Token | Republican |
Token ID | 3415 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
haps | +0.432 |
Medic | +0.405 |
ggle | +0.391 |
ombo | +0.389 |
Kappa | +0.372 |
Neg logit contributions | |
retard | -0.396 |
strip | -0.342 |
lesbians | -0.319 |
clean | -0.301 |
LS | -0.298 |
Token | politicians |
Token ID | 7602 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
retard | +0.825 |
strip | +0.726 |
lesbians | +0.685 |
LS | +0.642 |
clean | +0.639 |
Neg logit contributions | |
haps | -0.736 |
Medic | -0.677 |
ombo | -0.659 |
ggle | -0.658 |
Kappa | -0.610 |
Token | still |
Token ID | 991 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
haps | +0.398 |
Medic | +0.367 |
ggle | +0.361 |
ombo | +0.359 |
Kappa | +0.336 |
Neg logit contributions | |
retard | -0.383 |
strip | -0.332 |
lesbians | -0.317 |
LS | -0.300 |
clean | -0.295 |
Token | c |
Token ID | 269 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
haps | +1.092 |
ggle | +1.008 |
Medic | +1.006 |
ombo | +0.993 |
Kappa | +0.928 |
Neg logit contributions | |
retard | -1.005 |
strip | -0.870 |
lesbians | -0.829 |
LS | -0.791 |
clean | -0.773 |
Token | ower |
Token ID | 789 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
haps | +0.393 |
ggle | +0.350 |
ombo | +0.346 |
Medic | +0.345 |
auld | +0.322 |
Neg logit contributions | |
retard | -0.491 |
strip | -0.433 |
lesbians | -0.418 |
LS | -0.390 |
rebellious | -0.386 |
Token | before |
Token ID | 878 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
haps | +0.041 |
Medic | +0.038 |
ombo | +0.038 |
ggle | +0.038 |
Kappa | +0.035 |
Neg logit contributions | |
retard | -0.032 |
strip | -0.028 |
lesbians | -0.026 |
LS | -0.024 |
clean | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
haps | +5.103 |
Medic | +4.731 |
ombo | +4.533 |
ggle | +4.459 |
Kappa | +4.342 |
Neg logit contributions | |
retard | -5.252 |
strip | -4.497 |
lesbians | -4.288 |
clean | -4.126 |
susp | -4.049 |
Token | power |
Token ID | 1176 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
haps | +0.873 |
Medic | +0.832 |
ombo | +0.792 |
ggle | +0.783 |
Kappa | +0.745 |
Neg logit contributions | |
retard | -0.900 |
strip | -0.787 |
lesbians | -0.740 |
clean | -0.696 |
susp | -0.677 |
Token | of |
Token ID | 286 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
haps | +0.785 |
Medic | +0.744 |
ggle | +0.724 |
ombo | +0.714 |
Kappa | +0.682 |
Neg logit contributions | |
retard | -0.728 |
strip | -0.623 |
lesbians | -0.577 |
LS | -0.539 |
rebellious | -0.537 |
Token | movement |
Token ID | 3356 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
haps | +0.223 |
Medic | +0.210 |
ombo | +0.204 |
ggle | +0.202 |
Kappa | +0.192 |
Neg logit contributions | |
retard | -0.212 |
strip | -0.182 |
lesbians | -0.171 |
clean | -0.161 |
LS | -0.157 |
Token | conservatism |
Token ID | 33933 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
haps | +0.049 |
Medic | +0.046 |
ombo | +0.045 |
ggle | +0.045 |
Kappa | +0.042 |
Neg logit contributions | |
retard | -0.048 |
strip | -0.042 |
lesbians | -0.039 |
clean | -0.036 |
LS | -0.036 |
Token | full |
Token ID | 1336 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
retard | +0.467 |
strip | +0.402 |
lesbians | +0.375 |
clean | +0.351 |
LS | +0.346 |
Neg logit contributions | |
haps | -0.502 |
Medic | -0.479 |
ombo | -0.458 |
ggle | -0.453 |
Kappa | -0.434 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
retard | +2.279 |
strip | +1.982 |
lesbians | +1.856 |
clean | +1.710 |
LS | +1.709 |
Neg logit contributions | |
haps | -2.383 |
Medic | -2.235 |
ombo | -2.173 |
ggle | -2.152 |
Kappa | -2.017 |
Token | : |
Token ID | 25 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
haps | +1.076 |
Medic | +1.017 |
ombo | +0.980 |
ggle | +0.978 |
rals | +0.916 |
Neg logit contributions | |
retard | -1.155 |
strip | -1.007 |
lesbians | -0.952 |
rebellious | -0.883 |
clean | -0.881 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
haps | +0.092 |
Medic | +0.086 |
ombo | +0.083 |
ggle | +0.082 |
Kappa | +0.076 |
Neg logit contributions | |
retard | -0.118 |
strip | -0.105 |
lesbians | -0.099 |
rebellious | -0.092 |
clean | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
haps | +0.666 |
Medic | +0.625 |
ombo | +0.594 |
ggle | +0.591 |
Kappa | +0.549 |
Neg logit contributions | |
retard | -0.938 |
strip | -0.831 |
lesbians | -0.787 |
rebellious | -0.746 |
LS | -0.733 |
Token | https |
Token ID | 5450 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
haps | +0.846 |
Medic | +0.784 |
ombo | +0.767 |
ggle | +0.753 |
rals | +0.702 |
Neg logit contributions | |
retard | -1.101 |
strip | -0.977 |
lesbians | -0.925 |
LS | -0.864 |
rebellious | -0.857 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
haps | +3.315 |
Medic | +2.984 |
ggle | +2.876 |
ombo | +2.845 |
mia | +2.693 |
Neg logit contributions | |
retard | -6.504 |
strip | -5.856 |
lesbians | -5.568 |
rebellious | -5.458 |
surg | -5.270 |
Token | www |
Token ID | 2503 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
haps | +0.857 |
ombo | +0.781 |
Medic | +0.781 |
ggle | +0.764 |
rals | +0.708 |
Neg logit contributions | |
retard | -1.096 |
strip | -0.982 |
lesbians | -0.920 |
LS | -0.862 |
rebellious | -0.858 |
Token | . |
Token ID | 13 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
haps | +0.498 |
Medic | +0.470 |
ggle | +0.455 |
ombo | +0.453 |
Kappa | +0.425 |
Neg logit contributions | |
retard | -0.518 |
strip | -0.448 |
lesbians | -0.420 |
rebellious | -0.397 |
LS | -0.384 |
Token | eff |
Token ID | 14822 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
retard | +1.915 |
strip | +1.726 |
lesbians | +1.634 |
LS | +1.542 |
rebellious | +1.533 |
Neg logit contributions | |
haps | -1.186 |
Medic | -1.078 |
ombo | -1.049 |
ggle | -1.033 |
rals | -0.938 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
retard | +0.278 |
strip | +0.241 |
lesbians | +0.225 |
rebellious | +0.206 |
LS | +0.206 |
Neg logit contributions | |
haps | -0.306 |
Medic | -0.284 |
ombo | -0.280 |
ggle | -0.277 |
rals | -0.259 |
Token | screen |
Token ID | 3159 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
haps | +0.714 |
Medic | +0.681 |
ombo | +0.646 |
ggle | +0.642 |
Kappa | +0.600 |
Neg logit contributions | |
retard | -0.868 |
strip | -0.760 |
lesbians | -0.724 |
rebellious | -0.673 |
clean | -0.670 |
Token | grab |
Token ID | 5552 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
haps | +0.393 |
Medic | +0.366 |
ggle | +0.351 |
ombo | +0.348 |
Kappa | +0.314 |
Neg logit contributions | |
retard | -0.630 |
strip | -0.555 |
lesbians | -0.540 |
rebellious | -0.507 |
LS | -0.499 |
Token | ] |
Token ID | 60 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
haps | +1.992 |
Medic | +1.922 |
ggle | +1.805 |
ombo | +1.798 |
rals | +1.671 |
Neg logit contributions | |
retard | -2.484 |
strip | -2.159 |
lesbians | -2.076 |
rebellious | -1.929 |
clean | -1.908 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
haps | +0.775 |
Medic | +0.723 |
ombo | +0.715 |
ggle | +0.704 |
rals | +0.665 |
Neg logit contributions | |
retard | -0.619 |
strip | -0.535 |
lesbians | -0.492 |
LS | -0.453 |
clean | -0.448 |
Token | ( |
Token ID | 7 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
retard | +0.423 |
strip | +0.370 |
lesbians | +0.345 |
rebellious | +0.320 |
LS | +0.319 |
Neg logit contributions | |
haps | -0.404 |
Medic | -0.374 |
ombo | -0.367 |
ggle | -0.361 |
rals | -0.336 |
Token | Updated |
Token ID | 17354 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
haps | +1.029 |
Medic | +0.967 |
ombo | +0.930 |
ggle | +0.916 |
Kappa | +0.865 |
Neg logit contributions | |
retard | -1.073 |
strip | -0.929 |
lesbians | -0.876 |
rebellious | -0.811 |
LS | -0.795 |
Token | below |
Token ID | 2174 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
haps | +4.741 |
Medic | +4.616 |
ombo | +4.403 |
ggle | +4.230 |
Kappa | +4.094 |
Neg logit contributions | |
retard | -4.851 |
strip | -4.086 |
lesbians | -3.924 |
clean | -3.640 |
rebellious | -3.639 |
Token | ) |
Token ID | 8 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
retard | +0.043 |
strip | +0.037 |
lesbians | +0.036 |
rebellious | +0.033 |
clean | +0.033 |
Neg logit contributions | |
haps | -0.040 |
Medic | -0.038 |
ombo | -0.036 |
ggle | -0.036 |
Kappa | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
haps | +0.408 |
Medic | +0.392 |
ombo | +0.365 |
ggle | +0.361 |
Kappa | +0.345 |
Neg logit contributions | |
retard | -0.472 |
strip | -0.410 |
lesbians | -0.385 |
rebellious | -0.362 |
clean | -0.359 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
haps | +0.392 |
Medic | +0.369 |
ombo | +0.346 |
ggle | +0.345 |
Kappa | +0.321 |
Neg logit contributions | |
retard | -0.578 |
strip | -0.510 |
lesbians | -0.484 |
rebellious | -0.463 |
LS | -0.449 |
Token | The |
Token ID | 464 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
haps | +0.757 |
Medic | +0.703 |
ombo | +0.684 |
ggle | +0.674 |
mia | +0.624 |
Neg logit contributions | |
retard | -0.797 |
strip | -0.692 |
lesbians | -0.640 |
rebellious | -0.599 |
LS | -0.593 |
Token | he |
Token ID | 339 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
retard | +0.278 |
strip | +0.241 |
lesbians | +0.227 |
clean | +0.210 |
rebellious | +0.207 |
Neg logit contributions | |
haps | -0.319 |
Medic | -0.300 |
ombo | -0.291 |
ggle | -0.287 |
Kappa | -0.272 |
Token | p |
Token ID | 279 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
retard | +1.122 |
strip | +0.995 |
lesbians | +0.944 |
LS | +0.884 |
clean | +0.878 |
Neg logit contributions | |
haps | -0.919 |
Medic | -0.849 |
ggle | -0.821 |
ombo | -0.821 |
Kappa | -0.760 |
Token | ales |
Token ID | 2040 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
retard | +0.273 |
strip | +0.239 |
lesbians | +0.224 |
rebellious | +0.206 |
LS | +0.206 |
Neg logit contributions | |
haps | -0.289 |
Medic | -0.266 |
ombo | -0.263 |
ggle | -0.258 |
rals | -0.242 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
retard | +1.387 |
strip | +1.204 |
lesbians | +1.124 |
LS | +1.032 |
rebellious | +1.028 |
Neg logit contributions | |
haps | -1.595 |
Medic | -1.488 |
ombo | -1.462 |
ggle | -1.446 |
Kappa | -1.355 |
Token | com |
Token ID | 401 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
haps | +1.166 |
Medic | +1.055 |
ombo | +1.045 |
ggle | +1.018 |
Kappa | +0.941 |
Neg logit contributions | |
retard | -1.597 |
strip | -1.420 |
lesbians | -1.382 |
clean | -1.295 |
rebellious | -1.283 |
Token | |
Token ID | 3907 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
retard | +0.486 |
strip | +0.432 |
lesbians | +0.415 |
rebellious | +0.387 |
LS | +0.383 |
Neg logit contributions | |
haps | -0.374 |
Medic | -0.340 |
ombo | -0.333 |
ggle | -0.330 |
rals | -0.307 |
Token | par |
Token ID | 1845 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
haps | +4.795 |
Medic | +4.253 |
ombo | +4.226 |
ggle | +4.167 |
mia | +3.895 |
Neg logit contributions | |
retard | -4.934 |
strip | -4.429 |
lesbians | -4.168 |
rebellious | -3.819 |
LS | -3.753 |
Token | |
Token ID | 3907 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
haps | +0.458 |
Medic | +0.416 |
ombo | +0.406 |
ggle | +0.403 |
rals | +0.374 |
Neg logit contributions | |
retard | -0.583 |
strip | -0.522 |
lesbians | -0.499 |
rebellious | -0.461 |
clean | -0.458 |
Token | is |
Token ID | 271 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
haps | +3.378 |
Medic | +2.883 |
ombo | +2.855 |
ggle | +2.812 |
rals | +2.649 |
Neg logit contributions | |
retard | -4.780 |
strip | -4.437 |
lesbians | -4.213 |
rebellious | -3.973 |
LS | -3.875 |
Token | |
Token ID | 3907 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
retard | +0.583 |
strip | +0.517 |
lesbians | +0.490 |
LS | +0.457 |
clean | +0.457 |
Neg logit contributions | |
haps | -0.478 |
Medic | -0.440 |
ombo | -0.428 |
ggle | -0.421 |
rals | -0.394 |
Token | on |
Token ID | 261 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
haps | +3.562 |
Medic | +3.192 |
ombo | +3.152 |
ggle | +3.111 |
rals | +2.929 |
Neg logit contributions | |
retard | -3.936 |
strip | -3.543 |
lesbians | -3.351 |
rebellious | -3.151 |
clean | -3.050 |
Token | my |
Token ID | 616 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
haps | +0.381 |
Medic | +0.360 |
ombo | +0.349 |
ggle | +0.345 |
Kappa | +0.325 |
Neg logit contributions | |
retard | -0.324 |
strip | -0.275 |
lesbians | -0.255 |
rebellious | -0.234 |
LS | -0.233 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
haps | +0.120 |
Medic | +0.114 |
ombo | +0.109 |
ggle | +0.107 |
rals | +0.100 |
Neg logit contributions | |
retard | -0.122 |
strip | -0.103 |
lesbians | -0.098 |
clean | -0.091 |
LS | -0.090 |
Token | essentials |
Token ID | 41954 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
haps | +1.542 |
Medic | +1.476 |
ombo | +1.406 |
ggle | +1.399 |
mia | +1.303 |
Neg logit contributions | |
retard | -1.435 |
strip | -1.205 |
lesbians | -1.150 |
rebellious | -1.063 |
LS | -1.056 |
Token | ! |
Token ID | 0 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
haps | +2.502 |
Medic | +2.403 |
ggle | +2.296 |
ombo | +2.286 |
Kappa | +2.157 |
Neg logit contributions | |
retard | -2.364 |
strip | -1.957 |
lesbians | -1.893 |
clean | -1.765 |
rebellious | -1.761 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
haps | +0.358 |
Medic | +0.337 |
ombo | +0.321 |
ggle | +0.318 |
Kappa | +0.299 |
Neg logit contributions | |
retard | -0.441 |
strip | -0.387 |
lesbians | -0.365 |
rebellious | -0.342 |
clean | -0.339 |
Token | Posted |
Token ID | 14231 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
haps | +0.346 |
Medic | +0.319 |
ombo | +0.315 |
ggle | +0.309 |
rals | +0.287 |
Neg logit contributions | |
retard | -0.364 |
strip | -0.319 |
lesbians | -0.296 |
rebellious | -0.276 |
LS | -0.275 |
Token | on |
Token ID | 319 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
haps | +4.539 |
Medic | +4.385 |
ombo | +4.167 |
ggle | +4.152 |
Kappa | +3.896 |
Neg logit contributions | |
retard | -4.858 |
strip | -4.107 |
lesbians | -3.854 |
clean | -3.689 |
rebellious | -3.664 |
Token | by |
Token ID | 416 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
retard | +0.277 |
strip | +0.239 |
lesbians | +0.223 |
clean | +0.208 |
rebellious | +0.208 |
Neg logit contributions | |
haps | -0.267 |
Medic | -0.258 |
ombo | -0.245 |
ggle | -0.243 |
Kappa | -0.230 |
Token | | |
Token ID | 930 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
retard | +2.062 |
strip | +1.814 |
lesbians | +1.697 |
LS | +1.573 |
clean | +1.569 |
Neg logit contributions | |
haps | -1.960 |
Medic | -1.832 |
ombo | -1.781 |
ggle | -1.761 |
Kappa | -1.642 |
Token | in |
Token ID | 287 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
retard | +0.825 |
strip | +0.728 |
lesbians | +0.687 |
rebellious | +0.646 |
clean | +0.638 |
Neg logit contributions | |
haps | -0.633 |
Medic | -0.603 |
ombo | -0.566 |
ggle | -0.558 |
Kappa | -0.527 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
retard | +2.918 |
strip | +2.572 |
lesbians | +2.402 |
LS | +2.231 |
rebellious | +2.228 |
Neg logit contributions | |
haps | -2.696 |
Medic | -2.525 |
ombo | -2.449 |
ggle | -2.419 |
Kappa | -2.254 |
Token | News |
Token ID | 3000 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
retard | +0.338 |
strip | +0.288 |
lesbians | +0.274 |
clean | +0.248 |
rebellious | +0.246 |
Neg logit contributions | |
haps | -0.308 |
Medic | -0.299 |
ombo | -0.288 |
ggle | -0.277 |
Kappa | -0.263 |
Token | 24 |
Token ID | 1987 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
haps | +1.016 |
Medic | +0.975 |
ombo | +0.955 |
ggle | +0.899 |
Kappa | +0.862 |
Neg logit contributions | |
retard | -1.086 |
strip | -0.918 |
lesbians | -0.867 |
clean | -0.805 |
rebellious | -0.794 |
Token | . |
Token ID | 13 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
haps | +1.564 |
Medic | +1.486 |
ombo | +1.443 |
ggle | +1.418 |
rals | +1.322 |
Neg logit contributions | |
retard | -1.621 |
strip | -1.362 |
lesbians | -1.285 |
clean | -1.185 |
rebellious | -1.175 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
haps | +0.415 |
Medic | +0.399 |
ombo | +0.383 |
ggle | +0.379 |
Kappa | +0.357 |
Neg logit contributions | |
retard | -0.405 |
strip | -0.340 |
lesbians | -0.322 |
rebellious | -0.294 |
clean | -0.292 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
haps | +0.475 |
Medic | +0.446 |
ggle | +0.422 |
ombo | +0.421 |
Kappa | +0.389 |
Neg logit contributions | |
retard | -0.700 |
strip | -0.619 |
lesbians | -0.590 |
rebellious | -0.562 |
LS | -0.547 |
Token | Topics |
Token ID | 25902 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
haps | +0.342 |
Medic | +0.308 |
ombo | +0.302 |
ggle | +0.296 |
rals | +0.265 |
Neg logit contributions | |
retard | -0.616 |
strip | -0.550 |
lesbians | -0.522 |
LS | -0.493 |
rebellious | -0.491 |
Token | : |
Token ID | 25 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
haps | +3.466 |
Medic | +3.293 |
ombo | +3.128 |
ggle | +3.043 |
Difficulty | +2.827 |
Neg logit contributions | |
retard | -5.884 |
strip | -5.134 |
lesbians | -4.952 |
rebellious | -4.732 |
LS | -4.671 |
Token | beef |
Token ID | 12023 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
retard | +1.555 |
strip | +1.369 |
lesbians | +1.280 |
LS | +1.201 |
clean | +1.192 |
Neg logit contributions | |
haps | -1.398 |
Medic | -1.345 |
ombo | -1.292 |
ggle | -1.271 |
rals | -1.188 |
Token | - |
Token ID | 12 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
retard | +0.994 |
strip | +0.867 |
lesbians | +0.810 |
LS | +0.749 |
rebellious | +0.747 |
Neg logit contributions | |
haps | -0.992 |
Medic | -0.926 |
ombo | -0.910 |
ggle | -0.892 |
Kappa | -0.833 |
Token | c |
Token ID | 66 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
retard | +1.721 |
strip | +1.510 |
lesbians | +1.418 |
LS | +1.330 |
rebellious | +1.317 |
Neg logit contributions | |
haps | -1.518 |
Medic | -1.417 |
ombo | -1.403 |
ggle | -1.354 |
rals | -1.277 |
Token | attle |
Token ID | 1999 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
retard | +0.495 |
strip | +0.449 |
lesbians | +0.431 |
LS | +0.410 |
rebellious | +0.409 |
Neg logit contributions | |
haps | -0.234 |
ombo | -0.203 |
Medic | -0.202 |
ggle | -0.201 |
ombs | -0.182 |
Token | gy |
Token ID | 1360 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
haps | +1.384 |
Medic | +1.279 |
ggle | +1.254 |
ombo | +1.253 |
mia | +1.176 |
Neg logit contributions | |
retard | -1.531 |
strip | -1.330 |
lesbians | -1.287 |
LS | -1.177 |
rebellious | -1.167 |
Token | for |
Token ID | 329 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
haps | +1.623 |
Medic | +1.491 |
ombo | +1.451 |
ggle | +1.436 |
Kappa | +1.361 |
Neg logit contributions | |
retard | -1.554 |
strip | -1.302 |
lesbians | -1.257 |
LS | -1.180 |
clean | -1.150 |
Token | herself |
Token ID | 5223 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
retard | +0.451 |
strip | +0.393 |
lesbians | +0.365 |
LS | +0.342 |
clean | +0.339 |
Neg logit contributions | |
haps | -0.479 |
Medic | -0.449 |
ombo | -0.434 |
ggle | -0.428 |
Kappa | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
retard | +0.648 |
strip | +0.562 |
lesbians | +0.528 |
LS | +0.496 |
clean | +0.485 |
Neg logit contributions | |
haps | -0.664 |
Medic | -0.617 |
ombo | -0.597 |
ggle | -0.596 |
Kappa | -0.560 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
retard | +0.729 |
strip | +0.633 |
lesbians | +0.599 |
rebellious | +0.555 |
clean | +0.555 |
Neg logit contributions | |
haps | -0.656 |
Medic | -0.627 |
ggle | -0.583 |
ombo | -0.579 |
Kappa | -0.553 |
Token | Posted |
Token ID | 14231 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
retard | +0.150 |
strip | +0.131 |
lesbians | +0.122 |
rebellious | +0.113 |
LS | +0.113 |
Neg logit contributions | |
haps | -0.144 |
Medic | -0.133 |
ombo | -0.130 |
ggle | -0.128 |
rals | -0.119 |
Token | on |
Token ID | 319 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
haps | +4.508 |
Medic | +4.351 |
ombo | +4.132 |
ggle | +4.105 |
Kappa | +3.857 |
Neg logit contributions | |
retard | -4.779 |
strip | -4.044 |
lesbians | -3.787 |
clean | -3.629 |
rebellious | -3.602 |
Token | // |
Token ID | 3373 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
retard | +0.256 |
strip | +0.221 |
lesbians | +0.206 |
clean | +0.193 |
rebellious | +0.192 |
Neg logit contributions | |
haps | -0.249 |
Medic | -0.240 |
ombo | -0.228 |
ggle | -0.226 |
Kappa | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
retard | +0.538 |
strip | +0.468 |
lesbians | +0.436 |
rebellious | +0.406 |
LS | +0.403 |
Neg logit contributions | |
haps | -0.515 |
Medic | -0.488 |
ombo | -0.467 |
ggle | -0.463 |
Kappa | -0.433 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
retard | +1.293 |
strip | +1.148 |
lesbians | +1.081 |
rebellious | +1.013 |
LS | +1.010 |
Neg logit contributions | |
haps | -0.993 |
Medic | -0.922 |
ombo | -0.889 |
ggle | -0.881 |
Kappa | -0.814 |
Token | According |
Token ID | 4821 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
retard | +1.148 |
strip | +1.003 |
lesbians | +0.930 |
rebellious | +0.862 |
LS | +0.862 |
Neg logit contributions | |
haps | -1.129 |
Medic | -1.051 |
ombo | -1.025 |
ggle | -1.014 |
Kappa | -0.939 |
Token | free |
Token ID | 1479 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
retard | +0.723 |
strip | +0.641 |
lesbians | +0.601 |
LS | +0.561 |
rebellious | +0.557 |
Neg logit contributions | |
haps | -0.624 |
Medic | -0.578 |
ombo | -0.564 |
ggle | -0.557 |
rals | -0.516 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
retard | +0.607 |
strip | +0.545 |
lesbians | +0.513 |
LS | +0.484 |
rebellious | +0.480 |
Neg logit contributions | |
haps | -0.468 |
Medic | -0.420 |
ombo | -0.411 |
ggle | -0.408 |
�� | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
haps | +1.496 |
Medic | +1.415 |
ggle | +1.369 |
ombo | +1.367 |
Kappa | +1.279 |
Neg logit contributions | |
retard | -1.571 |
strip | -1.338 |
lesbians | -1.286 |
rebellious | -1.194 |
LS | -1.188 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
haps | +0.233 |
Medic | +0.224 |
ombo | +0.215 |
ggle | +0.214 |
Kappa | +0.202 |
Neg logit contributions | |
retard | -0.182 |
strip | -0.154 |
lesbians | -0.143 |
rebellious | -0.130 |
clean | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
retard | +0.187 |
strip | +0.166 |
lesbians | +0.157 |
rebellious | +0.149 |
LS | +0.146 |
Neg logit contributions | |
haps | -0.134 |
Medic | -0.125 |
ombo | -0.119 |
ggle | -0.118 |
Kappa | -0.110 |
Token | Update |
Token ID | 10260 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
haps | +0.259 |
Medic | +0.241 |
ombo | +0.230 |
ggle | +0.229 |
mia | +0.213 |
Neg logit contributions | |
retard | -0.273 |
strip | -0.237 |
lesbians | -0.218 |
rebellious | -0.206 |
LS | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
haps | +3.952 |
Medic | +3.856 |
ombo | +3.548 |
ggle | +3.456 |
Kappa | +3.402 |
Neg logit contributions | |
retard | -4.964 |
strip | -4.207 |
lesbians | -4.087 |
clean | -3.812 |
rebellious | -3.809 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
haps | +1.529 |
Medic | +1.474 |
ombo | +1.379 |
ggle | +1.356 |
Kappa | +1.307 |
Neg logit contributions | |
retard | -1.625 |
strip | -1.398 |
lesbians | -1.320 |
clean | -1.235 |
rebellious | -1.226 |
Token | : |
Token ID | 25 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
haps | +0.738 |
Medic | +0.687 |
ombo | +0.650 |
ggle | +0.649 |
Kappa | +0.599 |
Neg logit contributions | |
retard | -1.042 |
strip | -0.931 |
lesbians | -0.874 |
clean | -0.822 |
LS | -0.817 |
Token | 01 |
Token ID | 486 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Medic | +1.553 |
haps | +1.506 |
ggle | +1.378 |
Kappa | +1.374 |
ombo | +1.345 |
Neg logit contributions | |
retard | -1.781 |
strip | -1.511 |
lesbians | -1.421 |
rebellious | -1.366 |
surg | -1.316 |
Token | p |
Token ID | 279 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
retard | +0.537 |
strip | +0.482 |
lesbians | +0.451 |
clean | +0.420 |
rebellious | +0.418 |
Neg logit contributions | |
haps | -0.408 |
Medic | -0.386 |
ombo | -0.361 |
ggle | -0.359 |
Kappa | -0.337 |
Token | 45 |
Token ID | 2231 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
retard | +0.034 |
strip | +0.029 |
lesbians | +0.027 |
rebellious | +0.026 |
clean | +0.025 |
Neg logit contributions | |
haps | -0.034 |
Medic | -0.033 |
ggle | -0.031 |
ombo | -0.031 |
Kappa | -0.030 |
Token | 366 |
Token ID | 44856 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
haps | +0.352 |
Medic | +0.335 |
ombo | +0.316 |
ggle | +0.315 |
Kappa | +0.299 |
Neg logit contributions | |
retard | -0.382 |
strip | -0.333 |
lesbians | -0.314 |
rebellious | -0.294 |
clean | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
haps | +1.428 |
Medic | +1.341 |
ombo | +1.299 |
ggle | +1.259 |
rals | +1.204 |
Neg logit contributions | |
retard | -1.421 |
strip | -1.218 |
lesbians | -1.159 |
rebellious | -1.067 |
clean | -1.066 |
Token |
|
Token ID | 198 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
haps | +0.283 |
Medic | +0.268 |
ombo | +0.258 |
ggle | +0.256 |
rals | +0.240 |
Neg logit contributions | |
retard | -0.255 |
strip | -0.220 |
lesbians | -0.205 |
rebellious | -0.187 |
LS | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
haps | +0.216 |
Medic | +0.202 |
ombo | +0.193 |
ggle | +0.192 |
Kappa | +0.177 |
Neg logit contributions | |
retard | -0.303 |
strip | -0.269 |
lesbians | -0.255 |
rebellious | -0.241 |
LS | -0.237 |
Token | Topics |
Token ID | 25902 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
haps | +0.137 |
Medic | +0.123 |
ombo | +0.120 |
ggle | +0.119 |
rals | +0.109 |
Neg logit contributions | |
retard | -0.212 |
strip | -0.190 |
lesbians | -0.179 |
LS | -0.170 |
rebellious | -0.168 |
Token | : |
Token ID | 25 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
haps | +3.351 |
Medic | +3.189 |
ombo | +3.008 |
ggle | +2.949 |
Difficulty | +2.749 |
Neg logit contributions | |
retard | -5.433 |
strip | -4.754 |
lesbians | -4.562 |
rebellious | -4.334 |
LS | -4.288 |
Token | community |
Token ID | 2055 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
retard | +2.128 |
strip | +1.876 |
lesbians | +1.749 |
LS | +1.643 |
clean | +1.634 |
Neg logit contributions | |
haps | -1.959 |
Medic | -1.838 |
ombo | -1.786 |
ggle | -1.765 |
rals | -1.649 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
retard | +1.581 |
strip | +1.380 |
lesbians | +1.286 |
LS | +1.190 |
rebellious | +1.184 |
Neg logit contributions | |
haps | -1.666 |
Medic | -1.557 |
ombo | -1.532 |
ggle | -1.500 |
rals | -1.407 |
Token | and |
Token ID | 392 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
retard | +0.535 |
strip | +0.474 |
lesbians | +0.449 |
rebellious | +0.418 |
LS | +0.415 |
Neg logit contributions | |
haps | -0.439 |
ombo | -0.416 |
Medic | -0.411 |
ggle | -0.389 |
rals | -0.377 |
Token | - |
Token ID | 12 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
retard | +1.498 |
strip | +1.304 |
lesbians | +1.213 |
LS | +1.116 |
rebellious | +1.110 |
Neg logit contributions | |
haps | -1.652 |
Medic | -1.544 |
ombo | -1.510 |
ggle | -1.494 |
rals | -1.399 |
Token | into |
Token ID | 656 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
haps | +0.298 |
Medic | +0.285 |
ombo | +0.277 |
ggle | +0.276 |
Kappa | +0.261 |
Neg logit contributions | |
retard | -0.225 |
strip | -0.192 |
lesbians | -0.181 |
LS | -0.165 |
rebellious | -0.162 |
Token | them |
Token ID | 606 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
haps | +0.617 |
Medic | +0.587 |
ombo | +0.568 |
ggle | +0.558 |
Kappa | +0.524 |
Neg logit contributions | |
retard | -0.664 |
strip | -0.576 |
lesbians | -0.556 |
LS | -0.509 |
clean | -0.506 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
haps | +0.300 |
Medic | +0.283 |
ombo | +0.276 |
ggle | +0.271 |
Kappa | +0.254 |
Neg logit contributions | |
retard | -0.309 |
strip | -0.268 |
lesbians | -0.256 |
LS | -0.239 |
rebellious | -0.236 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
haps | +0.367 |
Medic | +0.348 |
ggle | +0.325 |
ombo | +0.323 |
Kappa | +0.303 |
Neg logit contributions | |
retard | -0.554 |
strip | -0.490 |
lesbians | -0.466 |
rebellious | -0.449 |
LS | -0.433 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
haps | +0.665 |
Medic | +0.622 |
ggle | +0.590 |
ombo | +0.590 |
Kappa | +0.547 |
Neg logit contributions | |
retard | -0.955 |
strip | -0.846 |
lesbians | -0.803 |
rebellious | -0.764 |
LS | -0.748 |
Token | Topics |
Token ID | 25902 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
haps | +0.637 |
Medic | +0.589 |
ombo | +0.577 |
ggle | +0.571 |
rals | +0.528 |
Neg logit contributions | |
retard | -0.682 |
strip | -0.596 |
lesbians | -0.558 |
rebellious | -0.521 |
LS | -0.521 |
Token | : |
Token ID | 25 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
haps | +3.320 |
Medic | +3.186 |
ombo | +2.977 |
ggle | +2.935 |
Difficulty | +2.742 |
Neg logit contributions | |
retard | -5.405 |
strip | -4.734 |
lesbians | -4.547 |
rebellious | -4.319 |
LS | -4.261 |
Token | marine |
Token ID | 16050 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
retard | +2.300 |
strip | +2.032 |
lesbians | +1.913 |
LS | +1.791 |
clean | +1.773 |
Neg logit contributions | |
haps | -2.065 |
Medic | -1.949 |
ombo | -1.893 |
ggle | -1.863 |
rals | -1.733 |
Token | - |
Token ID | 12 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
retard | +0.587 |
strip | +0.511 |
lesbians | +0.475 |
LS | +0.437 |
rebellious | +0.435 |
Neg logit contributions | |
haps | -0.651 |
Medic | -0.609 |
ombo | -0.596 |
ggle | -0.589 |
rals | -0.552 |
Token | biology |
Token ID | 43592 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
retard | +2.099 |
strip | +1.860 |
lesbians | +1.753 |
LS | +1.634 |
rebellious | +1.625 |
Neg logit contributions | |
haps | -1.758 |
Medic | -1.625 |
ombo | -1.589 |
ggle | -1.565 |
rals | -1.453 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
retard | +0.375 |
strip | +0.327 |
lesbians | +0.307 |
rebellious | +0.289 |
LS | +0.282 |
Neg logit contributions | |
haps | -0.339 |
Medic | -0.317 |
ombo | -0.313 |
ggle | -0.301 |
Kappa | -0.289 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
haps | +0.721 |
Medic | +0.684 |
ombo | +0.661 |
ggle | +0.660 |
Kappa | +0.627 |
Neg logit contributions | |
retard | -0.738 |
strip | -0.644 |
lesbians | -0.613 |
clean | -0.561 |
rebellious | -0.559 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
haps | +0.931 |
Medic | +0.912 |
ggle | +0.831 |
ombo | +0.825 |
Kappa | +0.793 |
Neg logit contributions | |
retard | -1.510 |
strip | -1.338 |
lesbians | -1.287 |
rebellious | -1.208 |
clean | -1.192 |
Token | � |
Token ID | 251 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
haps | +0.835 |
Medic | +0.762 |
ggle | +0.753 |
ombo | +0.739 |
�� | +0.718 |
Neg logit contributions | |
retard | -1.047 |
strip | -0.924 |
lesbians | -0.876 |
clean | -0.816 |
LS | -0.809 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
haps | +0.758 |
Medic | +0.725 |
ggle | +0.688 |
ombo | +0.686 |
Kappa | +0.649 |
Neg logit contributions | |
retard | -0.924 |
strip | -0.809 |
lesbians | -0.769 |
rebellious | -0.713 |
clean | -0.707 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
haps | +0.570 |
Medic | +0.536 |
ombo | +0.507 |
ggle | +0.507 |
Kappa | +0.471 |
Neg logit contributions | |
retard | -0.818 |
strip | -0.724 |
lesbians | -0.688 |
rebellious | -0.654 |
LS | -0.638 |
Token | https |
Token ID | 5450 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
haps | +0.144 |
Medic | +0.134 |
ombo | +0.131 |
ggle | +0.130 |
rals | +0.121 |
Neg logit contributions | |
retard | -0.151 |
strip | -0.133 |
lesbians | -0.124 |
rebellious | -0.114 |
LS | -0.113 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
haps | +3.086 |
Medic | +2.823 |
ggle | +2.733 |
ombo | +2.628 |
Kappa | +2.515 |
Neg logit contributions | |
retard | -5.667 |
strip | -5.090 |
lesbians | -4.829 |
rebellious | -4.721 |
surg | -4.558 |
Token | twitter |
Token ID | 6956 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
haps | +0.561 |
ombo | +0.506 |
Medic | +0.505 |
ggle | +0.497 |
rals | +0.462 |
Neg logit contributions | |
retard | -0.727 |
strip | -0.649 |
lesbians | -0.611 |
rebellious | -0.570 |
LS | -0.564 |
Token | . |
Token ID | 13 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
retard | +0.686 |
strip | +0.594 |
lesbians | +0.553 |
rebellious | +0.511 |
LS | +0.506 |
Neg logit contributions | |
haps | -0.756 |
Medic | -0.711 |
ombo | -0.693 |
ggle | -0.686 |
Kappa | -0.646 |
Token | com |
Token ID | 785 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
retard | +2.109 |
strip | +1.882 |
lesbians | +1.758 |
clean | +1.661 |
LS | +1.654 |
Neg logit contributions | |
haps | -1.824 |
Medic | -1.671 |
ombo | -1.644 |
ggle | -1.609 |
�� | -1.534 |
Token | / |
Token ID | 14 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
retard | +1.745 |
strip | +1.471 |
lesbians | +1.339 |
LS | +1.233 |
clean | +1.221 |
Neg logit contributions | |
haps | -2.691 |
Medic | -2.517 |
ombo | -2.484 |
ggle | -2.439 |
rals | -2.336 |
Token | di |
Token ID | 10989 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
haps | +2.631 |
ggle | +2.332 |
Medic | +2.322 |
ombo | +2.278 |
rals | +2.195 |
Neg logit contributions | |
retard | -2.826 |
strip | -2.530 |
lesbians | -2.405 |
rebellious | -2.206 |
drag | -2.168 |
Token | |
Token ID | 3907 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
haps | +0.483 |
Medic | +0.440 |
ombo | +0.434 |
ggle | +0.432 |
Kappa | +0.398 |
Neg logit contributions | |
retard | -0.625 |
strip | -0.551 |
lesbians | -0.533 |
rebellious | -0.492 |
LS | -0.492 |
Token | um |
Token ID | 388 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
haps | +2.618 |
ggle | +2.297 |
Medic | +2.289 |
ombo | +2.270 |
rals | +2.105 |
Neg logit contributions | |
retard | -4.012 |
strip | -3.607 |
lesbians | -3.461 |
rebellious | -3.240 |
LS | -3.206 |
Token | and |
Token ID | 290 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
retard | +1.100 |
strip | +0.956 |
lesbians | +0.908 |
rebellious | +0.836 |
LS | +0.833 |
Neg logit contributions | |
haps | -1.092 |
Medic | -1.022 |
ombo | -0.995 |
ggle | -0.986 |
Kappa | -0.925 |
Token | al |
Token ID | 435 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
haps | +0.310 |
Medic | +0.294 |
ombo | +0.284 |
ggle | +0.281 |
Kappa | +0.269 |
Neg logit contributions | |
retard | -0.296 |
strip | -0.254 |
lesbians | -0.244 |
clean | -0.227 |
rebellious | -0.222 |
Token | |
Token ID | 3907 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
retard | +0.450 |
strip | +0.398 |
lesbians | +0.380 |
rebellious | +0.354 |
LS | +0.352 |
Neg logit contributions | |
haps | -0.356 |
Medic | -0.328 |
ombo | -0.322 |
ggle | -0.316 |
Kappa | -0.292 |
Token | l |
Token ID | 75 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
haps | +4.368 |
ombo | +3.843 |
ggle | +3.787 |
Medic | +3.713 |
mia | +3.521 |
Neg logit contributions | |
retard | -4.505 |
strip | -4.092 |
lesbians | -3.805 |
rebellious | -3.512 |
LS | -3.466 |
Token | owed |
Token ID | 6972 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
haps | +1.409 |
ombo | +1.261 |
Medic | +1.252 |
ggle | +1.214 |
ounced | +1.129 |
Neg logit contributions | |
retard | -1.848 |
strip | -1.668 |
lesbians | -1.591 |
rebellious | -1.476 |
LS | -1.471 |
Token | only |
Token ID | 691 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
haps | +1.110 |
Medic | +1.035 |
ggle | +1.008 |
ombo | +1.005 |
Kappa | +0.945 |
Neg logit contributions | |
retard | -1.180 |
strip | -1.025 |
lesbians | -0.994 |
clean | -0.915 |
rebellious | -0.908 |
Token | a |
Token ID | 257 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
haps | +0.935 |
Medic | +0.877 |
ombo | +0.851 |
ggle | +0.840 |
Kappa | +0.803 |
Neg logit contributions | |
retard | -1.066 |
strip | -0.931 |
lesbians | -0.902 |
clean | -0.836 |
rebellious | -0.827 |
Token | brief |
Token ID | 4506 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
retard | +0.453 |
strip | +0.389 |
lesbians | +0.377 |
clean | +0.342 |
LS | +0.341 |
Neg logit contributions | |
haps | -0.475 |
Medic | -0.449 |
ombo | -0.434 |
ggle | -0.431 |
Kappa | -0.411 |
Token | ing |
Token ID | 278 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
haps | +4.001 |
Medic | +3.579 |
ggle | +3.573 |
ombo | +3.527 |
rals | +3.327 |
Neg logit contributions | |
retard | -3.347 |
strip | -2.940 |
lesbians | -2.757 |
rebellious | -2.509 |
LS | -2.446 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
haps | +0.563 |
Medic | +0.526 |
ggle | +0.508 |
ombo | +0.506 |
Kappa | +0.481 |
Neg logit contributions | |
retard | -0.520 |
strip | -0.445 |
lesbians | -0.417 |
LS | -0.390 |
clean | -0.388 |
Token | Carter |
Token ID | 10831 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
haps | +1.005 |
Medic | +0.970 |
ombo | +0.917 |
ggle | +0.903 |
Kappa | +0.873 |
Neg logit contributions | |
retard | -1.151 |
strip | -1.002 |
lesbians | -0.959 |
rebellious | -0.886 |
clean | -0.879 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
retard | +0.555 |
strip | +0.485 |
lesbians | +0.456 |
LS | +0.426 |
clean | +0.418 |
Neg logit contributions | |
haps | -0.546 |
Medic | -0.510 |
ombo | -0.493 |
ggle | -0.490 |
Kappa | -0.461 |
Token | Al |
Token ID | 978 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
haps | +0.117 |
Medic | +0.113 |
ombo | +0.105 |
ggle | +0.105 |
Kappa | +0.101 |
Neg logit contributions | |
retard | -0.127 |
strip | -0.110 |
lesbians | -0.105 |
rebellious | -0.097 |
clean | -0.096 |
Token | |
Token ID | 3907 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
haps | +0.155 |
Medic | +0.143 |
ombo | +0.141 |
ggle | +0.136 |
Kappa | +0.127 |
Neg logit contributions | |
retard | -0.207 |
strip | -0.184 |
lesbians | -0.175 |
rebellious | -0.163 |
LS | -0.163 |
Token | though |
Token ID | 2016 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
haps | +4.144 |
ombo | +3.641 |
ggle | +3.635 |
Medic | +3.555 |
lus | +3.327 |
Neg logit contributions | |
retard | -4.570 |
strip | -4.165 |
lesbians | -3.933 |
rebellious | -3.618 |
LS | -3.586 |
Token | he |
Token ID | 339 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
haps | +0.850 |
Medic | +0.778 |
ombo | +0.766 |
ggle | +0.754 |
Kappa | +0.713 |
Neg logit contributions | |
retard | -0.783 |
strip | -0.673 |
lesbians | -0.639 |
clean | -0.598 |
LS | -0.588 |
Token | left |
Token ID | 1364 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
haps | +1.290 |
Medic | +1.173 |
ggle | +1.157 |
ombo | +1.138 |
Kappa | +1.065 |
Neg logit contributions | |
retard | -1.542 |
strip | -1.355 |
lesbians | -1.305 |
clean | -1.223 |
LS | -1.222 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
retard | +0.488 |
strip | +0.416 |
lesbians | +0.392 |
clean | +0.361 |
LS | +0.353 |
Neg logit contributions | |
haps | -0.597 |
Medic | -0.567 |
ombo | -0.552 |
ggle | -0.547 |
Kappa | -0.519 |
Token | White |
Token ID | 2635 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
retard | +0.217 |
strip | +0.185 |
lesbians | +0.177 |
clean | +0.166 |
susp | +0.159 |
Neg logit contributions | |
haps | -0.244 |
Medic | -0.237 |
ombo | -0.226 |
ggle | -0.225 |
Kappa | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
retard | +0.063 |
strip | +0.055 |
lesbians | +0.051 |
LS | +0.048 |
clean | +0.047 |
Neg logit contributions | |
haps | -0.066 |
Medic | -0.062 |
ombo | -0.061 |
ggle | -0.060 |
Kappa | -0.056 |
Token | start |
Token ID | 923 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
retard | +1.436 |
strip | +1.246 |
lesbians | +1.178 |
LS | +1.085 |
clean | +1.075 |
Neg logit contributions | |
haps | -1.543 |
Medic | -1.453 |
ombo | -1.414 |
ggle | -1.409 |
rals | -1.307 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
retard | +1.071 |
strip | +0.934 |
lesbians | +0.877 |
LS | +0.816 |
rebellious | +0.804 |
Neg logit contributions | |
haps | -1.103 |
Medic | -1.028 |
ombo | -0.997 |
ggle | -0.997 |
Kappa | -0.931 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
retard | +1.159 |
strip | +1.013 |
lesbians | +0.952 |
rebellious | +0.886 |
clean | +0.883 |
Neg logit contributions | |
haps | -1.014 |
Medic | -0.966 |
ombo | -0.905 |
ggle | -0.904 |
Kappa | -0.859 |
Token | Abstract |
Token ID | 23839 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
retard | +0.274 |
strip | +0.240 |
lesbians | +0.223 |
rebellious | +0.207 |
LS | +0.207 |
Neg logit contributions | |
haps | -0.261 |
Medic | -0.241 |
ombo | -0.237 |
ggle | -0.234 |
rals | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
haps | +0.899 |
Medic | +0.869 |
ombo | +0.816 |
ggle | +0.802 |
Kappa | +0.764 |
Neg logit contributions | |
retard | -1.132 |
strip | -1.000 |
lesbians | -0.936 |
rebellious | -0.882 |
clean | -0.877 |
Token |
|
Token ID | 198 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
haps | +2.881 |
Medic | +2.835 |
ggle | +2.540 |
ombo | +2.498 |
Kappa | +2.406 |
Neg logit contributions | |
retard | -5.400 |
strip | -4.793 |
lesbians | -4.601 |
rebellious | -4.508 |
surg | -4.316 |
Token | Background |
Token ID | 21756 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
haps | +3.519 |
Medic | +3.305 |
ombo | +3.225 |
ggle | +3.131 |
mia | +2.905 |
Neg logit contributions | |
retard | -4.118 |
strip | -3.640 |
lesbians | -3.349 |
rebellious | -3.168 |
LS | -3.112 |
Token | Depression |
Token ID | 22483 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Medic | +3.711 |
haps | +3.599 |
ombo | +3.317 |
ggle | +3.255 |
Difficulty | +3.238 |
Neg logit contributions | |
retard | -4.078 |
strip | -3.502 |
lesbians | -3.249 |
rebellious | -3.135 |
clean | -3.084 |
Token | presents |
Token ID | 10969 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
haps | +0.469 |
Medic | +0.439 |
ombo | +0.415 |
ggle | +0.410 |
Kappa | +0.390 |
Neg logit contributions | |
retard | -0.515 |
strip | -0.463 |
lesbians | -0.434 |
clean | -0.412 |
rebellious | -0.405 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
haps | +1.688 |
Medic | +1.609 |
ombo | +1.531 |
ggle | +1.491 |
Kappa | +1.431 |
Neg logit contributions | |
retard | -1.689 |
strip | -1.484 |
lesbians | -1.385 |
clean | -1.335 |
rebellious | -1.283 |
Token | intro |
Token ID | 18951 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
retard | +0.129 |
strip | +0.113 |
lesbians | +0.106 |
clean | +0.100 |
LS | +0.098 |
Neg logit contributions | |
haps | -0.115 |
Medic | -0.107 |
ombo | -0.103 |
ggle | -0.102 |
Kappa | -0.095 |
Token | vert |
Token ID | 1851 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
retard | +0.080 |
strip | +0.067 |
lesbians | +0.061 |
LS | +0.054 |
clean | +0.054 |
Neg logit contributions | |
haps | -0.131 |
Medic | -0.124 |
ggle | -0.120 |
ombo | -0.120 |
Kappa | -0.114 |
Token | online |
Token ID | 2691 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
haps | +1.214 |
Medic | +1.139 |
ombo | +1.095 |
ggle | +1.095 |
Kappa | +1.025 |
Neg logit contributions | |
retard | -1.329 |
strip | -1.166 |
lesbians | -1.097 |
clean | -1.034 |
LS | -1.027 |
Token | ? |
Token ID | 30 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
haps | +0.077 |
Medic | +0.072 |
ombo | +0.070 |
ggle | +0.069 |
Kappa | +0.065 |
Neg logit contributions | |
retard | -0.090 |
strip | -0.079 |
lesbians | -0.075 |
clean | -0.070 |
LS | -0.070 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
haps | +0.411 |
Medic | +0.396 |
ombo | +0.372 |
ggle | +0.371 |
Kappa | +0.355 |
Neg logit contributions | |
retard | -0.393 |
strip | -0.338 |
lesbians | -0.315 |
rebellious | -0.292 |
clean | -0.292 |
Token | Update |
Token ID | 10260 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
retard | +0.117 |
strip | +0.102 |
lesbians | +0.095 |
rebellious | +0.088 |
LS | +0.088 |
Neg logit contributions | |
haps | -0.111 |
Medic | -0.103 |
ombo | -0.101 |
ggle | -0.099 |
rals | -0.092 |
Token | : |
Token ID | 25 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
haps | +3.631 |
Medic | +3.543 |
ombo | +3.279 |
ggle | +3.221 |
Kappa | +3.122 |
Neg logit contributions | |
retard | -4.571 |
strip | -3.890 |
lesbians | -3.742 |
rebellious | -3.506 |
clean | -3.488 |
Token | You |
Token ID | 921 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
haps | +2.908 |
Medic | +2.878 |
ombo | +2.609 |
ggle | +2.597 |
Kappa | +2.550 |
Neg logit contributions | |
retard | -3.080 |
strip | -2.610 |
lesbians | -2.454 |
clean | -2.306 |
rebellious | -2.305 |
Token | can |
Token ID | 460 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
haps | +1.101 |
Medic | +1.024 |
ggle | +0.975 |
ombo | +0.957 |
Kappa | +0.895 |
Neg logit contributions | |
retard | -1.404 |
strip | -1.233 |
lesbians | -1.185 |
clean | -1.115 |
rebellious | -1.114 |
Token | find |
Token ID | 1064 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
haps | +0.244 |
Medic | +0.227 |
ggle | +0.220 |
ombo | +0.218 |
Kappa | +0.203 |
Neg logit contributions | |
retard | -0.258 |
strip | -0.223 |
lesbians | -0.215 |
rebellious | -0.201 |
clean | -0.197 |
Token | a |
Token ID | 257 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
haps | +0.463 |
Medic | +0.440 |
ombo | +0.418 |
ggle | +0.413 |
Kappa | +0.394 |
Neg logit contributions | |
retard | -0.441 |
strip | -0.380 |
lesbians | -0.356 |
clean | -0.330 |
rebellious | -0.329 |
Token | ( |
Token ID | 357 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
retard | +0.831 |
strip | +0.726 |
lesbians | +0.672 |
LS | +0.622 |
rebellious | +0.616 |
Neg logit contributions | |
haps | -0.910 |
Medic | -0.848 |
ombo | -0.830 |
ggle | -0.821 |
rals | -0.770 |
Token | direction |
Token ID | 37295 |
Feature activation | -2.83e-04 |
Pos logit contributions | |
retard | +0.800 |
strip | +0.699 |
lesbians | +0.659 |
rebellious | +0.605 |
LS | +0.605 |
Neg logit contributions | |
haps | -0.790 |
Medic | -0.729 |
ombo | -0.725 |
ggle | -0.714 |
rals | -0.664 |
Token | versus |
Token ID | 9051 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
retard | +0.002 |
strip | +0.001 |
lesbians | +0.001 |
clean | +0.001 |
LS | +0.001 |
Neg logit contributions | |
haps | -0.001 |
Medic | -0.001 |
ombo | -0.001 |
ggle | -0.001 |
Kappa | -0.001 |
Token | cue |
Token ID | 28381 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
retard | +1.530 |
strip | +1.337 |
lesbians | +1.257 |
LS | +1.159 |
clean | +1.156 |
Neg logit contributions | |
haps | -1.532 |
Medic | -1.431 |
ombo | -1.400 |
ggle | -1.384 |
Kappa | -1.292 |
Token | ). |
Token ID | 737 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
haps | +1.280 |
Medic | +1.190 |
ombo | +1.186 |
ggle | +1.172 |
Kappa | +1.102 |
Neg logit contributions | |
retard | -1.214 |
strip | -1.037 |
lesbians | -0.986 |
clean | -0.916 |
rebellious | -0.911 |
Token | https |
Token ID | 3740 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
haps | +0.382 |
Medic | +0.366 |
ombo | +0.350 |
ggle | +0.346 |
Kappa | +0.329 |
Neg logit contributions | |
retard | -0.418 |
strip | -0.364 |
lesbians | -0.346 |
clean | -0.320 |
rebellious | -0.320 |
Token | :// |
Token ID | 1378 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
haps | +2.851 |
Medic | +2.639 |
ggle | +2.542 |
ombo | +2.469 |
mia | +2.300 |
Neg logit contributions | |
retard | -5.224 |
strip | -4.677 |
lesbians | -4.496 |
rebellious | -4.405 |
surg | -4.230 |
Token | doi |
Token ID | 34023 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
haps | +0.331 |
Medic | +0.307 |
ombo | +0.303 |
ggle | +0.301 |
rals | +0.284 |
Neg logit contributions | |
retard | -0.265 |
strip | -0.228 |
lesbians | -0.210 |
rebellious | -0.195 |
LS | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
retard | +0.952 |
strip | +0.821 |
lesbians | +0.766 |
rebellious | +0.716 |
LS | +0.701 |
Neg logit contributions | |
haps | -0.999 |
Medic | -0.939 |
ombo | -0.914 |
ggle | -0.907 |
Kappa | -0.855 |
Token | org |
Token ID | 2398 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
retard | +0.606 |
strip | +0.539 |
lesbians | +0.509 |
LS | +0.475 |
rebellious | +0.474 |
Neg logit contributions | |
haps | -0.477 |
Medic | -0.439 |
ombo | -0.429 |
ggle | -0.423 |
Kappa | -0.389 |
Token | / |
Token ID | 14 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
retard | +0.507 |
strip | +0.433 |
lesbians | +0.403 |
rebellious | +0.375 |
LS | +0.365 |
Neg logit contributions | |
haps | -0.582 |
Medic | -0.552 |
ombo | -0.535 |
ggle | -0.533 |
Kappa | -0.502 |
Token | ales |
Token ID | 2040 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
retard | +0.273 |
strip | +0.239 |
lesbians | +0.224 |
rebellious | +0.206 |
LS | +0.206 |
Neg logit contributions | |
haps | -0.289 |
Medic | -0.266 |
ombo | -0.263 |
ggle | -0.258 |
rals | -0.242 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
retard | +1.387 |
strip | +1.204 |
lesbians | +1.124 |
LS | +1.032 |
rebellious | +1.028 |
Neg logit contributions | |
haps | -1.595 |
Medic | -1.488 |
ombo | -1.462 |
ggle | -1.446 |
Kappa | -1.355 |
Token | com |
Token ID | 401 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
haps | +1.166 |
Medic | +1.055 |
ombo | +1.045 |
ggle | +1.018 |
Kappa | +0.941 |
Neg logit contributions | |
retard | -1.597 |
strip | -1.420 |
lesbians | -1.382 |
clean | -1.295 |
rebellious | -1.283 |
Token | |
Token ID | 3907 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
retard | +0.486 |
strip | +0.432 |
lesbians | +0.415 |
rebellious | +0.387 |
LS | +0.383 |
Neg logit contributions | |
haps | -0.374 |
Medic | -0.340 |
ombo | -0.333 |
ggle | -0.330 |
rals | -0.307 |
Token | par |
Token ID | 1845 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
haps | +4.795 |
Medic | +4.253 |
ombo | +4.226 |
ggle | +4.167 |
mia | +3.895 |
Neg logit contributions | |
retard | -4.934 |
strip | -4.429 |
lesbians | -4.168 |
rebellious | -3.819 |
LS | -3.753 |
Token | |
Token ID | 3907 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
haps | +0.458 |
Medic | +0.416 |
ombo | +0.406 |
ggle | +0.403 |
rals | +0.374 |
Neg logit contributions | |
retard | -0.583 |
strip | -0.522 |
lesbians | -0.499 |
rebellious | -0.461 |
clean | -0.458 |
Token | is |
Token ID | 271 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
haps | +3.378 |
Medic | +2.883 |
ombo | +2.855 |
ggle | +2.812 |
rals | +2.649 |
Neg logit contributions | |
retard | -4.780 |
strip | -4.437 |
lesbians | -4.213 |
rebellious | -3.973 |
LS | -3.875 |
Token | |
Token ID | 3907 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
retard | +0.583 |
strip | +0.517 |
lesbians | +0.490 |
LS | +0.457 |
clean | +0.457 |
Neg logit contributions | |
haps | -0.478 |
Medic | -0.440 |
ombo | -0.428 |
ggle | -0.421 |
rals | -0.394 |
Token | on |
Token ID | 261 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
haps | +3.562 |
Medic | +3.192 |
ombo | +3.152 |
ggle | +3.111 |
rals | +2.929 |
Neg logit contributions | |
retard | -3.936 |
strip | -3.543 |
lesbians | -3.351 |
rebellious | -3.151 |
clean | -3.050 |
Token | to |
Token ID | 284 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
haps | +0.068 |
Medic | +0.063 |
ombo | +0.061 |
ggle | +0.060 |
Kappa | +0.057 |
Neg logit contributions | |
retard | -0.068 |
strip | -0.060 |
lesbians | -0.057 |
clean | -0.052 |
rebellious | -0.052 |
Token | this |
Token ID | 428 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
haps | +0.248 |
Medic | +0.234 |
ombo | +0.226 |
ggle | +0.226 |
Kappa | +0.213 |
Neg logit contributions | |
retard | -0.238 |
strip | -0.207 |
lesbians | -0.197 |
clean | -0.182 |
susp | -0.179 |
Token | Carter |
Token ID | 10831 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
haps | +0.144 |
Medic | +0.139 |
ombo | +0.132 |
ggle | +0.131 |
Kappa | +0.124 |
Neg logit contributions | |
retard | -0.163 |
strip | -0.143 |
lesbians | -0.136 |
clean | -0.125 |
rebellious | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
retard | +0.100 |
strip | +0.087 |
lesbians | +0.083 |
LS | +0.076 |
clean | +0.076 |
Neg logit contributions | |
haps | -0.096 |
Medic | -0.090 |
ombo | -0.087 |
ggle | -0.086 |
Kappa | -0.081 |
Token | � |
Token ID | 447 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
haps | +0.202 |
Medic | +0.191 |
ombo | +0.183 |
ggle | +0.181 |
Kappa | +0.173 |
Neg logit contributions | |
retard | -0.185 |
strip | -0.161 |
lesbians | -0.154 |
rebellious | -0.139 |
clean | -0.139 |
Token | � |
Token ID | 251 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
haps | +0.910 |
Medic | +0.820 |
ggle | +0.800 |
ombo | +0.800 |
�� | +0.764 |
Neg logit contributions | |
retard | -1.271 |
strip | -1.137 |
lesbians | -1.076 |
clean | -1.006 |
LS | -1.004 |
Token | ex |
Token ID | 409 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
haps | +1.134 |
Medic | +1.070 |
ombo | +1.014 |
ggle | +1.011 |
Kappa | +0.971 |
Neg logit contributions | |
retard | -1.055 |
strip | -0.910 |
lesbians | -0.872 |
clean | -0.807 |
rebellious | -0.794 |
Token | |
Token ID | 3907 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
haps | +0.686 |
Medic | +0.621 |
ombo | +0.601 |
ggle | +0.597 |
Kappa | +0.548 |
Neg logit contributions | |
retard | -0.876 |
strip | -0.777 |
lesbians | -0.739 |
rebellious | -0.693 |
LS | -0.686 |
Token | claimed |
Token ID | 12795 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
haps | +4.168 |
Medic | +3.644 |
ggle | +3.581 |
ombo | +3.530 |
ounced | +3.384 |
Neg logit contributions | |
retard | -4.026 |
strip | -3.653 |
lesbians | -3.404 |
rebellious | -3.169 |
LS | -3.147 |
Token | Marco |
Token ID | 16556 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
haps | +0.438 |
Medic | +0.415 |
ombo | +0.395 |
ggle | +0.394 |
Kappa | +0.377 |
Neg logit contributions | |
retard | -0.418 |
strip | -0.362 |
lesbians | -0.346 |
clean | -0.322 |
rebellious | -0.314 |
Token | Ru |
Token ID | 11667 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
haps | +1.066 |
Medic | +1.036 |
ombo | +0.974 |
ggle | +0.966 |
Kappa | +0.913 |
Neg logit contributions | |
retard | -1.386 |
strip | -1.219 |
lesbians | -1.178 |
clean | -1.102 |
rebellious | -1.100 |
Token | |
Token ID | 3907 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
haps | +0.673 |
ombo | +0.615 |
Medic | +0.614 |
ggle | +0.596 |
rals | +0.545 |
Neg logit contributions | |
retard | -0.919 |
strip | -0.832 |
lesbians | -0.793 |
rebellious | -0.746 |
LS | -0.733 |
Token | b |
Token ID | 65 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
haps | +2.643 |
Medic | +2.355 |
ggle | +2.340 |
ombo | +2.338 |
rals | +2.155 |
Neg logit contributions | |
retard | -3.092 |
strip | -2.755 |
lesbians | -2.636 |
rebellious | -2.439 |
LS | -2.421 |
Token | of |
Token ID | 286 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
haps | +0.690 |
Medic | +0.647 |
ggle | +0.628 |
ombo | +0.627 |
Kappa | +0.590 |
Neg logit contributions | |
retard | -0.628 |
strip | -0.540 |
lesbians | -0.509 |
LS | -0.467 |
clean | -0.465 |
Token | ! |
Token ID | 0 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
haps | +1.136 |
Medic | +1.072 |
ombo | +1.045 |
ggle | +1.032 |
Kappa | +0.979 |
Neg logit contributions | |
retard | -1.143 |
strip | -0.990 |
lesbians | -0.935 |
clean | -0.865 |
rebellious | -0.862 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
retard | +0.050 |
strip | +0.043 |
lesbians | +0.041 |
rebellious | +0.039 |
clean | +0.038 |
Neg logit contributions | |
haps | -0.042 |
Medic | -0.041 |
ombo | -0.038 |
ggle | -0.038 |
Kappa | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
haps | +0.565 |
Medic | +0.536 |
ggle | +0.498 |
ombo | +0.496 |
Kappa | +0.466 |
Neg logit contributions | |
retard | -0.896 |
strip | -0.787 |
lesbians | -0.754 |
rebellious | -0.724 |
surg | -0.700 |
Token | V |
Token ID | 53 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
haps | +0.668 |
Medic | +0.618 |
ombo | +0.604 |
ggle | +0.597 |
rals | +0.552 |
Neg logit contributions | |
retard | -0.715 |
strip | -0.625 |
lesbians | -0.589 |
rebellious | -0.543 |
LS | -0.537 |
Token | end |
Token ID | 437 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
haps | +1.562 |
Medic | +1.441 |
ombo | +1.437 |
ggle | +1.423 |
endi | +1.328 |
Neg logit contributions | |
retard | -1.467 |
strip | -1.305 |
lesbians | -1.227 |
LS | -1.124 |
rebellious | -1.101 |
Token | read |
Token ID | 961 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
haps | +2.698 |
Medic | +2.362 |
ombo | +2.348 |
ggle | +2.237 |
�� | +2.038 |
Neg logit contributions | |
retard | -5.332 |
strip | -4.856 |
lesbians | -4.701 |
LS | -4.363 |
rebellious | -4.318 |
Token | Re |
Token ID | 797 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
haps | +0.758 |
Medic | +0.723 |
ombo | +0.693 |
ggle | +0.672 |
Kappa | +0.639 |
Neg logit contributions | |
retard | -0.897 |
strip | -0.781 |
lesbians | -0.743 |
rebellious | -0.691 |
clean | -0.687 |
Token | origin |
Token ID | 47103 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
haps | +0.609 |
Medic | +0.553 |
ombo | +0.546 |
ggle | +0.542 |
Kappa | +0.497 |
Neg logit contributions | |
retard | -0.645 |
strip | -0.567 |
lesbians | -0.531 |
rebellious | -0.490 |
LS | -0.482 |
Token | is |
Token ID | 318 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
haps | +0.420 |
Medic | +0.393 |
ombo | +0.379 |
ggle | +0.371 |
Kappa | +0.350 |
Neg logit contributions | |
retard | -0.494 |
strip | -0.432 |
lesbians | -0.415 |
rebellious | -0.384 |
clean | -0.378 |
Token | a |
Token ID | 257 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
haps | +0.073 |
Medic | +0.069 |
ombo | +0.066 |
ggle | +0.065 |
Kappa | +0.062 |
Neg logit contributions | |
retard | -0.075 |
strip | -0.064 |
lesbians | -0.061 |
clean | -0.057 |
rebellious | -0.056 |
Token | � |
Token ID | 564 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
retard | +1.009 |
strip | +0.879 |
lesbians | +0.834 |
LS | +0.778 |
clean | +0.776 |
Neg logit contributions | |
haps | -0.946 |
Medic | -0.881 |
ombo | -0.854 |
ggle | -0.846 |
Kappa | -0.797 |
Token | � |
Token ID | 250 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
haps | +0.583 |
Medic | +0.528 |
ggle | +0.516 |
ombo | +0.514 |
�� | +0.505 |
Neg logit contributions | |
retard | -0.634 |
strip | -0.553 |
lesbians | -0.524 |
LS | -0.486 |
clean | -0.480 |
Token | was |
Token ID | 9776 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
retard | +0.043 |
strip | +0.038 |
lesbians | +0.036 |
LS | +0.034 |
rebellious | +0.033 |
Neg logit contributions | |
haps | -0.036 |
Medic | -0.032 |
ombo | -0.032 |
ggle | -0.031 |
rals | -0.029 |
Token | po |
Token ID | 745 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
haps | +0.472 |
Medic | +0.435 |
ombo | +0.426 |
ggle | +0.423 |
Kappa | +0.398 |
Neg logit contributions | |
retard | -0.448 |
strip | -0.382 |
lesbians | -0.370 |
LS | -0.339 |
clean | -0.336 |
Token | in |
Token ID | 259 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
haps | +0.521 |
Medic | +0.471 |
ombo | +0.465 |
ggle | +0.456 |
rals | +0.419 |
Neg logit contributions | |
retard | -0.663 |
strip | -0.594 |
lesbians | -0.566 |
rebellious | -0.525 |
LS | -0.520 |
Token | |
Token ID | 3907 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
retard | +0.707 |
strip | +0.626 |
lesbians | +0.601 |
rebellious | +0.558 |
LS | +0.556 |
Neg logit contributions | |
haps | -0.551 |
Medic | -0.506 |
ggle | -0.488 |
ombo | -0.487 |
rals | -0.449 |
Token | ted |
Token ID | 1513 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
haps | +3.704 |
ggle | +3.215 |
Medic | +3.155 |
ombo | +3.151 |
ounced | +3.017 |
Neg logit contributions | |
retard | -4.280 |
strip | -3.877 |
lesbians | -3.664 |
LS | -3.435 |
rebellious | -3.398 |
Token | ly |
Token ID | 306 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
retard | +0.760 |
strip | +0.656 |
lesbians | +0.622 |
LS | +0.570 |
clean | +0.565 |
Neg logit contributions | |
haps | -0.880 |
Medic | -0.822 |
ombo | -0.805 |
ggle | -0.798 |
Kappa | -0.754 |
Token | denied |
Token ID | 6699 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
haps | +0.699 |
Medic | +0.655 |
ombo | +0.638 |
ggle | +0.631 |
Kappa | +0.601 |
Neg logit contributions | |
retard | -0.656 |
strip | -0.559 |
lesbians | -0.541 |
clean | -0.499 |
LS | -0.497 |
Token | a |
Token ID | 257 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
haps | +1.704 |
Medic | +1.630 |
ggle | +1.549 |
ombo | +1.539 |
Kappa | +1.491 |
Neg logit contributions | |
retard | -1.698 |
strip | -1.455 |
lesbians | -1.405 |
clean | -1.297 |
rebellious | -1.291 |
Token | spot |
Token ID | 4136 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
haps | +0.261 |
Medic | +0.251 |
ombo | +0.240 |
ggle | +0.237 |
Kappa | +0.229 |
Neg logit contributions | |
retard | -0.254 |
strip | -0.217 |
lesbians | -0.212 |
clean | -0.193 |
rebellious | -0.191 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
retard | +0.361 |
strip | +0.317 |
lesbians | +0.302 |
rebellious | +0.280 |
clean | +0.277 |
Neg logit contributions | |
haps | -0.304 |
Medic | -0.287 |
ombo | -0.275 |
ggle | -0.272 |
Kappa | -0.259 |
Token | this |
Token ID | 428 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
retard | +1.816 |
strip | +1.544 |
lesbians | +1.425 |
LS | +1.294 |
rebellious | +1.293 |
Neg logit contributions | |
haps | -2.461 |
Medic | -2.321 |
ombo | -2.271 |
ggle | -2.254 |
Kappa | -2.122 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
retard | +1.827 |
strip | +1.582 |
lesbians | +1.459 |
LS | +1.339 |
rebellious | +1.327 |
Neg logit contributions | |
haps | -2.201 |
Medic | -2.060 |
ombo | -2.023 |
ggle | -2.000 |
rals | -1.880 |
Token | on |
Token ID | 319 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
retard | +0.533 |
strip | +0.442 |
lesbians | +0.415 |
rebellious | +0.379 |
clean | +0.371 |
Neg logit contributions | |
haps | -0.763 |
Medic | -0.728 |
ombo | -0.704 |
ggle | -0.701 |
Kappa | -0.670 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
haps | +0.792 |
Medic | +0.750 |
ggle | +0.710 |
ombo | +0.705 |
Kappa | +0.664 |
Neg logit contributions | |
retard | -1.093 |
strip | -0.939 |
lesbians | -0.903 |
rebellious | -0.855 |
clean | -0.839 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
retard | +1.231 |
strip | +1.081 |
lesbians | +1.007 |
LS | +0.934 |
clean | +0.927 |
Neg logit contributions | |
haps | -1.237 |
Medic | -1.151 |
ombo | -1.128 |
ggle | -1.114 |
rals | -1.040 |
Token | this |
Token ID | 428 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
retard | +3.920 |
strip | +3.385 |
lesbians | +3.020 |
LS | +2.719 |
drag | +2.663 |
Neg logit contributions | |
haps | -6.473 |
Medic | -6.074 |
ombo | -6.016 |
ggle | -5.927 |
�� | -5.756 |
Token | comment |
Token ID | 2912 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
retard | +2.058 |
strip | +1.782 |
lesbians | +1.638 |
LS | +1.503 |
rebellious | +1.488 |
Neg logit contributions | |
haps | -2.507 |
Medic | -2.344 |
ombo | -2.305 |
ggle | -2.279 |
�� | -2.148 |
Token | on |
Token ID | 319 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
retard | +0.338 |
strip | +0.280 |
lesbians | +0.263 |
rebellious | +0.241 |
clean | +0.236 |
Neg logit contributions | |
haps | -0.482 |
Medic | -0.459 |
ombo | -0.444 |
ggle | -0.443 |
Kappa | -0.422 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
haps | +0.801 |
Medic | +0.780 |
ombo | +0.737 |
ggle | +0.729 |
Kappa | +0.704 |
Neg logit contributions | |
retard | -0.792 |
strip | -0.686 |
lesbians | -0.650 |
rebellious | -0.601 |
clean | -0.596 |
Token |
|
Token ID | 198 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
retard | +0.263 |
strip | +0.234 |
lesbians | +0.220 |
LS | +0.205 |
clean | +0.204 |
Neg logit contributions | |
haps | -0.219 |
Medic | -0.202 |
ombo | -0.197 |
ggle | -0.194 |
rals | -0.180 |
Token | Poe |
Token ID | 34815 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
retard | +1.385 |
strip | +1.205 |
lesbians | +1.121 |
LS | +1.028 |
rebellious | +1.026 |
Neg logit contributions | |
haps | -1.505 |
Medic | -1.417 |
ombo | -1.373 |
ggle | -1.363 |
Kappa | -1.277 |
Token | hler |
Token ID | 49737 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
retard | +0.533 |
strip | +0.455 |
lesbians | +0.434 |
rebellious | +0.395 |
clean | +0.395 |
Neg logit contributions | |
haps | -0.570 |
Medic | -0.539 |
ombo | -0.512 |
ggle | -0.508 |
Kappa | -0.483 |
Token | Parks |
Token ID | 20604 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
retard | +2.049 |
strip | +1.786 |
lesbians | +1.668 |
rebellious | +1.540 |
LS | +1.536 |
Neg logit contributions | |
haps | -2.053 |
Medic | -1.932 |
ombo | -1.867 |
ggle | -1.850 |
Kappa | -1.736 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
retard | +1.525 |
strip | +1.292 |
lesbians | +1.227 |
LS | +1.125 |
rebellious | +1.119 |
Neg logit contributions | |
haps | -1.607 |
Medic | -1.529 |
ombo | -1.500 |
ggle | -1.440 |
Kappa | -1.388 |
Token | Recreation |
Token ID | 34285 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
retard | +0.623 |
strip | +0.526 |
lesbians | +0.519 |
rebellious | +0.479 |
LS | +0.477 |
Neg logit contributions | |
haps | -0.403 |
Medic | -0.387 |
ombo | -0.340 |
ggle | -0.332 |
Kappa | -0.326 |
Token | NBC |
Token ID | 9716 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
retard | +2.570 |
strip | +2.257 |
lesbians | +2.108 |
LS | +1.954 |
rebellious | +1.944 |
Neg logit contributions | |
haps | -2.507 |
Medic | -2.334 |
ombo | -2.280 |
ggle | -2.253 |
rals | -2.099 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
retard | +4.935 |
strip | +4.381 |
lesbians | +4.091 |
LS | +3.832 |
clean | +3.747 |
Neg logit contributions | |
haps | -4.979 |
ombo | -4.578 |
Medic | -4.546 |
ggle | -4.480 |
�� | -4.162 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
haps | +0.145 |
Medic | +0.135 |
ombo | +0.129 |
ggle | +0.129 |
Kappa | +0.119 |
Neg logit contributions | |
retard | -0.197 |
strip | -0.175 |
lesbians | -0.166 |
rebellious | -0.156 |
LS | -0.154 |
Token | Out |
Token ID | 7975 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
retard | +0.513 |
strip | +0.443 |
lesbians | +0.409 |
LS | +0.374 |
rebellious | +0.372 |
Neg logit contributions | |
haps | -0.612 |
Medic | -0.574 |
ombo | -0.562 |
ggle | -0.556 |
�� | -0.521 |
Token | standing |
Token ID | 5646 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
retard | +0.225 |
strip | +0.200 |
lesbians | +0.188 |
rebellious | +0.177 |
LS | +0.177 |
Neg logit contributions | |
haps | -0.169 |
Medic | -0.154 |
ombo | -0.150 |
ggle | -0.147 |
rals | -0.138 |
Token | New |
Token ID | 968 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
retard | +0.296 |
strip | +0.261 |
lesbians | +0.248 |
clean | +0.228 |
LS | +0.228 |
Neg logit contributions | |
haps | -0.251 |
Medic | -0.236 |
ombo | -0.226 |
ggle | -0.222 |
Kappa | -0.208 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
retard | +0.403 |
strip | +0.354 |
lesbians | +0.338 |
rebellious | +0.314 |
clean | +0.310 |
Neg logit contributions | |
haps | -0.336 |
Medic | -0.318 |
ombo | -0.304 |
ggle | -0.301 |
Kappa | -0.287 |
Token | this |
Token ID | 428 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
retard | +1.626 |
strip | +1.380 |
lesbians | +1.280 |
rebellious | +1.169 |
LS | +1.164 |
Neg logit contributions | |
haps | -2.139 |
Medic | -2.021 |
ombo | -1.974 |
ggle | -1.962 |
Kappa | -1.847 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
retard | +1.908 |
strip | +1.651 |
lesbians | +1.525 |
LS | +1.400 |
rebellious | +1.388 |
Neg logit contributions | |
haps | -2.291 |
Medic | -2.144 |
ombo | -2.104 |
ggle | -2.081 |
rals | -1.955 |
Token | on |
Token ID | 319 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
retard | +0.560 |
strip | +0.463 |
lesbians | +0.437 |
rebellious | +0.401 |
clean | +0.390 |
Neg logit contributions | |
haps | -0.788 |
Medic | -0.753 |
ombo | -0.727 |
ggle | -0.724 |
Kappa | -0.693 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
haps | +0.847 |
Medic | +0.803 |
ggle | +0.760 |
ombo | +0.753 |
Kappa | +0.712 |
Neg logit contributions | |
retard | -1.201 |
strip | -1.029 |
lesbians | -0.993 |
rebellious | -0.943 |
clean | -0.921 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
retard | +1.154 |
strip | +1.012 |
lesbians | +0.945 |
LS | +0.876 |
rebellious | +0.871 |
Neg logit contributions | |
haps | -1.145 |
Medic | -1.066 |
ombo | -1.042 |
ggle | -1.030 |
rals | -0.960 |
Token | this |
Token ID | 428 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
retard | +3.659 |
strip | +3.153 |
lesbians | +2.828 |
LS | +2.547 |
drag | +2.488 |
Neg logit contributions | |
haps | -5.874 |
Medic | -5.511 |
ombo | -5.452 |
ggle | -5.374 |
�� | -5.193 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
retard | +2.001 |
strip | +1.733 |
lesbians | +1.594 |
LS | +1.463 |
rebellious | +1.448 |
Neg logit contributions | |
haps | -2.430 |
Medic | -2.273 |
ombo | -2.234 |
ggle | -2.209 |
�� | -2.081 |
Token | on |
Token ID | 319 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
retard | +0.228 |
strip | +0.188 |
lesbians | +0.178 |
rebellious | +0.163 |
clean | +0.159 |
Neg logit contributions | |
haps | -0.320 |
Medic | -0.305 |
ombo | -0.295 |
ggle | -0.294 |
Kappa | -0.281 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
haps | +0.922 |
Medic | +0.902 |
ombo | +0.849 |
ggle | +0.840 |
Kappa | +0.814 |
Neg logit contributions | |
retard | -0.931 |
strip | -0.806 |
lesbians | -0.765 |
rebellious | -0.709 |
clean | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
retard | +0.097 |
strip | +0.086 |
lesbians | +0.081 |
LS | +0.075 |
rebellious | +0.075 |
Neg logit contributions | |
haps | -0.080 |
Medic | -0.073 |
ombo | -0.072 |
ggle | -0.071 |
rals | -0.065 |
Token | fulfill |
Token ID | 14658 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
retard | +0.440 |
strip | +0.374 |
lesbians | +0.366 |
LS | +0.335 |
rebellious | +0.335 |
Neg logit contributions | |
haps | -0.515 |
Medic | -0.485 |
ggle | -0.472 |
ombo | -0.469 |
Kappa | -0.437 |
Token | that |
Token ID | 326 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
haps | +1.075 |
Medic | +1.020 |
ombo | +0.963 |
ggle | +0.930 |
Kappa | +0.898 |
Neg logit contributions | |
retard | -1.356 |
strip | -1.202 |
lesbians | -1.152 |
clean | -1.083 |
LS | -1.069 |
Token | in |
Token ID | 287 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
retard | +0.013 |
strip | +0.011 |
lesbians | +0.011 |
clean | +0.010 |
LS | +0.010 |
Neg logit contributions | |
haps | -0.010 |
Medic | -0.009 |
ombo | -0.009 |
ggle | -0.008 |
Kappa | -0.008 |
Token | oil |
Token ID | 3056 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
retard | +0.018 |
strip | +0.016 |
lesbians | +0.015 |
LS | +0.014 |
clean | +0.014 |
Neg logit contributions | |
haps | -0.018 |
Medic | -0.016 |
ombo | -0.016 |
ggle | -0.016 |
rals | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
retard | +0.461 |
strip | +0.392 |
lesbians | +0.375 |
LS | +0.345 |
rebellious | +0.341 |
Neg logit contributions | |
haps | -0.515 |
Medic | -0.479 |
ombo | -0.471 |
ggle | -0.464 |
rals | -0.436 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
retard | +1.009 |
strip | +0.873 |
lesbians | +0.830 |
LS | +0.765 |
rebellious | +0.757 |
Neg logit contributions | |
haps | -1.019 |
Medic | -0.939 |
ombo | -0.928 |
ggle | -0.905 |
rals | -0.856 |
Token | gas |
Token ID | 3623 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
retard | +4.655 |
strip | +4.079 |
lesbians | +3.790 |
LS | +3.511 |
rebellious | +3.485 |
Neg logit contributions | |
haps | -4.838 |
Medic | -4.501 |
ombo | -4.419 |
ggle | -4.362 |
rals | -4.083 |
Token | - |
Token ID | 12 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
retard | +1.468 |
strip | +1.268 |
lesbians | +1.210 |
LS | +1.120 |
rebellious | +1.114 |
Neg logit contributions | |
haps | -1.445 |
Medic | -1.351 |
ombo | -1.326 |
ggle | -1.303 |
rals | -1.219 |
Token | related |
Token ID | 5363 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
retard | +1.260 |
strip | +1.097 |
lesbians | +1.045 |
LS | +0.970 |
rebellious | +0.955 |
Neg logit contributions | |
haps | -1.212 |
Medic | -1.109 |
ombo | -1.096 |
ggle | -1.064 |
rals | -1.008 |
Token | matters |
Token ID | 6067 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
retard | +0.092 |
strip | +0.080 |
lesbians | +0.076 |
LS | +0.071 |
clean | +0.071 |
Neg logit contributions | |
haps | -0.075 |
Medic | -0.072 |
ombo | -0.069 |
ggle | -0.068 |
rals | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
retard | +0.622 |
strip | +0.538 |
lesbians | +0.507 |
LS | +0.472 |
clean | +0.469 |
Neg logit contributions | |
haps | -0.638 |
Medic | -0.601 |
ombo | -0.581 |
ggle | -0.576 |
rals | -0.541 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
retard | +0.205 |
strip | +0.180 |
lesbians | +0.171 |
rebellious | +0.158 |
clean | +0.158 |
Neg logit contributions | |
haps | -0.173 |
Medic | -0.163 |
ombo | -0.156 |
ggle | -0.155 |
Kappa | -0.148 |
Token | this |
Token ID | 428 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
retard | +1.598 |
strip | +1.357 |
lesbians | +1.259 |
rebellious | +1.154 |
LS | +1.147 |
Neg logit contributions | |
haps | -2.073 |
Medic | -1.960 |
ombo | -1.913 |
ggle | -1.904 |
Kappa | -1.790 |
Token | comment |
Token ID | 2912 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
retard | +2.072 |
strip | +1.794 |
lesbians | +1.651 |
LS | +1.516 |
rebellious | +1.499 |
Neg logit contributions | |
haps | -2.523 |
Medic | -2.359 |
ombo | -2.319 |
ggle | -2.292 |
�� | -2.159 |
Token | on |
Token ID | 319 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
retard | +0.806 |
strip | +0.668 |
lesbians | +0.627 |
rebellious | +0.573 |
clean | +0.559 |
Neg logit contributions | |
haps | -1.156 |
Medic | -1.102 |
ombo | -1.068 |
ggle | -1.063 |
Kappa | -1.015 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
haps | +0.857 |
Medic | +0.811 |
ggle | +0.767 |
ombo | +0.764 |
Kappa | +0.721 |
Neg logit contributions | |
retard | -1.213 |
strip | -1.039 |
lesbians | -1.005 |
rebellious | -0.949 |
clean | -0.930 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
retard | +1.228 |
strip | +1.078 |
lesbians | +1.004 |
LS | +0.931 |
clean | +0.924 |
Neg logit contributions | |
haps | -1.236 |
Medic | -1.149 |
ombo | -1.127 |
ggle | -1.112 |
rals | -1.039 |
Token | this |
Token ID | 428 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
retard | +3.626 |
strip | +3.114 |
lesbians | +2.811 |
LS | +2.536 |
clean | +2.471 |
Neg logit contributions | |
haps | -5.689 |
Medic | -5.346 |
ombo | -5.279 |
ggle | -5.206 |
�� | -5.008 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
retard | +2.148 |
strip | +1.860 |
lesbians | +1.707 |
LS | +1.567 |
rebellious | +1.549 |
Neg logit contributions | |
haps | -2.630 |
Medic | -2.459 |
ombo | -2.419 |
ggle | -2.391 |
�� | -2.256 |
Token | on |
Token ID | 319 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
retard | +0.461 |
strip | +0.382 |
lesbians | +0.360 |
rebellious | +0.329 |
clean | +0.321 |
Neg logit contributions | |
haps | -0.659 |
Medic | -0.628 |
ombo | -0.608 |
ggle | -0.606 |
Kappa | -0.578 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
haps | +0.893 |
Medic | +0.875 |
ombo | +0.820 |
ggle | +0.812 |
Kappa | +0.789 |
Neg logit contributions | |
retard | -0.915 |
strip | -0.792 |
lesbians | -0.753 |
rebellious | -0.699 |
clean | -0.692 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
retard | +0.412 |
strip | +0.366 |
lesbians | +0.344 |
LS | +0.321 |
rebellious | +0.319 |
Neg logit contributions | |
haps | -0.344 |
Medic | -0.317 |
ombo | -0.310 |
ggle | -0.306 |
rals | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
haps | +0.019 |
Medic | +0.017 |
ombo | +0.017 |
ggle | +0.017 |
rals | +0.015 |
Neg logit contributions | |
retard | -0.022 |
strip | -0.020 |
lesbians | -0.019 |
LS | -0.017 |
clean | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
retard | +0.898 |
strip | +0.797 |
lesbians | +0.751 |
rebellious | +0.702 |
LS | +0.702 |
Neg logit contributions | |
haps | -0.704 |
Medic | -0.652 |
ombo | -0.632 |
ggle | -0.625 |
Kappa | -0.577 |
Token | I |
Token ID | 40 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
retard | +1.473 |
strip | +1.280 |
lesbians | +1.192 |
rebellious | +1.101 |
LS | +1.091 |
Neg logit contributions | |
haps | -1.566 |
Medic | -1.457 |
ombo | -1.427 |
ggle | -1.406 |
Kappa | -1.314 |
Token | have |
Token ID | 423 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
haps | +1.491 |
Medic | +1.376 |
ggle | +1.347 |
ombo | +1.339 |
rals | +1.231 |
Neg logit contributions | |
retard | -1.669 |
strip | -1.433 |
lesbians | -1.374 |
rebellious | -1.288 |
clean | -1.271 |
Token | to |
Token ID | 284 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
haps | +0.221 |
Medic | +0.206 |
ombo | +0.201 |
ggle | +0.198 |
Kappa | +0.185 |
Neg logit contributions | |
retard | -0.237 |
strip | -0.207 |
lesbians | -0.195 |
clean | -0.182 |
rebellious | -0.180 |
Token | admit |
Token ID | 9159 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
retard | +0.081 |
strip | +0.069 |
lesbians | +0.067 |
LS | +0.061 |
rebellious | +0.061 |
Neg logit contributions | |
haps | -0.086 |
Medic | -0.079 |
ggle | -0.078 |
ombo | -0.076 |
Kappa | -0.071 |
Token | that |
Token ID | 326 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
retard | +3.689 |
strip | +3.155 |
lesbians | +2.894 |
LS | +2.639 |
rebellious | +2.603 |
Neg logit contributions | |
haps | -5.117 |
Medic | -4.831 |
ombo | -4.736 |
ggle | -4.682 |
rals | -4.436 |
Token | I |
Token ID | 314 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
retard | +0.996 |
strip | +0.868 |
lesbians | +0.811 |
clean | +0.748 |
rebellious | +0.748 |
Neg logit contributions | |
haps | -1.037 |
Medic | -0.963 |
ombo | -0.940 |
ggle | -0.927 |
Kappa | -0.872 |
Token | know |
Token ID | 760 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
haps | +0.064 |
Medic | +0.059 |
ggle | +0.058 |
ombo | +0.058 |
Kappa | +0.053 |
Neg logit contributions | |
retard | -0.075 |
strip | -0.065 |
lesbians | -0.062 |
clean | -0.058 |
rebellious | -0.058 |
Token | very |
Token ID | 845 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
retard | +0.166 |
strip | +0.143 |
lesbians | +0.133 |
clean | +0.123 |
rebellious | +0.123 |
Neg logit contributions | |
haps | -0.191 |
Medic | -0.178 |
ombo | -0.173 |
ggle | -0.172 |
Kappa | -0.163 |
Token | little |
Token ID | 1310 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
retard | +0.103 |
strip | +0.090 |
lesbians | +0.084 |
LS | +0.078 |
rebellious | +0.078 |
Neg logit contributions | |
haps | -0.100 |
Medic | -0.094 |
ggle | -0.090 |
ombo | -0.089 |
Kappa | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
retard | +0.163 |
strip | +0.142 |
lesbians | +0.134 |
rebellious | +0.123 |
clean | +0.122 |
Neg logit contributions | |
haps | -0.155 |
Medic | -0.149 |
ombo | -0.140 |
ggle | -0.139 |
Kappa | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
retard | +0.295 |
strip | +0.262 |
lesbians | +0.248 |
rebellious | +0.233 |
LS | +0.231 |
Neg logit contributions | |
haps | -0.218 |
Medic | -0.204 |
ombo | -0.195 |
ggle | -0.194 |
Kappa | -0.179 |
Token | What |
Token ID | 2061 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
retard | +0.277 |
strip | +0.243 |
lesbians | +0.228 |
LS | +0.209 |
rebellious | +0.209 |
Neg logit contributions | |
haps | -0.275 |
Medic | -0.254 |
ombo | -0.248 |
ggle | -0.246 |
rals | -0.229 |
Token | we |
Token ID | 356 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
haps | +0.417 |
Medic | +0.394 |
ombo | +0.375 |
ggle | +0.374 |
Kappa | +0.352 |
Neg logit contributions | |
retard | -0.427 |
strip | -0.374 |
lesbians | -0.353 |
LS | -0.326 |
clean | -0.326 |
Token | end |
Token ID | 886 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
retard | +0.160 |
strip | +0.139 |
lesbians | +0.132 |
LS | +0.124 |
clean | +0.123 |
Neg logit contributions | |
haps | -0.150 |
Medic | -0.140 |
ggle | -0.135 |
ombo | -0.134 |
Kappa | -0.125 |
Token | up |
Token ID | 510 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
retard | +0.115 |
strip | +0.094 |
lesbians | +0.087 |
LS | +0.078 |
clean | +0.077 |
Neg logit contributions | |
haps | -0.192 |
Medic | -0.181 |
ombo | -0.179 |
ggle | -0.177 |
rals | -0.168 |
Token | with |
Token ID | 351 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
retard | +4.049 |
strip | +3.566 |
lesbians | +3.292 |
rebellious | +2.987 |
LS | +2.986 |
Neg logit contributions | |
haps | -4.688 |
Medic | -4.372 |
ombo | -4.325 |
ggle | -4.243 |
rals | -4.021 |
Token | is |
Token ID | 318 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
retard | +0.795 |
strip | +0.698 |
lesbians | +0.655 |
LS | +0.608 |
rebellious | +0.603 |
Neg logit contributions | |
haps | -0.759 |
Medic | -0.709 |
ombo | -0.688 |
ggle | -0.679 |
rals | -0.635 |
Token | a |
Token ID | 257 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
haps | +0.793 |
Medic | +0.746 |
ombo | +0.718 |
ggle | +0.714 |
Kappa | +0.668 |
Neg logit contributions | |
retard | -0.806 |
strip | -0.708 |
lesbians | -0.668 |
LS | -0.620 |
clean | -0.614 |
Token | strange |
Token ID | 6283 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
haps | +0.356 |
Medic | +0.341 |
ggle | +0.326 |
ombo | +0.325 |
Kappa | +0.306 |
Neg logit contributions | |
retard | -0.354 |
strip | -0.305 |
lesbians | -0.296 |
LS | -0.271 |
clean | -0.269 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
haps | +0.680 |
Medic | +0.644 |
ombo | +0.618 |
ggle | +0.617 |
Kappa | +0.583 |
Neg logit contributions | |
retard | -0.672 |
strip | -0.577 |
lesbians | -0.562 |
clean | -0.514 |
LS | -0.514 |
Token | Guard |
Token ID | 4932 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
retard | +1.190 |
strip | +1.039 |
lesbians | +0.978 |
clean | +0.889 |
LS | +0.888 |
Neg logit contributions | |
haps | -1.259 |
Medic | -1.197 |
ombo | -1.157 |
ggle | -1.139 |
Kappa | -1.077 |
Token | { |
Token ID | 1391 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
haps | +1.611 |
Medic | +1.534 |
ombo | +1.456 |
ggle | +1.396 |
Kappa | +1.323 |
Neg logit contributions | |
retard | -2.585 |
strip | -2.320 |
lesbians | -2.243 |
LS | -2.073 |
rebellious | -2.066 |
Token | ... |
Token ID | 2644 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
retard | +2.297 |
strip | +2.010 |
lesbians | +1.884 |
LS | +1.736 |
clean | +1.727 |
Neg logit contributions | |
haps | -2.328 |
Medic | -2.179 |
ombo | -2.124 |
ggle | -2.098 |
Kappa | -1.962 |
Token | } |
Token ID | 1782 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
haps | +0.359 |
Medic | +0.343 |
ombo | +0.326 |
ggle | +0.320 |
Kappa | +0.306 |
Neg logit contributions | |
retard | -0.402 |
strip | -0.351 |
lesbians | -0.340 |
LS | -0.306 |
rebellious | -0.305 |
Token | pub |
Token ID | 2240 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
retard | +1.136 |
strip | +1.001 |
lesbians | +0.943 |
LS | +0.871 |
clean | +0.871 |
Neg logit contributions | |
haps | -1.032 |
Medic | -0.972 |
ombo | -0.939 |
ggle | -0.927 |
Kappa | -0.866 |
Token | fn |
Token ID | 24714 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
retard | +2.559 |
strip | +2.212 |
lesbians | +2.039 |
LS | +1.871 |
rebellious | +1.854 |
Neg logit contributions | |
haps | -3.157 |
Medic | -2.955 |
ombo | -2.902 |
ggle | -2.871 |
rals | -2.699 |
Token | pin |
Token ID | 6757 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
retard | +4.105 |
strip | +3.598 |
lesbians | +3.260 |
LS | +3.037 |
rebellious | +3.016 |
Neg logit contributions | |
haps | -4.702 |
Medic | -4.334 |
ombo | -4.297 |
ggle | -4.257 |
rals | -4.004 |
Token | () |
Token ID | 7499 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
retard | +0.337 |
strip | +0.293 |
lesbians | +0.279 |
LS | +0.257 |
rebellious | +0.254 |
Neg logit contributions | |
haps | -0.331 |
Medic | -0.311 |
ombo | -0.301 |
ggle | -0.296 |
Kappa | -0.278 |
Token | -> |
Token ID | 4613 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
haps | +0.521 |
Medic | +0.493 |
ggle | +0.468 |
ombo | +0.465 |
Kappa | +0.428 |
Neg logit contributions | |
retard | -0.744 |
strip | -0.659 |
lesbians | -0.629 |
clean | -0.588 |
LS | -0.587 |
Token | Guard |
Token ID | 4932 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
haps | +1.502 |
Medic | +1.470 |
ombo | +1.382 |
ggle | +1.358 |
Kappa | +1.309 |
Neg logit contributions | |
retard | -1.527 |
strip | -1.324 |
lesbians | -1.283 |
clean | -1.180 |
rebellious | -1.156 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
haps | +1.121 |
Medic | +1.066 |
ombo | +1.001 |
ggle | +0.971 |
Kappa | +0.924 |
Neg logit contributions | |
retard | -1.781 |
strip | -1.580 |
lesbians | -1.531 |
clean | -1.427 |
LS | -1.424 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
retard | +0.100 |
strip | +0.086 |
lesbians | +0.080 |
LS | +0.074 |
rebellious | +0.074 |
Neg logit contributions | |
haps | -0.122 |
Medic | -0.114 |
ombo | -0.113 |
ggle | -0.110 |
Kappa | -0.104 |
Token | Cu |
Token ID | 46141 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
retard | +1.092 |
strip | +0.978 |
lesbians | +0.924 |
rebellious | +0.874 |
LS | +0.867 |
Neg logit contributions | |
haps | -0.745 |
Medic | -0.688 |
ombo | -0.665 |
ggle | -0.655 |
Kappa | -0.602 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
retard | +0.256 |
strip | +0.219 |
lesbians | +0.209 |
rebellious | +0.195 |
LS | +0.193 |
Neg logit contributions | |
haps | -0.248 |
Medic | -0.230 |
ombo | -0.228 |
ggle | -0.223 |
Kappa | -0.209 |
Token | O |
Token ID | 46 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
retard | +1.662 |
strip | +1.454 |
lesbians | +1.361 |
rebellious | +1.263 |
LS | +1.250 |
Neg logit contributions | |
haps | -1.671 |
Medic | -1.580 |
ombo | -1.541 |
ggle | -1.513 |
Kappa | -1.429 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
retard | +0.394 |
strip | +0.334 |
lesbians | +0.313 |
rebellious | +0.291 |
LS | +0.283 |
Neg logit contributions | |
haps | -0.473 |
Medic | -0.448 |
ombo | -0.437 |
ggle | -0.435 |
Kappa | -0.410 |
Token | + |
Token ID | 10 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
retard | +0.622 |
strip | +0.552 |
lesbians | +0.523 |
LS | +0.485 |
rebellious | +0.485 |
Neg logit contributions | |
haps | -0.539 |
Medic | -0.502 |
ombo | -0.490 |
ggle | -0.481 |
Kappa | -0.448 |
Token | x |
Token ID | 87 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
retard | +3.004 |
strip | +2.487 |
lesbians | +2.210 |
clean | +1.975 |
LS | +1.959 |
Neg logit contributions | |
haps | -5.609 |
Medic | -5.329 |
ombo | -5.204 |
ggle | -5.173 |
�� | -4.943 |
Token | oscill |
Token ID | 24969 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
retard | +0.608 |
strip | +0.536 |
lesbians | +0.508 |
rebellious | +0.477 |
LS | +0.476 |
Neg logit contributions | |
haps | -0.544 |
Medic | -0.507 |
ombo | -0.497 |
ggle | -0.482 |
Kappa | -0.455 |
Token | ates |
Token ID | 689 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
retard | +1.315 |
strip | +1.190 |
lesbians | +1.135 |
LS | +1.074 |
rebellious | +1.073 |
Neg logit contributions | |
haps | -0.722 |
Medic | -0.648 |
ombo | -0.635 |
ggle | -0.621 |
rals | -0.559 |
Token | between |
Token ID | 1022 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
retard | +1.730 |
strip | +1.498 |
lesbians | +1.392 |
LS | +1.273 |
clean | +1.271 |
Neg logit contributions | |
haps | -2.109 |
Medic | -1.982 |
ombo | -1.942 |
ggle | -1.917 |
Kappa | -1.816 |
Token | two |
Token ID | 734 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
retard | +1.264 |
strip | +1.109 |
lesbians | +1.038 |
LS | +0.958 |
clean | +0.956 |
Neg logit contributions | |
haps | -1.264 |
Medic | -1.182 |
ombo | -1.154 |
ggle | -1.134 |
Kappa | -1.068 |
Token | � |
Token ID | 251 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
haps | +1.085 |
Medic | +0.969 |
ggle | +0.949 |
ombo | +0.933 |
�� | +0.887 |
Neg logit contributions | |
retard | -1.833 |
strip | -1.656 |
lesbians | -1.576 |
rebellious | -1.469 |
clean | -1.461 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
haps | +0.872 |
Medic | +0.846 |
ggle | +0.783 |
ombo | +0.773 |
Kappa | +0.747 |
Neg logit contributions | |
retard | -1.324 |
strip | -1.173 |
lesbians | -1.126 |
rebellious | -1.078 |
clean | -1.048 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
haps | +0.602 |
Medic | +0.568 |
ggle | +0.535 |
ombo | +0.535 |
Kappa | +0.498 |
Neg logit contributions | |
retard | -0.888 |
strip | -0.787 |
lesbians | -0.750 |
rebellious | -0.714 |
LS | -0.694 |
Token | ( |
Token ID | 7 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
haps | +0.081 |
Medic | +0.075 |
ombo | +0.073 |
ggle | +0.072 |
�� | +0.067 |
Neg logit contributions | |
retard | -0.098 |
strip | -0.087 |
lesbians | -0.082 |
rebellious | -0.076 |
LS | -0.076 |
Token | Fed |
Token ID | 42268 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
haps | +0.650 |
Medic | +0.609 |
ombo | +0.588 |
ggle | +0.580 |
rals | +0.544 |
Neg logit contributions | |
retard | -0.678 |
strip | -0.588 |
lesbians | -0.550 |
rebellious | -0.510 |
LS | -0.508 |
Token | up |
Token ID | 510 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
retard | +0.504 |
strip | +0.421 |
lesbians | +0.394 |
rebellious | +0.362 |
LS | +0.362 |
Neg logit contributions | |
haps | -0.642 |
Medic | -0.610 |
ombo | -0.593 |
ggle | -0.583 |
rals | -0.554 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
retard | +3.876 |
strip | +3.371 |
lesbians | +3.104 |
rebellious | +2.833 |
LS | +2.826 |
Neg logit contributions | |
haps | -4.702 |
Medic | -4.380 |
ombo | -4.338 |
ggle | -4.260 |
rals | -4.016 |
Token | hungry |
Token ID | 14720 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
retard | +0.974 |
strip | +0.840 |
lesbians | +0.786 |
LS | +0.725 |
clean | +0.725 |
Neg logit contributions | |
haps | -1.054 |
Medic | -1.000 |
ombo | -0.956 |
ggle | -0.951 |
Kappa | -0.899 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
retard | +1.545 |
strip | +1.360 |
lesbians | +1.277 |
LS | +1.198 |
clean | +1.194 |
Neg logit contributions | |
haps | -1.322 |
Medic | -1.237 |
ombo | -1.194 |
ggle | -1.179 |
Kappa | -1.102 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
retard | +0.700 |
strip | +0.596 |
lesbians | +0.561 |
LS | +0.522 |
clean | +0.522 |
Neg logit contributions | |
haps | -0.780 |
Medic | -0.737 |
ggle | -0.713 |
ombo | -0.707 |
Kappa | -0.671 |
Token | in |
Token ID | 287 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
retard | +0.878 |
strip | +0.750 |
lesbians | +0.704 |
clean | +0.657 |
LS | +0.655 |
Neg logit contributions | |
haps | -0.970 |
Medic | -0.915 |
ggle | -0.889 |
ombo | -0.880 |
Kappa | -0.834 |
Token | null |
Token ID | 9242 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
retard | +0.202 |
strip | +0.175 |
lesbians | +0.169 |
LS | +0.152 |
susp | +0.149 |
Neg logit contributions | |
haps | -0.206 |
Medic | -0.198 |
ombo | -0.190 |
ggle | -0.185 |
Kappa | -0.177 |
Token | atomic |
Token ID | 17226 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
haps | +0.617 |
Medic | +0.572 |
ombo | +0.556 |
ggle | +0.529 |
Kappa | +0.501 |
Neg logit contributions | |
retard | -0.905 |
strip | -0.810 |
lesbians | -0.784 |
rebellious | -0.715 |
LS | -0.715 |
Token | pointer |
Token ID | 17562 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
retard | +0.636 |
strip | +0.552 |
lesbians | +0.528 |
rebellious | +0.479 |
LS | +0.477 |
Neg logit contributions | |
haps | -0.643 |
Medic | -0.614 |
ombo | -0.597 |
ggle | -0.580 |
Kappa | -0.557 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
retard | +0.050 |
strip | +0.043 |
lesbians | +0.042 |
rebellious | +0.038 |
clean | +0.038 |
Neg logit contributions | |
haps | -0.049 |
Medic | -0.047 |
ombo | -0.045 |
ggle | -0.044 |
Kappa | -0.043 |
Token | pub |
Token ID | 2240 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
retard | +0.088 |
strip | +0.076 |
lesbians | +0.073 |
rebellious | +0.066 |
LS | +0.066 |
Neg logit contributions | |
haps | -0.092 |
Medic | -0.088 |
ombo | -0.083 |
ggle | -0.082 |
Kappa | -0.079 |
Token | fn |
Token ID | 24714 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
retard | +2.136 |
strip | +1.838 |
lesbians | +1.705 |
LS | +1.560 |
rebellious | +1.551 |
Neg logit contributions | |
haps | -2.610 |
Medic | -2.455 |
ombo | -2.399 |
ggle | -2.372 |
Kappa | -2.231 |
Token | null |
Token ID | 9242 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
retard | +3.509 |
strip | +3.020 |
lesbians | +2.722 |
LS | +2.485 |
clean | +2.458 |
Neg logit contributions | |
haps | -5.016 |
Medic | -4.683 |
ombo | -4.625 |
ggle | -4.601 |
rals | -4.339 |
Token | () |
Token ID | 7499 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
haps | +1.418 |
Medic | +1.327 |
ombo | +1.297 |
ggle | +1.259 |
Kappa | +1.199 |
Neg logit contributions | |
retard | -1.514 |
strip | -1.322 |
lesbians | -1.260 |
LS | -1.155 |
rebellious | -1.150 |
Token | -> |
Token ID | 4613 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
haps | +0.325 |
Medic | +0.304 |
ombo | +0.290 |
ggle | +0.290 |
Kappa | +0.267 |
Neg logit contributions | |
retard | -0.465 |
strip | -0.411 |
lesbians | -0.392 |
LS | -0.366 |
clean | -0.366 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
haps | +0.931 |
Medic | +0.903 |
ombo | +0.845 |
ggle | +0.818 |
Kappa | +0.790 |
Neg logit contributions | |
retard | -1.268 |
strip | -1.121 |
lesbians | -1.080 |
clean | -0.997 |
rebellious | -0.994 |
Token | < |
Token ID | 1279 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
haps | +0.438 |
Medic | +0.405 |
ombo | +0.387 |
ggle | +0.365 |
Kappa | +0.340 |
Neg logit contributions | |
retard | -0.919 |
strip | -0.832 |
lesbians | -0.796 |
rebellious | -0.753 |
clean | -0.748 |
Token | < |
Token ID | 1279 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
haps | +0.799 |
Medic | +0.741 |
ombo | +0.713 |
ggle | +0.685 |
Kappa | +0.633 |
Neg logit contributions | |
retard | -1.292 |
strip | -1.160 |
lesbians | -1.102 |
rebellious | -1.036 |
LS | -1.034 |
Token | T |
Token ID | 309 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
haps | +1.158 |
Medic | +1.133 |
ombo | +1.054 |
ggle | +1.038 |
Kappa | +0.990 |
Neg logit contributions | |
retard | -1.461 |
strip | -1.285 |
lesbians | -1.232 |
clean | -1.147 |
susp | -1.131 |
Token | > |
Token ID | 1875 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
retard | +0.515 |
strip | +0.445 |
lesbians | +0.417 |
rebellious | +0.381 |
clean | +0.380 |
Neg logit contributions | |
haps | -0.575 |
Medic | -0.542 |
ombo | -0.526 |
ggle | -0.520 |
Kappa | -0.489 |
Token | { |
Token ID | 1391 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
haps | +0.377 |
Medic | +0.356 |
ombo | +0.343 |
ggle | +0.336 |
Kappa | +0.314 |
Neg logit contributions | |
retard | -0.449 |
strip | -0.397 |
lesbians | -0.373 |
clean | -0.348 |
LS | -0.346 |
Token | pub |
Token ID | 2240 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
retard | +0.807 |
strip | +0.703 |
lesbians | +0.660 |
LS | +0.608 |
rebellious | +0.604 |
Neg logit contributions | |
haps | -0.838 |
Medic | -0.786 |
ombo | -0.765 |
ggle | -0.757 |
Kappa | -0.708 |
Token | fn |
Token ID | 24714 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
retard | +1.978 |
strip | +1.702 |
lesbians | +1.578 |
LS | +1.442 |
rebellious | +1.435 |
Neg logit contributions | |
haps | -2.434 |
Medic | -2.292 |
ombo | -2.237 |
ggle | -2.214 |
Kappa | -2.084 |
Token | new |
Token ID | 649 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
retard | +4.037 |
strip | +3.551 |
lesbians | +3.247 |
LS | +3.008 |
rebellious | +2.977 |
Neg logit contributions | |
haps | -4.467 |
Medic | -4.131 |
ombo | -4.080 |
ggle | -4.054 |
rals | -3.789 |
Token | ( |
Token ID | 357 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
haps | +2.052 |
Medic | +1.955 |
ombo | +1.884 |
ggle | +1.823 |
Kappa | +1.735 |
Neg logit contributions | |
retard | -2.412 |
strip | -2.110 |
lesbians | -2.024 |
LS | -1.846 |
rebellious | -1.841 |
Token | t |
Token ID | 256 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
haps | +0.162 |
Medic | +0.152 |
ombo | +0.144 |
ggle | +0.141 |
Kappa | +0.131 |
Neg logit contributions | |
retard | -0.259 |
strip | -0.231 |
lesbians | -0.224 |
LS | -0.208 |
rebellious | -0.206 |
Token | : |
Token ID | 1058 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
haps | +0.153 |
Medic | +0.142 |
ombo | +0.137 |
ggle | +0.134 |
Kappa | +0.125 |
Neg logit contributions | |
retard | -0.198 |
strip | -0.174 |
lesbians | -0.166 |
LS | -0.154 |
rebellious | -0.154 |
Token | T |
Token ID | 309 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
haps | +0.919 |
Medic | +0.893 |
ombo | +0.828 |
ggle | +0.809 |
Kappa | +0.784 |
Neg logit contributions | |
retard | -1.223 |
strip | -1.073 |
lesbians | -1.037 |
clean | -0.959 |
susp | -0.956 |
Token | him |
Token ID | 683 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
haps | +0.405 |
Medic | +0.388 |
ombo | +0.368 |
ggle | +0.364 |
Kappa | +0.341 |
Neg logit contributions | |
retard | -0.501 |
strip | -0.440 |
lesbians | -0.419 |
clean | -0.391 |
LS | -0.385 |
Token | out |
Token ID | 503 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
retard | +0.189 |
strip | +0.158 |
lesbians | +0.148 |
LS | +0.134 |
clean | +0.133 |
Neg logit contributions | |
haps | -0.252 |
Medic | -0.241 |
ggle | -0.235 |
ombo | -0.234 |
Kappa | -0.220 |
Token | of |
Token ID | 286 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
haps | +1.779 |
Medic | +1.688 |
ombo | +1.635 |
ggle | +1.601 |
rals | +1.553 |
Neg logit contributions | |
retard | -1.847 |
strip | -1.594 |
lesbians | -1.494 |
LS | -1.390 |
rebellious | -1.386 |
Token | action |
Token ID | 2223 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
haps | +0.670 |
Medic | +0.646 |
ombo | +0.624 |
ggle | +0.610 |
Kappa | +0.580 |
Neg logit contributions | |
retard | -0.693 |
strip | -0.594 |
lesbians | -0.571 |
clean | -0.531 |
LS | -0.523 |
Token | not |
Token ID | 407 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
retard | +0.145 |
strip | +0.126 |
lesbians | +0.118 |
clean | +0.111 |
LS | +0.110 |
Neg logit contributions | |
haps | -0.136 |
Medic | -0.128 |
ombo | -0.124 |
ggle | -0.123 |
Kappa | -0.115 |
Token | only |
Token ID | 691 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
haps | +0.752 |
Medic | +0.701 |
ombo | +0.690 |
ggle | +0.672 |
rals | +0.643 |
Neg logit contributions | |
retard | -0.723 |
strip | -0.625 |
lesbians | -0.592 |
clean | -0.555 |
LS | -0.545 |
Token | for |
Token ID | 329 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
retard | +4.008 |
strip | +3.502 |
lesbians | +3.245 |
LS | +2.996 |
rebellious | +2.969 |
Neg logit contributions | |
haps | -4.441 |
Medic | -4.138 |
ombo | -4.055 |
ggle | -4.017 |
�� | -3.764 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
retard | +1.120 |
strip | +0.970 |
lesbians | +0.906 |
clean | +0.835 |
rebellious | +0.827 |
Neg logit contributions | |
haps | -1.210 |
Medic | -1.147 |
ombo | -1.107 |
ggle | -1.098 |
Kappa | -1.036 |
Token | balance |
Token ID | 5236 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
retard | +0.707 |
strip | +0.613 |
lesbians | +0.575 |
clean | +0.537 |
rebellious | +0.528 |
Neg logit contributions | |
haps | -0.723 |
Medic | -0.691 |
ombo | -0.663 |
ggle | -0.653 |
Kappa | -0.619 |
Token | of |
Token ID | 286 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
haps | +0.269 |
Medic | +0.254 |
ombo | +0.248 |
ggle | +0.245 |
Kappa | +0.231 |
Neg logit contributions | |
retard | -0.231 |
strip | -0.200 |
lesbians | -0.187 |
rebellious | -0.171 |
clean | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
retard | +0.315 |
strip | +0.272 |
lesbians | +0.256 |
clean | +0.237 |
rebellious | +0.234 |
Neg logit contributions | |
haps | -0.324 |
Medic | -0.309 |
ombo | -0.298 |
ggle | -0.293 |
Kappa | -0.277 |
Token | WR |
Token ID | 18564 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
retard | +0.436 |
strip | +0.360 |
lesbians | +0.328 |
LS | +0.292 |
rebellious | +0.290 |
Neg logit contributions | |
haps | -0.735 |
Medic | -0.696 |
ombo | -0.682 |
ggle | -0.679 |
Kappa | -0.644 |
Token | had |
Token ID | 550 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
retard | +0.325 |
strip | +0.281 |
lesbians | +0.268 |
rebellious | +0.250 |
clean | +0.248 |
Neg logit contributions | |
haps | -0.289 |
Medic | -0.274 |
ombo | -0.264 |
ggle | -0.260 |
Kappa | -0.245 |
Token | been |
Token ID | 587 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
retard | +1.961 |
strip | +1.717 |
lesbians | +1.610 |
clean | +1.490 |
LS | +1.485 |
Neg logit contributions | |
haps | -1.886 |
Medic | -1.760 |
ombo | -1.712 |
ggle | -1.699 |
Kappa | -1.583 |
Token | configured |
Token ID | 17839 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
retard | +0.816 |
strip | +0.691 |
lesbians | +0.658 |
clean | +0.602 |
LS | +0.594 |
Neg logit contributions | |
haps | -0.911 |
Medic | -0.855 |
ggle | -0.827 |
ombo | -0.826 |
Kappa | -0.782 |
Token | so |
Token ID | 523 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
retard | +1.565 |
strip | +1.358 |
lesbians | +1.295 |
rebellious | +1.195 |
clean | +1.189 |
Neg logit contributions | |
haps | -1.395 |
Medic | -1.305 |
ombo | -1.271 |
ggle | -1.265 |
Kappa | -1.171 |
Token | long |
Token ID | 890 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
retard | +0.986 |
strip | +0.835 |
lesbians | +0.778 |
clean | +0.705 |
rebellious | +0.705 |
Neg logit contributions | |
haps | -1.276 |
Medic | -1.190 |
ombo | -1.157 |
ggle | -1.154 |
Kappa | -1.086 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
retard | +3.583 |
strip | +3.068 |
lesbians | +2.825 |
LS | +2.571 |
rebellious | +2.553 |
Neg logit contributions | |
haps | -4.790 |
Medic | -4.500 |
ombo | -4.415 |
ggle | -4.372 |
Kappa | -4.114 |
Token | that |
Token ID | 326 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
retard | +1.175 |
strip | +0.994 |
lesbians | +0.921 |
rebellious | +0.835 |
clean | +0.830 |
Neg logit contributions | |
haps | -1.629 |
Medic | -1.532 |
ombo | -1.493 |
ggle | -1.486 |
Kappa | -1.409 |
Token | I |
Token ID | 314 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
haps | +0.181 |
Medic | +0.168 |
ombo | +0.160 |
ggle | +0.159 |
Kappa | +0.150 |
Neg logit contributions | |
retard | -0.198 |
strip | -0.172 |
lesbians | -0.162 |
clean | -0.151 |
rebellious | -0.151 |
Token | completely |
Token ID | 3190 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
haps | +0.445 |
Medic | +0.410 |
ggle | +0.400 |
ombo | +0.399 |
Kappa | +0.366 |
Neg logit contributions | |
retard | -0.510 |
strip | -0.438 |
lesbians | -0.423 |
rebellious | -0.397 |
clean | -0.392 |
Token | forgot |
Token ID | 16453 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
retard | +0.198 |
strip | +0.171 |
lesbians | +0.167 |
rebellious | +0.155 |
LS | +0.155 |
Neg logit contributions | |
haps | -0.167 |
Medic | -0.156 |
ggle | -0.152 |
ombo | -0.151 |
Kappa | -0.139 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
retard | +0.195 |
strip | +0.172 |
lesbians | +0.162 |
rebellious | +0.151 |
clean | +0.151 |
Neg logit contributions | |
haps | -0.186 |
Medic | -0.174 |
ombo | -0.172 |
ggle | -0.165 |
Kappa | -0.159 |
Token | Cu |
Token ID | 46141 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
retard | +0.593 |
strip | +0.526 |
lesbians | +0.496 |
rebellious | +0.460 |
LS | +0.457 |
Neg logit contributions | |
haps | -0.539 |
Medic | -0.504 |
ombo | -0.493 |
ggle | -0.483 |
Kappa | -0.455 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
retard | +0.095 |
strip | +0.083 |
lesbians | +0.078 |
rebellious | +0.072 |
LS | +0.071 |
Neg logit contributions | |
haps | -0.099 |
Medic | -0.093 |
ombo | -0.092 |
ggle | -0.089 |
Kappa | -0.085 |
Token | O |
Token ID | 46 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
retard | +1.404 |
strip | +1.223 |
lesbians | +1.135 |
LS | +1.048 |
rebellious | +1.039 |
Neg logit contributions | |
haps | -1.547 |
Medic | -1.445 |
ombo | -1.414 |
ggle | -1.399 |
rals | -1.310 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
retard | +0.053 |
strip | +0.045 |
lesbians | +0.042 |
rebellious | +0.038 |
LS | +0.038 |
Neg logit contributions | |
haps | -0.067 |
Medic | -0.063 |
ombo | -0.062 |
ggle | -0.062 |
Kappa | -0.058 |
Token | + |
Token ID | 10 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
retard | +0.500 |
strip | +0.443 |
lesbians | +0.420 |
rebellious | +0.389 |
LS | +0.388 |
Neg logit contributions | |
haps | -0.429 |
Medic | -0.400 |
ombo | -0.391 |
ggle | -0.383 |
Kappa | -0.359 |
Token | x |
Token ID | 87 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
retard | +3.400 |
strip | +2.900 |
lesbians | +2.647 |
LS | +2.409 |
clean | +2.396 |
Neg logit contributions | |
haps | -4.813 |
Medic | -4.536 |
ombo | -4.437 |
ggle | -4.397 |
�� | -4.158 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
haps | +0.029 |
Medic | +0.027 |
ombo | +0.027 |
ggle | +0.026 |
Kappa | +0.025 |
Neg logit contributions | |
retard | -0.031 |
strip | -0.027 |
lesbians | -0.026 |
rebellious | -0.024 |
clean | -0.024 |
Token | is |
Token ID | 318 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
retard | +0.535 |
strip | +0.472 |
lesbians | +0.446 |
clean | +0.415 |
rebellious | +0.413 |
Neg logit contributions | |
haps | -0.492 |
Medic | -0.458 |
ombo | -0.448 |
ggle | -0.437 |
Kappa | -0.416 |
Token | one |
Token ID | 530 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
retard | +1.741 |
strip | +1.516 |
lesbians | +1.423 |
clean | +1.310 |
LS | +1.309 |
Neg logit contributions | |
haps | -1.842 |
Medic | -1.722 |
ombo | -1.685 |
ggle | -1.657 |
Kappa | -1.564 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
retard | +0.364 |
strip | +0.315 |
lesbians | +0.299 |
clean | +0.273 |
LS | +0.271 |
Neg logit contributions | |
haps | -0.410 |
Medic | -0.386 |
ombo | -0.377 |
ggle | -0.372 |
Kappa | -0.351 |
Token | 21 |
Token ID | 2481 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
haps | +0.233 |
Medic | +0.218 |
ombo | +0.214 |
ggle | +0.212 |
rals | +0.198 |
Neg logit contributions | |
retard | -0.215 |
strip | -0.185 |
lesbians | -0.173 |
LS | -0.160 |
rebellious | -0.158 |
Token | O |
Token ID | 440 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
haps | +0.409 |
Medic | +0.405 |
ombo | +0.379 |
ggle | +0.374 |
Kappa | +0.368 |
Neg logit contributions | |
retard | -0.343 |
strip | -0.287 |
lesbians | -0.266 |
rebellious | -0.250 |
clean | -0.243 |
Token | & |
Token ID | 5 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
retard | +0.912 |
strip | +0.786 |
lesbians | +0.729 |
rebellious | +0.675 |
LS | +0.666 |
Neg logit contributions | |
haps | -1.035 |
Medic | -0.969 |
ggle | -0.939 |
ombo | -0.937 |
Kappa | -0.877 |
Token | A |
Token ID | 32 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
retard | +1.885 |
strip | +1.656 |
lesbians | +1.544 |
LS | +1.432 |
clean | +1.422 |
Neg logit contributions | |
haps | -1.882 |
Medic | -1.751 |
ombo | -1.715 |
ggle | -1.694 |
rals | -1.580 |
Token | - |
Token ID | 12 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
retard | +1.084 |
strip | +0.939 |
lesbians | +0.876 |
rebellious | +0.817 |
LS | +0.803 |
Neg logit contributions | |
haps | -1.118 |
Medic | -1.057 |
ombo | -1.019 |
ggle | -1.012 |
Kappa | -0.953 |
Token | WOR |
Token ID | 45359 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
retard | +0.031 |
strip | +0.027 |
lesbians | +0.025 |
rebellious | +0.024 |
LS | +0.024 |
Neg logit contributions | |
haps | -0.028 |
Medic | -0.026 |
ombo | -0.025 |
ggle | -0.025 |
Kappa | -0.023 |
Token | ST |
Token ID | 2257 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
retard | +3.438 |
strip | +2.935 |
lesbians | +2.693 |
LS | +2.450 |
clean | +2.427 |
Neg logit contributions | |
haps | -4.782 |
Medic | -4.496 |
ombo | -4.414 |
ggle | -4.367 |
rals | -4.121 |
Token | OF |
Token ID | 3963 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
retard | +1.461 |
strip | +1.252 |
lesbians | +1.153 |
LS | +1.048 |
rebellious | +1.046 |
Neg logit contributions | |
haps | -1.921 |
Medic | -1.811 |
ombo | -1.773 |
ggle | -1.754 |
Kappa | -1.654 |
Token | - |
Token ID | 12 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
retard | +0.394 |
strip | +0.343 |
lesbians | +0.318 |
LS | +0.293 |
rebellious | +0.291 |
Neg logit contributions | |
haps | -0.447 |
Medic | -0.417 |
ombo | -0.409 |
ggle | -0.405 |
rals | -0.379 |
Token | Penn |
Token ID | 39899 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
haps | +0.215 |
Medic | +0.204 |
ombo | +0.195 |
ggle | +0.191 |
Kappa | +0.180 |
Neg logit contributions | |
retard | -0.247 |
strip | -0.216 |
lesbians | -0.201 |
rebellious | -0.190 |
LS | -0.188 |
Token | J |
Token ID | 449 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
retard | +1.072 |
strip | +0.946 |
lesbians | +0.895 |
rebellious | +0.835 |
clean | +0.823 |
Neg logit contributions | |
haps | -0.922 |
Medic | -0.866 |
ombo | -0.833 |
ggle | -0.819 |
Kappa | -0.773 |
Token | comes |
Token ID | 2058 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
retard | +0.013 |
strip | +0.011 |
lesbians | +0.011 |
clean | +0.010 |
LS | +0.010 |
Neg logit contributions | |
haps | -0.013 |
Medic | -0.012 |
ombo | -0.012 |
ggle | -0.012 |
Kappa | -0.011 |
Token | next |
Token ID | 1306 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
retard | +0.015 |
strip | +0.013 |
lesbians | +0.011 |
LS | +0.010 |
rebellious | +0.010 |
Neg logit contributions | |
haps | -0.023 |
Medic | -0.022 |
ggle | -0.022 |
ombo | -0.021 |
Kappa | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
retard | +2.672 |
strip | +2.354 |
lesbians | +2.202 |
LS | +2.045 |
clean | +2.033 |
Neg logit contributions | |
haps | -2.517 |
Medic | -2.345 |
ombo | -2.286 |
ggle | -2.258 |
rals | -2.100 |
Token | flu |
Token ID | 6562 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
haps | +0.335 |
Medic | +0.324 |
ombo | +0.306 |
ggle | +0.304 |
Kappa | +0.282 |
Neg logit contributions | |
retard | -0.373 |
strip | -0.328 |
lesbians | -0.308 |
clean | -0.288 |
LS | -0.286 |
Token | fight |
Token ID | 1907 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
retard | +0.488 |
strip | +0.434 |
lesbians | +0.410 |
LS | +0.380 |
clean | +0.374 |
Neg logit contributions | |
haps | -0.444 |
Medic | -0.424 |
ggle | -0.405 |
ombo | -0.405 |
Kappa | -0.376 |
Token | WHO |
Token ID | 19494 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
haps | +0.270 |
Medic | +0.260 |
ombo | +0.245 |
ggle | +0.244 |
Kappa | +0.228 |
Neg logit contributions | |
retard | -0.297 |
strip | -0.262 |
lesbians | -0.245 |
clean | -0.229 |
LS | -0.227 |
Token | chief |
Token ID | 4039 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
retard | +3.921 |
strip | +3.419 |
lesbians | +3.178 |
LS | +2.931 |
rebellious | +2.910 |
Neg logit contributions | |
haps | -4.288 |
Medic | -3.972 |
ombo | -3.917 |
ggle | -3.872 |
�� | -3.629 |
Token | Margaret |
Token ID | 19579 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
retard | +0.542 |
strip | +0.468 |
lesbians | +0.436 |
LS | +0.401 |
clean | +0.398 |
Neg logit contributions | |
haps | -0.616 |
Medic | -0.595 |
ombo | -0.566 |
ggle | -0.560 |
Kappa | -0.528 |
Token | Chan |
Token ID | 18704 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
retard | +1.463 |
strip | +1.303 |
lesbians | +1.233 |
clean | +1.157 |
rebellious | +1.152 |
Neg logit contributions | |
haps | -1.023 |
Medic | -0.986 |
ombo | -0.933 |
ggle | -0.890 |
Kappa | -0.851 |
Token | talked |
Token ID | 6619 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
retard | +0.644 |
strip | +0.558 |
lesbians | +0.520 |
LS | +0.479 |
rebellious | +0.478 |
Neg logit contributions | |
haps | -0.700 |
Medic | -0.667 |
ombo | -0.639 |
ggle | -0.632 |
Kappa | -0.596 |
Token | to |
Token ID | 284 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
retard | +0.925 |
strip | +0.805 |
lesbians | +0.745 |
LS | +0.688 |
clean | +0.686 |
Neg logit contributions | |
haps | -1.038 |
Medic | -0.985 |
ombo | -0.952 |
ggle | -0.942 |
Kappa | -0.881 |
Token | The |
Token ID | 383 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
retard | +0.388 |
strip | +0.339 |
lesbians | +0.325 |
rebellious | +0.302 |
LS | +0.296 |
Neg logit contributions | |
haps | -0.345 |
Medic | -0.325 |
ombo | -0.312 |
ggle | -0.306 |
Kappa | -0.290 |
Token | solution |
Token ID | 4610 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
retard | +0.546 |
strip | +0.474 |
lesbians | +0.450 |
rebellious | +0.412 |
clean | +0.410 |
Neg logit contributions | |
haps | -0.563 |
Medic | -0.532 |
ombo | -0.516 |
ggle | -0.501 |
Kappa | -0.480 |
Token | that |
Token ID | 326 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
retard | +0.972 |
strip | +0.846 |
lesbians | +0.804 |
rebellious | +0.742 |
LS | +0.738 |
Neg logit contributions | |
haps | -0.929 |
Medic | -0.868 |
ombo | -0.848 |
ggle | -0.832 |
Kappa | -0.784 |
Token | I |
Token ID | 314 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
retard | +1.232 |
strip | +1.081 |
lesbians | +1.019 |
rebellious | +0.944 |
LS | +0.940 |
Neg logit contributions | |
haps | -1.179 |
Medic | -1.097 |
ombo | -1.067 |
ggle | -1.048 |
Kappa | -0.986 |
Token | end |
Token ID | 886 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
retard | +0.514 |
strip | +0.446 |
lesbians | +0.425 |
rebellious | +0.395 |
LS | +0.394 |
Neg logit contributions | |
haps | -0.491 |
Medic | -0.456 |
ombo | -0.447 |
ggle | -0.439 |
rals | -0.411 |
Token | up |
Token ID | 510 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
retard | +0.167 |
strip | +0.137 |
lesbians | +0.128 |
LS | +0.113 |
rebellious | +0.113 |
Neg logit contributions | |
haps | -0.276 |
Medic | -0.261 |
ombo | -0.257 |
ggle | -0.255 |
Kappa | -0.241 |
Token | with |
Token ID | 351 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
retard | +3.569 |
strip | +3.118 |
lesbians | +2.837 |
LS | +2.611 |
clean | +2.579 |
Neg logit contributions | |
haps | -4.518 |
Medic | -4.244 |
ombo | -4.163 |
ggle | -4.130 |
rals | -3.893 |
Token | requires |
Token ID | 4433 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
retard | +1.018 |
strip | +0.893 |
lesbians | +0.844 |
rebellious | +0.782 |
LS | +0.778 |
Neg logit contributions | |
haps | -0.941 |
Medic | -0.875 |
ombo | -0.855 |
ggle | -0.842 |
Kappa | -0.792 |
Token | that |
Token ID | 326 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
retard | +1.207 |
strip | +1.047 |
lesbians | +0.985 |
rebellious | +0.909 |
LS | +0.902 |
Neg logit contributions | |
haps | -1.278 |
Medic | -1.200 |
ombo | -1.167 |
ggle | -1.148 |
Kappa | -1.082 |
Token | I |
Token ID | 314 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
haps | +0.363 |
Medic | +0.341 |
ombo | +0.328 |
ggle | +0.318 |
Kappa | +0.307 |
Neg logit contributions | |
retard | -0.369 |
strip | -0.321 |
lesbians | -0.305 |
rebellious | -0.285 |
LS | -0.279 |
Token | write |
Token ID | 3551 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
haps | +0.195 |
Medic | +0.183 |
ombo | +0.179 |
ggle | +0.176 |
Kappa | +0.165 |
Neg logit contributions | |
retard | -0.171 |
strip | -0.144 |
lesbians | -0.142 |
rebellious | -0.131 |
LS | -0.129 |
Token | interested |
Token ID | 4609 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
haps | +0.049 |
Medic | +0.046 |
ggle | +0.044 |
ombo | +0.044 |
Kappa | +0.042 |
Neg logit contributions | |
retard | -0.046 |
strip | -0.039 |
lesbians | -0.037 |
clean | -0.034 |
LS | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
retard | +0.480 |
strip | +0.416 |
lesbians | +0.382 |
rebellious | +0.350 |
LS | +0.348 |
Neg logit contributions | |
haps | -0.607 |
Medic | -0.568 |
ombo | -0.558 |
ggle | -0.551 |
�� | -0.519 |
Token | characters |
Token ID | 3435 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
retard | +0.832 |
strip | +0.717 |
lesbians | +0.671 |
clean | +0.623 |
LS | +0.618 |
Neg logit contributions | |
haps | -0.875 |
Medic | -0.829 |
ggle | -0.800 |
ombo | -0.799 |
Kappa | -0.751 |
Token | that |
Token ID | 326 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
retard | +1.573 |
strip | +1.345 |
lesbians | +1.251 |
clean | +1.166 |
LS | +1.161 |
Neg logit contributions | |
haps | -1.823 |
Medic | -1.713 |
ombo | -1.670 |
ggle | -1.664 |
Kappa | -1.569 |
Token | start |
Token ID | 923 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
retard | +1.675 |
strip | +1.449 |
lesbians | +1.364 |
clean | +1.274 |
LS | +1.265 |
Neg logit contributions | |
haps | -1.714 |
Medic | -1.601 |
ggle | -1.547 |
ombo | -1.545 |
Kappa | -1.440 |
Token | off |
Token ID | 572 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
retard | +0.899 |
strip | +0.762 |
lesbians | +0.695 |
clean | +0.642 |
LS | +0.637 |
Neg logit contributions | |
haps | -1.278 |
Medic | -1.208 |
ombo | -1.184 |
ggle | -1.182 |
Kappa | -1.108 |
Token | one |
Token ID | 530 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
retard | +3.718 |
strip | +3.216 |
lesbians | +2.981 |
LS | +2.740 |
clean | +2.720 |
Neg logit contributions | |
haps | -4.384 |
Medic | -4.108 |
ombo | -4.023 |
ggle | -3.982 |
Kappa | -3.732 |
Token | way |
Token ID | 835 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
haps | +0.114 |
Medic | +0.108 |
ggle | +0.105 |
ombo | +0.104 |
Kappa | +0.098 |
Neg logit contributions | |
retard | -0.094 |
strip | -0.079 |
lesbians | -0.076 |
clean | -0.071 |
LS | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
haps | +0.303 |
Medic | +0.283 |
ggle | +0.274 |
ombo | +0.270 |
Kappa | +0.257 |
Neg logit contributions | |
retard | -0.309 |
strip | -0.268 |
lesbians | -0.253 |
LS | -0.238 |
clean | -0.234 |
Token | end |
Token ID | 886 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
retard | +0.261 |
strip | +0.223 |
lesbians | +0.210 |
clean | +0.199 |
LS | +0.197 |
Neg logit contributions | |
haps | -0.306 |
Medic | -0.288 |
ombo | -0.276 |
ggle | -0.274 |
Kappa | -0.260 |
Token | another |
Token ID | 1194 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
haps | +1.356 |
Medic | +1.276 |
ombo | +1.262 |
ggle | +1.249 |
Kappa | +1.176 |
Neg logit contributions | |
retard | -0.961 |
strip | -0.809 |
lesbians | -0.748 |
clean | -0.698 |
LS | -0.681 |
Token | . |
Token ID | 13 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
haps | +1.154 |
Medic | +1.098 |
ggle | +1.046 |
ombo | +1.046 |
Kappa | +0.990 |
Neg logit contributions | |
retard | -1.238 |
strip | -1.056 |
lesbians | -1.014 |
rebellious | -0.965 |
LS | -0.916 |
Token | parse |
Token ID | 29572 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
retard | +0.414 |
strip | +0.370 |
lesbians | +0.353 |
rebellious | +0.333 |
LS | +0.330 |
Neg logit contributions | |
haps | -0.273 |
Medic | -0.245 |
ombo | -0.243 |
ggle | -0.239 |
rals | -0.216 |
Token | _ |
Token ID | 62 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
haps | +0.419 |
Medic | +0.396 |
ombo | +0.381 |
ggle | +0.381 |
Kappa | +0.356 |
Neg logit contributions | |
retard | -0.460 |
strip | -0.400 |
lesbians | -0.379 |
rebellious | -0.356 |
LS | -0.346 |
Token | args |
Token ID | 22046 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
haps | +0.513 |
Medic | +0.468 |
ombo | +0.455 |
ggle | +0.451 |
rals | +0.419 |
Neg logit contributions | |
retard | -0.741 |
strip | -0.666 |
lesbians | -0.627 |
rebellious | -0.589 |
LS | -0.587 |
Token | ()) |
Token ID | 28955 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
haps | +0.209 |
Medic | +0.196 |
ombo | +0.192 |
ggle | +0.190 |
rals | +0.179 |
Neg logit contributions | |
retard | -0.173 |
strip | -0.148 |
lesbians | -0.136 |
rebellious | -0.127 |
LS | -0.124 |
Token | # |
Token ID | 1303 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
retard | +1.229 |
strip | +1.107 |
lesbians | +1.010 |
LS | +0.966 |
clean | +0.954 |
Neg logit contributions | |
haps | -0.977 |
Medic | -0.884 |
ombo | -0.879 |
ggle | -0.861 |
�� | -0.805 |
Token | initialize |
Token ID | 41216 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
retard | +4.696 |
strip | +4.207 |
lesbians | +3.964 |
LS | +3.725 |
clean | +3.703 |
Neg logit contributions | |
haps | -3.368 |
Medic | -3.089 |
ombo | -3.010 |
ggle | -2.962 |
rals | -2.720 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
retard | +1.226 |
strip | +1.072 |
lesbians | +0.997 |
LS | +0.921 |
rebellious | +0.914 |
Neg logit contributions | |
haps | -1.310 |
Medic | -1.222 |
ombo | -1.197 |
ggle | -1.183 |
rals | -1.106 |
Token | rectangular |
Token ID | 36954 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
retard | +0.480 |
strip | +0.393 |
lesbians | +0.373 |
LS | +0.336 |
clean | +0.335 |
Neg logit contributions | |
haps | -0.702 |
Medic | -0.673 |
ombo | -0.659 |
ggle | -0.656 |
Kappa | -0.621 |
Token | and |
Token ID | 290 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
haps | +1.233 |
Medic | +1.182 |
ombo | +1.134 |
ggle | +1.123 |
Kappa | +1.076 |
Neg logit contributions | |
retard | -1.151 |
strip | -0.974 |
lesbians | -0.941 |
rebellious | -0.875 |
clean | -0.869 |
Token | square |
Token ID | 6616 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
retard | +1.463 |
strip | +1.286 |
lesbians | +1.216 |
LS | +1.133 |
clean | +1.126 |
Neg logit contributions | |
haps | -1.294 |
Medic | -1.203 |
ombo | -1.173 |
ggle | -1.161 |
Kappa | -1.078 |
Token | |
Token ID | 3907 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
retard | +0.240 |
strip | +0.213 |
lesbians | +0.202 |
LS | +0.188 |
rebellious | +0.188 |
Neg logit contributions | |
haps | -0.196 |
Medic | -0.181 |
ombo | -0.176 |
ggle | -0.174 |
Kappa | -0.161 |
Token | log |
Token ID | 6404 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
haps | +3.825 |
Medic | +3.444 |
ombo | +3.350 |
ggle | +3.317 |
lus | +3.106 |
Neg logit contributions | |
retard | -4.023 |
strip | -3.583 |
lesbians | -3.428 |
rebellious | -3.177 |
LS | -3.132 |
Token | y |
Token ID | 88 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
haps | +1.334 |
Medic | +1.204 |
ombo | +1.200 |
ggle | +1.172 |
rals | +1.089 |
Neg logit contributions | |
retard | -1.639 |
strip | -1.446 |
lesbians | -1.404 |
LS | -1.303 |
rebellious | -1.299 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
haps | +0.815 |
Medic | +0.772 |
ombo | +0.741 |
ggle | +0.740 |
Kappa | +0.704 |
Neg logit contributions | |
retard | -0.752 |
strip | -0.651 |
lesbians | -0.627 |
clean | -0.578 |
rebellious | -0.577 |
Token | ma |
Token ID | 17266 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
retard | +0.818 |
strip | +0.712 |
lesbians | +0.687 |
clean | +0.625 |
LS | +0.620 |
Neg logit contributions | |
haps | -0.862 |
Medic | -0.817 |
ombo | -0.788 |
ggle | -0.782 |
Kappa | -0.739 |
Token | |
Token ID | 3907 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
haps | +1.273 |
Medic | +1.158 |
ombo | +1.122 |
ggle | +1.122 |
Kappa | +1.046 |
Neg logit contributions | |
retard | -1.841 |
strip | -1.631 |
lesbians | -1.587 |
rebellious | -1.498 |
LS | -1.465 |
Token | j |
Token ID | 73 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
haps | +2.765 |
ggle | +2.428 |
Medic | +2.427 |
ombo | +2.425 |
rals | +2.198 |
Neg logit contributions | |
retard | -3.475 |
strip | -3.136 |
lesbians | -2.988 |
rebellious | -2.794 |
LS | -2.779 |
Token | or |
Token ID | 273 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
haps | +1.149 |
ombo | +1.097 |
Medic | +1.070 |
ggle | +1.050 |
appa | +0.985 |
Neg logit contributions | |
retard | -1.321 |
strip | -1.169 |
lesbians | -1.118 |
rebellious | -1.030 |
LS | -1.014 |
Token | thrust |
Token ID | 14613 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
haps | +0.841 |
Medic | +0.786 |
ombo | +0.767 |
ggle | +0.755 |
Kappa | +0.712 |
Neg logit contributions | |
retard | -0.817 |
strip | -0.710 |
lesbians | -0.701 |
clean | -0.637 |
rebellious | -0.632 |
Token | of |
Token ID | 286 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
retard | +0.902 |
strip | +0.776 |
lesbians | +0.741 |
rebellious | +0.682 |
LS | +0.680 |
Neg logit contributions | |
haps | -0.980 |
Medic | -0.918 |
ombo | -0.901 |
ggle | -0.889 |
Kappa | -0.838 |
Token | his |
Token ID | 465 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
retard | +1.545 |
strip | +1.350 |
lesbians | +1.272 |
clean | +1.176 |
LS | +1.168 |
Neg logit contributions | |
haps | -1.582 |
Medic | -1.488 |
ombo | -1.445 |
ggle | -1.428 |
Kappa | -1.345 |
Token | land |
Token ID | 1044 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
haps | +0.524 |
Medic | +0.487 |
ombo | +0.479 |
ggle | +0.474 |
rals | +0.450 |
Neg logit contributions | |
retard | -0.579 |
strip | -0.506 |
lesbians | -0.480 |
LS | -0.441 |
rebellious | -0.441 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
retard | +0.007 |
strip | +0.006 |
lesbians | +0.006 |
rebellious | +0.005 |
LS | +0.005 |
Neg logit contributions | |
haps | -0.008 |
Medic | -0.007 |
ombo | -0.007 |
ggle | -0.007 |
Kappa | -0.006 |
Token | By |
Token ID | 3886 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
retard | +0.378 |
strip | +0.331 |
lesbians | +0.308 |
rebellious | +0.286 |
LS | +0.285 |
Neg logit contributions | |
haps | -0.363 |
Medic | -0.335 |
ombo | -0.329 |
ggle | -0.324 |
rals | -0.301 |
Token | Sam |
Token ID | 3409 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
haps | +0.706 |
Medic | +0.669 |
ombo | +0.647 |
ggle | +0.641 |
Kappa | +0.602 |
Neg logit contributions | |
retard | -0.728 |
strip | -0.628 |
lesbians | -0.590 |
clean | -0.551 |
rebellious | -0.547 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
retard | +0.453 |
strip | +0.395 |
lesbians | +0.374 |
clean | +0.346 |
rebellious | +0.346 |
Neg logit contributions | |
haps | -0.405 |
Medic | -0.381 |
ombo | -0.371 |
ggle | -0.361 |
Kappa | -0.340 |
Token | updated |
Token ID | 6153 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
retard | +0.508 |
strip | +0.444 |
lesbians | +0.416 |
clean | +0.388 |
rebellious | +0.386 |
Neg logit contributions | |
haps | -0.482 |
Medic | -0.459 |
ombo | -0.436 |
ggle | -0.426 |
Kappa | -0.408 |
Token | on |
Token ID | 319 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
haps | +3.084 |
Medic | +2.984 |
ombo | +2.836 |
ggle | +2.733 |
Kappa | +2.649 |
Neg logit contributions | |
retard | -3.323 |
strip | -2.857 |
lesbians | -2.696 |
clean | -2.536 |
rebellious | -2.523 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
retard | +0.437 |
strip | +0.380 |
lesbians | +0.356 |
clean | +0.332 |
rebellious | +0.331 |
Neg logit contributions | |
haps | -0.415 |
Medic | -0.396 |
ombo | -0.379 |
ggle | -0.375 |
Kappa | -0.354 |
Token | July |
Token ID | 2901 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
retard | +0.239 |
strip | +0.209 |
lesbians | +0.195 |
rebellious | +0.182 |
LS | +0.180 |
Neg logit contributions | |
haps | -0.208 |
Medic | -0.198 |
ombo | -0.188 |
ggle | -0.188 |
Kappa | -0.175 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
retard | +1.354 |
strip | +1.185 |
lesbians | +1.116 |
rebellious | +1.047 |
clean | +1.035 |
Neg logit contributions | |
haps | -1.193 |
Medic | -1.130 |
ombo | -1.087 |
ggle | -1.066 |
Kappa | -1.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
retard | +0.416 |
strip | +0.365 |
lesbians | +0.345 |
rebellious | +0.323 |
clean | +0.318 |
Neg logit contributions | |
haps | -0.363 |
Medic | -0.345 |
ombo | -0.331 |
ggle | -0.322 |
Kappa | -0.306 |
Token | the |
Token ID | 262 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
retard | +0.881 |
strip | +0.763 |
lesbians | +0.715 |
clean | +0.659 |
rebellious | +0.654 |
Neg logit contributions | |
haps | -0.924 |
Medic | -0.870 |
ombo | -0.843 |
ggle | -0.831 |
Kappa | -0.792 |
Token | same |
Token ID | 976 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
retard | +0.312 |
strip | +0.263 |
lesbians | +0.242 |
clean | +0.218 |
LS | +0.215 |
Neg logit contributions | |
haps | -0.454 |
Medic | -0.436 |
ombo | -0.419 |
ggle | -0.414 |
Kappa | -0.400 |
Token | person |
Token ID | 1048 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
retard | +0.697 |
strip | +0.612 |
lesbians | +0.582 |
clean | +0.540 |
rebellious | +0.535 |
Neg logit contributions | |
haps | -0.592 |
Medic | -0.562 |
ombo | -0.537 |
ggle | -0.530 |
Kappa | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
haps | +0.271 |
Medic | +0.252 |
ombo | +0.245 |
ggle | +0.242 |
Kappa | +0.232 |
Neg logit contributions | |
retard | -0.269 |
strip | -0.234 |
lesbians | -0.222 |
LS | -0.205 |
rebellious | -0.204 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
haps | +0.608 |
Medic | +0.594 |
ombo | +0.555 |
ggle | +0.550 |
Kappa | +0.537 |
Neg logit contributions | |
retard | -0.587 |
strip | -0.506 |
lesbians | -0.478 |
rebellious | -0.442 |
clean | -0.435 |
Token | Published |
Token ID | 24492 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
retard | +0.150 |
strip | +0.132 |
lesbians | +0.122 |
rebellious | +0.114 |
LS | +0.113 |
Neg logit contributions | |
haps | -0.144 |
Medic | -0.133 |
ombo | -0.131 |
ggle | -0.128 |
rals | -0.119 |
Token | on |
Token ID | 319 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
haps | +3.269 |
Medic | +3.160 |
ombo | +3.036 |
ggle | +2.974 |
Kappa | +2.807 |
Neg logit contributions | |
retard | -3.363 |
strip | -2.846 |
lesbians | -2.663 |
rebellious | -2.535 |
clean | -2.530 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
retard | +0.566 |
strip | +0.494 |
lesbians | +0.462 |
clean | +0.429 |
rebellious | +0.428 |
Neg logit contributions | |
haps | -0.513 |
Medic | -0.493 |
ombo | -0.468 |
ggle | -0.465 |
Kappa | -0.439 |
Token | December |
Token ID | 3426 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
retard | +0.200 |
strip | +0.175 |
lesbians | +0.164 |
rebellious | +0.153 |
LS | +0.152 |
Neg logit contributions | |
haps | -0.171 |
Medic | -0.163 |
ggle | -0.153 |
ombo | -0.153 |
Kappa | -0.143 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
retard | +1.397 |
strip | +1.217 |
lesbians | +1.143 |
rebellious | +1.074 |
clean | +1.064 |
Neg logit contributions | |
haps | -1.259 |
Medic | -1.203 |
ombo | -1.149 |
ggle | -1.129 |
Kappa | -1.071 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
retard | +0.134 |
strip | +0.117 |
lesbians | +0.111 |
rebellious | +0.104 |
clean | +0.103 |
Neg logit contributions | |
haps | -0.111 |
Medic | -0.105 |
ombo | -0.100 |
ggle | -0.098 |
Kappa | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
haps | +1.363 |
Medic | +1.281 |
ombo | +1.256 |
ggle | +1.242 |
rals | +1.166 |
Neg logit contributions | |
retard | -1.128 |
strip | -0.973 |
lesbians | -0.903 |
LS | -0.828 |
rebellious | -0.822 |
Token | Department |
Token ID | 2732 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
retard | +0.487 |
strip | +0.423 |
lesbians | +0.399 |
LS | +0.370 |
rebellious | +0.370 |
Neg logit contributions | |
haps | -0.474 |
Medic | -0.453 |
ombo | -0.436 |
ggle | -0.432 |
Kappa | -0.405 |
Token | of |
Token ID | 286 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
retard | +1.422 |
strip | +1.226 |
lesbians | +1.132 |
LS | +1.036 |
rebellious | +1.029 |
Neg logit contributions | |
haps | -1.769 |
Medic | -1.660 |
ombo | -1.627 |
ggle | -1.610 |
rals | -1.513 |
Token | Defense |
Token ID | 5947 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
haps | +0.068 |
Medic | +0.065 |
ombo | +0.063 |
ggle | +0.062 |
Kappa | +0.058 |
Neg logit contributions | |
retard | -0.072 |
strip | -0.063 |
lesbians | -0.059 |
LS | -0.055 |
rebellious | -0.054 |
Token | Africa |
Token ID | 5478 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
haps | +0.276 |
Medic | +0.266 |
ombo | +0.253 |
ggle | +0.252 |
Kappa | +0.235 |
Neg logit contributions | |
retard | -0.302 |
strip | -0.264 |
lesbians | -0.253 |
rebellious | -0.234 |
clean | -0.234 |
Token | Command |
Token ID | 9455 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
haps | +0.048 |
Medic | +0.046 |
ombo | +0.044 |
ggle | +0.043 |
Kappa | +0.041 |
Neg logit contributions | |
retard | -0.056 |
strip | -0.049 |
lesbians | -0.047 |
rebellious | -0.044 |
LS | -0.044 |
Token | website |
Token ID | 3052 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
haps | +2.553 |
Medic | +2.546 |
ombo | +2.376 |
ggle | +2.352 |
rals | +2.216 |
Neg logit contributions | |
retard | -2.849 |
strip | -2.454 |
lesbians | -2.386 |
rebellious | -2.220 |
clean | -2.216 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
haps | +1.189 |
Medic | +1.125 |
ombo | +1.074 |
ggle | +1.060 |
Kappa | +0.999 |
Neg logit contributions | |
retard | -1.287 |
strip | -1.120 |
lesbians | -1.068 |
clean | -0.991 |
rebellious | -0.988 |
Token | the |
Token ID | 262 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
haps | +0.164 |
Medic | +0.156 |
ombo | +0.150 |
ggle | +0.147 |
Kappa | +0.140 |
Neg logit contributions | |
retard | -0.158 |
strip | -0.137 |
lesbians | -0.127 |
clean | -0.120 |
LS | -0.118 |
Token | United |
Token ID | 1578 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
haps | +0.427 |
Medic | +0.413 |
ombo | +0.395 |
ggle | +0.389 |
Kappa | +0.373 |
Neg logit contributions | |
retard | -0.381 |
strip | -0.327 |
lesbians | -0.302 |
clean | -0.288 |
LS | -0.280 |
Token | States |
Token ID | 1829 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
haps | +1.754 |
Medic | +1.658 |
ombo | +1.621 |
ggle | +1.597 |
rals | +1.512 |
Neg logit contributions | |
retard | -1.403 |
strip | -1.209 |
lesbians | -1.112 |
LS | -1.017 |
clean | -1.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
haps | +0.212 |
Medic | +0.199 |
ombo | +0.194 |
ggle | +0.192 |
Kappa | +0.181 |
Neg logit contributions | |
retard | -0.175 |
strip | -0.151 |
lesbians | -0.140 |
LS | -0.128 |
rebellious | -0.128 |
Token | Snap |
Token ID | 16026 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
haps | +0.452 |
Medic | +0.422 |
ombo | +0.403 |
ggle | +0.398 |
Kappa | +0.368 |
Neg logit contributions | |
retard | -0.640 |
strip | -0.568 |
lesbians | -0.542 |
rebellious | -0.504 |
clean | -0.504 |
Token | on |
Token ID | 319 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
haps | +0.406 |
Medic | +0.380 |
ombo | +0.371 |
ggle | +0.366 |
rals | +0.343 |
Neg logit contributions | |
retard | -0.371 |
strip | -0.319 |
lesbians | -0.300 |
rebellious | -0.276 |
LS | -0.275 |
Token | Ubuntu |
Token ID | 14949 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
haps | +0.276 |
Medic | +0.260 |
ombo | +0.251 |
ggle | +0.248 |
Kappa | +0.232 |
Neg logit contributions | |
retard | -0.291 |
strip | -0.253 |
lesbians | -0.237 |
clean | -0.220 |
LS | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
haps | +1.076 |
Medic | +1.031 |
ombo | +0.981 |
ggle | +0.970 |
Kappa | +0.922 |
Neg logit contributions | |
retard | -1.078 |
strip | -0.924 |
lesbians | -0.871 |
clean | -0.801 |
rebellious | -0.799 |
Token | Fedora |
Token ID | 32245 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
haps | +0.771 |
Medic | +0.702 |
ombo | +0.665 |
ggle | +0.657 |
Kappa | +0.593 |
Neg logit contributions | |
retard | -1.450 |
strip | -1.297 |
lesbians | -1.251 |
LS | -1.175 |
rebellious | -1.174 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
haps | +2.754 |
Medic | +2.618 |
ombo | +2.509 |
ggle | +2.431 |
Kappa | +2.346 |
Neg logit contributions | |
retard | -2.837 |
strip | -2.401 |
lesbians | -2.294 |
LS | -2.118 |
susp | -2.114 |
Token | see |
Token ID | 766 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
haps | +0.498 |
Medic | +0.459 |
ggle | +0.440 |
ombo | +0.435 |
Kappa | +0.392 |
Neg logit contributions | |
retard | -0.877 |
strip | -0.780 |
lesbians | -0.755 |
clean | -0.714 |
rebellious | -0.713 |
Token | how |
Token ID | 703 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
haps | +1.382 |
Medic | +1.304 |
ombo | +1.257 |
ggle | +1.251 |
Kappa | +1.169 |
Neg logit contributions | |
retard | -1.470 |
strip | -1.277 |
lesbians | -1.204 |
clean | -1.125 |
LS | -1.115 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
retard | +0.759 |
strip | +0.654 |
lesbians | +0.610 |
clean | +0.559 |
LS | +0.559 |
Neg logit contributions | |
haps | -0.876 |
Medic | -0.826 |
ombo | -0.802 |
ggle | -0.795 |
Kappa | -0.744 |
Token | experiences |
Token ID | 6461 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
retard | +0.140 |
strip | +0.121 |
lesbians | +0.114 |
clean | +0.105 |
LS | +0.104 |
Neg logit contributions | |
haps | -0.146 |
Medic | -0.140 |
ombo | -0.135 |
ggle | -0.133 |
Kappa | -0.126 |
Token | cuts |
Token ID | 6630 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
haps | +0.321 |
Medic | +0.312 |
ombo | +0.296 |
ggle | +0.288 |
Kappa | +0.273 |
Neg logit contributions | |
retard | -0.307 |
strip | -0.266 |
lesbians | -0.253 |
LS | -0.232 |
clean | -0.232 |
Token | that |
Token ID | 326 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
retard | +1.045 |
strip | +0.908 |
lesbians | +0.861 |
clean | +0.790 |
LS | +0.785 |
Neg logit contributions | |
haps | -1.184 |
Medic | -1.111 |
ombo | -1.082 |
ggle | -1.060 |
rals | -1.003 |
Token | have |
Token ID | 423 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
retard | +0.123 |
strip | +0.107 |
lesbians | +0.101 |
clean | +0.094 |
LS | +0.092 |
Neg logit contributions | |
haps | -0.139 |
Medic | -0.131 |
ombo | -0.125 |
ggle | -0.123 |
Kappa | -0.116 |
Token | already |
Token ID | 1541 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
retard | +0.898 |
strip | +0.798 |
lesbians | +0.758 |
clean | +0.711 |
LS | +0.708 |
Neg logit contributions | |
haps | -0.694 |
Medic | -0.637 |
ombo | -0.624 |
ggle | -0.610 |
Kappa | -0.564 |
Token | been |
Token ID | 587 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
haps | +0.045 |
Medic | +0.041 |
ombo | +0.040 |
ggle | +0.040 |
Kappa | +0.036 |
Neg logit contributions | |
retard | -0.063 |
strip | -0.056 |
lesbians | -0.054 |
clean | -0.051 |
LS | -0.051 |
Token | introduced |
Token ID | 5495 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
retard | +0.856 |
strip | +0.741 |
lesbians | +0.703 |
clean | +0.650 |
LS | +0.644 |
Neg logit contributions | |
haps | -0.912 |
Medic | -0.846 |
ombo | -0.828 |
ggle | -0.816 |
ounced | -0.763 |
Token | will |
Token ID | 481 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
haps | +0.356 |
Medic | +0.332 |
ombo | +0.321 |
ggle | +0.321 |
rals | +0.299 |
Neg logit contributions | |
retard | -0.353 |
strip | -0.306 |
lesbians | -0.294 |
LS | -0.273 |
clean | -0.272 |
Token | begin |
Token ID | 2221 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
retard | +0.287 |
strip | +0.247 |
lesbians | +0.242 |
rebellious | +0.225 |
LS | +0.224 |
Neg logit contributions | |
haps | -0.305 |
Medic | -0.278 |
ombo | -0.276 |
ggle | -0.272 |
rals | -0.252 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
retard | +0.620 |
strip | +0.540 |
lesbians | +0.513 |
clean | +0.478 |
rebellious | +0.478 |
Neg logit contributions | |
haps | -0.568 |
Medic | -0.529 |
ombo | -0.515 |
ggle | -0.505 |
rals | -0.476 |
Token | take |
Token ID | 1011 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
retard | +0.955 |
strip | +0.825 |
lesbians | +0.794 |
LS | +0.732 |
rebellious | +0.731 |
Neg logit contributions | |
haps | -1.043 |
Medic | -0.966 |
ombo | -0.948 |
ggle | -0.942 |
Kappa | -0.876 |
Token | effect |
Token ID | 1245 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
retard | +0.713 |
strip | +0.615 |
lesbians | +0.577 |
clean | +0.543 |
LS | +0.529 |
Neg logit contributions | |
haps | -0.794 |
Medic | -0.751 |
ombo | -0.727 |
ggle | -0.724 |
rals | -0.679 |
Token | British |
Token ID | 3517 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
retard | +0.079 |
strip | +0.068 |
lesbians | +0.064 |
clean | +0.061 |
susp | +0.059 |
Neg logit contributions | |
haps | -0.087 |
Medic | -0.085 |
ombo | -0.080 |
ggle | -0.079 |
Kappa | -0.076 |
Token | Columbia |
Token ID | 9309 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
haps | +0.031 |
Medic | +0.030 |
ombo | +0.028 |
ggle | +0.027 |
Kappa | +0.026 |
Neg logit contributions | |
retard | -0.033 |
strip | -0.028 |
lesbians | -0.027 |
clean | -0.026 |
susp | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
retard | +1.106 |
strip | +0.943 |
lesbians | +0.893 |
clean | +0.832 |
LS | +0.831 |
Neg logit contributions | |
haps | -1.176 |
Medic | -1.130 |
ombo | -1.071 |
ggle | -1.056 |
Kappa | -1.007 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
retard | +0.880 |
strip | +0.760 |
lesbians | +0.709 |
clean | +0.657 |
LS | +0.651 |
Neg logit contributions | |
haps | -0.951 |
Medic | -0.896 |
ombo | -0.865 |
ggle | -0.844 |
Kappa | -0.807 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
haps | +0.129 |
Medic | +0.122 |
ombo | +0.117 |
ggle | +0.114 |
rals | +0.110 |
Neg logit contributions | |
retard | -0.126 |
strip | -0.109 |
lesbians | -0.104 |
LS | -0.095 |
clean | -0.095 |
Token | 25 |
Token ID | 1679 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
retard | +0.688 |
strip | +0.596 |
lesbians | +0.561 |
LS | +0.524 |
clean | +0.517 |
Neg logit contributions | |
haps | -0.690 |
Medic | -0.651 |
ombo | -0.619 |
ggle | -0.615 |
Kappa | -0.589 |
Token | years |
Token ID | 812 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
haps | +0.367 |
Medic | +0.348 |
ombo | +0.335 |
ggle | +0.327 |
rals | +0.311 |
Neg logit contributions | |
retard | -0.312 |
strip | -0.265 |
lesbians | -0.253 |
clean | -0.235 |
LS | -0.233 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
retard | +0.360 |
strip | +0.315 |
lesbians | +0.294 |
clean | +0.271 |
LS | +0.271 |
Neg logit contributions | |
haps | -0.415 |
Medic | -0.391 |
ombo | -0.383 |
ggle | -0.376 |
Kappa | -0.357 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
haps | +0.860 |
Medic | +0.803 |
ombo | +0.777 |
ggle | +0.761 |
Kappa | +0.723 |
Neg logit contributions | |
retard | -0.855 |
strip | -0.739 |
lesbians | -0.694 |
LS | -0.655 |
clean | -0.646 |
Token | when |
Token ID | 618 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
retard | +0.050 |
strip | +0.042 |
lesbians | +0.039 |
clean | +0.036 |
LS | +0.036 |
Neg logit contributions | |
haps | -0.059 |
Medic | -0.056 |
ombo | -0.054 |
ggle | -0.053 |
Kappa | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
retard | +0.269 |
strip | +0.231 |
lesbians | +0.214 |
clean | +0.204 |
LS | +0.202 |
Neg logit contributions | |
haps | -0.287 |
Medic | -0.270 |
ombo | -0.258 |
ggle | -0.254 |
Kappa | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
haps | +0.508 |
Medic | +0.477 |
ombo | +0.458 |
ggle | +0.457 |
Kappa | +0.432 |
Neg logit contributions | |
retard | -0.462 |
strip | -0.397 |
lesbians | -0.376 |
LS | -0.351 |
rebellious | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
haps | +0.405 |
Medic | +0.398 |
ggle | +0.364 |
ombo | +0.359 |
Kappa | +0.348 |
Neg logit contributions | |
retard | -0.501 |
strip | -0.434 |
lesbians | -0.418 |
rebellious | -0.393 |
clean | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
retard | +0.485 |
strip | +0.431 |
lesbians | +0.407 |
rebellious | +0.382 |
LS | +0.379 |
Neg logit contributions | |
haps | -0.368 |
Medic | -0.342 |
ombo | -0.329 |
ggle | -0.327 |
Kappa | -0.302 |
Token | That |
Token ID | 2504 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
retard | +0.411 |
strip | +0.356 |
lesbians | +0.336 |
rebellious | +0.312 |
LS | +0.307 |
Neg logit contributions | |
haps | -0.411 |
Medic | -0.386 |
ggle | -0.372 |
ombo | -0.370 |
rals | -0.346 |
Token | said |
Token ID | 531 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
retard | +0.470 |
strip | +0.410 |
lesbians | +0.389 |
LS | +0.360 |
rebellious | +0.358 |
Neg logit contributions | |
haps | -0.459 |
Medic | -0.429 |
ombo | -0.414 |
ggle | -0.412 |
rals | -0.384 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
retard | +0.789 |
strip | +0.693 |
lesbians | +0.636 |
LS | +0.589 |
rebellious | +0.583 |
Neg logit contributions | |
haps | -0.874 |
Medic | -0.816 |
ombo | -0.808 |
ggle | -0.794 |
rals | -0.743 |
Token | books |
Token ID | 3835 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
haps | +0.121 |
Medic | +0.115 |
ggle | +0.109 |
ombo | +0.109 |
Kappa | +0.103 |
Neg logit contributions | |
retard | -0.117 |
strip | -0.099 |
lesbians | -0.095 |
rebellious | -0.087 |
clean | -0.087 |
Token | raise |
Token ID | 5298 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
haps | +0.209 |
Medic | +0.194 |
ggle | +0.187 |
ombo | +0.185 |
Kappa | +0.174 |
Neg logit contributions | |
retard | -0.204 |
strip | -0.177 |
lesbians | -0.170 |
LS | -0.159 |
rebellious | -0.157 |
Token | very |
Token ID | 845 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
haps | +0.722 |
Medic | +0.680 |
ggle | +0.647 |
ombo | +0.638 |
rals | +0.603 |
Neg logit contributions | |
retard | -0.828 |
strip | -0.720 |
lesbians | -0.685 |
clean | -0.649 |
LS | -0.635 |
Token | special |
Token ID | 2041 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
haps | +0.469 |
Medic | +0.447 |
ggle | +0.420 |
ombo | +0.416 |
rals | +0.391 |
Neg logit contributions | |
retard | -0.534 |
strip | -0.465 |
lesbians | -0.444 |
clean | -0.412 |
LS | -0.412 |
Token | privacy |
Token ID | 6782 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
haps | +1.209 |
Medic | +1.148 |
ggle | +1.080 |
ombo | +1.077 |
rals | +1.027 |
Neg logit contributions | |
retard | -1.362 |
strip | -1.180 |
lesbians | -1.135 |
clean | -1.066 |
LS | -1.053 |
Token | t |
Token ID | 83 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
retard | +0.823 |
strip | +0.748 |
lesbians | +0.722 |
rebellious | +0.685 |
LS | +0.679 |
Neg logit contributions | |
haps | -0.366 |
Medic | -0.317 |
ggle | -0.311 |
ombo | -0.304 |
rals | -0.275 |
Token | proposing |
Token ID | 24634 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
haps | +0.296 |
Medic | +0.277 |
ombo | +0.267 |
ggle | +0.264 |
Kappa | +0.251 |
Neg logit contributions | |
retard | -0.271 |
strip | -0.234 |
lesbians | -0.219 |
LS | -0.203 |
clean | -0.203 |
Token | wildly |
Token ID | 20278 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
retard | +1.473 |
strip | +1.289 |
lesbians | +1.210 |
LS | +1.118 |
rebellious | +1.112 |
Neg logit contributions | |
haps | -1.472 |
Medic | -1.375 |
ombo | -1.336 |
ggle | -1.321 |
rals | -1.239 |
Token | unaff |
Token ID | 25312 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
retard | +0.658 |
strip | +0.578 |
lesbians | +0.550 |
LS | +0.503 |
clean | +0.497 |
Neg logit contributions | |
haps | -0.641 |
Medic | -0.600 |
ombo | -0.580 |
ggle | -0.577 |
Kappa | -0.536 |
Token | ordable |
Token ID | 16819 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
haps | +0.841 |
Medic | +0.714 |
ombo | +0.706 |
ggle | +0.685 |
rals | +0.612 |
Neg logit contributions | |
retard | -1.945 |
strip | -1.794 |
lesbians | -1.714 |
rebellious | -1.619 |
LS | -1.614 |
Token | stuff |
Token ID | 3404 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
haps | +0.289 |
Medic | +0.274 |
ombo | +0.259 |
ggle | +0.258 |
rals | +0.244 |
Neg logit contributions | |
retard | -0.297 |
strip | -0.261 |
lesbians | -0.248 |
rebellious | -0.228 |
LS | -0.228 |
Token | ; |
Token ID | 26 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
haps | +0.807 |
Medic | +0.746 |
ombo | +0.718 |
ggle | +0.713 |
Kappa | +0.679 |
Neg logit contributions | |
retard | -0.798 |
strip | -0.701 |
lesbians | -0.659 |
LS | -0.621 |
rebellious | -0.611 |
Token | Bernie |
Token ID | 10477 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
retard | +1.828 |
strip | +1.605 |
lesbians | +1.509 |
LS | +1.400 |
clean | +1.398 |
Neg logit contributions | |
haps | -1.766 |
Medic | -1.646 |
ombo | -1.582 |
ggle | -1.565 |
Kappa | -1.477 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
haps | +1.114 |
Medic | +1.065 |
ggle | +1.002 |
ombo | +0.991 |
rals | +0.952 |
Neg logit contributions | |
retard | -1.267 |
strip | -1.098 |
lesbians | -1.051 |
clean | -1.001 |
LS | -0.985 |
Token | hasn |
Token ID | 5818 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
haps | +1.062 |
Medic | +0.986 |
ombo | +0.942 |
ggle | +0.925 |
Kappa | +0.876 |
Neg logit contributions | |
retard | -1.184 |
strip | -1.042 |
lesbians | -0.985 |
LS | -0.928 |
rebellious | -0.916 |
Token | � |
Token ID | 447 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
retard | +1.606 |
strip | +1.420 |
lesbians | +1.334 |
rebellious | +1.241 |
LS | +1.240 |
Neg logit contributions | |
haps | -1.386 |
Medic | -1.286 |
ombo | -1.252 |
ggle | -1.238 |
rals | -1.152 |
Token | box |
Token ID | 3524 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
haps | +0.505 |
Medic | +0.471 |
ggle | +0.461 |
ombo | +0.458 |
Kappa | +0.423 |
Neg logit contributions | |
retard | -0.549 |
strip | -0.479 |
lesbians | -0.454 |
LS | -0.418 |
rebellious | -0.418 |
Token | How |
Token ID | 1374 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
haps | +0.216 |
Medic | +0.204 |
ombo | +0.198 |
ggle | +0.196 |
Kappa | +0.184 |
Neg logit contributions | |
retard | -0.224 |
strip | -0.194 |
lesbians | -0.184 |
rebellious | -0.169 |
clean | -0.169 |
Token | - |
Token ID | 12 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
retard | +1.110 |
strip | +0.972 |
lesbians | +0.911 |
LS | +0.838 |
rebellious | +0.835 |
Neg logit contributions | |
haps | -1.086 |
Medic | -1.019 |
ombo | -0.995 |
ggle | -0.992 |
rals | -0.914 |
Token | To |
Token ID | 2514 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
haps | +0.044 |
Medic | +0.041 |
ombo | +0.040 |
ggle | +0.039 |
Kappa | +0.036 |
Neg logit contributions | |
retard | -0.057 |
strip | -0.051 |
lesbians | -0.048 |
LS | -0.045 |
rebellious | -0.045 |
Token | page |
Token ID | 2443 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
retard | +1.908 |
strip | +1.680 |
lesbians | +1.579 |
LS | +1.466 |
rebellious | +1.463 |
Neg logit contributions | |
haps | -1.701 |
Medic | -1.585 |
ombo | -1.541 |
ggle | -1.524 |
Kappa | -1.413 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
retard | +1.736 |
strip | +1.516 |
lesbians | +1.425 |
rebellious | +1.322 |
LS | +1.315 |
Neg logit contributions | |
haps | -1.639 |
Medic | -1.531 |
ombo | -1.492 |
ggle | -1.469 |
Kappa | -1.371 |
Token |
|
Token ID | 198 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
haps | +0.599 |
Medic | +0.561 |
ombo | +0.532 |
ggle | +0.532 |
Kappa | +0.492 |
Neg logit contributions | |
retard | -0.875 |
strip | -0.773 |
lesbians | -0.737 |
rebellious | -0.701 |
LS | -0.684 |
Token | another |
Token ID | 29214 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
haps | +0.207 |
Medic | +0.189 |
ombo | +0.188 |
ggle | +0.186 |
rals | +0.171 |
Neg logit contributions | |
retard | -0.223 |
strip | -0.196 |
lesbians | -0.183 |
LS | -0.169 |
rebellious | -0.168 |
Token | informative |
Token ID | 30304 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
retard | +0.821 |
strip | +0.714 |
lesbians | +0.679 |
LS | +0.614 |
clean | +0.612 |
Neg logit contributions | |
haps | -0.848 |
Medic | -0.794 |
ombo | -0.772 |
ggle | -0.769 |
Kappa | -0.712 |
Token | site |
Token ID | 2524 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
haps | +0.889 |
Medic | +0.846 |
ombo | +0.813 |
ggle | +0.806 |
Kappa | +0.757 |
Neg logit contributions | |
retard | -0.817 |
strip | -0.695 |
lesbians | -0.671 |
clean | -0.608 |
rebellious | -0.604 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
haps | +0.068 |
Medic | +0.064 |
ombo | +0.062 |
ggle | +0.062 |
Kappa | +0.058 |
Neg logit contributions | |
retard | -0.064 |
strip | -0.055 |
lesbians | -0.052 |
rebellious | -0.048 |
LS | -0.048 |
Token | mortgage |
Token ID | 13682 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
retard | +0.016 |
strip | +0.014 |
lesbians | +0.013 |
clean | +0.012 |
susp | +0.012 |
Neg logit contributions | |
haps | -0.015 |
Medic | -0.014 |
ombo | -0.014 |
ggle | -0.014 |
Kappa | -0.013 |
Token | money |
Token ID | 1637 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
retard | +0.191 |
strip | +0.168 |
lesbians | +0.160 |
susp | +0.148 |
clean | +0.148 |
Neg logit contributions | |
haps | -0.180 |
Medic | -0.169 |
ombo | -0.163 |
ggle | -0.163 |
Kappa | -0.153 |
Token | diminish |
Token ID | 29889 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
retard | +0.970 |
strip | +0.835 |
lesbians | +0.796 |
LS | +0.737 |
rebellious | +0.728 |
Neg logit contributions | |
haps | -1.115 |
Medic | -1.047 |
ombo | -1.018 |
ggle | -1.001 |
Kappa | -0.947 |
Token | to |
Token ID | 284 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
haps | +0.190 |
Medic | +0.180 |
ombo | +0.173 |
ggle | +0.172 |
Kappa | +0.164 |
Neg logit contributions | |
retard | -0.179 |
strip | -0.157 |
lesbians | -0.149 |
clean | -0.139 |
LS | -0.137 |
Token | what |
Token ID | 644 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
haps | +1.003 |
Medic | +0.944 |
ombo | +0.912 |
ggle | +0.901 |
Kappa | +0.852 |
Neg logit contributions | |
retard | -0.971 |
strip | -0.837 |
lesbians | -0.804 |
susp | -0.747 |
clean | -0.746 |
Token | the |
Token ID | 262 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
haps | +0.976 |
Medic | +0.913 |
ombo | +0.867 |
ggle | +0.862 |
Kappa | +0.816 |
Neg logit contributions | |
retard | -1.063 |
strip | -0.930 |
lesbians | -0.882 |
clean | -0.825 |
susp | -0.815 |
Token | private |
Token ID | 2839 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
retard | +0.375 |
strip | +0.324 |
lesbians | +0.305 |
clean | +0.285 |
susp | +0.281 |
Neg logit contributions | |
haps | -0.402 |
Medic | -0.385 |
ombo | -0.367 |
ggle | -0.362 |
Kappa | -0.347 |
Token | debt |
Token ID | 5057 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
retard | +0.080 |
strip | +0.069 |
lesbians | +0.067 |
clean | +0.062 |
rebellious | +0.062 |
Neg logit contributions | |
haps | -0.068 |
Medic | -0.065 |
ggle | -0.062 |
ombo | -0.062 |
Kappa | -0.058 |
Token | market |
Token ID | 1910 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
haps | +0.060 |
Medic | +0.057 |
ombo | +0.055 |
ggle | +0.054 |
Kappa | +0.051 |
Neg logit contributions | |
retard | -0.059 |
strip | -0.051 |
lesbians | -0.048 |
clean | -0.046 |
susp | -0.045 |
Token | would |
Token ID | 561 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
retard | +0.697 |
strip | +0.604 |
lesbians | +0.572 |
clean | +0.535 |
LS | +0.534 |
Neg logit contributions | |
haps | -0.683 |
Medic | -0.643 |
ggle | -0.623 |
ombo | -0.619 |
Kappa | -0.578 |
Token | support |
Token ID | 1104 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
retard | +0.690 |
strip | +0.591 |
lesbians | +0.574 |
LS | +0.534 |
rebellious | +0.534 |
Neg logit contributions | |
haps | -0.718 |
Medic | -0.662 |
ggle | -0.649 |
ombo | -0.643 |
Kappa | -0.601 |
Token | way |
Token ID | 835 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
retard | +1.002 |
strip | +0.855 |
lesbians | +0.809 |
LS | +0.745 |
clean | +0.743 |
Neg logit contributions | |
haps | -1.130 |
Medic | -1.081 |
ombo | -1.041 |
ggle | -1.027 |
Kappa | -0.975 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
retard | +0.527 |
strip | +0.452 |
lesbians | +0.427 |
LS | +0.396 |
rebellious | +0.390 |
Neg logit contributions | |
haps | -0.555 |
Medic | -0.519 |
ombo | -0.509 |
ggle | -0.505 |
Kappa | -0.474 |
Token | Their |
Token ID | 5334 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Medic | +0.159 |
haps | +0.158 |
ggle | +0.145 |
ombo | +0.144 |
Kappa | +0.141 |
Neg logit contributions | |
retard | -0.172 |
strip | -0.146 |
lesbians | -0.140 |
rebellious | -0.131 |
clean | -0.129 |
Token | success |
Token ID | 1943 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
haps | +0.196 |
Medic | +0.187 |
ombo | +0.181 |
ggle | +0.176 |
Kappa | +0.167 |
Neg logit contributions | |
retard | -0.201 |
strip | -0.173 |
lesbians | -0.165 |
clean | -0.153 |
LS | -0.152 |
Token | has |
Token ID | 468 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
retard | +1.121 |
strip | +0.981 |
lesbians | +0.931 |
LS | +0.866 |
clean | +0.863 |
Neg logit contributions | |
haps | -1.022 |
Medic | -0.947 |
ombo | -0.926 |
ggle | -0.914 |
Kappa | -0.857 |
Token | generally |
Token ID | 4143 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
haps | +0.430 |
Medic | +0.400 |
ombo | +0.390 |
ggle | +0.384 |
Kappa | +0.360 |
Neg logit contributions | |
retard | -0.490 |
strip | -0.429 |
lesbians | -0.407 |
clean | -0.384 |
LS | -0.379 |
Token | come |
Token ID | 1282 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
retard | +0.659 |
strip | +0.587 |
lesbians | +0.556 |
clean | +0.523 |
LS | +0.522 |
Neg logit contributions | |
haps | -0.498 |
Medic | -0.456 |
ombo | -0.446 |
ggle | -0.438 |
Kappa | -0.406 |
Token | against |
Token ID | 1028 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
retard | +0.839 |
strip | +0.719 |
lesbians | +0.672 |
LS | +0.620 |
rebellious | +0.613 |
Neg logit contributions | |
haps | -1.019 |
Medic | -0.955 |
ombo | -0.943 |
ggle | -0.937 |
Kappa | -0.876 |
Token | sides |
Token ID | 5389 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
retard | +1.129 |
strip | +0.973 |
lesbians | +0.915 |
clean | +0.858 |
LS | +0.845 |
Neg logit contributions | |
haps | -1.182 |
Medic | -1.129 |
ombo | -1.089 |
ggle | -1.071 |
Kappa | -1.012 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
retard | +0.031 |
strip | +0.026 |
lesbians | +0.025 |
clean | +0.023 |
LS | +0.022 |
Neg logit contributions | |
haps | -0.037 |
Medic | -0.035 |
ombo | -0.034 |
ggle | -0.034 |
Kappa | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
haps | +0.083 |
Medic | +0.079 |
ombo | +0.077 |
ggle | +0.076 |
Kappa | +0.071 |
Neg logit contributions | |
retard | -0.073 |
strip | -0.062 |
lesbians | -0.058 |
clean | -0.054 |
LS | -0.054 |
Token | � |
Token ID | 247 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
retard | +0.598 |
strip | +0.506 |
lesbians | +0.466 |
LS | +0.419 |
clean | +0.417 |
Neg logit contributions | |
haps | -0.864 |
Medic | -0.812 |
ombo | -0.796 |
ggle | -0.793 |
�� | -0.755 |
Token | s |
Token ID | 82 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
retard | +0.281 |
strip | +0.246 |
lesbians | +0.231 |
rebellious | +0.213 |
LS | +0.213 |
Neg logit contributions | |
haps | -0.277 |
Medic | -0.258 |
ombo | -0.250 |
ggle | -0.250 |
rals | -0.233 |
Token | partners |
Token ID | 4887 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
haps | +0.724 |
Medic | +0.679 |
ombo | +0.648 |
ggle | +0.636 |
Kappa | +0.607 |
Neg logit contributions | |
retard | -0.851 |
strip | -0.750 |
lesbians | -0.714 |
clean | -0.663 |
LS | -0.661 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
haps | +0.605 |
Medic | +0.568 |
ombo | +0.549 |
ggle | +0.546 |
Kappa | +0.514 |
Neg logit contributions | |
retard | -0.553 |
strip | -0.479 |
lesbians | -0.450 |
LS | -0.415 |
clean | -0.412 |
Token | � |
Token ID | 564 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
haps | +0.934 |
Medic | +0.869 |
ggle | +0.829 |
ombo | +0.825 |
Kappa | +0.778 |
Neg logit contributions | |
retard | -1.097 |
strip | -0.959 |
lesbians | -0.912 |
LS | -0.851 |
susp | -0.850 |
Token | � |
Token ID | 250 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
haps | +0.247 |
Medic | +0.220 |
ggle | +0.215 |
ombo | +0.213 |
�� | +0.206 |
Neg logit contributions | |
retard | -0.380 |
strip | -0.341 |
lesbians | -0.323 |
LS | -0.302 |
clean | -0.301 |
Token | s |
Token ID | 82 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
retard | +0.117 |
strip | +0.103 |
lesbians | +0.096 |
LS | +0.089 |
rebellious | +0.088 |
Neg logit contributions | |
haps | -0.116 |
Medic | -0.107 |
ombo | -0.104 |
ggle | -0.104 |
rals | -0.096 |
Token | ustain |
Token ID | 19542 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
haps | +0.185 |
Medic | +0.167 |
ombo | +0.162 |
ggle | +0.161 |
Kappa | +0.151 |
Neg logit contributions | |
retard | -0.211 |
strip | -0.186 |
lesbians | -0.174 |
LS | -0.165 |
clean | -0.161 |
Token | ability |
Token ID | 1799 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
retard | +1.730 |
strip | +1.549 |
lesbians | +1.466 |
LS | +1.374 |
rebellious | +1.371 |
Neg logit contributions | |
haps | -1.223 |
Medic | -1.128 |
ombo | -1.093 |
ggle | -1.082 |
rals | -1.006 |
Token | of |
Token ID | 286 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
retard | +0.513 |
strip | +0.456 |
lesbians | +0.430 |
LS | +0.407 |
rebellious | +0.402 |
Neg logit contributions | |
haps | -0.402 |
Medic | -0.374 |
ombo | -0.359 |
ggle | -0.357 |
Kappa | -0.330 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
retard | +1.254 |
strip | +1.100 |
lesbians | +1.036 |
LS | +0.961 |
clean | +0.953 |
Neg logit contributions | |
haps | -1.153 |
Medic | -1.085 |
ombo | -1.048 |
ggle | -1.040 |
Kappa | -0.967 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
retard | +0.488 |
strip | +0.423 |
lesbians | +0.401 |
LS | +0.370 |
clean | +0.370 |
Neg logit contributions | |
haps | -0.514 |
Medic | -0.489 |
ombo | -0.474 |
ggle | -0.469 |
Kappa | -0.441 |
Token | moved |
Token ID | 3888 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
haps | +0.509 |
Medic | +0.484 |
ombo | +0.467 |
ggle | +0.462 |
Kappa | +0.433 |
Neg logit contributions | |
retard | -0.481 |
strip | -0.415 |
lesbians | -0.399 |
LS | -0.376 |
clean | -0.366 |
Token | more |
Token ID | 517 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
retard | +0.894 |
strip | +0.775 |
lesbians | +0.731 |
LS | +0.679 |
clean | +0.671 |
Neg logit contributions | |
haps | -0.942 |
Medic | -0.890 |
ombo | -0.866 |
ggle | -0.850 |
Kappa | -0.802 |
Token | than |
Token ID | 621 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
haps | +0.374 |
Medic | +0.356 |
ombo | +0.343 |
ggle | +0.332 |
rals | +0.318 |
Neg logit contributions | |
retard | -0.407 |
strip | -0.354 |
lesbians | -0.336 |
LS | -0.317 |
clean | -0.313 |
Token | 430 |
Token ID | 35090 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
haps | +0.967 |
Medic | +0.912 |
ombo | +0.871 |
ggle | +0.857 |
Kappa | +0.827 |
Neg logit contributions | |
retard | -0.933 |
strip | -0.804 |
lesbians | -0.756 |
clean | -0.711 |
LS | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
retard | +0.057 |
strip | +0.049 |
lesbians | +0.047 |
LS | +0.043 |
clean | +0.043 |
Neg logit contributions | |
haps | -0.054 |
Medic | -0.050 |
ombo | -0.049 |
ggle | -0.048 |
rals | -0.045 |
Token | 000 |
Token ID | 830 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
retard | +0.764 |
strip | +0.655 |
lesbians | +0.610 |
LS | +0.563 |
rebellious | +0.562 |
Neg logit contributions | |
haps | -0.898 |
Medic | -0.839 |
ombo | -0.818 |
ggle | -0.810 |
Kappa | -0.766 |
Token | people |
Token ID | 661 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
haps | +0.920 |
Medic | +0.885 |
ombo | +0.853 |
ggle | +0.838 |
Kappa | +0.793 |
Neg logit contributions | |
retard | -0.944 |
strip | -0.808 |
lesbians | -0.763 |
clean | -0.709 |
LS | -0.707 |
Token | from |
Token ID | 422 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
haps | +0.381 |
Medic | +0.357 |
ombo | +0.346 |
ggle | +0.344 |
Kappa | +0.321 |
Neg logit contributions | |
retard | -0.374 |
strip | -0.324 |
lesbians | -0.306 |
LS | -0.287 |
clean | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
retard | +0.154 |
strip | +0.131 |
lesbians | +0.124 |
clean | +0.115 |
LS | +0.114 |
Neg logit contributions | |
haps | -0.162 |
Medic | -0.155 |
ombo | -0.152 |
ggle | -0.146 |
Kappa | -0.139 |
Token | southeast |
Token ID | 26015 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
retard | +0.965 |
strip | +0.811 |
lesbians | +0.774 |
clean | +0.713 |
LS | +0.706 |
Neg logit contributions | |
haps | -1.172 |
Medic | -1.130 |
ombo | -1.093 |
ggle | -1.066 |
Kappa | -1.021 |
Token | how |
Token ID | 703 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
retard | +0.314 |
strip | +0.272 |
lesbians | +0.257 |
clean | +0.237 |
rebellious | +0.236 |
Neg logit contributions | |
haps | -0.319 |
Medic | -0.300 |
ombo | -0.288 |
ggle | -0.287 |
Kappa | -0.269 |
Token | long |
Token ID | 890 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
retard | +1.346 |
strip | +1.172 |
lesbians | +1.096 |
LS | +1.007 |
clean | +1.005 |
Neg logit contributions | |
haps | -1.434 |
Medic | -1.346 |
ombo | -1.314 |
ggle | -1.301 |
rals | -1.215 |
Token | do |
Token ID | 466 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
retard | +2.122 |
strip | +1.861 |
lesbians | +1.744 |
clean | +1.622 |
LS | +1.613 |
Neg logit contributions | |
haps | -2.100 |
Medic | -1.956 |
ombo | -1.904 |
ggle | -1.892 |
rals | -1.768 |
Token | you |
Token ID | 345 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
retard | +1.339 |
strip | +1.170 |
lesbians | +1.087 |
LS | +1.008 |
rebellious | +0.998 |
Neg logit contributions | |
haps | -1.482 |
Medic | -1.383 |
ombo | -1.355 |
ggle | -1.339 |
�� | -1.257 |
Token | feel |
Token ID | 1254 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
retard | +0.939 |
strip | +0.814 |
lesbians | +0.765 |
LS | +0.705 |
clean | +0.703 |
Neg logit contributions | |
haps | -1.001 |
Medic | -0.930 |
ombo | -0.914 |
ggle | -0.908 |
rals | -0.845 |
Token | it |
Token ID | 340 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
haps | +0.267 |
Medic | +0.254 |
ombo | +0.244 |
ggle | +0.242 |
Kappa | +0.226 |
Neg logit contributions | |
retard | -0.269 |
strip | -0.233 |
lesbians | -0.219 |
clean | -0.204 |
rebellious | -0.200 |
Token | will |
Token ID | 481 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
retard | +0.868 |
strip | +0.766 |
lesbians | +0.720 |
LS | +0.670 |
clean | +0.668 |
Neg logit contributions | |
haps | -0.762 |
Medic | -0.704 |
ombo | -0.688 |
ggle | -0.679 |
rals | -0.631 |
Token | take |
Token ID | 1011 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
retard | +0.399 |
strip | +0.343 |
lesbians | +0.322 |
clean | +0.298 |
rebellious | +0.296 |
Neg logit contributions | |
haps | -0.485 |
Medic | -0.450 |
ombo | -0.442 |
ggle | -0.437 |
Kappa | -0.411 |
Token | to |
Token ID | 284 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
haps | +0.511 |
Medic | +0.481 |
ombo | +0.465 |
ggle | +0.462 |
rals | +0.432 |
Neg logit contributions | |
retard | -0.557 |
strip | -0.487 |
lesbians | -0.458 |
clean | -0.430 |
rebellious | -0.423 |
Token | get |
Token ID | 651 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
haps | +0.046 |
Medic | +0.043 |
ggle | +0.042 |
ombo | +0.042 |
Kappa | +0.039 |
Neg logit contributions | |
retard | -0.044 |
strip | -0.038 |
lesbians | -0.036 |
rebellious | -0.033 |
clean | -0.033 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
retard | +0.212 |
strip | +0.181 |
lesbians | +0.170 |
clean | +0.156 |
rebellious | +0.154 |
Neg logit contributions | |
haps | -0.234 |
Medic | -0.222 |
ombo | -0.215 |
ggle | -0.214 |
rals | -0.200 |
Token | WE |
Token ID | 12887 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
haps | +0.621 |
Medic | +0.590 |
ombo | +0.567 |
ggle | +0.559 |
Kappa | +0.529 |
Neg logit contributions | |
retard | -0.590 |
strip | -0.509 |
lesbians | -0.481 |
rebellious | -0.443 |
clean | -0.436 |
Token | ARE |
Token ID | 15986 |
Feature activation | -9.38e-03 |
Pos logit contributions | |
retard | +1.085 |
strip | +0.930 |
lesbians | +0.863 |
rebellious | +0.788 |
clean | +0.787 |
Neg logit contributions | |
haps | -1.362 |
Medic | -1.310 |
ombo | -1.273 |
ggle | -1.269 |
Kappa | -1.199 |
Token | WITH |
Token ID | 13315 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
retard | +0.042 |
strip | +0.036 |
lesbians | +0.034 |
clean | +0.031 |
rebellious | +0.031 |
Neg logit contributions | |
haps | -0.044 |
Medic | -0.042 |
ombo | -0.040 |
ggle | -0.040 |
Kappa | -0.039 |
Token | YOU |
Token ID | 7013 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
haps | +0.415 |
Medic | +0.399 |
ggle | +0.384 |
ombo | +0.377 |
Kappa | +0.366 |
Neg logit contributions | |
retard | -0.459 |
strip | -0.399 |
lesbians | -0.371 |
clean | -0.349 |
rebellious | -0.346 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
retard | +1.086 |
strip | +0.956 |
lesbians | +0.894 |
clean | +0.830 |
rebellious | +0.830 |
Neg logit contributions | |
haps | -0.989 |
Medic | -0.934 |
ombo | -0.904 |
ggle | -0.890 |
Kappa | -0.839 |
Token | GOD |
Token ID | 29562 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
retard | +0.626 |
strip | +0.547 |
lesbians | +0.515 |
rebellious | +0.482 |
clean | +0.479 |
Neg logit contributions | |
haps | -0.544 |
Medic | -0.519 |
ombo | -0.488 |
ggle | -0.487 |
Kappa | -0.465 |
Token | BL |
Token ID | 9878 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
retard | +3.064 |
strip | +2.712 |
lesbians | +2.557 |
rebellious | +2.369 |
LS | +2.365 |
Neg logit contributions | |
haps | -2.639 |
Medic | -2.451 |
ombo | -2.380 |
ggle | -2.355 |
Kappa | -2.192 |
Token | ESS |
Token ID | 7597 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
retard | +1.184 |
strip | +1.031 |
lesbians | +0.960 |
rebellious | +0.884 |
LS | +0.879 |
Neg logit contributions | |
haps | -1.280 |
Medic | -1.204 |
ombo | -1.169 |
ggle | -1.162 |
Kappa | -1.089 |
Token | ! |
Token ID | 0 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
retard | +0.055 |
strip | +0.048 |
lesbians | +0.045 |
clean | +0.042 |
rebellious | +0.042 |
Neg logit contributions | |
haps | -0.049 |
Medic | -0.047 |
ggle | -0.044 |
ombo | -0.044 |
Kappa | -0.043 |
Token | — |
Token ID | 851 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
retard | +0.218 |
strip | +0.195 |
lesbians | +0.186 |
rebellious | +0.175 |
clean | +0.175 |
Neg logit contributions | |
haps | -0.126 |
Medic | -0.118 |
ombo | -0.110 |
ggle | -0.110 |
Kappa | -0.101 |
Token | Donald |
Token ID | 3759 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
haps | +0.430 |
Medic | +0.400 |
ombo | +0.377 |
ggle | +0.367 |
Kappa | +0.350 |
Neg logit contributions | |
retard | -0.671 |
strip | -0.598 |
lesbians | -0.576 |
rebellious | -0.534 |
clean | -0.533 |
Token | them |
Token ID | 606 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
retard | +0.696 |
strip | +0.617 |
lesbians | +0.584 |
clean | +0.543 |
rebellious | +0.539 |
Neg logit contributions | |
haps | -0.588 |
Medic | -0.549 |
ombo | -0.531 |
ggle | -0.519 |
Kappa | -0.487 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
haps | +0.218 |
Medic | +0.205 |
ombo | +0.199 |
ggle | +0.196 |
Kappa | +0.186 |
Neg logit contributions | |
retard | -0.216 |
strip | -0.187 |
lesbians | -0.178 |
LS | -0.163 |
rebellious | -0.162 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
retard | +0.572 |
strip | +0.493 |
lesbians | +0.466 |
rebellious | +0.434 |
clean | +0.427 |
Neg logit contributions | |
haps | -0.560 |
Medic | -0.543 |
ombo | -0.508 |
ggle | -0.507 |
Kappa | -0.486 |
Token | numbering |
Token ID | 47622 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
retard | +0.690 |
strip | +0.594 |
lesbians | +0.565 |
clean | +0.518 |
rebellious | +0.514 |
Neg logit contributions | |
haps | -0.754 |
Medic | -0.715 |
ombo | -0.685 |
ggle | -0.673 |
Kappa | -0.643 |
Token | isn |
Token ID | 2125 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
retard | +0.319 |
strip | +0.274 |
lesbians | +0.263 |
clean | +0.243 |
rebellious | +0.243 |
Neg logit contributions | |
haps | -0.320 |
Medic | -0.301 |
ombo | -0.293 |
ggle | -0.289 |
Kappa | -0.274 |
Token | 't |
Token ID | 470 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
retard | +1.781 |
strip | +1.562 |
lesbians | +1.457 |
LS | +1.350 |
clean | +1.341 |
Neg logit contributions | |
haps | -1.792 |
Medic | -1.668 |
ombo | -1.632 |
ggle | -1.613 |
rals | -1.505 |
Token | part |
Token ID | 636 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
retard | +2.805 |
strip | +2.434 |
lesbians | +2.299 |
LS | +2.117 |
clean | +2.105 |
Neg logit contributions | |
haps | -2.915 |
Medic | -2.736 |
ombo | -2.664 |
ggle | -2.629 |
Kappa | -2.464 |
Token | of |
Token ID | 286 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
retard | +0.373 |
strip | +0.321 |
lesbians | +0.302 |
rebellious | +0.275 |
LS | +0.275 |
Neg logit contributions | |
haps | -0.422 |
Medic | -0.398 |
ombo | -0.385 |
ggle | -0.381 |
Kappa | -0.360 |
Token | styles |
Token ID | 12186 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
haps | +0.161 |
Medic | +0.152 |
ombo | +0.147 |
ggle | +0.144 |
�� | +0.136 |
Neg logit contributions | |
retard | -0.153 |
strip | -0.133 |
lesbians | -0.126 |
rebellious | -0.115 |
clean | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
haps | +0.209 |
Medic | +0.191 |
ombo | +0.189 |
ggle | +0.184 |
Kappa | +0.173 |
Neg logit contributions | |
retard | -0.213 |
strip | -0.183 |
lesbians | -0.175 |
rebellious | -0.163 |
clean | -0.160 |
Token | either |
Token ID | 2035 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
retard | +0.247 |
strip | +0.212 |
lesbians | +0.199 |
clean | +0.183 |
rebellious | +0.183 |
Neg logit contributions | |
haps | -0.294 |
Medic | -0.278 |
ombo | -0.267 |
ggle | -0.266 |
Kappa | -0.253 |
Token | = |
Token ID | 796 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
haps | +0.313 |
Medic | +0.298 |
ombo | +0.280 |
ggle | +0.279 |
Kappa | +0.268 |
Neg logit contributions | |
retard | -0.398 |
strip | -0.349 |
lesbians | -0.334 |
rebellious | -0.314 |
clean | -0.310 |
Token | '. |
Token ID | 45302 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
retard | +0.275 |
strip | +0.239 |
lesbians | +0.229 |
rebellious | +0.212 |
clean | +0.210 |
Neg logit contributions | |
haps | -0.247 |
Medic | -0.233 |
ombo | -0.226 |
ggle | -0.222 |
Kappa | -0.210 |
Token | cl |
Token ID | 565 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
retard | +0.818 |
strip | +0.711 |
lesbians | +0.667 |
rebellious | +0.616 |
LS | +0.613 |
Neg logit contributions | |
haps | -0.836 |
Medic | -0.777 |
ombo | -0.763 |
ggle | -0.754 |
rals | -0.706 |
Token | j |
Token ID | 73 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
retard | +0.549 |
strip | +0.485 |
lesbians | +0.454 |
LS | +0.423 |
rebellious | +0.421 |
Neg logit contributions | |
haps | -0.492 |
Medic | -0.456 |
ombo | -0.445 |
ggle | -0.440 |
rals | -0.408 |
Token | ' |
Token ID | 6 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
haps | +0.075 |
Medic | +0.070 |
ombo | +0.068 |
ggle | +0.068 |
Kappa | +0.064 |
Neg logit contributions | |
retard | -0.066 |
strip | -0.056 |
lesbians | -0.053 |
rebellious | -0.049 |
LS | -0.049 |
Token | OR |
Token ID | 6375 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
retard | +0.347 |
strip | +0.298 |
lesbians | +0.284 |
rebellious | +0.262 |
clean | +0.260 |
Neg logit contributions | |
haps | -0.374 |
Medic | -0.357 |
ombo | -0.341 |
ggle | -0.336 |
Kappa | -0.327 |
Token | RIGHT |
Token ID | 33621 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
retard | +2.855 |
strip | +2.498 |
lesbians | +2.357 |
rebellious | +2.173 |
clean | +2.172 |
Neg logit contributions | |
haps | -2.728 |
Medic | -2.550 |
ombo | -2.484 |
ggle | -2.451 |
Kappa | -2.298 |
Token | ( |
Token ID | 357 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
haps | +1.199 |
Medic | +1.119 |
ombo | +1.096 |
ggle | +1.083 |
rals | +1.013 |
Neg logit contributions | |
retard | -1.123 |
strip | -0.980 |
lesbians | -0.912 |
LS | -0.841 |
rebellious | -0.837 |
Token | path |
Token ID | 3108 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
haps | +0.679 |
Medic | +0.644 |
ombo | +0.625 |
ggle | +0.614 |
Kappa | +0.590 |
Neg logit contributions | |
retard | -0.559 |
strip | -0.468 |
lesbians | -0.449 |
rebellious | -0.409 |
clean | -0.400 |
Token | , |
Token ID | 837 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
retard | +0.218 |
strip | +0.182 |
lesbians | +0.163 |
LS | +0.146 |
clean | +0.144 |
Neg logit contributions | |
haps | -0.391 |
Medic | -0.370 |
ombo | -0.364 |
ggle | -0.361 |
rals | -0.342 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
haps | +1.615 |
Medic | +1.533 |
ombo | +1.468 |
ggle | +1.436 |
Kappa | +1.400 |
Neg logit contributions | |
retard | -1.699 |
strip | -1.460 |
lesbians | -1.412 |
rebellious | -1.310 |
susp | -1.282 |
Token | works |
Token ID | 2499 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
retard | +1.477 |
strip | +1.282 |
lesbians | +1.201 |
rebellious | +1.113 |
LS | +1.104 |
Neg logit contributions | |
haps | -1.612 |
Medic | -1.519 |
ombo | -1.468 |
ggle | -1.452 |
Kappa | -1.373 |
Token | really |
Token ID | 1107 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
retard | +0.196 |
strip | +0.171 |
lesbians | +0.159 |
rebellious | +0.149 |
LS | +0.148 |
Neg logit contributions | |
haps | -0.213 |
Medic | -0.199 |
ombo | -0.195 |
ggle | -0.192 |
Kappa | -0.182 |
Token | really |
Token ID | 1107 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
retard | +0.288 |
strip | +0.254 |
lesbians | +0.238 |
rebellious | +0.222 |
LS | +0.222 |
Neg logit contributions | |
haps | -0.282 |
Medic | -0.262 |
ombo | -0.254 |
ggle | -0.250 |
Kappa | -0.237 |
Token | well |
Token ID | 880 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
retard | +1.022 |
strip | +0.898 |
lesbians | +0.840 |
rebellious | +0.783 |
LS | +0.782 |
Neg logit contributions | |
haps | -1.030 |
Medic | -0.959 |
ombo | -0.930 |
ggle | -0.917 |
Kappa | -0.866 |
Token | . |
Token ID | 764 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
retard | +0.928 |
strip | +0.808 |
lesbians | +0.760 |
rebellious | +0.706 |
LS | +0.694 |
Neg logit contributions | |
haps | -1.029 |
Medic | -0.966 |
ombo | -0.942 |
ggle | -0.924 |
Kappa | -0.877 |
Token | Tape |
Token ID | 40849 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
retard | +1.136 |
strip | +0.974 |
lesbians | +0.921 |
rebellious | +0.855 |
clean | +0.838 |
Neg logit contributions | |
haps | -1.184 |
Medic | -1.131 |
ombo | -1.082 |
ggle | -1.067 |
Kappa | -1.016 |
Token | is |
Token ID | 318 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
retard | +2.907 |
strip | +2.560 |
lesbians | +2.405 |
LS | +2.232 |
rebellious | +2.226 |
Neg logit contributions | |
haps | -2.649 |
Medic | -2.463 |
ombo | -2.406 |
ggle | -2.369 |
rals | -2.207 |
Token | great |
Token ID | 1049 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
retard | +0.593 |
strip | +0.512 |
lesbians | +0.487 |
clean | +0.449 |
LS | +0.446 |
Neg logit contributions | |
haps | -0.610 |
Medic | -0.574 |
ombo | -0.557 |
ggle | -0.546 |
Kappa | -0.516 |
Token | because |
Token ID | 780 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
retard | +1.660 |
strip | +1.449 |
lesbians | +1.367 |
rebellious | +1.257 |
clean | +1.254 |
Neg logit contributions | |
haps | -1.737 |
Medic | -1.635 |
ombo | -1.590 |
ggle | -1.566 |
Kappa | -1.472 |
Token | it |
Token ID | 340 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
retard | +0.835 |
strip | +0.729 |
lesbians | +0.691 |
rebellious | +0.640 |
clean | +0.640 |
Neg logit contributions | |
haps | -0.762 |
Medic | -0.715 |
ombo | -0.695 |
ggle | -0.680 |
Kappa | -0.640 |
Token | � |
Token ID | 447 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
retard | +0.174 |
strip | +0.151 |
lesbians | +0.145 |
rebellious | +0.135 |
LS | +0.135 |
Neg logit contributions | |
haps | -0.153 |
Medic | -0.143 |
ombo | -0.138 |
ggle | -0.136 |
Kappa | -0.128 |
Token | not |
Token ID | 407 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
haps | +1.424 |
Medic | +1.355 |
ombo | +1.285 |
ggle | +1.276 |
Kappa | +1.219 |
Neg logit contributions | |
retard | -1.429 |
strip | -1.224 |
lesbians | -1.152 |
clean | -1.088 |
LS | -1.072 |
Token | quite |
Token ID | 2407 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
retard | +0.805 |
strip | +0.697 |
lesbians | +0.648 |
clean | +0.605 |
LS | +0.604 |
Neg logit contributions | |
haps | -0.864 |
Medic | -0.814 |
ombo | -0.780 |
ggle | -0.778 |
Kappa | -0.736 |
Token | sure |
Token ID | 1654 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
haps | +1.754 |
Medic | +1.680 |
ggle | +1.590 |
ombo | +1.582 |
Kappa | +1.511 |
Neg logit contributions | |
retard | -1.618 |
strip | -1.394 |
lesbians | -1.283 |
susp | -1.215 |
clean | -1.208 |
Token | what |
Token ID | 644 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
retard | +1.316 |
strip | +1.149 |
lesbians | +1.069 |
clean | +0.996 |
LS | +0.992 |
Neg logit contributions | |
haps | -1.324 |
Medic | -1.244 |
ombo | -1.202 |
ggle | -1.191 |
Kappa | -1.120 |
Token | F |
Token ID | 376 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
haps | +0.127 |
Medic | +0.121 |
ombo | +0.116 |
ggle | +0.115 |
Kappa | +0.109 |
Neg logit contributions | |
retard | -0.124 |
strip | -0.107 |
lesbians | -0.100 |
clean | -0.095 |
LS | -0.093 |
Token | UB |
Token ID | 10526 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
retard | +1.283 |
strip | +1.138 |
lesbians | +1.069 |
LS | +0.997 |
rebellious | +0.994 |
Neg logit contributions | |
haps | -1.055 |
Medic | -0.976 |
ombo | -0.951 |
ggle | -0.935 |
�� | -0.865 |
Token | AR |
Token ID | 1503 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
retard | +2.863 |
strip | +2.497 |
lesbians | +2.361 |
rebellious | +2.197 |
clean | +2.193 |
Neg logit contributions | |
haps | -2.817 |
Medic | -2.659 |
ombo | -2.592 |
ggle | -2.553 |
Kappa | -2.398 |
Token | means |
Token ID | 1724 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
retard | +1.381 |
strip | +1.214 |
lesbians | +1.136 |
clean | +1.069 |
rebellious | +1.062 |
Neg logit contributions | |
haps | -1.242 |
Medic | -1.158 |
ombo | -1.112 |
ggle | -1.100 |
Kappa | -1.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
haps | +0.872 |
Medic | +0.821 |
ombo | +0.790 |
ggle | +0.785 |
Kappa | +0.750 |
Neg logit contributions | |
retard | -0.864 |
strip | -0.754 |
lesbians | -0.701 |
LS | -0.661 |
clean | -0.659 |
Token | She |
Token ID | 1375 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
haps | +0.454 |
Medic | +0.439 |
ggle | +0.405 |
ombo | +0.405 |
Kappa | +0.397 |
Neg logit contributions | |
retard | -0.481 |
strip | -0.415 |
lesbians | -0.388 |
rebellious | -0.367 |
clean | -0.362 |
Token | was |
Token ID | 373 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
haps | +0.128 |
Medic | +0.119 |
ggle | +0.115 |
ombo | +0.114 |
Kappa | +0.107 |
Neg logit contributions | |
retard | -0.150 |
strip | -0.131 |
lesbians | -0.123 |
clean | -0.117 |
rebellious | -0.116 |