Token | government |
Token ID | 1230 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
rolet | +0.154 |
orth | +0.148 |
oppy | +0.140 |
NTS | +0.136 |
olls | +0.134 |
Neg logit contributions | |
xual | -0.168 |
menstru | -0.155 |
Bir | -0.145 |
20439 | -0.142 |
pees | -0.141 |
Token | faces |
Token ID | 6698 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
xual | +0.120 |
menstru | +0.114 |
Bir | +0.106 |
pees | +0.104 |
ferment | +0.103 |
Neg logit contributions | |
rolet | -0.099 |
orth | -0.095 |
oppy | -0.088 |
NTS | -0.084 |
olls | -0.084 |
Token | aboriginal |
Token ID | 48328 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
rolet | +1.470 |
orth | +1.415 |
oppy | +1.323 |
NTS | +1.286 |
olls | +1.284 |
Neg logit contributions | |
xual | -1.737 |
menstru | -1.602 |
Bir | -1.520 |
pees | -1.488 |
20439 | -1.479 |
Token | opposition |
Token ID | 5471 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
xual | +1.426 |
menstru | +1.344 |
Bir | +1.247 |
pees | +1.220 |
ferment | +1.219 |
Neg logit contributions | |
rolet | -1.320 |
orth | -1.265 |
oppy | -1.194 |
olls | -1.128 |
NTS | -1.125 |
Token | to |
Token ID | 284 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
xual | +0.768 |
menstru | +0.730 |
Bir | +0.680 |
ferment | +0.666 |
pees | +0.666 |
Neg logit contributions | |
rolet | -0.611 |
orth | -0.582 |
oppy | -0.546 |
olls | -0.515 |
NTS | -0.513 |
Token | Kinder |
Token ID | 46832 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
rolet | +0.178 |
orth | +0.172 |
oppy | +0.162 |
olls | +0.156 |
NTS | +0.155 |
Neg logit contributions | |
xual | -0.191 |
menstru | -0.176 |
Bir | -0.165 |
20439 | -0.160 |
pees | -0.160 |
Token | Morgan |
Token ID | 10805 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
xual | +7.745 |
menstru | +7.684 |
Bir | +7.178 |
ferment | +6.941 |
pees | +6.915 |
Neg logit contributions | |
rolet | -7.459 |
orth | -6.949 |
oppy | -6.599 |
olls | -6.250 |
rays | -6.241 |
Token | � |
Token ID | 447 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
xual | +0.729 |
menstru | +0.681 |
Bir | +0.630 |
pees | +0.619 |
20439 | +0.617 |
Neg logit contributions | |
rolet | -0.677 |
orth | -0.654 |
oppy | -0.616 |
olls | -0.584 |
NTS | -0.584 |
Token | � |
Token ID | 247 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rolet | +0.745 |
orth | +0.720 |
oppy | +0.686 |
olls | +0.662 |
rays | +0.661 |
Neg logit contributions | |
xual | -0.498 |
menstru | -0.465 |
Bir | -0.413 |
ferment | -0.412 |
20439 | -0.402 |
Token | s |
Token ID | 82 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
rolet | +0.181 |
orth | +0.179 |
oppy | +0.163 |
NTS | +0.156 |
rays | +0.154 |
Neg logit contributions | |
xual | -0.233 |
menstru | -0.222 |
Bir | -0.205 |
ferment | -0.203 |
20439 | -0.202 |
Token | Trans |
Token ID | 3602 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
rolet | +0.246 |
orth | +0.238 |
oppy | +0.224 |
olls | +0.215 |
NTS | +0.213 |
Neg logit contributions | |
xual | -0.289 |
menstru | -0.265 |
Bir | -0.248 |
pees | -0.244 |
20439 | -0.244 |
Token | a |
Token ID | 257 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
rolet | +0.702 |
orth | +0.686 |
oppy | +0.642 |
NTS | +0.624 |
rays | +0.609 |
Neg logit contributions | |
xual | -0.746 |
menstru | -0.685 |
Bir | -0.643 |
pees | -0.637 |
20439 | -0.632 |
Token | white |
Token ID | 2330 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
xual | +1.279 |
menstru | +1.202 |
Bir | +1.112 |
pees | +1.100 |
20439 | +1.097 |
Neg logit contributions | |
rolet | -1.234 |
orth | -1.183 |
oppy | -1.120 |
NTS | -1.064 |
olls | -1.058 |
Token | , |
Token ID | 11 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
xual | +0.839 |
menstru | +0.784 |
Bir | +0.722 |
pees | +0.714 |
20439 | +0.712 |
Neg logit contributions | |
rolet | -0.942 |
orth | -0.912 |
oppy | -0.866 |
NTS | -0.829 |
olls | -0.814 |
Token | straight |
Token ID | 3892 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
xual | +0.728 |
menstru | +0.673 |
Bir | +0.624 |
pees | +0.616 |
20439 | +0.615 |
Neg logit contributions | |
rolet | -0.863 |
orth | -0.837 |
oppy | -0.792 |
NTS | -0.763 |
olls | -0.751 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
xual | +1.911 |
menstru | +1.798 |
Bir | +1.656 |
pees | +1.626 |
ferment | +1.624 |
Neg logit contributions | |
rolet | -1.993 |
orth | -1.915 |
oppy | -1.814 |
NTS | -1.717 |
olls | -1.715 |
Token | cis |
Token ID | 33325 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
xual | +0.205 |
menstru | +0.188 |
Bir | +0.176 |
20439 | +0.174 |
pees | +0.174 |
Neg logit contributions | |
rolet | -0.233 |
orth | -0.227 |
oppy | -0.214 |
NTS | -0.207 |
olls | -0.202 |
Token | g |
Token ID | 70 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
xual | +6.633 |
menstru | +6.231 |
Bir | +5.678 |
ferment | +5.587 |
pees | +5.477 |
Neg logit contributions | |
rolet | -6.959 |
orth | -6.536 |
oppy | -6.343 |
olls | -6.095 |
NTS | -5.909 |
Token | endered |
Token ID | 30398 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
xual | +0.532 |
menstru | +0.487 |
Bir | +0.429 |
pees | +0.428 |
ferment | +0.418 |
Neg logit contributions | |
rolet | -0.993 |
orth | -0.972 |
oppy | -0.924 |
olls | -0.882 |
NTS | -0.880 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
xual | +3.691 |
menstru | +3.484 |
Bir | +3.187 |
ferment | +3.130 |
pees | +3.097 |
Neg logit contributions | |
rolet | -4.140 |
orth | -3.947 |
oppy | -3.768 |
olls | -3.575 |
NTS | -3.543 |
Token | American |
Token ID | 1605 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
xual | +0.478 |
menstru | +0.441 |
Bir | +0.410 |
pees | +0.405 |
20439 | +0.403 |
Neg logit contributions | |
rolet | -0.564 |
orth | -0.549 |
oppy | -0.518 |
NTS | -0.499 |
olls | -0.490 |
Token | man |
Token ID | 582 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
rolet | +0.122 |
orth | +0.119 |
oppy | +0.112 |
NTS | +0.108 |
igl | +0.106 |
Neg logit contributions | |
xual | -0.112 |
menstru | -0.106 |
Bir | -0.097 |
pees | -0.097 |
20439 | -0.096 |
Token | also |
Token ID | 635 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
xual | +0.796 |
menstru | +0.752 |
Bir | +0.701 |
20439 | +0.697 |
pees | +0.687 |
Neg logit contributions | |
rolet | -0.615 |
orth | -0.590 |
oppy | -0.549 |
olls | -0.520 |
rays | -0.513 |
Token | features |
Token ID | 3033 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
xual | +1.376 |
menstru | +1.282 |
Bir | +1.198 |
20439 | +1.192 |
pees | +1.173 |
Neg logit contributions | |
rolet | -1.283 |
orth | -1.244 |
oppy | -1.160 |
olls | -1.108 |
rays | -1.100 |
Token | unusual |
Token ID | 8468 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
xual | +1.906 |
menstru | +1.793 |
Bir | +1.655 |
pees | +1.621 |
ferment | +1.617 |
Neg logit contributions | |
rolet | -1.894 |
orth | -1.814 |
oppy | -1.721 |
olls | -1.627 |
NTS | -1.620 |
Token | men |
Token ID | 1450 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
xual | +0.425 |
menstru | +0.393 |
Bir | +0.364 |
20439 | +0.360 |
pees | +0.357 |
Neg logit contributions | |
rolet | -0.438 |
orth | -0.423 |
oppy | -0.402 |
olls | -0.380 |
NTS | -0.377 |
Token | 's |
Token ID | 338 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
xual | +2.266 |
menstru | +2.143 |
Bir | +1.958 |
ferment | +1.933 |
pees | +1.928 |
Neg logit contributions | |
rolet | -2.449 |
orth | -2.333 |
oppy | -2.215 |
NTS | -2.103 |
olls | -2.100 |
Token | ur |
Token ID | 2956 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
rolet | +0.142 |
orth | +0.137 |
oppy | +0.131 |
olls | +0.123 |
NTS | +0.121 |
Neg logit contributions | |
xual | -0.145 |
menstru | -0.132 |
Bir | -0.124 |
20439 | -0.123 |
pees | -0.121 |
Token | inals |
Token ID | 6897 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
xual | +4.896 |
menstru | +4.473 |
pees | +4.187 |
Bir | +4.038 |
ferment | +3.926 |
Neg logit contributions | |
rolet | -7.902 |
orth | -7.529 |
oppy | -7.256 |
NTS | -6.924 |
olls | -6.853 |
Token | in |
Token ID | 287 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
xual | +1.220 |
menstru | +1.157 |
Bir | +1.080 |
20439 | +1.058 |
pees | +1.055 |
Neg logit contributions | |
rolet | -0.962 |
orth | -0.920 |
oppy | -0.863 |
olls | -0.812 |
NTS | -0.806 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
xual | +0.905 |
menstru | +0.844 |
Bir | +0.787 |
20439 | +0.778 |
pees | +0.770 |
Neg logit contributions | |
rolet | -0.869 |
orth | -0.841 |
oppy | -0.800 |
NTS | -0.754 |
olls | -0.751 |
Token | shape |
Token ID | 5485 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
xual | +0.636 |
menstru | +0.589 |
Bir | +0.552 |
20439 | +0.551 |
pees | +0.544 |
Neg logit contributions | |
rolet | -0.576 |
orth | -0.557 |
oppy | -0.529 |
NTS | -0.499 |
olls | -0.497 |
Token | of |
Token ID | 286 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
xual | +3.489 |
menstru | +3.340 |
Bir | +3.127 |
ferment | +3.085 |
pees | +3.069 |
Neg logit contributions | |
rolet | -2.205 |
orth | -2.065 |
oppy | -1.929 |
olls | -1.782 |
NTS | -1.769 |
Token | of |
Token ID | 286 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
rolet | +0.474 |
orth | +0.444 |
oppy | +0.417 |
olls | +0.388 |
NTS | +0.385 |
Neg logit contributions | |
xual | -0.702 |
menstru | -0.669 |
Bir | -0.624 |
ferment | -0.616 |
pees | -0.611 |
Token | self |
Token ID | 2116 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
orth | +0.722 |
rolet | +0.714 |
oppy | +0.668 |
olls | +0.646 |
NTS | +0.641 |
Neg logit contributions | |
xual | -0.778 |
menstru | -0.717 |
Bir | -0.697 |
20439 | -0.692 |
pees | -0.688 |
Token | to |
Token ID | 284 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
rolet | +0.723 |
orth | +0.700 |
oppy | +0.645 |
olls | +0.607 |
rays | +0.605 |
Neg logit contributions | |
xual | -0.988 |
menstru | -0.940 |
Bir | -0.886 |
pees | -0.874 |
20439 | -0.868 |
Token | others |
Token ID | 1854 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
xual | +0.635 |
menstru | +0.592 |
Bir | +0.564 |
pees | +0.552 |
20439 | +0.550 |
Neg logit contributions | |
rolet | -0.615 |
orth | -0.603 |
oppy | -0.560 |
olls | -0.536 |
rays | -0.530 |
Token | as |
Token ID | 355 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
xual | +0.833 |
menstru | +0.791 |
Bir | +0.746 |
pees | +0.734 |
ferment | +0.728 |
Neg logit contributions | |
rolet | -0.625 |
orth | -0.600 |
oppy | -0.557 |
olls | -0.525 |
NTS | -0.522 |
Token | masculine |
Token ID | 27543 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
xual | +0.248 |
menstru | +0.226 |
Bir | +0.214 |
pees | +0.214 |
20439 | +0.210 |
Neg logit contributions | |
rolet | -0.314 |
orth | -0.309 |
oppy | -0.291 |
NTS | -0.282 |
olls | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
xual | +6.175 |
menstru | +5.757 |
Bir | +5.209 |
ferment | +5.191 |
pees | +5.057 |
Neg logit contributions | |
rolet | -5.993 |
orth | -5.521 |
oppy | -5.412 |
olls | -5.029 |
NTS | -4.989 |
Token | feminine |
Token ID | 23564 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
xual | +0.244 |
menstru | +0.222 |
Bir | +0.202 |
pees | +0.199 |
20439 | +0.195 |
Neg logit contributions | |
rolet | -0.430 |
orth | -0.419 |
oppy | -0.397 |
rays | -0.382 |
olls | -0.381 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
xual | +3.549 |
menstru | +3.366 |
ferment | +3.036 |
Bir | +3.009 |
tur | +2.923 |
Neg logit contributions | |
rolet | -3.538 |
orth | -3.276 |
oppy | -3.172 |
olls | -3.005 |
NTS | -2.956 |
Token | both |
Token ID | 1111 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
xual | +0.335 |
menstru | +0.310 |
Bir | +0.292 |
pees | +0.290 |
20439 | +0.288 |
Neg logit contributions | |
rolet | -0.351 |
orth | -0.343 |
oppy | -0.322 |
NTS | -0.306 |
rays | -0.305 |
Token | , |
Token ID | 11 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
rolet | +0.063 |
orth | +0.060 |
oppy | +0.056 |
olls | +0.053 |
NTS | +0.053 |
Neg logit contributions | |
xual | -0.075 |
menstru | -0.071 |
Bir | -0.067 |
pees | -0.066 |
20439 | -0.065 |
Token | � |
Token ID | 447 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
rolet | +1.083 |
orth | +1.038 |
oppy | +0.977 |
olls | +0.921 |
NTS | +0.919 |
Neg logit contributions | |
xual | -1.181 |
menstru | -1.109 |
Bir | -1.032 |
pees | -1.015 |
20439 | -1.013 |
Token | � |
Token ID | 247 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
rolet | +0.195 |
orth | +0.188 |
oppy | +0.181 |
olls | +0.174 |
rays | +0.173 |
Neg logit contributions | |
xual | -0.114 |
menstru | -0.105 |
Bir | -0.094 |
20439 | -0.092 |
ferment | -0.092 |
Token | dinner |
Token ID | 8073 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
xual | +0.529 |
menstru | +0.500 |
Bir | +0.462 |
ferment | +0.454 |
pees | +0.452 |
Neg logit contributions | |
rolet | -0.514 |
orth | -0.490 |
oppy | -0.465 |
olls | -0.439 |
NTS | -0.437 |
Token | at |
Token ID | 379 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
xual | +0.816 |
menstru | +0.774 |
Bir | +0.719 |
ferment | +0.706 |
pees | +0.704 |
Neg logit contributions | |
rolet | -0.698 |
orth | -0.664 |
oppy | -0.627 |
olls | -0.589 |
NTS | -0.587 |
Token | El |
Token ID | 2574 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
rolet | +0.077 |
orth | +0.073 |
oppy | +0.069 |
olls | +0.065 |
NTS | +0.065 |
Neg logit contributions | |
xual | -0.087 |
menstru | -0.082 |
Bir | -0.076 |
pees | -0.074 |
20439 | -0.074 |
Token | Gau |
Token ID | 35094 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
xual | +3.898 |
menstru | +3.740 |
Bir | +3.518 |
ferment | +3.430 |
pees | +3.428 |
Neg logit contributions | |
rolet | -3.263 |
orth | -3.065 |
oppy | -2.923 |
NTS | -2.734 |
olls | -2.731 |
Token | cho |
Token ID | 6679 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
xual | +4.879 |
menstru | +4.712 |
Bir | +4.287 |
pees | +4.243 |
ferment | +4.211 |
Neg logit contributions | |
rolet | -6.533 |
orth | -6.349 |
oppy | -6.165 |
olls | -5.800 |
NTS | -5.723 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rolet | +0.271 |
orth | +0.261 |
oppy | +0.243 |
olls | +0.230 |
NTS | +0.230 |
Neg logit contributions | |
xual | -0.328 |
menstru | -0.310 |
Bir | -0.289 |
20439 | -0.285 |
pees | -0.283 |
Token | Erik |
Token ID | 22722 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
rolet | +0.274 |
orth | +0.261 |
oppy | +0.247 |
NTS | +0.233 |
olls | +0.231 |
Neg logit contributions | |
xual | -0.312 |
menstru | -0.294 |
Bir | -0.274 |
pees | -0.269 |
20439 | -0.267 |
Token | Johnson |
Token ID | 5030 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
rolet | +0.368 |
orth | +0.352 |
oppy | +0.331 |
olls | +0.311 |
NTS | +0.308 |
Neg logit contributions | |
xual | -0.451 |
menstru | -0.426 |
Bir | -0.394 |
20439 | -0.390 |
pees | -0.390 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
xual | +0.166 |
menstru | +0.157 |
Bir | +0.146 |
ferment | +0.144 |
pees | +0.144 |
Neg logit contributions | |
rolet | -0.135 |
orth | -0.129 |
oppy | -0.121 |
olls | -0.114 |
NTS | -0.113 |
Token | people |
Token ID | 661 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
xual | +2.544 |
menstru | +2.391 |
Bir | +2.172 |
ferment | +2.125 |
pees | +2.117 |
Neg logit contributions | |
rolet | -3.274 |
orth | -3.140 |
oppy | -3.001 |
olls | -2.851 |
NTS | -2.843 |
Token | to |
Token ID | 284 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
xual | +1.298 |
menstru | +1.231 |
Bir | +1.144 |
ferment | +1.125 |
pees | +1.122 |
Neg logit contributions | |
rolet | -1.084 |
orth | -1.031 |
oppy | -0.972 |
olls | -0.913 |
NTS | -0.909 |
Token | use |
Token ID | 779 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
xual | +0.981 |
menstru | +0.897 |
Bir | +0.858 |
20439 | +0.857 |
pees | +0.843 |
Neg logit contributions | |
rolet | -0.807 |
orth | -0.771 |
oppy | -0.719 |
olls | -0.689 |
NTS | -0.680 |
Token | the |
Token ID | 262 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
rolet | +0.428 |
orth | +0.413 |
oppy | +0.390 |
olls | +0.376 |
NTS | +0.375 |
Neg logit contributions | |
xual | -0.415 |
menstru | -0.380 |
Bir | -0.356 |
20439 | -0.351 |
ferment | -0.351 |
Token | proper |
Token ID | 1774 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
rolet | +0.133 |
orth | +0.128 |
oppy | +0.122 |
NTS | +0.117 |
olls | +0.116 |
Neg logit contributions | |
xual | -0.124 |
menstru | -0.114 |
Bir | -0.106 |
pees | -0.105 |
ferment | -0.104 |
Token | bathroom |
Token ID | 12436 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
xual | +1.495 |
menstru | +1.386 |
Bir | +1.267 |
ferment | +1.243 |
pees | +1.243 |
Neg logit contributions | |
rolet | -1.853 |
orth | -1.784 |
oppy | -1.701 |
olls | -1.620 |
NTS | -1.620 |
Token | , |
Token ID | 11 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
xual | +6.125 |
menstru | +5.951 |
Bir | +5.428 |
pees | +5.361 |
ferment | +5.352 |
Neg logit contributions | |
rolet | -5.439 |
orth | -5.041 |
oppy | -4.872 |
rays | -4.475 |
NTS | -4.458 |
Token | saying |
Token ID | 2282 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
rolet | +0.114 |
orth | +0.110 |
oppy | +0.103 |
NTS | +0.098 |
olls | +0.096 |
Neg logit contributions | |
xual | -0.145 |
menstru | -0.134 |
Bir | -0.127 |
pees | -0.125 |
20439 | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
rolet | +0.238 |
orth | +0.226 |
oppy | +0.213 |
NTS | +0.202 |
olls | +0.202 |
Neg logit contributions | |
xual | -0.287 |
menstru | -0.267 |
Bir | -0.252 |
pees | -0.250 |
ferment | -0.248 |
Token | � |
Token ID | 564 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
rolet | +0.566 |
orth | +0.543 |
oppy | +0.518 |
olls | +0.490 |
NTS | +0.487 |
Neg logit contributions | |
xual | -0.499 |
menstru | -0.472 |
Bir | -0.431 |
ferment | -0.421 |
pees | -0.419 |
Token | � |
Token ID | 250 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
xual | +0.167 |
menstru | +0.156 |
Bir | +0.141 |
ferment | +0.141 |
pees | +0.139 |
Neg logit contributions | |
rolet | -0.175 |
orth | -0.167 |
oppy | -0.159 |
olls | -0.150 |
NTS | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
xual | +1.930 |
menstru | +1.823 |
Bir | +1.689 |
ferment | +1.657 |
pees | +1.655 |
Neg logit contributions | |
rolet | -1.805 |
orth | -1.727 |
oppy | -1.636 |
olls | -1.543 |
NTS | -1.542 |
Token | story |
Token ID | 1621 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
xual | +0.355 |
menstru | +0.336 |
Bir | +0.314 |
pees | +0.308 |
20439 | +0.308 |
Neg logit contributions | |
rolet | -0.289 |
orth | -0.276 |
oppy | -0.260 |
NTS | -0.247 |
olls | -0.245 |
Token | begins |
Token ID | 6140 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
xual | +0.344 |
menstru | +0.324 |
Bir | +0.304 |
20439 | +0.296 |
pees | +0.295 |
Neg logit contributions | |
rolet | -0.280 |
orth | -0.270 |
oppy | -0.255 |
NTS | -0.240 |
olls | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
rolet | +0.540 |
orth | +0.512 |
oppy | +0.479 |
NTS | +0.452 |
olls | +0.450 |
Neg logit contributions | |
xual | -0.725 |
menstru | -0.685 |
Bir | -0.642 |
pees | -0.631 |
20439 | -0.629 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
xual | +0.274 |
menstru | +0.257 |
pees | +0.237 |
ferment | +0.236 |
Bir | +0.236 |
Neg logit contributions | |
rolet | -0.208 |
orth | -0.200 |
oppy | -0.186 |
NTS | -0.176 |
olls | -0.175 |
Token | Cur |
Token ID | 26628 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
xual | +0.431 |
menstru | +0.401 |
ferment | +0.365 |
Bir | +0.361 |
pees | +0.360 |
Neg logit contributions | |
rolet | -0.429 |
orth | -0.415 |
oppy | -0.391 |
olls | -0.370 |
rays | -0.369 |
Token | iously |
Token ID | 6819 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
xual | +4.340 |
menstru | +4.036 |
Bir | +3.622 |
pees | +3.565 |
ferment | +3.498 |
Neg logit contributions | |
rolet | -6.797 |
orth | -6.451 |
oppy | -6.218 |
NTS | -5.979 |
olls | -5.925 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
xual | +2.868 |
menstru | +2.718 |
Bir | +2.475 |
ferment | +2.426 |
pees | +2.407 |
Neg logit contributions | |
rolet | -3.198 |
orth | -3.034 |
oppy | -2.903 |
olls | -2.760 |
NTS | -2.725 |
Token | that |
Token ID | 326 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
xual | +0.251 |
menstru | +0.236 |
Bir | +0.220 |
20439 | +0.217 |
ferment | +0.217 |
Neg logit contributions | |
rolet | -0.219 |
orth | -0.211 |
oppy | -0.200 |
NTS | -0.190 |
olls | -0.189 |
Token | � |
Token ID | 447 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
xual | +0.222 |
menstru | +0.207 |
Bir | +0.193 |
pees | +0.191 |
20439 | +0.190 |
Neg logit contributions | |
rolet | -0.194 |
orth | -0.187 |
oppy | -0.176 |
olls | -0.166 |
NTS | -0.166 |
Token | � |
Token ID | 247 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
xual | +0.680 |
menstru | +0.626 |
Bir | +0.554 |
ferment | +0.538 |
pees | +0.537 |
Neg logit contributions | |
rolet | -1.267 |
orth | -1.223 |
oppy | -1.176 |
olls | -1.127 |
NTS | -1.122 |
Token | 45 |
Token ID | 2231 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
rolet | +0.636 |
orth | +0.622 |
oppy | +0.577 |
NTS | +0.559 |
olls | +0.555 |
Neg logit contributions | |
xual | -0.670 |
menstru | -0.632 |
pees | -0.574 |
ferment | -0.573 |
Bir | -0.561 |
Token | 366 |
Token ID | 44856 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
xual | +0.715 |
menstru | +0.675 |
Bir | +0.621 |
pees | +0.615 |
ferment | +0.612 |
Neg logit contributions | |
rolet | -0.700 |
orth | -0.674 |
oppy | -0.634 |
NTS | -0.606 |
olls | -0.604 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
xual | +2.493 |
menstru | +2.368 |
Bir | +2.198 |
ferment | +2.162 |
pees | +2.151 |
Neg logit contributions | |
rolet | -2.089 |
orth | -1.980 |
oppy | -1.875 |
olls | -1.752 |
NTS | -1.744 |
Token |
|
Token ID | 198 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
xual | +1.015 |
menstru | +0.961 |
Bir | +0.891 |
ferment | +0.871 |
pees | +0.867 |
Neg logit contributions | |
rolet | -0.959 |
orth | -0.912 |
oppy | -0.866 |
olls | -0.812 |
NTS | -0.811 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
xual | +0.142 |
menstru | +0.132 |
pees | +0.123 |
ferment | +0.122 |
Bir | +0.122 |
Neg logit contributions | |
rolet | -0.104 |
orth | -0.101 |
oppy | -0.093 |
NTS | -0.088 |
olls | -0.088 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
xual | +0.331 |
menstru | +0.310 |
ferment | +0.281 |
Bir | +0.281 |
pees | +0.278 |
Neg logit contributions | |
rolet | -0.355 |
orth | -0.344 |
oppy | -0.325 |
olls | -0.310 |
rays | -0.307 |
Token | : |
Token ID | 25 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
xual | +5.674 |
menstru | +5.436 |
Bir | +5.013 |
ferment | +4.872 |
20439 | +4.815 |
Neg logit contributions | |
rolet | -5.479 |
orth | -5.096 |
oppy | -4.967 |
olls | -4.639 |
NTS | -4.545 |
Token | community |
Token ID | 2055 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
xual | +2.119 |
menstru | +2.011 |
Bir | +1.846 |
ferment | +1.818 |
pees | +1.802 |
Neg logit contributions | |
rolet | -2.136 |
orth | -2.035 |
oppy | -1.937 |
olls | -1.825 |
NTS | -1.820 |
Token | - |
Token ID | 12 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
rolet | +0.394 |
orth | +0.379 |
oppy | +0.349 |
olls | +0.328 |
rays | +0.321 |
Neg logit contributions | |
xual | -0.635 |
menstru | -0.597 |
Bir | -0.563 |
20439 | -0.559 |
pees | -0.557 |
Token | and |
Token ID | 392 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
xual | +0.389 |
menstru | +0.367 |
Bir | +0.340 |
ferment | +0.333 |
20439 | +0.331 |
Neg logit contributions | |
rolet | -0.363 |
orth | -0.350 |
oppy | -0.330 |
olls | -0.312 |
rays | -0.308 |
Token | - |
Token ID | 12 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
rolet | +0.146 |
orth | +0.140 |
oppy | +0.129 |
olls | +0.120 |
NTS | +0.118 |
Neg logit contributions | |
xual | -0.230 |
menstru | -0.218 |
Bir | -0.205 |
pees | -0.202 |
20439 | -0.202 |
Token | into |
Token ID | 656 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
xual | +0.091 |
menstru | +0.085 |
Bir | +0.081 |
pees | +0.080 |
20439 | +0.080 |
Neg logit contributions | |
rolet | -0.066 |
orth | -0.063 |
oppy | -0.059 |
NTS | -0.056 |
olls | -0.056 |
Token | them |
Token ID | 606 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
xual | +1.885 |
menstru | +1.759 |
Bir | +1.627 |
pees | +1.597 |
20439 | +1.591 |
Neg logit contributions | |
rolet | -1.983 |
orth | -1.903 |
oppy | -1.810 |
olls | -1.721 |
NTS | -1.716 |
Token | ". |
Token ID | 1911 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
rolet | +0.235 |
orth | +0.223 |
oppy | +0.208 |
olls | +0.196 |
NTS | +0.194 |
Neg logit contributions | |
xual | -0.337 |
menstru | -0.320 |
Bir | -0.302 |
pees | -0.296 |
20439 | -0.294 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
xual | +0.117 |
menstru | +0.111 |
Bir | +0.103 |
ferment | +0.102 |
pees | +0.102 |
Neg logit contributions | |
rolet | -0.092 |
orth | -0.089 |
oppy | -0.082 |
olls | -0.078 |
NTS | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
xual | +0.428 |
menstru | +0.401 |
pees | +0.371 |
ferment | +0.369 |
Bir | +0.369 |
Neg logit contributions | |
rolet | -0.325 |
orth | -0.314 |
oppy | -0.291 |
NTS | -0.275 |
olls | -0.273 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
xual | +0.440 |
menstru | +0.416 |
Bir | +0.383 |
ferment | +0.379 |
pees | +0.378 |
Neg logit contributions | |
rolet | -0.384 |
orth | -0.367 |
oppy | -0.346 |
olls | -0.326 |
NTS | -0.324 |
Token | : |
Token ID | 25 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
xual | +5.568 |
menstru | +5.336 |
Bir | +4.934 |
ferment | +4.780 |
20439 | +4.736 |
Neg logit contributions | |
rolet | -5.447 |
orth | -5.068 |
oppy | -4.945 |
olls | -4.626 |
rays | -4.508 |
Token | marine |
Token ID | 16050 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
xual | +1.934 |
menstru | +1.845 |
Bir | +1.679 |
ferment | +1.663 |
pees | +1.638 |
Neg logit contributions | |
rolet | -1.991 |
orth | -1.892 |
oppy | -1.803 |
olls | -1.694 |
NTS | -1.683 |
Token | - |
Token ID | 12 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rolet | +1.303 |
orth | +1.225 |
oppy | +1.174 |
olls | +1.094 |
NTS | +1.094 |
Neg logit contributions | |
xual | -1.645 |
menstru | -1.592 |
Bir | -1.467 |
ferment | -1.456 |
pees | -1.427 |
Token | biology |
Token ID | 43592 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
xual | +0.309 |
menstru | +0.295 |
Bir | +0.274 |
ferment | +0.270 |
pees | +0.269 |
Neg logit contributions | |
rolet | -0.229 |
orth | -0.215 |
oppy | -0.203 |
NTS | -0.189 |
olls | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rolet | +1.687 |
orth | +1.665 |
oppy | +1.511 |
olls | +1.422 |
NTS | +1.422 |
Neg logit contributions | |
xual | -2.602 |
menstru | -2.439 |
Bir | -2.323 |
20439 | -2.285 |
pees | -2.273 |
Token | to |
Token ID | 284 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
xual | +0.540 |
menstru | +0.520 |
Bir | +0.472 |
ferment | +0.466 |
pees | +0.465 |
Neg logit contributions | |
rolet | -0.489 |
orth | -0.464 |
oppy | -0.436 |
olls | -0.412 |
NTS | -0.410 |
Token | appear |
Token ID | 1656 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
xual | +0.050 |
menstru | +0.045 |
20439 | +0.044 |
Bir | +0.044 |
pees | +0.043 |
Neg logit contributions | |
rolet | -0.043 |
orth | -0.041 |
oppy | -0.039 |
NTS | -0.037 |
olls | -0.036 |
Token | at |
Token ID | 379 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
rolet | +0.222 |
orth | +0.215 |
oppy | +0.200 |
olls | +0.187 |
NTS | +0.187 |
Neg logit contributions | |
xual | -0.295 |
menstru | -0.273 |
Bir | -0.260 |
20439 | -0.258 |
pees | -0.256 |
Token | his |
Token ID | 465 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
rolet | +1.376 |
orth | +1.321 |
oppy | +1.257 |
NTS | +1.186 |
olls | +1.183 |
Neg logit contributions | |
xual | -1.560 |
menstru | -1.442 |
Bir | -1.351 |
20439 | -1.336 |
pees | -1.331 |
Token | university |
Token ID | 6403 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
rolet | +0.523 |
orth | +0.505 |
oppy | +0.476 |
NTS | +0.448 |
olls | +0.441 |
Neg logit contributions | |
xual | -0.723 |
menstru | -0.663 |
20439 | -0.628 |
pees | -0.626 |
Bir | -0.625 |
Token | disciplinary |
Token ID | 24737 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
xual | +1.105 |
menstru | +1.042 |
Bir | +0.969 |
pees | +0.953 |
ferment | +0.952 |
Neg logit contributions | |
rolet | -0.954 |
orth | -0.916 |
oppy | -0.862 |
olls | -0.809 |
NTS | -0.809 |
Token | hearing |
Token ID | 4854 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
xual | +5.234 |
menstru | +5.220 |
ferment | +4.765 |
Bir | +4.711 |
tur | +4.534 |
Neg logit contributions | |
rolet | -5.652 |
orth | -5.235 |
oppy | -5.028 |
olls | -4.743 |
rays | -4.696 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
xual | +2.196 |
menstru | +2.091 |
Bir | +1.945 |
ferment | +1.915 |
pees | +1.907 |
Neg logit contributions | |
rolet | -1.697 |
orth | -1.605 |
oppy | -1.513 |
olls | -1.416 |
NTS | -1.405 |
Token | He |
Token ID | 679 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
rolet | +0.280 |
orth | +0.267 |
oppy | +0.251 |
NTS | +0.241 |
olls | +0.235 |
Neg logit contributions | |
xual | -0.343 |
menstru | -0.324 |
ferment | -0.297 |
pees | -0.297 |
Bir | -0.297 |
Token | contends |
Token ID | 33799 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
rolet | +0.960 |
orth | +0.924 |
oppy | +0.863 |
olls | +0.821 |
rays | +0.819 |
Neg logit contributions | |
xual | -1.238 |
menstru | -1.144 |
Bir | -1.087 |
20439 | -1.085 |
pees | -1.056 |
Token | their |
Token ID | 511 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rolet | +1.040 |
orth | +1.005 |
oppy | +0.956 |
NTS | +0.921 |
rays | +0.895 |
Neg logit contributions | |
xual | -1.370 |
menstru | -1.268 |
Bir | -1.209 |
pees | -1.208 |
20439 | -1.200 |
Token | Tweet |
Token ID | 47845 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
xual | +0.117 |
menstru | +0.110 |
Bir | +0.100 |
ferment | +0.100 |
pees | +0.099 |
Neg logit contributions | |
rolet | -0.114 |
orth | -0.110 |
oppy | -0.103 |
olls | -0.098 |
NTS | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
xual | +1.387 |
menstru | +1.314 |
Bir | +1.216 |
ferment | +1.197 |
pees | +1.187 |
Neg logit contributions | |
rolet | -1.283 |
orth | -1.225 |
oppy | -1.167 |
olls | -1.092 |
NTS | -1.087 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
xual | +0.397 |
menstru | +0.373 |
pees | +0.343 |
ferment | +0.342 |
Bir | +0.342 |
Neg logit contributions | |
rolet | -0.302 |
orth | -0.291 |
oppy | -0.270 |
NTS | -0.256 |
olls | -0.255 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
xual | +0.628 |
menstru | +0.592 |
Bir | +0.543 |
ferment | +0.535 |
pees | +0.532 |
Neg logit contributions | |
rolet | -0.655 |
orth | -0.628 |
oppy | -0.595 |
olls | -0.564 |
NTS | -0.561 |
Token | via |
Token ID | 2884 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
xual | +3.577 |
menstru | +3.410 |
Bir | +3.177 |
ferment | +3.116 |
pees | +3.065 |
Neg logit contributions | |
rolet | -3.406 |
orth | -3.240 |
oppy | -3.110 |
olls | -2.905 |
rays | -2.898 |
Token | RSS |
Token ID | 25012 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
xual | +0.856 |
menstru | +0.794 |
Bir | +0.705 |
ferment | +0.686 |
pees | +0.680 |
Neg logit contributions | |
rolet | -1.536 |
orth | -1.481 |
oppy | -1.426 |
olls | -1.364 |
NTS | -1.359 |
Token | or |
Token ID | 393 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
xual | +5.244 |
menstru | +5.029 |
Bir | +4.685 |
ferment | +4.638 |
20439 | +4.546 |
Neg logit contributions | |
rolet | -5.529 |
orth | -5.289 |
oppy | -5.003 |
NTS | -4.714 |
olls | -4.688 |
Token | daily |
Token ID | 4445 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
rolet | +1.164 |
orth | +1.103 |
oppy | +1.031 |
olls | +0.987 |
NTS | +0.982 |
Neg logit contributions | |
xual | -1.350 |
menstru | -1.264 |
Bir | -1.175 |
pees | -1.164 |
ferment | -1.147 |
Token | email |
Token ID | 3053 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
xual | +2.434 |
menstru | +2.324 |
Bir | +2.157 |
ferment | +2.127 |
pees | +2.112 |
Neg logit contributions | |
rolet | -1.995 |
orth | -1.895 |
oppy | -1.789 |
olls | -1.676 |
NTS | -1.666 |
Token | Contact |
Token ID | 14039 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
xual | +1.347 |
menstru | +1.277 |
Bir | +1.186 |
ferment | +1.166 |
pees | +1.163 |
Neg logit contributions | |
rolet | -1.131 |
orth | -1.076 |
oppy | -1.015 |
olls | -0.953 |
NTS | -0.950 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
xual | +0.671 |
menstru | +0.636 |
Bir | +0.588 |
ferment | +0.578 |
pees | +0.574 |
Neg logit contributions | |
rolet | -0.637 |
orth | -0.609 |
oppy | -0.577 |
olls | -0.545 |
NTS | -0.540 |
Token | students |
Token ID | 2444 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
xual | +0.687 |
menstru | +0.649 |
Bir | +0.606 |
20439 | +0.599 |
pees | +0.598 |
Neg logit contributions | |
rolet | -0.507 |
orth | -0.486 |
oppy | -0.454 |
NTS | -0.430 |
olls | -0.426 |
Token | to |
Token ID | 284 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
xual | +0.660 |
menstru | +0.626 |
Bir | +0.582 |
ferment | +0.572 |
pees | +0.571 |
Neg logit contributions | |
rolet | -0.539 |
orth | -0.513 |
oppy | -0.483 |
olls | -0.452 |
NTS | -0.452 |
Token | access |
Token ID | 1895 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
xual | +0.343 |
menstru | +0.314 |
20439 | +0.302 |
Bir | +0.301 |
pees | +0.295 |
Neg logit contributions | |
rolet | -0.303 |
orth | -0.290 |
oppy | -0.270 |
NTS | -0.261 |
olls | -0.256 |
Token | co |
Token ID | 763 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
rolet | +0.591 |
orth | +0.574 |
oppy | +0.538 |
NTS | +0.519 |
olls | +0.509 |
Neg logit contributions | |
xual | -0.655 |
menstru | -0.614 |
Bir | -0.571 |
20439 | -0.567 |
pees | -0.560 |
Token | - |
Token ID | 12 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
rolet | +1.352 |
orth | +1.299 |
oppy | +1.201 |
NTS | +1.115 |
olls | +1.113 |
Neg logit contributions | |
xual | -1.932 |
menstru | -1.839 |
Bir | -1.704 |
ferment | -1.687 |
20439 | -1.679 |
Token | cur |
Token ID | 22019 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
xual | +1.433 |
menstru | +1.353 |
Bir | +1.247 |
ferment | +1.223 |
pees | +1.219 |
Neg logit contributions | |
rolet | -1.462 |
orth | -1.395 |
oppy | -1.326 |
olls | -1.253 |
NTS | -1.248 |
Token | ricular |
Token ID | 41001 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
xual | +5.200 |
menstru | +4.908 |
Bir | +4.545 |
pees | +4.458 |
ferment | +4.433 |
Neg logit contributions | |
rolet | -5.736 |
orth | -5.451 |
oppy | -5.237 |
olls | -4.940 |
NTS | -4.916 |
Token | activities |
Token ID | 4568 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
xual | +2.723 |
menstru | +2.583 |
Bir | +2.391 |
ferment | +2.350 |
pees | +2.337 |
Neg logit contributions | |
rolet | -2.498 |
orth | -2.376 |
oppy | -2.253 |
olls | -2.121 |
NTS | -2.108 |
Token | to |
Token ID | 284 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
xual | +1.217 |
menstru | +1.155 |
Bir | +1.078 |
pees | +1.061 |
ferment | +1.056 |
Neg logit contributions | |
rolet | -0.935 |
orth | -0.892 |
oppy | -0.834 |
NTS | -0.787 |
olls | -0.780 |
Token | supplement |
Token ID | 10327 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
xual | +0.194 |
menstru | +0.179 |
Bir | +0.170 |
20439 | +0.168 |
pees | +0.166 |
Neg logit contributions | |
rolet | -0.171 |
orth | -0.165 |
oppy | -0.154 |
NTS | -0.148 |
olls | -0.145 |
Token | their |
Token ID | 511 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
rolet | +0.145 |
orth | +0.141 |
oppy | +0.134 |
NTS | +0.128 |
olls | +0.127 |
Neg logit contributions | |
xual | -0.127 |
menstru | -0.119 |
Bir | -0.110 |
20439 | -0.108 |
pees | -0.107 |
Token | hard |
Token ID | 10424 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
xual | +0.312 |
menstru | +0.293 |
Bir | +0.267 |
ferment | +0.266 |
20439 | +0.264 |
Neg logit contributions | |
rolet | -0.314 |
orth | -0.305 |
oppy | -0.286 |
rays | -0.270 |
olls | -0.270 |
Token | core |
Token ID | 7295 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
rolet | +1.491 |
orth | +1.425 |
oppy | +1.330 |
NTS | +1.230 |
olls | +1.226 |
Neg logit contributions | |
xual | -2.091 |
menstru | -1.986 |
Bir | -1.846 |
pees | -1.833 |
20439 | -1.821 |
Token | " |
Token ID | 1 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
rolet | +0.428 |
orth | +0.413 |
oppy | +0.383 |
NTS | +0.356 |
rays | +0.353 |
Neg logit contributions | |
xual | -0.627 |
menstru | -0.600 |
Bir | -0.564 |
pees | -0.560 |
20439 | -0.559 |
Token | and |
Token ID | 290 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
xual | +0.204 |
menstru | +0.194 |
Bir | +0.182 |
20439 | +0.180 |
pees | +0.180 |
Neg logit contributions | |
rolet | -0.160 |
orth | -0.155 |
oppy | -0.145 |
NTS | -0.137 |
olls | -0.135 |
Token | more |
Token ID | 517 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
xual | +0.503 |
menstru | +0.470 |
Bir | +0.441 |
pees | +0.440 |
20439 | +0.434 |
Neg logit contributions | |
rolet | -0.455 |
orth | -0.442 |
oppy | -0.415 |
NTS | -0.395 |
olls | -0.389 |
Token | masculine |
Token ID | 27543 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
xual | +1.073 |
menstru | +1.008 |
Bir | +0.940 |
pees | +0.931 |
20439 | +0.924 |
Neg logit contributions | |
rolet | -0.978 |
orth | -0.943 |
oppy | -0.886 |
NTS | -0.841 |
olls | -0.831 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
xual | +5.805 |
menstru | +5.486 |
ferment | +5.055 |
Bir | +4.994 |
pees | +4.886 |
Neg logit contributions | |
rolet | -5.145 |
orth | -4.813 |
oppy | -4.583 |
olls | -4.300 |
NTS | -4.249 |
Token | Through |
Token ID | 9561 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
xual | +0.464 |
menstru | +0.441 |
pees | +0.405 |
Bir | +0.404 |
ferment | +0.402 |
Neg logit contributions | |
rolet | -0.396 |
orth | -0.382 |
oppy | -0.359 |
NTS | -0.345 |
olls | -0.336 |
Token | this |
Token ID | 428 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
xual | +0.546 |
menstru | +0.513 |
Bir | +0.482 |
pees | +0.475 |
20439 | +0.472 |
Neg logit contributions | |
rolet | -0.537 |
orth | -0.515 |
oppy | -0.491 |
olls | -0.462 |
NTS | -0.462 |
Token | decade |
Token ID | 5707 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
xual | +0.766 |
menstru | +0.714 |
Bir | +0.673 |
pees | +0.672 |
20439 | +0.662 |
Neg logit contributions | |
rolet | -0.656 |
orth | -0.633 |
oppy | -0.601 |
NTS | -0.566 |
olls | -0.559 |
Token | or |
Token ID | 393 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
xual | +1.757 |
menstru | +1.667 |
Bir | +1.551 |
ferment | +1.522 |
pees | +1.520 |
Neg logit contributions | |
rolet | -1.474 |
orth | -1.403 |
oppy | -1.325 |
olls | -1.242 |
NTS | -1.239 |
Token | similar |
Token ID | 2092 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
xual | +0.627 |
menstru | +0.586 |
Bir | +0.545 |
20439 | +0.538 |
pees | +0.536 |
Neg logit contributions | |
rolet | -0.586 |
orth | -0.563 |
oppy | -0.533 |
NTS | -0.507 |
olls | -0.502 |
Token | range |
Token ID | 2837 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
rolet | +1.131 |
orth | +1.080 |
oppy | +1.008 |
NTS | +0.961 |
olls | +0.934 |
Neg logit contributions | |
xual | -1.601 |
menstru | -1.496 |
20439 | -1.413 |
Bir | -1.412 |
pees | -1.393 |
Token | , |
Token ID | 11 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
xual | +0.854 |
menstru | +0.811 |
Bir | +0.753 |
ferment | +0.742 |
pees | +0.738 |
Neg logit contributions | |
rolet | -0.693 |
orth | -0.658 |
oppy | -0.624 |
olls | -0.580 |
NTS | -0.578 |
Token | such |
Token ID | 884 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
xual | +0.193 |
menstru | +0.183 |
Bir | +0.170 |
ferment | +0.168 |
pees | +0.167 |
Neg logit contributions | |
rolet | -0.152 |
orth | -0.145 |
oppy | -0.136 |
olls | -0.128 |
NTS | -0.128 |
Token | as |
Token ID | 355 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
rolet | +0.361 |
orth | +0.344 |
oppy | +0.318 |
NTS | +0.298 |
olls | +0.297 |
Neg logit contributions | |
xual | -0.600 |
menstru | -0.567 |
Bir | -0.533 |
pees | -0.528 |
20439 | -0.526 |
Token | Alpha |
Token ID | 12995 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
rolet | +0.235 |
orth | +0.225 |
oppy | +0.212 |
NTS | +0.201 |
olls | +0.199 |
Neg logit contributions | |
xual | -0.275 |
menstru | -0.258 |
Bir | -0.241 |
ferment | -0.236 |
20439 | -0.235 |
Token | Delta |
Token ID | 16978 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
xual | +5.528 |
menstru | +5.243 |
Bir | +4.898 |
ferment | +4.790 |
pees | +4.750 |
Neg logit contributions | |
rolet | -5.345 |
orth | -4.961 |
oppy | -4.780 |
olls | -4.495 |
rays | -4.423 |
Token | Phi |
Token ID | 47256 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
xual | +3.714 |
menstru | +3.529 |
Bir | +3.268 |
pees | +3.210 |
ferment | +3.210 |
Neg logit contributions | |
rolet | -3.255 |
orth | -3.057 |
oppy | -2.918 |
olls | -2.735 |
rays | -2.708 |
Token | ($ |
Token ID | 7198 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
xual | +3.966 |
menstru | +3.794 |
Bir | +3.514 |
pees | +3.456 |
ferment | +3.438 |
Neg logit contributions | |
rolet | -3.507 |
orth | -3.303 |
oppy | -3.159 |
olls | -2.955 |
rays | -2.925 |
Token | 400 |
Token ID | 7029 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
rolet | +0.953 |
orth | +0.927 |
oppy | +0.873 |
olls | +0.840 |
rays | +0.837 |
Neg logit contributions | |
xual | -0.707 |
menstru | -0.666 |
ferment | -0.594 |
Bir | -0.582 |
pees | -0.574 |
Token | per |
Token ID | 583 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
xual | +0.184 |
menstru | +0.175 |
Bir | +0.164 |
ferment | +0.161 |
pees | +0.161 |
Neg logit contributions | |
rolet | -0.123 |
orth | -0.116 |
oppy | -0.109 |
olls | -0.101 |
NTS | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
rolet | +0.821 |
orth | +0.782 |
oppy | +0.727 |
olls | +0.690 |
NTS | +0.677 |
Neg logit contributions | |
xual | -1.038 |
menstru | -0.972 |
Bir | -0.907 |
pees | -0.894 |
20439 | -0.892 |
Token | who |
Token ID | 508 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
xual | +0.140 |
menstru | +0.131 |
Bir | +0.122 |
pees | +0.121 |
20439 | +0.120 |
Neg logit contributions | |
rolet | -0.121 |
orth | -0.117 |
oppy | -0.110 |
NTS | -0.103 |
olls | -0.103 |
Token | had |
Token ID | 550 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rolet | +1.618 |
orth | +1.580 |
oppy | +1.461 |
olls | +1.401 |
NTS | +1.369 |
Neg logit contributions | |
xual | -1.988 |
menstru | -1.817 |
20439 | -1.720 |
Bir | -1.717 |
pees | -1.703 |
Token | scored |
Token ID | 7781 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
xual | +0.236 |
menstru | +0.220 |
Bir | +0.206 |
20439 | +0.203 |
pees | +0.203 |
Neg logit contributions | |
rolet | -0.212 |
orth | -0.204 |
oppy | -0.192 |
olls | -0.182 |
NTS | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
xual | +2.731 |
menstru | +2.572 |
Bir | +2.374 |
pees | +2.325 |
ferment | +2.323 |
Neg logit contributions | |
rolet | -2.725 |
orth | -2.609 |
oppy | -2.475 |
olls | -2.341 |
NTS | -2.336 |
Token | hat |
Token ID | 6877 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
xual | +0.022 |
menstru | +0.021 |
Bir | +0.019 |
pees | +0.019 |
20439 | +0.019 |
Neg logit contributions | |
rolet | -0.018 |
orth | -0.018 |
oppy | -0.017 |
olls | -0.016 |
NTS | -0.016 |
Token | - |
Token ID | 12 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
xual | +5.875 |
menstru | +5.588 |
Bir | +5.250 |
ferment | +5.163 |
pees | +5.121 |
Neg logit contributions | |
rolet | -4.868 |
orth | -4.564 |
oppy | -4.367 |
olls | -4.126 |
NTS | -4.117 |
Token | tr |
Token ID | 2213 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
rolet | +0.649 |
orth | +0.629 |
oppy | +0.592 |
olls | +0.560 |
rays | +0.559 |
Neg logit contributions | |
xual | -0.573 |
menstru | -0.538 |
Bir | -0.485 |
ferment | -0.483 |
20439 | -0.481 |
Token | ick |
Token ID | 624 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
rolet | +0.035 |
orth | +0.033 |
oppy | +0.031 |
olls | +0.027 |
rays | +0.025 |
Neg logit contributions | |
xual | -0.091 |
menstru | -0.087 |
Bir | -0.082 |
20439 | -0.082 |
ferment | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
rolet | +0.446 |
orth | +0.427 |
oppy | +0.398 |
olls | +0.369 |
NTS | +0.367 |
Neg logit contributions | |
xual | -0.646 |
menstru | -0.612 |
Bir | -0.571 |
pees | -0.569 |
20439 | -0.566 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rolet | +0.244 |
orth | +0.235 |
oppy | +0.222 |
NTS | +0.207 |
olls | +0.206 |
Neg logit contributions | |
xual | -0.307 |
menstru | -0.287 |
Bir | -0.267 |
pees | -0.264 |
20439 | -0.263 |
Token | racial |
Token ID | 8425 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
xual | +0.092 |
menstru | +0.087 |
Bir | +0.080 |
pees | +0.080 |
20439 | +0.080 |
Neg logit contributions | |
rolet | -0.085 |
orth | -0.082 |
oppy | -0.077 |
olls | -0.073 |
NTS | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
xual | +0.278 |
menstru | +0.253 |
20439 | +0.233 |
Bir | +0.232 |
pees | +0.229 |
Neg logit contributions | |
rolet | -0.369 |
orth | -0.359 |
oppy | -0.341 |
NTS | -0.327 |
olls | -0.323 |
Token | religious |
Token ID | 4158 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
xual | +0.441 |
menstru | +0.417 |
Bir | +0.387 |
pees | +0.380 |
ferment | +0.380 |
Neg logit contributions | |
rolet | -0.398 |
orth | -0.381 |
oppy | -0.360 |
olls | -0.339 |
NTS | -0.338 |
Token | or |
Token ID | 393 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
rolet | +0.966 |
orth | +0.940 |
oppy | +0.875 |
NTS | +0.821 |
olls | +0.815 |
Neg logit contributions | |
xual | -1.293 |
menstru | -1.202 |
20439 | -1.138 |
pees | -1.136 |
Bir | -1.132 |
Token | sexual |
Token ID | 3206 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
rolet | +2.248 |
orth | +2.200 |
oppy | +2.048 |
NTS | +1.987 |
olls | +1.980 |
Neg logit contributions | |
xual | -2.216 |
menstru | -2.044 |
pees | -1.977 |
Bir | -1.936 |
20439 | -1.919 |
Token | slur |
Token ID | 40066 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
xual | +1.687 |
menstru | +1.591 |
Bir | +1.481 |
pees | +1.454 |
20439 | +1.451 |
Neg logit contributions | |
rolet | -1.478 |
orth | -1.417 |
oppy | -1.337 |
olls | -1.256 |
NTS | -1.253 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
xual | +5.593 |
menstru | +5.313 |
Bir | +4.884 |
ferment | +4.853 |
pees | +4.824 |
Neg logit contributions | |
rolet | -5.047 |
orth | -4.729 |
oppy | -4.581 |
olls | -4.245 |
NTS | -4.209 |
Token | quick |
Token ID | 2068 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
xual | +0.380 |
menstru | +0.360 |
Bir | +0.335 |
pees | +0.329 |
ferment | +0.328 |
Neg logit contributions | |
rolet | -0.316 |
orth | -0.302 |
oppy | -0.285 |
olls | -0.267 |
NTS | -0.267 |
Token | to |
Token ID | 284 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
rolet | +2.151 |
orth | +2.041 |
oppy | +1.931 |
olls | +1.811 |
NTS | +1.804 |
Neg logit contributions | |
xual | -2.555 |
menstru | -2.429 |
Bir | -2.252 |
ferment | -2.217 |
pees | -2.205 |
Token | lose |
Token ID | 4425 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
xual | +0.703 |
menstru | +0.660 |
Bir | +0.618 |
pees | +0.606 |
20439 | +0.605 |
Neg logit contributions | |
rolet | -0.654 |
orth | -0.627 |
oppy | -0.591 |
olls | -0.560 |
NTS | -0.557 |
Token | a |
Token ID | 257 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
rolet | +1.626 |
orth | +1.611 |
oppy | +1.495 |
olls | +1.416 |
rays | +1.413 |
Neg logit contributions | |
xual | -2.022 |
menstru | -1.904 |
Bir | -1.806 |
20439 | -1.767 |
pees | -1.763 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
rolet | +0.258 |
orth | +0.246 |
oppy | +0.234 |
olls | +0.219 |
NTS | +0.218 |
Neg logit contributions | |
xual | -0.284 |
menstru | -0.269 |
Bir | -0.249 |
ferment | -0.245 |
pees | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
rolet | +0.492 |
orth | +0.472 |
oppy | +0.437 |
NTS | +0.419 |
olls | +0.411 |
Neg logit contributions | |
xual | -0.676 |
menstru | -0.631 |
pees | -0.585 |
ferment | -0.583 |
20439 | -0.581 |
Token | When |
Token ID | 2215 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rolet | +0.414 |
orth | +0.399 |
oppy | +0.375 |
olls | +0.356 |
NTS | +0.354 |
Neg logit contributions | |
xual | -0.434 |
menstru | -0.403 |
ferment | -0.367 |
pees | -0.362 |
Bir | -0.359 |
Token | Gu |
Token ID | 1962 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
rolet | +0.165 |
orth | +0.157 |
oppy | +0.146 |
NTS | +0.137 |
olls | +0.137 |
Neg logit contributions | |
xual | -0.251 |
menstru | -0.238 |
Bir | -0.223 |
pees | -0.220 |
ferment | -0.219 |
Token | cc |
Token ID | 535 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
xual | +2.389 |
menstru | +2.239 |
Bir | +2.036 |
ferment | +1.985 |
pees | +1.978 |
Neg logit contributions | |
rolet | -3.262 |
orth | -3.125 |
oppy | -2.993 |
NTS | -2.849 |
olls | -2.848 |
Token | ifer |
Token ID | 7087 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
rolet | +0.076 |
orth | +0.074 |
oppy | +0.071 |
olls | +0.067 |
igl | +0.067 |
Neg logit contributions | |
xual | -0.055 |
menstru | -0.051 |
Bir | -0.046 |
ferment | -0.044 |
20439 | -0.044 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
xual | +5.162 |
menstru | +4.939 |
Bir | +4.628 |
ferment | +4.538 |
tur | +4.441 |
Neg logit contributions | |
rolet | -5.306 |
orth | -5.080 |
oppy | -4.815 |
igl | -4.521 |
olls | -4.519 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
rolet | +0.180 |
orth | +0.174 |
oppy | +0.162 |
NTS | +0.153 |
olls | +0.151 |
Neg logit contributions | |
xual | -0.264 |
menstru | -0.251 |
Bir | -0.232 |
ferment | -0.230 |
pees | -0.230 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
xual | +0.446 |
menstru | +0.422 |
Bir | +0.384 |
ferment | +0.382 |
pees | +0.380 |
Neg logit contributions | |
rolet | -0.424 |
orth | -0.407 |
oppy | -0.387 |
olls | -0.364 |
NTS | -0.364 |
Token | took |
Token ID | 1718 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
rolet | +0.485 |
orth | +0.467 |
oppy | +0.437 |
olls | +0.409 |
NTS | +0.404 |
Neg logit contributions | |
xual | -0.665 |
menstru | -0.625 |
Bir | -0.584 |
20439 | -0.577 |
pees | -0.574 |
Token | credit |
Token ID | 3884 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
rolet | +1.745 |
orth | +1.656 |
oppy | +1.555 |
olls | +1.467 |
NTS | +1.462 |
Neg logit contributions | |
xual | -2.586 |
menstru | -2.431 |
Bir | -2.296 |
20439 | -2.266 |
pees | -2.243 |
Token | appeared |
Token ID | 4120 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
xual | +1.717 |
menstru | +1.620 |
Bir | +1.499 |
ferment | +1.476 |
20439 | +1.473 |
Neg logit contributions | |
rolet | -1.589 |
orth | -1.530 |
oppy | -1.445 |
olls | -1.368 |
NTS | -1.367 |
Token | to |
Token ID | 284 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
xual | +0.119 |
menstru | +0.114 |
Bir | +0.105 |
ferment | +0.104 |
pees | +0.102 |
Neg logit contributions | |
rolet | -0.110 |
orth | -0.103 |
oppy | -0.099 |
olls | -0.093 |
NTS | -0.092 |
Token | be |
Token ID | 307 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
xual | +0.144 |
menstru | +0.137 |
Bir | +0.125 |
ferment | +0.123 |
pees | +0.122 |
Neg logit contributions | |
rolet | -0.151 |
orth | -0.143 |
oppy | -0.138 |
olls | -0.129 |
NTS | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
rolet | +1.052 |
orth | +1.017 |
oppy | +0.961 |
NTS | +0.917 |
olls | +0.912 |
Neg logit contributions | |
xual | -1.134 |
menstru | -1.053 |
Bir | -0.993 |
20439 | -0.983 |
pees | -0.973 |
Token | grease |
Token ID | 35537 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
rolet | +0.183 |
orth | +0.176 |
oppy | +0.165 |
NTS | +0.157 |
olls | +0.157 |
Neg logit contributions | |
xual | -0.199 |
menstru | -0.185 |
Bir | -0.174 |
20439 | -0.172 |
pees | -0.172 |
Token | pencil |
Token ID | 21613 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
xual | +0.091 |
menstru | +0.085 |
Bir | +0.080 |
20439 | +0.079 |
pees | +0.078 |
Neg logit contributions | |
rolet | -0.083 |
orth | -0.079 |
oppy | -0.075 |
NTS | -0.071 |
olls | -0.070 |
Token | ." |
Token ID | 526 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
xual | +5.633 |
menstru | +5.427 |
ferment | +4.978 |
pees | +4.859 |
Bir | +4.850 |
Neg logit contributions | |
rolet | -5.074 |
orth | -4.624 |
oppy | -4.442 |
olls | -4.158 |
NTS | -4.125 |
Token |
|
Token ID | 198 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
rolet | +1.051 |
orth | +1.001 |
oppy | +0.947 |
olls | +0.890 |
NTS | +0.886 |
Neg logit contributions | |
xual | -1.188 |
menstru | -1.126 |
Bir | -1.044 |
ferment | -1.025 |
pees | -1.022 |
Token |
|
Token ID | 198 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
xual | +0.116 |
menstru | +0.108 |
pees | +0.100 |
ferment | +0.100 |
Bir | +0.100 |
Neg logit contributions | |
rolet | -0.087 |
orth | -0.084 |
oppy | -0.078 |
NTS | -0.074 |
olls | -0.073 |
Token | " |
Token ID | 1 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
xual | +0.184 |
menstru | +0.169 |
ferment | +0.156 |
pees | +0.153 |
20439 | +0.151 |
Neg logit contributions | |
rolet | -0.169 |
orth | -0.164 |
oppy | -0.153 |
rays | -0.146 |
NTS | -0.145 |
Token | As |
Token ID | 1722 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
xual | +0.761 |
menstru | +0.709 |
ferment | +0.643 |
pees | +0.637 |
Bir | +0.631 |
Neg logit contributions | |
rolet | -0.790 |
orth | -0.765 |
oppy | -0.721 |
NTS | -0.687 |
olls | -0.683 |
Token | News |
Token ID | 3000 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
xual | +0.320 |
menstru | +0.304 |
Bir | +0.281 |
ferment | +0.277 |
pees | +0.277 |
Neg logit contributions | |
rolet | -0.278 |
orth | -0.266 |
oppy | -0.251 |
olls | -0.237 |
NTS | -0.236 |
Token | 24 |
Token ID | 1987 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
rolet | +1.250 |
orth | +1.206 |
oppy | +1.127 |
NTS | +1.074 |
olls | +1.070 |
Neg logit contributions | |
xual | -1.525 |
menstru | -1.449 |
Bir | -1.341 |
pees | -1.327 |
ferment | -1.326 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
xual | +1.016 |
menstru | +0.965 |
Bir | +0.898 |
ferment | +0.882 |
pees | +0.879 |
Neg logit contributions | |
rolet | -0.841 |
orth | -0.798 |
oppy | -0.754 |
olls | -0.706 |
NTS | -0.703 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
xual | +0.467 |
menstru | +0.442 |
Bir | +0.408 |
ferment | +0.404 |
pees | +0.401 |
Neg logit contributions | |
rolet | -0.416 |
orth | -0.397 |
oppy | -0.375 |
olls | -0.355 |
NTS | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | +5.94e-03 |
Pos logit contributions | |
rolet | +0.218 |
orth | +0.212 |
oppy | +0.194 |
NTS | +0.184 |
olls | +0.184 |
Neg logit contributions | |
xual | -0.307 |
menstru | -0.286 |
pees | -0.266 |
ferment | -0.265 |
20439 | -0.262 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
xual | +0.012 |
menstru | +0.011 |
ferment | +0.010 |
Bir | +0.010 |
pees | +0.010 |
Neg logit contributions | |
rolet | -0.013 |
orth | -0.012 |
oppy | -0.012 |
olls | -0.011 |
rays | -0.011 |
Token | : |
Token ID | 25 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
xual | +5.394 |
menstru | +5.179 |
Bir | +4.774 |
ferment | +4.655 |
20439 | +4.578 |
Neg logit contributions | |
rolet | -5.145 |
orth | -4.793 |
oppy | -4.659 |
olls | -4.358 |
NTS | -4.277 |
Token | beef |
Token ID | 12023 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
xual | +1.547 |
menstru | +1.454 |
Bir | +1.317 |
ferment | +1.295 |
pees | +1.282 |
Neg logit contributions | |
rolet | -2.012 |
orth | -1.928 |
oppy | -1.845 |
olls | -1.753 |
NTS | -1.746 |
Token | - |
Token ID | 12 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
xual | +1.086 |
menstru | +1.027 |
Bir | +0.956 |
ferment | +0.943 |
pees | +0.932 |
Neg logit contributions | |
rolet | -0.936 |
orth | -0.879 |
oppy | -0.851 |
NTS | -0.796 |
olls | -0.795 |
Token | c |
Token ID | 66 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
xual | +0.112 |
menstru | +0.105 |
Bir | +0.096 |
ferment | +0.094 |
20439 | +0.094 |
Neg logit contributions | |
rolet | -0.131 |
orth | -0.128 |
oppy | -0.120 |
olls | -0.115 |
rays | -0.114 |
Token | attle |
Token ID | 1999 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
xual | +0.320 |
menstru | +0.294 |
Bir | +0.256 |
ferment | +0.250 |
20439 | +0.247 |
Neg logit contributions | |
rolet | -0.697 |
orth | -0.679 |
oppy | -0.653 |
olls | -0.627 |
rays | -0.621 |
Token | Committee |
Token ID | 4606 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
xual | +2.522 |
menstru | +2.400 |
Bir | +2.245 |
ferment | +2.228 |
pees | +2.212 |
Neg logit contributions | |
rolet | -1.454 |
orth | -1.350 |
oppy | -1.268 |
olls | -1.163 |
NTS | -1.150 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
rolet | +0.299 |
orth | +0.284 |
oppy | +0.267 |
olls | +0.250 |
NTS | +0.249 |
Neg logit contributions | |
xual | -0.385 |
menstru | -0.366 |
Bir | -0.341 |
ferment | -0.335 |
pees | -0.334 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
rolet | +0.373 |
orth | +0.355 |
oppy | +0.335 |
NTS | +0.316 |
olls | +0.314 |
Neg logit contributions | |
xual | -0.442 |
menstru | -0.418 |
Bir | -0.386 |
ferment | -0.382 |
pees | -0.381 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
rolet | +0.272 |
orth | +0.264 |
oppy | +0.243 |
NTS | +0.232 |
olls | +0.228 |
Neg logit contributions | |
xual | -0.384 |
menstru | -0.357 |
pees | -0.332 |
ferment | -0.330 |
20439 | -0.328 |
Token | F |
Token ID | 37 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
rolet | +0.072 |
orth | +0.069 |
oppy | +0.065 |
olls | +0.062 |
rays | +0.061 |
Neg logit contributions | |
xual | -0.074 |
menstru | -0.069 |
ferment | -0.063 |
Bir | -0.062 |
pees | -0.062 |
Token | emin |
Token ID | 14857 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
rolet | +1.673 |
orth | +1.645 |
oppy | +1.528 |
olls | +1.451 |
rays | +1.416 |
Neg logit contributions | |
xual | -1.977 |
menstru | -1.864 |
Bir | -1.723 |
ferment | -1.696 |
20439 | -1.695 |
Token | ist |
Token ID | 396 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
xual | +5.654 |
menstru | +5.445 |
Bir | +5.112 |
pees | +5.005 |
ferment | +4.964 |
Neg logit contributions | |
rolet | -4.694 |
orth | -4.356 |
oppy | -4.051 |
rays | -3.898 |
NTS | -3.841 |
Token | groups |
Token ID | 2628 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
rolet | +0.821 |
orth | +0.785 |
oppy | +0.741 |
olls | +0.695 |
NTS | +0.695 |
Neg logit contributions | |
xual | -1.038 |
menstru | -0.975 |
Bir | -0.907 |
pees | -0.899 |
20439 | -0.897 |
Token | financed |
Token ID | 29768 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
rolet | +0.398 |
orth | +0.378 |
oppy | +0.353 |
NTS | +0.329 |
olls | +0.329 |
Neg logit contributions | |
xual | -0.554 |
menstru | -0.524 |
Bir | -0.492 |
pees | -0.483 |
20439 | -0.481 |
Token | include |
Token ID | 2291 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
xual | +0.179 |
menstru | +0.167 |
Bir | +0.153 |
pees | +0.150 |
ferment | +0.150 |
Neg logit contributions | |
rolet | -0.220 |
orth | -0.211 |
oppy | -0.201 |
olls | -0.191 |
NTS | -0.190 |
Token | the |
Token ID | 262 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
xual | +1.526 |
menstru | +1.442 |
Bir | +1.332 |
ferment | +1.308 |
pees | +1.304 |
Neg logit contributions | |
rolet | -1.479 |
orth | -1.412 |
oppy | -1.339 |
olls | -1.263 |
NTS | -1.259 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
xual | +2.606 |
menstru | +2.496 |
Bir | +2.349 |
ferment | +2.319 |
pees | +2.299 |
Neg logit contributions | |
rolet | -1.558 |
orth | -1.456 |
oppy | -1.361 |
olls | -1.259 |
NTS | -1.231 |
Token | Great |
Token ID | 3878 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
rolet | +0.334 |
orth | +0.319 |
oppy | +0.300 |
NTS | +0.284 |
olls | +0.280 |
Neg logit contributions | |
xual | -0.417 |
menstru | -0.394 |
Bir | -0.367 |
pees | -0.362 |
20439 | -0.361 |
Token | Depression |
Token ID | 22483 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
xual | +0.260 |
menstru | +0.245 |
Bir | +0.225 |
pees | +0.222 |
ferment | +0.221 |
Neg logit contributions | |
rolet | -0.244 |
orth | -0.234 |
oppy | -0.221 |
NTS | -0.209 |
olls | -0.208 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
rolet | +0.356 |
orth | +0.339 |
oppy | +0.319 |
NTS | +0.300 |
olls | +0.299 |
Neg logit contributions | |
xual | -0.444 |
menstru | -0.422 |
Bir | -0.392 |
pees | -0.386 |
ferment | -0.384 |
Token | W |
Token ID | 54 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
xual | +0.082 |
menstru | +0.076 |
ferment | +0.069 |
Bir | +0.068 |
pees | +0.068 |
Neg logit contributions | |
rolet | -0.086 |
orth | -0.083 |
oppy | -0.078 |
rays | -0.074 |
olls | -0.074 |
Token | ALTH |
Token ID | 40818 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
rolet | +0.291 |
orth | +0.280 |
oppy | +0.262 |
olls | +0.245 |
NTS | +0.242 |
Neg logit contributions | |
xual | -0.345 |
menstru | -0.326 |
Bir | -0.301 |
ferment | -0.297 |
pees | -0.297 |
Token | AM |
Token ID | 2390 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
orth | +4.732 |
rolet | +4.632 |
oppy | +4.253 |
NTS | +4.192 |
olls | +4.101 |
Neg logit contributions | |
xual | -7.248 |
menstru | -6.803 |
pees | -6.303 |
20439 | -6.240 |
ferment | -6.180 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
rolet | +1.667 |
orth | +1.610 |
oppy | +1.472 |
NTS | +1.412 |
olls | +1.386 |
Neg logit contributions | |
xual | -2.430 |
menstru | -2.298 |
pees | -2.114 |
Bir | -2.110 |
ferment | -2.107 |
Token | Mass |
Token ID | 5674 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
xual | +0.037 |
menstru | +0.035 |
Bir | +0.034 |
pees | +0.033 |
20439 | +0.033 |
Neg logit contributions | |
rolet | -0.014 |
orth | -0.013 |
oppy | -0.011 |
NTS | -0.010 |
olls | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
rolet | +3.314 |
orth | +3.112 |
oppy | +2.905 |
NTS | +2.756 |
olls | +2.723 |
Neg logit contributions | |
xual | -4.777 |
menstru | -4.526 |
Bir | -4.205 |
ferment | -4.157 |
20439 | -4.150 |
Token | -- |
Token ID | 1377 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
xual | +0.623 |
menstru | +0.593 |
Bir | +0.554 |
ferment | +0.544 |
pees | +0.542 |
Neg logit contributions | |
rolet | -0.465 |
orth | -0.441 |
oppy | -0.415 |
olls | -0.387 |
NTS | -0.384 |
Token | do |
Token ID | 466 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
rolet | +0.137 |
orth | +0.131 |
oppy | +0.122 |
NTS | +0.116 |
olls | +0.115 |
Neg logit contributions | |
xual | -0.171 |
menstru | -0.159 |
Bir | -0.151 |
20439 | -0.150 |
pees | -0.148 |
Token | is |
Token ID | 318 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
rolet | +0.099 |
orth | +0.095 |
oppy | +0.088 |
NTS | +0.083 |
olls | +0.083 |
Neg logit contributions | |
xual | -0.125 |
menstru | -0.119 |
Bir | -0.111 |
pees | -0.109 |
ferment | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
rolet | +1.147 |
orth | +1.096 |
oppy | +1.020 |
NTS | +0.980 |
olls | +0.957 |
Neg logit contributions | |
xual | -1.437 |
menstru | -1.350 |
Bir | -1.279 |
pees | -1.260 |
20439 | -1.252 |
Token | determine |
Token ID | 5004 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
rolet | +0.335 |
orth | +0.320 |
oppy | +0.299 |
NTS | +0.288 |
olls | +0.282 |
Neg logit contributions | |
xual | -0.394 |
menstru | -0.367 |
Bir | -0.350 |
20439 | -0.345 |
pees | -0.342 |
Token | how |
Token ID | 703 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
xual | +0.887 |
menstru | +0.839 |
Bir | +0.779 |
pees | +0.764 |
ferment | +0.763 |
Neg logit contributions | |
rolet | -0.794 |
orth | -0.758 |
oppy | -0.716 |
NTS | -0.676 |
olls | -0.674 |
Token | much |
Token ID | 881 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
xual | +0.012 |
menstru | +0.011 |
Bir | +0.010 |
20439 | +0.010 |
pees | +0.010 |
Neg logit contributions | |
rolet | -0.008 |
orth | -0.008 |
oppy | -0.008 |
NTS | -0.007 |
olls | -0.007 |
Token | R |
Token ID | 371 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
orth | +4.567 |
rolet | +4.486 |
NTS | +4.312 |
oppy | +4.171 |
rays | +3.975 |
Neg logit contributions | |
xual | -6.747 |
menstru | -6.230 |
20439 | -6.048 |
Bir | -5.986 |
pees | -5.960 |
Token | FI |
Token ID | 11674 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
rolet | +0.201 |
orth | +0.191 |
oppy | +0.183 |
olls | +0.174 |
NTS | +0.173 |
Neg logit contributions | |
xual | -0.158 |
menstru | -0.148 |
Bir | -0.136 |
ferment | -0.133 |
pees | -0.133 |
Token | is |
Token ID | 318 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
rolet | +0.656 |
orth | +0.634 |
oppy | +0.596 |
NTS | +0.569 |
olls | +0.559 |
Neg logit contributions | |
xual | -0.803 |
menstru | -0.754 |
Bir | -0.706 |
20439 | -0.694 |
pees | -0.690 |
Token | being |
Token ID | 852 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
rolet | +0.346 |
orth | +0.334 |
oppy | +0.314 |
NTS | +0.301 |
olls | +0.299 |
Neg logit contributions | |
xual | -0.371 |
menstru | -0.344 |
Bir | -0.324 |
20439 | -0.317 |
pees | -0.315 |
Token | generated |
Token ID | 7560 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
rolet | +0.062 |
orth | +0.060 |
oppy | +0.056 |
NTS | +0.054 |
olls | +0.054 |
Neg logit contributions | |
xual | -0.071 |
menstru | -0.066 |
Bir | -0.062 |
20439 | -0.061 |
pees | -0.060 |
Token | Stella |
Token ID | 45856 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
rolet | +0.071 |
orth | +0.068 |
oppy | +0.065 |
NTS | +0.061 |
olls | +0.061 |
Neg logit contributions | |
xual | -0.084 |
menstru | -0.079 |
Bir | -0.074 |
pees | -0.073 |
20439 | -0.072 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
rolet | +0.916 |
orth | +0.895 |
oppy | +0.842 |
olls | +0.789 |
NTS | +0.782 |
Neg logit contributions | |
xual | -1.100 |
menstru | -1.006 |
Bir | -0.959 |
20439 | -0.959 |
pees | -0.943 |
Token | 't |
Token ID | 470 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
xual | +0.957 |
menstru | +0.892 |
Bir | +0.814 |
ferment | +0.810 |
pees | +0.808 |
Neg logit contributions | |
rolet | -0.979 |
orth | -0.949 |
oppy | -0.893 |
NTS | -0.847 |
olls | -0.845 |
Token | know |
Token ID | 760 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
xual | +1.097 |
menstru | +1.020 |
Bir | +0.973 |
20439 | +0.953 |
pees | +0.948 |
Neg logit contributions | |
rolet | -0.902 |
orth | -0.864 |
oppy | -0.813 |
olls | -0.766 |
NTS | -0.759 |
Token | how |
Token ID | 703 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
xual | +1.394 |
menstru | +1.315 |
Bir | +1.225 |
pees | +1.199 |
ferment | +1.199 |
Neg logit contributions | |
rolet | -1.218 |
orth | -1.166 |
oppy | -1.099 |
olls | -1.036 |
NTS | -1.033 |
Token | much |
Token ID | 881 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
rolet | +0.114 |
orth | +0.111 |
oppy | +0.104 |
NTS | +0.098 |
olls | +0.098 |
Neg logit contributions | |
xual | -0.154 |
menstru | -0.143 |
Bir | -0.135 |
20439 | -0.133 |
pees | -0.133 |
Token | it |
Token ID | 340 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
orth | +4.104 |
rolet | +3.976 |
oppy | +3.793 |
NTS | +3.659 |
rays | +3.561 |
Neg logit contributions | |
xual | -6.917 |
20439 | -6.203 |
pees | -6.164 |
menstru | -6.101 |
Bir | -6.079 |
Token | had |
Token ID | 550 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
rolet | +0.636 |
orth | +0.619 |
oppy | +0.580 |
olls | +0.545 |
rays | +0.543 |
Neg logit contributions | |
xual | -0.813 |
menstru | -0.741 |
Bir | -0.712 |
20439 | -0.711 |
pees | -0.703 |
Token | worsened |
Token ID | 44838 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
xual | +0.356 |
menstru | +0.330 |
Bir | +0.313 |
20439 | +0.309 |
pees | +0.306 |
Neg logit contributions | |
rolet | -0.312 |
orth | -0.297 |
oppy | -0.283 |
olls | -0.266 |
NTS | -0.263 |
Token | , |
Token ID | 11 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
rolet | +0.095 |
orth | +0.091 |
oppy | +0.085 |
olls | +0.080 |
NTS | +0.080 |
Neg logit contributions | |
xual | -0.125 |
menstru | -0.118 |
Bir | -0.111 |
20439 | -0.110 |
pees | -0.109 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
rolet | +0.108 |
orth | +0.103 |
oppy | +0.097 |
olls | +0.091 |
NTS | +0.090 |
Neg logit contributions | |
xual | -0.140 |
menstru | -0.131 |
Bir | -0.123 |
pees | -0.122 |
20439 | -0.121 |
Token | 2 |
Token ID | 362 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
xual | +0.427 |
menstru | +0.406 |
Bir | +0.376 |
pees | +0.372 |
ferment | +0.371 |
Neg logit contributions | |
rolet | -0.355 |
orth | -0.340 |
oppy | -0.318 |
NTS | -0.302 |
olls | -0.301 |
Token | - |
Token ID | 12 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
rolet | +1.617 |
orth | +1.554 |
oppy | +1.443 |
NTS | +1.366 |
olls | +1.362 |
Neg logit contributions | |
xual | -2.171 |
menstru | -2.072 |
pees | -1.907 |
Bir | -1.902 |
20439 | -1.894 |
Token | 3 |
Token ID | 18 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
rolet | +0.805 |
orth | +0.788 |
oppy | +0.734 |
olls | +0.708 |
rays | +0.707 |
Neg logit contributions | |
xual | -0.715 |
menstru | -0.674 |
ferment | -0.603 |
pees | -0.598 |
Bir | -0.597 |
Token | ). |
Token ID | 737 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
rolet | +1.258 |
orth | +1.201 |
oppy | +1.102 |
NTS | +1.036 |
olls | +1.031 |
Neg logit contributions | |
xual | -2.159 |
menstru | -2.071 |
Bir | -1.937 |
pees | -1.935 |
20439 | -1.918 |
Token | The |
Token ID | 383 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
xual | +0.218 |
menstru | +0.205 |
pees | +0.189 |
Bir | +0.189 |
ferment | +0.187 |
Neg logit contributions | |
rolet | -0.188 |
orth | -0.181 |
oppy | -0.169 |
NTS | -0.161 |
olls | -0.160 |
Token | general |
Token ID | 2276 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
rolet | +1.244 |
orth | +1.214 |
oppy | +1.129 |
NTS | +1.084 |
olls | +1.071 |
Neg logit contributions | |
xual | -1.534 |
menstru | -1.408 |
pees | -1.331 |
Bir | -1.322 |
20439 | -1.308 |
Token | - |
Token ID | 12 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
rolet | +5.019 |
orth | +5.017 |
oppy | +4.571 |
NTS | +4.397 |
rays | +4.322 |
Neg logit contributions | |
xual | -6.074 |
menstru | -5.534 |
pees | -5.344 |
20439 | -5.258 |
Bir | -5.249 |
Token | circ |
Token ID | 21170 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
xual | +0.070 |
menstru | +0.067 |
Bir | +0.062 |
ferment | +0.061 |
pees | +0.061 |
Neg logit contributions | |
rolet | -0.066 |
orth | -0.062 |
oppy | -0.059 |
NTS | -0.055 |
olls | -0.055 |
Token | ulation |
Token ID | 1741 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
rolet | +0.616 |
orth | +0.580 |
oppy | +0.533 |
rays | +0.496 |
olls | +0.495 |
Neg logit contributions | |
xual | -1.178 |
menstru | -1.133 |
Bir | -1.071 |
ferment | -1.052 |
20439 | -1.049 |
Token | models |
Token ID | 4981 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
xual | +0.272 |
menstru | +0.256 |
Bir | +0.237 |
pees | +0.235 |
20439 | +0.232 |
Neg logit contributions | |
rolet | -0.241 |
orth | -0.232 |
oppy | -0.218 |
NTS | -0.206 |
olls | -0.206 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
xual | +0.092 |
menstru | +0.086 |
Bir | +0.081 |
pees | +0.080 |
20439 | +0.079 |
Neg logit contributions | |
rolet | -0.075 |
orth | -0.072 |
oppy | -0.067 |
NTS | -0.064 |
olls | -0.063 |
Token | � |
Token ID | 447 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
rolet | +1.172 |
orth | +1.124 |
oppy | +1.046 |
olls | +0.982 |
NTS | +0.969 |
Neg logit contributions | |
xual | -1.573 |
menstru | -1.494 |
Bir | -1.390 |
20439 | -1.369 |
ferment | -1.368 |
Token | � |
Token ID | 247 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
rolet | +0.539 |
orth | +0.514 |
oppy | +0.477 |
olls | +0.444 |
NTS | +0.443 |
Neg logit contributions | |
xual | -0.823 |
menstru | -0.792 |
Bir | -0.736 |
ferment | -0.730 |
pees | -0.726 |
Token | s |
Token ID | 82 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
rolet | +0.685 |
orth | +0.656 |
oppy | +0.613 |
olls | +0.575 |
NTS | +0.572 |
Neg logit contributions | |
xual | -0.870 |
menstru | -0.827 |
Bir | -0.764 |
ferment | -0.756 |
pees | -0.751 |
Token | younger |
Token ID | 7099 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
rolet | +0.523 |
orth | +0.499 |
oppy | +0.473 |
olls | +0.446 |
NTS | +0.443 |
Neg logit contributions | |
xual | -0.604 |
menstru | -0.564 |
Bir | -0.524 |
20439 | -0.520 |
pees | -0.514 |
Token | brother |
Token ID | 3956 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
xual | +0.888 |
menstru | +0.825 |
Bir | +0.758 |
20439 | +0.749 |
pees | +0.747 |
Neg logit contributions | |
rolet | -1.018 |
orth | -0.974 |
oppy | -0.929 |
NTS | -0.884 |
olls | -0.882 |
Token | Vin |
Token ID | 11820 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
rolet | +0.799 |
orth | +0.763 |
oppy | +0.716 |
NTS | +0.674 |
olls | +0.672 |
Neg logit contributions | |
xual | -1.010 |
menstru | -0.956 |
Bir | -0.887 |
ferment | -0.872 |
20439 | -0.870 |
Token | od |
Token ID | 375 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
rolet | +4.145 |
orth | +4.036 |
oppy | +3.664 |
olls | +3.448 |
rays | +3.330 |
Neg logit contributions | |
xual | -7.191 |
menstru | -6.857 |
Bir | -6.386 |
20439 | -6.350 |
ferment | -6.323 |
Token | , |
Token ID | 11 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
rolet | +1.747 |
orth | +1.664 |
oppy | +1.560 |
olls | +1.465 |
NTS | +1.455 |
Neg logit contributions | |
xual | -2.271 |
menstru | -2.153 |
Bir | -2.003 |
ferment | -1.979 |
pees | -1.966 |
Token | brother |
Token ID | 3956 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
rolet | +0.142 |
orth | +0.135 |
oppy | +0.127 |
NTS | +0.120 |
olls | +0.119 |
Neg logit contributions | |
xual | -0.178 |
menstru | -0.168 |
Bir | -0.156 |
pees | -0.154 |
20439 | -0.153 |
Token | - |
Token ID | 12 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
rolet | +1.359 |
orth | +1.287 |
oppy | +1.196 |
NTS | +1.112 |
olls | +1.110 |
Neg logit contributions | |
xual | -2.186 |
menstru | -2.081 |
Bir | -1.944 |
ferment | -1.917 |
pees | -1.914 |
Token | in |
Token ID | 259 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
rolet | +0.491 |
orth | +0.470 |
oppy | +0.447 |
rays | +0.423 |
olls | +0.423 |
Neg logit contributions | |
xual | -0.440 |
menstru | -0.408 |
Bir | -0.370 |
20439 | -0.367 |
ferment | -0.366 |
Token | , |
Token ID | 11 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
xual | +0.017 |
menstru | +0.016 |
Bir | +0.015 |
pees | +0.015 |
20439 | +0.014 |
Neg logit contributions | |
rolet | -0.013 |
orth | -0.012 |
oppy | -0.012 |
NTS | -0.011 |
olls | -0.011 |
Token | but |
Token ID | 475 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
rolet | +0.148 |
orth | +0.141 |
oppy | +0.133 |
NTS | +0.125 |
olls | +0.124 |
Neg logit contributions | |
xual | -0.191 |
menstru | -0.178 |
Bir | -0.168 |
pees | -0.165 |
20439 | -0.165 |
Token | there |
Token ID | 612 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
xual | +1.232 |
menstru | +1.156 |
Bir | +1.080 |
pees | +1.064 |
20439 | +1.061 |
Neg logit contributions | |
rolet | -1.084 |
orth | -1.036 |
oppy | -0.978 |
NTS | -0.927 |
olls | -0.923 |
Token | is |
Token ID | 318 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
rolet | +0.841 |
orth | +0.811 |
oppy | +0.756 |
olls | +0.718 |
NTS | +0.716 |
Neg logit contributions | |
xual | -1.034 |
menstru | -0.978 |
Bir | -0.907 |
pees | -0.896 |
20439 | -0.896 |
Token | not |
Token ID | 407 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
rolet | +0.612 |
orth | +0.593 |
oppy | +0.557 |
NTS | +0.534 |
olls | +0.527 |
Neg logit contributions | |
xual | -0.671 |
menstru | -0.627 |
Bir | -0.589 |
pees | -0.585 |
20439 | -0.582 |
Token | much |
Token ID | 881 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
xual | +0.482 |
menstru | +0.455 |
Bir | +0.421 |
ferment | +0.413 |
pees | +0.413 |
Neg logit contributions | |
rolet | -0.456 |
orth | -0.436 |
oppy | -0.412 |
olls | -0.389 |
NTS | -0.388 |
Token | I |
Token ID | 314 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
orth | +4.388 |
rolet | +4.184 |
oppy | +3.942 |
NTS | +3.922 |
olls | +3.655 |
Neg logit contributions | |
xual | -6.510 |
menstru | -5.974 |
pees | -5.861 |
Bir | -5.778 |
20439 | -5.722 |
Token | can |
Token ID | 460 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
rolet | +0.410 |
orth | +0.392 |
oppy | +0.364 |
NTS | +0.347 |
olls | +0.342 |
Neg logit contributions | |
xual | -0.498 |
menstru | -0.464 |
Bir | -0.438 |
pees | -0.431 |
20439 | -0.430 |
Token | do |
Token ID | 466 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
rolet | +0.681 |
orth | +0.648 |
oppy | +0.602 |
NTS | +0.573 |
olls | +0.569 |
Neg logit contributions | |
xual | -0.852 |
menstru | -0.793 |
Bir | -0.754 |
20439 | -0.745 |
pees | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
xual | +0.176 |
menstru | +0.167 |
Bir | +0.156 |
pees | +0.153 |
ferment | +0.152 |
Neg logit contributions | |
rolet | -0.144 |
orth | -0.138 |
oppy | -0.129 |
NTS | -0.121 |
olls | -0.121 |
Token | As |
Token ID | 1081 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
rolet | +0.936 |
orth | +0.893 |
oppy | +0.832 |
NTS | +0.810 |
olls | +0.782 |
Neg logit contributions | |
xual | -1.181 |
menstru | -1.107 |
pees | -1.020 |
ferment | -1.016 |
Bir | -1.015 |
Token | that |
Token ID | 326 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
rolet | +1.117 |
orth | +1.072 |
oppy | +1.000 |
NTS | +0.955 |
olls | +0.949 |
Neg logit contributions | |
xual | -1.409 |
menstru | -1.319 |
Bir | -1.236 |
pees | -1.231 |
20439 | -1.217 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
rolet | +0.817 |
orth | +0.794 |
oppy | +0.748 |
NTS | +0.716 |
olls | +0.709 |
Neg logit contributions | |
xual | -0.958 |
menstru | -0.891 |
pees | -0.839 |
Bir | -0.835 |
20439 | -0.832 |
Token | reference |
Token ID | 4941 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
rolet | +0.469 |
orth | +0.453 |
oppy | +0.427 |
NTS | +0.407 |
olls | +0.403 |
Neg logit contributions | |
xual | -0.545 |
menstru | -0.509 |
Bir | -0.474 |
pees | -0.472 |
20439 | -0.468 |
Token | to |
Token ID | 284 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
rolet | +0.236 |
orth | +0.226 |
oppy | +0.212 |
NTS | +0.203 |
olls | +0.200 |
Neg logit contributions | |
xual | -0.309 |
menstru | -0.290 |
Bir | -0.271 |
pees | -0.268 |
20439 | -0.267 |
Token | Sh |
Token ID | 911 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
rolet | +0.384 |
orth | +0.370 |
oppy | +0.350 |
NTS | +0.333 |
olls | +0.332 |
Neg logit contributions | |
xual | -0.418 |
menstru | -0.388 |
Bir | -0.362 |
pees | -0.361 |
20439 | -0.359 |
Token | av |
Token ID | 615 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
rolet | +0.522 |
orth | +0.507 |
oppy | +0.475 |
olls | +0.445 |
rays | +0.438 |
Neg logit contributions | |
xual | -0.622 |
menstru | -0.588 |
Bir | -0.547 |
ferment | -0.537 |
pees | -0.537 |
Token | iv |
Token ID | 452 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rolet | +5.831 |
orth | +5.725 |
oppy | +5.202 |
olls | +5.078 |
igl | +5.049 |
Neg logit contributions | |
xual | -5.374 |
menstru | -5.040 |
20439 | -4.738 |
Bir | -4.618 |
女 | -4.536 |
Token | ( |
Token ID | 357 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
rolet | +2.314 |
orth | +2.225 |
oppy | +2.082 |
olls | +1.967 |
rays | +1.965 |
Neg logit contributions | |
xual | -2.656 |
menstru | -2.484 |
Bir | -2.289 |
20439 | -2.279 |
pees | -2.279 |
Token | 2008 |
Token ID | 11528 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
rolet | +0.598 |
orth | +0.583 |
oppy | +0.547 |
rays | +0.520 |
NTS | +0.519 |
Neg logit contributions | |
xual | -0.546 |
menstru | -0.508 |
ferment | -0.460 |
pees | -0.455 |
Bir | -0.454 |
Token | ) |
Token ID | 8 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
rolet | +0.515 |
orth | +0.487 |
oppy | +0.453 |
NTS | +0.422 |
olls | +0.421 |
Neg logit contributions | |
xual | -0.791 |
menstru | -0.752 |
Bir | -0.703 |
pees | -0.695 |
ferment | -0.694 |
Token | should |
Token ID | 815 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
rolet | +0.369 |
orth | +0.355 |
oppy | +0.332 |
NTS | +0.314 |
olls | +0.313 |
Neg logit contributions | |
xual | -0.461 |
menstru | -0.436 |
Bir | -0.407 |
pees | -0.400 |
ferment | -0.399 |
Token | 121 |
Token ID | 20416 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
rolet | +0.503 |
orth | +0.487 |
oppy | +0.458 |
NTS | +0.442 |
olls | +0.435 |
Neg logit contributions | |
xual | -0.522 |
menstru | -0.484 |
Bir | -0.449 |
20439 | -0.448 |
pees | -0.447 |
Token | months |
Token ID | 1933 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
xual | +1.780 |
menstru | +1.671 |
Bir | +1.524 |
ferment | +1.493 |
pees | +1.485 |
Neg logit contributions | |
rolet | -2.212 |
orth | -2.121 |
oppy | -2.024 |
olls | -1.925 |
NTS | -1.916 |
Token | . |
Token ID | 13 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
xual | +0.170 |
menstru | +0.161 |
Bir | +0.150 |
ferment | +0.147 |
pees | +0.147 |
Neg logit contributions | |
rolet | -0.136 |
orth | -0.129 |
oppy | -0.121 |
olls | -0.114 |
NTS | -0.113 |
Token | On |
Token ID | 1550 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
xual | +0.199 |
menstru | +0.189 |
ferment | +0.173 |
pees | +0.173 |
Bir | +0.172 |
Neg logit contributions | |
rolet | -0.162 |
orth | -0.155 |
oppy | -0.145 |
NTS | -0.139 |
olls | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
rolet | +2.405 |
orth | +2.343 |
oppy | +2.199 |
NTS | +2.088 |
olls | +2.077 |
Neg logit contributions | |
xual | -2.737 |
menstru | -2.573 |
Bir | -2.376 |
pees | -2.360 |
20439 | -2.352 |
Token | flip |
Token ID | 14283 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
rolet | +0.914 |
orth | +0.878 |
oppy | +0.825 |
NTS | +0.788 |
olls | +0.784 |
Neg logit contributions | |
xual | -1.010 |
menstru | -0.951 |
Bir | -0.881 |
pees | -0.871 |
20439 | -0.864 |
Token | side |
Token ID | 1735 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
rolet | +3.497 |
orth | +3.408 |
oppy | +3.019 |
olls | +2.701 |
NTS | +2.669 |
Neg logit contributions | |
xual | -7.677 |
menstru | -7.319 |
Bir | -6.900 |
pees | -6.857 |
20439 | -6.815 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
rolet | +1.991 |
orth | +1.887 |
oppy | +1.788 |
olls | +1.673 |
NTS | +1.663 |
Neg logit contributions | |
xual | -2.401 |
menstru | -2.280 |
Bir | -2.119 |
ferment | -2.085 |
pees | -2.072 |
Token | there |
Token ID | 612 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
rolet | +0.057 |
orth | +0.055 |
oppy | +0.052 |
NTS | +0.049 |
olls | +0.049 |
Neg logit contributions | |
xual | -0.065 |
menstru | -0.062 |
Bir | -0.057 |
pees | -0.057 |
ferment | -0.056 |
Token | seems |
Token ID | 2331 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
rolet | +0.859 |
orth | +0.824 |
oppy | +0.769 |
olls | +0.731 |
NTS | +0.727 |
Neg logit contributions | |
xual | -1.037 |
menstru | -0.983 |
Bir | -0.910 |
ferment | -0.898 |
20439 | -0.892 |
Token | to |
Token ID | 284 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
rolet | +0.719 |
orth | +0.682 |
oppy | +0.649 |
olls | +0.607 |
NTS | +0.604 |
Neg logit contributions | |
xual | -0.818 |
menstru | -0.777 |
Bir | -0.720 |
ferment | -0.710 |
pees | -0.704 |
Token | would |
Token ID | 561 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
rolet | +0.757 |
orth | +0.743 |
oppy | +0.693 |
olls | +0.660 |
rays | +0.650 |
Neg logit contributions | |
xual | -0.958 |
menstru | -0.887 |
20439 | -0.859 |
Bir | -0.846 |
pees | -0.825 |
Token | have |
Token ID | 423 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
rolet | +0.599 |
orth | +0.575 |
oppy | +0.544 |
olls | +0.509 |
NTS | +0.505 |
Neg logit contributions | |
xual | -0.617 |
menstru | -0.579 |
Bir | -0.550 |
20439 | -0.547 |
pees | -0.538 |
Token | created |
Token ID | 2727 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
rolet | +0.274 |
orth | +0.261 |
oppy | +0.246 |
olls | +0.232 |
NTS | +0.231 |
Neg logit contributions | |
xual | -0.327 |
menstru | -0.307 |
Bir | -0.290 |
20439 | -0.286 |
pees | -0.284 |
Token | just |
Token ID | 655 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
xual | +1.201 |
menstru | +1.134 |
Bir | +1.052 |
pees | +1.032 |
20439 | +1.030 |
Neg logit contributions | |
rolet | -1.129 |
orth | -1.081 |
oppy | -1.024 |
olls | -0.965 |
NTS | -0.965 |
Token | too |
Token ID | 1165 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
rolet | +0.781 |
orth | +0.756 |
oppy | +0.709 |
NTS | +0.667 |
olls | +0.666 |
Neg logit contributions | |
xual | -0.951 |
menstru | -0.895 |
20439 | -0.839 |
Bir | -0.838 |
pees | -0.825 |
Token | much |
Token ID | 881 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
orth | +3.660 |
rolet | +3.638 |
oppy | +3.444 |
NTS | +3.142 |
olls | +3.099 |
Neg logit contributions | |
xual | -6.571 |
menstru | -6.171 |
20439 | -6.073 |
Bir | -5.939 |
pees | -5.910 |
Token | tension |
Token ID | 12097 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
rolet | +5.062 |
orth | +5.028 |
oppy | +4.793 |
NTS | +4.700 |
Registry | +4.446 |
Neg logit contributions | |
xual | -5.548 |
20439 | -5.094 |
menstru | -5.011 |
pees | -4.969 |
Bir | -4.855 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
xual | +0.223 |
menstru | +0.212 |
Bir | +0.199 |
20439 | +0.195 |
pees | +0.195 |
Neg logit contributions | |
rolet | -0.168 |
orth | -0.160 |
oppy | -0.150 |
olls | -0.141 |
NTS | -0.140 |
Token | knowing |
Token ID | 6970 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
rolet | +0.407 |
orth | +0.392 |
oppy | +0.367 |
NTS | +0.350 |
olls | +0.344 |
Neg logit contributions | |
xual | -0.520 |
menstru | -0.486 |
20439 | -0.464 |
Bir | -0.461 |
pees | -0.456 |
Token | you |
Token ID | 345 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
rolet | +0.062 |
orth | +0.059 |
oppy | +0.056 |
NTS | +0.053 |
olls | +0.052 |
Neg logit contributions | |
xual | -0.078 |
menstru | -0.073 |
Bir | -0.069 |
20439 | -0.068 |
pees | -0.068 |
Token | were |
Token ID | 547 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
rolet | +1.400 |
orth | +1.341 |
oppy | +1.254 |
NTS | +1.189 |
olls | +1.182 |
Neg logit contributions | |
xual | -1.694 |
menstru | -1.536 |
20439 | -1.491 |
Bir | -1.476 |
pees | -1.464 |
Token | on |
Token ID | 319 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
rolet | +0.323 |
orth | +0.309 |
oppy | +0.295 |
NTS | +0.276 |
olls | +0.275 |
Neg logit contributions | |
xual | -0.421 |
menstru | -0.397 |
Bir | -0.374 |
pees | -0.367 |
20439 | -0.365 |
Token | just |
Token ID | 655 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
rolet | +0.619 |
orth | +0.592 |
oppy | +0.560 |
NTS | +0.529 |
olls | +0.523 |
Neg logit contributions | |
xual | -0.788 |
menstru | -0.745 |
Bir | -0.697 |
pees | -0.687 |
20439 | -0.683 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
rolet | +0.921 |
orth | +0.896 |
oppy | +0.836 |
NTS | +0.801 |
olls | +0.790 |
Neg logit contributions | |
xual | -1.211 |
menstru | -1.141 |
Bir | -1.072 |
20439 | -1.059 |
pees | -1.052 |
Token | see |
Token ID | 766 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
rolet | +0.415 |
orth | +0.403 |
oppy | +0.379 |
NTS | +0.361 |
olls | +0.358 |
Neg logit contributions | |
xual | -0.460 |
menstru | -0.428 |
Bir | -0.405 |
20439 | -0.399 |
pees | -0.394 |
Token | how |
Token ID | 703 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
xual | +0.343 |
menstru | +0.324 |
Bir | +0.303 |
pees | +0.297 |
20439 | +0.296 |
Neg logit contributions | |
rolet | -0.274 |
orth | -0.263 |
oppy | -0.248 |
NTS | -0.234 |
olls | -0.232 |
Token | much |
Token ID | 881 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
rolet | +0.543 |
orth | +0.525 |
oppy | +0.497 |
NTS | +0.469 |
rays | +0.462 |
Neg logit contributions | |
xual | -0.781 |
menstru | -0.736 |
Bir | -0.693 |
20439 | -0.685 |
pees | -0.682 |
Token | R |
Token ID | 371 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
orth | +4.441 |
rolet | +4.403 |
NTS | +4.166 |
oppy | +4.140 |
rays | +4.048 |
Neg logit contributions | |
xual | -6.241 |
menstru | -5.778 |
20439 | -5.557 |
Bir | -5.529 |
pees | -5.482 |
Token | FI |
Token ID | 11674 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
rolet | +0.025 |
orth | +0.024 |
oppy | +0.023 |
olls | +0.022 |
NTS | +0.022 |
Neg logit contributions | |
xual | -0.023 |
menstru | -0.021 |
Bir | -0.019 |
ferment | -0.019 |
20439 | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
rolet | +0.401 |
orth | +0.385 |
oppy | +0.362 |
NTS | +0.343 |
olls | +0.341 |
Neg logit contributions | |
xual | -0.527 |
menstru | -0.494 |
Bir | -0.463 |
20439 | -0.455 |
pees | -0.452 |
Token | getting |
Token ID | 1972 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rolet | +0.375 |
orth | +0.360 |
oppy | +0.338 |
NTS | +0.324 |
olls | +0.323 |
Neg logit contributions | |
xual | -0.409 |
menstru | -0.377 |
Bir | -0.355 |
20439 | -0.347 |
pees | -0.346 |
Token | into |
Token ID | 656 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
xual | +0.227 |
menstru | +0.214 |
Bir | +0.200 |
20439 | +0.196 |
pees | +0.195 |
Neg logit contributions | |
rolet | -0.206 |
orth | -0.198 |
oppy | -0.187 |
olls | -0.178 |
NTS | -0.177 |
Token | not |
Token ID | 407 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
xual | +0.901 |
menstru | +0.856 |
Bir | +0.796 |
ferment | +0.781 |
pees | +0.780 |
Neg logit contributions | |
rolet | -0.739 |
orth | -0.703 |
oppy | -0.662 |
olls | -0.621 |
NTS | -0.621 |
Token | a |
Token ID | 257 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
xual | +0.747 |
menstru | +0.704 |
Bir | +0.653 |
ferment | +0.640 |
pees | +0.639 |
Neg logit contributions | |
rolet | -0.685 |
orth | -0.652 |
oppy | -0.617 |
olls | -0.582 |
NTS | -0.581 |
Token | backup |
Token ID | 11559 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
rolet | +0.420 |
orth | +0.398 |
oppy | +0.375 |
NTS | +0.351 |
olls | +0.350 |
Neg logit contributions | |
xual | -0.545 |
menstru | -0.515 |
Bir | -0.481 |
pees | -0.472 |
ferment | -0.471 |
Token | system |
Token ID | 1080 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
rolet | +1.177 |
orth | +1.127 |
oppy | +1.063 |
NTS | +1.004 |
olls | +0.991 |
Neg logit contributions | |
xual | -1.430 |
menstru | -1.350 |
Bir | -1.250 |
pees | -1.243 |
20439 | -1.238 |
Token | . |
Token ID | 764 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
xual | +0.270 |
menstru | +0.256 |
Bir | +0.239 |
ferment | +0.235 |
pees | +0.235 |
Neg logit contributions | |
rolet | -0.209 |
orth | -0.198 |
oppy | -0.186 |
olls | -0.175 |
NTS | -0.174 |
Token | Rest |
Token ID | 8324 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
rolet | +0.831 |
orth | +0.788 |
oppy | +0.746 |
NTS | +0.714 |
olls | +0.698 |
Neg logit contributions | |
xual | -1.007 |
menstru | -0.948 |
Bir | -0.874 |
ferment | -0.864 |
pees | -0.862 |
Token | ores |
Token ID | 2850 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
rolet | +2.921 |
orth | +2.732 |
oppy | +2.495 |
rays | +2.169 |
olls | +2.158 |
Neg logit contributions | |
xual | -8.196 |
menstru | -7.827 |
Bir | -7.447 |
20439 | -7.353 |
ferment | -7.295 |
Token | are |
Token ID | 389 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
rolet | +1.873 |
orth | +1.780 |
oppy | +1.692 |
NTS | +1.605 |
rays | +1.595 |
Neg logit contributions | |
xual | -2.161 |
menstru | -2.032 |
Bir | -1.907 |
20439 | -1.858 |
pees | -1.848 |
Token | a |
Token ID | 257 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
xual | +0.204 |
menstru | +0.192 |
Bir | +0.179 |
20439 | +0.175 |
pees | +0.174 |
Neg logit contributions | |
rolet | -0.182 |
orth | -0.173 |
oppy | -0.163 |
NTS | -0.155 |
olls | -0.154 |
Token | non |
Token ID | 1729 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
xual | +0.717 |
menstru | +0.680 |
Bir | +0.632 |
pees | +0.620 |
ferment | +0.620 |
Neg logit contributions | |
rolet | -0.602 |
orth | -0.572 |
oppy | -0.540 |
olls | -0.506 |
NTS | -0.505 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
rolet | +0.385 |
orth | +0.365 |
oppy | +0.345 |
olls | +0.323 |
NTS | +0.321 |
Neg logit contributions | |
xual | -0.488 |
menstru | -0.465 |
Bir | -0.432 |
ferment | -0.426 |
pees | -0.424 |
Token | of |
Token ID | 286 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
rolet | +1.315 |
orth | +1.256 |
oppy | +1.169 |
olls | +1.090 |
NTS | +1.088 |
Neg logit contributions | |
xual | -2.017 |
menstru | -1.914 |
Bir | -1.797 |
20439 | -1.772 |
pees | -1.770 |
Token | the |
Token ID | 262 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
xual | +0.066 |
menstru | +0.062 |
Bir | +0.057 |
ferment | +0.056 |
pees | +0.056 |
Neg logit contributions | |
rolet | -0.068 |
orth | -0.065 |
oppy | -0.062 |
olls | -0.059 |
NTS | -0.059 |
Token | two |
Token ID | 734 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
rolet | +0.502 |
orth | +0.482 |
oppy | +0.460 |
NTS | +0.438 |
olls | +0.434 |
Neg logit contributions | |
xual | -0.461 |
menstru | -0.428 |
Bir | -0.394 |
20439 | -0.392 |
pees | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
rolet | +0.738 |
orth | +0.719 |
oppy | +0.684 |
olls | +0.653 |
NTS | +0.651 |
Neg logit contributions | |
xual | -0.623 |
menstru | -0.573 |
Bir | -0.525 |
20439 | -0.524 |
pees | -0.517 |
Token | Not |
Token ID | 1892 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
rolet | +0.056 |
orth | +0.054 |
oppy | +0.051 |
NTS | +0.049 |
olls | +0.048 |
Neg logit contributions | |
xual | -0.064 |
menstru | -0.061 |
ferment | -0.056 |
pees | -0.055 |
Bir | -0.055 |
Token | much |
Token ID | 881 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
xual | +1.002 |
menstru | +0.935 |
Bir | +0.870 |
20439 | +0.858 |
pees | +0.855 |
Neg logit contributions | |
rolet | -0.933 |
orth | -0.902 |
oppy | -0.846 |
NTS | -0.804 |
olls | -0.800 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
orth | +4.472 |
rolet | +4.309 |
oppy | +4.075 |
NTS | +4.026 |
rays | +3.862 |
Neg logit contributions | |
xual | -6.091 |
menstru | -5.587 |
20439 | -5.501 |
pees | -5.408 |
Bir | -5.391 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
rolet | +1.322 |
orth | +1.276 |
oppy | +1.179 |
olls | +1.117 |
NTS | +1.114 |
Neg logit contributions | |
xual | -1.726 |
menstru | -1.620 |
Bir | -1.519 |
20439 | -1.510 |
pees | -1.499 |
Token | go |
Token ID | 467 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
xual | +0.403 |
menstru | +0.374 |
Bir | +0.351 |
20439 | +0.350 |
pees | +0.346 |
Neg logit contributions | |
rolet | -0.344 |
orth | -0.330 |
oppy | -0.313 |
olls | -0.296 |
NTS | -0.292 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rolet | +0.333 |
orth | +0.320 |
oppy | +0.301 |
olls | +0.282 |
NTS | +0.279 |
Neg logit contributions | |
xual | -0.446 |
menstru | -0.420 |
Bir | -0.394 |
20439 | -0.392 |
pees | -0.387 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
rolet | +0.264 |
orth | +0.252 |
oppy | +0.238 |
olls | +0.223 |
NTS | +0.223 |
Neg logit contributions | |
xual | -0.321 |
menstru | -0.300 |
Bir | -0.278 |
20439 | -0.276 |
pees | -0.275 |
Token | don |
Token ID | 836 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
xual | +0.336 |
menstru | +0.313 |
Bir | +0.295 |
20439 | +0.292 |
pees | +0.291 |
Neg logit contributions | |
rolet | -0.289 |
orth | -0.277 |
oppy | -0.262 |
olls | -0.246 |
NTS | -0.245 |
Token | 't |
Token ID | 470 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
xual | +0.216 |
menstru | +0.201 |
ferment | +0.183 |
pees | +0.183 |
Bir | +0.183 |
Neg logit contributions | |
rolet | -0.212 |
orth | -0.206 |
oppy | -0.193 |
rays | -0.182 |
NTS | -0.182 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
xual | +0.682 |
menstru | +0.643 |
Bir | +0.607 |
20439 | +0.596 |
pees | +0.595 |
Neg logit contributions | |
rolet | -0.558 |
orth | -0.532 |
oppy | -0.502 |
olls | -0.471 |
NTS | -0.470 |
Token | really |
Token ID | 1107 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
rolet | +1.973 |
orth | +1.874 |
oppy | +1.774 |
NTS | +1.665 |
olls | +1.659 |
Neg logit contributions | |
xual | -2.507 |
menstru | -2.295 |
Bir | -2.254 |
20439 | -2.248 |
pees | -2.202 |
Token | see |
Token ID | 766 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
rolet | +0.598 |
orth | +0.573 |
oppy | +0.538 |
olls | +0.507 |
NTS | +0.506 |
Neg logit contributions | |
xual | -0.736 |
menstru | -0.683 |
Bir | -0.658 |
20439 | -0.651 |
pees | -0.642 |
Token | much |
Token ID | 881 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
rolet | +0.020 |
orth | +0.019 |
oppy | +0.018 |
olls | +0.017 |
NTS | +0.017 |
Neg logit contributions | |
xual | -0.022 |
menstru | -0.020 |
Bir | -0.019 |
pees | -0.019 |
20439 | -0.019 |
Token | about |
Token ID | 546 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
orth | +3.761 |
rolet | +3.738 |
oppy | +3.511 |
NTS | +3.316 |
rays | +3.207 |
Neg logit contributions | |
xual | -6.719 |
menstru | -6.355 |
Bir | -6.195 |
pees | -6.152 |
20439 | -6.128 |
Token | the |
Token ID | 262 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
rolet | +0.730 |
orth | +0.701 |
oppy | +0.666 |
olls | +0.631 |
NTS | +0.630 |
Neg logit contributions | |
xual | -0.770 |
menstru | -0.726 |
Bir | -0.680 |
20439 | -0.664 |
pees | -0.664 |
Token | past |
Token ID | 1613 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
rolet | +0.914 |
orth | +0.878 |
oppy | +0.840 |
NTS | +0.791 |
olls | +0.789 |
Neg logit contributions | |
xual | -1.006 |
menstru | -0.946 |
Bir | -0.890 |
20439 | -0.873 |
pees | -0.868 |
Token | there |
Token ID | 612 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
rolet | +0.085 |
orth | +0.081 |
oppy | +0.076 |
olls | +0.071 |
NTS | +0.071 |
Neg logit contributions | |
xual | -0.110 |
menstru | -0.105 |
Bir | -0.098 |
pees | -0.096 |
ferment | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
rolet | +1.218 |
orth | +1.161 |
oppy | +1.085 |
olls | +1.015 |
NTS | +1.009 |
Neg logit contributions | |
xual | -1.661 |
menstru | -1.583 |
Bir | -1.480 |
pees | -1.455 |
20439 | -1.450 |
Token | manually |
Token ID | 14500 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
rolet | +0.818 |
orth | +0.782 |
oppy | +0.735 |
NTS | +0.698 |
olls | +0.692 |
Neg logit contributions | |
xual | -0.984 |
menstru | -0.907 |
20439 | -0.884 |
Bir | -0.875 |
pees | -0.850 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
xual | +0.563 |
menstru | +0.523 |
Bir | +0.498 |
20439 | +0.491 |
pees | +0.484 |
Neg logit contributions | |
rolet | -0.488 |
orth | -0.469 |
oppy | -0.439 |
NTS | -0.418 |
olls | -0.412 |
Token | track |
Token ID | 2610 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
rolet | +0.258 |
orth | +0.253 |
oppy | +0.238 |
NTS | +0.228 |
olls | +0.227 |
Neg logit contributions | |
xual | -0.288 |
menstru | -0.267 |
Bir | -0.254 |
20439 | -0.246 |
pees | -0.244 |
Token | of |
Token ID | 286 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
xual | +1.365 |
menstru | +1.310 |
Bir | +1.210 |
ferment | +1.202 |
pees | +1.192 |
Neg logit contributions | |
rolet | -0.961 |
orth | -0.892 |
oppy | -0.839 |
olls | -0.783 |
NTS | -0.776 |
Token | how |
Token ID | 703 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
rolet | +0.530 |
orth | +0.521 |
oppy | +0.492 |
NTS | +0.469 |
olls | +0.466 |
Neg logit contributions | |
xual | -0.629 |
menstru | -0.581 |
Bir | -0.557 |
20439 | -0.541 |
pees | -0.539 |
Token | much |
Token ID | 881 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
xual | +0.373 |
menstru | +0.349 |
Bir | +0.326 |
20439 | +0.319 |
pees | +0.318 |
Neg logit contributions | |
rolet | -0.323 |
orth | -0.317 |
oppy | -0.300 |
olls | -0.284 |
NTS | -0.283 |
Token | text |
Token ID | 2420 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
orth | +4.390 |
rolet | +4.180 |
oppy | +4.068 |
NTS | +3.990 |
olls | +3.880 |
Neg logit contributions | |
xual | -6.220 |
menstru | -5.637 |
Bir | -5.477 |
20439 | -5.471 |
pees | -5.391 |
Token | can |
Token ID | 460 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
rolet | +0.324 |
orth | +0.320 |
oppy | +0.302 |
olls | +0.287 |
NTS | +0.285 |
Neg logit contributions | |
xual | -0.382 |
menstru | -0.355 |
Bir | -0.333 |
20439 | -0.328 |
pees | -0.322 |
Token | go |
Token ID | 467 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
rolet | +0.191 |
orth | +0.189 |
oppy | +0.175 |
olls | +0.167 |
igl | +0.164 |
Neg logit contributions | |
xual | -0.227 |
menstru | -0.210 |
Bir | -0.201 |
20439 | -0.199 |
pees | -0.193 |
Token | in |
Token ID | 287 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
rolet | +0.198 |
orth | +0.193 |
oppy | +0.179 |
olls | +0.170 |
NTS | +0.168 |
Neg logit contributions | |
xual | -0.269 |
menstru | -0.253 |
Bir | -0.241 |
20439 | -0.236 |
pees | -0.233 |
Token | each |
Token ID | 1123 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
rolet | +0.454 |
orth | +0.444 |
oppy | +0.419 |
NTS | +0.395 |
olls | +0.394 |
Neg logit contributions | |
xual | -0.522 |
menstru | -0.489 |
Bir | -0.460 |
pees | -0.448 |
20439 | -0.446 |
Token | said |
Token ID | 531 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
rolet | +0.764 |
orth | +0.720 |
oppy | +0.669 |
NTS | +0.622 |
olls | +0.617 |
Neg logit contributions | |
xual | -1.383 |
menstru | -1.318 |
Bir | -1.232 |
pees | -1.221 |
20439 | -1.217 |
Token | Drew |
Token ID | 18624 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
rolet | +0.922 |
orth | +0.880 |
oppy | +0.827 |
NTS | +0.783 |
olls | +0.774 |
Neg logit contributions | |
xual | -1.327 |
menstru | -1.251 |
Bir | -1.170 |
pees | -1.160 |
20439 | -1.154 |
Token | T |
Token ID | 309 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rolet | +0.857 |
orth | +0.819 |
oppy | +0.770 |
olls | +0.722 |
NTS | +0.720 |
Neg logit contributions | |
xual | -1.068 |
menstru | -1.013 |
Bir | -0.937 |
ferment | -0.924 |
20439 | -0.921 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
xual | +0.844 |
menstru | +0.800 |
Bir | +0.744 |
ferment | +0.731 |
pees | +0.730 |
Neg logit contributions | |
rolet | -0.720 |
orth | -0.683 |
oppy | -0.646 |
NTS | -0.607 |
olls | -0.605 |
Token | Sh |
Token ID | 911 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
xual | +0.688 |
menstru | +0.655 |
Bir | +0.611 |
ferment | +0.599 |
pees | +0.597 |
Neg logit contributions | |
rolet | -0.551 |
orth | -0.522 |
oppy | -0.493 |
olls | -0.461 |
NTS | -0.458 |
Token | ind |
Token ID | 521 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
rolet | +0.684 |
orth | +0.664 |
oppy | +0.624 |
olls | +0.590 |
rays | +0.579 |
Neg logit contributions | |
xual | -0.755 |
menstru | -0.719 |
Bir | -0.664 |
ferment | -0.653 |
20439 | -0.652 |
Token | ell |
Token ID | 695 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
orth | +5.931 |
rolet | +5.917 |
oppy | +5.521 |
olls | +5.353 |
igl | +5.250 |
Neg logit contributions | |
xual | -4.791 |
menstru | -4.622 |
Bir | -4.235 |
20439 | -4.138 |
女 | -4.098 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
rolet | +1.681 |
orth | +1.602 |
oppy | +1.506 |
olls | +1.409 |
NTS | +1.405 |
Neg logit contributions | |
xual | -2.151 |
menstru | -2.044 |
Bir | -1.899 |
ferment | -1.868 |
pees | -1.868 |
Token | professor |
Token ID | 6240 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
xual | +0.531 |
menstru | +0.502 |
Bir | +0.465 |
pees | +0.456 |
ferment | +0.456 |
Neg logit contributions | |
rolet | -0.482 |
orth | -0.461 |
oppy | -0.436 |
olls | -0.410 |
NTS | -0.410 |
Token | of |
Token ID | 286 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
rolet | +1.764 |
orth | +1.699 |
oppy | +1.556 |
NTS | +1.454 |
olls | +1.441 |
Neg logit contributions | |
xual | -3.133 |
menstru | -2.964 |
Bir | -2.791 |
pees | -2.772 |
20439 | -2.754 |
Token | climate |
Token ID | 4258 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
rolet | +0.664 |
orth | +0.639 |
oppy | +0.599 |
NTS | +0.567 |
olls | +0.565 |
Neg logit contributions | |
xual | -0.790 |
menstru | -0.736 |
Bir | -0.690 |
20439 | -0.685 |
pees | -0.680 |
Token | � |
Token ID | 247 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
rolet | +0.976 |
orth | +0.940 |
oppy | +0.900 |
rays | +0.863 |
olls | +0.862 |
Neg logit contributions | |
xual | -0.600 |
menstru | -0.557 |
Bir | -0.505 |
ferment | -0.490 |
20439 | -0.487 |
Token | s |
Token ID | 82 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
rolet | +0.217 |
orth | +0.212 |
oppy | +0.197 |
rays | +0.187 |
NTS | +0.187 |
Neg logit contributions | |
xual | -0.241 |
menstru | -0.230 |
Bir | -0.213 |
ferment | -0.210 |
20439 | -0.209 |
Token | silly |
Token ID | 14397 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
xual | +0.150 |
menstru | +0.141 |
Bir | +0.130 |
pees | +0.128 |
20439 | +0.128 |
Neg logit contributions | |
rolet | -0.146 |
orth | -0.141 |
oppy | -0.132 |
NTS | -0.127 |
rays | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
xual | +0.047 |
menstru | +0.044 |
Bir | +0.041 |
ferment | +0.041 |
pees | +0.041 |
Neg logit contributions | |
rolet | -0.036 |
orth | -0.035 |
oppy | -0.032 |
NTS | -0.030 |
olls | -0.030 |
Token | Not |
Token ID | 1892 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
xual | +0.104 |
menstru | +0.098 |
Bir | +0.091 |
20439 | +0.090 |
ferment | +0.090 |
Neg logit contributions | |
rolet | -0.090 |
orth | -0.087 |
oppy | -0.081 |
NTS | -0.078 |
olls | -0.076 |
Token | much |
Token ID | 881 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
xual | +1.130 |
menstru | +1.062 |
Bir | +0.985 |
pees | +0.970 |
ferment | +0.969 |
Neg logit contributions | |
rolet | -0.996 |
orth | -0.958 |
oppy | -0.900 |
NTS | -0.854 |
olls | -0.845 |
Token | to |
Token ID | 284 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
orth | +4.412 |
rolet | +4.284 |
oppy | +3.991 |
NTS | +3.984 |
rays | +3.712 |
Neg logit contributions | |
xual | -6.112 |
menstru | -5.656 |
20439 | -5.372 |
pees | -5.358 |
Bir | -5.325 |
Token | grasp |
Token ID | 13180 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
rolet | +0.427 |
orth | +0.409 |
oppy | +0.384 |
NTS | +0.367 |
olls | +0.361 |
Neg logit contributions | |
xual | -0.501 |
menstru | -0.468 |
Bir | -0.436 |
20439 | -0.431 |
pees | -0.429 |
Token | at |
Token ID | 379 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
rolet | +1.354 |
orth | +1.305 |
oppy | +1.202 |
NTS | +1.158 |
rays | +1.125 |
Neg logit contributions | |
xual | -1.826 |
menstru | -1.716 |
Bir | -1.614 |
20439 | -1.596 |
pees | -1.596 |
Token | here |
Token ID | 994 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
rolet | +1.280 |
orth | +1.235 |
oppy | +1.165 |
olls | +1.109 |
NTS | +1.108 |
Neg logit contributions | |
xual | -1.265 |
menstru | -1.173 |
Bir | -1.082 |
20439 | -1.072 |
ferment | -1.066 |
Token | – |
Token ID | 784 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
rolet | +0.382 |
orth | +0.363 |
oppy | +0.339 |
NTS | +0.319 |
olls | +0.316 |
Neg logit contributions | |
xual | -0.525 |
menstru | -0.497 |
Bir | -0.463 |
pees | -0.458 |
ferment | -0.457 |
Token | transparent |
Token ID | 13245 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
xual | +0.784 |
menstru | +0.741 |
Bir | +0.693 |
pees | +0.680 |
ferment | +0.675 |
Neg logit contributions | |
rolet | -0.651 |
orth | -0.623 |
oppy | -0.585 |
NTS | -0.553 |
olls | -0.550 |
Token | ly |
Token ID | 306 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
rolet | +0.715 |
orth | +0.690 |
oppy | +0.640 |
NTS | +0.604 |
rays | +0.600 |
Neg logit contributions | |
xual | -0.987 |
menstru | -0.938 |
Bir | -0.882 |
pees | -0.864 |
ferment | -0.862 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
xual | +1.241 |
menstru | +1.178 |
Bir | +1.103 |
pees | +1.080 |
ferment | +1.079 |
Neg logit contributions | |
rolet | -0.965 |
orth | -0.922 |
oppy | -0.865 |
NTS | -0.810 |
olls | -0.809 |
Token | you |
Token ID | 345 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
xual | +0.347 |
menstru | +0.325 |
Bir | +0.304 |
pees | +0.296 |
20439 | +0.295 |
Neg logit contributions | |
rolet | -0.349 |
orth | -0.340 |
oppy | -0.322 |
NTS | -0.307 |
olls | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rolet | +0.458 |
orth | +0.439 |
oppy | +0.408 |
NTS | +0.386 |
olls | +0.384 |
Neg logit contributions | |
xual | -0.602 |
menstru | -0.570 |
Bir | -0.535 |
pees | -0.527 |
20439 | -0.523 |
Token | Rest |
Token ID | 8324 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
rolet | +0.189 |
orth | +0.182 |
oppy | +0.170 |
NTS | +0.164 |
olls | +0.161 |
Neg logit contributions | |
xual | -0.227 |
menstru | -0.215 |
Bir | -0.198 |
ferment | -0.197 |
pees | -0.197 |
Token | assured |
Token ID | 13933 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
rolet | +2.979 |
orth | +2.932 |
oppy | +2.569 |
NTS | +2.419 |
rays | +2.351 |
Neg logit contributions | |
xual | -7.763 |
menstru | -7.394 |
Bir | -7.056 |
女 | -6.936 |
pees | -6.925 |
Token | , |
Token ID | 11 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
xual | +0.890 |
menstru | +0.844 |
Bir | +0.785 |
ferment | +0.770 |
pees | +0.770 |
Neg logit contributions | |
rolet | -0.746 |
orth | -0.711 |
oppy | -0.671 |
olls | -0.630 |
NTS | -0.630 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
xual | +0.199 |
menstru | +0.187 |
Bir | +0.175 |
pees | +0.171 |
20439 | +0.170 |
Neg logit contributions | |
rolet | -0.191 |
orth | -0.184 |
oppy | -0.174 |
NTS | -0.166 |
olls | -0.165 |
Token | techn |
Token ID | 1579 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
xual | +0.009 |
menstru | +0.008 |
Bir | +0.008 |
pees | +0.007 |
20439 | +0.007 |
Neg logit contributions | |
rolet | -0.008 |
orth | -0.008 |
oppy | -0.008 |
NTS | -0.007 |
olls | -0.007 |
Token | ologists |
Token ID | 9251 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
rolet | +2.492 |
orth | +2.447 |
oppy | +2.325 |
olls | +2.224 |
igl | +2.180 |
Neg logit contributions | |
xual | -2.028 |
menstru | -1.904 |
Bir | -1.725 |
pees | -1.692 |
20439 | -1.691 |
Token | It |
Token ID | 632 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
rolet | +0.366 |
orth | +0.349 |
oppy | +0.324 |
NTS | +0.319 |
olls | +0.304 |
Neg logit contributions | |
xual | -0.493 |
menstru | -0.464 |
pees | -0.427 |
ferment | -0.425 |
Bir | -0.424 |
Token | would |
Token ID | 561 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
rolet | +0.757 |
orth | +0.743 |
oppy | +0.693 |
olls | +0.660 |
rays | +0.650 |
Neg logit contributions | |
xual | -0.958 |
menstru | -0.887 |
20439 | -0.859 |
Bir | -0.846 |
pees | -0.825 |
Token | have |
Token ID | 423 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
rolet | +0.599 |
orth | +0.575 |
oppy | +0.544 |
olls | +0.509 |
NTS | +0.505 |
Neg logit contributions | |
xual | -0.617 |
menstru | -0.579 |
Bir | -0.550 |
20439 | -0.547 |
pees | -0.538 |
Token | created |
Token ID | 2727 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
rolet | +0.274 |
orth | +0.261 |
oppy | +0.246 |
olls | +0.232 |
NTS | +0.231 |
Neg logit contributions | |
xual | -0.327 |
menstru | -0.307 |
Bir | -0.290 |
20439 | -0.286 |
pees | -0.284 |
Token | just |
Token ID | 655 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
xual | +1.201 |
menstru | +1.134 |
Bir | +1.052 |
pees | +1.032 |
20439 | +1.030 |
Neg logit contributions | |
rolet | -1.129 |
orth | -1.081 |
oppy | -1.024 |
olls | -0.965 |
NTS | -0.965 |
Token | too |
Token ID | 1165 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
rolet | +0.781 |
orth | +0.756 |
oppy | +0.709 |
NTS | +0.667 |
olls | +0.666 |
Neg logit contributions | |
xual | -0.951 |
menstru | -0.895 |
20439 | -0.839 |
Bir | -0.838 |
pees | -0.825 |
Token | much |
Token ID | 881 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
orth | +3.660 |
rolet | +3.638 |
oppy | +3.444 |
NTS | +3.142 |
olls | +3.099 |
Neg logit contributions | |
xual | -6.571 |
menstru | -6.171 |
20439 | -6.073 |
Bir | -5.939 |
pees | -5.910 |
Token | tension |
Token ID | 12097 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
rolet | +5.062 |
orth | +5.028 |
oppy | +4.793 |
NTS | +4.700 |
Registry | +4.446 |
Neg logit contributions | |
xual | -5.548 |
20439 | -5.094 |
menstru | -5.011 |
pees | -4.969 |
Bir | -4.855 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
xual | +0.223 |
menstru | +0.212 |
Bir | +0.199 |
20439 | +0.195 |
pees | +0.195 |
Neg logit contributions | |
rolet | -0.168 |
orth | -0.160 |
oppy | -0.150 |
olls | -0.141 |
NTS | -0.140 |
Token | knowing |
Token ID | 6970 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
rolet | +0.407 |
orth | +0.392 |
oppy | +0.367 |
NTS | +0.350 |
olls | +0.344 |
Neg logit contributions | |
xual | -0.520 |
menstru | -0.486 |
20439 | -0.464 |
Bir | -0.461 |
pees | -0.456 |
Token | you |
Token ID | 345 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
rolet | +0.062 |
orth | +0.059 |
oppy | +0.056 |
NTS | +0.053 |
olls | +0.052 |
Neg logit contributions | |
xual | -0.078 |
menstru | -0.073 |
Bir | -0.069 |
20439 | -0.068 |
pees | -0.068 |
Token | them |
Token ID | 606 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
rolet | +0.593 |
orth | +0.570 |
oppy | +0.543 |
olls | +0.515 |
NTS | +0.515 |
Neg logit contributions | |
xual | -0.643 |
menstru | -0.600 |
Bir | -0.558 |
20439 | -0.554 |
pees | -0.545 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
rolet | +0.358 |
orth | +0.342 |
oppy | +0.325 |
olls | +0.304 |
NTS | +0.303 |
Neg logit contributions | |
xual | -0.447 |
menstru | -0.420 |
Bir | -0.394 |
20439 | -0.389 |
pees | -0.386 |
Token | size |
Token ID | 2546 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
rolet | +0.441 |
orth | +0.421 |
oppy | +0.400 |
NTS | +0.378 |
olls | +0.376 |
Neg logit contributions | |
xual | -0.486 |
menstru | -0.460 |
Bir | -0.425 |
pees | -0.418 |
20439 | -0.418 |
Token | of |
Token ID | 286 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
xual | +2.486 |
menstru | +2.389 |
Bir | +2.228 |
ferment | +2.197 |
pees | +2.168 |
Neg logit contributions | |
rolet | -1.846 |
orth | -1.739 |
oppy | -1.628 |
olls | -1.506 |
NTS | -1.490 |
Token | my |
Token ID | 616 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
rolet | +0.549 |
orth | +0.524 |
oppy | +0.505 |
olls | +0.479 |
NTS | +0.477 |
Neg logit contributions | |
xual | -0.537 |
menstru | -0.494 |
Bir | -0.460 |
20439 | -0.457 |
pees | -0.449 |
Token | thumb |
Token ID | 15683 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
rolet | +0.097 |
orth | +0.092 |
oppy | +0.088 |
NTS | +0.083 |
olls | +0.082 |
Neg logit contributions | |
xual | -0.111 |
menstru | -0.103 |
Bir | -0.096 |
20439 | -0.095 |
pees | -0.095 |
Token | ). |
Token ID | 737 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
rolet | +3.947 |
orth | +3.938 |
oppy | +3.617 |
olls | +3.450 |
rays | +3.378 |
Neg logit contributions | |
xual | -6.346 |
menstru | -6.020 |
Bir | -5.722 |
20439 | -5.721 |
pees | -5.450 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rolet | +0.434 |
orth | +0.413 |
oppy | +0.387 |
NTS | +0.371 |
olls | +0.364 |
Neg logit contributions | |
xual | -0.549 |
menstru | -0.519 |
20439 | -0.475 |
Bir | -0.475 |
pees | -0.475 |
Token | throw |
Token ID | 3714 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
rolet | +2.216 |
orth | +2.126 |
oppy | +1.987 |
NTS | +1.887 |
olls | +1.858 |
Neg logit contributions | |
xual | -2.706 |
menstru | -2.498 |
20439 | -2.410 |
Bir | -2.398 |
pees | -2.356 |
Token | it |
Token ID | 340 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
xual | +1.394 |
menstru | +1.316 |
Bir | +1.212 |
ferment | +1.189 |
pees | +1.184 |
Neg logit contributions | |
rolet | -1.444 |
orth | -1.381 |
oppy | -1.312 |
olls | -1.240 |
NTS | -1.236 |
Token | on |
Token ID | 319 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
rolet | +0.020 |
orth | +0.019 |
oppy | +0.018 |
NTS | +0.017 |
olls | +0.017 |
Neg logit contributions | |
xual | -0.022 |
menstru | -0.021 |
Bir | -0.019 |
20439 | -0.019 |
pees | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rolet | +0.347 |
orth | +0.333 |
oppy | +0.317 |
NTS | +0.301 |
olls | +0.299 |
Neg logit contributions | |
xual | -0.374 |
menstru | -0.348 |
Bir | -0.324 |
20439 | -0.321 |
pees | -0.320 |
Token | fans |
Token ID | 3296 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
rolet | +0.198 |
orth | +0.189 |
oppy | +0.179 |
NTS | +0.171 |
olls | +0.170 |
Neg logit contributions | |
xual | -0.233 |
menstru | -0.216 |
Bir | -0.203 |
20439 | -0.202 |
pees | -0.200 |
Token | were |
Token ID | 547 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
xual | +1.690 |
menstru | +1.587 |
Bir | +1.479 |
pees | +1.450 |
20439 | +1.445 |
Neg logit contributions | |
rolet | -1.503 |
orth | -1.435 |
oppy | -1.354 |
olls | -1.277 |
NTS | -1.270 |
Token | not |
Token ID | 407 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
xual | +0.256 |
menstru | +0.236 |
Bir | +0.222 |
20439 | +0.217 |
pees | +0.217 |
Neg logit contributions | |
rolet | -0.244 |
orth | -0.234 |
oppy | -0.221 |
olls | -0.211 |
NTS | -0.209 |
Token | missing |
Token ID | 4814 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
xual | +1.031 |
menstru | +0.961 |
Bir | +0.894 |
pees | +0.875 |
20439 | +0.872 |
Neg logit contributions | |
rolet | -1.018 |
orth | -0.974 |
oppy | -0.923 |
olls | -0.877 |
NTS | -0.869 |
Token | much |
Token ID | 881 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
rolet | +0.895 |
orth | +0.870 |
oppy | +0.810 |
olls | +0.765 |
rays | +0.759 |
Neg logit contributions | |
xual | -1.271 |
menstru | -1.185 |
Bir | -1.115 |
20439 | -1.104 |
pees | -1.101 |
Token | action |
Token ID | 2223 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
orth | +3.824 |
rolet | +3.796 |
oppy | +3.557 |
NTS | +3.406 |
olls | +3.335 |
Neg logit contributions | |
xual | -6.346 |
menstru | -5.795 |
pees | -5.651 |
20439 | -5.642 |
Bir | -5.559 |
Token | , |
Token ID | 11 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
xual | +0.559 |
menstru | +0.530 |
Bir | +0.495 |
pees | +0.486 |
ferment | +0.486 |
Neg logit contributions | |
rolet | -0.427 |
orth | -0.406 |
oppy | -0.382 |
olls | -0.357 |
NTS | -0.356 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
rolet | +0.674 |
orth | +0.646 |
oppy | +0.609 |
NTS | +0.570 |
olls | +0.567 |
Neg logit contributions | |
xual | -0.901 |
menstru | -0.838 |
Bir | -0.787 |
pees | -0.779 |
20439 | -0.778 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
xual | +0.859 |
menstru | +0.804 |
Bir | +0.747 |
pees | +0.734 |
20439 | +0.732 |
Neg logit contributions | |
rolet | -0.815 |
orth | -0.780 |
oppy | -0.741 |
olls | -0.701 |
NTS | -0.700 |
Token | conditions |
Token ID | 3403 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
rolet | +0.038 |
orth | +0.036 |
oppy | +0.034 |
NTS | +0.033 |
olls | +0.032 |
Neg logit contributions | |
xual | -0.045 |
menstru | -0.042 |
Bir | -0.039 |
20439 | -0.039 |
pees | -0.039 |
Token | federal |
Token ID | 2717 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
xual | +0.282 |
menstru | +0.266 |
Bir | +0.247 |
20439 | +0.243 |
pees | +0.243 |
Neg logit contributions | |
rolet | -0.224 |
orth | -0.213 |
oppy | -0.201 |
NTS | -0.190 |
olls | -0.189 |
Token | government |
Token ID | 1230 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
xual | +0.907 |
menstru | +0.853 |
Bir | +0.779 |
ferment | +0.762 |
pees | +0.761 |
Neg logit contributions | |
rolet | -1.074 |
orth | -1.032 |
oppy | -0.983 |
NTS | -0.937 |
olls | -0.934 |
Token | . |
Token ID | 13 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
rolet | +0.062 |
orth | +0.058 |
oppy | +0.055 |
olls | +0.051 |
NTS | +0.051 |
Neg logit contributions | |
xual | -0.083 |
menstru | -0.079 |
Bir | -0.074 |
ferment | -0.072 |
pees | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
xual | +0.195 |
menstru | +0.185 |
Bir | +0.174 |
ferment | +0.168 |
pees | +0.168 |
Neg logit contributions | |
rolet | -0.179 |
orth | -0.170 |
oppy | -0.162 |
olls | -0.152 |
rays | -0.150 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
rolet | +0.390 |
orth | +0.375 |
oppy | +0.347 |
NTS | +0.332 |
olls | +0.326 |
Neg logit contributions | |
xual | -0.552 |
menstru | -0.515 |
pees | -0.476 |
ferment | -0.475 |
skelet | -0.471 |
Token | Er |
Token ID | 9139 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
rolet | +0.363 |
orth | +0.348 |
oppy | +0.329 |
NTS | +0.310 |
olls | +0.309 |
Neg logit contributions | |
xual | -0.389 |
menstru | -0.365 |
ferment | -0.331 |
Bir | -0.329 |
pees | -0.328 |
Token | n |
Token ID | 77 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
xual | +4.637 |
menstru | +4.439 |
Bir | +4.087 |
pees | +4.058 |
tur | +4.015 |
Neg logit contributions | |
rolet | -5.092 |
orth | -4.858 |
oppy | -4.652 |
NTS | -4.438 |
olls | -4.376 |
Token | est |
Token ID | 395 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
xual | +0.011 |
menstru | +0.011 |
Bir | +0.010 |
ferment | +0.010 |
pees | +0.010 |
Neg logit contributions | |
rolet | -0.010 |
orth | -0.010 |
oppy | -0.009 |
olls | -0.009 |
NTS | -0.008 |
Token | o |
Token ID | 78 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
xual | +0.052 |
menstru | +0.050 |
Bir | +0.047 |
ferment | +0.046 |
pees | +0.046 |
Neg logit contributions | |
rolet | -0.034 |
orth | -0.032 |
oppy | -0.030 |
olls | -0.028 |
NTS | -0.028 |
Token | Gal |
Token ID | 5027 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
rolet | +0.336 |
orth | +0.320 |
oppy | +0.301 |
NTS | +0.282 |
olls | +0.281 |
Neg logit contributions | |
xual | -0.451 |
menstru | -0.428 |
Bir | -0.397 |
ferment | -0.392 |
pees | -0.392 |
Token | ar |
Token ID | 283 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
rolet | +1.542 |
orth | +1.500 |
oppy | +1.412 |
igl | +1.326 |
rays | +1.323 |
Neg logit contributions | |
xual | -1.536 |
menstru | -1.447 |
Bir | -1.336 |
20439 | -1.325 |
ferment | -1.312 |
Token | Sciences |
Token ID | 13473 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
xual | +1.419 |
menstru | +1.349 |
Bir | +1.243 |
ferment | +1.225 |
pees | +1.205 |
Neg logit contributions | |
rolet | -1.478 |
orth | -1.374 |
oppy | -1.320 |
olls | -1.244 |
NTS | -1.237 |
Token | in |
Token ID | 287 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
xual | +0.645 |
menstru | +0.611 |
Bir | +0.567 |
pees | +0.560 |
ferment | +0.560 |
Neg logit contributions | |
rolet | -0.521 |
orth | -0.499 |
oppy | -0.466 |
NTS | -0.439 |
olls | -0.437 |
Token | Memory |
Token ID | 14059 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
xual | +0.598 |
menstru | +0.570 |
Bir | +0.530 |
ferment | +0.521 |
pees | +0.517 |
Neg logit contributions | |
rolet | -0.501 |
orth | -0.473 |
oppy | -0.448 |
olls | -0.420 |
NTS | -0.416 |
Token | of |
Token ID | 286 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
xual | +0.183 |
menstru | +0.175 |
Bir | +0.164 |
ferment | +0.161 |
20439 | +0.159 |
Neg logit contributions | |
rolet | -0.124 |
orth | -0.116 |
oppy | -0.111 |
olls | -0.103 |
rays | -0.101 |
Token | Alfred |
Token ID | 22044 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
xual | +0.523 |
menstru | +0.490 |
Bir | +0.445 |
ferment | +0.435 |
pees | +0.434 |
Neg logit contributions | |
rolet | -0.690 |
orth | -0.663 |
oppy | -0.633 |
olls | -0.603 |
NTS | -0.601 |
Token | Nobel |
Token ID | 20715 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
xual | +0.349 |
menstru | +0.320 |
Bir | +0.291 |
pees | +0.289 |
20439 | +0.289 |
Neg logit contributions | |
rolet | -0.412 |
orth | -0.402 |
oppy | -0.380 |
NTS | -0.366 |
olls | -0.360 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
xual | +4.609 |
menstru | +4.388 |
Bir | +4.078 |
ferment | +3.993 |
pees | +3.937 |
Neg logit contributions | |
rolet | -4.299 |
orth | -4.034 |
oppy | -3.943 |
olls | -3.671 |
rays | -3.647 |
Token | founder |
Token ID | 9119 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
xual | +0.064 |
menstru | +0.061 |
Bir | +0.056 |
pees | +0.055 |
ferment | +0.055 |
Neg logit contributions | |
rolet | -0.055 |
orth | -0.053 |
oppy | -0.049 |
NTS | -0.047 |
olls | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
rolet | +0.968 |
orth | +0.912 |
oppy | +0.851 |
olls | +0.789 |
NTS | +0.785 |
Neg logit contributions | |
xual | -1.521 |
menstru | -1.452 |
Bir | -1.361 |
ferment | -1.341 |
pees | -1.337 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
rolet | +0.742 |
orth | +0.715 |
oppy | +0.671 |
NTS | +0.637 |
olls | +0.635 |
Neg logit contributions | |
xual | -0.764 |
menstru | -0.713 |
Bir | -0.658 |
pees | -0.652 |
20439 | -0.649 |
Token | Nobel |
Token ID | 20715 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
rolet | +0.495 |
orth | +0.474 |
oppy | +0.446 |
NTS | +0.424 |
olls | +0.421 |
Neg logit contributions | |
xual | -0.559 |
menstru | -0.523 |
Bir | -0.484 |
pees | -0.480 |
20439 | -0.480 |
Token | , |
Token ID | 11 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
rolet | +0.821 |
orth | +0.782 |
oppy | +0.727 |
olls | +0.690 |
NTS | +0.677 |
Neg logit contributions | |
xual | -1.038 |
menstru | -0.972 |
Bir | -0.907 |
pees | -0.894 |
20439 | -0.892 |
Token | who |
Token ID | 508 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
xual | +0.140 |
menstru | +0.131 |
Bir | +0.122 |
pees | +0.121 |
20439 | +0.120 |
Neg logit contributions | |
rolet | -0.121 |
orth | -0.117 |
oppy | -0.110 |
NTS | -0.103 |
olls | -0.103 |
Token | had |
Token ID | 550 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rolet | +1.618 |
orth | +1.580 |
oppy | +1.461 |
olls | +1.401 |
NTS | +1.369 |
Neg logit contributions | |
xual | -1.988 |
menstru | -1.817 |
20439 | -1.720 |
Bir | -1.717 |
pees | -1.703 |
Token | scored |
Token ID | 7781 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
xual | +0.236 |
menstru | +0.220 |
Bir | +0.206 |
20439 | +0.203 |
pees | +0.203 |
Neg logit contributions | |
rolet | -0.212 |
orth | -0.204 |
oppy | -0.192 |
olls | -0.182 |
NTS | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
xual | +2.731 |
menstru | +2.572 |
Bir | +2.374 |
pees | +2.325 |
ferment | +2.323 |
Neg logit contributions | |
rolet | -2.725 |
orth | -2.609 |
oppy | -2.475 |
olls | -2.341 |
NTS | -2.336 |
Token | hat |
Token ID | 6877 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
xual | +0.022 |
menstru | +0.021 |
Bir | +0.019 |
pees | +0.019 |
20439 | +0.019 |
Neg logit contributions | |
rolet | -0.018 |
orth | -0.018 |
oppy | -0.017 |
olls | -0.016 |
NTS | -0.016 |
Token | - |
Token ID | 12 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
xual | +5.875 |
menstru | +5.588 |
Bir | +5.250 |
ferment | +5.163 |
pees | +5.121 |
Neg logit contributions | |
rolet | -4.868 |
orth | -4.564 |
oppy | -4.367 |
olls | -4.126 |
NTS | -4.117 |
Token | tr |
Token ID | 2213 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
rolet | +0.649 |
orth | +0.629 |
oppy | +0.592 |
olls | +0.560 |
rays | +0.559 |
Neg logit contributions | |
xual | -0.573 |
menstru | -0.538 |
Bir | -0.485 |
ferment | -0.483 |
20439 | -0.481 |
Token | ick |
Token ID | 624 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
rolet | +0.035 |
orth | +0.033 |
oppy | +0.031 |
olls | +0.027 |
rays | +0.025 |
Neg logit contributions | |
xual | -0.091 |
menstru | -0.087 |
Bir | -0.082 |
20439 | -0.082 |
ferment | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
rolet | +0.446 |
orth | +0.427 |
oppy | +0.398 |
olls | +0.369 |
NTS | +0.367 |
Neg logit contributions | |
xual | -0.646 |
menstru | -0.612 |
Bir | -0.571 |
pees | -0.569 |
20439 | -0.566 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rolet | +0.244 |
orth | +0.235 |
oppy | +0.222 |
NTS | +0.207 |
olls | +0.206 |
Neg logit contributions | |
xual | -0.307 |
menstru | -0.287 |
Bir | -0.267 |
pees | -0.264 |
20439 | -0.263 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
xual | +3.039 |
menstru | +2.889 |
Bir | +2.678 |
ferment | +2.649 |
pees | +2.616 |
Neg logit contributions | |
rolet | -2.592 |
orth | -2.447 |
oppy | -2.323 |
olls | -2.184 |
NTS | -2.160 |
Token | the |
Token ID | 262 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
xual | +0.221 |
menstru | +0.207 |
Bir | +0.192 |
20439 | +0.189 |
pees | +0.188 |
Neg logit contributions | |
rolet | -0.204 |
orth | -0.196 |
oppy | -0.185 |
NTS | -0.175 |
olls | -0.175 |
Token | intersection |
Token ID | 16246 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
xual | +0.201 |
menstru | +0.188 |
Bir | +0.174 |
20439 | +0.172 |
pees | +0.171 |
Neg logit contributions | |
rolet | -0.179 |
orth | -0.171 |
oppy | -0.162 |
NTS | -0.154 |
olls | -0.153 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
xual | +1.160 |
menstru | +1.104 |
Bir | +1.028 |
ferment | +1.012 |
pees | +1.008 |
Neg logit contributions | |
rolet | -0.888 |
orth | -0.841 |
oppy | -0.792 |
olls | -0.740 |
NTS | -0.736 |
Token | Y |
Token ID | 575 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
rolet | +0.246 |
orth | +0.236 |
oppy | +0.222 |
NTS | +0.210 |
olls | +0.210 |
Neg logit contributions | |
xual | -0.286 |
menstru | -0.268 |
Bir | -0.248 |
20439 | -0.245 |
pees | -0.244 |
Token | onge |
Token ID | 14220 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
xual | +2.598 |
menstru | +2.423 |
Bir | +2.209 |
ferment | +2.153 |
pees | +2.146 |
Neg logit contributions | |
rolet | -3.781 |
orth | -3.600 |
oppy | -3.459 |
olls | -3.297 |
NTS | -3.297 |
Token | and |
Token ID | 290 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
xual | +4.704 |
menstru | +4.508 |
Bir | +4.219 |
ferment | +4.159 |
pees | +4.120 |
Neg logit contributions | |
rolet | -4.306 |
orth | -4.036 |
oppy | -3.827 |
olls | -3.599 |
NTS | -3.574 |
Token | E |
Token ID | 412 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
xual | +0.800 |
menstru | +0.748 |
Bir | +0.690 |
20439 | +0.679 |
pees | +0.677 |
Neg logit contributions | |
rolet | -0.765 |
orth | -0.739 |
oppy | -0.698 |
olls | -0.663 |
NTS | -0.660 |
Token | gl |
Token ID | 4743 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
xual | +2.670 |
menstru | +2.566 |
Bir | +2.430 |
ferment | +2.400 |
pees | +2.394 |
Neg logit contributions | |
rolet | -1.026 |
orth | -0.945 |
oppy | -0.854 |
olls | -0.762 |
NTS | -0.755 |
Token | inton |
Token ID | 2371 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
rolet | +1.057 |
orth | +1.047 |
oppy | +0.954 |
olls | +0.882 |
oise | +0.880 |
Neg logit contributions | |
xual | -1.716 |
menstru | -1.640 |
20439 | -1.555 |
Bir | -1.525 |
ferment | -1.490 |
Token | will |
Token ID | 481 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
xual | +0.704 |
menstru | +0.665 |
Bir | +0.617 |
20439 | +0.608 |
ferment | +0.605 |
Neg logit contributions | |
rolet | -0.569 |
orth | -0.547 |
oppy | -0.513 |
olls | -0.485 |
NTS | -0.482 |
Token | red |
Token ID | 2266 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
xual | +1.588 |
menstru | +1.494 |
Bir | +1.374 |
ferment | +1.346 |
pees | +1.344 |
Neg logit contributions | |
rolet | -1.678 |
orth | -1.606 |
oppy | -1.527 |
olls | -1.446 |
NTS | -1.441 |
Token | and |
Token ID | 290 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
rolet | +0.320 |
orth | +0.311 |
oppy | +0.297 |
olls | +0.283 |
rays | +0.281 |
Neg logit contributions | |
xual | -0.237 |
menstru | -0.218 |
Bir | -0.198 |
20439 | -0.195 |
pees | -0.192 |
Token | yellow |
Token ID | 7872 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
xual | +0.901 |
menstru | +0.847 |
Bir | +0.785 |
pees | +0.772 |
20439 | +0.768 |
Neg logit contributions | |
rolet | -0.842 |
orth | -0.806 |
oppy | -0.765 |
olls | -0.719 |
NTS | -0.718 |
Token | peppers |
Token ID | 31804 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
xual | +0.415 |
menstru | +0.386 |
Bir | +0.354 |
20439 | +0.345 |
pees | +0.344 |
Neg logit contributions | |
rolet | -0.505 |
orth | -0.486 |
oppy | -0.464 |
olls | -0.441 |
NTS | -0.439 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
rolet | +0.565 |
orth | +0.537 |
oppy | +0.506 |
olls | +0.474 |
NTS | +0.467 |
Neg logit contributions | |
xual | -0.752 |
menstru | -0.712 |
Bir | -0.668 |
20439 | -0.655 |
pees | -0.652 |
Token | cour |
Token ID | 1093 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
xual | +0.597 |
menstru | +0.556 |
Bir | +0.510 |
pees | +0.499 |
20439 | +0.499 |
Neg logit contributions | |
rolet | -0.684 |
orth | -0.658 |
oppy | -0.627 |
olls | -0.595 |
NTS | -0.593 |
Token | get |
Token ID | 1136 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
xual | +2.869 |
menstru | +2.596 |
Bir | +2.259 |
pees | +2.238 |
ferment | +2.194 |
Neg logit contributions | |
rolet | -6.090 |
orth | -5.819 |
oppy | -5.664 |
NTS | -5.460 |
olls | -5.387 |
Token | tes |
Token ID | 4879 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
xual | +0.655 |
menstru | +0.611 |
Bir | +0.552 |
ferment | +0.541 |
pees | +0.538 |
Neg logit contributions | |
rolet | -0.918 |
orth | -0.881 |
oppy | -0.844 |
olls | -0.804 |
NTS | -0.803 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
xual | +2.765 |
menstru | +2.624 |
Bir | +2.415 |
ferment | +2.407 |
pees | +2.385 |
Neg logit contributions | |
rolet | -2.413 |
orth | -2.282 |
oppy | -2.158 |
olls | -2.021 |
NTS | -2.015 |
Token | basil |
Token ID | 37792 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
xual | +0.512 |
menstru | +0.479 |
Bir | +0.440 |
pees | +0.431 |
20439 | +0.429 |
Neg logit contributions | |
rolet | -0.568 |
orth | -0.545 |
oppy | -0.519 |
olls | -0.491 |
NTS | -0.490 |
Token | and |
Token ID | 290 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
rolet | +0.716 |
orth | +0.686 |
oppy | +0.647 |
olls | +0.605 |
NTS | +0.597 |
Neg logit contributions | |
xual | -0.940 |
menstru | -0.885 |
Bir | -0.826 |
20439 | -0.810 |
pees | -0.809 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
rolet | +1.088 |
orth | +1.039 |
oppy | +0.960 |
olls | +0.906 |
NTS | +0.903 |
Neg logit contributions | |
xual | -1.602 |
menstru | -1.516 |
Bir | -1.427 |
20439 | -1.399 |
pees | -1.399 |
Token | 188 |
Token ID | 20356 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
xual | +1.028 |
menstru | +0.956 |
Bir | +0.870 |
ferment | +0.843 |
pees | +0.839 |
Neg logit contributions | |
rolet | -1.476 |
orth | -1.413 |
oppy | -1.360 |
olls | -1.296 |
NTS | -1.293 |
Token | ] |
Token ID | 60 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
xual | +1.392 |
menstru | +1.319 |
Bir | +1.231 |
ferment | +1.203 |
20439 | +1.185 |
Neg logit contributions | |
rolet | -1.247 |
orth | -1.170 |
oppy | -1.120 |
olls | -1.050 |
rays | -1.048 |
Token | The |
Token ID | 383 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
xual | +0.214 |
menstru | +0.201 |
Bir | +0.185 |
pees | +0.184 |
ferment | +0.184 |
Neg logit contributions | |
rolet | -0.187 |
orth | -0.179 |
oppy | -0.168 |
NTS | -0.161 |
olls | -0.160 |
Token | party |
Token ID | 2151 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
rolet | +0.716 |
orth | +0.686 |
oppy | +0.647 |
olls | +0.619 |
NTS | +0.618 |
Neg logit contributions | |
xual | -0.855 |
menstru | -0.801 |
Bir | -0.750 |
pees | -0.739 |
20439 | -0.737 |
Token | with |
Token ID | 351 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
xual | +0.742 |
menstru | +0.701 |
Bir | +0.652 |
pees | +0.641 |
ferment | +0.639 |
Neg logit contributions | |
rolet | -0.620 |
orth | -0.593 |
oppy | -0.557 |
olls | -0.526 |
NTS | -0.523 |
Token | majority |
Token ID | 3741 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
xual | +1.290 |
menstru | +1.214 |
Bir | +1.119 |
ferment | +1.096 |
pees | +1.094 |
Neg logit contributions | |
rolet | -1.338 |
orth | -1.281 |
oppy | -1.215 |
olls | -1.153 |
NTS | -1.147 |
Token | support |
Token ID | 1104 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
xual | +1.515 |
menstru | +1.436 |
Bir | +1.335 |
ferment | +1.310 |
pees | +1.309 |
Neg logit contributions | |
rolet | -1.278 |
orth | -1.217 |
oppy | -1.147 |
olls | -1.080 |
NTS | -1.077 |
Token | in |
Token ID | 287 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
xual | +0.879 |
menstru | +0.832 |
Bir | +0.776 |
ferment | +0.759 |
pees | +0.759 |
Neg logit contributions | |
rolet | -0.736 |
orth | -0.701 |
oppy | -0.659 |
olls | -0.623 |
NTS | -0.618 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
xual | +0.947 |
menstru | +0.880 |
Bir | +0.821 |
20439 | +0.806 |
pees | +0.804 |
Neg logit contributions | |
rolet | -0.966 |
orth | -0.931 |
oppy | -0.881 |
olls | -0.848 |
NTS | -0.840 |
Token | House |
Token ID | 2097 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
xual | +0.063 |
menstru | +0.059 |
Bir | +0.055 |
20439 | +0.055 |
pees | +0.054 |
Neg logit contributions | |
rolet | -0.057 |
orth | -0.054 |
oppy | -0.051 |
olls | -0.049 |
NTS | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
xual | +0.841 |
menstru | +0.792 |
Bir | +0.730 |
ferment | +0.714 |
pees | +0.714 |
Neg logit contributions | |
rolet | -0.928 |
orth | -0.892 |
oppy | -0.847 |
olls | -0.806 |
NTS | -0.805 |
Token | earth |
Token ID | 4534 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
xual | +0.146 |
menstru | +0.138 |
Bir | +0.130 |
pees | +0.128 |
20439 | +0.128 |
Neg logit contributions | |
rolet | -0.118 |
orth | -0.113 |
oppy | -0.106 |
NTS | -0.101 |
olls | -0.100 |
Token | — |
Token ID | 960 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
xual | +1.400 |
menstru | +1.332 |
Bir | +1.237 |
ferment | +1.218 |
pees | +1.213 |
Neg logit contributions | |
rolet | -1.130 |
orth | -1.073 |
oppy | -1.012 |
olls | -0.947 |
NTS | -0.943 |
Token | from |
Token ID | 6738 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
xual | +0.271 |
menstru | +0.256 |
Bir | +0.234 |
ferment | +0.234 |
20439 | +0.232 |
Neg logit contributions | |
rolet | -0.247 |
orth | -0.239 |
oppy | -0.224 |
olls | -0.212 |
NTS | -0.211 |
Token | Armenia |
Token ID | 32369 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
xual | +0.703 |
menstru | +0.658 |
Bir | +0.609 |
20439 | +0.599 |
pees | +0.597 |
Neg logit contributions | |
rolet | -0.726 |
orth | -0.697 |
oppy | -0.662 |
olls | -0.631 |
NTS | -0.631 |
Token | , |
Token ID | 11 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
rolet | +0.473 |
orth | +0.451 |
oppy | +0.422 |
NTS | +0.398 |
olls | +0.398 |
Neg logit contributions | |
xual | -0.570 |
menstru | -0.541 |
Bir | -0.502 |
ferment | -0.494 |
pees | -0.493 |
Token | Arts |
Token ID | 11536 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
xual | +0.839 |
menstru | +0.776 |
Bir | +0.696 |
pees | +0.684 |
20439 | +0.683 |
Neg logit contributions | |
rolet | -1.278 |
orth | -1.234 |
oppy | -1.180 |
NTS | -1.133 |
olls | -1.132 |
Token | akh |
Token ID | 11322 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
xual | +1.341 |
menstru | +1.241 |
Bir | +1.098 |
20439 | +1.071 |
ferment | +1.068 |
Neg logit contributions | |
rolet | -2.391 |
orth | -2.326 |
oppy | -2.225 |
olls | -2.133 |
NTS | -2.125 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
xual | +0.124 |
menstru | +0.117 |
Bir | +0.109 |
ferment | +0.107 |
pees | +0.107 |
Neg logit contributions | |
rolet | -0.102 |
orth | -0.096 |
oppy | -0.091 |
olls | -0.085 |
NTS | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
xual | +0.467 |
menstru | +0.434 |
Bir | +0.392 |
20439 | +0.391 |
pees | +0.389 |
Neg logit contributions | |
rolet | -0.592 |
orth | -0.574 |
oppy | -0.546 |
NTS | -0.525 |
olls | -0.525 |
Token | Jav |
Token ID | 49247 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
xual | +0.274 |
menstru | +0.257 |
Bir | +0.233 |
20439 | +0.232 |
pees | +0.232 |
Neg logit contributions | |
rolet | -0.339 |
orth | -0.328 |
oppy | -0.311 |
olls | -0.300 |
NTS | -0.300 |
Token | s |
Token ID | 82 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
xual | +0.171 |
menstru | +0.162 |
Bir | +0.148 |
ferment | +0.146 |
pees | +0.146 |
Neg logit contributions | |
rolet | -0.166 |
orth | -0.162 |
oppy | -0.152 |
NTS | -0.144 |
rays | -0.143 |
Token | micro |
Token ID | 4580 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
xual | +0.203 |
menstru | +0.190 |
Bir | +0.178 |
pees | +0.174 |
20439 | +0.174 |
Neg logit contributions | |
rolet | -0.182 |
orth | -0.174 |
oppy | -0.165 |
NTS | -0.158 |
olls | -0.157 |
Token | circuitry |
Token ID | 42344 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
rolet | +0.418 |
orth | +0.397 |
oppy | +0.375 |
NTS | +0.354 |
olls | +0.353 |
Neg logit contributions | |
xual | -0.447 |
menstru | -0.419 |
Bir | -0.388 |
pees | -0.379 |
ferment | -0.378 |
Token | it |
Token ID | 340 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
rolet | +1.940 |
orth | +1.886 |
oppy | +1.777 |
NTS | +1.738 |
rays | +1.683 |
Neg logit contributions | |
xual | -2.294 |
menstru | -2.136 |
Bir | -2.020 |
pees | -1.987 |
20439 | -1.973 |
Token | is |
Token ID | 318 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
xual | +0.901 |
menstru | +0.852 |
Bir | +0.791 |
pees | +0.777 |
ferment | +0.777 |
Neg logit contributions | |
rolet | -0.776 |
orth | -0.745 |
oppy | -0.699 |
olls | -0.662 |
NTS | -0.659 |
Token | not |
Token ID | 407 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
xual | +0.275 |
menstru | +0.255 |
Bir | +0.236 |
pees | +0.232 |
20439 | +0.231 |
Neg logit contributions | |
rolet | -0.293 |
orth | -0.284 |
oppy | -0.267 |
NTS | -0.257 |
olls | -0.254 |
Token | impossible |
Token ID | 5340 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
xual | +0.988 |
menstru | +0.926 |
Bir | +0.854 |
pees | +0.839 |
20439 | +0.836 |
Neg logit contributions | |
rolet | -1.003 |
orth | -0.966 |
oppy | -0.911 |
NTS | -0.866 |
olls | -0.864 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
rolet | +2.120 |
orth | +2.014 |
oppy | +1.858 |
NTS | +1.793 |
rays | +1.741 |
Neg logit contributions | |
xual | -2.996 |
menstru | -2.825 |
Bir | -2.627 |
pees | -2.624 |
20439 | -2.603 |
Token | It |
Token ID | 632 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
rolet | +0.413 |
orth | +0.396 |
oppy | +0.369 |
NTS | +0.361 |
olls | +0.348 |
Neg logit contributions | |
xual | -0.510 |
menstru | -0.481 |
pees | -0.440 |
ferment | -0.440 |
Bir | -0.438 |
Token | is |
Token ID | 318 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
rolet | +0.915 |
orth | +0.888 |
oppy | +0.825 |
olls | +0.792 |
rays | +0.781 |
Neg logit contributions | |
xual | -1.116 |
menstru | -1.051 |
Bir | -0.975 |
20439 | -0.967 |
pees | -0.960 |
Token | also |
Token ID | 635 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
xual | +0.150 |
menstru | +0.140 |
Bir | +0.130 |
pees | +0.128 |
20439 | +0.128 |
Neg logit contributions | |
rolet | -0.148 |
orth | -0.143 |
oppy | -0.134 |
NTS | -0.129 |
olls | -0.128 |
Token | unsupported |
Token ID | 24222 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
xual | +1.121 |
menstru | +1.044 |
Bir | +0.987 |
pees | +0.968 |
20439 | +0.964 |
Neg logit contributions | |
rolet | -0.868 |
orth | -0.832 |
oppy | -0.777 |
NTS | -0.748 |
rays | -0.723 |
Token | on |
Token ID | 319 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
rolet | +0.529 |
orth | +0.507 |
oppy | +0.452 |
NTS | +0.438 |
rays | +0.418 |
Neg logit contributions | |
xual | -1.027 |
menstru | -0.972 |
Bir | -0.910 |
ferment | -0.903 |
pees | -0.901 |
Token | your |
Token ID | 534 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
rolet | +0.497 |
orth | +0.481 |
oppy | +0.453 |
NTS | +0.441 |
olls | +0.425 |
Neg logit contributions | |
xual | -0.690 |
menstru | -0.638 |
Bir | -0.604 |
pees | -0.594 |
ferment | -0.592 |
Token | device |
Token ID | 3335 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
xual | +0.023 |
menstru | +0.021 |
Bir | +0.020 |
女 | +0.020 |
pees | +0.020 |
Neg logit contributions | |
rolet | -0.016 |
orth | -0.016 |
oppy | -0.015 |
NTS | -0.014 |
olls | -0.014 |
Token | Media |
Token ID | 6343 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
xual | +1.616 |
menstru | +1.520 |
Bir | +1.395 |
ferment | +1.380 |
pees | +1.374 |
Neg logit contributions | |
rolet | -1.595 |
orth | -1.525 |
oppy | -1.452 |
NTS | -1.381 |
olls | -1.365 |
Token | caption |
Token ID | 8305 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
xual | +0.204 |
menstru | +0.188 |
Bir | +0.170 |
pees | +0.168 |
20439 | +0.167 |
Neg logit contributions | |
rolet | -0.289 |
orth | -0.281 |
oppy | -0.266 |
NTS | -0.256 |
rays | -0.254 |
Token | Prof |
Token ID | 4415 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
xual | +1.019 |
menstru | +0.966 |
Bir | +0.897 |
ferment | +0.883 |
pees | +0.881 |
Neg logit contributions | |
rolet | -0.836 |
orth | -0.796 |
oppy | -0.749 |
NTS | -0.705 |
olls | -0.703 |
Token | Re |
Token ID | 797 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
rolet | +2.151 |
orth | +2.081 |
oppy | +1.928 |
olls | +1.831 |
NTS | +1.829 |
Neg logit contributions | |
xual | -2.782 |
menstru | -2.661 |
Bir | -2.440 |
20439 | -2.439 |
ferment | -2.414 |
Token | iner |
Token ID | 7274 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
rolet | +0.709 |
orth | +0.686 |
oppy | +0.651 |
igl | +0.609 |
olls | +0.608 |
Neg logit contributions | |
xual | -0.671 |
menstru | -0.633 |
Bir | -0.577 |
20439 | -0.573 |
ferment | -0.569 |
Token | R |
Token ID | 371 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
xual | +0.004 |
menstru | +0.003 |
Bir | +0.003 |
ferment | +0.003 |
pees | +0.003 |
Neg logit contributions | |
rolet | -0.003 |
orth | -0.003 |
oppy | -0.002 |
olls | -0.002 |
NTS | -0.002 |
Token | umm |
Token ID | 13929 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
xual | +1.318 |
menstru | +1.247 |
Bir | +1.154 |
ferment | +1.133 |
pees | +1.129 |
Neg logit contributions | |
rolet | -1.235 |
orth | -1.176 |
oppy | -1.115 |
olls | -1.050 |
NTS | -1.047 |
Token | he |
Token ID | 339 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
xual | +0.594 |
menstru | +0.561 |
Bir | +0.522 |
ferment | +0.515 |
pees | +0.515 |
Neg logit contributions | |
rolet | -0.489 |
orth | -0.467 |
oppy | -0.439 |
olls | -0.412 |
NTS | -0.411 |
Token | said |
Token ID | 531 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
xual | +1.561 |
menstru | +1.489 |
Bir | +1.398 |
ferment | +1.378 |
pees | +1.373 |
Neg logit contributions | |
rolet | -0.945 |
orth | -0.890 |
oppy | -0.828 |
olls | -0.765 |
NTS | -0.760 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
xual | +0.464 |
menstru | +0.442 |
Bir | +0.410 |
ferment | +0.404 |
pees | +0.402 |
Neg logit contributions | |
rolet | -0.370 |
orth | -0.350 |
oppy | -0.331 |
olls | -0.309 |
NTS | -0.308 |
Token | � |
Token ID | 564 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
xual | +0.296 |
menstru | +0.279 |
Bir | +0.256 |
ferment | +0.255 |
pees | +0.254 |
Neg logit contributions | |
rolet | -0.268 |
orth | -0.256 |
oppy | -0.241 |
NTS | -0.228 |
olls | -0.227 |
Token | � |
Token ID | 250 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
rolet | +0.563 |
orth | +0.540 |
oppy | +0.515 |
olls | +0.489 |
NTS | +0.488 |
Neg logit contributions | |
xual | -0.468 |
menstru | -0.440 |
Bir | -0.402 |
ferment | -0.393 |
pees | -0.392 |
Token | Something |
Token ID | 22210 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
rolet | +0.848 |
orth | +0.824 |
oppy | +0.771 |
olls | +0.737 |
rays | +0.736 |
Neg logit contributions | |
xual | -0.818 |
menstru | -0.761 |
ferment | -0.696 |
20439 | -0.685 |
pees | -0.678 |
Token | � |
Token ID | 447 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
xual | +4.187 |
menstru | +3.985 |
Bir | +3.673 |
ferment | +3.611 |
pees | +3.586 |
Neg logit contributions | |
rolet | -3.929 |
orth | -3.715 |
oppy | -3.533 |
olls | -3.313 |
NTS | -3.289 |
Token | � |
Token ID | 247 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
xual | +0.363 |
menstru | +0.339 |
Bir | +0.308 |
ferment | +0.301 |
pees | +0.300 |
Neg logit contributions | |
rolet | -0.481 |
orth | -0.462 |
oppy | -0.442 |
olls | -0.421 |
rays | -0.420 |
Token | s |
Token ID | 82 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
xual | +0.369 |
menstru | +0.350 |
Bir | +0.324 |
ferment | +0.318 |
pees | +0.316 |
Neg logit contributions | |
rolet | -0.348 |
orth | -0.338 |
oppy | -0.317 |
olls | -0.301 |
rays | -0.299 |
Token | going |
Token ID | 1016 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
xual | +0.201 |
menstru | +0.189 |
Bir | +0.176 |
20439 | +0.173 |
pees | +0.172 |
Neg logit contributions | |
rolet | -0.177 |
orth | -0.171 |
oppy | -0.160 |
olls | -0.152 |
NTS | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
xual | +2.037 |
menstru | +1.960 |
Bir | +1.813 |
ferment | +1.803 |
pees | +1.771 |
Neg logit contributions | |
rolet | -1.709 |
orth | -1.616 |
oppy | -1.531 |
olls | -1.416 |
NTS | -1.408 |
Token | when |
Token ID | 618 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
rolet | +0.036 |
orth | +0.034 |
oppy | +0.032 |
NTS | +0.030 |
olls | +0.030 |
Neg logit contributions | |
xual | -0.050 |
menstru | -0.047 |
Bir | -0.045 |
pees | -0.044 |
20439 | -0.044 |
Token | D |
Token ID | 360 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
xual | +0.428 |
menstru | +0.394 |
Bir | +0.372 |
20439 | +0.367 |
pees | +0.366 |
Neg logit contributions | |
rolet | -0.423 |
orth | -0.413 |
oppy | -0.389 |
olls | -0.372 |
NTS | -0.372 |
Token | NR |
Token ID | 24723 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
xual | +0.466 |
menstru | +0.439 |
Bir | +0.405 |
ferment | +0.400 |
20439 | +0.396 |
Neg logit contributions | |
rolet | -0.424 |
orth | -0.406 |
oppy | -0.382 |
olls | -0.360 |
NTS | -0.356 |
Token | biologists |
Token ID | 43149 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
xual | +1.725 |
menstru | +1.629 |
Bir | +1.512 |
ferment | +1.490 |
20439 | +1.485 |
Neg logit contributions | |
rolet | -1.542 |
orth | -1.480 |
oppy | -1.384 |
olls | -1.320 |
NTS | -1.314 |
Token | take |
Token ID | 1011 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
rolet | +1.011 |
orth | +0.973 |
oppy | +0.912 |
olls | +0.868 |
NTS | +0.866 |
Neg logit contributions | |
xual | -1.220 |
menstru | -1.121 |
Bir | -1.076 |
20439 | -1.062 |
pees | -1.056 |
Token | groups |
Token ID | 2628 |
Feature activation | +8.37e-03 |
Pos logit contributions | |
rolet | +1.844 |
orth | +1.789 |
oppy | +1.670 |
olls | +1.617 |
NTS | +1.605 |
Neg logit contributions | |
xual | -2.152 |
menstru | -2.008 |
Bir | -1.905 |
20439 | -1.898 |
pees | -1.870 |
Token | of |
Token ID | 286 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
xual | +0.021 |
menstru | +0.020 |
Bir | +0.019 |
pees | +0.018 |
ferment | +0.018 |
Neg logit contributions | |
rolet | -0.014 |
orth | -0.013 |
oppy | -0.012 |
NTS | -0.011 |
olls | -0.011 |
Token | people |
Token ID | 661 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
xual | +0.406 |
menstru | +0.374 |
Bir | +0.349 |
20439 | +0.341 |
pees | +0.339 |
Neg logit contributions | |
rolet | -0.488 |
orth | -0.474 |
oppy | -0.447 |
NTS | -0.432 |
olls | -0.432 |
Token | to |
Token ID | 284 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rolet | +0.221 |
orth | +0.211 |
oppy | +0.197 |
NTS | +0.186 |
olls | +0.186 |
Neg logit contributions | |
xual | -0.310 |
menstru | -0.289 |
Bir | -0.274 |
pees | -0.270 |
20439 | -0.270 |
Token | dens |
Token ID | 29509 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
xual | +0.260 |
menstru | +0.241 |
Bir | +0.224 |
20439 | +0.222 |
pees | +0.219 |
Neg logit contributions | |
rolet | -0.248 |
orth | -0.237 |
oppy | -0.225 |
olls | -0.214 |
NTS | -0.213 |
Token | during |
Token ID | 1141 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
xual | +2.096 |
menstru | +1.992 |
Bir | +1.853 |
ferment | +1.822 |
pees | +1.816 |
Neg logit contributions | |
rolet | -1.695 |
orth | -1.610 |
oppy | -1.518 |
olls | -1.422 |
NTS | -1.416 |
Token | Government |
Token ID | 5070 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
rolet | +0.540 |
orth | +0.516 |
oppy | +0.489 |
NTS | +0.466 |
olls | +0.461 |
Neg logit contributions | |
xual | -0.575 |
menstru | -0.538 |
Bir | -0.501 |
ferment | -0.490 |
pees | -0.490 |
Token | should |
Token ID | 815 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
rolet | +1.236 |
orth | +1.181 |
oppy | +1.108 |
NTS | +1.055 |
rays | +1.044 |
Neg logit contributions | |
xual | -1.385 |
menstru | -1.289 |
Bir | -1.217 |
20439 | -1.184 |
pees | -1.183 |
Token | immediately |
Token ID | 3393 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
rolet | +0.675 |
orth | +0.639 |
oppy | +0.600 |
NTS | +0.573 |
olls | +0.566 |
Neg logit contributions | |
xual | -0.720 |
menstru | -0.665 |
Bir | -0.638 |
20439 | -0.622 |
pees | -0.620 |
Token | bring |
Token ID | 2222 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
rolet | +0.003 |
orth | +0.003 |
oppy | +0.003 |
NTS | +0.003 |
olls | +0.003 |
Neg logit contributions | |
xual | -0.004 |
menstru | -0.003 |
Bir | -0.003 |
20439 | -0.003 |
pees | -0.003 |
Token | amendments |
Token ID | 17835 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
xual | +0.599 |
menstru | +0.569 |
Bir | +0.535 |
pees | +0.524 |
ferment | +0.523 |
Neg logit contributions | |
rolet | -0.410 |
orth | -0.388 |
oppy | -0.362 |
NTS | -0.339 |
olls | -0.337 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
rolet | +0.047 |
orth | +0.045 |
oppy | +0.042 |
NTS | +0.040 |
olls | +0.040 |
Neg logit contributions | |
xual | -0.059 |
menstru | -0.056 |
Bir | -0.053 |
ferment | -0.052 |
pees | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
rolet | +0.515 |
orth | +0.492 |
oppy | +0.466 |
NTS | +0.441 |
olls | +0.440 |
Neg logit contributions | |
xual | -0.521 |
menstru | -0.490 |
Bir | -0.454 |
ferment | -0.444 |
pees | -0.443 |
Token | present |
Token ID | 1944 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
rolet | +0.521 |
orth | +0.495 |
oppy | +0.465 |
NTS | +0.440 |
olls | +0.437 |
Neg logit contributions | |
xual | -0.676 |
menstru | -0.637 |
Bir | -0.597 |
pees | -0.586 |
ferment | -0.584 |
Token | Motor |
Token ID | 12533 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
rolet | +0.499 |
orth | +0.474 |
oppy | +0.441 |
NTS | +0.419 |
olls | +0.415 |
Neg logit contributions | |
xual | -0.698 |
menstru | -0.659 |
Bir | -0.618 |
pees | -0.610 |
ferment | -0.605 |
Token | Vehicle |
Token ID | 21501 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
rolet | +0.800 |
orth | +0.755 |
oppy | +0.709 |
olls | +0.659 |
rays | +0.654 |
Neg logit contributions | |
xual | -1.150 |
menstru | -1.103 |
Bir | -1.035 |
ferment | -1.014 |
pees | -1.008 |
Token | Act |
Token ID | 2191 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
rolet | +0.708 |
orth | +0.670 |
oppy | +0.633 |
olls | +0.593 |
rays | +0.587 |
Neg logit contributions | |
xual | -0.894 |
menstru | -0.852 |
Bir | -0.793 |
ferment | -0.780 |
pees | -0.774 |
Token | users |
Token ID | 2985 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
rolet | +0.082 |
orth | +0.079 |
oppy | +0.076 |
NTS | +0.072 |
olls | +0.071 |
Neg logit contributions | |
xual | -0.074 |
menstru | -0.069 |
Bir | -0.063 |
pees | -0.062 |
20439 | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
xual | +0.737 |
menstru | +0.700 |
Bir | +0.651 |
ferment | +0.640 |
pees | +0.638 |
Neg logit contributions | |
rolet | -0.599 |
orth | -0.568 |
oppy | -0.536 |
olls | -0.503 |
NTS | -0.500 |
Token | install |
Token ID | 2721 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
xual | +0.643 |
menstru | +0.602 |
Bir | +0.568 |
20439 | +0.558 |
pees | +0.555 |
Neg logit contributions | |
rolet | -0.580 |
orth | -0.553 |
oppy | -0.521 |
NTS | -0.496 |
olls | -0.488 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
rolet | +0.111 |
orth | +0.106 |
oppy | +0.101 |
NTS | +0.095 |
olls | +0.094 |
Neg logit contributions | |
xual | -0.133 |
menstru | -0.125 |
Bir | -0.117 |
pees | -0.115 |
20439 | -0.114 |
Token | remove |
Token ID | 4781 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
rolet | +0.360 |
orth | +0.344 |
oppy | +0.323 |
NTS | +0.309 |
olls | +0.304 |
Neg logit contributions | |
xual | -0.396 |
menstru | -0.370 |
Bir | -0.348 |
20439 | -0.341 |
pees | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
xual | +0.300 |
menstru | +0.282 |
Bir | +0.261 |
pees | +0.256 |
20439 | +0.256 |
Neg logit contributions | |
rolet | -0.285 |
orth | -0.274 |
oppy | -0.260 |
NTS | -0.246 |
olls | -0.244 |
Token | MS |
Token ID | 5653 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
xual | +0.048 |
menstru | +0.046 |
ferment | +0.042 |
Bir | +0.042 |
pees | +0.042 |
Neg logit contributions | |
rolet | -0.041 |
orth | -0.039 |
oppy | -0.037 |
NTS | -0.035 |
olls | -0.035 |
Token | I |
Token ID | 40 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
rolet | +0.620 |
orth | +0.605 |
oppy | +0.567 |
igl | +0.537 |
olls | +0.535 |
Neg logit contributions | |
xual | -0.543 |
menstru | -0.508 |
ferment | -0.466 |
pees | -0.465 |
20439 | -0.463 |
Token | exclusive |
Token ID | 8568 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
rolet | +0.749 |
orth | +0.720 |
oppy | +0.668 |
NTS | +0.639 |
olls | +0.628 |
Neg logit contributions | |
xual | -0.875 |
menstru | -0.828 |
Bir | -0.768 |
20439 | -0.763 |
pees | -0.760 |
Token | Un |
Token ID | 791 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
xual | +0.890 |
menstru | +0.839 |
Bir | +0.779 |
pees | +0.769 |
ferment | +0.766 |
Neg logit contributions | |
rolet | -0.751 |
orth | -0.718 |
oppy | -0.675 |
NTS | -0.639 |
olls | -0.632 |
Token | locked |
Token ID | 24162 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
rolet | +0.249 |
orth | +0.237 |
oppy | +0.224 |
olls | +0.209 |
NTS | +0.208 |
Neg logit contributions | |
xual | -0.306 |
menstru | -0.291 |
Bir | -0.270 |
ferment | -0.266 |
pees | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
xual | +0.063 |
menstru | +0.060 |
Bir | +0.055 |
pees | +0.054 |
ferment | +0.054 |
Neg logit contributions | |
rolet | -0.055 |
orth | -0.053 |
oppy | -0.050 |
olls | -0.047 |
NTS | -0.047 |
Token | � |
Token ID | 447 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
xual | +0.524 |
menstru | +0.495 |
Bir | +0.459 |
pees | +0.450 |
ferment | +0.450 |
Neg logit contributions | |
rolet | -0.485 |
orth | -0.462 |
oppy | -0.437 |
olls | -0.412 |
NTS | -0.411 |
Token | � |
Token ID | 251 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
rolet | +0.094 |
orth | +0.090 |
oppy | +0.087 |
rays | +0.082 |
olls | +0.082 |
Neg logit contributions | |
xual | -0.058 |
menstru | -0.053 |
Bir | -0.048 |
ferment | -0.046 |
20439 | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
xual | +0.883 |
menstru | +0.837 |
Bir | +0.778 |
pees | +0.762 |
20439 | +0.760 |
Neg logit contributions | |
rolet | -0.870 |
orth | -0.840 |
oppy | -0.788 |
olls | -0.747 |
NTS | -0.746 |
Token | powerful |
Token ID | 3665 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
xual | +0.450 |
menstru | +0.427 |
Bir | +0.401 |
20439 | +0.392 |
pees | +0.392 |
Neg logit contributions | |
rolet | -0.402 |
orth | -0.387 |
oppy | -0.361 |
NTS | -0.344 |
olls | -0.339 |
Token | � |
Token ID | 564 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
xual | +1.322 |
menstru | +1.245 |
Bir | +1.167 |
pees | +1.144 |
20439 | +1.141 |
Neg logit contributions | |
rolet | -1.217 |
orth | -1.165 |
oppy | -1.088 |
NTS | -1.031 |
rays | -1.024 |
Token | � |
Token ID | 250 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
xual | +0.845 |
menstru | +0.797 |
Bir | +0.732 |
ferment | +0.717 |
pees | +0.714 |
Neg logit contributions | |
rolet | -0.921 |
orth | -0.881 |
oppy | -0.838 |
olls | -0.794 |
NTS | -0.790 |
Token | set |
Token ID | 2617 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
rolet | +0.565 |
orth | +0.551 |
oppy | +0.508 |
rays | +0.489 |
olls | +0.485 |
Neg logit contributions | |
xual | -0.566 |
menstru | -0.538 |
Bir | -0.491 |
ferment | -0.489 |
20439 | -0.483 |
Token | their |
Token ID | 511 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
xual | +0.080 |
menstru | +0.076 |
Bir | +0.071 |
pees | +0.070 |
20439 | +0.070 |
Neg logit contributions | |
rolet | -0.067 |
orth | -0.064 |
oppy | -0.060 |
olls | -0.057 |
rays | -0.057 |
Token | seal |
Token ID | 13810 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
xual | +0.939 |
menstru | +0.885 |
Bir | +0.824 |
20439 | +0.811 |
pees | +0.803 |
Neg logit contributions | |
rolet | -0.892 |
orth | -0.860 |
oppy | -0.805 |
olls | -0.762 |
NTS | -0.762 |
Token | on |
Token ID | 319 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
xual | +1.091 |
menstru | +1.040 |
Bir | +0.974 |
ferment | +0.959 |
pees | +0.956 |
Neg logit contributions | |
rolet | -0.726 |
orth | -0.686 |
oppy | -0.640 |
olls | -0.596 |
NTS | -0.593 |
Token | Morning |
Token ID | 14410 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
rolet | +0.386 |
orth | +0.368 |
oppy | +0.322 |
NTS | +0.291 |
olls | +0.287 |
Neg logit contributions | |
xual | -1.135 |
menstru | -1.087 |
ferment | -1.031 |
Bir | -1.023 |
20439 | -1.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
xual | +0.166 |
menstru | +0.158 |
Bir | +0.147 |
ferment | +0.145 |
pees | +0.144 |
Neg logit contributions | |
rolet | -0.129 |
orth | -0.123 |
oppy | -0.115 |
NTS | -0.108 |
olls | -0.108 |
Token | 16 |
Token ID | 1467 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
xual | +0.446 |
menstru | +0.425 |
Bir | +0.393 |
ferment | +0.391 |
pees | +0.385 |
Neg logit contributions | |
rolet | -0.369 |
orth | -0.354 |
oppy | -0.331 |
olls | -0.312 |
NTS | -0.311 |
Token | W |
Token ID | 370 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
rolet | +0.678 |
orth | +0.661 |
oppy | +0.619 |
NTS | +0.589 |
rays | +0.583 |
Neg logit contributions | |
xual | -0.751 |
menstru | -0.708 |
Bir | -0.649 |
ferment | -0.645 |
pees | -0.641 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
rolet | +0.798 |
orth | +0.771 |
oppy | +0.726 |
olls | +0.684 |
NTS | +0.676 |
Neg logit contributions | |
xual | -0.926 |
menstru | -0.873 |
Bir | -0.803 |
ferment | -0.791 |
20439 | -0.788 |
Token | Madison |
Token ID | 14909 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
rolet | +0.044 |
orth | +0.042 |
oppy | +0.040 |
NTS | +0.038 |
olls | +0.038 |
Neg logit contributions | |
xual | -0.051 |
menstru | -0.048 |
Bir | -0.044 |
ferment | -0.044 |
pees | -0.044 |
Token | St |
Token ID | 520 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
xual | +0.052 |
menstru | +0.049 |
Bir | +0.046 |
ferment | +0.045 |
20439 | +0.045 |
Neg logit contributions | |
rolet | -0.042 |
orth | -0.040 |
oppy | -0.038 |
NTS | -0.036 |
olls | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
rolet | +2.014 |
orth | +1.945 |
oppy | +1.821 |
NTS | +1.717 |
olls | +1.712 |
Neg logit contributions | |
xual | -2.550 |
menstru | -2.414 |
ferment | -2.205 |
Bir | -2.203 |
20439 | -2.198 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
rolet | +0.201 |
orth | +0.192 |
oppy | +0.180 |
NTS | +0.170 |
olls | +0.169 |
Neg logit contributions | |
xual | -0.260 |
menstru | -0.247 |
Bir | -0.226 |
ferment | -0.226 |
pees | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
rolet | +2.026 |
orth | +1.953 |
oppy | +1.793 |
NTS | +1.717 |
rays | +1.698 |
Neg logit contributions | |
xual | -3.092 |
menstru | -2.913 |
pees | -2.695 |
Bir | -2.683 |
ferment | -2.678 |
Token | MD |
Token ID | 10670 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
rolet | +0.696 |
orth | +0.652 |
oppy | +0.590 |
NTS | +0.545 |
rays | +0.539 |
Neg logit contributions | |
xual | -1.528 |
menstru | -1.453 |
Bir | -1.360 |
ferment | -1.360 |
pees | -1.359 |
Token | � |
Token ID | 447 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
rolet | +0.110 |
orth | +0.105 |
oppy | +0.099 |
NTS | +0.094 |
olls | +0.093 |
Neg logit contributions | |
xual | -0.122 |
menstru | -0.115 |
Bir | -0.106 |
ferment | -0.105 |
pees | -0.105 |
Token | � |
Token ID | 251 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
rolet | +0.610 |
orth | +0.585 |
oppy | +0.559 |
olls | +0.530 |
NTS | +0.529 |
Neg logit contributions | |
xual | -0.501 |
menstru | -0.470 |
Bir | -0.429 |
ferment | -0.420 |
pees | -0.419 |
Token | In |
Token ID | 554 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
rolet | +0.492 |
orth | +0.471 |
oppy | +0.444 |
NTS | +0.423 |
olls | +0.418 |
Neg logit contributions | |
xual | -0.565 |
menstru | -0.531 |
ferment | -0.486 |
Bir | -0.486 |
pees | -0.485 |
Token | reality |
Token ID | 3950 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
rolet | +0.420 |
orth | +0.406 |
oppy | +0.383 |
NTS | +0.363 |
olls | +0.360 |
Neg logit contributions | |
xual | -0.461 |
menstru | -0.434 |
Bir | -0.401 |
pees | -0.396 |
ferment | -0.396 |
Token | the |
Token ID | 262 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
rolet | +0.611 |
orth | +0.580 |
oppy | +0.549 |
olls | +0.515 |
NTS | +0.511 |
Neg logit contributions | |
xual | -0.701 |
menstru | -0.669 |
Bir | -0.621 |
ferment | -0.608 |
pees | -0.604 |
Token | photo |
Token ID | 4590 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
xual | +0.738 |
menstru | +0.700 |
Bir | +0.659 |
pees | +0.650 |
20439 | +0.650 |
Neg logit contributions | |
rolet | -0.452 |
orth | -0.428 |
oppy | -0.400 |
NTS | -0.373 |
olls | -0.370 |
Token | was |
Token ID | 373 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
rolet | +2.446 |
orth | +2.359 |
oppy | +2.190 |
NTS | +2.136 |
olls | +2.113 |
Neg logit contributions | |
xual | -3.375 |
menstru | -3.177 |
20439 | -3.015 |
Bir | -2.983 |
pees | -2.944 |
Token | taken |
Token ID | 2077 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
rolet | +0.076 |
orth | +0.072 |
oppy | +0.068 |
NTS | +0.064 |
olls | +0.064 |
Neg logit contributions | |
xual | -0.092 |
menstru | -0.087 |
Bir | -0.081 |
pees | -0.080 |
20439 | -0.079 |
Token | by |
Token ID | 416 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
rolet | +2.622 |
orth | +2.483 |
oppy | +2.320 |
NTS | +2.229 |
olls | +2.193 |
Neg logit contributions | |
xual | -3.828 |
menstru | -3.570 |
20439 | -3.407 |
Bir | -3.395 |
pees | -3.376 |
Token | Reuters |
Token ID | 8428 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
rolet | +0.767 |
orth | +0.733 |
oppy | +0.693 |
NTS | +0.661 |
olls | +0.655 |
Neg logit contributions | |
xual | -0.877 |
menstru | -0.822 |
Bir | -0.764 |
pees | -0.755 |
20439 | -0.752 |
Token | in |
Token ID | 287 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
rolet | +0.446 |
orth | +0.426 |
oppy | +0.394 |
NTS | +0.368 |
olls | +0.366 |
Neg logit contributions | |
xual | -0.683 |
menstru | -0.652 |
Bir | -0.610 |
pees | -0.603 |
ferment | -0.602 |
Token | It |
Token ID | 1026 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
rolet | +0.811 |
orth | +0.786 |
oppy | +0.738 |
olls | +0.701 |
NTS | +0.693 |
Neg logit contributions | |
xual | -0.845 |
menstru | -0.783 |
ferment | -0.718 |
pees | -0.703 |
20439 | -0.696 |
Token | also |
Token ID | 635 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
xual | +0.485 |
menstru | +0.457 |
Bir | +0.428 |
20439 | +0.420 |
pees | +0.419 |
Neg logit contributions | |
rolet | -0.397 |
orth | -0.380 |
oppy | -0.357 |
olls | -0.337 |
NTS | -0.334 |
Token | means |
Token ID | 1724 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
xual | +0.389 |
menstru | +0.365 |
Bir | +0.343 |
20439 | +0.337 |
pees | +0.335 |
Neg logit contributions | |
rolet | -0.325 |
orth | -0.313 |
oppy | -0.294 |
olls | -0.278 |
rays | -0.276 |
Token | that |
Token ID | 326 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
xual | +0.701 |
menstru | +0.660 |
Bir | +0.612 |
pees | +0.605 |
20439 | +0.602 |
Neg logit contributions | |
rolet | -0.595 |
orth | -0.569 |
oppy | -0.534 |
NTS | -0.507 |
olls | -0.505 |
Token | all |
Token ID | 477 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
xual | +0.883 |
menstru | +0.829 |
Bir | +0.768 |
20439 | +0.762 |
pees | +0.760 |
Neg logit contributions | |
rolet | -0.769 |
orth | -0.739 |
oppy | -0.699 |
NTS | -0.663 |
olls | -0.658 |
Token | law |
Token ID | 1099 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
xual | +1.642 |
menstru | +1.556 |
Bir | +1.450 |
pees | +1.426 |
ferment | +1.425 |
Neg logit contributions | |
rolet | -1.229 |
orth | -1.169 |
oppy | -1.099 |
NTS | -1.030 |
olls | -1.027 |
Token | students |
Token ID | 2444 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
rolet | +2.356 |
orth | +2.345 |
oppy | +2.126 |
NTS | +2.010 |
rays | +1.973 |
Neg logit contributions | |
xual | -3.859 |
menstru | -3.611 |
20439 | -3.385 |
Bir | -3.381 |
pees | -3.370 |
Token | , |
Token ID | 11 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
xual | +0.837 |
menstru | +0.789 |
Bir | +0.740 |
pees | +0.727 |
ferment | +0.725 |
Neg logit contributions | |
rolet | -0.629 |
orth | -0.601 |
oppy | -0.560 |
NTS | -0.527 |
olls | -0.525 |
Token | regardless |
Token ID | 7692 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
xual | +0.805 |
menstru | +0.762 |
Bir | +0.708 |
ferment | +0.698 |
pees | +0.696 |
Neg logit contributions | |
rolet | -0.672 |
orth | -0.638 |
oppy | -0.601 |
olls | -0.565 |
NTS | -0.565 |
Token | of |
Token ID | 286 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
rolet | +0.254 |
orth | +0.242 |
oppy | +0.222 |
NTS | +0.208 |
olls | +0.204 |
Neg logit contributions | |
xual | -0.468 |
menstru | -0.445 |
Bir | -0.420 |
pees | -0.416 |
ferment | -0.415 |
Token | their |
Token ID | 511 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
rolet | +0.713 |
orth | +0.686 |
oppy | +0.650 |
NTS | +0.624 |
olls | +0.614 |
Neg logit contributions | |
xual | -0.740 |
menstru | -0.688 |
Bir | -0.643 |
20439 | -0.636 |
pees | -0.636 |
Token | support |
Token ID | 1104 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
xual | +2.028 |
menstru | +1.927 |
Bir | +1.802 |
ferment | +1.771 |
pees | +1.769 |
Neg logit contributions | |
rolet | -1.493 |
orth | -1.415 |
oppy | -1.328 |
olls | -1.241 |
NTS | -1.236 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
xual | +0.991 |
menstru | +0.941 |
Bir | +0.880 |
ferment | +0.866 |
pees | +0.864 |
Neg logit contributions | |
rolet | -0.728 |
orth | -0.691 |
oppy | -0.648 |
olls | -0.607 |
NTS | -0.605 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
xual | +0.923 |
menstru | +0.876 |
Bir | +0.814 |
ferment | +0.801 |
pees | +0.798 |
Neg logit contributions | |
rolet | -0.764 |
orth | -0.727 |
oppy | -0.685 |
olls | -0.643 |
NTS | -0.640 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
xual | +0.030 |
menstru | +0.028 |
ferment | +0.026 |
Bir | +0.026 |
pees | +0.026 |
Neg logit contributions | |
rolet | -0.025 |
orth | -0.024 |
oppy | -0.022 |
NTS | -0.021 |
olls | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
xual | +0.007 |
menstru | +0.007 |
pees | +0.006 |
ferment | +0.006 |
Bir | +0.006 |
Neg logit contributions | |
rolet | -0.005 |
orth | -0.005 |
oppy | -0.005 |
NTS | -0.004 |
olls | -0.004 |
Token | Back |
Token ID | 7282 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
xual | +0.077 |
menstru | +0.072 |
ferment | +0.066 |
pees | +0.065 |
Bir | +0.064 |
Neg logit contributions | |
rolet | -0.071 |
orth | -0.069 |
oppy | -0.065 |
olls | -0.061 |
rays | -0.061 |
Token | during |
Token ID | 1141 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
rolet | +2.678 |
orth | +2.506 |
oppy | +2.338 |
NTS | +2.242 |
olls | +2.220 |
Neg logit contributions | |
xual | -3.555 |
menstru | -3.342 |
Bir | -3.128 |
pees | -3.096 |
ferment | -3.082 |
Token | the |
Token ID | 262 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
rolet | +1.068 |
orth | +1.018 |
oppy | +0.969 |
olls | +0.923 |
NTS | +0.922 |
Neg logit contributions | |
xual | -1.145 |
menstru | -1.057 |
Bir | -0.994 |
pees | -0.983 |
20439 | -0.973 |
Token | early |
Token ID | 1903 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
rolet | +0.079 |
orth | +0.075 |
oppy | +0.071 |
NTS | +0.067 |
olls | +0.067 |
Neg logit contributions | |
xual | -0.110 |
menstru | -0.103 |
Bir | -0.097 |
pees | -0.096 |
20439 | -0.095 |
Token | parts |
Token ID | 3354 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
xual | +0.208 |
menstru | +0.195 |
Bir | +0.181 |
pees | +0.177 |
20439 | +0.176 |
Neg logit contributions | |
rolet | -0.195 |
orth | -0.187 |
oppy | -0.177 |
NTS | -0.167 |
olls | -0.167 |
Token | of |
Token ID | 286 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
rolet | +0.477 |
orth | +0.458 |
oppy | +0.416 |
NTS | +0.392 |
olls | +0.381 |
Neg logit contributions | |
xual | -0.932 |
menstru | -0.887 |
Bir | -0.838 |
pees | -0.834 |
ferment | -0.828 |
Token | � |
Token ID | 12466 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
rolet | +1.558 |
orth | +1.487 |
oppy | +1.387 |
NTS | +1.307 |
olls | +1.299 |
Neg logit contributions | |
xual | -1.787 |
menstru | -1.687 |
Bir | -1.564 |
pees | -1.542 |
ferment | -1.535 |
Token | � |
Token ID | 111 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
rolet | +1.813 |
orth | +1.744 |
oppy | +1.648 |
olls | +1.587 |
NTS | +1.567 |
Neg logit contributions | |
xual | -1.455 |
menstru | -1.360 |
Bir | -1.246 |
pees | -1.216 |
ferment | -1.212 |
Token | о |
Token ID | 15166 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
rolet | +1.220 |
orth | +1.154 |
oppy | +1.078 |
olls | +1.006 |
NTS | +1.001 |
Neg logit contributions | |
xual | -1.620 |
menstru | -1.544 |
Bir | -1.436 |
ferment | -1.420 |
pees | -1.409 |
Token | р |
Token ID | 21169 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
rolet | +1.236 |
orth | +1.182 |
oppy | +1.096 |
NTS | +1.028 |
olls | +1.027 |
Neg logit contributions | |
xual | -1.548 |
menstru | -1.471 |
Bir | -1.364 |
pees | -1.357 |
ferment | -1.343 |
Token | я |
Token ID | 40623 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
rolet | +1.529 |
orth | +1.464 |
oppy | +1.364 |
NTS | +1.269 |
rays | +1.269 |
Neg logit contributions | |
xual | -1.862 |
menstru | -1.781 |
Bir | -1.636 |
pees | -1.632 |
ferment | -1.620 |
Token | � |
Token ID | 141 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
rolet | +2.102 |
orth | +2.018 |
oppy | +1.880 |
NTS | +1.804 |
olls | +1.789 |
Neg logit contributions | |
xual | -1.915 |
menstru | -1.792 |
Bir | -1.641 |
pees | -1.625 |
ferment | -1.611 |
Token | � |
Token ID | 229 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
rolet | +2.559 |
orth | +2.444 |
oppy | +2.311 |
olls | +2.193 |
rays | +2.182 |
Neg logit contributions | |
xual | -2.557 |
menstru | -2.395 |
Bir | -2.236 |
pees | -2.211 |
20439 | -2.190 |
Token | и |
Token ID | 18849 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
rolet | +1.168 |
orth | +1.126 |
oppy | +1.060 |
NTS | +0.997 |
olls | +0.994 |
Neg logit contributions | |
xual | -1.308 |
menstru | -1.236 |
Bir | -1.148 |
pees | -1.127 |
20439 | -1.127 |
Token | � |
Token ID | 141 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
rolet | +1.778 |
orth | +1.717 |
oppy | +1.611 |
NTS | +1.524 |
olls | +1.517 |
Neg logit contributions | |
xual | -1.762 |
menstru | -1.650 |
Bir | -1.530 |
20439 | -1.490 |
ferment | -1.484 |
Token | � |
Token ID | 227 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
rolet | +2.881 |
orth | +2.762 |
oppy | +2.609 |
NTS | +2.478 |
rays | +2.469 |
Neg logit contributions | |
xual | -2.914 |
menstru | -2.736 |
Bir | -2.553 |
20439 | -2.509 |
pees | -2.505 |
Token | |
Token ID | 220 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
rolet | +0.507 |
orth | +0.482 |
oppy | +0.450 |
NTS | +0.425 |
olls | +0.422 |
Neg logit contributions | |
xual | -0.656 |
menstru | -0.621 |
Bir | -0.578 |
pees | -0.571 |
ferment | -0.567 |
Token | FI |
Token ID | 11674 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
rolet | +0.025 |
orth | +0.024 |
oppy | +0.023 |
olls | +0.022 |
NTS | +0.022 |
Neg logit contributions | |
xual | -0.023 |
menstru | -0.021 |
Bir | -0.019 |
ferment | -0.019 |
20439 | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
rolet | +0.401 |
orth | +0.385 |
oppy | +0.362 |
NTS | +0.343 |
olls | +0.341 |
Neg logit contributions | |
xual | -0.527 |
menstru | -0.494 |
Bir | -0.463 |
20439 | -0.455 |
pees | -0.452 |
Token | getting |
Token ID | 1972 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rolet | +0.375 |
orth | +0.360 |
oppy | +0.338 |
NTS | +0.324 |
olls | +0.323 |
Neg logit contributions | |
xual | -0.409 |
menstru | -0.377 |
Bir | -0.355 |
20439 | -0.347 |
pees | -0.346 |
Token | into |
Token ID | 656 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
xual | +0.227 |
menstru | +0.214 |
Bir | +0.200 |
20439 | +0.196 |
pees | +0.195 |
Neg logit contributions | |
rolet | -0.206 |
orth | -0.198 |
oppy | -0.187 |
olls | -0.178 |
NTS | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
rolet | +0.686 |
orth | +0.660 |
oppy | +0.628 |
NTS | +0.596 |
olls | +0.590 |
Neg logit contributions | |
xual | -0.704 |
menstru | -0.664 |
Bir | -0.616 |
pees | -0.602 |
20439 | -0.602 |
Token | radio |
Token ID | 5243 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
rolet | +0.662 |
orth | +0.638 |
oppy | +0.602 |
NTS | +0.576 |
rays | +0.564 |
Neg logit contributions | |
xual | -0.845 |
menstru | -0.794 |
Bir | -0.743 |
20439 | -0.737 |
pees | -0.730 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
rolet | +2.425 |
orth | +2.366 |
oppy | +2.221 |
NTS | +2.106 |
rays | +2.074 |
Neg logit contributions | |
xual | -3.357 |
menstru | -3.154 |
Bir | -2.964 |
20439 | -2.954 |
女 | -2.873 |
Token | The |
Token ID | 383 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
rolet | +0.391 |
orth | +0.376 |
oppy | +0.352 |
NTS | +0.340 |
olls | +0.331 |
Neg logit contributions | |
xual | -0.464 |
menstru | -0.438 |
Bir | -0.401 |
ferment | -0.398 |
pees | -0.398 |
Token | following |
Token ID | 1708 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
rolet | +1.206 |
orth | +1.170 |
oppy | +1.097 |
NTS | +1.049 |
olls | +1.019 |
Neg logit contributions | |
xual | -1.611 |
menstru | -1.518 |
Bir | -1.421 |
20439 | -1.406 |
pees | -1.397 |
Token | is |
Token ID | 318 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
rolet | +1.604 |
orth | +1.553 |
oppy | +1.441 |
NTS | +1.416 |
rays | +1.368 |
Neg logit contributions | |
xual | -2.087 |
menstru | -1.938 |
Bir | -1.825 |
pees | -1.792 |
20439 | -1.788 |
Token | a |
Token ID | 257 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
rolet | +0.764 |
orth | +0.737 |
oppy | +0.691 |
NTS | +0.661 |
olls | +0.650 |
Neg logit contributions | |
xual | -0.863 |
menstru | -0.813 |
Bir | -0.759 |
pees | -0.743 |
ferment | -0.738 |