Token | the |
Token ID | 262 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
� | +0.267 |
upgr | +0.250 |
nodd | +0.220 |
王 | +0.220 |
mathemat | +0.216 |
Neg logit contributions | |
ocry | -0.208 |
sho | -0.201 |
KE | -0.200 |
iple | -0.199 |
enty | -0.195 |
Token | feedback |
Token ID | 7538 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ocry | +0.185 |
sho | +0.180 |
iple | +0.177 |
KE | +0.177 |
enty | +0.173 |
Neg logit contributions | |
� | -0.216 |
upgr | -0.201 |
nodd | -0.177 |
王 | -0.177 |
mathemat | -0.173 |
Token | loop |
Token ID | 9052 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ocry | +0.674 |
iple | +0.655 |
sho | +0.653 |
KE | +0.645 |
enty | +0.622 |
Neg logit contributions | |
� | -1.047 |
upgr | -0.985 |
nodd | -0.869 |
王 | -0.862 |
mathemat | -0.861 |
Token | between |
Token ID | 1022 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ocry | +0.605 |
iple | +0.585 |
sho | +0.583 |
KE | +0.580 |
enty | +0.558 |
Neg logit contributions | |
� | -0.829 |
upgr | -0.788 |
nodd | -0.689 |
王 | -0.688 |
mathemat | -0.683 |
Token | acc |
Token ID | 697 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
� | +1.574 |
upgr | +1.478 |
王 | +1.293 |
nodd | +1.282 |
mathemat | +1.276 |
Neg logit contributions | |
ocry | -1.247 |
sho | -1.195 |
iple | -1.195 |
KE | -1.185 |
enty | -1.149 |
Token | ru |
Token ID | 622 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ocry | +1.068 |
iple | +1.052 |
enty | +0.999 |
cript | +0.993 |
KE | +0.991 |
Neg logit contributions | |
� | -1.170 |
upgr | -1.123 |
nodd | -0.983 |
王 | -0.979 |
mathemat | -0.962 |
Token | al |
Token ID | 282 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
ocry | +4.614 |
iple | +4.218 |
enty | +4.183 |
sho | +4.110 |
ff | +4.016 |
Neg logit contributions | |
� | -6.751 |
upgr | -6.740 |
nodd | -6.189 |
mathemat | -5.988 |
王 | -5.881 |
Token | of |
Token ID | 286 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
ocry | +0.177 |
iple | +0.171 |
sho | +0.168 |
KE | +0.164 |
enty | +0.161 |
Neg logit contributions | |
� | -0.269 |
upgr | -0.257 |
nodd | -0.227 |
王 | -0.227 |
mathemat | -0.226 |
Token | information |
Token ID | 1321 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
� | +0.221 |
upgr | +0.207 |
nodd | +0.184 |
王 | +0.183 |
mathemat | +0.179 |
Neg logit contributions | |
ocry | -0.158 |
sho | -0.154 |
iple | -0.152 |
KE | -0.151 |
enty | -0.144 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ocry | +0.297 |
sho | +0.286 |
iple | +0.281 |
KE | +0.279 |
enty | +0.271 |
Neg logit contributions | |
� | -0.491 |
upgr | -0.460 |
nodd | -0.413 |
王 | -0.409 |
mathemat | -0.404 |
Token | acc |
Token ID | 697 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
sho | +0.623 |
ocry | +0.619 |
KE | +0.593 |
iple | +0.590 |
cript | +0.572 |
Neg logit contributions | |
� | -0.762 |
upgr | -0.684 |
王 | -0.630 |
nodd | -0.629 |
isphere | -0.602 |
Token | xx |
Token ID | 5324 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
ocry | +0.390 |
iple | +0.367 |
enty | +0.358 |
KE | +0.347 |
sho | +0.345 |
Neg logit contributions | |
� | -0.642 |
upgr | -0.631 |
nodd | -0.549 |
mathemat | -0.548 |
王 | -0.543 |
Token | brand |
Token ID | 17938 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
� | +0.437 |
upgr | +0.421 |
mathemat | +0.365 |
nodd | +0.364 |
王 | +0.359 |
Neg logit contributions | |
ocry | -0.312 |
iple | -0.295 |
KE | -0.292 |
sho | -0.290 |
enty | -0.287 |
Token | ? |
Token ID | 30 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
� | +0.295 |
upgr | +0.283 |
mathemat | +0.248 |
nodd | +0.246 |
王 | +0.241 |
Neg logit contributions | |
ocry | -0.219 |
iple | -0.209 |
sho | -0.206 |
KE | -0.206 |
enty | -0.202 |
Token | f |
Token ID | 69 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ocry | +0.381 |
iple | +0.369 |
sho | +0.361 |
KE | +0.359 |
enty | +0.353 |
Neg logit contributions | |
� | -0.407 |
upgr | -0.390 |
mathemat | -0.339 |
nodd | -0.332 |
王 | -0.326 |
Token | ref |
Token ID | 5420 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ocry | +0.088 |
iple | +0.087 |
sho | +0.086 |
KE | +0.085 |
enty | +0.085 |
Neg logit contributions | |
� | -0.058 |
upgr | -0.055 |
mathemat | -0.045 |
nodd | -0.045 |
王 | -0.044 |
Token | = |
Token ID | 28 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
iple | +0.574 |
ocry | +0.572 |
sho | +0.560 |
KE | +0.556 |
enty | +0.552 |
Neg logit contributions | |
� | -0.597 |
upgr | -0.588 |
mathemat | -0.511 |
nodd | -0.497 |
王 | -0.482 |
Token | ts |
Token ID | 912 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
iple | +1.885 |
ocry | +1.844 |
KE | +1.652 |
enty | +1.650 |
sho | +1.583 |
Neg logit contributions | |
� | -8.993 |
upgr | -8.964 |
mathemat | -8.150 |
nodd | -8.082 |
tuning | -7.893 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ocry | +0.860 |
iple | +0.815 |
sho | +0.803 |
KE | +0.802 |
enty | +0.789 |
Neg logit contributions | |
� | -1.218 |
upgr | -1.186 |
nodd | -1.044 |
mathemat | -1.038 |
王 | -1.011 |
Token | A |
Token ID | 32 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
� | +0.992 |
upgr | +0.967 |
nodd | +0.858 |
mathemat | +0.848 |
tuning | +0.802 |
Neg logit contributions | |
ocry | -0.889 |
iple | -0.846 |
KE | -0.820 |
sho | -0.819 |
enty | -0.817 |
Token | month |
Token ID | 1227 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
� | +0.657 |
upgr | +0.627 |
mathemat | +0.536 |
王 | +0.533 |
nodd | +0.533 |
Neg logit contributions | |
ocry | -0.523 |
sho | -0.504 |
iple | -0.504 |
KE | -0.500 |
enty | -0.482 |
Token | before |
Token ID | 878 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
� | +1.151 |
upgr | +1.104 |
mathemat | +0.983 |
王 | +0.967 |
nodd | +0.965 |
Neg logit contributions | |
ocry | -0.674 |
iple | -0.633 |
sho | -0.629 |
KE | -0.621 |
enty | -0.611 |
Token | index |
Token ID | 9630 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
ocry | +1.653 |
KE | +1.598 |
sho | +1.532 |
enty | +1.526 |
iple | +1.522 |
Neg logit contributions | |
� | -2.887 |
upgr | -2.802 |
mathemat | -2.534 |
nodd | -2.493 |
王 | -2.415 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ocry | +1.590 |
iple | +1.470 |
sho | +1.454 |
KE | +1.443 |
enty | +1.422 |
Neg logit contributions | |
� | -2.632 |
upgr | -2.562 |
mathemat | -2.335 |
nodd | -2.324 |
unemploy | -2.220 |
Token | php |
Token ID | 10121 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ocry | +0.921 |
iple | +0.875 |
KE | +0.858 |
sho | +0.853 |
enty | +0.846 |
Neg logit contributions | |
� | -1.093 |
upgr | -1.048 |
mathemat | -0.911 |
nodd | -0.910 |
王 | -0.892 |
Token | ? |
Token ID | 30 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ocry | +1.123 |
sho | +1.062 |
KE | +1.048 |
enty | +1.045 |
iple | +1.042 |
Neg logit contributions | |
� | -1.928 |
upgr | -1.885 |
nodd | -1.721 |
mathemat | -1.718 |
unemploy | -1.634 |
Token | topic |
Token ID | 26652 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ocry | +1.215 |
iple | +1.183 |
sho | +1.167 |
KE | +1.155 |
cript | +1.155 |
Neg logit contributions | |
� | -2.974 |
upgr | -2.906 |
nodd | -2.665 |
mathemat | -2.622 |
unemploy | -2.567 |
Token | = |
Token ID | 28 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ocry | +2.960 |
sho | +2.863 |
enty | +2.818 |
iple | +2.795 |
cript | +2.794 |
Neg logit contributions | |
upgr | -3.428 |
� | -3.292 |
nodd | -3.169 |
mathemat | -3.050 |
unemploy | -2.917 |
Token | 28 |
Token ID | 2078 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ocry | +3.913 |
KE | +3.737 |
sho | +3.665 |
enty | +3.628 |
グ | +3.607 |
Neg logit contributions | |
� | -6.621 |
upgr | -6.580 |
mathemat | -6.163 |
nodd | -6.153 |
unemploy | -5.767 |
Token | 18 |
Token ID | 1507 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ocry | +1.718 |
KE | +1.614 |
sho | +1.599 |
iple | +1.569 |
enty | +1.556 |
Neg logit contributions | |
� | -2.880 |
upgr | -2.809 |
mathemat | -2.566 |
nodd | -2.557 |
unemploy | -2.438 |
Token | 48 |
Token ID | 2780 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ocry | +1.859 |
KE | +1.772 |
sho | +1.719 |
iple | +1.707 |
enty | +1.691 |
Neg logit contributions | |
� | -3.137 |
upgr | -3.041 |
nodd | -2.787 |
mathemat | -2.776 |
unemploy | -2.649 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ocry | +1.773 |
KE | +1.685 |
iple | +1.661 |
sho | +1.626 |
enty | +1.599 |
Neg logit contributions | |
� | -3.158 |
upgr | -3.039 |
nodd | -2.749 |
mathemat | -2.729 |
王 | -2.660 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ocry | +0.493 |
iple | +0.469 |
sho | +0.459 |
KE | +0.458 |
enty | +0.448 |
Neg logit contributions | |
� | -0.730 |
upgr | -0.697 |
nodd | -0.609 |
mathemat | -0.603 |
王 | -0.595 |
Token | _. |
Token ID | 44807 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
� | +1.428 |
upgr | +1.358 |
mathemat | +1.167 |
王 | +1.165 |
nodd | +1.165 |
Neg logit contributions | |
ocry | -1.072 |
iple | -1.009 |
KE | -0.994 |
sho | -0.989 |
enty | -0.971 |
Token | Exception |
Token ID | 16922 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
� | +2.524 |
upgr | +2.292 |
王 | +1.749 |
mathemat | +1.733 |
nodd | +1.719 |
Neg logit contributions | |
ocry | -4.705 |
iple | -4.541 |
KE | -4.500 |
sho | -4.488 |
enty | -4.416 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
� | +0.625 |
upgr | +0.605 |
nodd | +0.542 |
mathemat | +0.540 |
王 | +0.522 |
Neg logit contributions | |
ocry | -0.403 |
iple | -0.378 |
KE | -0.374 |
sho | -0.373 |
enty | -0.365 |
Token | Message |
Token ID | 12837 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
� | +1.209 |
upgr | +1.155 |
nodd | +0.983 |
mathemat | +0.980 |
王 | +0.970 |
Neg logit contributions | |
ocry | -1.107 |
iple | -1.050 |
KE | -1.036 |
sho | -1.030 |
enty | -1.013 |
Token | )" |
Token ID | 16725 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
ocry | +2.186 |
iple | +2.058 |
KE | +2.039 |
sho | +2.035 |
enty | +2.008 |
Neg logit contributions | |
� | -2.519 |
upgr | -2.418 |
nodd | -2.066 |
mathemat | -2.058 |
王 | -2.049 |
Token | break |
Token ID | 2270 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ocry | +2.967 |
sho | +2.854 |
KE | +2.774 |
ff | +2.755 |
Blu | +2.751 |
Neg logit contributions | |
� | -4.280 |
upgr | -4.044 |
nodd | -3.886 |
mathemat | -3.849 |
王 | -3.694 |
Token | } |
Token ID | 1782 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
sho | +2.354 |
ocry | +2.335 |
KE | +2.309 |
FF | +2.237 |
ff | +2.202 |
Neg logit contributions | |
� | -8.031 |
upgr | -7.690 |
nodd | -7.576 |
mathemat | -7.495 |
王 | -7.151 |
Token | } |
Token ID | 1782 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ocry | +2.114 |
sho | +2.040 |
KE | +1.985 |
iple | +1.935 |
NET | +1.888 |
Neg logit contributions | |
� | -6.054 |
upgr | -5.726 |
王 | -5.305 |
nodd | -5.264 |
mathemat | -5.234 |
Token | End |
Token ID | 5268 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ocry | +1.431 |
sho | +1.401 |
KE | +1.377 |
iple | +1.335 |
NET | +1.319 |
Neg logit contributions | |
� | -2.970 |
upgr | -2.785 |
nodd | -2.571 |
王 | -2.560 |
mathemat | -2.538 |
Token | { |
Token ID | 1391 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ocry | +1.338 |
iple | +1.259 |
KE | +1.258 |
sho | +1.251 |
cript | +1.234 |
Neg logit contributions | |
� | -1.951 |
upgr | -1.857 |
mathemat | -1.681 |
王 | -1.659 |
nodd | -1.650 |
Token | Try |
Token ID | 9993 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ocry | +1.735 |
sho | +1.692 |
KE | +1.669 |
iple | +1.632 |
NET | +1.601 |
Neg logit contributions | |
� | -3.375 |
upgr | -3.166 |
王 | -2.896 |
nodd | -2.885 |
mathemat | -2.872 |
Token | Home |
Token ID | 16060 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ocry | +1.032 |
iple | +0.948 |
sho | +0.922 |
enty | +0.904 |
KE | +0.893 |
Neg logit contributions | |
� | -1.969 |
upgr | -1.927 |
mathemat | -1.730 |
nodd | -1.718 |
王 | -1.690 |
Token | page |
Token ID | 7700 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ocry | +1.135 |
iple | +1.089 |
sho | +1.067 |
KE | +1.051 |
enty | +1.047 |
Neg logit contributions | |
� | -1.118 |
upgr | -1.083 |
nodd | -0.981 |
mathemat | -0.976 |
王 | -0.907 |
Token | ] |
Token ID | 60 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ocry | +2.967 |
KE | +2.794 |
sho | +2.793 |
iple | +2.710 |
enty | +2.704 |
Neg logit contributions | |
� | -4.872 |
upgr | -4.806 |
nodd | -4.687 |
mathemat | -4.644 |
unemploy | -4.219 |
Token | [ |
Token ID | 685 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
� | +0.211 |
upgr | +0.200 |
王 | +0.168 |
mathemat | +0.168 |
nodd | +0.167 |
Neg logit contributions | |
ocry | -0.216 |
iple | -0.205 |
KE | -0.203 |
sho | -0.203 |
enty | -0.199 |
Token | App |
Token ID | 4677 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ocry | +1.775 |
iple | +1.681 |
sho | +1.648 |
enty | +1.623 |
KE | +1.609 |
Neg logit contributions | |
� | -1.742 |
upgr | -1.681 |
mathemat | -1.460 |
nodd | -1.450 |
王 | -1.413 |
Token | Brain |
Token ID | 44687 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ocry | +1.965 |
iple | +1.821 |
sho | +1.779 |
cript | +1.778 |
グ | +1.766 |
Neg logit contributions | |
� | -1.922 |
upgr | -1.918 |
nodd | -1.807 |
mathemat | -1.796 |
tuning | -1.595 |
Token | ] |
Token ID | 60 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ocry | +3.598 |
KE | +3.354 |
sho | +3.343 |
Blu | +3.256 |
FF | +3.246 |
Neg logit contributions | |
nodd | -6.543 |
mathemat | -6.500 |
upgr | -6.495 |
� | -6.402 |
unemploy | -5.822 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ocry | +0.863 |
iple | +0.815 |
KE | +0.805 |
sho | +0.804 |
enty | +0.788 |
Neg logit contributions | |
� | -1.058 |
upgr | -1.005 |
王 | -0.866 |
mathemat | -0.864 |
nodd | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ocry | +0.795 |
sho | +0.751 |
KE | +0.750 |
iple | +0.741 |
enty | +0.729 |
Neg logit contributions | |
� | -1.046 |
upgr | -1.029 |
nodd | -0.950 |
mathemat | -0.950 |
unemploy | -0.870 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ocry | +0.630 |
iple | +0.597 |
sho | +0.583 |
enty | +0.579 |
KE | +0.577 |
Neg logit contributions | |
� | -0.757 |
upgr | -0.736 |
mathemat | -0.663 |
nodd | -0.663 |
tuning | -0.625 |
Token | D |
Token ID | 35 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
� | +0.789 |
upgr | +0.750 |
mathemat | +0.659 |
nodd | +0.655 |
王 | +0.650 |
Neg logit contributions | |
ocry | -0.531 |
iple | -0.504 |
KE | -0.495 |
sho | -0.491 |
enty | -0.484 |
Token | Share |
Token ID | 8734 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
ocry | +0.205 |
iple | +0.190 |
KE | +0.185 |
sho | +0.183 |
enty | +0.178 |
Neg logit contributions | |
� | -0.483 |
upgr | -0.464 |
nodd | -0.414 |
mathemat | -0.414 |
王 | -0.410 |
Token | this |
Token ID | 428 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
ocry | +0.519 |
iple | +0.493 |
KE | +0.490 |
sho | +0.487 |
enty | +0.480 |
Neg logit contributions | |
� | -0.510 |
upgr | -0.487 |
nodd | -0.422 |
mathemat | -0.418 |
王 | -0.401 |
Token | story |
Token ID | 1621 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ocry | +0.322 |
iple | +0.302 |
KE | +0.297 |
sho | +0.297 |
enty | +0.289 |
Neg logit contributions | |
� | -0.500 |
upgr | -0.476 |
nodd | -0.418 |
mathemat | -0.418 |
王 | -0.412 |
Token | : |
Token ID | 25 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ocry | +0.489 |
iple | +0.462 |
KE | +0.457 |
sho | +0.457 |
enty | +0.448 |
Neg logit contributions | |
� | -0.584 |
upgr | -0.561 |
mathemat | -0.493 |
nodd | -0.491 |
王 | -0.471 |
Token | http |
Token ID | 2638 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ocry | +0.176 |
sho | +0.171 |
KE | +0.171 |
iple | +0.170 |
enty | +0.167 |
Neg logit contributions | |
� | -0.155 |
upgr | -0.146 |
mathemat | -0.122 |
nodd | -0.119 |
王 | -0.118 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
ocry | +2.026 |
KE | +1.887 |
sho | +1.880 |
iple | +1.877 |
enty | +1.859 |
Neg logit contributions | |
upgr | -2.396 |
� | -2.384 |
nodd | -2.173 |
mathemat | -2.162 |
unemploy | -2.002 |
Token | usat |
Token ID | 37937 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ocry | +4.500 |
cript | +4.464 |
enty | +4.450 |
sho | +4.309 |
iple | +4.274 |
Neg logit contributions | |
� | -5.052 |
upgr | -5.023 |
mathemat | -4.183 |
nodd | -4.094 |
tuning | -3.982 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ocry | +2.327 |
KE | +2.165 |
iple | +2.165 |
sho | +2.161 |
cript | +2.112 |
Neg logit contributions | |
upgr | -4.228 |
� | -4.202 |
mathemat | -3.986 |
nodd | -3.983 |
unemploy | -3.700 |
Token | ly |
Token ID | 306 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ocry | +1.491 |
iple | +1.407 |
sho | +1.373 |
KE | +1.367 |
enty | +1.343 |
Neg logit contributions | |
� | -2.376 |
upgr | -2.273 |
nodd | -2.033 |
mathemat | -2.030 |
王 | -1.975 |
Token | / |
Token ID | 14 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
� | +0.403 |
upgr | +0.393 |
nodd | +0.349 |
mathemat | +0.348 |
王 | +0.327 |
Neg logit contributions | |
ocry | -0.355 |
iple | -0.335 |
KE | -0.334 |
sho | -0.333 |
enty | -0.326 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ocry | +3.318 |
KE | +3.162 |
cript | +3.148 |
enty | +3.137 |
iple | +3.118 |
Neg logit contributions | |
� | -3.606 |
upgr | -3.597 |
nodd | -3.268 |
mathemat | -3.211 |
unemploy | -2.970 |
Token | beneficiary |
Token ID | 33867 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
ocry | +0.270 |
sho | +0.265 |
iple | +0.257 |
KE | +0.256 |
enty | +0.247 |
Neg logit contributions | |
� | -0.367 |
upgr | -0.346 |
nodd | -0.300 |
mathemat | -0.300 |
王 | -0.299 |
Token | of |
Token ID | 286 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
ocry | +0.371 |
iple | +0.348 |
sho | +0.343 |
KE | +0.343 |
enty | +0.335 |
Neg logit contributions | |
� | -0.554 |
upgr | -0.529 |
mathemat | -0.458 |
nodd | -0.458 |
王 | -0.456 |
Token | another |
Token ID | 1194 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
� | +0.349 |
upgr | +0.328 |
王 | +0.284 |
mathemat | +0.284 |
nodd | +0.283 |
Neg logit contributions | |
ocry | -0.267 |
iple | -0.253 |
KE | -0.253 |
sho | -0.253 |
enty | -0.245 |
Token | trust |
Token ID | 3774 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
ocry | +1.166 |
sho | +1.137 |
iple | +1.124 |
KE | +1.122 |
FF | +1.078 |
Neg logit contributions | |
� | -1.438 |
upgr | -1.328 |
王 | -1.170 |
mathemat | -1.169 |
nodd | -1.154 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
� | +0.289 |
upgr | +0.273 |
mathemat | +0.241 |
nodd | +0.241 |
王 | +0.240 |
Neg logit contributions | |
ocry | -0.185 |
sho | -0.176 |
KE | -0.174 |
iple | -0.171 |
enty | -0.166 |
Token | called |
Token ID | 1444 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ocry | +1.776 |
KE | +1.726 |
sho | +1.709 |
iple | +1.681 |
FF | +1.647 |
Neg logit contributions | |
� | -2.492 |
upgr | -2.322 |
mathemat | -2.048 |
王 | -2.036 |
nodd | -2.035 |
Token | the |
Token ID | 262 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
ocry | +4.032 |
KE | +4.008 |
sho | +3.919 |
FF | +3.901 |
iple | +3.809 |
Neg logit contributions | |
� | -5.388 |
upgr | -5.045 |
mathemat | -4.485 |
isphere | -4.478 |
王 | -4.433 |
Token | Mor |
Token ID | 3461 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ocry | +2.286 |
KE | +2.230 |
sho | +2.210 |
iple | +2.167 |
FF | +2.140 |
Neg logit contributions | |
� | -3.042 |
upgr | -2.865 |
mathemat | -2.513 |
nodd | -2.508 |
王 | -2.504 |
Token | neau |
Token ID | 46533 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ocry | +0.412 |
iple | +0.386 |
sho | +0.362 |
KE | +0.361 |
enty | +0.357 |
Neg logit contributions | |
� | -0.814 |
upgr | -0.788 |
mathemat | -0.703 |
nodd | -0.700 |
王 | -0.698 |
Token | McCain |
Token ID | 14264 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
� | +0.964 |
upgr | +0.914 |
mathemat | +0.800 |
nodd | +0.793 |
王 | +0.787 |
Neg logit contributions | |
ocry | -0.690 |
iple | -0.647 |
KE | -0.646 |
sho | -0.645 |
enty | -0.623 |
Token | Family |
Token ID | 7884 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
ocry | +1.055 |
KE | +0.993 |
iple | +0.990 |
sho | +0.987 |
FF | +0.952 |
Neg logit contributions | |
� | -1.408 |
upgr | -1.336 |
mathemat | -1.192 |
nodd | -1.182 |
王 | -1.160 |
Token | veterans |
Token ID | 11255 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
ocry | +0.111 |
iple | +0.105 |
sho | +0.105 |
KE | +0.104 |
enty | +0.102 |
Neg logit contributions | |
� | -0.145 |
upgr | -0.136 |
mathemat | -0.120 |
nodd | -0.119 |
王 | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
ocry | +0.397 |
sho | +0.376 |
iple | +0.374 |
KE | +0.371 |
enty | +0.368 |
Neg logit contributions | |
� | -0.469 |
upgr | -0.454 |
mathemat | -0.399 |
nodd | -0.394 |
王 | -0.387 |
Token | female |
Token ID | 4048 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
� | +0.385 |
upgr | +0.359 |
王 | +0.320 |
mathemat | +0.317 |
nodd | +0.317 |
Neg logit contributions | |
ocry | -0.307 |
sho | -0.293 |
KE | -0.293 |
iple | -0.288 |
enty | -0.279 |
Token | reporters |
Token ID | 7638 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
� | +1.195 |
upgr | +1.127 |
王 | +0.976 |
mathemat | +0.974 |
nodd | +0.973 |
Neg logit contributions | |
ocry | -0.929 |
iple | -0.877 |
sho | -0.872 |
KE | -0.871 |
enty | -0.852 |
Token | ). |
Token ID | 737 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ocry | +0.151 |
sho | +0.144 |
KE | +0.143 |
iple | +0.143 |
enty | +0.142 |
Neg logit contributions | |
� | -0.153 |
upgr | -0.148 |
mathemat | -0.127 |
nodd | -0.125 |
王 | -0.123 |
Token | Asked |
Token ID | 26220 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
ocry | +0.881 |
KE | +0.854 |
enty | +0.820 |
sho | +0.816 |
グ | +0.797 |
Neg logit contributions | |
upgr | -1.184 |
� | -1.178 |
mathemat | -1.075 |
nodd | -1.073 |
isphere | -1.011 |
Token | about |
Token ID | 546 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ocry | +3.007 |
sho | +2.962 |
KE | +2.879 |
iple | +2.826 |
enty | +2.743 |
Neg logit contributions | |
� | -6.283 |
upgr | -6.014 |
mathemat | -5.506 |
nodd | -5.445 |
王 | -5.318 |
Token | sexual |
Token ID | 3206 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ocry | +0.089 |
KE | +0.085 |
sho | +0.085 |
iple | +0.083 |
enty | +0.082 |
Neg logit contributions | |
� | -0.109 |
upgr | -0.102 |
nodd | -0.090 |
mathemat | -0.090 |
王 | -0.088 |
Token | harassment |
Token ID | 10556 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ocry | +0.609 |
sho | +0.588 |
iple | +0.583 |
KE | +0.580 |
enty | +0.567 |
Neg logit contributions | |
� | -0.670 |
upgr | -0.616 |
mathemat | -0.553 |
nodd | -0.547 |
王 | -0.533 |
Token | in |
Token ID | 287 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ocry | +0.967 |
sho | +0.903 |
iple | +0.897 |
KE | +0.890 |
enty | +0.885 |
Neg logit contributions | |
� | -1.547 |
upgr | -1.487 |
nodd | -1.316 |
mathemat | -1.311 |
王 | -1.288 |
Token | increasingly |
Token ID | 6481 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ocry | +1.520 |
KE | +1.465 |
iple | +1.450 |
sho | +1.425 |
enty | +1.405 |
Neg logit contributions | |
� | -1.837 |
upgr | -1.736 |
mathemat | -1.526 |
nodd | -1.509 |
王 | -1.507 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
ocry | +0.203 |
sho | +0.186 |
iple | +0.185 |
KE | +0.184 |
cript | +0.178 |
Neg logit contributions | |
� | -0.461 |
upgr | -0.443 |
nodd | -0.397 |
王 | -0.393 |
mathemat | -0.393 |
Token | this |
Token ID | 428 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
� | +0.006 |
upgr | +0.006 |
nodd | +0.005 |
mathemat | +0.005 |
王 | +0.005 |
Neg logit contributions | |
ocry | -0.006 |
KE | -0.005 |
iple | -0.005 |
sho | -0.005 |
enty | -0.005 |
Token | story |
Token ID | 1621 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
� | +0.017 |
upgr | +0.016 |
mathemat | +0.014 |
nodd | +0.014 |
王 | +0.014 |
Neg logit contributions | |
ocry | -0.011 |
iple | -0.011 |
KE | -0.010 |
sho | -0.010 |
enty | -0.010 |
Token | : |
Token ID | 25 |
Feature activation | -2.60e-03 |
Pos logit contributions | |
ocry | +0.059 |
iple | +0.056 |
KE | +0.055 |
sho | +0.055 |
enty | +0.054 |
Neg logit contributions | |
� | -0.066 |
upgr | -0.063 |
mathemat | -0.054 |
nodd | -0.053 |
王 | -0.053 |
Token | http |
Token ID | 2638 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
� | +0.012 |
upgr | +0.012 |
mathemat | +0.010 |
王 | +0.010 |
nodd | +0.009 |
Neg logit contributions | |
ocry | -0.015 |
KE | -0.014 |
sho | -0.014 |
iple | -0.014 |
enty | -0.014 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
ocry | +2.150 |
KE | +2.017 |
sho | +2.009 |
iple | +1.983 |
enty | +1.978 |
Neg logit contributions | |
upgr | -2.554 |
� | -2.541 |
mathemat | -2.321 |
nodd | -2.319 |
unemploy | -2.130 |
Token | on |
Token ID | 261 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ocry | +4.654 |
enty | +4.499 |
cript | +4.473 |
sho | +4.399 |
KE | +4.388 |
Neg logit contributions | |
� | -4.864 |
upgr | -4.800 |
mathemat | -4.048 |
nodd | -3.965 |
tuning | -3.925 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ocry | +0.967 |
iple | +0.898 |
sho | +0.887 |
KE | +0.876 |
enty | +0.871 |
Neg logit contributions | |
� | -1.517 |
upgr | -1.473 |
mathemat | -1.335 |
nodd | -1.324 |
王 | -1.277 |
Token | c |
Token ID | 66 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
� | +1.678 |
upgr | +1.618 |
nodd | +1.405 |
mathemat | +1.400 |
王 | +1.380 |
Neg logit contributions | |
ocry | -1.207 |
iple | -1.138 |
sho | -1.128 |
KE | -1.123 |
enty | -1.098 |
Token | ps |
Token ID | 862 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
� | +0.091 |
upgr | +0.087 |
nodd | +0.075 |
mathemat | +0.075 |
王 | +0.074 |
Neg logit contributions | |
ocry | -0.074 |
iple | -0.070 |
KE | -0.069 |
sho | -0.069 |
enty | -0.067 |
Token | j |
Token ID | 73 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ocry | +0.363 |
iple | +0.332 |
sho | +0.324 |
KE | +0.323 |
enty | +0.315 |
Neg logit contributions | |
� | -0.874 |
upgr | -0.839 |
mathemat | -0.747 |
nodd | -0.747 |
王 | -0.745 |
Token | Share |
Token ID | 8734 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ocry | +0.039 |
iple | +0.036 |
KE | +0.035 |
sho | +0.035 |
enty | +0.034 |
Neg logit contributions | |
� | -0.092 |
upgr | -0.088 |
nodd | -0.079 |
mathemat | -0.079 |
王 | -0.078 |
Token | this |
Token ID | 428 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
ocry | +0.188 |
iple | +0.178 |
KE | +0.177 |
sho | +0.176 |
enty | +0.173 |
Neg logit contributions | |
� | -0.189 |
upgr | -0.181 |
nodd | -0.159 |
mathemat | -0.157 |
王 | -0.150 |
Token | story |
Token ID | 1621 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ocry | +0.339 |
iple | +0.318 |
KE | +0.314 |
sho | +0.313 |
enty | +0.304 |
Neg logit contributions | |
� | -0.528 |
upgr | -0.503 |
nodd | -0.442 |
mathemat | -0.442 |
王 | -0.436 |
Token | : |
Token ID | 25 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ocry | +0.578 |
iple | +0.546 |
KE | +0.540 |
sho | +0.540 |
enty | +0.528 |
Neg logit contributions | |
� | -0.694 |
upgr | -0.668 |
mathemat | -0.589 |
nodd | -0.587 |
王 | -0.562 |
Token | http |
Token ID | 2638 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ocry | +0.074 |
KE | +0.073 |
sho | +0.071 |
iple | +0.071 |
enty | +0.069 |
Neg logit contributions | |
� | -0.072 |
upgr | -0.068 |
mathemat | -0.058 |
nodd | -0.056 |
王 | -0.056 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ocry | +2.000 |
KE | +1.863 |
iple | +1.855 |
sho | +1.855 |
enty | +1.833 |
Neg logit contributions | |
upgr | -2.381 |
� | -2.370 |
nodd | -2.169 |
mathemat | -2.163 |
unemploy | -1.994 |
Token | cin |
Token ID | 17879 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ocry | +3.218 |
enty | +3.131 |
cript | +3.082 |
iple | +3.024 |
KE | +3.021 |
Neg logit contributions | |
� | -6.169 |
upgr | -6.138 |
mathemat | -5.401 |
nodd | -5.349 |
tuning | -5.204 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ocry | +2.002 |
enty | +1.808 |
iple | +1.790 |
sho | +1.786 |
KE | +1.771 |
Neg logit contributions | |
� | -3.355 |
upgr | -3.274 |
mathemat | -3.010 |
nodd | -2.951 |
王 | -2.916 |
Token | ci |
Token ID | 979 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
� | +1.195 |
upgr | +1.136 |
王 | +0.978 |
mathemat | +0.969 |
nodd | +0.967 |
Neg logit contributions | |
ocry | -0.828 |
iple | -0.776 |
KE | -0.762 |
sho | -0.757 |
enty | -0.748 |
Token | / |
Token ID | 14 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ocry | +0.031 |
iple | +0.029 |
sho | +0.028 |
KE | +0.028 |
enty | +0.028 |
Neg logit contributions | |
� | -0.037 |
upgr | -0.036 |
nodd | -0.033 |
mathemat | -0.032 |
王 | -0.031 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
ocry | +3.748 |
cript | +3.557 |
enty | +3.550 |
iple | +3.547 |
KE | +3.540 |
Neg logit contributions | |
� | -4.339 |
upgr | -4.207 |
nodd | -3.872 |
mathemat | -3.818 |
unemploy | -3.525 |
Token | Share |
Token ID | 8734 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
� | +0.125 |
upgr | +0.120 |
nodd | +0.108 |
mathemat | +0.108 |
王 | +0.107 |
Neg logit contributions | |
ocry | -0.052 |
iple | -0.048 |
KE | -0.047 |
sho | -0.047 |
enty | -0.046 |
Token | this |
Token ID | 428 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
ocry | +0.187 |
iple | +0.178 |
KE | +0.176 |
sho | +0.175 |
enty | +0.172 |
Neg logit contributions | |
� | -0.181 |
upgr | -0.173 |
nodd | -0.149 |
mathemat | -0.148 |
王 | -0.143 |
Token | story |
Token ID | 1621 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ocry | +0.120 |
iple | +0.113 |
KE | +0.111 |
sho | +0.111 |
enty | +0.108 |
Neg logit contributions | |
� | -0.183 |
upgr | -0.175 |
nodd | -0.153 |
mathemat | -0.153 |
王 | -0.151 |
Token | : |
Token ID | 25 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ocry | +0.168 |
iple | +0.159 |
KE | +0.157 |
sho | +0.157 |
enty | +0.154 |
Neg logit contributions | |
� | -0.198 |
upgr | -0.190 |
mathemat | -0.166 |
nodd | -0.165 |
王 | -0.160 |
Token | http |
Token ID | 2638 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
ocry | +0.142 |
KE | +0.138 |
sho | +0.138 |
iple | +0.136 |
enty | +0.134 |
Neg logit contributions | |
� | -0.123 |
upgr | -0.116 |
mathemat | -0.097 |
王 | -0.095 |
nodd | -0.094 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
ocry | +2.126 |
KE | +1.987 |
sho | +1.978 |
iple | +1.965 |
enty | +1.957 |
Neg logit contributions | |
upgr | -2.596 |
� | -2.568 |
nodd | -2.381 |
mathemat | -2.372 |
unemploy | -2.184 |
Token | usat |
Token ID | 37937 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ocry | +4.583 |
cript | +4.548 |
enty | +4.543 |
sho | +4.409 |
iple | +4.391 |
Neg logit contributions | |
upgr | -4.766 |
� | -4.763 |
mathemat | -3.993 |
nodd | -3.895 |
王 | -3.831 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ocry | +2.446 |
iple | +2.276 |
KE | +2.270 |
sho | +2.268 |
cript | +2.224 |
Neg logit contributions | |
upgr | -4.568 |
� | -4.516 |
mathemat | -4.343 |
nodd | -4.331 |
unemploy | -4.014 |
Token | ly |
Token ID | 306 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ocry | +1.463 |
iple | +1.383 |
sho | +1.348 |
KE | +1.342 |
enty | +1.317 |
Neg logit contributions | |
� | -2.336 |
upgr | -2.240 |
nodd | -2.008 |
mathemat | -2.006 |
王 | -1.946 |
Token | / |
Token ID | 14 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
� | +0.555 |
upgr | +0.541 |
nodd | +0.479 |
mathemat | +0.478 |
王 | +0.450 |
Neg logit contributions | |
ocry | -0.493 |
iple | -0.466 |
KE | -0.463 |
sho | -0.462 |
enty | -0.453 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocry | +3.416 |
cript | +3.258 |
iple | +3.229 |
enty | +3.226 |
KE | +3.226 |
Neg logit contributions | |
� | -3.703 |
upgr | -3.694 |
nodd | -3.340 |
mathemat | -3.271 |
unemploy | -3.041 |
Token | from |
Token ID | 422 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ocry | +1.143 |
iple | +1.108 |
KE | +1.098 |
sho | +1.096 |
cript | +1.050 |
Neg logit contributions | |
� | -1.941 |
upgr | -1.836 |
nodd | -1.650 |
mathemat | -1.638 |
王 | -1.618 |
Token | this |
Token ID | 428 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
ocry | +0.651 |
KE | +0.634 |
iple | +0.623 |
sho | +0.620 |
FF | +0.599 |
Neg logit contributions | |
� | -0.963 |
upgr | -0.904 |
nodd | -0.803 |
mathemat | -0.795 |
王 | -0.791 |
Token | year |
Token ID | 614 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
ocry | +0.376 |
iple | +0.362 |
sho | +0.361 |
KE | +0.359 |
arij | +0.340 |
Neg logit contributions | |
� | -0.531 |
upgr | -0.496 |
nodd | -0.441 |
mathemat | -0.438 |
王 | -0.435 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ocry | +0.238 |
iple | +0.228 |
sho | +0.224 |
KE | +0.223 |
cript | +0.217 |
Neg logit contributions | |
� | -0.388 |
upgr | -0.373 |
mathemat | -0.332 |
nodd | -0.332 |
王 | -0.326 |
Token | also |
Token ID | 635 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
ocry | +0.555 |
KE | +0.536 |
iple | +0.533 |
sho | +0.528 |
cript | +0.511 |
Neg logit contributions | |
� | -0.805 |
upgr | -0.762 |
nodd | -0.678 |
mathemat | -0.672 |
王 | -0.664 |
Token | related |
Token ID | 3519 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ocry | +2.375 |
KE | +2.322 |
sho | +2.312 |
iple | +2.261 |
cript | +2.168 |
Neg logit contributions | |
� | -3.757 |
upgr | -3.463 |
王 | -3.116 |
nodd | -3.102 |
mathemat | -3.095 |
Token | to |
Token ID | 284 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
ocry | +3.708 |
sho | +3.323 |
KE | +3.312 |
iple | +3.304 |
enty | +3.235 |
Neg logit contributions | |
� | -5.780 |
upgr | -5.486 |
王 | -4.764 |
nodd | -4.760 |
mathemat | -4.720 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ocry | +2.189 |
KE | +2.135 |
sho | +2.119 |
iple | +2.087 |
FF | +2.041 |
Neg logit contributions | |
� | -2.849 |
upgr | -2.627 |
王 | -2.338 |
nodd | -2.316 |
mathemat | -2.259 |
Token | chamber |
Token ID | 11847 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ocry | +1.282 |
KE | +1.247 |
sho | +1.247 |
iple | +1.227 |
FF | +1.182 |
Neg logit contributions | |
� | -1.551 |
upgr | -1.424 |
nodd | -1.264 |
王 | -1.258 |
mathemat | -1.233 |
Token | � |
Token ID | 447 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
ocry | +1.292 |
iple | +1.253 |
sho | +1.230 |
KE | +1.226 |
enty | +1.181 |
Neg logit contributions | |
� | -1.481 |
upgr | -1.406 |
nodd | -1.223 |
mathemat | -1.221 |
王 | -1.212 |
Token | � |
Token ID | 247 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ocry | +0.025 |
iple | +0.022 |
KE | +0.022 |
sho | +0.022 |
enty | +0.021 |
Neg logit contributions | |
� | -0.077 |
upgr | -0.075 |
mathemat | -0.068 |
nodd | -0.067 |
王 | -0.066 |
Token | cell |
Token ID | 2685 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
� | +0.659 |
upgr | +0.621 |
王 | +0.549 |
mathemat | +0.543 |
nodd | +0.542 |
Neg logit contributions | |
ocry | -0.458 |
KE | -0.430 |
sho | -0.427 |
iple | -0.426 |
enty | -0.411 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
� | +0.965 |
upgr | +0.912 |
王 | +0.798 |
mathemat | +0.795 |
nodd | +0.791 |
Neg logit contributions | |
ocry | -0.670 |
iple | -0.632 |
KE | -0.628 |
sho | -0.623 |
enty | -0.605 |
Token | as |
Token ID | 355 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
ocry | +0.466 |
sho | +0.450 |
KE | +0.450 |
iple | +0.447 |
enty | +0.428 |
Neg logit contributions | |
� | -0.690 |
upgr | -0.645 |
王 | -0.573 |
nodd | -0.568 |
mathemat | -0.558 |
Token | shown |
Token ID | 3402 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
� | +0.396 |
upgr | +0.369 |
王 | +0.328 |
nodd | +0.323 |
mathemat | +0.317 |
Neg logit contributions | |
ocry | -0.276 |
KE | -0.267 |
sho | -0.262 |
iple | -0.261 |
cript | -0.251 |
Token | in |
Token ID | 287 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ocry | +2.221 |
sho | +2.169 |
KE | +2.154 |
iple | +2.076 |
cript | +2.056 |
Neg logit contributions | |
� | -3.681 |
upgr | -3.484 |
nodd | -3.080 |
王 | -3.069 |
mathemat | -3.065 |
Token | Figure |
Token ID | 11291 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ocry | +0.536 |
KE | +0.517 |
iple | +0.505 |
sho | +0.502 |
ff | +0.478 |
Neg logit contributions | |
� | -0.895 |
upgr | -0.865 |
王 | -0.755 |
nodd | -0.748 |
mathemat | -0.744 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ocry | +3.827 |
KE | +3.742 |
sho | +3.732 |
iple | +3.709 |
ff | +3.600 |
Neg logit contributions | |
� | -5.367 |
upgr | -5.114 |
mathemat | -4.557 |
nodd | -4.553 |
王 | -4.522 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ocry | +1.287 |
KE | +1.201 |
iple | +1.197 |
sho | +1.184 |
ff | +1.146 |
Neg logit contributions | |
� | -2.156 |
upgr | -2.070 |
mathemat | -1.826 |
nodd | -1.825 |
王 | -1.784 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ocry | +0.713 |
KE | +0.695 |
sho | +0.674 |
iple | +0.672 |
Blu | +0.655 |
Neg logit contributions | |
� | -0.948 |
upgr | -0.913 |
nodd | -0.814 |
mathemat | -0.806 |
王 | -0.779 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ocry | +0.651 |
KE | +0.616 |
sho | +0.614 |
iple | +0.609 |
enty | +0.593 |
Neg logit contributions | |
� | -0.860 |
upgr | -0.844 |
nodd | -0.778 |
mathemat | -0.778 |
unemploy | -0.713 |
Token | Figure |
Token ID | 11337 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ocry | +0.581 |
iple | +0.560 |
KE | +0.532 |
sho | +0.530 |
cript | +0.529 |
Neg logit contributions | |
� | -0.754 |
upgr | -0.735 |
nodd | -0.655 |
mathemat | -0.645 |
tuning | -0.610 |
Token | = |
Token ID | 28 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
� | +2.341 |
upgr | +2.172 |
王 | +1.781 |
mathemat | +1.738 |
nodd | +1.729 |
Neg logit contributions | |
ocry | -2.895 |
iple | -2.758 |
KE | -2.717 |
sho | -2.713 |
enty | -2.677 |
Token | 20 |
Token ID | 1238 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ocry | +1.246 |
KE | +1.124 |
enty | +1.122 |
iple | +1.117 |
sho | +1.077 |
Neg logit contributions | |
� | -3.264 |
upgr | -3.167 |
nodd | -2.910 |
mathemat | -2.905 |
王 | -2.794 |
Token | dB |
Token ID | 30221 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
ocry | +0.894 |
KE | +0.862 |
iple | +0.827 |
sho | +0.804 |
ff | +0.799 |
Neg logit contributions | |
� | -2.757 |
upgr | -2.662 |
nodd | -2.488 |
mathemat | -2.470 |
王 | -2.407 |
Token | m |
Token ID | 76 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
� | +0.373 |
upgr | +0.358 |
nodd | +0.314 |
mathemat | +0.313 |
王 | +0.302 |
Neg logit contributions | |
ocry | -0.334 |
iple | -0.319 |
sho | -0.313 |
KE | -0.312 |
enty | -0.308 |
Token | Ret |
Token ID | 4990 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
� | +0.171 |
upgr | +0.164 |
mathemat | +0.148 |
nodd | +0.148 |
王 | +0.148 |
Neg logit contributions | |
ocry | -0.076 |
iple | -0.070 |
KE | -0.070 |
sho | -0.069 |
enty | -0.067 |
Token | ry |
Token ID | 563 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
ocry | +1.136 |
iple | +1.059 |
enty | +1.020 |
sho | +1.012 |
KE | +1.009 |
Neg logit contributions | |
� | -1.860 |
upgr | -1.800 |
mathemat | -1.640 |
nodd | -1.636 |
王 | -1.605 |
Token | short |
Token ID | 1790 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ocry | +2.649 |
sho | +2.548 |
KE | +2.522 |
iple | +2.455 |
FF | +2.430 |
Neg logit contributions | |
� | -6.439 |
upgr | -6.204 |
mathemat | -5.639 |
isphere | -5.631 |
王 | -5.616 |
Token | limit |
Token ID | 4179 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ocry | +0.086 |
iple | +0.082 |
KE | +0.082 |
sho | +0.081 |
enty | +0.079 |
Neg logit contributions | |
� | -0.126 |
upgr | -0.122 |
mathemat | -0.110 |
nodd | -0.109 |
王 | -0.106 |
Token | : |
Token ID | 25 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
� | +1.971 |
upgr | +1.840 |
王 | +1.557 |
mathemat | +1.507 |
tuning | +1.506 |
Neg logit contributions | |
ocry | -1.902 |
iple | -1.810 |
KE | -1.774 |
sho | -1.769 |
enty | -1.748 |
Token | 7 |
Token ID | 22 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
� | +0.273 |
upgr | +0.261 |
mathemat | +0.228 |
nodd | +0.226 |
王 | +0.219 |
Neg logit contributions | |
ocry | -0.252 |
iple | -0.240 |
KE | -0.239 |
sho | -0.235 |
enty | -0.232 |
Token | R |
Token ID | 371 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
KE | +1.179 |
ocry | +1.162 |
iple | +1.102 |
sho | +1.048 |
NET | +1.044 |
Neg logit contributions | |
� | -4.773 |
upgr | -4.626 |
mathemat | -4.381 |
nodd | -4.359 |
王 | -4.268 |
Token | Home |
Token ID | 16060 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ocry | +0.268 |
iple | +0.249 |
sho | +0.243 |
KE | +0.238 |
enty | +0.237 |
Neg logit contributions | |
� | -0.469 |
upgr | -0.457 |
mathemat | -0.406 |
nodd | -0.405 |
王 | -0.399 |
Token | page |
Token ID | 7700 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ocry | +0.713 |
iple | +0.685 |
sho | +0.671 |
KE | +0.662 |
enty | +0.659 |
Neg logit contributions | |
� | -0.692 |
upgr | -0.667 |
nodd | -0.597 |
mathemat | -0.594 |
王 | -0.560 |
Token | ] |
Token ID | 60 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ocry | +2.722 |
KE | +2.567 |
sho | +2.566 |
iple | +2.504 |
enty | +2.479 |
Neg logit contributions | |
� | -4.318 |
upgr | -4.226 |
nodd | -4.049 |
mathemat | -4.015 |
王 | -3.682 |
Token | [ |
Token ID | 685 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
� | +0.733 |
upgr | +0.692 |
王 | +0.582 |
mathemat | +0.581 |
nodd | +0.579 |
Neg logit contributions | |
ocry | -0.727 |
iple | -0.692 |
KE | -0.683 |
sho | -0.682 |
enty | -0.670 |
Token | App |
Token ID | 4677 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ocry | +1.168 |
iple | +1.111 |
sho | +1.089 |
enty | +1.072 |
KE | +1.064 |
Neg logit contributions | |
� | -1.182 |
upgr | -1.144 |
mathemat | -0.990 |
nodd | -0.989 |
王 | -0.958 |
Token | Brain |
Token ID | 44687 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ocry | +1.131 |
iple | +1.055 |
sho | +1.033 |
cript | +1.026 |
KE | +1.022 |
Neg logit contributions | |
� | -1.059 |
upgr | -1.040 |
nodd | -0.949 |
mathemat | -0.947 |
tuning | -0.854 |
Token | ] |
Token ID | 60 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ocry | +3.354 |
sho | +3.139 |
KE | +3.136 |
Blu | +3.052 |
FF | +3.023 |
Neg logit contributions | |
� | -5.708 |
upgr | -5.680 |
nodd | -5.587 |
mathemat | -5.556 |
unemploy | -5.027 |
Token |
|
Token ID | 198 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
ocry | +0.564 |
iple | +0.533 |
KE | +0.526 |
sho | +0.526 |
enty | +0.515 |
Neg logit contributions | |
� | -0.696 |
upgr | -0.661 |
王 | -0.569 |
mathemat | -0.567 |
nodd | -0.563 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ocry | +0.426 |
sho | +0.401 |
KE | +0.401 |
iple | +0.398 |
enty | +0.390 |
Neg logit contributions | |
� | -0.544 |
upgr | -0.532 |
mathemat | -0.484 |
nodd | -0.484 |
王 | -0.448 |
Token | Ret |
Token ID | 9781 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ocry | +0.628 |
iple | +0.596 |
enty | +0.580 |
sho | +0.578 |
KE | +0.574 |
Neg logit contributions | |
� | -0.739 |
upgr | -0.723 |
nodd | -0.641 |
mathemat | -0.638 |
tuning | -0.610 |
Token | ro |
Token ID | 305 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ocry | +0.545 |
iple | +0.522 |
enty | +0.498 |
sho | +0.492 |
KE | +0.490 |
Neg logit contributions | |
� | -0.874 |
upgr | -0.835 |
nodd | -0.746 |
mathemat | -0.743 |
王 | -0.737 |
Token | _. |
Token ID | 44807 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
� | +0.532 |
upgr | +0.509 |
nodd | +0.448 |
mathemat | +0.448 |
王 | +0.440 |
Neg logit contributions | |
ocry | -0.332 |
iple | -0.312 |
sho | -0.305 |
KE | -0.302 |
enty | -0.298 |
Token | Exception |
Token ID | 16922 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
� | +2.390 |
upgr | +2.264 |
nodd | +1.923 |
mathemat | +1.916 |
王 | +1.894 |
Neg logit contributions | |
ocry | -2.383 |
iple | -2.272 |
KE | -2.236 |
sho | -2.226 |
enty | -2.195 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ocry | +0.227 |
iple | +0.218 |
sho | +0.213 |
KE | +0.212 |
enty | +0.211 |
Neg logit contributions | |
� | -0.281 |
upgr | -0.272 |
mathemat | -0.238 |
nodd | -0.238 |
王 | -0.230 |
Token | Message |
Token ID | 12837 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
� | +1.166 |
upgr | +1.107 |
nodd | +0.950 |
mathemat | +0.943 |
王 | +0.930 |
Neg logit contributions | |
ocry | -1.144 |
iple | -1.088 |
KE | -1.076 |
sho | -1.075 |
enty | -1.052 |
Token | )" |
Token ID | 16725 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ocry | +1.515 |
sho | +1.434 |
iple | +1.433 |
KE | +1.418 |
cript | +1.399 |
Neg logit contributions | |
� | -2.083 |
upgr | -2.010 |
nodd | -1.794 |
mathemat | -1.779 |
王 | -1.762 |
Token | break |
Token ID | 2270 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
ocry | +1.786 |
sho | +1.724 |
KE | +1.693 |
Blu | +1.628 |
iple | +1.627 |
Neg logit contributions | |
� | -3.655 |
upgr | -3.446 |
王 | -3.175 |
nodd | -3.155 |
mathemat | -3.135 |
Token | } |
Token ID | 1782 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ocry | +2.319 |
sho | +2.260 |
KE | +2.201 |
iple | +2.122 |
FF | +2.114 |
Neg logit contributions | |
� | -6.748 |
upgr | -6.390 |
王 | -5.915 |
nodd | -5.906 |
mathemat | -5.905 |
Token | } |
Token ID | 1782 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ocry | +2.037 |
sho | +2.007 |
KE | +1.977 |
iple | +1.882 |
NET | +1.879 |
Neg logit contributions | |
� | -4.783 |
upgr | -4.426 |
王 | -4.146 |
nodd | -4.126 |
mathemat | -4.075 |
Token | Process |
Token ID | 10854 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ocry | +1.580 |
sho | +1.544 |
KE | +1.528 |
iple | +1.473 |
NET | +1.454 |
Neg logit contributions | |
� | -3.036 |
upgr | -2.796 |
王 | -2.590 |
nodd | -2.565 |
mathemat | -2.535 |
Token | { |
Token ID | 1391 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ocry | +1.170 |
KE | +1.112 |
sho | +1.105 |
iple | +1.097 |
cript | +1.064 |
Neg logit contributions | |
� | -1.562 |
upgr | -1.449 |
mathemat | -1.301 |
nodd | -1.300 |
王 | -1.288 |
Token | # |
Token ID | 1303 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ocry | +1.099 |
KE | +1.059 |
sho | +1.057 |
iple | +1.028 |
enty | +1.011 |
Neg logit contributions | |
� | -1.693 |
upgr | -1.579 |
nodd | -1.424 |
王 | -1.421 |
mathemat | -1.414 |
Token | the |
Token ID | 262 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
� | +0.568 |
upgr | +0.524 |
mathemat | +0.465 |
nodd | +0.461 |
王 | +0.460 |
Neg logit contributions | |
ocry | -0.430 |
sho | -0.424 |
KE | -0.415 |
iple | -0.413 |
enty | -0.395 |
Token | witness |
Token ID | 4973 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
� | +0.313 |
upgr | +0.292 |
mathemat | +0.258 |
王 | +0.257 |
nodd | +0.257 |
Neg logit contributions | |
ocry | -0.250 |
sho | -0.250 |
KE | -0.241 |
iple | -0.240 |
enty | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
� | +1.171 |
upgr | +1.115 |
mathemat | +0.982 |
nodd | +0.980 |
王 | +0.968 |
Neg logit contributions | |
ocry | -0.783 |
sho | -0.758 |
KE | -0.737 |
iple | -0.736 |
enty | -0.705 |
Token | who |
Token ID | 508 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
� | +0.145 |
upgr | +0.137 |
mathemat | +0.120 |
nodd | +0.120 |
王 | +0.119 |
Neg logit contributions | |
ocry | -0.098 |
sho | -0.096 |
KE | -0.096 |
iple | -0.094 |
enty | -0.091 |
Token | goes |
Token ID | 2925 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
� | +0.034 |
upgr | +0.033 |
mathemat | +0.028 |
nodd | +0.028 |
王 | +0.028 |
Neg logit contributions | |
sho | -0.026 |
ocry | -0.026 |
KE | -0.025 |
iple | -0.025 |
enty | -0.023 |
Token | by |
Token ID | 416 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
ocry | +0.596 |
sho | +0.585 |
KE | +0.552 |
iple | +0.533 |
enty | +0.477 |
Neg logit contributions | |
� | -2.549 |
upgr | -2.451 |
mathemat | -2.206 |
isphere | -2.206 |
王 | -2.181 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
KE | +3.650 |
ocry | +3.596 |
sho | +3.575 |
iple | +3.394 |
Blu | +3.379 |
Neg logit contributions | |
� | -5.108 |
upgr | -4.976 |
mathemat | -4.411 |
nodd | -4.359 |
isphere | -4.314 |
Token | handle |
Token ID | 5412 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ocry | +1.429 |
KE | +1.407 |
sho | +1.405 |
iple | +1.362 |
FF | +1.323 |
Neg logit contributions | |
� | -1.470 |
upgr | -1.399 |
mathemat | -1.238 |
nodd | -1.205 |
isphere | -1.203 |
Token | j |
Token ID | 474 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ocry | +1.067 |
sho | +1.038 |
KE | +1.037 |
iple | +1.013 |
enty | +0.972 |
Neg logit contributions | |
� | -1.622 |
upgr | -1.554 |
mathemat | -1.368 |
nodd | -1.361 |
王 | -1.351 |
Token | _ |
Token ID | 62 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ocry | +1.272 |
iple | +1.195 |
sho | +1.171 |
enty | +1.165 |
KE | +1.156 |
Neg logit contributions | |
� | -1.666 |
upgr | -1.623 |
mathemat | -1.405 |
nodd | -1.404 |
王 | -1.369 |
Token | patrick |
Token ID | 29615 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ocry | +0.531 |
iple | +0.507 |
sho | +0.497 |
KE | +0.492 |
enty | +0.492 |
Neg logit contributions | |
� | -0.709 |
upgr | -0.681 |
mathemat | -0.591 |
nodd | -0.590 |
王 | -0.576 |
Token | convert |
Token ID | 10385 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
� | +1.216 |
upgr | +1.150 |
nodd | +1.044 |
mathemat | +1.026 |
王 | +1.006 |
Neg logit contributions | |
ocry | -0.867 |
KE | -0.818 |
iple | -0.810 |
sho | -0.805 |
cript | -0.781 |
Token | it |
Token ID | 340 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ocry | +0.451 |
sho | +0.425 |
KE | +0.424 |
iple | +0.422 |
enty | +0.407 |
Neg logit contributions | |
� | -0.608 |
upgr | -0.579 |
nodd | -0.523 |
mathemat | -0.519 |
王 | -0.502 |
Token | to |
Token ID | 284 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ocry | +0.638 |
sho | +0.600 |
KE | +0.596 |
iple | +0.590 |
enty | +0.571 |
Neg logit contributions | |
� | -0.947 |
upgr | -0.915 |
nodd | -0.840 |
mathemat | -0.837 |
王 | -0.795 |
Token | gr |
Token ID | 1036 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ocry | +1.272 |
sho | +1.246 |
iple | +1.206 |
KE | +1.203 |
enty | +1.163 |
Neg logit contributions | |
� | -2.614 |
upgr | -2.488 |
nodd | -2.296 |
mathemat | -2.280 |
王 | -2.240 |
Token | ays |
Token ID | 592 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
� | +1.377 |
upgr | +1.327 |
mathemat | +1.191 |
nodd | +1.190 |
王 | +1.189 |
Neg logit contributions | |
ocry | -0.412 |
iple | -0.368 |
KE | -0.356 |
sho | -0.353 |
enty | -0.341 |
Token | cale |
Token ID | 38765 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
ocry | +0.984 |
iple | +0.929 |
enty | +0.887 |
cript | +0.886 |
KE | +0.872 |
Neg logit contributions | |
� | -1.613 |
upgr | -1.581 |
nodd | -1.484 |
mathemat | -1.458 |
王 | -1.384 |
Token | image |
Token ID | 2939 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
sho | +2.366 |
KE | +2.301 |
ocry | +2.255 |
iple | +2.159 |
ff | +2.089 |
Neg logit contributions | |
� | -6.642 |
upgr | -6.215 |
nodd | -6.144 |
mathemat | -6.011 |
王 | -5.779 |
Token | = |
Token ID | 796 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
� | +1.182 |
upgr | +1.123 |
mathemat | +0.949 |
nodd | +0.949 |
王 | +0.930 |
Neg logit contributions | |
ocry | -1.234 |
iple | -1.175 |
KE | -1.162 |
sho | -1.157 |
enty | -1.139 |
Token | c |
Token ID | 269 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ocry | +1.248 |
sho | +1.205 |
KE | +1.180 |
iple | +1.139 |
ff | +1.127 |
Neg logit contributions | |
� | -2.828 |
upgr | -2.693 |
nodd | -2.567 |
mathemat | -2.540 |
王 | -2.476 |
Token | v |
Token ID | 85 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
� | +2.238 |
upgr | +2.129 |
nodd | +1.824 |
mathemat | +1.817 |
王 | +1.764 |
Neg logit contributions | |
ocry | -2.484 |
iple | -2.367 |
sho | -2.324 |
KE | -2.315 |
enty | -2.297 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
� | +3.124 |
upgr | +2.899 |
王 | +2.373 |
mathemat | +2.291 |
tuning | +2.290 |
Neg logit contributions | |
ocry | -3.850 |
iple | -3.678 |
KE | -3.631 |
sho | -3.618 |
enty | -3.562 |
Token | 14 |
Token ID | 1478 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
� | +1.292 |
upgr | +1.228 |
nodd | +1.098 |
mathemat | +1.092 |
王 | +1.078 |
Neg logit contributions | |
ocry | -0.791 |
iple | -0.732 |
KE | -0.731 |
sho | -0.718 |
enty | -0.711 |
Token | nm |
Token ID | 21533 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
� | +0.056 |
upgr | +0.053 |
nodd | +0.049 |
mathemat | +0.049 |
王 | +0.049 |
Neg logit contributions | |
ocry | -0.017 |
KE | -0.015 |
iple | -0.015 |
sho | -0.015 |
enty | -0.014 |
Token | 28 |
Token ID | 2579 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ocry | +1.195 |
KE | +1.089 |
sho | +1.071 |
iple | +1.037 |
enty | +1.011 |
Neg logit contributions | |
� | -2.557 |
upgr | -2.410 |
nodd | -2.234 |
mathemat | -2.207 |
王 | -2.182 |
Token | nm |
Token ID | 21533 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ocry | +0.478 |
KE | +0.421 |
sho | +0.413 |
iple | +0.411 |
enty | +0.392 |
Neg logit contributions | |
� | -1.405 |
upgr | -1.343 |
mathemat | -1.243 |
nodd | -1.240 |
王 | -1.218 |
Token | 28 |
Token ID | 2579 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ocry | +2.101 |
KE | +2.027 |
sho | +1.910 |
NET | +1.886 |
FF | +1.881 |
Neg logit contributions | |
� | -5.363 |
upgr | -5.048 |
nodd | -4.880 |
mathemat | -4.860 |
isphere | -4.712 |
Token | nm |
Token ID | 21533 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ocry | +1.027 |
iple | +0.918 |
KE | +0.888 |
sho | +0.879 |
enty | +0.864 |
Neg logit contributions | |
� | -2.788 |
upgr | -2.696 |
mathemat | -2.518 |
nodd | -2.507 |
王 | -2.398 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ocry | +2.390 |
KE | +2.320 |
NET | +2.167 |
sho | +2.152 |
FF | +2.123 |
Neg logit contributions | |
� | -6.411 |
upgr | -6.003 |
nodd | -5.849 |
mathemat | -5.835 |
isphere | -5.686 |
Token | nm |
Token ID | 21533 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ocry | +1.276 |
iple | +1.113 |
KE | +1.111 |
sho | +1.075 |
enty | +1.054 |
Neg logit contributions | |
� | -3.696 |
upgr | -3.512 |
mathemat | -3.262 |
nodd | -3.230 |
王 | -3.186 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ocry | +2.086 |
KE | +2.010 |
sho | +1.908 |
NET | +1.871 |
Blu | +1.866 |
Neg logit contributions | |
� | -4.594 |
upgr | -4.325 |
nodd | -4.129 |
mathemat | -4.111 |
isphere | -4.011 |
Token | nm |
Token ID | 21533 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ocry | +1.379 |
iple | +1.230 |
KE | +1.192 |
sho | +1.173 |
enty | +1.158 |
Neg logit contributions | |
� | -3.774 |
upgr | -3.655 |
mathemat | -3.459 |
nodd | -3.443 |
unemploy | -3.252 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ocry | +2.163 |
KE | +2.066 |
sho | +1.968 |
NET | +1.936 |
iple | +1.919 |
Neg logit contributions | |
� | -4.293 |
upgr | -4.032 |
nodd | -3.817 |
mathemat | -3.799 |
isphere | -3.718 |
Token | levels |
Token ID | 2974 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
sho | +2.115 |
ocry | +2.105 |
KE | +2.088 |
NET | +2.017 |
FF | +1.993 |
Neg logit contributions | |
� | -3.008 |
upgr | -2.822 |
王 | -2.576 |
mathemat | -2.572 |
nodd | -2.502 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ocry | +0.134 |
iple | +0.125 |
sho | +0.124 |
KE | +0.124 |
enty | +0.119 |
Neg logit contributions | |
� | -0.219 |
upgr | -0.209 |
nodd | -0.185 |
王 | -0.184 |
mathemat | -0.184 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ocry | +0.687 |
sho | +0.665 |
KE | +0.663 |
iple | +0.644 |
NET | +0.638 |
Neg logit contributions | |
� | -1.027 |
upgr | -0.972 |
王 | -0.874 |
mathemat | -0.861 |
nodd | -0.855 |
Token | neurotrans |
Token ID | 39307 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
ocry | +0.715 |
KE | +0.691 |
sho | +0.689 |
iple | +0.677 |
NET | +0.654 |
Neg logit contributions | |
� | -1.090 |
upgr | -1.031 |
王 | -0.931 |
nodd | -0.921 |
mathemat | -0.917 |
Token | mitter |
Token ID | 37974 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ocry | +0.044 |
iple | +0.043 |
KE | +0.041 |
sho | +0.041 |
enty | +0.041 |
Neg logit contributions | |
� | -0.055 |
upgr | -0.053 |
王 | -0.046 |
nodd | -0.045 |
mathemat | -0.045 |
Token | acet |
Token ID | 25174 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ocry | +0.890 |
sho | +0.887 |
KE | +0.877 |
NET | +0.857 |
iple | +0.841 |
Neg logit contributions | |
� | -1.812 |
upgr | -1.725 |
王 | -1.605 |
mathemat | -1.537 |
nodd | -1.536 |
Token | yl |
Token ID | 2645 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ocry | +2.552 |
iple | +2.496 |
enty | +2.218 |
KE | +2.122 |
aft | +2.094 |
Neg logit contributions | |
upgr | -6.400 |
� | -6.362 |
nodd | -5.898 |
王 | -5.847 |
mathemat | -5.756 |
Token | ch |
Token ID | 354 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ocry | +1.542 |
sho | +1.495 |
iple | +1.465 |
KE | +1.460 |
enty | +1.432 |
Neg logit contributions | |
� | -2.264 |
upgr | -2.166 |
王 | -2.014 |
nodd | -1.990 |
mathemat | -1.914 |
Token | oline |
Token ID | 14453 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
ocry | +1.076 |
iple | +1.064 |
enty | +0.976 |
KE | +0.956 |
arij | +0.937 |
Neg logit contributions | |
upgr | -1.961 |
� | -1.886 |
mathemat | -1.789 |
王 | -1.754 |
nodd | -1.733 |
Token | in |
Token ID | 287 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
ocry | +0.114 |
iple | +0.107 |
KE | +0.107 |
sho | +0.107 |
enty | +0.103 |
Neg logit contributions | |
� | -0.192 |
upgr | -0.184 |
王 | -0.163 |
nodd | -0.162 |
mathemat | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ocry | +0.252 |
sho | +0.249 |
KE | +0.242 |
iple | +0.233 |
FF | +0.231 |
Neg logit contributions | |
� | -0.313 |
upgr | -0.296 |
王 | -0.265 |
mathemat | -0.263 |
nodd | -0.255 |
Token | sq |
Token ID | 19862 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
ocry | +0.989 |
sho | +0.950 |
iple | +0.926 |
KE | +0.916 |
ff | +0.899 |
Neg logit contributions | |
� | -1.551 |
upgr | -1.450 |
王 | -1.316 |
mathemat | -1.302 |
nodd | -1.290 |
Token | K |
Token ID | 42 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
� | +0.617 |
upgr | +0.594 |
mathemat | +0.529 |
nodd | +0.529 |
王 | +0.526 |
Neg logit contributions | |
ocry | -0.242 |
iple | -0.221 |
KE | -0.216 |
sho | -0.214 |
enty | -0.208 |
Token | ernel |
Token ID | 7948 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
� | +0.360 |
upgr | +0.345 |
nodd | +0.297 |
mathemat | +0.297 |
王 | +0.293 |
Neg logit contributions | |
ocry | -0.303 |
iple | -0.287 |
KE | -0.280 |
sho | -0.279 |
enty | -0.277 |
Token | = |
Token ID | 796 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
� | +1.831 |
upgr | +1.698 |
王 | +1.410 |
mathemat | +1.363 |
tuning | +1.362 |
Neg logit contributions | |
ocry | -2.066 |
iple | -1.970 |
KE | -1.937 |
sho | -1.936 |
enty | -1.910 |
Token | c |
Token ID | 269 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
� | +0.552 |
upgr | +0.527 |
mathemat | +0.475 |
nodd | +0.474 |
王 | +0.467 |
Neg logit contributions | |
ocry | -0.303 |
KE | -0.281 |
iple | -0.281 |
sho | -0.280 |
enty | -0.269 |
Token | v |
Token ID | 85 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
� | +4.134 |
upgr | +3.793 |
王 | +3.049 |
isphere | +2.985 |
tuning | +2.959 |
Neg logit contributions | |
ocry | -5.346 |
KE | -5.136 |
iple | -5.114 |
sho | -5.069 |
teasp | -5.031 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
� | +4.311 |
upgr | +3.894 |
王 | +3.164 |
Instance | +3.084 |
isphere | +3.025 |
Neg logit contributions | |
ocry | -5.996 |
teasp | -5.807 |
iple | -5.728 |
KE | -5.662 |
sho | -5.652 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
� | +4.254 |
upgr | +3.906 |
王 | +3.375 |
Instance | +3.286 |
tuning | +3.260 |
Neg logit contributions | |
ocry | -3.490 |
teasp | -3.332 |
iple | -3.320 |
arij | -3.218 |
KE | -3.206 |
Token | get |
Token ID | 1136 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
� | +3.245 |
upgr | +3.014 |
王 | +2.502 |
Instance | +2.471 |
isphere | +2.430 |
Neg logit contributions | |
ocry | -3.490 |
teasp | -3.250 |
sho | -3.245 |
iple | -3.241 |
KE | -3.229 |
Token | Struct |
Token ID | 44909 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
� | +1.621 |
upgr | +1.477 |
mathemat | +1.070 |
nodd | +1.069 |
王 | +1.040 |
Neg logit contributions | |
ocry | -3.905 |
iple | -3.768 |
KE | -3.734 |
sho | -3.723 |
enty | -3.685 |
Token | uring |
Token ID | 870 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
� | +2.214 |
upgr | +2.102 |
nodd | +1.808 |
mathemat | +1.801 |
王 | +1.755 |
Neg logit contributions | |
ocry | -2.272 |
iple | -2.178 |
KE | -2.120 |
sho | -2.118 |
enty | -2.102 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
� | +0.008 |
upgr | +0.008 |
nodd | +0.007 |
mathemat | +0.007 |
王 | +0.006 |
Neg logit contributions | |
ocry | -0.005 |
iple | -0.005 |
KE | -0.005 |
sho | -0.005 |
enty | -0.004 |
Token | bit |
Token ID | 2545 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
� | +0.691 |
upgr | +0.666 |
nodd | +0.594 |
mathemat | +0.590 |
王 | +0.583 |
Neg logit contributions | |
ocry | -0.307 |
iple | -0.290 |
enty | -0.271 |
sho | -0.270 |
KE | -0.270 |
Token | map |
Token ID | 8899 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
� | +1.169 |
upgr | +1.114 |
nodd | +0.956 |
mathemat | +0.955 |
王 | +0.940 |
Neg logit contributions | |
ocry | -1.061 |
iple | -1.013 |
KE | -0.986 |
sho | -0.985 |
enty | -0.972 |
Token | ($ |
Token ID | 16763 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ocry | +0.785 |
KE | +0.745 |
sho | +0.743 |
iple | +0.734 |
enty | +0.711 |
Neg logit contributions | |
� | -1.322 |
upgr | -1.236 |
nodd | -1.119 |
王 | -1.110 |
mathemat | -1.099 |
Token | SR |
Token ID | 12562 |
Feature activation | -9.09e-03 |
Pos logit contributions | |
� | +1.213 |
upgr | +1.158 |
nodd | +1.033 |
mathemat | +1.021 |
王 | +1.004 |
Neg logit contributions | |
ocry | -0.749 |
iple | -0.708 |
sho | -0.685 |
KE | -0.684 |
enty | -0.676 |
Token | . |
Token ID | 13 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
� | +0.057 |
upgr | +0.054 |
nodd | +0.047 |
王 | +0.047 |
mathemat | +0.047 |
Neg logit contributions | |
ocry | -0.039 |
iple | -0.036 |
KE | -0.036 |
sho | -0.036 |
enty | -0.035 |
Token | Width |
Token ID | 30916 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
� | +4.685 |
upgr | +4.370 |
王 | +3.599 |
mathemat | +3.542 |
nodd | +3.507 |
Neg logit contributions | |
ocry | -5.596 |
iple | -5.321 |
KE | -5.280 |
sho | -5.273 |
enty | -5.189 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
� | +1.132 |
upgr | +1.083 |
nodd | +0.957 |
王 | +0.949 |
mathemat | +0.948 |
Neg logit contributions | |
ocry | -0.674 |
iple | -0.632 |
KE | -0.627 |
sho | -0.625 |
enty | -0.611 |
Token | $ |
Token ID | 3 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
� | +1.993 |
upgr | +1.898 |
nodd | +1.650 |
mathemat | +1.649 |
王 | +1.642 |
Neg logit contributions | |
ocry | -1.325 |
iple | -1.246 |
KE | -1.224 |
sho | -1.220 |
enty | -1.197 |
Token | SR |
Token ID | 12562 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
� | +0.255 |
upgr | +0.245 |
nodd | +0.220 |
mathemat | +0.219 |
王 | +0.212 |
Neg logit contributions | |
ocry | -0.127 |
iple | -0.120 |
sho | -0.115 |
KE | -0.114 |
enty | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ocry | +0.012 |
iple | +0.011 |
KE | +0.011 |
sho | +0.011 |
enty | +0.011 |
Neg logit contributions | |
� | -0.019 |
upgr | -0.018 |
nodd | -0.017 |
mathemat | -0.016 |
王 | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ocry | +0.385 |
KE | +0.373 |
sho | +0.373 |
iple | +0.369 |
enty | +0.351 |
Neg logit contributions | |
� | -0.620 |
upgr | -0.591 |
mathemat | -0.527 |
王 | -0.526 |
nodd | -0.520 |
Token | I |
Token ID | 314 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
� | +0.179 |
upgr | +0.173 |
mathemat | +0.155 |
nodd | +0.153 |
王 | +0.148 |
Neg logit contributions | |
ocry | -0.124 |
KE | -0.121 |
iple | -0.118 |
sho | -0.117 |
enty | -0.114 |
Token | was |
Token ID | 373 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
� | +0.162 |
upgr | +0.153 |
王 | +0.133 |
mathemat | +0.133 |
nodd | +0.132 |
Neg logit contributions | |
ocry | -0.121 |
sho | -0.116 |
KE | -0.114 |
iple | -0.114 |
enty | -0.111 |
Token | also |
Token ID | 635 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
� | +0.873 |
upgr | +0.823 |
王 | +0.732 |
mathemat | +0.732 |
nodd | +0.723 |
Neg logit contributions | |
ocry | -0.527 |
sho | -0.509 |
iple | -0.500 |
KE | -0.499 |
enty | -0.479 |
Token | told |
Token ID | 1297 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
� | +1.561 |
upgr | +1.478 |
mathemat | +1.311 |
王 | +1.309 |
nodd | +1.302 |
Neg logit contributions | |
ocry | -0.912 |
sho | -0.868 |
iple | -0.858 |
KE | -0.851 |
enty | -0.820 |
Token | to |
Token ID | 284 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
� | +1.044 |
upgr | +0.987 |
mathemat | +0.864 |
王 | +0.858 |
nodd | +0.855 |
Neg logit contributions | |
ocry | -0.742 |
KE | -0.697 |
sho | -0.695 |
iple | -0.695 |
enty | -0.673 |
Token | " |
Token ID | 366 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
� | +5.328 |
upgr | +5.081 |
nodd | +4.249 |
mathemat | +4.243 |
王 | +4.221 |
Neg logit contributions | |
ocry | -4.891 |
iple | -4.641 |
KE | -4.522 |
arij | -4.466 |
enty | -4.466 |
Token | watch |
Token ID | 8340 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
� | +1.159 |
upgr | +1.104 |
mathemat | +0.958 |
nodd | +0.949 |
王 | +0.939 |
Neg logit contributions | |
ocry | -0.958 |
iple | -0.912 |
KE | -0.898 |
sho | -0.897 |
enty | -0.883 |
Token | how |
Token ID | 703 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
� | +2.142 |
upgr | +2.024 |
mathemat | +1.767 |
王 | +1.760 |
nodd | +1.760 |
Neg logit contributions | |
ocry | -1.478 |
iple | -1.411 |
KE | -1.408 |
sho | -1.393 |
enty | -1.347 |
Token | I |
Token ID | 314 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
� | +0.713 |
upgr | +0.677 |
王 | +0.594 |
mathemat | +0.590 |
nodd | +0.588 |
Neg logit contributions | |
ocry | -0.515 |
KE | -0.500 |
iple | -0.492 |
sho | -0.490 |
enty | -0.472 |
Token | speak |
Token ID | 2740 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ocry | +0.207 |
sho | +0.202 |
iple | +0.198 |
KE | +0.197 |
enty | +0.192 |
Neg logit contributions | |
� | -0.228 |
upgr | -0.220 |
王 | -0.191 |
mathemat | -0.188 |
nodd | -0.188 |
Token | work |
Token ID | 670 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ocry | +1.491 |
sho | +1.433 |
KE | +1.424 |
iple | +1.396 |
FF | +1.354 |
Neg logit contributions | |
� | -1.940 |
upgr | -1.826 |
王 | -1.566 |
mathemat | -1.564 |
nodd | -1.557 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ocry | +0.927 |
sho | +0.900 |
iple | +0.894 |
KE | +0.885 |
cript | +0.858 |
Neg logit contributions | |
� | -1.583 |
upgr | -1.517 |
mathemat | -1.345 |
王 | -1.331 |
nodd | -1.319 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ocry | +0.775 |
KE | +0.757 |
sho | +0.737 |
iple | +0.729 |
enty | +0.715 |
Neg logit contributions | |
� | -1.051 |
upgr | -1.021 |
mathemat | -0.909 |
nodd | -0.904 |
王 | -0.865 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ocry | +0.772 |
KE | +0.729 |
sho | +0.729 |
iple | +0.720 |
enty | +0.707 |
Neg logit contributions | |
� | -1.019 |
upgr | -1.006 |
mathemat | -0.931 |
nodd | -0.930 |
unemploy | -0.850 |
Token | Ward |
Token ID | 49021 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
ocry | +0.774 |
iple | +0.739 |
enty | +0.720 |
KE | +0.716 |
sho | +0.715 |
Neg logit contributions | |
� | -0.858 |
upgr | -0.838 |
nodd | -0.737 |
mathemat | -0.734 |
tuning | -0.689 |
Token | Breaker |
Token ID | 44478 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ocry | +0.187 |
iple | +0.176 |
KE | +0.174 |
sho | +0.173 |
enty | +0.170 |
Neg logit contributions | |
� | -0.247 |
upgr | -0.235 |
mathemat | -0.203 |
王 | -0.201 |
nodd | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
� | +5.922 |
upgr | +5.596 |
王 | +4.818 |
mathemat | +4.789 |
nodd | +4.788 |
Neg logit contributions | |
ocry | -4.273 |
iple | -4.024 |
KE | -3.916 |
sho | -3.880 |
arij | -3.865 |
Token | Part |
Token ID | 2142 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
� | +1.744 |
upgr | +1.660 |
mathemat | +1.421 |
nodd | +1.419 |
王 | +1.412 |
Neg logit contributions | |
ocry | -1.400 |
iple | -1.326 |
KE | -1.308 |
sho | -1.305 |
enty | -1.279 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
� | +0.153 |
upgr | +0.146 |
mathemat | +0.124 |
nodd | +0.124 |
王 | +0.123 |
Neg logit contributions | |
ocry | -0.145 |
iple | -0.139 |
KE | -0.137 |
sho | -0.136 |
enty | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocry | +1.367 |
iple | +1.276 |
KE | +1.276 |
sho | +1.262 |
enty | +1.241 |
Neg logit contributions | |
� | -1.737 |
upgr | -1.664 |
mathemat | -1.439 |
nodd | -1.432 |
王 | -1.416 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ocry | +0.841 |
KE | +0.797 |
sho | +0.794 |
iple | +0.785 |
enty | +0.771 |
Neg logit contributions | |
� | -1.117 |
upgr | -1.100 |
mathemat | -1.017 |
nodd | -1.016 |
unemploy | -0.928 |
Token | Share |
Token ID | 8734 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ocry | +0.030 |
iple | +0.028 |
KE | +0.027 |
sho | +0.027 |
enty | +0.026 |
Neg logit contributions | |
� | -0.072 |
upgr | -0.069 |
nodd | -0.062 |
mathemat | -0.062 |
王 | -0.061 |
Token | To |
Token ID | 1675 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ocry | +1.252 |
KE | +1.181 |
sho | +1.147 |
FF | +1.144 |
cript | +1.138 |
Neg logit contributions | |
� | -1.565 |
upgr | -1.498 |
nodd | -1.354 |
mathemat | -1.315 |
王 | -1.268 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
� | +1.621 |
upgr | +1.536 |
mathemat | +1.303 |
nodd | +1.301 |
王 | +1.299 |
Neg logit contributions | |
ocry | -1.441 |
iple | -1.366 |
KE | -1.347 |
sho | -1.342 |
enty | -1.320 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
� | +0.713 |
upgr | +0.686 |
mathemat | +0.599 |
nodd | +0.599 |
王 | +0.576 |
Neg logit contributions | |
ocry | -0.602 |
iple | -0.568 |
KE | -0.565 |
sho | -0.562 |
enty | -0.551 |
Token | In |
Token ID | 818 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
ocry | +0.014 |
iple | +0.013 |
KE | +0.013 |
sho | +0.013 |
enty | +0.013 |
Neg logit contributions | |
� | -0.016 |
upgr | -0.016 |
nodd | -0.014 |
mathemat | -0.014 |
tuning | -0.013 |
Token | n |
Token ID | 77 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
� | +0.470 |
upgr | +0.450 |
mathemat | +0.390 |
nodd | +0.387 |
王 | +0.383 |
Neg logit contributions | |
ocry | -0.361 |
iple | -0.341 |
sho | -0.339 |
KE | -0.337 |
enty | -0.330 |
Token | ocent |
Token ID | 29421 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
� | +5.353 |
upgr | +5.016 |
mathemat | +4.255 |
王 | +4.255 |
nodd | +4.247 |
Neg logit contributions | |
ocry | -4.726 |
iple | -4.488 |
KE | -4.449 |
sho | -4.412 |
enty | -4.345 |
Token | people |
Token ID | 661 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
� | +1.989 |
upgr | +1.898 |
mathemat | +1.638 |
nodd | +1.630 |
王 | +1.627 |
Neg logit contributions | |
ocry | -1.509 |
iple | -1.429 |
sho | -1.416 |
KE | -1.404 |
enty | -1.364 |
Token | from |
Token ID | 422 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ocry | +0.879 |
sho | +0.862 |
KE | +0.833 |
iple | +0.829 |
enty | +0.810 |
Neg logit contributions | |
� | -1.156 |
upgr | -1.122 |
mathemat | -0.978 |
王 | -0.970 |
nodd | -0.958 |
Token | black |
Token ID | 2042 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
� | +0.977 |
upgr | +0.931 |
mathemat | +0.812 |
nodd | +0.804 |
王 | +0.802 |
Neg logit contributions | |
ocry | -0.707 |
sho | -0.670 |
KE | -0.670 |
iple | -0.664 |
enty | -0.644 |
Token | communities |
Token ID | 5348 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ocry | +1.181 |
sho | +1.136 |
iple | +1.105 |
KE | +1.100 |
enty | +1.072 |
Neg logit contributions | |
� | -1.483 |
upgr | -1.438 |
mathemat | -1.273 |
nodd | -1.237 |
王 | -1.205 |
Token | art |
Token ID | 433 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ocry | +0.039 |
iple | +0.036 |
KE | +0.035 |
sho | +0.035 |
enty | +0.034 |
Neg logit contributions | |
� | -0.086 |
upgr | -0.082 |
nodd | -0.073 |
mathemat | -0.073 |
王 | -0.073 |
Token | ext |
Token ID | 2302 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
� | +2.434 |
upgr | +2.289 |
王 | +1.916 |
mathemat | +1.905 |
nodd | +1.895 |
Neg logit contributions | |
ocry | -2.380 |
iple | -2.260 |
KE | -2.243 |
sho | -2.232 |
enty | -2.187 |
Token | [ |
Token ID | 58 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
� | +1.622 |
upgr | +1.490 |
王 | +1.162 |
mathemat | +1.145 |
nodd | +1.141 |
Neg logit contributions | |
ocry | -2.697 |
iple | -2.591 |
KE | -2.566 |
sho | -2.554 |
enty | -2.523 |
Token | $ |
Token ID | 3 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
� | +2.627 |
upgr | +2.449 |
王 | +2.084 |
tuning | +2.009 |
Instance | +2.006 |
Neg logit contributions | |
ocry | -2.414 |
iple | -2.276 |
KE | -2.260 |
sho | -2.232 |
arij | -2.198 |
Token | i |
Token ID | 72 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
� | +1.531 |
upgr | +1.463 |
nodd | +1.270 |
mathemat | +1.270 |
王 | +1.261 |
Neg logit contributions | |
ocry | -1.060 |
iple | -0.998 |
KE | -0.977 |
sho | -0.975 |
enty | -0.958 |
Token | - |
Token ID | 12 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
� | +4.018 |
upgr | +3.700 |
王 | +3.162 |
Instance | +3.059 |
tuning | +3.044 |
Neg logit contributions | |
ocry | -3.602 |
iple | -3.416 |
KE | -3.356 |
sho | -3.341 |
teasp | -3.302 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
� | +3.668 |
upgr | +3.177 |
王 | +2.544 |
Instance | +2.408 |
Sup | +2.365 |
Neg logit contributions | |
ocry | -6.378 |
KE | -6.099 |
teasp | -6.088 |
iple | -6.073 |
sho | -6.041 |
Token | ], |
Token ID | 4357 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
� | +2.539 |
upgr | +2.360 |
王 | +1.963 |
tuning | +1.890 |
mathemat | +1.886 |
Neg logit contributions | |
ocry | -2.850 |
iple | -2.706 |
KE | -2.678 |
sho | -2.666 |
enty | -2.624 |
Token | $ |
Token ID | 720 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
� | +0.301 |
upgr | +0.287 |
nodd | +0.248 |
mathemat | +0.248 |
王 | +0.241 |
Neg logit contributions | |
ocry | -0.277 |
iple | -0.263 |
KE | -0.262 |
sho | -0.261 |
enty | -0.256 |
Token | font |
Token ID | 10331 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ocry | +0.995 |
iple | +0.959 |
enty | +0.924 |
cript | +0.915 |
sho | +0.909 |
Neg logit contributions | |
� | -1.304 |
upgr | -1.257 |
nodd | -1.095 |
mathemat | -1.091 |
王 | -1.058 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
� | +2.559 |
upgr | +2.411 |
mathemat | +2.003 |
nodd | +1.999 |
王 | +1.982 |
Neg logit contributions | |
ocry | -2.959 |
iple | -2.826 |
KE | -2.787 |
sho | -2.780 |
enty | -2.743 |
Token |
|
Token ID | 198 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ocry | +0.400 |
KE | +0.378 |
sho | +0.377 |
iple | +0.375 |
enty | +0.367 |
Neg logit contributions | |
� | -0.513 |
upgr | -0.501 |
nodd | -0.456 |
mathemat | -0.456 |
王 | -0.422 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
ocry | +0.260 |
iple | +0.245 |
KE | +0.241 |
enty | +0.239 |
sho | +0.237 |
Neg logit contributions | |
� | -0.379 |
upgr | -0.375 |
nodd | -0.344 |
mathemat | -0.343 |
tuning | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
ocry | +0.038 |
KE | +0.036 |
iple | +0.036 |
sho | +0.035 |
enty | +0.034 |
Neg logit contributions | |
� | -0.053 |
upgr | -0.052 |
mathemat | -0.047 |
nodd | -0.047 |
王 | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
� | +0.386 |
upgr | +0.373 |
nodd | +0.331 |
mathemat | +0.331 |
王 | +0.315 |
Neg logit contributions | |
ocry | -0.315 |
iple | -0.297 |
KE | -0.297 |
sho | -0.296 |
enty | -0.289 |
Token | In |
Token ID | 818 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
� | +0.403 |
upgr | +0.396 |
nodd | +0.352 |
mathemat | +0.350 |
tuning | +0.326 |
Neg logit contributions | |
ocry | -0.417 |
iple | -0.399 |
KE | -0.394 |
enty | -0.390 |
sho | -0.389 |
Token | n |
Token ID | 77 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
� | +0.954 |
upgr | +0.904 |
mathemat | +0.772 |
王 | +0.768 |
nodd | +0.764 |
Neg logit contributions | |
ocry | -0.827 |
iple | -0.787 |
sho | -0.780 |
KE | -0.775 |
enty | -0.758 |
Token | ovation |
Token ID | 17882 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
� | +5.142 |
upgr | +4.796 |
nodd | +4.050 |
王 | +4.038 |
mathemat | +4.036 |
Neg logit contributions | |
ocry | -4.797 |
iple | -4.563 |
KE | -4.507 |
sho | -4.482 |
enty | -4.405 |
Token | FT |
Token ID | 19446 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ocry | +0.703 |
sho | +0.677 |
KE | +0.676 |
iple | +0.675 |
enty | +0.648 |
Neg logit contributions | |
� | -0.901 |
upgr | -0.849 |
王 | -0.755 |
mathemat | -0.752 |
nodd | -0.745 |
Token | W |
Token ID | 54 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
� | +1.489 |
upgr | +1.437 |
nodd | +1.255 |
mathemat | +1.254 |
王 | +1.239 |
Neg logit contributions | |
ocry | -0.957 |
sho | -0.909 |
iple | -0.901 |
KE | -0.900 |
enty | -0.869 |
Token | ! |
Token ID | 0 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
� | +0.135 |
upgr | +0.129 |
mathemat | +0.114 |
nodd | +0.113 |
王 | +0.113 |
Neg logit contributions | |
ocry | -0.072 |
KE | -0.068 |
iple | -0.068 |
sho | -0.068 |
enty | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
� | +0.897 |
upgr | +0.855 |
nodd | +0.744 |
mathemat | +0.741 |
王 | +0.732 |
Neg logit contributions | |
ocry | -0.697 |
KE | -0.671 |
iple | -0.660 |
sho | -0.656 |
enty | -0.641 |
Token | chances |
Token ID | 8395 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ocry | +0.229 |
sho | +0.226 |
KE | +0.224 |
iple | +0.218 |
enty | +0.213 |
Neg logit contributions | |
� | -0.295 |
upgr | -0.276 |
王 | -0.246 |
nodd | -0.242 |
mathemat | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
� | +0.116 |
upgr | +0.112 |
nodd | +0.099 |
mathemat | +0.099 |
王 | +0.098 |
Neg logit contributions | |
ocry | -0.072 |
sho | -0.068 |
iple | -0.067 |
KE | -0.067 |
enty | -0.066 |
Token | � |
Token ID | 564 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ocry | +0.128 |
KE | +0.122 |
iple | +0.121 |
sho | +0.120 |
enty | +0.118 |
Neg logit contributions | |
� | -0.154 |
upgr | -0.150 |
mathemat | -0.130 |
nodd | -0.129 |
isphere | -0.126 |
Token | � |
Token ID | 250 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ocry | +0.349 |
iple | +0.309 |
KE | +0.299 |
sho | +0.296 |
enty | +0.290 |
Neg logit contributions | |
� | -1.089 |
upgr | -1.067 |
mathemat | -0.968 |
nodd | -0.962 |
王 | -0.940 |
Token | As |
Token ID | 1722 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
� | +1.028 |
upgr | +1.005 |
nodd | +0.873 |
mathemat | +0.873 |
王 | +0.817 |
Neg logit contributions | |
ocry | -1.000 |
iple | -0.951 |
KE | -0.946 |
sho | -0.929 |
enty | -0.928 |
Token | always |
Token ID | 1464 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
� | +0.217 |
upgr | +0.210 |
mathemat | +0.187 |
王 | +0.187 |
nodd | +0.185 |
Neg logit contributions | |
ocry | -0.123 |
iple | -0.115 |
KE | -0.115 |
sho | -0.113 |
enty | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
� | +5.945 |
upgr | +5.609 |
mathemat | +4.860 |
nodd | +4.845 |
王 | +4.833 |
Neg logit contributions | |
ocry | -4.042 |
iple | -3.773 |
KE | -3.689 |
sho | -3.687 |
enty | -3.628 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
� | +1.027 |
upgr | +0.996 |
nodd | +0.870 |
王 | +0.866 |
mathemat | +0.864 |
Neg logit contributions | |
ocry | -0.728 |
iple | -0.697 |
KE | -0.694 |
sho | -0.686 |
enty | -0.668 |
Token | � |
Token ID | 447 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ocry | +0.081 |
iple | +0.079 |
sho | +0.078 |
KE | +0.076 |
enty | +0.075 |
Neg logit contributions | |
� | -0.073 |
upgr | -0.071 |
nodd | -0.061 |
王 | -0.060 |
mathemat | -0.060 |
Token | � |
Token ID | 247 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ocry | +0.235 |
iple | +0.214 |
KE | +0.202 |
sho | +0.201 |
enty | +0.197 |
Neg logit contributions | |
� | -0.818 |
upgr | -0.796 |
mathemat | -0.732 |
nodd | -0.727 |
王 | -0.712 |
Token | s |
Token ID | 82 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
ocry | +0.531 |
iple | +0.503 |
sho | +0.488 |
KE | +0.487 |
enty | +0.480 |
Neg logit contributions | |
� | -0.898 |
upgr | -0.862 |
mathemat | -0.773 |
nodd | -0.771 |
王 | -0.763 |
Token | Chest |
Token ID | 25544 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
� | +0.181 |
upgr | +0.176 |
mathemat | +0.153 |
nodd | +0.151 |
王 | +0.151 |
Neg logit contributions | |
ocry | -0.126 |
KE | -0.118 |
sho | -0.116 |
iple | -0.115 |
enty | -0.114 |
Token | o |
Token ID | 78 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
� | +0.824 |
upgr | +0.802 |
mathemat | +0.690 |
nodd | +0.678 |
王 | +0.674 |
Neg logit contributions | |
ocry | -0.736 |
sho | -0.694 |
iple | -0.687 |
KE | -0.677 |
enty | -0.675 |
Token | can |
Token ID | 460 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
� | +2.041 |
upgr | +1.965 |
mathemat | +1.676 |
nodd | +1.667 |
王 | +1.646 |
Neg logit contributions | |
ocry | -1.765 |
iple | -1.677 |
KE | -1.669 |
sho | -1.663 |
enty | -1.634 |
Token | be |
Token ID | 307 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
� | +0.342 |
upgr | +0.327 |
mathemat | +0.283 |
nodd | +0.283 |
王 | +0.278 |
Neg logit contributions | |
ocry | -0.258 |
KE | -0.243 |
iple | -0.241 |
sho | -0.239 |
enty | -0.235 |
Token | reached |
Token ID | 4251 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
� | +0.637 |
upgr | +0.613 |
mathemat | +0.554 |
nodd | +0.552 |
王 | +0.551 |
Neg logit contributions | |
ocry | -0.188 |
sho | -0.169 |
KE | -0.167 |
iple | -0.163 |
enty | -0.158 |
Token | at |
Token ID | 379 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
� | +2.026 |
upgr | +1.932 |
mathemat | +1.712 |
nodd | +1.702 |
王 | +1.680 |
Neg logit contributions | |
ocry | -1.221 |
iple | -1.131 |
KE | -1.129 |
sho | -1.117 |
enty | -1.101 |
Token | j |
Token ID | 474 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
� | +7.091 |
upgr | +6.797 |
nodd | +6.094 |
mathemat | +6.056 |
王 | +5.985 |
Neg logit contributions | |
ocry | -2.806 |
iple | -2.559 |
enty | -2.419 |
sho | -2.417 |
KE | -2.405 |
Token | on |
Token ID | 261 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
� | +1.105 |
upgr | +1.054 |
mathemat | +0.894 |
nodd | +0.890 |
王 | +0.887 |
Neg logit contributions | |
ocry | -1.022 |
iple | -0.967 |
KE | -0.952 |
sho | -0.948 |
enty | -0.942 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
� | +2.259 |
upgr | +2.179 |
mathemat | +1.894 |
nodd | +1.878 |
王 | +1.875 |
Neg logit contributions | |
ocry | -1.550 |
iple | -1.454 |
KE | -1.428 |
sho | -1.421 |
enty | -1.405 |
Token | chest |
Token ID | 46713 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
� | +1.164 |
upgr | +1.090 |
mathemat | +0.890 |
nodd | +0.889 |
王 | +0.889 |
Neg logit contributions | |
ocry | -1.442 |
iple | -1.377 |
KE | -1.362 |
sho | -1.357 |
enty | -1.338 |
Token | o |
Token ID | 78 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ocry | +0.705 |
iple | +0.647 |
sho | +0.639 |
enty | +0.631 |
cript | +0.613 |
Neg logit contributions | |
upgr | -1.135 |
� | -1.128 |
nodd | -1.045 |
mathemat | -1.039 |
王 | -0.999 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
� | +2.597 |
upgr | +2.403 |
王 | +1.974 |
mathemat | +1.905 |
nodd | +1.905 |
Neg logit contributions | |
ocry | -3.180 |
iple | -3.036 |
KE | -2.996 |
sho | -2.987 |
enty | -2.946 |
Token | ]) |
Token ID | 12962 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
� | +1.430 |
upgr | +1.347 |
mathemat | +1.143 |
王 | +1.141 |
nodd | +1.137 |
Neg logit contributions | |
ocry | -1.271 |
iple | -1.204 |
KE | -1.189 |
sho | -1.185 |
enty | -1.161 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ocry | +0.745 |
KE | +0.720 |
sho | +0.712 |
iple | +0.696 |
enty | +0.672 |
Neg logit contributions | |
� | -1.295 |
upgr | -1.266 |
nodd | -1.157 |
mathemat | -1.154 |
王 | -1.110 |
Token | $ |
Token ID | 720 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
ocry | +2.044 |
sho | +1.930 |
KE | +1.910 |
iple | +1.908 |
enty | +1.848 |
Neg logit contributions | |
� | -2.648 |
upgr | -2.500 |
mathemat | -2.179 |
王 | -2.177 |
nodd | -2.168 |
Token | s |
Token ID | 82 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ocry | +0.083 |
iple | +0.079 |
sho | +0.076 |
enty | +0.075 |
KE | +0.075 |
Neg logit contributions | |
� | -0.126 |
upgr | -0.121 |
nodd | -0.107 |
mathemat | -0.106 |
王 | -0.104 |
Token | z |
Token ID | 89 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
� | +2.872 |
upgr | +2.761 |
mathemat | +2.445 |
nodd | +2.445 |
王 | +2.439 |
Neg logit contributions | |
ocry | -1.285 |
iple | -1.183 |
KE | -1.149 |
sho | -1.143 |
enty | -1.120 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
� | +4.278 |
upgr | +3.944 |
王 | +3.211 |
mathemat | +3.192 |
nodd | +3.186 |
Neg logit contributions | |
ocry | -5.495 |
KE | -5.215 |
iple | -5.212 |
sho | -5.179 |
enty | -5.100 |
Token | = |
Token ID | 796 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
� | +2.183 |
upgr | +2.048 |
王 | +1.700 |
mathemat | +1.688 |
nodd | +1.684 |
Neg logit contributions | |
ocry | -2.375 |
iple | -2.262 |
KE | -2.232 |
sho | -2.224 |
enty | -2.193 |
Token | [ |
Token ID | 685 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
� | +1.056 |
upgr | +0.994 |
mathemat | +0.825 |
nodd | +0.825 |
王 | +0.824 |
Neg logit contributions | |
ocry | -1.155 |
iple | -1.100 |
KE | -1.086 |
sho | -1.084 |
enty | -1.067 |
Token | system |
Token ID | 10057 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
� | +1.366 |
upgr | +1.307 |
nodd | +1.146 |
mathemat | +1.143 |
王 | +1.131 |
Neg logit contributions | |
ocry | -0.879 |
iple | -0.825 |
sho | -0.804 |
KE | -0.803 |
enty | -0.791 |
Token | . |
Token ID | 13 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
� | +2.167 |
upgr | +2.047 |
王 | +1.764 |
mathemat | +1.734 |
nodd | +1.727 |
Neg logit contributions | |
ocry | -1.569 |
iple | -1.481 |
KE | -1.454 |
sho | -1.444 |
enty | -1.419 |
Token | done |
Token ID | 1760 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ocry | +0.931 |
sho | +0.894 |
KE | +0.879 |
iple | +0.873 |
enty | +0.857 |
Neg logit contributions | |
� | -1.278 |
upgr | -1.221 |
王 | -1.073 |
mathemat | -1.071 |
nodd | -1.045 |
Token | . |
Token ID | 13 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
ocry | +0.540 |
sho | +0.518 |
iple | +0.510 |
KE | +0.504 |
enty | +0.490 |
Neg logit contributions | |
� | -0.885 |
upgr | -0.859 |
mathemat | -0.751 |
王 | -0.750 |
nodd | -0.743 |
Token |
|
Token ID | 198 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
� | +0.549 |
upgr | +0.543 |
mathemat | +0.482 |
nodd | +0.477 |
isphere | +0.459 |
Neg logit contributions | |
ocry | -0.428 |
KE | -0.412 |
sho | -0.403 |
iple | -0.402 |
enty | -0.396 |
Token |
|
Token ID | 198 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
ocry | +0.266 |
KE | +0.251 |
sho | +0.249 |
iple | +0.249 |
enty | +0.244 |
Neg logit contributions | |
� | -0.334 |
upgr | -0.327 |
mathemat | -0.295 |
nodd | -0.295 |
王 | -0.274 |
Token | P |
Token ID | 47 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
ocry | +0.337 |
iple | +0.322 |
enty | +0.315 |
KE | +0.315 |
sho | +0.311 |
Neg logit contributions | |
upgr | -0.369 |
� | -0.363 |
mathemat | -0.332 |
nodd | -0.331 |
tuning | -0.307 |
Token | ier |
Token ID | 959 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
� | +0.543 |
upgr | +0.529 |
mathemat | +0.467 |
王 | +0.461 |
nodd | +0.458 |
Neg logit contributions | |
ocry | -0.408 |
iple | -0.389 |
enty | -0.377 |
sho | -0.372 |
KE | -0.370 |
Token | 57 |
Token ID | 7632 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
� | +5.863 |
upgr | +5.570 |
mathemat | +4.827 |
王 | +4.820 |
nodd | +4.818 |
Neg logit contributions | |
ocry | -3.870 |
iple | -3.636 |
KE | -3.565 |
sho | -3.545 |
enty | -3.485 |
Token | is |
Token ID | 318 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
� | +1.031 |
upgr | +0.985 |
mathemat | +0.852 |
nodd | +0.847 |
王 | +0.844 |
Neg logit contributions | |
ocry | -0.827 |
iple | -0.783 |
sho | -0.777 |
KE | -0.775 |
enty | -0.759 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
� | +0.132 |
upgr | +0.126 |
王 | +0.111 |
mathemat | +0.110 |
nodd | +0.109 |
Neg logit contributions | |
ocry | -0.097 |
sho | -0.092 |
iple | -0.092 |
KE | -0.091 |
enty | -0.089 |
Token | h |
Token ID | 289 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
� | +1.309 |
upgr | +1.241 |
王 | +1.074 |
mathemat | +1.067 |
nodd | +1.059 |
Neg logit contributions | |
ocry | -1.043 |
sho | -0.998 |
iple | -0.988 |
KE | -0.983 |
enty | -0.955 |
Token | ul |
Token ID | 377 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
� | +0.557 |
upgr | +0.537 |
mathemat | +0.468 |
王 | +0.467 |
nodd | +0.466 |
Neg logit contributions | |
ocry | -0.404 |
iple | -0.379 |
sho | -0.371 |
enty | -0.368 |
KE | -0.367 |
Token | 4 |
Token ID | 604 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
� | +1.190 |
upgr | +1.124 |
mathemat | +0.945 |
nodd | +0.943 |
王 | +0.941 |
Neg logit contributions | |
ocry | -1.167 |
iple | -1.107 |
KE | -1.094 |
sho | -1.090 |
enty | -1.074 |
Token | 64 |
Token ID | 2414 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
� | +1.918 |
upgr | +1.821 |
王 | +1.554 |
nodd | +1.545 |
mathemat | +1.544 |
Neg logit contributions | |
ocry | -1.578 |
iple | -1.506 |
KE | -1.474 |
sho | -1.472 |
enty | -1.445 |
Token | 406 |
Token ID | 29703 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
� | +1.821 |
upgr | +1.731 |
mathemat | +1.464 |
nodd | +1.460 |
王 | +1.452 |
Neg logit contributions | |
ocry | -1.615 |
iple | -1.524 |
KE | -1.504 |
sho | -1.495 |
enty | -1.481 |
Token | Mem |
Token ID | 4942 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
� | +0.096 |
upgr | +0.092 |
王 | +0.081 |
mathemat | +0.081 |
nodd | +0.081 |
Neg logit contributions | |
ocry | -0.054 |
iple | -0.050 |
KE | -0.050 |
sho | -0.049 |
enty | -0.048 |
Token | c |
Token ID | 66 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
� | +0.421 |
upgr | +0.405 |
nodd | +0.358 |
mathemat | +0.354 |
王 | +0.337 |
Neg logit contributions | |
ocry | -0.469 |
iple | -0.443 |
sho | -0.432 |
cript | -0.432 |
enty | -0.431 |
Token | py |
Token ID | 9078 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
� | +2.807 |
upgr | +2.503 |
王 | +1.837 |
tuning | +1.784 |
isphere | +1.776 |
Neg logit contributions | |
ocry | -5.665 |
KE | -5.466 |
sho | -5.425 |
iple | -5.418 |
arij | -5.331 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
� | +4.580 |
upgr | +4.280 |
王 | +3.529 |
mathemat | +3.478 |
nodd | +3.439 |
Neg logit contributions | |
ocry | -5.000 |
iple | -4.805 |
sho | -4.723 |
KE | -4.716 |
arij | -4.629 |
Token | 55 |
Token ID | 5996 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
� | +0.692 |
upgr | +0.658 |
mathemat | +0.578 |
nodd | +0.574 |
王 | +0.572 |
Neg logit contributions | |
ocry | -0.421 |
iple | -0.391 |
KE | -0.389 |
sho | -0.387 |
enty | -0.378 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
� | +1.910 |
upgr | +1.832 |
王 | +1.633 |
mathemat | +1.623 |
nodd | +1.622 |
Neg logit contributions | |
ocry | -0.715 |
iple | -0.653 |
KE | -0.632 |
sho | -0.628 |
enty | -0.610 |
Token | 953 |
Token ID | 49649 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
� | +0.672 |
upgr | +0.639 |
nodd | +0.541 |
mathemat | +0.539 |
王 | +0.532 |
Neg logit contributions | |
ocry | -0.673 |
iple | -0.644 |
KE | -0.632 |
sho | -0.631 |
enty | -0.619 |
Token | 16 |
Token ID | 1467 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
� | +1.013 |
upgr | +0.969 |
mathemat | +0.847 |
nodd | +0.846 |
王 | +0.844 |
Neg logit contributions | |
ocry | -0.588 |
iple | -0.546 |
KE | -0.539 |
sho | -0.535 |
enty | -0.524 |
Token | )) |
Token ID | 4008 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ocry | +1.020 |
iple | +0.938 |
KE | +0.937 |
sho | +0.917 |
enty | +0.916 |
Neg logit contributions | |
� | -2.043 |
upgr | -1.971 |
nodd | -1.818 |
mathemat | -1.807 |
王 | -1.756 |
Token | sq |
Token ID | 19862 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
ocry | +0.989 |
sho | +0.950 |
iple | +0.926 |
KE | +0.916 |
ff | +0.899 |
Neg logit contributions | |
� | -1.551 |
upgr | -1.450 |
王 | -1.316 |
mathemat | -1.302 |
nodd | -1.290 |
Token | K |
Token ID | 42 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
� | +0.617 |
upgr | +0.594 |
mathemat | +0.529 |
nodd | +0.529 |
王 | +0.526 |
Neg logit contributions | |
ocry | -0.242 |
iple | -0.221 |
KE | -0.216 |
sho | -0.214 |
enty | -0.208 |
Token | ernel |
Token ID | 7948 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
� | +0.360 |
upgr | +0.345 |
nodd | +0.297 |
mathemat | +0.297 |
王 | +0.293 |
Neg logit contributions | |
ocry | -0.303 |
iple | -0.287 |
KE | -0.280 |
sho | -0.279 |
enty | -0.277 |
Token | = |
Token ID | 796 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
� | +1.831 |
upgr | +1.698 |
王 | +1.410 |
mathemat | +1.363 |
tuning | +1.362 |
Neg logit contributions | |
ocry | -2.066 |
iple | -1.970 |
KE | -1.937 |
sho | -1.936 |
enty | -1.910 |
Token | c |
Token ID | 269 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
� | +0.552 |
upgr | +0.527 |
mathemat | +0.475 |
nodd | +0.474 |
王 | +0.467 |
Neg logit contributions | |
ocry | -0.303 |
KE | -0.281 |
iple | -0.281 |
sho | -0.280 |
enty | -0.269 |
Token | v |
Token ID | 85 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
� | +4.134 |
upgr | +3.793 |
王 | +3.049 |
isphere | +2.985 |
tuning | +2.959 |
Neg logit contributions | |
ocry | -5.346 |
KE | -5.136 |
iple | -5.114 |
sho | -5.069 |
teasp | -5.031 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
� | +4.311 |
upgr | +3.894 |
王 | +3.164 |
Instance | +3.084 |
isphere | +3.025 |
Neg logit contributions | |
ocry | -5.996 |
teasp | -5.807 |
iple | -5.728 |
KE | -5.662 |
sho | -5.652 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
� | +4.254 |
upgr | +3.906 |
王 | +3.375 |
Instance | +3.286 |
tuning | +3.260 |
Neg logit contributions | |
ocry | -3.490 |
teasp | -3.332 |
iple | -3.320 |
arij | -3.218 |
KE | -3.206 |
Token | get |
Token ID | 1136 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
� | +3.245 |
upgr | +3.014 |
王 | +2.502 |
Instance | +2.471 |
isphere | +2.430 |
Neg logit contributions | |
ocry | -3.490 |
teasp | -3.250 |
sho | -3.245 |
iple | -3.241 |
KE | -3.229 |
Token | Struct |
Token ID | 44909 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
� | +1.621 |
upgr | +1.477 |
mathemat | +1.070 |
nodd | +1.069 |
王 | +1.040 |
Neg logit contributions | |
ocry | -3.905 |
iple | -3.768 |
KE | -3.734 |
sho | -3.723 |
enty | -3.685 |
Token | art |
Token ID | 433 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
� | +0.930 |
upgr | +0.897 |
nodd | +0.801 |
mathemat | +0.798 |
王 | +0.788 |
Neg logit contributions | |
ocry | -0.419 |
iple | -0.389 |
sho | -0.375 |
KE | -0.373 |
enty | -0.370 |
Token | ext |
Token ID | 2302 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
� | +2.210 |
upgr | +2.081 |
王 | +1.743 |
mathemat | +1.737 |
nodd | +1.731 |
Neg logit contributions | |
ocry | -2.149 |
iple | -2.041 |
KE | -2.022 |
sho | -2.012 |
enty | -1.975 |
Token | [ |
Token ID | 58 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
� | +1.445 |
upgr | +1.338 |
mathemat | +1.045 |
王 | +1.043 |
nodd | +1.043 |
Neg logit contributions | |
ocry | -2.367 |
iple | -2.273 |
KE | -2.249 |
sho | -2.242 |
enty | -2.215 |
Token | $ |
Token ID | 3 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
� | +2.817 |
upgr | +2.624 |
王 | +2.230 |
Instance | +2.152 |
tuning | +2.151 |
Neg logit contributions | |
ocry | -2.615 |
iple | -2.462 |
KE | -2.450 |
sho | -2.414 |
arij | -2.379 |
Token | i |
Token ID | 72 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
� | +1.666 |
upgr | +1.587 |
mathemat | +1.369 |
nodd | +1.367 |
王 | +1.367 |
Neg logit contributions | |
ocry | -1.172 |
iple | -1.102 |
KE | -1.085 |
sho | -1.080 |
enty | -1.060 |
Token | - |
Token ID | 12 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
� | +3.646 |
upgr | +3.378 |
王 | +2.872 |
tuning | +2.783 |
Instance | +2.781 |
Neg logit contributions | |
ocry | -3.218 |
iple | -3.045 |
KE | -3.008 |
sho | -2.982 |
enty | -2.934 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
� | +3.584 |
upgr | +3.172 |
王 | +2.517 |
Instance | +2.408 |
isphere | +2.401 |
Neg logit contributions | |
ocry | -5.866 |
KE | -5.592 |
iple | -5.560 |
sho | -5.538 |
teasp | -5.512 |
Token | ], |
Token ID | 4357 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
� | +2.521 |
upgr | +2.338 |
王 | +1.945 |
tuning | +1.876 |
isphere | +1.868 |
Neg logit contributions | |
ocry | -2.846 |
iple | -2.701 |
KE | -2.686 |
sho | -2.666 |
enty | -2.622 |
Token | $ |
Token ID | 720 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
� | +0.183 |
upgr | +0.175 |
mathemat | +0.152 |
nodd | +0.152 |
王 | +0.146 |
Neg logit contributions | |
ocry | -0.167 |
iple | -0.158 |
KE | -0.157 |
sho | -0.157 |
enty | -0.153 |
Token | font |
Token ID | 10331 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
ocry | +0.788 |
iple | +0.755 |
KE | +0.729 |
sho | +0.728 |
enty | +0.726 |
Neg logit contributions | |
� | -0.956 |
upgr | -0.916 |
mathemat | -0.783 |
nodd | -0.782 |
王 | -0.771 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
� | +2.751 |
upgr | +2.587 |
mathemat | +2.137 |
nodd | +2.133 |
王 | +2.124 |
Neg logit contributions | |
ocry | -3.215 |
iple | -3.069 |
KE | -3.030 |
sho | -3.021 |
enty | -2.980 |
Token | = |
Token ID | 796 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
� | +3.337 |
upgr | +3.010 |
王 | +2.522 |
Instance | +2.428 |
isphere | +2.402 |
Neg logit contributions | |
ocry | -4.008 |
iple | -3.830 |
KE | -3.746 |
sho | -3.731 |
arij | -3.717 |
Token | New |
Token ID | 968 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
� | +1.272 |
upgr | +1.210 |
nodd | +1.053 |
mathemat | +1.052 |
王 | +1.037 |
Neg logit contributions | |
ocry | -0.991 |
iple | -0.932 |
KE | -0.927 |
sho | -0.921 |
enty | -0.902 |
Token | - |
Token ID | 12 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
� | +1.772 |
upgr | +1.674 |
王 | +1.427 |
mathemat | +1.409 |
nodd | +1.406 |
Neg logit contributions | |
ocry | -1.459 |
iple | -1.384 |
KE | -1.357 |
sho | -1.352 |
enty | -1.331 |
Token | Object |
Token ID | 10267 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
� | +2.561 |
upgr | +2.361 |
王 | +2.003 |
Instance | +1.957 |
tuning | +1.898 |
Neg logit contributions | |
ocry | -2.718 |
iple | -2.601 |
KE | -2.541 |
sho | -2.539 |
arij | -2.507 |
Token | System |
Token ID | 4482 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
� | +0.573 |
upgr | +0.552 |
nodd | +0.497 |
mathemat | +0.496 |
王 | +0.490 |
Neg logit contributions | |
ocry | -0.218 |
iple | -0.197 |
KE | -0.194 |
sho | -0.193 |
enty | -0.187 |
Token | . |
Token ID | 13 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
� | +2.455 |
upgr | +2.296 |
王 | +1.983 |
tuning | +1.926 |
Instance | +1.913 |
Neg logit contributions | |
ocry | -1.856 |
iple | -1.763 |
KE | -1.715 |
sho | -1.704 |
arij | -1.682 |
Token | Draw |
Token ID | 25302 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
� | +4.729 |
upgr | +4.196 |
王 | +3.715 |
Instance | +3.671 |
Sup | +3.599 |
Neg logit contributions | |
ocry | -4.728 |
teasp | -4.615 |
iple | -4.549 |
sho | -4.435 |
KE | -4.431 |
Token | ing |
Token ID | 278 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
� | +1.380 |
upgr | +1.298 |
王 | +1.084 |
mathemat | +1.077 |
nodd | +1.075 |
Neg logit contributions | |
ocry | -1.414 |
iple | -1.347 |
KE | -1.329 |
sho | -1.324 |
enty | -1.303 |
Token | . |
Token ID | 13 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
� | +1.609 |
upgr | +1.528 |
王 | +1.318 |
mathemat | +1.310 |
nodd | +1.307 |
Neg logit contributions | |
ocry | -1.140 |
iple | -1.074 |
KE | -1.054 |
sho | -1.049 |
enty | -1.031 |
Token | Rect |
Token ID | 45474 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
� | +2.616 |
upgr | +2.500 |
nodd | +2.133 |
mathemat | +2.122 |
王 | +2.039 |
Neg logit contributions | |
ocry | -2.923 |
iple | -2.783 |
KE | -2.745 |
sho | -2.727 |
enty | -2.706 |
Token | angle |
Token ID | 9248 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +1.948 |
upgr | +1.880 |
nodd | +1.693 |
mathemat | +1.691 |
王 | +1.679 |
Neg logit contributions | |
ocry | -0.667 |
iple | -0.605 |
KE | -0.581 |
sho | -0.578 |
enty | -0.565 |
Token | presidents |
Token ID | 19033 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ocry | +0.183 |
sho | +0.176 |
KE | +0.176 |
iple | +0.172 |
enty | +0.169 |
Neg logit contributions | |
� | -0.220 |
upgr | -0.209 |
nodd | -0.179 |
mathemat | -0.179 |
王 | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ocry | +1.276 |
sho | +1.260 |
iple | +1.225 |
KE | +1.222 |
enty | +1.198 |
Neg logit contributions | |
� | -1.836 |
upgr | -1.795 |
mathemat | -1.546 |
nodd | -1.543 |
王 | -1.521 |
Token | veterans |
Token ID | 11255 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ocry | +0.480 |
sho | +0.473 |
iple | +0.468 |
KE | +0.460 |
enty | +0.448 |
Neg logit contributions | |
� | -0.604 |
upgr | -0.567 |
王 | -0.493 |
mathemat | -0.490 |
nodd | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
ocry | +0.576 |
sho | +0.550 |
iple | +0.540 |
KE | +0.537 |
enty | +0.526 |
Neg logit contributions | |
� | -0.901 |
upgr | -0.874 |
nodd | -0.772 |
mathemat | -0.771 |
王 | -0.758 |
Token | Why |
Token ID | 4162 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ocry | +0.319 |
KE | +0.308 |
sho | +0.296 |
enty | +0.291 |
iple | +0.291 |
Neg logit contributions | |
� | -0.441 |
upgr | -0.435 |
mathemat | -0.392 |
nodd | -0.390 |
tuning | -0.364 |
Token | not |
Token ID | 407 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
� | +0.925 |
upgr | +0.887 |
nodd | +0.767 |
mathemat | +0.766 |
王 | +0.761 |
Neg logit contributions | |
ocry | -0.786 |
sho | -0.744 |
KE | -0.728 |
iple | -0.712 |
enty | -0.709 |
Token | raise |
Token ID | 5298 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
� | +5.056 |
upgr | +4.807 |
nodd | +4.079 |
mathemat | +4.078 |
王 | +4.058 |
Neg logit contributions | |
ocry | -4.355 |
iple | -4.138 |
KE | -4.048 |
sho | -4.030 |
enty | -3.984 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ocry | +0.328 |
KE | +0.316 |
sho | +0.312 |
iple | +0.308 |
enty | +0.301 |
Neg logit contributions | |
� | -0.428 |
upgr | -0.399 |
mathemat | -0.350 |
王 | -0.347 |
nodd | -0.345 |
Token | slave |
Token ID | 11778 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
� | +0.825 |
upgr | +0.775 |
mathemat | +0.659 |
王 | +0.654 |
nodd | +0.652 |
Neg logit contributions | |
ocry | -0.780 |
KE | -0.749 |
sho | -0.748 |
iple | -0.739 |
enty | -0.723 |
Token | monument |
Token ID | 17757 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
ocry | +0.247 |
iple | +0.235 |
sho | +0.234 |
KE | +0.229 |
enty | +0.224 |
Neg logit contributions | |
� | -0.304 |
upgr | -0.289 |
mathemat | -0.257 |
nodd | -0.251 |
王 | -0.250 |
Token | alongside |
Token ID | 7848 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
� | +0.422 |
upgr | +0.402 |
mathemat | +0.354 |
nodd | +0.350 |
王 | +0.348 |
Neg logit contributions | |
ocry | -0.290 |
sho | -0.272 |
iple | -0.271 |
KE | -0.271 |
enty | -0.263 |
Token | kernel |
Token ID | 9720 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ocry | +1.528 |
KE | +1.501 |
sho | +1.489 |
iple | +1.479 |
enty | +1.384 |
Neg logit contributions | |
� | -3.077 |
upgr | -2.936 |
mathemat | -2.715 |
nodd | -2.713 |
王 | -2.672 |
Token | rect |
Token ID | 13621 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ocry | +0.258 |
iple | +0.246 |
KE | +0.245 |
sho | +0.245 |
enty | +0.239 |
Neg logit contributions | |
� | -0.282 |
upgr | -0.267 |
nodd | -0.234 |
mathemat | -0.232 |
王 | -0.231 |
Token | K |
Token ID | 42 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
� | +3.879 |
upgr | +3.663 |
王 | +3.289 |
Instance | +3.200 |
tuning | +3.197 |
Neg logit contributions | |
ocry | -1.684 |
iple | -1.534 |
sho | -1.499 |
KE | -1.473 |
enty | -1.457 |
Token | ernel |
Token ID | 7948 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
� | +1.662 |
upgr | +1.573 |
mathemat | +1.333 |
王 | +1.331 |
nodd | +1.331 |
Neg logit contributions | |
ocry | -1.460 |
iple | -1.383 |
KE | -1.365 |
sho | -1.359 |
enty | -1.336 |
Token | = |
Token ID | 796 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
� | +3.250 |
upgr | +2.878 |
王 | +2.420 |
Instance | +2.375 |
isphere | +2.312 |
Neg logit contributions | |
ocry | -4.124 |
iple | -3.936 |
teasp | -3.928 |
sho | -3.868 |
arij | -3.865 |
Token | c |
Token ID | 269 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
� | +1.256 |
upgr | +1.199 |
mathemat | +1.077 |
nodd | +1.077 |
王 | +1.064 |
Neg logit contributions | |
ocry | -0.686 |
KE | -0.635 |
iple | -0.635 |
sho | -0.634 |
enty | -0.610 |
Token | v |
Token ID | 85 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
� | +4.057 |
upgr | +3.736 |
王 | +3.014 |
isphere | +2.941 |
tuning | +2.926 |
Neg logit contributions | |
ocry | -5.139 |
KE | -4.921 |
iple | -4.903 |
sho | -4.866 |
enty | -4.773 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
� | +3.771 |
upgr | +3.428 |
王 | +2.789 |
Instance | +2.694 |
tuning | +2.669 |
Neg logit contributions | |
ocry | -5.031 |
iple | -4.807 |
teasp | -4.764 |
KE | -4.750 |
sho | -4.740 |
Token | . |
Token ID | 13 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
� | +3.889 |
upgr | +3.599 |
王 | +3.097 |
tuning | +3.010 |
Instance | +3.006 |
Neg logit contributions | |
ocry | -3.116 |
iple | -2.958 |
teasp | -2.923 |
KE | -2.871 |
arij | -2.858 |
Token | get |
Token ID | 1136 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
� | +2.962 |
upgr | +2.771 |
王 | +2.275 |
isphere | +2.240 |
Instance | +2.235 |
Neg logit contributions | |
ocry | -3.204 |
KE | -2.985 |
sho | -2.973 |
iple | -2.970 |
teasp | -2.950 |
Token | Struct |
Token ID | 44909 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
� | +1.417 |
upgr | +1.303 |
nodd | +0.963 |
mathemat | +0.961 |
王 | +0.917 |
Neg logit contributions | |
ocry | -3.361 |
iple | -3.242 |
KE | -3.207 |
sho | -3.200 |
enty | -3.169 |
Token | Br |
Token ID | 9414 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
� | +1.410 |
upgr | +1.355 |
mathemat | +1.191 |
nodd | +1.190 |
王 | +1.162 |
Neg logit contributions | |
ocry | -0.931 |
iple | -0.874 |
KE | -0.859 |
sho | -0.853 |
enty | -0.840 |
Token | ush |
Token ID | 1530 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
� | +1.697 |
upgr | +1.606 |
王 | +1.359 |
mathemat | +1.358 |
nodd | +1.356 |
Neg logit contributions | |
ocry | -1.493 |
iple | -1.414 |
KE | -1.396 |
sho | -1.389 |
enty | -1.366 |
Token | ( |
Token ID | 357 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
� | +1.171 |
upgr | +1.120 |
mathemat | +0.978 |
nodd | +0.977 |
王 | +0.971 |
Neg logit contributions | |
ocry | -0.737 |
iple | -0.690 |
KE | -0.679 |
sho | -0.676 |
enty | -0.662 |
Token | [ |
Token ID | 685 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
� | +2.440 |
upgr | +2.289 |
mathemat | +1.886 |
nodd | +1.874 |
王 | +1.849 |
Neg logit contributions | |
ocry | -2.960 |
iple | -2.822 |
KE | -2.794 |
sho | -2.774 |
enty | -2.730 |
Token | System |
Token ID | 11964 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
� | +1.915 |
upgr | +1.816 |
王 | +1.555 |
mathemat | +1.552 |
nodd | +1.548 |
Neg logit contributions | |
ocry | -1.495 |
iple | -1.412 |
KE | -1.392 |
sho | -1.385 |
enty | -1.360 |
Token | . |
Token ID | 13 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
� | +2.669 |
upgr | +2.498 |
王 | +2.154 |
tuning | +2.094 |
Instance | +2.077 |
Neg logit contributions | |
ocry | -2.010 |
iple | -1.908 |
KE | -1.860 |
sho | -1.846 |
arij | -1.821 |
Token | Draw |
Token ID | 25302 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
� | +4.679 |
upgr | +4.238 |
王 | +3.706 |
Instance | +3.605 |
Sup | +3.555 |
Neg logit contributions | |
ocry | -4.399 |
iple | -4.218 |
teasp | -4.144 |
KE | -4.143 |
sho | -4.128 |
Token | ing |
Token ID | 278 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
� | +1.536 |
upgr | +1.443 |
王 | +1.204 |
mathemat | +1.193 |
nodd | +1.190 |
Neg logit contributions | |
ocry | -1.581 |
iple | -1.507 |
KE | -1.488 |
sho | -1.481 |
enty | -1.457 |
Token | . |
Token ID | 13 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
� | +1.431 |
upgr | +1.366 |
mathemat | +1.186 |
nodd | +1.185 |
王 | +1.177 |
Neg logit contributions | |
ocry | -0.990 |
iple | -0.930 |
KE | -0.916 |
sho | -0.912 |
enty | -0.895 |
Token | Color |
Token ID | 10258 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
� | +2.316 |
upgr | +2.141 |
王 | +1.663 |
mathemat | +1.663 |
nodd | +1.658 |
Neg logit contributions | |
ocry | -3.884 |
iple | -3.731 |
KE | -3.693 |
sho | -3.683 |
enty | -3.639 |
Token | ] |
Token ID | 60 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
� | +1.028 |
upgr | +0.977 |
mathemat | +0.835 |
nodd | +0.834 |
王 | +0.831 |
Neg logit contributions | |
ocry | -0.851 |
iple | -0.804 |
KE | -0.793 |
sho | -0.789 |
enty | -0.776 |
Token | Inc |
Token ID | 3457 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
� | +2.013 |
upgr | +1.894 |
mathemat | +1.589 |
nodd | +1.583 |
王 | +1.580 |
Neg logit contributions | |
ocry | -2.132 |
iple | -2.026 |
KE | -2.017 |
sho | -2.007 |
enty | -1.972 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
� | +1.426 |
upgr | +1.355 |
mathemat | +1.165 |
nodd | +1.163 |
王 | +1.162 |
Neg logit contributions | |
ocry | -1.068 |
iple | -1.006 |
KE | -0.991 |
sho | -0.987 |
enty | -0.968 |
Token | 144 |
Token ID | 20224 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
ocry | +0.088 |
KE | +0.083 |
iple | +0.083 |
sho | +0.082 |
enty | +0.080 |
Neg logit contributions | |
� | -0.147 |
upgr | -0.139 |
nodd | -0.122 |
王 | -0.122 |
mathemat | -0.122 |
Token | 69 |
Token ID | 3388 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
� | +0.285 |
upgr | +0.273 |
mathemat | +0.243 |
nodd | +0.242 |
王 | +0.237 |
Neg logit contributions | |
ocry | -0.156 |
KE | -0.146 |
iple | -0.144 |
sho | -0.144 |
enty | -0.140 |
Token | 77 |
Token ID | 3324 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
� | +0.224 |
upgr | +0.215 |
mathemat | +0.190 |
nodd | +0.190 |
王 | +0.185 |
Neg logit contributions | |
ocry | -0.137 |
KE | -0.128 |
sho | -0.127 |
iple | -0.127 |
enty | -0.123 |
Token | Ontario |
Token ID | 10553 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ocry | +0.199 |
KE | +0.188 |
sho | +0.186 |
iple | +0.186 |
enty | +0.181 |
Neg logit contributions | |
� | -0.222 |
upgr | -0.212 |
mathemat | -0.185 |
nodd | -0.184 |
王 | -0.177 |
Token | Inc |
Token ID | 3457 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
� | +4.627 |
upgr | +4.382 |
王 | +3.669 |
nodd | +3.648 |
mathemat | +3.647 |
Neg logit contributions | |
ocry | -4.398 |
iple | -4.193 |
sho | -4.086 |
KE | -4.070 |
enty | -4.034 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
� | +1.756 |
upgr | +1.667 |
mathemat | +1.432 |
nodd | +1.428 |
王 | +1.427 |
Neg logit contributions | |
ocry | -1.339 |
iple | -1.262 |
KE | -1.244 |
sho | -1.239 |
enty | -1.213 |
Token | 213 |
Token ID | 28658 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ocry | +0.080 |
KE | +0.075 |
sho | +0.074 |
iple | +0.074 |
enty | +0.072 |
Neg logit contributions | |
� | -0.152 |
upgr | -0.144 |
nodd | -0.128 |
王 | -0.128 |
mathemat | -0.127 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
� | +1.207 |
upgr | +1.165 |
mathemat | +1.032 |
nodd | +1.028 |
王 | +1.002 |
Neg logit contributions | |
ocry | -0.739 |
KE | -0.687 |
iple | -0.684 |
sho | -0.680 |
enty | -0.663 |
Token | 42 |
Token ID | 3682 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
� | +0.780 |
upgr | +0.751 |
mathemat | +0.668 |
nodd | +0.663 |
王 | +0.647 |
Neg logit contributions | |
ocry | -0.485 |
KE | -0.456 |
sho | -0.451 |
iple | -0.449 |
enty | -0.436 |
Token | Inc |
Token ID | 3457 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
� | +4.627 |
upgr | +4.382 |
王 | +3.669 |
nodd | +3.648 |
mathemat | +3.647 |
Neg logit contributions | |
ocry | -4.398 |
iple | -4.193 |
sho | -4.086 |
KE | -4.070 |
enty | -4.034 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
� | +1.756 |
upgr | +1.667 |
mathemat | +1.432 |
nodd | +1.428 |
王 | +1.427 |
Neg logit contributions | |
ocry | -1.339 |
iple | -1.262 |
KE | -1.244 |
sho | -1.239 |
enty | -1.213 |
Token | 213 |
Token ID | 28658 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ocry | +0.080 |
KE | +0.075 |
sho | +0.074 |
iple | +0.074 |
enty | +0.072 |
Neg logit contributions | |
� | -0.152 |
upgr | -0.144 |
nodd | -0.128 |
王 | -0.128 |
mathemat | -0.127 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
� | +1.207 |
upgr | +1.165 |
mathemat | +1.032 |
nodd | +1.028 |
王 | +1.002 |
Neg logit contributions | |
ocry | -0.739 |
KE | -0.687 |
iple | -0.684 |
sho | -0.680 |
enty | -0.663 |
Token | 42 |
Token ID | 3682 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
� | +0.780 |
upgr | +0.751 |
mathemat | +0.668 |
nodd | +0.663 |
王 | +0.647 |
Neg logit contributions | |
ocry | -0.485 |
KE | -0.456 |
sho | -0.451 |
iple | -0.449 |
enty | -0.436 |
Token | Ontario |
Token ID | 10553 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
� | +0.398 |
upgr | +0.378 |
mathemat | +0.326 |
nodd | +0.323 |
王 | +0.313 |
Neg logit contributions | |
ocry | -0.416 |
KE | -0.394 |
iple | -0.392 |
sho | -0.391 |
enty | -0.382 |
Token | Inc |
Token ID | 3457 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
� | +3.933 |
upgr | +3.685 |
王 | +2.969 |
mathemat | +2.955 |
nodd | +2.951 |
Neg logit contributions | |
ocry | -5.084 |
iple | -4.880 |
sho | -4.771 |
KE | -4.757 |
enty | -4.716 |
Token | . |
Token ID | 13 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
� | +2.260 |
upgr | +2.142 |
mathemat | +1.836 |
王 | +1.829 |
nodd | +1.827 |
Neg logit contributions | |
ocry | -1.785 |
iple | -1.683 |
KE | -1.662 |
sho | -1.653 |
enty | -1.616 |
Token | and |
Token ID | 290 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
� | +0.512 |
upgr | +0.489 |
nodd | +0.427 |
mathemat | +0.427 |
王 | +0.424 |
Neg logit contributions | |
ocry | -0.317 |
iple | -0.298 |
KE | -0.295 |
sho | -0.293 |
enty | -0.286 |
Token | 213 |
Token ID | 28658 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ocry | +0.232 |
KE | +0.222 |
sho | +0.219 |
iple | +0.217 |
enty | +0.211 |
Neg logit contributions | |
� | -0.425 |
upgr | -0.402 |
nodd | -0.357 |
mathemat | -0.357 |
王 | -0.357 |
Token | 50 |
Token ID | 1120 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ocry | +0.045 |
KE | +0.042 |
sho | +0.042 |
iple | +0.042 |
enty | +0.041 |
Neg logit contributions | |
� | -0.082 |
upgr | -0.080 |
mathemat | -0.072 |
nodd | -0.071 |
isphere | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
� | +0.958 |
upgr | +0.931 |
mathemat | +0.822 |
nodd | +0.814 |
王 | +0.797 |
Neg logit contributions | |
ocry | -0.706 |
KE | -0.677 |
iple | -0.665 |
sho | -0.660 |
enty | -0.644 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
� | +1.610 |
upgr | +1.529 |
mathemat | +1.305 |
nodd | +1.303 |
王 | +1.292 |
Neg logit contributions | |
ocry | -1.419 |
iple | -1.343 |
KE | -1.327 |
sho | -1.322 |
enty | -1.300 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
� | +1.317 |
upgr | +1.296 |
nodd | +1.135 |
mathemat | +1.134 |
tuning | +1.064 |
Neg logit contributions | |
ocry | -1.236 |
iple | -1.178 |
KE | -1.156 |
sho | -1.144 |
enty | -1.142 |
Token | to |
Token ID | 284 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
� | +0.948 |
upgr | +0.903 |
mathemat | +0.785 |
nodd | +0.782 |
王 | +0.778 |
Neg logit contributions | |
ocry | -0.665 |
iple | -0.624 |
KE | -0.621 |
sho | -0.615 |
enty | -0.604 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ocry | +1.254 |
KE | +1.226 |
iple | +1.198 |
sho | +1.197 |
FF | +1.158 |
Neg logit contributions | |
� | -1.757 |
upgr | -1.679 |
nodd | -1.453 |
mathemat | -1.452 |
王 | -1.441 |
Token | Sch |
Token ID | 3059 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
ocry | +0.473 |
KE | +0.447 |
iple | +0.442 |
sho | +0.436 |
enty | +0.422 |
Neg logit contributions | |
� | -0.838 |
upgr | -0.802 |
mathemat | -0.701 |
王 | -0.700 |
nodd | -0.699 |
Token | m |
Token ID | 76 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ocry | +2.829 |
iple | +2.670 |
sho | +2.553 |
enty | +2.546 |
KE | +2.521 |
Neg logit contributions | |
� | -3.837 |
upgr | -3.761 |
王 | -3.257 |
mathemat | -3.245 |
nodd | -3.203 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ocry | +0.825 |
iple | +0.769 |
KE | +0.747 |
enty | +0.742 |
sho | +0.739 |
Neg logit contributions | |
� | -1.068 |
upgr | -1.034 |
mathemat | -0.905 |
王 | -0.892 |
nodd | -0.883 |
Token | Know |
Token ID | 9365 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ocry | +1.332 |
sho | +1.252 |
KE | +1.238 |
iple | +1.231 |
enty | +1.204 |
Neg logit contributions | |
� | -2.330 |
upgr | -2.233 |
mathemat | -1.968 |
王 | -1.952 |
nodd | -1.942 |
Token | Movie |
Token ID | 15875 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
ocry | +0.257 |
sho | +0.241 |
iple | +0.240 |
KE | +0.238 |
enty | +0.234 |
Neg logit contributions | |
� | -0.348 |
upgr | -0.330 |
mathemat | -0.294 |
nodd | -0.288 |
王 | -0.284 |
Token | Show |
Token ID | 5438 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
ocry | +0.300 |
sho | +0.284 |
iple | +0.282 |
KE | +0.282 |
enty | +0.273 |
Neg logit contributions | |
� | -0.469 |
upgr | -0.446 |
mathemat | -0.393 |
王 | -0.389 |
nodd | -0.385 |
Token | / |
Token ID | 14 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ocry | +1.629 |
KE | +1.538 |
iple | +1.526 |
sho | +1.521 |
enty | +1.502 |
Neg logit contributions | |
� | -1.999 |
upgr | -1.965 |
nodd | -1.769 |
mathemat | -1.765 |
unemploy | -1.652 |
Token | index |
Token ID | 9630 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
ocry | +1.653 |
KE | +1.598 |
sho | +1.532 |
enty | +1.526 |
iple | +1.522 |
Neg logit contributions | |
� | -2.887 |
upgr | -2.802 |
mathemat | -2.534 |
nodd | -2.493 |
王 | -2.415 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ocry | +1.590 |
iple | +1.470 |
sho | +1.454 |
KE | +1.443 |
enty | +1.422 |
Neg logit contributions | |
� | -2.632 |
upgr | -2.562 |
mathemat | -2.335 |
nodd | -2.324 |
unemploy | -2.220 |
Token | php |
Token ID | 10121 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ocry | +0.921 |
iple | +0.875 |
KE | +0.858 |
sho | +0.853 |
enty | +0.846 |
Neg logit contributions | |
� | -1.093 |
upgr | -1.048 |
mathemat | -0.911 |
nodd | -0.910 |
王 | -0.892 |
Token | ? |
Token ID | 30 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ocry | +1.123 |
sho | +1.062 |
KE | +1.048 |
enty | +1.045 |
iple | +1.042 |
Neg logit contributions | |
� | -1.928 |
upgr | -1.885 |
nodd | -1.721 |
mathemat | -1.718 |
unemploy | -1.634 |
Token | topic |
Token ID | 26652 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ocry | +1.215 |
iple | +1.183 |
sho | +1.167 |
KE | +1.155 |
cript | +1.155 |
Neg logit contributions | |
� | -2.974 |
upgr | -2.906 |
nodd | -2.665 |
mathemat | -2.622 |
unemploy | -2.567 |
Token | = |
Token ID | 28 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ocry | +2.960 |
sho | +2.863 |
enty | +2.818 |
iple | +2.795 |
cript | +2.794 |
Neg logit contributions | |
upgr | -3.428 |
� | -3.292 |
nodd | -3.169 |
mathemat | -3.050 |
unemploy | -2.917 |
Token | 28 |
Token ID | 2078 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ocry | +3.913 |
KE | +3.737 |
sho | +3.665 |
enty | +3.628 |
グ | +3.607 |
Neg logit contributions | |
� | -6.621 |
upgr | -6.580 |
mathemat | -6.163 |
nodd | -6.153 |
unemploy | -5.767 |
Token | 18 |
Token ID | 1507 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ocry | +1.718 |
KE | +1.614 |
sho | +1.599 |
iple | +1.569 |
enty | +1.556 |
Neg logit contributions | |
� | -2.880 |
upgr | -2.809 |
mathemat | -2.566 |
nodd | -2.557 |
unemploy | -2.438 |
Token | 48 |
Token ID | 2780 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ocry | +1.859 |
KE | +1.772 |
sho | +1.719 |
iple | +1.707 |
enty | +1.691 |
Neg logit contributions | |
� | -3.137 |
upgr | -3.041 |
nodd | -2.787 |
mathemat | -2.776 |
unemploy | -2.649 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ocry | +1.773 |
KE | +1.685 |
iple | +1.661 |
sho | +1.626 |
enty | +1.599 |
Neg logit contributions | |
� | -3.158 |
upgr | -3.039 |
nodd | -2.749 |
mathemat | -2.729 |
王 | -2.660 |
Token | Walter |
Token ID | 15819 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ocry | +0.869 |
KE | +0.860 |
sho | +0.832 |
iple | +0.806 |
Blu | +0.788 |
Neg logit contributions | |
� | -1.947 |
upgr | -1.921 |
mathemat | -1.697 |
isphere | -1.669 |
nodd | -1.651 |
Token | M |
Token ID | 337 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
ocry | +0.573 |
KE | +0.570 |
sho | +0.543 |
Blu | +0.531 |
iple | +0.521 |
Neg logit contributions | |
� | -1.229 |
upgr | -1.188 |
mathemat | -1.079 |
nodd | -1.052 |
王 | -1.036 |
Token | itty |
Token ID | 9760 |
Feature activation | -9.36e-04 |
Pos logit contributions | |
� | +0.513 |
upgr | +0.499 |
mathemat | +0.441 |
王 | +0.437 |
nodd | +0.435 |
Neg logit contributions | |
ocry | -0.246 |
iple | -0.237 |
sho | -0.233 |
KE | -0.230 |
enty | -0.226 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
� | +0.006 |
upgr | +0.006 |
nodd | +0.005 |
mathemat | +0.005 |
王 | +0.005 |
Neg logit contributions | |
ocry | -0.004 |
iple | -0.003 |
sho | -0.003 |
KE | -0.003 |
enty | -0.003 |
Token | photo |
Token ID | 4590 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ocry | +0.974 |
sho | +0.954 |
KE | +0.936 |
iple | +0.916 |
Blu | +0.892 |
Neg logit contributions | |
� | -1.335 |
upgr | -1.259 |
mathemat | -1.090 |
nodd | -1.086 |
王 | -1.082 |
Token | journal |
Token ID | 24891 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ocry | +0.942 |
sho | +0.886 |
iple | +0.849 |
KE | +0.839 |
enty | +0.818 |
Neg logit contributions | |
� | -2.407 |
upgr | -2.287 |
nodd | -2.057 |
mathemat | -2.053 |
王 | -2.021 |
Token | ist |
Token ID | 396 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ocry | +2.426 |
sho | +2.309 |
iple | +2.234 |
KE | +2.229 |
enty | +2.170 |
Neg logit contributions | |
� | -4.212 |
upgr | -4.016 |
mathemat | -3.595 |
nodd | -3.554 |
王 | -3.552 |
Token | Sean |
Token ID | 11465 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
ocry | +0.994 |
KE | +0.971 |
sho | +0.964 |
iple | +0.930 |
Blu | +0.912 |
Neg logit contributions | |
� | -1.755 |
upgr | -1.689 |
nodd | -1.492 |
mathemat | -1.480 |
王 | -1.472 |
Token | O |
Token ID | 440 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
� | +0.083 |
upgr | +0.079 |
mathemat | +0.070 |
nodd | +0.069 |
王 | +0.069 |
Neg logit contributions | |
ocry | -0.053 |
KE | -0.050 |
sho | -0.049 |
iple | -0.049 |
enty | -0.048 |
Token | ' |
Token ID | 6 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
ocry | +0.930 |
sho | +0.867 |
iple | +0.858 |
KE | +0.856 |
enty | +0.856 |
Neg logit contributions | |
� | -1.824 |
upgr | -1.776 |
mathemat | -1.581 |
王 | -1.567 |
nodd | -1.543 |
Token | Connell |
Token ID | 15559 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
� | +0.226 |
upgr | +0.216 |
mathemat | +0.187 |
nodd | +0.182 |
王 | +0.182 |
Neg logit contributions | |
ocry | -0.178 |
KE | -0.167 |
iple | -0.166 |
sho | -0.166 |
enty | -0.161 |
Token | says |
Token ID | 1139 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ocry | +1.478 |
sho | +1.475 |
KE | +1.430 |
iple | +1.416 |
enty | +1.377 |
Neg logit contributions | |
� | -1.677 |
upgr | -1.519 |
王 | -1.357 |
nodd | -1.325 |
mathemat | -1.317 |
Token | it |
Token ID | 340 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
� | +0.220 |
upgr | +0.203 |
王 | +0.179 |
nodd | +0.176 |
mathemat | +0.176 |
Neg logit contributions | |
ocry | -0.157 |
sho | -0.150 |
KE | -0.149 |
iple | -0.148 |
enty | -0.143 |
Token | will |
Token ID | 481 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ocry | +0.354 |
sho | +0.354 |
KE | +0.340 |
iple | +0.338 |
enty | +0.336 |
Neg logit contributions | |
� | -0.347 |
upgr | -0.328 |
mathemat | -0.286 |
王 | -0.286 |
nodd | -0.283 |
Token | run |
Token ID | 1057 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
ocry | +0.590 |
sho | +0.573 |
KE | +0.558 |
iple | +0.557 |
enty | +0.546 |
Neg logit contributions | |
� | -0.781 |
upgr | -0.730 |
王 | -0.652 |
mathemat | -0.648 |
nodd | -0.641 |
Token | out |
Token ID | 503 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ocry | +0.251 |
sho | +0.237 |
KE | +0.232 |
iple | +0.230 |
enty | +0.228 |
Neg logit contributions | |
� | -0.476 |
upgr | -0.453 |
mathemat | -0.402 |
nodd | -0.400 |
王 | -0.398 |
Token | of |
Token ID | 286 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
ocry | +1.787 |
iple | +1.667 |
sho | +1.659 |
KE | +1.652 |
enty | +1.603 |
Neg logit contributions | |
� | -2.921 |
upgr | -2.776 |
mathemat | -2.440 |
王 | -2.429 |
nodd | -2.412 |
Token | borrowed |
Token ID | 22546 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
sho | +2.920 |
ocry | +2.853 |
KE | +2.774 |
FF | +2.660 |
iple | +2.657 |
Neg logit contributions | |
� | -4.847 |
upgr | -4.326 |
王 | -4.045 |
nodd | -3.949 |
mathemat | -3.948 |
Token | money |
Token ID | 1637 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ocry | +1.545 |
sho | +1.489 |
KE | +1.453 |
iple | +1.412 |
enty | +1.388 |
Neg logit contributions | |
� | -3.014 |
upgr | -2.813 |
王 | -2.547 |
mathemat | -2.535 |
nodd | -2.522 |
Token | remains |
Token ID | 3793 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
� | +0.089 |
upgr | +0.083 |
王 | +0.074 |
mathemat | +0.073 |
nodd | +0.072 |
Neg logit contributions | |
ocry | -0.069 |
sho | -0.066 |
KE | -0.065 |
iple | -0.065 |
enty | -0.064 |
Token | Oct |
Token ID | 2556 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
� | +0.762 |
upgr | +0.713 |
王 | +0.630 |
nodd | +0.627 |
mathemat | +0.624 |
Neg logit contributions | |
ocry | -0.524 |
sho | -0.500 |
iple | -0.493 |
KE | -0.491 |
enty | -0.477 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ocry | +0.648 |
iple | +0.604 |
sho | +0.596 |
KE | +0.591 |
enty | +0.582 |
Neg logit contributions | |
� | -1.033 |
upgr | -0.994 |
nodd | -0.905 |
mathemat | -0.901 |
王 | -0.867 |
Token | / |
Token ID | 14 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
� | +1.286 |
upgr | +1.216 |
mathemat | +1.023 |
nodd | +1.022 |
王 | +1.021 |
Neg logit contributions | |
ocry | -1.232 |
iple | -1.170 |
KE | -1.154 |
sho | -1.150 |
enty | -1.132 |
Token | CBC |
Token ID | 29208 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
� | +0.460 |
upgr | +0.442 |
nodd | +0.384 |
mathemat | +0.383 |
王 | +0.367 |
Neg logit contributions | |
ocry | -0.416 |
iple | -0.395 |
KE | -0.391 |
sho | -0.388 |
enty | -0.383 |
Token | ) |
Token ID | 8 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
� | +1.262 |
upgr | +1.201 |
王 | +1.033 |
mathemat | +1.031 |
nodd | +1.031 |
Neg logit contributions | |
ocry | -0.912 |
iple | -0.861 |
KE | -0.845 |
sho | -0.840 |
enty | -0.827 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
� | +1.944 |
upgr | +1.854 |
mathemat | +1.629 |
nodd | +1.624 |
王 | +1.601 |
Neg logit contributions | |
ocry | -1.430 |
KE | -1.356 |
iple | -1.343 |
sho | -1.338 |
enty | -1.307 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
� | +1.297 |
upgr | +1.235 |
mathemat | +1.059 |
nodd | +1.059 |
王 | +1.043 |
Neg logit contributions | |
ocry | -1.132 |
iple | -1.071 |
KE | -1.059 |
sho | -1.055 |
enty | -1.037 |
Token | Insp |
Token ID | 41502 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
� | +0.822 |
upgr | +0.798 |
nodd | +0.708 |
mathemat | +0.704 |
tuning | +0.657 |
Neg logit contributions | |
ocry | -0.804 |
iple | -0.766 |
KE | -0.754 |
enty | -0.752 |
sho | -0.749 |
Token | ired |
Token ID | 1202 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ocry | +0.978 |
iple | +0.825 |
KE | +0.749 |
enty | +0.718 |
arij | +0.699 |
Neg logit contributions | |
� | -5.695 |
upgr | -5.539 |
mathemat | -5.127 |
nodd | -5.116 |
王 | -5.102 |
Token | by |
Token ID | 416 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
ocry | +1.483 |
sho | +1.426 |
KE | +1.365 |
iple | +1.306 |
enty | +1.302 |
Neg logit contributions | |
� | -4.287 |
upgr | -4.029 |
王 | -3.724 |
nodd | -3.703 |
mathemat | -3.687 |
Token | initiatives |
Token ID | 15446 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ocry | +0.239 |
sho | +0.231 |
KE | +0.227 |
iple | +0.222 |
enty | +0.219 |
Neg logit contributions | |
� | -0.301 |
upgr | -0.283 |
王 | -0.248 |
mathemat | -0.244 |
nodd | -0.243 |
Token | in |
Token ID | 287 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ocry | +1.428 |
sho | +1.392 |
KE | +1.380 |
iple | +1.328 |
enty | +1.296 |
Neg logit contributions | |
� | -2.718 |
upgr | -2.579 |
王 | -2.321 |
nodd | -2.305 |
mathemat | -2.288 |
Token | other |
Token ID | 584 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ocry | +0.994 |
sho | +0.972 |
KE | +0.959 |
iple | +0.930 |
enty | +0.903 |
Neg logit contributions | |
� | -1.326 |
upgr | -1.252 |
王 | -1.111 |
isphere | -1.087 |
nodd | -1.085 |
Token | which |
Token ID | 543 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ocry | +0.907 |
sho | +0.873 |
KE | +0.861 |
iple | +0.843 |
enty | +0.820 |
Neg logit contributions | |
� | -1.349 |
upgr | -1.339 |
nodd | -1.181 |
mathemat | -1.161 |
王 | -1.152 |
Token | is |
Token ID | 318 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
ocry | +0.785 |
iple | +0.756 |
sho | +0.755 |
KE | +0.748 |
enty | +0.720 |
Neg logit contributions | |
� | -0.755 |
upgr | -0.742 |
mathemat | -0.622 |
王 | -0.620 |
nodd | -0.616 |
Token | basically |
Token ID | 6209 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ocry | +0.338 |
sho | +0.323 |
KE | +0.318 |
iple | +0.317 |
enty | +0.303 |
Neg logit contributions | |
� | -0.411 |
upgr | -0.396 |
王 | -0.341 |
mathemat | -0.341 |
nodd | -0.339 |
Token | white |
Token ID | 2330 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
� | +0.743 |
upgr | +0.713 |
王 | +0.613 |
mathemat | +0.612 |
nodd | +0.609 |
Neg logit contributions | |
ocry | -0.563 |
sho | -0.535 |
iple | -0.529 |
KE | -0.527 |
enty | -0.507 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
� | +0.231 |
upgr | +0.224 |
mathemat | +0.197 |
王 | +0.194 |
nodd | +0.193 |
Neg logit contributions | |
ocry | -0.150 |
iple | -0.142 |
sho | -0.142 |
KE | -0.140 |
enty | -0.136 |
Token | � |
Token ID | 447 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ocry | +0.180 |
KE | +0.173 |
sho | +0.169 |
iple | +0.167 |
Blu | +0.164 |
Neg logit contributions | |
upgr | -0.233 |
� | -0.232 |
nodd | -0.205 |
mathemat | -0.204 |
isphere | -0.197 |
Token | � |
Token ID | 251 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
ocry | +0.315 |
iple | +0.280 |
KE | +0.278 |
sho | +0.274 |
enty | +0.270 |
Neg logit contributions | |
� | -0.812 |
upgr | -0.788 |
mathemat | -0.701 |
nodd | -0.694 |
王 | -0.693 |
Token | And |
Token ID | 843 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
� | +0.482 |
upgr | +0.472 |
mathemat | +0.413 |
nodd | +0.411 |
王 | +0.398 |
Neg logit contributions | |
ocry | -0.366 |
KE | -0.348 |
sho | -0.342 |
iple | -0.339 |
enty | -0.334 |
Token | for |
Token ID | 329 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
� | +0.989 |
upgr | +0.957 |
王 | +0.833 |
mathemat | +0.832 |
nodd | +0.829 |
Neg logit contributions | |
ocry | -0.628 |
sho | -0.592 |
KE | -0.590 |
iple | -0.588 |
enty | -0.573 |
Token | some |
Token ID | 617 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
� | +0.135 |
upgr | +0.129 |
mathemat | +0.114 |
nodd | +0.112 |
王 | +0.112 |
Neg logit contributions | |
ocry | -0.092 |
KE | -0.087 |
sho | -0.086 |
iple | -0.085 |
enty | -0.085 |
Token | reason |
Token ID | 1738 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
� | +0.759 |
upgr | +0.730 |
mathemat | +0.634 |
nodd | +0.621 |
王 | +0.618 |
Neg logit contributions | |
ocry | -0.588 |
iple | -0.552 |
sho | -0.550 |
KE | -0.547 |
enty | -0.537 |
Token | different |
Token ID | 1180 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
ocry | +0.186 |
sho | +0.177 |
KE | +0.177 |
iple | +0.175 |
enty | +0.170 |
Neg logit contributions | |
� | -0.259 |
upgr | -0.245 |
王 | -0.214 |
mathemat | -0.213 |
nodd | -0.212 |
Token | boot |
Token ID | 6297 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ocry | +0.236 |
iple | +0.227 |
KE | +0.226 |
sho | +0.226 |
enty | +0.217 |
Neg logit contributions | |
� | -0.291 |
upgr | -0.273 |
nodd | -0.238 |
mathemat | -0.238 |
王 | -0.237 |
Token | mode |
Token ID | 4235 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ocry | +1.204 |
iple | +1.160 |
sho | +1.139 |
KE | +1.136 |
cript | +1.099 |
Neg logit contributions | |
� | -2.083 |
upgr | -1.981 |
mathemat | -1.779 |
nodd | -1.769 |
王 | -1.754 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ocry | +0.420 |
iple | +0.405 |
KE | +0.401 |
sho | +0.398 |
enty | +0.384 |
Neg logit contributions | |
� | -0.709 |
upgr | -0.672 |
王 | -0.596 |
mathemat | -0.594 |
nodd | -0.594 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ocry | +0.604 |
KE | +0.593 |
sho | +0.576 |
iple | +0.574 |
NET | +0.559 |
Neg logit contributions | |
� | -0.821 |
upgr | -0.781 |
mathemat | -0.693 |
nodd | -0.690 |
王 | -0.683 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ocry | +0.746 |
KE | +0.712 |
sho | +0.708 |
iple | +0.699 |
enty | +0.685 |
Neg logit contributions | |
� | -1.010 |
upgr | -0.997 |
mathemat | -0.928 |
nodd | -0.928 |
unemploy | -0.846 |
Token | * |
Token ID | 9 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
ocry | +0.826 |
iple | +0.799 |
KE | +0.787 |
sho | +0.773 |
enty | +0.768 |
Neg logit contributions | |
� | -0.914 |
upgr | -0.882 |
mathemat | -0.773 |
nodd | -0.772 |
王 | -0.733 |
Token | IF |
Token ID | 5064 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
ocry | +0.013 |
KE | +0.012 |
iple | +0.012 |
sho | +0.012 |
enty | +0.012 |
Neg logit contributions | |
� | -0.014 |
upgr | -0.014 |
mathemat | -0.012 |
nodd | -0.012 |
王 | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
� | +0.295 |
upgr | +0.282 |
mathemat | +0.249 |
nodd | +0.248 |
王 | +0.246 |
Neg logit contributions | |
ocry | -0.189 |
KE | -0.183 |
iple | -0.177 |
sho | -0.177 |
enty | -0.173 |
Token | WITH |
Token ID | 13315 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.391 |
upgr | +0.376 |
mathemat | +0.331 |
nodd | +0.330 |
王 | +0.328 |
Neg logit contributions | |
ocry | -0.240 |
KE | -0.229 |
iple | -0.227 |
sho | -0.224 |
enty | -0.217 |
Token | THE |
Token ID | 3336 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
� | +0.951 |
upgr | +0.912 |
nodd | +0.798 |
mathemat | +0.797 |
王 | +0.795 |
Neg logit contributions | |
ocry | -0.580 |
KE | -0.547 |
iple | -0.547 |
sho | -0.538 |
enty | -0.525 |
Token | finished |
Token ID | 5201 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
sho | +1.196 |
ocry | +1.188 |
KE | +1.154 |
iple | +1.108 |
cript | +1.085 |
Neg logit contributions | |
� | -1.829 |
upgr | -1.684 |
王 | -1.514 |
mathemat | -1.486 |
isphere | -1.473 |
Token | tie |
Token ID | 9839 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
sho | +1.698 |
ocry | +1.685 |
KE | +1.643 |
iple | +1.568 |
cript | +1.545 |
Neg logit contributions | |
� | -3.104 |
upgr | -2.953 |
王 | -2.710 |
mathemat | -2.622 |
isphere | -2.611 |
Token | a |
Token ID | 257 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
� | +1.358 |
upgr | +1.294 |
mathemat | +1.135 |
王 | +1.128 |
nodd | +1.104 |
Neg logit contributions | |
ocry | -1.004 |
sho | -0.978 |
KE | -0.957 |
iple | -0.950 |
enty | -0.911 |
Token | knot |
Token ID | 29654 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
sho | +0.821 |
ocry | +0.804 |
KE | +0.782 |
iple | +0.735 |
Blu | +0.723 |
Neg logit contributions | |
� | -1.357 |
upgr | -1.300 |
mathemat | -1.157 |
王 | -1.155 |
isphere | -1.126 |
Token | on |
Token ID | 319 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ocry | +1.152 |
sho | +1.136 |
KE | +1.105 |
iple | +1.102 |
NET | +1.042 |
Neg logit contributions | |
� | -1.853 |
upgr | -1.804 |
mathemat | -1.597 |
王 | -1.581 |
nodd | -1.548 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
sho | +0.547 |
ocry | +0.545 |
KE | +0.527 |
iple | +0.518 |
NET | +0.496 |
Neg logit contributions | |
� | -0.729 |
upgr | -0.692 |
王 | -0.615 |
mathemat | -0.611 |
nodd | -0.588 |
Token | wrong |
Token ID | 2642 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ocry | +0.451 |
sho | +0.448 |
KE | +0.434 |
iple | +0.420 |
enty | +0.403 |
Neg logit contributions | |
� | -0.779 |
upgr | -0.739 |
王 | -0.663 |
mathemat | -0.660 |
nodd | -0.645 |
Token | side |
Token ID | 1735 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
sho | +0.912 |
ocry | +0.902 |
KE | +0.864 |
iple | +0.843 |
enty | +0.801 |
Neg logit contributions | |
� | -1.736 |
upgr | -1.666 |
mathemat | -1.504 |
王 | -1.498 |
nodd | -1.450 |
Token | of |
Token ID | 286 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
ocry | +0.610 |
sho | +0.592 |
iple | +0.590 |
KE | +0.575 |
enty | +0.543 |
Neg logit contributions | |
� | -1.073 |
upgr | -1.038 |
mathemat | -0.921 |
王 | -0.914 |
nodd | -0.899 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
� | +1.155 |
upgr | +1.098 |
mathemat | +0.942 |
王 | +0.935 |
nodd | +0.923 |
Neg logit contributions | |
ocry | -1.059 |
sho | -1.020 |
iple | -1.008 |
KE | -1.004 |
enty | -0.975 |
Token | fabric |
Token ID | 9664 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
sho | +0.450 |
ocry | +0.449 |
KE | +0.431 |
iple | +0.423 |
enty | +0.405 |
Neg logit contributions | |
� | -0.768 |
upgr | -0.731 |
mathemat | -0.652 |
王 | -0.648 |
nodd | -0.639 |
Token | When |
Token ID | 1649 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
ocry | +0.019 |
KE | +0.018 |
sho | +0.018 |
iple | +0.018 |
FF | +0.017 |
Neg logit contributions | |
� | -0.025 |
upgr | -0.024 |
nodd | -0.022 |
mathemat | -0.022 |
王 | -0.021 |
Token | you |
Token ID | 345 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
sho | +0.141 |
ocry | +0.140 |
KE | +0.135 |
iple | +0.134 |
FF | +0.131 |
Neg logit contributions | |
� | -0.200 |
upgr | -0.186 |
王 | -0.169 |
mathemat | -0.165 |
nodd | -0.162 |
Token | want |
Token ID | 765 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ocry | +0.064 |
sho | +0.064 |
KE | +0.062 |
iple | +0.061 |
enty | +0.060 |
Neg logit contributions | |
� | -0.075 |
upgr | -0.071 |
王 | -0.064 |
nodd | -0.062 |
mathemat | -0.061 |
Token | something |
Token ID | 1223 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ocry | +0.140 |
sho | +0.135 |
KE | +0.132 |
iple | +0.132 |
enty | +0.125 |
Neg logit contributions | |
� | -0.216 |
upgr | -0.204 |
王 | -0.183 |
nodd | -0.182 |
mathemat | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
� | +0.861 |
upgr | +0.815 |
王 | +0.734 |
mathemat | +0.727 |
nodd | +0.725 |
Neg logit contributions | |
ocry | -0.603 |
sho | -0.583 |
iple | -0.569 |
KE | -0.568 |
enty | -0.544 |
Token | oscill |
Token ID | 24969 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
� | +1.161 |
upgr | +1.091 |
mathemat | +0.964 |
王 | +0.962 |
nodd | +0.952 |
Neg logit contributions | |
ocry | -1.007 |
sho | -0.971 |
KE | -0.952 |
iple | -0.947 |
enty | -0.927 |
Token | ate |
Token ID | 378 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ocry | +0.715 |
iple | +0.678 |
enty | +0.657 |
KE | +0.640 |
sho | +0.627 |
Neg logit contributions | |
� | -1.514 |
upgr | -1.508 |
王 | -1.370 |
mathemat | -1.360 |
nodd | -1.359 |
Token | over |
Token ID | 625 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
� | +1.573 |
upgr | +1.510 |
王 | +1.323 |
mathemat | +1.314 |
nodd | +1.308 |
Neg logit contributions | |
ocry | -1.012 |
iple | -0.957 |
sho | -0.955 |
KE | -0.944 |
enty | -0.911 |
Token | time |
Token ID | 640 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
� | +1.164 |
upgr | +1.108 |
mathemat | +0.961 |
nodd | +0.954 |
王 | +0.949 |
Neg logit contributions | |
ocry | -0.975 |
sho | -0.926 |
iple | -0.918 |
KE | -0.918 |
enty | -0.894 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
� | +1.471 |
upgr | +1.417 |
mathemat | +1.252 |
王 | +1.250 |
nodd | +1.245 |
Neg logit contributions | |
ocry | -0.829 |
iple | -0.785 |
sho | -0.773 |
KE | -0.768 |
enty | -0.745 |
Token | a |
Token ID | 257 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
� | +1.160 |
upgr | +1.089 |
王 | +0.977 |
mathemat | +0.947 |
nodd | +0.945 |
Neg logit contributions | |
ocry | -0.850 |
sho | -0.830 |
KE | -0.825 |
iple | -0.818 |
enty | -0.783 |
Token | alongside |
Token ID | 7848 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
� | +0.909 |
upgr | +0.859 |
nodd | +0.748 |
mathemat | +0.748 |
王 | +0.747 |
Neg logit contributions | |
ocry | -0.601 |
sho | -0.578 |
KE | -0.573 |
iple | -0.561 |
enty | -0.549 |
Token | their |
Token ID | 511 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
� | +2.486 |
upgr | +2.354 |
mathemat | +2.011 |
nodd | +2.008 |
王 | +2.003 |
Neg logit contributions | |
ocry | -2.061 |
iple | -1.958 |
KE | -1.942 |
sho | -1.941 |
enty | -1.888 |
Token | German |
Token ID | 2679 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
� | +1.317 |
upgr | +1.246 |
nodd | +1.080 |
mathemat | +1.071 |
王 | +1.067 |
Neg logit contributions | |
ocry | -0.993 |
sho | -0.950 |
iple | -0.945 |
KE | -0.944 |
enty | -0.910 |
Token | allies |
Token ID | 7681 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
� | +1.667 |
upgr | +1.578 |
nodd | +1.359 |
mathemat | +1.355 |
王 | +1.342 |
Neg logit contributions | |
ocry | -1.368 |
iple | -1.299 |
sho | -1.287 |
KE | -1.284 |
enty | -1.253 |
Token | , |
Token ID | 11 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
� | +2.098 |
upgr | +2.013 |
nodd | +1.750 |
mathemat | +1.742 |
王 | +1.732 |
Neg logit contributions | |
ocry | -1.398 |
KE | -1.312 |
iple | -1.312 |
sho | -1.307 |
enty | -1.275 |
Token | receiving |
Token ID | 6464 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ocry | +0.101 |
sho | +0.098 |
KE | +0.098 |
iple | +0.097 |
enty | +0.093 |
Neg logit contributions | |
� | -0.147 |
upgr | -0.139 |
nodd | -0.122 |
mathemat | -0.121 |
王 | -0.119 |
Token | favorable |
Token ID | 17070 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
ocry | +0.568 |
sho | +0.563 |
KE | +0.554 |
iple | +0.544 |
Blu | +0.533 |
Neg logit contributions | |
� | -0.749 |
upgr | -0.687 |
王 | -0.604 |
nodd | -0.603 |
mathemat | -0.596 |
Token | reports |
Token ID | 3136 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ocry | +0.285 |
sho | +0.280 |
KE | +0.277 |
iple | +0.271 |
enty | +0.264 |
Neg logit contributions | |
� | -0.379 |
upgr | -0.355 |
mathemat | -0.311 |
nodd | -0.310 |
王 | -0.310 |
Token | and |
Token ID | 290 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ocry | +0.041 |
sho | +0.038 |
KE | +0.038 |
iple | +0.038 |
enty | +0.037 |
Neg logit contributions | |
� | -0.068 |
upgr | -0.064 |
nodd | -0.057 |
mathemat | -0.056 |
王 | -0.056 |
Token | taking |
Token ID | 2263 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
� | +0.188 |
upgr | +0.175 |
王 | +0.152 |
nodd | +0.151 |
mathemat | +0.150 |
Neg logit contributions | |
ocry | -0.152 |
sho | -0.148 |
KE | -0.146 |
iple | -0.143 |
enty | -0.140 |
Token | heavy |
Token ID | 4334 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
sho | +2.514 |
KE | +2.503 |
ocry | +2.457 |
iple | +2.391 |
Blu | +2.370 |
Neg logit contributions | |
� | -3.497 |
upgr | -3.159 |
nodd | -2.883 |
王 | -2.848 |
mathemat | -2.827 |
Token | years |
Token ID | 812 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
ocry | +0.435 |
sho | +0.422 |
KE | +0.421 |
iple | +0.417 |
enty | +0.409 |
Neg logit contributions | |
� | -0.521 |
upgr | -0.487 |
mathemat | -0.427 |
nodd | -0.426 |
王 | -0.422 |
Token | . |
Token ID | 13 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
� | +0.008 |
upgr | +0.008 |
mathemat | +0.007 |
nodd | +0.007 |
王 | +0.007 |
Neg logit contributions | |
ocry | -0.005 |
iple | -0.005 |
sho | -0.005 |
KE | -0.005 |
enty | -0.005 |
Token | In |
Token ID | 554 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
ocry | +0.419 |
KE | +0.410 |
sho | +0.399 |
iple | +0.395 |
enty | +0.389 |
Neg logit contributions | |
� | -0.548 |
upgr | -0.529 |
mathemat | -0.477 |
nodd | -0.473 |
isphere | -0.451 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
� | +0.594 |
upgr | +0.565 |
mathemat | +0.499 |
nodd | +0.492 |
王 | +0.491 |
Neg logit contributions | |
ocry | -0.400 |
iple | -0.380 |
sho | -0.378 |
KE | -0.376 |
enty | -0.365 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ocry | +0.062 |
iple | +0.058 |
KE | +0.058 |
sho | +0.058 |
enty | +0.057 |
Neg logit contributions | |
� | -0.105 |
upgr | -0.100 |
mathemat | -0.089 |
nodd | -0.089 |
王 | -0.088 |
Token | we |
Token ID | 356 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
ocry | +0.565 |
KE | +0.547 |
sho | +0.542 |
iple | +0.541 |
enty | +0.526 |
Neg logit contributions | |
� | -0.820 |
upgr | -0.770 |
mathemat | -0.682 |
nodd | -0.678 |
王 | -0.673 |
Token | celebrated |
Token ID | 13943 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
� | +0.623 |
upgr | +0.595 |
nodd | +0.524 |
mathemat | +0.521 |
王 | +0.520 |
Neg logit contributions | |
ocry | -0.377 |
iple | -0.356 |
sho | -0.351 |
KE | -0.349 |
enty | -0.340 |
Token | our |
Token ID | 674 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
ocry | +0.122 |
KE | +0.116 |
sho | +0.116 |
iple | +0.116 |
enty | +0.112 |
Neg logit contributions | |
� | -0.166 |
upgr | -0.155 |
nodd | -0.136 |
mathemat | -0.136 |
王 | -0.136 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
� | +0.392 |
upgr | +0.372 |
mathemat | +0.330 |
nodd | +0.329 |
王 | +0.327 |
Neg logit contributions | |
ocry | -0.226 |
iple | -0.216 |
sho | -0.211 |
KE | -0.209 |
enty | -0.204 |
Token | million |
Token ID | 1510 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
� | +0.099 |
upgr | +0.095 |
mathemat | +0.084 |
nodd | +0.084 |
王 | +0.082 |
Neg logit contributions | |
ocry | -0.061 |
iple | -0.058 |
sho | -0.057 |
KE | -0.057 |
enty | -0.055 |
Token | th |
Token ID | 400 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
� | +0.634 |
upgr | +0.601 |
mathemat | +0.534 |
nodd | +0.520 |
王 | +0.518 |
Neg logit contributions | |
ocry | -0.463 |
iple | -0.442 |
sho | -0.441 |
KE | -0.441 |
enty | -0.420 |
Token | Frank |
Token ID | 5278 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
� | +1.665 |
upgr | +1.610 |
mathemat | +1.415 |
nodd | +1.404 |
王 | +1.402 |
Neg logit contributions | |
ocry | -0.870 |
KE | -0.832 |
sho | -0.809 |
iple | -0.799 |
enty | -0.784 |
Token | L |
Token ID | 406 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
� | +0.822 |
upgr | +0.815 |
mathemat | +0.725 |
nodd | +0.705 |
王 | +0.696 |
Neg logit contributions | |
ocry | -0.395 |
sho | -0.378 |
iple | -0.374 |
KE | -0.372 |
enty | -0.357 |
Token | unt |
Token ID | 2797 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
iple | +0.972 |
ocry | +0.971 |
enty | +0.936 |
arij | +0.914 |
sho | +0.912 |
Neg logit contributions | |
� | -0.938 |
upgr | -0.890 |
nodd | -0.798 |
mathemat | -0.791 |
unemploy | -0.733 |
Token | z |
Token ID | 89 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ocry | +0.243 |
iple | +0.227 |
KE | +0.216 |
sho | +0.213 |
enty | +0.211 |
Neg logit contributions | |
� | -0.635 |
upgr | -0.625 |
mathemat | -0.563 |
nodd | -0.557 |
王 | -0.552 |
Token | : |
Token ID | 25 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
� | +1.594 |
upgr | +1.537 |
mathemat | +1.323 |
nodd | +1.316 |
王 | +1.306 |
Neg logit contributions | |
ocry | -1.196 |
iple | -1.127 |
sho | -1.125 |
KE | -1.121 |
enty | -1.105 |
Token | � |
Token ID | 564 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
� | +1.691 |
upgr | +1.625 |
mathemat | +1.421 |
nodd | +1.414 |
王 | +1.388 |
Neg logit contributions | |
ocry | -1.249 |
KE | -1.168 |
sho | -1.161 |
iple | -1.161 |
enty | -1.147 |
Token | � |
Token ID | 250 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
� | +1.097 |
upgr | +1.063 |
nodd | +0.960 |
mathemat | +0.960 |
王 | +0.939 |
Neg logit contributions | |
ocry | -0.407 |
iple | -0.369 |
KE | -0.358 |
sho | -0.356 |
enty | -0.352 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
� | +0.463 |
upgr | +0.445 |
nodd | +0.384 |
mathemat | +0.383 |
王 | +0.372 |
Neg logit contributions | |
ocry | -0.425 |
iple | -0.401 |
enty | -0.397 |
KE | -0.396 |
sho | -0.395 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ocry | +0.397 |
iple | +0.381 |
sho | +0.374 |
KE | +0.371 |
enty | +0.366 |
Neg logit contributions | |
� | -0.668 |
upgr | -0.648 |
nodd | -0.570 |
mathemat | -0.568 |
王 | -0.563 |
Token | there |
Token ID | 612 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
� | +0.894 |
upgr | +0.844 |
nodd | +0.744 |
王 | +0.741 |
mathemat | +0.740 |
Neg logit contributions | |
ocry | -0.621 |
KE | -0.590 |
sho | -0.588 |
iple | -0.585 |
enty | -0.575 |
Token | � |
Token ID | 447 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
� | +1.471 |
upgr | +1.408 |
nodd | +1.186 |
mathemat | +1.179 |
王 | +1.163 |
Neg logit contributions | |
ocry | -1.571 |
iple | -1.499 |
sho | -1.485 |
KE | -1.475 |
enty | -1.467 |
Token | atched |
Token ID | 14265 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
ocry | +0.783 |
iple | +0.713 |
sho | +0.687 |
arij | +0.683 |
KE | +0.675 |
Neg logit contributions | |
� | -1.832 |
upgr | -1.811 |
mathemat | -1.647 |
nodd | -1.623 |
王 | -1.597 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
ocry | +0.191 |
iple | +0.179 |
sho | +0.177 |
KE | +0.175 |
enty | +0.174 |
Neg logit contributions | |
� | -0.338 |
upgr | -0.325 |
mathemat | -0.289 |
nodd | -0.286 |
王 | -0.282 |
Token | Schumer |
Token ID | 26107 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
� | +0.114 |
upgr | +0.108 |
mathemat | +0.095 |
nodd | +0.094 |
王 | +0.093 |
Neg logit contributions | |
ocry | -0.079 |
KE | -0.076 |
sho | -0.076 |
iple | -0.075 |
enty | -0.073 |
Token | is |
Token ID | 318 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
� | +0.902 |
upgr | +0.855 |
王 | +0.732 |
mathemat | +0.732 |
nodd | +0.731 |
Neg logit contributions | |
ocry | -0.776 |
sho | -0.751 |
KE | -0.734 |
iple | -0.730 |
enty | -0.710 |
Token | featured |
Token ID | 8096 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
� | +0.853 |
upgr | +0.801 |
nodd | +0.703 |
mathemat | +0.702 |
王 | +0.697 |
Neg logit contributions | |
ocry | -0.616 |
sho | -0.602 |
KE | -0.591 |
iple | -0.588 |
enty | -0.567 |
Token | wielding |
Token ID | 33949 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
� | +0.173 |
upgr | +0.166 |
mathemat | +0.144 |
王 | +0.144 |
nodd | +0.143 |
Neg logit contributions | |
ocry | -0.117 |
sho | -0.113 |
KE | -0.111 |
iple | -0.110 |
enty | -0.107 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
� | +1.424 |
upgr | +1.355 |
王 | +1.182 |
mathemat | +1.179 |
nodd | +1.177 |
Neg logit contributions | |
ocry | -1.023 |
sho | -0.966 |
KE | -0.962 |
iple | -0.956 |
enty | -0.931 |
Token | gun |
Token ID | 2485 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
� | +0.843 |
upgr | +0.806 |
王 | +0.704 |
mathemat | +0.703 |
nodd | +0.703 |
Neg logit contributions | |
ocry | -0.565 |
sho | -0.536 |
KE | -0.535 |
iple | -0.527 |
enty | -0.512 |
Token | . |
Token ID | 13 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
� | +1.756 |
upgr | +1.673 |
mathemat | +1.465 |
nodd | +1.457 |
王 | +1.455 |
Neg logit contributions | |
ocry | -1.152 |
iple | -1.081 |
sho | -1.077 |
KE | -1.067 |
enty | -1.040 |
Token |
|
Token ID | 198 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
� | +0.314 |
upgr | +0.304 |
mathemat | +0.272 |
nodd | +0.270 |
isphere | +0.256 |
Neg logit contributions | |
ocry | -0.236 |
KE | -0.228 |
sho | -0.223 |
iple | -0.220 |
enty | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ocry | +0.444 |
KE | +0.420 |
sho | +0.418 |
iple | +0.417 |
enty | +0.408 |
Neg logit contributions | |
� | -0.577 |
upgr | -0.565 |
mathemat | -0.517 |
nodd | -0.516 |
unemploy | -0.476 |
Token | ays |
Token ID | 592 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ocry | +0.382 |
iple | +0.363 |
KE | +0.359 |
sho | +0.354 |
enty | +0.349 |
Neg logit contributions | |
� | -0.457 |
upgr | -0.436 |
王 | -0.379 |
nodd | -0.371 |
mathemat | -0.370 |
Token | it |
Token ID | 340 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ocry | +1.172 |
KE | +1.113 |
sho | +1.096 |
iple | +1.087 |
enty | +1.063 |
Neg logit contributions | |
� | -1.483 |
upgr | -1.422 |
王 | -1.248 |
mathemat | -1.238 |
nodd | -1.220 |
Token | � |
Token ID | 447 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
ocry | +0.614 |
sho | +0.583 |
iple | +0.583 |
KE | +0.580 |
enty | +0.562 |
Neg logit contributions | |
� | -0.576 |
upgr | -0.551 |
王 | -0.471 |
nodd | -0.468 |
mathemat | -0.462 |
Token | � |
Token ID | 251 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ocry | +0.181 |
iple | +0.167 |
KE | +0.166 |
sho | +0.162 |
enty | +0.159 |
Neg logit contributions | |
� | -0.408 |
upgr | -0.395 |
mathemat | -0.356 |
nodd | -0.354 |
王 | -0.350 |
Token | in |
Token ID | 287 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ocry | +1.216 |
KE | +1.141 |
iple | +1.132 |
sho | +1.130 |
enty | +1.104 |
Neg logit contributions | |
� | -1.401 |
upgr | -1.349 |
mathemat | -1.163 |
王 | -1.161 |
nodd | -1.160 |
Token | AR |
Token ID | 5923 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
ocry | +0.938 |
KE | +0.890 |
sho | +0.879 |
iple | +0.879 |
enty | +0.847 |
Neg logit contributions | |
� | -1.202 |
upgr | -1.145 |
王 | -1.021 |
mathemat | -0.987 |
nodd | -0.985 |
Token | 4 |
Token ID | 19 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
� | +0.277 |
upgr | +0.262 |
mathemat | +0.216 |
nodd | +0.216 |
王 | +0.215 |
Neg logit contributions | |
ocry | -0.336 |
iple | -0.322 |
KE | -0.319 |
sho | -0.314 |
enty | -0.312 |
Token | with |
Token ID | 351 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ocry | +1.438 |
KE | +1.342 |
iple | +1.321 |
sho | +1.320 |
cript | +1.286 |
Neg logit contributions | |
� | -1.824 |
upgr | -1.760 |
王 | -1.554 |
mathemat | -1.539 |
nodd | -1.537 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
ocry | +0.579 |
KE | +0.562 |
sho | +0.552 |
iple | +0.547 |
enty | +0.528 |
Neg logit contributions | |
� | -0.745 |
upgr | -0.707 |
王 | -0.626 |
mathemat | -0.613 |
nodd | -0.607 |
Token | Bern |
Token ID | 6206 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
� | +0.263 |
upgr | +0.248 |
王 | +0.217 |
nodd | +0.214 |
mathemat | +0.214 |
Neg logit contributions | |
ocry | -0.224 |
KE | -0.215 |
iple | -0.213 |
sho | -0.212 |
enty | -0.204 |
Token | formula |
Token ID | 10451 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
� | +0.236 |
upgr | +0.228 |
王 | +0.202 |
nodd | +0.201 |
mathemat | +0.199 |
Neg logit contributions | |
ocry | -0.124 |
KE | -0.116 |
iple | -0.116 |
sho | -0.113 |
enty | -0.112 |
Token | s |
Token ID | 264 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +2.268 |
upgr | +2.156 |
王 | +1.881 |
mathemat | +1.879 |
nodd | +1.873 |
Neg logit contributions | |
ocry | -1.403 |
iple | -1.318 |
sho | -1.305 |
KE | -1.303 |
enty | -1.262 |
Token | green |
Token ID | 14809 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
� | +0.930 |
upgr | +0.890 |
mathemat | +0.780 |
nodd | +0.777 |
王 | +0.761 |
Neg logit contributions | |
ocry | -0.623 |
iple | -0.591 |
sho | -0.574 |
KE | -0.570 |
enty | -0.568 |
Token | berg |
Token ID | 3900 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
ocry | +0.298 |
iple | +0.281 |
enty | +0.279 |
sho | +0.277 |
KE | +0.277 |
Neg logit contributions | |
� | -0.264 |
upgr | -0.252 |
mathemat | -0.220 |
nodd | -0.219 |
王 | -0.207 |
Token | @ |
Token ID | 31 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
� | +0.348 |
upgr | +0.327 |
mathemat | +0.270 |
nodd | +0.269 |
王 | +0.262 |
Neg logit contributions | |
ocry | -0.457 |
iple | -0.439 |
KE | -0.438 |
sho | -0.438 |
enty | -0.433 |
Token | s |
Token ID | 82 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ocry | +1.234 |
iple | +1.199 |
KE | +1.151 |
enty | +1.134 |
sho | +1.124 |
Neg logit contributions | |
� | -1.695 |
upgr | -1.649 |
mathemat | -1.428 |
nodd | -1.383 |
unemploy | -1.367 |
Token | unt |
Token ID | 2797 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
� | +1.280 |
upgr | +1.220 |
nodd | +1.050 |
mathemat | +1.046 |
王 | +1.012 |
Neg logit contributions | |
ocry | -1.212 |
iple | -1.163 |
enty | -1.127 |
KE | -1.117 |
sho | -1.112 |
Token | imes |
Token ID | 999 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
� | +0.592 |
upgr | +0.574 |
mathemat | +0.503 |
王 | +0.499 |
nodd | +0.496 |
Neg logit contributions | |
ocry | -0.360 |
iple | -0.342 |
KE | -0.328 |
sho | -0.323 |
enty | -0.323 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
� | +1.585 |
upgr | +1.522 |
nodd | +1.340 |
mathemat | +1.338 |
王 | +1.327 |
Neg logit contributions | |
ocry | -1.041 |
iple | -0.975 |
sho | -0.951 |
KE | -0.946 |
enty | -0.942 |
Token | com |
Token ID | 785 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
� | +1.514 |
upgr | +1.469 |
nodd | +1.300 |
mathemat | +1.285 |
王 | +1.276 |
Neg logit contributions | |
ocry | -0.738 |
iple | -0.686 |
KE | -0.671 |
sho | -0.667 |
enty | -0.665 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
� | +0.601 |
upgr | +0.579 |
mathemat | +0.505 |
nodd | +0.503 |
王 | +0.498 |
Neg logit contributions | |
ocry | -0.399 |
iple | -0.378 |
KE | -0.373 |
sho | -0.370 |
enty | -0.363 |
Token | Nintendo |
Token ID | 32348 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
� | +0.705 |
upgr | +0.686 |
nodd | +0.605 |
mathemat | +0.598 |
tuning | +0.567 |
Neg logit contributions | |
ocry | -0.640 |
iple | -0.607 |
KE | -0.589 |
sho | -0.589 |
enty | -0.588 |
Token | one |
Token ID | 530 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
� | +0.570 |
upgr | +0.540 |
王 | +0.467 |
mathemat | +0.467 |
nodd | +0.464 |
Neg logit contributions | |
ocry | -0.464 |
sho | -0.441 |
iple | -0.435 |
KE | -0.434 |
enty | -0.419 |
Token | about |
Token ID | 546 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ocry | +0.086 |
sho | +0.082 |
KE | +0.081 |
iple | +0.078 |
enty | +0.077 |
Neg logit contributions | |
� | -0.160 |
upgr | -0.152 |
mathemat | -0.135 |
王 | -0.135 |
nodd | -0.134 |
Token | gang |
Token ID | 7706 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
� | +1.468 |
upgr | +1.391 |
王 | +1.200 |
mathemat | +1.196 |
nodd | +1.193 |
Neg logit contributions | |
ocry | -1.100 |
sho | -1.065 |
KE | -1.051 |
iple | -1.039 |
enty | -1.010 |
Token | members |
Token ID | 1866 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
� | +2.396 |
upgr | +2.277 |
mathemat | +1.994 |
nodd | +1.973 |
王 | +1.967 |
Neg logit contributions | |
ocry | -1.673 |
iple | -1.572 |
sho | -1.549 |
KE | -1.544 |
enty | -1.503 |
Token | going |
Token ID | 1016 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
� | +1.742 |
upgr | +1.659 |
mathemat | +1.433 |
王 | +1.431 |
nodd | +1.420 |
Neg logit contributions | |
ocry | -1.349 |
sho | -1.290 |
iple | -1.277 |
KE | -1.270 |
enty | -1.236 |
Token | around |
Token ID | 1088 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
� | +1.572 |
upgr | +1.481 |
王 | +1.298 |
mathemat | +1.296 |
nodd | +1.288 |
Neg logit contributions | |
ocry | -1.067 |
sho | -1.020 |
iple | -1.004 |
KE | -1.001 |
enty | -0.970 |
Token | with |
Token ID | 351 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
� | +3.007 |
upgr | +2.857 |
mathemat | +2.462 |
王 | +2.451 |
nodd | +2.446 |
Neg logit contributions | |
ocry | -2.308 |
iple | -2.180 |
sho | -2.165 |
KE | -2.160 |
enty | -2.097 |
Token | their |
Token ID | 511 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
� | +2.034 |
upgr | +1.924 |
王 | +1.674 |
mathemat | +1.668 |
nodd | +1.662 |
Neg logit contributions | |
ocry | -1.514 |
sho | -1.457 |
KE | -1.436 |
iple | -1.427 |
enty | -1.383 |
Token | car |
Token ID | 1097 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
� | +1.035 |
upgr | +0.981 |
mathemat | +0.853 |
王 | +0.852 |
nodd | +0.846 |
Neg logit contributions | |
ocry | -0.761 |
sho | -0.750 |
KE | -0.729 |
iple | -0.720 |
enty | -0.699 |
Token | headlights |
Token ID | 46783 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
� | +1.960 |
upgr | +1.889 |
王 | +1.645 |
mathemat | +1.645 |
nodd | +1.638 |
Neg logit contributions | |
ocry | -1.328 |
iple | -1.254 |
sho | -1.247 |
KE | -1.233 |
enty | -1.200 |
Token | off |
Token ID | 572 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
� | +3.300 |
upgr | +3.155 |
mathemat | +2.748 |
王 | +2.742 |
nodd | +2.732 |
Neg logit contributions | |
ocry | -2.167 |
iple | -2.032 |
sho | -2.006 |
KE | -2.004 |
enty | -1.951 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ocry | +2.546 |
グ | +2.465 |
iple | +2.448 |
KE | +2.447 |
sho | +2.420 |
Neg logit contributions | |
upgr | -3.343 |
� | -3.319 |
mathemat | -3.208 |
nodd | -3.198 |
unemploy | -2.895 |
Token | Images |
Token ID | 5382 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
KE | +0.271 |
ocry | +0.268 |
sho | +0.243 |
iple | +0.240 |
enty | +0.232 |
Neg logit contributions | |
� | -1.152 |
upgr | -1.125 |
nodd | -1.044 |
mathemat | -1.031 |
王 | -1.011 |
Token | ) |
Token ID | 8 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
ocry | +0.361 |
iple | +0.338 |
KE | +0.335 |
sho | +0.333 |
enty | +0.326 |
Neg logit contributions | |
� | -0.532 |
upgr | -0.509 |
nodd | -0.445 |
mathemat | -0.445 |
王 | -0.439 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
ocry | +0.191 |
iple | +0.180 |
KE | +0.178 |
sho | +0.177 |
enty | +0.174 |
Neg logit contributions | |
� | -0.251 |
upgr | -0.239 |
mathemat | -0.205 |
nodd | -0.205 |
王 | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
� | +0.011 |
upgr | +0.011 |
nodd | +0.010 |
mathemat | +0.010 |
王 | +0.009 |
Neg logit contributions | |
ocry | -0.009 |
KE | -0.009 |
iple | -0.009 |
sho | -0.008 |
enty | -0.008 |
Token | SW |
Token ID | 17887 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
� | +0.236 |
upgr | +0.229 |
nodd | +0.203 |
mathemat | +0.201 |
tuning | +0.192 |
Neg logit contributions | |
ocry | -0.206 |
iple | -0.196 |
KE | -0.194 |
sho | -0.193 |
enty | -0.190 |
Token | IP |
Token ID | 4061 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
� | +3.089 |
upgr | +2.960 |
mathemat | +2.573 |
nodd | +2.570 |
王 | +2.547 |
Neg logit contributions | |
ocry | -2.063 |
iple | -1.933 |
KE | -1.919 |
sho | -1.898 |
enty | -1.871 |
Token | E |
Token ID | 36 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ocry | +0.192 |
KE | +0.188 |
sho | +0.181 |
iple | +0.178 |
NET | +0.176 |
Neg logit contributions | |
� | -0.265 |
upgr | -0.257 |
nodd | -0.227 |
mathemat | -0.227 |
王 | -0.216 |
Token | AT |
Token ID | 5161 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
ocry | +0.074 |
KE | +0.074 |
sho | +0.070 |
iple | +0.069 |
NET | +0.068 |
Neg logit contributions | |
� | -0.125 |
upgr | -0.121 |
mathemat | -0.107 |
nodd | -0.107 |
isphere | -0.104 |
Token | M |
Token ID | 337 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
� | +0.486 |
upgr | +0.465 |
mathemat | +0.413 |
nodd | +0.412 |
王 | +0.409 |
Neg logit contributions | |
ocry | -0.252 |
KE | -0.241 |
iple | -0.236 |
sho | -0.234 |
enty | -0.227 |
Token | CC |
Token ID | 4093 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
� | +0.102 |
upgr | +0.098 |
mathemat | +0.087 |
nodd | +0.086 |
王 | +0.085 |
Neg logit contributions | |
ocry | -0.073 |
KE | -0.071 |
iple | -0.070 |
sho | -0.069 |
enty | -0.068 |
Token | strategy |
Token ID | 4811 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
� | +0.249 |
upgr | +0.233 |
nodd | +0.204 |
王 | +0.203 |
mathemat | +0.202 |
Neg logit contributions | |
ocry | -0.200 |
sho | -0.194 |
KE | -0.192 |
iple | -0.191 |
enty | -0.186 |
Token | to |
Token ID | 284 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
� | +0.051 |
upgr | +0.049 |
nodd | +0.043 |
mathemat | +0.043 |
王 | +0.043 |
Neg logit contributions | |
ocry | -0.037 |
sho | -0.035 |
iple | -0.035 |
KE | -0.035 |
enty | -0.034 |
Token | counter |
Token ID | 3753 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
� | +0.224 |
upgr | +0.208 |
王 | +0.182 |
nodd | +0.182 |
mathemat | +0.178 |
Neg logit contributions | |
ocry | -0.199 |
sho | -0.193 |
KE | -0.191 |
iple | -0.189 |
enty | -0.187 |
Token | drug |
Token ID | 2563 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
ocry | +2.341 |
KE | +2.313 |
sho | +2.287 |
iple | +2.261 |
enty | +2.261 |
Neg logit contributions | |
� | -3.008 |
upgr | -2.834 |
王 | -2.497 |
nodd | -2.495 |
mathemat | -2.470 |
Token | trafficking |
Token ID | 14616 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ocry | +0.004 |
KE | +0.004 |
sho | +0.004 |
iple | +0.004 |
enty | +0.003 |
Neg logit contributions | |
� | -0.007 |
upgr | -0.006 |
nodd | -0.006 |
王 | -0.006 |
mathemat | -0.006 |
Token | requires |
Token ID | 4433 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ocry | +0.481 |
sho | +0.462 |
KE | +0.457 |
iple | +0.448 |
enty | +0.444 |
Neg logit contributions | |
� | -0.597 |
upgr | -0.567 |
nodd | -0.500 |
王 | -0.498 |
mathemat | -0.491 |
Token | more |
Token ID | 517 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
� | +2.837 |
upgr | +2.662 |
王 | +2.298 |
nodd | +2.292 |
mathemat | +2.274 |
Neg logit contributions | |
ocry | -2.297 |
iple | -2.180 |
sho | -2.174 |
KE | -2.171 |
enty | -2.114 |
Token | time |
Token ID | 640 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
� | +0.941 |
upgr | +0.884 |
王 | +0.783 |
nodd | +0.781 |
mathemat | +0.769 |
Neg logit contributions | |
ocry | -0.534 |
sho | -0.512 |
KE | -0.509 |
iple | -0.509 |
enty | -0.486 |
Token | , |
Token ID | 11 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
ocry | +0.568 |
sho | +0.547 |
iple | +0.546 |
KE | +0.543 |
enty | +0.522 |
Neg logit contributions | |
� | -1.103 |
upgr | -1.056 |
nodd | -0.935 |
王 | -0.933 |
mathemat | -0.932 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ocry | +0.331 |
sho | +0.327 |
KE | +0.320 |
iple | +0.308 |
enty | +0.305 |
Neg logit contributions | |
� | -0.492 |
upgr | -0.457 |
王 | -0.408 |
nodd | -0.408 |
mathemat | -0.395 |
Token | as |
Token ID | 355 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
� | +0.674 |
upgr | +0.623 |
王 | +0.552 |
nodd | +0.546 |
mathemat | +0.536 |
Neg logit contributions | |
ocry | -0.506 |
KE | -0.490 |
sho | -0.490 |
iple | -0.480 |
enty | -0.468 |
Token | wh |
Token ID | 348 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
� | +0.691 |
upgr | +0.655 |
王 | +0.562 |
mathemat | +0.561 |
nodd | +0.559 |
Neg logit contributions | |
ocry | -0.558 |
sho | -0.547 |
KE | -0.538 |
iple | -0.533 |
enty | -0.516 |
Token | ips |
Token ID | 2419 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
� | +0.931 |
upgr | +0.908 |
mathemat | +0.803 |
王 | +0.799 |
nodd | +0.798 |
Neg logit contributions | |
ocry | -0.594 |
iple | -0.555 |
enty | -0.532 |
KE | -0.532 |
sho | -0.526 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
� | +2.203 |
upgr | +2.113 |
王 | +1.835 |
mathemat | +1.835 |
nodd | +1.828 |
Neg logit contributions | |
ocry | -1.444 |
iple | -1.363 |
sho | -1.341 |
KE | -1.336 |
enty | -1.314 |
Token | sc |
Token ID | 629 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
� | +0.943 |
upgr | +0.902 |
王 | +0.774 |
mathemat | +0.770 |
isphere | +0.762 |
Neg logit contributions | |
ocry | -0.750 |
sho | -0.730 |
KE | -0.715 |
iple | -0.713 |
enty | -0.687 |
Token | orns |
Token ID | 19942 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
� | +0.391 |
upgr | +0.377 |
王 | +0.329 |
mathemat | +0.327 |
nodd | +0.323 |
Neg logit contributions | |
ocry | -0.298 |
iple | -0.283 |
KE | -0.278 |
enty | -0.275 |
sho | -0.274 |
Token | of |
Token ID | 286 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
� | +2.536 |
upgr | +2.425 |
mathemat | +2.103 |
王 | +2.102 |
nodd | +2.098 |
Neg logit contributions | |
ocry | -1.701 |
iple | -1.602 |
sho | -1.580 |
KE | -1.579 |
enty | -1.543 |
Token | time |
Token ID | 640 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
� | +2.583 |
upgr | +2.442 |
王 | +2.093 |
mathemat | +2.092 |
nodd | +2.074 |
Neg logit contributions | |
ocry | -2.171 |
sho | -2.068 |
KE | -2.049 |
iple | -2.045 |
enty | -1.991 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
� | +0.316 |
upgr | +0.304 |
mathemat | +0.268 |
王 | +0.266 |
nodd | +0.263 |
Neg logit contributions | |
ocry | -0.196 |
sho | -0.186 |
KE | -0.183 |
iple | -0.183 |
enty | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ocry | +0.598 |
sho | +0.578 |
KE | +0.568 |
iple | +0.556 |
enty | +0.551 |
Neg logit contributions | |
� | -0.836 |
upgr | -0.803 |
mathemat | -0.692 |
王 | -0.690 |
nodd | -0.689 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
� | +1.949 |
upgr | +1.828 |
王 | +1.545 |
mathemat | +1.507 |
nodd | +1.506 |
Neg logit contributions | |
ocry | -1.812 |
iple | -1.723 |
KE | -1.689 |
sho | -1.679 |
enty | -1.660 |
Token | The |
Token ID | 464 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
� | +0.931 |
upgr | +0.895 |
mathemat | +0.768 |
nodd | +0.764 |
王 | +0.750 |
Neg logit contributions | |
ocry | -0.799 |
iple | -0.759 |
sho | -0.746 |
KE | -0.746 |
enty | -0.741 |
Token | themes |
Token ID | 13460 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
ocry | +0.603 |
sho | +0.585 |
KE | +0.580 |
iple | +0.573 |
enty | +0.554 |
Neg logit contributions | |
� | -0.788 |
upgr | -0.735 |
王 | -0.647 |
mathemat | -0.643 |
nodd | -0.640 |
Token | for |
Token ID | 329 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
� | +0.282 |
upgr | +0.269 |
nodd | +0.235 |
mathemat | +0.234 |
王 | +0.233 |
Neg logit contributions | |
ocry | -0.193 |
iple | -0.181 |
sho | -0.179 |
KE | -0.179 |
enty | -0.174 |
Token | her |
Token ID | 607 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
� | +0.794 |
upgr | +0.748 |
王 | +0.651 |
mathemat | +0.645 |
nodd | +0.644 |
Neg logit contributions | |
ocry | -0.612 |
iple | -0.580 |
sho | -0.579 |
KE | -0.579 |
enty | -0.559 |
Token | thru |
Token ID | 33834 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ocry | +0.140 |
sho | +0.133 |
KE | +0.133 |
iple | +0.132 |
enty | +0.129 |
Neg logit contributions | |
� | -0.186 |
upgr | -0.174 |
王 | -0.153 |
mathemat | -0.151 |
nodd | -0.151 |
Token | - |
Token ID | 12 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
� | +2.681 |
upgr | +2.530 |
王 | +2.139 |
mathemat | +2.117 |
nodd | +2.102 |
Neg logit contributions | |
ocry | -2.243 |
iple | -2.127 |
KE | -2.100 |
sho | -2.079 |
enty | -2.052 |
Token | h |
Token ID | 71 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
� | +2.824 |
upgr | +2.688 |
mathemat | +2.328 |
王 | +2.324 |
nodd | +2.324 |
Neg logit contributions | |
ocry | -1.886 |
iple | -1.771 |
KE | -1.745 |
sho | -1.733 |
enty | -1.699 |
Token | ikes |
Token ID | 7938 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
� | +3.455 |
upgr | +3.314 |
mathemat | +2.929 |
nodd | +2.926 |
王 | +2.924 |
Neg logit contributions | |
ocry | -1.579 |
iple | -1.455 |
KE | -1.424 |
sho | -1.415 |
enty | -1.380 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ocry | +0.096 |
iple | +0.089 |
sho | +0.089 |
KE | +0.088 |
enty | +0.086 |
Neg logit contributions | |
� | -0.156 |
upgr | -0.150 |
nodd | -0.132 |
mathemat | -0.132 |
王 | -0.131 |
Token | In |
Token ID | 554 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ocry | +0.801 |
KE | +0.785 |
sho | +0.752 |
iple | +0.737 |
enty | +0.729 |
Neg logit contributions | |
� | -1.097 |
upgr | -1.075 |
mathemat | -0.968 |
nodd | -0.967 |
unemploy | -0.919 |
Token | Los |
Token ID | 5401 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
� | +1.042 |
upgr | +0.996 |
mathemat | +0.876 |
王 | +0.860 |
nodd | +0.858 |
Neg logit contributions | |
ocry | -0.734 |
iple | -0.691 |
KE | -0.686 |
sho | -0.686 |
enty | -0.663 |
Token | Angeles |
Token ID | 5652 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
ocry | +0.564 |
KE | +0.531 |
iple | +0.524 |
sho | +0.521 |
enty | +0.511 |
Neg logit contributions | |
� | -0.896 |
upgr | -0.878 |
mathemat | -0.798 |
nodd | -0.794 |
王 | -0.750 |