Token | forms |
Token ID | 23914 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
IDE | +3.059 |
Falk | +2.963 |
Christensen | +2.825 |
apter | +2.705 |
ides | +2.669 |
Neg logit contributions | |
rush | -6.415 |
RL | -5.559 |
okane | -5.551 |
anyl | -5.525 |
itton | -5.326 |
Token | . |
Token ID | 13 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
IDE | +0.939 |
Falk | +0.935 |
Christensen | +0.908 |
apter | +0.867 |
ides | +0.837 |
Neg logit contributions | |
rush | -1.234 |
okane | -1.035 |
anyl | -1.030 |
RL | -1.026 |
itton | -0.981 |
Token | text |
Token ID | 5239 |
Feature activation | -5.11e-03 |
Pos logit contributions | |
Falk | +0.068 |
IDE | +0.067 |
Christensen | +0.066 |
apter | +0.063 |
ides | +0.061 |
Neg logit contributions | |
rush | -0.054 |
anyl | -0.042 |
okane | -0.042 |
RL | -0.042 |
itton | -0.040 |
Token | rend |
Token ID | 10920 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
rush | +0.039 |
okane | +0.032 |
RL | +0.032 |
anyl | +0.031 |
itton | +0.030 |
Neg logit contributions | |
IDE | -0.036 |
Falk | -0.036 |
Christensen | -0.035 |
apter | -0.034 |
ides | -0.033 |
Token | erer |
Token ID | 11882 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
rush | +0.526 |
okane | +0.402 |
RL | +0.397 |
anyl | +0.397 |
itton | +0.366 |
Neg logit contributions | |
Falk | -0.828 |
IDE | -0.828 |
Christensen | -0.813 |
apter | -0.792 |
ides | -0.765 |
Token | ] |
Token ID | 60 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
IDE | +1.347 |
Falk | +1.344 |
Christensen | +1.318 |
apter | +1.273 |
ides | +1.244 |
Neg logit contributions | |
rush | -0.815 |
okane | -0.622 |
anyl | -0.615 |
RL | -0.608 |
itton | -0.568 |
Token | :: |
Token ID | 3712 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
IDE | +3.687 |
Falk | +3.323 |
Christensen | +3.117 |
apter | +3.099 |
ides | +2.930 |
Neg logit contributions | |
rush | -12.302 |
rall | -11.490 |
okane | -11.298 |
anyl | -11.076 |
RL | -10.951 |
Token | Measure |
Token ID | 47384 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
Falk | +0.688 |
IDE | +0.685 |
Christensen | +0.670 |
apter | +0.641 |
ides | +0.617 |
Neg logit contributions | |
rush | -0.700 |
okane | -0.567 |
RL | -0.566 |
anyl | -0.565 |
itton | -0.535 |
Token | Text |
Token ID | 8206 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Falk | +0.490 |
IDE | +0.486 |
Christensen | +0.478 |
apter | +0.457 |
ides | +0.440 |
Neg logit contributions | |
rush | -0.483 |
RL | -0.390 |
okane | -0.389 |
anyl | -0.388 |
itton | -0.367 |
Token | ($ |
Token ID | 16763 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
Falk | +1.683 |
IDE | +1.680 |
Christensen | +1.623 |
apter | +1.540 |
ides | +1.486 |
Neg logit contributions | |
rush | -2.276 |
okane | -1.908 |
anyl | -1.898 |
RL | -1.897 |
itton | -1.806 |
Token | art |
Token ID | 433 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Falk | +0.535 |
IDE | +0.531 |
Christensen | +0.521 |
apter | +0.491 |
ides | +0.468 |
Neg logit contributions | |
rush | -0.706 |
RL | -0.586 |
anyl | -0.586 |
okane | -0.583 |
itton | -0.559 |
Token | 28 |
Token ID | 2579 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Falk | +0.194 |
IDE | +0.193 |
Christensen | +0.189 |
apter | +0.180 |
ides | +0.174 |
Neg logit contributions | |
rush | -0.209 |
okane | -0.171 |
anyl | -0.171 |
RL | -0.170 |
itton | -0.162 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
rush | +1.287 |
RL | +1.060 |
okane | +1.054 |
anyl | +1.049 |
itton | +0.994 |
Neg logit contributions | |
Falk | -1.139 |
IDE | -1.136 |
Christensen | -1.106 |
apter | -1.062 |
ides | -1.012 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
rush | +0.241 |
okane | +0.182 |
RL | +0.181 |
anyl | +0.181 |
itton | +0.167 |
Neg logit contributions | |
Falk | -0.381 |
IDE | -0.380 |
Christensen | -0.373 |
apter | -0.360 |
ides | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Falk | +0.459 |
IDE | +0.457 |
Christensen | +0.446 |
apter | +0.423 |
ides | +0.406 |
Neg logit contributions | |
rush | -0.575 |
okane | -0.478 |
anyl | -0.476 |
RL | -0.476 |
itton | -0.454 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
rush | +1.443 |
RL | +1.210 |
okane | +1.201 |
anyl | +1.197 |
itton | +1.139 |
Neg logit contributions | |
Falk | -1.006 |
IDE | -1.003 |
Christensen | -0.975 |
apter | -0.928 |
ides | -0.888 |
Token | / |
Token ID | 14 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
IDE | +4.782 |
Falk | +4.760 |
Christensen | +4.627 |
apter | +4.262 |
ides | +4.231 |
Neg logit contributions | |
rush | -4.815 |
okane | -4.115 |
anyl | -4.053 |
itton | -3.842 |
RL | -3.814 |
Token | Michael |
Token ID | 13256 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
IDE | +6.836 |
Falk | +6.592 |
Christensen | +6.239 |
Dou | +6.219 |
apter | +5.727 |
Neg logit contributions | |
rush | -7.694 |
okane | -6.983 |
anyl | -6.889 |
itton | -6.750 |
decay | -6.524 |
Token | K |
Token ID | 509 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Falk | +2.193 |
Christensen | +2.144 |
IDE | +2.061 |
apter | +1.957 |
Dou | +1.908 |
Neg logit contributions | |
rush | -2.454 |
anyl | -1.998 |
RL | -1.984 |
okane | -1.958 |
itton | -1.855 |
Token | lim |
Token ID | 2475 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
IDE | +1.945 |
Falk | +1.936 |
Christensen | +1.885 |
apter | +1.820 |
ides | +1.738 |
Neg logit contributions | |
rush | -2.854 |
RL | -2.529 |
anyl | -2.497 |
okane | -2.461 |
WARN | -2.396 |
Token | enty |
Token ID | 3787 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
Falk | +0.120 |
IDE | +0.119 |
Christensen | +0.113 |
apter | +0.101 |
ides | +0.095 |
Neg logit contributions | |
rush | -0.401 |
okane | -0.351 |
RL | -0.351 |
anyl | -0.351 |
itton | -0.340 |
Token | ev |
Token ID | 1990 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Falk | +0.467 |
IDE | +0.464 |
Christensen | +0.449 |
apter | +0.427 |
ides | +0.415 |
Neg logit contributions | |
rush | -0.732 |
okane | -0.622 |
anyl | -0.618 |
RL | -0.616 |
itton | -0.598 |
Token | 26 |
Token ID | 2608 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Falk | +1.973 |
IDE | +1.956 |
Christensen | +1.911 |
apter | +1.797 |
ides | +1.751 |
Neg logit contributions | |
rush | -2.210 |
anyl | -1.843 |
okane | -1.830 |
RL | -1.782 |
itton | -1.745 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
rush | +0.706 |
RL | +0.580 |
okane | +0.579 |
anyl | +0.576 |
itton | +0.547 |
Neg logit contributions | |
Falk | -0.612 |
IDE | -0.610 |
Christensen | -0.595 |
apter | -0.570 |
ides | -0.544 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
Falk | +1.500 |
IDE | +1.493 |
Christensen | +1.465 |
apter | +1.410 |
ides | +1.370 |
Neg logit contributions | |
rush | -1.037 |
okane | -0.797 |
anyl | -0.794 |
RL | -0.792 |
itton | -0.738 |
Token | . |
Token ID | 13 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
Falk | +0.557 |
IDE | +0.555 |
Christensen | +0.541 |
apter | +0.514 |
ides | +0.494 |
Neg logit contributions | |
rush | -0.695 |
okane | -0.577 |
anyl | -0.575 |
RL | -0.575 |
itton | -0.548 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
rush | +0.547 |
RL | +0.458 |
okane | +0.455 |
anyl | +0.452 |
itton | +0.431 |
Neg logit contributions | |
Falk | -0.384 |
IDE | -0.383 |
Christensen | -0.372 |
apter | -0.355 |
ides | -0.339 |
Token | / |
Token ID | 14 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
IDE | +4.827 |
Falk | +4.782 |
Christensen | +4.643 |
apter | +4.308 |
ides | +4.281 |
Neg logit contributions | |
rush | -4.748 |
okane | -4.040 |
anyl | -3.992 |
RL | -3.796 |
itton | -3.767 |
Token | En |
Token ID | 4834 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
IDE | +6.906 |
Falk | +6.668 |
Christensen | +6.365 |
Dou | +6.273 |
ides | +6.012 |
Neg logit contributions | |
rush | -7.563 |
okane | -6.639 |
anyl | -6.559 |
RL | -6.379 |
itton | -6.361 |
Token | rique |
Token ID | 33865 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Falk | +0.296 |
IDE | +0.294 |
Christensen | +0.287 |
apter | +0.274 |
ides | +0.266 |
Neg logit contributions | |
rush | -0.339 |
okane | -0.279 |
anyl | -0.278 |
RL | -0.277 |
itton | -0.265 |
Token | de |
Token ID | 390 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
Falk | +1.549 |
IDE | +1.545 |
Christensen | +1.503 |
apter | +1.432 |
ides | +1.370 |
Neg logit contributions | |
rush | -1.984 |
okane | -1.648 |
RL | -1.647 |
anyl | -1.643 |
itton | -1.566 |
Token | la |
Token ID | 8591 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
IDE | +0.451 |
Falk | +0.449 |
Christensen | +0.439 |
apter | +0.419 |
ides | +0.402 |
Neg logit contributions | |
rush | -0.530 |
RL | -0.437 |
anyl | -0.436 |
okane | -0.434 |
itton | -0.412 |
Token | Os |
Token ID | 8834 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
rush | +0.472 |
okane | +0.374 |
anyl | +0.371 |
RL | +0.368 |
itton | +0.346 |
Neg logit contributions | |
Falk | -0.586 |
IDE | -0.581 |
Christensen | -0.572 |
apter | -0.545 |
ides | -0.532 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Falk | +1.851 |
IDE | +1.846 |
Christensen | +1.787 |
apter | +1.685 |
ides | +1.639 |
Neg logit contributions | |
rush | -2.619 |
okane | -2.218 |
anyl | -2.210 |
RL | -2.181 |
itton | -2.120 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Falk | +1.378 |
IDE | +1.377 |
Christensen | +1.332 |
apter | +1.260 |
ides | +1.219 |
Neg logit contributions | |
rush | -1.896 |
okane | -1.603 |
anyl | -1.598 |
RL | -1.575 |
itton | -1.529 |
Token | 27 |
Token ID | 1983 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Falk | +1.128 |
IDE | +1.117 |
Christensen | +1.093 |
apter | +1.038 |
ides | +0.990 |
Neg logit contributions | |
rush | -1.538 |
RL | -1.283 |
okane | -1.281 |
anyl | -1.275 |
itton | -1.216 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Falk | +1.932 |
IDE | +1.931 |
Christensen | +1.882 |
apter | +1.788 |
ides | +1.729 |
Neg logit contributions | |
rush | -2.188 |
anyl | -1.797 |
okane | -1.796 |
RL | -1.783 |
itton | -1.708 |
Token |
|
Token ID | 198 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Falk | +2.506 |
IDE | +2.501 |
Christensen | +2.428 |
apter | +2.268 |
ides | +2.226 |
Neg logit contributions | |
rush | -3.724 |
okane | -3.175 |
anyl | -3.164 |
RL | -3.090 |
itton | -3.051 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
IDE | +4.055 |
Falk | +3.979 |
Christensen | +3.819 |
ides | +3.572 |
apter | +3.540 |
Neg logit contributions | |
rush | -6.954 |
okane | -6.142 |
anyl | -6.100 |
rall | -6.044 |
itton | -5.956 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
IDE | +4.381 |
Falk | +3.850 |
Christensen | +3.840 |
Dou | +3.589 |
ides | +3.561 |
Neg logit contributions | |
rush | -10.141 |
RL | -8.974 |
okane | -8.917 |
itton | -8.897 |
anyl | -8.870 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
IDE | +2.569 |
Falk | +2.556 |
Christensen | +2.506 |
apter | +2.375 |
ides | +2.321 |
Neg logit contributions | |
rush | -2.768 |
anyl | -2.277 |
okane | -2.272 |
RL | -2.228 |
itton | -2.182 |
Token | this |
Token ID | 428 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Falk | +3.472 |
IDE | +3.395 |
Christensen | +3.394 |
apter | +3.088 |
ides | +3.065 |
Neg logit contributions | |
rush | -5.817 |
okane | -4.997 |
anyl | -4.988 |
itton | -4.827 |
RL | -4.821 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
IDE | +4.322 |
Falk | +4.295 |
Christensen | +4.271 |
ides | +3.910 |
apter | +3.898 |
Neg logit contributions | |
rush | -5.002 |
okane | -4.142 |
anyl | -4.103 |
itton | -3.944 |
RL | -3.928 |
Token | on |
Token ID | 319 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Falk | +2.838 |
IDE | +2.821 |
Christensen | +2.775 |
apter | +2.621 |
ides | +2.566 |
Neg logit contributions | |
rush | -2.990 |
anyl | -2.479 |
okane | -2.476 |
RL | -2.395 |
itton | -2.341 |
Token | 11 |
Token ID | 1367 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Falk | +0.194 |
IDE | +0.193 |
Christensen | +0.189 |
apter | +0.181 |
ides | +0.174 |
Neg logit contributions | |
rush | -0.201 |
RL | -0.163 |
okane | -0.163 |
anyl | -0.162 |
itton | -0.154 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
rush | +2.197 |
RL | +1.805 |
okane | +1.796 |
anyl | +1.785 |
itton | +1.682 |
Neg logit contributions | |
Falk | -2.000 |
IDE | -1.992 |
Christensen | -1.941 |
apter | -1.868 |
ides | -1.778 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
rush | +1.791 |
RL | +1.411 |
okane | +1.377 |
anyl | +1.363 |
itton | +1.280 |
Neg logit contributions | |
IDE | -2.438 |
Falk | -2.428 |
Christensen | -2.377 |
apter | -2.309 |
ides | -2.226 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
rush | +3.163 |
RL | +2.580 |
okane | +2.566 |
anyl | +2.522 |
itton | +2.402 |
Neg logit contributions | |
IDE | -2.860 |
Falk | -2.844 |
Christensen | -2.784 |
apter | -2.725 |
ides | -2.574 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
rush | +1.818 |
RL | +1.521 |
okane | +1.499 |
anyl | +1.494 |
itton | +1.420 |
Neg logit contributions | |
IDE | -1.336 |
Falk | -1.328 |
Christensen | -1.293 |
apter | -1.244 |
ides | -1.187 |
Token | / |
Token ID | 14 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Falk | +4.931 |
IDE | +4.884 |
Christensen | +4.769 |
apter | +4.408 |
ides | +4.365 |
Neg logit contributions | |
rush | -4.790 |
okane | -4.024 |
anyl | -4.023 |
RL | -3.779 |
itton | -3.751 |
Token | Cl |
Token ID | 2601 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
IDE | +6.440 |
Falk | +6.433 |
Christensen | +6.076 |
Dou | +5.987 |
apter | +5.621 |
Neg logit contributions | |
rush | -7.312 |
okane | -6.318 |
anyl | -6.155 |
RL | -5.998 |
itton | -5.951 |
Token | od |
Token ID | 375 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Falk | +1.795 |
IDE | +1.748 |
Christensen | +1.713 |
apter | +1.648 |
ides | +1.575 |
Neg logit contributions | |
rush | -2.562 |
RL | -2.208 |
okane | -2.189 |
anyl | -2.179 |
decay | -2.068 |
Token | agh |
Token ID | 10471 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
rush | +2.326 |
RL | +1.981 |
anyl | +1.945 |
okane | +1.945 |
itton | +1.863 |
Neg logit contributions | |
IDE | -1.207 |
Falk | -1.145 |
Christensen | -1.086 |
apter | -1.075 |
Dou | -0.999 |
Token | Kil |
Token ID | 19902 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
rush | +1.206 |
RL | +0.969 |
okane | +0.952 |
anyl | +0.944 |
itton | +0.877 |
Neg logit contributions | |
IDE | -1.247 |
Falk | -1.232 |
Christensen | -1.209 |
apter | -1.184 |
Azerbai | -1.131 |
Token | c |
Token ID | 66 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
rush | +0.903 |
okane | +0.739 |
anyl | +0.737 |
RL | +0.737 |
itton | +0.698 |
Neg logit contributions | |
Falk | -0.790 |
IDE | -0.788 |
Christensen | -0.767 |
apter | -0.731 |
ides | -0.702 |
Token | 23 |
Token ID | 2242 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Falk | +1.246 |
IDE | +1.238 |
Christensen | +1.210 |
apter | +1.145 |
ides | +1.111 |
Neg logit contributions | |
rush | -1.363 |
anyl | -1.122 |
okane | -1.121 |
RL | -1.101 |
itton | -1.067 |
Token | , |
Token ID | 11 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
rush | +1.107 |
RL | +0.911 |
okane | +0.911 |
anyl | +0.906 |
itton | +0.860 |
Neg logit contributions | |
Falk | -0.965 |
IDE | -0.961 |
Christensen | -0.939 |
apter | -0.896 |
ides | -0.856 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
rush | +0.172 |
RL | +0.121 |
okane | +0.119 |
anyl | +0.119 |
itton | +0.105 |
Neg logit contributions | |
Falk | -0.380 |
IDE | -0.379 |
Christensen | -0.373 |
apter | -0.362 |
ides | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
rush | +0.804 |
okane | +0.661 |
RL | +0.661 |
anyl | +0.658 |
itton | +0.624 |
Neg logit contributions | |
Falk | -0.691 |
IDE | -0.687 |
Christensen | -0.672 |
apter | -0.643 |
ides | -0.613 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
rush | +1.301 |
RL | +1.089 |
okane | +1.081 |
anyl | +1.078 |
itton | +1.026 |
Neg logit contributions | |
IDE | -0.922 |
Falk | -0.922 |
Christensen | -0.892 |
apter | -0.854 |
ides | -0.815 |
Token | / |
Token ID | 14 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
IDE | +4.813 |
Falk | +4.790 |
Christensen | +4.679 |
apter | +4.300 |
Dou | +4.261 |
Neg logit contributions | |
rush | -4.907 |
okane | -4.203 |
anyl | -4.147 |
itton | -3.929 |
RL | -3.903 |
Token | Joshua |
Token ID | 47740 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
IDE | +6.624 |
Falk | +6.578 |
Christensen | +6.287 |
Dou | +6.275 |
NIC | +5.834 |
Neg logit contributions | |
rush | -6.767 |
okane | -5.832 |
anyl | -5.828 |
itton | -5.659 |
RL | -5.455 |
Token | Roberts |
Token ID | 10918 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Christensen | +3.149 |
Falk | +3.142 |
IDE | +3.033 |
ides | +2.795 |
apter | +2.767 |
Neg logit contributions | |
rush | -3.255 |
anyl | -2.653 |
okane | -2.622 |
RL | -2.445 |
decay | -2.415 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
Falk | +0.992 |
IDE | +0.988 |
Christensen | +0.961 |
apter | +0.912 |
ides | +0.872 |
Neg logit contributions | |
rush | -1.366 |
okane | -1.142 |
RL | -1.140 |
anyl | -1.138 |
itton | -1.086 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
rush | +0.024 |
okane | +0.020 |
RL | +0.020 |
anyl | +0.020 |
itton | +0.019 |
Neg logit contributions | |
Falk | -0.019 |
IDE | -0.019 |
Christensen | -0.018 |
apter | -0.018 |
ides | -0.017 |
Token | DE |
Token ID | 7206 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Falk | +0.294 |
IDE | +0.293 |
Christensen | +0.287 |
apter | +0.274 |
ides | +0.264 |
Neg logit contributions | |
rush | -0.291 |
okane | -0.235 |
RL | -0.235 |
anyl | -0.234 |
itton | -0.221 |
Token | 66 |
Token ID | 2791 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
rush | +1.577 |
RL | +1.329 |
okane | +1.324 |
anyl | +1.314 |
itton | +1.246 |
Neg logit contributions | |
Falk | -1.101 |
IDE | -1.096 |
Christensen | -1.071 |
apter | -1.009 |
ides | -0.959 |
Token | 284 |
Token ID | 30336 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
rush | +0.608 |
okane | +0.494 |
anyl | +0.493 |
RL | +0.492 |
itton | +0.466 |
Neg logit contributions | |
Falk | -0.573 |
IDE | -0.568 |
Christensen | -0.556 |
apter | -0.529 |
ides | -0.507 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
rush | +1.366 |
RL | +1.099 |
okane | +1.098 |
anyl | +1.091 |
itton | +1.028 |
Neg logit contributions | |
Falk | -1.441 |
IDE | -1.436 |
Christensen | -1.407 |
apter | -1.342 |
ides | -1.295 |
Token | 64 |
Token ID | 2414 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Falk | +0.486 |
IDE | +0.484 |
Christensen | +0.471 |
apter | +0.446 |
ides | +0.426 |
Neg logit contributions | |
rush | -0.688 |
okane | -0.576 |
RL | -0.575 |
anyl | -0.574 |
itton | -0.548 |
Token | 406 |
Token ID | 29703 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
IDE | +2.716 |
Falk | +2.698 |
Christensen | +2.632 |
apter | +2.518 |
ides | +2.419 |
Neg logit contributions | |
rush | -3.441 |
okane | -2.854 |
RL | -2.852 |
anyl | -2.825 |
itton | -2.701 |
Token | Mem |
Token ID | 4942 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
rush | +0.696 |
RL | +0.592 |
okane | +0.587 |
anyl | +0.587 |
itton | +0.560 |
Neg logit contributions | |
IDE | -0.422 |
Falk | -0.422 |
Christensen | -0.409 |
apter | -0.385 |
ides | -0.366 |
Token | c |
Token ID | 66 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
IDE | +5.014 |
Falk | +4.933 |
Christensen | +4.810 |
apter | +4.781 |
ides | +4.626 |
Neg logit contributions | |
rush | -8.015 |
RL | -7.072 |
rall | -6.999 |
anyl | -6.951 |
okane | -6.940 |
Token | py |
Token ID | 9078 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
IDE | +1.971 |
Falk | +1.969 |
Christensen | +1.906 |
apter | +1.869 |
ides | +1.797 |
Neg logit contributions | |
rush | -2.095 |
RL | -1.738 |
okane | -1.726 |
anyl | -1.712 |
itton | -1.634 |
Token | Reading |
Token ID | 36120 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
rush | +1.382 |
RL | +1.093 |
anyl | +1.089 |
okane | +1.080 |
itton | +1.010 |
Neg logit contributions | |
Falk | -1.563 |
IDE | -1.537 |
Christensen | -1.536 |
apter | -1.453 |
ides | -1.404 |
Token | 55 |
Token ID | 5996 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Falk | +1.332 |
IDE | +1.323 |
Christensen | +1.293 |
apter | +1.235 |
ides | +1.189 |
Neg logit contributions | |
rush | -1.445 |
okane | -1.174 |
anyl | -1.173 |
RL | -1.167 |
itton | -1.110 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Falk | +0.936 |
IDE | +0.931 |
Christensen | +0.898 |
apter | +0.839 |
ides | +0.791 |
Neg logit contributions | |
rush | -1.939 |
okane | -1.667 |
RL | -1.664 |
anyl | -1.663 |
itton | -1.600 |
Token | 24 |
Token ID | 1987 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
rush | +0.594 |
RL | +0.485 |
okane | +0.481 |
anyl | +0.478 |
itton | +0.452 |
Neg logit contributions | |
Falk | -0.570 |
IDE | -0.569 |
Christensen | -0.555 |
apter | -0.534 |
ides | -0.512 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
rush | +1.936 |
RL | +1.588 |
okane | +1.580 |
anyl | +1.565 |
itton | +1.482 |
Neg logit contributions | |
Falk | -1.762 |
IDE | -1.757 |
Christensen | -1.714 |
apter | -1.645 |
ides | -1.563 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
rush | +0.795 |
RL | +0.592 |
okane | +0.584 |
anyl | +0.577 |
itton | +0.531 |
Neg logit contributions | |
Falk | -1.392 |
IDE | -1.390 |
Christensen | -1.363 |
apter | -1.325 |
ides | -1.281 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
rush | +1.138 |
RL | +0.933 |
okane | +0.933 |
anyl | +0.928 |
itton | +0.879 |
Neg logit contributions | |
Falk | -0.987 |
IDE | -0.987 |
Christensen | -0.961 |
apter | -0.921 |
ides | -0.880 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
rush | +1.467 |
RL | +1.227 |
okane | +1.215 |
anyl | +1.206 |
itton | +1.150 |
Neg logit contributions | |
IDE | -1.048 |
Falk | -1.044 |
Christensen | -1.015 |
apter | -0.973 |
ides | -0.933 |
Token | / |
Token ID | 14 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
IDE | +4.652 |
Falk | +4.599 |
Christensen | +4.431 |
apter | +4.175 |
ides | +4.139 |
Neg logit contributions | |
rush | -4.616 |
okane | -3.898 |
anyl | -3.889 |
RL | -3.697 |
rall | -3.655 |
Token | Nick |
Token ID | 23609 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
IDE | +6.078 |
Falk | +5.916 |
Dou | +5.690 |
Christensen | +5.678 |
apter | +5.307 |
Neg logit contributions | |
rush | -7.150 |
okane | -6.186 |
anyl | -6.137 |
RL | -6.046 |
itton | -5.906 |
Token | Oxford |
Token ID | 13643 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Falk | +2.255 |
IDE | +2.241 |
Christensen | +2.195 |
apter | +2.088 |
ides | +2.005 |
Neg logit contributions | |
rush | -2.649 |
okane | -2.186 |
anyl | -2.180 |
RL | -2.178 |
itton | -2.071 |
Token | / |
Token ID | 14 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Falk | +2.149 |
IDE | +2.127 |
Christensen | +2.091 |
apter | +1.972 |
ides | +1.932 |
Neg logit contributions | |
rush | -2.108 |
okane | -1.703 |
anyl | -1.694 |
RL | -1.682 |
itton | -1.601 |
Token | File |
Token ID | 8979 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Falk | +0.815 |
IDE | +0.810 |
Christensen | +0.778 |
apter | +0.719 |
ides | +0.670 |
Neg logit contributions | |
rush | -2.044 |
okane | -1.772 |
RL | -1.769 |
anyl | -1.767 |
itton | -1.704 |
Token | Photo |
Token ID | 5555 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Falk | +1.772 |
IDE | +1.707 |
Christensen | +1.683 |
apter | +1.523 |
ides | +1.441 |
Neg logit contributions | |
rush | -4.024 |
okane | -3.457 |
RL | -3.447 |
anyl | -3.443 |
itton | -3.339 |
Token |
|
Token ID | 198 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
Falk | +1.004 |
IDE | +1.000 |
Christensen | +0.973 |
apter | +0.921 |
ides | +0.889 |
Neg logit contributions | |
rush | -1.341 |
okane | -1.123 |
anyl | -1.120 |
RL | -1.113 |
itton | -1.070 |
Token |
|
Token ID | 198 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
Falk | +0.571 |
IDE | +0.570 |
Christensen | +0.554 |
apter | +0.526 |
ides | +0.506 |
Neg logit contributions | |
rush | -0.744 |
okane | -0.622 |
anyl | -0.620 |
RL | -0.617 |
itton | -0.591 |
Token | 19 |
Token ID | 1129 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Falk | +0.042 |
IDE | +0.041 |
Christensen | +0.041 |
apter | +0.039 |
ides | +0.037 |
Neg logit contributions | |
rush | -0.057 |
RL | -0.047 |
okane | -0.047 |
anyl | -0.046 |
itton | -0.044 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Falk | +1.522 |
IDE | +1.516 |
Christensen | +1.480 |
apter | +1.413 |
ides | +1.360 |
Neg logit contributions | |
rush | -1.659 |
okane | -1.356 |
RL | -1.353 |
anyl | -1.352 |
itton | -1.282 |
Token |
|
Token ID | 198 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Falk | +2.185 |
IDE | +2.180 |
Christensen | +2.116 |
apter | +1.981 |
ides | +1.938 |
Neg logit contributions | |
rush | -3.176 |
okane | -2.701 |
anyl | -2.691 |
RL | -2.635 |
itton | -2.591 |
Token |
|
Token ID | 198 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
IDE | +3.878 |
Falk | +3.811 |
Christensen | +3.662 |
ides | +3.413 |
apter | +3.399 |
Neg logit contributions | |
rush | -6.553 |
okane | -5.780 |
anyl | -5.739 |
rall | -5.677 |
itton | -5.596 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
IDE | +4.137 |
Falk | +3.683 |
Christensen | +3.661 |
Dou | +3.398 |
ides | +3.353 |
Neg logit contributions | |
rush | -9.317 |
RL | -8.225 |
anyl | -8.169 |
okane | -8.168 |
itton | -8.114 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
IDE | +2.711 |
Falk | +2.702 |
Christensen | +2.647 |
apter | +2.508 |
ides | +2.448 |
Neg logit contributions | |
rush | -2.901 |
anyl | -2.384 |
okane | -2.377 |
RL | -2.338 |
itton | -2.281 |
Token | this |
Token ID | 428 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Falk | +3.339 |
IDE | +3.272 |
Christensen | +3.262 |
apter | +2.979 |
ides | +2.949 |
Neg logit contributions | |
rush | -5.517 |
okane | -4.729 |
anyl | -4.721 |
RL | -4.578 |
itton | -4.563 |
Token | comment |
Token ID | 2912 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
IDE | +4.423 |
Falk | +4.398 |
Christensen | +4.380 |
ides | +3.995 |
apter | +3.967 |
Neg logit contributions | |
rush | -5.207 |
okane | -4.301 |
anyl | -4.275 |
itton | -4.107 |
RL | -4.086 |
Token | on |
Token ID | 319 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Falk | +2.693 |
IDE | +2.678 |
Christensen | +2.632 |
apter | +2.487 |
ides | +2.433 |
Neg logit contributions | |
rush | -2.819 |
anyl | -2.335 |
okane | -2.329 |
RL | -2.258 |
itton | -2.202 |
Token | January |
Token ID | 3269 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Falk | +0.770 |
IDE | +0.767 |
Christensen | +0.741 |
apter | +0.701 |
ides | +0.661 |
Neg logit contributions | |
rush | -1.331 |
okane | -1.128 |
RL | -1.128 |
anyl | -1.125 |
itton | -1.077 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Falk | +2.850 |
IDE | +2.804 |
Christensen | +2.713 |
apter | +2.518 |
ides | +2.433 |
Neg logit contributions | |
rush | -4.921 |
anyl | -4.199 |
okane | -4.176 |
RL | -4.119 |
itton | -4.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
IDE | +1.613 |
Falk | +1.612 |
Christensen | +1.559 |
apter | +1.483 |
ides | +1.436 |
Neg logit contributions | |
rush | -2.058 |
okane | -1.730 |
anyl | -1.723 |
RL | -1.705 |
itton | -1.646 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Falk | +3.281 |
IDE | +3.229 |
Christensen | +3.172 |
apter | +2.966 |
ides | +2.937 |
Neg logit contributions | |
rush | -3.632 |
okane | -3.041 |
anyl | -2.994 |
RL | -2.936 |
itton | -2.882 |
Token | Que |
Token ID | 15681 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
IDE | +2.417 |
Falk | +2.354 |
Christensen | +2.267 |
apter | +2.155 |
Dou | +2.134 |
Neg logit contributions | |
rush | -3.275 |
anyl | -2.792 |
okane | -2.787 |
RL | -2.734 |
itton | -2.673 |
Token | er |
Token ID | 263 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
IDE | +3.893 |
Falk | +3.810 |
Christensen | +3.732 |
apter | +3.613 |
ides | +3.450 |
Neg logit contributions | |
rush | -6.179 |
okane | -5.384 |
anyl | -5.359 |
RL | -5.277 |
rall | -5.131 |
Token | magnet |
Token ID | 19972 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
IDE | +5.604 |
Falk | +5.586 |
Christensen | +5.374 |
apter | +5.248 |
ether | +4.941 |
Neg logit contributions | |
rush | -7.220 |
okane | -6.287 |
anyl | -6.093 |
RL | -6.017 |
itton | -5.848 |
Token | ? |
Token ID | 30 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
IDE | +4.438 |
Falk | +4.402 |
Christensen | +4.238 |
apter | +3.956 |
ides | +3.930 |
Neg logit contributions | |
rush | -6.629 |
anyl | -5.639 |
okane | -5.595 |
RL | -5.518 |
itton | -5.378 |
Token |
|
Token ID | 198 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Falk | +3.457 |
IDE | +3.450 |
Christensen | +3.342 |
apter | +3.150 |
ides | +3.033 |
Neg logit contributions | |
rush | -5.101 |
okane | -4.284 |
anyl | -4.267 |
RL | -4.225 |
itton | -4.092 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
IDE | +3.742 |
Falk | +3.732 |
Christensen | +3.591 |
apter | +3.361 |
ides | +3.286 |
Neg logit contributions | |
rush | -6.340 |
okane | -5.575 |
anyl | -5.526 |
rall | -5.469 |
itton | -5.361 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Falk | +2.694 |
IDE | +2.678 |
Christensen | +2.640 |
apter | +2.549 |
ides | +2.475 |
Neg logit contributions | |
rush | -1.474 |
okane | -1.069 |
anyl | -1.069 |
RL | -1.067 |
itton | -0.975 |
Token | The |
Token ID | 464 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
IDE | +4.763 |
Falk | +4.717 |
Christensen | +4.573 |
apter | +4.306 |
Dou | +4.268 |
Neg logit contributions | |
rush | -5.900 |
okane | -4.941 |
anyl | -4.912 |
RL | -4.815 |
itton | -4.704 |
Token | Best |
Token ID | 13014 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Falk | +0.750 |
IDE | +0.747 |
Christensen | +0.719 |
apter | +0.670 |
ides | +0.633 |
Neg logit contributions | |
rush | -1.575 |
okane | -1.355 |
RL | -1.353 |
anyl | -1.352 |
itton | -1.301 |
Token | T |
Token ID | 51 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
IDE | +4.108 |
Falk | +4.077 |
Christensen | +3.958 |
apter | +3.761 |
Dou | +3.704 |
Neg logit contributions | |
rush | -4.464 |
okane | -3.680 |
anyl | -3.648 |
RL | -3.616 |
itton | -3.475 |
Token | reek |
Token ID | 10316 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Falk | +0.748 |
IDE | +0.748 |
Christensen | +0.728 |
apter | +0.694 |
ides | +0.668 |
Neg logit contributions | |
rush | -0.879 |
okane | -0.724 |
RL | -0.723 |
anyl | -0.722 |
itton | -0.685 |
Token | As |
Token ID | 1722 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
IDE | +3.559 |
Falk | +3.546 |
Christensen | +3.441 |
apter | +3.292 |
ides | +3.211 |
Neg logit contributions | |
rush | -3.966 |
okane | -3.299 |
anyl | -3.281 |
RL | -3.264 |
itton | -3.124 |
Token | yu |
Token ID | 24767 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
IDE | +2.062 |
Falk | +2.043 |
Christensen | +1.947 |
apter | +1.812 |
ides | +1.738 |
Neg logit contributions | |
rush | -4.540 |
okane | -3.918 |
RL | -3.912 |
anyl | -3.904 |
itton | -3.776 |
Token | K |
Token ID | 42 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
IDE | +6.254 |
Falk | +6.148 |
Christensen | +5.985 |
Dou | +5.671 |
apter | +5.594 |
Neg logit contributions | |
rush | -6.685 |
okane | -5.498 |
anyl | -5.445 |
RL | -5.353 |
itton | -5.221 |
Token | ong |
Token ID | 506 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
Falk | +0.800 |
IDE | +0.797 |
Christensen | +0.772 |
apter | +0.730 |
ides | +0.697 |
Neg logit contributions | |
rush | -1.261 |
okane | -1.064 |
RL | -1.064 |
anyl | -1.062 |
itton | -1.016 |
Token | Ch |
Token ID | 1925 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
IDE | +5.791 |
Falk | +5.636 |
Christensen | +5.551 |
Dou | +5.214 |
apter | +5.145 |
Neg logit contributions | |
rush | -7.040 |
okane | -5.981 |
RL | -5.834 |
anyl | -5.799 |
itton | -5.608 |
Token | oya |
Token ID | 23790 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Falk | +0.710 |
IDE | +0.707 |
Christensen | +0.692 |
apter | +0.676 |
ides | +0.653 |
Neg logit contributions | |
rush | -0.526 |
RL | -0.413 |
anyl | -0.404 |
okane | -0.400 |
WARN | -0.379 |
Token | Week |
Token ID | 20916 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
IDE | +5.219 |
Falk | +5.138 |
Christensen | +4.979 |
Dou | +4.760 |
apter | +4.744 |
Neg logit contributions | |
rush | -5.307 |
okane | -4.382 |
anyl | -4.299 |
RL | -4.247 |
itton | -4.096 |
Token | materials |
Token ID | 5696 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Falk | +0.709 |
IDE | +0.707 |
Christensen | +0.691 |
apter | +0.659 |
ides | +0.634 |
Neg logit contributions | |
rush | -0.790 |
okane | -0.647 |
anyl | -0.646 |
RL | -0.645 |
itton | -0.612 |
Token | to |
Token ID | 284 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
Falk | +2.933 |
IDE | +2.913 |
Christensen | +2.875 |
apter | +2.730 |
ides | +2.656 |
Neg logit contributions | |
rush | -3.121 |
anyl | -2.525 |
okane | -2.517 |
RL | -2.494 |
itton | -2.396 |
Token | v |
Token ID | 410 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
rush | +0.299 |
okane | +0.237 |
RL | +0.237 |
anyl | +0.235 |
itton | +0.221 |
Neg logit contributions | |
IDE | -0.357 |
Falk | -0.357 |
Christensen | -0.349 |
apter | -0.335 |
ides | -0.324 |
Token | p |
Token ID | 79 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Falk | +0.866 |
IDE | +0.863 |
Christensen | +0.841 |
apter | +0.803 |
ides | +0.773 |
Neg logit contributions | |
rush | -1.013 |
RL | -0.835 |
okane | -0.834 |
anyl | -0.832 |
itton | -0.790 |
Token | @ |
Token ID | 31 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
Falk | +0.182 |
IDE | +0.181 |
Christensen | +0.177 |
apter | +0.169 |
Dou | +0.162 |
Neg logit contributions | |
rush | -0.191 |
okane | -0.156 |
anyl | -0.155 |
RL | -0.155 |
itton | -0.147 |
Token | peace |
Token ID | 22988 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Falk | +0.328 |
IDE | +0.327 |
Christensen | +0.320 |
apter | +0.305 |
ides | +0.293 |
Neg logit contributions | |
rush | -0.352 |
okane | -0.287 |
RL | -0.286 |
anyl | -0.286 |
itton | -0.271 |
Token | cor |
Token ID | 10215 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
IDE | +4.372 |
Falk | +4.288 |
apter | +4.071 |
Christensen | +4.049 |
ides | +3.942 |
Neg logit contributions | |
rush | -8.219 |
RL | -7.243 |
anyl | -7.054 |
okane | -7.027 |
WARN | -6.820 |
Token | ps |
Token ID | 862 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rush | +1.939 |
okane | +1.508 |
anyl | +1.490 |
RL | +1.474 |
itton | +1.397 |
Neg logit contributions | |
Falk | -2.473 |
IDE | -2.451 |
Christensen | -2.408 |
apter | -2.276 |
�士 | -2.229 |
Token | connect |
Token ID | 8443 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
Falk | +0.712 |
IDE | +0.706 |
Christensen | +0.689 |
apter | +0.648 |
ides | +0.616 |
Neg logit contributions | |
rush | -1.096 |
okane | -0.923 |
anyl | -0.920 |
RL | -0.919 |
itton | -0.880 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Falk | +0.104 |
IDE | +0.104 |
Christensen | +0.101 |
apter | +0.096 |
ides | +0.092 |
Neg logit contributions | |
rush | -0.127 |
okane | -0.105 |
RL | -0.105 |
anyl | -0.105 |
itton | -0.100 |
Token | org |
Token ID | 2398 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
IDE | +0.719 |
Falk | +0.715 |
Christensen | +0.681 |
apter | +0.626 |
ides | +0.582 |
Neg logit contributions | |
rush | -2.154 |
okane | -1.883 |
anyl | -1.882 |
RL | -1.879 |
itton | -1.820 |
Token | T |
Token ID | 51 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
IDE | +4.108 |
Falk | +4.077 |
Christensen | +3.958 |
apter | +3.761 |
Dou | +3.704 |
Neg logit contributions | |
rush | -4.464 |
okane | -3.680 |
anyl | -3.648 |
RL | -3.616 |
itton | -3.475 |
Token | reek |
Token ID | 10316 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Falk | +0.748 |
IDE | +0.748 |
Christensen | +0.728 |
apter | +0.694 |
ides | +0.668 |
Neg logit contributions | |
rush | -0.879 |
okane | -0.724 |
RL | -0.723 |
anyl | -0.722 |
itton | -0.685 |
Token | As |
Token ID | 1722 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
IDE | +3.559 |
Falk | +3.546 |
Christensen | +3.441 |
apter | +3.292 |
ides | +3.211 |
Neg logit contributions | |
rush | -3.966 |
okane | -3.299 |
anyl | -3.281 |
RL | -3.264 |
itton | -3.124 |
Token | yu |
Token ID | 24767 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
IDE | +2.062 |
Falk | +2.043 |
Christensen | +1.947 |
apter | +1.812 |
ides | +1.738 |
Neg logit contributions | |
rush | -4.540 |
okane | -3.918 |
RL | -3.912 |
anyl | -3.904 |
itton | -3.776 |
Token | K |
Token ID | 42 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
IDE | +6.254 |
Falk | +6.148 |
Christensen | +5.985 |
Dou | +5.671 |
apter | +5.594 |
Neg logit contributions | |
rush | -6.685 |
okane | -5.498 |
anyl | -5.445 |
RL | -5.353 |
itton | -5.221 |
Token | ong |
Token ID | 506 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
Falk | +0.800 |
IDE | +0.797 |
Christensen | +0.772 |
apter | +0.730 |
ides | +0.697 |
Neg logit contributions | |
rush | -1.261 |
okane | -1.064 |
RL | -1.064 |
anyl | -1.062 |
itton | -1.016 |
Token | Ch |
Token ID | 1925 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
IDE | +5.791 |
Falk | +5.636 |
Christensen | +5.551 |
Dou | +5.214 |
apter | +5.145 |
Neg logit contributions | |
rush | -7.040 |
okane | -5.981 |
RL | -5.834 |
anyl | -5.799 |
itton | -5.608 |
Token | oya |
Token ID | 23790 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Falk | +0.710 |
IDE | +0.707 |
Christensen | +0.692 |
apter | +0.676 |
ides | +0.653 |
Neg logit contributions | |
rush | -0.526 |
RL | -0.413 |
anyl | -0.404 |
okane | -0.400 |
WARN | -0.379 |
Token | Week |
Token ID | 20916 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
IDE | +5.219 |
Falk | +5.138 |
Christensen | +4.979 |
Dou | +4.760 |
apter | +4.744 |
Neg logit contributions | |
rush | -5.307 |
okane | -4.382 |
anyl | -4.299 |
RL | -4.247 |
itton | -4.096 |
Token | end |
Token ID | 437 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
IDE | +3.212 |
Falk | +3.145 |
Christensen | +2.966 |
apter | +2.861 |
ides | +2.718 |
Neg logit contributions | |
rush | -7.232 |
RL | -6.422 |
anyl | -6.350 |
okane | -6.334 |
WARN | -6.167 |
Token | T |
Token ID | 51 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
IDE | +4.221 |
Falk | +4.167 |
Christensen | +4.036 |
apter | +3.865 |
Dou | +3.822 |
Neg logit contributions | |
rush | -4.036 |
okane | -3.304 |
anyl | -3.254 |
RL | -3.203 |
itton | -3.085 |
Token | prime |
Token ID | 6994 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
rush | +0.751 |
RL | +0.618 |
okane | +0.617 |
anyl | +0.616 |
itton | +0.585 |
Neg logit contributions | |
Falk | -0.638 |
IDE | -0.637 |
Christensen | -0.620 |
apter | -0.592 |
ides | -0.568 |
Token | challenge |
Token ID | 4427 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
rush | +1.202 |
RL | +0.969 |
okane | +0.967 |
anyl | +0.966 |
itton | +0.909 |
Neg logit contributions | |
Falk | -1.219 |
IDE | -1.216 |
Christensen | -1.188 |
apter | -1.142 |
ides | -1.095 |
Token | Belfast |
Token ID | 29713 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Falk | +0.528 |
IDE | +0.526 |
Christensen | +0.514 |
apter | +0.491 |
ides | +0.471 |
Neg logit contributions | |
rush | -0.591 |
RL | -0.484 |
okane | -0.484 |
anyl | -0.482 |
itton | -0.458 |
Token | Te |
Token ID | 6767 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
rush | +2.199 |
RL | +1.815 |
anyl | +1.813 |
okane | +1.813 |
itton | +1.720 |
Neg logit contributions | |
Falk | -1.493 |
IDE | -1.469 |
Christensen | -1.459 |
apter | -1.379 |
ides | -1.306 |
Token | legraph |
Token ID | 16606 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
rush | +1.751 |
RL | +1.282 |
anyl | +1.267 |
okane | +1.260 |
itton | +1.146 |
Neg logit contributions | |
Falk | -3.144 |
IDE | -3.119 |
Christensen | -3.084 |
apter | -2.950 |
ides | -2.887 |
Token | . |
Token ID | 13 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
rush | +1.403 |
RL | +1.166 |
okane | +1.140 |
anyl | +1.125 |
itton | +1.082 |
Neg logit contributions | |
Falk | -1.292 |
IDE | -1.289 |
Christensen | -1.258 |
apter | -1.218 |
ides | -1.169 |
Token | co |
Token ID | 1073 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
IDE | +4.016 |
Falk | +4.014 |
Christensen | +3.665 |
ides | +3.486 |
Dou | +3.458 |
Neg logit contributions | |
rush | -8.600 |
anyl | -7.700 |
okane | -7.660 |
RL | -7.450 |
rall | -7.377 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Falk | +1.935 |
IDE | +1.909 |
Christensen | +1.855 |
apter | +1.772 |
ides | +1.708 |
Neg logit contributions | |
rush | -2.700 |
anyl | -2.287 |
okane | -2.277 |
RL | -2.275 |
itton | -2.163 |
Token | uk |
Token ID | 2724 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Falk | +3.033 |
IDE | +2.979 |
Christensen | +2.864 |
apter | +2.775 |
ides | +2.742 |
Neg logit contributions | |
rush | -2.489 |
anyl | -2.032 |
okane | -2.015 |
RL | -2.009 |
itton | -1.919 |
Token | Dis |
Token ID | 3167 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
rush | +3.047 |
RL | +2.533 |
anyl | +2.445 |
okane | +2.442 |
WARN | +2.341 |
Neg logit contributions | |
IDE | -2.695 |
Falk | -2.652 |
Christensen | -2.602 |
apter | -2.549 |
ides | -2.427 |
Token | ruption |
Token ID | 6417 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
rush | +0.668 |
okane | +0.543 |
anyl | +0.540 |
RL | +0.538 |
itton | +0.511 |
Neg logit contributions | |
Falk | -0.627 |
IDE | -0.624 |
Christensen | -0.611 |
apter | -0.580 |
ides | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Falk | +0.026 |
IDE | +0.026 |
Christensen | +0.025 |
apter | +0.024 |
ides | +0.023 |
Neg logit contributions | |
rush | -0.031 |
RL | -0.026 |
okane | -0.026 |
anyl | -0.026 |
itton | -0.024 |
Token | How |
Token ID | 1374 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
Falk | +1.055 |
IDE | +1.044 |
Christensen | +1.024 |
apter | +0.973 |
ides | +0.933 |
Neg logit contributions | |
rush | -1.239 |
okane | -1.028 |
RL | -1.017 |
anyl | -1.017 |
itton | -0.976 |
Token | St |
Token ID | 1273 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rush | +0.443 |
okane | +0.348 |
RL | +0.348 |
anyl | +0.347 |
itton | +0.325 |
Neg logit contributions | |
Falk | -0.552 |
IDE | -0.550 |
Christensen | -0.539 |
apter | -0.518 |
ides | -0.501 |
Token | uff |
Token ID | 1648 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
rush | +0.961 |
okane | +0.809 |
RL | +0.807 |
anyl | +0.807 |
itton | +0.772 |
Neg logit contributions | |
Falk | -0.634 |
IDE | -0.630 |
Christensen | -0.613 |
apter | -0.579 |
ides | -0.552 |
Token | Works |
Token ID | 23044 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
IDE | +2.612 |
Christensen | +2.453 |
Falk | +2.444 |
Dou | +2.259 |
ides | +2.246 |
Neg logit contributions | |
rush | -4.954 |
anyl | -4.332 |
okane | -4.322 |
RL | -4.302 |
itton | -4.180 |
Token | . |
Token ID | 13 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
IDE | +1.862 |
Falk | +1.850 |
Christensen | +1.798 |
apter | +1.711 |
ides | +1.645 |
Neg logit contributions | |
rush | -2.523 |
anyl | -2.134 |
okane | -2.133 |
RL | -2.097 |
itton | -2.022 |
Token | com |
Token ID | 785 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
IDE | +2.947 |
Falk | +2.701 |
Christensen | +2.624 |
apter | +2.515 |
ides | +2.412 |
Neg logit contributions | |
rush | -9.366 |
okane | -8.612 |
anyl | -8.529 |
rall | -8.486 |
RL | -8.428 |
Token |
|
Token ID | 198 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
Falk | +0.769 |
IDE | +0.765 |
Christensen | +0.744 |
apter | +0.707 |
ides | +0.677 |
Neg logit contributions | |
rush | -1.023 |
okane | -0.854 |
anyl | -0.851 |
RL | -0.851 |
itton | -0.813 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Falk | +0.336 |
IDE | +0.335 |
Christensen | +0.326 |
apter | +0.310 |
ides | +0.298 |
Neg logit contributions | |
rush | -0.430 |
okane | -0.358 |
anyl | -0.356 |
RL | -0.356 |
itton | -0.340 |
Token | The |
Token ID | 464 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
rush | +1.423 |
anyl | +1.150 |
RL | +1.148 |
okane | +1.143 |
itton | +1.076 |
Neg logit contributions | |
Falk | -1.338 |
IDE | -1.317 |
Christensen | -1.311 |
apter | -1.246 |
ides | -1.194 |
Token | next |
Token ID | 1306 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
rush | +0.022 |
okane | +0.018 |
RL | +0.018 |
anyl | +0.018 |
itton | +0.017 |
Neg logit contributions | |
Falk | -0.020 |
IDE | -0.020 |
Christensen | -0.019 |
apter | -0.018 |
ides | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Falk | +1.348 |
IDE | +1.335 |
Christensen | +1.302 |
apter | +1.225 |
ides | +1.186 |
Neg logit contributions | |
rush | -1.846 |
okane | -1.552 |
anyl | -1.552 |
RL | -1.532 |
itton | -1.484 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Falk | +1.169 |
IDE | +1.168 |
Christensen | +1.131 |
apter | +1.070 |
ides | +1.034 |
Neg logit contributions | |
rush | -1.594 |
okane | -1.345 |
anyl | -1.341 |
RL | -1.323 |
itton | -1.283 |
Token | 55 |
Token ID | 2816 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Falk | +1.041 |
IDE | +1.031 |
Christensen | +1.009 |
apter | +0.957 |
ides | +0.913 |
Neg logit contributions | |
rush | -1.457 |
RL | -1.216 |
okane | -1.216 |
anyl | -1.209 |
itton | -1.154 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Falk | +1.779 |
IDE | +1.774 |
Christensen | +1.729 |
apter | +1.646 |
ides | +1.590 |
Neg logit contributions | |
rush | -1.985 |
okane | -1.626 |
anyl | -1.625 |
RL | -1.620 |
itton | -1.544 |
Token |
|
Token ID | 198 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
Falk | +1.795 |
IDE | +1.786 |
Christensen | +1.738 |
apter | +1.630 |
ides | +1.590 |
Neg logit contributions | |
rush | -2.555 |
okane | -2.162 |
anyl | -2.156 |
RL | -2.119 |
itton | -2.075 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
IDE | +3.844 |
Falk | +3.789 |
Christensen | +3.628 |
ides | +3.384 |
apter | +3.358 |
Neg logit contributions | |
rush | -6.544 |
okane | -5.774 |
anyl | -5.733 |
rall | -5.673 |
itton | -5.593 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
IDE | +3.875 |
Falk | +3.514 |
Christensen | +3.490 |
Dou | +3.214 |
ides | +3.165 |
Neg logit contributions | |
rush | -8.716 |
RL | -7.661 |
okane | -7.607 |
anyl | -7.596 |
itton | -7.565 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
IDE | +2.656 |
Falk | +2.649 |
Christensen | +2.595 |
apter | +2.461 |
ides | +2.403 |
Neg logit contributions | |
rush | -2.849 |
anyl | -2.340 |
okane | -2.337 |
RL | -2.290 |
itton | -2.243 |
Token | this |
Token ID | 428 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Falk | +3.683 |
Christensen | +3.612 |
IDE | +3.572 |
apter | +3.278 |
ides | +3.249 |
Neg logit contributions | |
rush | -6.311 |
anyl | -5.425 |
okane | -5.402 |
RL | -5.225 |
itton | -5.221 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
IDE | +4.346 |
Falk | +4.316 |
Christensen | +4.302 |
ides | +3.924 |
apter | +3.888 |
Neg logit contributions | |
rush | -5.131 |
okane | -4.219 |
anyl | -4.203 |
RL | -4.025 |
itton | -4.021 |
Token | on |
Token ID | 319 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Falk | +2.864 |
IDE | +2.843 |
Christensen | +2.801 |
apter | +2.642 |
ides | +2.587 |
Neg logit contributions | |
rush | -3.061 |
anyl | -2.546 |
okane | -2.533 |
RL | -2.455 |
itton | -2.395 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
Falk | +0.274 |
IDE | +0.273 |
Christensen | +0.267 |
apter | +0.254 |
ides | +0.242 |
Neg logit contributions | |
rush | -0.354 |
RL | -0.294 |
okane | -0.294 |
anyl | -0.293 |
itton | -0.279 |
Token | : |
Token ID | 25 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
rush | +0.448 |
RL | +0.368 |
okane | +0.367 |
anyl | +0.366 |
itton | +0.348 |
Neg logit contributions | |
Falk | -0.385 |
IDE | -0.383 |
Christensen | -0.375 |
apter | -0.357 |
ides | -0.342 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
rush | +0.698 |
RL | +0.579 |
okane | +0.571 |
anyl | +0.569 |
itton | +0.542 |
Neg logit contributions | |
Falk | -0.553 |
IDE | -0.546 |
Christensen | -0.539 |
apter | -0.511 |
ides | -0.485 |
Token | : |
Token ID | 25 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Falk | +0.756 |
IDE | +0.755 |
Christensen | +0.734 |
apter | +0.699 |
ides | +0.672 |
Neg logit contributions | |
rush | -0.925 |
okane | -0.769 |
anyl | -0.766 |
RL | -0.763 |
itton | -0.729 |
Token | 00 |
Token ID | 405 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Falk | +0.936 |
IDE | +0.932 |
Christensen | +0.895 |
apter | +0.828 |
ides | +0.776 |
Neg logit contributions | |
rush | -2.251 |
okane | -1.948 |
anyl | -1.943 |
RL | -1.943 |
itton | -1.873 |
Token | N |
Token ID | 45 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
IDE | +2.809 |
Falk | +2.804 |
Christensen | +2.710 |
apter | +2.551 |
ides | +2.448 |
Neg logit contributions | |
rush | -4.362 |
okane | -3.710 |
anyl | -3.706 |
RL | -3.658 |
itton | -3.544 |
Token | / |
Token ID | 14 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
IDE | +4.882 |
Falk | +4.667 |
Christensen | +4.476 |
apter | +4.295 |
ides | +4.282 |
Neg logit contributions | |
rush | -7.603 |
okane | -6.417 |
anyl | -6.417 |
RL | -6.308 |
itton | -6.104 |
Token | A |
Token ID | 32 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
IDE | +4.084 |
Falk | +3.976 |
Christensen | +3.895 |
apter | +3.669 |
Dou | +3.632 |
Neg logit contributions | |
rush | -4.307 |
okane | -3.614 |
anyl | -3.552 |
RL | -3.467 |
itton | -3.392 |
Token | ( |
Token ID | 357 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Falk | +1.930 |
IDE | +1.926 |
Christensen | +1.865 |
apter | +1.779 |
ides | +1.713 |
Neg logit contributions | |
rush | -2.323 |
okane | -1.930 |
anyl | -1.917 |
RL | -1.912 |
itton | -1.826 |
Token | because |
Token ID | 13893 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Falk | +0.918 |
IDE | +0.915 |
Christensen | +0.890 |
apter | +0.846 |
ides | +0.811 |
Neg logit contributions | |
rush | -1.188 |
okane | -0.988 |
RL | -0.986 |
anyl | -0.985 |
itton | -0.938 |
Token | I |
Token ID | 314 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
rush | +1.055 |
RL | +0.882 |
anyl | +0.867 |
okane | +0.866 |
itton | +0.825 |
Neg logit contributions | |
Falk | -0.838 |
IDE | -0.837 |
Christensen | -0.818 |
apter | -0.781 |
ides | -0.743 |
Token | York |
Token ID | 1971 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Falk | +2.328 |
IDE | +2.312 |
Christensen | +2.255 |
apter | +2.137 |
ides | +2.057 |
Neg logit contributions | |
rush | -3.047 |
okane | -2.549 |
anyl | -2.534 |
RL | -2.530 |
itton | -2.410 |
Token | Times |
Token ID | 3782 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Falk | +2.743 |
IDE | +2.725 |
Christensen | +2.652 |
apter | +2.509 |
ides | +2.419 |
Neg logit contributions | |
rush | -3.471 |
okane | -2.941 |
anyl | -2.893 |
RL | -2.865 |
itton | -2.762 |
Token | 's |
Token ID | 338 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Falk | +3.188 |
IDE | +3.101 |
Christensen | +3.042 |
apter | +2.924 |
Dou | +2.786 |
Neg logit contributions | |
rush | -3.663 |
okane | -3.074 |
anyl | -3.014 |
RL | -2.964 |
itton | -2.869 |
Token | products |
Token ID | 3186 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Falk | +2.670 |
IDE | +2.638 |
Christensen | +2.559 |
apter | +2.433 |
ides | +2.363 |
Neg logit contributions | |
rush | -2.772 |
okane | -2.321 |
anyl | -2.273 |
RL | -2.270 |
itton | -2.168 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Falk | +4.314 |
IDE | +4.254 |
Christensen | +4.139 |
ides | +3.862 |
apter | +3.768 |
Neg logit contributions | |
rush | -5.877 |
anyl | -5.125 |
okane | -5.005 |
RL | -4.813 |
itton | -4.811 |
Token | services |
Token ID | 2594 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Falk | +1.219 |
IDE | +1.216 |
Christensen | +1.187 |
apter | +1.137 |
ides | +1.101 |
Neg logit contributions | |
rush | -1.112 |
okane | -0.898 |
RL | -0.891 |
anyl | -0.890 |
itton | -0.843 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Falk | +4.577 |
IDE | +4.528 |
Christensen | +4.331 |
apter | +4.058 |
ides | +3.994 |
Neg logit contributions | |
rush | -7.647 |
okane | -6.646 |
anyl | -6.643 |
rall | -6.583 |
RL | -6.397 |
Token | Thank |
Token ID | 6952 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Falk | +0.757 |
IDE | +0.739 |
Christensen | +0.725 |
apter | +0.672 |
Dou | +0.652 |
Neg logit contributions | |
rush | -1.065 |
okane | -0.899 |
anyl | -0.890 |
RL | -0.883 |
itton | -0.857 |
Token | you |
Token ID | 345 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Falk | +1.302 |
IDE | +1.293 |
Christensen | +1.268 |
apter | +1.201 |
ides | +1.175 |
Neg logit contributions | |
rush | -1.398 |
okane | -1.155 |
anyl | -1.141 |
RL | -1.134 |
itton | -1.082 |
Token | for |
Token ID | 329 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Falk | +2.445 |
IDE | +2.410 |
Christensen | +2.339 |
apter | +2.206 |
ides | +2.165 |
Neg logit contributions | |
rush | -3.433 |
okane | -2.917 |
anyl | -2.874 |
RL | -2.833 |
itton | -2.754 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Falk | +4.345 |
IDE | +4.315 |
Christensen | +4.234 |
ides | +4.053 |
apter | +4.043 |
Neg logit contributions | |
rush | -2.932 |
okane | -2.322 |
anyl | -2.230 |
RL | -2.178 |
itton | -2.065 |
Token | engage |
Token ID | 8209 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
Falk | +3.743 |
IDE | +3.682 |
Christensen | +3.622 |
apter | +3.490 |
ides | +3.352 |
Neg logit contributions | |
rush | -3.477 |
okane | -2.829 |
anyl | -2.785 |
RL | -2.773 |
itton | -2.630 |
Token | in |
Token ID | 287 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Falk | +0.730 |
IDE | +0.728 |
Christensen | +0.711 |
apter | +0.681 |
ides | +0.657 |
Neg logit contributions | |
rush | -0.713 |
okane | -0.576 |
RL | -0.574 |
anyl | -0.574 |
itton | -0.542 |
Token | an |
Token ID | 281 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Falk | +2.012 |
IDE | +1.987 |
Christensen | +1.953 |
apter | +1.854 |
ides | +1.787 |
Neg logit contributions | |
rush | -2.330 |
okane | -1.919 |
anyl | -1.917 |
RL | -1.903 |
itton | -1.825 |
Token | open |
Token ID | 1280 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Falk | +0.760 |
IDE | +0.754 |
Christensen | +0.728 |
apter | +0.678 |
ides | +0.643 |
Neg logit contributions | |
rush | -1.555 |
okane | -1.337 |
anyl | -1.331 |
RL | -1.327 |
itton | -1.283 |
Token | and |
Token ID | 290 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Falk | +2.275 |
IDE | +2.261 |
Christensen | +2.217 |
apter | +2.086 |
ides | +2.040 |
Neg logit contributions | |
rush | -2.571 |
okane | -2.114 |
anyl | -2.106 |
RL | -2.086 |
itton | -2.007 |
Token | straightforward |
Token ID | 15836 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Falk | +2.648 |
IDE | +2.615 |
Christensen | +2.572 |
apter | +2.396 |
ides | +2.347 |
Neg logit contributions | |
rush | -3.494 |
okane | -2.949 |
anyl | -2.915 |
RL | -2.896 |
itton | -2.784 |
Token | communication |
Token ID | 6946 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Falk | +4.650 |
IDE | +4.577 |
Christensen | +4.464 |
ides | +4.125 |
apter | +4.028 |
Neg logit contributions | |
rush | -7.479 |
okane | -6.444 |
anyl | -6.292 |
RL | -6.151 |
itton | -6.140 |
Token | with |
Token ID | 351 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Falk | +2.659 |
IDE | +2.647 |
Christensen | +2.587 |
apter | +2.439 |
ides | +2.363 |
Neg logit contributions | |
rush | -3.363 |
okane | -2.807 |
anyl | -2.777 |
RL | -2.759 |
itton | -2.666 |
Token | staff |
Token ID | 3085 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Falk | +0.843 |
IDE | +0.838 |
Christensen | +0.824 |
apter | +0.788 |
ides | +0.766 |
Neg logit contributions | |
rush | -0.669 |
okane | -0.527 |
anyl | -0.522 |
RL | -0.521 |
itton | -0.491 |
Token | , |
Token ID | 11 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Falk | +2.015 |
IDE | +2.002 |
Christensen | +1.954 |
apter | +1.855 |
ides | +1.796 |
Neg logit contributions | |
rush | -2.365 |
okane | -1.951 |
anyl | -1.946 |
RL | -1.944 |
itton | -1.851 |
Token | clearly |
Token ID | 4084 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Falk | +3.277 |
IDE | +3.221 |
Christensen | +3.170 |
apter | +2.959 |
ides | +2.901 |
Neg logit contributions | |
rush | -3.669 |
okane | -3.015 |
anyl | -2.995 |
RL | -2.940 |
itton | -2.856 |
Token | all |
Token ID | 477 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Falk | +0.893 |
IDE | +0.887 |
Christensen | +0.866 |
apter | +0.819 |
ides | +0.785 |
Neg logit contributions | |
rush | -1.239 |
okane | -1.035 |
anyl | -1.033 |
RL | -1.030 |
itton | -0.987 |
Token | materials |
Token ID | 5696 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Falk | +2.400 |
IDE | +2.387 |
Christensen | +2.347 |
apter | +2.235 |
ides | +2.155 |
Neg logit contributions | |
rush | -2.583 |
anyl | -2.113 |
okane | -2.099 |
RL | -2.083 |
itton | -1.996 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Falk | +1.959 |
IDE | +1.941 |
Christensen | +1.910 |
apter | +1.819 |
ides | +1.770 |
Neg logit contributions | |
rush | -2.053 |
anyl | -1.667 |
okane | -1.658 |
RL | -1.640 |
itton | -1.577 |
Token | groups |
Token ID | 2628 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
rush | +1.480 |
RL | +1.205 |
okane | +1.187 |
anyl | +1.186 |
itton | +1.117 |
Neg logit contributions | |
IDE | -1.587 |
Falk | -1.579 |
Christensen | -1.544 |
apter | -1.485 |
ides | -1.431 |
Token | @ |
Token ID | 31 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
rush | +0.066 |
okane | +0.054 |
RL | +0.054 |
anyl | +0.054 |
itton | +0.051 |
Neg logit contributions | |
Falk | -0.059 |
IDE | -0.058 |
Christensen | -0.057 |
apter | -0.054 |
ides | -0.052 |
Token | peace |
Token ID | 22988 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Falk | +0.130 |
IDE | +0.129 |
Christensen | +0.127 |
apter | +0.121 |
ides | +0.116 |
Neg logit contributions | |
rush | -0.138 |
okane | -0.113 |
anyl | -0.112 |
RL | -0.112 |
itton | -0.107 |
Token | cor |
Token ID | 10215 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
IDE | +4.007 |
Falk | +3.895 |
apter | +3.746 |
ides | +3.655 |
Christensen | +3.648 |
Neg logit contributions | |
rush | -7.755 |
RL | -6.903 |
okane | -6.728 |
anyl | -6.680 |
rall | -6.650 |
Token | ps |
Token ID | 862 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
rush | +2.136 |
okane | +1.651 |
anyl | +1.636 |
RL | +1.611 |
itton | +1.528 |
Neg logit contributions | |
Falk | -2.774 |
IDE | -2.745 |
Christensen | -2.701 |
apter | -2.545 |
�士 | -2.522 |
Token | connect |
Token ID | 8443 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
Falk | +0.955 |
IDE | +0.948 |
Christensen | +0.923 |
apter | +0.869 |
ides | +0.828 |
Neg logit contributions | |
rush | -1.485 |
okane | -1.252 |
anyl | -1.248 |
RL | -1.248 |
itton | -1.194 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
rush | +0.033 |
okane | +0.027 |
RL | +0.027 |
anyl | +0.027 |
itton | +0.026 |
Neg logit contributions | |
Falk | -0.027 |
IDE | -0.027 |
Christensen | -0.027 |
apter | -0.025 |
ides | -0.024 |
Token | org |
Token ID | 2398 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Falk | +0.481 |
IDE | +0.481 |
Christensen | +0.458 |
apter | +0.420 |
ides | +0.390 |
Neg logit contributions | |
rush | -1.397 |
okane | -1.219 |
anyl | -1.217 |
RL | -1.216 |
itton | -1.176 |
Token | Green |
Token ID | 3469 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Falk | +0.497 |
IDE | +0.494 |
Christensen | +0.483 |
apter | +0.461 |
ides | +0.444 |
Neg logit contributions | |
rush | -0.539 |
okane | -0.441 |
RL | -0.440 |
anyl | -0.439 |
itton | -0.416 |
Token | Park |
Token ID | 3250 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
rush | +0.624 |
okane | +0.510 |
RL | +0.510 |
anyl | +0.509 |
itton | +0.483 |
Neg logit contributions | |
IDE | -0.538 |
Falk | -0.537 |
Christensen | -0.522 |
apter | -0.500 |
ides | -0.479 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
rush | +0.591 |
RL | +0.482 |
okane | +0.478 |
anyl | +0.475 |
itton | +0.454 |
Neg logit contributions | |
IDE | -0.552 |
Falk | -0.551 |
Christensen | -0.537 |
apter | -0.522 |
ides | -0.492 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Falk | +1.426 |
IDE | +1.412 |
Christensen | +1.383 |
apter | +1.302 |
ides | +1.267 |
Neg logit contributions | |
rush | -1.584 |
okane | -1.304 |
anyl | -1.301 |
RL | -1.290 |
itton | -1.230 |
Token | Animals |
Token ID | 25390 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
Falk | +1.168 |
IDE | +1.160 |
Christensen | +1.135 |
apter | +1.080 |
ides | +1.045 |
Neg logit contributions | |
rush | -1.204 |
okane | -0.980 |
anyl | -0.975 |
RL | -0.972 |
itton | -0.923 |
Token | in |
Token ID | 287 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Falk | +0.027 |
IDE | +0.027 |
Christensen | +0.026 |
apter | +0.025 |
ides | +0.024 |
Neg logit contributions | |
rush | -0.027 |
okane | -0.022 |
anyl | -0.022 |
RL | -0.022 |
itton | -0.020 |
Token | War |
Token ID | 1810 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
rush | +4.293 |
RL | +2.995 |
okane | +2.674 |
Ruin | +2.500 |
decay | +2.457 |
Neg logit contributions | |
IDE | -10.564 |
Christensen | -10.186 |
apter | -10.146 |
�士 | -10.135 |
Falk | -9.953 |
Token | memorial |
Token ID | 17357 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
rush | +1.228 |
RL | +0.981 |
anyl | +0.972 |
okane | +0.972 |
itton | +0.916 |
Neg logit contributions | |
IDE | -1.378 |
Falk | -1.378 |
Christensen | -1.348 |
apter | -1.305 |
ides | -1.249 |
Token | in |
Token ID | 287 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
rush | +0.321 |
RL | +0.259 |
okane | +0.259 |
anyl | +0.257 |
itton | +0.244 |
Neg logit contributions | |
Falk | -0.326 |
IDE | -0.325 |
Christensen | -0.318 |
apter | -0.306 |
ides | -0.293 |
Token | Park |
Token ID | 3250 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
rush | +0.668 |
RL | +0.549 |
okane | +0.544 |
anyl | +0.540 |
itton | +0.514 |
Neg logit contributions | |
IDE | -0.596 |
Falk | -0.587 |
Christensen | -0.576 |
apter | -0.558 |
ides | -0.530 |
Token | Lane |
Token ID | 15016 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
rush | +0.142 |
RL | +0.114 |
okane | +0.114 |
anyl | +0.113 |
itton | +0.107 |
Neg logit contributions | |
IDE | -0.135 |
Falk | -0.135 |
Christensen | -0.133 |
apter | -0.128 |
Dou | -0.121 |
Token | knife |
Token ID | 9845 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
rush | +2.959 |
RL | +2.211 |
anyl | +2.134 |
okane | +2.070 |
itton | +1.898 |
Neg logit contributions | |
Falk | -5.507 |
IDE | -5.488 |
Christensen | -5.399 |
apter | -5.255 |
�士 | -5.187 |
Token | . |
Token ID | 13 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
rush | +3.742 |
RL | +3.046 |
anyl | +2.976 |
okane | +2.942 |
itton | +2.795 |
Neg logit contributions | |
IDE | -3.696 |
Falk | -3.680 |
Christensen | -3.607 |
�士 | -3.462 |
apter | -3.414 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
rush | +2.349 |
RL | +1.910 |
okane | +1.902 |
anyl | +1.888 |
itton | +1.794 |
Neg logit contributions | |
Falk | -2.162 |
IDE | -2.150 |
Christensen | -2.075 |
apter | -2.006 |
ides | -1.949 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
rush | +0.903 |
RL | +0.744 |
okane | +0.737 |
anyl | +0.735 |
itton | +0.698 |
Neg logit contributions | |
Falk | -0.771 |
IDE | -0.766 |
Christensen | -0.749 |
apter | -0.715 |
ides | -0.683 |
Token | In |
Token ID | 554 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
rush | +5.246 |
RL | +4.161 |
anyl | +3.984 |
okane | +3.964 |
Ruin | +3.922 |
Neg logit contributions | |
IDE | -5.758 |
Falk | -5.660 |
Christensen | -5.614 |
apter | -5.426 |
ides | -5.305 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rush | +4.343 |
RL | +3.409 |
anyl | +3.330 |
okane | +3.277 |
decay | +3.054 |
Neg logit contributions | |
IDE | -5.780 |
Falk | -5.721 |
Christensen | -5.586 |
�士 | -5.493 |
apter | -5.373 |
Token | large |
Token ID | 1588 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
rush | +5.435 |
RL | +4.315 |
anyl | +4.216 |
okane | +3.924 |
decay | +3.779 |
Neg logit contributions | |
IDE | -8.941 |
Falk | -8.808 |
�士 | -8.719 |
apter | -8.645 |
Christensen | -8.567 |
Token | bowl |
Token ID | 9396 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
rush | +2.655 |
RL | +2.056 |
anyl | +2.007 |
okane | +1.955 |
itton | +1.810 |
Neg logit contributions | |
IDE | -4.031 |
Falk | -4.008 |
Christensen | -3.954 |
apter | -3.859 |
emi | -3.743 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
rush | +2.752 |
RL | +2.228 |
anyl | +2.184 |
okane | +2.165 |
itton | +2.053 |
Neg logit contributions | |
IDE | -2.603 |
Falk | -2.590 |
Christensen | -2.541 |
apter | -2.438 |
�士 | -2.360 |
Token | combine |
Token ID | 12082 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
rush | +2.288 |
anyl | +1.643 |
RL | +1.624 |
okane | +1.579 |
itton | +1.494 |
Neg logit contributions | |
IDE | -3.899 |
Falk | -3.882 |
Christensen | -3.820 |
apter | -3.674 |
�士 | -3.614 |
Token | the |
Token ID | 262 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
rush | +4.890 |
RL | +3.982 |
anyl | +3.941 |
okane | +3.782 |
decay | +3.664 |
Neg logit contributions | |
IDE | -5.777 |
Falk | -5.670 |
Christensen | -5.527 |
�士 | -5.409 |
apter | -5.385 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Falk | +1.163 |
IDE | +1.159 |
Christensen | +1.113 |
apter | +1.036 |
ides | +0.973 |
Neg logit contributions | |
rush | -2.606 |
okane | -2.251 |
anyl | -2.246 |
RL | -2.243 |
itton | -2.158 |
Token | B |
Token ID | 33 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
rush | +0.096 |
RL | +0.079 |
anyl | +0.079 |
okane | +0.078 |
itton | +0.075 |
Neg logit contributions | |
Falk | -0.072 |
IDE | -0.070 |
Christensen | -0.070 |
apter | -0.066 |
ides | -0.063 |
Token | mp |
Token ID | 3149 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
rush | +0.864 |
anyl | +0.724 |
RL | +0.724 |
okane | +0.722 |
itton | +0.693 |
Neg logit contributions | |
Falk | -0.575 |
IDE | -0.568 |
Christensen | -0.559 |
apter | -0.523 |
ides | -0.498 |
Token | ); |
Token ID | 1776 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
rush | +1.095 |
RL | +0.910 |
okane | +0.902 |
anyl | +0.902 |
itton | +0.857 |
Neg logit contributions | |
Falk | -0.882 |
IDE | -0.871 |
Christensen | -0.861 |
apter | -0.812 |
ides | -0.774 |
Token | $ |
Token ID | 720 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Falk | +2.067 |
IDE | +2.058 |
Christensen | +2.006 |
apter | +1.922 |
ides | +1.850 |
Neg logit contributions | |
rush | -2.177 |
okane | -1.780 |
anyl | -1.771 |
RL | -1.761 |
itton | -1.673 |
Token | b |
Token ID | 65 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
rush | +2.835 |
RL | +2.361 |
anyl | +2.335 |
okane | +2.311 |
itton | +2.233 |
Neg logit contributions | |
Falk | -2.042 |
Christensen | -1.998 |
IDE | -1.988 |
apter | -1.856 |
Azerbai | -1.781 |
Token | mp |
Token ID | 3149 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
rush | +5.634 |
anyl | +4.061 |
okane | +4.028 |
itton | +3.820 |
RL | +3.744 |
Neg logit contributions | |
Falk | -8.868 |
�士 | -8.783 |
IDE | -8.723 |
Christensen | -8.644 |
��� | -8.138 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
rush | +2.094 |
okane | +1.720 |
RL | +1.716 |
anyl | +1.703 |
itton | +1.626 |
Neg logit contributions | |
Falk | -1.830 |
IDE | -1.805 |
Christensen | -1.785 |
apter | -1.684 |
Azerbai | -1.610 |
Token | Dis |
Token ID | 7279 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Falk | +0.414 |
IDE | +0.403 |
Christensen | +0.398 |
apter | +0.361 |
ides | +0.332 |
Neg logit contributions | |
rush | -1.122 |
RL | -0.971 |
okane | -0.968 |
anyl | -0.966 |
itton | -0.932 |
Token | pose |
Token ID | 3455 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
rush | +2.020 |
okane | +1.647 |
anyl | +1.639 |
RL | +1.615 |
itton | +1.540 |
Neg logit contributions | |
Falk | -1.803 |
IDE | -1.765 |
Christensen | -1.759 |
apter | -1.615 |
�士 | -1.602 |
Token | (); |
Token ID | 9783 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
rush | +1.141 |
RL | +0.931 |
okane | +0.926 |
anyl | +0.923 |
itton | +0.875 |
Neg logit contributions | |
Falk | -1.081 |
IDE | -1.065 |
Christensen | -1.056 |
apter | -1.004 |
ides | -0.961 |
Token | and |
Token ID | 290 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
rush | +2.044 |
RL | +1.651 |
okane | +1.633 |
anyl | +1.618 |
itton | +1.528 |
Neg logit contributions | |
Falk | -2.162 |
IDE | -2.159 |
Christensen | -2.104 |
apter | -2.022 |
ides | -1.942 |
Token | it |
Token ID | 340 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
rush | +5.590 |
RL | +4.570 |
okane | +4.358 |
anyl | +4.334 |
itton | +4.187 |
Neg logit contributions | |
IDE | -5.617 |
Falk | -5.557 |
Christensen | -5.454 |
�士 | -5.290 |
apter | -5.222 |
Token | 's |
Token ID | 338 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
rush | +4.260 |
RL | +3.373 |
okane | +3.261 |
anyl | +3.229 |
itton | +2.997 |
Neg logit contributions | |
IDE | -5.451 |
Falk | -5.434 |
Christensen | -5.319 |
apter | -5.074 |
�士 | -5.042 |
Token | not |
Token ID | 407 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
rush | +5.037 |
RL | +4.173 |
anyl | +4.005 |
okane | +3.947 |
itton | +3.770 |
Neg logit contributions | |
IDE | -5.779 |
Falk | -5.746 |
Christensen | -5.623 |
�士 | -5.463 |
apter | -5.435 |
Token | what |
Token ID | 644 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
rush | +4.366 |
RL | +3.488 |
okane | +3.433 |
anyl | +3.421 |
decay | +3.225 |
Neg logit contributions | |
Falk | -4.444 |
IDE | -4.433 |
Christensen | -4.244 |
apter | -4.116 |
�士 | -4.029 |
Token | you |
Token ID | 345 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
rush | +4.208 |
RL | +3.270 |
okane | +3.150 |
anyl | +3.135 |
decay | +2.924 |
Neg logit contributions | |
IDE | -5.812 |
Falk | -5.768 |
Christensen | -5.663 |
�士 | -5.568 |
apter | -5.510 |
Token | think |
Token ID | 892 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
rush | +5.175 |
RL | +3.888 |
okane | +3.880 |
anyl | +3.701 |
itton | +3.583 |
Neg logit contributions | |
Falk | -8.333 |
IDE | -8.233 |
Christensen | -7.989 |
�士 | -7.821 |
apter | -7.765 |
Token | it |
Token ID | 340 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
rush | +4.512 |
RL | +3.706 |
okane | +3.531 |
anyl | +3.525 |
decay | +3.427 |
Neg logit contributions | |
IDE | -4.482 |
Falk | -4.428 |
Christensen | -4.310 |
�士 | -4.191 |
apter | -4.154 |
Token | is |
Token ID | 318 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
rush | +3.196 |
RL | +2.642 |
anyl | +2.561 |
okane | +2.558 |
decay | +2.413 |
Neg logit contributions | |
Falk | -3.258 |
IDE | -3.227 |
Christensen | -3.132 |
apter | -3.023 |
�士 | -3.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
rush | +3.554 |
okane | +2.871 |
RL | +2.862 |
anyl | +2.855 |
itton | +2.674 |
Neg logit contributions | |
Falk | -3.760 |
IDE | -3.737 |
Christensen | -3.638 |
apter | -3.473 |
ides | -3.355 |
Token | which |
Token ID | 543 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
rush | +1.361 |
RL | +1.118 |
okane | +1.112 |
anyl | +1.111 |
itton | +1.057 |
Neg logit contributions | |
Falk | -1.211 |
IDE | -1.208 |
Christensen | -1.178 |
apter | -1.123 |
ides | -1.078 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
rush | +3.560 |
anyl | +2.851 |
RL | +2.776 |
okane | +2.761 |
decay | +2.589 |
Neg logit contributions | |
IDE | -4.589 |
Falk | -4.563 |
Christensen | -4.402 |
apter | -4.359 |
emi | -4.184 |
Token | for |
Token ID | 329 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
rush | +2.445 |
anyl | +1.996 |
RL | +1.982 |
okane | +1.917 |
decay | +1.849 |
Neg logit contributions | |
IDE | -2.431 |
Falk | -2.416 |
Christensen | -2.381 |
apter | -2.254 |
�士 | -2.250 |
Token | a |
Token ID | 257 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
rush | +1.960 |
anyl | +1.553 |
RL | +1.549 |
okane | +1.519 |
decay | +1.424 |
Neg logit contributions | |
Falk | -2.287 |
IDE | -2.283 |
Christensen | -2.221 |
apter | -2.138 |
�士 | -2.084 |
Token | few |
Token ID | 1178 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
rush | +2.803 |
anyl | +2.302 |
RL | +2.274 |
okane | +2.242 |
itton | +2.183 |
Neg logit contributions | |
Falk | -2.416 |
IDE | -2.411 |
Christensen | -2.332 |
apter | -2.244 |
�士 | -2.217 |
Token | minutes |
Token ID | 2431 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
rush | +1.291 |
anyl | +1.046 |
RL | +1.036 |
okane | +1.023 |
itton | +0.973 |
Neg logit contributions | |
IDE | -1.384 |
Falk | -1.370 |
Christensen | -1.338 |
apter | -1.301 |
�士 | -1.254 |
Token | until |
Token ID | 1566 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
rush | +1.489 |
anyl | +1.158 |
RL | +1.148 |
okane | +1.135 |
itton | +1.070 |
Neg logit contributions | |
IDE | -1.874 |
Falk | -1.859 |
Christensen | -1.836 |
apter | -1.745 |
ides | -1.702 |
Token | fork |
Token ID | 15563 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
rush | +6.578 |
anyl | +5.464 |
RL | +5.370 |
okane | +5.333 |
decay | +5.276 |
Neg logit contributions | |
IDE | -6.450 |
Falk | -6.399 |
Christensen | -6.199 |
�士 | -6.098 |
apter | -5.937 |
Token | - |
Token ID | 12 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Falk | +2.163 |
IDE | +2.135 |
Christensen | +2.104 |
apter | +2.006 |
ides | +1.927 |
Neg logit contributions | |
rush | -2.440 |
okane | -2.036 |
anyl | -2.013 |
RL | -2.004 |
itton | -1.926 |
Token | t |
Token ID | 83 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
rush | +0.236 |
okane | +0.192 |
anyl | +0.191 |
RL | +0.191 |
itton | +0.181 |
Neg logit contributions | |
Falk | -0.215 |
IDE | -0.214 |
Christensen | -0.209 |
apter | -0.198 |
ides | -0.191 |
Token | ender |
Token ID | 2194 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Falk | +1.658 |
IDE | +1.653 |
Christensen | +1.596 |
apter | +1.533 |
ides | +1.431 |
Neg logit contributions | |
rush | -3.456 |
RL | -2.997 |
okane | -2.988 |
anyl | -2.958 |
WARN | -2.838 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
rush | +1.770 |
RL | +1.450 |
anyl | +1.428 |
okane | +1.427 |
itton | +1.354 |
Neg logit contributions | |
Falk | -1.597 |
IDE | -1.586 |
Christensen | -1.548 |
apter | -1.473 |
�士 | -1.427 |
Token | ul |
Token ID | 377 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
rush | +2.903 |
okane | +2.325 |
anyl | +2.310 |
RL | +2.310 |
itton | +2.194 |
Neg logit contributions | |
Falk | -2.880 |
Christensen | -2.772 |
IDE | -2.756 |
apter | -2.575 |
Azerbai | -2.494 |
Token | > |
Token ID | 29 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Falk | +0.060 |
IDE | +0.060 |
Christensen | +0.058 |
apter | +0.056 |
ides | +0.054 |
Neg logit contributions | |
rush | -0.053 |
okane | -0.043 |
RL | -0.043 |
anyl | -0.042 |
itton | -0.040 |
Token | < |
Token ID | 1279 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
rush | +0.791 |
RL | +0.643 |
okane | +0.640 |
anyl | +0.640 |
itton | +0.607 |
Neg logit contributions | |
Falk | -0.784 |
IDE | -0.776 |
Christensen | -0.759 |
apter | -0.728 |
ides | -0.698 |
Token | li |
Token ID | 4528 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
rush | +1.401 |
okane | +1.162 |
RL | +1.160 |
anyl | +1.157 |
itton | +1.106 |
Neg logit contributions | |
Falk | -1.037 |
IDE | -1.013 |
Christensen | -1.002 |
apter | -0.937 |
ides | -0.890 |
Token | ng |
Token ID | 23370 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
rush | +2.993 |
RL | +2.437 |
okane | +2.415 |
anyl | +2.389 |
itton | +2.282 |
Neg logit contributions | |
Falk | -3.336 |
IDE | -3.284 |
Christensen | -3.202 |
apter | -3.061 |
ides | -2.951 |
Token | - |
Token ID | 12 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
rush | +2.159 |
RL | +1.710 |
okane | +1.698 |
anyl | +1.695 |
itton | +1.596 |
Neg logit contributions | |
Falk | -2.346 |
IDE | -2.320 |
Christensen | -2.280 |
apter | -2.181 |
ides | -2.095 |
Token | repeat |
Token ID | 44754 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
rush | +4.721 |
okane | +3.300 |
anyl | +3.267 |
RL | +3.149 |
itton | +3.121 |
Neg logit contributions | |
Falk | -8.634 |
Christensen | -8.456 |
IDE | -8.287 |
apter | -7.905 |
Azerbai | -7.901 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
rush | +0.531 |
okane | +0.442 |
RL | +0.441 |
anyl | +0.441 |
itton | +0.420 |
Neg logit contributions | |
Falk | -0.403 |
IDE | -0.401 |
Christensen | -0.391 |
apter | -0.371 |
ides | -0.356 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
rush | +0.991 |
anyl | +0.822 |
okane | +0.820 |
RL | +0.815 |
itton | +0.780 |
Neg logit contributions | |
Falk | -0.737 |
IDE | -0.719 |
Christensen | -0.710 |
apter | -0.669 |
ides | -0.632 |
Token | in |
Token ID | 287 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
rush | +1.718 |
RL | +1.377 |
okane | +1.376 |
anyl | +1.370 |
itton | +1.291 |
Neg logit contributions | |
Falk | -1.878 |
IDE | -1.862 |
Christensen | -1.830 |
apter | -1.751 |
ides | -1.682 |
Token | phones |
Token ID | 9512 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
rush | +1.061 |
okane | +0.871 |
RL | +0.870 |
anyl | +0.869 |
itton | +0.824 |
Neg logit contributions | |
Falk | -0.934 |
IDE | -0.929 |
Christensen | -0.906 |
apter | -0.865 |
ides | -0.827 |
Token | OR |
Token ID | 1581 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
rush | +1.367 |
RL | +1.143 |
okane | +1.137 |
anyl | +1.136 |
itton | +1.084 |
Neg logit contributions | |
Falk | -1.017 |
IDE | -0.993 |
Christensen | -0.990 |
apter | -0.928 |
ides | -0.891 |
Token | PH |
Token ID | 11909 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
IDE | +2.495 |
Falk | +2.419 |
Christensen | +2.358 |
apter | +2.267 |
Dou | +2.181 |
Neg logit contributions | |
rush | -3.249 |
okane | -2.743 |
RL | -2.714 |
anyl | -2.696 |
itton | -2.600 |
Token | _ |
Token ID | 62 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Falk | +0.135 |
IDE | +0.135 |
Christensen | +0.132 |
apter | +0.126 |
ides | +0.122 |
Neg logit contributions | |
rush | -0.130 |
okane | -0.105 |
anyl | -0.105 |
RL | -0.104 |
itton | -0.099 |
Token | RECT |
Token ID | 23988 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
rush | +0.962 |
RL | +0.769 |
okane | +0.769 |
anyl | +0.765 |
itton | +0.721 |
Neg logit contributions | |
Falk | -1.059 |
IDE | -1.052 |
Christensen | -1.033 |
apter | -0.990 |
ides | -0.955 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
rush | +2.680 |
RL | +2.227 |
anyl | +2.144 |
okane | +2.144 |
itton | +2.012 |
Neg logit contributions | |
Falk | -2.598 |
IDE | -2.562 |
Christensen | -2.539 |
apter | -2.436 |
�士 | -2.373 |
Token | ( |
Token ID | 357 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
rush | +3.189 |
RL | +2.634 |
anyl | +2.525 |
okane | +2.524 |
itton | +2.383 |
Neg logit contributions | |
IDE | -3.386 |
Falk | -3.385 |
Christensen | -3.303 |
apter | -3.192 |
�士 | -3.127 |
Token | 21 |
Token ID | 2481 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
rush | +5.757 |
anyl | +4.570 |
okane | +4.438 |
RL | +4.419 |
itton | +4.086 |
Neg logit contributions | |
Falk | -7.395 |
Christensen | -7.217 |
IDE | -7.213 |
�士 | -6.852 |
emi | -6.795 |
Token | , |
Token ID | 11 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
rush | +0.640 |
RL | +0.526 |
okane | +0.524 |
anyl | +0.523 |
itton | +0.496 |
Neg logit contributions | |
Falk | -0.553 |
IDE | -0.550 |
Christensen | -0.538 |
apter | -0.512 |
ides | -0.491 |
Token | 21 |
Token ID | 2310 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
rush | +4.472 |
RL | +3.580 |
anyl | +3.308 |
okane | +3.269 |
WARN | +3.102 |
Neg logit contributions | |
IDE | -7.050 |
Falk | -6.989 |
Christensen | -6.828 |
�士 | -6.681 |
apter | -6.626 |
Token | )) |
Token ID | 4008 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
rush | +3.864 |
RL | +3.069 |
okane | +2.995 |
anyl | +2.981 |
itton | +2.803 |
Neg logit contributions | |
Falk | -4.819 |
IDE | -4.779 |
Christensen | -4.713 |
apter | -4.519 |
�士 | -4.438 |
Token | # |
Token ID | 1303 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
rush | +5.308 |
RL | +4.351 |
okane | +4.318 |
anyl | +4.254 |
WARN | +4.081 |
Neg logit contributions | |
Falk | -5.550 |
IDE | -5.465 |
Christensen | -5.401 |
apter | -5.084 |
Dou | -4.953 |
Token | convert |
Token ID | 10385 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
rush | +3.619 |
RL | +2.865 |
okane | +2.806 |
anyl | +2.798 |
decay | +2.669 |
Neg logit contributions | |
Falk | -4.646 |
IDE | -4.640 |
Christensen | -4.518 |
apter | -4.339 |
�士 | -4.236 |
Token | it |
Token ID | 340 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
rush | +5.080 |
RL | +4.173 |
anyl | +3.980 |
okane | +3.954 |
itton | +3.834 |
Neg logit contributions | |
IDE | -5.211 |
Falk | -5.117 |
Christensen | -5.018 |
�士 | -4.939 |
apter | -4.818 |
Token | to |
Token ID | 284 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
rush | +4.704 |
RL | +3.757 |
anyl | +3.540 |
okane | +3.462 |
decay | +3.343 |
Neg logit contributions | |
IDE | -6.662 |
Falk | -6.655 |
Christensen | -6.537 |
�士 | -6.524 |
apter | -6.279 |
Token | gr |
Token ID | 1036 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
rush | +2.629 |
RL | +2.105 |
anyl | +2.038 |
okane | +2.016 |
itton | +1.895 |
Neg logit contributions | |
IDE | -3.731 |
Falk | -3.704 |
Christensen | -3.644 |
apter | -3.533 |
�士 | -3.405 |
Token | ays |
Token ID | 592 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
Falk | +0.385 |
IDE | +0.383 |
Christensen | +0.369 |
apter | +0.344 |
ides | +0.325 |
Neg logit contributions | |
rush | -0.829 |
okane | -0.714 |
RL | -0.713 |
anyl | -0.712 |
itton | -0.685 |
Token | cale |
Token ID | 38765 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
Falk | +0.278 |
IDE | +0.278 |
Christensen | +0.270 |
apter | +0.258 |
ides | +0.248 |
Neg logit contributions | |
rush | -0.343 |
RL | -0.284 |
okane | -0.284 |
anyl | -0.283 |
itton | -0.270 |
Token | image |
Token ID | 2939 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
rush | +5.447 |
RL | +4.543 |
anyl | +4.280 |
okane | +4.167 |
decay | +4.043 |
Neg logit contributions | |
Christensen | -7.478 |
IDE | -7.442 |
Falk | -7.439 |
�士 | -7.190 |
apter | -7.060 |
Token | = |
Token ID | 796 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
rush | +3.811 |
RL | +3.213 |
okane | +3.064 |
anyl | +3.015 |
WARN | +2.905 |
Neg logit contributions | |
Falk | -3.504 |
IDE | -3.461 |
Christensen | -3.379 |
�士 | -3.270 |
apter | -3.222 |
Token | c |
Token ID | 269 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
rush | +2.365 |
RL | +2.030 |
anyl | +1.991 |
okane | +1.991 |
WARN | +1.899 |
Neg logit contributions | |
Falk | -1.548 |
IDE | -1.546 |
Christensen | -1.489 |
apter | -1.411 |
ides | -1.338 |
Token | v |
Token ID | 85 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
rush | +2.241 |
okane | +1.657 |
RL | +1.648 |
anyl | +1.641 |
itton | +1.506 |
Neg logit contributions | |
Falk | -3.736 |
IDE | -3.731 |
Christensen | -3.672 |
apter | -3.502 |
Azerbai | -3.413 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
rush | +2.120 |
RL | +1.701 |
okane | +1.671 |
anyl | +1.665 |
itton | +1.578 |
Neg logit contributions | |
Falk | -2.202 |
IDE | -2.167 |
Christensen | -2.150 |
apter | -2.035 |
�士 | -1.974 |
Token | hold |
Token ID | 1745 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
rush | +3.522 |
RL | +2.525 |
anyl | +2.425 |
okane | +2.339 |
itton | +2.281 |
Neg logit contributions | |
IDE | -7.492 |
Falk | -7.486 |
Christensen | -7.468 |
�士 | -7.277 |
apter | -7.051 |
Token | together |
Token ID | 1978 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
rush | +0.920 |
RL | +0.758 |
okane | +0.757 |
anyl | +0.755 |
itton | +0.719 |
Neg logit contributions | |
Falk | -0.787 |
IDE | -0.784 |
Christensen | -0.763 |
apter | -0.729 |
ides | -0.699 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
rush | +2.356 |
RL | +1.925 |
okane | +1.874 |
anyl | +1.872 |
itton | +1.775 |
Neg logit contributions | |
Falk | -2.231 |
IDE | -2.218 |
Christensen | -2.174 |
apter | -2.072 |
�士 | -2.071 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
rush | +1.317 |
anyl | +1.056 |
RL | +1.054 |
okane | +1.052 |
itton | +0.991 |
Neg logit contributions | |
Falk | -1.369 |
IDE | -1.361 |
Christensen | -1.331 |
apter | -1.276 |
ides | -1.231 |
Token | . |
Token ID | 13 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
rush | +0.997 |
RL | +0.821 |
okane | +0.812 |
anyl | +0.810 |
itton | +0.767 |
Neg logit contributions | |
Falk | -0.861 |
IDE | -0.855 |
Christensen | -0.836 |
apter | -0.799 |
ides | -0.763 |
Token | Make |
Token ID | 6889 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
rush | +4.964 |
RL | +4.050 |
Ruin | +3.888 |
okane | +3.821 |
anyl | +3.806 |
Neg logit contributions | |
IDE | -5.048 |
Falk | -5.028 |
Christensen | -4.960 |
apter | -4.858 |
ides | -4.636 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
rush | +5.313 |
RL | +4.209 |
okane | +4.017 |
anyl | +3.916 |
decay | +3.712 |
Neg logit contributions | |
Falk | -7.677 |
IDE | -7.634 |
Christensen | -7.452 |
�士 | -7.266 |
apter | -7.262 |
Token | p |
Token ID | 279 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
rush | +4.062 |
RL | +3.226 |
anyl | +3.131 |
okane | +3.077 |
decay | +2.993 |
Neg logit contributions | |
IDE | -5.053 |
Falk | -4.970 |
Christensen | -4.808 |
�士 | -4.798 |
apter | -4.659 |
Token | att |
Token ID | 1078 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
rush | +2.422 |
okane | +1.967 |
anyl | +1.945 |
RL | +1.920 |
itton | +1.874 |
Neg logit contributions | |
Falk | -2.334 |
IDE | -2.293 |
Christensen | -2.252 |
�士 | -2.125 |
apter | -2.081 |
Token | ies |
Token ID | 444 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
Falk | +1.749 |
IDE | +1.743 |
Christensen | +1.695 |
apter | +1.606 |
ides | +1.542 |
Neg logit contributions | |
rush | -2.582 |
okane | -2.171 |
RL | -2.168 |
anyl | -2.163 |
itton | -2.067 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
Falk | +0.348 |
IDE | +0.347 |
Christensen | +0.338 |
apter | +0.323 |
ides | +0.309 |
Neg logit contributions | |
rush | -0.421 |
RL | -0.347 |
okane | -0.346 |
anyl | -0.345 |
itton | -0.328 |
Token | # |
Token ID | 1303 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
rush | +2.833 |
RL | +2.337 |
anyl | +2.286 |
okane | +2.286 |
WARN | +2.184 |
Neg logit contributions | |
IDE | -2.747 |
Falk | -2.736 |
Christensen | -2.680 |
apter | -2.533 |
Dou | -2.465 |
Token | load |
Token ID | 3440 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
rush | +2.173 |
RL | +1.747 |
anyl | +1.703 |
okane | +1.674 |
WARN | +1.594 |
Neg logit contributions | |
IDE | -2.751 |
Falk | -2.744 |
Christensen | -2.701 |
apter | -2.581 |
ides | -2.529 |
Token | the |
Token ID | 262 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
rush | +3.119 |
RL | +2.575 |
okane | +2.485 |
anyl | +2.442 |
itton | +2.302 |
Neg logit contributions | |
IDE | -3.372 |
Falk | -3.342 |
Christensen | -3.264 |
�士 | -3.137 |
apter | -3.135 |
Token | image |
Token ID | 2939 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
rush | +3.254 |
RL | +2.682 |
anyl | +2.575 |
okane | +2.549 |
decay | +2.399 |
Neg logit contributions | |
Falk | -3.877 |
IDE | -3.867 |
Christensen | -3.823 |
apter | -3.696 |
�士 | -3.605 |
Token | , |
Token ID | 11 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
rush | +4.136 |
RL | +3.401 |
anyl | +3.288 |
okane | +3.261 |
itton | +3.098 |
Neg logit contributions | |
IDE | -4.184 |
Falk | -4.090 |
Christensen | -4.041 |
�士 | -3.861 |
apter | -3.860 |
Token | resize |
Token ID | 47558 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
rush | +4.321 |
RL | +3.235 |
okane | +3.110 |
anyl | +3.097 |
decay | +2.862 |
Neg logit contributions | |
IDE | -7.243 |
Falk | -7.214 |
Christensen | -7.107 |
apter | -6.858 |
�士 | -6.693 |
Token | it |
Token ID | 340 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
rush | +6.036 |
RL | +4.917 |
okane | +4.519 |
decay | +4.492 |
anyl | +4.472 |
Neg logit contributions | |
IDE | -6.920 |
�士 | -6.884 |
Falk | -6.717 |
Christensen | -6.636 |
��� | -6.562 |
Token | , |
Token ID | 11 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
rush | +4.460 |
RL | +3.699 |
anyl | +3.449 |
okane | +3.425 |
decay | +3.325 |
Neg logit contributions | |
IDE | -4.957 |
Falk | -4.866 |
�士 | -4.783 |
Christensen | -4.772 |
apter | -4.639 |
Token | and |
Token ID | 290 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
rush | +3.289 |
RL | +2.656 |
okane | +2.604 |
anyl | +2.566 |
decay | +2.466 |
Neg logit contributions | |
Falk | -3.674 |
IDE | -3.649 |
Christensen | -3.563 |
apter | -3.419 |
�士 | -3.348 |
Token | convert |
Token ID | 10385 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
rush | +3.619 |
RL | +2.865 |
okane | +2.806 |
anyl | +2.798 |
decay | +2.669 |
Neg logit contributions | |
Falk | -4.646 |
IDE | -4.640 |
Christensen | -4.518 |
apter | -4.339 |
�士 | -4.236 |
Token | it |
Token ID | 340 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
rush | +5.080 |
RL | +4.173 |
anyl | +3.980 |
okane | +3.954 |
itton | +3.834 |
Neg logit contributions | |
IDE | -5.211 |
Falk | -5.117 |
Christensen | -5.018 |
�士 | -4.939 |
apter | -4.818 |
Token | 75 |
Token ID | 2425 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Falk | +0.673 |
IDE | +0.670 |
Christensen | +0.653 |
apter | +0.621 |
ides | +0.594 |
Neg logit contributions | |
rush | -0.883 |
RL | -0.735 |
okane | -0.734 |
anyl | -0.730 |
itton | -0.697 |
Token | million |
Token ID | 1510 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Falk | +0.190 |
IDE | +0.190 |
Christensen | +0.185 |
apter | +0.176 |
ides | +0.170 |
Neg logit contributions | |
rush | -0.219 |
okane | -0.180 |
anyl | -0.179 |
RL | -0.179 |
itton | -0.170 |
Token | ( |
Token ID | 357 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rush | +1.783 |
RL | +1.485 |
okane | +1.462 |
anyl | +1.446 |
itton | +1.392 |
Neg logit contributions | |
Falk | -1.570 |
IDE | -1.566 |
Christensen | -1.530 |
apter | -1.473 |
ides | -1.398 |
Token | 35 |
Token ID | 2327 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Falk | +0.826 |
IDE | +0.821 |
Christensen | +0.802 |
apter | +0.763 |
ides | +0.730 |
Neg logit contributions | |
rush | -1.022 |
okane | -0.844 |
RL | -0.844 |
anyl | -0.842 |
itton | -0.802 |
Token | th |
Token ID | 400 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
rush | +1.612 |
RL | +1.329 |
okane | +1.320 |
anyl | +1.312 |
itton | +1.250 |
Neg logit contributions | |
Falk | -1.451 |
IDE | -1.446 |
Christensen | -1.415 |
apter | -1.351 |
ides | -1.294 |
Token | among |
Token ID | 1871 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
rush | +0.349 |
RL | +0.284 |
okane | +0.283 |
anyl | +0.282 |
itton | +0.268 |
Neg logit contributions | |
Falk | -0.332 |
IDE | -0.331 |
Christensen | -0.324 |
apter | -0.309 |
ides | -0.298 |
Token | guards |
Token ID | 10942 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
rush | +6.257 |
RL | +5.419 |
anyl | +5.009 |
okane | +5.002 |
WARN | +4.817 |
Neg logit contributions | |
IDE | -6.463 |
Christensen | -6.341 |
Falk | -6.233 |
apter | -6.219 |
Dou | -5.823 |
Token | ) |
Token ID | 8 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rush | +1.799 |
RL | +1.483 |
okane | +1.469 |
anyl | +1.448 |
itton | +1.392 |
Neg logit contributions | |
Falk | -1.659 |
IDE | -1.651 |
Christensen | -1.619 |
apter | -1.553 |
Dou | -1.476 |
Token |
|
Token ID | 198 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Falk | +0.684 |
IDE | +0.680 |
Christensen | +0.663 |
apter | +0.629 |
ides | +0.604 |
Neg logit contributions | |
rush | -0.876 |
okane | -0.727 |
anyl | -0.726 |
RL | -0.725 |
itton | -0.690 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Falk | +0.602 |
IDE | +0.600 |
Christensen | +0.583 |
apter | +0.553 |
ides | +0.532 |
Neg logit contributions | |
rush | -0.788 |
okane | -0.659 |
anyl | -0.657 |
RL | -0.653 |
itton | -0.627 |
Token | F |
Token ID | 37 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
Falk | +0.178 |
IDE | +0.176 |
Christensen | +0.173 |
apter | +0.164 |
ides | +0.157 |
Neg logit contributions | |
rush | -0.235 |
RL | -0.194 |
okane | -0.194 |
anyl | -0.194 |
itton | -0.185 |
Token | other |
Token ID | 584 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
rush | +0.914 |
RL | +0.778 |
anyl | +0.774 |
okane | +0.763 |
itton | +0.731 |
Neg logit contributions | |
Falk | -0.590 |
IDE | -0.587 |
Christensen | -0.566 |
apter | -0.541 |
ides | -0.511 |
Token | ingredients |
Token ID | 9391 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
rush | +0.721 |
RL | +0.572 |
anyl | +0.568 |
okane | +0.554 |
itton | +0.515 |
Neg logit contributions | |
Falk | -0.970 |
IDE | -0.970 |
Christensen | -0.942 |
apter | -0.920 |
ides | -0.883 |
Token | and |
Token ID | 290 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
rush | +0.774 |
RL | +0.626 |
anyl | +0.611 |
okane | +0.610 |
itton | +0.573 |
Neg logit contributions | |
Falk | -0.831 |
IDE | -0.825 |
Christensen | -0.808 |
apter | -0.778 |
�士 | -0.758 |
Token | mix |
Token ID | 5022 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
rush | +1.908 |
RL | +1.483 |
anyl | +1.471 |
okane | +1.443 |
itton | +1.401 |
Neg logit contributions | |
Falk | -2.363 |
IDE | -2.348 |
Christensen | -2.311 |
apter | -2.229 |
�士 | -2.163 |
Token | well |
Token ID | 880 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Falk | +0.174 |
IDE | +0.172 |
Christensen | +0.164 |
apter | +0.155 |
�士 | +0.146 |
Neg logit contributions | |
rush | -0.427 |
RL | -0.371 |
anyl | -0.369 |
okane | -0.365 |
itton | -0.355 |
Token | until |
Token ID | 1566 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
rush | +1.972 |
anyl | +1.532 |
RL | +1.529 |
okane | +1.492 |
itton | +1.408 |
Neg logit contributions | |
IDE | -2.567 |
Falk | -2.558 |
Christensen | -2.518 |
apter | -2.425 |
�士 | -2.369 |
Token | the |
Token ID | 262 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
rush | +5.452 |
RL | +4.420 |
anyl | +4.285 |
okane | +4.204 |
decay | +4.150 |
Neg logit contributions | |
�士 | -7.137 |
IDE | -7.103 |
Falk | -7.098 |
Christensen | -6.967 |
��� | -6.750 |
Token | mixture |
Token ID | 11710 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
rush | +3.818 |
anyl | +3.080 |
RL | +3.046 |
decay | +2.899 |
okane | +2.885 |
Neg logit contributions | |
Falk | -4.381 |
IDE | -4.330 |
Christensen | -4.290 |
�士 | -4.182 |
apter | -4.138 |
Token | feels |
Token ID | 5300 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
rush | +4.587 |
RL | +3.757 |
anyl | +3.744 |
okane | +3.605 |
decay | +3.515 |
Neg logit contributions | |
IDE | -4.628 |
Falk | -4.565 |
Christensen | -4.542 |
�士 | -4.478 |
apter | -4.340 |
Token | like |
Token ID | 588 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
rush | +3.777 |
RL | +3.087 |
anyl | +3.038 |
okane | +2.983 |
itton | +2.900 |
Neg logit contributions | |
IDE | -3.816 |
Falk | -3.798 |
Christensen | -3.739 |
�士 | -3.604 |
apter | -3.571 |
Token | it |
Token ID | 340 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
rush | +4.846 |
RL | +3.954 |
anyl | +3.818 |
okane | +3.716 |
itton | +3.687 |
Neg logit contributions | |
IDE | -5.050 |
Falk | -4.957 |
Christensen | -4.883 |
�士 | -4.825 |
apter | -4.682 |
Token | the |
Token ID | 262 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
rush | +3.113 |
RL | +2.547 |
okane | +2.458 |
anyl | +2.445 |
itton | +2.307 |
Neg logit contributions | |
IDE | -3.284 |
Falk | -3.273 |
Christensen | -3.190 |
apter | -3.069 |
�士 | -3.025 |
Token | pan |
Token ID | 3425 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
rush | +5.306 |
RL | +4.374 |
anyl | +4.223 |
okane | +4.091 |
decay | +4.017 |
Neg logit contributions | |
IDE | -5.649 |
Falk | -5.554 |
Christensen | -5.345 |
�士 | -5.328 |
apter | -5.271 |
Token | ; |
Token ID | 26 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
rush | +4.116 |
RL | +3.306 |
anyl | +3.105 |
okane | +3.055 |
WARN | +3.006 |
Neg logit contributions | |
Falk | -4.840 |
�士 | -4.803 |
IDE | -4.795 |
��� | -4.721 |
Christensen | -4.691 |
Token | only |
Token ID | 691 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
rush | +6.135 |
RL | +5.176 |
anyl | +5.097 |
okane | +4.928 |
decay | +4.925 |
Neg logit contributions | |
Falk | -4.938 |
IDE | -4.866 |
Christensen | -4.727 |
�士 | -4.656 |
apter | -4.440 |
Token | cook |
Token ID | 4255 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
rush | +4.496 |
RL | +3.738 |
anyl | +3.703 |
okane | +3.631 |
WARN | +3.517 |
Neg logit contributions | |
Falk | -3.632 |
IDE | -3.628 |
Christensen | -3.433 |
apter | -3.285 |
�士 | -3.241 |
Token | about |
Token ID | 546 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
rush | +3.180 |
anyl | +2.635 |
RL | +2.630 |
okane | +2.604 |
decay | +2.444 |
Neg logit contributions | |
Falk | -2.541 |
IDE | -2.540 |
Christensen | -2.435 |
apter | -2.330 |
�士 | -2.263 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
rush | +5.145 |
RL | +4.140 |
okane | +3.784 |
anyl | +3.745 |
MV | +3.645 |
Neg logit contributions | |
Falk | -7.402 |
IDE | -7.324 |
�士 | -7.234 |
Christensen | -7.072 |
apter | -7.016 |
Token | f |
Token ID | 277 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
rush | +2.987 |
RL | +2.564 |
anyl | +2.525 |
okane | +2.476 |
itton | +2.429 |
Neg logit contributions | |
IDE | -1.922 |
Falk | -1.891 |
Christensen | -1.841 |
apter | -1.751 |
�士 | -1.735 |
Token | rit |
Token ID | 799 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
rush | +2.200 |
anyl | +1.562 |
RL | +1.533 |
okane | +1.508 |
itton | +1.433 |
Neg logit contributions | |
Falk | -4.194 |
IDE | -4.164 |
Christensen | -4.112 |
�士 | -3.892 |
apter | -3.887 |
Token | ters |
Token ID | 1010 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
rush | +2.098 |
anyl | +1.657 |
RL | +1.657 |
okane | +1.649 |
itton | +1.565 |
Neg logit contributions | |
Falk | -2.262 |
IDE | -2.247 |
Christensen | -2.192 |
apter | -2.087 |
�士 | -2.022 |
Token | at |
Token ID | 379 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
rush | +2.375 |
RL | +1.839 |
anyl | +1.800 |
okane | +1.790 |
itton | +1.669 |
Neg logit contributions | |
Falk | -3.179 |
IDE | -3.162 |
Christensen | -3.087 |
�士 | -2.959 |
apter | -2.955 |
Token | fork |
Token ID | 15563 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
rush | +6.578 |
anyl | +5.464 |
RL | +5.370 |
okane | +5.333 |
decay | +5.276 |
Neg logit contributions | |
IDE | -6.450 |
Falk | -6.399 |
Christensen | -6.199 |
�士 | -6.098 |
apter | -5.937 |
Token | - |
Token ID | 12 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Falk | +2.163 |
IDE | +2.135 |
Christensen | +2.104 |
apter | +2.006 |
ides | +1.927 |
Neg logit contributions | |
rush | -2.440 |
okane | -2.036 |
anyl | -2.013 |
RL | -2.004 |
itton | -1.926 |
Token | t |
Token ID | 83 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
rush | +0.236 |
okane | +0.192 |
anyl | +0.191 |
RL | +0.191 |
itton | +0.181 |
Neg logit contributions | |
Falk | -0.215 |
IDE | -0.214 |
Christensen | -0.209 |
apter | -0.198 |
ides | -0.191 |
Token | ender |
Token ID | 2194 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Falk | +1.658 |
IDE | +1.653 |
Christensen | +1.596 |
apter | +1.533 |
ides | +1.431 |
Neg logit contributions | |
rush | -3.456 |
RL | -2.997 |
okane | -2.988 |
anyl | -2.958 |
WARN | -2.838 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
rush | +1.770 |
RL | +1.450 |
anyl | +1.428 |
okane | +1.427 |
itton | +1.354 |
Neg logit contributions | |
Falk | -1.597 |
IDE | -1.586 |
Christensen | -1.548 |
apter | -1.473 |
�士 | -1.427 |
Token | Chop |
Token ID | 40159 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
rush | +3.295 |
RL | +2.490 |
anyl | +2.452 |
okane | +2.443 |
itton | +2.310 |
Neg logit contributions | |
IDE | -4.210 |
Falk | -4.140 |
Christensen | -4.015 |
apter | -3.882 |
ides | -3.849 |
Token | fl |
Token ID | 781 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
rush | +4.078 |
RL | +3.114 |
anyl | +3.065 |
okane | +2.849 |
decay | +2.824 |
Neg logit contributions | |
IDE | -8.519 |
Falk | -8.274 |
Christensen | -8.236 |
apter | -8.122 |
�士 | -8.044 |
Token | ore |
Token ID | 382 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
IDE | +0.151 |
Falk | +0.151 |
Christensen | +0.146 |
apter | +0.141 |
ides | +0.135 |
Neg logit contributions | |
rush | -0.197 |
okane | -0.165 |
RL | -0.164 |
anyl | -0.163 |
itton | -0.155 |
Token | ts |
Token ID | 912 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Falk | +0.688 |
IDE | +0.686 |
Christensen | +0.672 |
apter | +0.646 |
ides | +0.626 |
Neg logit contributions | |
rush | -0.598 |
okane | -0.476 |
RL | -0.476 |
anyl | -0.474 |
itton | -0.446 |
Token | into |
Token ID | 656 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Falk | +0.408 |
IDE | +0.406 |
Christensen | +0.398 |
apter | +0.381 |
ides | +0.367 |
Neg logit contributions | |
rush | -0.355 |
anyl | -0.282 |
RL | -0.281 |
okane | -0.281 |
itton | -0.263 |
Token | small |
Token ID | 1402 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
rush | +1.864 |
anyl | +1.493 |
RL | +1.481 |
okane | +1.435 |
itton | +1.331 |
Neg logit contributions | |
Falk | -2.576 |
IDE | -2.575 |
Christensen | -2.514 |
apter | -2.433 |
�士 | -2.376 |
Token | v |
Token ID | 85 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
rush | +3.536 |
okane | +2.443 |
anyl | +2.424 |
RL | +2.400 |
itton | +2.174 |
Neg logit contributions | |
Falk | -6.667 |
IDE | -6.632 |
Christensen | -6.600 |
�士 | -6.422 |
Azerbai | -6.199 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
rush | +4.009 |
RL | +3.103 |
anyl | +2.992 |
okane | +2.975 |
itton | +2.820 |
Neg logit contributions | |
Falk | -4.754 |
Christensen | -4.658 |
IDE | -4.589 |
�士 | -4.518 |
��� | -4.441 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
rush | +4.522 |
RL | +3.665 |
okane | +3.480 |
anyl | +3.478 |
WARN | +3.323 |
Neg logit contributions | |
Falk | -4.796 |
Christensen | -4.702 |
IDE | -4.696 |
�士 | -4.672 |
��� | -4.631 |
Token | im |
Token ID | 320 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
rush | +6.465 |
RL | +5.452 |
okane | +5.425 |
anyl | +5.386 |
itton | +5.235 |
Neg logit contributions | |
Falk | -2.780 |
Christensen | -2.725 |
IDE | -2.607 |
apter | -2.336 |
�士 | -2.253 |
Token | read |
Token ID | 961 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
rush | +4.664 |
anyl | +3.622 |
okane | +3.516 |
RL | +3.439 |
itton | +3.363 |
Neg logit contributions | |
Christensen | -5.705 |
Falk | -5.699 |
IDE | -5.578 |
�士 | -5.416 |
Hedge | -5.147 |
Token | ( |
Token ID | 7 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
rush | +3.592 |
RL | +2.829 |
anyl | +2.691 |
okane | +2.675 |
WARN | +2.510 |
Neg logit contributions | |
Falk | -4.764 |
Christensen | -4.728 |
IDE | -4.673 |
�士 | -4.569 |
apter | -4.466 |
Token | image |
Token ID | 9060 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
rush | +7.277 |
anyl | +5.924 |
RL | +5.734 |
okane | +5.729 |
rake | +5.297 |
Neg logit contributions | |
Christensen | -5.917 |
Falk | -5.816 |
�士 | -5.630 |
��� | -5.432 |
IDE | -5.357 |
Token | Path |
Token ID | 15235 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
rush | +2.263 |
RL | +1.898 |
anyl | +1.864 |
okane | +1.862 |
itton | +1.767 |
Neg logit contributions | |
Falk | -1.601 |
IDE | -1.550 |
Christensen | -1.545 |
apter | -1.465 |
�士 | -1.444 |
Token | ) |
Token ID | 8 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
rush | +3.222 |
RL | +2.631 |
okane | +2.577 |
anyl | +2.557 |
WARN | +2.419 |
Neg logit contributions | |
Falk | -3.209 |
IDE | -3.184 |
Christensen | -3.146 |
�士 | -2.992 |
apter | -2.990 |
Token | image |
Token ID | 2939 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
rush | +3.340 |
RL | +2.722 |
anyl | +2.664 |
okane | +2.626 |
WARN | +2.487 |
Neg logit contributions | |
IDE | -3.733 |
Falk | -3.726 |
Christensen | -3.697 |
apter | -3.517 |
�士 | -3.394 |
Token | = |
Token ID | 796 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
rush | +1.530 |
RL | +1.268 |
okane | +1.256 |
anyl | +1.248 |
itton | +1.189 |
Neg logit contributions | |
Falk | -1.246 |
IDE | -1.230 |
Christensen | -1.209 |
apter | -1.150 |
ides | -1.099 |
Token | M |
Token ID | 337 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
rush | +3.330 |
RL | +2.900 |
okane | +2.643 |
anyl | +2.624 |
MV | +2.559 |
Neg logit contributions | |
IDE | -3.354 |
Falk | -3.238 |
apter | -3.200 |
Christensen | -3.165 |
�士 | -3.031 |
Token | ., |
Token ID | 1539 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
rush | +0.849 |
okane | +0.703 |
RL | +0.702 |
anyl | +0.701 |
itton | +0.668 |
Neg logit contributions | |
Falk | -0.699 |
IDE | -0.695 |
Christensen | -0.678 |
apter | -0.645 |
ides | -0.617 |
Token | Sch |
Token ID | 3059 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
rush | +2.035 |
RL | +1.720 |
okane | +1.688 |
anyl | +1.667 |
itton | +1.596 |
Neg logit contributions | |
IDE | -1.622 |
Falk | -1.572 |
Christensen | -1.522 |
apter | -1.505 |
ides | -1.422 |
Token | ol |
Token ID | 349 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
rush | +1.069 |
okane | +0.878 |
anyl | +0.876 |
RL | +0.875 |
itton | +0.832 |
Neg logit contributions | |
Falk | -0.926 |
IDE | -0.923 |
Christensen | -0.900 |
apter | -0.856 |
ides | -0.823 |
Token | te |
Token ID | 660 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Falk | +0.037 |
IDE | +0.037 |
Christensen | +0.036 |
apter | +0.034 |
ides | +0.033 |
Neg logit contributions | |
rush | -0.036 |
okane | -0.029 |
anyl | -0.029 |
RL | -0.029 |
itton | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
rush | +2.527 |
RL | +2.090 |
okane | +2.051 |
anyl | +2.046 |
itton | +1.938 |
Neg logit contributions | |
IDE | -2.332 |
Falk | -2.316 |
Christensen | -2.247 |
apter | -2.168 |
�士 | -2.075 |
Token | R |
Token ID | 371 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rush | +4.638 |
RL | +3.886 |
anyl | +3.288 |
okane | +3.284 |
WARN | +3.104 |
Neg logit contributions | |
IDE | -7.801 |
Falk | -7.592 |
apter | -7.422 |
Christensen | -7.353 |
Dou | -7.113 |
Token | ., |
Token ID | 1539 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
rush | +0.872 |
RL | +0.721 |
okane | +0.720 |
anyl | +0.720 |
itton | +0.685 |
Neg logit contributions | |
Falk | -0.730 |
IDE | -0.725 |
Christensen | -0.708 |
apter | -0.674 |
ides | -0.644 |
Token | Sal |
Token ID | 4849 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
rush | +3.887 |
RL | +3.326 |
okane | +3.231 |
anyl | +3.171 |
Kap | +3.060 |
Neg logit contributions | |
IDE | -3.084 |
Falk | -2.924 |
apter | -2.856 |
Christensen | -2.827 |
Dou | -2.686 |
Token | m |
Token ID | 76 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
rush | +0.684 |
okane | +0.560 |
anyl | +0.558 |
RL | +0.557 |
itton | +0.529 |
Neg logit contributions | |
Falk | -0.609 |
IDE | -0.607 |
Christensen | -0.592 |
apter | -0.564 |
ides | -0.541 |
Token | iv |
Token ID | 452 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
rush | +2.849 |
okane | +2.244 |
RL | +2.241 |
anyl | +2.232 |
itton | +2.115 |
Neg logit contributions | |
IDE | -3.708 |
Falk | -3.690 |
Christensen | -3.612 |
apter | -3.449 |
Dou | -3.374 |
Token | GR |
Token ID | 10761 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
rush | +3.029 |
RL | +2.338 |
anyl | +2.279 |
okane | +2.258 |
itton | +2.141 |
Neg logit contributions | |
Falk | -4.460 |
Christensen | -4.375 |
IDE | -4.318 |
apter | -4.178 |
ides | -4.044 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
rush | +2.162 |
RL | +1.763 |
anyl | +1.710 |
okane | +1.708 |
itton | +1.621 |
Neg logit contributions | |
Falk | -2.228 |
Christensen | -2.168 |
IDE | -2.164 |
apter | -2.074 |
ides | -1.986 |
Token | G |
Token ID | 38 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
rush | +1.637 |
RL | +1.372 |
okane | +1.351 |
anyl | +1.344 |
itton | +1.280 |
Neg logit contributions | |
Falk | -1.285 |
IDE | -1.258 |
Christensen | -1.251 |
apter | -1.193 |
ides | -1.136 |
Token | RAY |
Token ID | 30631 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
rush | +1.614 |
RL | +1.314 |
okane | +1.308 |
anyl | +1.306 |
itton | +1.236 |
Neg logit contributions | |
Falk | -1.544 |
IDE | -1.526 |
Christensen | -1.504 |
apter | -1.434 |
ides | -1.380 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
rush | +2.389 |
RL | +2.057 |
okane | +2.020 |
anyl | +2.008 |
WARN | +1.934 |
Neg logit contributions | |
Falk | -1.288 |
IDE | -1.270 |
Christensen | -1.234 |
apter | -1.160 |
�士 | -1.100 |
Token | # |
Token ID | 1303 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
rush | +3.645 |
RL | +3.003 |
okane | +2.929 |
anyl | +2.919 |
itton | +2.790 |
Neg logit contributions | |
Falk | -3.508 |
IDE | -3.493 |
Christensen | -3.441 |
apter | -3.249 |
Dou | -3.138 |
Token | smooth |
Token ID | 7209 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
rush | +5.370 |
RL | +4.151 |
anyl | +4.085 |
okane | +3.932 |
decay | +3.829 |
Neg logit contributions | |
Falk | -7.217 |
IDE | -7.152 |
Christensen | -6.957 |
apter | -6.708 |
Dou | -6.554 |
Token | the |
Token ID | 262 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
rush | +3.708 |
RL | +3.056 |
okane | +2.935 |
anyl | +2.862 |
decay | +2.758 |
Neg logit contributions | |
IDE | -4.070 |
Falk | -4.047 |
Christensen | -3.955 |
apter | -3.821 |
�士 | -3.816 |
Token | image |
Token ID | 2939 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
rush | +4.244 |
RL | +3.502 |
anyl | +3.340 |
okane | +3.285 |
decay | +3.166 |
Neg logit contributions | |
Falk | -5.236 |
IDE | -5.198 |
Christensen | -5.168 |
apter | -4.993 |
�士 | -4.924 |
Token | using |
Token ID | 1262 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
rush | +4.553 |
RL | +3.674 |
anyl | +3.620 |
okane | +3.494 |
decay | +3.405 |
Neg logit contributions | |
IDE | -5.344 |
Falk | -5.334 |
Christensen | -5.188 |
apter | -4.995 |
�士 | -4.986 |
Token | a |
Token ID | 257 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
rush | +2.793 |
RL | +2.238 |
anyl | +2.175 |
okane | +2.145 |
decay | +2.031 |
Neg logit contributions | |
IDE | -3.344 |
Falk | -3.338 |
Christensen | -3.258 |
apter | -3.141 |
�士 | -3.086 |
Token | c |
Token ID | 269 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
rush | +2.213 |
RL | +1.901 |
anyl | +1.863 |
okane | +1.860 |
decay | +1.776 |
Neg logit contributions | |
Falk | -1.450 |
IDE | -1.443 |
Christensen | -1.384 |
apter | -1.323 |
Dou | -1.248 |
Token | v |
Token ID | 85 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
rush | +2.161 |
okane | +1.573 |
RL | +1.571 |
anyl | +1.564 |
itton | +1.431 |
Neg logit contributions | |
Falk | -3.658 |
IDE | -3.643 |
Christensen | -3.595 |
apter | -3.431 |
�士 | -3.354 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
rush | +1.445 |
RL | +1.164 |
okane | +1.147 |
anyl | +1.144 |
itton | +1.084 |
Neg logit contributions | |
Falk | -1.463 |
IDE | -1.440 |
Christensen | -1.426 |
apter | -1.357 |
ides | -1.298 |
Token | . |
Token ID | 764 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
rush | +3.020 |
RL | +2.632 |
okane | +2.568 |
anyl | +2.555 |
WARN | +2.469 |
Neg logit contributions | |
Falk | -1.423 |
IDE | -1.409 |
Christensen | -1.366 |
apter | -1.267 |
�士 | -1.234 |
Token | Ga |
Token ID | 12822 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
rush | +3.616 |
RL | +2.977 |
anyl | +2.871 |
okane | +2.868 |
decay | +2.741 |
Neg logit contributions | |
IDE | -4.023 |
Falk | -3.991 |
Christensen | -3.885 |
apter | -3.768 |
ides | -3.598 |
Token | ussian |
Token ID | 31562 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
rush | +2.535 |
anyl | +1.945 |
okane | +1.945 |
RL | +1.933 |
itton | +1.799 |
Neg logit contributions | |
Falk | -3.568 |
IDE | -3.531 |
Christensen | -3.475 |
apter | -3.305 |
�士 | -3.216 |
Token | Bl |
Token ID | 3629 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
rush | +4.529 |
RL | +3.356 |
okane | +3.021 |
anyl | +2.973 |
WARN | +2.831 |
Neg logit contributions | |
Falk | -7.763 |
IDE | -7.761 |
Christensen | -7.634 |
apter | -7.438 |
�士 | -7.393 |
Token | ur |
Token ID | 333 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
rush | +3.843 |
okane | +3.044 |
anyl | +3.024 |
RL | +3.000 |
itton | +2.860 |
Neg logit contributions | |
Falk | -4.263 |
IDE | -4.248 |
Christensen | -4.186 |
apter | -3.919 |
�士 | -3.884 |
Token | ( |
Token ID | 357 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
rush | +0.969 |
RL | +0.791 |
anyl | +0.777 |
okane | +0.776 |
itton | +0.734 |
Neg logit contributions | |
Falk | -0.953 |
IDE | -0.946 |
Christensen | -0.928 |
apter | -0.886 |
ides | -0.853 |
Token | gray |
Token ID | 12768 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
rush | +3.272 |
RL | +2.438 |
anyl | +2.312 |
okane | +2.233 |
decay | +2.190 |
Neg logit contributions | |
IDE | -6.741 |
Christensen | -6.666 |
Falk | -6.631 |
apter | -6.452 |
�士 | -6.320 |
Token | , |
Token ID | 837 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
rush | +1.443 |
RL | +1.260 |
okane | +1.249 |
anyl | +1.248 |
itton | +1.206 |
Neg logit contributions | |
Falk | -0.500 |
IDE | -0.499 |
Christensen | -0.475 |
apter | -0.434 |
ides | -0.398 |
Token | convert |
Token ID | 10385 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
rush | +3.502 |
RL | +2.760 |
okane | +2.707 |
anyl | +2.700 |
decay | +2.591 |
Neg logit contributions | |
Falk | -4.594 |
IDE | -4.585 |
Christensen | -4.452 |
apter | -4.270 |
�士 | -4.202 |
Token | it |
Token ID | 340 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
rush | +4.571 |
RL | +3.748 |
anyl | +3.565 |
okane | +3.552 |
decay | +3.435 |
Neg logit contributions | |
IDE | -4.640 |
Falk | -4.578 |
Christensen | -4.462 |
�士 | -4.433 |
apter | -4.302 |
Token | to |
Token ID | 284 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
rush | +3.817 |
RL | +3.043 |
anyl | +2.887 |
okane | +2.848 |
decay | +2.702 |
Neg logit contributions | |
Falk | -5.137 |
IDE | -5.105 |
Christensen | -5.026 |
�士 | -4.943 |
apter | -4.847 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
rush | +2.748 |
RL | +2.185 |
anyl | +2.123 |
okane | +2.086 |
decay | +1.972 |
Neg logit contributions | |
IDE | -3.986 |
Falk | -3.952 |
Christensen | -3.881 |
apter | -3.777 |
�士 | -3.672 |
Token | ays |
Token ID | 592 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
Falk | +0.708 |
IDE | +0.707 |
Christensen | +0.679 |
apter | +0.635 |
ides | +0.606 |
Neg logit contributions | |
rush | -1.586 |
RL | -1.368 |
okane | -1.367 |
anyl | -1.361 |
itton | -1.315 |
Token | cale |
Token ID | 38765 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
Falk | +0.227 |
IDE | +0.227 |
Christensen | +0.220 |
apter | +0.210 |
ides | +0.202 |
Neg logit contributions | |
rush | -0.279 |
okane | -0.231 |
RL | -0.231 |
anyl | -0.230 |
itton | -0.219 |
Token | image |
Token ID | 2939 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
rush | +5.265 |
RL | +4.331 |
anyl | +4.113 |
okane | +3.975 |
decay | +3.896 |
Neg logit contributions | |
Falk | -6.976 |
IDE | -6.938 |
Christensen | -6.924 |
�士 | -6.784 |
apter | -6.608 |
Token | = |
Token ID | 796 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
rush | +4.464 |
RL | +3.643 |
okane | +3.543 |
anyl | +3.505 |
itton | +3.335 |
Neg logit contributions | |
Falk | -4.192 |
Christensen | -4.076 |
IDE | -4.069 |
�士 | -3.989 |
apter | -3.830 |
Token | c |
Token ID | 269 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
rush | +2.885 |
RL | +2.471 |
anyl | +2.426 |
okane | +2.421 |
decay | +2.312 |
Neg logit contributions | |
Falk | -1.908 |
IDE | -1.907 |
Christensen | -1.834 |
apter | -1.747 |
�士 | -1.657 |
Token | v |
Token ID | 85 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
rush | +3.536 |
okane | +2.443 |
anyl | +2.424 |
RL | +2.400 |
itton | +2.174 |
Neg logit contributions | |
Falk | -6.667 |
IDE | -6.632 |
Christensen | -6.600 |
�士 | -6.422 |
Azerbai | -6.199 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
rush | +4.009 |
RL | +3.103 |
anyl | +2.992 |
okane | +2.975 |
itton | +2.820 |
Neg logit contributions | |
Falk | -4.754 |
Christensen | -4.658 |
IDE | -4.589 |
�士 | -4.518 |
��� | -4.441 |
Token | younger |
Token ID | 7099 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
rush | +1.231 |
RL | +1.007 |
anyl | +0.994 |
okane | +0.988 |
itton | +0.940 |
Neg logit contributions | |
IDE | -1.169 |
Falk | -1.163 |
Christensen | -1.134 |
apter | -1.089 |
Dou | -1.045 |
Token | you |
Token ID | 345 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
Falk | +1.963 |
IDE | +1.942 |
Christensen | +1.901 |
apter | +1.798 |
ides | +1.762 |
Neg logit contributions | |
rush | -2.290 |
okane | -1.907 |
anyl | -1.902 |
RL | -1.872 |
itton | -1.791 |
Token | are |
Token ID | 389 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
Falk | +0.520 |
IDE | +0.519 |
Christensen | +0.507 |
apter | +0.485 |
ides | +0.468 |
Neg logit contributions | |
rush | -0.508 |
okane | -0.410 |
RL | -0.409 |
anyl | -0.409 |
itton | -0.386 |
Token | ," |
Token ID | 553 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
rush | +0.113 |
okane | +0.093 |
RL | +0.093 |
anyl | +0.092 |
itton | +0.088 |
Neg logit contributions | |
Falk | -0.097 |
IDE | -0.096 |
Christensen | -0.094 |
apter | -0.090 |
ides | -0.086 |
Token | D |
Token ID | 360 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
Falk | +0.101 |
IDE | +0.100 |
Christensen | +0.098 |
apter | +0.093 |
ides | +0.089 |
Neg logit contributions | |
rush | -0.139 |
okane | -0.116 |
RL | -0.116 |
anyl | -0.115 |
itton | -0.110 |
Token | ella |
Token ID | 12627 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
rush | +0.519 |
okane | +0.429 |
RL | +0.429 |
anyl | +0.428 |
itton | +0.407 |
Neg logit contributions | |
Falk | -0.419 |
IDE | -0.418 |
Christensen | -0.407 |
apter | -0.388 |
ides | -0.372 |
Token | Vol |
Token ID | 4709 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
rush | +4.293 |
RL | +3.376 |
okane | +3.035 |
anyl | +3.027 |
MV | +2.840 |
Neg logit contributions | |
IDE | -7.910 |
Falk | -7.632 |
Christensen | -7.538 |
apter | -7.516 |
�士 | -7.477 |
Token | pe |
Token ID | 431 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rush | +1.318 |
okane | +1.092 |
RL | +1.091 |
anyl | +1.088 |
itton | +1.035 |
Neg logit contributions | |
Falk | -1.069 |
IDE | -1.066 |
Christensen | -1.038 |
apter | -0.990 |
ides | -0.951 |
Token | says |
Token ID | 1139 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
IDE | +0.740 |
Falk | +0.739 |
Christensen | +0.715 |
apter | +0.684 |
ides | +0.649 |
Neg logit contributions | |
rush | -0.978 |
RL | -0.815 |
okane | -0.813 |
anyl | -0.812 |
itton | -0.774 |
Token | , |
Token ID | 11 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Falk | +1.697 |
IDE | +1.688 |
Christensen | +1.648 |
apter | +1.564 |
ides | +1.513 |
Neg logit contributions | |
rush | -2.113 |
okane | -1.753 |
anyl | -1.746 |
RL | -1.745 |
itton | -1.664 |
Token | " |
Token ID | 366 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
Falk | +0.321 |
IDE | +0.320 |
Christensen | +0.313 |
apter | +0.298 |
ides | +0.287 |
Neg logit contributions | |
rush | -0.367 |
okane | -0.302 |
RL | -0.301 |
anyl | -0.301 |
itton | -0.286 |
Token | Reply |
Token ID | 14883 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Falk | +1.260 |
IDE | +1.231 |
Christensen | +1.190 |
apter | +1.079 |
ides | +1.023 |
Neg logit contributions | |
rush | -3.066 |
anyl | -2.676 |
okane | -2.670 |
RL | -2.639 |
itton | -2.581 |
Token |
|
Token ID | 198 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
Falk | +1.004 |
IDE | +1.000 |
Christensen | +0.973 |
apter | +0.921 |
ides | +0.889 |
Neg logit contributions | |
rush | -1.341 |
okane | -1.123 |
anyl | -1.120 |
RL | -1.113 |
itton | -1.070 |
Token |
|
Token ID | 198 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
Falk | +0.571 |
IDE | +0.570 |
Christensen | +0.554 |
apter | +0.526 |
ides | +0.506 |
Neg logit contributions | |
rush | -0.744 |
okane | -0.622 |
anyl | -0.620 |
RL | -0.617 |
itton | -0.591 |
Token | 19 |
Token ID | 1129 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Falk | +0.042 |
IDE | +0.041 |
Christensen | +0.041 |
apter | +0.039 |
ides | +0.037 |
Neg logit contributions | |
rush | -0.057 |
RL | -0.047 |
okane | -0.047 |
anyl | -0.046 |
itton | -0.044 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Falk | +1.522 |
IDE | +1.516 |
Christensen | +1.480 |
apter | +1.413 |
ides | +1.360 |
Neg logit contributions | |
rush | -1.659 |
okane | -1.356 |
RL | -1.353 |
anyl | -1.352 |
itton | -1.282 |
Token |
|
Token ID | 198 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Falk | +2.185 |
IDE | +2.180 |
Christensen | +2.116 |
apter | +1.981 |
ides | +1.938 |
Neg logit contributions | |
rush | -3.176 |
okane | -2.701 |
anyl | -2.691 |
RL | -2.635 |
itton | -2.591 |
Token |
|
Token ID | 198 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
IDE | +3.878 |
Falk | +3.811 |
Christensen | +3.662 |
ides | +3.413 |
apter | +3.399 |
Neg logit contributions | |
rush | -6.553 |
okane | -5.780 |
anyl | -5.739 |
rall | -5.677 |
itton | -5.596 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
IDE | +4.137 |
Falk | +3.683 |
Christensen | +3.661 |
Dou | +3.398 |
ides | +3.353 |
Neg logit contributions | |
rush | -9.317 |
RL | -8.225 |
anyl | -8.169 |
okane | -8.168 |
itton | -8.114 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
IDE | +2.711 |
Falk | +2.702 |
Christensen | +2.647 |
apter | +2.508 |
ides | +2.448 |
Neg logit contributions | |
rush | -2.901 |
anyl | -2.384 |
okane | -2.377 |
RL | -2.338 |
itton | -2.281 |
Token | this |
Token ID | 428 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Falk | +3.339 |
IDE | +3.272 |
Christensen | +3.262 |
apter | +2.979 |
ides | +2.949 |
Neg logit contributions | |
rush | -5.517 |
okane | -4.729 |
anyl | -4.721 |
RL | -4.578 |
itton | -4.563 |
Token | comment |
Token ID | 2912 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
IDE | +4.423 |
Falk | +4.398 |
Christensen | +4.380 |
ides | +3.995 |
apter | +3.967 |
Neg logit contributions | |
rush | -5.207 |
okane | -4.301 |
anyl | -4.275 |
itton | -4.107 |
RL | -4.086 |
Token | as |
Token ID | 355 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Falk | +0.202 |
IDE | +0.201 |
Christensen | +0.197 |
apter | +0.188 |
ides | +0.181 |
Neg logit contributions | |
rush | -0.206 |
okane | -0.168 |
RL | -0.167 |
anyl | -0.167 |
itton | -0.158 |
Token | much |
Token ID | 881 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
rush | +0.079 |
RL | +0.065 |
okane | +0.065 |
anyl | +0.065 |
itton | +0.061 |
Neg logit contributions | |
Falk | -0.071 |
IDE | -0.071 |
Christensen | -0.069 |
apter | -0.066 |
ides | -0.063 |
Token | fun |
Token ID | 1257 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
Falk | +0.983 |
IDE | +0.979 |
Christensen | +0.953 |
apter | +0.905 |
ides | +0.877 |
Neg logit contributions | |
rush | -1.135 |
okane | -0.940 |
anyl | -0.934 |
RL | -0.927 |
itton | -0.887 |
Token | as |
Token ID | 355 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Falk | +0.580 |
IDE | +0.578 |
Christensen | +0.565 |
apter | +0.541 |
ides | +0.523 |
Neg logit contributions | |
rush | -0.552 |
okane | -0.445 |
RL | -0.443 |
anyl | -0.443 |
itton | -0.418 |
Token | " |
Token ID | 1 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Falk | +1.156 |
IDE | +1.150 |
Christensen | +1.123 |
apter | +1.071 |
ides | +1.033 |
Neg logit contributions | |
rush | -1.258 |
okane | -1.030 |
anyl | -1.025 |
RL | -1.024 |
itton | -0.972 |
Token | followed |
Token ID | 3940 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
Falk | +1.430 |
IDE | +1.421 |
Christensen | +1.388 |
apter | +1.318 |
ides | +1.281 |
Neg logit contributions | |
rush | -1.510 |
okane | -1.236 |
anyl | -1.229 |
RL | -1.225 |
itton | -1.166 |
Token | by |
Token ID | 416 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Falk | +4.490 |
IDE | +4.464 |
Christensen | +4.323 |
ides | +4.091 |
apter | +4.067 |
Neg logit contributions | |
rush | -4.835 |
okane | -3.982 |
anyl | -3.974 |
RL | -3.946 |
itton | -3.791 |
Token | a |
Token ID | 257 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Falk | +1.724 |
IDE | +1.713 |
Christensen | +1.671 |
apter | +1.592 |
ides | +1.542 |
Neg logit contributions | |
rush | -1.935 |
okane | -1.593 |
anyl | -1.584 |
RL | -1.579 |
itton | -1.509 |
Token | drop |
Token ID | 4268 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
Falk | +0.511 |
IDE | +0.509 |
Christensen | +0.497 |
apter | +0.475 |
ides | +0.458 |
Neg logit contributions | |
rush | -0.529 |
okane | -0.430 |
RL | -0.429 |
anyl | -0.428 |
itton | -0.405 |
Token | - |
Token ID | 12 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
Falk | +0.661 |
IDE | +0.659 |
Christensen | +0.642 |
apter | +0.613 |
ides | +0.593 |
Neg logit contributions | |
rush | -0.691 |
okane | -0.566 |
anyl | -0.564 |
RL | -0.562 |
itton | -0.536 |
Token | down |
Token ID | 2902 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
rush | +0.236 |
RL | +0.186 |
okane | +0.186 |
anyl | +0.186 |
itton | +0.174 |
Neg logit contributions | |
Falk | -0.258 |
IDE | -0.256 |
Christensen | -0.252 |
apter | -0.241 |
ides | -0.232 |
Token | - |
Token ID | 532 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
rush | +0.328 |
RL | +0.272 |
okane | +0.269 |
anyl | +0.266 |
itton | +0.253 |
Neg logit contributions | |
IDE | -0.280 |
Falk | -0.280 |
Christensen | -0.272 |
apter | -0.263 |
ides | -0.250 |
Token | January |
Token ID | 3269 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Falk | +0.770 |
IDE | +0.767 |
Christensen | +0.741 |
apter | +0.701 |
ides | +0.661 |
Neg logit contributions | |
rush | -1.331 |
okane | -1.128 |
RL | -1.128 |
anyl | -1.125 |
itton | -1.077 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Falk | +2.850 |
IDE | +2.804 |
Christensen | +2.713 |
apter | +2.518 |
ides | +2.433 |
Neg logit contributions | |
rush | -4.921 |
anyl | -4.199 |
okane | -4.176 |
RL | -4.119 |
itton | -4.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
IDE | +1.613 |
Falk | +1.612 |
Christensen | +1.559 |
apter | +1.483 |
ides | +1.436 |
Neg logit contributions | |
rush | -2.058 |
okane | -1.730 |
anyl | -1.723 |
RL | -1.705 |
itton | -1.646 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Falk | +3.281 |
IDE | +3.229 |
Christensen | +3.172 |
apter | +2.966 |
ides | +2.937 |
Neg logit contributions | |
rush | -3.632 |
okane | -3.041 |
anyl | -2.994 |
RL | -2.936 |
itton | -2.882 |
Token | Que |
Token ID | 15681 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
IDE | +2.417 |
Falk | +2.354 |
Christensen | +2.267 |
apter | +2.155 |
Dou | +2.134 |
Neg logit contributions | |
rush | -3.275 |
anyl | -2.792 |
okane | -2.787 |
RL | -2.734 |
itton | -2.673 |
Token | er |
Token ID | 263 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
IDE | +3.893 |
Falk | +3.810 |
Christensen | +3.732 |
apter | +3.613 |
ides | +3.450 |
Neg logit contributions | |
rush | -6.179 |
okane | -5.384 |
anyl | -5.359 |
RL | -5.277 |
rall | -5.131 |
Token | magnet |
Token ID | 19972 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
IDE | +5.604 |
Falk | +5.586 |
Christensen | +5.374 |
apter | +5.248 |
ether | +4.941 |
Neg logit contributions | |
rush | -7.220 |
okane | -6.287 |
anyl | -6.093 |
RL | -6.017 |
itton | -5.848 |
Token | ? |
Token ID | 30 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
IDE | +4.438 |
Falk | +4.402 |
Christensen | +4.238 |
apter | +3.956 |
ides | +3.930 |
Neg logit contributions | |
rush | -6.629 |
anyl | -5.639 |
okane | -5.595 |
RL | -5.518 |
itton | -5.378 |
Token |
|
Token ID | 198 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Falk | +3.457 |
IDE | +3.450 |
Christensen | +3.342 |
apter | +3.150 |
ides | +3.033 |
Neg logit contributions | |
rush | -5.101 |
okane | -4.284 |
anyl | -4.267 |
RL | -4.225 |
itton | -4.092 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
IDE | +3.742 |
Falk | +3.732 |
Christensen | +3.591 |
apter | +3.361 |
ides | +3.286 |
Neg logit contributions | |
rush | -6.340 |
okane | -5.575 |
anyl | -5.526 |
rall | -5.469 |
itton | -5.361 |
Token | opsis |
Token ID | 24608 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
rush | +1.491 |
okane | +1.276 |
anyl | +1.271 |
RL | +1.261 |
itton | +1.215 |
Neg logit contributions | |
Falk | -0.857 |
IDE | -0.842 |
Christensen | -0.815 |
apter | -0.763 |
Dou | -0.718 |
Token | _ |
Token ID | 62 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Falk | +1.556 |
IDE | +1.548 |
Christensen | +1.512 |
apter | +1.444 |
ides | +1.394 |
Neg logit contributions | |
rush | -1.722 |
okane | -1.407 |
RL | -1.405 |
anyl | -1.404 |
itton | -1.334 |
Token | an |
Token ID | 272 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
IDE | +2.067 |
Falk | +2.064 |
Christensen | +2.003 |
apter | +1.918 |
ides | +1.850 |
Neg logit contributions | |
rush | -2.501 |
RL | -2.074 |
okane | -2.070 |
anyl | -2.065 |
itton | -1.968 |
Token | ac |
Token ID | 330 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
Falk | +0.245 |
IDE | +0.243 |
Christensen | +0.236 |
apter | +0.220 |
ides | +0.209 |
Neg logit contributions | |
rush | -0.428 |
okane | -0.365 |
anyl | -0.364 |
RL | -0.363 |
itton | -0.348 |
Token | ard |
Token ID | 446 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
rush | +0.389 |
anyl | +0.327 |
okane | +0.327 |
RL | +0.325 |
itton | +0.311 |
Neg logit contributions | |
Falk | -0.260 |
IDE | -0.255 |
Christensen | -0.248 |
apter | -0.232 |
Dou | -0.223 |
Token | io |
Token ID | 952 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
IDE | +2.128 |
Falk | +2.117 |
Christensen | +2.053 |
apter | +1.954 |
ides | +1.861 |
Neg logit contributions | |
rush | -3.893 |
RL | -3.338 |
okane | -3.333 |
anyl | -3.333 |
itton | -3.183 |
Token | ides |
Token ID | 1460 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
IDE | +0.334 |
Falk | +0.227 |
Christensen | +0.146 |
ides | +0.013 |
apter | -0.017 |
Neg logit contributions | |
rush | -8.417 |
RL | -7.600 |
okane | -7.570 |
anyl | -7.562 |
itton | -7.379 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Falk | +2.618 |
IDE | +2.612 |
Christensen | +2.542 |
apter | +2.412 |
ides | +2.331 |
Neg logit contributions | |
rush | -3.328 |
okane | -2.769 |
anyl | -2.766 |
RL | -2.762 |
itton | -2.638 |
Token | pdf |
Token ID | 12315 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Falk | +1.124 |
IDE | +1.118 |
Christensen | +1.079 |
apter | +1.011 |
ides | +0.957 |
Neg logit contributions | |
rush | -2.188 |
okane | -1.875 |
RL | -1.872 |
anyl | -1.871 |
itton | -1.799 |
Token |
|
Token ID | 198 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
rush | +1.328 |
RL | +1.101 |
okane | +1.100 |
anyl | +1.084 |
itton | +1.035 |
Neg logit contributions | |
IDE | -1.065 |
Falk | -1.058 |
Christensen | -1.032 |
apter | -0.989 |
ides | -0.945 |
Token |
|
Token ID | 198 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
Falk | +0.534 |
IDE | +0.532 |
Christensen | +0.518 |
apter | +0.492 |
ides | +0.472 |
Neg logit contributions | |
rush | -0.688 |
okane | -0.574 |
anyl | -0.572 |
RL | -0.571 |
itton | -0.545 |
Token | x |
Token ID | 87 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
rush | +0.377 |
RL | +0.310 |
anyl | +0.310 |
okane | +0.309 |
itton | +0.294 |
Neg logit contributions | |
Falk | -0.300 |
IDE | -0.296 |
Christensen | -0.291 |
apter | -0.275 |
ides | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
Falk | +0.790 |
IDE | +0.789 |
Christensen | +0.767 |
apter | +0.730 |
ides | +0.701 |
Neg logit contributions | |
rush | -1.000 |
okane | -0.832 |
anyl | -0.829 |
RL | -0.827 |
itton | -0.790 |
Token | x |
Token ID | 87 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
rush | +0.377 |
anyl | +0.309 |
RL | +0.309 |
okane | +0.309 |
itton | +0.293 |
Neg logit contributions | |
Falk | -0.301 |
IDE | -0.297 |
Christensen | -0.292 |
apter | -0.277 |
ides | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
IDE | +0.923 |
Falk | +0.921 |
Christensen | +0.890 |
apter | +0.848 |
ides | +0.818 |
Neg logit contributions | |
rush | -1.202 |
okane | -1.011 |
anyl | -1.004 |
RL | -1.001 |
itton | -0.958 |
Token | 126 |
Token ID | 19420 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
IDE | +0.238 |
Falk | +0.237 |
Christensen | +0.228 |
apter | +0.216 |
ides | +0.207 |
Neg logit contributions | |
rush | -0.387 |
okane | -0.332 |
RL | -0.330 |
anyl | -0.328 |
itton | -0.316 |
Token | 11 |
Token ID | 1367 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Falk | +2.184 |
IDE | +2.164 |
Christensen | +2.124 |
apter | +1.989 |
ides | +1.936 |
Neg logit contributions | |
rush | -2.853 |
okane | -2.393 |
anyl | -2.387 |
RL | -2.337 |
itton | -2.266 |
Token | 458 |
Token ID | 29334 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
IDE | +3.258 |
Falk | +3.250 |
Christensen | +3.142 |
apter | +2.936 |
ides | +2.851 |
Neg logit contributions | |
rush | -5.198 |
anyl | -4.432 |
okane | -4.397 |
RL | -4.338 |
itton | -4.246 |
Token | 72 |
Token ID | 4761 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
Falk | +1.138 |
IDE | +1.133 |
Christensen | +1.102 |
apter | +1.044 |
ides | +0.997 |
Neg logit contributions | |
rush | -1.637 |
okane | -1.372 |
RL | -1.370 |
anyl | -1.368 |
itton | -1.307 |
Token | x |
Token ID | 2124 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
rush | +0.661 |
RL | +0.548 |
okane | +0.545 |
anyl | +0.543 |
itton | +0.518 |
Neg logit contributions | |
Falk | -0.534 |
IDE | -0.532 |
Christensen | -0.518 |
apter | -0.495 |
ides | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
IDE | +1.473 |
Falk | +1.471 |
Christensen | +1.427 |
apter | +1.356 |
ides | +1.308 |
Neg logit contributions | |
rush | -1.941 |
okane | -1.631 |
anyl | -1.624 |
RL | -1.609 |
itton | -1.549 |
Token | x |
Token ID | 87 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Falk | +0.449 |
IDE | +0.446 |
Christensen | +0.435 |
apter | +0.413 |
ides | +0.394 |
Neg logit contributions | |
rush | -0.588 |
okane | -0.488 |
RL | -0.488 |
anyl | -0.487 |
itton | -0.464 |
Token | panels |
Token ID | 13043 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Falk | +1.465 |
IDE | +1.461 |
Christensen | +1.433 |
apter | +1.382 |
ides | +1.348 |
Neg logit contributions | |
rush | -0.874 |
okane | -0.655 |
anyl | -0.651 |
RL | -0.649 |
itton | -0.599 |
Token | were |
Token ID | 547 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Falk | +0.777 |
IDE | +0.774 |
Christensen | +0.757 |
apter | +0.724 |
ides | +0.697 |
Neg logit contributions | |
rush | -0.804 |
okane | -0.653 |
RL | -0.652 |
anyl | -0.651 |
itton | -0.616 |
Token | controlled |
Token ID | 6856 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Falk | +1.672 |
IDE | +1.664 |
Christensen | +1.622 |
apter | +1.546 |
ides | +1.493 |
Neg logit contributions | |
rush | -1.887 |
okane | -1.555 |
anyl | -1.545 |
RL | -1.541 |
itton | -1.465 |
Token | from |
Token ID | 422 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Falk | +2.101 |
IDE | +2.095 |
Christensen | +2.034 |
apter | +1.939 |
ides | +1.894 |
Neg logit contributions | |
rush | -2.169 |
okane | -1.778 |
anyl | -1.756 |
RL | -1.749 |
itton | -1.667 |
Token | a |
Token ID | 257 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Falk | +1.127 |
IDE | +1.123 |
Christensen | +1.096 |
apter | +1.048 |
ides | +1.007 |
Neg logit contributions | |
rush | -1.224 |
okane | -1.000 |
RL | -0.998 |
anyl | -0.996 |
itton | -0.945 |
Token | central |
Token ID | 4318 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
Falk | +1.515 |
IDE | +1.508 |
Christensen | +1.470 |
apter | +1.394 |
ides | +1.351 |
Neg logit contributions | |
rush | -1.748 |
okane | -1.445 |
anyl | -1.434 |
RL | -1.428 |
itton | -1.365 |
Token | computer |
Token ID | 3644 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
Falk | +0.314 |
IDE | +0.313 |
Christensen | +0.306 |
apter | +0.293 |
ides | +0.280 |
Neg logit contributions | |
rush | -0.349 |
RL | -0.287 |
okane | -0.284 |
anyl | -0.284 |
itton | -0.269 |
Token | in |
Token ID | 287 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rush | +0.457 |
RL | +0.374 |
okane | +0.370 |
anyl | +0.369 |
itton | +0.350 |
Neg logit contributions | |
Falk | -0.433 |
IDE | -0.430 |
Christensen | -0.423 |
apter | -0.405 |
Dou | -0.386 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Falk | +0.805 |
IDE | +0.803 |
Christensen | +0.783 |
apter | +0.749 |
ides | +0.720 |
Neg logit contributions | |
rush | -0.872 |
RL | -0.711 |
okane | -0.711 |
anyl | -0.709 |
itton | -0.671 |
Token | screened |
Token ID | 32862 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
Falk | +1.115 |
IDE | +1.111 |
Christensen | +1.084 |
apter | +1.032 |
ides | +0.993 |
Neg logit contributions | |
rush | -1.289 |
okane | -1.060 |
RL | -1.057 |
anyl | -1.056 |
itton | -1.004 |
Token | area |
Token ID | 1989 |
Feature activation | -4.77e-03 |
Pos logit contributions | |
rush | +0.567 |
RL | +0.471 |
anyl | +0.464 |
okane | +0.463 |
itton | +0.439 |
Neg logit contributions | |
Falk | -0.492 |
IDE | -0.491 |
Christensen | -0.480 |
apter | -0.464 |
ides | -0.439 |
Token | = |
Token ID | 796 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
Falk | +0.959 |
IDE | +0.952 |
Christensen | +0.931 |
apter | +0.876 |
ides | +0.845 |
Neg logit contributions | |
rush | -1.287 |
okane | -1.072 |
anyl | -1.071 |
RL | -1.065 |
itton | -1.023 |
Token | k |
Token ID | 479 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
rush | +0.337 |
okane | +0.264 |
RL | +0.264 |
anyl | +0.263 |
itton | +0.246 |
Neg logit contributions | |
Falk | -0.428 |
IDE | -0.427 |
Christensen | -0.418 |
apter | -0.402 |
ides | -0.389 |
Token | ( |
Token ID | 357 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
rush | +0.275 |
okane | +0.225 |
RL | +0.224 |
anyl | +0.224 |
itton | +0.212 |
Neg logit contributions | |
Falk | -0.254 |
IDE | -0.253 |
Christensen | -0.247 |
apter | -0.236 |
ides | -0.227 |
Token | T |
Token ID | 51 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
rush | +0.306 |
okane | +0.245 |
RL | +0.245 |
anyl | +0.244 |
itton | +0.230 |
Neg logit contributions | |
Falk | -0.331 |
IDE | -0.330 |
Christensen | -0.323 |
apter | -0.310 |
ides | -0.299 |
Token | ( |
Token ID | 7 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Falk | +1.869 |
IDE | +1.866 |
Christensen | +1.818 |
apter | +1.742 |
ides | +1.677 |
Neg logit contributions | |
rush | -1.953 |
okane | -1.592 |
RL | -1.575 |
anyl | -1.573 |
itton | -1.489 |
Token | t |
Token ID | 83 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
rush | +2.490 |
okane | +1.993 |
anyl | +1.991 |
RL | +1.988 |
itton | +1.887 |
Neg logit contributions | |
Falk | -2.430 |
IDE | -2.403 |
Christensen | -2.372 |
apter | -2.232 |
�士 | -2.158 |
Token | )- |
Token ID | 13219 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Falk | +2.732 |
IDE | +2.726 |
Christensen | +2.652 |
apter | +2.572 |
Dou | +2.476 |
Neg logit contributions | |
rush | -2.654 |
RL | -2.176 |
okane | -2.160 |
anyl | -2.128 |
itton | -2.047 |
Token | T |
Token ID | 309 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Falk | +1.846 |
IDE | +1.836 |
Christensen | +1.800 |
apter | +1.716 |
ides | +1.653 |
Neg logit contributions | |
rush | -1.866 |
okane | -1.511 |
anyl | -1.501 |
RL | -1.489 |
itton | -1.418 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Falk | +1.028 |
IDE | +1.025 |
Christensen | +1.000 |
apter | +0.953 |
ides | +0.917 |
Neg logit contributions | |
rush | -1.187 |
okane | -0.977 |
RL | -0.971 |
anyl | -0.970 |
itton | -0.922 |
Token | ) |
Token ID | 1267 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
Falk | +0.604 |
IDE | +0.599 |
Christensen | +0.580 |
apter | +0.539 |
ides | +0.507 |
Neg logit contributions | |
rush | -1.309 |
okane | -1.126 |
RL | -1.122 |
anyl | -1.121 |
itton | -1.080 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rush | +0.427 |
RL | +0.352 |
okane | +0.352 |
anyl | +0.351 |
itton | +0.333 |
Neg logit contributions | |
Falk | -0.359 |
IDE | -0.358 |
Christensen | -0.349 |
apter | -0.334 |
ides | -0.319 |
Token | develop |
Token ID | 1205 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
rush | +0.742 |
RL | +0.595 |
okane | +0.592 |
anyl | +0.591 |
itton | +0.558 |
Neg logit contributions | |
Falk | -0.796 |
IDE | -0.796 |
Christensen | -0.778 |
apter | -0.744 |
ides | -0.718 |
Token | adaptive |
Token ID | 29605 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
Falk | +0.744 |
IDE | +0.740 |
Christensen | +0.725 |
apter | +0.689 |
ides | +0.665 |
Neg logit contributions | |
rush | -0.835 |
okane | -0.685 |
anyl | -0.683 |
RL | -0.680 |
itton | -0.649 |
Token | mechanisms |
Token ID | 11701 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Falk | +0.405 |
IDE | +0.402 |
Christensen | +0.395 |
apter | +0.374 |
ides | +0.362 |
Neg logit contributions | |
rush | -0.444 |
okane | -0.364 |
anyl | -0.363 |
RL | -0.359 |
itton | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Falk | +1.411 |
IDE | +1.409 |
Christensen | +1.378 |
apter | +1.312 |
ides | +1.273 |
Neg logit contributions | |
rush | -1.549 |
okane | -1.271 |
anyl | -1.269 |
RL | -1.257 |
itton | -1.207 |
Token | security |
Token ID | 2324 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Falk | +1.647 |
IDE | +1.636 |
Christensen | +1.610 |
apter | +1.536 |
ides | +1.485 |
Neg logit contributions | |
rush | -1.594 |
okane | -1.297 |
anyl | -1.279 |
RL | -1.274 |
itton | -1.218 |
Token | that |
Token ID | 326 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Falk | +0.347 |
IDE | +0.345 |
Christensen | +0.338 |
apter | +0.320 |
ides | +0.310 |
Neg logit contributions | |
rush | -0.397 |
okane | -0.327 |
anyl | -0.326 |
RL | -0.324 |
itton | -0.310 |
Token | can |
Token ID | 460 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
Falk | +1.312 |
IDE | +1.302 |
Christensen | +1.277 |
apter | +1.222 |
ides | +1.184 |
Neg logit contributions | |
rush | -1.198 |
okane | -0.963 |
anyl | -0.960 |
RL | -0.956 |
itton | -0.903 |
Token | match |
Token ID | 2872 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rush | +0.308 |
RL | +0.245 |
okane | +0.245 |
anyl | +0.245 |
itton | +0.231 |
Neg logit contributions | |
Falk | -0.343 |
IDE | -0.342 |
Christensen | -0.335 |
apter | -0.321 |
ides | -0.310 |
Token | or |
Token ID | 393 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Falk | +0.718 |
IDE | +0.715 |
Christensen | +0.698 |
apter | +0.663 |
ides | +0.639 |
Neg logit contributions | |
rush | -0.877 |
okane | -0.728 |
anyl | -0.725 |
RL | -0.723 |
itton | -0.689 |
Token | exceed |
Token ID | 7074 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
Falk | +1.919 |
IDE | +1.908 |
Christensen | +1.863 |
apter | +1.779 |
ides | +1.710 |
Neg logit contributions | |
rush | -2.208 |
okane | -1.835 |
RL | -1.818 |
anyl | -1.815 |
itton | -1.727 |
Token | the |
Token ID | 262 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
Falk | +0.211 |
IDE | +0.210 |
Christensen | +0.204 |
apter | +0.195 |
ides | +0.187 |
Neg logit contributions | |
rush | -0.261 |
RL | -0.216 |
okane | -0.216 |
anyl | -0.215 |
itton | -0.205 |
Token | in |
Token ID | 287 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Falk | +1.485 |
IDE | +1.481 |
Christensen | +1.445 |
apter | +1.376 |
ides | +1.330 |
Neg logit contributions | |
rush | -1.598 |
okane | -1.308 |
anyl | -1.302 |
RL | -1.300 |
itton | -1.230 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Falk | +0.728 |
IDE | +0.725 |
Christensen | +0.708 |
apter | +0.676 |
ides | +0.651 |
Neg logit contributions | |
rush | -0.791 |
okane | -0.646 |
RL | -0.645 |
anyl | -0.644 |
itton | -0.611 |
Token | old |
Token ID | 1468 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Falk | +0.978 |
IDE | +0.976 |
Christensen | +0.952 |
apter | +0.910 |
ides | +0.874 |
Neg logit contributions | |
rush | -1.088 |
okane | -0.891 |
RL | -0.890 |
anyl | -0.888 |
itton | -0.843 |
Token | Naval |
Token ID | 20818 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Falk | +1.571 |
IDE | +1.556 |
Christensen | +1.522 |
apter | +1.440 |
ides | +1.395 |
Neg logit contributions | |
rush | -1.801 |
okane | -1.483 |
anyl | -1.477 |
RL | -1.473 |
itton | -1.403 |
Token | Air |
Token ID | 3701 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
rush | +0.251 |
RL | +0.207 |
okane | +0.206 |
anyl | +0.205 |
itton | +0.196 |
Neg logit contributions | |
Falk | -0.212 |
IDE | -0.212 |
Christensen | -0.208 |
apter | -0.199 |
ides | -0.189 |
Token | Station |
Token ID | 9327 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
IDE | +0.163 |
Falk | +0.162 |
Christensen | +0.159 |
apter | +0.150 |
ides | +0.142 |
Neg logit contributions | |
rush | -0.268 |
RL | -0.226 |
okane | -0.224 |
anyl | -0.223 |
itton | -0.215 |
Token | in |
Token ID | 287 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Falk | +1.511 |
IDE | +1.494 |
Christensen | +1.460 |
apter | +1.378 |
ides | +1.343 |
Neg logit contributions | |
rush | -1.708 |
anyl | -1.411 |
okane | -1.407 |
RL | -1.392 |
itton | -1.326 |
Token | South |
Token ID | 2520 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
IDE | +0.305 |
Falk | +0.305 |
Christensen | +0.296 |
apter | +0.281 |
ides | +0.269 |
Neg logit contributions | |
rush | -0.434 |
RL | -0.362 |
okane | -0.362 |
anyl | -0.361 |
itton | -0.345 |
Token | We |
Token ID | 775 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
Falk | +1.003 |
IDE | +0.998 |
Christensen | +0.970 |
apter | +0.920 |
ides | +0.882 |
Neg logit contributions | |
rush | -1.419 |
okane | -1.189 |
anyl | -1.188 |
RL | -1.186 |
itton | -1.132 |
Token | ym |
Token ID | 4948 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
rush | +0.081 |
okane | +0.067 |
RL | +0.067 |
anyl | +0.067 |
itton | +0.064 |
Neg logit contributions | |
Falk | -0.059 |
IDE | -0.058 |
Christensen | -0.057 |
apter | -0.054 |
Dou | -0.051 |
Token | outh |
Token ID | 1536 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
rush | +1.949 |
okane | +1.458 |
RL | +1.442 |
anyl | +1.432 |
itton | +1.342 |
Neg logit contributions | |
IDE | -3.165 |
Falk | -3.158 |
Christensen | -3.099 |
apter | -2.968 |
Azerbai | -2.893 |
Token | sent |
Token ID | 1908 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Falk | +1.169 |
IDE | +1.157 |
Christensen | +1.131 |
apter | +1.073 |
ides | +1.042 |
Neg logit contributions | |
rush | -1.345 |
okane | -1.109 |
anyl | -1.109 |
RL | -1.100 |
itton | -1.049 |
Token | to |
Token ID | 284 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
rush | +0.243 |
okane | +0.197 |
RL | +0.197 |
anyl | +0.196 |
itton | +0.185 |
Neg logit contributions | |
Falk | -0.239 |
IDE | -0.238 |
Christensen | -0.233 |
apter | -0.223 |
ides | -0.214 |
Token | the |
Token ID | 262 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Falk | +0.633 |
IDE | +0.631 |
Christensen | +0.615 |
apter | +0.588 |
ides | +0.563 |
Neg logit contributions | |
rush | -0.738 |
RL | -0.607 |
okane | -0.607 |
anyl | -0.606 |
itton | -0.575 |
Token | Star |
Token ID | 2907 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
Falk | +0.346 |
IDE | +0.345 |
Christensen | +0.335 |
apter | +0.319 |
ides | +0.303 |
Neg logit contributions | |
rush | -0.487 |
RL | -0.408 |
okane | -0.407 |
anyl | -0.406 |
itton | -0.388 |
Token | on |
Token ID | 319 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
Falk | +0.028 |
IDE | +0.027 |
Christensen | +0.027 |
apter | +0.026 |
ides | +0.025 |
Neg logit contributions | |
rush | -0.030 |
okane | -0.024 |
anyl | -0.024 |
RL | -0.024 |
itton | -0.023 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Falk | +0.312 |
IDE | +0.312 |
Christensen | +0.303 |
apter | +0.290 |
ides | +0.277 |
Neg logit contributions | |
rush | -0.372 |
RL | -0.306 |
okane | -0.306 |
anyl | -0.305 |
itton | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
Falk | +0.173 |
IDE | +0.173 |
Christensen | +0.169 |
apter | +0.161 |
ides | +0.154 |
Neg logit contributions | |
rush | -0.208 |
okane | -0.171 |
RL | -0.171 |
anyl | -0.171 |
itton | -0.162 |
Token | She |
Token ID | 1375 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
rush | +0.074 |
RL | +0.061 |
okane | +0.060 |
anyl | +0.060 |
itton | +0.057 |
Neg logit contributions | |
Falk | -0.067 |
IDE | -0.067 |
Christensen | -0.065 |
apter | -0.062 |
ides | -0.060 |
Token | added |
Token ID | 2087 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
rush | +0.592 |
RL | +0.489 |
okane | +0.487 |
anyl | +0.484 |
itton | +0.463 |
Neg logit contributions | |
IDE | -0.513 |
Falk | -0.510 |
Christensen | -0.496 |
apter | -0.476 |
Dou | -0.452 |
Token | that |
Token ID | 326 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
rush | +0.086 |
RL | +0.071 |
okane | +0.071 |
anyl | +0.071 |
itton | +0.067 |
Neg logit contributions | |
Falk | -0.074 |
IDE | -0.074 |
Christensen | -0.072 |
apter | -0.069 |
ides | -0.066 |
Token | trustees |
Token ID | 36636 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Falk | +0.283 |
IDE | +0.283 |
Christensen | +0.276 |
apter | +0.264 |
ides | +0.253 |
Neg logit contributions | |
rush | -0.329 |
RL | -0.271 |
okane | -0.270 |
anyl | -0.270 |
itton | -0.257 |
Token | are |
Token ID | 389 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Falk | +1.044 |
IDE | +1.038 |
Christensen | +1.015 |
apter | +0.962 |
ides | +0.931 |
Neg logit contributions | |
rush | -1.155 |
okane | -0.943 |
anyl | -0.942 |
RL | -0.940 |
itton | -0.895 |
Token | determined |
Token ID | 5295 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
Falk | +1.714 |
IDE | +1.703 |
Christensen | +1.664 |
apter | +1.570 |
ides | +1.532 |
Neg logit contributions | |
rush | -1.922 |
okane | -1.582 |
anyl | -1.574 |
RL | -1.566 |
itton | -1.489 |
Token | to |
Token ID | 284 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
Falk | +0.659 |
IDE | +0.656 |
Christensen | +0.642 |
apter | +0.613 |
ides | +0.593 |
Neg logit contributions | |
rush | -0.645 |
okane | -0.519 |
anyl | -0.519 |
RL | -0.519 |
itton | -0.489 |
Token | make |
Token ID | 787 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Falk | +0.727 |
IDE | +0.724 |
Christensen | +0.708 |
apter | +0.680 |
ides | +0.657 |
Neg logit contributions | |
rush | -0.640 |
okane | -0.511 |
RL | -0.509 |
anyl | -0.508 |
itton | -0.478 |
Token | it |
Token ID | 340 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
rush | +0.108 |
RL | +0.089 |
okane | +0.089 |
anyl | +0.088 |
itton | +0.084 |
Neg logit contributions | |
Falk | -0.092 |
IDE | -0.092 |
Christensen | -0.090 |
apter | -0.086 |
ides | -0.083 |
Token | happen |
Token ID | 1645 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
rush | +2.646 |
RL | +2.152 |
okane | +2.131 |
anyl | +2.108 |
itton | +1.971 |
Neg logit contributions | |
IDE | -2.615 |
Falk | -2.614 |
Christensen | -2.562 |
apter | -2.485 |
ides | -2.355 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Falk | +0.063 |
IDE | +0.063 |
Christensen | +0.062 |
apter | +0.059 |
ides | +0.056 |
Neg logit contributions | |
rush | -0.075 |
okane | -0.062 |
RL | -0.062 |
anyl | -0.062 |
itton | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
rush | +0.222 |
RL | +0.184 |
okane | +0.183 |
anyl | +0.182 |
itton | +0.173 |
Neg logit contributions | |
IDE | -0.181 |
Falk | -0.181 |
Christensen | -0.175 |
apter | -0.169 |
ides | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Falk | +0.302 |
IDE | +0.301 |
Christensen | +0.293 |
apter | +0.279 |
ides | +0.268 |
Neg logit contributions | |
rush | -0.388 |
okane | -0.323 |
anyl | -0.322 |
RL | -0.322 |
itton | -0.307 |
Token | "[ |
Token ID | 17912 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Falk | +0.103 |
IDE | +0.102 |
Christensen | +0.101 |
apter | +0.097 |
ides | +0.092 |
Neg logit contributions | |
rush | -0.105 |
anyl | -0.085 |
okane | -0.084 |
RL | -0.084 |
itton | -0.080 |
Token | The |
Token ID | 464 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Falk | +0.759 |
IDE | +0.756 |
Christensen | +0.738 |
apter | +0.705 |
ides | +0.677 |
Neg logit contributions | |
rush | -0.841 |
okane | -0.689 |
RL | -0.687 |
anyl | -0.686 |
itton | -0.651 |
Token | | |
Token ID | 930 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
rush | +0.612 |
RL | +0.417 |
okane | +0.414 |
anyl | +0.405 |
itton | +0.361 |
Neg logit contributions | |
Falk | -1.479 |
IDE | -1.471 |
Christensen | -1.448 |
apter | -1.408 |
ides | -1.372 |
Token | | |
Token ID | 930 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Falk | +0.814 |
IDE | +0.811 |
Christensen | +0.798 |
apter | +0.773 |
ides | +0.753 |
Neg logit contributions | |
rush | -0.378 |
RL | -0.264 |
okane | -0.263 |
anyl | -0.262 |
itton | -0.235 |
Token | org |
Token ID | 8745 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Falk | +1.146 |
IDE | +1.142 |
Christensen | +1.116 |
apter | +1.069 |
ides | +1.030 |
Neg logit contributions | |
rush | -1.128 |
okane | -0.911 |
RL | -0.910 |
anyl | -0.908 |
itton | -0.858 |
Token | . |
Token ID | 764 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
IDE | +1.052 |
Falk | +1.050 |
Christensen | +1.010 |
apter | +0.924 |
ides | +0.850 |
Neg logit contributions | |
rush | -3.038 |
okane | -2.663 |
anyl | -2.659 |
RL | -2.634 |
itton | -2.570 |
Token | cl |
Token ID | 537 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Falk | +0.506 |
IDE | +0.503 |
Christensen | +0.488 |
apter | +0.459 |
ides | +0.436 |
Neg logit contributions | |
rush | -0.866 |
okane | -0.735 |
RL | -0.734 |
anyl | -0.733 |
itton | -0.703 |
Token | ojure |
Token ID | 32511 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Falk | +0.178 |
IDE | +0.177 |
Christensen | +0.175 |
apter | +0.170 |
ides | +0.166 |
Neg logit contributions | |
rush | -0.067 |
okane | -0.043 |
RL | -0.043 |
anyl | -0.043 |
itton | -0.038 |
Token | / |
Token ID | 1220 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
rush | +1.509 |
RL | +1.137 |
okane | +1.123 |
anyl | +1.118 |
itton | +1.028 |
Neg logit contributions | |
Falk | -2.529 |
IDE | -2.510 |
Christensen | -2.471 |
apter | -2.391 |
ides | -2.318 |
Token | cl |
Token ID | 537 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
Falk | +1.753 |
IDE | +1.751 |
Christensen | +1.699 |
apter | +1.596 |
ides | +1.506 |
Neg logit contributions | |
rush | -3.138 |
okane | -2.676 |
anyl | -2.660 |
RL | -2.650 |
itton | -2.556 |
Token | ojure |
Token ID | 32511 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
Falk | +0.511 |
IDE | +0.510 |
Christensen | +0.503 |
apter | +0.489 |
ides | +0.476 |
Neg logit contributions | |
rush | -0.193 |
okane | -0.126 |
RL | -0.126 |
anyl | -0.125 |
itton | -0.109 |
Token | | |
Token ID | 930 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
Falk | +0.763 |
IDE | +0.762 |
Christensen | +0.749 |
apter | +0.725 |
ides | +0.707 |
Neg logit contributions | |
rush | -0.351 |
okane | -0.245 |
anyl | -0.244 |
RL | -0.243 |
itton | -0.220 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Falk | +0.167 |
IDE | +0.166 |
Christensen | +0.162 |
apter | +0.155 |
ides | +0.149 |
Neg logit contributions | |
rush | -0.193 |
RL | -0.159 |
okane | -0.159 |
anyl | -0.158 |
itton | -0.150 |
Token | Reporter |
Token ID | 25869 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
rush | +0.042 |
RL | +0.033 |
okane | +0.033 |
anyl | +0.033 |
itton | +0.031 |
Neg logit contributions | |
Falk | -0.046 |
IDE | -0.046 |
Christensen | -0.045 |
apter | -0.043 |
ides | -0.042 |
Token | Today |
Token ID | 6288 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
rush | +2.632 |
RL | +2.115 |
anyl | +2.105 |
okane | +2.101 |
itton | +1.985 |
Neg logit contributions | |
IDE | -2.825 |
Falk | -2.823 |
Christensen | -2.759 |
apter | -2.650 |
ides | -2.563 |
Token | ! |
Token ID | 0 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
rush | +1.904 |
RL | +1.466 |
okane | +1.454 |
anyl | +1.447 |
itton | +1.366 |
Neg logit contributions | |
Falk | -2.554 |
IDE | -2.543 |
Christensen | -2.529 |
apter | -2.430 |
ides | -2.339 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
rush | +2.003 |
okane | +1.661 |
RL | +1.658 |
anyl | +1.655 |
itton | +1.576 |
Neg logit contributions | |
Falk | -1.591 |
IDE | -1.585 |
Christensen | -1.545 |
apter | -1.469 |
ides | -1.409 |
Token | A |
Token ID | 32 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rush | +0.941 |
anyl | +0.770 |
RL | +0.766 |
okane | +0.764 |
itton | +0.725 |
Neg logit contributions | |
Falk | -0.801 |
IDE | -0.782 |
Christensen | -0.781 |
apter | -0.741 |
ides | -0.706 |
Token | usterity |
Token ID | 20761 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Falk | +0.808 |
IDE | +0.805 |
Christensen | +0.785 |
apter | +0.749 |
ides | +0.721 |
Neg logit contributions | |
rush | -0.905 |
okane | -0.742 |
RL | -0.740 |
anyl | -0.740 |
itton | -0.701 |
Token | has |
Token ID | 468 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
rush | +1.066 |
RL | +0.872 |
anyl | +0.868 |
okane | +0.868 |
itton | +0.821 |
Neg logit contributions | |
Falk | -0.971 |
IDE | -0.969 |
Christensen | -0.941 |
apter | -0.909 |
ides | -0.867 |
Token | failed |
Token ID | 4054 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Falk | +0.381 |
IDE | +0.379 |
Christensen | +0.370 |
apter | +0.354 |
ides | +0.340 |
Neg logit contributions | |
rush | -0.410 |
okane | -0.335 |
RL | -0.334 |
anyl | -0.334 |
itton | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
rush | +2.414 |
RL | +1.947 |
okane | +1.926 |
anyl | +1.918 |
itton | +1.802 |
Neg logit contributions | |
IDE | -2.468 |
Falk | -2.439 |
Christensen | -2.389 |
apter | -2.347 |
Dou | -2.211 |
Token | It |
Token ID | 632 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
Falk | +1.963 |
IDE | +1.935 |
Christensen | +1.902 |
apter | +1.795 |
ides | +1.731 |
Neg logit contributions | |
rush | -2.256 |
okane | -1.864 |
anyl | -1.857 |
RL | -1.836 |
itton | -1.769 |
Token | turned |
Token ID | 2900 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
Falk | +0.609 |
IDE | +0.608 |
Christensen | +0.593 |
apter | +0.566 |
ides | +0.544 |
Neg logit contributions | |
rush | -0.673 |
okane | -0.550 |
RL | -0.549 |
anyl | -0.549 |
itton | -0.520 |
Token |
|
Token ID | 198 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
IDE | +0.718 |
Falk | +0.714 |
Christensen | +0.687 |
apter | +0.672 |
ides | +0.645 |
Neg logit contributions | |
rush | -0.843 |
RL | -0.705 |
okane | -0.692 |
anyl | -0.685 |
itton | -0.652 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
rush | +0.406 |
RL | +0.336 |
okane | +0.334 |
anyl | +0.333 |
itton | +0.317 |
Neg logit contributions | |
Falk | -0.331 |
IDE | -0.330 |
Christensen | -0.322 |
apter | -0.307 |
ides | -0.293 |
Token | Both |
Token ID | 10265 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Falk | +0.174 |
IDE | +0.169 |
Christensen | +0.169 |
apter | +0.162 |
ides | +0.154 |
Neg logit contributions | |
rush | -0.194 |
RL | -0.158 |
anyl | -0.157 |
okane | -0.157 |
itton | -0.148 |
Token | schools |
Token ID | 4266 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Falk | +0.135 |
IDE | +0.135 |
Christensen | +0.130 |
apter | +0.126 |
ides | +0.120 |
Neg logit contributions | |
rush | -0.164 |
RL | -0.136 |
okane | -0.136 |
anyl | -0.134 |
itton | -0.128 |
Token | have |
Token ID | 423 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
Falk | +1.343 |
IDE | +1.338 |
Christensen | +1.310 |
apter | +1.249 |
ides | +1.210 |
Neg logit contributions | |
rush | -1.347 |
okane | -1.093 |
anyl | -1.091 |
RL | -1.088 |
itton | -1.030 |
Token | a |
Token ID | 257 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
rush | +0.017 |
RL | +0.014 |
okane | +0.014 |
anyl | +0.014 |
itton | +0.013 |
Neg logit contributions | |
Falk | -0.017 |
IDE | -0.017 |
Christensen | -0.016 |
apter | -0.016 |
ides | -0.015 |
Token | religious |
Token ID | 4158 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
rush | +0.244 |
RL | +0.202 |
okane | +0.201 |
anyl | +0.200 |
itton | +0.190 |
Neg logit contributions | |
IDE | -0.206 |
Falk | -0.206 |
Christensen | -0.200 |
apter | -0.192 |
ides | -0.183 |
Token | focus |
Token ID | 2962 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
rush | +0.785 |
RL | +0.647 |
okane | +0.643 |
anyl | +0.638 |
itton | +0.608 |
Neg logit contributions | |
Falk | -0.708 |
IDE | -0.707 |
Christensen | -0.688 |
apter | -0.665 |
ides | -0.633 |
Token | , |
Token ID | 11 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
rush | +0.189 |
RL | +0.155 |
okane | +0.155 |
anyl | +0.153 |
itton | +0.146 |
Neg logit contributions | |
Falk | -0.173 |
IDE | -0.172 |
Christensen | -0.167 |
apter | -0.161 |
ides | -0.154 |
Token | with |
Token ID | 351 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
IDE | +0.424 |
Falk | +0.422 |
Christensen | +0.408 |
apter | +0.398 |
ides | +0.380 |
Neg logit contributions | |
rush | -0.459 |
RL | -0.378 |
okane | -0.374 |
anyl | -0.373 |
itton | -0.355 |
Token | Clara |
Token ID | 27443 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
rush | +1.377 |
RL | +1.151 |
okane | +1.121 |
anyl | +1.119 |
itton | +1.062 |
Neg logit contributions | |
IDE | -1.184 |
Falk | -1.166 |
Christensen | -1.114 |
apter | -1.101 |
ides | -1.043 |
Token | typically |
Token ID | 6032 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
rush | +1.120 |
RL | +0.902 |
okane | +0.894 |
anyl | +0.887 |
itton | +0.842 |
Neg logit contributions | |
Falk | -1.170 |
IDE | -1.169 |
Christensen | -1.140 |
apter | -1.096 |
Dou | -1.046 |
Token | pay |
Token ID | 1414 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
Falk | +0.735 |
IDE | +0.733 |
Christensen | +0.717 |
apter | +0.687 |
ides | +0.663 |
Neg logit contributions | |
rush | -0.694 |
okane | -0.558 |
RL | -0.557 |
anyl | -0.555 |
itton | -0.524 |
Token | none |
Token ID | 4844 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Falk | +0.225 |
IDE | +0.224 |
Christensen | +0.219 |
apter | +0.208 |
ides | +0.200 |
Neg logit contributions | |
rush | -0.276 |
okane | -0.228 |
anyl | -0.227 |
RL | -0.227 |
itton | -0.217 |
Token | of |
Token ID | 286 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
rush | +0.856 |
RL | +0.701 |
okane | +0.700 |
anyl | +0.698 |
itton | +0.662 |
Neg logit contributions | |
Falk | -0.780 |
IDE | -0.777 |
Christensen | -0.758 |
apter | -0.725 |
ides | -0.695 |
Token | these |
Token ID | 777 |
Feature activation | -7.16e-03 |
Pos logit contributions | |
rush | +0.211 |
RL | +0.174 |
okane | +0.174 |
anyl | +0.173 |
itton | +0.164 |
Neg logit contributions | |
Falk | -0.178 |
IDE | -0.177 |
Christensen | -0.173 |
apter | -0.165 |
ides | -0.158 |
Token | costs |
Token ID | 3484 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
rush | +0.056 |
okane | +0.046 |
RL | +0.046 |
anyl | +0.046 |
itton | +0.044 |
Neg logit contributions | |
Falk | -0.049 |
IDE | -0.049 |
Christensen | -0.048 |
apter | -0.045 |
ides | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
rush | +1.871 |
RL | +1.542 |
okane | +1.523 |
anyl | +1.521 |
itton | +1.435 |
Neg logit contributions | |
Falk | -1.735 |
IDE | -1.729 |
Christensen | -1.683 |
apter | -1.621 |
Dou | -1.535 |
Token | he |
Token ID | 339 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
rush | +0.642 |
RL | +0.517 |
okane | +0.517 |
anyl | +0.516 |
itton | +0.487 |
Neg logit contributions | |
Falk | -0.661 |
IDE | -0.661 |
Christensen | -0.643 |
apter | -0.619 |
ides | -0.595 |
Token | noted |
Token ID | 4367 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
rush | +1.470 |
RL | +1.226 |
anyl | +1.218 |
okane | +1.217 |
itton | +1.168 |
Neg logit contributions | |
IDE | -1.164 |
Falk | -1.159 |
Christensen | -1.120 |
apter | -1.068 |
Dou | -1.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
rush | +0.911 |
okane | +0.751 |
RL | +0.751 |
anyl | +0.749 |
itton | +0.713 |
Neg logit contributions | |
Falk | -0.765 |
IDE | -0.763 |
Christensen | -0.743 |
apter | -0.708 |
ides | -0.678 |
Token | Instead |
Token ID | 5455 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
rush | +1.394 |
RL | +1.153 |
okane | +1.134 |
anyl | +1.131 |
itton | +1.068 |
Neg logit contributions | |
IDE | -1.257 |
Falk | -1.248 |
Christensen | -1.210 |
apter | -1.174 |
ides | -1.122 |
Token | a |
Token ID | 257 |
Feature activation | +5.08e-03 |
Pos logit contributions | |
Falk | +0.847 |
IDE | +0.841 |
Christensen | +0.823 |
apter | +0.782 |
ides | +0.754 |
Neg logit contributions | |
rush | -0.991 |
okane | -0.822 |
anyl | -0.819 |
RL | -0.815 |
itton | -0.779 |
Token | one |
Token ID | 530 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
Falk | +0.035 |
IDE | +0.035 |
Christensen | +0.034 |
apter | +0.033 |
ides | +0.031 |
Neg logit contributions | |
rush | -0.039 |
okane | -0.032 |
RL | -0.032 |
anyl | -0.032 |
itton | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
rush | +0.485 |
okane | +0.395 |
RL | +0.393 |
anyl | +0.393 |
itton | +0.372 |
Neg logit contributions | |
Falk | -0.475 |
IDE | -0.473 |
Christensen | -0.462 |
apter | -0.442 |
ides | -0.426 |
Token | to |
Token ID | 1462 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
rush | +1.724 |
anyl | +1.334 |
okane | +1.322 |
RL | +1.319 |
itton | +1.232 |
Neg logit contributions | |
Falk | -2.100 |
IDE | -2.073 |
Christensen | -2.050 |
apter | -1.954 |
Azerbai | -1.881 |
Token | - |
Token ID | 12 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
rush | +1.355 |
okane | +1.087 |
RL | +1.087 |
anyl | +1.086 |
itton | +1.027 |
Neg logit contributions | |
Falk | -1.388 |
IDE | -1.382 |
Christensen | -1.352 |
apter | -1.292 |
ides | -1.241 |
Token | one |
Token ID | 505 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
rush | +0.480 |
anyl | +0.385 |
okane | +0.384 |
RL | +0.383 |
itton | +0.364 |
Neg logit contributions | |
Falk | -0.484 |
IDE | -0.479 |
Christensen | -0.471 |
apter | -0.449 |
ides | -0.432 |
Token | replacement |
Token ID | 9014 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
rush | +4.011 |
RL | +3.257 |
anyl | +3.213 |
okane | +3.130 |
decay | +3.009 |
Neg logit contributions | |
IDE | -4.116 |
Falk | -4.063 |
Christensen | -4.027 |
apter | -3.838 |
emi | -3.685 |
Token | for |
Token ID | 329 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rush | +0.705 |
RL | +0.579 |
okane | +0.576 |
anyl | +0.576 |
itton | +0.545 |
Neg logit contributions | |
Falk | -0.620 |
IDE | -0.619 |
Christensen | -0.604 |
apter | -0.576 |
ides | -0.552 |
Token | the |
Token ID | 262 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
Falk | +0.893 |
IDE | +0.885 |
Christensen | +0.865 |
apter | +0.823 |
ides | +0.795 |
Neg logit contributions | |
rush | -1.012 |
okane | -0.835 |
anyl | -0.828 |
RL | -0.826 |
itton | -0.789 |
Token | 600 |
Token ID | 10053 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Falk | +0.554 |
IDE | +0.552 |
Christensen | +0.538 |
apter | +0.513 |
ides | +0.493 |
Neg logit contributions | |
rush | -0.647 |
okane | -0.532 |
RL | -0.531 |
anyl | -0.531 |
itton | -0.504 |
Token | - |
Token ID | 12 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
rush | +1.693 |
anyl | +1.368 |
RL | +1.368 |
okane | +1.364 |
itton | +1.289 |
Neg logit contributions | |
IDE | -1.594 |
Falk | -1.588 |
Christensen | -1.559 |
apter | -1.494 |
ides | -1.421 |
Token | ina |
Token ID | 1437 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
rush | +0.910 |
RL | +0.734 |
anyl | +0.731 |
okane | +0.728 |
itton | +0.691 |
Neg logit contributions | |
Falk | -0.851 |
IDE | -0.846 |
Christensen | -0.829 |
apter | -0.796 |
Dou | -0.761 |
Token | Fern |
Token ID | 38982 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
rush | +1.744 |
RL | +1.531 |
anyl | +1.515 |
okane | +1.514 |
itton | +1.452 |
Neg logit contributions | |
IDE | -0.565 |
Falk | -0.557 |
Christensen | -0.538 |
apter | -0.510 |
Dou | -0.455 |
Token | á |
Token ID | 6557 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
rush | +1.556 |
RL | +1.247 |
anyl | +1.241 |
okane | +1.237 |
itton | +1.154 |
Neg logit contributions | |
Falk | -1.702 |
IDE | -1.695 |
Christensen | -1.664 |
apter | -1.605 |
Dou | -1.528 |
Token | nd |
Token ID | 358 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
rush | +1.658 |
okane | +1.391 |
RL | +1.389 |
anyl | +1.387 |
itton | +1.325 |
Neg logit contributions | |
Falk | -1.145 |
IDE | -1.140 |
Christensen | -1.108 |
apter | -1.050 |
ides | -1.002 |
Token | ez |
Token ID | 8471 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
rush | +3.303 |
RL | +2.629 |
okane | +2.619 |
anyl | +2.618 |
itton | +2.449 |
Neg logit contributions | |
Falk | -3.439 |
IDE | -3.438 |
Christensen | -3.378 |
apter | -3.252 |
Dou | -3.094 |
Token | de |
Token ID | 390 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
rush | +2.212 |
RL | +1.889 |
anyl | +1.874 |
okane | +1.870 |
itton | +1.787 |
Neg logit contributions | |
IDE | -1.243 |
Falk | -1.212 |
Christensen | -1.186 |
apter | -1.139 |
ides | -1.065 |
Token | Kir |
Token ID | 7385 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
rush | +4.567 |
RL | +3.748 |
anyl | +3.685 |
okane | +3.525 |
Kap | +3.422 |
Neg logit contributions | |
IDE | -4.998 |
apter | -4.835 |
Christensen | -4.741 |
Falk | -4.699 |
emi | -4.505 |
Token | ch |
Token ID | 354 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
rush | +0.705 |
okane | +0.560 |
RL | +0.560 |
anyl | +0.559 |
itton | +0.529 |
Neg logit contributions | |
IDE | -0.750 |
Falk | -0.749 |
Christensen | -0.731 |
apter | -0.706 |
ides | -0.675 |
Token | ner |
Token ID | 1008 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Falk | +0.489 |
IDE | +0.481 |
Christensen | +0.475 |
apter | +0.456 |
ides | +0.442 |
Neg logit contributions | |
rush | -0.458 |
okane | -0.371 |
RL | -0.369 |
anyl | -0.369 |
itton | -0.346 |
Token | � |
Token ID | 447 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
Falk | +0.116 |
IDE | +0.116 |
Christensen | +0.113 |
apter | +0.108 |
ides | +0.103 |
Neg logit contributions | |
rush | -0.127 |
okane | -0.104 |
RL | -0.104 |
anyl | -0.103 |
itton | -0.098 |
Token | � |
Token ID | 247 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
rush | +0.461 |
okane | +0.366 |
anyl | +0.365 |
RL | +0.362 |
itton | +0.342 |
Neg logit contributions | |
Falk | -0.558 |
IDE | -0.556 |
Christensen | -0.546 |
apter | -0.523 |
ides | -0.508 |
Token | has |
Token ID | 468 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Falk | +0.878 |
IDE | +0.875 |
Christensen | +0.852 |
apter | +0.812 |
ides | +0.777 |
Neg logit contributions | |
rush | -1.086 |
okane | -0.898 |
RL | -0.897 |
anyl | -0.896 |
itton | -0.852 |
Token | been |
Token ID | 587 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
rush | +3.646 |
RL | +2.966 |
anyl | +2.920 |
okane | +2.914 |
itton | +2.768 |
Neg logit contributions | |
Falk | -4.271 |
IDE | -4.222 |
Christensen | -4.163 |
apter | -4.007 |
Hedge | -3.808 |
Token | the |
Token ID | 262 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
rush | +3.886 |
RL | +3.127 |
okane | +3.113 |
anyl | +3.096 |
itton | +2.945 |
Neg logit contributions | |
Falk | -3.983 |
IDE | -3.920 |
Christensen | -3.842 |
apter | -3.698 |
Dou | -3.541 |
Token | greatest |
Token ID | 6000 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
rush | +4.172 |
RL | +3.381 |
okane | +3.358 |
anyl | +3.349 |
itton | +3.241 |
Neg logit contributions | |
IDE | -3.890 |
Falk | -3.870 |
Christensen | -3.819 |
apter | -3.702 |
�士 | -3.515 |
Token | honor |
Token ID | 7522 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
rush | +2.684 |
RL | +2.131 |
anyl | +2.102 |
okane | +2.066 |
itton | +1.985 |
Neg logit contributions | |
Christensen | -3.141 |
Falk | -3.140 |
IDE | -3.101 |
apter | -3.094 |
�士 | -2.934 |
Token | of |
Token ID | 286 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
rush | +3.236 |
RL | +2.613 |
anyl | +2.567 |
okane | +2.567 |
itton | +2.418 |
Neg logit contributions | |
Falk | -3.656 |
IDE | -3.616 |
Christensen | -3.563 |
apter | -3.472 |
ides | -3.258 |
Token | my |
Token ID | 616 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
rush | +5.631 |
RL | +4.848 |
anyl | +4.758 |
decay | +4.611 |
okane | +4.596 |
Neg logit contributions | |
IDE | -3.464 |
Falk | -3.375 |
Christensen | -3.281 |
apter | -3.215 |
�士 | -3.165 |
Token | life |
Token ID | 1204 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
rush | +2.585 |
RL | +2.098 |
anyl | +2.053 |
okane | +1.995 |
itton | +1.890 |
Neg logit contributions | |
IDE | -3.249 |
Falk | -3.237 |
Christensen | -3.180 |
apter | -3.131 |
�士 | -2.958 |
Token | , |
Token ID | 11 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
rush | +1.901 |
RL | +1.527 |
okane | +1.519 |
anyl | +1.513 |
itton | +1.424 |
Neg logit contributions | |
Falk | -2.015 |
IDE | -2.004 |
Christensen | -1.964 |
apter | -1.905 |
Dou | -1.792 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
rush | +0.535 |
RL | +0.437 |
okane | +0.437 |
anyl | +0.436 |
itton | +0.412 |
Neg logit contributions | |
Falk | -0.495 |
IDE | -0.493 |
Christensen | -0.481 |
apter | -0.462 |
ides | -0.441 |
Token | I |
Token ID | 314 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
rush | +1.824 |
RL | +1.527 |
anyl | +1.507 |
okane | +1.504 |
itton | +1.423 |
Neg logit contributions | |
Falk | -1.427 |
IDE | -1.404 |
Christensen | -1.373 |
apter | -1.341 |
Dou | -1.246 |
Token | xx |
Token ID | 5324 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
Falk | +0.511 |
IDE | +0.503 |
Christensen | +0.497 |
apter | +0.458 |
Dou | +0.438 |
Neg logit contributions | |
rush | -0.785 |
anyl | -0.662 |
okane | -0.661 |
RL | -0.650 |
itton | -0.633 |
Token | brand |
Token ID | 17938 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Falk | +0.063 |
IDE | +0.062 |
Christensen | +0.061 |
apter | +0.058 |
ides | +0.055 |
Neg logit contributions | |
rush | -0.076 |
okane | -0.062 |
RL | -0.062 |
anyl | -0.062 |
itton | -0.059 |
Token | ? |
Token ID | 30 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
rush | +0.395 |
RL | +0.322 |
okane | +0.322 |
anyl | +0.319 |
itton | +0.306 |
Neg logit contributions | |
Falk | -0.351 |
IDE | -0.347 |
Christensen | -0.341 |
apter | -0.328 |
Dou | -0.312 |
Token | f |
Token ID | 69 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
rush | +1.566 |
RL | +1.302 |
okane | +1.271 |
anyl | +1.263 |
WARN | +1.189 |
Neg logit contributions | |
IDE | -1.322 |
Falk | -1.312 |
Christensen | -1.299 |
apter | -1.230 |
ides | -1.179 |
Token | ref |
Token ID | 5420 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
rush | +2.084 |
RL | +1.726 |
anyl | +1.691 |
okane | +1.687 |
itton | +1.599 |
Neg logit contributions | |
Falk | -1.937 |
IDE | -1.925 |
Christensen | -1.904 |
apter | -1.800 |
Dou | -1.745 |
Token | = |
Token ID | 28 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
rush | +3.017 |
RL | +2.545 |
okane | +2.477 |
anyl | +2.477 |
itton | +2.346 |
Neg logit contributions | |
IDE | -2.207 |
Falk | -2.197 |
Christensen | -2.145 |
apter | -2.013 |
ides | -1.963 |
Token | ts |
Token ID | 912 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
rush | +3.487 |
RL | +2.608 |
okane | +2.563 |
anyl | +2.488 |
onga | +2.355 |
Neg logit contributions | |
IDE | -5.130 |
Falk | -5.105 |
Christensen | -5.030 |
apter | -4.734 |
Azerbai | -4.670 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
rush | +2.885 |
RL | +2.413 |
okane | +2.370 |
anyl | +2.344 |
itton | +2.243 |
Neg logit contributions | |
Falk | -2.312 |
IDE | -2.292 |
Christensen | -2.260 |
apter | -2.157 |
Dou | -2.063 |
Token | A |
Token ID | 32 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
rush | +1.212 |
anyl | +0.989 |
RL | +0.983 |
okane | +0.979 |
itton | +0.930 |
Neg logit contributions | |
Falk | -1.039 |
Christensen | -1.014 |
IDE | -1.009 |
apter | -0.961 |
ides | -0.913 |
Token | month |
Token ID | 1227 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
Falk | +0.310 |
IDE | +0.309 |
Christensen | +0.302 |
apter | +0.288 |
ides | +0.276 |
Neg logit contributions | |
rush | -0.351 |
okane | -0.288 |
RL | -0.287 |
anyl | -0.287 |
itton | -0.272 |
Token | before |
Token ID | 878 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Falk | +0.440 |
IDE | +0.438 |
Christensen | +0.428 |
apter | +0.409 |
ides | +0.395 |
Neg logit contributions | |
rush | -0.454 |
okane | -0.369 |
RL | -0.368 |
anyl | -0.368 |
itton | -0.348 |
Token | supplied |
Token ID | 14275 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
rush | +0.789 |
okane | +0.643 |
RL | +0.643 |
anyl | +0.640 |
itton | +0.607 |
Neg logit contributions | |
Falk | -0.739 |
IDE | -0.737 |
Christensen | -0.718 |
apter | -0.688 |
ides | -0.660 |
Token | by |
Token ID | 416 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Falk | +0.713 |
IDE | +0.711 |
Christensen | +0.695 |
apter | +0.662 |
ides | +0.643 |
Neg logit contributions | |
rush | -0.712 |
okane | -0.578 |
RL | -0.574 |
anyl | -0.574 |
itton | -0.544 |
Token | the |
Token ID | 262 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
rush | +0.887 |
RL | +0.730 |
okane | +0.727 |
anyl | +0.726 |
itton | +0.689 |
Neg logit contributions | |
IDE | -0.755 |
Falk | -0.753 |
Christensen | -0.731 |
apter | -0.702 |
ides | -0.670 |
Token | Australian |
Token ID | 6638 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Falk | +0.484 |
IDE | +0.480 |
Christensen | +0.471 |
apter | +0.446 |
ides | +0.432 |
Neg logit contributions | |
rush | -0.539 |
okane | -0.443 |
anyl | -0.440 |
RL | -0.439 |
itton | -0.418 |
Token | Communications |
Token ID | 14620 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
rush | +0.214 |
RL | +0.178 |
okane | +0.178 |
anyl | +0.177 |
itton | +0.169 |
Neg logit contributions | |
Falk | -0.159 |
IDE | -0.158 |
Christensen | -0.154 |
apter | -0.146 |
ides | -0.140 |
Token | and |
Token ID | 290 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Falk | +1.701 |
IDE | +1.686 |
Christensen | +1.666 |
apter | +1.556 |
ides | +1.531 |
Neg logit contributions | |
rush | -1.963 |
okane | -1.661 |
anyl | -1.644 |
RL | -1.604 |
itton | -1.566 |
Token | Media |
Token ID | 6343 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
rush | +4.268 |
RL | +3.511 |
okane | +3.448 |
anyl | +3.425 |
itton | +3.207 |
Neg logit contributions | |
IDE | -3.846 |
Falk | -3.827 |
Christensen | -3.745 |
apter | -3.618 |
ides | -3.421 |
Token | Authority |
Token ID | 11416 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
rush | +0.775 |
okane | +0.613 |
anyl | +0.603 |
RL | +0.601 |
itton | +0.561 |
Neg logit contributions | |
Falk | -1.026 |
IDE | -1.022 |
Christensen | -1.005 |
apter | -0.962 |
ides | -0.939 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
Falk | +1.071 |
IDE | +1.066 |
Christensen | +1.039 |
apter | +0.987 |
ides | +0.958 |
Neg logit contributions | |
rush | -1.215 |
okane | -1.005 |
anyl | -1.001 |
RL | -0.992 |
itton | -0.948 |
Token | However |
Token ID | 2102 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
rush | +0.356 |
RL | +0.293 |
okane | +0.292 |
anyl | +0.291 |
itton | +0.277 |
Neg logit contributions | |
Falk | -0.312 |
IDE | -0.311 |
Christensen | -0.303 |
apter | -0.289 |
ides | -0.278 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
rush | +0.870 |
okane | +0.716 |
RL | +0.716 |
anyl | +0.715 |
itton | +0.680 |
Neg logit contributions | |
Falk | -0.743 |
IDE | -0.742 |
Christensen | -0.721 |
apter | -0.690 |
ides | -0.661 |