Token | x |
Token ID | 2124 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Weld | +1.851 |
ationally | +1.800 |
ammy | +1.757 |
netflix | +1.694 |
ittle | +1.692 |
Neg logit contributions | |
eret | -2.019 |
cano | -1.914 |
hell | -1.838 |
voic | -1.801 |
bras | -1.780 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
eret | +1.390 |
cano | +1.285 |
hell | +1.268 |
voic | +1.218 |
bras | +1.209 |
Neg logit contributions | |
Weld | -1.599 |
ationally | -1.580 |
ammy | -1.566 |
ittle | -1.507 |
netflix | -1.506 |
Token | x |
Token ID | 87 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ationally | +1.421 |
Weld | +1.412 |
ammy | +1.367 |
netflix | +1.319 |
ittle | +1.306 |
Neg logit contributions | |
eret | -2.507 |
cano | -2.406 |
voic | -2.362 |
bras | -2.347 |
hell | -2.311 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
Weld | +2.318 |
ationally | +2.262 |
ammy | +2.185 |
netflix | +2.138 |
ittle | +2.119 |
Neg logit contributions | |
eret | -2.624 |
cano | -2.494 |
voic | -2.406 |
bras | -2.374 |
hell | -2.361 |
Token | x |
Token ID | 87 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
ationally | +3.123 |
Weld | +3.000 |
ammy | +2.955 |
netflix | +2.869 |
gans | +2.866 |
Neg logit contributions | |
eret | -6.824 |
voic | -6.693 |
bras | -6.661 |
cano | -6.626 |
notor | -6.479 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+01 |
Pos logit contributions | |
Weld | +5.767 |
ationally | +5.402 |
ammy | +5.267 |
gans | +5.166 |
ittle | +5.118 |
Neg logit contributions | |
eret | -8.586 |
notor | -8.425 |
voic | -8.289 |
cano | -8.243 |
bras | -8.108 |
Token | 151 |
Token ID | 24309 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Weld | +5.288 |
uld | +4.409 |
ammy | +4.247 |
gans | +4.201 |
ationally | +4.154 |
Neg logit contributions | |
eret | -18.081 |
voic | -17.346 |
bras | -17.171 |
cano | -17.026 |
Xperia | -16.841 |
Token | 103 |
Token ID | 15349 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
eret | +1.125 |
cano | +1.054 |
hell | +1.035 |
voic | +1.008 |
bras | +0.997 |
Neg logit contributions | |
Weld | -1.112 |
ationally | -1.101 |
ammy | -1.085 |
ittle | -1.046 |
netflix | -1.044 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eret | +4.282 |
hell | +3.963 |
cano | +3.858 |
tes | +3.727 |
bras | +3.707 |
Neg logit contributions | |
ationally | -5.555 |
ammy | -5.531 |
Weld | -5.421 |
ittle | -5.253 |
netflix | -5.213 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
eret | +0.799 |
cano | +0.743 |
hell | +0.729 |
voic | +0.705 |
bras | +0.699 |
Neg logit contributions | |
Weld | -0.889 |
ationally | -0.878 |
ammy | -0.867 |
ittle | -0.836 |
netflix | -0.836 |
Token | x |
Token ID | 2124 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
eret | +0.682 |
cano | +0.634 |
hell | +0.621 |
voic | +0.604 |
bras | +0.599 |
Neg logit contributions | |
Weld | -0.748 |
ationally | -0.739 |
ammy | -0.728 |
netflix | -0.704 |
ittle | -0.703 |
Token | x |
Token ID | 2124 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
eret | +0.884 |
cano | +0.819 |
hell | +0.804 |
voic | +0.783 |
bras | +0.776 |
Neg logit contributions | |
Weld | -0.978 |
ationally | -0.965 |
ammy | -0.953 |
netflix | -0.920 |
ittle | -0.919 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
eret | +1.950 |
cano | +1.791 |
hell | +1.782 |
voic | +1.694 |
bras | +1.683 |
Neg logit contributions | |
Weld | -2.349 |
ationally | -2.327 |
ammy | -2.315 |
ittle | -2.225 |
netflix | -2.220 |
Token | x |
Token ID | 87 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
Weld | +0.132 |
ationally | +0.131 |
ammy | +0.127 |
netflix | +0.122 |
ittle | +0.122 |
Neg logit contributions | |
eret | -0.203 |
cano | -0.193 |
hell | -0.188 |
voic | -0.186 |
bras | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
Weld | +2.475 |
ationally | +2.413 |
ammy | +2.332 |
netflix | +2.276 |
ittle | +2.260 |
Neg logit contributions | |
eret | -2.829 |
cano | -2.695 |
voic | -2.598 |
bras | -2.567 |
hell | -2.546 |
Token | x |
Token ID | 87 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ationally | +3.847 |
ammy | +3.740 |
Weld | +3.737 |
gans | +3.534 |
ittle | +3.516 |
Neg logit contributions | |
bras | -9.153 |
eret | -9.116 |
voic | -9.109 |
notor | -9.023 |
contrace | -8.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
Weld | +6.696 |
ationally | +6.205 |
ammy | +6.130 |
^^^^ | +6.080 |
ittle | +6.080 |
Neg logit contributions | |
notor | -11.254 |
eret | -10.784 |
contrace | -10.779 |
voic | -10.570 |
bras | -10.544 |
Token | 153 |
Token ID | 21395 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Weld | +6.240 |
ittle | +5.968 |
ammy | +5.851 |
ationally | +5.655 |
uld | +5.631 |
Neg logit contributions | |
eret | -14.358 |
bras | -14.258 |
cano | -13.913 |
Instr | -13.846 |
notor | -13.825 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
eret | +1.302 |
cano | +1.219 |
hell | +1.200 |
voic | +1.170 |
bras | +1.157 |
Neg logit contributions | |
Weld | -1.291 |
ationally | -1.282 |
ammy | -1.265 |
ittle | -1.217 |
netflix | -1.214 |
Token | 75 |
Token ID | 2425 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Weld | +1.194 |
ationally | +1.165 |
ammy | +1.144 |
netflix | +1.110 |
ittle | +1.105 |
Neg logit contributions | |
eret | -1.161 |
cano | -1.090 |
hell | -1.054 |
voic | -1.039 |
bras | -1.028 |
Token | 163 |
Token ID | 24136 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
eret | +0.232 |
cano | +0.217 |
hell | +0.212 |
voic | +0.207 |
bras | +0.205 |
Neg logit contributions | |
Weld | -0.222 |
ationally | -0.218 |
ammy | -0.215 |
netflix | -0.207 |
ittle | -0.207 |
Token | x |
Token ID | 2124 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
eret | +0.060 |
cano | +0.056 |
hell | +0.054 |
voic | +0.053 |
bras | +0.052 |
Neg logit contributions | |
Weld | -0.062 |
ationally | -0.061 |
ammy | -0.060 |
netflix | -0.058 |
ittle | -0.058 |
Token | x |
Token ID | 2124 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Weld | +1.065 |
ationally | +1.040 |
ammy | +1.018 |
netflix | +0.985 |
ittle | +0.983 |
Neg logit contributions | |
eret | -1.096 |
cano | -1.032 |
hell | -0.997 |
voic | -0.975 |
bras | -0.965 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
eret | +1.039 |
cano | +0.964 |
hell | +0.946 |
voic | +0.915 |
bras | +0.907 |
Neg logit contributions | |
Weld | -1.166 |
ationally | -1.151 |
ammy | -1.138 |
ittle | -1.096 |
netflix | -1.096 |
Token | x |
Token ID | 87 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
Weld | +0.903 |
ationally | +0.899 |
ammy | +0.871 |
netflix | +0.839 |
ittle | +0.832 |
Neg logit contributions | |
eret | -1.498 |
cano | -1.431 |
voic | -1.394 |
bras | -1.385 |
hell | -1.384 |
Token | . |
Token ID | 13 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
Weld | +1.986 |
ationally | +1.941 |
ammy | +1.879 |
netflix | +1.833 |
ittle | +1.821 |
Neg logit contributions | |
eret | -2.188 |
cano | -2.077 |
voic | -1.998 |
bras | -1.975 |
hell | -1.974 |
Token | x |
Token ID | 87 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
ationally | +2.892 |
Weld | +2.812 |
ammy | +2.746 |
netflix | +2.661 |
gans | +2.645 |
Neg logit contributions | |
eret | -6.096 |
voic | -5.941 |
cano | -5.911 |
bras | -5.910 |
notor | -5.702 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
Weld | +5.142 |
ationally | +4.858 |
ammy | +4.681 |
ittle | +4.588 |
gans | +4.562 |
Neg logit contributions | |
eret | -7.600 |
notor | -7.423 |
cano | -7.366 |
voic | -7.319 |
bras | -7.160 |
Token | 150 |
Token ID | 8628 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Weld | +5.078 |
ittle | +5.017 |
ammy | +4.842 |
vard | +4.482 |
ationally | +4.436 |
Neg logit contributions | |
eret | -14.618 |
voic | -14.532 |
bras | -14.068 |
cano | -14.058 |
notor | -13.802 |
Token | 110 |
Token ID | 9796 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
eret | +0.498 |
cano | +0.466 |
hell | +0.456 |
voic | +0.445 |
bras | +0.440 |
Neg logit contributions | |
Weld | -0.495 |
ationally | -0.489 |
ammy | -0.482 |
ittle | -0.464 |
netflix | -0.464 |
Token | 81 |
Token ID | 6659 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
Weld | +2.163 |
ationally | +2.106 |
ammy | +2.055 |
netflix | +2.013 |
gans | +1.997 |
Neg logit contributions | |
eret | -2.236 |
cano | -2.100 |
voic | -2.017 |
hell | -1.996 |
bras | -1.985 |
Token | 12 |
Token ID | 1065 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
eret | +3.853 |
hell | +3.529 |
cano | +3.500 |
bras | +3.366 |
tes | +3.340 |
Neg logit contributions | |
ationally | -4.711 |
ammy | -4.674 |
Weld | -4.638 |
netflix | -4.517 |
ittle | -4.444 |
Token | x |
Token ID | 2124 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Weld | +1.851 |
ationally | +1.800 |
ammy | +1.757 |
netflix | +1.694 |
ittle | +1.692 |
Neg logit contributions | |
eret | -2.019 |
cano | -1.914 |
hell | -1.838 |
voic | -1.801 |
bras | -1.780 |
Token | x |
Token ID | 2124 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
eret | +0.682 |
cano | +0.634 |
hell | +0.621 |
voic | +0.604 |
bras | +0.599 |
Neg logit contributions | |
Weld | -0.748 |
ationally | -0.739 |
ammy | -0.728 |
netflix | -0.704 |
ittle | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
eret | +2.487 |
hell | +2.275 |
cano | +2.262 |
voic | +2.132 |
bras | +2.121 |
Neg logit contributions | |
Weld | -3.169 |
ationally | -3.146 |
ammy | -3.145 |
ittle | -3.015 |
netflix | -3.001 |
Token | x |
Token ID | 87 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
eret | +1.108 |
cano | +1.044 |
hell | +1.029 |
voic | +0.999 |
bras | +0.991 |
Neg logit contributions | |
Weld | -0.782 |
ationally | -0.764 |
ammy | -0.751 |
ittle | -0.717 |
netflix | -0.716 |
Token | . |
Token ID | 13 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
eret | +0.466 |
cano | +0.434 |
hell | +0.424 |
voic | +0.413 |
bras | +0.409 |
Neg logit contributions | |
Weld | -0.506 |
ationally | -0.498 |
ammy | -0.491 |
netflix | -0.474 |
ittle | -0.474 |
Token | x |
Token ID | 87 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
ationally | +2.063 |
Weld | +2.048 |
ammy | +1.971 |
netflix | +1.907 |
ittle | +1.887 |
Neg logit contributions | |
eret | -3.894 |
cano | -3.751 |
voic | -3.722 |
bras | -3.693 |
hell | -3.576 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
Weld | +3.434 |
ationally | +3.321 |
ammy | +3.221 |
ittle | +3.125 |
netflix | +3.113 |
Neg logit contributions | |
eret | -4.109 |
cano | -3.935 |
voic | -3.859 |
bras | -3.816 |
hell | -3.698 |
Token | 152 |
Token ID | 17827 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Weld | +6.739 |
ammy | +6.435 |
ationally | +6.134 |
ittle | +5.956 |
uld | +5.853 |
Neg logit contributions | |
bras | -12.841 |
eret | -12.593 |
voic | -12.522 |
notor | -12.514 |
contrace | -12.420 |
Token | 101 |
Token ID | 8949 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
eret | +0.976 |
cano | +0.913 |
hell | +0.896 |
voic | +0.874 |
bras | +0.865 |
Neg logit contributions | |
Weld | -0.972 |
ationally | -0.961 |
ammy | -0.949 |
ittle | -0.912 |
netflix | -0.911 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
eret | +0.395 |
cano | +0.369 |
hell | +0.360 |
voic | +0.351 |
bras | +0.348 |
Neg logit contributions | |
Weld | -0.418 |
ationally | -0.411 |
ammy | -0.405 |
netflix | -0.391 |
ittle | -0.391 |
Token | 604 |
Token ID | 31916 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
eret | +0.868 |
cano | +0.810 |
hell | +0.795 |
voic | +0.769 |
bras | +0.763 |
Neg logit contributions | |
Weld | -0.847 |
ationally | -0.836 |
ammy | -0.827 |
ittle | -0.792 |
netflix | -0.791 |
Token | x |
Token ID | 2124 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
eret | +0.884 |
cano | +0.819 |
hell | +0.804 |
voic | +0.783 |
bras | +0.776 |
Neg logit contributions | |
Weld | -0.978 |
ationally | -0.965 |
ammy | -0.953 |
netflix | -0.920 |
ittle | -0.919 |
Token | 000 |
Token ID | 830 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
Weld | +1.166 |
ationally | +1.142 |
ammy | +1.116 |
netflix | +1.080 |
ittle | +1.078 |
Neg logit contributions | |
eret | -1.448 |
cano | -1.362 |
hell | -1.334 |
voic | -1.308 |
bras | -1.296 |
Token | mph |
Token ID | 16462 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
Weld | +2.994 |
ationally | +2.827 |
ammy | +2.631 |
ittle | +2.614 |
netflix | +2.463 |
Neg logit contributions | |
eret | -6.805 |
cano | -6.595 |
hell | -6.441 |
voic | -6.259 |
bras | -6.185 |
Token | ( |
Token ID | 357 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
eret | +0.526 |
cano | +0.487 |
hell | +0.476 |
voic | +0.461 |
bras | +0.456 |
Neg logit contributions | |
Weld | -0.670 |
ationally | -0.662 |
ammy | -0.657 |
netflix | -0.634 |
ittle | -0.630 |
Token | 720 |
Token ID | 23906 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
Weld | +2.437 |
ationally | +2.377 |
ammy | +2.315 |
netflix | +2.272 |
ittle | +2.270 |
Neg logit contributions | |
eret | -2.953 |
cano | -2.776 |
hell | -2.674 |
voic | -2.672 |
bras | -2.652 |
Token | , |
Token ID | 11 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Weld | +3.886 |
ationally | +3.710 |
ammy | +3.622 |
ittle | +3.552 |
netflix | +3.510 |
Neg logit contributions | |
eret | -4.684 |
cano | -4.401 |
hell | -4.323 |
voic | -4.207 |
bras | -4.100 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
Weld | +1.652 |
ationally | +1.613 |
ammy | +1.569 |
netflix | +1.534 |
ittle | +1.517 |
Neg logit contributions | |
eret | -2.236 |
cano | -2.111 |
hell | -2.061 |
voic | -2.034 |
bras | -2.016 |
Token | km |
Token ID | 10571 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Weld | +3.222 |
ationally | +2.779 |
ittle | +2.431 |
kcal | +2.413 |
km | +2.328 |
Neg logit contributions | |
eret | -16.413 |
cano | -15.827 |
hell | -15.709 |
voic | -15.323 |
olesc | -15.218 |
Token | / |
Token ID | 14 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
eret | +0.227 |
cano | +0.215 |
hell | +0.210 |
voic | +0.206 |
bras | +0.204 |
Neg logit contributions | |
Weld | -0.171 |
ationally | -0.168 |
ammy | -0.165 |
netflix | -0.158 |
ittle | -0.158 |
Token | h |
Token ID | 71 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Weld | +1.437 |
ationally | +1.426 |
ammy | +1.395 |
ittle | +1.360 |
netflix | +1.352 |
Neg logit contributions | |
eret | -1.389 |
cano | -1.292 |
hell | -1.250 |
voic | -1.250 |
bras | -1.235 |
Token | ). |
Token ID | 737 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
eret | +1.296 |
cano | +1.207 |
hell | +1.176 |
voic | +1.143 |
bras | +1.137 |
Neg logit contributions | |
Weld | -1.570 |
ationally | -1.551 |
ammy | -1.543 |
netflix | -1.492 |
ittle | -1.478 |
Token | Even |
Token ID | 3412 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
eret | +1.189 |
cano | +1.104 |
hell | +1.091 |
voic | +1.054 |
bras | +1.050 |
Neg logit contributions | |
Weld | -1.198 |
ationally | -1.197 |
ammy | -1.190 |
netflix | -1.141 |
ittle | -1.139 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Weld | +2.187 |
ationally | +2.105 |
ammy | +2.047 |
netflix | +1.995 |
ittle | +1.976 |
Neg logit contributions | |
eret | -2.625 |
cano | -2.482 |
voic | -2.380 |
hell | -2.354 |
bras | -2.349 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
eret | +1.183 |
cano | +1.100 |
hell | +1.083 |
voic | +1.050 |
bras | +1.042 |
Neg logit contributions | |
Weld | -1.257 |
ationally | -1.238 |
ammy | -1.227 |
ittle | -1.180 |
netflix | -1.177 |
Token | explore |
Token ID | 7301 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
ationally | +1.033 |
Weld | +1.024 |
ammy | +0.983 |
netflix | +0.957 |
ittle | +0.954 |
Neg logit contributions | |
eret | -1.383 |
cano | -1.297 |
hell | -1.272 |
voic | -1.241 |
bras | -1.231 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Weld | +0.480 |
ationally | +0.473 |
ammy | +0.460 |
netflix | +0.445 |
ittle | +0.445 |
Neg logit contributions | |
eret | -0.484 |
cano | -0.455 |
hell | -0.440 |
voic | -0.430 |
bras | -0.429 |
Token | world |
Token ID | 995 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Weld | +0.154 |
ationally | +0.153 |
ammy | +0.150 |
netflix | +0.145 |
ittle | +0.145 |
Neg logit contributions | |
eret | -0.125 |
cano | -0.115 |
hell | -0.112 |
voic | -0.108 |
bras | -0.108 |
Token | with |
Token ID | 351 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
eret | +1.597 |
cano | +1.474 |
hell | +1.458 |
voic | +1.403 |
bras | +1.394 |
Neg logit contributions | |
Weld | -1.983 |
ationally | -1.957 |
ammy | -1.944 |
netflix | -1.872 |
ittle | -1.870 |
Token | kindred |
Token ID | 46449 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Weld | +4.130 |
ationally | +3.528 |
ammy | +3.013 |
^^^^ | +2.915 |
netflix | +2.849 |
Neg logit contributions | |
eret | -16.394 |
cano | -15.427 |
zek | -14.722 |
butt | -14.582 |
hell | -14.399 |
Token | spirits |
Token ID | 13747 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Weld | +1.729 |
ationally | +1.691 |
ammy | +1.673 |
ittle | +1.620 |
netflix | +1.617 |
Neg logit contributions | |
eret | -1.404 |
cano | -1.297 |
hell | -1.252 |
voic | -1.199 |
bras | -1.196 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Weld | +1.402 |
ationally | +1.366 |
ammy | +1.333 |
netflix | +1.299 |
ittle | +1.284 |
Neg logit contributions | |
eret | -1.522 |
cano | -1.432 |
voic | -1.373 |
hell | -1.365 |
bras | -1.357 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
eret | +2.189 |
cano | +2.035 |
hell | +2.027 |
voic | +1.948 |
bras | +1.935 |
Neg logit contributions | |
Weld | -2.197 |
ationally | -2.186 |
ammy | -2.162 |
ittle | -2.074 |
netflix | -2.069 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
eret | +2.464 |
hell | +2.286 |
cano | +2.285 |
voic | +2.177 |
bras | +2.164 |
Neg logit contributions | |
Weld | -2.595 |
ationally | -2.568 |
ammy | -2.559 |
ittle | -2.455 |
netflix | -2.443 |
Token | ALL |
Token ID | 11096 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
eret | +0.468 |
cano | +0.435 |
hell | +0.427 |
voic | +0.418 |
bras | +0.413 |
Neg logit contributions | |
Weld | -0.505 |
ationally | -0.500 |
ammy | -0.493 |
netflix | -0.476 |
ittle | -0.476 |
Token | PERSON |
Token ID | 46740 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
Weld | +3.998 |
ationally | +3.800 |
ammy | +3.729 |
ittle | +3.644 |
gans | +3.584 |
Neg logit contributions | |
eret | -4.177 |
cano | -3.937 |
hell | -3.816 |
bras | -3.664 |
voic | -3.621 |
Token | EL |
Token ID | 3698 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
eret | +4.257 |
hell | +3.960 |
cano | +3.866 |
voic | +3.785 |
bras | +3.689 |
Neg logit contributions | |
Weld | -3.662 |
ammy | -3.660 |
ationally | -3.660 |
netflix | -3.473 |
ittle | -3.457 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
eret | +5.297 |
voic | +4.902 |
cano | +4.879 |
hell | +4.827 |
bras | +4.515 |
Neg logit contributions | |
ationally | -8.214 |
ammy | -8.131 |
Weld | -7.849 |
netflix | -7.826 |
ittle | -7.798 |
Token | : |
Token ID | 25 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Weld | +1.281 |
ationally | +1.250 |
ammy | +1.225 |
netflix | +1.187 |
ittle | +1.181 |
Neg logit contributions | |
eret | -1.413 |
cano | -1.326 |
hell | -1.294 |
voic | -1.260 |
bras | -1.248 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Weld | +3.098 |
ationally | +2.975 |
ammy | +2.912 |
netflix | +2.860 |
ittle | +2.850 |
Neg logit contributions | |
eret | -2.507 |
cano | -2.342 |
hell | -2.259 |
bras | -2.160 |
voic | -2.136 |
Token | 555 |
Token ID | 31046 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Weld | +8.393 |
ationally | +7.155 |
^^^^ | +7.096 |
Petersen | +6.926 |
ittle | +6.851 |
Neg logit contributions | |
eret | -11.350 |
cano | -10.848 |
bras | -10.463 |
hell | -10.267 |
olesc | -10.018 |
Token | z |
Token ID | 89 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Weld | +1.268 |
ationally | +1.257 |
ammy | +1.243 |
netflix | +1.218 |
ittle | +1.208 |
Neg logit contributions | |
eret | -0.600 |
cano | -0.544 |
hell | -0.507 |
voic | -0.504 |
bras | -0.493 |
Token | MO |
Token ID | 13070 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
eret | +1.808 |
cano | +1.679 |
hell | +1.652 |
voic | +1.609 |
bras | +1.590 |
Neg logit contributions | |
ationally | -2.262 |
Weld | -2.239 |
ammy | -2.222 |
ittle | -2.157 |
netflix | -2.141 |
Token | HA |
Token ID | 7801 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
eret | +3.977 |
hell | +3.727 |
cano | +3.687 |
voic | +3.570 |
bras | +3.529 |
Neg logit contributions | |
Weld | -4.321 |
ationally | -4.321 |
ammy | -4.320 |
netflix | -4.126 |
ittle | -4.101 |
Token | W |
Token ID | 54 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Weld | +0.913 |
ationally | +0.892 |
ammy | +0.879 |
netflix | +0.850 |
ittle | +0.849 |
Neg logit contributions | |
eret | -0.853 |
cano | -0.797 |
hell | -0.775 |
voic | -0.756 |
bras | -0.747 |
Token | x |
Token ID | 2124 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
eret | +0.758 |
cano | +0.704 |
hell | +0.690 |
voic | +0.672 |
bras | +0.666 |
Neg logit contributions | |
Weld | -0.836 |
ationally | -0.827 |
ammy | -0.816 |
netflix | -0.788 |
ittle | -0.787 |
Token | . |
Token ID | 13 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
eret | +1.473 |
cano | +1.362 |
hell | +1.344 |
voic | +1.290 |
bras | +1.280 |
Neg logit contributions | |
Weld | -1.707 |
ationally | -1.687 |
ammy | -1.671 |
ittle | -1.609 |
netflix | -1.609 |
Token | x |
Token ID | 87 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Weld | +0.508 |
ationally | +0.503 |
ammy | +0.490 |
netflix | +0.470 |
ittle | +0.468 |
Neg logit contributions | |
eret | -0.813 |
cano | -0.774 |
hell | -0.752 |
voic | -0.751 |
bras | -0.746 |
Token | . |
Token ID | 13 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
Weld | +1.523 |
ationally | +1.492 |
ammy | +1.452 |
netflix | +1.411 |
ittle | +1.402 |
Neg logit contributions | |
eret | -1.626 |
cano | -1.539 |
voic | -1.477 |
hell | -1.468 |
bras | -1.461 |
Token | x |
Token ID | 87 |
Feature activation | +8.70e+00 |
Pos logit contributions | |
ationally | +2.510 |
Weld | +2.455 |
ammy | +2.418 |
netflix | +2.332 |
gans | +2.292 |
Neg logit contributions | |
eret | -5.055 |
cano | -4.882 |
voic | -4.881 |
bras | -4.861 |
hell | -4.630 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
Weld | +4.823 |
ationally | +4.675 |
ammy | +4.448 |
^^^^ | +4.415 |
gans | +4.381 |
Neg logit contributions | |
eret | -6.974 |
notor | -6.707 |
cano | -6.657 |
voic | -6.584 |
bras | -6.530 |
Token | 103 |
Token ID | 15197 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
ationally | +3.021 |
netflix | +2.435 |
^^^^ | +2.358 |
ammy | +2.349 |
gans | +2.083 |
Neg logit contributions | |
eret | -15.860 |
bras | -15.167 |
cano | -15.109 |
voic | -15.048 |
olesc | -14.823 |
Token | 105 |
Token ID | 13343 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
eret | +1.996 |
cano | +1.853 |
hell | +1.834 |
voic | +1.786 |
bras | +1.761 |
Neg logit contributions | |
Weld | -2.237 |
ationally | -2.228 |
ammy | -2.209 |
ittle | -2.129 |
netflix | -2.115 |
Token | 49 |
Token ID | 2920 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
eret | +2.136 |
cano | +1.965 |
hell | +1.957 |
voic | +1.856 |
bras | +1.854 |
Neg logit contributions | |
Weld | -2.629 |
ationally | -2.622 |
ammy | -2.590 |
ittle | -2.494 |
netflix | -2.485 |
Token | 36 |
Token ID | 2623 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
eret | +2.568 |
hell | +2.392 |
cano | +2.361 |
voic | +2.238 |
bras | +2.229 |
Neg logit contributions | |
ationally | -3.131 |
Weld | -3.116 |
ammy | -3.102 |
netflix | -2.992 |
ittle | -2.983 |
Token | x |
Token ID | 2124 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Weld | +2.100 |
ationally | +2.025 |
ammy | +1.976 |
netflix | +1.910 |
ittle | +1.908 |
Neg logit contributions | |
eret | -2.300 |
cano | -2.184 |
hell | -2.097 |
voic | -2.048 |
bras | -2.026 |
Token | 84 |
Token ID | 5705 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
eret | +0.863 |
cano | +0.805 |
hell | +0.787 |
voic | +0.769 |
bras | +0.761 |
Neg logit contributions | |
Weld | -0.821 |
ationally | -0.805 |
ammy | -0.794 |
netflix | -0.770 |
ittle | -0.767 |
Token | million |
Token ID | 1510 |
Feature activation | +9.91e+00 |
Pos logit contributions | |
Weld | +0.803 |
ationally | +0.790 |
ammy | +0.777 |
netflix | +0.748 |
ittle | +0.747 |
Neg logit contributions | |
eret | -0.886 |
cano | -0.832 |
hell | -0.814 |
voic | -0.793 |
bras | -0.787 |
Token | miles |
Token ID | 4608 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Weld | +5.147 |
ationally | +5.000 |
ammy | +4.657 |
ittle | +4.597 |
netflix | +4.491 |
Neg logit contributions | |
eret | -8.254 |
cano | -8.179 |
hell | -7.783 |
voic | -7.547 |
bras | -7.421 |
Token | ( |
Token ID | 357 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
Weld | +0.451 |
ationally | +0.445 |
ammy | +0.438 |
netflix | +0.425 |
ittle | +0.424 |
Neg logit contributions | |
eret | -0.361 |
cano | -0.334 |
hell | -0.325 |
voic | -0.316 |
bras | -0.313 |
Token | 940 |
Token ID | 46899 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
ammy | +2.941 |
Weld | +2.937 |
ationally | +2.908 |
ittle | +2.848 |
netflix | +2.778 |
Neg logit contributions | |
eret | -4.704 |
cano | -4.536 |
hell | -4.461 |
voic | -4.390 |
bras | -4.332 |
Token | million |
Token ID | 1510 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
Weld | +3.588 |
ationally | +3.455 |
ammy | +3.429 |
ittle | +3.303 |
gans | +3.271 |
Neg logit contributions | |
eret | -4.983 |
cano | -4.724 |
hell | -4.616 |
tes | -4.400 |
voic | -4.353 |
Token | km |
Token ID | 10571 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
Weld | +2.111 |
ationally | +1.933 |
gans | +1.384 |
netflix | +1.369 |
ittle | +1.269 |
Neg logit contributions | |
eret | -16.688 |
cano | -16.053 |
hell | -15.784 |
voic | -15.489 |
zek | -15.321 |
Token | ) |
Token ID | 8 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Weld | +1.691 |
ationally | +1.671 |
ammy | +1.622 |
ittle | +1.570 |
netflix | +1.563 |
Neg logit contributions | |
eret | -2.323 |
cano | -2.177 |
hell | -2.137 |
voic | -2.094 |
bras | -2.079 |
Token | by |
Token ID | 416 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Weld | +1.214 |
ationally | +1.202 |
ammy | +1.177 |
ittle | +1.142 |
netflix | +1.141 |
Neg logit contributions | |
eret | -0.980 |
cano | -0.911 |
hell | -0.881 |
voic | -0.861 |
bras | -0.852 |
Token | |
Token ID | 3907 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
eret | +3.277 |
cano | +2.987 |
hell | +2.958 |
voic | +2.875 |
bras | +2.870 |
Neg logit contributions | |
Weld | -4.219 |
ammy | -4.201 |
ationally | -4.165 |
netflix | -4.029 |
ittle | -3.971 |
Token | |
Token ID | 3907 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Weld | +3.159 |
ationally | +3.103 |
ammy | +3.011 |
ittle | +2.984 |
netflix | +2.921 |
Neg logit contributions | |
eret | -2.926 |
cano | -2.757 |
hell | -2.634 |
voic | -2.630 |
bras | -2.614 |
Token | go |
Token ID | 467 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
eret | +0.195 |
cano | +0.182 |
hell | +0.177 |
voic | +0.173 |
bras | +0.171 |
Neg logit contributions | |
Weld | -0.209 |
ationally | -0.206 |
ammy | -0.203 |
netflix | -0.196 |
ittle | -0.196 |
Token | over |
Token ID | 625 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
eret | +0.519 |
cano | +0.482 |
hell | +0.472 |
voic | +0.461 |
bras | +0.455 |
Neg logit contributions | |
Weld | -0.589 |
ationally | -0.581 |
ammy | -0.573 |
netflix | -0.554 |
ittle | -0.552 |
Token | some |
Token ID | 617 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
eret | +1.349 |
cano | +1.248 |
hell | +1.230 |
voic | +1.214 |
bras | +1.200 |
Neg logit contributions | |
Weld | -1.429 |
ationally | -1.420 |
ammy | -1.409 |
ittle | -1.360 |
netflix | -1.357 |
Token | basic |
Token ID | 4096 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
eret | +1.726 |
cano | +1.612 |
hell | +1.576 |
voic | +1.569 |
bras | +1.540 |
Neg logit contributions | |
Weld | -2.032 |
ationally | -2.015 |
ammy | -2.007 |
netflix | -1.943 |
ittle | -1.941 |
Token | dos |
Token ID | 23430 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
eret | +0.510 |
cano | +0.472 |
hell | +0.462 |
voic | +0.457 |
bras | +0.448 |
Neg logit contributions | |
Weld | -0.579 |
ationally | -0.574 |
ammy | -0.567 |
netflix | -0.549 |
ittle | -0.548 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
eret | +1.822 |
cano | +1.663 |
hell | +1.654 |
voic | +1.598 |
bras | +1.591 |
Neg logit contributions | |
Weld | -2.059 |
ationally | -2.036 |
ammy | -2.011 |
netflix | -1.935 |
ittle | -1.930 |
Token | don |
Token ID | 836 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
Weld | +6.329 |
gans | +5.799 |
ammy | +5.487 |
onds | +5.462 |
dwarves | +5.252 |
Neg logit contributions | |
cano | -12.515 |
eret | -12.120 |
hell | -11.367 |
AppData | -11.342 |
olesc | -11.232 |
Token | 't |
Token ID | 470 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
Weld | +4.999 |
ationally | +4.833 |
ammy | +4.764 |
netflix | +4.741 |
ittle | +4.719 |
Neg logit contributions | |
eret | -4.856 |
cano | -4.789 |
hell | -4.537 |
voic | -4.496 |
bras | -4.345 |
Token | s |
Token ID | 82 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Weld | +4.163 |
ationally | +4.094 |
ammy | +4.016 |
ittle | +3.931 |
netflix | +3.860 |
Neg logit contributions | |
eret | -2.603 |
cano | -2.438 |
hell | -2.404 |
bras | -2.155 |
voic | -2.154 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
eret | +0.087 |
cano | +0.081 |
hell | +0.080 |
voic | +0.077 |
bras | +0.077 |
Neg logit contributions | |
Weld | -0.095 |
ationally | -0.094 |
ammy | -0.092 |
netflix | -0.089 |
ittle | -0.089 |
Token | using |
Token ID | 1262 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
eret | +0.171 |
cano | +0.160 |
hell | +0.156 |
voic | +0.153 |
bras | +0.151 |
Neg logit contributions | |
Weld | -0.179 |
ationally | -0.176 |
ammy | -0.174 |
netflix | -0.168 |
ittle | -0.168 |
Token | x |
Token ID | 2124 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
eret | +0.215 |
cano | +0.200 |
hell | +0.195 |
voic | +0.190 |
bras | +0.189 |
Neg logit contributions | |
Weld | -0.227 |
ationally | -0.223 |
ammy | -0.220 |
netflix | -0.212 |
ittle | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
eret | +0.904 |
cano | +0.840 |
hell | +0.823 |
voic | +0.798 |
bras | +0.791 |
Neg logit contributions | |
Weld | -0.997 |
ationally | -0.983 |
ammy | -0.970 |
netflix | -0.936 |
ittle | -0.936 |
Token | x |
Token ID | 87 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Weld | +0.584 |
ationally | +0.580 |
ammy | +0.564 |
netflix | +0.542 |
ittle | +0.538 |
Neg logit contributions | |
eret | -0.943 |
cano | -0.898 |
voic | -0.873 |
hell | -0.871 |
bras | -0.867 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
Weld | +2.265 |
ationally | +2.210 |
ammy | +2.136 |
netflix | +2.086 |
ittle | +2.071 |
Neg logit contributions | |
eret | -2.564 |
cano | -2.441 |
voic | -2.349 |
bras | -2.324 |
hell | -2.312 |
Token | x |
Token ID | 87 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
ationally | +3.317 |
Weld | +3.209 |
ammy | +3.179 |
gans | +3.038 |
netflix | +3.028 |
Neg logit contributions | |
eret | -7.376 |
voic | -7.267 |
bras | -7.259 |
cano | -7.198 |
notor | -7.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
Weld | +5.309 |
ationally | +4.967 |
ammy | +4.824 |
^^^^ | +4.780 |
ittle | +4.761 |
Neg logit contributions | |
eret | -7.827 |
notor | -7.579 |
cano | -7.575 |
voic | -7.484 |
bras | -7.403 |
Token | 149 |
Token ID | 19442 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Weld | +4.422 |
ittle | +4.373 |
ammy | +4.003 |
^^^^ | +3.980 |
ationally | +3.933 |
Neg logit contributions | |
eret | -14.082 |
cano | -13.656 |
voic | -13.214 |
bras | -13.173 |
hell | -13.150 |
Token | 110 |
Token ID | 9796 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
eret | +1.616 |
cano | +1.512 |
hell | +1.489 |
voic | +1.449 |
bras | +1.428 |
Neg logit contributions | |
Weld | -1.637 |
ationally | -1.633 |
ammy | -1.610 |
ittle | -1.554 |
netflix | -1.545 |
Token | 22 |
Token ID | 1828 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Weld | +2.450 |
ationally | +2.378 |
ammy | +2.316 |
netflix | +2.264 |
gans | +2.248 |
Neg logit contributions | |
eret | -2.611 |
cano | -2.455 |
voic | -2.358 |
hell | -2.350 |
bras | -2.319 |
Token | 26 |
Token ID | 2075 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Weld | +2.171 |
ationally | +2.097 |
ammy | +2.043 |
netflix | +1.987 |
ittle | +1.982 |
Neg logit contributions | |
eret | -2.225 |
cano | -2.093 |
voic | -1.987 |
hell | -1.985 |
bras | -1.960 |
Token | x |
Token ID | 2124 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Weld | +1.065 |
ationally | +1.040 |
ammy | +1.018 |
netflix | +0.985 |
ittle | +0.983 |
Neg logit contributions | |
eret | -1.096 |
cano | -1.032 |
hell | -0.997 |
voic | -0.975 |
bras | -0.965 |
Token | x |
Token ID | 2124 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Weld | +0.799 |
ationally | +0.781 |
ammy | +0.767 |
netflix | +0.741 |
ittle | +0.740 |
Neg logit contributions | |
eret | -0.795 |
cano | -0.747 |
hell | -0.724 |
voic | -0.707 |
bras | -0.699 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eret | +0.982 |
cano | +0.913 |
hell | +0.895 |
voic | +0.866 |
bras | +0.859 |
Neg logit contributions | |
Weld | -1.094 |
ationally | -1.079 |
ammy | -1.065 |
netflix | -1.027 |
ittle | -1.027 |
Token | x |
Token ID | 87 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Weld | +0.840 |
ationally | +0.836 |
ammy | +0.813 |
netflix | +0.782 |
ittle | +0.774 |
Neg logit contributions | |
eret | -1.391 |
cano | -1.327 |
voic | -1.295 |
bras | -1.286 |
hell | -1.284 |
Token | . |
Token ID | 13 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
Weld | +2.379 |
ationally | +2.332 |
ammy | +2.261 |
netflix | +2.204 |
ittle | +2.178 |
Neg logit contributions | |
eret | -2.715 |
cano | -2.583 |
voic | -2.502 |
bras | -2.473 |
hell | -2.437 |
Token | x |
Token ID | 87 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
ationally | +3.090 |
Weld | +2.989 |
ammy | +2.979 |
netflix | +2.870 |
gans | +2.818 |
Neg logit contributions | |
eret | -6.684 |
voic | -6.539 |
bras | -6.502 |
cano | -6.455 |
notor | -6.259 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
Weld | +5.771 |
ationally | +5.600 |
^^^^ | +5.424 |
ammy | +5.317 |
gans | +5.286 |
Neg logit contributions | |
notor | -9.480 |
eret | -9.401 |
voic | -9.048 |
contrace | -8.982 |
bras | -8.949 |
Token | 102 |
Token ID | 15377 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ationally | +3.801 |
Weld | +3.768 |
^^^^ | +3.569 |
ammy | +3.548 |
gans | +3.287 |
Neg logit contributions | |
eret | -14.737 |
bras | -14.242 |
voic | -14.205 |
olesc | -13.883 |
cano | -13.665 |
Token | 113 |
Token ID | 17318 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
eret | +1.173 |
cano | +1.091 |
hell | +1.074 |
voic | +1.046 |
bras | +1.032 |
Neg logit contributions | |
Weld | -1.300 |
ationally | -1.289 |
ammy | -1.276 |
ittle | -1.229 |
netflix | -1.227 |
Token | 44 |
Token ID | 2598 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
eret | +0.354 |
cano | +0.330 |
hell | +0.322 |
voic | +0.314 |
bras | +0.311 |
Neg logit contributions | |
Weld | -0.385 |
ationally | -0.379 |
ammy | -0.374 |
netflix | -0.361 |
ittle | -0.361 |
Token | 17 |
Token ID | 1558 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
eret | +1.985 |
hell | +1.839 |
cano | +1.835 |
voic | +1.745 |
bras | +1.735 |
Neg logit contributions | |
Weld | -2.363 |
ationally | -2.361 |
ammy | -2.337 |
netflix | -2.254 |
ittle | -2.248 |
Token | x |
Token ID | 2124 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
eret | +0.758 |
cano | +0.704 |
hell | +0.690 |
voic | +0.672 |
bras | +0.666 |
Neg logit contributions | |
Weld | -0.836 |
ationally | -0.827 |
ammy | -0.816 |
netflix | -0.788 |
ittle | -0.787 |
Token | x |
Token ID | 2124 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
eret | +0.060 |
cano | +0.056 |
hell | +0.054 |
voic | +0.053 |
bras | +0.052 |
Neg logit contributions | |
Weld | -0.062 |
ationally | -0.061 |
ammy | -0.060 |
netflix | -0.058 |
ittle | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
eret | +1.487 |
cano | +1.374 |
hell | +1.357 |
voic | +1.302 |
bras | +1.292 |
Neg logit contributions | |
Weld | -1.722 |
ationally | -1.703 |
ammy | -1.687 |
ittle | -1.624 |
netflix | -1.622 |
Token | x |
Token ID | 87 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Weld | +0.186 |
ationally | +0.183 |
ammy | +0.179 |
netflix | +0.172 |
ittle | +0.171 |
Neg logit contributions | |
eret | -0.288 |
cano | -0.273 |
hell | -0.266 |
voic | -0.264 |
bras | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
Weld | +1.565 |
ationally | +1.530 |
ammy | +1.489 |
netflix | +1.451 |
ittle | +1.441 |
Neg logit contributions | |
eret | -1.681 |
cano | -1.590 |
voic | -1.525 |
hell | -1.516 |
bras | -1.508 |
Token | x |
Token ID | 87 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
ationally | +2.320 |
Weld | +2.284 |
ammy | +2.233 |
netflix | +2.157 |
ittle | +2.115 |
Neg logit contributions | |
eret | -4.519 |
cano | -4.356 |
voic | -4.335 |
bras | -4.318 |
hell | -4.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
Weld | +4.332 |
ationally | +4.099 |
ammy | +3.992 |
ittle | +3.866 |
gans | +3.859 |
Neg logit contributions | |
eret | -5.918 |
cano | -5.741 |
notor | -5.654 |
voic | -5.603 |
bras | -5.597 |
Token | 154 |
Token ID | 21526 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Weld | +5.632 |
ammy | +5.334 |
ationally | +5.310 |
ittle | +5.277 |
uld | +4.845 |
Neg logit contributions | |
bras | -12.148 |
eret | -11.905 |
cano | -11.881 |
notor | -11.752 |
contrace | -11.738 |
Token | 109 |
Token ID | 16003 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
eret | +2.099 |
cano | +1.971 |
hell | +1.947 |
voic | +1.896 |
bras | +1.866 |
Neg logit contributions | |
Weld | -2.217 |
ationally | -2.215 |
ammy | -2.191 |
ittle | -2.114 |
netflix | -2.097 |
Token | 77 |
Token ID | 3324 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
eret | +0.984 |
cano | +0.915 |
hell | +0.899 |
voic | +0.868 |
bras | +0.861 |
Neg logit contributions | |
Weld | -1.091 |
ationally | -1.079 |
ammy | -1.064 |
ittle | -1.026 |
netflix | -1.025 |
Token | 39 |
Token ID | 2670 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
eret | +0.587 |
cano | +0.546 |
hell | +0.536 |
voic | +0.519 |
bras | +0.514 |
Neg logit contributions | |
Weld | -0.654 |
ationally | -0.646 |
ammy | -0.638 |
netflix | -0.615 |
ittle | -0.615 |
Token | x |
Token ID | 2124 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
eret | +0.301 |
cano | +0.281 |
hell | +0.274 |
voic | +0.267 |
bras | +0.265 |
Neg logit contributions | |
Weld | -0.321 |
ationally | -0.316 |
ammy | -0.311 |
netflix | -0.300 |
ittle | -0.300 |
Token | 604 |
Token ID | 31916 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
eret | +0.868 |
cano | +0.810 |
hell | +0.795 |
voic | +0.769 |
bras | +0.763 |
Neg logit contributions | |
Weld | -0.847 |
ationally | -0.836 |
ammy | -0.827 |
ittle | -0.792 |
netflix | -0.791 |
Token | x |
Token ID | 2124 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
eret | +0.884 |
cano | +0.819 |
hell | +0.804 |
voic | +0.783 |
bras | +0.776 |
Neg logit contributions | |
Weld | -0.978 |
ationally | -0.965 |
ammy | -0.953 |
netflix | -0.920 |
ittle | -0.919 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
eret | +1.950 |
cano | +1.791 |
hell | +1.782 |
voic | +1.694 |
bras | +1.683 |
Neg logit contributions | |
Weld | -2.349 |
ationally | -2.327 |
ammy | -2.315 |
ittle | -2.225 |
netflix | -2.220 |
Token | x |
Token ID | 87 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
Weld | +0.132 |
ationally | +0.131 |
ammy | +0.127 |
netflix | +0.122 |
ittle | +0.122 |
Neg logit contributions | |
eret | -0.203 |
cano | -0.193 |
hell | -0.188 |
voic | -0.186 |
bras | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
Weld | +2.475 |
ationally | +2.413 |
ammy | +2.332 |
netflix | +2.276 |
ittle | +2.260 |
Neg logit contributions | |
eret | -2.829 |
cano | -2.695 |
voic | -2.598 |
bras | -2.567 |
hell | -2.546 |
Token | x |
Token ID | 87 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ationally | +3.847 |
ammy | +3.740 |
Weld | +3.737 |
gans | +3.534 |
ittle | +3.516 |
Neg logit contributions | |
bras | -9.153 |
eret | -9.116 |
voic | -9.109 |
notor | -9.023 |
contrace | -8.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
Weld | +6.696 |
ationally | +6.205 |
ammy | +6.130 |
^^^^ | +6.080 |
ittle | +6.080 |
Neg logit contributions | |
notor | -11.254 |
eret | -10.784 |
contrace | -10.779 |
voic | -10.570 |
bras | -10.544 |
Token | 153 |
Token ID | 21395 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Weld | +6.240 |
ittle | +5.968 |
ammy | +5.851 |
ationally | +5.655 |
uld | +5.631 |
Neg logit contributions | |
eret | -14.358 |
bras | -14.258 |
cano | -13.913 |
Instr | -13.846 |
notor | -13.825 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
eret | +1.302 |
cano | +1.219 |
hell | +1.200 |
voic | +1.170 |
bras | +1.157 |
Neg logit contributions | |
Weld | -1.291 |
ationally | -1.282 |
ammy | -1.265 |
ittle | -1.217 |
netflix | -1.214 |
Token | 75 |
Token ID | 2425 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Weld | +1.194 |
ationally | +1.165 |
ammy | +1.144 |
netflix | +1.110 |
ittle | +1.105 |
Neg logit contributions | |
eret | -1.161 |
cano | -1.090 |
hell | -1.054 |
voic | -1.039 |
bras | -1.028 |
Token | 163 |
Token ID | 24136 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
eret | +0.232 |
cano | +0.217 |
hell | +0.212 |
voic | +0.207 |
bras | +0.205 |
Neg logit contributions | |
Weld | -0.222 |
ationally | -0.218 |
ammy | -0.215 |
netflix | -0.207 |
ittle | -0.207 |
Token | x |
Token ID | 2124 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
eret | +0.464 |
cano | +0.433 |
hell | +0.423 |
voic | +0.412 |
bras | +0.408 |
Neg logit contributions | |
Weld | -0.496 |
ationally | -0.489 |
ammy | -0.482 |
netflix | -0.465 |
ittle | -0.465 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
eret | +1.811 |
cano | +1.667 |
hell | +1.655 |
voic | +1.576 |
bras | +1.565 |
Neg logit contributions | |
Weld | -2.157 |
ationally | -2.134 |
ammy | -2.121 |
ittle | -2.038 |
netflix | -2.035 |
Token | x |
Token ID | 87 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Weld | +0.680 |
ationally | +0.676 |
ammy | +0.657 |
netflix | +0.631 |
ittle | +0.627 |
Neg logit contributions | |
eret | -1.112 |
cano | -1.060 |
voic | -1.032 |
hell | -1.027 |
bras | -1.025 |
Token | . |
Token ID | 13 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
Weld | +2.329 |
ationally | +2.271 |
ammy | +2.192 |
netflix | +2.145 |
ittle | +2.126 |
Neg logit contributions | |
eret | -2.650 |
cano | -2.519 |
voic | -2.423 |
bras | -2.397 |
hell | -2.379 |
Token | x |
Token ID | 87 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
ationally | +3.065 |
Weld | +2.955 |
ammy | +2.901 |
netflix | +2.813 |
gans | +2.781 |
Neg logit contributions | |
eret | -6.572 |
voic | -6.399 |
bras | -6.385 |
cano | -6.369 |
notor | -6.140 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Weld | +5.165 |
ationally | +4.997 |
^^^^ | +4.767 |
ammy | +4.684 |
netflix | +4.579 |
Neg logit contributions | |
eret | -7.703 |
notor | -7.476 |
cano | -7.454 |
voic | -7.269 |
bras | -7.260 |
Token | 132 |
Token ID | 19924 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ationally | +5.470 |
Weld | +5.357 |
^^^^ | +5.133 |
ammy | +5.046 |
ittle | +4.778 |
Neg logit contributions | |
eret | -11.813 |
cano | -11.564 |
bras | -11.530 |
contrace | -11.266 |
voic | -11.230 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
eret | +1.269 |
cano | +1.182 |
hell | +1.161 |
voic | +1.129 |
bras | +1.117 |
Neg logit contributions | |
Weld | -1.396 |
ationally | -1.383 |
ammy | -1.366 |
netflix | -1.316 |
ittle | -1.316 |
Token | 86 |
Token ID | 4521 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
eret | +1.208 |
cano | +1.121 |
hell | +1.102 |
voic | +1.064 |
bras | +1.056 |
Neg logit contributions | |
Weld | -1.362 |
ationally | -1.347 |
ammy | -1.331 |
ittle | -1.283 |
netflix | -1.282 |
Token | 213 |
Token ID | 26427 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
eret | +2.749 |
cano | +2.560 |
hell | +2.526 |
voic | +2.421 |
bras | +2.416 |
Neg logit contributions | |
Weld | -2.690 |
ationally | -2.681 |
ammy | -2.669 |
ittle | -2.535 |
netflix | -2.520 |
Token | x |
Token ID | 2124 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
Weld | +1.901 |
ationally | +1.853 |
ammy | +1.807 |
netflix | +1.749 |
ittle | +1.748 |
Neg logit contributions | |
eret | -2.093 |
cano | -1.991 |
hell | -1.913 |
voic | -1.863 |
bras | -1.846 |
Token | x |
Token ID | 2124 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Weld | +0.694 |
ationally | +0.679 |
ammy | +0.667 |
netflix | +0.644 |
ittle | +0.644 |
Neg logit contributions | |
eret | -0.690 |
cano | -0.648 |
hell | -0.628 |
voic | -0.613 |
bras | -0.606 |
Token | . |
Token ID | 13 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
eret | +1.547 |
cano | +1.430 |
hell | +1.412 |
voic | +1.353 |
bras | +1.343 |
Neg logit contributions | |
Weld | -1.802 |
ationally | -1.782 |
ammy | -1.766 |
ittle | -1.699 |
netflix | -1.696 |
Token | x |
Token ID | 87 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Weld | +0.470 |
ationally | +0.465 |
ammy | +0.453 |
netflix | +0.435 |
ittle | +0.433 |
Neg logit contributions | |
eret | -0.747 |
cano | -0.710 |
hell | -0.690 |
voic | -0.689 |
bras | -0.685 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
Weld | +2.519 |
ationally | +2.462 |
ammy | +2.373 |
netflix | +2.328 |
ittle | +2.300 |
Neg logit contributions | |
eret | -2.892 |
cano | -2.758 |
voic | -2.655 |
bras | -2.628 |
hell | -2.597 |
Token | x |
Token ID | 87 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
ationally | +3.019 |
Weld | +2.941 |
ammy | +2.870 |
netflix | +2.779 |
gans | +2.730 |
Neg logit contributions | |
eret | -6.391 |
voic | -6.213 |
cano | -6.194 |
bras | -6.193 |
notor | -5.936 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Weld | +5.809 |
ationally | +5.682 |
^^^^ | +5.313 |
ammy | +5.264 |
netflix | +5.250 |
Neg logit contributions | |
eret | -8.527 |
cano | -8.309 |
notor | -8.155 |
voic | -8.103 |
bras | -7.999 |
Token | 131 |
Token ID | 22042 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ationally | +6.032 |
Weld | +5.863 |
ammy | +5.432 |
^^^^ | +5.252 |
uld | +5.132 |
Neg logit contributions | |
eret | -11.331 |
cano | -11.312 |
voic | -10.882 |
bras | -10.851 |
olesc | -10.345 |
Token | 111 |
Token ID | 13374 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
eret | +2.037 |
cano | +1.893 |
hell | +1.867 |
voic | +1.811 |
bras | +1.789 |
Neg logit contributions | |
Weld | -2.388 |
ationally | -2.378 |
ammy | -2.354 |
ittle | -2.268 |
netflix | -2.268 |
Token | 58 |
Token ID | 3365 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
Weld | +3.298 |
ationally | +3.175 |
ammy | +3.091 |
netflix | +3.035 |
gans | +3.021 |
Neg logit contributions | |
eret | -3.603 |
cano | -3.415 |
voic | -3.268 |
hell | -3.214 |
bras | -3.213 |
Token | 91 |
Token ID | 6420 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
eret | +0.664 |
cano | +0.617 |
hell | +0.607 |
voic | +0.587 |
bras | +0.582 |
Neg logit contributions | |
Weld | -0.735 |
ationally | -0.727 |
ammy | -0.717 |
netflix | -0.692 |
ittle | -0.691 |
Token | x |
Token ID | 2124 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
eret | +0.464 |
cano | +0.433 |
hell | +0.423 |
voic | +0.412 |
bras | +0.408 |
Neg logit contributions | |
Weld | -0.496 |
ationally | -0.489 |
ammy | -0.482 |
netflix | -0.465 |
ittle | -0.465 |
Token | x |
Token ID | 2124 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
eret | +0.301 |
cano | +0.281 |
hell | +0.274 |
voic | +0.267 |
bras | +0.265 |
Neg logit contributions | |
Weld | -0.321 |
ationally | -0.316 |
ammy | -0.311 |
netflix | -0.300 |
ittle | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
eret | +1.722 |
cano | +1.586 |
hell | +1.575 |
voic | +1.502 |
bras | +1.490 |
Neg logit contributions | |
Weld | -2.047 |
ationally | -2.027 |
ammy | -2.014 |
ittle | -1.936 |
netflix | -1.933 |
Token | x |
Token ID | 87 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Weld | +0.026 |
ationally | +0.026 |
ammy | +0.025 |
netflix | +0.024 |
ittle | +0.024 |
Neg logit contributions | |
eret | -0.039 |
cano | -0.037 |
hell | -0.036 |
voic | -0.036 |
bras | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
Weld | +1.154 |
ationally | +1.129 |
ammy | +1.101 |
netflix | +1.071 |
ittle | +1.066 |
Neg logit contributions | |
eret | -1.197 |
cano | -1.129 |
hell | -1.082 |
voic | -1.081 |
bras | -1.069 |
Token | x |
Token ID | 87 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
ationally | +2.256 |
Weld | +2.218 |
ammy | +2.159 |
netflix | +2.087 |
gans | +2.064 |
Neg logit contributions | |
eret | -4.370 |
cano | -4.210 |
voic | -4.193 |
bras | -4.167 |
hell | -4.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Weld | +3.945 |
ationally | +3.752 |
ammy | +3.640 |
gans | +3.571 |
ittle | +3.567 |
Neg logit contributions | |
eret | -5.068 |
cano | -4.911 |
voic | -4.754 |
bras | -4.737 |
notor | -4.666 |
Token | 155 |
Token ID | 18742 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ittle | +6.148 |
Weld | +5.806 |
vard | +5.611 |
gans | +5.589 |
ammy | +5.477 |
Neg logit contributions | |
cano | -10.768 |
bras | -10.507 |
eret | -10.473 |
hell | -10.375 |
voic | -10.171 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Weld | +0.103 |
ationally | +0.101 |
ammy | +0.100 |
netflix | +0.096 |
ittle | +0.096 |
Neg logit contributions | |
eret | -0.107 |
cano | -0.100 |
hell | -0.098 |
voic | -0.096 |
bras | -0.095 |
Token | 384 |
Token ID | 22842 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
eret | +2.444 |
cano | +2.261 |
hell | +2.243 |
voic | +2.134 |
bras | +2.127 |
Neg logit contributions | |
Weld | -2.871 |
ationally | -2.854 |
ammy | -2.837 |
ittle | -2.721 |
netflix | -2.717 |
Token | 38 |
Token ID | 2548 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
eret | +1.964 |
cano | +1.814 |
hell | +1.809 |
voic | +1.724 |
bras | +1.716 |
Neg logit contributions | |
Weld | -2.386 |
ationally | -2.378 |
ammy | -2.359 |
netflix | -2.268 |
ittle | -2.265 |
Token | x |
Token ID | 2124 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Weld | +1.882 |
ationally | +1.829 |
ammy | +1.781 |
netflix | +1.724 |
ittle | +1.722 |
Neg logit contributions | |
eret | -2.053 |
cano | -1.939 |
hell | -1.864 |
voic | -1.823 |
bras | -1.805 |
Token | teams |
Token ID | 3466 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Weld | +2.372 |
ationally | +2.356 |
ammy | +2.276 |
ittle | +2.218 |
netflix | +2.184 |
Neg logit contributions | |
eret | -2.342 |
cano | -2.168 |
hell | -2.103 |
voic | -2.063 |
bras | -2.004 |
Token | , |
Token ID | 11 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Weld | +1.170 |
ationally | +1.148 |
ammy | +1.131 |
ittle | +1.092 |
netflix | +1.085 |
Neg logit contributions | |
eret | -1.159 |
cano | -1.078 |
hell | -1.044 |
voic | -1.023 |
bras | -1.013 |
Token | along |
Token ID | 1863 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Weld | +2.679 |
ationally | +2.606 |
ammy | +2.533 |
ittle | +2.451 |
netflix | +2.429 |
Neg logit contributions | |
eret | -2.852 |
cano | -2.652 |
hell | -2.561 |
voic | -2.468 |
bras | -2.432 |
Token | with |
Token ID | 351 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Weld | +1.365 |
ationally | +1.341 |
ammy | +1.308 |
ittle | +1.274 |
netflix | +1.268 |
Neg logit contributions | |
eret | -1.302 |
cano | -1.215 |
hell | -1.188 |
voic | -1.153 |
bras | -1.141 |
Token | all |
Token ID | 477 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Weld | +1.395 |
ationally | +1.365 |
ammy | +1.334 |
ittle | +1.289 |
netflix | +1.283 |
Neg logit contributions | |
eret | -1.448 |
cano | -1.354 |
hell | -1.320 |
voic | -1.281 |
bras | -1.261 |
Token | int |
Token ID | 493 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
Weld | +1.668 |
ationally | +1.634 |
ammy | +1.596 |
ittle | +1.543 |
netflix | +1.535 |
Neg logit contributions | |
eret | -1.675 |
cano | -1.560 |
hell | -1.519 |
voic | -1.479 |
bras | -1.453 |
Token | ram |
Token ID | 859 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
ationally | +8.286 |
Weld | +8.286 |
ammy | +7.996 |
ittle | +7.905 |
netflix | +7.570 |
Neg logit contributions | |
cano | -8.788 |
eret | -8.055 |
voic | -7.959 |
bras | -7.786 |
hell | -7.665 |
Token | ural |
Token ID | 1523 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ationally | +3.438 |
Weld | +3.271 |
ammy | +3.210 |
ittle | +2.964 |
netflix | +2.906 |
Neg logit contributions | |
eret | -6.886 |
cano | -6.648 |
voic | -6.409 |
bras | -6.401 |
hell | -6.381 |
Token | activities |
Token ID | 4568 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Weld | +0.152 |
ationally | +0.149 |
ammy | +0.147 |
netflix | +0.142 |
ittle | +0.142 |
Neg logit contributions | |
eret | -0.149 |
cano | -0.139 |
hell | -0.136 |
voic | -0.133 |
bras | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Weld | +1.737 |
ationally | +1.704 |
ammy | +1.662 |
ittle | +1.614 |
netflix | +1.602 |
Neg logit contributions | |
eret | -1.753 |
cano | -1.634 |
hell | -1.583 |
voic | -1.553 |
bras | -1.529 |
Token | including |
Token ID | 1390 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Weld | +1.907 |
ationally | +1.860 |
ammy | +1.818 |
ittle | +1.766 |
netflix | +1.752 |
Neg logit contributions | |
eret | -1.945 |
cano | -1.806 |
hell | -1.761 |
voic | -1.703 |
bras | -1.680 |
Token | x |
Token ID | 2124 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
eret | +1.012 |
cano | +0.940 |
hell | +0.921 |
voic | +0.896 |
bras | +0.888 |
Neg logit contributions | |
Weld | -1.111 |
ationally | -1.097 |
ammy | -1.082 |
ittle | -1.044 |
netflix | -1.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
eret | +1.914 |
cano | +1.756 |
hell | +1.748 |
voic | +1.662 |
bras | +1.651 |
Neg logit contributions | |
Weld | -2.311 |
ationally | -2.290 |
ammy | -2.280 |
ittle | -2.189 |
netflix | -2.184 |
Token | x |
Token ID | 87 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
eret | +0.240 |
cano | +0.228 |
hell | +0.223 |
voic | +0.219 |
bras | +0.218 |
Neg logit contributions | |
Weld | -0.161 |
ationally | -0.158 |
ammy | -0.155 |
netflix | -0.148 |
ittle | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
Weld | +0.112 |
ationally | +0.110 |
ammy | +0.108 |
netflix | +0.105 |
ittle | +0.105 |
Neg logit contributions | |
eret | -0.108 |
cano | -0.101 |
hell | -0.098 |
voic | -0.096 |
bras | -0.095 |
Token | x |
Token ID | 87 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ationally | +2.176 |
Weld | +2.142 |
ammy | +2.086 |
netflix | +2.008 |
gans | +1.995 |
Neg logit contributions | |
eret | -4.160 |
cano | -4.010 |
voic | -3.979 |
bras | -3.957 |
hell | -3.817 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
Weld | +2.224 |
ationally | +2.171 |
ammy | +2.113 |
netflix | +2.050 |
ittle | +2.036 |
Neg logit contributions | |
eret | -2.515 |
cano | -2.380 |
voic | -2.299 |
bras | -2.274 |
hell | -2.262 |
Token | 172 |
Token ID | 23628 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ammy | +5.909 |
ationally | +5.777 |
^^^^ | +5.745 |
uld | +5.565 |
Weld | +5.511 |
Neg logit contributions | |
eret | -11.149 |
bras | -10.446 |
voic | -10.435 |
contrace | -10.263 |
cano | -10.013 |
Token | 100 |
Token ID | 1802 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
eret | +0.219 |
cano | +0.205 |
hell | +0.201 |
voic | +0.196 |
bras | +0.194 |
Neg logit contributions | |
Weld | -0.208 |
ationally | -0.205 |
ammy | -0.202 |
netflix | -0.195 |
ittle | -0.194 |
Token | 79 |
Token ID | 3720 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
eret | +0.483 |
cano | +0.451 |
hell | +0.440 |
voic | +0.429 |
bras | +0.425 |
Neg logit contributions | |
Weld | -0.514 |
ationally | -0.506 |
ammy | -0.499 |
netflix | -0.481 |
ittle | -0.481 |
Token | 72 |
Token ID | 4761 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
eret | +3.039 |
hell | +2.833 |
cano | +2.798 |
tes | +2.637 |
voic | +2.629 |
Neg logit contributions | |
ationally | -3.777 |
ammy | -3.753 |
Weld | -3.750 |
ittle | -3.597 |
netflix | -3.584 |
Token | x |
Token ID | 2124 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
eret | +0.424 |
cano | +0.395 |
hell | +0.386 |
voic | +0.376 |
bras | +0.372 |
Neg logit contributions | |
Weld | -0.456 |
ationally | -0.449 |
ammy | -0.443 |
netflix | -0.427 |
ittle | -0.427 |
Token | x |
Token ID | 2124 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
eret | +0.023 |
cano | +0.022 |
hell | +0.021 |
voic | +0.021 |
bras | +0.021 |
Neg logit contributions | |
Weld | -0.025 |
ationally | -0.024 |
ammy | -0.024 |
netflix | -0.023 |
ittle | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
eret | +1.164 |
cano | +1.078 |
hell | +1.061 |
voic | +1.023 |
bras | +1.015 |
Neg logit contributions | |
Weld | -1.318 |
ationally | -1.301 |
ammy | -1.287 |
ittle | -1.240 |
netflix | -1.239 |
Token | x |
Token ID | 87 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Weld | +0.962 |
ationally | +0.960 |
ammy | +0.930 |
netflix | +0.894 |
ittle | +0.888 |
Neg logit contributions | |
eret | -1.616 |
cano | -1.542 |
voic | -1.506 |
bras | -1.497 |
hell | -1.490 |
Token | . |
Token ID | 13 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
Weld | +1.389 |
ationally | +1.362 |
ammy | +1.325 |
netflix | +1.292 |
ittle | +1.283 |
Neg logit contributions | |
eret | -1.464 |
cano | -1.382 |
voic | -1.328 |
hell | -1.321 |
bras | -1.312 |
Token | x |
Token ID | 87 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ationally | +2.638 |
Weld | +2.566 |
ammy | +2.509 |
netflix | +2.435 |
gans | +2.433 |
Neg logit contributions | |
eret | -5.416 |
voic | -5.241 |
cano | -5.229 |
bras | -5.204 |
notor | -4.996 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
Weld | +2.785 |
ationally | +2.715 |
ammy | +2.634 |
netflix | +2.572 |
gans | +2.551 |
Neg logit contributions | |
eret | -3.258 |
cano | -3.086 |
voic | -2.999 |
bras | -2.958 |
hell | -2.914 |
Token | 171 |
Token ID | 27192 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
uld | +4.339 |
ationally | +4.288 |
gans | +4.283 |
ammy | +4.234 |
Weld | +4.098 |
Neg logit contributions | |
eret | -13.154 |
cano | -12.116 |
voic | -12.101 |
bras | -12.000 |
Xperia | -11.606 |
Token | 102 |
Token ID | 15143 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
eret | +0.524 |
cano | +0.491 |
hell | +0.481 |
voic | +0.470 |
bras | +0.465 |
Neg logit contributions | |
Weld | -0.484 |
ationally | -0.477 |
ammy | -0.470 |
netflix | -0.452 |
ittle | -0.452 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
eret | +1.908 |
cano | +1.767 |
hell | +1.748 |
voic | +1.686 |
bras | +1.683 |
Neg logit contributions | |
Weld | -2.000 |
ationally | -1.989 |
ammy | -1.968 |
ittle | -1.882 |
netflix | -1.880 |
Token | 86 |
Token ID | 4521 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
eret | +1.528 |
cano | +1.414 |
hell | +1.409 |
voic | +1.341 |
bras | +1.332 |
Neg logit contributions | |
Weld | -1.811 |
ationally | -1.798 |
ammy | -1.783 |
ittle | -1.718 |
netflix | -1.714 |
Token | x |
Token ID | 2124 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
eret | +1.012 |
cano | +0.940 |
hell | +0.921 |
voic | +0.896 |
bras | +0.888 |
Neg logit contributions | |
Weld | -1.111 |
ationally | -1.097 |
ammy | -1.082 |
ittle | -1.044 |
netflix | -1.044 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
eret | +2.695 |
cano | +2.522 |
hell | +2.473 |
bras | +2.357 |
voic | +2.349 |
Neg logit contributions | |
Weld | -3.321 |
ationally | -3.279 |
ammy | -3.276 |
netflix | -3.174 |
ittle | -3.158 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
eret | +0.318 |
cano | +0.297 |
hell | +0.291 |
voic | +0.283 |
bras | +0.281 |
Neg logit contributions | |
Weld | -0.305 |
ationally | -0.301 |
ammy | -0.296 |
ittle | -0.285 |
netflix | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
eret | +1.581 |
cano | +1.468 |
hell | +1.459 |
voic | +1.402 |
bras | +1.392 |
Neg logit contributions | |
Weld | -1.590 |
ationally | -1.573 |
ammy | -1.557 |
ittle | -1.495 |
netflix | -1.493 |
Token | T |
Token ID | 51 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
eret | +1.690 |
hell | +1.580 |
cano | +1.576 |
voic | +1.496 |
bras | +1.485 |
Neg logit contributions | |
Weld | -1.751 |
ationally | -1.723 |
ammy | -1.699 |
ittle | -1.648 |
netflix | -1.632 |
Token | RE |
Token ID | 2200 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
Weld | +1.723 |
ationally | +1.700 |
ammy | +1.676 |
ittle | +1.613 |
netflix | +1.592 |
Neg logit contributions | |
eret | -1.826 |
cano | -1.730 |
hell | -1.676 |
voic | -1.646 |
bras | -1.628 |
Token | AS |
Token ID | 1921 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
eret | +4.160 |
cano | +3.699 |
hell | +3.674 |
voic | +3.518 |
bras | +3.500 |
Neg logit contributions | |
ammy | -6.492 |
Weld | -6.366 |
ationally | -6.303 |
netflix | -6.289 |
ittle | -6.254 |
Token | URE |
Token ID | 11335 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
eret | +8.960 |
hell | +8.725 |
cano | +7.797 |
zek | +7.559 |
voic | +7.444 |
Neg logit contributions | |
ammy | -10.755 |
Weld | -10.666 |
netflix | -10.543 |
ationally | -10.370 |
gans | -10.328 |
Token | HUN |
Token ID | 41041 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
eret | +3.834 |
hell | +3.700 |
cano | +3.541 |
voic | +3.417 |
bras | +3.363 |
Neg logit contributions | |
ationally | -6.362 |
ammy | -6.328 |
Weld | -6.213 |
ittle | -6.191 |
netflix | -6.175 |
Token | TER |
Token ID | 5781 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
eret | +5.903 |
hell | +5.575 |
tes | +5.407 |
cano | +5.140 |
butt | +5.012 |
Neg logit contributions | |
ammy | -12.268 |
ationally | -11.900 |
ittle | -11.501 |
netflix | -11.480 |
Weld | -11.243 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
eret | +3.879 |
hell | +3.653 |
cano | +3.595 |
voic | +3.503 |
bras | +3.492 |
Neg logit contributions | |
ationally | -4.372 |
Weld | -4.370 |
ammy | -4.340 |
ittle | -4.202 |
netflix | -4.138 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
eret | +2.423 |
hell | +2.247 |
cano | +2.234 |
voic | +2.130 |
bras | +2.116 |
Neg logit contributions | |
Weld | -2.609 |
ationally | -2.590 |
ammy | -2.575 |
ittle | -2.469 |
netflix | -2.458 |
Token | D |
Token ID | 35 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
eret | +7.289 |
hell | +6.766 |
cano | +6.747 |
bras | +6.463 |
tes | +6.446 |
Neg logit contributions | |
ammy | -7.246 |
ationally | -7.242 |
Weld | -7.140 |
netflix | -7.002 |
ittle | -6.931 |
Token | � |
Token ID | 127 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
eret | +4.229 |
cano | +3.973 |
hell | +3.943 |
voic | +3.848 |
bras | +3.844 |
Neg logit contributions | |
Weld | -2.155 |
ationally | -2.132 |
ammy | -2.109 |
netflix | -2.024 |
ittle | -1.998 |
Token | � |
Token ID | 228 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
eret | +5.750 |
cano | +5.471 |
hell | +5.459 |
voic | +5.319 |
bras | +5.300 |
Neg logit contributions | |
ationally | -2.771 |
Weld | -2.708 |
ammy | -2.642 |
netflix | -2.593 |
ittle | -2.576 |
Token | P |
Token ID | 350 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
eret | +4.369 |
hell | +4.019 |
cano | +4.015 |
voic | +3.885 |
bras | +3.882 |
Neg logit contributions | |
ammy | -5.352 |
ationally | -5.340 |
Weld | -5.272 |
netflix | -5.133 |
ittle | -5.094 |
Token | ART |
Token ID | 24278 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
eret | +6.160 |
hell | +5.766 |
bras | +5.573 |
cano | +5.541 |
voic | +5.534 |
Neg logit contributions | |
ationally | -8.058 |
ammy | -8.045 |
netflix | -7.923 |
Weld | -7.811 |
ittle | -7.722 |
Token | IS |
Token ID | 1797 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
eret | +7.474 |
hell | +6.724 |
cano | +6.536 |
bras | +6.498 |
voic | +6.421 |
Neg logit contributions | |
ammy | -8.132 |
ationally | -8.064 |
Weld | -7.897 |
netflix | -7.691 |
ittle | -7.587 |
Token | . |
Token ID | 764 |
Feature activation | -8.72e+00 |
Pos logit contributions | |
eret | +8.151 |
hell | +7.584 |
bras | +7.115 |
cano | +7.080 |
voic | +7.054 |
Neg logit contributions | |
ammy | -11.573 |
ationally | -11.319 |
Weld | -11.050 |
netflix | -10.910 |
ittle | -10.902 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
eret | +5.601 |
hell | +5.078 |
cano | +5.051 |
bras | +4.856 |
voic | +4.845 |
Neg logit contributions | |
ationally | -6.408 |
Weld | -6.373 |
ammy | -6.332 |
netflix | -6.198 |
ittle | -6.063 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
eret | +3.061 |
hell | +2.858 |
cano | +2.800 |
voic | +2.673 |
tes | +2.662 |
Neg logit contributions | |
ationally | -3.497 |
Weld | -3.490 |
ammy | -3.477 |
ittle | -3.327 |
netflix | -3.315 |
Token | Faith |
Token ID | 45536 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
eret | +2.486 |
hell | +2.325 |
cano | +2.306 |
voic | +2.169 |
bras | +2.141 |
Neg logit contributions | |
Weld | -3.194 |
ationally | -3.144 |
ammy | -3.106 |
netflix | -3.001 |
ittle | -2.992 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
eret | +0.845 |
cano | +0.785 |
hell | +0.765 |
voic | +0.745 |
bras | +0.738 |
Neg logit contributions | |
Weld | -0.996 |
ationally | -0.981 |
ammy | -0.966 |
netflix | -0.935 |
ittle | -0.935 |
Token | F |
Token ID | 37 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
eret | +0.636 |
cano | +0.593 |
hell | +0.580 |
voic | +0.565 |
bras | +0.557 |
Neg logit contributions | |
Weld | -0.675 |
ationally | -0.662 |
ammy | -0.655 |
netflix | -0.634 |
ittle | -0.627 |
Token | LECT |
Token ID | 16779 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
Weld | +1.682 |
ationally | +1.661 |
ammy | +1.623 |
ittle | +1.607 |
netflix | +1.570 |
Neg logit contributions | |
eret | -1.365 |
cano | -1.294 |
hell | -1.238 |
voic | -1.219 |
bras | -1.203 |
Token | _ |
Token ID | 62 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
eret | +2.614 |
cano | +2.424 |
hell | +2.393 |
voic | +2.334 |
bras | +2.318 |
Neg logit contributions | |
Weld | -3.156 |
ammy | -3.112 |
ationally | -3.091 |
ittle | -2.977 |
netflix | -2.966 |
Token | CLASS |
Token ID | 31631 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
eret | +3.173 |
hell | +2.970 |
cano | +2.963 |
voic | +2.797 |
tes | +2.786 |
Neg logit contributions | |
Weld | -3.758 |
ationally | -3.656 |
ammy | -3.608 |
ittle | -3.504 |
netflix | -3.449 |
Token | _ |
Token ID | 62 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
eret | +4.469 |
cano | +4.143 |
hell | +4.121 |
voic | +3.971 |
bras | +3.949 |
Neg logit contributions | |
Weld | -6.393 |
ammy | -6.370 |
ationally | -6.326 |
ittle | -6.090 |
netflix | -6.070 |
Token | ST |
Token ID | 2257 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
eret | +6.810 |
hell | +6.649 |
cano | +6.392 |
tes | +6.218 |
shut | +6.065 |
Neg logit contributions | |
Weld | -9.183 |
ammy | -9.014 |
ationally | -8.927 |
ittle | -8.635 |
gans | -8.348 |
Token | ART |
Token ID | 7227 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
eret | +9.863 |
hell | +9.322 |
OFF | +8.900 |
tes | +8.656 |
butt | +8.593 |
Neg logit contributions | |
ammy | -9.562 |
Weld | -9.496 |
ationally | -9.466 |
ittle | -9.327 |
netflix | -9.266 |
Token | () |
Token ID | 3419 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
eret | +0.695 |
cano | +0.649 |
hell | +0.634 |
voic | +0.617 |
bras | +0.612 |
Neg logit contributions | |
Weld | -0.739 |
ationally | -0.728 |
ammy | -0.719 |
netflix | -0.695 |
ittle | -0.692 |
Token | above |
Token ID | 2029 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
eret | +1.127 |
cano | +1.051 |
hell | +1.029 |
voic | +1.002 |
bras | +0.992 |
Neg logit contributions | |
Weld | -1.181 |
ationally | -1.165 |
ammy | -1.150 |
netflix | -1.112 |
ittle | -1.103 |
Token | is |
Token ID | 318 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
eret | +2.087 |
cano | +1.948 |
hell | +1.904 |
voic | +1.862 |
bras | +1.845 |
Neg logit contributions | |
Weld | -2.202 |
ationally | -2.179 |
ammy | -2.160 |
netflix | -2.096 |
ittle | -2.062 |
Token | the |
Token ID | 262 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
eret | +1.222 |
cano | +1.137 |
hell | +1.113 |
voic | +1.087 |
bras | +1.076 |
Neg logit contributions | |
Weld | -1.300 |
ationally | -1.280 |
ammy | -1.267 |
netflix | -1.225 |
ittle | -1.217 |
Token | TI |
Token ID | 25621 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
eret | +6.075 |
cano | +5.445 |
tes | +5.369 |
hell | +5.365 |
voic | +5.243 |
Neg logit contributions | |
ammy | -7.340 |
ationally | -7.172 |
Weld | -7.067 |
netflix | -7.016 |
ittle | -6.750 |
Token | � |
Token ID | 127 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
eret | +2.903 |
cano | +2.645 |
hell | +2.639 |
voic | +2.544 |
bras | +2.527 |
Neg logit contributions | |
ationally | -3.531 |
Weld | -3.528 |
ammy | -3.518 |
netflix | -3.381 |
ittle | -3.373 |
Token | � |
Token ID | 228 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
eret | +6.024 |
cano | +5.729 |
hell | +5.728 |
voic | +5.579 |
bras | +5.547 |
Neg logit contributions | |
ationally | -3.034 |
ammy | -2.888 |
Weld | -2.879 |
netflix | -2.803 |
ittle | -2.793 |
Token | P |
Token ID | 350 |
Feature activation | -9.69e+00 |
Pos logit contributions | |
eret | +4.152 |
cano | +3.828 |
hell | +3.827 |
voic | +3.704 |
bras | +3.671 |
Neg logit contributions | |
ammy | -5.039 |
ationally | -5.011 |
Weld | -4.963 |
netflix | -4.828 |
ittle | -4.778 |
Token | ART |
Token ID | 24278 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
eret | +4.680 |
hell | +4.217 |
cano | +4.082 |
bras | +4.045 |
voic | +4.009 |
Neg logit contributions | |
ationally | -8.480 |
ammy | -8.420 |
netflix | -8.288 |
Weld | -8.282 |
ittle | -8.149 |
Token | IS |
Token ID | 1797 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
eret | +7.489 |
hell | +6.640 |
bras | +6.487 |
cano | +6.481 |
voic | +6.361 |
Neg logit contributions | |
ammy | -9.016 |
ationally | -8.906 |
Weld | -8.655 |
netflix | -8.443 |
ittle | -8.411 |
Token | . |
Token ID | 764 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
eret | +6.496 |
hell | +5.790 |
cano | +5.495 |
bras | +5.379 |
voic | +5.343 |
Neg logit contributions | |
ammy | -12.224 |
ationally | -12.027 |
Weld | -11.830 |
ittle | -11.622 |
netflix | -11.599 |
Token |
|
Token ID | 198 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
eret | +5.299 |
cano | +4.777 |
hell | +4.766 |
bras | +4.578 |
voic | +4.561 |
Neg logit contributions | |
ationally | -6.135 |
Weld | -6.117 |
ammy | -6.037 |
netflix | -5.915 |
ittle | -5.833 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
eret | +2.832 |
hell | +2.636 |
cano | +2.592 |
voic | +2.474 |
bras | +2.460 |
Neg logit contributions | |
Weld | -3.171 |
ationally | -3.170 |
ammy | -3.150 |
ittle | -3.016 |
netflix | -3.009 |
Token | Pen |
Token ID | 25553 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
eret | +2.577 |
hell | +2.389 |
cano | +2.389 |
voic | +2.245 |
bras | +2.221 |
Neg logit contributions | |
Weld | -3.282 |
ationally | -3.228 |
ammy | -3.185 |
netflix | -3.090 |
ittle | -3.068 |
Token | ance |
Token ID | 590 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
eret | +4.706 |
cano | +4.288 |
hell | +4.284 |
voic | +4.050 |
bras | +4.001 |
Neg logit contributions | |
Weld | -4.050 |
ammy | -3.948 |
ationally | -3.905 |
netflix | -3.759 |
ittle | -3.726 |
Token | large |
Token ID | 1588 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Weld | +0.404 |
ationally | +0.397 |
ammy | +0.390 |
ittle | +0.376 |
netflix | +0.375 |
Neg logit contributions | |
eret | -0.452 |
cano | -0.426 |
hell | -0.415 |
voic | -0.404 |
bras | -0.401 |
Token | reservoir |
Token ID | 22115 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Weld | +0.688 |
ationally | +0.675 |
ammy | +0.662 |
netflix | +0.635 |
ittle | +0.634 |
Neg logit contributions | |
eret | -0.933 |
cano | -0.881 |
hell | -0.863 |
voic | -0.843 |
bras | -0.837 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Weld | +0.025 |
ationally | +0.024 |
ammy | +0.024 |
netflix | +0.023 |
ittle | +0.023 |
Neg logit contributions | |
eret | -0.021 |
cano | -0.020 |
hell | -0.019 |
voic | -0.019 |
bras | -0.019 |
Token | M |
Token ID | 337 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
eret | +1.149 |
cano | +1.068 |
hell | +1.046 |
voic | +1.021 |
bras | +1.014 |
Neg logit contributions | |
Weld | -1.245 |
ationally | -1.227 |
ammy | -1.216 |
netflix | -1.172 |
ittle | -1.165 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
eret | +0.376 |
cano | +0.352 |
hell | +0.344 |
voic | +0.336 |
bras | +0.333 |
Neg logit contributions | |
Weld | -0.368 |
ationally | -0.362 |
ammy | -0.356 |
ittle | -0.343 |
netflix | -0.343 |
Token | le |
Token ID | 443 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
eret | +2.140 |
cano | +2.004 |
hell | +1.962 |
bras | +1.935 |
voic | +1.922 |
Neg logit contributions | |
Weld | -2.017 |
ationally | -1.978 |
ammy | -1.978 |
netflix | -1.875 |
ittle | -1.871 |
Token | p |
Token ID | 79 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
cano | +7.309 |
eret | +7.167 |
hell | +6.717 |
zek | +6.483 |
tes | +6.307 |
Neg logit contributions | |
Weld | -11.532 |
ammy | -10.968 |
ationally | -10.957 |
netflix | -10.816 |
^^^^ | -10.528 |
Token | ra |
Token ID | 430 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
eret | +5.820 |
cano | +5.456 |
hell | +5.294 |
bras | +4.998 |
tes | +4.962 |
Neg logit contributions | |
Weld | -9.340 |
ammy | -9.296 |
ationally | -9.287 |
ittle | -8.853 |
Municip | -8.776 |
Token | e |
Token ID | 68 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
eret | +1.505 |
cano | +1.400 |
hell | +1.375 |
voic | +1.327 |
bras | +1.325 |
Neg logit contributions | |
Weld | -1.493 |
ationally | -1.468 |
ammy | -1.454 |
netflix | -1.397 |
ittle | -1.393 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
eret | +5.713 |
hell | +5.350 |
cano | +5.325 |
bras | +5.111 |
voic | +5.032 |
Neg logit contributions | |
ammy | -7.026 |
Weld | -6.982 |
ationally | -6.934 |
netflix | -6.537 |
ittle | -6.490 |
Token | may |
Token ID | 743 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
eret | +2.152 |
cano | +2.011 |
hell | +1.970 |
bras | +1.924 |
voic | +1.917 |
Neg logit contributions | |
Weld | -2.293 |
ationally | -2.271 |
ammy | -2.243 |
netflix | -2.165 |
ittle | -2.132 |
Token | 107 |
Token ID | 16226 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
eret | +2.108 |
cano | +1.967 |
hell | +1.934 |
voic | +1.876 |
bras | +1.874 |
Neg logit contributions | |
ammy | -2.744 |
ationally | -2.739 |
Weld | -2.735 |
netflix | -2.632 |
ittle | -2.622 |
Token | P |
Token ID | 47 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
eret | +2.762 |
cano | +2.616 |
hell | +2.574 |
voic | +2.473 |
bras | +2.443 |
Neg logit contributions | |
Weld | -3.047 |
ationally | -3.014 |
ammy | -3.013 |
netflix | -2.929 |
ittle | -2.869 |
Token | / |
Token ID | 14 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
eret | +0.419 |
cano | +0.396 |
hell | +0.389 |
voic | +0.379 |
bras | +0.376 |
Neg logit contributions | |
Weld | -0.320 |
ationally | -0.317 |
ammy | -0.313 |
netflix | -0.302 |
ittle | -0.299 |
Token | Wilson |
Token ID | 37349 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
eret | +0.756 |
cano | +0.711 |
hell | +0.701 |
voic | +0.677 |
bras | +0.674 |
Neg logit contributions | |
Weld | -0.670 |
ationally | -0.663 |
ammy | -0.654 |
ittle | -0.628 |
netflix | -0.627 |
Token | – |
Token ID | 1906 |
Feature activation | -9.65e+00 |
Pos logit contributions | |
eret | +4.450 |
cano | +4.115 |
hell | +4.098 |
voic | +3.929 |
bras | +3.915 |
Neg logit contributions | |
ationally | -4.859 |
ammy | -4.822 |
Weld | -4.754 |
netflix | -4.722 |
ittle | -4.604 |
Token | Har |
Token ID | 13587 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
eret | +5.066 |
hell | +4.754 |
cano | +4.574 |
tes | +4.376 |
voic | +4.352 |
Neg logit contributions | |
ationally | -7.900 |
ammy | -7.791 |
Weld | -7.767 |
netflix | -7.453 |
gans | -7.452 |
Token | rington |
Token ID | 24833 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
eret | +6.634 |
cano | +6.275 |
hell | +6.187 |
zek | +5.750 |
butt | +5.703 |
Neg logit contributions | |
Weld | -11.925 |
ammy | -11.874 |
ationally | -11.703 |
Municip | -11.259 |
netflix | -10.957 |
Token | . |
Token ID | 13 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Weld | +1.708 |
ationally | +1.671 |
ammy | +1.632 |
ittle | +1.577 |
netflix | +1.573 |
Neg logit contributions | |
eret | -1.711 |
cano | -1.596 |
hell | -1.551 |
voic | -1.528 |
bras | -1.506 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Weld | +0.418 |
ationally | +0.408 |
ammy | +0.401 |
ittle | +0.388 |
netflix | +0.388 |
Neg logit contributions | |
eret | -0.409 |
cano | -0.382 |
hell | -0.372 |
voic | -0.363 |
bras | -0.360 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
eret | +1.301 |
cano | +1.211 |
hell | +1.196 |
voic | +1.157 |
bras | +1.147 |
Neg logit contributions | |
Weld | -1.278 |
ationally | -1.263 |
ammy | -1.249 |
ittle | -1.200 |
netflix | -1.198 |
Token | The |
Token ID | 464 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
eret | +0.888 |
cano | +0.827 |
hell | +0.817 |
voic | +0.780 |
bras | +0.776 |
Neg logit contributions | |
Weld | -1.016 |
ationally | -1.000 |
ammy | -0.990 |
ittle | -0.950 |
netflix | -0.950 |
Token | = |
Token ID | 796 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
eret | +3.441 |
hell | +3.105 |
cano | +3.101 |
bras | +2.963 |
voic | +2.942 |
Neg logit contributions | |
ationally | -4.033 |
Weld | -4.024 |
ammy | -3.991 |
ittle | -3.772 |
netflix | -3.748 |
Token | c |
Token ID | 269 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Weld | +1.077 |
ationally | +1.054 |
ammy | +1.025 |
netflix | +1.000 |
ittle | +0.998 |
Neg logit contributions | |
eret | -1.015 |
cano | -0.945 |
hell | -0.916 |
voic | -0.891 |
bras | -0.878 |
Token | v |
Token ID | 85 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
Weld | +2.042 |
ationally | +2.027 |
ammy | +1.989 |
netflix | +1.934 |
ittle | +1.934 |
Neg logit contributions | |
eret | -1.892 |
cano | -1.759 |
bras | -1.718 |
voic | -1.714 |
hell | -1.674 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Weld | +3.544 |
ationally | +3.408 |
netflix | +3.277 |
ammy | +3.250 |
gans | +3.250 |
Neg logit contributions | |
eret | -4.347 |
cano | -4.104 |
voic | -4.063 |
bras | -3.966 |
notor | -3.911 |
Token | . |
Token ID | 764 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
eret | +0.473 |
cano | +0.423 |
hell | +0.405 |
voic | +0.388 |
bras | +0.381 |
Neg logit contributions | |
Weld | -1.100 |
ationally | -1.087 |
ammy | -1.074 |
netflix | -1.048 |
ittle | -1.047 |
Token | morphology |
Token ID | 46320 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
eret | +2.115 |
cano | +1.966 |
hell | +1.901 |
voic | +1.874 |
bras | +1.850 |
Neg logit contributions | |
Weld | -3.080 |
ationally | -3.032 |
ammy | -2.989 |
ittle | -2.944 |
netflix | -2.940 |
Token | Ex |
Token ID | 3109 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
eret | +3.380 |
hell | +3.154 |
cano | +2.645 |
voic | +2.552 |
AppData | +2.383 |
Neg logit contributions | |
ammy | -14.847 |
ationally | -14.627 |
ittle | -14.615 |
netflix | -14.240 |
Weld | -14.050 |
Token | ( |
Token ID | 357 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
eret | +2.823 |
hell | +2.589 |
cano | +2.534 |
voic | +2.408 |
bras | +2.395 |
Neg logit contributions | |
Weld | -4.462 |
ationally | -4.448 |
ammy | -4.448 |
ittle | -4.259 |
netflix | -4.241 |
Token | gray |
Token ID | 12768 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Weld | +1.086 |
ationally | +1.053 |
ammy | +1.010 |
ittle | +0.982 |
netflix | +0.969 |
Neg logit contributions | |
eret | -2.152 |
cano | -2.057 |
hell | -1.999 |
voic | -1.952 |
bras | -1.942 |
Token | , |
Token ID | 837 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Weld | +2.342 |
ationally | +2.268 |
ammy | +2.231 |
netflix | +2.216 |
ittle | +2.199 |
Neg logit contributions | |
eret | -1.732 |
cano | -1.630 |
hell | -1.529 |
voic | -1.512 |
bras | -1.494 |
Token | c |
Token ID | 269 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
eret | +1.624 |
cano | +1.499 |
hell | +1.470 |
voic | +1.434 |
bras | +1.421 |
Neg logit contributions | |
Weld | -2.104 |
ationally | -2.082 |
ammy | -2.076 |
ittle | -1.993 |
netflix | -1.991 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
eret | +1.581 |
cano | +1.468 |
hell | +1.459 |
voic | +1.402 |
bras | +1.392 |
Neg logit contributions | |
Weld | -1.590 |
ationally | -1.573 |
ammy | -1.557 |
ittle | -1.495 |
netflix | -1.493 |
Token | T |
Token ID | 51 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
eret | +1.690 |
hell | +1.580 |
cano | +1.576 |
voic | +1.496 |
bras | +1.485 |
Neg logit contributions | |
Weld | -1.751 |
ationally | -1.723 |
ammy | -1.699 |
ittle | -1.648 |
netflix | -1.632 |
Token | RE |
Token ID | 2200 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
Weld | +1.723 |
ationally | +1.700 |
ammy | +1.676 |
ittle | +1.613 |
netflix | +1.592 |
Neg logit contributions | |
eret | -1.826 |
cano | -1.730 |
hell | -1.676 |
voic | -1.646 |
bras | -1.628 |
Token | AS |
Token ID | 1921 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
eret | +4.160 |
cano | +3.699 |
hell | +3.674 |
voic | +3.518 |
bras | +3.500 |
Neg logit contributions | |
ammy | -6.492 |
Weld | -6.366 |
ationally | -6.303 |
netflix | -6.289 |
ittle | -6.254 |
Token | URE |
Token ID | 11335 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
eret | +8.960 |
hell | +8.725 |
cano | +7.797 |
zek | +7.559 |
voic | +7.444 |
Neg logit contributions | |
ammy | -10.755 |
Weld | -10.666 |
netflix | -10.543 |
ationally | -10.370 |
gans | -10.328 |
Token | HUN |
Token ID | 41041 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
eret | +3.834 |
hell | +3.700 |
cano | +3.541 |
voic | +3.417 |
bras | +3.363 |
Neg logit contributions | |
ationally | -6.362 |
ammy | -6.328 |
Weld | -6.213 |
ittle | -6.191 |
netflix | -6.175 |
Token | TER |
Token ID | 5781 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
eret | +5.903 |
hell | +5.575 |
tes | +5.407 |
cano | +5.140 |
butt | +5.012 |
Neg logit contributions | |
ammy | -12.268 |
ationally | -11.900 |
ittle | -11.501 |
netflix | -11.480 |
Weld | -11.243 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
eret | +3.879 |
hell | +3.653 |
cano | +3.595 |
voic | +3.503 |
bras | +3.492 |
Neg logit contributions | |
ationally | -4.372 |
Weld | -4.370 |
ammy | -4.340 |
ittle | -4.202 |
netflix | -4.138 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
eret | +2.423 |
hell | +2.247 |
cano | +2.234 |
voic | +2.130 |
bras | +2.116 |
Neg logit contributions | |
Weld | -2.609 |
ationally | -2.590 |
ammy | -2.575 |
ittle | -2.469 |
netflix | -2.458 |
Token | 2007 |
Token ID | 12726 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
eret | +2.979 |
hell | +2.768 |
cano | +2.752 |
bras | +2.570 |
voic | +2.569 |
Neg logit contributions | |
Weld | -3.754 |
ationally | -3.685 |
ammy | -3.640 |
ittle | -3.547 |
netflix | -3.512 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
eret | +0.452 |
cano | +0.421 |
hell | +0.413 |
voic | +0.402 |
bras | +0.398 |
Neg logit contributions | |
Weld | -0.445 |
ationally | -0.438 |
ammy | -0.432 |
ittle | -0.417 |
netflix | -0.416 |
Token | E |
Token ID | 36 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
eret | +2.325 |
cano | +2.183 |
hell | +2.144 |
voic | +2.057 |
bras | +2.033 |
Neg logit contributions | |
Weld | -2.500 |
ationally | -2.423 |
ammy | -2.375 |
netflix | -2.337 |
ittle | -2.312 |
Token | mpire |
Token ID | 35386 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
eret | +4.680 |
cano | +4.379 |
tes | +4.265 |
hell | +4.234 |
voic | +4.067 |
Neg logit contributions | |
Weld | -4.951 |
ationally | -4.794 |
ammy | -4.765 |
netflix | -4.672 |
ittle | -4.532 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Weld | +0.559 |
ationally | +0.550 |
ammy | +0.542 |
netflix | +0.522 |
ittle | +0.521 |
Neg logit contributions | |
eret | -0.545 |
cano | -0.508 |
hell | -0.496 |
voic | -0.483 |
bras | -0.477 |
Token | FIN |
Token ID | 20032 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
eret | +2.233 |
cano | +2.073 |
hell | +2.037 |
voic | +1.996 |
bras | +1.980 |
Neg logit contributions | |
Weld | -2.219 |
ationally | -2.212 |
ammy | -2.193 |
netflix | -2.106 |
ittle | -2.096 |
Token | DE |
Token ID | 5550 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
eret | +3.523 |
cano | +3.224 |
hell | +3.183 |
voic | +3.107 |
bras | +3.078 |
Neg logit contributions | |
Weld | -4.221 |
ammy | -4.170 |
ationally | -4.131 |
netflix | -4.041 |
ittle | -3.991 |
Token | TRAN |
Token ID | 48213 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
eret | +3.653 |
cano | +3.362 |
hell | +3.315 |
voic | +3.262 |
bras | +3.250 |
Neg logit contributions | |
ationally | -3.977 |
Weld | -3.965 |
ammy | -3.947 |
netflix | -3.802 |
ittle | -3.798 |
Token | SM |
Token ID | 12310 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
eret | +6.280 |
cano | +5.478 |
voic | +5.432 |
hell | +5.375 |
bras | +5.367 |
Neg logit contributions | |
Weld | -11.565 |
ammy | -11.508 |
ationally | -11.418 |
ittle | -11.142 |
netflix | -10.870 |
Token | ISSION |
Token ID | 40373 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Weld | +1.485 |
ationally | +1.451 |
ammy | +1.402 |
ittle | +1.363 |
netflix | +1.352 |
Neg logit contributions | |
eret | -2.079 |
cano | -1.974 |
hell | -1.918 |
voic | -1.887 |
bras | -1.882 |
Token | /// |
Token ID | 34013 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
eret | +1.370 |
cano | +1.284 |
hell | +1.263 |
voic | +1.239 |
bras | +1.231 |
Neg logit contributions | |
Weld | -1.017 |
ationally | -1.002 |
ammy | -0.989 |
netflix | -0.945 |
ittle | -0.942 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Weld | +0.503 |
ationally | +0.495 |
ammy | +0.484 |
netflix | +0.463 |
ittle | +0.462 |
Neg logit contributions | |
eret | -0.736 |
cano | -0.696 |
hell | -0.682 |
voic | -0.669 |
bras | -0.663 |
Token | Our |
Token ID | 5122 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Weld | +2.744 |
ationally | +2.728 |
ammy | +2.672 |
netflix | +2.641 |
ittle | +2.585 |
Neg logit contributions | |
eret | -2.639 |
cano | -2.469 |
voic | -2.364 |
bras | -2.345 |
hell | -2.339 |
Token | S |
Token ID | 50 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
eret | +1.510 |
cano | +1.400 |
hell | +1.381 |
voic | +1.328 |
bras | +1.312 |
Neg logit contributions | |
Weld | -1.681 |
ationally | -1.656 |
ammy | -1.638 |
netflix | -1.584 |
ittle | -1.574 |
Token | U |
Token ID | 471 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
eret | +4.267 |
cano | +3.892 |
hell | +3.886 |
voic | +3.724 |
bras | +3.680 |
Neg logit contributions | |
Weld | -5.021 |
ationally | -4.989 |
ammy | -4.981 |
netflix | -4.867 |
ittle | -4.752 |
Token | PP |
Token ID | 10246 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
eret | +4.237 |
cano | +3.911 |
hell | +3.894 |
tes | +3.739 |
bras | +3.731 |
Neg logit contributions | |
ammy | -3.890 |
ationally | -3.888 |
Weld | -3.873 |
netflix | -3.749 |
ittle | -3.706 |
Token | LE |
Token ID | 2538 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
eret | +2.984 |
hell | +2.707 |
cano | +2.704 |
voic | +2.595 |
bras | +2.577 |
Neg logit contributions | |
ationally | -3.449 |
ammy | -3.425 |
Weld | -3.419 |
netflix | -3.312 |
ittle | -3.272 |
Token | MENT |
Token ID | 10979 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
eret | +3.956 |
cano | +3.640 |
hell | +3.633 |
bras | +3.495 |
voic | +3.494 |
Neg logit contributions | |
ationally | -4.380 |
ammy | -4.360 |
Weld | -4.357 |
netflix | -4.243 |
ittle | -4.152 |
Token | UM |
Token ID | 5883 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
eret | +3.087 |
cano | +2.807 |
hell | +2.803 |
voic | +2.714 |
bras | +2.687 |
Neg logit contributions | |
Weld | -3.658 |
ammy | -3.617 |
ationally | -3.612 |
netflix | -3.503 |
ittle | -3.477 |
Token | T |
Token ID | 309 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
eret | +7.606 |
hell | +7.073 |
bras | +6.835 |
voic | +6.813 |
cano | +6.750 |
Neg logit contributions | |
ammy | -10.151 |
ationally | -10.001 |
netflix | -9.919 |
Weld | -9.669 |
ittle | -9.561 |
Token | ER |
Token ID | 13793 |
Feature activation | -9.81e+00 |
Pos logit contributions | |
eret | +3.401 |
cano | +3.061 |
hell | +3.055 |
voic | +2.955 |
bras | +2.937 |
Neg logit contributions | |
ationally | -4.102 |
Weld | -4.087 |
ammy | -4.082 |
netflix | -3.990 |
ittle | -3.888 |
Token | TI |
Token ID | 25621 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
eret | +6.075 |
cano | +5.445 |
tes | +5.369 |
hell | +5.365 |
voic | +5.243 |
Neg logit contributions | |
ammy | -7.340 |
ationally | -7.172 |
Weld | -7.067 |
netflix | -7.016 |
ittle | -6.750 |
Token | � |
Token ID | 127 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
eret | +2.903 |
cano | +2.645 |
hell | +2.639 |
voic | +2.544 |
bras | +2.527 |
Neg logit contributions | |
ationally | -3.531 |
Weld | -3.528 |
ammy | -3.518 |
netflix | -3.381 |
ittle | -3.373 |
Token | � |
Token ID | 228 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
eret | +6.024 |
cano | +5.729 |
hell | +5.728 |
voic | +5.579 |
bras | +5.547 |
Neg logit contributions | |
ationally | -3.034 |
ammy | -2.888 |
Weld | -2.879 |
netflix | -2.803 |
ittle | -2.793 |
Token | 21 |
Token ID | 2481 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Weld | +2.591 |
ationally | +2.548 |
ammy | +2.488 |
netflix | +2.422 |
ittle | +2.408 |
Neg logit contributions | |
eret | -2.347 |
cano | -2.181 |
voic | -2.103 |
hell | -2.099 |
bras | -2.033 |
Token | O |
Token ID | 440 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
eret | +1.972 |
cano | +1.828 |
hell | +1.814 |
voic | +1.765 |
bras | +1.743 |
Neg logit contributions | |
ationally | -2.048 |
Weld | -2.041 |
ammy | -2.018 |
ittle | -1.950 |
netflix | -1.937 |
Token | & |
Token ID | 5 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Weld | +0.776 |
ationally | +0.763 |
ammy | +0.743 |
netflix | +0.708 |
ittle | +0.707 |
Neg logit contributions | |
eret | -1.287 |
cano | -1.225 |
hell | -1.186 |
voic | -1.176 |
bras | -1.170 |
Token | A |
Token ID | 32 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
eret | +1.124 |
cano | +1.037 |
hell | +1.019 |
voic | +0.975 |
bras | +0.964 |
Neg logit contributions | |
Weld | -1.591 |
ationally | -1.569 |
ammy | -1.555 |
netflix | -1.510 |
ittle | -1.509 |
Token | - |
Token ID | 12 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
eret | +2.342 |
hell | +2.166 |
cano | +2.154 |
voic | +2.057 |
bras | +2.036 |
Neg logit contributions | |
ationally | -2.768 |
Weld | -2.768 |
ammy | -2.750 |
ittle | -2.659 |
netflix | -2.634 |
Token | WOR |
Token ID | 45359 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
eret | +4.279 |
hell | +4.160 |
cano | +4.012 |
voic | +3.901 |
bras | +3.829 |
Neg logit contributions | |
Weld | -4.562 |
ationally | -4.536 |
ammy | -4.418 |
ittle | -4.297 |
netflix | -4.224 |
Token | ST |
Token ID | 2257 |
Feature activation | -8.42e+00 |
Pos logit contributions | |
eret | +5.388 |
hell | +5.079 |
cano | +4.856 |
tes | +4.788 |
voic | +4.510 |
Neg logit contributions | |
ammy | -12.054 |
netflix | -11.699 |
ationally | -11.664 |
Weld | -11.543 |
enhagen | -11.302 |
Token | OF |
Token ID | 3963 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
eret | +4.312 |
voic | +3.956 |
hell | +3.935 |
cano | +3.923 |
bras | +3.770 |
Neg logit contributions | |
ationally | -7.048 |
Weld | -6.947 |
ammy | -6.936 |
ittle | -6.835 |
netflix | -6.791 |
Token | - |
Token ID | 12 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
eret | +4.821 |
hell | +4.462 |
voic | +4.416 |
cano | +4.410 |
bras | +4.298 |
Neg logit contributions | |
ationally | -6.190 |
Weld | -6.080 |
ittle | -6.072 |
ammy | -6.049 |
netflix | -5.942 |
Token | Penn |
Token ID | 39899 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
eret | +3.677 |
hell | +3.532 |
cano | +3.444 |
voic | +3.340 |
bras | +3.277 |
Neg logit contributions | |
Weld | -3.434 |
ationally | -3.403 |
ammy | -3.309 |
ittle | -3.221 |
netflix | -3.150 |
Token | J |
Token ID | 449 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
eret | +1.407 |
cano | +1.309 |
hell | +1.291 |
voic | +1.256 |
bras | +1.238 |
Neg logit contributions | |
Weld | -1.371 |
ationally | -1.357 |
ammy | -1.328 |
netflix | -1.297 |
ittle | -1.286 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Weld | +1.762 |
ationally | +1.712 |
ammy | +1.671 |
netflix | +1.621 |
ittle | +1.607 |
Neg logit contributions | |
eret | -1.868 |
cano | -1.752 |
hell | -1.690 |
voic | -1.679 |
bras | -1.665 |
Token | Old |
Token ID | 5706 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
eret | +1.982 |
cano | +1.864 |
hell | +1.822 |
voic | +1.771 |
bras | +1.755 |
Neg logit contributions | |
ationally | -1.736 |
Weld | -1.714 |
ammy | -1.699 |
netflix | -1.651 |
ittle | -1.642 |
Token | gift |
Token ID | 6979 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Weld | +3.089 |
ationally | +3.019 |
ammy | +2.973 |
ittle | +2.877 |
netflix | +2.834 |
Neg logit contributions | |
eret | -3.473 |
cano | -3.303 |
hell | -3.227 |
voic | -3.118 |
bras | -3.107 |
Token | – |
Token ID | 1906 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
eret | +2.307 |
cano | +2.162 |
hell | +2.098 |
voic | +2.043 |
bras | +2.032 |
Neg logit contributions | |
Weld | -2.243 |
ationally | -2.217 |
ammy | -2.164 |
netflix | -2.123 |
ittle | -2.101 |
Token | be |
Token ID | 1350 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
eret | +3.547 |
cano | +3.246 |
hell | +3.215 |
tes | +2.981 |
voic | +2.938 |
Neg logit contributions | |
Weld | -5.330 |
ationally | -5.183 |
ammy | -5.056 |
netflix | -4.924 |
ittle | -4.919 |
Token | arer |
Token ID | 11258 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
Weld | +0.099 |
ationally | +0.098 |
ammy | +0.097 |
ittle | +0.094 |
netflix | +0.094 |
Neg logit contributions | |
eret | -0.068 |
cano | -0.063 |
hell | -0.061 |
voic | -0.060 |
bras | -0.059 |
Token | setting |
Token ID | 4634 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
eret | +4.629 |
voic | +3.641 |
cano | +3.325 |
hell | +3.310 |
tes | +3.171 |
Neg logit contributions | |
ammy | -13.003 |
ationally | -12.857 |
Weld | -12.772 |
ittle | -12.724 |
netflix | -12.678 |
Token | box |
Token ID | 3091 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
eret | +1.305 |
cano | +1.223 |
hell | +1.204 |
voic | +1.176 |
bras | +1.167 |
Neg logit contributions | |
Weld | -1.052 |
ationally | -1.039 |
ammy | -1.022 |
netflix | -0.977 |
ittle | -0.974 |
Token | underneath |
Token ID | 14638 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
eret | +4.545 |
cano | +4.235 |
hell | +4.098 |
bras | +3.916 |
voic | +3.895 |
Neg logit contributions | |
Weld | -6.348 |
ationally | -6.273 |
ammy | -6.199 |
gans | -5.993 |
netflix | -5.983 |
Token | roughly |
Token ID | 7323 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
ationally | +1.066 |
Weld | +1.060 |
ammy | +1.020 |
ittle | +1.003 |
netflix | +0.986 |
Neg logit contributions | |
eret | -0.871 |
cano | -0.809 |
hell | -0.801 |
voic | -0.777 |
bras | -0.760 |
Token | ( |
Token ID | 357 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
eret | +2.867 |
cano | +2.658 |
hell | +2.578 |
voic | +2.500 |
bras | +2.470 |
Neg logit contributions | |
Weld | -4.244 |
ammy | -4.220 |
ationally | -4.218 |
ittle | -4.030 |
netflix | -4.030 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Weld | +3.651 |
ationally | +3.617 |
ammy | +3.475 |
netflix | +3.388 |
ittle | +3.357 |
Neg logit contributions | |
eret | -4.082 |
cano | -3.864 |
hell | -3.685 |
bras | -3.625 |
voic | -3.608 |
Token |
|
Token ID | 198 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
eret | +1.098 |
cano | +1.025 |
hell | +1.011 |
voic | +0.983 |
bras | +0.972 |
Neg logit contributions | |
Weld | -1.112 |
ationally | -1.097 |
ammy | -1.086 |
ittle | -1.045 |
netflix | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Weld | +0.626 |
ationally | +0.612 |
ammy | +0.596 |
netflix | +0.580 |
ittle | +0.575 |
Neg logit contributions | |
eret | -0.752 |
cano | -0.711 |
hell | -0.685 |
voic | -0.679 |
bras | -0.672 |
Token | T |
Token ID | 51 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Weld | +3.089 |
ationally | +3.069 |
ammy | +3.015 |
netflix | +2.955 |
ittle | +2.905 |
Neg logit contributions | |
eret | -2.991 |
cano | -2.774 |
voic | -2.671 |
bras | -2.639 |
hell | -2.638 |
Token | RE |
Token ID | 2200 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
Weld | +1.511 |
ationally | +1.496 |
ammy | +1.473 |
ittle | +1.420 |
netflix | +1.403 |
Neg logit contributions | |
eret | -1.543 |
cano | -1.458 |
hell | -1.417 |
voic | -1.388 |
bras | -1.374 |
Token | AS |
Token ID | 1921 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
eret | +3.780 |
cano | +3.468 |
hell | +3.439 |
voic | +3.340 |
bras | +3.322 |
Neg logit contributions | |
Weld | -4.350 |
ammy | -4.339 |
ationally | -4.249 |
netflix | -4.205 |
ittle | -4.180 |
Token | URE |
Token ID | 11335 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
eret | +7.621 |
hell | +7.611 |
cano | +7.107 |
voic | +6.844 |
zek | +6.814 |
Neg logit contributions | |
ammy | -9.372 |
netflix | -9.048 |
Weld | -8.816 |
ittle | -8.793 |
ationally | -8.653 |
Token | HUN |
Token ID | 41041 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
eret | +0.973 |
cano | +0.909 |
hell | +0.891 |
voic | +0.868 |
bras | +0.861 |
Neg logit contributions | |
Weld | -1.073 |
ationally | -1.059 |
ammy | -1.051 |
ittle | -1.013 |
netflix | -1.013 |
Token | TER |
Token ID | 5781 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
eret | +5.079 |
cano | +4.674 |
hell | +4.658 |
tes | +4.564 |
voic | +4.526 |
Neg logit contributions | |
ationally | -6.897 |
ammy | -6.844 |
Weld | -6.723 |
netflix | -6.552 |
ittle | -6.535 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
eret | +1.417 |
cano | +1.324 |
hell | +1.304 |
voic | +1.271 |
bras | +1.260 |
Neg logit contributions | |
Weld | -1.454 |
ationally | -1.440 |
ammy | -1.422 |
ittle | -1.370 |
netflix | -1.367 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Weld | +1.245 |
ationally | +1.209 |
ammy | +1.174 |
netflix | +1.144 |
ittle | +1.133 |
Neg logit contributions | |
eret | -1.586 |
cano | -1.508 |
voic | -1.440 |
hell | -1.439 |
bras | -1.426 |
Token | Railroad |
Token ID | 36289 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
eret | +3.306 |
hell | +3.106 |
cano | +3.092 |
voic | +3.009 |
bras | +2.981 |
Neg logit contributions | |
ammy | -2.460 |
Weld | -2.436 |
ationally | -2.436 |
ittle | -2.361 |
netflix | -2.329 |
Token | Company |
Token ID | 5834 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
eret | +1.899 |
cano | +1.769 |
hell | +1.751 |
voic | +1.689 |
bras | +1.686 |
Neg logit contributions | |
Weld | -2.001 |
ationally | -1.996 |
ammy | -1.970 |
ittle | -1.902 |
netflix | -1.902 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
eret | +2.788 |
cano | +2.584 |
hell | +2.539 |
voic | +2.465 |
bras | +2.452 |
Neg logit contributions | |
Weld | -3.031 |
ammy | -3.019 |
ationally | -3.015 |
ittle | -2.900 |
netflix | -2.887 |
Token | 118 |
Token ID | 19035 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
eret | +1.515 |
cano | +1.396 |
hell | +1.378 |
voic | +1.349 |
bras | +1.331 |
Neg logit contributions | |
Weld | -1.713 |
ationally | -1.697 |
ammy | -1.696 |
ittle | -1.621 |
netflix | -1.614 |
Token | U |
Token ID | 471 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
Weld | +1.246 |
ationally | +1.223 |
ammy | +1.197 |
netflix | +1.150 |
ittle | +1.147 |
Neg logit contributions | |
eret | -1.274 |
cano | -1.199 |
hell | -1.167 |
voic | -1.141 |
bras | -1.128 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
eret | +4.466 |
hell | +4.104 |
cano | +3.979 |
tes | +3.911 |
bras | +3.680 |
Neg logit contributions | |
ammy | -6.818 |
ationally | -6.742 |
Weld | -6.695 |
ittle | -6.615 |
netflix | -6.474 |
Token | S |
Token ID | 50 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
eret | +3.991 |
hell | +3.392 |
tes | +3.347 |
cano | +3.266 |
bras | +3.114 |
Neg logit contributions | |
ammy | -13.034 |
ittle | -12.755 |
netflix | -12.715 |
ationally | -12.685 |
gans | -12.574 |
Token | . |
Token ID | 13 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
eret | +4.395 |
hell | +4.043 |
cano | +3.948 |
tes | +3.733 |
bras | +3.682 |
Neg logit contributions | |
ammy | -6.436 |
ationally | -6.391 |
Weld | -6.328 |
ittle | -6.209 |
netflix | -6.170 |
Token | 39 |
Token ID | 5014 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
eret | +2.791 |
cano | +2.586 |
hell | +2.556 |
bras | +2.444 |
voic | +2.437 |
Neg logit contributions | |
ammy | -3.745 |
Weld | -3.733 |
ationally | -3.729 |
ittle | -3.585 |
netflix | -3.566 |
Token | 4 |
Token ID | 19 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
eret | +3.187 |
hell | +2.912 |
cano | +2.910 |
voic | +2.789 |
bras | +2.769 |
Neg logit contributions | |
ammy | -4.069 |
ationally | -4.067 |
Weld | -4.049 |
ittle | -3.918 |
netflix | -3.917 |
Token | ( |
Token ID | 357 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
eret | +3.537 |
hell | +3.175 |
cano | +3.106 |
voic | +3.028 |
bras | +3.013 |
Neg logit contributions | |
ammy | -4.613 |
ationally | -4.539 |
Weld | -4.525 |
ittle | -4.442 |
netflix | -4.358 |
Token | lesbian |
Token ID | 17834 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Weld | +2.110 |
ationally | +2.084 |
ammy | +2.028 |
ittle | +1.955 |
gans | +1.927 |
Neg logit contributions | |
eret | -2.394 |
cano | -2.315 |
hell | -2.199 |
voic | -2.144 |
bras | -2.129 |
Token | spouses |
Token ID | 30250 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
eret | +1.269 |
cano | +1.175 |
hell | +1.149 |
voic | +1.122 |
bras | +1.111 |
Neg logit contributions | |
Weld | -1.461 |
ationally | -1.441 |
ammy | -1.426 |
netflix | -1.378 |
ittle | -1.373 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Weld | +0.278 |
ationally | +0.274 |
ammy | +0.270 |
netflix | +0.261 |
ittle | +0.261 |
Neg logit contributions | |
eret | -0.248 |
cano | -0.231 |
hell | -0.225 |
voic | -0.219 |
bras | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
eret | +0.386 |
cano | +0.361 |
hell | +0.353 |
voic | +0.345 |
bras | +0.342 |
Neg logit contributions | |
Weld | -0.366 |
ationally | -0.360 |
ammy | -0.354 |
netflix | -0.341 |
ittle | -0.341 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Weld | +0.355 |
ationally | +0.348 |
ammy | +0.340 |
netflix | +0.329 |
ittle | +0.328 |
Neg logit contributions | |
eret | -0.416 |
cano | -0.393 |
hell | -0.380 |
voic | -0.375 |
bras | -0.372 |
Token | Cre |
Token ID | 12443 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
eret | +0.234 |
cano | +0.217 |
hell | +0.213 |
voic | +0.206 |
bras | +0.204 |
Neg logit contributions | |
Weld | -0.266 |
ationally | -0.262 |
ammy | -0.258 |
netflix | -0.249 |
ittle | -0.249 |
Token | ighton |
Token ID | 42993 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
eret | +9.066 |
cano | +8.194 |
hell | +8.173 |
tes | +7.981 |
zek | +7.664 |
Neg logit contributions | |
Weld | -8.622 |
ammy | -8.035 |
netflix | -7.745 |
ittle | -7.563 |
Municip | -7.553 |
Token | University |
Token ID | 2059 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Weld | +0.885 |
ationally | +0.867 |
ammy | +0.846 |
ittle | +0.820 |
netflix | +0.815 |
Neg logit contributions | |
eret | -0.791 |
cano | -0.738 |
hell | -0.715 |
voic | -0.701 |
bras | -0.693 |
Token | in |
Token ID | 287 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
eret | +1.140 |
cano | +1.064 |
hell | +1.044 |
voic | +1.013 |
bras | +1.005 |
Neg logit contributions | |
Weld | -1.167 |
ationally | -1.150 |
ammy | -1.142 |
netflix | -1.108 |
ittle | -1.099 |
Token | Omaha |
Token ID | 37053 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
eret | +1.089 |
cano | +1.020 |
hell | +0.998 |
voic | +0.974 |
bras | +0.966 |
Neg logit contributions | |
Weld | -1.007 |
ationally | -0.991 |
ammy | -0.975 |
netflix | -0.940 |
ittle | -0.938 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
eret | +0.092 |
cano | +0.086 |
hell | +0.084 |
voic | +0.082 |
bras | +0.081 |
Neg logit contributions | |
Weld | -0.089 |
ationally | -0.088 |
ammy | -0.086 |
netflix | -0.083 |
ittle | -0.083 |
Token | My |
Token ID | 2011 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Weld | +0.480 |
ationally | +0.471 |
ammy | +0.460 |
ittle | +0.449 |
netflix | +0.447 |
Neg logit contributions | |
eret | -0.481 |
cano | -0.453 |
hell | -0.441 |
voic | -0.427 |
bras | -0.422 |
Token | c |
Token ID | 66 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Weld | +1.424 |
ationally | +1.403 |
ammy | +1.383 |
netflix | +1.339 |
ittle | +1.338 |
Neg logit contributions | |
eret | -1.169 |
cano | -1.086 |
hell | -1.055 |
voic | -1.033 |
bras | -1.017 |
Token | ob |
Token ID | 672 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
eret | +1.343 |
cano | +1.227 |
hell | +1.206 |
voic | +1.165 |
bras | +1.159 |
Neg logit contributions | |
Weld | -1.962 |
ationally | -1.930 |
ammy | -1.922 |
netflix | -1.856 |
ittle | -1.854 |
Token | acter |
Token ID | 7321 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
eret | +0.887 |
cano | +0.799 |
hell | +0.781 |
voic | +0.733 |
bras | +0.724 |
Neg logit contributions | |
Weld | -1.601 |
ationally | -1.564 |
ammy | -1.553 |
netflix | -1.508 |
ittle | -1.499 |
Token | ium |
Token ID | 1505 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
eret | +2.101 |
hell | +1.776 |
bras | +1.757 |
voic | +1.667 |
cano | +1.620 |
Neg logit contributions | |
ammy | -8.214 |
ationally | -8.111 |
Weld | -8.096 |
netflix | -7.934 |
ittle | -7.821 |
Token | le |
Token ID | 443 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
eret | +3.488 |
bras | +3.273 |
cano | +3.232 |
hell | +3.223 |
voic | +3.175 |
Neg logit contributions | |
ammy | -4.166 |
Weld | -4.110 |
ationally | -4.072 |
netflix | -3.940 |
ittle | -3.919 |
Token | p |
Token ID | 79 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
eret | +7.104 |
cano | +6.972 |
hell | +6.600 |
zek | +6.250 |
voic | +6.202 |
Neg logit contributions | |
Weld | -9.829 |
ationally | -9.603 |
netflix | -9.485 |
ammy | -9.452 |
^^^^ | -9.038 |
Token | ra |
Token ID | 430 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
eret | +4.916 |
hell | +4.647 |
cano | +4.570 |
tes | +4.290 |
sett | +4.270 |
Neg logit contributions | |
Weld | -6.267 |
ationally | -6.233 |
ammy | -6.115 |
netflix | -5.993 |
^^^^ | -5.910 |
Token | e |
Token ID | 68 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
eret | +2.279 |
cano | +2.126 |
hell | +2.090 |
voic | +2.020 |
bras | +2.011 |
Neg logit contributions | |
Weld | -2.200 |
ationally | -2.157 |
ammy | -2.126 |
netflix | -2.053 |
ittle | -2.049 |
Token | .[ |
Token ID | 3693 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
eret | +5.634 |
cano | +5.225 |
hell | +5.211 |
bras | +5.004 |
voic | +4.963 |
Neg logit contributions | |
Weld | -6.271 |
ationally | -6.164 |
ammy | -6.159 |
netflix | -5.839 |
ittle | -5.817 |
Token | 116 |
Token ID | 18298 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Weld | +1.269 |
ationally | +1.250 |
ammy | +1.227 |
netflix | +1.178 |
ittle | +1.177 |
Neg logit contributions | |
eret | -1.622 |
cano | -1.525 |
hell | -1.484 |
voic | -1.465 |
bras | -1.456 |
Token | of |
Token ID | 286 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Weld | +0.855 |
ationally | +0.842 |
ammy | +0.824 |
ittle | +0.802 |
netflix | +0.798 |
Neg logit contributions | |
eret | -0.779 |
cano | -0.723 |
hell | -0.706 |
voic | -0.689 |
bras | -0.682 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Weld | +0.086 |
ationally | +0.085 |
ammy | +0.083 |
ittle | +0.081 |
netflix | +0.081 |
Neg logit contributions | |
eret | -0.080 |
cano | -0.075 |
hell | -0.072 |
voic | -0.070 |
bras | -0.069 |
Token | vagina |
Token ID | 26150 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
eret | +0.655 |
cano | +0.604 |
hell | +0.588 |
voic | +0.570 |
bras | +0.565 |
Neg logit contributions | |
Weld | -0.906 |
ationally | -0.894 |
ammy | -0.882 |
netflix | -0.856 |
ittle | -0.854 |
Token | and |
Token ID | 290 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
eret | +0.770 |
cano | +0.718 |
hell | +0.703 |
voic | +0.684 |
bras | +0.679 |
Neg logit contributions | |
Weld | -0.810 |
ationally | -0.798 |
ammy | -0.788 |
netflix | -0.761 |
ittle | -0.758 |
Token | restricts |
Token ID | 47075 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
eret | +2.003 |
cano | +1.856 |
hell | +1.812 |
voic | +1.772 |
bras | +1.771 |
Neg logit contributions | |
Weld | -2.371 |
ationally | -2.353 |
ammy | -2.325 |
netflix | -2.254 |
ittle | -2.228 |
Token | path |
Token ID | 3108 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
eret | +1.839 |
cano | +1.697 |
hell | +1.662 |
voic | +1.624 |
bras | +1.614 |
Neg logit contributions | |
Weld | -2.125 |
ationally | -2.105 |
ammy | -2.082 |
netflix | -2.009 |
ittle | -1.995 |
Token | ogen |
Token ID | 6644 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
eret | +7.239 |
hell | +6.813 |
cano | +6.627 |
voic | +6.374 |
tes | +6.336 |
Neg logit contributions | |
ammy | -9.709 |
Weld | -9.529 |
ationally | -9.345 |
netflix | -9.307 |
gerald | -8.972 |
Token | growth |
Token ID | 3349 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
eret | +2.348 |
cano | +2.180 |
hell | +2.164 |
voic | +2.102 |
bras | +2.073 |
Neg logit contributions | |
Weld | -2.504 |
ationally | -2.469 |
ammy | -2.467 |
netflix | -2.371 |
ittle | -2.345 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
eret | +3.823 |
hell | +3.552 |
cano | +3.552 |
bras | +3.398 |
voic | +3.352 |
Neg logit contributions | |
Weld | -4.761 |
ammy | -4.757 |
ationally | -4.669 |
netflix | -4.595 |
ittle | -4.470 |
Token | A |
Token ID | 317 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
eret | +2.220 |
cano | +2.060 |
hell | +2.037 |
bras | +1.973 |
voic | +1.972 |
Neg logit contributions | |
ationally | -2.190 |
Weld | -2.181 |
ammy | -2.167 |
netflix | -2.087 |
ittle | -2.074 |
Token | � |
Token ID | 564 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
eret | +1.775 |
cano | +1.648 |
hell | +1.622 |
voic | +1.584 |
bras | +1.574 |
Neg logit contributions | |
Weld | -1.786 |
ationally | -1.756 |
ammy | -1.735 |
netflix | -1.672 |
ittle | -1.666 |
Token | � |
Token ID | 18074 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
eret | +1.823 |
cano | +1.684 |
hell | +1.650 |
voic | +1.612 |
bras | +1.588 |
Neg logit contributions | |
Weld | -2.177 |
ationally | -2.158 |
ammy | -2.135 |
netflix | -2.071 |
ittle | -2.055 |
Token | � |
Token ID | 228 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
eret | +2.042 |
cano | +1.894 |
hell | +1.877 |
voic | +1.829 |
bras | +1.803 |
Neg logit contributions | |
Weld | -1.881 |
ationally | -1.855 |
ammy | -1.834 |
netflix | -1.776 |
ittle | -1.759 |
Token | � |
Token ID | 138 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
eret | +0.520 |
cano | +0.479 |
hell | +0.465 |
voic | +0.450 |
bras | +0.445 |
Neg logit contributions | |
Weld | -0.766 |
ationally | -0.756 |
ammy | -0.746 |
netflix | -0.724 |
ittle | -0.724 |
Token | � |
Token ID | 116 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
eret | +1.066 |
cano | +0.996 |
hell | +0.975 |
voic | +0.950 |
bras | +0.943 |
Neg logit contributions | |
Weld | -1.085 |
ationally | -1.069 |
ammy | -1.058 |
netflix | -1.024 |
ittle | -1.019 |
Token | ε |
Token ID | 30950 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
eret | +1.631 |
cano | +1.478 |
hell | +1.455 |
voic | +1.400 |
bras | +1.377 |
Neg logit contributions | |
Weld | -2.610 |
ationally | -2.574 |
ammy | -2.553 |
netflix | -2.489 |
ittle | -2.472 |
Token | � |
Token ID | 45495 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
eret | +2.756 |
cano | +2.487 |
hell | +2.464 |
voic | +2.356 |
bras | +2.320 |
Neg logit contributions | |
Weld | -4.412 |
ationally | -4.364 |
ammy | -4.343 |
netflix | -4.254 |
ittle | -4.192 |
Token | � |
Token ID | 115 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
eret | +8.523 |
hell | +7.912 |
cano | +7.873 |
bras | +7.872 |
tes | +7.870 |
Neg logit contributions | |
ammy | -8.253 |
ationally | -8.118 |
netflix | -8.080 |
Weld | -7.987 |
ittle | -7.404 |
Token | ρ |
Token ID | 33643 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
eret | +3.370 |
hell | +3.038 |
cano | +3.020 |
voic | +2.951 |
bras | +2.917 |
Neg logit contributions | |
Weld | -4.992 |
ammy | -4.945 |
ationally | -4.940 |
netflix | -4.824 |
ittle | -4.742 |
Token | ε |
Token ID | 30950 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
eret | +3.925 |
cano | +3.562 |
hell | +3.559 |
voic | +3.504 |
bras | +3.446 |
Neg logit contributions | |
Weld | -5.233 |
ammy | -5.208 |
ationally | -5.193 |
netflix | -5.050 |
ittle | -4.959 |
Token | ι |
Token ID | 29945 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
eret | +2.764 |
cano | +2.504 |
hell | +2.477 |
voic | +2.387 |
bras | +2.350 |
Neg logit contributions | |
Weld | -4.226 |
ammy | -4.191 |
ationally | -4.189 |
netflix | -4.081 |
ittle | -4.024 |
Token | � |
Token ID | 7377 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
eret | +3.603 |
cano | +3.266 |
hell | +3.256 |
voic | +3.172 |
bras | +3.108 |
Neg logit contributions | |
Weld | -5.775 |
ammy | -5.755 |
ationally | -5.740 |
netflix | -5.581 |
ittle | -5.466 |
Token | about |
Token ID | 546 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
eret | +3.096 |
cano | +2.872 |
hell | +2.863 |
voic | +2.814 |
bras | +2.791 |
Neg logit contributions | |
Weld | -3.180 |
ationally | -3.175 |
ammy | -3.149 |
netflix | -3.011 |
ittle | -2.991 |
Token | as |
Token ID | 355 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
eret | +1.980 |
cano | +1.837 |
hell | +1.826 |
voic | +1.779 |
bras | +1.767 |
Neg logit contributions | |
Weld | -2.187 |
ationally | -2.164 |
ammy | -2.146 |
netflix | -2.075 |
ittle | -2.045 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
eret | +2.695 |
cano | +2.524 |
hell | +2.467 |
voic | +2.439 |
bras | +2.424 |
Neg logit contributions | |
Weld | -2.658 |
ationally | -2.649 |
ammy | -2.593 |
ittle | -2.510 |
netflix | -2.509 |
Token | as |
Token ID | 355 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
Weld | +1.138 |
ationally | +1.106 |
ammy | +1.084 |
netflix | +1.041 |
ittle | +1.040 |
Neg logit contributions | |
eret | -1.554 |
cano | -1.463 |
hell | -1.428 |
voic | -1.401 |
bras | -1.386 |
Token | could |
Token ID | 714 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
eret | +3.291 |
cano | +3.086 |
hell | +3.032 |
voic | +2.996 |
bras | +2.974 |
Neg logit contributions | |
ationally | -3.430 |
ammy | -3.388 |
Weld | -3.382 |
ittle | -3.263 |
netflix | -3.231 |
Token | be |
Token ID | 307 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
eret | +4.858 |
hell | +4.432 |
cano | +4.389 |
bras | +4.265 |
voic | +4.203 |
Neg logit contributions | |
Weld | -6.861 |
ammy | -6.851 |
ationally | -6.556 |
ittle | -6.473 |
netflix | -6.382 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
eret | +6.821 |
hell | +6.413 |
bras | +6.379 |
voic | +6.319 |
cano | +6.274 |
Neg logit contributions | |
ammy | -9.564 |
ationally | -9.451 |
netflix | -9.068 |
Weld | -9.065 |
ittle | -8.994 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
eret | +1.402 |
cano | +1.315 |
hell | +1.288 |
voic | +1.260 |
bras | +1.252 |
Neg logit contributions | |
Weld | -1.414 |
ationally | -1.408 |
ammy | -1.393 |
ittle | -1.336 |
netflix | -1.336 |
Token | certainly |
Token ID | 3729 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
eret | +2.289 |
cano | +2.136 |
hell | +2.100 |
voic | +2.069 |
bras | +2.047 |
Neg logit contributions | |
ationally | -2.429 |
ammy | -2.406 |
Weld | -2.404 |
netflix | -2.308 |
ittle | -2.302 |
Token | will |
Token ID | 481 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
eret | +1.618 |
cano | +1.511 |
hell | +1.481 |
voic | +1.461 |
bras | +1.453 |
Neg logit contributions | |
ationally | -1.744 |
Weld | -1.734 |
ammy | -1.707 |
ittle | -1.646 |
netflix | -1.645 |
Token | look |
Token ID | 804 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
eret | +0.925 |
cano | +0.858 |
hell | +0.839 |
voic | +0.822 |
bras | +0.813 |
Neg logit contributions | |
Weld | -1.036 |
ationally | -1.021 |
ammy | -1.005 |
netflix | -0.971 |
ittle | -0.967 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
eret | +0.962 |
cano | +0.900 |
hell | +0.881 |
voic | +0.861 |
bras | +0.854 |
Neg logit contributions | |
Weld | -0.876 |
ationally | -0.860 |
ammy | -0.848 |
netflix | -0.817 |
ittle | -0.813 |
Token | body |
Token ID | 1767 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Weld | +0.804 |
ationally | +0.792 |
ammy | +0.781 |
ittle | +0.752 |
netflix | +0.748 |
Neg logit contributions | |
eret | -0.823 |
cano | -0.771 |
hell | -0.753 |
voic | -0.731 |
bras | -0.725 |
Token | � |
Token ID | 447 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
eret | +2.601 |
cano | +2.436 |
hell | +2.383 |
voic | +2.322 |
bras | +2.308 |
Neg logit contributions | |
Weld | -2.496 |
ationally | -2.423 |
ammy | -2.403 |
netflix | -2.321 |
ittle | -2.292 |
Token | � |
Token ID | 247 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
eret | +0.517 |
cano | +0.482 |
hell | +0.471 |
voic | +0.459 |
bras | +0.454 |
Neg logit contributions | |
Weld | -0.544 |
ationally | -0.536 |
ammy | -0.529 |
netflix | -0.511 |
ittle | -0.509 |
Token | s |
Token ID | 82 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Weld | +0.285 |
ationally | +0.282 |
ammy | +0.278 |
ittle | +0.271 |
netflix | +0.271 |
Neg logit contributions | |
eret | -0.154 |
cano | -0.139 |
hell | -0.135 |
voic | -0.130 |
bras | -0.129 |
Token | natural |
Token ID | 3288 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
eret | +1.265 |
cano | +1.187 |
hell | +1.162 |
voic | +1.136 |
bras | +1.129 |
Neg logit contributions | |
Weld | -1.129 |
ationally | -1.106 |
ammy | -1.091 |
netflix | -1.053 |
ittle | -1.048 |
Token | shifts |
Token ID | 15381 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
eret | +7.819 |
voic | +7.163 |
cano | +7.148 |
bras | +7.067 |
hell | +6.996 |
Neg logit contributions | |
Weld | -8.661 |
ammy | -8.567 |
ationally | -8.388 |
netflix | -8.199 |
ittle | -7.978 |
Token | between |
Token ID | 1022 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
eret | +0.326 |
cano | +0.303 |
hell | +0.297 |
voic | +0.288 |
bras | +0.286 |
Neg logit contributions | |
Weld | -0.345 |
ationally | -0.339 |
ammy | -0.335 |
netflix | -0.323 |
ittle | -0.322 |
Token | sympathetic |
Token ID | 22335 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
eret | +1.352 |
cano | +1.260 |
hell | +1.233 |
voic | +1.204 |
bras | +1.195 |
Neg logit contributions | |
Weld | -1.370 |
ationally | -1.348 |
ammy | -1.330 |
netflix | -1.285 |
ittle | -1.280 |
Token | ( |
Token ID | 357 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
eret | +0.098 |
cano | +0.091 |
hell | +0.089 |
voic | +0.087 |
bras | +0.086 |
Neg logit contributions | |
Weld | -0.099 |
ationally | -0.097 |
ammy | -0.096 |
netflix | -0.093 |
ittle | -0.092 |
Token | � |
Token ID | 447 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
Weld | +1.741 |
ationally | +1.738 |
ammy | +1.716 |
ittle | +1.667 |
netflix | +1.666 |
Neg logit contributions | |
eret | -1.476 |
cano | -1.382 |
hell | -1.323 |
voic | -1.319 |
bras | -1.313 |
Token | golden |
Token ID | 10861 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
Weld | +4.346 |
ationally | +4.251 |
ittle | +4.085 |
ammy | +3.990 |
netflix | +3.893 |
Neg logit contributions | |
eret | -5.364 |
cano | -4.951 |
hell | -4.807 |
voic | -4.662 |
zek | -4.612 |
Token | brown |
Token ID | 7586 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Weld | +4.353 |
ationally | +4.154 |
ittle | +4.063 |
ammy | +4.025 |
netflix | +3.850 |
Neg logit contributions | |
eret | -6.327 |
cano | -5.976 |
hell | -5.751 |
bras | -5.660 |
voic | -5.609 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
Weld | +3.411 |
ationally | +3.330 |
ammy | +3.228 |
ittle | +3.200 |
netflix | +3.144 |
Neg logit contributions | |
eret | -3.569 |
cano | -3.343 |
hell | -3.252 |
voic | -3.155 |
bras | -3.123 |
Token | These |
Token ID | 2312 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Weld | +3.543 |
ationally | +3.295 |
ammy | +3.242 |
ittle | +3.180 |
netflix | +3.130 |
Neg logit contributions | |
eret | -3.977 |
cano | -3.694 |
hell | -3.609 |
voic | -3.560 |
bras | -3.467 |
Token | are |
Token ID | 389 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
eret | +0.614 |
cano | +0.576 |
hell | +0.564 |
voic | +0.552 |
bras | +0.547 |
Neg logit contributions | |
Weld | -0.591 |
ationally | -0.584 |
ammy | -0.575 |
netflix | -0.554 |
ittle | -0.550 |
Token | lightly |
Token ID | 15376 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
Weld | +2.054 |
ationally | +2.009 |
ammy | +1.978 |
ittle | +1.916 |
netflix | +1.891 |
Neg logit contributions | |
eret | -2.145 |
cano | -1.983 |
hell | -1.944 |
voic | -1.875 |
bras | -1.862 |
Token | fried |
Token ID | 23018 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
Weld | +5.868 |
ittle | +5.620 |
ationally | +5.595 |
ammy | +5.513 |
netflix | +5.305 |
Neg logit contributions | |
eret | -7.797 |
cano | -7.318 |
hell | -6.966 |
zek | -6.624 |
voic | -6.621 |
Token | and |
Token ID | 290 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
Weld | +3.704 |
ationally | +3.577 |
ammy | +3.492 |
ittle | +3.422 |
netflix | +3.377 |
Neg logit contributions | |
eret | -3.992 |
cano | -3.728 |
hell | -3.587 |
voic | -3.497 |
tes | -3.436 |
Token | not |
Token ID | 407 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Weld | +4.492 |
ationally | +4.317 |
ammy | +4.278 |
ittle | +4.226 |
netflix | +4.101 |
Neg logit contributions | |
eret | -5.150 |
cano | -4.763 |
hell | -4.655 |
bras | -4.444 |
voic | -4.435 |
Token | deep |
Token ID | 2769 |
Feature activation | +9.71e+00 |
Pos logit contributions | |
ationally | +4.426 |
Weld | +4.426 |
ammy | +4.248 |
ittle | +4.224 |
netflix | +4.062 |
Neg logit contributions | |
eret | -5.588 |
cano | -5.240 |
hell | -5.035 |
bras | -4.879 |
voic | -4.864 |
Token | fried |
Token ID | 23018 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
Weld | +4.631 |
ationally | +4.549 |
ammy | +4.380 |
ittle | +4.139 |
netflix | +4.103 |
Neg logit contributions | |
eret | -8.644 |
cano | -8.146 |
hell | -7.977 |
tes | -7.845 |
voic | -7.771 |
Token | 170 |
Token ID | 17279 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
eret | +2.592 |
cano | +2.409 |
hell | +2.375 |
voic | +2.302 |
bras | +2.298 |
Neg logit contributions | |
Weld | -2.522 |
ationally | -2.505 |
ammy | -2.496 |
ittle | -2.365 |
netflix | -2.364 |
Token | x |
Token ID | 2124 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
eret | +0.215 |
cano | +0.200 |
hell | +0.195 |
voic | +0.190 |
bras | +0.189 |
Neg logit contributions | |
Weld | -0.227 |
ationally | -0.223 |
ammy | -0.220 |
netflix | -0.212 |
ittle | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
eret | +0.904 |
cano | +0.840 |
hell | +0.823 |
voic | +0.798 |
bras | +0.791 |
Neg logit contributions | |
Weld | -0.997 |
ationally | -0.983 |
ammy | -0.970 |
netflix | -0.936 |
ittle | -0.936 |
Token | x |
Token ID | 87 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Weld | +0.584 |
ationally | +0.580 |
ammy | +0.564 |
netflix | +0.542 |
ittle | +0.538 |
Neg logit contributions | |
eret | -0.943 |
cano | -0.898 |
voic | -0.873 |
hell | -0.871 |
bras | -0.867 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
Weld | +2.265 |
ationally | +2.210 |
ammy | +2.136 |
netflix | +2.086 |
ittle | +2.071 |
Neg logit contributions | |
eret | -2.564 |
cano | -2.441 |
voic | -2.349 |
bras | -2.324 |
hell | -2.312 |
Token | x |
Token ID | 87 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
ationally | +3.317 |
Weld | +3.209 |
ammy | +3.179 |
gans | +3.038 |
netflix | +3.028 |
Neg logit contributions | |
eret | -7.376 |
voic | -7.267 |
bras | -7.259 |
cano | -7.198 |
notor | -7.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
Weld | +5.309 |
ationally | +4.967 |
ammy | +4.824 |
^^^^ | +4.780 |
ittle | +4.761 |
Neg logit contributions | |
eret | -7.827 |
notor | -7.579 |
cano | -7.575 |
voic | -7.484 |
bras | -7.403 |
Token | 149 |
Token ID | 19442 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Weld | +4.422 |
ittle | +4.373 |
ammy | +4.003 |
^^^^ | +3.980 |
ationally | +3.933 |
Neg logit contributions | |
eret | -14.082 |
cano | -13.656 |
voic | -13.214 |
bras | -13.173 |
hell | -13.150 |
Token | 110 |
Token ID | 9796 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
eret | +1.616 |
cano | +1.512 |
hell | +1.489 |
voic | +1.449 |
bras | +1.428 |
Neg logit contributions | |
Weld | -1.637 |
ationally | -1.633 |
ammy | -1.610 |
ittle | -1.554 |
netflix | -1.545 |
Token | 22 |
Token ID | 1828 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Weld | +2.450 |
ationally | +2.378 |
ammy | +2.316 |
netflix | +2.264 |
gans | +2.248 |
Neg logit contributions | |
eret | -2.611 |
cano | -2.455 |
voic | -2.358 |
hell | -2.350 |
bras | -2.319 |
Token | 26 |
Token ID | 2075 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Weld | +2.171 |
ationally | +2.097 |
ammy | +2.043 |
netflix | +1.987 |
ittle | +1.982 |
Neg logit contributions | |
eret | -2.225 |
cano | -2.093 |
voic | -1.987 |
hell | -1.985 |
bras | -1.960 |
Token |
|
Token ID | 198 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
eret | +0.276 |
cano | +0.259 |
hell | +0.252 |
voic | +0.247 |
bras | +0.245 |
Neg logit contributions | |
Weld | -0.248 |
ationally | -0.243 |
ammy | -0.239 |
netflix | -0.230 |
ittle | -0.230 |
Token | Read |
Token ID | 5569 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
eret | +0.574 |
cano | +0.530 |
hell | +0.518 |
voic | +0.500 |
bras | +0.495 |
Neg logit contributions | |
Weld | -0.770 |
ationally | -0.760 |
ammy | -0.751 |
ittle | -0.726 |
netflix | -0.726 |
Token | More |
Token ID | 3125 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
eret | +1.304 |
cano | +1.208 |
hell | +1.191 |
voic | +1.150 |
bras | +1.141 |
Neg logit contributions | |
Weld | -1.455 |
ationally | -1.450 |
ammy | -1.438 |
netflix | -1.383 |
ittle | -1.381 |
Token | About |
Token ID | 7994 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
Weld | +3.596 |
ationally | +3.400 |
ammy | +3.317 |
gans | +3.188 |
ittle | +3.160 |
Neg logit contributions | |
eret | -3.826 |
cano | -3.518 |
hell | -3.443 |
voic | -3.408 |
bras | -3.361 |
Token | Dw |
Token ID | 19113 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
Weld | +5.057 |
ationally | +4.565 |
ammy | +4.362 |
Municip | +4.280 |
gans | +4.270 |
Neg logit contributions | |
eret | -6.595 |
cano | -6.104 |
voic | -6.075 |
hell | -6.028 |
bras | -5.879 |
Token | ark |
Token ID | 668 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
ationally | +3.199 |
ammy | +3.122 |
Weld | +3.122 |
netflix | +2.970 |
ittle | +2.929 |
Neg logit contributions | |
eret | -5.795 |
voic | -5.612 |
cano | -5.558 |
hell | -5.453 |
bras | -5.433 |
Token | adh |
Token ID | 24411 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ammy | +5.589 |
ationally | +5.431 |
ittle | +5.131 |
Weld | +5.093 |
arta | +4.866 |
Neg logit contributions | |
eret | -7.847 |
bras | -7.547 |
voic | -7.520 |
cano | -7.513 |
hell | -7.226 |
Token | ish |
Token ID | 680 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
eret | +0.320 |
cano | +0.298 |
hell | +0.291 |
voic | +0.283 |
bras | +0.281 |
Neg logit contributions | |
Weld | -0.347 |
ationally | -0.342 |
ammy | -0.337 |
ittle | -0.325 |
netflix | -0.325 |
Token | Temple |
Token ID | 10857 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
eret | +1.663 |
cano | +1.469 |
hell | +1.432 |
voic | +1.330 |
bras | +1.315 |
Neg logit contributions | |
ationally | -3.722 |
Weld | -3.710 |
ammy | -3.666 |
netflix | -3.607 |
ittle | -3.586 |
Token | Here |
Token ID | 3423 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
eret | +3.142 |
hell | +2.856 |
cano | +2.782 |
bras | +2.550 |
tes | +2.530 |
Neg logit contributions | |
ationally | -5.631 |
ammy | -5.609 |
Weld | -5.528 |
netflix | -5.458 |
ittle | -5.413 |
Token |
|
Token ID | 198 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Weld | +0.451 |
ationally | +0.443 |
ammy | +0.436 |
netflix | +0.420 |
ittle | +0.420 |
Neg logit contributions | |
eret | -0.490 |
cano | -0.459 |
hell | -0.448 |
voic | -0.438 |
bras | -0.435 |
Token | proven |
Token ID | 42874 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
eret | +3.350 |
hell | +3.156 |
cano | +3.134 |
tes | +2.934 |
voic | +2.931 |
Neg logit contributions | |
Weld | -4.040 |
ationally | -3.901 |
ammy | -3.832 |
ittle | -3.773 |
netflix | -3.694 |
Token | oil |
Token ID | 3056 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
eret | +1.170 |
cano | +1.101 |
hell | +1.082 |
voic | +1.063 |
bras | +1.053 |
Neg logit contributions | |
Weld | -0.898 |
ationally | -0.885 |
ammy | -0.874 |
netflix | -0.839 |
ittle | -0.837 |
Token | reserves |
Token ID | 14072 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
eret | +3.114 |
cano | +2.860 |
hell | +2.705 |
voic | +2.662 |
bras | +2.647 |
Neg logit contributions | |
Weld | -6.238 |
ationally | -6.180 |
ammy | -6.159 |
netflix | -6.023 |
ittle | -5.997 |
Token | : |
Token ID | 25 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
eret | +3.436 |
cano | +3.262 |
hell | +3.204 |
voic | +3.071 |
bras | +3.050 |
Neg logit contributions | |
Weld | -4.004 |
ationally | -3.934 |
ammy | -3.875 |
ittle | -3.773 |
netflix | -3.757 |
Token | 140 |
Token ID | 12713 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
eret | +2.074 |
cano | +1.934 |
hell | +1.888 |
voic | +1.837 |
bras | +1.804 |
Neg logit contributions | |
Weld | -3.027 |
ationally | -3.008 |
ammy | -2.985 |
netflix | -2.888 |
ittle | -2.886 |
Token | billion |
Token ID | 2997 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
eret | +1.593 |
cano | +1.490 |
hell | +1.461 |
voic | +1.426 |
bras | +1.419 |
Neg logit contributions | |
Weld | -1.635 |
ationally | -1.614 |
ammy | -1.586 |
netflix | -1.554 |
ittle | -1.533 |
Token | barrels |
Token ID | 17907 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Weld | +4.124 |
ationally | +3.825 |
ammy | +3.539 |
ittle | +3.401 |
netflix | +3.378 |
Neg logit contributions | |
eret | -9.225 |
cano | -8.899 |
hell | -8.611 |
zek | -8.439 |
voic | -8.419 |
Token | ), |
Token ID | 828 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
eret | +3.702 |
cano | +3.515 |
hell | +3.436 |
bras | +3.328 |
voic | +3.327 |
Neg logit contributions | |
Weld | -4.666 |
ationally | -4.662 |
ammy | -4.616 |
netflix | -4.490 |
ittle | -4.433 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
eret | +4.577 |
hell | +4.158 |
cano | +4.060 |
voic | +4.046 |
bras | +3.915 |
Neg logit contributions | |
ammy | -6.191 |
ationally | -6.129 |
Weld | -6.097 |
netflix | -5.983 |
ittle | -5.952 |
Token | pedd |
Token ID | 36145 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Weld | +0.848 |
ationally | +0.833 |
ammy | +0.813 |
netflix | +0.785 |
ittle | +0.784 |
Neg logit contributions | |
eret | -0.977 |
cano | -0.916 |
hell | -0.894 |
voic | -0.872 |
bras | -0.866 |
Token | led |
Token ID | 992 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
eret | +2.749 |
cano | +2.534 |
hell | +2.505 |
bras | +2.385 |
voic | +2.382 |
Neg logit contributions | |
Weld | -3.085 |
ationally | -3.025 |
ammy | -3.006 |
netflix | -2.923 |
ittle | -2.868 |
Token | x |
Token ID | 2124 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
eret | +0.060 |
cano | +0.056 |
hell | +0.054 |
voic | +0.053 |
bras | +0.052 |
Neg logit contributions | |
Weld | -0.062 |
ationally | -0.061 |
ammy | -0.060 |
netflix | -0.058 |
ittle | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
eret | +1.487 |
cano | +1.374 |
hell | +1.357 |
voic | +1.302 |
bras | +1.292 |
Neg logit contributions | |
Weld | -1.722 |
ationally | -1.703 |
ammy | -1.687 |
ittle | -1.624 |
netflix | -1.622 |
Token | x |
Token ID | 87 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Weld | +0.186 |
ationally | +0.183 |
ammy | +0.179 |
netflix | +0.172 |
ittle | +0.171 |
Neg logit contributions | |
eret | -0.288 |
cano | -0.273 |
hell | -0.266 |
voic | -0.264 |
bras | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
Weld | +1.565 |
ationally | +1.530 |
ammy | +1.489 |
netflix | +1.451 |
ittle | +1.441 |
Neg logit contributions | |
eret | -1.681 |
cano | -1.590 |
voic | -1.525 |
hell | -1.516 |
bras | -1.508 |
Token | x |
Token ID | 87 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
ationally | +2.320 |
Weld | +2.284 |
ammy | +2.233 |
netflix | +2.157 |
ittle | +2.115 |
Neg logit contributions | |
eret | -4.519 |
cano | -4.356 |
voic | -4.335 |
bras | -4.318 |
hell | -4.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
Weld | +4.332 |
ationally | +4.099 |
ammy | +3.992 |
ittle | +3.866 |
gans | +3.859 |
Neg logit contributions | |
eret | -5.918 |
cano | -5.741 |
notor | -5.654 |
voic | -5.603 |
bras | -5.597 |
Token | 154 |
Token ID | 21526 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Weld | +5.632 |
ammy | +5.334 |
ationally | +5.310 |
ittle | +5.277 |
uld | +4.845 |
Neg logit contributions | |
bras | -12.148 |
eret | -11.905 |
cano | -11.881 |
notor | -11.752 |
contrace | -11.738 |
Token | 109 |
Token ID | 16003 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
eret | +2.099 |
cano | +1.971 |
hell | +1.947 |
voic | +1.896 |
bras | +1.866 |
Neg logit contributions | |
Weld | -2.217 |
ationally | -2.215 |
ammy | -2.191 |
ittle | -2.114 |
netflix | -2.097 |
Token | 77 |
Token ID | 3324 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
eret | +0.984 |
cano | +0.915 |
hell | +0.899 |
voic | +0.868 |
bras | +0.861 |
Neg logit contributions | |
Weld | -1.091 |
ationally | -1.079 |
ammy | -1.064 |
ittle | -1.026 |
netflix | -1.025 |
Token | 39 |
Token ID | 2670 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
eret | +0.587 |
cano | +0.546 |
hell | +0.536 |
voic | +0.519 |
bras | +0.514 |
Neg logit contributions | |
Weld | -0.654 |
ationally | -0.646 |
ammy | -0.638 |
netflix | -0.615 |
ittle | -0.615 |
Token | x |
Token ID | 2124 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
eret | +0.301 |
cano | +0.281 |
hell | +0.274 |
voic | +0.267 |
bras | +0.265 |
Neg logit contributions | |
Weld | -0.321 |
ationally | -0.316 |
ammy | -0.311 |
netflix | -0.300 |
ittle | -0.300 |
Token | ials |
Token ID | 8231 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
eret | +0.617 |
cano | +0.554 |
hell | +0.537 |
voic | +0.518 |
bras | +0.506 |
Neg logit contributions | |
Weld | -1.232 |
ationally | -1.218 |
ammy | -1.207 |
netflix | -1.175 |
ittle | -1.174 |
Token | / |
Token ID | 14 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Weld | +2.519 |
ationally | +2.468 |
ammy | +2.427 |
ittle | +2.341 |
netflix | +2.336 |
Neg logit contributions | |
eret | -2.564 |
cano | -2.414 |
hell | -2.323 |
bras | -2.263 |
voic | -2.247 |
Token | Deb |
Token ID | 16587 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Weld | +0.404 |
ationally | +0.398 |
ammy | +0.391 |
netflix | +0.377 |
ittle | +0.377 |
Neg logit contributions | |
eret | -0.376 |
cano | -0.351 |
hell | -0.341 |
bras | -0.332 |
voic | -0.331 |
Token | ate |
Token ID | 378 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Weld | +0.103 |
ationally | +0.101 |
ammy | +0.099 |
netflix | +0.096 |
ittle | +0.095 |
Neg logit contributions | |
eret | -0.103 |
cano | -0.096 |
hell | -0.094 |
voic | -0.091 |
bras | -0.091 |
Token | Op |
Token ID | 8670 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Weld | +2.158 |
ationally | +2.108 |
ammy | +2.055 |
ittle | +1.986 |
netflix | +1.969 |
Neg logit contributions | |
eret | -2.117 |
cano | -1.983 |
hell | -1.925 |
bras | -1.854 |
voic | -1.847 |
Token | in |
Token ID | 259 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
Weld | +1.229 |
ationally | +1.208 |
ammy | +1.181 |
ittle | +1.134 |
netflix | +1.123 |
Neg logit contributions | |
eret | -1.517 |
cano | -1.437 |
hell | -1.394 |
voic | -1.356 |
bras | -1.352 |
Token | ions |
Token ID | 507 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Weld | +2.246 |
ationally | +2.188 |
ammy | +2.059 |
ittle | +2.033 |
netflix | +1.931 |
Neg logit contributions | |
eret | -4.948 |
cano | -4.740 |
bras | -4.561 |
hell | -4.555 |
voic | -4.506 |
Token | expressed |
Token ID | 6241 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Weld | +1.591 |
ationally | +1.561 |
ammy | +1.522 |
ittle | +1.472 |
netflix | +1.463 |
Neg logit contributions | |
eret | -1.581 |
cano | -1.477 |
hell | -1.431 |
bras | -1.384 |
voic | -1.384 |
Token | in |
Token ID | 287 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
eret | +0.440 |
cano | +0.408 |
hell | +0.399 |
voic | +0.388 |
bras | +0.382 |
Neg logit contributions | |
Weld | -0.534 |
ationally | -0.525 |
ammy | -0.519 |
netflix | -0.503 |
ittle | -0.501 |
Token | USA |
Token ID | 4916 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
eret | +1.750 |
cano | +1.615 |
hell | +1.584 |
voic | +1.562 |
bras | +1.535 |
Neg logit contributions | |
Weld | -1.847 |
ationally | -1.827 |
ammy | -1.807 |
netflix | -1.757 |
ittle | -1.736 |
Token | TODAY |
Token ID | 20092 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Weld | +1.164 |
ationally | +1.148 |
ammy | +1.125 |
ittle | +1.095 |
netflix | +1.085 |
Neg logit contributions | |
eret | -0.978 |
cano | -0.908 |
hell | -0.886 |
voic | -0.857 |
bras | -0.853 |
Token | makes |
Token ID | 1838 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
eret | +2.498 |
cano | +2.342 |
hell | +2.303 |
voic | +2.243 |
bras | +2.230 |
Neg logit contributions | |
Weld | -2.673 |
ationally | -2.640 |
ammy | -2.606 |
netflix | -2.535 |
ittle | -2.496 |
Token | a |
Token ID | 257 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
eret | +0.268 |
cano | +0.250 |
hell | +0.244 |
voic | +0.237 |
bras | +0.235 |
Neg logit contributions | |
Weld | -0.294 |
ationally | -0.290 |
ammy | -0.285 |
netflix | -0.276 |
ittle | -0.275 |
Token | great |
Token ID | 1049 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Weld | +0.442 |
ationally | +0.433 |
ammy | +0.426 |
netflix | +0.411 |
ittle | +0.409 |
Neg logit contributions | |
eret | -0.472 |
cano | -0.446 |
hell | -0.432 |
voic | -0.420 |
bras | -0.418 |
Token | case |
Token ID | 1339 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
eret | +2.496 |
cano | +2.325 |
hell | +2.282 |
voic | +2.275 |
bras | +2.207 |
Neg logit contributions | |
ationally | -2.365 |
Weld | -2.362 |
ammy | -2.324 |
netflix | -2.256 |
ittle | -2.248 |
Token | for |
Token ID | 329 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
eret | +1.443 |
cano | +1.331 |
hell | +1.294 |
voic | +1.266 |
bras | +1.238 |
Neg logit contributions | |
Weld | -1.899 |
ationally | -1.871 |
ammy | -1.851 |
netflix | -1.796 |
ittle | -1.785 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Weld | +0.139 |
ationally | +0.136 |
ammy | +0.134 |
netflix | +0.130 |
ittle | +0.130 |
Neg logit contributions | |
eret | -0.135 |
cano | -0.126 |
hell | -0.123 |
voic | -0.120 |
bras | -0.119 |
Token | N |
Token ID | 399 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Weld | +1.490 |
ationally | +1.454 |
ammy | +1.445 |
ittle | +1.378 |
netflix | +1.376 |
Neg logit contributions | |
eret | -1.538 |
cano | -1.430 |
hell | -1.403 |
voic | -1.349 |
bras | -1.346 |
Token | 64 |
Token ID | 2414 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Weld | +0.302 |
ationally | +0.298 |
ammy | +0.294 |
netflix | +0.285 |
ittle | +0.285 |
Neg logit contributions | |
eret | -0.210 |
cano | -0.193 |
hell | -0.188 |
voic | -0.182 |
bras | -0.180 |
Token | as |
Token ID | 355 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
eret | +1.119 |
cano | +1.052 |
hell | +1.028 |
voic | +1.005 |
bras | +0.992 |
Neg logit contributions | |
Weld | -1.090 |
ationally | -1.078 |
ammy | -1.057 |
netflix | -1.029 |
ittle | -1.021 |
Token | the |
Token ID | 262 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Weld | +2.672 |
ationally | +2.603 |
ammy | +2.567 |
netflix | +2.459 |
ittle | +2.453 |
Neg logit contributions | |
eret | -2.815 |
cano | -2.650 |
hell | -2.584 |
voic | -2.492 |
bras | -2.489 |
Token | New |
Token ID | 968 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Weld | +0.299 |
ationally | +0.294 |
ammy | +0.289 |
netflix | +0.278 |
ittle | +0.277 |
Neg logit contributions | |
eret | -0.323 |
cano | -0.302 |
hell | -0.296 |
voic | -0.287 |
bras | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
eret | +2.322 |
cano | +2.162 |
hell | +2.118 |
voic | +2.045 |
bras | +2.036 |
Neg logit contributions | |
Weld | -2.720 |
ationally | -2.688 |
ammy | -2.676 |
netflix | -2.581 |
ittle | -2.579 |
Token | life |
Token ID | 1204 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
eret | +1.813 |
hell | +1.644 |
cano | +1.643 |
voic | +1.595 |
bras | +1.580 |
Neg logit contributions | |
Weld | -2.754 |
ationally | -2.726 |
ammy | -2.712 |
ittle | -2.629 |
netflix | -2.610 |
Token | of |
Token ID | 286 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
eret | +3.312 |
cano | +3.100 |
hell | +3.029 |
bras | +2.930 |
voic | +2.879 |
Neg logit contributions | |
Weld | -4.773 |
ammy | -4.681 |
ationally | -4.675 |
ittle | -4.506 |
netflix | -4.501 |
Token | me |
Token ID | 502 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
eret | +0.804 |
cano | +0.743 |
hell | +0.726 |
voic | +0.707 |
bras | +0.701 |
Neg logit contributions | |
Weld | -1.036 |
ationally | -1.022 |
ammy | -1.014 |
netflix | -0.980 |
ittle | -0.978 |
Token | remember |
Token ID | 3505 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
eret | +1.061 |
cano | +0.985 |
hell | +0.963 |
voic | +0.938 |
bras | +0.929 |
Neg logit contributions | |
Weld | -1.328 |
ationally | -1.302 |
ammy | -1.296 |
netflix | -1.257 |
ittle | -1.244 |
Token | anything |
Token ID | 1997 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Weld | +2.262 |
ationally | +2.203 |
ammy | +2.157 |
ittle | +2.077 |
netflix | +2.076 |
Neg logit contributions | |
eret | -2.148 |
cano | -2.028 |
hell | -1.946 |
voic | -1.884 |
bras | -1.853 |
Token | that |
Token ID | 326 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Weld | +3.054 |
ationally | +2.980 |
ammy | +2.910 |
ittle | +2.842 |
netflix | +2.799 |
Neg logit contributions | |
eret | -3.156 |
cano | -2.938 |
hell | -2.814 |
voic | -2.719 |
bras | -2.710 |
Token | preceded |
Token ID | 27165 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Weld | +2.830 |
ationally | +2.725 |
ammy | +2.678 |
ittle | +2.597 |
netflix | +2.563 |
Neg logit contributions | |
eret | -3.197 |
cano | -2.991 |
hell | -2.910 |
voic | -2.805 |
bras | -2.781 |
Token | Alfred |
Token ID | 22044 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Weld | +1.953 |
ationally | +1.907 |
ammy | +1.875 |
ittle | +1.811 |
netflix | +1.807 |
Neg logit contributions | |
eret | -2.043 |
cano | -1.908 |
hell | -1.864 |
voic | -1.813 |
bras | -1.790 |
Token | o |
Token ID | 78 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
eret | +1.161 |
cano | +1.043 |
hell | +1.010 |
voic | +0.957 |
bras | +0.943 |
Neg logit contributions | |
Weld | -2.332 |
ationally | -2.307 |
ammy | -2.280 |
netflix | -2.226 |
ittle | -2.217 |
Token | 's |
Token ID | 338 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
Weld | +0.892 |
ationally | +0.874 |
ammy | +0.858 |
netflix | +0.824 |
ittle | +0.823 |
Neg logit contributions | |
eret | -1.094 |
cano | -1.029 |
hell | -1.009 |
voic | -0.985 |
bras | -0.976 |
Token | oral |
Token ID | 6864 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
eret | +0.958 |
cano | +0.894 |
hell | +0.875 |
voic | +0.851 |
bras | +0.840 |
Neg logit contributions | |
Weld | -0.935 |
ationally | -0.919 |
ammy | -0.905 |
netflix | -0.878 |
ittle | -0.866 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
eret | +0.096 |
cano | +0.089 |
hell | +0.087 |
voic | +0.085 |
bras | +0.084 |
Neg logit contributions | |
Weld | -0.108 |
ationally | -0.106 |
ammy | -0.104 |
netflix | -0.101 |
ittle | -0.101 |
Token | anthrop |
Token ID | 17911 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Weld | +0.933 |
ationally | +0.920 |
ammy | +0.902 |
ittle | +0.872 |
netflix | +0.869 |
Neg logit contributions | |
eret | -0.962 |
cano | -0.899 |
hell | -0.875 |
voic | -0.848 |
bras | -0.845 |
Token | omorphic |
Token ID | 46374 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
eret | +2.333 |
cano | +2.133 |
hell | +2.121 |
voic | +1.983 |
zek | +1.914 |
Neg logit contributions | |
Weld | -3.874 |
ammy | -3.741 |
ationally | -3.735 |
netflix | -3.639 |
ittle | -3.618 |
Token | div |
Token ID | 2659 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
eret | +0.881 |
cano | +0.822 |
hell | +0.804 |
voic | +0.785 |
bras | +0.777 |
Neg logit contributions | |
Weld | -0.979 |
ationally | -0.966 |
ammy | -0.952 |
netflix | -0.923 |
ittle | -0.918 |
Token | in |
Token ID | 259 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Weld | +2.606 |
ationally | +2.574 |
ammy | +2.532 |
ittle | +2.450 |
netflix | +2.395 |
Neg logit contributions | |
eret | -2.757 |
cano | -2.577 |
hell | -2.497 |
voic | -2.469 |
bras | -2.450 |
Token | ities |
Token ID | 871 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ationally | +0.812 |
Weld | +0.791 |
ammy | +0.731 |
ittle | +0.642 |
netflix | +0.586 |
Neg logit contributions | |
eret | -4.665 |
cano | -4.521 |
hell | -4.418 |
bras | -4.411 |
voic | -4.394 |
Token | became |
Token ID | 2627 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Weld | +0.951 |
ationally | +0.933 |
ammy | +0.914 |
ittle | +0.880 |
netflix | +0.880 |
Neg logit contributions | |
eret | -1.078 |
cano | -1.008 |
hell | -0.982 |
voic | -0.960 |
bras | -0.952 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
eret | +0.969 |
cano | +0.908 |
hell | +0.887 |
voic | +0.870 |
bras | +0.860 |
Neg logit contributions | |
Weld | -0.957 |
ationally | -0.942 |
ammy | -0.932 |
netflix | -0.899 |
ittle | -0.896 |
Token | to |
Token ID | 284 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
eret | +1.069 |
cano | +0.998 |
hell | +0.977 |
voic | +0.953 |
bras | +0.945 |
Neg logit contributions | |
Weld | -1.131 |
ationally | -1.112 |
ammy | -1.103 |
netflix | -1.062 |
ittle | -1.059 |
Token | the |
Token ID | 262 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Weld | +1.434 |
ationally | +1.411 |
ammy | +1.373 |
ittle | +1.333 |
netflix | +1.312 |
Neg logit contributions | |
eret | -1.480 |
cano | -1.387 |
hell | -1.348 |
voic | -1.302 |
bras | -1.287 |
Token | one |
Token ID | 530 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
Weld | +2.610 |
ationally | +2.538 |
ammy | +2.433 |
ittle | +2.392 |
netflix | +2.352 |
Neg logit contributions | |
eret | -2.906 |
cano | -2.739 |
hell | -2.647 |
voic | -2.525 |
tes | -2.505 |
Token | caveat |
Token ID | 36531 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Weld | +3.251 |
ationally | +3.218 |
ammy | +3.083 |
ittle | +3.030 |
netflix | +2.986 |
Neg logit contributions | |
eret | -3.285 |
cano | -3.052 |
hell | -2.946 |
bras | -2.801 |
zek | -2.765 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Weld | +2.804 |
ationally | +2.750 |
ammy | +2.678 |
ittle | +2.590 |
netflix | +2.581 |
Neg logit contributions | |
eret | -3.083 |
cano | -2.893 |
hell | -2.801 |
voic | -2.713 |
bras | -2.704 |
Token | Yes |
Token ID | 3363 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
Weld | +1.625 |
ationally | +1.556 |
ammy | +1.524 |
netflix | +1.477 |
ittle | +1.471 |
Neg logit contributions | |
eret | -1.776 |
cano | -1.679 |
hell | -1.615 |
voic | -1.579 |
bras | -1.562 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Weld | +0.027 |
ationally | +0.026 |
ammy | +0.026 |
netflix | +0.025 |
ittle | +0.025 |
Neg logit contributions | |
eret | -0.026 |
cano | -0.024 |
hell | -0.024 |
voic | -0.023 |
bras | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Weld | +1.693 |
ationally | +1.660 |
ammy | +1.612 |
ittle | +1.565 |
netflix | +1.552 |
Neg logit contributions | |
eret | -1.770 |
cano | -1.673 |
hell | -1.614 |
voic | -1.553 |
bras | -1.536 |
Token | cabinet |
Token ID | 13447 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Weld | +1.370 |
ationally | +1.345 |
ammy | +1.324 |
ittle | +1.268 |
netflix | +1.261 |
Neg logit contributions | |
eret | -1.483 |
cano | -1.393 |
hell | -1.355 |
voic | -1.311 |
bras | -1.298 |
Token | represents |
Token ID | 6870 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
eret | +0.435 |
cano | +0.406 |
hell | +0.396 |
voic | +0.386 |
bras | +0.382 |
Neg logit contributions | |
Weld | -0.466 |
ationally | -0.459 |
ammy | -0.452 |
netflix | -0.437 |
ittle | -0.436 |
Token | several |
Token ID | 1811 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
eret | +0.458 |
cano | +0.427 |
hell | +0.418 |
voic | +0.408 |
bras | +0.404 |
Neg logit contributions | |
Weld | -0.484 |
ationally | -0.477 |
ammy | -0.470 |
netflix | -0.454 |
ittle | -0.454 |
Token | core |
Token ID | 4755 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
eret | +1.904 |
cano | +1.762 |
hell | +1.731 |
voic | +1.724 |
bras | +1.701 |
Neg logit contributions | |
Weld | -2.048 |
ammy | -2.010 |
ationally | -2.005 |
netflix | -1.954 |
ittle | -1.937 |
Token | Canadian |
Token ID | 5398 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Weld | +0.241 |
ationally | +0.237 |
ammy | +0.233 |
netflix | +0.225 |
ittle | +0.224 |
Neg logit contributions | |
eret | -0.258 |
cano | -0.242 |
hell | -0.237 |
voic | -0.231 |
bras | -0.229 |
Token | set |
Token ID | 900 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
eret | +2.665 |
cano | +2.451 |
hell | +2.427 |
voic | +2.424 |
bras | +2.369 |
Neg logit contributions | |
Weld | -2.600 |
ationally | -2.591 |
ammy | -2.572 |
netflix | -2.468 |
ittle | -2.446 |
Token | of |
Token ID | 286 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
eret | +1.192 |
cano | +1.104 |
hell | +1.078 |
voic | +1.050 |
bras | +1.035 |
Neg logit contributions | |
Weld | -1.421 |
ationally | -1.400 |
ammy | -1.383 |
netflix | -1.335 |
ittle | -1.334 |
Token | two |
Token ID | 734 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
eret | +3.439 |
cano | +3.158 |
voic | +3.142 |
hell | +3.105 |
bras | +3.092 |
Neg logit contributions | |
ationally | -3.527 |
ammy | -3.524 |
Weld | -3.520 |
netflix | -3.394 |
ittle | -3.358 |
Token | 7 |
Token ID | 767 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
eret | +4.634 |
voic | +4.285 |
cano | +4.230 |
bras | +4.222 |
hell | +4.215 |
Neg logit contributions | |
ationally | -4.623 |
ammy | -4.618 |
Weld | -4.578 |
netflix | -4.427 |
ittle | -4.378 |
Token | - |
Token ID | 12 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Weld | +0.131 |
ationally | +0.129 |
ammy | +0.127 |
netflix | +0.122 |
ittle | +0.122 |
Neg logit contributions | |
eret | -0.128 |
cano | -0.120 |
hell | -0.117 |
voic | -0.114 |
bras | -0.113 |
Token | bar |
Token ID | 5657 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
eret | +1.081 |
cano | +1.005 |
hell | +0.989 |
voic | +0.955 |
bras | +0.946 |
Neg logit contributions | |
Weld | -1.168 |
ationally | -1.146 |
ammy | -1.133 |
netflix | -1.096 |
ittle | -1.090 |
Token | LED |
Token ID | 12365 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
eret | +2.389 |
cano | +2.225 |
hell | +2.165 |
voic | +2.117 |
bras | +2.095 |
Neg logit contributions | |
Weld | -2.840 |
ationally | -2.824 |
ammy | -2.772 |
netflix | -2.691 |
ittle | -2.673 |
Token | panels |
Token ID | 13043 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
eret | +0.428 |
cano | +0.396 |
hell | +0.386 |
voic | +0.375 |
bras | +0.371 |
Neg logit contributions | |
Weld | -0.558 |
ationally | -0.550 |
ammy | -0.543 |
netflix | -0.526 |
ittle | -0.526 |
Token | ( |
Token ID | 357 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
eret | +4.569 |
hell | +4.328 |
cano | +4.267 |
voic | +4.195 |
bras | +4.129 |
Neg logit contributions | |
ationally | -4.868 |
Weld | -4.793 |
ammy | -4.768 |
netflix | -4.649 |
ittle | -4.619 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
eret | +1.202 |
cano | +1.125 |
hell | +1.104 |
voic | +1.063 |
bras | +1.055 |
Neg logit contributions | |
Weld | -1.288 |
ationally | -1.269 |
ammy | -1.250 |
netflix | -1.206 |
ittle | -1.206 |
Token | cm |
Token ID | 12067 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
eret | +0.712 |
cano | +0.665 |
hell | +0.652 |
voic | +0.636 |
bras | +0.631 |
Neg logit contributions | |
Weld | -0.710 |
ationally | -0.699 |
ammy | -0.690 |
netflix | -0.666 |
ittle | -0.664 |
Token | � |
Token ID | 251 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
eret | +0.205 |
cano | +0.192 |
hell | +0.187 |
voic | +0.182 |
bras | +0.181 |
Neg logit contributions | |
Weld | -0.212 |
ationally | -0.209 |
ammy | -0.206 |
netflix | -0.199 |
ittle | -0.199 |
Token | pioneering |
Token ID | 36304 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
Weld | +1.740 |
ationally | +1.720 |
ammy | +1.682 |
ittle | +1.623 |
netflix | +1.616 |
Neg logit contributions | |
eret | -1.774 |
cano | -1.652 |
hell | -1.600 |
voic | -1.551 |
bras | -1.548 |
Token | lingu |
Token ID | 20280 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
eret | +0.043 |
cano | +0.040 |
hell | +0.039 |
voic | +0.038 |
bras | +0.038 |
Neg logit contributions | |
Weld | -0.044 |
ationally | -0.043 |
ammy | -0.043 |
ittle | -0.041 |
netflix | -0.041 |
Token | ist |
Token ID | 396 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
eret | +0.644 |
cano | +0.588 |
hell | +0.574 |
voic | +0.554 |
bras | +0.546 |
Neg logit contributions | |
Weld | -0.975 |
ationally | -0.959 |
ammy | -0.950 |
netflix | -0.923 |
ittle | -0.921 |
Token | William |
Token ID | 3977 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
eret | +0.694 |
cano | +0.649 |
hell | +0.638 |
voic | +0.622 |
bras | +0.616 |
Neg logit contributions | |
Weld | -0.649 |
ationally | -0.641 |
ammy | -0.630 |
netflix | -0.609 |
ittle | -0.608 |
Token | Lab |
Token ID | 3498 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
eret | +1.481 |
cano | +1.382 |
hell | +1.365 |
voic | +1.324 |
bras | +1.316 |
Neg logit contributions | |
Weld | -1.323 |
ationally | -1.322 |
ammy | -1.303 |
netflix | -1.260 |
ittle | -1.254 |
Token | ov |
Token ID | 709 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
eret | +0.394 |
cano | +0.367 |
hell | +0.358 |
voic | +0.349 |
bras | +0.346 |
Neg logit contributions | |
Weld | -0.425 |
ationally | -0.419 |
ammy | -0.413 |
netflix | -0.399 |
ittle | -0.398 |
Token | told |
Token ID | 1297 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Weld | +3.616 |
ationally | +3.584 |
ammy | +3.461 |
ittle | +3.388 |
netflix | +3.307 |
Neg logit contributions | |
eret | -3.552 |
cano | -3.276 |
voic | -3.188 |
hell | -3.173 |
bras | -3.098 |
Token | City |
Token ID | 2254 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
eret | +2.385 |
cano | +2.201 |
hell | +2.180 |
voic | +2.139 |
bras | +2.101 |
Neg logit contributions | |
Weld | -2.513 |
ationally | -2.482 |
ammy | -2.471 |
netflix | -2.407 |
ittle | -2.367 |
Token | Paper |
Token ID | 14962 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Weld | +1.013 |
ationally | +0.994 |
ammy | +0.973 |
ittle | +0.944 |
netflix | +0.935 |
Neg logit contributions | |
eret | -0.955 |
cano | -0.883 |
hell | -0.859 |
bras | -0.846 |
voic | -0.842 |
Token | in |
Token ID | 287 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
eret | +1.095 |
cano | +1.019 |
hell | +0.998 |
voic | +0.971 |
bras | +0.960 |
Neg logit contributions | |
Weld | -1.206 |
ationally | -1.188 |
ammy | -1.174 |
netflix | -1.139 |
ittle | -1.130 |
Token | ro |
Token ID | 305 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
eret | +0.988 |
cano | +0.922 |
hell | +0.903 |
voic | +0.878 |
bras | +0.871 |
Neg logit contributions | |
Weld | -1.003 |
ationally | -0.988 |
ammy | -0.972 |
netflix | -0.937 |
ittle | -0.936 |
Token | ‑ |
Token ID | 20977 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Weld | +0.885 |
ationally | +0.872 |
ammy | +0.858 |
netflix | +0.830 |
ittle | +0.828 |
Neg logit contributions | |
eret | -0.801 |
cano | -0.745 |
hell | -0.727 |
voic | -0.707 |
bras | -0.701 |
Token | Cub |
Token ID | 43632 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Weld | +0.886 |
ationally | +0.868 |
ammy | +0.836 |
netflix | +0.780 |
ittle | +0.774 |
Neg logit contributions | |
eret | -2.640 |
cano | -2.517 |
hell | -2.470 |
voic | -2.434 |
bras | -2.424 |
Token | ans |
Token ID | 504 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
eret | +2.395 |
cano | +2.233 |
hell | +2.167 |
voic | +2.097 |
tes | +2.072 |
Neg logit contributions | |
Weld | -2.979 |
ationally | -2.891 |
ammy | -2.855 |
netflix | -2.799 |
ittle | -2.790 |
Token | ( |
Token ID | 357 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
eret | +0.979 |
cano | +0.913 |
hell | +0.894 |
voic | +0.870 |
bras | +0.861 |
Neg logit contributions | |
Weld | -1.063 |
ationally | -1.046 |
ammy | -1.033 |
netflix | -1.005 |
ittle | -0.995 |
Token | bl |
Token ID | 2436 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
eret | +0.128 |
cano | +0.120 |
hell | +0.117 |
voic | +0.114 |
bras | +0.112 |
Neg logit contributions | |
Weld | -0.144 |
ationally | -0.142 |
ammy | -0.140 |
netflix | -0.135 |
ittle | -0.135 |
Token | acks |
Token ID | 4595 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
eret | +3.623 |
hell | +3.287 |
cano | +3.251 |
voic | +3.063 |
tes | +3.032 |
Neg logit contributions | |
Weld | -4.680 |
ationally | -4.466 |
netflix | -4.402 |
ammy | -4.356 |
gans | -4.227 |
Token | and |
Token ID | 290 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
eret | +1.090 |
cano | +1.018 |
hell | +0.997 |
voic | +0.971 |
bras | +0.959 |
Neg logit contributions | |
Weld | -1.162 |
ationally | -1.144 |
ammy | -1.129 |
netflix | -1.092 |
ittle | -1.083 |
Token | mul |
Token ID | 35971 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Weld | +2.022 |
ationally | +1.962 |
ammy | +1.945 |
ittle | +1.893 |
netflix | +1.851 |
Neg logit contributions | |
eret | -2.273 |
cano | -2.146 |
hell | -2.077 |
voic | -2.002 |
bras | -1.976 |
Token | att |
Token ID | 1078 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
eret | +1.667 |
hell | +1.531 |
cano | +1.531 |
bras | +1.453 |
voic | +1.447 |
Neg logit contributions | |
Weld | -1.958 |
ationally | -1.933 |
ammy | -1.903 |
netflix | -1.861 |
ittle | -1.826 |
Token | os |
Token ID | 418 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
eret | +3.392 |
cano | +3.046 |
hell | +2.988 |
tes | +2.820 |
voic | +2.757 |
Neg logit contributions | |
Weld | -6.902 |
ationally | -6.817 |
ammy | -6.703 |
ittle | -6.472 |
netflix | -6.441 |
Token | toe |
Token ID | 21189 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
Weld | +0.502 |
ationally | +0.492 |
ammy | +0.486 |
netflix | +0.468 |
ittle | +0.468 |
Neg logit contributions | |
eret | -0.470 |
cano | -0.439 |
hell | -0.428 |
voic | -0.415 |
bras | -0.412 |
Token | - |
Token ID | 12 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
eret | +3.766 |
cano | +3.602 |
hell | +3.580 |
voic | +3.461 |
bras | +3.384 |
Neg logit contributions | |
Weld | -4.783 |
ationally | -4.777 |
ammy | -4.747 |
ittle | -4.655 |
netflix | -4.537 |
Token | to |
Token ID | 1462 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
eret | +1.963 |
cano | +1.850 |
hell | +1.843 |
voic | +1.759 |
bras | +1.732 |
Neg logit contributions | |
Weld | -2.088 |
ationally | -2.063 |
ammy | -2.023 |
netflix | -1.963 |
ittle | -1.957 |
Token | - |
Token ID | 12 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Weld | +1.062 |
ationally | +1.048 |
ammy | +1.032 |
ittle | +0.997 |
netflix | +0.996 |
Neg logit contributions | |
eret | -1.163 |
cano | -1.101 |
hell | -1.060 |
voic | -1.047 |
bras | -1.047 |
Token | toe |
Token ID | 44579 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
eret | +0.178 |
cano | +0.165 |
hell | +0.159 |
voic | +0.158 |
bras | +0.156 |
Neg logit contributions | |
Weld | -0.213 |
ationally | -0.211 |
ammy | -0.208 |
ittle | -0.202 |
netflix | -0.201 |
Token | with |
Token ID | 351 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
eret | +2.416 |
cano | +2.216 |
hell | +2.205 |
voic | +2.136 |
bras | +2.121 |
Neg logit contributions | |
Weld | -2.934 |
ationally | -2.922 |
ammy | -2.876 |
netflix | -2.811 |
ittle | -2.791 |
Token | the |
Token ID | 262 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
Weld | +0.385 |
ationally | +0.377 |
ammy | +0.371 |
netflix | +0.357 |
ittle | +0.356 |
Neg logit contributions | |
eret | -0.406 |
cano | -0.380 |
hell | -0.371 |
voic | -0.361 |
bras | -0.358 |
Token | world |
Token ID | 995 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
eret | +0.644 |
cano | +0.601 |
hell | +0.587 |
voic | +0.571 |
bras | +0.566 |
Neg logit contributions | |
Weld | -0.665 |
ationally | -0.655 |
ammy | -0.644 |
netflix | -0.621 |
ittle | -0.621 |
Token | � |
Token ID | 447 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
eret | +2.450 |
cano | +2.313 |
hell | +2.280 |
voic | +2.230 |
bras | +2.216 |
Neg logit contributions | |
Weld | -2.435 |
ationally | -2.395 |
ammy | -2.379 |
netflix | -2.331 |
ittle | -2.301 |
Token | � |
Token ID | 247 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
eret | +2.166 |
cano | +2.024 |
hell | +1.982 |
voic | +1.907 |
bras | +1.885 |
Neg logit contributions | |
Weld | -2.538 |
ationally | -2.510 |
ammy | -2.491 |
netflix | -2.416 |
ittle | -2.388 |
Token | s |
Token ID | 82 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
eret | +0.981 |
cano | +0.906 |
hell | +0.883 |
voic | +0.852 |
bras | +0.842 |
Neg logit contributions | |
Weld | -1.380 |
ationally | -1.357 |
ammy | -1.347 |
netflix | -1.308 |
ittle | -1.302 |
Token | had |
Token ID | 550 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Weld | +0.659 |
ationally | +0.645 |
ammy | +0.632 |
ittle | +0.609 |
netflix | +0.607 |
Neg logit contributions | |
eret | -0.718 |
cano | -0.676 |
hell | -0.658 |
voic | -0.641 |
bras | -0.635 |
Token | been |
Token ID | 587 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
eret | +0.835 |
cano | +0.778 |
hell | +0.761 |
voic | +0.744 |
bras | +0.737 |
Neg logit contributions | |
Weld | -0.870 |
ationally | -0.858 |
ammy | -0.847 |
netflix | -0.817 |
ittle | -0.815 |
Token | set |
Token ID | 900 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
eret | +0.819 |
cano | +0.767 |
hell | +0.747 |
voic | +0.728 |
bras | +0.723 |
Neg logit contributions | |
Weld | -0.813 |
ationally | -0.800 |
ammy | -0.786 |
ittle | -0.758 |
netflix | -0.757 |
Token | at |
Token ID | 379 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Weld | +0.629 |
ationally | +0.621 |
ammy | +0.607 |
ittle | +0.587 |
netflix | +0.584 |
Neg logit contributions | |
eret | -0.635 |
cano | -0.598 |
hell | -0.582 |
voic | -0.566 |
bras | -0.565 |
Token | 22 |
Token ID | 2534 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
eret | +1.923 |
cano | +1.772 |
hell | +1.736 |
voic | +1.712 |
bras | +1.681 |
Neg logit contributions | |
Weld | -2.448 |
ationally | -2.436 |
ammy | -2.415 |
netflix | -2.340 |
ittle | -2.318 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Weld | +2.339 |
ationally | +2.281 |
ammy | +2.233 |
ittle | +2.161 |
gans | +2.108 |
Neg logit contributions | |
eret | -2.531 |
cano | -2.399 |
hell | -2.333 |
voic | -2.257 |
bras | -2.218 |
Token | 500 |
Token ID | 4059 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Weld | +0.197 |
ationally | +0.194 |
ammy | +0.190 |
netflix | +0.183 |
ittle | +0.182 |
Neg logit contributions | |
eret | -0.247 |
cano | -0.232 |
hell | -0.227 |
voic | -0.222 |
bras | -0.220 |
Token | students |
Token ID | 2444 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Weld | +1.158 |
ationally | +1.134 |
ammy | +1.105 |
ittle | +1.075 |
netflix | +1.061 |
Neg logit contributions | |
eret | -1.212 |
cano | -1.150 |
hell | -1.120 |
voic | -1.079 |
bras | -1.072 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
eret | +1.069 |
cano | +0.992 |
hell | +0.972 |
voic | +0.945 |
bras | +0.935 |
Neg logit contributions | |
Weld | -1.189 |
ationally | -1.173 |
ammy | -1.158 |
netflix | -1.121 |
ittle | -1.116 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
eret | +1.609 |
cano | +1.489 |
hell | +1.467 |
voic | +1.419 |
bras | +1.406 |
Neg logit contributions | |
ationally | -1.639 |
Weld | -1.634 |
ammy | -1.617 |
netflix | -1.566 |
ittle | -1.552 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
eret | +0.880 |
cano | +0.822 |
hell | +0.808 |
voic | +0.785 |
bras | +0.778 |
Neg logit contributions | |
Weld | -0.839 |
ationally | -0.827 |
ammy | -0.816 |
ittle | -0.784 |
netflix | -0.784 |
Token | much |
Token ID | 881 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
eret | +2.161 |
cano | +2.018 |
hell | +1.966 |
voic | +1.910 |
bras | +1.898 |
Neg logit contributions | |
Weld | -2.971 |
ationally | -2.931 |
ammy | -2.900 |
netflix | -2.827 |
gans | -2.753 |
Token | as |
Token ID | 355 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Weld | +1.218 |
ationally | +1.193 |
ammy | +1.159 |
ittle | +1.112 |
netflix | +1.105 |
Neg logit contributions | |
eret | -1.806 |
cano | -1.704 |
hell | -1.659 |
voic | -1.637 |
bras | -1.616 |
Token | $ |
Token ID | 720 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
eret | +1.561 |
cano | +1.433 |
hell | +1.413 |
voic | +1.373 |
bras | +1.359 |
Neg logit contributions | |
Weld | -2.162 |
ationally | -2.138 |
ammy | -2.124 |
netflix | -2.062 |
ittle | -2.054 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
eret | +1.177 |
cano | +1.099 |
hell | +1.087 |
voic | +1.044 |
bras | +1.037 |
Neg logit contributions | |
Weld | -1.223 |
ationally | -1.210 |
ammy | -1.198 |
netflix | -1.149 |
ittle | -1.148 |
Token | million |
Token ID | 1510 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
eret | +1.591 |
cano | +1.480 |
hell | +1.456 |
voic | +1.428 |
bras | +1.420 |
Neg logit contributions | |
Weld | -1.696 |
ationally | -1.685 |
ammy | -1.656 |
netflix | -1.618 |
ittle | -1.601 |
Token | .) |
Token ID | 2014 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
Weld | +0.050 |
ationally | +0.050 |
ammy | +0.049 |
netflix | +0.047 |
ittle | +0.047 |
Neg logit contributions | |
eret | -0.057 |
cano | -0.054 |
hell | -0.053 |
voic | -0.051 |
bras | -0.051 |
Token | The |
Token ID | 383 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
eret | +4.941 |
hell | +4.654 |
cano | +4.477 |
voic | +4.432 |
bras | +4.388 |
Neg logit contributions | |
ationally | -5.673 |
ammy | -5.547 |
Weld | -5.439 |
ittle | -5.344 |
netflix | -5.307 |
Token | private |
Token ID | 2839 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
eret | +1.395 |
cano | +1.293 |
hell | +1.261 |
voic | +1.232 |
bras | +1.216 |
Neg logit contributions | |
Weld | -1.830 |
ationally | -1.814 |
ammy | -1.786 |
netflix | -1.734 |
ittle | -1.733 |
Token | school |
Token ID | 1524 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
Weld | +1.455 |
ationally | +1.419 |
ammy | +1.394 |
ittle | +1.342 |
netflix | +1.334 |
Neg logit contributions | |
eret | -1.676 |
cano | -1.596 |
hell | -1.546 |
voic | -1.501 |
bras | -1.495 |
Token | she |
Token ID | 673 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
eret | +0.632 |
cano | +0.591 |
hell | +0.580 |
voic | +0.564 |
bras | +0.561 |
Neg logit contributions | |
Weld | -0.608 |
ationally | -0.599 |
ammy | -0.590 |
netflix | -0.570 |
ittle | -0.568 |
Token | attended |
Token ID | 9141 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Weld | +2.865 |
ationally | +2.844 |
ammy | +2.757 |
ittle | +2.683 |
netflix | +2.614 |
Neg logit contributions | |
eret | -3.686 |
cano | -3.476 |
voic | -3.370 |
hell | -3.347 |
bras | -3.270 |
Token | or |
Token ID | 393 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Weld | +0.168 |
ationally | +0.165 |
ammy | +0.162 |
ittle | +0.157 |
netflix | +0.157 |
Neg logit contributions | |
eret | -0.169 |
cano | -0.157 |
hell | -0.153 |
bras | -0.149 |
voic | -0.148 |
Token | call |
Token ID | 869 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
eret | +3.659 |
cano | +3.393 |
voic | +3.373 |
hell | +3.342 |
bras | +3.159 |
Neg logit contributions | |
Weld | -5.034 |
ationally | -4.871 |
ammy | -4.847 |
ittle | -4.724 |
netflix | -4.546 |
Token | 0 |
Token ID | 657 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
eret | +2.289 |
cano | +2.094 |
hell | +2.060 |
voic | +2.034 |
tes | +1.915 |
Neg logit contributions | |
Weld | -4.282 |
ationally | -4.258 |
ammy | -4.187 |
ittle | -4.078 |
netflix | -3.997 |
Token | 207 |
Token ID | 22745 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
eret | +4.953 |
voic | +4.869 |
cano | +4.641 |
hell | +4.624 |
tes | +4.579 |
Neg logit contributions | |
Weld | -7.329 |
ammy | -6.890 |
ittle | -6.884 |
gans | -6.782 |
ationally | -6.688 |
Token | 7 |
Token ID | 767 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
eret | +3.498 |
cano | +3.299 |
hell | +3.238 |
voic | +3.201 |
bras | +3.115 |
Neg logit contributions | |
Weld | -6.094 |
ationally | -5.887 |
ammy | -5.883 |
ittle | -5.786 |
netflix | -5.659 |
Token | 82 |
Token ID | 6469 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
eret | +3.262 |
cano | +3.164 |
voic | +3.048 |
hell | +2.996 |
tes | +2.903 |
Neg logit contributions | |
Weld | -4.593 |
ationally | -4.545 |
ammy | -4.531 |
ittle | -4.453 |
netflix | -4.392 |
Token | 4 |
Token ID | 604 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
eret | +3.018 |
cano | +2.925 |
hell | +2.720 |
voic | +2.639 |
bras | +2.573 |
Neg logit contributions | |
Weld | -7.244 |
ammy | -7.236 |
ationally | -7.219 |
ittle | -7.044 |
netflix | -6.887 |
Token | 368 |
Token ID | 27412 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
eret | +3.482 |
cano | +3.360 |
hell | +3.214 |
voic | +3.174 |
tes | +3.026 |
Neg logit contributions | |
Weld | -4.089 |
ationally | -4.043 |
ittle | -3.967 |
ammy | -3.963 |
gans | -3.840 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
eret | +2.972 |
cano | +2.955 |
voic | +2.877 |
hell | +2.858 |
bras | +2.689 |
Neg logit contributions | |
Weld | -5.136 |
ationally | -5.053 |
ammy | -4.996 |
ittle | -4.949 |
netflix | -4.822 |
Token | To |
Token ID | 2514 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
Weld | +2.264 |
ationally | +2.247 |
ammy | +2.205 |
netflix | +2.167 |
ittle | +2.130 |
Neg logit contributions | |
eret | -2.170 |
cano | -2.026 |
voic | -1.940 |
hell | -1.930 |
bras | -1.923 |
Token | all |
Token ID | 477 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
Weld | +0.614 |
ationally | +0.605 |
ammy | +0.595 |
ittle | +0.574 |
netflix | +0.574 |
Neg logit contributions | |
eret | -0.589 |
cano | -0.550 |
hell | -0.537 |
voic | -0.522 |
bras | -0.518 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Weld | +2.609 |
ationally | +2.549 |
ammy | +2.485 |
ittle | +2.396 |
netflix | +2.387 |
Neg logit contributions | |
eret | -2.835 |
cano | -2.649 |
hell | -2.557 |
voic | -2.517 |
bras | -2.481 |
Token | so |
Token ID | 523 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
Weld | +1.547 |
ationally | +1.513 |
ammy | +1.473 |
ittle | +1.430 |
netflix | +1.425 |
Neg logit contributions | |
eret | -1.595 |
cano | -1.484 |
hell | -1.437 |
voic | -1.401 |
bras | -1.386 |
Token | caveat |
Token ID | 36531 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
eret | +2.438 |
cano | +2.279 |
hell | +2.253 |
voic | +2.191 |
bras | +2.181 |
Neg logit contributions | |
Weld | -2.512 |
ationally | -2.494 |
ammy | -2.482 |
netflix | -2.396 |
ittle | -2.380 |
Token | empt |
Token ID | 23909 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Weld | +0.919 |
ationally | +0.909 |
ammy | +0.896 |
netflix | +0.873 |
ittle | +0.873 |
Neg logit contributions | |
eret | -0.453 |
cano | -0.409 |
hell | -0.395 |
voic | -0.378 |
bras | -0.373 |
Token | or |
Token ID | 273 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
eret | +2.678 |
hell | +2.340 |
cano | +2.339 |
voic | +2.218 |
bras | +2.160 |
Neg logit contributions | |
Weld | -4.674 |
ationally | -4.605 |
ammy | -4.510 |
netflix | -4.497 |
ittle | -4.408 |
Token | .) |
Token ID | 2014 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
eret | +0.941 |
cano | +0.881 |
hell | +0.864 |
voic | +0.844 |
bras | +0.837 |
Neg logit contributions | |
Weld | -0.905 |
ationally | -0.896 |
ammy | -0.881 |
netflix | -0.853 |
ittle | -0.848 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eret | +5.020 |
hell | +4.743 |
cano | +4.583 |
voic | +4.504 |
bras | +4.500 |
Neg logit contributions | |
ationally | -5.928 |
ammy | -5.907 |
netflix | -5.781 |
ittle | -5.754 |
Weld | -5.725 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
eret | +0.866 |
cano | +0.810 |
hell | +0.795 |
voic | +0.773 |
bras | +0.767 |
Neg logit contributions | |
Weld | -0.821 |
ationally | -0.809 |
ammy | -0.798 |
netflix | -0.767 |
ittle | -0.767 |
Token | Another |
Token ID | 6610 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
eret | +3.199 |
hell | +3.043 |
cano | +2.975 |
tes | +2.819 |
voic | +2.809 |
Neg logit contributions | |
Weld | -3.794 |
ationally | -3.704 |
ammy | -3.682 |
ittle | -3.571 |
netflix | -3.538 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
eret | +0.302 |
cano | +0.282 |
hell | +0.276 |
voic | +0.269 |
bras | +0.266 |
Neg logit contributions | |
Weld | -0.313 |
ationally | -0.309 |
ammy | -0.304 |
netflix | -0.294 |
ittle | -0.294 |
Token | Moore |
Token ID | 8877 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Weld | +2.350 |
ationally | +2.292 |
ammy | +2.257 |
netflix | +2.155 |
ittle | +2.135 |
Neg logit contributions | |
eret | -2.339 |
cano | -2.189 |
hell | -2.110 |
voic | -2.067 |
bras | -2.037 |
Token | two |
Token ID | 734 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
Weld | +4.186 |
ationally | +4.101 |
ammy | +3.975 |
gans | +3.824 |
netflix | +3.812 |
Neg logit contributions | |
eret | -5.332 |
cano | -5.134 |
hell | -4.925 |
zek | -4.701 |
tes | -4.681 |
Token | parties |
Token ID | 4671 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Weld | +2.180 |
ationally | +2.131 |
ammy | +2.051 |
ittle | +1.982 |
netflix | +1.980 |
Neg logit contributions | |
eret | -2.828 |
cano | -2.690 |
hell | -2.617 |
voic | -2.516 |
bras | -2.486 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Weld | +0.486 |
ationally | +0.476 |
ammy | +0.468 |
ittle | +0.453 |
netflix | +0.452 |
Neg logit contributions | |
eret | -0.479 |
cano | -0.448 |
hell | -0.435 |
voic | -0.425 |
bras | -0.422 |
Token |
|
Token ID | 198 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Weld | +0.286 |
ationally | +0.280 |
ammy | +0.275 |
netflix | +0.265 |
ittle | +0.265 |
Neg logit contributions | |
eret | -0.294 |
cano | -0.276 |
hell | -0.269 |
voic | -0.262 |
bras | -0.260 |
Token |
|
Token ID | 198 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
eret | +2.020 |
hell | +1.871 |
cano | +1.862 |
voic | +1.786 |
bras | +1.772 |
Neg logit contributions | |
Weld | -2.136 |
ationally | -2.113 |
ammy | -2.111 |
ittle | -2.029 |
netflix | -2.006 |
Token | Prep |
Token ID | 37534 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
eret | +0.042 |
cano | +0.039 |
hell | +0.039 |
voic | +0.038 |
bras | +0.037 |
Neg logit contributions | |
Weld | -0.046 |
ationally | -0.045 |
ammy | -0.045 |
netflix | -0.043 |
ittle | -0.043 |
Token | aring |
Token ID | 1723 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
eret | +4.606 |
cano | +4.052 |
hell | +3.993 |
voic | +3.901 |
bras | +3.797 |
Neg logit contributions | |
Weld | -6.224 |
ationally | -6.096 |
ammy | -6.007 |
netflix | -5.983 |
ittle | -5.922 |
Token | for |
Token ID | 329 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Weld | +0.121 |
ationally | +0.119 |
ammy | +0.117 |
netflix | +0.114 |
ittle | +0.113 |
Neg logit contributions | |
eret | -0.105 |
cano | -0.098 |
hell | -0.096 |
voic | -0.093 |
bras | -0.092 |
Token | independence |
Token ID | 10404 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
eret | +0.786 |
cano | +0.733 |
hell | +0.717 |
voic | +0.700 |
bras | +0.693 |
Neg logit contributions | |
Weld | -0.819 |
ationally | -0.810 |
ammy | -0.798 |
netflix | -0.770 |
ittle | -0.770 |
Token | : |
Token ID | 25 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
eret | +0.899 |
cano | +0.839 |
hell | +0.822 |
voic | +0.802 |
bras | +0.796 |
Neg logit contributions | |
Weld | -0.891 |
ationally | -0.880 |
ammy | -0.868 |
netflix | -0.834 |
ittle | -0.833 |
Token | 1961 |
Token ID | 20510 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
eret | +0.339 |
cano | +0.315 |
hell | +0.308 |
voic | +0.301 |
bras | +0.298 |
Neg logit contributions | |
Weld | -0.363 |
ationally | -0.358 |
ammy | -0.353 |
netflix | -0.341 |
ittle | -0.340 |
Token | highlight |
Token ID | 7238 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
eret | +0.460 |
cano | +0.429 |
hell | +0.419 |
voic | +0.408 |
bras | +0.404 |
Neg logit contributions | |
Weld | -0.490 |
ationally | -0.483 |
ammy | -0.476 |
netflix | -0.460 |
ittle | -0.459 |
Token | her |
Token ID | 607 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
eret | +0.999 |
cano | +0.929 |
hell | +0.910 |
voic | +0.893 |
bras | +0.884 |
Neg logit contributions | |
Weld | -1.050 |
ationally | -1.036 |
ammy | -1.025 |
netflix | -0.991 |
ittle | -0.987 |
Token | support |
Token ID | 1104 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Weld | +0.521 |
ationally | +0.512 |
ammy | +0.504 |
ittle | +0.485 |
netflix | +0.485 |
Neg logit contributions | |
eret | -0.511 |
cano | -0.477 |
hell | -0.465 |
voic | -0.452 |
bras | -0.448 |
Token | for |
Token ID | 329 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Weld | +1.829 |
ationally | +1.800 |
ammy | +1.755 |
ittle | +1.711 |
netflix | +1.711 |
Neg logit contributions | |
eret | -1.570 |
cano | -1.461 |
hell | -1.427 |
voic | -1.374 |
bras | -1.370 |
Token | free |
Token ID | 1479 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
eret | +0.181 |
cano | +0.170 |
hell | +0.166 |
voic | +0.161 |
bras | +0.160 |
Neg logit contributions | |
Weld | -0.179 |
ationally | -0.176 |
ammy | -0.173 |
netflix | -0.167 |
ittle | -0.167 |
Token | trade |
Token ID | 3292 |
Feature activation | -8.88e+00 |
Pos logit contributions | |
eret | +1.246 |
cano | +1.164 |
voic | +1.141 |
hell | +1.133 |
bras | +1.125 |
Neg logit contributions | |
ammy | -1.420 |
ationally | -1.412 |
Weld | -1.410 |
netflix | -1.352 |
ittle | -1.349 |
Token | , |
Token ID | 11 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
eret | +4.986 |
hell | +4.644 |
cano | +4.624 |
voic | +4.621 |
bras | +4.621 |
Neg logit contributions | |
ammy | -7.056 |
ationally | -7.005 |
Weld | -6.979 |
netflix | -6.958 |
ittle | -6.587 |
Token | but |
Token ID | 475 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
eret | +0.283 |
cano | +0.264 |
hell | +0.258 |
voic | +0.251 |
bras | +0.249 |
Neg logit contributions | |
Weld | -0.286 |
ationally | -0.282 |
ammy | -0.277 |
netflix | -0.268 |
ittle | -0.267 |
Token | also |
Token ID | 635 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
eret | +0.481 |
cano | +0.449 |
hell | +0.440 |
voic | +0.431 |
bras | +0.428 |
Neg logit contributions | |
Weld | -0.461 |
ationally | -0.455 |
ammy | -0.450 |
netflix | -0.432 |
ittle | -0.431 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
eret | +1.211 |
cano | +1.131 |
hell | +1.109 |
voic | +1.092 |
bras | +1.080 |
Neg logit contributions | |
Weld | -1.295 |
ationally | -1.281 |
ammy | -1.271 |
netflix | -1.222 |
ittle | -1.214 |
Token | concerns |
Token ID | 4786 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Weld | +1.538 |
ationally | +1.503 |
ammy | +1.487 |
ittle | +1.424 |
netflix | +1.412 |
Neg logit contributions | |
eret | -1.659 |
cano | -1.548 |
hell | -1.508 |
bras | -1.448 |
voic | -1.445 |