0.868 |
Token | work |
Token ID | 670 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
doct | +0.792 |
)=( | +0.768 |
nton | +0.766 |
Doct | +0.752 |
Omaha | +0.746 |
Neg logit contributions | |
imilar | -0.829 |
aiman | -0.819 |
Iro | -0.815 |
200000 | -0.775 |
annis | -0.764 |
Token | very |
Token ID | 845 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
aiman | +5.361 |
imilar | +5.325 |
Iro | +5.242 |
sabotage | +5.058 |
Kara | +5.040 |
Neg logit contributions | |
nton | -5.396 |
)=( | -5.275 |
doct | -5.236 |
Omaha | -5.137 |
Doct | -5.038 |
Token | well |
Token ID | 880 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
imilar | +12.472 |
Kara | +11.995 |
sabotage | +11.989 |
Iro | +11.986 |
aiman | +11.331 |
Neg logit contributions | |
bringing | -16.897 |
nton | -16.812 |
)=( | -16.391 |
Omaha | -15.467 |
noon | -15.359 |
Token | and |
Token ID | 290 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
imilar | +2.539 |
aiman | +2.526 |
Iro | +2.483 |
200000 | +2.365 |
Kara | +2.334 |
Neg logit contributions | |
doct | -2.418 |
nton | -2.407 |
)=( | -2.383 |
Omaha | -2.343 |
Doct | -2.311 |
Token | last |
Token ID | 938 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Iro | +4.411 |
imilar | +4.405 |
aiman | +4.345 |
sabotage | +4.203 |
Kara | +4.188 |
Neg logit contributions | |
nton | -4.474 |
doct | -4.378 |
)=( | -4.318 |
Omaha | -4.238 |
Doct | -4.126 |
Token | very |
Token ID | 845 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
doct | +2.159 |
)=( | +2.083 |
nton | +2.067 |
Doct | +2.035 |
Omaha | +2.012 |
Neg logit contributions | |
imilar | -2.610 |
aiman | -2.576 |
Iro | -2.565 |
200000 | -2.454 |
annis | -2.420 |
Token | long |
Token ID | 890 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
imilar | +4.762 |
aiman | +4.600 |
Iro | +4.576 |
Kara | +4.363 |
annis | +4.332 |
Neg logit contributions | |
nton | -8.222 |
doct | -8.196 |
)=( | -8.151 |
Omaha | -8.084 |
Doct | -8.076 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Iro | +4.458 |
imilar | +4.387 |
aiman | +4.331 |
Kara | +4.191 |
200000 | +4.157 |
Neg logit contributions | |
doct | -4.261 |
)=( | -4.192 |
nton | -4.180 |
Doct | -4.053 |
Omaha | -4.032 |
Token | Kodi |
Token ID | 44129 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Iro | +5.345 |
imilar | +5.219 |
Kara | +5.112 |
aiman | +5.007 |
200000 | +4.947 |
Neg logit contributions | |
doct | -5.907 |
nton | -5.739 |
Doct | -5.669 |
)=( | -5.641 |
glers | -5.519 |
Token | 17 |
Token ID | 1596 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
doct | +0.200 |
nton | +0.193 |
)=( | +0.193 |
Doct | +0.190 |
Omaha | +0.187 |
Neg logit contributions | |
imilar | -0.199 |
Iro | -0.197 |
aiman | -0.197 |
200000 | -0.186 |
annis | -0.184 |
Token | Krypt |
Token ID | 44679 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
Iro | +4.009 |
imilar | +3.873 |
aiman | +3.834 |
Kara | +3.770 |
200000 | +3.683 |
Neg logit contributions | |
doct | -4.328 |
nton | -4.179 |
)=( | -4.178 |
Doct | -4.125 |
Omaha | -4.055 |
Token | on |
Token ID | 261 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
imilar | +4.717 |
Iro | +4.622 |
aiman | +4.520 |
akov | +4.442 |
200000 | +4.421 |
Neg logit contributions | |
doct | -6.986 |
)=( | -6.836 |
Omaha | -6.701 |
Doct | -6.675 |
glers | -6.589 |
Token | as |
Token ID | 355 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Iro | +3.710 |
imilar | +3.588 |
aiman | +3.581 |
Kara | +3.442 |
200000 | +3.415 |
Neg logit contributions | |
doct | -3.839 |
)=( | -3.702 |
nton | -3.688 |
Doct | -3.648 |
Omaha | -3.561 |
Token | dexter |
Token ID | 44405 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
imilar | +14.567 |
Iro | +13.899 |
Kara | +13.757 |
200000 | +12.830 |
Bash | +12.798 |
Neg logit contributions | |
nton | -14.357 |
doct | -13.702 |
Omaha | -13.374 |
Doct | -13.354 |
)=( | -13.350 |
Token | ously |
Token ID | 3481 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
imilar | +5.489 |
Iro | +5.425 |
aiman | +5.287 |
arius | +5.189 |
200000 | +5.150 |
Neg logit contributions | |
doct | -5.793 |
)=( | -5.684 |
Omaha | -5.658 |
Doct | -5.628 |
nton | -5.554 |
Token | as |
Token ID | 355 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
imilar | +9.823 |
Iro | +9.801 |
sabotage | +9.320 |
200000 | +9.290 |
Kara | +9.136 |
Neg logit contributions | |
)=( | -12.529 |
nton | -12.374 |
Omaha | -12.075 |
bringing | -11.898 |
Doct | -11.887 |
Token | Kodi |
Token ID | 44129 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Iro | +7.718 |
imilar | +7.554 |
Kara | +7.372 |
aiman | +7.271 |
akov | +7.124 |
Neg logit contributions | |
nton | -7.863 |
doct | -7.794 |
)=( | -7.732 |
Omaha | -7.439 |
Doct | -7.375 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Iro | +1.552 |
imilar | +1.549 |
aiman | +1.542 |
akov | +1.453 |
annis | +1.448 |
Neg logit contributions | |
doct | -1.486 |
nton | -1.455 |
)=( | -1.452 |
Doct | -1.421 |
Omaha | -1.409 |
Token | O |
Token ID | 440 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Iro | +8.158 |
Kara | +7.819 |
imilar | +7.757 |
aiman | +7.713 |
annis | +7.465 |
Neg logit contributions | |
nton | -6.730 |
doct | -6.660 |
)=( | -6.537 |
Omaha | -6.170 |
Doct | -6.121 |
Token | lic |
Token ID | 677 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
imilar | +1.650 |
aiman | +1.648 |
Iro | +1.619 |
200000 | +1.563 |
annis | +1.558 |
Neg logit contributions | |
doct | -1.422 |
)=( | -1.378 |
nton | -1.354 |
Doct | -1.340 |
Omaha | -1.339 |
Token | ity |
Token ID | 414 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
Iro | +0.632 |
imilar | +0.630 |
aiman | +0.630 |
200000 | +0.575 |
akov | +0.571 |
Neg logit contributions | |
doct | -1.078 |
)=( | -1.055 |
nton | -1.037 |
Doct | -1.028 |
Omaha | -1.019 |
Token | . |
Token ID | 13 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Iro | +7.140 |
Kara | +6.897 |
aiman | +6.884 |
imilar | +6.752 |
arius | +6.541 |
Neg logit contributions | |
doct | -6.413 |
nton | -6.233 |
)=( | -6.194 |
Omaha | -5.949 |
Doct | -5.916 |
Token | Oliver |
Token ID | 15416 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
Iro | +8.384 |
Kara | +7.982 |
aiman | +7.704 |
imilar | +7.678 |
200000 | +7.515 |
Neg logit contributions | |
doct | -8.729 |
nton | -8.428 |
)=( | -8.117 |
mater | -7.741 |
Omaha | -7.728 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Iro | +7.586 |
Kara | +7.114 |
aiman | +7.058 |
imilar | +6.952 |
annis | +6.866 |
Neg logit contributions | |
doct | -6.956 |
)=( | -6.898 |
nton | -6.646 |
Omaha | -6.640 |
glers | -6.395 |
Token | Fel |
Token ID | 13937 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Kara | +15.960 |
Iro | +15.768 |
Lena | +14.159 |
Archer | +13.848 |
Bash | +13.800 |
Neg logit contributions | |
nton | -15.660 |
doct | -14.853 |
)=( | -14.485 |
olphins | -13.759 |
bringing | -13.572 |
Token | icity |
Token ID | 8467 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
Iro | +2.777 |
aiman | +2.757 |
Kara | +2.527 |
imilar | +2.498 |
onne | +2.430 |
Neg logit contributions | |
doct | -18.144 |
Omaha | -18.081 |
nton | -18.023 |
)=( | -17.863 |
glers | -17.778 |
Token | may |
Token ID | 743 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Iro | +9.302 |
aiman | +8.850 |
Kara | +8.640 |
sabotage | +8.535 |
imilar | +8.393 |
Neg logit contributions | |
nton | -8.800 |
doct | -8.631 |
)=( | -8.332 |
glers | -8.135 |
Doct | -8.047 |
Token | have |
Token ID | 423 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
sabotage | +10.328 |
Iro | +10.195 |
imilar | +9.818 |
200000 | +9.582 |
Kara | +9.503 |
Neg logit contributions | |
)=( | -12.783 |
nton | -12.377 |
doct | -12.038 |
Omaha | -12.035 |
Doct | -11.995 |
Token | danced |
Token ID | 39480 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Iro | +5.583 |
imilar | +5.378 |
aiman | +5.260 |
Kara | +5.232 |
sabotage | +5.193 |
Neg logit contributions | |
nton | -5.061 |
)=( | -5.027 |
doct | -4.835 |
Doct | -4.758 |
Omaha | -4.752 |
Token | wall |
Token ID | 3355 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
imilar | +0.741 |
aiman | +0.733 |
Iro | +0.731 |
200000 | +0.695 |
annis | +0.684 |
Neg logit contributions | |
doct | -0.727 |
)=( | -0.715 |
nton | -0.708 |
Doct | -0.695 |
Omaha | -0.688 |
Token | is |
Token ID | 318 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
doct | +0.225 |
nton | +0.218 |
)=( | +0.218 |
Doct | +0.213 |
Omaha | +0.211 |
Neg logit contributions | |
imilar | -0.294 |
aiman | -0.292 |
Iro | -0.291 |
200000 | -0.278 |
annis | -0.275 |
Token | actually |
Token ID | 1682 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
imilar | +1.631 |
Iro | +1.620 |
aiman | +1.614 |
200000 | +1.540 |
Kara | +1.515 |
Neg logit contributions | |
doct | -1.513 |
)=( | -1.492 |
nton | -1.491 |
Doct | -1.457 |
Omaha | -1.440 |
Token | coming |
Token ID | 2406 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Iro | +4.026 |
imilar | +4.003 |
aiman | +3.956 |
sabotage | +3.805 |
200000 | +3.798 |
Neg logit contributions | |
nton | -3.937 |
)=( | -3.918 |
doct | -3.889 |
Doct | -3.802 |
Omaha | -3.764 |
Token | along |
Token ID | 1863 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
imilar | +2.970 |
aiman | +2.930 |
Iro | +2.914 |
200000 | +2.807 |
Kara | +2.766 |
Neg logit contributions | |
doct | -2.856 |
)=( | -2.828 |
nton | -2.818 |
Doct | -2.778 |
Omaha | -2.747 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
aiman | +5.907 |
imilar | +5.811 |
Iro | +5.779 |
Kara | +5.611 |
200000 | +5.448 |
Neg logit contributions | |
doct | -6.237 |
)=( | -6.202 |
nton | -6.180 |
Doct | -5.946 |
Omaha | -5.862 |
Token | well |
Token ID | 880 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Kara | +10.627 |
eas | +10.619 |
imilar | +10.572 |
Iro | +10.502 |
bas | +10.464 |
Neg logit contributions | |
)=( | -17.451 |
nton | -17.141 |
bringing | -16.881 |
noon | -16.195 |
enthal | -16.190 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aiman | +5.001 |
imilar | +4.930 |
Iro | +4.890 |
200000 | +4.723 |
Kara | +4.657 |
Neg logit contributions | |
doct | -5.345 |
nton | -5.328 |
)=( | -5.319 |
Omaha | -5.173 |
Doct | -5.147 |
Token | That |
Token ID | 1320 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
imilar | +1.375 |
Iro | +1.372 |
aiman | +1.353 |
200000 | +1.302 |
Kara | +1.281 |
Neg logit contributions | |
doct | -1.236 |
nton | -1.202 |
)=( | -1.192 |
Doct | -1.153 |
Omaha | -1.149 |
Token | will |
Token ID | 481 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
imilar | +3.979 |
aiman | +3.942 |
Iro | +3.916 |
200000 | +3.777 |
sabotage | +3.687 |
Neg logit contributions | |
doct | -3.682 |
)=( | -3.606 |
nton | -3.592 |
Doct | -3.543 |
Omaha | -3.482 |
Token | also |
Token ID | 635 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
imilar | +1.370 |
Iro | +1.353 |
aiman | +1.352 |
200000 | +1.305 |
sabotage | +1.288 |
Neg logit contributions | |
doct | -1.532 |
)=( | -1.519 |
nton | -1.489 |
Doct | -1.471 |
Omaha | -1.461 |
Token | if |
Token ID | 611 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Iro | +5.913 |
aiman | +5.859 |
imilar | +5.809 |
sabotage | +5.504 |
Kara | +5.500 |
Neg logit contributions | |
nton | -6.210 |
doct | -6.186 |
)=( | -6.027 |
Doct | -5.988 |
Omaha | -5.683 |
Token | you |
Token ID | 345 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Iro | +4.007 |
imilar | +3.899 |
aiman | +3.890 |
Kara | +3.715 |
200000 | +3.673 |
Neg logit contributions | |
nton | -4.134 |
doct | -4.131 |
)=( | -4.069 |
Doct | -3.985 |
bringing | -3.835 |
Token | want |
Token ID | 765 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Iro | +2.975 |
imilar | +2.967 |
aiman | +2.954 |
sabotage | +2.830 |
200000 | +2.761 |
Neg logit contributions | |
)=( | -2.802 |
doct | -2.798 |
nton | -2.762 |
Doct | -2.731 |
Omaha | -2.662 |
Token | to |
Token ID | 284 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Iro | +5.057 |
imilar | +4.955 |
aiman | +4.834 |
sabotage | +4.727 |
200000 | +4.697 |
Neg logit contributions | |
nton | -5.183 |
doct | -5.166 |
)=( | -5.076 |
Doct | -5.025 |
bringing | -4.888 |
Token | go |
Token ID | 467 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
Iro | +3.825 |
imilar | +3.775 |
aiman | +3.747 |
sabotage | +3.739 |
200000 | +3.588 |
Neg logit contributions | |
)=( | -3.862 |
nton | -3.819 |
doct | -3.803 |
Doct | -3.687 |
bringing | -3.663 |
Token | really |
Token ID | 1107 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Iro | +8.708 |
aiman | +8.329 |
imilar | +8.279 |
sabotage | +8.250 |
Kara | +8.217 |
Neg logit contributions | |
nton | -8.691 |
)=( | -8.623 |
doct | -8.393 |
Doct | -8.233 |
bringing | -8.215 |
Token | hard |
Token ID | 1327 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
sabotage | +12.971 |
Iro | +12.752 |
Kara | +12.282 |
imilar | +11.929 |
aiman | +11.907 |
Neg logit contributions | |
nton | -15.450 |
)=( | -15.143 |
bringing | -15.142 |
glers | -15.019 |
Ey | -14.515 |
Token | , |
Token ID | 11 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
aiman | +5.766 |
Iro | +5.744 |
imilar | +5.691 |
sabotage | +5.342 |
Kara | +5.291 |
Neg logit contributions | |
doct | -6.257 |
Doct | -6.197 |
nton | -6.167 |
)=( | -6.136 |
bringing | -5.924 |
Token | then |
Token ID | 788 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Iro | +5.796 |
imilar | +5.710 |
aiman | +5.621 |
sabotage | +5.516 |
Kara | +5.445 |
Neg logit contributions | |
nton | -5.828 |
)=( | -5.804 |
doct | -5.745 |
Doct | -5.582 |
bringing | -5.340 |
Token | you |
Token ID | 345 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Iro | +2.207 |
imilar | +2.199 |
aiman | +2.184 |
200000 | +2.065 |
sabotage | +2.060 |
Neg logit contributions | |
doct | -2.001 |
nton | -1.965 |
)=( | -1.957 |
Doct | -1.904 |
Omaha | -1.848 |
Token | can |
Token ID | 460 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Iro | +1.868 |
imilar | +1.866 |
aiman | +1.858 |
sabotage | +1.757 |
200000 | +1.747 |
Neg logit contributions | |
doct | -1.753 |
)=( | -1.741 |
nton | -1.720 |
Doct | -1.697 |
Omaha | -1.673 |
Token | _ |
Token ID | 4808 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
Iro | +5.439 |
200000 | +5.405 |
imilar | +5.391 |
bas | +5.268 |
aiman | +5.203 |
Neg logit contributions | |
doct | -8.131 |
nton | -7.998 |
bringing | -7.978 |
)=( | -7.946 |
Omaha | -7.934 |
Token | full |
Token ID | 1336 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
imilar | +0.551 |
aiman | +0.540 |
Iro | +0.540 |
200000 | +0.519 |
annis | +0.512 |
Neg logit contributions | |
doct | -0.463 |
)=( | -0.455 |
nton | -0.454 |
Doct | -0.446 |
Omaha | -0.442 |
Token | v |
Token ID | 410 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
imilar | +2.064 |
aiman | +2.009 |
Iro | +1.986 |
200000 | +1.907 |
annis | +1.891 |
Neg logit contributions | |
doct | -1.648 |
)=( | -1.639 |
nton | -1.625 |
Omaha | -1.613 |
Doct | -1.607 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
imilar | +5.341 |
aiman | +5.132 |
Iro | +5.081 |
bas | +4.903 |
arius | +4.841 |
Neg logit contributions | |
bringing | -11.075 |
)=( | -11.048 |
nton | -11.026 |
Omaha | -11.026 |
Doct | -10.686 |
Token | { |
Token ID | 1391 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Iro | +5.247 |
imilar | +5.153 |
aiman | +4.995 |
bas | +4.903 |
arius | +4.859 |
Neg logit contributions | |
)=( | -14.247 |
bringing | -13.637 |
nton | -13.598 |
Omaha | -13.284 |
doct | -13.161 |
Token | v |
Token ID | 410 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
doct | +2.913 |
)=( | +2.609 |
nton | +2.577 |
Doct | +2.560 |
Omaha | +2.489 |
Neg logit contributions | |
imilar | -5.934 |
aiman | -5.914 |
Iro | -5.902 |
200000 | -5.706 |
annis | -5.674 |
Token | . |
Token ID | 764 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
Iro | +5.645 |
bas | +5.482 |
200000 | +4.775 |
imilar | +4.695 |
aiman | +4.660 |
Neg logit contributions | |
� | -26.458 |
ModLoader | -25.373 |
millenn | -23.844 |
)=( | -23.695 |
� | -23.599 |
Token | vertex |
Token ID | 37423 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
doct | +5.253 |
nton | +4.853 |
)=( | +4.801 |
Doct | +4.720 |
mater | +4.620 |
Neg logit contributions | |
aiman | -6.426 |
Iro | -6.323 |
imilar | -6.269 |
200000 | -5.993 |
annis | -5.946 |
Token | . |
Token ID | 764 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Iro | +5.563 |
bas | +5.025 |
imilar | +4.859 |
200000 | +4.708 |
Kara | +4.506 |
Neg logit contributions | |
)=( | -20.309 |
� | -20.212 |
ModLoader | -19.867 |
bringing | -19.631 |
nton | -19.059 |
Token | x |
Token ID | 2124 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
doct | +1.808 |
)=( | +1.697 |
nton | +1.696 |
Doct | +1.677 |
Omaha | +1.648 |
Neg logit contributions | |
aiman | -2.330 |
imilar | -2.325 |
Iro | -2.291 |
200000 | -2.200 |
annis | -2.192 |
Token | yz |
Token ID | 45579 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
imilar | +5.879 |
aiman | +5.655 |
Iro | +5.516 |
bas | +5.409 |
arius | +5.361 |
Neg logit contributions | |
)=( | -7.496 |
doct | -7.296 |
Omaha | -7.290 |
nton | -7.263 |
Doct | -7.144 |
Token | is |
Token ID | 318 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Iro | +5.055 |
aiman | +4.996 |
imilar | +4.958 |
arius | +4.799 |
Kara | +4.699 |
Neg logit contributions | |
doct | -4.427 |
nton | -4.390 |
)=( | -4.341 |
Doct | -4.157 |
Omaha | -4.128 |
Token | supposed |
Token ID | 4385 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Iro | +4.311 |
aiman | +4.225 |
imilar | +4.172 |
Kara | +4.006 |
arius | +3.999 |
Neg logit contributions | |
)=( | -4.115 |
nton | -4.085 |
doct | -3.981 |
Doct | -3.847 |
Omaha | -3.841 |
Token | to |
Token ID | 284 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
imilar | +3.449 |
Iro | +3.429 |
aiman | +3.426 |
200000 | +3.278 |
Kara | +3.220 |
Neg logit contributions | |
doct | -3.334 |
nton | -3.198 |
)=( | -3.190 |
Doct | -3.168 |
Omaha | -3.158 |
Token | be |
Token ID | 307 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Iro | +5.820 |
aiman | +5.646 |
imilar | +5.608 |
sabotage | +5.574 |
Kara | +5.426 |
Neg logit contributions | |
)=( | -6.252 |
nton | -6.131 |
doct | -6.110 |
bringing | -5.903 |
Doct | -5.801 |
Token | thrown |
Token ID | 8754 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
Iro | +7.245 |
aiman | +6.937 |
Kara | +6.811 |
imilar | +6.728 |
arius | +6.682 |
Neg logit contributions | |
)=( | -7.462 |
nton | -7.381 |
doct | -6.964 |
bringing | -6.932 |
Doct | -6.732 |
Token | as |
Token ID | 355 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Iro | +7.272 |
aiman | +7.143 |
imilar | +7.078 |
Kara | +6.879 |
arius | +6.727 |
Neg logit contributions | |
nton | -7.168 |
doct | -7.092 |
)=( | -7.058 |
bringing | -6.720 |
Omaha | -6.710 |
Token | soon |
Token ID | 2582 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
imilar | +13.404 |
Iro | +13.137 |
Kara | +12.597 |
sabotage | +12.439 |
aiman | +11.934 |
Neg logit contributions | |
)=( | -14.438 |
bringing | -14.236 |
nton | -14.213 |
phant | -13.912 |
doct | -13.691 |
Token | as |
Token ID | 355 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
imilar | +6.385 |
Iro | +6.193 |
aiman | +5.969 |
sabotage | +5.617 |
arius | +5.579 |
Neg logit contributions | |
doct | -12.106 |
)=( | -12.058 |
nton | -11.881 |
bringing | -11.563 |
Doct | -11.500 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Iro | +6.786 |
imilar | +6.657 |
Kara | +6.411 |
sabotage | +6.282 |
aiman | +6.231 |
Neg logit contributions | |
)=( | -7.882 |
doct | -7.823 |
nton | -7.742 |
bringing | -7.426 |
glers | -7.214 |
Token | receiver |
Token ID | 9733 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Iro | +2.047 |
imilar | +2.014 |
aiman | +1.961 |
arius | +1.870 |
sabotage | +1.868 |
Neg logit contributions | |
)=( | -2.508 |
doct | -2.497 |
nton | -2.476 |
Doct | -2.358 |
bringing | -2.352 |
Token | plants |
Token ID | 6134 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
imilar | +1.171 |
Iro | +1.168 |
aiman | +1.153 |
200000 | +1.090 |
arius | +1.087 |
Neg logit contributions | |
doct | -1.170 |
)=( | -1.150 |
nton | -1.139 |
Doct | -1.117 |
Omaha | -1.113 |
Token | Sh |
Token ID | 911 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
doct | +0.259 |
)=( | +0.252 |
nton | +0.252 |
Doct | +0.247 |
Omaha | +0.243 |
Neg logit contributions | |
imilar | -0.274 |
aiman | -0.271 |
Iro | -0.271 |
200000 | -0.257 |
akov | -0.253 |
Token | kind |
Token ID | 11031 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
aiman | +2.236 |
imilar | +2.180 |
akov | +1.889 |
bas | +1.763 |
henko | +1.752 |
Neg logit contributions | |
doct | -8.338 |
Doct | -8.109 |
)=( | -8.059 |
Omaha | -8.034 |
nton | -7.939 |
Token | el |
Token ID | 417 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
doct | +1.346 |
nton | +1.307 |
)=( | +1.302 |
Doct | +1.257 |
Omaha | +1.235 |
Neg logit contributions | |
imilar | -2.329 |
Iro | -2.318 |
aiman | -2.306 |
200000 | -2.209 |
annis | -2.194 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
imilar | +0.783 |
aiman | +0.783 |
Iro | +0.776 |
200000 | +0.736 |
akov | +0.733 |
Neg logit contributions | |
doct | -0.733 |
)=( | -0.711 |
nton | -0.705 |
Doct | -0.693 |
Omaha | -0.682 |
Token | Mal |
Token ID | 4434 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
doct | +0.298 |
)=( | +0.289 |
nton | +0.288 |
Doct | +0.283 |
Omaha | +0.278 |
Neg logit contributions | |
imilar | -0.315 |
aiman | -0.313 |
Iro | -0.312 |
200000 | -0.295 |
akov | -0.291 |
Token | anch |
Token ID | 3702 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
aiman | +4.495 |
imilar | +4.386 |
akov | +4.175 |
henko | +4.028 |
annis | +3.966 |
Neg logit contributions | |
doct | -7.378 |
Omaha | -7.219 |
Doct | -7.121 |
)=( | -6.992 |
glers | -6.868 |
Token | ak |
Token ID | 461 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
akov | +10.384 |
aiman | +9.493 |
bas | +9.077 |
ak | +9.046 |
henko | +8.507 |
Neg logit contributions | |
� | -24.247 |
hemor | -22.797 |
ModLoader | -22.497 |
millenn | -21.889 |
� | -20.992 |
Token | and |
Token ID | 290 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
imilar | +0.123 |
aiman | +0.123 |
Iro | +0.122 |
200000 | +0.115 |
annis | +0.114 |
Neg logit contributions | |
doct | -0.105 |
)=( | -0.103 |
nton | -0.102 |
Doct | -0.100 |
Omaha | -0.098 |
Token | Mak |
Token ID | 15841 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
aiman | +3.718 |
Iro | +3.707 |
imilar | +3.632 |
Kara | +3.536 |
henko | +3.465 |
Neg logit contributions | |
doct | -3.808 |
)=( | -3.729 |
nton | -3.693 |
Doct | -3.590 |
glers | -3.540 |
Token | ovi |
Token ID | 47297 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
imilar | +4.875 |
aiman | +4.841 |
Iro | +4.661 |
akov | +4.607 |
arius | +4.550 |
Neg logit contributions | |
doct | -3.765 |
Omaha | -3.587 |
Doct | -3.579 |
)=( | -3.560 |
nton | -3.531 |
Token | ich |
Token ID | 488 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
doct | +1.288 |
nton | +1.252 |
)=( | +1.243 |
Doct | +1.214 |
Omaha | +1.201 |
Neg logit contributions | |
imilar | -1.410 |
Iro | -1.397 |
aiman | -1.387 |
200000 | -1.323 |
annis | -1.302 |
Token | Muslim |
Token ID | 17067 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
imilar | +1.440 |
aiman | +1.432 |
Iro | +1.416 |
200000 | +1.351 |
annis | +1.339 |
Neg logit contributions | |
doct | -1.532 |
)=( | -1.491 |
Doct | -1.470 |
nton | -1.464 |
Omaha | -1.457 |
Token | content |
Token ID | 2695 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Iro | +4.422 |
aiman | +4.417 |
imilar | +4.384 |
sabotage | +4.154 |
Kara | +4.124 |
Neg logit contributions | |
)=( | -4.235 |
nton | -4.121 |
Doct | -4.016 |
doct | -4.005 |
Omaha | -3.981 |
Token | on |
Token ID | 319 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
imilar | +2.630 |
Iro | +2.616 |
aiman | +2.583 |
Kara | +2.449 |
200000 | +2.427 |
Neg logit contributions | |
)=( | -2.408 |
nton | -2.362 |
doct | -2.343 |
Omaha | -2.290 |
Doct | -2.284 |
Token | social |
Token ID | 1919 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
Iro | +4.535 |
imilar | +4.501 |
aiman | +4.409 |
Kara | +4.233 |
sabotage | +4.086 |
Neg logit contributions | |
)=( | -5.830 |
nton | -5.768 |
doct | -5.682 |
glers | -5.609 |
Doct | -5.607 |
Token | media |
Token ID | 2056 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
doct | +0.963 |
nton | +0.938 |
)=( | +0.938 |
Doct | +0.920 |
Omaha | +0.909 |
Neg logit contributions | |
imilar | -0.963 |
aiman | -0.949 |
Iro | -0.947 |
200000 | -0.897 |
annis | -0.884 |
Token | as |
Token ID | 355 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
imilar | +2.783 |
Iro | +2.776 |
aiman | +2.759 |
200000 | +2.583 |
Kara | +2.580 |
Neg logit contributions | |
)=( | -2.536 |
nton | -2.512 |
doct | -2.508 |
Doct | -2.439 |
Omaha | -2.418 |
Token | well |
Token ID | 880 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
imilar | +12.389 |
Iro | +11.801 |
Kara | +11.519 |
sabotage | +11.195 |
Lena | +10.719 |
Neg logit contributions | |
nton | -15.290 |
glers | -15.245 |
)=( | -14.849 |
roying | -14.577 |
bringing | -14.379 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
imilar | +4.339 |
aiman | +4.303 |
Iro | +4.283 |
Kara | +4.028 |
200000 | +4.004 |
Neg logit contributions | |
)=( | -5.028 |
doct | -4.936 |
nton | -4.880 |
Doct | -4.813 |
Omaha | -4.793 |
Token | such |
Token ID | 884 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
doct | +3.983 |
nton | +3.716 |
Doct | +3.668 |
)=( | +3.633 |
Omaha | +3.598 |
Neg logit contributions | |
imilar | -5.196 |
aiman | -5.141 |
Iro | -5.029 |
200000 | -4.953 |
annis | -4.865 |
Token | as |
Token ID | 355 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
imilar | +3.573 |
Iro | +3.567 |
aiman | +3.556 |
200000 | +3.329 |
sabotage | +3.312 |
Neg logit contributions | |
)=( | -5.037 |
doct | -5.008 |
nton | -4.994 |
Doct | -4.928 |
Omaha | -4.846 |
Token | when |
Token ID | 618 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
doct | +2.223 |
nton | +2.119 |
)=( | +2.114 |
Doct | +2.087 |
Omaha | +2.061 |
Neg logit contributions | |
imilar | -2.545 |
aiman | -2.520 |
Iro | -2.496 |
200000 | -2.398 |
annis | -2.363 |
Token | - |
Token ID | 12 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
imilar | +4.909 |
aiman | +4.862 |
Iro | +4.750 |
arius | +4.609 |
annis | +4.607 |
Neg logit contributions | |
doct | -5.310 |
)=( | -5.199 |
nton | -5.187 |
Omaha | -5.156 |
Doct | -5.149 |
Token | drops |
Token ID | 49253 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
aiman | +9.084 |
imilar | +8.934 |
bas | +8.808 |
annis | +8.608 |
akov | +8.563 |
Neg logit contributions | |
)=( | -8.038 |
doct | -8.012 |
Omaha | -8.009 |
Doct | -7.835 |
nton | -7.377 |
Token | - |
Token ID | 12 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
aiman | +8.392 |
Iro | +8.105 |
imilar | +8.030 |
Kara | +7.895 |
akov | +7.794 |
Neg logit contributions | |
)=( | -10.228 |
doct | -10.083 |
Omaha | -9.778 |
Doct | -9.751 |
nton | -9.698 |
Token | re |
Token ID | 260 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
aiman | +12.138 |
bas | +12.105 |
imilar | +11.714 |
200000 | +11.626 |
annis | +11.413 |
Neg logit contributions | |
)=( | -10.513 |
doct | -10.470 |
Omaha | -10.214 |
Doct | -9.993 |
glers | -9.317 |
Token | za |
Token ID | 4496 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
aiman | +2.762 |
imilar | +2.761 |
Iro | +2.649 |
200000 | +2.610 |
annis | +2.594 |
Neg logit contributions | |
doct | -2.586 |
)=( | -2.484 |
Doct | -2.463 |
Omaha | -2.439 |
nton | -2.391 |
Token | - |
Token ID | 12 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
imilar | +9.425 |
aiman | +9.094 |
Iro | +8.992 |
200000 | +8.816 |
bas | +8.692 |
Neg logit contributions | |
doct | -14.062 |
)=( | -14.049 |
nton | -13.817 |
Doct | -13.803 |
glers | -13.717 |
Token | as |
Token ID | 292 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
bas | +14.677 |
imilar | +14.324 |
aiman | +14.263 |
200000 | +13.969 |
annis | +13.565 |
Neg logit contributions | |
)=( | -15.272 |
Omaha | -14.984 |
doct | -14.939 |
Doct | -14.867 |
Ply | -14.254 |
Token | lan |
Token ID | 9620 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
imilar | +5.869 |
aiman | +5.579 |
henko | +4.911 |
akov | +4.904 |
annis | +4.895 |
Neg logit contributions | |
doct | -14.062 |
Doct | -13.600 |
Omaha | -13.586 |
)=( | -13.088 |
Hume | -12.995 |
Token | - |
Token ID | 12 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
aiman | +4.956 |
imilar | +4.913 |
Iro | +4.870 |
200000 | +4.644 |
annis | +4.640 |
Neg logit contributions | |
doct | -5.289 |
)=( | -5.188 |
nton | -5.140 |
Omaha | -5.099 |
Doct | -5.060 |
Token | after |
Token ID | 8499 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
aiman | +9.776 |
bas | +9.641 |
imilar | +9.607 |
annis | +9.359 |
200000 | +9.309 |
Neg logit contributions | |
Omaha | -9.116 |
)=( | -8.983 |
doct | -8.950 |
Doct | -8.652 |
nton | -8.248 |
Token | - |
Token ID | 12 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
imilar | +4.793 |
aiman | +4.714 |
Iro | +4.694 |
bas | +4.464 |
200000 | +4.452 |
Neg logit contributions | |
doct | -5.118 |
)=( | -5.083 |
Doct | -5.012 |
Omaha | -5.008 |
nton | -4.988 |
Token | always |
Token ID | 1464 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
doct | +4.498 |
nton | +4.403 |
)=( | +4.343 |
Doct | +4.234 |
Omaha | +4.231 |
Neg logit contributions | |
imilar | -5.931 |
aiman | -5.895 |
Iro | -5.826 |
200000 | -5.647 |
annis | -5.536 |
Token | touched |
Token ID | 12615 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
doct | +1.209 |
)=( | +1.167 |
nton | +1.165 |
Doct | +1.144 |
Omaha | +1.133 |
Neg logit contributions | |
imilar | -1.334 |
aiman | -1.319 |
Iro | -1.311 |
200000 | -1.250 |
annis | -1.235 |
Token | on |
Token ID | 319 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
imilar | +2.622 |
Iro | +2.598 |
aiman | +2.554 |
200000 | +2.426 |
annis | +2.395 |
Neg logit contributions | |
doct | -2.545 |
nton | -2.467 |
)=( | -2.465 |
Doct | -2.386 |
Omaha | -2.345 |
Token | doing |
Token ID | 1804 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
imilar | +2.723 |
Iro | +2.707 |
aiman | +2.646 |
200000 | +2.506 |
Kara | +2.504 |
Neg logit contributions | |
doct | -2.780 |
nton | -2.719 |
)=( | -2.707 |
Doct | -2.639 |
Omaha | -2.580 |
Token | things |
Token ID | 1243 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
imilar | +5.300 |
Iro | +5.217 |
aiman | +5.129 |
sabotage | +4.925 |
Kara | +4.888 |
Neg logit contributions | |
)=( | -5.539 |
nton | -5.508 |
doct | -5.463 |
Doct | -5.226 |
glers | -5.104 |
Token | as |
Token ID | 355 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
imilar | +7.617 |
Iro | +7.583 |
aiman | +7.337 |
Kara | +7.199 |
sabotage | +7.009 |
Neg logit contributions | |
)=( | -7.449 |
nton | -7.393 |
doct | -7.302 |
glers | -7.049 |
Omaha | -6.863 |
Token | a |
Token ID | 257 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
imilar | +13.727 |
Iro | +13.408 |
Kara | +12.978 |
sabotage | +12.667 |
Ashe | +11.967 |
Neg logit contributions | |
)=( | -14.553 |
nton | -14.220 |
roying | -14.001 |
bringing | -13.798 |
doct | -13.781 |
Token | unit |
Token ID | 4326 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Iro | +6.276 |
imilar | +6.191 |
aiman | +6.017 |
sabotage | +5.864 |
arius | +5.836 |
Neg logit contributions | |
)=( | -6.711 |
doct | -6.392 |
nton | -6.297 |
bringing | -6.244 |
Omaha | -6.124 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
imilar | +4.543 |
aiman | +4.430 |
Iro | +4.373 |
arius | +4.159 |
annis | +4.107 |
Neg logit contributions | |
doct | -4.425 |
)=( | -4.340 |
nton | -4.296 |
Doct | -4.210 |
Omaha | -4.202 |
Token | that |
Token ID | 326 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
Iro | +5.484 |
imilar | +5.358 |
aiman | +5.310 |
Kara | +5.117 |
sabotage | +5.072 |
Neg logit contributions | |
doct | -4.950 |
nton | -4.928 |
)=( | -4.897 |
Doct | -4.696 |
Omaha | -4.658 |
Token | � |
Token ID | 447 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
imilar | +0.877 |
aiman | +0.874 |
Iro | +0.871 |
200000 | +0.826 |
annis | +0.815 |
Neg logit contributions | |
doct | -0.714 |
nton | -0.690 |
)=( | -0.687 |
Doct | -0.677 |
Omaha | -0.664 |
Token | . |
Token ID | 764 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Iro | +5.214 |
bas | +4.757 |
imilar | +4.697 |
200000 | +4.574 |
Kara | +4.355 |
Neg logit contributions | |
� | -17.503 |
ModLoader | -16.779 |
)=( | -16.378 |
hemor | -16.080 |
bringing | -16.047 |
Token | im |
Token ID | 545 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
doct | +3.001 |
)=( | +2.720 |
Doct | +2.681 |
nton | +2.646 |
Omaha | +2.600 |
Neg logit contributions | |
aiman | -6.357 |
imilar | -6.351 |
Iro | -6.184 |
akov | -6.141 |
200000 | -6.114 |
Token | read |
Token ID | 961 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
imilar | +4.310 |
aiman | +4.024 |
bas | +4.022 |
Iro | +3.871 |
arius | +3.804 |
Neg logit contributions | |
)=( | -14.843 |
Doct | -14.195 |
doct | -14.147 |
Omaha | -14.013 |
nton | -13.878 |
Token | ( |
Token ID | 357 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Iro | +6.483 |
imilar | +6.372 |
aiman | +6.255 |
bas | +6.223 |
200000 | +6.173 |
Neg logit contributions | |
)=( | -8.341 |
nton | -8.169 |
doct | -8.138 |
bringing | -7.996 |
glers | -7.969 |
Token | image |
Token ID | 2939 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Iro | +7.796 |
imilar | +7.713 |
aiman | +7.502 |
200000 | +7.466 |
sabotage | +7.312 |
Neg logit contributions | |
nton | -6.789 |
glers | -6.490 |
bringing | -6.358 |
)=( | -6.352 |
Doct | -6.303 |
Token | Path |
Token ID | 15235 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
imilar | +3.658 |
Iro | +3.598 |
aiman | +3.521 |
200000 | +3.473 |
arius | +3.410 |
Neg logit contributions | |
doct | -2.834 |
nton | -2.775 |
)=( | -2.750 |
Omaha | -2.688 |
Doct | -2.639 |
Token | ) |
Token ID | 1267 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
bas | +5.998 |
Iro | +5.895 |
200000 | +5.732 |
imilar | +4.828 |
Kara | +4.741 |
Neg logit contributions | |
� | -25.255 |
hemor | -24.909 |
ModLoader | -24.295 |
tradem | -23.976 |
millenn | -23.459 |
Token | image |
Token ID | 2939 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Iro | +8.607 |
imilar | +8.242 |
sabotage | +7.999 |
200000 | +7.994 |
aiman | +7.867 |
Neg logit contributions | |
glers | -7.925 |
nton | -7.917 |
bringing | -7.725 |
)=( | -7.485 |
Doct | -7.483 |
Token | = |
Token ID | 796 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Iro | +5.595 |
imilar | +5.334 |
200000 | +5.330 |
bas | +5.204 |
arius | +5.152 |
Neg logit contributions | |
bringing | -13.128 |
)=( | -13.046 |
nton | -13.021 |
doct | -13.000 |
� | -12.881 |
Token | im |
Token ID | 545 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
imilar | +2.686 |
Iro | +2.680 |
aiman | +2.676 |
200000 | +2.562 |
annis | +2.522 |
Neg logit contributions | |
doct | -1.771 |
)=( | -1.739 |
nton | -1.734 |
Doct | -1.693 |
Omaha | -1.671 |
Token | utils |
Token ID | 26791 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
doct | +0.307 |
nton | +0.298 |
)=( | +0.297 |
Doct | +0.292 |
Omaha | +0.289 |
Neg logit contributions | |
imilar | -0.265 |
aiman | -0.262 |
Iro | -0.261 |
200000 | -0.246 |
annis | -0.242 |
Token | away |
Token ID | 1497 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
imilar | +3.868 |
aiman | +3.844 |
Iro | +3.763 |
annis | +3.621 |
Kara | +3.612 |
Neg logit contributions | |
doct | -3.907 |
)=( | -3.797 |
Doct | -3.751 |
nton | -3.747 |
Omaha | -3.645 |
Token | . |
Token ID | 13 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
imilar | +2.529 |
aiman | +2.518 |
Iro | +2.481 |
200000 | +2.366 |
annis | +2.327 |
Neg logit contributions | |
doct | -2.476 |
)=( | -2.426 |
nton | -2.398 |
Doct | -2.379 |
Omaha | -2.338 |
Token | You |
Token ID | 921 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Iro | +5.064 |
imilar | +4.871 |
Kara | +4.811 |
aiman | +4.711 |
200000 | +4.662 |
Neg logit contributions | |
doct | -4.866 |
)=( | -4.741 |
nton | -4.736 |
bringing | -4.548 |
glers | -4.471 |
Token | even |
Token ID | 772 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
imilar | +8.614 |
aiman | +8.550 |
bas | +8.526 |
sabotage | +8.340 |
Iro | +8.293 |
Neg logit contributions | |
)=( | -8.766 |
Omaha | -8.734 |
glers | -8.626 |
Doct | -8.583 |
nton | -8.382 |
Token | went |
Token ID | 1816 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Iro | +4.222 |
aiman | +4.197 |
imilar | +4.194 |
sabotage | +4.029 |
Kara | +3.967 |
Neg logit contributions | |
)=( | -4.200 |
nton | -4.103 |
Omaha | -4.079 |
Doct | -4.040 |
doct | -4.033 |
Token | as |
Token ID | 355 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
imilar | +4.920 |
aiman | +4.917 |
Iro | +4.894 |
sabotage | +4.714 |
Kara | +4.694 |
Neg logit contributions | |
)=( | -3.022 |
doct | -2.988 |
nton | -2.976 |
Doct | -2.829 |
Omaha | -2.792 |
Token | far |
Token ID | 1290 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
imilar | +7.779 |
sabotage | +7.451 |
Iro | +7.187 |
Kara | +7.126 |
annis | +6.964 |
Neg logit contributions | |
glers | -19.848 |
)=( | -19.364 |
roying | -19.320 |
bringing | -19.286 |
nton | -18.965 |
Token | as |
Token ID | 355 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
imilar | +6.964 |
Iro | +6.860 |
aiman | +6.705 |
sabotage | +6.468 |
Kara | +6.399 |
Neg logit contributions | |
)=( | -10.036 |
nton | -9.863 |
glers | -9.840 |
doct | -9.831 |
Omaha | -9.625 |
Token | to |
Token ID | 284 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Iro | +5.848 |
imilar | +5.784 |
aiman | +5.729 |
Kara | +5.670 |
akov | +5.647 |
Neg logit contributions | |
)=( | -5.964 |
glers | -5.943 |
nton | -5.913 |
doct | -5.878 |
Omaha | -5.832 |
Token | tell |
Token ID | 1560 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
sabotage | +6.822 |
Iro | +6.600 |
imilar | +6.522 |
aiman | +6.488 |
Kara | +6.327 |
Neg logit contributions | |
)=( | -8.196 |
glers | -8.035 |
nton | -7.993 |
Omaha | -7.923 |
Doct | -7.811 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Iro | +5.189 |
imilar | +5.138 |
Kara | +4.992 |
aiman | +4.982 |
sabotage | +4.702 |
Neg logit contributions | |
)=( | -5.277 |
doct | -5.228 |
nton | -5.192 |
Doct | -5.055 |
glers | -5.025 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
imilar | +2.481 |
Iro | +2.421 |
aiman | +2.414 |
200000 | +2.325 |
akov | +2.263 |
Neg logit contributions | |
doct | -2.182 |
)=( | -2.112 |
nton | -2.109 |
Doct | -2.091 |
Omaha | -2.068 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
imilar | +0.420 |
aiman | +0.411 |
Iro | +0.409 |
200000 | +0.393 |
annis | +0.388 |
Neg logit contributions | |
doct | -0.321 |
)=( | -0.312 |
nton | -0.309 |
Doct | -0.306 |
Omaha | -0.304 |
Token | void |
Token ID | 7951 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
imilar | +1.589 |
Iro | +1.547 |
aiman | +1.543 |
200000 | +1.470 |
annis | +1.457 |
Neg logit contributions | |
doct | -1.634 |
)=( | -1.607 |
nton | -1.588 |
Doct | -1.574 |
Omaha | -1.565 |
Token | vert |
Token ID | 9421 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
doct | +5.342 |
nton | +4.815 |
)=( | +4.439 |
Doct | +4.352 |
mater | +4.268 |
Neg logit contributions | |
aiman | -13.050 |
imilar | -12.929 |
Iro | -12.891 |
200000 | -12.392 |
annis | -12.286 |
Token | ( |
Token ID | 357 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
imilar | +0.909 |
aiman | +0.902 |
Iro | +0.898 |
200000 | +0.859 |
annis | +0.847 |
Neg logit contributions | |
doct | -0.728 |
)=( | -0.712 |
nton | -0.706 |
Doct | -0.690 |
Omaha | -0.684 |
Token | in |
Token ID | 287 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
imilar | +8.216 |
Iro | +8.143 |
sabotage | +7.699 |
aiman | +7.620 |
bas | +7.341 |
Neg logit contributions | |
glers | -12.142 |
bringing | -11.988 |
nton | -11.942 |
Doct | -11.848 |
)=( | -11.792 |
Token | out |
Token ID | 448 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
imilar | +8.850 |
Iro | +8.066 |
aiman | +8.048 |
bas | +7.983 |
akov | +7.570 |
Neg logit contributions | |
)=( | -19.365 |
glers | -19.337 |
ModLoader | -19.032 |
Doct | -18.592 |
bringing | -18.590 |
Token | app |
Token ID | 598 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Iro | +3.057 |
imilar | +2.898 |
Kara | +2.633 |
sabotage | +2.524 |
bas | +2.404 |
Neg logit contributions | |
bringing | -12.723 |
nton | -12.639 |
)=( | -12.624 |
glers | -12.612 |
Omaha | -12.381 |
Token | data |
Token ID | 7890 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
imilar | +4.810 |
bas | +4.701 |
200000 | +4.367 |
annis | +4.134 |
arius | +4.107 |
Neg logit contributions | |
Omaha | -12.141 |
Doct | -12.048 |
doct | -11.924 |
)=( | -11.910 |
nton | -11.458 |
Token | _ |
Token ID | 4808 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
Iro | +5.439 |
200000 | +5.405 |
imilar | +5.391 |
bas | +5.268 |
aiman | +5.203 |
Neg logit contributions | |
doct | -8.131 |
nton | -7.998 |
bringing | -7.978 |
)=( | -7.946 |
Omaha | -7.934 |
Token | full |
Token ID | 1336 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
imilar | +0.551 |
aiman | +0.540 |
Iro | +0.540 |
200000 | +0.519 |
annis | +0.512 |
Neg logit contributions | |
doct | -0.463 |
)=( | -0.455 |
nton | -0.454 |
Doct | -0.446 |
Omaha | -0.442 |
Token | like |
Token ID | 588 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
Iro | +2.916 |
imilar | +2.879 |
aiman | +2.797 |
Kara | +2.685 |
sabotage | +2.682 |
Neg logit contributions | |
)=( | -2.726 |
doct | -2.672 |
nton | -2.657 |
Doct | -2.580 |
Omaha | -2.513 |
Token | life |
Token ID | 1204 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
imilar | +0.228 |
Iro | +0.227 |
aiman | +0.226 |
200000 | +0.214 |
annis | +0.213 |
Neg logit contributions | |
doct | -0.210 |
)=( | -0.205 |
nton | -0.203 |
Doct | -0.199 |
Omaha | -0.196 |
Token | could |
Token ID | 714 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Iro | +2.634 |
aiman | +2.597 |
imilar | +2.595 |
Kara | +2.455 |
annis | +2.450 |
Neg logit contributions | |
doct | -2.434 |
)=( | -2.409 |
nton | -2.401 |
Doct | -2.347 |
Omaha | -2.308 |
Token | go |
Token ID | 467 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Iro | +3.807 |
imilar | +3.786 |
aiman | +3.719 |
sabotage | +3.653 |
200000 | +3.608 |
Neg logit contributions | |
)=( | -4.366 |
doct | -4.282 |
nton | -4.159 |
Doct | -4.152 |
Omaha | -4.098 |
Token | on |
Token ID | 319 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Iro | +6.187 |
imilar | +5.952 |
aiman | +5.937 |
Kara | +5.838 |
bas | +5.585 |
Neg logit contributions | |
)=( | -7.005 |
doct | -6.882 |
nton | -6.784 |
Doct | -6.677 |
bringing | -6.595 |
Token | as |
Token ID | 355 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Iro | +8.660 |
aiman | +8.330 |
Kara | +8.263 |
imilar | +8.037 |
bas | +7.942 |
Neg logit contributions | |
)=( | -9.554 |
nton | -9.546 |
doct | -9.088 |
Doct | -8.951 |
Omaha | -8.686 |
Token | before |
Token ID | 878 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Iro | +13.815 |
Kara | +12.696 |
imilar | +12.000 |
sabotage | +11.502 |
Ashe | +11.436 |
Neg logit contributions | |
)=( | -15.204 |
nton | -14.599 |
bringing | -14.490 |
roying | -14.432 |
olphins | -13.643 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Iro | +2.612 |
imilar | +2.598 |
aiman | +2.594 |
200000 | +2.460 |
annis | +2.443 |
Neg logit contributions | |
doct | -2.563 |
)=( | -2.541 |
nton | -2.512 |
Doct | -2.436 |
Omaha | -2.381 |
Token | William |
Token ID | 3977 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
Iro | +4.014 |
imilar | +3.782 |
aiman | +3.776 |
Kara | +3.721 |
200000 | +3.653 |
Neg logit contributions | |
doct | -4.024 |
)=( | -3.904 |
nton | -3.871 |
Doct | -3.666 |
bringing | -3.665 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Iro | +1.047 |
aiman | +1.041 |
imilar | +1.037 |
annis | +0.981 |
Kara | +0.976 |
Neg logit contributions | |
doct | -0.967 |
)=( | -0.953 |
nton | -0.930 |
Doct | -0.909 |
Omaha | -0.904 |
Token | Conquer |
Token ID | 40963 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Iro | +2.341 |
imilar | +2.201 |
aiman | +2.153 |
annis | +1.971 |
Kara | +1.916 |
Neg logit contributions | |
)=( | -6.262 |
nton | -6.166 |
doct | -6.158 |
Omaha | -5.964 |
Doct | -5.886 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Iro | +11.160 |
Kara | +10.624 |
Renew | +10.169 |
aiman | +9.993 |
imilar | +9.814 |
Neg logit contributions | |
doct | -10.326 |
nton | -10.298 |
)=( | -9.966 |
glers | -9.527 |
bringing | -9.401 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
imilar | +1.491 |
Iro | +1.479 |
aiman | +1.472 |
200000 | +1.423 |
Kara | +1.381 |
Neg logit contributions | |
doct | -1.423 |
)=( | -1.375 |
nton | -1.366 |
Doct | -1.347 |
Omaha | -1.339 |
Token | As |
Token ID | 1722 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
aiman | +7.077 |
imilar | +7.029 |
Iro | +6.974 |
200000 | +6.972 |
bas | +6.878 |
Neg logit contributions | |
doct | -7.584 |
Omaha | -7.169 |
nton | -7.093 |
Doct | -7.001 |
)=( | -6.996 |
Token | for |
Token ID | 329 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Kara | +10.828 |
imilar | +10.720 |
Iro | +10.704 |
aiman | +10.431 |
annis | +9.988 |
Neg logit contributions | |
nton | -10.548 |
)=( | -10.533 |
doct | -10.142 |
glers | -9.935 |
bringing | -9.499 |
Token | Oliver |
Token ID | 15416 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Kara | +11.351 |
Iro | +11.016 |
aiman | +10.272 |
annis | +10.230 |
Lena | +10.192 |
Neg logit contributions | |
nton | -11.437 |
)=( | -11.091 |
doct | -10.930 |
glers | -10.358 |
Omaha | -10.136 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Iro | +4.808 |
aiman | +4.614 |
Kara | +4.553 |
imilar | +4.492 |
annis | +4.461 |
Neg logit contributions | |
doct | -4.808 |
)=( | -4.692 |
nton | -4.574 |
Omaha | -4.540 |
Doct | -4.385 |
Token | Fel |
Token ID | 13937 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Kara | +13.251 |
Iro | +12.911 |
Lena | +11.725 |
aiman | +11.313 |
Archer | +10.963 |
Neg logit contributions | |
nton | -16.204 |
doct | -15.919 |
)=( | -15.310 |
bringing | -14.478 |
olphins | -14.476 |
Token | icity |
Token ID | 8467 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
aiman | +3.722 |
imilar | +3.305 |
Iro | +3.273 |
200000 | +3.092 |
Kara | +3.036 |
Neg logit contributions | |
doct | -15.003 |
Omaha | -14.626 |
nton | -14.371 |
)=( | -14.260 |
glers | -14.097 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Iro | +6.175 |
aiman | +6.141 |
imilar | +5.983 |
Kara | +5.877 |
annis | +5.861 |
Neg logit contributions | |
doct | -5.687 |
nton | -5.600 |
)=( | -5.533 |
Omaha | -5.385 |
Doct | -5.275 |
Token | they |
Token ID | 484 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Iro | +9.616 |
Kara | +9.567 |
imilar | +9.196 |
aiman | +9.097 |
Lena | +8.822 |
Neg logit contributions | |
)=( | -9.917 |
nton | -9.839 |
doct | -9.718 |
glers | -8.964 |
Omaha | -8.795 |
Token | may |
Token ID | 743 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
imilar | +4.369 |
aiman | +4.320 |
Iro | +4.253 |
200000 | +4.057 |
akov | +4.054 |
Neg logit contributions | |
doct | -3.929 |
)=( | -3.915 |
nton | -3.863 |
Omaha | -3.835 |
Doct | -3.804 |
Token | save |
Token ID | 3613 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
imilar | +1.369 |
aiman | +1.365 |
Iro | +1.364 |
200000 | +1.297 |
annis | +1.274 |
Neg logit contributions | |
doct | -1.109 |
)=( | -1.089 |
nton | -1.085 |
Doct | -1.067 |
Omaha | -1.054 |
Token | , |
Token ID | 11 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
imilar | +1.988 |
Iro | +1.979 |
aiman | +1.966 |
200000 | +1.908 |
Kara | +1.847 |
Neg logit contributions | |
doct | -2.181 |
nton | -2.105 |
Doct | -2.090 |
)=( | -2.081 |
Omaha | -2.069 |
Token | your |
Token ID | 534 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
doct | +3.703 |
)=( | +3.608 |
nton | +3.473 |
Omaha | +3.454 |
Doct | +3.352 |
Neg logit contributions | |
imilar | -7.743 |
aiman | -7.730 |
Iro | -7.523 |
annis | -7.309 |
insula | -7.270 |
Token | character |
Token ID | 2095 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
doct | +3.285 |
nton | +3.024 |
)=( | +2.964 |
Doct | +2.898 |
Omaha | +2.888 |
Neg logit contributions | |
imilar | -5.405 |
Iro | -5.335 |
aiman | -5.296 |
200000 | -5.089 |
annis | -5.052 |
Token | now |
Token ID | 783 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
imilar | +0.437 |
aiman | +0.436 |
Iro | +0.432 |
200000 | +0.412 |
annis | +0.404 |
Neg logit contributions | |
doct | -0.543 |
)=( | -0.535 |
nton | -0.529 |
Doct | -0.523 |
Omaha | -0.520 |
Token | receives |
Token ID | 11583 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
doct | +5.324 |
Doct | +4.894 |
)=( | +4.885 |
nton | +4.713 |
ey | +4.639 |
Neg logit contributions | |
aiman | -9.385 |
imilar | -9.340 |
Iro | -8.985 |
annis | -8.828 |
akov | -8.712 |
Token | secret |
Token ID | 3200 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
doct | +5.345 |
ey | +4.304 |
)=( | +4.219 |
nton | +4.185 |
mater | +4.152 |
Neg logit contributions | |
imilar | -18.592 |
aiman | -18.411 |
Iro | -17.717 |
akov | -17.201 |
annis | -17.130 |
Token | voices |
Token ID | 10839 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
doct | +4.339 |
nton | +3.626 |
memories | +3.505 |
)=( | +3.502 |
eyeb | +3.460 |
Neg logit contributions | |
imilar | -20.884 |
aiman | -19.906 |
arius | -19.833 |
Iro | -19.593 |
insula | -19.490 |
Token | in |
Token ID | 287 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Iro | +4.313 |
imilar | +4.303 |
aiman | +4.234 |
200000 | +4.105 |
bas | +4.022 |
Neg logit contributions | |
doct | -4.871 |
nton | -4.808 |
Doct | -4.725 |
)=( | -4.713 |
Omaha | -4.675 |
Token | his |
Token ID | 465 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
doct | +1.577 |
)=( | +1.530 |
nton | +1.523 |
Doct | +1.491 |
Omaha | +1.481 |
Neg logit contributions | |
imilar | -1.710 |
aiman | -1.689 |
Iro | -1.679 |
200000 | -1.593 |
annis | -1.581 |
Token | or |
Token ID | 393 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
imilar | +3.771 |
Iro | +3.752 |
aiman | +3.748 |
200000 | +3.624 |
sabotage | +3.559 |
Neg logit contributions | |
)=( | -5.615 |
doct | -5.566 |
Doct | -5.518 |
nton | -5.453 |
Omaha | -5.371 |
Token | to |
Token ID | 284 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
aiman | +1.592 |
Iro | +1.590 |
imilar | +1.586 |
200000 | +1.506 |
akov | +1.488 |
Neg logit contributions | |
doct | -1.322 |
nton | -1.289 |
)=( | -1.273 |
Doct | -1.256 |
Omaha | -1.228 |
Token | pre |
Token ID | 662 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Iro | +2.754 |
imilar | +2.690 |
aiman | +2.682 |
sabotage | +2.621 |
200000 | +2.574 |
Neg logit contributions | |
)=( | -3.127 |
nton | -3.090 |
doct | -3.083 |
Doct | -2.968 |
bringing | -2.954 |
Token | - |
Token ID | 12 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
imilar | +0.940 |
aiman | +0.935 |
Iro | +0.931 |
annis | +0.885 |
200000 | +0.881 |
Neg logit contributions | |
doct | -0.908 |
)=( | -0.884 |
nton | -0.871 |
Doct | -0.865 |
Omaha | -0.848 |
Token | order |
Token ID | 2875 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
imilar | +0.623 |
aiman | +0.620 |
Iro | +0.613 |
200000 | +0.587 |
annis | +0.580 |
Neg logit contributions | |
doct | -0.731 |
)=( | -0.710 |
nton | -0.702 |
Doct | -0.700 |
Omaha | -0.691 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
doct | +3.630 |
)=( | +3.486 |
Omaha | +3.443 |
nton | +3.438 |
Doct | +3.431 |
Neg logit contributions | |
imilar | -4.152 |
aiman | -4.109 |
Iro | -4.020 |
200000 | -3.891 |
annis | -3.873 |
Token | next |
Token ID | 1306 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
doct | +1.792 |
)=( | +1.727 |
nton | +1.724 |
Doct | +1.700 |
Omaha | +1.690 |
Neg logit contributions | |
imilar | -1.884 |
aiman | -1.860 |
Iro | -1.843 |
200000 | -1.764 |
annis | -1.743 |
Token | batch |
Token ID | 15458 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
doct | +10.083 |
Omaha | +9.761 |
mater | +9.289 |
Doct | +9.255 |
nton | +9.218 |
Neg logit contributions | |
imilar | -10.628 |
aiman | -10.430 |
200000 | -10.298 |
annis | -10.116 |
akov | -10.059 |
Token | of |
Token ID | 286 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
doct | +0.757 |
)=( | +0.728 |
nton | +0.726 |
Doct | +0.711 |
Omaha | +0.703 |
Neg logit contributions | |
imilar | -1.122 |
aiman | -1.111 |
Iro | -1.106 |
200000 | -1.060 |
annis | -1.049 |
Token | am |
Token ID | 716 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
doct | +7.077 |
Omaha | +6.776 |
Doct | +6.595 |
)=( | +6.533 |
nton | +6.487 |
Neg logit contributions | |
imilar | -7.602 |
aiman | -7.537 |
200000 | -7.250 |
annis | -7.238 |
Iro | -7.131 |
Token | i |
Token ID | 72 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
imilar | +0.264 |
aiman | +0.261 |
Iro | +0.259 |
200000 | +0.245 |
annis | +0.242 |
Neg logit contributions | |
doct | -0.270 |
)=( | -0.262 |
nton | -0.261 |
Doct | -0.258 |
Omaha | -0.254 |
Token | ibo |
Token ID | 26762 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
doct | +0.593 |
nton | +0.573 |
)=( | +0.573 |
Doct | +0.561 |
Omaha | +0.553 |
Neg logit contributions | |
imilar | -0.736 |
aiman | -0.728 |
Iro | -0.725 |
200000 | -0.690 |
annis | -0.684 |
Token | the |
Token ID | 262 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
doct | +1.342 |
)=( | +1.300 |
nton | +1.297 |
Doct | +1.275 |
Omaha | +1.263 |
Neg logit contributions | |
imilar | -1.373 |
aiman | -1.357 |
Iro | -1.350 |
200000 | -1.283 |
annis | -1.267 |
Token | Mid |
Token ID | 7215 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
imilar | +0.851 |
Iro | +0.845 |
aiman | +0.836 |
annis | +0.791 |
200000 | +0.789 |
Neg logit contributions | |
doct | -0.800 |
)=( | -0.795 |
nton | -0.792 |
Doct | -0.769 |
Omaha | -0.751 |
Token | western |
Token ID | 14197 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
imilar | +1.081 |
Iro | +1.071 |
aiman | +1.063 |
200000 | +1.008 |
annis | +1.001 |
Neg logit contributions | |
doct | -0.874 |
)=( | -0.845 |
nton | -0.844 |
Doct | -0.828 |
Omaha | -0.808 |
Token | ers |
Token ID | 364 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
doct | +1.313 |
)=( | +1.270 |
nton | +1.267 |
Doct | +1.246 |
Omaha | +1.235 |
Neg logit contributions | |
imilar | -1.398 |
aiman | -1.382 |
Iro | -1.373 |
200000 | -1.309 |
annis | -1.291 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
doct | +1.744 |
)=( | +1.677 |
nton | +1.676 |
Doct | +1.648 |
Omaha | +1.632 |
Neg logit contributions | |
imilar | -2.057 |
aiman | -2.032 |
Iro | -2.017 |
200000 | -1.931 |
annis | -1.905 |
Token | Hill |
Token ID | 3327 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
doct | +1.234 |
)=( | +1.191 |
nton | +1.188 |
Doct | +1.171 |
Omaha | +1.159 |
Neg logit contributions | |
imilar | -1.470 |
aiman | -1.455 |
Iro | -1.438 |
200000 | -1.378 |
annis | -1.363 |
Token | quit |
Token ID | 47391 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
nton | +4.977 |
)=( | +4.660 |
ey | +4.543 |
cum | +4.536 |
doct | +4.388 |
Neg logit contributions | |
Iro | -15.380 |
imilar | -15.167 |
aiman | -14.897 |
insula | -14.657 |
Kara | -14.567 |
Token | was |
Token ID | 373 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Iro | +4.310 |
aiman | +4.191 |
imilar | +4.154 |
sabotage | +4.030 |
annis | +4.015 |
Neg logit contributions | |
)=( | -4.270 |
nton | -4.101 |
Doct | -4.095 |
doct | -4.081 |
Omaha | -4.039 |
Token | re |
Token ID | 302 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
Iro | +2.966 |
aiman | +2.882 |
imilar | +2.865 |
annis | +2.730 |
akov | +2.724 |
Neg logit contributions | |
)=( | -2.904 |
doct | -2.803 |
nton | -2.793 |
Doct | -2.759 |
glers | -2.725 |
Token | elected |
Token ID | 28604 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
imilar | +0.013 |
aiman | +0.013 |
Iro | +0.013 |
annis | +0.012 |
200000 | +0.012 |
Neg logit contributions | |
doct | -0.014 |
)=( | -0.013 |
nton | -0.013 |
Doct | -0.013 |
Omaha | -0.013 |
Token | National |
Token ID | 2351 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
doct | +2.733 |
nton | +2.603 |
)=( | +2.591 |
Doct | +2.567 |
Omaha | +2.554 |
Neg logit contributions | |
imilar | -3.699 |
aiman | -3.619 |
Iro | -3.561 |
200000 | -3.444 |
annis | -3.400 |
Token | teams |
Token ID | 3466 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
doct | +7.089 |
Omaha | +7.042 |
nton | +6.909 |
)=( | +6.861 |
Doct | +6.721 |
Neg logit contributions | |
imilar | -9.258 |
aiman | -9.076 |
Iro | -8.654 |
200000 | -8.561 |
annis | -8.386 |
Token | are |
Token ID | 389 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
doct | +8.352 |
Omaha | +8.311 |
)=( | +7.985 |
Doct | +7.942 |
nton | +7.819 |
Neg logit contributions | |
imilar | -9.769 |
aiman | -9.599 |
200000 | -9.404 |
Iro | -9.043 |
insula | -8.928 |
Token | allowed |
Token ID | 3142 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
doct | +9.510 |
Omaha | +9.194 |
Doct | +8.842 |
nton | +8.626 |
)=( | +8.619 |
Neg logit contributions | |
aiman | -10.477 |
imilar | -10.413 |
200000 | -9.952 |
insula | -9.933 |
annis | -9.690 |
Token | to |
Token ID | 284 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
doct | +6.817 |
Omaha | +6.653 |
)=( | +6.505 |
Doct | +6.491 |
nton | +6.333 |
Neg logit contributions | |
aiman | -10.286 |
imilar | -10.124 |
insula | -9.684 |
Iro | -9.680 |
akov | -9.674 |
Token | have |
Token ID | 423 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
doct | +7.439 |
nton | +6.928 |
Omaha | +6.917 |
Doct | +6.856 |
)=( | +6.590 |
Neg logit contributions | |
imilar | -11.807 |
aiman | -11.524 |
Iro | -11.111 |
insula | -11.110 |
200000 | -10.955 |
Token | two |
Token ID | 734 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
doct | +8.064 |
Omaha | +7.722 |
nton | +7.528 |
Doct | +7.477 |
)=( | +7.388 |
Neg logit contributions | |
imilar | -10.119 |
aiman | -10.079 |
insula | -9.713 |
akov | -9.698 |
200000 | -9.589 |
Token | players |
Token ID | 1938 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
doct | +9.726 |
Omaha | +9.438 |
nton | +9.079 |
Doct | +8.928 |
)=( | +8.761 |
Neg logit contributions | |
imilar | -11.243 |
aiman | -11.129 |
insula | -10.913 |
akov | -10.557 |
200000 | -10.555 |
Token | who |
Token ID | 508 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
doct | +7.490 |
nton | +7.234 |
Omaha | +7.110 |
)=( | +6.986 |
Doct | +6.872 |
Neg logit contributions | |
imilar | -10.423 |
aiman | -10.374 |
200000 | -9.966 |
Iro | -9.958 |
insula | -9.756 |
Token | are |
Token ID | 389 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
doct | +4.739 |
nton | +4.574 |
)=( | +4.482 |
Omaha | +4.448 |
Doct | +4.440 |
Neg logit contributions | |
imilar | -5.010 |
aiman | -4.973 |
Iro | -4.887 |
200000 | -4.797 |
annis | -4.702 |
Token | from |
Token ID | 422 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
doct | +7.109 |
Omaha | +6.835 |
nton | +6.728 |
Doct | +6.597 |
)=( | +6.577 |
Neg logit contributions | |
aiman | -8.092 |
imilar | -8.051 |
Iro | -7.673 |
200000 | -7.655 |
insula | -7.652 |
Token | outside |
Token ID | 2354 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
doct | +3.285 |
)=( | +3.165 |
Omaha | +3.165 |
nton | +3.145 |
Doct | +3.129 |
Neg logit contributions | |
imilar | -3.317 |
aiman | -3.310 |
Iro | -3.239 |
200000 | -3.164 |
annis | -3.110 |
Token | great |
Token ID | 1049 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
doct | +5.658 |
Doct | +5.309 |
Omaha | +5.308 |
nton | +5.304 |
)=( | +5.294 |
Neg logit contributions | |
aiman | -6.649 |
imilar | -6.641 |
Iro | -6.445 |
200000 | -6.223 |
akov | -6.160 |
Token | addition |
Token ID | 3090 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
imilar | +1.077 |
Iro | +1.067 |
aiman | +1.062 |
200000 | +1.017 |
annis | +1.000 |
Neg logit contributions | |
doct | -0.923 |
)=( | -0.897 |
nton | -0.896 |
Doct | -0.875 |
Omaha | -0.861 |
Token | to |
Token ID | 284 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
doct | +4.134 |
)=( | +3.968 |
Doct | +3.905 |
nton | +3.888 |
Omaha | +3.820 |
Neg logit contributions | |
imilar | -6.363 |
aiman | -6.264 |
Iro | -6.186 |
200000 | -6.006 |
annis | -5.905 |
Token | Power |
Token ID | 4333 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
imilar | +3.368 |
Iro | +3.335 |
aiman | +3.277 |
Kara | +3.115 |
sabotage | +3.063 |
Neg logit contributions | |
nton | -5.834 |
doct | -5.832 |
)=( | -5.721 |
Doct | -5.581 |
Omaha | -5.547 |
Token | BI |
Token ID | 20068 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
imilar | +1.680 |
Iro | +1.673 |
aiman | +1.650 |
200000 | +1.589 |
annis | +1.563 |
Neg logit contributions | |
doct | -1.351 |
nton | -1.310 |
)=( | -1.310 |
Doct | -1.276 |
Omaha | -1.253 |
Token | are |
Token ID | 389 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
doct | +1.200 |
)=( | +1.157 |
nton | +1.154 |
Doct | +1.132 |
Omaha | +1.120 |
Neg logit contributions | |
imilar | -1.598 |
aiman | -1.582 |
Iro | -1.573 |
200000 | -1.505 |
annis | -1.488 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
doct | +10.309 |
Doct | +9.543 |
)=( | +9.292 |
nton | +9.135 |
Omaha | +9.001 |
Neg logit contributions | |
aiman | -11.183 |
imilar | -11.051 |
arius | -10.979 |
200000 | -10.766 |
Iro | -10.697 |
Token | custom |
Token ID | 2183 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
doct | +9.961 |
Doct | +9.376 |
nton | +9.054 |
Omaha | +9.004 |
)=( | +8.951 |
Neg logit contributions | |
aiman | -9.931 |
imilar | -9.881 |
arius | -9.651 |
Iro | -9.458 |
200000 | -9.363 |
Token | visuals |
Token ID | 27329 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
doct | +2.646 |
nton | +2.515 |
)=( | +2.506 |
Doct | +2.497 |
Omaha | +2.449 |
Neg logit contributions | |
imilar | -2.827 |
aiman | -2.793 |
Iro | -2.765 |
200000 | -2.646 |
annis | -2.613 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
doct | +2.032 |
)=( | +1.949 |
nton | +1.941 |
Doct | +1.921 |
Omaha | +1.898 |
Neg logit contributions | |
imilar | -2.309 |
aiman | -2.286 |
Iro | -2.269 |
200000 | -2.169 |
annis | -2.140 |
Token | built |
Token ID | 3170 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
doct | +2.604 |
)=( | +2.500 |
nton | +2.489 |
Doct | +2.462 |
Omaha | +2.433 |
Neg logit contributions | |
imilar | -2.876 |
aiman | -2.852 |
Iro | -2.820 |
200000 | -2.703 |
annis | -2.679 |
Token | mostly |
Token ID | 4632 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
doct | +5.633 |
Doct | +5.423 |
nton | +5.389 |
Omaha | +5.350 |
)=( | +5.242 |
Neg logit contributions | |
aiman | -5.936 |
imilar | -5.920 |
Iro | -5.684 |
200000 | -5.571 |
annis | -5.511 |
Token | short |
Token ID | 1790 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
imilar | +0.155 |
Iro | +0.154 |
aiman | +0.153 |
200000 | +0.145 |
Kara | +0.143 |
Neg logit contributions | |
doct | -0.141 |
)=( | -0.138 |
nton | -0.138 |
Doct | -0.133 |
Omaha | -0.132 |
Token | stuff |
Token ID | 3404 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
doct | +0.079 |
)=( | +0.077 |
nton | +0.076 |
Doct | +0.075 |
Omaha | +0.074 |
Neg logit contributions | |
imilar | -0.079 |
Iro | -0.078 |
aiman | -0.078 |
200000 | -0.074 |
annis | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
doct | +3.482 |
nton | +3.362 |
Doct | +3.292 |
)=( | +3.291 |
Omaha | +3.256 |
Neg logit contributions | |
imilar | -4.497 |
aiman | -4.435 |
Iro | -4.414 |
200000 | -4.289 |
annis | -4.202 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
doct | +1.331 |
)=( | +1.280 |
nton | +1.280 |
Doct | +1.256 |
Omaha | +1.242 |
Neg logit contributions | |
imilar | -1.729 |
aiman | -1.712 |
Iro | -1.701 |
200000 | -1.630 |
annis | -1.610 |
Token | he |
Token ID | 339 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
imilar | +1.182 |
Iro | +1.173 |
aiman | +1.163 |
200000 | +1.097 |
Kara | +1.096 |
Neg logit contributions | |
doct | -1.107 |
)=( | -1.079 |
nton | -1.076 |
Doct | -1.034 |
Omaha | -1.031 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
doct | +0.609 |
)=( | +0.590 |
nton | +0.588 |
Doct | +0.578 |
Omaha | +0.573 |
Neg logit contributions | |
imilar | -0.683 |
aiman | -0.675 |
Iro | -0.671 |
200000 | -0.640 |
annis | -0.633 |
Token | � |
Token ID | 447 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
doct | +0.120 |
)=( | +0.115 |
nton | +0.115 |
Doct | +0.112 |
Omaha | +0.111 |
Neg logit contributions | |
imilar | -0.174 |
aiman | -0.172 |
Iro | -0.172 |
200000 | -0.165 |
annis | -0.162 |
Token | � |
Token ID | 247 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
imilar | +0.238 |
aiman | +0.235 |
Iro | +0.232 |
200000 | +0.223 |
annis | +0.220 |
Neg logit contributions | |
doct | -0.183 |
nton | -0.176 |
)=( | -0.176 |
Doct | -0.173 |
Omaha | -0.171 |
Token | t |
Token ID | 83 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
doct | +0.741 |
)=( | +0.719 |
nton | +0.715 |
Doct | +0.705 |
Omaha | +0.699 |
Neg logit contributions | |
imilar | -0.768 |
aiman | -0.758 |
Iro | -0.754 |
200000 | -0.718 |
annis | -0.708 |
Token | tested |
Token ID | 6789 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
doct | +2.910 |
nton | +2.756 |
Doct | +2.742 |
)=( | +2.727 |
Omaha | +2.707 |
Neg logit contributions | |
imilar | -3.051 |
aiman | -3.021 |
Iro | -2.993 |
200000 | -2.872 |
annis | -2.849 |
Token | a |
Token ID | 257 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
imilar | +2.025 |
Iro | +1.988 |
aiman | +1.977 |
200000 | +1.844 |
Kara | +1.827 |
Neg logit contributions | |
doct | -2.098 |
)=( | -2.082 |
nton | -2.077 |
Doct | -2.033 |
bringing | -1.957 |
Token | small |
Token ID | 1402 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
imilar | +0.599 |
Iro | +0.591 |
aiman | +0.591 |
200000 | +0.558 |
Kara | +0.546 |
Neg logit contributions | |
doct | -0.615 |
)=( | -0.608 |
nton | -0.603 |
Doct | -0.591 |
Omaha | -0.580 |
Token | number |
Token ID | 1271 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
Iro | +5.130 |
imilar | +5.075 |
aiman | +4.882 |
200000 | +4.838 |
sabotage | +4.698 |
Neg logit contributions | |
)=( | -6.478 |
doct | -6.336 |
Doct | -6.313 |
nton | -6.312 |
bringing | -6.178 |
Token | of |
Token ID | 286 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
imilar | +0.735 |
aiman | +0.725 |
Iro | +0.721 |
200000 | +0.691 |
annis | +0.679 |
Neg logit contributions | |
doct | -0.531 |
)=( | -0.514 |
nton | -0.513 |
Doct | -0.504 |
Omaha | -0.493 |
Token | companies |
Token ID | 2706 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
imilar | +3.730 |
Iro | +3.669 |
aiman | +3.591 |
200000 | +3.351 |
sabotage | +3.314 |
Neg logit contributions | |
)=( | -4.559 |
nton | -4.542 |
doct | -4.475 |
Doct | -4.411 |
bringing | -4.292 |
Token | , |
Token ID | 11 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
doct | +1.427 |
)=( | +1.378 |
nton | +1.375 |
Doct | +1.350 |
Omaha | +1.336 |
Neg logit contributions | |
imilar | -1.692 |
aiman | -1.674 |
Iro | -1.665 |
200000 | -1.589 |
annis | -1.570 |
Token | among |
Token ID | 1871 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
doct | +4.834 |
nton | +4.585 |
)=( | +4.554 |
Omaha | +4.539 |
Doct | +4.449 |
Neg logit contributions | |
aiman | -6.114 |
imilar | -6.108 |
Iro | -6.045 |
200000 | -5.862 |
annis | -5.848 |
Token | the |
Token ID | 262 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
doct | +2.417 |
nton | +2.307 |
)=( | +2.298 |
Omaha | +2.241 |
Doct | +2.235 |
Neg logit contributions | |
imilar | -3.959 |
aiman | -3.952 |
Iro | -3.925 |
200000 | -3.766 |
annis | -3.743 |
Token | biggest |
Token ID | 4094 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
doct | +1.993 |
nton | +1.903 |
)=( | +1.898 |
Omaha | +1.861 |
Doct | +1.861 |
Neg logit contributions | |
imilar | -2.759 |
aiman | -2.744 |
Iro | -2.713 |
200000 | -2.619 |
annis | -2.588 |
Token | of |
Token ID | 286 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
doct | +8.656 |
)=( | +8.403 |
Omaha | +8.395 |
nton | +8.236 |
Doct | +7.829 |
Neg logit contributions | |
aiman | -11.779 |
imilar | -11.563 |
Iro | -11.354 |
200000 | -11.079 |
akov | -10.997 |
Token | which |
Token ID | 543 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
doct | +3.649 |
nton | +3.516 |
)=( | +3.513 |
Omaha | +3.471 |
Doct | +3.430 |
Neg logit contributions | |
imilar | -4.199 |
aiman | -4.168 |
Iro | -4.126 |
200000 | -3.960 |
akov | -3.923 |
Token | ". |
Token ID | 1911 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
imilar | +4.426 |
aiman | +4.367 |
Iro | +4.289 |
sabotage | +4.101 |
200000 | +4.097 |
Neg logit contributions | |
)=( | -4.071 |
doct | -4.015 |
Doct | -3.958 |
nton | -3.956 |
Omaha | -3.842 |
Token | The |
Token ID | 383 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
doct | +0.794 |
)=( | +0.770 |
nton | +0.768 |
Doct | +0.754 |
Omaha | +0.746 |
Neg logit contributions | |
imilar | -0.838 |
aiman | -0.829 |
Iro | -0.825 |
200000 | -0.785 |
annis | -0.774 |
Token | investigation |
Token ID | 3645 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
doct | +2.808 |
nton | +2.678 |
)=( | +2.646 |
Omaha | +2.629 |
Doct | +2.619 |
Neg logit contributions | |
imilar | -2.881 |
aiman | -2.852 |
Iro | -2.795 |
200000 | -2.719 |
annis | -2.660 |
Token | p |
Token ID | 279 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Iro | +2.193 |
aiman | +2.159 |
imilar | +2.153 |
sabotage | +2.041 |
annis | +2.030 |
Neg logit contributions | |
)=( | -2.331 |
doct | -2.290 |
nton | -2.239 |
Doct | -2.222 |
Omaha | -2.205 |
Token | ored |
Token ID | 1850 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
imilar | +2.662 |
aiman | +2.637 |
Iro | +2.552 |
annis | +2.473 |
200000 | +2.403 |
Neg logit contributions | |
doct | -2.989 |
)=( | -2.970 |
nton | -2.876 |
Omaha | -2.876 |
Doct | -2.866 |
Token | over |
Token ID | 625 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
doct | +0.257 |
)=( | +0.250 |
nton | +0.250 |
Doct | +0.243 |
Omaha | +0.240 |
Neg logit contributions | |
imilar | -0.322 |
aiman | -0.320 |
Iro | -0.318 |
200000 | -0.303 |
annis | -0.300 |
Token | potential |
Token ID | 2785 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
doct | +2.889 |
nton | +2.717 |
)=( | +2.714 |
Omaha | +2.700 |
Doct | +2.698 |
Neg logit contributions | |
imilar | -3.097 |
aiman | -3.052 |
Iro | -3.007 |
200000 | -2.906 |
annis | -2.881 |
Token | triggers |
Token ID | 20022 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Iro | +3.456 |
aiman | +3.442 |
imilar | +3.413 |
sabotage | +3.337 |
200000 | +3.183 |
Neg logit contributions | |
)=( | -4.074 |
nton | -3.978 |
Doct | -3.942 |
doct | -3.937 |
Omaha | -3.810 |
Token | such |
Token ID | 884 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
imilar | +4.581 |
aiman | +4.560 |
Iro | +4.548 |
Kara | +4.305 |
sabotage | +4.267 |
Neg logit contributions | |
)=( | -4.387 |
doct | -4.245 |
nton | -4.239 |
Doct | -4.146 |
bringing | -4.014 |
Token | as |
Token ID | 355 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
sabotage | +6.337 |
Iro | +6.332 |
imilar | +6.205 |
aiman | +6.100 |
200000 | +5.900 |
Neg logit contributions | |
nton | -12.524 |
)=( | -12.485 |
Doct | -12.408 |
doct | -12.200 |
bringing | -12.170 |
Token | a |
Token ID | 257 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
doct | +3.370 |
)=( | +3.192 |
nton | +3.176 |
Omaha | +3.163 |
Doct | +3.147 |
Neg logit contributions | |
imilar | -3.566 |
aiman | -3.492 |
Iro | -3.421 |
200000 | -3.347 |
annis | -3.290 |
Token | find |
Token ID | 1064 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
aiman | +0.788 |
imilar | +0.788 |
Iro | +0.783 |
200000 | +0.742 |
akov | +0.734 |
Neg logit contributions | |
doct | -0.683 |
)=( | -0.676 |
nton | -0.670 |
Doct | -0.657 |
Omaha | -0.646 |
Token | that |
Token ID | 326 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Iro | +6.996 |
imilar | +6.884 |
aiman | +6.753 |
Kara | +6.580 |
sabotage | +6.471 |
Neg logit contributions | |
nton | -8.532 |
)=( | -8.404 |
Doct | -8.090 |
doct | -8.064 |
bringing | -7.731 |
Token | our |
Token ID | 674 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Iro | +7.226 |
aiman | +6.788 |
Kara | +6.741 |
imilar | +6.733 |
sabotage | +6.628 |
Neg logit contributions | |
nton | -7.989 |
)=( | -7.775 |
doct | -7.590 |
Doct | -7.452 |
ey | -7.198 |
Token | numbers |
Token ID | 3146 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Iro | +4.968 |
imilar | +4.818 |
aiman | +4.716 |
Kara | +4.663 |
sabotage | +4.611 |
Neg logit contributions | |
nton | -4.848 |
)=( | -4.840 |
doct | -4.752 |
Doct | -4.634 |
ey | -4.423 |
Token | are |
Token ID | 389 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
doct | +2.210 |
)=( | +2.120 |
nton | +2.113 |
Doct | +2.085 |
Omaha | +2.069 |
Neg logit contributions | |
imilar | -2.653 |
aiman | -2.627 |
Iro | -2.614 |
200000 | -2.501 |
annis | -2.462 |
Token | growing |
Token ID | 3957 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
doct | +7.195 |
Omaha | +6.679 |
Doct | +6.590 |
nton | +6.572 |
)=( | +6.415 |
Neg logit contributions | |
imilar | -8.897 |
aiman | -8.758 |
Iro | -8.476 |
200000 | -8.433 |
insula | -8.201 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
doct | +0.149 |
)=( | +0.146 |
nton | +0.144 |
Doct | +0.142 |
Omaha | +0.139 |
Neg logit contributions | |
imilar | -0.163 |
aiman | -0.162 |
Iro | -0.161 |
200000 | -0.153 |
annis | -0.151 |
Token | we |
Token ID | 356 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
imilar | +1.886 |
Iro | +1.860 |
aiman | +1.857 |
200000 | +1.756 |
Kara | +1.749 |
Neg logit contributions | |
doct | -1.650 |
nton | -1.629 |
)=( | -1.624 |
Doct | -1.575 |
Omaha | -1.527 |
Token | 're |
Token ID | 821 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
aiman | +3.100 |
Iro | +3.081 |
imilar | +3.076 |
sabotage | +2.947 |
akov | +2.893 |
Neg logit contributions | |
)=( | -3.301 |
nton | -3.273 |
doct | -3.263 |
Doct | -3.202 |
Omaha | -3.119 |
Token | getting |
Token ID | 1972 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Iro | +3.642 |
imilar | +3.594 |
aiman | +3.589 |
Kara | +3.427 |
200000 | +3.358 |
Neg logit contributions | |
)=( | -3.276 |
nton | -3.273 |
doct | -3.214 |
Doct | -3.157 |
Omaha | -3.031 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Iro | +6.529 |
imilar | +6.264 |
Kara | +6.235 |
aiman | +6.199 |
sabotage | +6.004 |
Neg logit contributions | |
nton | -6.719 |
)=( | -6.556 |
Doct | -6.457 |
doct | -6.276 |
bringing | -6.067 |
Token | Goldman |
Token ID | 18740 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
doct | +3.933 |
Omaha | +3.797 |
nton | +3.780 |
Doct | +3.751 |
)=( | +3.748 |
Neg logit contributions | |
imilar | -5.124 |
aiman | -5.085 |
Iro | -4.964 |
200000 | -4.904 |
annis | -4.783 |
Token | eight |
Token ID | 3624 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
doct | +2.345 |
)=( | +2.273 |
nton | +2.273 |
Doct | +2.229 |
Omaha | +2.219 |
Neg logit contributions | |
imilar | -2.548 |
aiman | -2.522 |
Iro | -2.502 |
200000 | -2.387 |
annis | -2.350 |
Token | years |
Token ID | 812 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
doct | +3.909 |
nton | +3.763 |
)=( | +3.727 |
Omaha | +3.697 |
Doct | +3.616 |
Neg logit contributions | |
imilar | -4.547 |
aiman | -4.526 |
Iro | -4.449 |
annis | -4.298 |
200000 | -4.292 |
Token | before |
Token ID | 878 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
doct | +0.289 |
)=( | +0.282 |
nton | +0.279 |
Doct | +0.275 |
Omaha | +0.272 |
Neg logit contributions | |
imilar | -0.285 |
aiman | -0.282 |
Iro | -0.281 |
200000 | -0.265 |
annis | -0.262 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
doct | +6.398 |
nton | +6.242 |
Omaha | +6.185 |
Doct | +6.169 |
)=( | +6.138 |
Neg logit contributions | |
imilar | -5.490 |
aiman | -5.359 |
Iro | -5.288 |
200000 | -5.071 |
arius | -4.939 |
Token | , |
Token ID | 11 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
doct | +6.131 |
nton | +5.941 |
)=( | +5.818 |
Omaha | +5.595 |
Doct | +5.575 |
Neg logit contributions | |
imilar | -9.661 |
Iro | -9.482 |
aiman | -9.312 |
200000 | -9.115 |
annis | -8.881 |
Token | had |
Token ID | 550 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
doct | +4.651 |
nton | +4.397 |
Doct | +4.321 |
Omaha | +4.285 |
)=( | +4.257 |
Neg logit contributions | |
imilar | -5.814 |
aiman | -5.669 |
Iro | -5.581 |
200000 | -5.485 |
akov | -5.326 |
Token | probably |
Token ID | 2192 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
doct | +4.854 |
nton | +4.561 |
Doct | +4.519 |
Omaha | +4.510 |
)=( | +4.441 |
Neg logit contributions | |
imilar | -5.897 |
aiman | -5.774 |
Iro | -5.615 |
200000 | -5.529 |
annis | -5.421 |
Token | earned |
Token ID | 7366 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
doct | +0.329 |
)=( | +0.322 |
nton | +0.319 |
Doct | +0.313 |
Omaha | +0.310 |
Neg logit contributions | |
imilar | -0.367 |
aiman | -0.364 |
Iro | -0.363 |
200000 | -0.345 |
annis | -0.341 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
doct | +3.520 |
nton | +3.386 |
Omaha | +3.361 |
)=( | +3.351 |
Doct | +3.351 |
Neg logit contributions | |
imilar | -4.374 |
aiman | -4.325 |
Iro | -4.259 |
200000 | -4.101 |
akov | -4.052 |
Token | right |
Token ID | 826 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
doct | +1.228 |
nton | +1.182 |
)=( | +1.181 |
Doct | +1.161 |
Omaha | +1.153 |
Neg logit contributions | |
imilar | -1.450 |
aiman | -1.433 |
Iro | -1.421 |
200000 | -1.360 |
annis | -1.344 |
Token | ocean |
Token ID | 9151 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
doct | +0.060 |
)=( | +0.059 |
nton | +0.059 |
Doct | +0.057 |
Omaha | +0.056 |
Neg logit contributions | |
imilar | -0.074 |
aiman | -0.073 |
Iro | -0.073 |
200000 | -0.070 |
annis | -0.069 |
Token | is |
Token ID | 318 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
aiman | +2.739 |
imilar | +2.717 |
Iro | +2.702 |
200000 | +2.566 |
Kara | +2.554 |
Neg logit contributions | |
doct | -2.471 |
)=( | -2.414 |
nton | -2.386 |
Doct | -2.367 |
Omaha | -2.317 |
Token | different |
Token ID | 1180 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
doct | +3.790 |
nton | +3.570 |
Omaha | +3.517 |
Doct | +3.517 |
)=( | +3.516 |
Neg logit contributions | |
imilar | -4.232 |
aiman | -4.180 |
Iro | -4.141 |
200000 | -4.002 |
annis | -3.949 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
doct | +1.683 |
)=( | +1.622 |
nton | +1.621 |
Doct | +1.590 |
Omaha | +1.573 |
Neg logit contributions | |
imilar | -2.067 |
aiman | -2.044 |
Iro | -2.036 |
200000 | -1.942 |
annis | -1.921 |
Token | A |
Token ID | 317 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Iro | +2.072 |
imilar | +2.043 |
aiman | +2.016 |
Kara | +1.950 |
200000 | +1.909 |
Neg logit contributions | |
doct | -2.052 |
)=( | -2.000 |
nton | -1.992 |
Doct | -1.903 |
bringing | -1.884 |
Token | similar |
Token ID | 2092 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
aiman | +4.533 |
imilar | +4.472 |
Iro | +4.435 |
Kara | +4.275 |
sabotage | +4.186 |
Neg logit contributions | |
)=( | -4.543 |
doct | -4.428 |
nton | -4.348 |
Doct | -4.313 |
Omaha | -4.205 |
Token | spill |
Token ID | 19431 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Iro | +7.469 |
Kara | +7.310 |
imilar | +7.220 |
aiman | +7.182 |
sabotage | +7.086 |
Neg logit contributions | |
)=( | -8.118 |
nton | -7.760 |
doct | -7.644 |
Doct | -7.549 |
glers | -7.530 |
Token | in |
Token ID | 287 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
imilar | +3.559 |
Iro | +3.557 |
aiman | +3.534 |
Kara | +3.342 |
sabotage | +3.317 |
Neg logit contributions | |
doct | -3.208 |
)=( | -3.113 |
nton | -3.087 |
Doct | -3.078 |
Omaha | -2.975 |
Token | the |
Token ID | 262 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Iro | +3.395 |
imilar | +3.307 |
aiman | +3.291 |
Kara | +3.199 |
sabotage | +3.062 |
Neg logit contributions | |
doct | -3.529 |
)=( | -3.474 |
nton | -3.448 |
Doct | -3.323 |
bringing | -3.268 |
Token | Arctic |
Token ID | 15723 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Iro | +3.814 |
aiman | +3.752 |
imilar | +3.731 |
Kara | +3.669 |
200000 | +3.536 |
Neg logit contributions | |
doct | -2.237 |
)=( | -2.192 |
nton | -2.181 |
Doct | -2.053 |
glers | -2.014 |
Token | would |
Token ID | 561 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Iro | +1.355 |
aiman | +1.350 |
imilar | +1.341 |
Kara | +1.275 |
200000 | +1.254 |
Neg logit contributions | |
doct | -1.303 |
)=( | -1.279 |
nton | -1.277 |
Doct | -1.242 |
Omaha | -1.215 |
Token | die |
Token ID | 4656 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
doct | +0.971 |
)=( | +0.946 |
nton | +0.942 |
Doct | +0.926 |
Omaha | +0.917 |
Neg logit contributions | |
imilar | -0.911 |
aiman | -0.902 |
Iro | -0.900 |
200000 | -0.853 |
annis | -0.839 |
Token | he |
Token ID | 339 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
Iro | +0.360 |
imilar | +0.359 |
aiman | +0.359 |
200000 | +0.338 |
annis | +0.334 |
Neg logit contributions | |
doct | -0.327 |
)=( | -0.321 |
nton | -0.319 |
Doct | -0.310 |
Omaha | -0.305 |
Token | will |
Token ID | 481 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
doct | +0.483 |
)=( | +0.471 |
nton | +0.466 |
Doct | +0.457 |
Omaha | +0.452 |
Neg logit contributions | |
imilar | -0.686 |
aiman | -0.680 |
Iro | -0.680 |
200000 | -0.649 |
annis | -0.643 |
Token | take |
Token ID | 1011 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Iro | +0.930 |
imilar | +0.924 |
aiman | +0.914 |
200000 | +0.880 |
sabotage | +0.868 |
Neg logit contributions | |
doct | -0.935 |
)=( | -0.935 |
nton | -0.915 |
Doct | -0.896 |
Omaha | -0.891 |
Token | the |
Token ID | 262 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
doct | +2.044 |
nton | +1.959 |
)=( | +1.958 |
Doct | +1.939 |
Omaha | +1.930 |
Neg logit contributions | |
imilar | -2.228 |
aiman | -2.200 |
Iro | -2.162 |
200000 | -2.074 |
annis | -2.053 |
Token | Turtles |
Token ID | 44356 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Iro | +0.623 |
imilar | +0.621 |
aiman | +0.616 |
200000 | +0.585 |
annis | +0.578 |
Neg logit contributions | |
doct | -0.560 |
)=( | -0.557 |
nton | -0.551 |
Doct | -0.533 |
Omaha | -0.526 |
Token | with |
Token ID | 351 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
Iro | +3.867 |
imilar | +3.793 |
aiman | +3.780 |
annis | +3.586 |
200000 | +3.583 |
Neg logit contributions | |
)=( | -3.431 |
doct | -3.397 |
nton | -3.371 |
Doct | -3.261 |
Omaha | -3.202 |
Token | him |
Token ID | 683 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Iro | +0.527 |
imilar | +0.522 |
aiman | +0.521 |
200000 | +0.488 |
annis | +0.482 |
Neg logit contributions | |
doct | -0.671 |
)=( | -0.662 |
nton | -0.658 |
Doct | -0.645 |
Omaha | -0.633 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
doct | +1.548 |
nton | +1.490 |
)=( | +1.490 |
Doct | +1.462 |
Omaha | +1.447 |
Neg logit contributions | |
imilar | -1.876 |
aiman | -1.852 |
Iro | -1.841 |
200000 | -1.760 |
annis | -1.736 |
Token | Don |
Token ID | 2094 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Iro | +1.587 |
imilar | +1.545 |
aiman | +1.534 |
200000 | +1.462 |
Kara | +1.449 |
Neg logit contributions | |
doct | -1.586 |
)=( | -1.541 |
nton | -1.539 |
Doct | -1.479 |
Omaha | -1.459 |
Token | atell |
Token ID | 7528 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Iro | +1.509 |
imilar | +1.504 |
aiman | +1.500 |
akov | +1.406 |
arius | +1.403 |
Neg logit contributions | |
doct | -1.217 |
)=( | -1.204 |
nton | -1.161 |
Doct | -1.149 |
Omaha | -1.141 |
Token | have |
Token ID | 423 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
doct | +1.579 |
)=( | +1.523 |
nton | +1.514 |
Doct | +1.494 |
Omaha | +1.474 |
Neg logit contributions | |
imilar | -1.843 |
aiman | -1.825 |
Iro | -1.814 |
200000 | -1.734 |
annis | -1.712 |
Token | been |
Token ID | 587 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
doct | +0.266 |
)=( | +0.259 |
nton | +0.259 |
Doct | +0.252 |
Omaha | +0.250 |
Neg logit contributions | |
imilar | -0.312 |
aiman | -0.309 |
Iro | -0.308 |
200000 | -0.293 |
annis | -0.288 |
Token | getting |
Token ID | 1972 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
imilar | +0.260 |
Iro | +0.257 |
aiman | +0.257 |
200000 | +0.242 |
annis | +0.240 |
Neg logit contributions | |
doct | -0.256 |
)=( | -0.252 |
nton | -0.251 |
Doct | -0.246 |
Omaha | -0.244 |
Token | a |
Token ID | 257 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Iro | +4.376 |
aiman | +4.328 |
imilar | +4.290 |
Kara | +4.152 |
sabotage | +4.068 |
Neg logit contributions | |
nton | -4.338 |
)=( | -4.226 |
doct | -4.179 |
Doct | -4.076 |
bringing | -4.042 |
Token | lot |
Token ID | 1256 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
imilar | +2.012 |
aiman | +2.005 |
Iro | +1.989 |
200000 | +1.848 |
Kara | +1.826 |
Neg logit contributions | |
doct | -2.733 |
)=( | -2.721 |
nton | -2.718 |
Omaha | -2.646 |
Doct | -2.643 |
Token | of |
Token ID | 286 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
aiman | +4.860 |
Iro | +4.844 |
imilar | +4.815 |
Kara | +4.527 |
akov | +4.475 |
Neg logit contributions | |
nton | -4.513 |
doct | -4.367 |
)=( | -4.351 |
Doct | -4.260 |
Omaha | -4.215 |
Token | attention |
Token ID | 3241 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Iro | +4.481 |
aiman | +4.372 |
imilar | +4.318 |
Kara | +4.183 |
sabotage | +4.104 |
Neg logit contributions | |
nton | -6.050 |
)=( | -5.891 |
doct | -5.809 |
bringing | -5.696 |
Doct | -5.658 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aiman | +4.606 |
Iro | +4.470 |
imilar | +4.463 |
Kara | +4.228 |
200000 | +4.211 |
Neg logit contributions | |
doct | -4.797 |
nton | -4.787 |
)=( | -4.763 |
Omaha | -4.626 |
Doct | -4.622 |
Token | especially |
Token ID | 2592 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
imilar | +1.548 |
Iro | +1.534 |
aiman | +1.531 |
200000 | +1.444 |
akov | +1.434 |
Neg logit contributions | |
doct | -1.384 |
nton | -1.358 |
)=( | -1.354 |
Doct | -1.319 |
Omaha | -1.311 |
Token | in |
Token ID | 287 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
aiman | +4.081 |
imilar | +4.071 |
Iro | +4.070 |
Kara | +3.842 |
200000 | +3.807 |
Neg logit contributions | |
nton | -3.646 |
doct | -3.633 |
)=( | -3.543 |
Omaha | -3.447 |
Doct | -3.439 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
imilar | +2.112 |
Iro | +2.087 |
aiman | +2.060 |
Kara | +1.942 |
200000 | +1.913 |
Neg logit contributions | |
doct | -2.227 |
nton | -2.212 |
)=( | -2.174 |
Doct | -2.137 |
Omaha | -2.081 |
Token | after |
Token ID | 706 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
doct | +1.820 |
)=( | +1.760 |
nton | +1.755 |
Doct | +1.722 |
Omaha | +1.707 |
Neg logit contributions | |
imilar | -2.051 |
aiman | -2.029 |
Iro | -2.009 |
200000 | -1.926 |
annis | -1.898 |
Token | his |
Token ID | 465 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
Iro | +2.002 |
aiman | +1.973 |
imilar | +1.970 |
200000 | +1.884 |
Kara | +1.883 |
Neg logit contributions | |
doct | -1.816 |
)=( | -1.792 |
nton | -1.758 |
Doct | -1.725 |
Omaha | -1.683 |
Token | daughter |
Token ID | 4957 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
imilar | +0.875 |
Iro | +0.873 |
aiman | +0.870 |
200000 | +0.832 |
Kara | +0.820 |
Neg logit contributions | |
doct | -0.728 |
)=( | -0.710 |
nton | -0.704 |
Doct | -0.687 |
Omaha | -0.673 |
Token | has |
Token ID | 468 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
Iro | +3.291 |
imilar | +3.167 |
aiman | +3.164 |
Kara | +3.102 |
200000 | +2.990 |
Neg logit contributions | |
)=( | -2.780 |
doct | -2.731 |
nton | -2.663 |
Doct | -2.648 |
Omaha | -2.580 |
Token | gone |
Token ID | 3750 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Iro | +0.748 |
imilar | +0.743 |
aiman | +0.739 |
200000 | +0.704 |
Kara | +0.700 |
Neg logit contributions | |
doct | -0.571 |
)=( | -0.566 |
nton | -0.558 |
Doct | -0.546 |
Omaha | -0.539 |
Token | to |
Token ID | 284 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Iro | +2.793 |
aiman | +2.732 |
imilar | +2.700 |
Kara | +2.636 |
200000 | +2.554 |
Neg logit contributions | |
doct | -2.624 |
)=( | -2.617 |
nton | -2.554 |
Doct | -2.540 |
Omaha | -2.470 |
Token | sleep |
Token ID | 3993 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Iro | +0.527 |
imilar | +0.524 |
aiman | +0.518 |
Kara | +0.491 |
200000 | +0.490 |
Neg logit contributions | |
doct | -0.513 |
)=( | -0.505 |
nton | -0.498 |
Doct | -0.487 |
Omaha | -0.477 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
doct | +1.233 |
)=( | +1.192 |
nton | +1.190 |
Doct | +1.167 |
Omaha | +1.156 |
Neg logit contributions | |
imilar | -1.420 |
aiman | -1.403 |
Iro | -1.396 |
200000 | -1.332 |
annis | -1.316 |
Token | At |
Token ID | 1629 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
doct | +2.686 |
nton | +2.616 |
)=( | +2.607 |
Omaha | +2.607 |
Doct | +2.603 |
Neg logit contributions | |
imilar | -3.474 |
aiman | -3.429 |
Iro | -3.340 |
annis | -3.247 |
200000 | -3.214 |
Token | a |
Token ID | 257 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
imilar | +0.017 |
Iro | +0.017 |
aiman | +0.017 |
200000 | +0.016 |
annis | +0.016 |
Neg logit contributions | |
doct | -0.016 |
)=( | -0.015 |
nton | -0.015 |
Doct | -0.015 |
Omaha | -0.014 |
Token | Le |
Token ID | 1004 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Iro | +7.129 |
Kara | +6.964 |
imilar | +6.952 |
aiman | +6.876 |
200000 | +6.625 |
Neg logit contributions | |
)=( | -7.234 |
doct | -6.883 |
nton | -6.835 |
Doct | -6.599 |
bringing | -6.599 |
Token | ways |
Token ID | 1322 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
imilar | +0.029 |
Iro | +0.028 |
aiman | +0.028 |
200000 | +0.027 |
annis | +0.027 |
Neg logit contributions | |
doct | -0.025 |
)=( | -0.024 |
nton | -0.024 |
Doct | -0.024 |
Omaha | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
imilar | +1.597 |
Iro | +1.580 |
aiman | +1.575 |
annis | +1.488 |
200000 | +1.481 |
Neg logit contributions | |
)=( | -1.466 |
doct | -1.463 |
nton | -1.444 |
Doct | -1.420 |
Omaha | -1.393 |
Token | did |
Token ID | 750 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
imilar | +0.498 |
aiman | +0.495 |
Iro | +0.494 |
200000 | +0.466 |
annis | +0.462 |
Neg logit contributions | |
doct | -0.450 |
nton | -0.441 |
)=( | -0.440 |
Doct | -0.430 |
Omaha | -0.424 |
Token | little |
Token ID | 1310 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aiman | +4.106 |
Iro | +4.071 |
imilar | +4.019 |
sabotage | +3.844 |
annis | +3.842 |
Neg logit contributions | |
)=( | -5.120 |
doct | -5.086 |
nton | -5.006 |
Doct | -4.840 |
Omaha | -4.836 |
Token | for |
Token ID | 329 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
imilar | +1.192 |
aiman | +1.191 |
Iro | +1.187 |
200000 | +1.114 |
sabotage | +1.109 |
Neg logit contributions | |
doct | -1.023 |
nton | -1.009 |
)=( | -1.008 |
Doct | -0.975 |
Omaha | -0.968 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Iro | +3.341 |
aiman | +3.337 |
imilar | +3.336 |
sabotage | +3.112 |
Kara | +3.100 |
Neg logit contributions | |
)=( | -3.743 |
nton | -3.726 |
doct | -3.703 |
Doct | -3.632 |
Omaha | -3.502 |
Token | economy |
Token ID | 3773 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Iro | +2.953 |
imilar | +2.949 |
aiman | +2.942 |
200000 | +2.744 |
Kara | +2.727 |
Neg logit contributions | |
)=( | -3.458 |
doct | -3.403 |
nton | -3.398 |
Doct | -3.357 |
Omaha | -3.253 |
Token | or |
Token ID | 393 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
imilar | +2.027 |
aiman | +2.005 |
Iro | +1.985 |
200000 | +1.873 |
annis | +1.870 |
Neg logit contributions | |
)=( | -2.085 |
doct | -2.069 |
nton | -2.021 |
Doct | -1.993 |
Omaha | -1.961 |
Token | for |
Token ID | 329 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
doct | +0.253 |
)=( | +0.247 |
nton | +0.247 |
Doct | +0.242 |
Omaha | +0.238 |
Neg logit contributions | |
imilar | -0.265 |
aiman | -0.263 |
Iro | -0.262 |
200000 | -0.248 |
annis | -0.245 |
Token | health |
Token ID | 1535 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Iro | +4.072 |
aiman | +4.039 |
imilar | +4.038 |
Kara | +3.805 |
sabotage | +3.799 |
Neg logit contributions | |
)=( | -4.622 |
doct | -4.577 |
nton | -4.566 |
Doct | -4.511 |
Omaha | -4.309 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
imilar | +3.444 |
aiman | +3.412 |
Iro | +3.385 |
sabotage | +3.204 |
200000 | +3.191 |
Neg logit contributions | |
)=( | -3.803 |
doct | -3.801 |
nton | -3.751 |
Doct | -3.734 |
Omaha | -3.643 |
Token | great |
Token ID | 1049 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
imilar | +0.458 |
aiman | +0.455 |
Iro | +0.452 |
200000 | +0.428 |
annis | +0.422 |
Neg logit contributions | |
doct | -0.464 |
)=( | -0.453 |
nton | -0.452 |
Doct | -0.443 |
Omaha | -0.439 |
Token | way |
Token ID | 835 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
aiman | +2.419 |
Iro | +2.418 |
imilar | +2.415 |
200000 | +2.258 |
Kara | +2.247 |
Neg logit contributions | |
doct | -2.520 |
nton | -2.478 |
)=( | -2.461 |
Doct | -2.409 |
Omaha | -2.373 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
imilar | +0.777 |
aiman | +0.774 |
Iro | +0.769 |
200000 | +0.728 |
annis | +0.720 |
Neg logit contributions | |
doct | -0.637 |
nton | -0.619 |
)=( | -0.612 |
Doct | -0.602 |
Omaha | -0.597 |
Token | utilize |
Token ID | 17624 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
doct | +0.232 |
)=( | +0.226 |
nton | +0.226 |
Doct | +0.221 |
Omaha | +0.220 |
Neg logit contributions | |
imilar | -0.231 |
aiman | -0.229 |
Iro | -0.228 |
200000 | -0.216 |
annis | -0.213 |
Token | a |
Token ID | 257 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
aiman | +4.036 |
Iro | +4.016 |
imilar | +4.006 |
Kara | +3.855 |
200000 | +3.732 |
Neg logit contributions | |
nton | -4.247 |
doct | -4.158 |
)=( | -4.141 |
Doct | -3.959 |
Omaha | -3.942 |
Token | very |
Token ID | 845 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aiman | +7.929 |
Kara | +7.693 |
Iro | +7.649 |
imilar | +7.502 |
200000 | +7.195 |
Neg logit contributions | |
)=( | -8.489 |
nton | -8.438 |
doct | -8.178 |
Omaha | -7.991 |
Doct | -7.974 |
Token | cool |
Token ID | 3608 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Iro | +9.995 |
Kara | +9.771 |
imilar | +9.766 |
aiman | +9.760 |
sabotage | +8.948 |
Neg logit contributions | |
nton | -10.570 |
)=( | -10.450 |
glers | -10.208 |
bringing | -10.206 |
Doct | -9.813 |
Token | character |
Token ID | 2095 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
aiman | +6.369 |
Iro | +6.304 |
Kara | +6.155 |
imilar | +6.033 |
200000 | +5.906 |
Neg logit contributions | |
nton | -6.535 |
doct | -6.504 |
)=( | -6.429 |
Doct | -6.166 |
glers | -6.144 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
imilar | +0.311 |
aiman | +0.310 |
Iro | +0.308 |
200000 | +0.292 |
annis | +0.288 |
Neg logit contributions | |
doct | -0.266 |
)=( | -0.259 |
nton | -0.257 |
Doct | -0.252 |
Omaha | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
doct | +1.968 |
)=( | +1.910 |
Doct | +1.891 |
nton | +1.886 |
Omaha | +1.864 |
Neg logit contributions | |
imilar | -2.492 |
aiman | -2.462 |
Iro | -2.418 |
200000 | -2.330 |
annis | -2.316 |
Token |
|
Token ID | 198 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
doct | +0.513 |
)=( | +0.495 |
nton | +0.494 |
Doct | +0.485 |
Omaha | +0.479 |
Neg logit contributions | |
imilar | -0.633 |
aiman | -0.626 |
Iro | -0.623 |
200000 | -0.594 |
annis | -0.588 |
Token | good |
Token ID | 922 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
imilar | +0.323 |
aiman | +0.319 |
Iro | +0.319 |
200000 | +0.302 |
annis | +0.298 |
Neg logit contributions | |
doct | -0.314 |
)=( | -0.307 |
nton | -0.306 |
Doct | -0.298 |
Omaha | -0.297 |
Token | way |
Token ID | 835 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
Iro | +5.687 |
aiman | +5.575 |
imilar | +5.393 |
Attribution | +5.332 |
sabotage | +5.320 |
Neg logit contributions | |
)=( | -6.555 |
nton | -6.509 |
doct | -6.361 |
Doct | -6.244 |
Omaha | -6.206 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
imilar | +0.761 |
aiman | +0.757 |
Iro | +0.754 |
200000 | +0.717 |
annis | +0.709 |
Neg logit contributions | |
doct | -0.617 |
nton | -0.599 |
)=( | -0.597 |
Doct | -0.583 |
Omaha | -0.581 |
Token | get |
Token ID | 651 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Iro | +1.907 |
imilar | +1.890 |
aiman | +1.880 |
sabotage | +1.794 |
200000 | +1.772 |
Neg logit contributions | |
)=( | -2.258 |
doct | -2.243 |
nton | -2.237 |
Omaha | -2.153 |
Doct | -2.152 |
Token | feedback |
Token ID | 7538 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Iro | +7.151 |
aiman | +6.918 |
Kara | +6.788 |
imilar | +6.714 |
sabotage | +6.599 |
Neg logit contributions | |
nton | -8.006 |
)=( | -7.865 |
doct | -7.462 |
Doct | -7.450 |
bringing | -7.391 |
Token | on |
Token ID | 319 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
imilar | +4.817 |
aiman | +4.779 |
Iro | +4.773 |
Kara | +4.497 |
200000 | +4.476 |
Neg logit contributions | |
nton | -4.154 |
)=( | -4.152 |
doct | -4.114 |
Omaha | -3.959 |
Doct | -3.933 |
Token | an |
Token ID | 281 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Iro | +10.950 |
Kara | +10.419 |
sabotage | +10.276 |
aiman | +10.182 |
imilar | +9.897 |
Neg logit contributions | |
nton | -12.669 |
)=( | -12.420 |
glers | -11.720 |
Doct | -11.285 |
doct | -11.264 |
Token | article |
Token ID | 2708 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Iro | +9.092 |
aiman | +8.785 |
imilar | +8.369 |
Attribution | +8.282 |
annis | +8.252 |
Neg logit contributions | |
nton | -10.937 |
glers | -10.487 |
)=( | -10.268 |
doct | -10.070 |
Doct | -9.965 |
Token | , |
Token ID | 11 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
Iro | +4.486 |
imilar | +4.460 |
aiman | +4.452 |
200000 | +4.212 |
Kara | +4.207 |
Neg logit contributions | |
)=( | -4.608 |
nton | -4.574 |
doct | -4.534 |
Omaha | -4.322 |
Doct | -4.291 |
Token | specially |
Token ID | 20905 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Iro | +6.588 |
imilar | +6.539 |
aiman | +6.504 |
Kara | +6.325 |
Attribution | +6.243 |
Neg logit contributions | |
nton | -6.985 |
)=( | -6.908 |
doct | -6.561 |
Omaha | -6.519 |
glers | -6.495 |
Token | if |
Token ID | 611 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Iro | +3.232 |
aiman | +3.230 |
imilar | +3.225 |
Kara | +3.050 |
sabotage | +3.018 |
Neg logit contributions | |
nton | -2.931 |
)=( | -2.884 |
doct | -2.846 |
Omaha | -2.772 |
Doct | -2.764 |
Token | Steel |
Token ID | 7851 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
imilar | +2.712 |
Iro | +2.711 |
aiman | +2.640 |
200000 | +2.540 |
Kara | +2.530 |
Neg logit contributions | |
)=( | -2.872 |
nton | -2.858 |
doct | -2.855 |
Doct | -2.752 |
Omaha | -2.702 |
Token | Poles |
Token ID | 45631 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
imilar | +0.287 |
Iro | +0.285 |
aiman | +0.283 |
200000 | +0.264 |
annis | +0.260 |
Neg logit contributions | |
doct | -0.366 |
)=( | -0.357 |
nton | -0.353 |
Doct | -0.348 |
Omaha | -0.347 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
doct | +0.232 |
)=( | +0.227 |
nton | +0.226 |
Doct | +0.221 |
Omaha | +0.218 |
Neg logit contributions | |
imilar | -0.253 |
aiman | -0.250 |
Iro | -0.250 |
200000 | -0.237 |
annis | -0.235 |
Token | It |
Token ID | 632 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
doct | +1.237 |
)=( | +1.195 |
nton | +1.188 |
Doct | +1.173 |
Omaha | +1.159 |
Neg logit contributions | |
imilar | -1.560 |
aiman | -1.543 |
Iro | -1.528 |
200000 | -1.463 |
annis | -1.450 |
Token | worked |
Token ID | 3111 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
imilar | +1.099 |
aiman | +1.091 |
Iro | +1.089 |
200000 | +1.041 |
annis | +1.027 |
Neg logit contributions | |
doct | -0.945 |
)=( | -0.924 |
nton | -0.915 |
Doct | -0.898 |
Omaha | -0.892 |
Token | amazingly |
Token ID | 32513 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Iro | +6.319 |
aiman | +6.185 |
imilar | +6.148 |
Kara | +6.069 |
bas | +5.942 |
Neg logit contributions | |
)=( | -6.878 |
nton | -6.812 |
doct | -6.759 |
Doct | -6.476 |
Omaha | -6.308 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
bas | +9.420 |
Iro | +9.385 |
imilar | +9.385 |
Kara | +9.284 |
aiman | +9.158 |
Neg logit contributions | |
)=( | -12.355 |
nton | -12.014 |
doct | -11.574 |
Doct | -11.415 |
Omaha | -11.254 |
Token | We |
Token ID | 775 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Iro | +1.173 |
imilar | +1.169 |
aiman | +1.156 |
200000 | +1.110 |
Kara | +1.098 |
Neg logit contributions | |
doct | -1.023 |
nton | -0.993 |
)=( | -0.985 |
Doct | -0.952 |
Omaha | -0.944 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
imilar | +2.044 |
Iro | +2.036 |
aiman | +2.032 |
200000 | +1.926 |
akov | +1.907 |
Neg logit contributions | |
)=( | -1.753 |
doct | -1.752 |
nton | -1.749 |
Doct | -1.709 |
Omaha | -1.681 |
Token | we |
Token ID | 356 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
doct | +2.608 |
)=( | +2.507 |
nton | +2.479 |
Doct | +2.465 |
Omaha | +2.440 |
Neg logit contributions | |
imilar | -3.250 |
aiman | -3.205 |
Iro | -3.183 |
200000 | -3.034 |
annis | -3.011 |
Token | were |
Token ID | 547 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
imilar | +3.429 |
aiman | +3.424 |
Iro | +3.387 |
200000 | +3.204 |
annis | +3.198 |
Neg logit contributions | |
nton | -3.621 |
)=( | -3.580 |
doct | -3.577 |
Doct | -3.529 |
Omaha | -3.508 |
Token | that |
Token ID | 326 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Iro | +7.733 |
imilar | +7.371 |
aiman | +7.315 |
Kara | +7.277 |
sabotage | +6.990 |
Neg logit contributions | |
nton | -8.329 |
)=( | -8.183 |
doct | -8.178 |
Doct | -7.565 |
glers | -7.541 |
Token | episode |
Token ID | 4471 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Iro | +7.821 |
aiman | +7.648 |
Kara | +7.447 |
sabotage | +7.234 |
imilar | +7.193 |
Neg logit contributions | |
nton | -8.011 |
)=( | -7.943 |
doct | -7.746 |
Doct | -7.584 |
glers | -7.286 |
Token | set |
Token ID | 900 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Iro | +4.726 |
aiman | +4.657 |
imilar | +4.577 |
Kara | +4.382 |
200000 | +4.335 |
Neg logit contributions | |
nton | -4.263 |
)=( | -4.229 |
doct | -4.194 |
Doct | -4.034 |
Omaha | -4.003 |
Token | that |
Token ID | 326 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Iro | +4.584 |
imilar | +4.405 |
aiman | +4.395 |
Kara | +4.326 |
200000 | +4.180 |
Neg logit contributions | |
doct | -4.132 |
nton | -4.082 |
)=( | -4.043 |
Doct | -3.857 |
bringing | -3.746 |
Token | theme |
Token ID | 7505 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Iro | +4.223 |
aiman | +4.051 |
imilar | +4.015 |
Kara | +3.938 |
sabotage | +3.853 |
Neg logit contributions | |
)=( | -3.437 |
doct | -3.397 |
nton | -3.376 |
Doct | -3.251 |
glers | -3.194 |
Token | for |
Token ID | 329 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Iro | +5.047 |
aiman | +4.959 |
imilar | +4.869 |
Kara | +4.774 |
bas | +4.634 |
Neg logit contributions | |
)=( | -4.645 |
doct | -4.553 |
nton | -4.539 |
Doct | -4.412 |
glers | -4.355 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Iro | +10.132 |
Kara | +10.065 |
aiman | +9.566 |
imilar | +9.284 |
sabotage | +9.194 |
Neg logit contributions | |
nton | -12.233 |
doct | -12.071 |
)=( | -11.867 |
glers | -11.321 |
Doct | -11.102 |
Token | whole |
Token ID | 2187 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
Iro | +9.926 |
Kara | +9.675 |
aiman | +9.538 |
imilar | +8.749 |
sabotage | +8.732 |
Neg logit contributions | |
)=( | -12.314 |
nton | -12.177 |
doct | -11.934 |
Doct | -11.454 |
bringing | -11.291 |
Token | show |
Token ID | 905 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Iro | +7.928 |
Kara | +7.473 |
aiman | +7.377 |
imilar | +7.073 |
sabotage | +6.816 |
Neg logit contributions | |
)=( | -10.467 |
nton | -10.345 |
doct | -10.248 |
glers | -9.913 |
Doct | -9.754 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
aiman | +2.719 |
imilar | +2.711 |
Iro | +2.686 |
200000 | +2.534 |
Kara | +2.494 |
Neg logit contributions | |
doct | -2.855 |
)=( | -2.802 |
nton | -2.760 |
Doct | -2.709 |
Omaha | -2.687 |
Token | So |
Token ID | 1406 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Iro | +6.861 |
Kara | +6.533 |
aiman | +6.255 |
imilar | +6.233 |
200000 | +6.140 |
Neg logit contributions | |
doct | -7.652 |
nton | -7.444 |
)=( | -7.380 |
bringing | -6.952 |
mater | -6.936 |
Token | to |
Token ID | 284 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
imilar | +2.737 |
Iro | +2.725 |
aiman | +2.704 |
200000 | +2.606 |
annis | +2.566 |
Neg logit contributions | |
doct | -2.315 |
nton | -2.270 |
)=( | -2.250 |
Doct | -2.214 |
Omaha | -2.208 |
Token | be |
Token ID | 307 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
imilar | +0.275 |
aiman | +0.270 |
Iro | +0.269 |
200000 | +0.258 |
sabotage | +0.250 |
Neg logit contributions | |
doct | -0.348 |
)=( | -0.341 |
nton | -0.339 |
Doct | -0.335 |
Omaha | -0.332 |
Token | worse |
Token ID | 4785 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
imilar | +0.916 |
Iro | +0.908 |
aiman | +0.908 |
200000 | +0.860 |
sabotage | +0.840 |
Neg logit contributions | |
doct | -0.961 |
)=( | -0.956 |
nton | -0.954 |
Doct | -0.937 |
Omaha | -0.918 |
Token | than |
Token ID | 621 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
aiman | +3.114 |
imilar | +3.097 |
Iro | +3.078 |
200000 | +2.965 |
sabotage | +2.907 |
Neg logit contributions | |
doct | -3.006 |
)=( | -2.949 |
nton | -2.895 |
Doct | -2.886 |
Omaha | -2.884 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Iro | +4.584 |
imilar | +4.500 |
aiman | +4.424 |
sabotage | +4.355 |
Kara | +4.336 |
Neg logit contributions | |
)=( | -4.526 |
nton | -4.458 |
doct | -4.418 |
Doct | -4.284 |
bringing | -4.187 |
Token | partial |
Token ID | 13027 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Iro | +2.922 |
imilar | +2.897 |
aiman | +2.853 |
sabotage | +2.749 |
Kara | +2.744 |
Neg logit contributions | |
)=( | -2.700 |
nton | -2.632 |
doct | -2.617 |
Doct | -2.536 |
Omaha | -2.496 |
Token | reactor |
Token ID | 21905 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Iro | +9.035 |
sabotage | +9.016 |
Kara | +8.583 |
imilar | +8.550 |
aiman | +8.075 |
Neg logit contributions | |
)=( | -12.601 |
nton | -12.331 |
Doct | -11.811 |
glers | -11.527 |
doct | -11.525 |
Token | meltdown |
Token ID | 37824 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Iro | +7.816 |
sabotage | +7.622 |
Kara | +7.260 |
imilar | +7.255 |
aiman | +7.034 |
Neg logit contributions | |
)=( | -9.860 |
nton | -9.541 |
Doct | -9.420 |
doct | -9.296 |
bringing | -9.034 |
Token | at |
Token ID | 379 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Iro | +9.801 |
imilar | +9.597 |
Kara | +9.499 |
sabotage | +9.485 |
aiman | +9.370 |
Neg logit contributions | |
)=( | -9.085 |
nton | -9.067 |
doct | -8.954 |
Doct | -8.774 |
glers | -8.461 |
Token | Three |
Token ID | 7683 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Iro | +4.540 |
imilar | +4.514 |
Kara | +4.341 |
aiman | +4.332 |
sabotage | +4.147 |
Neg logit contributions | |
)=( | -5.063 |
nton | -4.929 |
doct | -4.924 |
Doct | -4.736 |
bringing | -4.669 |
Token | Mile |
Token ID | 26004 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
imilar | +1.851 |
Iro | +1.835 |
aiman | +1.811 |
200000 | +1.741 |
Kara | +1.736 |
Neg logit contributions | |
doct | -1.227 |
)=( | -1.211 |
nton | -1.173 |
Doct | -1.127 |
Omaha | -1.105 |