Token | The |
Token ID | 383 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
ROR | +0.225 |
igent | +0.187 |
amily | +0.184 |
=# | +0.179 |
racket | +0.178 |
Neg logit contributions | |
wcs | -0.158 |
fitt | -0.153 |
fir | -0.151 |
Hatt | -0.151 |
Brid | -0.150 |
Token | terrain |
Token ID | 15510 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
wcs | +0.026 |
fitt | +0.025 |
fir | +0.025 |
Hatt | +0.025 |
Brid | +0.025 |
Neg logit contributions | |
ROR | -0.028 |
igent | -0.023 |
amily | -0.023 |
=# | -0.022 |
onica | -0.021 |
Token | would |
Token ID | 561 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
wcs | +0.935 |
fitt | +0.923 |
Hatt | +0.913 |
fir | +0.913 |
Brid | +0.907 |
Neg logit contributions | |
ROR | -1.197 |
igent | -0.984 |
amily | -0.972 |
=# | -0.936 |
onica | -0.924 |
Token | either |
Token ID | 2035 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
wcs | +0.330 |
fitt | +0.326 |
fir | +0.324 |
Hatt | +0.320 |
Brid | +0.318 |
Neg logit contributions | |
ROR | -0.439 |
igent | -0.361 |
amily | -0.357 |
=# | -0.344 |
onica | -0.340 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
wcs | +0.650 |
fitt | +0.640 |
fir | +0.635 |
Hatt | +0.630 |
Brid | +0.625 |
Neg logit contributions | |
ROR | -0.844 |
igent | -0.693 |
amily | -0.684 |
=# | -0.657 |
onica | -0.653 |
Token | ) |
Token ID | 8 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
ROR | +0.238 |
igent | +0.198 |
amily | +0.195 |
=# | +0.189 |
racket | +0.187 |
Neg logit contributions | |
wcs | -0.170 |
fitt | -0.166 |
fir | -0.164 |
Hatt | -0.164 |
Brid | -0.163 |
Token | still |
Token ID | 991 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ROR | +4.798 |
igent | +3.965 |
amily | +3.871 |
tre | +3.789 |
=# | +3.778 |
Neg logit contributions | |
wcs | -4.293 |
fitt | -4.149 |
Hatt | -4.147 |
Brid | -4.074 |
fir | -4.070 |
Token | be |
Token ID | 307 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ROR | +0.561 |
igent | +0.458 |
amily | +0.450 |
=# | +0.435 |
onica | +0.430 |
Neg logit contributions | |
wcs | -0.476 |
fitt | -0.466 |
fir | -0.463 |
Hatt | -0.462 |
Brid | -0.458 |
Token | too |
Token ID | 1165 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
wcs | +0.144 |
fitt | +0.141 |
fir | +0.140 |
Hatt | +0.140 |
Brid | +0.138 |
Neg logit contributions | |
ROR | -0.184 |
igent | -0.152 |
amily | -0.149 |
=# | -0.145 |
racket | -0.143 |
Token | random |
Token ID | 4738 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
wcs | +0.383 |
fitt | +0.374 |
fir | +0.372 |
Hatt | +0.371 |
Brid | +0.368 |
Neg logit contributions | |
ROR | -0.514 |
igent | -0.425 |
amily | -0.419 |
=# | -0.406 |
onica | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
wcs | +0.771 |
fitt | +0.753 |
fir | +0.748 |
Hatt | +0.746 |
Brid | +0.739 |
Neg logit contributions | |
ROR | -0.957 |
igent | -0.782 |
amily | -0.773 |
=# | -0.746 |
onica | -0.739 |
Token | , |
Token ID | 11 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ROR | +1.051 |
igent | +0.851 |
amily | +0.841 |
=# | +0.810 |
racket | +0.795 |
Neg logit contributions | |
wcs | -0.954 |
fitt | -0.932 |
fir | -0.928 |
Hatt | -0.924 |
Brid | -0.916 |
Token | reduce |
Token ID | 4646 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ROR | +0.459 |
igent | +0.378 |
amily | +0.372 |
=# | +0.358 |
onica | +0.355 |
Neg logit contributions | |
wcs | -0.361 |
fir | -0.355 |
fitt | -0.355 |
Hatt | -0.349 |
Brid | -0.348 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ROR | +1.069 |
igent | +0.878 |
amily | +0.866 |
=# | +0.834 |
onica | +0.826 |
Neg logit contributions | |
wcs | -0.862 |
fitt | -0.847 |
fir | -0.844 |
Hatt | -0.837 |
Brid | -0.833 |
Token | heat |
Token ID | 4894 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ROR | +1.534 |
igent | +1.237 |
amily | +1.216 |
=# | +1.170 |
onica | +1.155 |
Neg logit contributions | |
wcs | -1.506 |
fitt | -1.478 |
fir | -1.470 |
Hatt | -1.464 |
Brid | -1.456 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ROR | +1.886 |
igent | +1.517 |
amily | +1.485 |
=# | +1.434 |
racket | +1.420 |
Neg logit contributions | |
wcs | -1.898 |
fitt | -1.857 |
Hatt | -1.844 |
fir | -1.842 |
Brid | -1.830 |
Token | cover |
Token ID | 3002 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
ROR | +0.967 |
igent | +0.787 |
amily | +0.774 |
=# | +0.743 |
onica | +0.735 |
Neg logit contributions | |
wcs | -0.898 |
fitt | -0.886 |
fir | -0.884 |
Hatt | -0.875 |
Brid | -0.869 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ROR | +4.763 |
igent | +3.870 |
amily | +3.743 |
racket | +3.727 |
=# | +3.710 |
Neg logit contributions | |
wcs | -4.068 |
Hatt | -3.873 |
fitt | -3.854 |
fir | -3.823 |
Brid | -3.814 |
Token | let |
Token ID | 1309 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ROR | +1.058 |
igent | +0.868 |
amily | +0.855 |
=# | +0.822 |
onica | +0.815 |
Neg logit contributions | |
wcs | -0.905 |
fitt | -0.890 |
fir | -0.885 |
Hatt | -0.878 |
Brid | -0.872 |
Token | it |
Token ID | 340 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ROR | +1.319 |
igent | +1.095 |
amily | +1.077 |
=# | +1.043 |
racket | +1.033 |
Neg logit contributions | |
wcs | -0.964 |
fitt | -0.944 |
fir | -0.941 |
Hatt | -0.932 |
Brid | -0.927 |
Token | simmer |
Token ID | 32857 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ROR | +0.163 |
igent | +0.130 |
amily | +0.128 |
=# | +0.122 |
onica | +0.121 |
Neg logit contributions | |
wcs | -0.163 |
fir | -0.161 |
fitt | -0.160 |
Hatt | -0.157 |
Brid | -0.157 |
Token | until |
Token ID | 1566 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ROR | +2.534 |
igent | +2.116 |
amily | +2.065 |
=# | +2.029 |
racket | +2.008 |
Neg logit contributions | |
wcs | -1.866 |
fitt | -1.821 |
Hatt | -1.805 |
Brid | -1.790 |
fir | -1.777 |
Token | . |
Token ID | 13 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
wcs | +0.744 |
fir | +0.729 |
fitt | +0.724 |
Hatt | +0.723 |
Brid | +0.715 |
Neg logit contributions | |
ROR | -1.024 |
igent | -0.840 |
amily | -0.831 |
=# | -0.810 |
onica | -0.797 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ROR | +0.511 |
igent | +0.416 |
amily | +0.408 |
=# | +0.395 |
racket | +0.391 |
Neg logit contributions | |
wcs | -0.454 |
fitt | -0.444 |
fir | -0.439 |
Hatt | -0.438 |
Brid | -0.435 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ROR | +0.122 |
igent | +0.092 |
amily | +0.089 |
=# | +0.086 |
racket | +0.084 |
Neg logit contributions | |
wcs | -0.180 |
fitt | -0.177 |
fir | -0.175 |
Hatt | -0.175 |
Brid | -0.174 |
Token | At |
Token ID | 2953 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ROR | +0.271 |
igent | +0.221 |
amily | +0.217 |
=# | +0.210 |
racket | +0.209 |
Neg logit contributions | |
wcs | -0.239 |
fitt | -0.232 |
Hatt | -0.231 |
fir | -0.231 |
Brid | -0.230 |
Token | a |
Token ID | 257 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
wcs | +0.086 |
fitt | +0.084 |
fir | +0.084 |
Hatt | +0.084 |
Brid | +0.083 |
Neg logit contributions | |
ROR | -0.107 |
igent | -0.088 |
amily | -0.086 |
=# | -0.084 |
racket | -0.083 |
Token | glance |
Token ID | 16086 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
wcs | +0.064 |
fitt | +0.063 |
Hatt | +0.063 |
fir | +0.063 |
Brid | +0.062 |
Neg logit contributions | |
ROR | -0.065 |
igent | -0.052 |
amily | -0.051 |
=# | -0.049 |
onica | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ROR | +3.906 |
igent | +3.180 |
amily | +3.093 |
=# | +3.002 |
racket | +2.965 |
Neg logit contributions | |
wcs | -4.330 |
fitt | -4.226 |
fir | -4.134 |
Hatt | -4.080 |
Brid | -4.079 |
Token | H |
Token ID | 367 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ROR | +1.295 |
igent | +1.077 |
amily | +1.061 |
=# | +1.028 |
racket | +1.021 |
Neg logit contributions | |
wcs | -0.985 |
fitt | -0.957 |
fir | -0.944 |
Hatt | -0.941 |
Brid | -0.934 |
Token | ahn |
Token ID | 15386 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ROR | +0.220 |
igent | +0.172 |
amily | +0.167 |
=# | +0.160 |
racket | +0.157 |
Neg logit contributions | |
wcs | -0.277 |
fitt | -0.273 |
Hatt | -0.271 |
fir | -0.270 |
Brid | -0.269 |
Token | is |
Token ID | 318 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
wcs | +0.397 |
fitt | +0.392 |
fir | +0.390 |
Hatt | +0.389 |
Brid | +0.385 |
Neg logit contributions | |
ROR | -0.537 |
igent | -0.441 |
amily | -0.436 |
=# | -0.424 |
onica | -0.421 |
Token | an |
Token ID | 281 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ROR | +0.942 |
igent | +0.774 |
amily | +0.761 |
=# | +0.737 |
racket | +0.730 |
Neg logit contributions | |
wcs | -0.764 |
fitt | -0.745 |
Hatt | -0.740 |
fir | -0.740 |
Brid | -0.734 |
Token | , |
Token ID | 11 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
wcs | +0.112 |
fitt | +0.110 |
Hatt | +0.109 |
fir | +0.109 |
Brid | +0.108 |
Neg logit contributions | |
ROR | -0.138 |
igent | -0.113 |
amily | -0.111 |
=# | -0.108 |
racket | -0.107 |
Token | House |
Token ID | 2097 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
wcs | +0.488 |
fitt | +0.482 |
Hatt | +0.480 |
fir | +0.479 |
Brid | +0.476 |
Neg logit contributions | |
ROR | -0.611 |
igent | -0.500 |
amily | -0.495 |
=# | -0.481 |
onica | -0.475 |
Token | Speaker |
Token ID | 14931 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
ROR | +0.056 |
igent | +0.043 |
amily | +0.042 |
=# | +0.040 |
onica | +0.039 |
Neg logit contributions | |
wcs | -0.081 |
fitt | -0.080 |
fir | -0.079 |
Hatt | -0.079 |
Brid | -0.078 |
Token | Tip |
Token ID | 23095 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
wcs | +0.616 |
fir | +0.611 |
fitt | +0.611 |
Hatt | +0.608 |
Brid | +0.606 |
Neg logit contributions | |
ROR | -0.760 |
igent | -0.621 |
amily | -0.614 |
=# | -0.596 |
onica | -0.583 |
Token | O |
Token ID | 440 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
wcs | +0.800 |
fitt | +0.789 |
Hatt | +0.785 |
fir | +0.783 |
Brid | +0.779 |
Neg logit contributions | |
ROR | -0.899 |
igent | -0.728 |
amily | -0.717 |
=# | -0.693 |
racket | -0.685 |
Token | ' |
Token ID | 6 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
ROR | +1.350 |
igent | +1.081 |
amily | +1.059 |
=# | +1.021 |
racket | +1.011 |
Neg logit contributions | |
wcs | -1.398 |
fitt | -1.367 |
Hatt | -1.357 |
fir | -1.356 |
Brid | -1.347 |
Token | Neill |
Token ID | 26538 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ROR | +4.067 |
igent | +3.314 |
amily | +3.181 |
racket | +3.110 |
=# | +3.087 |
Neg logit contributions | |
wcs | -4.071 |
fitt | -3.937 |
Hatt | -3.832 |
fir | -3.784 |
Brid | -3.753 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
wcs | +0.389 |
fitt | +0.379 |
fir | +0.378 |
Hatt | +0.377 |
Brid | +0.375 |
Neg logit contributions | |
ROR | -0.441 |
igent | -0.358 |
amily | -0.352 |
=# | -0.342 |
onica | -0.337 |
Token | could |
Token ID | 714 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
wcs | +0.756 |
fitt | +0.748 |
fir | +0.746 |
Hatt | +0.743 |
Brid | +0.737 |
Neg logit contributions | |
ROR | -0.933 |
igent | -0.763 |
amily | -0.754 |
=# | -0.730 |
onica | -0.730 |
Token | hardly |
Token ID | 8941 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
wcs | +0.910 |
fir | +0.904 |
fitt | +0.901 |
Brid | +0.880 |
Hatt | +0.879 |
Neg logit contributions | |
ROR | -1.137 |
igent | -0.920 |
amily | -0.914 |
onica | -0.881 |
=# | -0.880 |
Token | have |
Token ID | 423 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
ROR | +0.345 |
igent | +0.283 |
amily | +0.280 |
=# | +0.269 |
onica | +0.268 |
Neg logit contributions | |
wcs | -0.267 |
fitt | -0.264 |
fir | -0.264 |
Hatt | -0.260 |
Brid | -0.258 |
Token | year |
Token ID | 1941 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ROR | +0.715 |
igent | +0.560 |
amily | +0.540 |
=# | +0.524 |
racket | +0.520 |
Neg logit contributions | |
wcs | -0.863 |
fitt | -0.846 |
fir | -0.841 |
Hatt | -0.836 |
Brid | -0.835 |
Token | - |
Token ID | 12 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
ROR | +0.357 |
igent | +0.292 |
amily | +0.286 |
=# | +0.279 |
onica | +0.275 |
Neg logit contributions | |
wcs | -0.295 |
fitt | -0.291 |
Hatt | -0.289 |
fir | -0.288 |
Brid | -0.286 |
Token | old |
Token ID | 727 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ROR | +0.479 |
igent | +0.393 |
amily | +0.386 |
=# | +0.373 |
tre | +0.371 |
Neg logit contributions | |
wcs | -0.416 |
fitt | -0.408 |
Hatt | -0.402 |
fir | -0.402 |
Brid | -0.401 |
Token | developer |
Token ID | 8517 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ROR | +0.194 |
igent | +0.156 |
amily | +0.154 |
=# | +0.148 |
onica | +0.147 |
Neg logit contributions | |
wcs | -0.177 |
fitt | -0.175 |
Hatt | -0.175 |
fir | -0.175 |
Brid | -0.174 |
Token | picked |
Token ID | 6497 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ROR | +0.411 |
igent | +0.333 |
amily | +0.328 |
=# | +0.317 |
onica | +0.314 |
Neg logit contributions | |
wcs | -0.354 |
fitt | -0.348 |
Hatt | -0.346 |
fir | -0.346 |
Brid | -0.343 |
Token | up |
Token ID | 510 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
ROR | +2.469 |
igent | +2.050 |
amily | +2.016 |
=# | +1.954 |
racket | +1.949 |
Neg logit contributions | |
wcs | -1.919 |
fitt | -1.845 |
fir | -1.830 |
Hatt | -1.830 |
Brid | -1.810 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ROR | +4.284 |
igent | +3.518 |
amily | +3.476 |
racket | +3.395 |
=# | +3.319 |
Neg logit contributions | |
wcs | -3.772 |
fitt | -3.553 |
Hatt | -3.512 |
fir | -3.510 |
Newsletter | -3.509 |
Token | former |
Token ID | 1966 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
ROR | +0.972 |
igent | +0.787 |
amily | +0.773 |
=# | +0.748 |
onica | +0.738 |
Neg logit contributions | |
wcs | -0.891 |
fitt | -0.877 |
fir | -0.870 |
Hatt | -0.870 |
Brid | -0.863 |
Token | Federal |
Token ID | 5618 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ROR | +0.786 |
igent | +0.649 |
amily | +0.637 |
=# | +0.618 |
racket | +0.612 |
Neg logit contributions | |
wcs | -0.620 |
fitt | -0.606 |
fir | -0.601 |
Hatt | -0.601 |
Brid | -0.597 |
Token | Reserve |
Token ID | 12224 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ROR | +0.507 |
igent | +0.432 |
amily | +0.425 |
=# | +0.415 |
racket | +0.412 |
Neg logit contributions | |
wcs | -0.264 |
fitt | -0.256 |
Hatt | -0.253 |
fir | -0.253 |
Brid | -0.250 |
Token | Building |
Token ID | 11819 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
ROR | +0.271 |
igent | +0.212 |
amily | +0.207 |
=# | +0.198 |
onica | +0.196 |
Neg logit contributions | |
wcs | -0.333 |
fitt | -0.328 |
fir | -0.326 |
Hatt | -0.326 |
Brid | -0.325 |
Token | ', |
Token ID | 3256 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
ROR | +0.960 |
igent | +0.773 |
amily | +0.758 |
=# | +0.727 |
racket | +0.724 |
Neg logit contributions | |
wcs | -0.950 |
fitt | -0.927 |
Hatt | -0.921 |
fir | -0.920 |
Brid | -0.913 |
Token | where |
Token ID | 810 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ROR | +0.622 |
igent | +0.514 |
amily | +0.505 |
=# | +0.488 |
onica | +0.485 |
Neg logit contributions | |
wcs | -0.478 |
fitt | -0.467 |
fir | -0.464 |
Hatt | -0.463 |
Brid | -0.459 |
Token | each |
Token ID | 1123 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ROR | +0.532 |
igent | +0.432 |
amily | +0.423 |
onica | +0.405 |
=# | +0.405 |
Neg logit contributions | |
wcs | -0.469 |
fitt | -0.462 |
fir | -0.458 |
Hatt | -0.457 |
Brid | -0.452 |
Token | part |
Token ID | 636 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ROR | +0.140 |
igent | +0.114 |
amily | +0.111 |
onica | +0.107 |
=# | +0.106 |
Neg logit contributions | |
wcs | -0.120 |
fitt | -0.118 |
fir | -0.117 |
Hatt | -0.117 |
Brid | -0.116 |
Token | between |
Token ID | 1022 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ROR | +1.277 |
igent | +1.043 |
amily | +1.024 |
=# | +0.984 |
onica | +0.982 |
Neg logit contributions | |
wcs | -1.068 |
fitt | -1.049 |
fir | -1.040 |
Hatt | -1.037 |
Brid | -1.029 |
Token | ' |
Token ID | 705 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
ROR | +2.539 |
igent | +2.049 |
amily | +2.012 |
=# | +1.957 |
racket | +1.933 |
Neg logit contributions | |
wcs | -2.481 |
fitt | -2.417 |
Hatt | -2.401 |
fir | -2.399 |
Brid | -2.386 |
Token | :' |
Token ID | 32105 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ROR | +3.827 |
igent | +3.062 |
amily | +2.986 |
=# | +2.961 |
=' | +2.913 |
Neg logit contributions | |
wcs | -4.154 |
fitt | -4.086 |
fir | -4.081 |
Hatt | -4.061 |
Brid | -4.059 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ROR | +1.199 |
igent | +0.977 |
amily | +0.956 |
=# | +0.917 |
onica | +0.915 |
Neg logit contributions | |
wcs | -1.076 |
fitt | -1.052 |
Hatt | -1.044 |
fir | -1.043 |
Brid | -1.034 |
Token | the |
Token ID | 262 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
wcs | +0.078 |
fitt | +0.077 |
fir | +0.076 |
Hatt | +0.076 |
Brid | +0.075 |
Neg logit contributions | |
ROR | -0.101 |
igent | -0.083 |
amily | -0.082 |
=# | -0.079 |
onica | -0.079 |
Token | argument |
Token ID | 4578 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
wcs | +0.383 |
fitt | +0.381 |
fir | +0.377 |
Hatt | +0.376 |
Brid | +0.373 |
Neg logit contributions | |
ROR | -0.416 |
igent | -0.336 |
amily | -0.331 |
=# | -0.316 |
onica | -0.316 |
Token | for |
Token ID | 329 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ROR | +1.067 |
igent | +0.869 |
amily | +0.853 |
=# | +0.824 |
racket | +0.816 |
Neg logit contributions | |
wcs | -0.951 |
fitt | -0.930 |
fir | -0.923 |
Hatt | -0.922 |
Brid | -0.916 |
Token | 00 |
Token ID | 3571 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ROR | +0.173 |
igent | +0.143 |
amily | +0.141 |
=# | +0.136 |
racket | +0.134 |
Neg logit contributions | |
wcs | -0.134 |
fitt | -0.130 |
Hatt | -0.130 |
fir | -0.130 |
Brid | -0.129 |
Token | : |
Token ID | 25 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ROR | +0.180 |
igent | +0.144 |
amily | +0.141 |
racket | +0.134 |
=# | +0.134 |
Neg logit contributions | |
wcs | -0.195 |
fitt | -0.191 |
Hatt | -0.190 |
fir | -0.190 |
Brid | -0.190 |
Token | 55 |
Token ID | 2816 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
wcs | +0.143 |
fitt | +0.139 |
Hatt | +0.138 |
fir | +0.138 |
Brid | +0.137 |
Neg logit contributions | |
ROR | -0.206 |
igent | -0.172 |
amily | -0.169 |
=# | -0.163 |
racket | -0.163 |
Token | : |
Token ID | 25 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
ROR | +0.183 |
igent | +0.145 |
amily | +0.143 |
=# | +0.136 |
racket | +0.135 |
Neg logit contributions | |
wcs | -0.201 |
fitt | -0.197 |
Hatt | -0.196 |
fir | -0.196 |
Brid | -0.195 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ROR | +0.057 |
igent | +0.048 |
amily | +0.047 |
=# | +0.045 |
racket | +0.045 |
Neg logit contributions | |
wcs | -0.041 |
fitt | -0.040 |
Hatt | -0.040 |
fir | -0.040 |
Brid | -0.040 |
Token | [ |
Token ID | 685 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
ROR | +0.958 |
igent | +0.784 |
amily | +0.770 |
=# | +0.744 |
racket | +0.738 |
Neg logit contributions | |
wcs | -0.823 |
fitt | -0.803 |
Hatt | -0.798 |
fir | -0.797 |
Brid | -0.793 |
Token | b |
Token ID | 65 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ROR | +3.320 |
igent | +2.539 |
amily | +2.470 |
=# | +2.401 |
tre | +2.362 |
Neg logit contributions | |
Hatt | -4.614 |
fitt | -4.607 |
wcs | -4.591 |
fir | -4.560 |
Brid | -4.512 |
Token | ] |
Token ID | 60 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ROR | +1.393 |
igent | +0.952 |
=# | +0.913 |
amily | +0.907 |
=' | +0.879 |
Neg logit contributions | |
wcs | -3.017 |
fitt | -2.988 |
Hatt | -2.937 |
fir | -2.926 |
Brid | -2.911 |
Token | Personal |
Token ID | 30228 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ROR | +0.307 |
igent | +0.258 |
amily | +0.255 |
=# | +0.247 |
racket | +0.246 |
Neg logit contributions | |
wcs | -0.193 |
fitt | -0.186 |
Hatt | -0.185 |
fir | -0.184 |
Brid | -0.183 |
Token | best |
Token ID | 1266 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
ROR | +0.453 |
igent | +0.379 |
amily | +0.375 |
=# | +0.363 |
onica | +0.359 |
Neg logit contributions | |
wcs | -0.276 |
fitt | -0.273 |
fir | -0.267 |
Hatt | -0.265 |
Brid | -0.264 |
Token | : |
Token ID | 25 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ROR | +0.006 |
igent | +0.005 |
amily | +0.005 |
=# | +0.005 |
racket | +0.005 |
Neg logit contributions | |
wcs | -0.008 |
fitt | -0.008 |
Hatt | -0.007 |
fir | -0.007 |
Brid | -0.007 |
Token | com |
Token ID | 785 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
wcs | +0.261 |
Hatt | +0.252 |
fir | +0.251 |
fitt | +0.251 |
Brid | +0.250 |
Neg logit contributions | |
ROR | -0.543 |
igent | -0.465 |
amily | -0.455 |
=# | -0.447 |
racket | -0.445 |
Token | and |
Token ID | 290 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
ROR | +0.155 |
igent | +0.127 |
amily | +0.123 |
=# | +0.119 |
racket | +0.119 |
Neg logit contributions | |
wcs | -0.142 |
fitt | -0.140 |
Hatt | -0.140 |
fir | -0.139 |
Brid | -0.139 |
Token | V |
Token ID | 569 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ROR | +0.703 |
igent | +0.575 |
amily | +0.563 |
=# | +0.544 |
racket | +0.539 |
Neg logit contributions | |
wcs | -0.617 |
fitt | -0.606 |
Hatt | -0.602 |
fir | -0.601 |
Brid | -0.598 |
Token | odka |
Token ID | 28601 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ROR | +0.247 |
igent | +0.201 |
amily | +0.196 |
=# | +0.190 |
racket | +0.190 |
Neg logit contributions | |
wcs | -0.225 |
fitt | -0.221 |
Hatt | -0.220 |
fir | -0.219 |
Brid | -0.218 |
Token | O |
Token ID | 440 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
wcs | +0.600 |
fitt | +0.594 |
Hatt | +0.592 |
Brid | +0.589 |
fir | +0.586 |
Neg logit contributions | |
ROR | -0.684 |
igent | -0.556 |
amily | -0.549 |
=# | -0.527 |
racket | -0.524 |
Token | ' |
Token ID | 6 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
wcs | +0.631 |
fitt | +0.625 |
Hatt | +0.622 |
Brid | +0.618 |
fir | +0.618 |
Neg logit contributions | |
ROR | -0.697 |
igent | -0.573 |
amily | -0.555 |
=# | -0.540 |
racket | -0.537 |
Token | Clock |
Token ID | 44758 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ROR | +4.403 |
igent | +3.593 |
amily | +3.513 |
=# | +3.438 |
onica | +3.422 |
Neg logit contributions | |
wcs | -3.561 |
fitt | -3.430 |
fir | -3.388 |
Hatt | -3.356 |
Brid | -3.322 |
Token | Podcast |
Token ID | 16036 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ROR | +2.162 |
igent | +1.766 |
amily | +1.732 |
=# | +1.680 |
racket | +1.662 |
Neg logit contributions | |
wcs | -1.878 |
fitt | -1.829 |
fir | -1.816 |
Hatt | -1.813 |
Brid | -1.801 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ROR | +0.581 |
igent | +0.474 |
amily | +0.464 |
=# | +0.450 |
racket | +0.446 |
Neg logit contributions | |
wcs | -0.510 |
fitt | -0.501 |
Hatt | -0.497 |
fir | -0.496 |
Brid | -0.494 |
Token | Author |
Token ID | 6434 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ROR | +0.166 |
igent | +0.136 |
amily | +0.133 |
=# | +0.128 |
racket | +0.128 |
Neg logit contributions | |
wcs | -0.151 |
Hatt | -0.149 |
Brid | -0.149 |
fitt | -0.148 |
fir | -0.148 |
Token | of |
Token ID | 286 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
wcs | +0.199 |
fitt | +0.196 |
Hatt | +0.195 |
fir | +0.194 |
Brid | +0.193 |
Neg logit contributions | |
ROR | -0.262 |
igent | -0.217 |
amily | -0.215 |
=# | -0.206 |
racket | -0.205 |
Token | / |
Token ID | 14 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ROR | +2.002 |
igent | +1.625 |
=# | +1.581 |
amily | +1.549 |
=' | +1.546 |
Neg logit contributions | |
wcs | -1.806 |
fitt | -1.734 |
Hatt | -1.726 |
Brid | -1.706 |
senal | -1.704 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ROR | +1.704 |
igent | +1.394 |
amily | +1.332 |
tre | +1.327 |
=# | +1.325 |
Neg logit contributions | |
wcs | -1.564 |
fitt | -1.553 |
senal | -1.536 |
Hatt | -1.510 |
Brid | -1.494 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ROR | +0.784 |
igent | +0.581 |
amily | +0.562 |
=# | +0.540 |
racket | +0.536 |
Neg logit contributions | |
wcs | -1.297 |
fitt | -1.271 |
Hatt | -1.261 |
Brid | -1.254 |
fir | -1.251 |
Token | until |
Token ID | 1566 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ROR | +2.086 |
igent | +1.702 |
amily | +1.696 |
racket | +1.653 |
tre | +1.633 |
Neg logit contributions | |
wcs | -1.768 |
fitt | -1.757 |
Hatt | -1.702 |
Canaver | -1.692 |
Brid | -1.678 |
Token | golden |
Token ID | 10861 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ROR | +1.658 |
igent | +1.167 |
amily | +1.079 |
racket | +1.068 |
=# | +1.056 |
Neg logit contributions | |
wcs | -4.081 |
Brid | -3.923 |
Hatt | -3.903 |
fitt | -3.874 |
Newsletter | -3.858 |
Token | brown |
Token ID | 7586 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
ROR | +2.331 |
racket | +1.691 |
igent | +1.688 |
=# | +1.585 |
amily | +1.562 |
Neg logit contributions | |
senal | -5.246 |
wcs | -5.107 |
Newsletter | -4.978 |
��� | -4.970 |
fitt | -4.913 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ROR | +3.409 |
igent | +2.685 |
=# | +2.619 |
tre | +2.582 |
=' | +2.582 |
Neg logit contributions | |
senal | -4.800 |
��� | -4.536 |
wcs | -4.456 |
occas | -4.429 |
fitt | -4.334 |
Token | These |
Token ID | 2312 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
ROR | +1.198 |
igent | +0.994 |
amily | +0.978 |
=# | +0.968 |
tre | +0.952 |
Neg logit contributions | |
wcs | -0.835 |
fitt | -0.819 |
Hatt | -0.790 |
fir | -0.787 |
heter | -0.777 |
Token | are |
Token ID | 389 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
wcs | +0.471 |
fitt | +0.457 |
Hatt | +0.454 |
Brid | +0.449 |
fir | +0.449 |
Neg logit contributions | |
ROR | -0.645 |
igent | -0.536 |
amily | -0.527 |
=# | -0.515 |
racket | -0.510 |
Token | lightly |
Token ID | 15376 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ROR | +0.061 |
igent | +0.046 |
amily | +0.045 |
racket | +0.043 |
=# | +0.043 |
Neg logit contributions | |
wcs | -0.086 |
fir | -0.085 |
fitt | -0.085 |
Hatt | -0.084 |
Brid | -0.083 |
Token | fried |
Token ID | 23018 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ROR | +2.046 |
igent | +1.671 |
=# | +1.607 |
amily | +1.605 |
racket | +1.601 |
Neg logit contributions | |
wcs | -1.837 |
Brid | -1.757 |
Hatt | -1.744 |
fitt | -1.737 |
Newsletter | -1.710 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ROR | +0.027 |
igent | +0.022 |
amily | +0.022 |
=# | +0.021 |
onica | +0.021 |
Neg logit contributions | |
wcs | -0.021 |
fitt | -0.021 |
fir | -0.020 |
Hatt | -0.020 |
Brid | -0.020 |
Token | state |
Token ID | 1181 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
ROR | +0.181 |
igent | +0.146 |
amily | +0.145 |
=# | +0.140 |
onica | +0.138 |
Neg logit contributions | |
wcs | -0.164 |
fitt | -0.161 |
fir | -0.161 |
Hatt | -0.159 |
Brid | -0.159 |
Token | -- |
Token ID | 1377 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
wcs | +0.492 |
fitt | +0.486 |
fir | +0.482 |
Hatt | +0.479 |
Brid | +0.474 |
Neg logit contributions | |
ROR | -0.574 |
amily | -0.465 |
igent | -0.464 |
onica | -0.447 |
=# | -0.445 |
Token | in |
Token ID | 287 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
wcs | +0.519 |
fitt | +0.510 |
fir | +0.508 |
Hatt | +0.504 |
Brid | +0.502 |
Neg logit contributions | |
ROR | -0.666 |
igent | -0.547 |
amily | -0.543 |
=# | -0.527 |
onica | -0.521 |
Token | this |
Token ID | 428 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
wcs | +0.060 |
fitt | +0.059 |
fir | +0.058 |
Hatt | +0.058 |
Brid | +0.058 |
Neg logit contributions | |
ROR | -0.083 |
igent | -0.069 |
amily | -0.068 |
=# | -0.066 |
onica | -0.065 |
Token | case |
Token ID | 1339 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
wcs | +0.389 |
fitt | +0.383 |
fir | +0.381 |
Hatt | +0.379 |
Brid | +0.377 |
Neg logit contributions | |
ROR | -0.446 |
igent | -0.363 |
amily | -0.359 |
=# | -0.346 |
onica | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
ROR | +4.103 |
igent | +3.351 |
amily | +3.229 |
racket | +3.210 |
=# | +3.183 |
Neg logit contributions | |
wcs | -3.784 |
fitt | -3.670 |
fir | -3.592 |
Hatt | -3.589 |
heter | -3.559 |
Token | federal |
Token ID | 2717 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
wcs | +0.005 |
fitt | +0.005 |
fir | +0.005 |
Hatt | +0.005 |
Brid | +0.005 |
Neg logit contributions | |
ROR | -0.005 |
igent | -0.004 |
amily | -0.004 |
=# | -0.004 |
onica | -0.004 |
Token | state |
Token ID | 1181 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ROR | +0.055 |
igent | +0.043 |
amily | +0.042 |
=# | +0.040 |
onica | +0.040 |
Neg logit contributions | |
wcs | -0.067 |
fitt | -0.066 |
fir | -0.065 |
Hatt | -0.065 |
Brid | -0.065 |
Token | -- |
Token ID | 1377 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
wcs | +0.398 |
fitt | +0.388 |
fir | +0.386 |
Hatt | +0.384 |
Brid | +0.383 |
Neg logit contributions | |
ROR | -0.587 |
amily | -0.487 |
igent | -0.486 |
=# | -0.469 |
onica | -0.467 |
Token | has |
Token ID | 468 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ROR | +0.647 |
igent | +0.523 |
amily | +0.513 |
=# | +0.495 |
onica | +0.490 |
Neg logit contributions | |
wcs | -0.612 |
fitt | -0.599 |
fir | -0.595 |
Hatt | -0.594 |
Brid | -0.590 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
wcs | +0.158 |
fitt | +0.154 |
Hatt | +0.154 |
fir | +0.154 |
Brid | +0.153 |
Neg logit contributions | |
ROR | -0.185 |
igent | -0.153 |
amily | -0.150 |
=# | -0.144 |
racket | -0.143 |
Token | : |
Token ID | 25 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ROR | +0.150 |
igent | +0.117 |
amily | +0.114 |
=# | +0.111 |
racket | +0.108 |
Neg logit contributions | |
wcs | -0.185 |
fitt | -0.181 |
fir | -0.179 |
Hatt | -0.179 |
Brid | -0.178 |
Token | 03 |
Token ID | 3070 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
wcs | +0.125 |
Hatt | +0.121 |
fitt | +0.121 |
fir | +0.121 |
Brid | +0.120 |
Neg logit contributions | |
ROR | -0.174 |
igent | -0.145 |
amily | -0.143 |
=# | -0.137 |
racket | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ROR | +1.354 |
igent | +1.098 |
amily | +1.077 |
=# | +1.041 |
racket | +1.031 |
Neg logit contributions | |
wcs | -1.258 |
fitt | -1.230 |
Hatt | -1.221 |
fir | -1.221 |
Brid | -1.212 |
Token | 78 |
Token ID | 3695 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ROR | +1.291 |
igent | +1.049 |
amily | +1.031 |
=# | +1.012 |
onica | +0.994 |
Neg logit contributions | |
wcs | -1.093 |
fitt | -1.070 |
fir | -1.054 |
Hatt | -1.050 |
Brid | -1.041 |
Token | [ |
Token ID | 685 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
wcs | +0.182 |
fitt | +0.178 |
Hatt | +0.177 |
fir | +0.177 |
Brid | +0.176 |
Neg logit contributions | |
ROR | -0.235 |
igent | -0.195 |
amily | -0.192 |
=# | -0.185 |
onica | -0.183 |
Token | b |
Token ID | 65 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ROR | +2.956 |
igent | +2.255 |
tre | +2.113 |
amily | +2.105 |
=# | +2.105 |
Neg logit contributions | |
Hatt | -4.807 |
senal | -4.798 |
fitt | -4.794 |
fir | -4.715 |
wcs | -4.694 |
Token | ] |
Token ID | 60 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ROR | +1.118 |
igent | +0.769 |
amily | +0.731 |
=# | +0.730 |
=' | +0.701 |
Neg logit contributions | |
wcs | -2.386 |
fitt | -2.360 |
Hatt | -2.322 |
fir | -2.315 |
Brid | -2.302 |
Token | Console |
Token ID | 47581 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ROR | +0.428 |
igent | +0.351 |
amily | +0.346 |
=# | +0.332 |
racket | +0.332 |
Neg logit contributions | |
wcs | -0.378 |
fitt | -0.365 |
Hatt | -0.361 |
fir | -0.361 |
Brid | -0.360 |
Token | : |
Token ID | 25 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
ROR | +0.678 |
igent | +0.529 |
amily | +0.512 |
=# | +0.501 |
racket | +0.492 |
Neg logit contributions | |
wcs | -0.844 |
fitt | -0.825 |
fir | -0.817 |
Hatt | -0.816 |
Brid | -0.810 |
Token | [/ |
Token ID | 13412 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
wcs | +0.568 |
fitt | +0.558 |
Hatt | +0.556 |
fir | +0.556 |
Brid | +0.553 |
Neg logit contributions | |
ROR | -0.357 |
igent | -0.267 |
amily | -0.259 |
=# | -0.246 |
racket | -0.243 |
Token | 07 |
Token ID | 2998 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
wcs | +0.156 |
Hatt | +0.151 |
fitt | +0.151 |
fir | +0.150 |
Brid | +0.150 |
Neg logit contributions | |
ROR | -0.276 |
igent | -0.235 |
amily | -0.231 |
racket | -0.223 |
=# | -0.223 |
Token | : |
Token ID | 25 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ROR | +0.339 |
igent | +0.266 |
amily | +0.259 |
=# | +0.251 |
racket | +0.246 |
Neg logit contributions | |
wcs | -0.414 |
fitt | -0.405 |
fir | -0.401 |
Hatt | -0.401 |
Brid | -0.399 |
Token | 14 |
Token ID | 1415 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
wcs | +0.191 |
Hatt | +0.187 |
fir | +0.186 |
fitt | +0.186 |
Brid | +0.186 |
Neg logit contributions | |
ROR | -0.238 |
igent | -0.197 |
amily | -0.193 |
racket | -0.185 |
=# | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ROR | +0.453 |
igent | +0.372 |
amily | +0.366 |
=# | +0.353 |
racket | +0.350 |
Neg logit contributions | |
wcs | -0.380 |
fitt | -0.371 |
fir | -0.368 |
Hatt | -0.368 |
Brid | -0.366 |
Token | 78 |
Token ID | 3695 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
ROR | +0.733 |
igent | +0.603 |
amily | +0.592 |
=# | +0.576 |
racket | +0.570 |
Neg logit contributions | |
wcs | -0.582 |
fitt | -0.568 |
fir | -0.562 |
Hatt | -0.562 |
Brid | -0.557 |
Token | [ |
Token ID | 685 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
wcs | +0.555 |
fitt | +0.544 |
Brid | +0.539 |
fir | +0.539 |
Hatt | +0.537 |
Neg logit contributions | |
ROR | -0.669 |
igent | -0.552 |
amily | -0.544 |
=# | -0.523 |
racket | -0.518 |
Token | b |
Token ID | 65 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ROR | +3.396 |
igent | +2.628 |
amily | +2.543 |
=# | +2.482 |
tre | +2.462 |
Neg logit contributions | |
Hatt | -4.357 |
fitt | -4.343 |
wcs | -4.327 |
fir | -4.307 |
Brid | -4.264 |
Token | ] |
Token ID | 60 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ROR | +1.125 |
igent | +0.781 |
amily | +0.749 |
=# | +0.741 |
=' | +0.706 |
Neg logit contributions | |
wcs | -2.317 |
fitt | -2.283 |
Hatt | -2.257 |
fir | -2.249 |
Brid | -2.239 |
Token | Console |
Token ID | 47581 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ROR | +0.152 |
igent | +0.126 |
amily | +0.124 |
=# | +0.120 |
racket | +0.119 |
Neg logit contributions | |
wcs | -0.120 |
fitt | -0.116 |
Hatt | -0.115 |
fir | -0.115 |
Brid | -0.115 |
Token | : |
Token ID | 25 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
ROR | +0.866 |
igent | +0.720 |
amily | +0.710 |
=# | +0.688 |
onica | +0.681 |
Neg logit contributions | |
wcs | -0.610 |
fitt | -0.598 |
fir | -0.591 |
Hatt | -0.590 |
Brid | -0.586 |
Token | [/ |
Token ID | 13412 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
wcs | +0.583 |
fitt | +0.571 |
Brid | +0.569 |
fir | +0.568 |
Hatt | +0.568 |
Neg logit contributions | |
ROR | -0.404 |
igent | -0.308 |
amily | -0.300 |
=# | -0.281 |
racket | -0.280 |
Token | address |
Token ID | 2209 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ROR | +1.387 |
igent | +1.108 |
amily | +1.085 |
=# | +1.046 |
racket | +1.035 |
Neg logit contributions | |
wcs | -1.458 |
fitt | -1.427 |
Hatt | -1.417 |
fir | -1.417 |
Brid | -1.408 |
Token | ] |
Token ID | 60 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
wcs | +0.417 |
fir | +0.407 |
fitt | +0.407 |
Hatt | +0.405 |
Brid | +0.405 |
Neg logit contributions | |
ROR | -0.342 |
igent | -0.266 |
amily | -0.262 |
onica | -0.247 |
=# | -0.244 |
Token | | |
Token ID | 930 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
wcs | +1.461 |
fir | +1.436 |
fitt | +1.430 |
Brid | +1.420 |
Hatt | +1.417 |
Neg logit contributions | |
ROR | -1.616 |
igent | -1.317 |
amily | -1.293 |
onica | -1.248 |
=# | -1.219 |
Token | - |
Token ID | 532 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
wcs | +1.908 |
fir | +1.878 |
fitt | +1.872 |
Brid | +1.857 |
Hatt | +1.846 |
Neg logit contributions | |
ROR | -2.103 |
igent | -1.710 |
amily | -1.686 |
onica | -1.623 |
=# | -1.583 |
Token | where |
Token ID | 810 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
wcs | +1.126 |
fitt | +1.106 |
fir | +1.100 |
Hatt | +1.091 |
Brid | +1.087 |
Neg logit contributions | |
ROR | -1.353 |
igent | -1.108 |
amily | -1.091 |
onica | -1.051 |
=# | -1.046 |
Token | ' |
Token ID | 705 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ROR | +1.760 |
igent | +1.450 |
amily | +1.421 |
=# | +1.383 |
racket | +1.374 |
Neg logit contributions | |
wcs | -1.447 |
fitt | -1.409 |
Hatt | -1.401 |
fir | -1.396 |
Brid | -1.386 |
Token | system |
Token ID | 10057 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ROR | +4.140 |
igent | +3.415 |
amily | +3.330 |
=# | +3.274 |
racket | +3.242 |
Neg logit contributions | |
wcs | -3.511 |
fitt | -3.483 |
Hatt | -3.450 |
fir | -3.448 |
Brid | -3.408 |
Token | ' |
Token ID | 6 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
wcs | +0.159 |
fitt | +0.155 |
fir | +0.153 |
Hatt | +0.153 |
Brid | +0.152 |
Neg logit contributions | |
ROR | -0.186 |
igent | -0.153 |
amily | -0.149 |
onica | -0.144 |
=# | -0.143 |
Token | will |
Token ID | 481 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
wcs | +0.446 |
fitt | +0.439 |
fir | +0.435 |
Hatt | +0.433 |
Brid | +0.430 |
Neg logit contributions | |
ROR | -0.492 |
igent | -0.401 |
amily | -0.392 |
onica | -0.376 |
=# | -0.375 |
Token | return |
Token ID | 1441 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ROR | +0.640 |
igent | +0.522 |
amily | +0.514 |
=# | +0.493 |
onica | +0.490 |
Neg logit contributions | |
wcs | -0.562 |
fitt | -0.553 |
fir | -0.549 |
Hatt | -0.546 |
Brid | -0.543 |
Token | + |
Token ID | 1343 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
ROR | +1.210 |
igent | +0.989 |
amily | +0.971 |
=# | +0.940 |
racket | +0.931 |
Neg logit contributions | |
wcs | -1.048 |
fitt | -1.023 |
Hatt | -1.016 |
fir | -1.016 |
Brid | -1.008 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ROR | +1.112 |
igent | +0.892 |
amily | +0.869 |
=# | +0.856 |
racket | +0.844 |
Neg logit contributions | |
wcs | -1.118 |
fitt | -1.091 |
Hatt | -1.071 |
fir | -1.064 |
Brid | -1.061 |
Token | / |
Token ID | 14 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ROR | +2.002 |
igent | +1.625 |
=# | +1.581 |
amily | +1.549 |
=' | +1.546 |
Neg logit contributions | |
wcs | -1.806 |
fitt | -1.734 |
Hatt | -1.726 |
Brid | -1.706 |
senal | -1.704 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ROR | +1.704 |
igent | +1.394 |
amily | +1.332 |
tre | +1.327 |
=# | +1.325 |
Neg logit contributions | |
wcs | -1.564 |
fitt | -1.553 |
senal | -1.536 |
Hatt | -1.510 |
Brid | -1.494 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ROR | +0.784 |
igent | +0.581 |
amily | +0.562 |
=# | +0.540 |
racket | +0.536 |
Neg logit contributions | |
wcs | -1.297 |
fitt | -1.271 |
Hatt | -1.261 |
Brid | -1.254 |
fir | -1.251 |
Token | until |
Token ID | 1566 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ROR | +2.086 |
igent | +1.702 |
amily | +1.696 |
racket | +1.653 |
tre | +1.633 |
Neg logit contributions | |
wcs | -1.768 |
fitt | -1.757 |
Hatt | -1.702 |
Canaver | -1.692 |
Brid | -1.678 |
Token | golden |
Token ID | 10861 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ROR | +1.658 |
igent | +1.167 |
amily | +1.079 |
racket | +1.068 |
=# | +1.056 |
Neg logit contributions | |
wcs | -4.081 |
Brid | -3.923 |
Hatt | -3.903 |
fitt | -3.874 |
Newsletter | -3.858 |
Token | brown |
Token ID | 7586 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
ROR | +2.331 |
racket | +1.691 |
igent | +1.688 |
=# | +1.585 |
amily | +1.562 |
Neg logit contributions | |
senal | -5.246 |
wcs | -5.107 |
Newsletter | -4.978 |
��� | -4.970 |
fitt | -4.913 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ROR | +3.409 |
igent | +2.685 |
=# | +2.619 |
tre | +2.582 |
=' | +2.582 |
Neg logit contributions | |
senal | -4.800 |
��� | -4.536 |
wcs | -4.456 |
occas | -4.429 |
fitt | -4.334 |
Token | These |
Token ID | 2312 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
ROR | +1.198 |
igent | +0.994 |
amily | +0.978 |
=# | +0.968 |
tre | +0.952 |
Neg logit contributions | |
wcs | -0.835 |
fitt | -0.819 |
Hatt | -0.790 |
fir | -0.787 |
heter | -0.777 |
Token | are |
Token ID | 389 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
wcs | +0.471 |
fitt | +0.457 |
Hatt | +0.454 |
Brid | +0.449 |
fir | +0.449 |
Neg logit contributions | |
ROR | -0.645 |
igent | -0.536 |
amily | -0.527 |
=# | -0.515 |
racket | -0.510 |
Token | lightly |
Token ID | 15376 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ROR | +0.061 |
igent | +0.046 |
amily | +0.045 |
racket | +0.043 |
=# | +0.043 |
Neg logit contributions | |
wcs | -0.086 |
fir | -0.085 |
fitt | -0.085 |
Hatt | -0.084 |
Brid | -0.083 |
Token | ce |
Token ID | 344 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ROR | +0.666 |
igent | +0.545 |
amily | +0.536 |
=# | +0.520 |
racket | +0.515 |
Neg logit contributions | |
wcs | -0.559 |
fitt | -0.546 |
Hatt | -0.542 |
fir | -0.541 |
Brid | -0.537 |
Token | / |
Token ID | 14 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ROR | +0.807 |
igent | +0.673 |
amily | +0.663 |
=# | +0.641 |
racket | +0.636 |
Neg logit contributions | |
wcs | -0.570 |
fitt | -0.555 |
Hatt | -0.552 |
fir | -0.551 |
Brid | -0.548 |
Token | edd |
Token ID | 6048 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ROR | +0.881 |
igent | +0.720 |
amily | +0.706 |
=# | +0.684 |
racket | +0.680 |
Neg logit contributions | |
wcs | -0.763 |
fitt | -0.742 |
fir | -0.738 |
Hatt | -0.736 |
Brid | -0.731 |
Token | 75 |
Token ID | 2425 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ROR | +0.202 |
igent | +0.164 |
amily | +0.161 |
=# | +0.156 |
racket | +0.156 |
Neg logit contributions | |
wcs | -0.174 |
fitt | -0.169 |
fir | -0.168 |
Hatt | -0.167 |
Brid | -0.167 |
Token | / |
Token ID | 14 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ROR | +0.501 |
igent | +0.414 |
amily | +0.406 |
=# | +0.393 |
racket | +0.391 |
Neg logit contributions | |
wcs | -0.385 |
fitt | -0.375 |
fir | -0.373 |
Hatt | -0.372 |
Brid | -0.370 |
Token | AUT |
Token ID | 39371 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
ROR | +1.399 |
igent | +1.065 |
amily | +1.046 |
=# | +1.016 |
tre | +1.011 |
Neg logit contributions | |
wcs | -1.882 |
fitt | -1.851 |
fir | -1.837 |
Hatt | -1.829 |
Brid | -1.828 |
Token | OC |
Token ID | 4503 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ROR | +5.392 |
PASS | +4.307 |
tre | +4.251 |
igent | +4.241 |
=# | +4.236 |
Neg logit contributions | |
fir | -2.538 |
fitt | -2.524 |
senal | -2.490 |
Canaver | -2.472 |
��� | -2.437 |
Token | R |
Token ID | 49 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ROR | +0.863 |
igent | +0.599 |
amily | +0.589 |
=# | +0.570 |
racket | +0.545 |
Neg logit contributions | |
wcs | -1.539 |
fitt | -1.512 |
Hatt | -1.498 |
fir | -1.493 |
Brid | -1.486 |
Token | OP |
Token ID | 3185 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ROR | +2.773 |
igent | +2.210 |
amily | +2.177 |
=# | +2.149 |
tre | +2.131 |
Neg logit contributions | |
wcs | -2.342 |
fir | -2.254 |
Hatt | -2.231 |
Brid | -2.223 |
fitt | -2.221 |
Token | / |
Token ID | 14 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ROR | +0.858 |
igent | +0.695 |
=# | +0.672 |
amily | +0.665 |
racket | +0.659 |
Neg logit contributions | |
wcs | -0.746 |
Hatt | -0.715 |
fitt | -0.715 |
Brid | -0.703 |
fir | -0.695 |
Token | h |
Token ID | 71 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ROR | +2.196 |
igent | +1.753 |
amily | +1.712 |
tre | +1.694 |
=# | +1.674 |
Neg logit contributions | |
wcs | -2.454 |
fitt | -2.396 |
fir | -2.392 |
Brid | -2.391 |
Hatt | -2.385 |
Token | feminine |
Token ID | 23564 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
wcs | +0.498 |
fitt | +0.490 |
Hatt | +0.488 |
fir | +0.488 |
Brid | +0.482 |
Neg logit contributions | |
ROR | -0.579 |
igent | -0.470 |
amily | -0.461 |
=# | -0.447 |
onica | -0.441 |
Token | suffix |
Token ID | 35488 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ROR | +0.101 |
igent | +0.084 |
amily | +0.082 |
=# | +0.080 |
racket | +0.080 |
Neg logit contributions | |
wcs | -0.075 |
fitt | -0.073 |
Hatt | -0.073 |
fir | -0.073 |
Brid | -0.072 |
Token | : |
Token ID | 25 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ROR | +0.606 |
igent | +0.497 |
amily | +0.488 |
=# | +0.473 |
racket | +0.469 |
Neg logit contributions | |
wcs | -0.508 |
fitt | -0.496 |
Hatt | -0.492 |
fir | -0.492 |
Brid | -0.488 |
Token | tem |
Token ID | 2169 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ROR | +0.259 |
igent | +0.213 |
amily | +0.209 |
=# | +0.203 |
onica | +0.201 |
Neg logit contributions | |
wcs | -0.209 |
fitt | -0.205 |
Hatt | -0.204 |
fir | -0.203 |
Brid | -0.202 |
Token | ür |
Token ID | 25151 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
ROR | +1.321 |
igent | +1.124 |
amily | +1.105 |
=# | +1.076 |
racket | +1.069 |
Neg logit contributions | |
wcs | -0.734 |
fitt | -0.712 |
Hatt | -0.705 |
fir | -0.703 |
Brid | -0.699 |
Token | ' |
Token ID | 705 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
ROR | +0.598 |
igent | +0.485 |
amily | +0.477 |
=# | +0.460 |
racket | +0.456 |
Neg logit contributions | |
wcs | -0.549 |
fitt | -0.538 |
fir | -0.535 |
Hatt | -0.534 |
Brid | -0.530 |
Token | iron |
Token ID | 1934 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ROR | +4.046 |
igent | +3.347 |
amily | +3.267 |
tre | +3.203 |
=# | +3.169 |
Neg logit contributions | |
wcs | -3.479 |
fitt | -3.381 |
Hatt | -3.379 |
Brid | -3.371 |
fir | -3.369 |
Token | ' |
Token ID | 6 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
wcs | +0.120 |
fitt | +0.119 |
fir | +0.117 |
Hatt | +0.117 |
Brid | +0.116 |
Neg logit contributions | |
ROR | -0.131 |
igent | -0.106 |
amily | -0.105 |
=# | -0.101 |
onica | -0.099 |
Token | + |
Token ID | 1343 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ROR | +0.633 |
igent | +0.513 |
amily | +0.504 |
=# | +0.486 |
racket | +0.482 |
Neg logit contributions | |
wcs | -0.582 |
fitt | -0.569 |
Hatt | -0.565 |
fir | -0.565 |
Brid | -0.561 |
Token | - |
Token ID | 532 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
ROR | +1.914 |
igent | +1.551 |
amily | +1.510 |
=# | +1.467 |
racket | +1.464 |
Neg logit contributions | |
wcs | -1.844 |
fitt | -1.787 |
Hatt | -1.779 |
Brid | -1.772 |
fir | -1.764 |
Token | cin |
Token ID | 17879 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ROR | +0.633 |
igent | +0.511 |
amily | +0.502 |
=# | +0.486 |
racket | +0.481 |
Neg logit contributions | |
wcs | -0.604 |
fitt | -0.590 |
fir | -0.587 |
Hatt | -0.586 |
Brid | -0.581 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
wcs | +0.426 |
fitt | +0.417 |
fir | +0.414 |
Hatt | +0.414 |
Brid | +0.412 |
Neg logit contributions | |
ROR | -0.522 |
igent | -0.430 |
amily | -0.422 |
=# | -0.407 |
racket | -0.402 |
Token | : |
Token ID | 25 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ROR | +0.405 |
igent | +0.331 |
amily | +0.326 |
=# | +0.312 |
racket | +0.309 |
Neg logit contributions | |
wcs | -0.358 |
fitt | -0.350 |
fir | -0.348 |
Hatt | -0.346 |
Brid | -0.345 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
wcs | +0.153 |
fitt | +0.149 |
Hatt | +0.149 |
fir | +0.148 |
Brid | +0.148 |
Neg logit contributions | |
ROR | -0.217 |
igent | -0.182 |
amily | -0.179 |
=# | -0.172 |
racket | -0.171 |
Token | : |
Token ID | 25 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ROR | +0.105 |
igent | +0.084 |
amily | +0.083 |
=# | +0.079 |
racket | +0.078 |
Neg logit contributions | |
wcs | -0.112 |
fitt | -0.110 |
Hatt | -0.109 |
fir | -0.109 |
Brid | -0.109 |
Token | 00 |
Token ID | 405 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
wcs | +0.152 |
Hatt | +0.147 |
fir | +0.147 |
fitt | +0.147 |
Brid | +0.146 |
Neg logit contributions | |
ROR | -0.171 |
igent | -0.141 |
amily | -0.137 |
racket | -0.131 |
=# | -0.131 |
Token | [ |
Token ID | 685 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
ROR | +0.160 |
igent | +0.131 |
amily | +0.129 |
=# | +0.123 |
racket | +0.123 |
Neg logit contributions | |
wcs | -0.147 |
fitt | -0.143 |
fir | -0.142 |
Hatt | -0.142 |
Brid | -0.142 |
Token | b |
Token ID | 65 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ROR | +3.851 |
igent | +3.095 |
amily | +3.014 |
=# | +2.970 |
tre | +2.941 |
Neg logit contributions | |
fitt | -3.630 |
wcs | -3.625 |
Hatt | -3.622 |
fir | -3.595 |
Brid | -3.552 |
Token | ] |
Token ID | 60 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ROR | +1.310 |
igent | +0.941 |
amily | +0.910 |
=# | +0.852 |
racket | +0.843 |
Neg logit contributions | |
wcs | -2.476 |
fitt | -2.434 |
fir | -2.422 |
Hatt | -2.421 |
Brid | -2.409 |
Token | Personal |
Token ID | 30228 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
wcs | +0.154 |
fitt | +0.150 |
fir | +0.149 |
Hatt | +0.149 |
Brid | +0.148 |
Neg logit contributions | |
ROR | -0.176 |
igent | -0.145 |
amily | -0.143 |
=# | -0.137 |
racket | -0.136 |
Token | best |
Token ID | 1266 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
wcs | +0.184 |
fitt | +0.184 |
fir | +0.181 |
Hatt | +0.181 |
Brid | +0.180 |
Neg logit contributions | |
ROR | -0.225 |
igent | -0.183 |
amily | -0.183 |
=# | -0.173 |
onica | -0.172 |
Token | : |
Token ID | 25 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
wcs | +0.452 |
fitt | +0.447 |
fir | +0.442 |
Hatt | +0.440 |
Brid | +0.439 |
Neg logit contributions | |
ROR | -0.483 |
igent | -0.388 |
amily | -0.383 |
=# | -0.367 |
onica | -0.363 |
Token | t |
Token ID | 83 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
wcs | +0.122 |
fitt | +0.121 |
fir | +0.120 |
Hatt | +0.120 |
Brid | +0.119 |
Neg logit contributions | |
ROR | -0.092 |
igent | -0.071 |
amily | -0.069 |
=# | -0.066 |
racket | -0.066 |
Token | work |
Token ID | 670 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ROR | +0.550 |
igent | +0.458 |
amily | +0.451 |
=# | +0.438 |
racket | +0.434 |
Neg logit contributions | |
wcs | -0.383 |
fitt | -0.373 |
fir | -0.370 |
Hatt | -0.369 |
Brid | -0.366 |
Token | is |
Token ID | 318 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ROR | +1.280 |
igent | +1.045 |
amily | +1.020 |
=# | +0.990 |
racket | +0.984 |
Neg logit contributions | |
wcs | -1.169 |
fitt | -1.133 |
Hatt | -1.127 |
fir | -1.125 |
Brid | -1.120 |
Token | because |
Token ID | 780 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ROR | +0.234 |
igent | +0.193 |
amily | +0.191 |
=# | +0.185 |
onica | +0.183 |
Neg logit contributions | |
wcs | -0.169 |
fitt | -0.165 |
fir | -0.164 |
Hatt | -0.164 |
Brid | -0.163 |
Token | a |
Token ID | 257 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ROR | +0.527 |
igent | +0.437 |
amily | +0.430 |
=# | +0.416 |
onica | +0.412 |
Neg logit contributions | |
wcs | -0.384 |
fitt | -0.376 |
fir | -0.373 |
Hatt | -0.373 |
Brid | -0.370 |
Token | ) |
Token ID | 8 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
wcs | +0.171 |
fitt | +0.168 |
fir | +0.167 |
Hatt | +0.167 |
Brid | +0.166 |
Neg logit contributions | |
ROR | -0.174 |
igent | -0.140 |
amily | -0.138 |
=# | -0.132 |
onica | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ROR | +4.143 |
igent | +3.453 |
amily | +3.381 |
racket | +3.316 |
=# | +3.310 |
Neg logit contributions | |
wcs | -3.355 |
fitt | -3.203 |
Hatt | -3.178 |
fir | -3.143 |
Brid | -3.121 |
Token | mouse |
Token ID | 10211 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ROR | +0.492 |
igent | +0.394 |
amily | +0.389 |
=# | +0.373 |
onica | +0.367 |
Neg logit contributions | |
wcs | -0.494 |
fitt | -0.487 |
fir | -0.484 |
Hatt | -0.482 |
Brid | -0.479 |
Token | would |
Token ID | 561 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
wcs | +0.587 |
fitt | +0.574 |
fir | +0.570 |
Hatt | +0.570 |
Brid | +0.564 |
Neg logit contributions | |
ROR | -0.714 |
igent | -0.586 |
amily | -0.576 |
=# | -0.558 |
onica | -0.552 |
Token | be |
Token ID | 307 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
wcs | +0.007 |
fitt | +0.006 |
fir | +0.006 |
Hatt | +0.006 |
Brid | +0.006 |
Neg logit contributions | |
ROR | -0.008 |
igent | -0.007 |
amily | -0.007 |
=# | -0.006 |
onica | -0.006 |
Token | locked |
Token ID | 8970 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ROR | +0.128 |
igent | +0.104 |
amily | +0.102 |
=# | +0.099 |
racket | +0.098 |
Neg logit contributions | |
wcs | -0.111 |
fitt | -0.108 |
Hatt | -0.107 |
fir | -0.107 |
Brid | -0.106 |
Token | line |
Token ID | 1627 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
fitt | +0.752 |
wcs | +0.747 |
fir | +0.743 |
Brid | +0.732 |
Hatt | +0.729 |
Neg logit contributions | |
ROR | -0.711 |
igent | -0.577 |
amily | -0.566 |
onica | -0.538 |
=# | -0.534 |
Token | , |
Token ID | 837 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
wcs | +1.216 |
fitt | +1.186 |
fir | +1.159 |
Hatt | +1.153 |
Brid | +1.146 |
Neg logit contributions | |
ROR | -2.716 |
igent | -2.349 |
amily | -2.318 |
=# | -2.265 |
racket | -2.249 |
Token | r |
Token ID | 374 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
fitt | +2.321 |
fir | +2.307 |
wcs | +2.306 |
Hatt | +2.272 |
Brid | +2.269 |
Neg logit contributions | |
ROR | -2.080 |
igent | -1.702 |
amily | -1.654 |
onica | -1.578 |
=# | -1.524 |
Token | ' |
Token ID | 705 |
Feature activation | +2.10e-04 |
Pos logit contributions | |
wcs | +1.140 |
fitt | +1.132 |
fir | +1.112 |
Brid | +1.106 |
Hatt | +1.103 |
Neg logit contributions | |
ROR | -1.259 |
igent | -1.042 |
amily | -1.022 |
=# | -0.980 |
racket | -0.970 |
Token | \ |
Token ID | 59 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ROR | +0.000 |
igent | +0.000 |
amily | +0.000 |
racket | +0.000 |
onica | +0.000 |
Neg logit contributions | |
wcs | -0.000 |
fitt | -0.000 |
fir | -0.000 |
Hatt | -0.000 |
Brid | -0.000 |
Token | [ |
Token ID | 58 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
ROR | +0.366 |
igent | +0.304 |
amily | +0.297 |
racket | +0.287 |
onica | +0.287 |
Neg logit contributions | |
wcs | -0.275 |
fitt | -0.267 |
fir | -0.265 |
Hatt | -0.264 |
Brid | -0.263 |
Token | + |
Token ID | 10 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ROR | +4.000 |
igent | +3.244 |
amily | +3.213 |
=# | +3.142 |
racket | +3.073 |
Neg logit contributions | |
wcs | -3.470 |
fitt | -3.414 |
Hatt | -3.377 |
fir | -3.367 |
Brid | -3.350 |
Token | \ |
Token ID | 59 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ROR | +2.287 |
igent | +1.837 |
amily | +1.800 |
=# | +1.741 |
racket | +1.719 |
Neg logit contributions | |
wcs | -2.295 |
fitt | -2.247 |
Hatt | -2.232 |
fir | -2.229 |
Brid | -2.214 |
Token | S |
Token ID | 50 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
wcs | +0.204 |
fir | +0.198 |
fitt | +0.197 |
Hatt | +0.196 |
Brid | +0.196 |
Neg logit contributions | |
ROR | -0.184 |
igent | -0.147 |
amily | -0.142 |
racket | -0.137 |
onica | -0.135 |
Token | + |
Token ID | 10 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ROR | +0.701 |
igent | +0.570 |
amily | +0.559 |
=# | +0.535 |
racket | +0.534 |
Neg logit contributions | |
wcs | -0.652 |
fitt | -0.637 |
fir | -0.634 |
Hatt | -0.632 |
Brid | -0.628 |
Token | \ |
Token ID | 59 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ROR | +0.845 |
igent | +0.679 |
amily | +0.663 |
=# | +0.634 |
racket | +0.633 |
Neg logit contributions | |
wcs | -0.868 |
fitt | -0.849 |
fir | -0.848 |
Hatt | -0.845 |
Brid | -0.841 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
ROR | +1.157 |
igent | +0.968 |
amily | +0.951 |
=# | +0.926 |
racket | +0.920 |
Neg logit contributions | |
wcs | -0.782 |
fitt | -0.759 |
Hatt | -0.753 |
fir | -0.751 |
Brid | -0.746 |
Token | / |
Token ID | 14 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ROR | +1.375 |
igent | +1.054 |
amily | +1.033 |
=# | +0.977 |
racket | +0.967 |
Neg logit contributions | |
wcs | -1.879 |
fitt | -1.850 |
fir | -1.845 |
Hatt | -1.832 |
Brid | -1.822 |
Token | 3 |
Token ID | 18 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ROR | +1.470 |
igent | +1.221 |
amily | +1.201 |
=# | +1.165 |
racket | +1.157 |
Neg logit contributions | |
wcs | -1.061 |
fitt | -1.035 |
fir | -1.027 |
Hatt | -1.023 |
Brid | -1.016 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ROR | +0.591 |
igent | +0.482 |
amily | +0.480 |
=# | +0.459 |
onica | +0.457 |
Neg logit contributions | |
fir | -0.476 |
wcs | -0.476 |
fitt | -0.470 |
Hatt | -0.463 |
Brid | -0.462 |
Token | until |
Token ID | 1566 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ROR | +2.135 |
igent | +1.751 |
amily | +1.718 |
=# | +1.668 |
racket | +1.653 |
Neg logit contributions | |
wcs | -1.783 |
fitt | -1.743 |
Hatt | -1.732 |
fir | -1.717 |
Brid | -1.714 |
Token | golden |
Token ID | 10861 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
ROR | +3.468 |
igent | +2.875 |
amily | +2.818 |
=# | +2.753 |
racket | +2.752 |
Neg logit contributions | |
wcs | -2.657 |
Hatt | -2.573 |
fitt | -2.567 |
Brid | -2.545 |
fir | -2.511 |
Token | brown |
Token ID | 7586 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
ROR | +3.144 |
igent | +2.436 |
amily | +2.382 |
=# | +2.300 |
racket | +2.298 |
Neg logit contributions | |
wcs | -4.304 |
Hatt | -4.186 |
fitt | -4.180 |
fir | -4.146 |
Brid | -4.142 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ROR | +3.589 |
igent | +2.923 |
amily | +2.838 |
=# | +2.787 |
racket | +2.755 |
Neg logit contributions | |
wcs | -3.553 |
fitt | -3.456 |
Hatt | -3.454 |
fir | -3.415 |
Brid | -3.406 |
Token | These |
Token ID | 2312 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ROR | +1.711 |
igent | +1.394 |
amily | +1.367 |
=# | +1.325 |
racket | +1.314 |
Neg logit contributions | |
wcs | -1.510 |
fitt | -1.475 |
Hatt | -1.461 |
fir | -1.460 |
Brid | -1.449 |
Token | are |
Token ID | 389 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
wcs | +0.541 |
fitt | +0.539 |
fir | +0.536 |
Hatt | +0.527 |
Brid | +0.522 |
Neg logit contributions | |
ROR | -0.672 |
igent | -0.553 |
amily | -0.546 |
=# | -0.521 |
onica | -0.520 |
Token | lightly |
Token ID | 15376 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
wcs | +0.159 |
fir | +0.156 |
fitt | +0.156 |
Hatt | +0.154 |
Brid | +0.152 |
Neg logit contributions | |
ROR | -0.205 |
igent | -0.170 |
amily | -0.167 |
onica | -0.161 |
=# | -0.161 |
Token | args |
Token ID | 26498 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
fitt | +1.142 |
wcs | +1.141 |
fir | +1.115 |
Hatt | +1.110 |
Brid | +1.092 |
Neg logit contributions | |
ROR | -2.209 |
igent | -1.868 |
amily | -1.866 |
=# | -1.798 |
onica | -1.785 |
Token | [ |
Token ID | 685 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
wcs | +0.742 |
fitt | +0.723 |
Hatt | +0.716 |
fir | +0.716 |
Brid | +0.710 |
Neg logit contributions | |
ROR | -0.993 |
igent | -0.824 |
amily | -0.809 |
=# | -0.786 |
racket | -0.779 |
Token | " |
Token ID | 366 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
wcs | +0.188 |
fitt | +0.186 |
Hatt | +0.185 |
fir | +0.185 |
Brid | +0.184 |
Neg logit contributions | |
ROR | -0.203 |
igent | -0.165 |
amily | -0.162 |
=# | -0.154 |
onica | -0.153 |
Token | images |
Token ID | 17566 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ROR | +0.741 |
igent | +0.603 |
amily | +0.587 |
=# | +0.573 |
racket | +0.564 |
Neg logit contributions | |
wcs | -0.675 |
fitt | -0.661 |
Hatt | -0.658 |
fir | -0.657 |
Brid | -0.654 |
Token | " |
Token ID | 1 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
wcs | +0.125 |
fitt | +0.122 |
Hatt | +0.122 |
fir | +0.121 |
Brid | +0.121 |
Neg logit contributions | |
ROR | -0.152 |
igent | -0.125 |
amily | -0.123 |
=# | -0.119 |
racket | -0.118 |
Token | ] |
Token ID | 2361 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
wcs | +0.353 |
fitt | +0.349 |
fir | +0.349 |
Hatt | +0.348 |
Brid | +0.347 |
Neg logit contributions | |
ROR | -0.255 |
igent | -0.194 |
amily | -0.190 |
=# | -0.180 |
racket | -0.178 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
wcs | +1.828 |
fitt | +1.826 |
fir | +1.760 |
Hatt | +1.755 |
Brid | +1.698 |
Neg logit contributions | |
ROR | -7.265 |
igent | -6.364 |
amily | -6.360 |
=# | -6.197 |
racket | -6.134 |
Token | : |
Token ID | 1058 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
fitt | +2.289 |
wcs | +2.269 |
fir | +2.259 |
Hatt | +2.228 |
Brid | +2.218 |
Neg logit contributions | |
ROR | -1.914 |
igent | -1.526 |
amily | -1.511 |
=# | -1.409 |
onica | -1.395 |
Token | # |
Token ID | 1303 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
fitt | +2.361 |
wcs | +2.357 |
fir | +2.351 |
Hatt | +2.320 |
Brid | +2.314 |
Neg logit contributions | |
ROR | -1.830 |
igent | -1.471 |
amily | -1.437 |
onica | -1.339 |
=# | -1.320 |
Token | load |
Token ID | 3440 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
fitt | +1.311 |
fir | +1.302 |
wcs | +1.292 |
Hatt | +1.262 |
Brid | +1.231 |
Neg logit contributions | |
ROR | -2.955 |
igent | -2.555 |
amily | -2.509 |
onica | -2.433 |
=# | -2.416 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ROR | +0.510 |
igent | +0.412 |
amily | +0.400 |
=# | +0.394 |
racket | +0.390 |
Neg logit contributions | |
wcs | -0.482 |
fitt | -0.464 |
Hatt | -0.457 |
fir | -0.456 |
Brid | -0.455 |
Token | in |
Token ID | 259 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
wcs | +1.874 |
Hatt | +1.824 |
fitt | +1.816 |
Brid | +1.813 |
fir | +1.812 |
Neg logit contributions | |
ROR | -2.664 |
amily | -2.121 |
igent | -2.120 |
racket | -2.110 |
=# | -2.096 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
wcs | +0.223 |
fitt | +0.218 |
Hatt | +0.217 |
fir | +0.217 |
Brid | +0.216 |
Neg logit contributions | |
ROR | -0.244 |
igent | -0.198 |
amily | -0.195 |
=# | -0.188 |
racket | -0.186 |
Token | Iowa |
Token ID | 9406 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
wcs | +0.555 |
Hatt | +0.536 |
fitt | +0.536 |
fir | +0.532 |
Brid | +0.530 |
Neg logit contributions | |
ROR | -1.041 |
igent | -0.881 |
amily | -0.872 |
=# | -0.848 |
racket | -0.840 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
wcs | +0.362 |
Hatt | +0.353 |
fitt | +0.352 |
fir | +0.352 |
Brid | +0.350 |
Neg logit contributions | |
ROR | -0.444 |
igent | -0.363 |
amily | -0.357 |
=# | -0.346 |
racket | -0.343 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
wcs | +0.434 |
Hatt | +0.427 |
fir | +0.425 |
Brid | +0.423 |
fitt | +0.422 |
Neg logit contributions | |
ROR | -0.665 |
igent | -0.559 |
amily | -0.550 |
=# | -0.530 |
racket | -0.529 |
Token | Caption |
Token ID | 11260 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
wcs | +1.599 |
Hatt | +1.564 |
fitt | +1.556 |
fir | +1.554 |
Brid | +1.544 |
Neg logit contributions | |
ROR | -2.265 |
igent | -1.889 |
amily | -1.863 |
=# | -1.794 |
racket | -1.784 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Hatt | +3.132 |
fir | +3.125 |
Brid | +3.045 |
fitt | +2.988 |
Guth | +2.905 |
Neg logit contributions | |
ROR | -5.702 |
amily | -5.002 |
igent | -4.817 |
racket | -4.621 |
onica | -4.511 |
Token | of |
Token ID | 286 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
wcs | +0.823 |
fitt | +0.803 |
Hatt | +0.795 |
fir | +0.795 |
Brid | +0.789 |
Neg logit contributions | |
ROR | -0.979 |
igent | -0.802 |
amily | -0.786 |
=# | -0.764 |
racket | -0.756 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ROR | +0.072 |
igent | +0.059 |
amily | +0.058 |
=# | +0.057 |
racket | +0.056 |
Neg logit contributions | |
wcs | -0.054 |
fitt | -0.052 |
fir | -0.052 |
Hatt | -0.051 |
Brid | -0.051 |
Token | Photos |
Token ID | 9434 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ROR | +0.119 |
igent | +0.097 |
=# | +0.094 |
amily | +0.094 |
onica | +0.092 |
Neg logit contributions | |
wcs | -0.101 |
fitt | -0.097 |
fir | -0.096 |
Hatt | -0.094 |
Brid | -0.094 |
Token | : |
Token ID | 25 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
wcs | +0.502 |
fitt | +0.492 |
fir | +0.488 |
Hatt | +0.488 |
Brid | +0.484 |
Neg logit contributions | |
ROR | -0.416 |
igent | -0.326 |
amily | -0.318 |
=# | -0.308 |
racket | -0.303 |
Token | me |
Token ID | 502 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
fitt | +1.275 |
fir | +1.274 |
wcs | +1.269 |
Hatt | +1.261 |
Brid | +1.259 |
Neg logit contributions | |
ROR | -1.616 |
igent | -1.322 |
amily | -1.299 |
=# | -1.263 |
racket | -1.241 |
Token | later |
Token ID | 1568 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
wcs | +0.064 |
fitt | +0.063 |
fir | +0.063 |
Hatt | +0.062 |
Brid | +0.062 |
Neg logit contributions | |
ROR | -0.079 |
igent | -0.065 |
amily | -0.063 |
=# | -0.062 |
onica | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ROR | +0.691 |
igent | +0.570 |
amily | +0.559 |
=# | +0.543 |
racket | +0.537 |
Neg logit contributions | |
wcs | -0.548 |
fitt | -0.535 |
fir | -0.532 |
Hatt | -0.532 |
Brid | -0.528 |
Token |
|
Token ID | 198 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ROR | +0.148 |
igent | +0.121 |
amily | +0.119 |
=# | +0.115 |
racket | +0.114 |
Neg logit contributions | |
wcs | -0.130 |
fitt | -0.127 |
Hatt | -0.126 |
fir | -0.126 |
Brid | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
wcs | +0.336 |
Hatt | +0.330 |
fir | +0.330 |
Brid | +0.329 |
fitt | +0.328 |
Neg logit contributions | |
ROR | -0.263 |
igent | -0.207 |
amily | -0.204 |
racket | -0.193 |
=# | -0.193 |
Token | Rated |
Token ID | 15322 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
wcs | +0.335 |
fitt | +0.326 |
fir | +0.325 |
Hatt | +0.324 |
Brid | +0.323 |
Neg logit contributions | |
ROR | -0.328 |
igent | -0.264 |
amily | -0.259 |
=# | -0.250 |
racket | -0.249 |
Token | 5 |
Token ID | 642 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
fir | +2.952 |
Brid | +2.921 |
Hatt | +2.892 |
fitt | +2.885 |
Guth | +2.733 |
Neg logit contributions | |
ROR | -5.563 |
igent | -4.682 |
amily | -4.596 |
tre | -4.463 |
=# | -4.427 |
Token | out |
Token ID | 503 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ROR | +0.057 |
igent | +0.044 |
amily | +0.043 |
=# | +0.042 |
racket | +0.041 |
Neg logit contributions | |
wcs | -0.069 |
fitt | -0.067 |
Hatt | -0.067 |
fir | -0.067 |
Brid | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
wcs | +0.185 |
fitt | +0.181 |
Hatt | +0.178 |
fir | +0.178 |
Brid | +0.177 |
Neg logit contributions | |
ROR | -0.214 |
igent | -0.175 |
amily | -0.171 |
=# | -0.167 |
racket | -0.165 |
Token | 5 |
Token ID | 642 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ROR | +0.108 |
igent | +0.089 |
amily | +0.087 |
=# | +0.085 |
racket | +0.085 |
Neg logit contributions | |
wcs | -0.088 |
fitt | -0.085 |
Hatt | -0.085 |
Brid | -0.084 |
fir | -0.084 |
Token | by |
Token ID | 416 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ROR | +0.620 |
igent | +0.500 |
amily | +0.488 |
=# | +0.475 |
racket | +0.470 |
Neg logit contributions | |
wcs | -0.608 |
fitt | -0.593 |
Hatt | -0.586 |
fir | -0.585 |
Brid | -0.582 |
Token | Women |
Token ID | 6926 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
Hatt | +0.463 |
Brid | +0.458 |
fir | +0.457 |
fitt | +0.457 |
wcs | +0.455 |
Neg logit contributions | |
ROR | -0.626 |
igent | -0.517 |
amily | -0.505 |
=# | -0.487 |
racket | -0.486 |
Token | in |
Token ID | 287 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
wcs | +0.526 |
fitt | +0.514 |
Hatt | +0.511 |
fir | +0.511 |
Brid | +0.507 |
Neg logit contributions | |
ROR | -0.630 |
igent | -0.516 |
amily | -0.507 |
=# | -0.491 |
racket | -0.485 |
Token | politics |
Token ID | 4819 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
wcs | +0.289 |
fitt | +0.283 |
Hatt | +0.281 |
fir | +0.281 |
Brid | +0.279 |
Neg logit contributions | |
ROR | -0.387 |
igent | -0.320 |
amily | -0.314 |
=# | -0.305 |
onica | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
wcs | +0.850 |
fitt | +0.831 |
fir | +0.828 |
Hatt | +0.828 |
Brid | +0.822 |
Neg logit contributions | |
ROR | -1.074 |
igent | -0.882 |
amily | -0.869 |
=# | -0.841 |
onica | -0.830 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
wcs | +0.069 |
fitt | +0.067 |
Hatt | +0.067 |
fir | +0.067 |
Brid | +0.066 |
Neg logit contributions | |
ROR | -0.099 |
igent | -0.082 |
amily | -0.081 |
=# | -0.078 |
racket | -0.078 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
wcs | +1.632 |
Hatt | +1.596 |
fitt | +1.589 |
fir | +1.588 |
Brid | +1.576 |
Neg logit contributions | |
ROR | -2.321 |
igent | -1.936 |
amily | -1.910 |
=# | -1.837 |
onica | -1.829 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Hatt | +2.706 |
fir | +2.677 |
Brid | +2.568 |
wcs | +2.549 |
fitt | +2.498 |
Neg logit contributions | |
ROR | -5.715 |
amily | -4.967 |
igent | -4.950 |
onica | -4.685 |
racket | -4.644 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
wcs | +1.179 |
fitt | +1.151 |
Hatt | +1.141 |
fir | +1.140 |
Brid | +1.132 |
Neg logit contributions | |
ROR | -1.417 |
igent | -1.163 |
amily | -1.140 |
=# | -1.107 |
racket | -1.096 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ROR | +0.822 |
igent | +0.680 |
amily | +0.658 |
=# | +0.657 |
=' | +0.648 |
Neg logit contributions | |
wcs | -0.668 |
fitt | -0.638 |
fir | -0.624 |
Brid | -0.619 |
Hatt | -0.619 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
ROR | +0.114 |
igent | +0.093 |
=# | +0.091 |
amily | +0.090 |
=' | +0.089 |
Neg logit contributions | |
wcs | -0.101 |
fitt | -0.097 |
fir | -0.095 |
Hatt | -0.094 |
heter | -0.093 |
Token | : |
Token ID | 25 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
wcs | +0.022 |
fitt | +0.021 |
fir | +0.021 |
Hatt | +0.021 |
Brid | +0.021 |
Neg logit contributions | |
ROR | -0.017 |
igent | -0.013 |
amily | -0.013 |
=# | -0.013 |
racket | -0.012 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
wcs | +0.043 |
fitt | +0.042 |
fir | +0.042 |
Hatt | +0.042 |
Brid | +0.042 |
Neg logit contributions | |
ROR | -0.041 |
igent | -0.033 |
amily | -0.032 |
=# | -0.031 |
onica | -0.030 |
Token | system |
Token ID | 1080 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
wcs | +0.214 |
fitt | +0.211 |
fir | +0.209 |
Hatt | +0.209 |
Brid | +0.207 |
Neg logit contributions | |
ROR | -0.196 |
igent | -0.155 |
amily | -0.152 |
=# | -0.146 |
onica | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
wcs | +0.375 |
fitt | +0.369 |
fir | +0.366 |
Hatt | +0.365 |
Brid | +0.362 |
Neg logit contributions | |
ROR | -0.462 |
igent | -0.378 |
amily | -0.371 |
=# | -0.360 |
onica | -0.356 |
Token |
|
Token ID | 198 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
wcs | +0.370 |
fitt | +0.363 |
Hatt | +0.363 |
fir | +0.362 |
Brid | +0.360 |
Neg logit contributions | |
ROR | -0.474 |
igent | -0.391 |
amily | -0.383 |
=# | -0.372 |
onica | -0.368 |
Token |
|
Token ID | 198 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
wcs | +0.666 |
fitt | +0.654 |
fir | +0.653 |
Hatt | +0.652 |
Brid | +0.649 |
Neg logit contributions | |
ROR | -0.482 |
igent | -0.370 |
amily | -0.363 |
=# | -0.343 |
racket | -0.341 |
Token | Rated |
Token ID | 15322 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
wcs | +0.659 |
fitt | +0.645 |
fir | +0.642 |
Hatt | +0.642 |
Brid | +0.638 |
Neg logit contributions | |
ROR | -0.490 |
igent | -0.378 |
amily | -0.369 |
=# | -0.352 |
racket | -0.349 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
fir | +2.897 |
Brid | +2.866 |
fitt | +2.865 |
Hatt | +2.839 |
Guth | +2.707 |
Neg logit contributions | |
ROR | -5.433 |
igent | -4.559 |
amily | -4.471 |
=# | -4.320 |
tre | -4.310 |
Token | out |
Token ID | 503 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ROR | +0.282 |
igent | +0.220 |
amily | +0.213 |
=# | +0.207 |
racket | +0.205 |
Neg logit contributions | |
wcs | -0.356 |
fitt | -0.348 |
Hatt | -0.346 |
fir | -0.344 |
Brid | -0.343 |
Token | of |
Token ID | 286 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
wcs | +0.278 |
fitt | +0.272 |
Hatt | +0.268 |
fir | +0.267 |
Brid | +0.266 |
Neg logit contributions | |
ROR | -0.319 |
igent | -0.260 |
amily | -0.254 |
=# | -0.249 |
racket | -0.245 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ROR | +0.187 |
igent | +0.154 |
amily | +0.149 |
=# | +0.148 |
racket | +0.146 |
Neg logit contributions | |
wcs | -0.158 |
fitt | -0.152 |
Hatt | -0.150 |
Brid | -0.149 |
fir | -0.148 |
Token | by |
Token ID | 416 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ROR | +0.792 |
igent | +0.634 |
amily | +0.614 |
=# | +0.604 |
racket | +0.597 |
Neg logit contributions | |
wcs | -0.824 |
fitt | -0.803 |
Hatt | -0.789 |
fir | -0.784 |
Brid | -0.781 |
Token | 20 |
Token ID | 1160 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
wcs | +0.238 |
fitt | +0.228 |
fir | +0.223 |
Hatt | +0.223 |
Brid | +0.220 |
Neg logit contributions | |
ROR | -0.383 |
igent | -0.323 |
amily | -0.316 |
=# | -0.311 |
racket | -0.309 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
wcs | +0.007 |
fitt | +0.007 |
Hatt | +0.007 |
fir | +0.007 |
Brid | +0.007 |
Neg logit contributions | |
ROR | -0.007 |
igent | -0.006 |
amily | -0.006 |
=# | -0.006 |
racket | -0.005 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ROR | +0.135 |
igent | +0.105 |
amily | +0.103 |
=# | +0.099 |
onica | +0.098 |
Neg logit contributions | |
wcs | -0.160 |
fitt | -0.158 |
fir | -0.157 |
Hatt | -0.157 |
Brid | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
wcs | +0.678 |
fir | +0.662 |
Hatt | +0.662 |
fitt | +0.662 |
Brid | +0.657 |
Neg logit contributions | |
ROR | -0.841 |
igent | -0.689 |
amily | -0.677 |
=# | -0.656 |
racket | -0.650 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ROR | +1.282 |
igent | +1.063 |
amily | +1.045 |
=# | +1.021 |
racket | +1.007 |
Neg logit contributions | |
wcs | -0.946 |
fitt | -0.918 |
fir | -0.897 |
Hatt | -0.896 |
Brid | -0.888 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
wcs | +1.616 |
Hatt | +1.579 |
fitt | +1.573 |
fir | +1.571 |
Brid | +1.560 |
Neg logit contributions | |
ROR | -2.290 |
igent | -1.910 |
amily | -1.884 |
=# | -1.812 |
racket | -1.805 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
wcs | +2.939 |
fir | +2.903 |
Hatt | +2.881 |
Brid | +2.869 |
fitt | +2.836 |
Neg logit contributions | |
ROR | -5.371 |
igent | -4.605 |
amily | -4.529 |
onica | -4.349 |
racket | -4.342 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
wcs | +1.211 |
fitt | +1.182 |
fir | +1.175 |
Hatt | +1.175 |
Brid | +1.165 |
Neg logit contributions | |
ROR | -1.489 |
igent | -1.224 |
amily | -1.204 |
=# | -1.163 |
racket | -1.155 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
ROR | +0.953 |
igent | +0.790 |
amily | +0.764 |
=# | +0.763 |
racket | +0.752 |
Neg logit contributions | |
wcs | -0.783 |
fitt | -0.746 |
fir | -0.729 |
Hatt | -0.725 |
Brid | -0.725 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ROR | +0.035 |
igent | +0.028 |
=# | +0.028 |
amily | +0.027 |
=' | +0.027 |
Neg logit contributions | |
wcs | -0.030 |
fitt | -0.029 |
fir | -0.029 |
Hatt | -0.028 |
heter | -0.028 |
Token | : |
Token ID | 25 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ROR | +0.011 |
igent | +0.008 |
amily | +0.008 |
=# | +0.008 |
racket | +0.008 |
Neg logit contributions | |
wcs | -0.013 |
fitt | -0.013 |
fir | -0.013 |
Hatt | -0.013 |
Brid | -0.013 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ROR | +1.427 |
igent | +1.203 |
amily | +1.185 |
=# | +1.156 |
racket | +1.145 |
Neg logit contributions | |
wcs | -0.845 |
fitt | -0.822 |
Hatt | -0.818 |
fir | -0.815 |
Brid | -0.810 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
wcs | +0.261 |
fir | +0.254 |
Hatt | +0.253 |
fitt | +0.253 |
Brid | +0.252 |
Neg logit contributions | |
ROR | -0.301 |
igent | -0.243 |
amily | -0.240 |
=# | -0.232 |
racket | -0.230 |
Token | California |
Token ID | 3442 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
wcs | +0.161 |
fir | +0.154 |
fitt | +0.154 |
Brid | +0.153 |
Hatt | +0.153 |
Neg logit contributions | |
ROR | -0.397 |
igent | -0.339 |
amily | -0.336 |
=# | -0.330 |
racket | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
wcs | +0.624 |
Hatt | +0.607 |
fir | +0.606 |
fitt | +0.604 |
Brid | +0.603 |
Neg logit contributions | |
ROR | -0.786 |
igent | -0.645 |
amily | -0.634 |
=# | -0.613 |
racket | -0.611 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ROR | +1.138 |
igent | +0.946 |
amily | +0.930 |
=# | +0.907 |
racket | +0.896 |
Neg logit contributions | |
wcs | -0.821 |
fitt | -0.799 |
fir | -0.785 |
Hatt | -0.784 |
Brid | -0.776 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
wcs | +1.204 |
fitt | +1.173 |
Hatt | +1.165 |
fir | +1.164 |
Brid | +1.155 |
Neg logit contributions | |
ROR | -1.637 |
igent | -1.358 |
amily | -1.335 |
=# | -1.296 |
racket | -1.285 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
fir | +2.920 |
Hatt | +2.914 |
Brid | +2.856 |
wcs | +2.827 |
Scal | +2.814 |
Neg logit contributions | |
ROR | -4.938 |
igent | -4.219 |
amily | -4.177 |
racket | -3.972 |
onica | -3.943 |
Token | of |
Token ID | 286 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
wcs | +1.764 |
fitt | +1.722 |
fir | +1.722 |
Hatt | +1.719 |
Brid | +1.703 |
Neg logit contributions | |
ROR | -2.265 |
igent | -1.868 |
amily | -1.848 |
=# | -1.771 |
racket | -1.765 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
ROR | +0.152 |
igent | +0.127 |
amily | +0.123 |
=# | +0.122 |
racket | +0.120 |
Neg logit contributions | |
wcs | -0.118 |
fitt | -0.113 |
fir | -0.111 |
Hatt | -0.111 |
Brid | -0.111 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ROR | +0.069 |
igent | +0.056 |
=# | +0.055 |
amily | +0.055 |
=' | +0.053 |
Neg logit contributions | |
wcs | -0.059 |
fitt | -0.058 |
fir | -0.056 |
Hatt | -0.056 |
heter | -0.055 |
Token | : |
Token ID | 25 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
wcs | +0.013 |
fitt | +0.013 |
fir | +0.013 |
Hatt | +0.013 |
Brid | +0.012 |
Neg logit contributions | |
ROR | -0.010 |
igent | -0.008 |
amily | -0.008 |
=# | -0.008 |
racket | -0.007 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
wcs | +0.407 |
fitt | +0.400 |
Hatt | +0.400 |
fir | +0.399 |
Brid | +0.398 |
Neg logit contributions | |
ROR | -0.419 |
igent | -0.335 |
amily | -0.330 |
=# | -0.321 |
onica | -0.316 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
wcs | +0.594 |
fir | +0.580 |
Hatt | +0.576 |
fitt | +0.575 |
Brid | +0.574 |
Neg logit contributions | |
ROR | -0.681 |
igent | -0.548 |
amily | -0.543 |
=# | -0.523 |
racket | -0.520 |
Token | California |
Token ID | 3442 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
wcs | +0.473 |
fitt | +0.455 |
fir | +0.454 |
Hatt | +0.451 |
Brid | +0.448 |
Neg logit contributions | |
ROR | -1.119 |
igent | -0.960 |
amily | -0.952 |
=# | -0.928 |
onica | -0.921 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
wcs | +0.793 |
fir | +0.771 |
Hatt | +0.771 |
fitt | +0.770 |
Brid | +0.765 |
Neg logit contributions | |
ROR | -0.992 |
igent | -0.811 |
amily | -0.799 |
=# | -0.775 |
racket | -0.771 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ROR | +0.099 |
igent | +0.083 |
amily | +0.081 |
=# | +0.079 |
racket | +0.078 |
Neg logit contributions | |
wcs | -0.067 |
fitt | -0.065 |
Hatt | -0.064 |
fir | -0.064 |
Brid | -0.064 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
wcs | +1.625 |
Hatt | +1.588 |
fitt | +1.581 |
fir | +1.579 |
Brid | +1.569 |
Neg logit contributions | |
ROR | -2.305 |
igent | -1.921 |
amily | -1.896 |
=# | -1.824 |
racket | -1.817 |
Token | 9 |
Token ID | 860 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
fir | +3.234 |
Hatt | +3.229 |
Brid | +3.138 |
fitt | +3.115 |
wcs | +3.070 |
Neg logit contributions | |
ROR | -4.702 |
amily | -4.096 |
igent | -3.982 |
onica | -3.724 |
racket | -3.685 |
Token | of |
Token ID | 286 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
wcs | +1.202 |
fitt | +1.173 |
fir | +1.165 |
Hatt | +1.165 |
Brid | +1.155 |
Neg logit contributions | |
ROR | -1.467 |
igent | -1.205 |
amily | -1.184 |
=# | -1.146 |
racket | -1.137 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ROR | +0.433 |
igent | +0.360 |
amily | +0.349 |
=# | +0.346 |
racket | +0.342 |
Neg logit contributions | |
wcs | -0.340 |
fitt | -0.325 |
fir | -0.319 |
Hatt | -0.317 |
Brid | -0.317 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ROR | +0.252 |
igent | +0.205 |
=# | +0.200 |
amily | +0.198 |
=' | +0.195 |
Neg logit contributions | |
wcs | -0.223 |
fitt | -0.216 |
fir | -0.210 |
Hatt | -0.207 |
heter | -0.207 |
Token | : |
Token ID | 25 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ROR | +0.120 |
igent | +0.093 |
amily | +0.090 |
=# | +0.089 |
racket | +0.086 |
Neg logit contributions | |
wcs | -0.152 |
fitt | -0.149 |
fir | -0.147 |
Hatt | -0.147 |
Brid | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
wcs | +0.642 |
fitt | +0.634 |
fir | +0.633 |
Hatt | +0.627 |
Brid | +0.622 |
Neg logit contributions | |
ROR | -0.843 |
igent | -0.695 |
amily | -0.681 |
=# | -0.658 |
onica | -0.655 |
Token | night |
Token ID | 1755 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ROR | +0.355 |
igent | +0.294 |
amily | +0.289 |
=# | +0.281 |
racket | +0.278 |
Neg logit contributions | |
wcs | -0.259 |
fitt | -0.254 |
fir | -0.251 |
Hatt | -0.251 |
Brid | -0.249 |
Token | ! |
Token ID | 0 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
ROR | +0.209 |
igent | +0.172 |
amily | +0.169 |
=# | +0.164 |
onica | +0.162 |
Neg logit contributions | |
wcs | -0.166 |
fitt | -0.163 |
fir | -0.162 |
Hatt | -0.161 |
Brid | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ROR | +0.443 |
igent | +0.360 |
amily | +0.353 |
=# | +0.342 |
racket | +0.338 |
Neg logit contributions | |
wcs | -0.396 |
fitt | -0.387 |
fir | -0.385 |
Hatt | -0.384 |
Brid | -0.382 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
wcs | +0.011 |
fitt | +0.010 |
Hatt | +0.010 |
fir | +0.010 |
Brid | +0.010 |
Neg logit contributions | |
ROR | -0.007 |
igent | -0.006 |
amily | -0.005 |
=# | -0.005 |
racket | -0.005 |
Token | Rated |
Token ID | 15322 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
wcs | +0.288 |
fitt | +0.283 |
Hatt | +0.281 |
fir | +0.281 |
Brid | +0.279 |
Neg logit contributions | |
ROR | -0.209 |
igent | -0.160 |
amily | -0.156 |
=# | -0.149 |
racket | -0.147 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
fir | +2.750 |
fitt | +2.726 |
Brid | +2.714 |
Hatt | +2.691 |
wcs | +2.574 |
Neg logit contributions | |
ROR | -5.056 |
igent | -4.243 |
amily | -4.162 |
=# | -4.015 |
tre | -4.005 |
Token | out |
Token ID | 503 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ROR | +0.464 |
igent | +0.361 |
amily | +0.349 |
=# | +0.340 |
racket | +0.338 |
Neg logit contributions | |
wcs | -0.600 |
fitt | -0.585 |
Hatt | -0.582 |
fir | -0.578 |
Brid | -0.577 |
Token | of |
Token ID | 286 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
wcs | +0.021 |
fitt | +0.021 |
Hatt | +0.021 |
fir | +0.020 |
Brid | +0.020 |
Neg logit contributions | |
ROR | -0.024 |
igent | -0.019 |
amily | -0.019 |
=# | -0.019 |
racket | -0.018 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ROR | +0.414 |
igent | +0.342 |
amily | +0.329 |
=# | +0.328 |
racket | +0.323 |
Neg logit contributions | |
wcs | -0.358 |
fitt | -0.343 |
Hatt | -0.339 |
Brid | -0.335 |
fir | -0.334 |
Token | by |
Token ID | 416 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ROR | +1.014 |
igent | +0.811 |
amily | +0.783 |
=# | +0.772 |
racket | +0.764 |
Neg logit contributions | |
wcs | -1.082 |
fitt | -1.054 |
Hatt | -1.034 |
fir | -1.025 |
Brid | -1.022 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
ROR | +0.208 |
igent | +0.164 |
amily | +0.161 |
=# | +0.156 |
onica | +0.154 |
Neg logit contributions | |
wcs | -0.231 |
fitt | -0.227 |
Hatt | -0.226 |
fir | -0.226 |
Brid | -0.225 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ROR | +0.073 |
igent | +0.059 |
amily | +0.058 |
=# | +0.056 |
racket | +0.055 |
Neg logit contributions | |
wcs | -0.068 |
fitt | -0.067 |
fir | -0.066 |
Hatt | -0.066 |
Brid | -0.066 |
Token | California |
Token ID | 3442 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ROR | +0.145 |
igent | +0.124 |
amily | +0.123 |
=# | +0.120 |
racket | +0.119 |
Neg logit contributions | |
wcs | -0.061 |
fitt | -0.059 |
fir | -0.059 |
Hatt | -0.058 |
Brid | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
wcs | +0.350 |
fitt | +0.340 |
fir | +0.340 |
Hatt | +0.339 |
Brid | +0.337 |
Neg logit contributions | |
ROR | -0.427 |
igent | -0.350 |
amily | -0.344 |
=# | -0.334 |
racket | -0.331 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ROR | +0.433 |
igent | +0.362 |
amily | +0.356 |
=# | +0.345 |
racket | +0.343 |
Neg logit contributions | |
wcs | -0.295 |
fitt | -0.287 |
Hatt | -0.286 |
fir | -0.285 |
Brid | -0.283 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
wcs | +1.546 |
Hatt | +1.509 |
fitt | +1.505 |
fir | +1.501 |
Brid | +1.491 |
Neg logit contributions | |
ROR | -2.170 |
igent | -1.808 |
amily | -1.782 |
=# | -1.718 |
racket | -1.709 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
fir | +2.029 |
Hatt | +2.027 |
wcs | +1.979 |
Brid | +1.951 |
fitt | +1.945 |
Neg logit contributions | |
ROR | -5.714 |
igent | -4.994 |
amily | -4.993 |
racket | -4.778 |
onica | -4.759 |
Token | of |
Token ID | 286 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
wcs | +1.443 |
fitt | +1.408 |
fir | +1.404 |
Hatt | +1.403 |
Brid | +1.391 |
Neg logit contributions | |
ROR | -1.814 |
igent | -1.494 |
amily | -1.474 |
=# | -1.418 |
racket | -1.411 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ROR | +0.166 |
igent | +0.138 |
amily | +0.134 |
=# | +0.132 |
racket | +0.131 |
Neg logit contributions | |
wcs | -0.127 |
fitt | -0.122 |
fir | -0.120 |
Hatt | -0.119 |
Brid | -0.119 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ROR | +0.112 |
igent | +0.092 |
=# | +0.089 |
amily | +0.089 |
=' | +0.087 |
Neg logit contributions | |
wcs | -0.097 |
fitt | -0.094 |
fir | -0.092 |
Hatt | -0.091 |
heter | -0.090 |
Token | : |
Token ID | 25 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
ROR | +0.092 |
igent | +0.071 |
amily | +0.069 |
=# | +0.068 |
racket | +0.066 |
Neg logit contributions | |
wcs | -0.116 |
fitt | -0.114 |
fir | -0.112 |
Hatt | -0.112 |
Brid | -0.111 |
Token | aga |
Token ID | 8126 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ROR | +0.289 |
igent | +0.226 |
amily | +0.221 |
=# | +0.215 |
racket | +0.212 |
Neg logit contributions | |
wcs | -0.328 |
Hatt | -0.319 |
fir | -0.319 |
fitt | -0.318 |
Brid | -0.318 |
Token | , |
Token ID | 11 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ROR | +0.684 |
igent | +0.551 |
amily | +0.541 |
=# | +0.522 |
racket | +0.517 |
Neg logit contributions | |
wcs | -0.665 |
fitt | -0.650 |
Hatt | -0.646 |
fir | -0.646 |
Brid | -0.641 |
Token | California |
Token ID | 3442 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
wcs | +0.363 |
Hatt | +0.355 |
fitt | +0.353 |
fir | +0.353 |
Brid | +0.351 |
Neg logit contributions | |
ROR | -0.750 |
igent | -0.637 |
amily | -0.631 |
=# | -0.614 |
racket | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
wcs | +0.672 |
fir | +0.654 |
Hatt | +0.653 |
fitt | +0.652 |
Brid | +0.649 |
Neg logit contributions | |
ROR | -0.833 |
igent | -0.680 |
amily | -0.671 |
=# | -0.650 |
racket | -0.647 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ROR | +0.642 |
igent | +0.536 |
amily | +0.527 |
=# | +0.512 |
racket | +0.508 |
Neg logit contributions | |
wcs | -0.442 |
fitt | -0.430 |
Hatt | -0.428 |
fir | -0.428 |
Brid | -0.425 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
wcs | +1.455 |
Hatt | +1.420 |
fitt | +1.417 |
fir | +1.413 |
Brid | +1.404 |
Neg logit contributions | |
ROR | -2.045 |
igent | -1.704 |
amily | -1.679 |
=# | -1.619 |
racket | -1.611 |
Token | 13 |
Token ID | 1511 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Hatt | +2.510 |
fir | +2.476 |
Brid | +2.311 |
Scal | +2.297 |
fitt | +2.292 |
Neg logit contributions | |
ROR | -5.266 |
amily | -4.640 |
igent | -4.528 |
racket | -4.304 |
=# | -4.246 |
Token | of |
Token ID | 286 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
wcs | +1.988 |
fir | +1.939 |
fitt | +1.939 |
Hatt | +1.938 |
Brid | +1.919 |
Neg logit contributions | |
ROR | -2.556 |
igent | -2.110 |
amily | -2.084 |
=# | -1.999 |
racket | -1.993 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ROR | +0.311 |
igent | +0.258 |
amily | +0.251 |
=# | +0.248 |
racket | +0.245 |
Neg logit contributions | |
wcs | -0.241 |
fitt | -0.231 |
fir | -0.227 |
Hatt | -0.226 |
Brid | -0.225 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ROR | +0.095 |
igent | +0.078 |
=# | +0.075 |
amily | +0.075 |
=' | +0.074 |
Neg logit contributions | |
wcs | -0.082 |
fitt | -0.079 |
fir | -0.077 |
Hatt | -0.076 |
heter | -0.076 |
Token | : |
Token ID | 25 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ROR | +0.193 |
igent | +0.150 |
amily | +0.145 |
=# | +0.143 |
racket | +0.138 |
Neg logit contributions | |
wcs | -0.247 |
fitt | -0.242 |
fir | -0.238 |
Hatt | -0.238 |
Brid | -0.237 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ROR | +1.556 |
igent | +1.255 |
amily | +1.224 |
=# | +1.183 |
onica | +1.170 |
Neg logit contributions | |
wcs | -1.584 |
fitt | -1.552 |
fir | -1.532 |
Hatt | -1.523 |
Brid | -1.512 |
Token | New |
Token ID | 968 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
wcs | +0.114 |
fitt | +0.112 |
Hatt | +0.112 |
fir | +0.111 |
Brid | +0.111 |
Neg logit contributions | |
ROR | -0.194 |
igent | -0.163 |
amily | -0.162 |
=# | -0.157 |
onica | -0.155 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
wcs | +0.536 |
fitt | +0.505 |
Hatt | +0.495 |
fir | +0.495 |
Brid | +0.486 |
Neg logit contributions | |
ROR | -2.277 |
igent | -2.002 |
amily | -1.979 |
=# | -1.940 |
racket | -1.929 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ROR | +1.397 |
igent | +1.145 |
amily | +1.120 |
=# | +1.083 |
onica | +1.074 |
Neg logit contributions | |
wcs | -1.257 |
fitt | -1.233 |
fir | -1.212 |
Hatt | -1.211 |
Brid | -1.200 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ROR | +0.943 |
igent | +0.783 |
amily | +0.769 |
=# | +0.751 |
racket | +0.742 |
Neg logit contributions | |
wcs | -0.680 |
fitt | -0.662 |
fir | -0.649 |
Hatt | -0.649 |
Brid | -0.642 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
wcs | +1.403 |
fitt | +1.366 |
Hatt | +1.362 |
fir | +1.359 |
Brid | +1.348 |
Neg logit contributions | |
ROR | -1.938 |
igent | -1.612 |
amily | -1.587 |
=# | -1.535 |
racket | -1.524 |
Token | 6 |
Token ID | 718 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
wcs | +2.786 |
fir | +2.775 |
Hatt | +2.734 |
Brid | +2.726 |
fitt | +2.720 |
Neg logit contributions | |
ROR | -4.920 |
igent | -4.157 |
amily | -4.127 |
racket | -3.965 |
onica | -3.944 |
Token | of |
Token ID | 286 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
wcs | +0.403 |
fitt | +0.393 |
Hatt | +0.388 |
fir | +0.387 |
Brid | +0.385 |
Neg logit contributions | |
ROR | -0.458 |
igent | -0.374 |
amily | -0.365 |
=# | -0.358 |
racket | -0.352 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ROR | +0.500 |
igent | +0.415 |
amily | +0.404 |
=# | +0.399 |
racket | +0.394 |
Neg logit contributions | |
wcs | -0.389 |
fitt | -0.374 |
fir | -0.367 |
Hatt | -0.365 |
Brid | -0.365 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ROR | +0.177 |
igent | +0.144 |
=# | +0.141 |
amily | +0.139 |
=' | +0.138 |
Neg logit contributions | |
wcs | -0.156 |
fitt | -0.151 |
fir | -0.147 |
Hatt | -0.145 |
heter | -0.145 |
Token | : |
Token ID | 25 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
wcs | +0.244 |
fitt | +0.239 |
fir | +0.236 |
Hatt | +0.236 |
Brid | +0.235 |
Neg logit contributions | |
ROR | -0.199 |
igent | -0.155 |
amily | -0.151 |
=# | -0.147 |
racket | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
wcs | +0.122 |
Hatt | +0.120 |
fitt | +0.120 |
fir | +0.119 |
Brid | +0.119 |
Neg logit contributions | |
ROR | -0.126 |
igent | -0.102 |
amily | -0.100 |
=# | -0.096 |
racket | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
wcs | +0.880 |
fitt | +0.864 |
Hatt | +0.862 |
fir | +0.862 |
Brid | +0.857 |
Neg logit contributions | |
ROR | -0.627 |
igent | -0.480 |
amily | -0.469 |
=# | -0.446 |
racket | -0.441 |
Token | No |
Token ID | 2949 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
wcs | +0.319 |
fitt | +0.308 |
Hatt | +0.308 |
fir | +0.306 |
Brid | +0.305 |
Neg logit contributions | |
ROR | -0.596 |
igent | -0.509 |
amily | -0.503 |
=# | -0.488 |
racket | -0.487 |
Token | one |
Token ID | 530 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
wcs | +0.391 |
fitt | +0.383 |
fir | +0.380 |
Hatt | +0.379 |
Brid | +0.375 |
Neg logit contributions | |
ROR | -0.531 |
igent | -0.439 |
amily | -0.432 |
=# | -0.420 |
racket | -0.415 |
Token | knows |
Token ID | 4206 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
fitt | +1.642 |
wcs | +1.637 |
fir | +1.627 |
Hatt | +1.612 |
Brid | +1.599 |
Neg logit contributions | |
ROR | -2.430 |
igent | -2.010 |
amily | -1.988 |
=# | -1.931 |
onica | -1.915 |
Token | exactly |
Token ID | 3446 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
wcs | +1.435 |
fir | +1.409 |
fitt | +1.406 |
Hatt | +1.400 |
Brid | +1.384 |
Neg logit contributions | |
ROR | -2.220 |
igent | -1.867 |
amily | -1.842 |
=# | -1.788 |
onica | -1.776 |
Token | how |
Token ID | 703 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
fir | +2.681 |
wcs | +2.671 |
fitt | +2.647 |
Hatt | +2.621 |
Brid | +2.614 |
Neg logit contributions | |
ROR | -5.012 |
igent | -4.236 |
amily | -4.185 |
=# | -4.061 |
onica | -4.019 |
Token | they |
Token ID | 484 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
wcs | +1.353 |
fitt | +1.352 |
Hatt | +1.347 |
Brid | +1.335 |
fir | +1.333 |
Neg logit contributions | |
ROR | -2.153 |
igent | -1.793 |
amily | -1.785 |
=# | -1.718 |
onica | -1.690 |
Token | were |
Token ID | 547 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
ROR | +0.336 |
igent | +0.279 |
amily | +0.274 |
=# | +0.266 |
racket | +0.264 |
Neg logit contributions | |
wcs | -0.247 |
fitt | -0.240 |
Hatt | -0.239 |
fir | -0.238 |
Brid | -0.236 |
Token | made |
Token ID | 925 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ROR | +0.667 |
igent | +0.548 |
amily | +0.538 |
=# | +0.521 |
racket | +0.517 |
Neg logit contributions | |
wcs | -0.551 |
fitt | -0.537 |
Hatt | -0.533 |
fir | -0.533 |
Brid | -0.529 |
Token | — |
Token ID | 851 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
wcs | +0.695 |
fitt | +0.680 |
fir | +0.676 |
Hatt | +0.675 |
Brid | +0.669 |
Neg logit contributions | |
ROR | -0.814 |
igent | -0.664 |
amily | -0.653 |
=# | -0.633 |
onica | -0.626 |
Token | Grove |
Token ID | 24144 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ROR | +1.029 |
igent | +0.803 |
amily | +0.782 |
=# | +0.748 |
racket | +0.739 |
Neg logit contributions | |
wcs | -1.342 |
fitt | -1.317 |
fir | -1.303 |
Hatt | -1.302 |
Brid | -1.293 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ROR | +0.866 |
igent | +0.701 |
amily | +0.685 |
=# | +0.662 |
racket | +0.655 |
Neg logit contributions | |
wcs | -0.857 |
fitt | -0.839 |
Hatt | -0.831 |
fir | -0.830 |
Brid | -0.824 |
Token | California |
Token ID | 3442 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
wcs | +0.585 |
fitt | +0.566 |
fir | +0.565 |
Hatt | +0.565 |
Brid | +0.561 |
Neg logit contributions | |
ROR | -1.387 |
igent | -1.187 |
amily | -1.177 |
=# | -1.148 |
onica | -1.139 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
wcs | +0.620 |
fitt | +0.604 |
fir | +0.603 |
Hatt | +0.602 |
Brid | +0.598 |
Neg logit contributions | |
ROR | -0.767 |
igent | -0.627 |
amily | -0.616 |
=# | -0.598 |
racket | -0.594 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ROR | +0.304 |
igent | +0.254 |
amily | +0.250 |
=# | +0.243 |
racket | +0.241 |
Neg logit contributions | |
wcs | -0.206 |
fitt | -0.200 |
Hatt | -0.198 |
fir | -0.198 |
Brid | -0.197 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
wcs | +1.498 |
Hatt | +1.461 |
fitt | +1.460 |
fir | +1.454 |
Brid | +1.445 |
Neg logit contributions | |
ROR | -2.095 |
igent | -1.745 |
amily | -1.719 |
=# | -1.658 |
racket | -1.649 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Hatt | +2.727 |
fir | +2.671 |
Brid | +2.625 |
fitt | +2.601 |
wcs | +2.548 |
Neg logit contributions | |
ROR | -4.940 |
amily | -4.247 |
igent | -4.187 |
=# | -3.965 |
racket | -3.960 |
Token | of |
Token ID | 286 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
wcs | +1.392 |
fitt | +1.359 |
Hatt | +1.350 |
fir | +1.350 |
Brid | +1.340 |
Neg logit contributions | |
ROR | -1.706 |
igent | -1.402 |
amily | -1.379 |
=# | -1.333 |
racket | -1.323 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
ROR | +0.650 |
igent | +0.539 |
amily | +0.523 |
=# | +0.520 |
=' | +0.513 |
Neg logit contributions | |
wcs | -0.518 |
fitt | -0.495 |
fir | -0.487 |
Hatt | -0.482 |
Brid | -0.481 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ROR | +0.502 |
igent | +0.380 |
amily | +0.369 |
=# | +0.353 |
racket | +0.347 |
Neg logit contributions | |
wcs | -0.743 |
fitt | -0.729 |
fir | -0.722 |
Hatt | -0.721 |
Brid | -0.717 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ROR | +0.012 |
igent | +0.009 |
amily | +0.009 |
=# | +0.009 |
racket | +0.009 |
Neg logit contributions | |
wcs | -0.019 |
fitt | -0.018 |
fir | -0.018 |
Hatt | -0.018 |
Brid | -0.018 |
Token | Hills |
Token ID | 14379 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
ROR | +0.522 |
igent | +0.423 |
amily | +0.415 |
=# | +0.401 |
racket | +0.397 |
Neg logit contributions | |
wcs | -0.483 |
fitt | -0.472 |
fir | -0.469 |
Hatt | -0.469 |
Brid | -0.465 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ROR | +0.716 |
igent | +0.578 |
amily | +0.567 |
=# | +0.547 |
racket | +0.542 |
Neg logit contributions | |
wcs | -0.689 |
fitt | -0.674 |
Hatt | -0.669 |
fir | -0.669 |
Brid | -0.664 |
Token | California |
Token ID | 3442 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
wcs | +0.238 |
fitt | +0.229 |
Hatt | +0.228 |
fir | +0.228 |
Brid | +0.225 |
Neg logit contributions | |
ROR | -0.535 |
igent | -0.457 |
amily | -0.452 |
=# | -0.442 |
racket | -0.438 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
wcs | +0.436 |
fitt | +0.424 |
fir | +0.424 |
Hatt | +0.423 |
Brid | +0.420 |
Neg logit contributions | |
ROR | -0.532 |
igent | -0.435 |
amily | -0.428 |
=# | -0.416 |
racket | -0.412 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ROR | +0.518 |
igent | +0.433 |
amily | +0.426 |
=# | +0.414 |
racket | +0.410 |
Neg logit contributions | |
wcs | -0.350 |
fitt | -0.340 |
Hatt | -0.338 |
fir | -0.338 |
Brid | -0.335 |
Token | Caption |
Token ID | 11260 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
wcs | +1.468 |
Hatt | +1.432 |
fitt | +1.430 |
fir | +1.425 |
Brid | +1.416 |
Neg logit contributions | |
ROR | -2.056 |
igent | -1.712 |
amily | -1.687 |
=# | -1.627 |
racket | -1.618 |
Token | 14 |
Token ID | 1478 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
wcs | +2.329 |
Hatt | +2.288 |
fir | +2.280 |
fitt | +2.259 |
Brid | +2.226 |
Neg logit contributions | |
ROR | -5.212 |
igent | -4.477 |
amily | -4.437 |
=# | -4.265 |
racket | -4.254 |
Token | of |
Token ID | 286 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
wcs | +1.899 |
fir | +1.853 |
fitt | +1.852 |
Hatt | +1.851 |
Brid | +1.832 |
Neg logit contributions | |
ROR | -2.436 |
igent | -2.008 |
amily | -1.985 |
=# | -1.904 |
racket | -1.898 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ROR | +0.367 |
igent | +0.305 |
amily | +0.297 |
=# | +0.294 |
racket | +0.290 |
Neg logit contributions | |
wcs | -0.285 |
fitt | -0.274 |
fir | -0.269 |
Hatt | -0.267 |
Brid | -0.267 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ROR | +0.086 |
igent | +0.070 |
=# | +0.068 |
amily | +0.068 |
onica | +0.066 |
Neg logit contributions | |
wcs | -0.074 |
fitt | -0.071 |
fir | -0.070 |
Hatt | -0.069 |
heter | -0.068 |
Token | : |
Token ID | 25 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ROR | +0.275 |
igent | +0.213 |
amily | +0.205 |
=# | +0.203 |
racket | +0.197 |
Neg logit contributions | |
wcs | -0.354 |
fitt | -0.347 |
fir | -0.341 |
Hatt | -0.341 |
Brid | -0.339 |
Token | < |
Token ID | 27 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
wcs | +1.312 |
fitt | +1.291 |
Hatt | +1.287 |
fir | +1.282 |
Brid | +1.271 |
Neg logit contributions | |
ROR | -2.057 |
igent | -1.724 |
amily | -1.700 |
=# | -1.644 |
racket | -1.636 |
Token | Part |
Token ID | 2142 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
wcs | +0.091 |
fitt | +0.089 |
Hatt | +0.088 |
fir | +0.088 |
Brid | +0.088 |
Neg logit contributions | |
ROR | -0.109 |
igent | -0.090 |
amily | -0.088 |
=# | -0.085 |
racket | -0.085 |
Token | icle |
Token ID | 1548 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
wcs | +1.114 |
fir | +1.077 |
fitt | +1.074 |
Hatt | +1.072 |
Brid | +1.066 |
Neg logit contributions | |
ROR | -1.851 |
igent | -1.543 |
amily | -1.535 |
racket | -1.486 |
=# | -1.483 |
Token | > |
Token ID | 1875 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
wcs | +1.447 |
fitt | +1.412 |
fir | +1.407 |
Hatt | +1.405 |
Brid | +1.394 |
Neg logit contributions | |
ROR | -1.590 |
igent | -1.294 |
amily | -1.271 |
=# | -1.215 |
racket | -1.212 |
Token | & |
Token ID | 1222 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
fitt | +2.708 |
fir | +2.702 |
wcs | +2.672 |
Hatt | +2.656 |
Brid | +2.625 |
Neg logit contributions | |
ROR | -4.097 |
igent | -3.428 |
amily | -3.393 |
=# | -3.249 |
onica | -3.234 |
Token | particles |
Token ID | 13166 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
wcs | +1.789 |
fitt | +1.774 |
fir | +1.760 |
Hatt | +1.745 |
Brid | +1.728 |
Neg logit contributions | |
ROR | -2.085 |
igent | -1.699 |
amily | -1.684 |
=# | -1.611 |
onica | -1.594 |
Token | ) |
Token ID | 1267 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
wcs | +2.160 |
fitt | +2.083 |
Hatt | +2.036 |
fir | +2.025 |
Brid | +2.013 |
Neg logit contributions | |
ROR | -5.272 |
igent | -4.541 |
amily | -4.511 |
racket | -4.410 |
=# | -4.345 |
Token | { |
Token ID | 1391 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
wcs | +0.609 |
fitt | +0.599 |
fir | +0.598 |
Hatt | +0.592 |
Brid | +0.590 |
Neg logit contributions | |
ROR | -0.748 |
igent | -0.617 |
amily | -0.606 |
=# | -0.583 |
onica | -0.581 |
Token | density |
Token ID | 12109 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
wcs | +0.481 |
fitt | +0.472 |
fir | +0.468 |
Hatt | +0.467 |
Brid | +0.465 |
Neg logit contributions | |
ROR | -0.613 |
igent | -0.505 |
amily | -0.497 |
=# | -0.481 |
onica | -0.477 |
Token | Grid |
Token ID | 41339 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
wcs | +0.803 |
fitt | +0.769 |
Hatt | +0.767 |
fir | +0.760 |
Brid | +0.757 |
Neg logit contributions | |
ROR | -1.799 |
igent | -1.544 |
amily | -1.528 |
racket | -1.484 |
onica | -1.477 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
wcs | +1.374 |
fitt | +1.345 |
fir | +1.337 |
Hatt | +1.336 |
Brid | +1.325 |
Neg logit contributions | |
ROR | -1.895 |
igent | -1.577 |
amily | -1.545 |
racket | -1.493 |
onica | -1.488 |
Token | the |
Token ID | 262 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ROR | +0.625 |
igent | +0.516 |
amily | +0.508 |
=# | +0.490 |
onica | +0.487 |
Neg logit contributions | |
wcs | -0.486 |
fitt | -0.477 |
Hatt | -0.476 |
fir | -0.474 |
Brid | -0.473 |
Token | entrance |
Token ID | 10384 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
wcs | +0.239 |
Hatt | +0.238 |
Brid | +0.237 |
fitt | +0.237 |
fir | +0.236 |
Neg logit contributions | |
ROR | -0.282 |
igent | -0.232 |
amily | -0.229 |
=# | -0.220 |
onica | -0.218 |
Token | to |
Token ID | 284 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ROR | +0.245 |
igent | +0.200 |
amily | +0.198 |
=# | +0.190 |
onica | +0.188 |
Neg logit contributions | |
wcs | -0.214 |
fitt | -0.210 |
fir | -0.208 |
Hatt | -0.207 |
Brid | -0.207 |
Token | the |
Token ID | 262 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
ROR | +0.492 |
igent | +0.405 |
amily | +0.399 |
=# | +0.386 |
onica | +0.382 |
Neg logit contributions | |
wcs | -0.388 |
fitt | -0.381 |
Hatt | -0.380 |
fir | -0.378 |
Brid | -0.378 |
Token | ch |
Token ID | 442 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ROR | +0.327 |
igent | +0.266 |
amily | +0.262 |
=# | +0.253 |
onica | +0.250 |
Neg logit contributions | |
wcs | -0.295 |
fitt | -0.291 |
fir | -0.289 |
Hatt | -0.289 |
Brid | -0.288 |
Token | ow |
Token ID | 322 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
ROR | +0.445 |
igent | +0.371 |
amily | +0.365 |
=# | +0.354 |
racket | +0.351 |
Neg logit contributions | |
wcs | -0.318 |
fitt | -0.309 |
Hatt | -0.307 |
fir | -0.307 |
Brid | -0.304 |
Token | hall |
Token ID | 6899 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
fir | +3.847 |
fitt | +3.775 |
wcs | +3.750 |
heter | +3.741 |
Brid | +3.737 |
Neg logit contributions | |
ROR | -3.588 |
igent | -2.774 |
amily | -2.745 |
=# | -2.732 |
onica | -2.658 |
Token | , |
Token ID | 11 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
ROR | +1.700 |
igent | +1.390 |
amily | +1.360 |
=# | +1.317 |
racket | +1.308 |
Neg logit contributions | |
wcs | -1.492 |
fitt | -1.457 |
Hatt | -1.447 |
fir | -1.446 |
Brid | -1.433 |
Token | known |
Token ID | 1900 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ROR | +0.527 |
igent | +0.441 |
amily | +0.434 |
=# | +0.422 |
racket | +0.418 |
Neg logit contributions | |
wcs | -0.356 |
fitt | -0.347 |
Hatt | -0.344 |
fir | -0.344 |
Brid | -0.341 |
Token | as |
Token ID | 355 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ROR | +0.748 |
igent | +0.607 |
amily | +0.596 |
=# | +0.575 |
racket | +0.569 |
Neg logit contributions | |
wcs | -0.699 |
fitt | -0.683 |
fir | -0.679 |
Hatt | -0.678 |
Brid | -0.674 |
Token | � |
Token ID | 564 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
ROR | +0.956 |
igent | +0.789 |
amily | +0.774 |
=# | +0.748 |
onica | +0.743 |
Neg logit contributions | |
wcs | -0.760 |
fitt | -0.744 |
Hatt | -0.741 |
fir | -0.739 |
Brid | -0.736 |
Token | Piece |
Token ID | 27053 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ROR | +0.584 |
igent | +0.476 |
amily | +0.467 |
=# | +0.454 |
racket | +0.450 |
Neg logit contributions | |
wcs | -0.509 |
fitt | -0.497 |
fir | -0.492 |
Hatt | -0.492 |
Brid | -0.487 |
Token | > |
Token ID | 1875 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
wcs | +0.109 |
fitt | +0.106 |
Hatt | +0.106 |
fir | +0.106 |
Brid | +0.105 |
Neg logit contributions | |
ROR | -0.114 |
igent | -0.092 |
amily | -0.091 |
=# | -0.088 |
racket | -0.087 |
Token | ; |
Token ID | 2162 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
wcs | +2.822 |
Hatt | +2.781 |
fir | +2.763 |
fitt | +2.732 |
Brid | +2.728 |
Neg logit contributions | |
ROR | -3.102 |
igent | -2.531 |
amily | -2.496 |
onica | -2.376 |
=# | -2.366 |
Token | 64 |
Token ID | 5598 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
wcs | +1.617 |
fitt | +1.584 |
fir | +1.582 |
Hatt | +1.578 |
Brid | +1.569 |
Neg logit contributions | |
ROR | -1.631 |
igent | -1.318 |
amily | -1.297 |
=# | -1.242 |
onica | -1.240 |
Token | ], |
Token ID | 16589 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
wcs | +0.559 |
fitt | +0.543 |
Hatt | +0.541 |
fir | +0.540 |
Brid | +0.535 |
Neg logit contributions | |
ROR | -0.718 |
igent | -0.593 |
amily | -0.583 |
=# | -0.565 |
racket | -0.560 |
Token | // |
Token ID | 3373 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
wcs | +2.633 |
fitt | +2.623 |
fir | +2.594 |
Hatt | +2.570 |
Brid | +2.554 |
Neg logit contributions | |
ROR | -2.448 |
igent | -1.960 |
amily | -1.933 |
onica | -1.860 |
=# | -1.831 |
Token | Where |
Token ID | 6350 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
wcs | +3.103 |
fitt | +3.088 |
Brid | +3.079 |
Hatt | +3.073 |
fir | +3.069 |
Neg logit contributions | |
ROR | -4.308 |
igent | -3.582 |
amily | -3.506 |
onica | -3.410 |
=# | -3.354 |
Token | are |
Token ID | 389 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ROR | +1.100 |
igent | +0.904 |
amily | +0.884 |
=# | +0.860 |
racket | +0.854 |
Neg logit contributions | |
wcs | -0.935 |
fitt | -0.906 |
Hatt | -0.902 |
fir | -0.901 |
Brid | -0.894 |
Token | the |
Token ID | 262 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
ROR | +0.732 |
igent | +0.608 |
amily | +0.597 |
=# | +0.581 |
racket | +0.577 |
Neg logit contributions | |
wcs | -0.539 |
fitt | -0.523 |
Hatt | -0.519 |
fir | -0.519 |
Brid | -0.515 |
Token | pieces |
Token ID | 5207 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ROR | +0.808 |
igent | +0.679 |
amily | +0.668 |
=# | +0.651 |
racket | +0.647 |
Neg logit contributions | |
wcs | -0.501 |
fitt | -0.485 |
Hatt | -0.481 |
fir | -0.481 |
Brid | -0.477 |
Token | ? |
Token ID | 30 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ROR | +0.612 |
igent | +0.503 |
amily | +0.494 |
=# | +0.479 |
racket | +0.475 |
Neg logit contributions | |
wcs | -0.497 |
fitt | -0.484 |
Hatt | -0.481 |
fir | -0.481 |
Brid | -0.477 |
Token | particles |
Token ID | 13166 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ROR | +0.731 |
igent | +0.573 |
amily | +0.559 |
=# | +0.538 |
racket | +0.533 |
Neg logit contributions | |
wcs | -0.879 |
fitt | -0.860 |
Hatt | -0.855 |
fir | -0.854 |
Brid | -0.849 |
Token | represent |
Token ID | 2380 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
wcs | +0.720 |
fitt | +0.710 |
fir | +0.705 |
Hatt | +0.698 |
Brid | +0.692 |
Neg logit contributions | |
ROR | -1.005 |
igent | -0.833 |
amily | -0.822 |
=# | -0.797 |
onica | -0.789 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
ROR | +0.287 |
igent | +0.235 |
amily | +0.231 |
=# | +0.223 |
racket | +0.221 |
Neg logit contributions | |
wcs | -0.241 |
fitt | -0.236 |
fir | -0.234 |
Hatt | -0.234 |
Brid | -0.232 |
Token | so |
Token ID | 523 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
ROR | +0.308 |
igent | +0.253 |
amily | +0.249 |
=# | +0.241 |
onica | +0.238 |
Neg logit contributions | |
wcs | -0.257 |
fitt | -0.252 |
fir | -0.250 |
Hatt | -0.249 |
Brid | -0.248 |
Token | multiply |
Token ID | 29162 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ROR | +0.075 |
igent | +0.062 |
amily | +0.061 |
=# | +0.059 |
onica | +0.059 |
Neg logit contributions | |
wcs | -0.058 |
fitt | -0.057 |
fir | -0.056 |
Hatt | -0.056 |
Brid | -0.055 |
Token | // |
Token ID | 3373 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
ROR | +1.209 |
igent | +0.990 |
amily | +0.973 |
=# | +0.940 |
racket | +0.933 |
Neg logit contributions | |
wcs | -1.024 |
fitt | -1.002 |
fir | -0.994 |
Hatt | -0.993 |
Brid | -0.986 |
Token | by |
Token ID | 416 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
fir | +3.040 |
wcs | +3.026 |
fitt | +3.013 |
Hatt | +3.002 |
Brid | +2.998 |
Neg logit contributions | |
ROR | -4.265 |
igent | -3.526 |
amily | -3.477 |
onica | -3.377 |
tre | -3.328 |
Token | the |
Token ID | 262 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
ROR | +0.530 |
igent | +0.436 |
amily | +0.429 |
=# | +0.415 |
onica | +0.411 |
Neg logit contributions | |
wcs | -0.429 |
fitt | -0.420 |
fir | -0.417 |
Hatt | -0.417 |
Brid | -0.414 |
Token | ratio |
Token ID | 8064 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
wcs | +0.336 |
fitt | +0.330 |
fir | +0.327 |
Hatt | +0.326 |
Brid | +0.324 |
Neg logit contributions | |
ROR | -0.475 |
igent | -0.396 |
amily | -0.391 |
=# | -0.378 |
onica | -0.375 |
Token | of |
Token ID | 286 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
ROR | +0.220 |
igent | +0.182 |
amily | +0.179 |
=# | +0.173 |
racket | +0.171 |
Neg logit contributions | |
wcs | -0.172 |
fitt | -0.168 |
fir | -0.167 |
Hatt | -0.166 |
Brid | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ROR | +0.727 |
igent | +0.599 |
amily | +0.590 |
=# | +0.571 |
racket | +0.565 |
Neg logit contributions | |
wcs | -0.573 |
fitt | -0.560 |
fir | -0.556 |
Hatt | -0.555 |
Brid | -0.551 |
Token | 6 |
Token ID | 718 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
wcs | +1.564 |
fitt | +1.557 |
fir | +1.546 |
Brid | +1.528 |
Hatt | +1.518 |
Neg logit contributions | |
ROR | -2.738 |
igent | -2.302 |
amily | -2.268 |
=# | -2.215 |
onica | -2.194 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
wcs | +0.482 |
fitt | +0.474 |
fir | +0.469 |
Hatt | +0.468 |
Brid | +0.466 |
Neg logit contributions | |
ROR | -0.603 |
igent | -0.496 |
amily | -0.487 |
=# | -0.474 |
racket | -0.467 |
Token | No |
Token ID | 1400 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
wcs | +0.671 |
Hatt | +0.661 |
fitt | +0.658 |
Brid | +0.656 |
fir | +0.656 |
Neg logit contributions | |
ROR | -0.891 |
igent | -0.739 |
amily | -0.727 |
=# | -0.701 |
onica | -0.696 |
Token | word |
Token ID | 1573 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
wcs | +0.227 |
fitt | +0.222 |
fir | +0.221 |
Hatt | +0.220 |
Brid | +0.218 |
Neg logit contributions | |
ROR | -0.284 |
igent | -0.234 |
amily | -0.229 |
=# | -0.222 |
onica | -0.220 |
Token | on |
Token ID | 319 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
wcs | +1.956 |
fir | +1.949 |
fitt | +1.943 |
Hatt | +1.894 |
Brid | +1.891 |
Neg logit contributions | |
ROR | -3.135 |
igent | -2.605 |
amily | -2.584 |
=# | -2.524 |
onica | -2.502 |
Token | if |
Token ID | 611 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
wcs | +1.848 |
fitt | +1.819 |
fir | +1.813 |
Hatt | +1.792 |
Brid | +1.783 |
Neg logit contributions | |
ROR | -2.726 |
igent | -2.276 |
amily | -2.244 |
=# | -2.186 |
onica | -2.156 |
Token | there |
Token ID | 612 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
wcs | +2.885 |
fitt | +2.834 |
Hatt | +2.824 |
fir | +2.822 |
Brid | +2.809 |
Neg logit contributions | |
ROR | -4.576 |
igent | -3.790 |
amily | -3.737 |
=# | -3.648 |
onica | -3.586 |
Token | will |
Token ID | 481 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
wcs | +0.226 |
fitt | +0.221 |
fir | +0.219 |
Hatt | +0.219 |
Brid | +0.217 |
Neg logit contributions | |
ROR | -0.304 |
igent | -0.252 |
amily | -0.248 |
=# | -0.241 |
racket | -0.238 |
Token | be |
Token ID | 307 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
wcs | +0.701 |
fitt | +0.686 |
fir | +0.683 |
Hatt | +0.679 |
Brid | +0.677 |
Neg logit contributions | |
ROR | -0.765 |
igent | -0.620 |
amily | -0.608 |
=# | -0.591 |
racket | -0.580 |
Token | a |
Token ID | 257 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
wcs | +0.515 |
fitt | +0.502 |
fir | +0.499 |
Hatt | +0.497 |
Brid | +0.494 |
Neg logit contributions | |
ROR | -0.748 |
igent | -0.623 |
amily | -0.613 |
=# | -0.596 |
onica | -0.589 |
Token | pre |
Token ID | 662 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
wcs | +0.457 |
fitt | +0.447 |
fir | +0.445 |
Hatt | +0.444 |
Brid | +0.441 |
Neg logit contributions | |
ROR | -0.548 |
igent | -0.449 |
amily | -0.440 |
=# | -0.427 |
onica | -0.421 |
Token | So |
Token ID | 1406 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ROR | +0.068 |
igent | +0.056 |
amily | +0.055 |
=# | +0.054 |
racket | +0.053 |
Neg logit contributions | |
wcs | -0.054 |
fitt | -0.053 |
Hatt | -0.053 |
fir | -0.052 |
Brid | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ROR | +0.980 |
igent | +0.812 |
amily | +0.796 |
=# | +0.775 |
racket | +0.770 |
Neg logit contributions | |
wcs | -0.747 |
fitt | -0.726 |
fir | -0.719 |
Hatt | -0.719 |
Brid | -0.714 |
Token | can |
Token ID | 460 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
wcs | +0.785 |
fitt | +0.773 |
fir | +0.767 |
Hatt | +0.763 |
Brid | +0.755 |
Neg logit contributions | |
ROR | -1.200 |
igent | -0.998 |
amily | -0.989 |
=# | -0.953 |
onica | -0.946 |
Token | either |
Token ID | 2035 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
wcs | +0.909 |
fitt | +0.902 |
fir | +0.896 |
Hatt | +0.887 |
Brid | +0.880 |
Neg logit contributions | |
ROR | -1.064 |
igent | -0.857 |
amily | -0.856 |
onica | -0.810 |
=# | -0.810 |
Token | pick |
Token ID | 2298 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
wcs | +0.537 |
fitt | +0.526 |
fir | +0.523 |
Hatt | +0.520 |
Brid | +0.515 |
Neg logit contributions | |
ROR | -0.701 |
igent | -0.576 |
amily | -0.569 |
=# | -0.547 |
onica | -0.545 |
Token | up |
Token ID | 510 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
ROR | +0.657 |
igent | +0.546 |
amily | +0.535 |
=# | +0.521 |
racket | +0.518 |
Neg logit contributions | |
wcs | -0.491 |
fitt | -0.476 |
Hatt | -0.472 |
fir | -0.472 |
Brid | -0.468 |
Token | the |
Token ID | 262 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ROR | +3.291 |
igent | +2.701 |
amily | +2.640 |
racket | +2.636 |
=# | +2.589 |
Neg logit contributions | |
wcs | -2.738 |
fitt | -2.626 |
fir | -2.588 |
Hatt | -2.585 |
heter | -2.565 |
Token | value |
Token ID | 1988 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
ROR | +0.718 |
igent | +0.582 |
amily | +0.572 |
=# | +0.552 |
onica | +0.545 |
Neg logit contributions | |
wcs | -0.661 |
fitt | -0.649 |
Hatt | -0.644 |
fir | -0.644 |
Brid | -0.640 |
Token | system |
Token ID | 1080 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ROR | +0.548 |
igent | +0.437 |
amily | +0.429 |
=# | +0.413 |
onica | +0.407 |
Neg logit contributions | |
wcs | -0.571 |
fitt | -0.560 |
fir | -0.556 |
Hatt | -0.556 |
Brid | -0.552 |
Token | which |
Token ID | 543 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
wcs | +0.325 |
fitt | +0.318 |
fir | +0.315 |
Hatt | +0.315 |
Brid | +0.312 |
Neg logit contributions | |
ROR | -0.420 |
igent | -0.345 |
amily | -0.339 |
=# | -0.329 |
onica | -0.326 |
Token | gives |
Token ID | 3607 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
wcs | +0.272 |
fitt | +0.268 |
Hatt | +0.266 |
fir | +0.266 |
Brid | +0.263 |
Neg logit contributions | |
ROR | -0.317 |
igent | -0.258 |
amily | -0.254 |
=# | -0.244 |
onica | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
ROR | +0.482 |
igent | +0.362 |
amily | +0.350 |
=# | +0.338 |
racket | +0.330 |
Neg logit contributions | |
wcs | -0.718 |
fitt | -0.707 |
Hatt | -0.700 |
fir | -0.700 |
Brid | -0.695 |
Token | View |
Token ID | 7680 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ROR | +0.463 |
igent | +0.360 |
amily | +0.351 |
=# | +0.336 |
racket | +0.333 |
Neg logit contributions | |
wcs | -0.595 |
fitt | -0.579 |
fir | -0.578 |
Hatt | -0.575 |
Brid | -0.574 |
Token | more |
Token ID | 517 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
wcs | +0.323 |
fitt | +0.316 |
fir | +0.313 |
Brid | +0.311 |
Hatt | +0.310 |
Neg logit contributions | |
ROR | -0.438 |
igent | -0.366 |
amily | -0.358 |
=# | -0.348 |
onica | -0.339 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ROR | +0.250 |
igent | +0.206 |
amily | +0.202 |
=# | +0.196 |
onica | +0.195 |
Neg logit contributions | |
wcs | -0.191 |
fitt | -0.186 |
fir | -0.185 |
Hatt | -0.185 |
Brid | -0.183 |
Token | About |
Token ID | 8585 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
wcs | +0.220 |
fitt | +0.212 |
Hatt | +0.211 |
fir | +0.211 |
Brid | +0.210 |
Neg logit contributions | |
ROR | -0.244 |
igent | -0.200 |
amily | -0.197 |
racket | -0.190 |
=# | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
wcs | +0.232 |
Hatt | +0.229 |
fitt | +0.229 |
Brid | +0.228 |
fir | +0.228 |
Neg logit contributions | |
ROR | -0.274 |
igent | -0.224 |
amily | -0.220 |
=# | -0.213 |
racket | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
ROR | +2.479 |
igent | +1.715 |
=# | +1.656 |
=' | +1.650 |
tre | +1.635 |
Neg logit contributions | |
senal | -4.886 |
wcs | -4.852 |
fitt | -4.747 |
��� | -4.684 |
occas | -4.652 |
Token | R |
Token ID | 49 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ROR | +3.562 |
igent | +2.862 |
amily | +2.798 |
=# | +2.744 |
tre | +2.718 |
Neg logit contributions | |
wcs | -3.181 |
fitt | -3.147 |
fir | -3.121 |
Hatt | -3.101 |
Brid | -3.071 |
Token | acing |
Token ID | 4092 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ROR | +0.211 |
igent | +0.175 |
amily | +0.172 |
=# | +0.167 |
racket | +0.165 |
Neg logit contributions | |
wcs | -0.158 |
fitt | -0.155 |
Hatt | -0.153 |
fir | -0.153 |
Brid | -0.152 |
Token | Apex |
Token ID | 49440 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
wcs | +1.030 |
fitt | +1.029 |
Hatt | +1.026 |
Brid | +1.022 |
fir | +1.015 |
Neg logit contributions | |
ROR | -1.203 |
igent | -0.993 |
amily | -0.976 |
=# | -0.942 |
onica | -0.921 |
Token | is |
Token ID | 318 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
wcs | +0.391 |
fitt | +0.387 |
Hatt | +0.384 |
fir | +0.382 |
Brid | +0.382 |
Neg logit contributions | |
ROR | -0.430 |
igent | -0.348 |
amily | -0.342 |
=# | -0.332 |
onica | -0.326 |
Token | kernel |
Token ID | 9720 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
wcs | +0.334 |
fitt | +0.334 |
fir | +0.332 |
Hatt | +0.330 |
Brid | +0.328 |
Neg logit contributions | |
ROR | -0.336 |
igent | -0.272 |
amily | -0.267 |
=# | -0.254 |
onica | -0.252 |
Token | will |
Token ID | 481 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ROR | +0.463 |
igent | +0.383 |
amily | +0.374 |
=# | +0.360 |
onica | +0.359 |
Neg logit contributions | |
wcs | -0.370 |
fitt | -0.366 |
fir | -0.365 |
Hatt | -0.362 |
Brid | -0.359 |
Token | panic |
Token ID | 13619 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ROR | +0.817 |
igent | +0.665 |
amily | +0.653 |
=# | +0.623 |
onica | +0.622 |
Neg logit contributions | |
wcs | -0.735 |
fitt | -0.730 |
fir | -0.726 |
Hatt | -0.720 |
Brid | -0.714 |
Token | just |
Token ID | 655 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
wcs | +0.097 |
fitt | +0.096 |
fir | +0.096 |
Hatt | +0.095 |
Brid | +0.094 |
Neg logit contributions | |
ROR | -0.119 |
igent | -0.098 |
amily | -0.096 |
=# | -0.093 |
onica | -0.092 |
Token | after |
Token ID | 706 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ROR | +0.267 |
igent | +0.222 |
amily | +0.218 |
=# | +0.210 |
onica | +0.209 |
Neg logit contributions | |
wcs | -0.201 |
fir | -0.198 |
fitt | -0.198 |
Hatt | -0.196 |
Brid | -0.194 |
Token | mounting |
Token ID | 17260 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ROR | +0.931 |
igent | +0.761 |
amily | +0.747 |
=# | +0.718 |
onica | +0.713 |
Neg logit contributions | |
wcs | -0.813 |
fitt | -0.803 |
fir | -0.799 |
Hatt | -0.794 |
Brid | -0.791 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ROR | +3.181 |
igent | +2.598 |
amily | +2.540 |
=# | +2.475 |
racket | +2.457 |
Neg logit contributions | |
wcs | -2.741 |
fitt | -2.628 |
Hatt | -2.619 |
fir | -2.592 |
Brid | -2.589 |
Token | boot |
Token ID | 6297 |
Feature activation | +8.72e-04 |
Pos logit contributions | |
ROR | +0.845 |
igent | +0.684 |
amily | +0.671 |
=# | +0.646 |
onica | +0.638 |
Neg logit contributions | |
wcs | -0.820 |
fitt | -0.809 |
fir | -0.804 |
Hatt | -0.802 |
Brid | -0.796 |
Token | partition |
Token ID | 18398 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ROR | +0.001 |
igent | +0.001 |
amily | +0.001 |
=# | +0.000 |
onica | +0.000 |
Neg logit contributions | |
wcs | -0.001 |
fitt | -0.001 |
fir | -0.001 |
Hatt | -0.001 |
Brid | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ROR | +1.069 |
igent | +0.872 |
amily | +0.857 |
=# | +0.828 |
racket | +0.820 |
Neg logit contributions | |
wcs | -0.934 |
fitt | -0.915 |
fir | -0.908 |
Hatt | -0.907 |
Brid | -0.900 |
Token | forcing |
Token ID | 10833 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
wcs | +0.068 |
fitt | +0.067 |
fir | +0.067 |
Hatt | +0.066 |
Brid | +0.066 |
Neg logit contributions | |
ROR | -0.089 |
igent | -0.073 |
amily | -0.072 |
=# | -0.070 |
onica | -0.069 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ROR | +0.352 |
igent | +0.291 |
amily | +0.288 |
=# | +0.278 |
onica | +0.276 |
Neg logit contributions | |
wcs | -0.272 |
fitt | -0.269 |
fir | -0.268 |
Hatt | -0.266 |
Brid | -0.264 |
Token | concern |
Token ID | 2328 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
wcs | +1.590 |
fitt | +1.584 |
fir | +1.583 |
Hatt | +1.556 |
Brid | +1.536 |
Neg logit contributions | |
ROR | -1.939 |
igent | -1.579 |
amily | -1.576 |
=# | -1.506 |
onica | -1.496 |
Token | — |
Token ID | 960 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
wcs | +0.464 |
fitt | +0.454 |
fir | +0.451 |
Hatt | +0.447 |
Brid | +0.444 |
Neg logit contributions | |
ROR | -0.591 |
igent | -0.484 |
amily | -0.479 |
=# | -0.465 |
onica | -0.458 |
Token | in |
Token ID | 259 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
wcs | +0.383 |
fir | +0.373 |
fitt | +0.371 |
Hatt | +0.370 |
Brid | +0.368 |
Neg logit contributions | |
ROR | -0.456 |
igent | -0.374 |
amily | -0.371 |
=# | -0.361 |
racket | -0.356 |
Token | this |
Token ID | 428 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
ROR | +0.135 |
igent | +0.111 |
amily | +0.110 |
=# | +0.107 |
onica | +0.107 |
Neg logit contributions | |
wcs | -0.102 |
fitt | -0.100 |
fir | -0.100 |
Hatt | -0.100 |
Brid | -0.099 |
Token | case |
Token ID | 1339 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
wcs | +0.513 |
fitt | +0.509 |
fir | +0.508 |
Hatt | +0.503 |
Brid | +0.502 |
Neg logit contributions | |
ROR | -0.585 |
amily | -0.476 |
igent | -0.475 |
=# | -0.456 |
onica | -0.454 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ROR | +3.716 |
igent | +3.013 |
amily | +2.915 |
racket | +2.882 |
=# | +2.854 |
Neg logit contributions | |
wcs | -3.637 |
fitt | -3.527 |
Hatt | -3.480 |
fir | -3.453 |
Brid | -3.443 |
Token | over |
Token ID | 625 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ROR | +0.855 |
igent | +0.702 |
amily | +0.690 |
=# | +0.668 |
onica | +0.661 |
Neg logit contributions | |
wcs | -0.710 |
fitt | -0.694 |
fir | -0.689 |
Hatt | -0.689 |
Brid | -0.684 |
Token | Yaz |
Token ID | 35856 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
wcs | +0.495 |
fir | +0.488 |
fitt | +0.487 |
Hatt | +0.486 |
Brid | +0.485 |
Neg logit contributions | |
ROR | -0.582 |
igent | -0.477 |
amily | -0.471 |
onica | -0.452 |
=# | -0.451 |
Token | idi |
Token ID | 19830 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
wcs | +0.393 |
fir | +0.388 |
Hatt | +0.386 |
Brid | +0.379 |
fitt | +0.378 |
Neg logit contributions | |
ROR | -0.592 |
igent | -0.489 |
amily | -0.483 |
=# | -0.469 |
racket | -0.467 |
Token | refugees |
Token ID | 8015 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Hatt | +0.976 |
fitt | +0.975 |
fir | +0.975 |
wcs | +0.961 |
Brid | +0.961 |
Neg logit contributions | |
ROR | -0.873 |
igent | -0.682 |
amily | -0.671 |
=# | -0.641 |
onica | -0.637 |
Token | ig |
Token ID | 328 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ROR | +0.877 |
igent | +0.721 |
amily | +0.703 |
=# | +0.680 |
onica | +0.673 |
Neg logit contributions | |
wcs | -0.781 |
fitt | -0.763 |
Hatt | -0.757 |
fir | -0.755 |
Brid | -0.750 |
Token | may |
Token ID | 743 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
wcs | +0.127 |
fitt | +0.127 |
Hatt | +0.126 |
fir | +0.126 |
Brid | +0.125 |
Neg logit contributions | |
ROR | -0.150 |
igent | -0.120 |
amily | -0.118 |
=# | -0.115 |
onica | -0.114 |
Token | have |
Token ID | 423 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ROR | +0.672 |
igent | +0.550 |
amily | +0.543 |
=# | +0.527 |
onica | +0.519 |
Neg logit contributions | |
wcs | -0.521 |
fitt | -0.514 |
fir | -0.509 |
Hatt | -0.504 |
Brid | -0.502 |
Token | found |
Token ID | 1043 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ROR | +0.979 |
igent | +0.797 |
amily | +0.783 |
=# | +0.757 |
onica | +0.747 |
Neg logit contributions | |
wcs | -0.857 |
fitt | -0.845 |
fir | -0.839 |
Hatt | -0.837 |
Brid | -0.832 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ROR | +0.461 |
igent | +0.379 |
amily | +0.372 |
=# | +0.363 |
onica | +0.359 |
Neg logit contributions | |
wcs | -0.348 |
fitt | -0.343 |
fir | -0.340 |
Hatt | -0.339 |
Brid | -0.337 |
Token | way |
Token ID | 835 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ROR | +1.969 |
igent | +1.649 |
amily | +1.622 |
racket | +1.578 |
=# | +1.565 |
Neg logit contributions | |
wcs | -1.434 |
fitt | -1.377 |
Hatt | -1.370 |
Brid | -1.358 |
fir | -1.357 |
Token | to |
Token ID | 284 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ROR | +2.334 |
igent | +1.865 |
amily | +1.828 |
=# | +1.760 |
racket | +1.753 |
Neg logit contributions | |
wcs | -2.456 |
fitt | -2.406 |
Hatt | -2.386 |
fir | -2.381 |
Brid | -2.368 |
Token | make |
Token ID | 787 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ROR | +1.358 |
igent | +1.108 |
amily | +1.088 |
=# | +1.053 |
racket | +1.044 |
Neg logit contributions | |
wcs | -1.194 |
fitt | -1.165 |
Hatt | -1.157 |
fir | -1.155 |
Brid | -1.147 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ROR | +0.844 |
igent | +0.694 |
amily | +0.681 |
=# | +0.662 |
onica | +0.656 |
Neg logit contributions | |
wcs | -0.664 |
fitt | -0.655 |
fir | -0.651 |
Hatt | -0.648 |
Brid | -0.646 |
Token | silk |
Token ID | 23938 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ROR | +1.265 |
igent | +1.033 |
amily | +1.012 |
=# | +0.981 |
onica | +0.969 |
Neg logit contributions | |
wcs | -1.094 |
fitt | -1.072 |
fir | -1.067 |
Hatt | -1.064 |
Brid | -1.057 |
Token | purse |
Token ID | 27517 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ROR | +0.765 |
igent | +0.614 |
amily | +0.607 |
=# | +0.585 |
onica | +0.575 |
Neg logit contributions | |
wcs | -0.729 |
fitt | -0.717 |
fir | -0.713 |
Hatt | -0.710 |
Brid | -0.707 |
Token | previous |
Token ID | 2180 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ROR | +0.196 |
igent | +0.160 |
amily | +0.157 |
=# | +0.152 |
racket | +0.150 |
Neg logit contributions | |
wcs | -0.171 |
fitt | -0.167 |
fir | -0.166 |
Hatt | -0.165 |
Brid | -0.164 |
Token | court |
Token ID | 2184 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
wcs | +0.007 |
fitt | +0.007 |
fir | +0.007 |
Hatt | +0.007 |
Brid | +0.007 |
Neg logit contributions | |
ROR | -0.010 |
igent | -0.008 |
amily | -0.008 |
=# | -0.008 |
onica | -0.008 |
Token | ruling |
Token ID | 6922 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
wcs | +0.064 |
fitt | +0.062 |
fir | +0.062 |
Hatt | +0.062 |
Brid | +0.061 |
Neg logit contributions | |
ROR | -0.086 |
igent | -0.071 |
amily | -0.070 |
=# | -0.068 |
onica | -0.067 |
Token | from |
Token ID | 422 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
wcs | +0.847 |
fir | +0.831 |
fitt | +0.827 |
Hatt | +0.820 |
Brid | +0.820 |
Neg logit contributions | |
ROR | -1.122 |
igent | -0.916 |
amily | -0.914 |
=# | -0.884 |
onica | -0.868 |
Token | last |
Token ID | 938 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
wcs | +0.639 |
fir | +0.631 |
fitt | +0.628 |
Hatt | +0.626 |
Brid | +0.623 |
Neg logit contributions | |
ROR | -1.056 |
igent | -0.884 |
amily | -0.876 |
=# | -0.852 |
onica | -0.836 |
Token | year |
Token ID | 614 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ROR | +0.321 |
igent | +0.275 |
amily | +0.270 |
=# | +0.264 |
racket | +0.263 |
Neg logit contributions | |
wcs | -0.153 |
fitt | -0.148 |
Hatt | -0.146 |
fir | -0.145 |
Brid | -0.144 |
Token | on |
Token ID | 319 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ROR | +0.160 |
igent | +0.131 |
amily | +0.130 |
=# | +0.126 |
onica | +0.123 |
Neg logit contributions | |
wcs | -0.127 |
fitt | -0.123 |
fir | -0.123 |
Hatt | -0.122 |
Brid | -0.122 |
Token | the |
Token ID | 262 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ROR | +0.205 |
igent | +0.169 |
amily | +0.166 |
=# | +0.161 |
racket | +0.159 |
Neg logit contributions | |
wcs | -0.159 |
fitt | -0.155 |
fir | -0.154 |
Hatt | -0.154 |
Brid | -0.153 |
Token | same |
Token ID | 976 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
wcs | +0.358 |
fitt | +0.350 |
fir | +0.349 |
Hatt | +0.347 |
Brid | +0.345 |
Neg logit contributions | |
ROR | -0.437 |
igent | -0.358 |
amily | -0.353 |
=# | -0.341 |
racket | -0.337 |
Token | subject |
Token ID | 2426 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
wcs | +0.075 |
fitt | +0.073 |
fir | +0.072 |
Hatt | +0.072 |
Brid | +0.072 |
Neg logit contributions | |
ROR | -0.093 |
igent | -0.077 |
amily | -0.076 |
=# | -0.073 |
racket | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
wcs | +0.069 |
fitt | +0.067 |
fir | +0.067 |
Hatt | +0.066 |
Brid | +0.066 |
Neg logit contributions | |
ROR | -0.085 |
igent | -0.069 |
amily | -0.068 |
=# | -0.066 |
onica | -0.065 |
Token | started |
Token ID | 2067 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ROR | +0.208 |
igent | +0.168 |
amily | +0.165 |
=# | +0.159 |
onica | +0.157 |
Neg logit contributions | |
wcs | -0.198 |
fitt | -0.197 |
fir | -0.195 |
Hatt | -0.194 |
Brid | -0.193 |
Token | but |
Token ID | 475 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
wcs | +0.428 |
fitt | +0.419 |
fir | +0.417 |
Hatt | +0.416 |
Brid | +0.413 |
Neg logit contributions | |
ROR | -0.531 |
igent | -0.437 |
amily | -0.430 |
=# | -0.416 |
racket | -0.411 |
Token | added |
Token ID | 2087 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
wcs | +0.080 |
fitt | +0.078 |
Hatt | +0.078 |
fir | +0.077 |
Brid | +0.077 |
Neg logit contributions | |
ROR | -0.108 |
igent | -0.089 |
amily | -0.088 |
=# | -0.085 |
onica | -0.084 |
Token | : |
Token ID | 25 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ROR | +1.138 |
igent | +0.908 |
amily | +0.888 |
=# | +0.857 |
racket | +0.851 |
Neg logit contributions | |
wcs | -1.214 |
fitt | -1.184 |
fir | -1.176 |
Hatt | -1.175 |
Brid | -1.165 |
Token | � |
Token ID | 564 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
wcs | +0.337 |
fitt | +0.330 |
Hatt | +0.327 |
fir | +0.327 |
Brid | +0.326 |
Neg logit contributions | |
ROR | -0.429 |
igent | -0.355 |
amily | -0.347 |
=# | -0.336 |
racket | -0.334 |
Token | � |
Token ID | 250 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
wcs | +0.248 |
fitt | +0.240 |
Hatt | +0.238 |
fir | +0.237 |
Brid | +0.235 |
Neg logit contributions | |
ROR | -0.444 |
igent | -0.376 |
amily | -0.372 |
=# | -0.363 |
racket | -0.358 |
Token | The |
Token ID | 464 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
ROR | +0.537 |
igent | +0.438 |
amily | +0.430 |
=# | +0.416 |
racket | +0.412 |
Neg logit contributions | |
wcs | -0.475 |
fitt | -0.464 |
Hatt | -0.461 |
fir | -0.461 |
Brid | -0.458 |
Token | force |
Token ID | 2700 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ROR | +0.444 |
igent | +0.361 |
amily | +0.355 |
=# | +0.343 |
onica | +0.339 |
Neg logit contributions | |
wcs | -0.396 |
fitt | -0.393 |
fir | -0.389 |
Hatt | -0.389 |
Brid | -0.387 |
Token | is |
Token ID | 318 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ROR | +0.591 |
igent | +0.483 |
amily | +0.474 |
=# | +0.458 |
racket | +0.454 |
Neg logit contributions | |
wcs | -0.512 |
fitt | -0.500 |
Hatt | -0.496 |
fir | -0.496 |
Brid | -0.492 |
Token | currently |
Token ID | 3058 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
wcs | +0.016 |
fitt | +0.015 |
fir | +0.015 |
Hatt | +0.015 |
Brid | +0.015 |
Neg logit contributions | |
ROR | -0.020 |
igent | -0.017 |
amily | -0.016 |
=# | -0.016 |
onica | -0.016 |
Token | aware |
Token ID | 3910 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
ROR | +1.187 |
igent | +0.981 |
amily | +0.962 |
=# | +0.934 |
racket | +0.927 |
Neg logit contributions | |
wcs | -0.924 |
fitt | -0.899 |
Hatt | -0.892 |
fir | -0.892 |
Brid | -0.884 |
Token | HD |
Token ID | 5572 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
wcs | +0.732 |
fitt | +0.705 |
Hatt | +0.697 |
fir | +0.696 |
Brid | +0.687 |
Neg logit contributions | |
ROR | -1.745 |
igent | -1.501 |
amily | -1.481 |
=# | -1.448 |
racket | -1.437 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
wcs | +0.789 |
fitt | +0.769 |
Hatt | +0.763 |
fir | +0.762 |
Brid | +0.756 |
Neg logit contributions | |
ROR | -0.991 |
igent | -0.815 |
amily | -0.802 |
=# | -0.777 |
racket | -0.771 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Hatt | +0.722 |
wcs | +0.721 |
Brid | +0.720 |
fir | +0.716 |
fitt | +0.713 |
Neg logit contributions | |
ROR | -0.873 |
igent | -0.725 |
amily | -0.709 |
racket | -0.680 |
=# | -0.675 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ROR | +0.660 |
igent | +0.491 |
amily | +0.472 |
=# | +0.461 |
racket | +0.448 |
Neg logit contributions | |
wcs | -1.022 |
fitt | -1.002 |
fir | -0.989 |
Hatt | -0.988 |
Brid | -0.982 |
Token | Here |
Token ID | 4342 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
ROR | +0.890 |
igent | +0.726 |
amily | +0.713 |
=# | +0.688 |
racket | +0.684 |
Neg logit contributions | |
wcs | -0.788 |
fitt | -0.770 |
Hatt | -0.764 |
fir | -0.764 |
Brid | -0.759 |
Token | 's |
Token ID | 338 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ROR | +0.629 |
igent | +0.520 |
amily | +0.511 |
=# | +0.495 |
racket | +0.491 |
Neg logit contributions | |
wcs | -0.465 |
fitt | -0.457 |
fir | -0.454 |
Hatt | -0.452 |
Brid | -0.450 |
Token | what |
Token ID | 644 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ROR | +0.166 |
igent | +0.137 |
amily | +0.135 |
=# | +0.130 |
racket | +0.129 |
Neg logit contributions | |
wcs | -0.127 |
fitt | -0.124 |
fir | -0.123 |
Hatt | -0.123 |
Brid | -0.122 |
Token | Gunn |
Token ID | 40837 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ROR | +0.695 |
igent | +0.581 |
amily | +0.572 |
=# | +0.555 |
racket | +0.551 |
Neg logit contributions | |
wcs | -0.461 |
fitt | -0.451 |
fir | -0.447 |
Hatt | -0.447 |
Brid | -0.444 |
Token | had |
Token ID | 550 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ROR | +0.515 |
igent | +0.430 |
amily | +0.424 |
=# | +0.412 |
racket | +0.409 |
Neg logit contributions | |
wcs | -0.334 |
fitt | -0.327 |
Hatt | -0.324 |
fir | -0.323 |
Brid | -0.321 |
Token | to |
Token ID | 284 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ROR | +0.475 |
igent | +0.381 |
amily | +0.375 |
=# | +0.360 |
racket | +0.356 |
Neg logit contributions | |
wcs | -0.470 |
fitt | -0.461 |
Hatt | -0.458 |
fir | -0.457 |
Brid | -0.454 |
Token | say |
Token ID | 910 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
wcs | +0.137 |
fitt | +0.135 |
Hatt | +0.134 |
fir | +0.134 |
Brid | +0.132 |
Neg logit contributions | |
ROR | -0.146 |
igent | -0.118 |
amily | -0.117 |
=# | -0.112 |
racket | -0.111 |
Token | causing |
Token ID | 6666 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ROR | +0.139 |
igent | +0.116 |
amily | +0.114 |
=# | +0.110 |
onica | +0.109 |
Neg logit contributions | |
wcs | -0.104 |
fitt | -0.102 |
fir | -0.101 |
Hatt | -0.101 |
Brid | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ROR | +0.630 |
igent | +0.520 |
amily | +0.511 |
=# | +0.495 |
racket | +0.491 |
Neg logit contributions | |
wcs | -0.498 |
fitt | -0.486 |
Hatt | -0.482 |
fir | -0.482 |
Brid | -0.478 |
Token | events |
Token ID | 2995 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ROR | +0.194 |
igent | +0.159 |
amily | +0.158 |
=# | +0.152 |
onica | +0.149 |
Neg logit contributions | |
wcs | -0.157 |
fitt | -0.157 |
Hatt | -0.155 |
fir | -0.154 |
Brid | -0.153 |
Token | ( |
Token ID | 357 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
ROR | +0.779 |
igent | +0.629 |
amily | +0.619 |
=# | +0.597 |
racket | +0.590 |
Neg logit contributions | |
wcs | -0.734 |
fitt | -0.719 |
fir | -0.714 |
Hatt | -0.713 |
Brid | -0.708 |
Token | in |
Token ID | 259 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
wcs | +0.483 |
fitt | +0.470 |
fir | +0.464 |
Hatt | +0.461 |
heter | +0.460 |
Neg logit contributions | |
ROR | -0.607 |
amily | -0.499 |
igent | -0.498 |
racket | -0.479 |
=# | -0.479 |
Token | some |
Token ID | 617 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
ROR | +0.753 |
igent | +0.618 |
amily | +0.609 |
=# | +0.592 |
racket | +0.584 |
Neg logit contributions | |
wcs | -0.586 |
fitt | -0.577 |
Hatt | -0.572 |
fir | -0.571 |
Brid | -0.566 |
Token | cases |
Token ID | 2663 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ROR | +0.454 |
igent | +0.380 |
amily | +0.374 |
=# | +0.363 |
racket | +0.360 |
Neg logit contributions | |
wcs | -0.305 |
fitt | -0.298 |
fir | -0.295 |
Hatt | -0.294 |
Brid | -0.292 |
Token | not |
Token ID | 407 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ROR | +1.724 |
igent | +1.456 |
amily | +1.434 |
=# | +1.397 |
racket | +1.386 |
Neg logit contributions | |
wcs | -1.008 |
fitt | -0.978 |
Hatt | -0.969 |
fir | -0.968 |
Brid | -0.959 |
Token | always |
Token ID | 1464 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ROR | +0.086 |
igent | +0.072 |
amily | +0.070 |
=# | +0.068 |
racket | +0.068 |
Neg logit contributions | |
wcs | -0.065 |
fitt | -0.063 |
fir | -0.063 |
Hatt | -0.062 |
Brid | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
wcs | +0.162 |
fitt | +0.159 |
fir | +0.157 |
Hatt | +0.157 |
Brid | +0.156 |
Neg logit contributions | |
ROR | -0.219 |
igent | -0.182 |
amily | -0.179 |
=# | -0.174 |
racket | -0.172 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ROR | +0.351 |
igent | +0.289 |
amily | +0.284 |
=# | +0.277 |
onica | +0.273 |
Neg logit contributions | |
wcs | -0.270 |
fitt | -0.266 |
fir | -0.264 |
Hatt | -0.263 |
Brid | -0.261 |
Token | least |
Token ID | 1551 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
wcs | +0.089 |
fitt | +0.089 |
fir | +0.087 |
Hatt | +0.087 |
Brid | +0.086 |
Neg logit contributions | |
ROR | -0.117 |
igent | -0.096 |
amily | -0.095 |
=# | -0.092 |
onica | -0.091 |
Token | one |
Token ID | 530 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
ROR | +0.185 |
igent | +0.153 |
amily | +0.151 |
=# | +0.146 |
racket | +0.145 |
Neg logit contributions | |
wcs | -0.141 |
fitt | -0.137 |
Hatt | -0.136 |
fir | -0.136 |
Brid | -0.135 |
Token | blank |
Token ID | 9178 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
wcs | +0.002 |
fitt | +0.002 |
fir | +0.002 |
Hatt | +0.002 |
Brid | +0.002 |
Neg logit contributions | |
ROR | -0.002 |
igent | -0.002 |
amily | -0.002 |
onica | -0.002 |
=# | -0.002 |
Token | character |
Token ID | 2095 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ROR | +0.166 |
igent | +0.133 |
amily | +0.131 |
=# | +0.125 |
onica | +0.124 |
Neg logit contributions | |
wcs | -0.166 |
fitt | -0.163 |
fir | -0.162 |
Hatt | -0.162 |
Brid | -0.161 |
Token | (< |
Token ID | 38155 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ROR | +0.674 |
igent | +0.554 |
amily | +0.545 |
=# | +0.530 |
racket | +0.524 |
Neg logit contributions | |
wcs | -0.551 |
fitt | -0.535 |
Hatt | -0.531 |
fir | -0.531 |
Brid | -0.527 |
Token | Space |
Token ID | 14106 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ROR | +1.723 |
igent | +1.406 |
amily | +1.381 |
=# | +1.348 |
racket | +1.325 |
Neg logit contributions | |
wcs | -1.474 |
fitt | -1.438 |
fir | -1.431 |
Hatt | -1.428 |
Brid | -1.419 |
Token | > |
Token ID | 29 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ROR | +0.985 |
igent | +0.817 |
amily | +0.801 |
=# | +0.775 |
racket | +0.771 |
Neg logit contributions | |
wcs | -0.738 |
fitt | -0.719 |
Hatt | -0.715 |
fir | -0.714 |
Brid | -0.708 |
Token | or |
Token ID | 393 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
wcs | +0.602 |
fitt | +0.588 |
Hatt | +0.587 |
fir | +0.585 |
Brid | +0.580 |
Neg logit contributions | |
ROR | -0.860 |
igent | -0.722 |
amily | -0.704 |
onica | -0.680 |
racket | -0.679 |
Token | < |
Token ID | 1279 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
wcs | +0.740 |
fir | +0.722 |
fitt | +0.719 |
Hatt | +0.718 |
Brid | +0.709 |
Neg logit contributions | |
ROR | -0.947 |
igent | -0.783 |
amily | -0.765 |
onica | -0.745 |
racket | -0.733 |
Token | Tab |
Token ID | 33349 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ROR | +0.864 |
igent | +0.707 |
amily | +0.693 |
=# | +0.671 |
racket | +0.665 |
Neg logit contributions | |
wcs | -0.747 |
fitt | -0.729 |
Hatt | -0.723 |
fir | -0.723 |
Brid | -0.718 |
Token | >) |
Token ID | 43734 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ROR | +0.261 |
igent | +0.215 |
amily | +0.210 |
=# | +0.203 |
racket | +0.202 |
Neg logit contributions | |
wcs | -0.216 |
fitt | -0.210 |
Hatt | -0.209 |
fir | -0.209 |
Brid | -0.207 |
Token | the |
Token ID | 262 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
ROR | +0.955 |
igent | +0.791 |
amily | +0.778 |
=# | +0.757 |
racket | +0.752 |
Neg logit contributions | |
wcs | -0.698 |
fitt | -0.679 |
fir | -0.673 |
Hatt | -0.670 |
Brid | -0.665 |
Token | trip |
Token ID | 5296 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ROR | +0.590 |
igent | +0.481 |
amily | +0.472 |
=# | +0.454 |
onica | +0.449 |
Neg logit contributions | |
wcs | -0.540 |
fitt | -0.533 |
Hatt | -0.531 |
fir | -0.530 |
Brid | -0.527 |
Token | being |
Token ID | 852 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ROR | +0.861 |
igent | +0.704 |
amily | +0.691 |
=# | +0.670 |
racket | +0.665 |
Neg logit contributions | |
wcs | -0.718 |
fitt | -0.700 |
fir | -0.695 |
Hatt | -0.693 |
Brid | -0.688 |
Token | discussed |
Token ID | 6693 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
wcs | +0.040 |
fitt | +0.039 |
fir | +0.039 |
Hatt | +0.039 |
Brid | +0.039 |
Neg logit contributions | |
ROR | -0.052 |
igent | -0.042 |
amily | -0.042 |
=# | -0.040 |
racket | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
wcs | +0.226 |
fitt | +0.220 |
Hatt | +0.219 |
fir | +0.219 |
Brid | +0.218 |
Neg logit contributions | |
ROR | -0.290 |
igent | -0.239 |
amily | -0.235 |
=# | -0.228 |
onica | -0.225 |
Token | years |
Token ID | 812 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
wcs | +0.067 |
fitt | +0.065 |
Hatt | +0.065 |
fir | +0.065 |
Brid | +0.064 |
Neg logit contributions | |
ROR | -0.099 |
igent | -0.083 |
amily | -0.082 |
=# | -0.079 |
racket | -0.078 |
Token | later |
Token ID | 1568 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
wcs | +0.194 |
fitt | +0.190 |
fir | +0.190 |
Hatt | +0.190 |
Brid | +0.189 |
Neg logit contributions | |
ROR | -0.132 |
igent | -0.100 |
amily | -0.097 |
=# | -0.093 |
racket | -0.091 |
Token | when |
Token ID | 618 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ROR | +0.022 |
igent | +0.018 |
amily | +0.018 |
=# | +0.017 |
racket | +0.017 |
Neg logit contributions | |
wcs | -0.016 |
fitt | -0.015 |
Hatt | -0.015 |
fir | -0.015 |
Brid | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
wcs | +1.106 |
Hatt | +1.095 |
Brid | +1.087 |
fitt | +1.082 |
fir | +1.077 |
Neg logit contributions | |
ROR | -1.581 |
igent | -1.312 |
amily | -1.291 |
=# | -1.247 |
onica | -1.240 |
Token | visited |
Token ID | 8672 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
wcs | +0.347 |
fitt | +0.340 |
Hatt | +0.339 |
fir | +0.338 |
Brid | +0.336 |
Neg logit contributions | |
ROR | -0.471 |
igent | -0.390 |
amily | -0.384 |
=# | -0.371 |
onica | -0.368 |
Token | Jones |
Token ID | 5437 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
wcs | +0.715 |
Hatt | +0.714 |
Brid | +0.708 |
fitt | +0.704 |
fir | +0.703 |
Neg logit contributions | |
ROR | -0.891 |
igent | -0.736 |
amily | -0.720 |
=# | -0.693 |
onica | -0.689 |
Token | country |
Token ID | 1499 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ROR | +0.039 |
igent | +0.032 |
amily | +0.031 |
=# | +0.030 |
onica | +0.030 |
Neg logit contributions | |
wcs | -0.033 |
fitt | -0.033 |
fir | -0.032 |
Hatt | -0.032 |
Brid | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
wcs | +0.154 |
fitt | +0.150 |
fir | +0.149 |
Hatt | +0.148 |
Brid | +0.147 |
Neg logit contributions | |
ROR | -0.190 |
igent | -0.155 |
amily | -0.153 |
=# | -0.149 |
onica | -0.146 |
Token | They |
Token ID | 1119 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
ROR | +0.207 |
igent | +0.173 |
amily | +0.170 |
=# | +0.165 |
racket | +0.164 |
Neg logit contributions | |
wcs | -0.142 |
fitt | -0.138 |
Hatt | -0.138 |
fir | -0.137 |
Brid | -0.136 |
Token | say |
Token ID | 910 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ROR | +0.571 |
igent | +0.463 |
amily | +0.454 |
=# | +0.439 |
racket | +0.434 |
Neg logit contributions | |
wcs | -0.529 |
fitt | -0.517 |
fir | -0.513 |
Hatt | -0.513 |
Brid | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
wcs | +0.146 |
fitt | +0.142 |
fir | +0.141 |
Hatt | +0.141 |
Brid | +0.140 |
Neg logit contributions | |
ROR | -0.208 |
igent | -0.172 |
amily | -0.170 |
=# | -0.165 |
onica | -0.164 |
Token | for |
Token ID | 329 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ROR | +0.401 |
igent | +0.330 |
amily | +0.325 |
=# | +0.316 |
onica | +0.312 |
Neg logit contributions | |
wcs | -0.315 |
fitt | -0.307 |
fir | -0.306 |
Hatt | -0.305 |
Brid | -0.305 |
Token | example |
Token ID | 1672 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
wcs | +0.213 |
fitt | +0.211 |
fir | +0.209 |
Hatt | +0.208 |
Brid | +0.208 |
Neg logit contributions | |
ROR | -0.249 |
igent | -0.200 |
amily | -0.200 |
=# | -0.193 |
onica | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
wcs | +0.640 |
fitt | +0.625 |
Hatt | +0.622 |
fir | +0.622 |
Brid | +0.617 |
Neg logit contributions | |
ROR | -0.674 |
igent | -0.545 |
amily | -0.534 |
=# | -0.516 |
racket | -0.511 |
Token | that |
Token ID | 326 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ROR | +0.057 |
igent | +0.047 |
amily | +0.046 |
=# | +0.045 |
onica | +0.045 |
Neg logit contributions | |
wcs | -0.040 |
fitt | -0.039 |
Hatt | -0.039 |
fir | -0.039 |
Brid | -0.039 |
Token | because |
Token ID | 780 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
wcs | +0.455 |
fitt | +0.445 |
fir | +0.443 |
Hatt | +0.442 |
Brid | +0.441 |
Neg logit contributions | |
ROR | -0.619 |
igent | -0.511 |
amily | -0.501 |
=# | -0.486 |
onica | -0.486 |
Token | of |
Token ID | 286 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
ROR | +0.296 |
igent | +0.246 |
amily | +0.242 |
=# | +0.235 |
racket | +0.232 |
Neg logit contributions | |
wcs | -0.218 |
fitt | -0.212 |
Hatt | -0.210 |
fir | -0.210 |
Brid | -0.209 |
Token | in |
Token ID | 287 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
wcs | +0.415 |
fitt | +0.408 |
fir | +0.404 |
Hatt | +0.404 |
Brid | +0.402 |
Neg logit contributions | |
ROR | -0.422 |
igent | -0.338 |
amily | -0.333 |
=# | -0.322 |
onica | -0.316 |
Token | when |
Token ID | 618 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ROR | +2.155 |
igent | +1.770 |
amily | +1.732 |
=# | +1.673 |
racket | +1.671 |
Neg logit contributions | |
wcs | -1.790 |
Hatt | -1.722 |
fitt | -1.720 |
fir | -1.715 |
Brid | -1.697 |
Token | there |
Token ID | 612 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ROR | +0.136 |
igent | +0.114 |
amily | +0.113 |
=# | +0.110 |
racket | +0.109 |
Neg logit contributions | |
wcs | -0.087 |
fitt | -0.084 |
Hatt | -0.084 |
fir | -0.084 |
Brid | -0.083 |
Token | � |
Token ID | 447 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ROR | +0.493 |
igent | +0.403 |
amily | +0.396 |
=# | +0.383 |
racket | +0.379 |
Neg logit contributions | |
wcs | -0.429 |
fitt | -0.419 |
Hatt | -0.416 |
fir | -0.416 |
Brid | -0.413 |
Token | � |
Token ID | 247 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
ROR | +0.343 |
igent | +0.293 |
amily | +0.290 |
=# | +0.283 |
racket | +0.279 |
Neg logit contributions | |
wcs | -0.187 |
fitt | -0.180 |
Hatt | -0.178 |
fir | -0.177 |
Brid | -0.176 |
Token | s |
Token ID | 82 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
wcs | +0.548 |
fitt | +0.541 |
fir | +0.540 |
Hatt | +0.535 |
Brid | +0.530 |
Neg logit contributions | |
ROR | -0.746 |
igent | -0.612 |
amily | -0.598 |
=# | -0.581 |
racket | -0.580 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
wcs | +1.155 |
fitt | +1.137 |
fir | +1.128 |
Hatt | +1.123 |
Brid | +1.114 |
Neg logit contributions | |
ROR | -1.552 |
igent | -1.266 |
amily | -1.251 |
=# | -1.219 |
onica | -1.206 |
Token | crisis |
Token ID | 4902 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ROR | +0.436 |
igent | +0.355 |
amily | +0.348 |
=# | +0.338 |
onica | +0.334 |
Neg logit contributions | |
wcs | -0.379 |
fitt | -0.372 |
fir | -0.370 |
Hatt | -0.369 |
Brid | -0.366 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
wcs | +0.009 |
fitt | +0.009 |
fir | +0.009 |
Hatt | +0.009 |
Brid | +0.009 |
Neg logit contributions | |
ROR | -0.012 |
igent | -0.010 |
amily | -0.009 |
=# | -0.009 |
onica | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ROR | +0.302 |
igent | +0.250 |
amily | +0.245 |
=# | +0.238 |
racket | +0.236 |
Neg logit contributions | |
wcs | -0.228 |
fitt | -0.223 |
Hatt | -0.221 |
fir | -0.221 |
Brid | -0.219 |
Token | � |
Token ID | 251 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ROR | +0.523 |
igent | +0.433 |
amily | +0.426 |
=# | +0.414 |
racket | +0.409 |
Neg logit contributions | |
wcs | -0.402 |
fitt | -0.390 |
Hatt | -0.388 |
fir | -0.387 |
Brid | -0.384 |
Token | the |
Token ID | 262 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
wcs | +0.216 |
fitt | +0.213 |
fir | +0.212 |
Hatt | +0.211 |
Brid | +0.210 |
Neg logit contributions | |
ROR | -0.260 |
igent | -0.211 |
amily | -0.210 |
=# | -0.202 |
onica | -0.200 |
Token | two |
Token ID | 734 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
ROR | +0.434 |
igent | +0.357 |
amily | +0.351 |
=# | +0.340 |
racket | +0.337 |
Neg logit contributions | |
wcs | -0.348 |
fitt | -0.340 |
fir | -0.337 |
Hatt | -0.337 |
Brid | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ROR | +0.656 |
igent | +0.541 |
amily | +0.528 |
=# | +0.514 |
racket | +0.512 |
Neg logit contributions | |
wcs | -0.547 |
fitt | -0.529 |
Hatt | -0.527 |
fir | -0.525 |
Brid | -0.522 |
Token | The |
Token ID | 383 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ROR | +0.194 |
igent | +0.160 |
amily | +0.157 |
=# | +0.153 |
racket | +0.151 |
Neg logit contributions | |
wcs | -0.156 |
fitt | -0.152 |
fir | -0.150 |
Hatt | -0.150 |
Brid | -0.149 |
Token | Acer |
Token ID | 49606 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
wcs | +0.239 |
fitt | +0.233 |
Hatt | +0.232 |
fir | +0.232 |
Brid | +0.230 |
Neg logit contributions | |
ROR | -0.315 |
igent | -0.260 |
amily | -0.256 |
=# | -0.248 |
racket | -0.246 |
Token | had |
Token ID | 550 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
wcs | +0.785 |
fitt | +0.772 |
Hatt | +0.766 |
fir | +0.764 |
Brid | +0.758 |
Neg logit contributions | |
ROR | -1.177 |
igent | -0.978 |
amily | -0.968 |
=# | -0.937 |
onica | -0.928 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
wcs | +0.174 |
fitt | +0.171 |
fir | +0.170 |
Hatt | +0.169 |
Brid | +0.168 |
Neg logit contributions | |
ROR | -0.241 |
igent | -0.199 |
amily | -0.197 |
=# | -0.191 |
onica | -0.188 |
Token | a |
Token ID | 257 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
wcs | +0.322 |
fitt | +0.318 |
fir | +0.317 |
Hatt | +0.314 |
Brid | +0.313 |
Neg logit contributions | |
ROR | -0.424 |
igent | -0.348 |
amily | -0.346 |
=# | -0.333 |
onica | -0.328 |
Token | marginally |
Token ID | 44108 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
ROR | +0.515 |
igent | +0.424 |
amily | +0.417 |
=# | +0.404 |
racket | +0.400 |
Neg logit contributions | |
wcs | -0.409 |
fitt | -0.399 |
fir | -0.396 |
Hatt | -0.396 |
Brid | -0.393 |
Token | lower |
Token ID | 2793 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
wcs | +0.465 |
fir | +0.461 |
fitt | +0.457 |
Hatt | +0.452 |
Brid | +0.448 |
Neg logit contributions | |
ROR | -0.811 |
igent | -0.682 |
amily | -0.677 |
=# | -0.656 |
onica | -0.651 |
Token | blur |
Token ID | 23671 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
wcs | +0.798 |
fir | +0.796 |
Hatt | +0.794 |
fitt | +0.793 |
Brid | +0.788 |
Neg logit contributions | |
ROR | -1.016 |
igent | -0.828 |
amily | -0.825 |
=# | -0.788 |
onica | -0.781 |
Token | with |
Token ID | 351 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
wcs | +0.145 |
fitt | +0.141 |
fir | +0.140 |
Hatt | +0.140 |
Brid | +0.139 |
Neg logit contributions | |
ROR | -0.176 |
igent | -0.145 |
amily | -0.141 |
=# | -0.137 |
racket | -0.135 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
wcs | +0.705 |
fitt | +0.698 |
Hatt | +0.697 |
fir | +0.693 |
Brid | +0.693 |
Neg logit contributions | |
ROR | -0.841 |
igent | -0.691 |
amily | -0.675 |
=# | -0.652 |
onica | -0.648 |
Token | — |
Token ID | 851 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
wcs | +0.873 |
fitt | +0.854 |
Hatt | +0.852 |
fir | +0.846 |
Brid | +0.845 |
Neg logit contributions | |
ROR | -1.095 |
igent | -0.903 |
amily | -0.881 |
=# | -0.862 |
onica | -0.850 |
Token | how |
Token ID | 703 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
wcs | +0.386 |
fitt | +0.379 |
Hatt | +0.378 |
fir | +0.378 |
Brid | +0.375 |
Neg logit contributions | |
ROR | -0.511 |
igent | -0.424 |
amily | -0.415 |
=# | -0.403 |
onica | -0.400 |
Token | do |
Token ID | 466 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
wcs | +0.422 |
fitt | +0.414 |
fir | +0.412 |
Hatt | +0.412 |
Brid | +0.411 |
Neg logit contributions | |
ROR | -0.568 |
igent | -0.470 |
amily | -0.462 |
=# | -0.447 |
onica | -0.444 |
Token | you |
Token ID | 345 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
wcs | +0.845 |
fitt | +0.823 |
Hatt | +0.819 |
Brid | +0.814 |
fir | +0.814 |
Neg logit contributions | |
ROR | -1.283 |
igent | -1.073 |
amily | -1.049 |
onica | -1.015 |
=# | -1.014 |
Token | see |
Token ID | 766 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
wcs | +0.217 |
fitt | +0.213 |
fir | +0.211 |
Hatt | +0.210 |
Brid | +0.208 |
Neg logit contributions | |
ROR | -0.289 |
igent | -0.240 |
amily | -0.236 |
=# | -0.227 |
onica | -0.226 |
Token | this |
Token ID | 428 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
wcs | +0.241 |
fitt | +0.236 |
Hatt | +0.234 |
fir | +0.233 |
Brid | +0.233 |
Neg logit contributions | |
ROR | -0.343 |
igent | -0.286 |
amily | -0.281 |
=# | -0.273 |
onica | -0.270 |
Token | book |
Token ID | 1492 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
wcs | +0.192 |
fitt | +0.187 |
fir | +0.186 |
Hatt | +0.185 |
Brid | +0.185 |
Neg logit contributions | |
ROR | -0.235 |
igent | -0.194 |
amily | -0.190 |
=# | -0.184 |
onica | -0.182 |
Token | affecting |
Token ID | 13891 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
wcs | +0.026 |
fitt | +0.026 |
fir | +0.026 |
Hatt | +0.025 |
Brid | +0.025 |
Neg logit contributions | |
ROR | -0.034 |
igent | -0.028 |
amily | -0.028 |
=# | -0.027 |
racket | -0.027 |
Token | your |
Token ID | 534 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
wcs | +0.132 |
fitt | +0.128 |
Hatt | +0.128 |
fir | +0.128 |
Brid | +0.127 |
Neg logit contributions | |
ROR | -0.198 |
igent | -0.167 |
amily | -0.163 |
=# | -0.159 |
onica | -0.157 |
Token | ring |
Token ID | 1806 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ROR | +0.098 |
igent | +0.081 |
amily | +0.079 |
=# | +0.077 |
racket | +0.076 |
Neg logit contributions | |
wcs | -0.079 |
fitt | -0.077 |
fir | -0.077 |
Hatt | -0.077 |
Brid | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ROR | +0.100 |
igent | +0.080 |
amily | +0.079 |
=# | +0.077 |
racket | +0.076 |
Neg logit contributions | |
wcs | -0.094 |
fitt | -0.093 |
Hatt | -0.093 |
fir | -0.092 |
Brid | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
ROR | +0.812 |
igent | +0.662 |
amily | +0.650 |
=# | +0.633 |
onica | +0.625 |
Neg logit contributions | |
wcs | -0.662 |
fitt | -0.650 |
Hatt | -0.644 |
fir | -0.644 |
Brid | -0.641 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ROR | +0.034 |
igent | +0.026 |
amily | +0.025 |
=# | +0.024 |
racket | +0.024 |
Neg logit contributions | |
wcs | -0.051 |
fitt | -0.050 |
Hatt | -0.049 |
fir | -0.049 |
Brid | -0.049 |
Token | All |
Token ID | 3237 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
wcs | +0.210 |
fitt | +0.204 |
fir | +0.202 |
Brid | +0.202 |
Hatt | +0.202 |
Neg logit contributions | |
ROR | -0.244 |
igent | -0.200 |
amily | -0.197 |
racket | -0.190 |
=# | -0.189 |
Token | manner |
Token ID | 5642 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ROR | +0.048 |
igent | +0.039 |
amily | +0.039 |
=# | +0.037 |
onica | +0.037 |
Neg logit contributions | |
wcs | -0.039 |
fitt | -0.038 |
Hatt | -0.038 |
fir | -0.038 |
Brid | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
wcs | +2.073 |
fitt | +2.045 |
fir | +2.041 |
Hatt | +2.028 |
Brid | +1.979 |
Neg logit contributions | |
ROR | -2.890 |
igent | -2.391 |
amily | -2.368 |
onica | -2.286 |
=# | -2.263 |
Token | schizophrenia |
Token ID | 22794 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
wcs | +1.126 |
fitt | +1.124 |
fir | +1.117 |
Hatt | +1.107 |
Brid | +1.093 |
Neg logit contributions | |
ROR | -1.223 |
igent | -0.983 |
amily | -0.978 |
onica | -0.934 |
=# | -0.932 |
Token | flows |
Token ID | 15623 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
wcs | +0.420 |
fitt | +0.412 |
fir | +0.409 |
Hatt | +0.406 |
Brid | +0.403 |
Neg logit contributions | |
ROR | -0.494 |
igent | -0.402 |
amily | -0.397 |
=# | -0.384 |
onica | -0.380 |
Token | from |
Token ID | 422 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
wcs | +0.063 |
fitt | +0.061 |
fir | +0.061 |
Hatt | +0.061 |
Brid | +0.060 |
Neg logit contributions | |
ROR | -0.084 |
igent | -0.069 |
amily | -0.068 |
=# | -0.066 |
racket | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
wcs | +0.166 |
fitt | +0.163 |
fir | +0.162 |
Hatt | +0.161 |
Brid | +0.160 |
Neg logit contributions | |
ROR | -0.212 |
igent | -0.175 |
amily | -0.172 |
=# | -0.166 |
onica | -0.165 |
Token | these |
Token ID | 777 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
ROR | +0.120 |
igent | +0.100 |
amily | +0.098 |
=# | +0.095 |
racket | +0.094 |
Neg logit contributions | |
wcs | -0.089 |
fitt | -0.087 |
Hatt | -0.086 |
fir | -0.086 |
Brid | -0.086 |
Token | videos |
Token ID | 5861 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
wcs | +0.004 |
fitt | +0.004 |
fir | +0.004 |
Hatt | +0.004 |
Brid | +0.004 |
Neg logit contributions | |
ROR | -0.004 |
igent | -0.003 |
amily | -0.003 |
=# | -0.003 |
racket | -0.003 |
Token | ? |
Token ID | 30 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
wcs | +0.225 |
fitt | +0.222 |
fir | +0.221 |
Hatt | +0.220 |
Brid | +0.219 |
Neg logit contributions | |
ROR | -0.297 |
igent | -0.246 |
amily | -0.241 |
=# | -0.233 |
racket | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
wcs | +0.693 |
Hatt | +0.688 |
Brid | +0.686 |
fitt | +0.681 |
fir | +0.680 |
Neg logit contributions | |
ROR | -0.859 |
igent | -0.710 |
amily | -0.697 |
onica | -0.668 |
=# | -0.666 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
wcs | +0.255 |
fitt | +0.250 |
Hatt | +0.249 |
fir | +0.249 |
Brid | +0.247 |
Neg logit contributions | |
ROR | -0.176 |
igent | -0.134 |
amily | -0.130 |
=# | -0.124 |
racket | -0.122 |
Token | Image |
Token ID | 5159 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ROR | +0.140 |
igent | +0.119 |
amily | +0.117 |
=# | +0.113 |
racket | +0.113 |
Neg logit contributions | |
wcs | -0.085 |
fitt | -0.082 |
Hatt | -0.081 |
fir | -0.081 |
Brid | -0.081 |
Token | via |
Token ID | 2884 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
fitt | +1.928 |
wcs | +1.925 |
Hatt | +1.911 |
Brid | +1.910 |
fir | +1.900 |
Neg logit contributions | |
ROR | -2.903 |
igent | -2.453 |
amily | -2.428 |
=# | -2.329 |
tre | -2.301 |
Token | Venus |
Token ID | 21094 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Hatt | +2.768 |
fir | +2.735 |
Brid | +2.729 |
wcs | +2.719 |
fitt | +2.714 |
Neg logit contributions | |
ROR | -3.221 |
igent | -2.629 |
amily | -2.545 |
=# | -2.436 |
tre | -2.419 |
Token | Angel |
Token ID | 3905 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
wcs | +0.625 |
fir | +0.611 |
fitt | +0.609 |
Hatt | +0.608 |
Brid | +0.606 |
Neg logit contributions | |
ROR | -1.226 |
igent | -1.041 |
amily | -1.025 |
=# | -0.999 |
racket | -0.996 |
Token | ic |
Token ID | 291 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
wcs | +0.179 |
fitt | +0.173 |
Hatt | +0.171 |
fir | +0.171 |
Brid | +0.170 |
Neg logit contributions | |
ROR | -0.330 |
igent | -0.281 |
amily | -0.276 |
=# | -0.269 |
racket | -0.267 |
Token | / |
Token ID | 14 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
wcs | +0.798 |
fitt | +0.790 |
fir | +0.785 |
Brid | +0.784 |
Hatt | +0.783 |
Neg logit contributions | |
ROR | -0.974 |
igent | -0.800 |
amily | -0.781 |
=# | -0.757 |
racket | -0.749 |
Token | . |
Token ID | 764 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
wcs | +1.191 |
fitt | +1.165 |
fir | +1.152 |
Hatt | +1.146 |
Brid | +1.133 |
Neg logit contributions | |
ROR | -2.433 |
igent | -2.071 |
amily | -2.041 |
=# | -1.996 |
racket | -1.980 |
Token | un |
Token ID | 403 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
wcs | +2.989 |
fitt | +2.951 |
fir | +2.915 |
Brid | +2.862 |
Hatt | +2.858 |
Neg logit contributions | |
ROR | -3.125 |
igent | -2.543 |
amily | -2.522 |
=# | -2.404 |
onica | -2.382 |
Token | wrap |
Token ID | 37150 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
wcs | +0.795 |
fitt | +0.764 |
Hatt | +0.754 |
fir | +0.754 |
Brid | +0.748 |
Neg logit contributions | |
ROR | -0.935 |
igent | -0.759 |
amily | -0.752 |
=# | -0.729 |
racket | -0.724 |
Token | ()) |
Token ID | 32865 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
wcs | +0.602 |
fitt | +0.579 |
fir | +0.571 |
Hatt | +0.571 |
Brid | +0.564 |
Neg logit contributions | |
ROR | -1.342 |
igent | -1.148 |
amily | -1.136 |
=# | -1.111 |
racket | -1.102 |
Token | } |
Token ID | 1782 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
wcs | +1.851 |
fitt | +1.828 |
fir | +1.816 |
Hatt | +1.794 |
Brid | +1.785 |
Neg logit contributions | |
ROR | -2.012 |
igent | -1.639 |
amily | -1.638 |
=# | -1.567 |
onica | -1.542 |
Token | } |
Token ID | 1782 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
wcs | +2.248 |
fitt | +2.241 |
fir | +2.213 |
Hatt | +2.195 |
Brid | +2.179 |
Neg logit contributions | |
ROR | -2.383 |
igent | -1.931 |
amily | -1.907 |
=# | -1.837 |
onica | -1.809 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
wcs | +2.849 |
fitt | +2.832 |
fir | +2.805 |
Hatt | +2.783 |
Brid | +2.770 |
Neg logit contributions | |
ROR | -2.732 |
igent | -2.199 |
amily | -2.158 |
=# | -2.060 |
onica | -2.040 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
wcs | +0.736 |
fitt | +0.717 |
fir | +0.709 |
Hatt | +0.704 |
Brid | +0.700 |
Neg logit contributions | |
ROR | -1.438 |
igent | -1.228 |
amily | -1.207 |
=# | -1.173 |
onica | -1.163 |
Token | apply |
Token ID | 4174 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
wcs | +0.340 |
fitt | +0.333 |
fir | +0.331 |
Hatt | +0.329 |
Brid | +0.327 |
Neg logit contributions | |
ROR | -0.436 |
igent | -0.359 |
amily | -0.353 |
=# | -0.341 |
onica | -0.338 |
Token | _ |
Token ID | 62 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
wcs | +0.651 |
fitt | +0.637 |
Hatt | +0.632 |
fir | +0.632 |
Brid | +0.628 |
Neg logit contributions | |
ROR | -0.702 |
igent | -0.569 |
amily | -0.558 |
=# | -0.540 |
racket | -0.534 |
Token | move |
Token ID | 21084 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
wcs | +0.629 |
fitt | +0.594 |
fir | +0.588 |
Hatt | +0.578 |
heter | +0.576 |
Neg logit contributions | |
ROR | -1.205 |
igent | -1.014 |
amily | -1.003 |
=# | -0.981 |
racket | -0.971 |
Token |
|
Token ID | 198 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
wcs | +0.576 |
fir | +0.564 |
Hatt | +0.564 |
fitt | +0.564 |
Brid | +0.561 |
Neg logit contributions | |
ROR | -0.421 |
igent | -0.327 |
amily | -0.320 |
racket | -0.303 |
=# | -0.302 |
Token | pur |
Token ID | 14225 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
wcs | +0.339 |
fitt | +0.325 |
fir | +0.321 |
Hatt | +0.321 |
Brid | +0.320 |
Neg logit contributions | |
ROR | -0.370 |
igent | -0.302 |
amily | -0.297 |
racket | -0.288 |
=# | -0.286 |
Token | ak |
Token ID | 461 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
wcs | +0.753 |
fitt | +0.724 |
fir | +0.723 |
Hatt | +0.717 |
Brid | +0.716 |
Neg logit contributions | |
ROR | -0.866 |
igent | -0.703 |
amily | -0.687 |
=# | -0.670 |
racket | -0.665 |
Token | ushi |
Token ID | 17731 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ROR | +0.955 |
igent | +0.778 |
amily | +0.764 |
=# | +0.739 |
racket | +0.732 |
Neg logit contributions | |
wcs | -0.850 |
fitt | -0.830 |
Hatt | -0.824 |
fir | -0.824 |
Brid | -0.818 |
Token | Profile |
Token ID | 13118 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
wcs | +0.112 |
fitt | +0.110 |
Hatt | +0.109 |
fir | +0.109 |
Brid | +0.108 |
Neg logit contributions | |
ROR | -0.137 |
igent | -0.113 |
amily | -0.110 |
=# | -0.107 |
onica | -0.106 |
Token | Joined |
Token ID | 16709 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
ROR | +0.609 |
igent | +0.464 |
amily | +0.453 |
=# | +0.429 |
racket | +0.425 |
Neg logit contributions | |
wcs | -0.861 |
fitt | -0.845 |
Hatt | -0.842 |
fir | -0.842 |
Brid | -0.839 |
Token | August |
Token ID | 2932 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Hatt | +1.332 |
Brid | +1.323 |
wcs | +1.315 |
fir | +1.300 |
fitt | +1.283 |
Neg logit contributions | |
ROR | -4.560 |
igent | -4.006 |
amily | -3.939 |
=# | -3.810 |
onica | -3.810 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
wcs | +0.216 |
fitt | +0.211 |
Hatt | +0.209 |
fir | +0.209 |
Brid | +0.208 |
Neg logit contributions | |
ROR | -0.256 |
igent | -0.210 |
amily | -0.206 |
=# | -0.199 |
racket | -0.197 |
Token | United |
Token ID | 1578 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ROR | +1.228 |
igent | +1.018 |
amily | +1.000 |
=# | +0.978 |
racket | +0.973 |
Neg logit contributions | |
wcs | -0.872 |
fitt | -0.845 |
fir | -0.830 |
Hatt | -0.827 |
Brid | -0.815 |
Token | States |
Token ID | 1829 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ROR | +0.627 |
igent | +0.522 |
amily | +0.513 |
=# | +0.499 |
racket | +0.494 |
Neg logit contributions | |
wcs | -0.445 |
fitt | -0.433 |
Hatt | -0.429 |
fir | -0.429 |
Brid | -0.426 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
wcs | +0.008 |
fitt | +0.008 |
Hatt | +0.008 |
fir | +0.008 |
Brid | +0.008 |
Neg logit contributions | |
ROR | -0.011 |
igent | -0.009 |
amily | -0.009 |
=# | -0.009 |
racket | -0.009 |
Token | B |
Token ID | 347 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ROR | +0.767 |
igent | +0.625 |
amily | +0.612 |
=# | +0.595 |
racket | +0.589 |
Neg logit contributions | |
wcs | -0.675 |
fitt | -0.657 |
fir | -0.650 |
Hatt | -0.648 |
Brid | -0.643 |
Token | ort |
Token ID | 419 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
wcs | +0.851 |
fir | +0.845 |
fitt | +0.843 |
Hatt | +0.840 |
Brid | +0.832 |
Neg logit contributions | |
ROR | -1.011 |
igent | -0.829 |
amily | -0.815 |
=# | -0.795 |
racket | -0.792 |
Token | les |
Token ID | 829 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ROR | +0.112 |
amily | +0.096 |
igent | +0.096 |
racket | +0.093 |
=# | +0.093 |
Neg logit contributions | |
wcs | -0.041 |
fitt | -0.040 |
fir | -0.040 |
Hatt | -0.040 |
Brid | -0.039 |
Token | is |
Token ID | 318 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ROR | +0.908 |
igent | +0.742 |
amily | +0.730 |
=# | +0.705 |
racket | +0.699 |
Neg logit contributions | |
wcs | -0.767 |
fitt | -0.752 |
fir | -0.746 |
Hatt | -0.746 |
Brid | -0.740 |
Token | clicking |
Token ID | 12264 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ROR | +0.339 |
igent | +0.279 |
amily | +0.275 |
=# | +0.266 |
racket | +0.263 |
Neg logit contributions | |
wcs | -0.268 |
fitt | -0.262 |
fir | -0.260 |
Hatt | -0.260 |
Brid | -0.258 |
Token | right |
Token ID | 826 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
wcs | +0.096 |
fitt | +0.094 |
fir | +0.093 |
Hatt | +0.093 |
Brid | +0.092 |
Neg logit contributions | |
ROR | -0.124 |
igent | -0.102 |
amily | -0.100 |
=# | -0.097 |
racket | -0.096 |
Token | now |
Token ID | 783 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
fir | +2.662 |
fitt | +2.635 |
wcs | +2.623 |
Hatt | +2.566 |
Brid | +2.559 |
Neg logit contributions | |
ROR | -3.596 |
amily | -2.942 |
igent | -2.887 |
=# | -2.803 |
onica | -2.720 |
Token | with |
Token ID | 351 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
wcs | +0.592 |
fir | +0.582 |
fitt | +0.581 |
Hatt | +0.577 |
Brid | +0.571 |
Neg logit contributions | |
ROR | -0.724 |
igent | -0.587 |
amily | -0.580 |
=# | -0.563 |
onica | -0.554 |
Token | his |
Token ID | 465 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ROR | +0.003 |
igent | +0.003 |
amily | +0.003 |
=# | +0.003 |
onica | +0.003 |
Neg logit contributions | |
wcs | -0.002 |
fitt | -0.002 |
fir | -0.002 |
Hatt | -0.002 |
Brid | -0.002 |
Token | three |
Token ID | 1115 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
fitt | +0.926 |
fir | +0.925 |
wcs | +0.920 |
Hatt | +0.905 |
Brid | +0.905 |
Neg logit contributions | |
ROR | -1.164 |
igent | -0.950 |
amily | -0.946 |
=# | -0.902 |
onica | -0.892 |
Token | main |
Token ID | 1388 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
wcs | +0.374 |
fitt | +0.370 |
fir | +0.368 |
Hatt | +0.363 |
Brid | +0.361 |
Neg logit contributions | |
ROR | -0.440 |
igent | -0.360 |
amily | -0.356 |
=# | -0.342 |
onica | -0.337 |