Token | as |
Token ID | 355 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
unts | +1.794 |
olas | +1.784 |
llo | +1.726 |
uria | +1.641 |
inant | +1.616 |
Neg logit contributions | |
su | -1.905 |
ements | -1.719 |
iences | -1.634 |
mingham | -1.599 |
��� | -1.588 |
Token | Treasury |
Token ID | 13419 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
olas | +0.659 |
unts | +0.654 |
llo | +0.636 |
uria | +0.597 |
inant | +0.596 |
Neg logit contributions | |
su | -0.532 |
ements | -0.465 |
iences | -0.440 |
mingham | -0.431 |
ement | -0.428 |
Token | secretary |
Token ID | 7705 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
unts | +0.959 |
olas | +0.956 |
llo | +0.932 |
uria | +0.866 |
inant | +0.860 |
Neg logit contributions | |
su | -1.051 |
ements | -0.952 |
iences | -0.903 |
mingham | -0.891 |
ement | -0.884 |
Token | . |
Token ID | 13 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
olas | +1.550 |
unts | +1.533 |
llo | +1.496 |
uria | +1.411 |
inant | +1.394 |
Neg logit contributions | |
su | -1.718 |
ements | -1.554 |
iences | -1.476 |
mingham | -1.438 |
��� | -1.431 |
Token | Blank |
Token ID | 31990 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
olas | +0.933 |
unts | +0.920 |
llo | +0.905 |
uria | +0.840 |
inant | +0.831 |
Neg logit contributions | |
su | -0.876 |
ements | -0.778 |
iences | -0.737 |
mingham | -0.724 |
ement | -0.719 |
Token | fe |
Token ID | 5036 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
olas | +2.005 |
unts | +1.976 |
llo | +1.924 |
uria | +1.768 |
inant | +1.734 |
Neg logit contributions | |
su | -2.471 |
ements | -2.263 |
mingham | -2.174 |
iences | -2.156 |
ruciating | -2.134 |
Token | in |
Token ID | 259 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
olas | +5.675 |
unts | +5.554 |
llo | +5.417 |
uria | +4.788 |
inant | +4.682 |
Neg logit contributions | |
su | -14.986 |
者 | -13.817 |
��� | -13.772 |
Priv | -13.752 |
ements | -13.659 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
su | +2.541 |
ements | +2.215 |
ement | +2.057 |
iences | +2.051 |
Priv | +2.003 |
Neg logit contributions | |
olas | -3.023 |
unts | -3.011 |
llo | -2.888 |
uria | -2.760 |
inant | -2.758 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
olas | +2.036 |
unts | +2.019 |
llo | +1.961 |
uria | +1.830 |
inant | +1.800 |
Neg logit contributions | |
su | -2.022 |
ements | -1.796 |
iences | -1.717 |
mingham | -1.698 |
ement | -1.662 |
Token | � |
Token ID | 447 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
olas | +2.490 |
unts | +2.444 |
llo | +2.412 |
uria | +2.227 |
inant | +2.186 |
Neg logit contributions | |
su | -2.588 |
ements | -2.345 |
iences | -2.251 |
mingham | -2.201 |
ement | -2.157 |
Token | � |
Token ID | 247 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
su | +0.603 |
ements | +0.537 |
iences | +0.504 |
ement | +0.502 |
mingham | +0.498 |
Neg logit contributions | |
olas | -0.559 |
unts | -0.554 |
llo | -0.534 |
uria | -0.502 |
inant | -0.498 |
Token | , |
Token ID | 11 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
su | +1.382 |
ements | +1.223 |
iences | +1.148 |
ement | +1.137 |
mingham | +1.130 |
Neg logit contributions | |
olas | -1.417 |
unts | -1.408 |
llo | -1.362 |
uria | -1.282 |
inant | -1.273 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
olas | +0.823 |
unts | +0.820 |
llo | +0.795 |
uria | +0.750 |
inant | +0.741 |
Neg logit contributions | |
su | -0.713 |
ements | -0.631 |
iences | -0.586 |
ement | -0.581 |
mingham | -0.580 |
Token | with |
Token ID | 351 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
su | +2.055 |
ements | +1.780 |
iences | +1.671 |
ement | +1.649 |
mingham | +1.620 |
Neg logit contributions | |
olas | -2.542 |
unts | -2.521 |
llo | -2.450 |
uria | -2.321 |
inant | -2.317 |
Token | the |
Token ID | 262 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
olas | +1.944 |
unts | +1.939 |
llo | +1.868 |
uria | +1.754 |
inant | +1.735 |
Neg logit contributions | |
su | -1.696 |
ements | -1.490 |
mingham | -1.391 |
iences | -1.385 |
Priv | -1.383 |
Token | brightest |
Token ID | 33871 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
olas | +0.404 |
unts | +0.403 |
llo | +0.391 |
uria | +0.368 |
inant | +0.365 |
Neg logit contributions | |
su | -0.344 |
ements | -0.301 |
iences | -0.281 |
mingham | -0.279 |
ement | -0.278 |
Token | br |
Token ID | 865 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
su | +1.017 |
ements | +0.892 |
iences | +0.832 |
ement | +0.824 |
mingham | +0.817 |
Neg logit contributions | |
olas | -1.188 |
unts | -1.180 |
llo | -1.145 |
uria | -1.081 |
inant | -1.076 |
Token | ights |
Token ID | 2337 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
unts | +9.675 |
olas | +9.325 |
llo | +8.936 |
inant | +8.137 |
uria | +7.924 |
Neg logit contributions | |
su | -10.664 |
��� | -10.501 |
ruciating | -9.927 |
ements | -9.842 |
ement | -9.690 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
olas | +1.030 |
unts | +1.014 |
llo | +0.988 |
uria | +0.930 |
inant | +0.913 |
Neg logit contributions | |
su | -0.950 |
ements | -0.837 |
iences | -0.778 |
mingham | -0.777 |
Priv | -0.776 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
olas | +0.556 |
unts | +0.552 |
llo | +0.534 |
uria | +0.503 |
inant | +0.496 |
Neg logit contributions | |
su | -0.485 |
ements | -0.425 |
iences | -0.400 |
mingham | -0.397 |
ement | -0.396 |
Token | black |
Token ID | 2042 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
olas | +1.752 |
unts | +1.748 |
llo | +1.702 |
uria | +1.588 |
inant | +1.586 |
Neg logit contributions | |
su | -1.460 |
ements | -1.271 |
iences | -1.197 |
mingham | -1.187 |
Priv | -1.181 |
Token | est |
Token ID | 395 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
su | +0.795 |
ements | +0.698 |
iences | +0.653 |
ement | +0.646 |
mingham | +0.642 |
Neg logit contributions | |
olas | -0.912 |
unts | -0.905 |
llo | -0.877 |
uria | -0.829 |
inant | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
olas | +2.055 |
unts | +2.024 |
llo | +1.975 |
uria | +1.864 |
inant | +1.832 |
Neg logit contributions | |
su | -2.274 |
ements | -2.069 |
iences | -1.953 |
��� | -1.935 |
mingham | -1.920 |
Token | P |
Token ID | 350 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
olas | +2.628 |
unts | +2.573 |
llo | +2.553 |
uria | +2.302 |
inant | +2.300 |
Neg logit contributions | |
su | -2.821 |
ements | -2.543 |
iences | -2.445 |
mingham | -2.414 |
ynam | -2.405 |
Token | ipp |
Token ID | 3974 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
su | +0.380 |
ements | +0.325 |
iences | +0.301 |
mingham | +0.295 |
Priv | +0.295 |
Neg logit contributions | |
olas | -0.582 |
unts | -0.578 |
llo | -0.562 |
uria | -0.533 |
inant | -0.531 |
Token | in |
Token ID | 259 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
olas | +0.254 |
unts | +0.252 |
llo | +0.242 |
ngth | +0.227 |
uria | +0.226 |
Neg logit contributions | |
su | -0.314 |
ements | -0.280 |
iences | -0.265 |
ement | -0.264 |
mingham | -0.261 |
Token | picks |
Token ID | 11103 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
olas | +0.794 |
unts | +0.789 |
llo | +0.765 |
uria | +0.718 |
inant | +0.709 |
Neg logit contributions | |
su | -0.730 |
ements | -0.646 |
iences | -0.608 |
mingham | -0.602 |
Priv | -0.601 |
Token | it |
Token ID | 340 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
olas | +4.114 |
unts | +3.891 |
llo | +3.858 |
inant | +3.487 |
uria | +3.486 |
Neg logit contributions | |
su | -4.650 |
ements | -4.256 |
iences | -4.022 |
mingham | -4.021 |
ynam | -4.019 |
Token | up |
Token ID | 510 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
olas | +7.063 |
unts | +6.629 |
llo | +6.628 |
uria | +5.436 |
inant | +5.402 |
Neg logit contributions | |
su | -12.587 |
ements | -12.216 |
��� | -12.154 |
ciating | -11.921 |
Priv | -11.874 |
Token | ; |
Token ID | 26 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
olas | +4.303 |
unts | +4.145 |
llo | +4.124 |
uria | +3.817 |
inant | +3.793 |
Neg logit contributions | |
su | -4.686 |
ements | -4.244 |
��� | -4.071 |
iences | -4.031 |
mingham | -4.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
olas | +1.120 |
unts | +1.094 |
llo | +1.069 |
uria | +0.998 |
inant | +0.996 |
Neg logit contributions | |
su | -1.082 |
ements | -0.963 |
iences | -0.905 |
mingham | -0.897 |
Priv | -0.888 |
Token | is |
Token ID | 318 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
olas | +2.324 |
unts | +2.292 |
llo | +2.221 |
uria | +2.068 |
inant | +2.059 |
Neg logit contributions | |
su | -2.168 |
ements | -1.924 |
iences | -1.836 |
Priv | -1.828 |
mingham | -1.809 |
Token | revealed |
Token ID | 4602 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
olas | +1.957 |
unts | +1.909 |
llo | +1.872 |
uria | +1.750 |
inant | +1.742 |
Neg logit contributions | |
su | -1.678 |
ements | -1.472 |
iences | -1.405 |
mingham | -1.385 |
Priv | -1.377 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
unts | +1.564 |
olas | +1.563 |
llo | +1.519 |
uria | +1.414 |
inant | +1.393 |
Neg logit contributions | |
su | -1.628 |
ements | -1.447 |
iences | -1.363 |
mingham | -1.349 |
��� | -1.349 |
Token | and |
Token ID | 290 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
su | +1.637 |
ements | +1.441 |
iences | +1.343 |
ement | +1.333 |
mingham | +1.312 |
Neg logit contributions | |
olas | -1.935 |
unts | -1.920 |
llo | -1.859 |
uria | -1.767 |
inant | -1.752 |
Token | seven |
Token ID | 3598 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
olas | +0.522 |
unts | +0.518 |
llo | +0.503 |
uria | +0.468 |
inant | +0.464 |
Neg logit contributions | |
su | -0.445 |
ements | -0.392 |
mingham | -0.367 |
iences | -0.367 |
ement | -0.363 |
Token | s |
Token ID | 82 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
unts | +2.558 |
olas | +2.520 |
llo | +2.449 |
uria | +2.207 |
inant | +2.206 |
Neg logit contributions | |
su | -3.152 |
ements | -2.823 |
��� | -2.785 |
mingham | -2.756 |
iences | -2.734 |
Token | and |
Token ID | 290 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
olas | +1.043 |
unts | +1.034 |
llo | +1.001 |
uria | +0.937 |
inant | +0.933 |
Neg logit contributions | |
su | -1.009 |
ements | -0.887 |
iences | -0.836 |
mingham | -0.828 |
Priv | -0.823 |
Token | n |
Token ID | 299 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
olas | +6.686 |
unts | +6.615 |
llo | +6.456 |
inant | +5.649 |
ftime | +5.517 |
Neg logit contributions | |
su | -6.052 |
ements | -5.390 |
��� | -5.372 |
mingham | -5.278 |
者 | -5.129 |
Token | ines |
Token ID | 1127 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
unts | +8.746 |
olas | +8.205 |
llo | +7.338 |
uria | +6.722 |
inant | +6.639 |
Neg logit contributions | |
��� | -11.759 |
su | -11.520 |
Pradesh | -11.028 |
Stronghold | -10.989 |
者 | -10.967 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
su | +1.304 |
ements | +1.148 |
iences | +1.074 |
ement | +1.064 |
mingham | +1.055 |
Neg logit contributions | |
olas | -1.448 |
unts | -1.439 |
llo | -1.394 |
uria | -1.316 |
inant | -1.307 |
Token |
|
Token ID | 198 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
olas | +2.262 |
unts | +2.253 |
llo | +2.217 |
uria | +2.017 |
inant | +2.009 |
Neg logit contributions | |
su | -2.299 |
ements | -2.056 |
iences | -1.951 |
��� | -1.945 |
mingham | -1.943 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
su | +0.741 |
ements | +0.639 |
ement | +0.594 |
Priv | +0.590 |
iences | +0.585 |
Neg logit contributions | |
olas | -0.886 |
unts | -0.875 |
llo | -0.836 |
ngth | -0.832 |
uria | -0.807 |
Token | RF |
Token ID | 32754 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
su | +4.230 |
ements | +3.692 |
Priv | +3.551 |
iences | +3.466 |
ement | +3.437 |
Neg logit contributions | |
unts | -4.186 |
olas | -4.180 |
llo | -3.990 |
ngth | -3.833 |
uria | -3.821 |
Token | 39 |
Token ID | 5014 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
su | +1.219 |
ements | +1.062 |
iences | +0.985 |
ement | +0.983 |
Priv | +0.970 |
Neg logit contributions | |
olas | -1.448 |
unts | -1.435 |
llo | -1.388 |
uria | -1.321 |
inant | -1.315 |
Token | Gra |
Token ID | 7037 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
olas | +1.024 |
unts | +1.013 |
llo | +0.996 |
uria | +0.929 |
inant | +0.919 |
Neg logit contributions | |
su | -0.902 |
ements | -0.800 |
iences | -0.754 |
mingham | -0.739 |
ement | -0.735 |
Token | ff |
Token ID | 487 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
llo | +8.476 |
olas | +8.436 |
unts | +8.359 |
uria | +7.438 |
inant | +7.317 |
Neg logit contributions | |
su | -7.834 |
ements | -7.482 |
��� | -7.167 |
者 | -7.096 |
Pradesh | -7.075 |
Token | car |
Token ID | 1097 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
olas | +0.996 |
unts | +0.983 |
llo | +0.960 |
uria | +0.898 |
inant | +0.892 |
Neg logit contributions | |
su | -0.974 |
ements | -0.869 |
iences | -0.819 |
mingham | -0.806 |
ement | -0.804 |
Token | of |
Token ID | 286 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
olas | +2.574 |
unts | +2.538 |
llo | +2.494 |
uria | +2.321 |
inant | +2.276 |
Neg logit contributions | |
su | -2.523 |
ements | -2.271 |
iences | -2.133 |
mingham | -2.092 |
��� | -2.088 |
Token | En |
Token ID | 2039 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
olas | +0.784 |
unts | +0.777 |
llo | +0.756 |
uria | +0.705 |
inant | +0.703 |
Neg logit contributions | |
su | -0.679 |
ements | -0.602 |
iences | -0.564 |
mingham | -0.555 |
ement | -0.555 |
Token | zo |
Token ID | 10872 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
olas | +11.944 |
llo | +11.090 |
unts | +11.003 |
uria | +10.510 |
ngth | +10.222 |
Neg logit contributions | |
��� | -7.670 |
ements | -7.176 |
ruciating | -7.151 |
su | -6.999 |
iences | -6.751 |
Token | Gu |
Token ID | 1962 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
su | +2.350 |
ements | +2.068 |
iences | +1.929 |
ement | +1.926 |
mingham | +1.890 |
Neg logit contributions | |
olas | -2.503 |
unts | -2.496 |
llo | -2.405 |
inant | -2.274 |
uria | -2.272 |
Token | ib |
Token ID | 571 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
su | +1.408 |
ements | +1.257 |
iences | +1.184 |
ement | +1.180 |
mingham | +1.165 |
Neg logit contributions | |
olas | -1.245 |
unts | -1.241 |
llo | -1.192 |
uria | -1.116 |
inant | -1.110 |
Token | bert |
Token ID | 4835 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
olas | +1.125 |
unts | +1.107 |
llo | +1.074 |
uria | +1.002 |
inant | +0.997 |
Neg logit contributions | |
su | -1.184 |
ements | -1.075 |
iences | -1.018 |
Priv | -1.004 |
Pradesh | -1.002 |
Token | , |
Token ID | 11 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
su | +0.379 |
ements | +0.335 |
iences | +0.315 |
ement | +0.311 |
mingham | +0.310 |
Neg logit contributions | |
olas | -0.402 |
unts | -0.398 |
llo | -0.387 |
uria | -0.364 |
inant | -0.361 |
Token | the |
Token ID | 262 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
su | +2.210 |
ements | +1.906 |
iences | +1.760 |
ement | +1.748 |
mingham | +1.737 |
Neg logit contributions | |
olas | -2.911 |
unts | -2.904 |
llo | -2.819 |
uria | -2.676 |
inant | -2.657 |
Token | University |
Token ID | 2059 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
su | +0.723 |
ements | +0.632 |
iences | +0.590 |
ement | +0.585 |
mingham | +0.580 |
Neg logit contributions | |
olas | -0.846 |
unts | -0.841 |
llo | -0.815 |
uria | -0.771 |
inant | -0.767 |
Token | of |
Token ID | 286 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
olas | +0.559 |
unts | +0.555 |
llo | +0.540 |
uria | +0.508 |
inant | +0.503 |
Neg logit contributions | |
su | -0.498 |
ements | -0.439 |
iences | -0.412 |
ement | -0.407 |
mingham | -0.404 |
Token | California |
Token ID | 3442 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
olas | +3.683 |
unts | +3.671 |
llo | +3.629 |
uria | +3.284 |
inant | +3.222 |
Neg logit contributions | |
su | -3.350 |
ements | -3.054 |
��� | -2.935 |
iences | -2.897 |
ement | -2.853 |
Token | , |
Token ID | 11 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
olas | +6.740 |
unts | +6.710 |
llo | +6.504 |
uria | +5.948 |
inant | +5.742 |
Neg logit contributions | |
su | -8.654 |
ements | -8.080 |
iences | -7.933 |
Priv | -7.933 |
��� | -7.799 |
Token | Santa |
Token ID | 8909 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
olas | +7.963 |
unts | +7.802 |
llo | +7.607 |
uria | +7.251 |
ngth | +6.892 |
Neg logit contributions | |
su | -7.817 |
Priv | -7.502 |
ements | -7.289 |
��� | -7.162 |
iences | -7.082 |
Token | Barbara |
Token ID | 16685 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
olas | +6.983 |
unts | +6.584 |
llo | +6.486 |
uria | +5.973 |
inant | +5.066 |
Neg logit contributions | |
su | -12.807 |
ements | -12.617 |
��� | -12.525 |
Priv | -12.248 |
ruciating | -12.171 |
Token | , |
Token ID | 11 |
Feature activation | -5.33e-04 |
Pos logit contributions | |
olas | +2.802 |
unts | +2.721 |
llo | +2.682 |
uria | +2.549 |
inant | +2.462 |
Neg logit contributions | |
su | -3.264 |
ements | -3.011 |
iences | -2.832 |
��� | -2.768 |
Priv | -2.762 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
su | +0.006 |
ements | +0.005 |
iences | +0.005 |
ement | +0.005 |
Priv | +0.005 |
Neg logit contributions | |
olas | -0.006 |
unts | -0.006 |
llo | -0.006 |
uria | -0.006 |
inant | -0.006 |
Token | an |
Token ID | 281 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
su | +2.348 |
ements | +2.013 |
iences | +1.872 |
ement | +1.865 |
mingham | +1.850 |
Neg logit contributions | |
olas | -2.982 |
unts | -2.975 |
llo | -2.875 |
uria | -2.728 |
inant | -2.716 |
Token | organizer |
Token ID | 26311 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
su | +1.775 |
ements | +1.521 |
iences | +1.407 |
ement | +1.403 |
Pradesh | +1.384 |
Neg logit contributions | |
unts | -2.339 |
olas | -2.338 |
llo | -2.258 |
ngth | -2.148 |
uria | -2.137 |
Token | ians |
Token ID | 1547 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
su | +0.437 |
ements | +0.399 |
iences | +0.382 |
ement | +0.380 |
mingham | +0.378 |
Neg logit contributions | |
olas | -0.217 |
unts | -0.215 |
llo | -0.204 |
uria | -0.186 |
inant | -0.184 |
Token | are |
Token ID | 389 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
su | +3.398 |
ements | +2.921 |
ement | +2.729 |
iences | +2.721 |
Stronghold | +2.680 |
Neg logit contributions | |
olas | -3.938 |
unts | -3.902 |
llo | -3.772 |
uria | -3.586 |
ngth | -3.570 |
Token | under |
Token ID | 739 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
su | +2.578 |
ements | +2.222 |
ement | +2.047 |
iences | +2.035 |
mingham | +2.023 |
Neg logit contributions | |
olas | -3.317 |
unts | -3.316 |
llo | -3.206 |
uria | -3.046 |
ngth | -3.041 |
Token | dogs |
Token ID | 22242 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
su | +0.749 |
ements | +0.647 |
iences | +0.599 |
ement | +0.592 |
mingham | +0.588 |
Neg logit contributions | |
olas | -1.050 |
unts | -1.044 |
llo | -1.015 |
uria | -0.963 |
inant | -0.958 |
Token | versus |
Token ID | 9051 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
su | +3.863 |
ements | +3.311 |
ement | +3.089 |
iences | +3.055 |
mingham | +3.028 |
Neg logit contributions | |
unts | -4.818 |
olas | -4.802 |
llo | -4.639 |
uria | -4.382 |
ngth | -4.380 |
Token | En |
Token ID | 2039 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
su | +1.561 |
ements | +1.357 |
iences | +1.261 |
ement | +1.250 |
mingham | +1.233 |
Neg logit contributions | |
olas | -1.947 |
unts | -1.934 |
llo | -1.879 |
uria | -1.782 |
inant | -1.771 |
Token | V |
Token ID | 53 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
olas | +8.049 |
unts | +7.584 |
uria | +7.561 |
llo | +7.501 |
inant | +6.695 |
Neg logit contributions | |
��� | -10.630 |
ruciating | -10.519 |
su | -10.261 |
ements | -10.229 |
iences | -10.043 |
Token | y |
Token ID | 88 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
su | +4.532 |
ements | +3.932 |
iences | +3.809 |
ynam | +3.807 |
ement | +3.739 |
Neg logit contributions | |
olas | -4.148 |
unts | -4.008 |
llo | -3.885 |
ngth | -3.703 |
uria | -3.541 |
Token | Us |
Token ID | 5842 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
su | +0.829 |
ements | +0.706 |
iences | +0.647 |
ement | +0.642 |
mingham | +0.633 |
Neg logit contributions | |
olas | -1.291 |
unts | -1.283 |
llo | -1.249 |
inant | -1.190 |
uria | -1.186 |
Token | , |
Token ID | 11 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
su | +2.689 |
ements | +2.334 |
iences | +2.179 |
ement | +2.170 |
mingham | +2.152 |
Neg logit contributions | |
olas | -3.109 |
unts | -3.101 |
llo | -3.000 |
inant | -2.824 |
uria | -2.813 |
Token | Titan |
Token ID | 11977 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
su | +0.662 |
ements | +0.581 |
iences | +0.543 |
ement | +0.537 |
mingham | +0.534 |
Neg logit contributions | |
olas | -0.777 |
unts | -0.772 |
llo | -0.749 |
uria | -0.708 |
inant | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
su | +0.519 |
ements | +0.461 |
iences | +0.433 |
ement | +0.427 |
mingham | +0.427 |
Neg logit contributions | |
olas | -0.530 |
unts | -0.526 |
llo | -0.513 |
uria | -0.477 |
inant | -0.475 |
Token |
|
Token ID | 198 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
su | +0.852 |
ements | +0.732 |
ement | +0.681 |
Priv | +0.677 |
iences | +0.671 |
Neg logit contributions | |
olas | -1.018 |
unts | -1.009 |
llo | -0.963 |
ngth | -0.955 |
uria | -0.931 |
Token | http |
Token ID | 4023 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
su | +0.943 |
ements | +0.820 |
iences | +0.764 |
ement | +0.758 |
Priv | +0.753 |
Neg logit contributions | |
olas | -1.136 |
unts | -1.128 |
llo | -1.093 |
uria | -1.038 |
inant | -1.030 |
Token | :// |
Token ID | 1378 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
olas | +1.623 |
unts | +1.612 |
llo | +1.576 |
uria | +1.465 |
inant | +1.449 |
Neg logit contributions | |
su | -1.679 |
ements | -1.501 |
iences | -1.423 |
ement | -1.396 |
��� | -1.394 |
Token | free |
Token ID | 5787 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
olas | +2.508 |
unts | +2.493 |
llo | +2.421 |
uria | +2.234 |
ngth | +2.230 |
Neg logit contributions | |
su | -2.535 |
ements | -2.399 |
��� | -2.296 |
Pradesh | -2.242 |
iences | -2.224 |
Token | be |
Token ID | 1350 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
su | +1.981 |
ements | +1.759 |
iences | +1.656 |
ement | +1.645 |
mingham | +1.630 |
Neg logit contributions | |
olas | -1.773 |
unts | -1.762 |
llo | -1.699 |
uria | -1.598 |
inant | -1.587 |
Token | acon |
Token ID | 7807 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
olas | +9.735 |
unts | +9.301 |
llo | +9.179 |
ngth | +8.532 |
inant | +8.269 |
Neg logit contributions | |
su | -9.828 |
Pradesh | -9.353 |
��� | -9.176 |
Stronghold | -8.879 |
者 | -8.878 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
su | +1.261 |
ements | +1.118 |
iences | +1.052 |
ement | +1.041 |
mingham | +1.034 |
Neg logit contributions | |
olas | -1.271 |
unts | -1.263 |
llo | -1.221 |
uria | -1.149 |
inant | -1.139 |
Token | com |
Token ID | 785 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
olas | +2.171 |
unts | +2.151 |
llo | +2.105 |
uria | +1.965 |
inant | +1.936 |
Neg logit contributions | |
su | -1.618 |
ements | -1.475 |
Pradesh | -1.368 |
iences | -1.367 |
��� | -1.357 |
Token | / |
Token ID | 14 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
su | +0.976 |
ements | +0.877 |
iences | +0.830 |
ement | +0.818 |
mingham | +0.815 |
Neg logit contributions | |
olas | -0.853 |
unts | -0.846 |
llo | -0.820 |
uria | -0.764 |
inant | -0.756 |
Token | politics |
Token ID | 34127 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
olas | +3.537 |
unts | +3.474 |
llo | +3.359 |
uria | +3.131 |
ngth | +3.090 |
Neg logit contributions | |
su | -3.238 |
ements | -3.011 |
iences | -2.827 |
Pradesh | -2.819 |
Stronghold | -2.807 |
Token | 2 |
Token ID | 362 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
olas | +5.220 |
llo | +5.135 |
unts | +5.106 |
uria | +4.659 |
inant | +4.587 |
Neg logit contributions | |
su | -5.839 |
��� | -5.457 |
ements | -5.357 |
iences | -5.257 |
mingham | -5.152 |
Token | 3 |
Token ID | 513 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
olas | +4.485 |
unts | +4.402 |
llo | +4.336 |
inant | +4.085 |
uria | +3.969 |
Neg logit contributions | |
su | -5.344 |
ements | -4.837 |
��� | -4.729 |
iences | -4.648 |
mingham | -4.595 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
olas | +4.323 |
unts | +4.047 |
llo | +3.973 |
uria | +3.727 |
inant | +3.704 |
Neg logit contributions | |
su | -6.052 |
ements | -5.626 |
iences | -5.364 |
者 | -5.334 |
mingham | -5.264 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
olas | +4.466 |
unts | +4.355 |
llo | +4.300 |
uria | +4.051 |
inant | +4.003 |
Neg logit contributions | |
su | -6.081 |
ements | -5.648 |
iences | -5.479 |
mingham | -5.462 |
ement | -5.359 |
Token | 6 |
Token ID | 718 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
olas | +5.683 |
llo | +5.407 |
unts | +5.096 |
inant | +4.844 |
uria | +4.829 |
Neg logit contributions | |
su | -9.143 |
ements | -8.442 |
mingham | -8.308 |
iences | -8.203 |
者 | -8.091 |
Token | 7 |
Token ID | 767 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
olas | +5.569 |
unts | +5.530 |
llo | +5.343 |
inant | +5.131 |
uria | +4.811 |
Neg logit contributions | |
su | -10.231 |
ements | -9.770 |
mingham | -9.755 |
iences | -9.445 |
者 | -9.270 |
Token | 8 |
Token ID | 807 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
olas | +6.451 |
unts | +5.927 |
llo | +5.641 |
inant | +5.407 |
uria | +5.184 |
Neg logit contributions | |
su | -12.599 |
ements | -11.807 |
mingham | -11.440 |
��� | -11.274 |
iences | -11.226 |
Token | void |
Token ID | 7951 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
unts | +6.222 |
olas | +6.067 |
inant | +5.946 |
llo | +5.917 |
uria | +5.533 |
Neg logit contributions | |
su | -11.793 |
ements | -11.003 |
mingham | -10.760 |
ement | -10.611 |
atom | -10.579 |
Token | vert |
Token ID | 9421 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
olas | +6.201 |
unts | +6.195 |
llo | +6.034 |
inant | +5.702 |
uria | +5.410 |
Neg logit contributions | |
su | -7.530 |
��� | -7.188 |
ements | -6.943 |
iences | -6.888 |
ruciating | -6.764 |
Token | ( |
Token ID | 357 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
olas | +1.566 |
unts | +1.553 |
llo | +1.517 |
uria | +1.413 |
inant | +1.406 |
Neg logit contributions | |
su | -1.481 |
ements | -1.312 |
iences | -1.243 |
��� | -1.221 |
ement | -1.213 |
Token | in |
Token ID | 287 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
su | +1.939 |
ements | +1.625 |
ement | +1.530 |
mingham | +1.518 |
Stronghold | +1.511 |
Neg logit contributions | |
olas | -2.627 |
unts | -2.623 |
llo | -2.518 |
ngth | -2.427 |
uria | -2.372 |
Token | , |
Token ID | 11 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
unts | +4.077 |
olas | +3.860 |
llo | +3.843 |
uria | +3.559 |
inant | +3.438 |
Neg logit contributions | |
su | -5.605 |
ements | -5.117 |
iences | -5.014 |
��� | -4.964 |
mingham | -4.857 |
Token | political |
Token ID | 1964 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
unts | +0.729 |
olas | +0.729 |
llo | +0.706 |
uria | +0.667 |
inant | +0.660 |
Neg logit contributions | |
su | -0.630 |
ements | -0.556 |
iences | -0.521 |
ement | -0.511 |
mingham | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
unts | +5.336 |
llo | +5.113 |
olas | +5.049 |
uria | +4.761 |
inant | +4.592 |
Neg logit contributions | |
su | -6.072 |
iences | -5.529 |
ements | -5.509 |
��� | -5.487 |
mingham | -5.295 |
Token | economic |
Token ID | 3034 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
unts | +1.480 |
olas | +1.477 |
llo | +1.433 |
inant | +1.341 |
uria | +1.341 |
Neg logit contributions | |
su | -1.336 |
ements | -1.180 |
iences | -1.119 |
ement | -1.091 |
mingham | -1.088 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
unts | +6.240 |
llo | +5.906 |
olas | +5.811 |
uria | +5.515 |
inant | +5.325 |
Neg logit contributions | |
su | -7.392 |
��� | -6.896 |
ements | -6.781 |
iences | -6.770 |
mingham | -6.526 |
Token | cultural |
Token ID | 6467 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
su | +0.130 |
ements | +0.114 |
iences | +0.106 |
ement | +0.105 |
mingham | +0.104 |
Neg logit contributions | |
olas | -0.162 |
unts | -0.161 |
llo | -0.157 |
uria | -0.148 |
inant | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
unts | +8.808 |
llo | +8.110 |
olas | +7.930 |
uria | +7.669 |
inant | +7.368 |
Neg logit contributions | |
su | -10.293 |
��� | -10.228 |
iences | -9.748 |
ements | -9.691 |
ciating | -9.374 |
Token | religious |
Token ID | 4158 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
su | +0.014 |
ements | +0.012 |
iences | +0.011 |
ement | +0.011 |
mingham | +0.011 |
Neg logit contributions | |
olas | -0.019 |
unts | -0.019 |
llo | -0.019 |
uria | -0.018 |
inant | -0.018 |
Token | separation |
Token ID | 14139 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
unts | +8.007 |
llo | +7.288 |
olas | +7.216 |
uria | +6.853 |
inant | +6.484 |
Neg logit contributions | |
su | -10.107 |
��� | -9.686 |
ements | -9.549 |
iences | -9.411 |
mingham | -9.314 |
Token | between |
Token ID | 1022 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
olas | +0.084 |
unts | +0.084 |
llo | +0.082 |
uria | +0.077 |
inant | +0.076 |
Neg logit contributions | |
su | -0.078 |
ements | -0.069 |
iences | -0.065 |
mingham | -0.064 |
ement | -0.064 |
Token | Gaza |
Token ID | 11010 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
unts | +1.425 |
olas | +1.414 |
llo | +1.372 |
uria | +1.299 |
inant | +1.273 |
Neg logit contributions | |
su | -1.264 |
ements | -1.109 |
iences | -1.050 |
mingham | -1.042 |
ement | -1.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
su | +2.193 |
ements | +1.896 |
iences | +1.763 |
ement | +1.742 |
mingham | +1.727 |
Neg logit contributions | |
olas | -2.917 |
unts | -2.911 |
llo | -2.821 |
uria | -2.675 |
inant | -2.672 |
Token | pile |
Token ID | 14540 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
su | +3.600 |
ements | +3.131 |
iences | +2.897 |
ement | +2.870 |
Pradesh | +2.826 |
Neg logit contributions | |
unts | -4.642 |
olas | -4.632 |
llo | -4.448 |
inant | -4.306 |
ngth | -4.292 |
Token | would |
Token ID | 561 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
unts | +1.734 |
olas | +1.731 |
llo | +1.666 |
uria | +1.584 |
inant | +1.549 |
Neg logit contributions | |
su | -1.671 |
ements | -1.478 |
iences | -1.397 |
mingham | -1.389 |
Priv | -1.383 |
Token | squeeze |
Token ID | 21229 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
su | +1.118 |
ements | +0.978 |
iences | +0.911 |
ement | +0.905 |
mingham | +0.896 |
Neg logit contributions | |
olas | -1.332 |
unts | -1.322 |
llo | -1.284 |
uria | -1.214 |
inant | -1.205 |
Token | the |
Token ID | 262 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
su | +2.498 |
ements | +2.161 |
iences | +2.017 |
ement | +2.001 |
Priv | +1.962 |
Neg logit contributions | |
olas | -3.183 |
unts | -3.162 |
llo | -3.080 |
inant | -2.934 |
uria | -2.914 |
Token | br |
Token ID | 865 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
su | +1.997 |
ements | +1.745 |
iences | +1.625 |
ement | +1.610 |
mingham | +1.590 |
Neg logit contributions | |
olas | -2.411 |
unts | -2.401 |
llo | -2.325 |
inant | -2.203 |
uria | -2.199 |
Token | ine |
Token ID | 500 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
olas | +6.011 |
unts | +5.750 |
llo | +5.397 |
uria | +5.036 |
inant | +5.033 |
Neg logit contributions | |
��� | -13.403 |
su | -13.379 |
Priv | -12.437 |
者 | -12.398 |
Stronghold | -12.364 |
Token | out |
Token ID | 503 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
olas | +2.525 |
unts | +2.469 |
llo | +2.450 |
uria | +2.294 |
ngth | +2.207 |
Neg logit contributions | |
su | -2.443 |
ements | -2.189 |
mingham | -2.074 |
iences | -2.061 |
��� | -2.058 |
Token | of |
Token ID | 286 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
olas | +1.452 |
unts | +1.426 |
llo | +1.397 |
uria | +1.324 |
ngth | +1.297 |
Neg logit contributions | |
su | -1.442 |
ements | -1.287 |
iences | -1.220 |
mingham | -1.211 |
��� | -1.200 |
Token | the |
Token ID | 262 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
olas | +0.312 |
unts | +0.309 |
llo | +0.300 |
uria | +0.284 |
inant | +0.280 |
Neg logit contributions | |
su | -0.261 |
ements | -0.230 |
iences | -0.213 |
mingham | -0.212 |
ement | -0.211 |
Token | past |
Token ID | 1613 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
su | +1.962 |
ements | +1.708 |
iences | +1.587 |
ement | +1.570 |
mingham | +1.549 |
Neg logit contributions | |
olas | -2.493 |
unts | -2.484 |
llo | -2.403 |
uria | -2.282 |
inant | -2.278 |
Token | has |
Token ID | 468 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
olas | +6.034 |
unts | +5.943 |
llo | +5.829 |
uria | +5.428 |
ngth | +5.241 |
Neg logit contributions | |
su | -6.469 |
ements | -5.921 |
��� | -5.737 |
mingham | -5.599 |
iences | -5.564 |
Token | now |
Token ID | 783 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
su | +0.891 |
ements | +0.779 |
iences | +0.727 |
ement | +0.721 |
mingham | +0.713 |
Neg logit contributions | |
olas | -1.048 |
unts | -1.042 |
llo | -1.010 |
uria | -0.956 |
inant | -0.950 |
Token | been |
Token ID | 587 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
su | +1.495 |
ements | +1.296 |
iences | +1.208 |
ement | +1.201 |
mingham | +1.181 |
Neg logit contributions | |
olas | -1.838 |
unts | -1.828 |
llo | -1.770 |
uria | -1.681 |
inant | -1.672 |
Token | dis |
Token ID | 595 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
olas | +0.054 |
unts | +0.054 |
llo | +0.052 |
uria | +0.049 |
inant | +0.049 |
Neg logit contributions | |
su | -0.045 |
ements | -0.040 |
iences | -0.037 |
mingham | -0.037 |
ement | -0.036 |
Token | owned |
Token ID | 11990 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
olas | +2.046 |
unts | +2.021 |
llo | +1.968 |
uria | +1.848 |
inant | +1.838 |
Neg logit contributions | |
su | -1.960 |
ements | -1.792 |
mingham | -1.672 |
iences | -1.670 |
��� | -1.667 |
Token | by |
Token ID | 416 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
olas | +3.402 |
unts | +3.373 |
llo | +3.270 |
uria | +3.121 |
inant | +3.023 |
Neg logit contributions | |
su | -3.895 |
ements | -3.528 |
��� | -3.453 |
iences | -3.341 |
mingham | -3.322 |
Token | celebrity |
Token ID | 16527 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
unts | +9.277 |
olas | +9.237 |
llo | +8.862 |
uria | +8.255 |
inant | +8.042 |
Neg logit contributions | |
su | -9.775 |
��� | -9.129 |
ements | -8.978 |
mingham | -8.974 |
ASHINGTON | -8.621 |
Token | YouTube |
Token ID | 7444 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
unts | +5.436 |
olas | +5.301 |
llo | +5.200 |
uria | +4.853 |
inant | +4.737 |
Neg logit contributions | |
su | -5.224 |
ements | -4.820 |
iences | -4.475 |
mingham | -4.474 |
��� | -4.442 |
Token | partners |
Token ID | 4887 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
unts | +2.397 |
olas | +2.362 |
llo | +2.296 |
uria | +2.113 |
inant | +2.108 |
Neg logit contributions | |
su | -2.682 |
ements | -2.430 |
mingham | -2.298 |
iences | -2.273 |
Priv | -2.266 |
Token | Yog |
Token ID | 31604 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
unts | +2.738 |
olas | +2.737 |
llo | +2.654 |
uria | +2.483 |
inant | +2.444 |
Neg logit contributions | |
su | -2.567 |
ements | -2.267 |
mingham | -2.148 |
iences | -2.121 |
��� | -2.120 |
Token | sc |
Token ID | 1416 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
olas | +3.035 |
unts | +3.007 |
llo | +2.889 |
uria | +2.793 |
ngth | +2.641 |
Neg logit contributions | |
su | -2.897 |
ements | -2.617 |
mingham | -2.491 |
iences | -2.474 |
��� | -2.440 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
unts | +2.746 |
olas | +2.729 |
llo | +2.630 |
inant | +2.439 |
uria | +2.427 |
Neg logit contributions | |
su | -2.787 |
ements | -2.474 |
��� | -2.397 |
mingham | -2.327 |
iences | -2.301 |
Token | While |
Token ID | 2893 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
olas | +2.204 |
unts | +2.198 |
llo | +2.151 |
uria | +1.984 |
inant | +1.962 |
Neg logit contributions | |
su | -2.053 |
ements | -1.837 |
iences | -1.744 |
ynam | -1.707 |
mingham | -1.705 |
Token | it |
Token ID | 340 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
su | +1.238 |
ements | +1.082 |
iences | +1.009 |
ement | +0.998 |
mingham | +0.990 |
Neg logit contributions | |
olas | -1.510 |
unts | -1.497 |
llo | -1.456 |
uria | -1.379 |
inant | -1.372 |
Token | had |
Token ID | 550 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
su | +0.456 |
ements | +0.404 |
iences | +0.380 |
ement | +0.376 |
mingham | +0.374 |
Neg logit contributions | |
olas | -0.457 |
unts | -0.454 |
llo | -0.439 |
uria | -0.413 |
inant | -0.410 |
Token | long |
Token ID | 890 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
unts | +4.086 |
olas | +4.052 |
llo | +3.904 |
uria | +3.616 |
inant | +3.539 |
Neg logit contributions | |
su | -4.526 |
ements | -4.054 |
iences | -3.848 |
mingham | -3.809 |
��� | -3.801 |
Token | been |
Token ID | 587 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
olas | +4.014 |
unts | +3.985 |
llo | +3.838 |
uria | +3.551 |
inant | +3.506 |
Neg logit contributions | |
su | -5.138 |
ements | -4.652 |
Priv | -4.507 |
iences | -4.466 |
mingham | -4.423 |
Token | assumed |
Token ID | 9672 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
olas | +8.524 |
unts | +8.517 |
llo | +8.121 |
uria | +7.378 |
inant | +6.988 |
Neg logit contributions | |
su | -10.464 |
ruciating | -9.920 |
iences | -9.697 |
ements | -9.660 |
ynam | -9.437 |
Token | that |
Token ID | 326 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
unts | +2.479 |
olas | +2.473 |
llo | +2.368 |
inant | +2.209 |
uria | +2.184 |
Neg logit contributions | |
su | -2.533 |
ements | -2.239 |
iences | -2.122 |
Stronghold | -2.102 |
ynam | -2.094 |
Token | women |
Token ID | 1466 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
unts | +0.374 |
olas | +0.373 |
llo | +0.358 |
uria | +0.338 |
inant | +0.335 |
Neg logit contributions | |
su | -0.336 |
ements | -0.295 |
iences | -0.277 |
Priv | -0.273 |
mingham | -0.273 |
Token | with |
Token ID | 351 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
su | +0.588 |
ements | +0.519 |
iences | +0.487 |
ement | +0.482 |
mingham | +0.480 |
Neg logit contributions | |
olas | -0.614 |
unts | -0.611 |
llo | -0.591 |
uria | -0.557 |
inant | -0.553 |
Token | younger |
Token ID | 7099 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
unts | +1.816 |
olas | +1.807 |
llo | +1.736 |
uria | +1.623 |
inant | +1.605 |
Neg logit contributions | |
su | -1.658 |
ements | -1.451 |
iences | -1.370 |
mingham | -1.361 |
Priv | -1.350 |
Token | music |
Token ID | 2647 |
Feature activation | +6.09e-04 |
Pos logit contributions | |
su | +1.053 |
ements | +0.924 |
iences | +0.865 |
ement | +0.857 |
mingham | +0.851 |
Neg logit contributions | |
olas | -1.181 |
unts | -1.173 |
llo | -1.135 |
uria | -1.073 |
inant | -1.065 |
Token | venue |
Token ID | 14359 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
olas | +0.007 |
unts | +0.007 |
llo | +0.007 |
uria | +0.006 |
inant | +0.006 |
Neg logit contributions | |
su | -0.007 |
ements | -0.006 |
iences | -0.006 |
ement | -0.006 |
mingham | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
olas | +1.942 |
unts | +1.930 |
llo | +1.901 |
inant | +1.755 |
uria | +1.739 |
Neg logit contributions | |
su | -1.785 |
ements | -1.593 |
iences | -1.489 |
ement | -1.474 |
Priv | -1.460 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
su | +0.983 |
ements | +0.860 |
iences | +0.803 |
ement | +0.795 |
mingham | +0.789 |
Neg logit contributions | |
olas | -1.163 |
unts | -1.155 |
llo | -1.121 |
uria | -1.059 |
inant | -1.053 |
Token | at |
Token ID | 379 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
olas | +2.043 |
unts | +2.021 |
llo | +1.986 |
uria | +1.839 |
inant | +1.828 |
Neg logit contributions | |
su | -1.898 |
ements | -1.708 |
iences | -1.603 |
ement | -1.580 |
mingham | -1.568 |
Token | 330 |
Token ID | 25508 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
olas | +1.581 |
unts | +1.564 |
llo | +1.525 |
inant | +1.415 |
uria | +1.414 |
Neg logit contributions | |
su | -1.400 |
ements | -1.226 |
iences | -1.153 |
mingham | -1.145 |
Priv | -1.137 |
Token | E |
Token ID | 412 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
llo | +9.788 |
olas | +9.574 |
unts | +9.489 |
Blossom | +8.832 |
uria | +8.523 |
Neg logit contributions | |
su | -8.792 |
��� | -8.062 |
ements | -7.956 |
mingham | -7.785 |
ruciating | -7.731 |
Token | . |
Token ID | 13 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
olas | +3.957 |
unts | +3.870 |
llo | +3.816 |
uria | +3.445 |
ngth | +3.441 |
Neg logit contributions | |
su | -4.268 |
ements | -3.933 |
��� | -3.790 |
Priv | -3.784 |
iences | -3.715 |
Token | Grayson |
Token ID | 42657 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
olas | +0.839 |
unts | +0.829 |
llo | +0.816 |
uria | +0.755 |
inant | +0.746 |
Neg logit contributions | |
su | -0.806 |
ements | -0.719 |
iences | -0.679 |
ement | -0.666 |
mingham | -0.663 |
Token | St |
Token ID | 520 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
su | +3.016 |
ements | +2.532 |
ement | +2.342 |
iences | +2.339 |
mingham | +2.298 |
Neg logit contributions | |
olas | -4.723 |
unts | -4.701 |
llo | -4.540 |
uria | -4.403 |
ngth | -4.379 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
su | +3.826 |
ements | +3.293 |
iences | +3.089 |
ement | +3.062 |
mingham | +3.025 |
Neg logit contributions | |
olas | -4.490 |
unts | -4.429 |
llo | -4.309 |
uria | -4.103 |
inant | -4.037 |
Token | has |
Token ID | 468 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
olas | +0.068 |
unts | +0.067 |
llo | +0.065 |
uria | +0.061 |
inant | +0.061 |
Neg logit contributions | |
su | -0.063 |
ements | -0.055 |
iences | -0.052 |
mingham | -0.051 |
ement | -0.051 |
Token | already |
Token ID | 1541 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
su | +0.860 |
ements | +0.760 |
iences | +0.714 |
ement | +0.704 |
mingham | +0.704 |
Neg logit contributions | |
olas | -0.915 |
unts | -0.908 |
llo | -0.880 |
uria | -0.829 |
inant | -0.821 |
Token | leaked |
Token ID | 14109 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
su | +2.361 |
ements | +2.066 |
ement | +1.931 |
iences | +1.931 |
mingham | +1.893 |
Neg logit contributions | |
olas | -2.549 |
unts | -2.541 |
llo | -2.459 |
uria | -2.317 |
inant | -2.316 |
Token | into |
Token ID | 656 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
su | +3.530 |
ements | +3.034 |
ement | +2.814 |
iences | +2.814 |
Pradesh | +2.783 |
Neg logit contributions | |
olas | -4.448 |
unts | -4.440 |
llo | -4.276 |
inant | -4.089 |
ngth | -4.071 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
su | +0.275 |
ements | +0.240 |
iences | +0.225 |
mingham | +0.222 |
ement | +0.222 |
Neg logit contributions | |
olas | -0.331 |
unts | -0.328 |
llo | -0.318 |
uria | -0.301 |
inant | -0.299 |
Token | br |
Token ID | 865 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
su | +0.132 |
ements | +0.117 |
iences | +0.110 |
mingham | +0.109 |
ement | +0.109 |
Neg logit contributions | |
olas | -0.134 |
unts | -0.133 |
llo | -0.129 |
uria | -0.121 |
inant | -0.120 |
Token | ack |
Token ID | 441 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
unts | +8.962 |
olas | +8.523 |
llo | +8.303 |
inant | +7.769 |
uria | +7.545 |
Neg logit contributions | |
��� | -10.435 |
su | -10.305 |
者 | -9.587 |
ements | -9.504 |
Priv | -9.376 |
Token | ish |
Token ID | 680 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
su | +1.089 |
ements | +0.950 |
iences | +0.886 |
ement | +0.875 |
mingham | +0.870 |
Neg logit contributions | |
olas | -1.342 |
unts | -1.333 |
llo | -1.294 |
uria | -1.224 |
inant | -1.216 |
Token | tidal |
Token ID | 40738 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
su | +1.162 |
ements | +1.017 |
iences | +0.948 |
ement | +0.942 |
mingham | +0.929 |
Neg logit contributions | |
olas | -1.358 |
unts | -1.348 |
llo | -1.306 |
uria | -1.236 |
inant | -1.230 |
Token | water |
Token ID | 1660 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
su | +3.143 |
ements | +2.749 |
ement | +2.590 |
iences | +2.534 |
Pradesh | +2.524 |
Neg logit contributions | |
olas | -3.478 |
unts | -3.446 |
llo | -3.300 |
ngth | -3.178 |
inant | -3.178 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
su | +3.613 |
ements | +3.098 |
ement | +2.907 |
iences | +2.894 |
Pradesh | +2.828 |
Neg logit contributions | |
olas | -4.230 |
unts | -4.185 |
llo | -4.025 |
inant | -3.840 |
uria | -3.816 |
Token | image |
Token ID | 2939 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
olas | +3.796 |
llo | +3.731 |
unts | +3.716 |
uria | +3.480 |
inant | +3.460 |
Neg logit contributions | |
su | -3.017 |
ements | -2.629 |
��� | -2.553 |
iences | -2.508 |
ruciating | -2.430 |
Token | Path |
Token ID | 15235 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
su | +1.133 |
ements | +0.899 |
Priv | +0.842 |
ement | +0.804 |
iences | +0.789 |
Neg logit contributions | |
olas | -2.458 |
unts | -2.433 |
llo | -2.318 |
ngth | -2.294 |
uria | -2.267 |
Token | in |
Token ID | 287 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
su | +3.045 |
ements | +2.478 |
ement | +2.293 |
mingham | +2.282 |
Priv | +2.274 |
Neg logit contributions | |
olas | -4.702 |
unts | -4.682 |
ngth | -4.504 |
llo | -4.391 |
inant | -4.211 |
Token | paths |
Token ID | 13532 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
olas | +0.089 |
unts | +0.088 |
llo | +0.086 |
uria | +0.082 |
inant | +0.082 |
Neg logit contributions | |
su | -0.049 |
ements | -0.042 |
iences | -0.038 |
ement | -0.037 |
mingham | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
olas | +3.567 |
unts | +3.543 |
llo | +3.506 |
uria | +3.217 |
inant | +3.141 |
Neg logit contributions | |
su | -4.249 |
��� | -3.901 |
ements | -3.837 |
iences | -3.706 |
ruciating | -3.681 |
Token | list |
Token ID | 4868 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
olas | +4.178 |
unts | +4.121 |
llo | +4.027 |
inant | +3.607 |
uria | +3.605 |
Neg logit contributions | |
��� | -7.582 |
su | -7.562 |
ements | -7.121 |
ruciating | -7.031 |
Stronghold | -6.988 |
Token | _ |
Token ID | 62 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
llo | +6.526 |
olas | +6.102 |
unts | +5.986 |
uria | +5.161 |
inant | +5.014 |
Neg logit contributions | |
��� | -14.905 |
practition | -13.156 |
occas | -12.998 |
pione | -12.965 |
ruciating | -12.580 |
Token | images |
Token ID | 17566 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
olas | +2.091 |
unts | +2.062 |
llo | +1.990 |
uria | +1.860 |
inant | +1.837 |
Neg logit contributions | |
su | -2.448 |
ements | -2.192 |
iences | -2.077 |
ement | -2.066 |
mingham | -2.060 |
Token | ( |
Token ID | 7 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
olas | +1.380 |
unts | +1.367 |
llo | +1.329 |
uria | +1.233 |
inant | +1.223 |
Neg logit contributions | |
su | -1.626 |
ements | -1.456 |
iences | -1.382 |
ement | -1.362 |
mingham | -1.361 |
Token | args |
Token ID | 22046 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
olas | +2.217 |
unts | +2.207 |
llo | +2.136 |
uria | +1.953 |
inant | +1.934 |
Neg logit contributions | |
su | -3.179 |
ements | -2.885 |
iences | -2.760 |
mingham | -2.733 |
ement | -2.729 |
Token | [" |
Token ID | 14692 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
unts | +2.648 |
olas | +2.637 |
llo | +2.583 |
uria | +2.364 |
inant | +2.267 |
Neg logit contributions | |
su | -4.512 |
��� | -4.156 |
ements | -4.109 |
ruciating | -3.981 |
iences | -3.980 |
Token | em |
Token ID | 795 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
unts | +7.283 |
olas | +7.072 |
llo | +6.972 |
uria | +6.581 |
inant | +6.214 |
Neg logit contributions | |
su | -6.781 |
ements | -6.184 |
iences | -6.094 |
��� | -5.977 |
ynam | -5.895 |
Token | be |
Token ID | 1350 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
olas | +4.768 |
unts | +4.642 |
llo | +4.409 |
uria | +4.191 |
inant | +3.843 |
Neg logit contributions | |
su | -7.818 |
ements | -7.707 |
Stronghold | -7.534 |
��� | -7.492 |
iences | -7.484 |
Token | zz |
Token ID | 3019 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
olas | +1.417 |
unts | +1.412 |
llo | +1.383 |
uria | +1.321 |
inant | +1.312 |
Neg logit contributions | |
su | -0.680 |
ements | -0.584 |
iences | -0.525 |
Priv | -0.509 |
ement | -0.506 |
Token | lement |
Token ID | 1732 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
su | +3.942 |
ements | +3.566 |
ement | +3.374 |
iences | +3.259 |
mingham | +3.200 |
Neg logit contributions | |
olas | -4.412 |
unts | -4.386 |
llo | -4.229 |
ngth | -4.084 |
uria | -4.025 |
Token | and |
Token ID | 290 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
olas | +1.061 |
unts | +1.053 |
llo | +1.026 |
uria | +0.964 |
inant | +0.949 |
Neg logit contributions | |
su | -1.049 |
ements | -0.931 |
iences | -0.890 |
mingham | -0.874 |
��� | -0.867 |
Token | char |
Token ID | 1149 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
olas | +3.806 |
unts | +3.805 |
llo | +3.695 |
uria | +3.497 |
inant | +3.338 |
Neg logit contributions | |
su | -3.377 |
ements | -2.999 |
iences | -2.879 |
mingham | -2.823 |
��� | -2.823 |
Token | lat |
Token ID | 15460 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
olas | +7.766 |
unts | +7.758 |
llo | +7.420 |
inant | +7.154 |
uria | +6.791 |
Neg logit contributions | |
su | -10.604 |
者 | -9.907 |
��� | -9.845 |
Stronghold | -9.843 |
iences | -9.680 |
Token | anism |
Token ID | 48162 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
su | +0.715 |
ements | +0.558 |
iences | +0.479 |
ement | +0.477 |
mingham | +0.461 |
Neg logit contributions | |
olas | -2.054 |
unts | -2.044 |
llo | -1.998 |
ngth | -1.918 |
uria | -1.916 |
Token | , |
Token ID | 11 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
olas | +0.639 |
unts | +0.634 |
llo | +0.613 |
uria | +0.577 |
inant | +0.571 |
Neg logit contributions | |
su | -0.662 |
ements | -0.593 |
iences | -0.562 |
mingham | -0.553 |
ement | -0.548 |
Token | all |
Token ID | 477 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
olas | +0.655 |
unts | +0.653 |
llo | +0.632 |
uria | +0.594 |
inant | +0.587 |
Neg logit contributions | |
su | -0.575 |
ements | -0.507 |
iences | -0.477 |
ement | -0.469 |
mingham | -0.469 |
Token | later |
Token ID | 1568 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
su | +2.346 |
ements | +2.047 |
ement | +1.886 |
iences | +1.882 |
mingham | +1.842 |
Neg logit contributions | |
olas | -3.005 |
unts | -2.982 |
llo | -2.908 |
uria | -2.755 |
inant | -2.751 |
Token | c |
Token ID | 66 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
su | +4.918 |
ements | +3.714 |
ement | +3.471 |
iences | +3.294 |
atom | +3.202 |
Neg logit contributions | |
unts | -9.297 |
olas | -9.163 |
ngth | -8.968 |
llo | -8.861 |
inant | -8.726 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
su | +1.045 |
ements | +0.907 |
iences | +0.847 |
ement | +0.845 |
mingham | +0.839 |
Neg logit contributions | |
olas | -1.110 |
unts | -1.103 |
llo | -1.071 |
inant | -1.004 |
uria | -1.003 |
Token | gov |
Token ID | 9567 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
su | +1.155 |
ements | +0.992 |
iences | +0.923 |
ement | +0.914 |
mingham | +0.913 |
Neg logit contributions | |
olas | -1.463 |
unts | -1.455 |
llo | -1.420 |
uria | -1.337 |
inant | -1.336 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
olas | +3.770 |
unts | +3.707 |
llo | +3.659 |
uria | +3.383 |
inant | +3.356 |
Neg logit contributions | |
su | -4.115 |
ements | -3.785 |
iences | -3.568 |
��� | -3.480 |
ynam | -3.470 |
Token | 7 |
Token ID | 767 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
olas | +2.338 |
unts | +2.319 |
llo | +2.258 |
uria | +2.112 |
inant | +2.094 |
Neg logit contributions | |
su | -2.059 |
ements | -1.831 |
iences | -1.729 |
Priv | -1.690 |
ement | -1.682 |
Token | 79 |
Token ID | 3720 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
unts | +5.368 |
olas | +5.367 |
llo | +5.161 |
uria | +4.720 |
inant | +4.673 |
Neg logit contributions | |
su | -6.246 |
ements | -5.933 |
iences | -5.650 |
��� | -5.622 |
mingham | -5.570 |
Token | - |
Token ID | 12 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
llo | +6.901 |
olas | +6.898 |
unts | +6.707 |
uria | +6.067 |
inant | +5.305 |
Neg logit contributions | |
su | -11.275 |
iences | -10.667 |
ruciating | -10.586 |
ements | -10.527 |
ynam | -10.326 |
Token | 488 |
Token ID | 33646 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
unts | +5.085 |
olas | +5.050 |
llo | +4.965 |
uria | +4.619 |
inant | +4.409 |
Neg logit contributions | |
su | -4.600 |
ements | -4.280 |
��� | -4.112 |
iences | -4.105 |
mingham | -3.982 |
Token | - |
Token ID | 12 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
llo | +5.858 |
olas | +5.797 |
unts | +5.757 |
uria | +4.875 |
inant | +4.864 |
Neg logit contributions | |
��� | -9.497 |
su | -9.140 |
ruciating | -8.634 |
ements | -8.502 |
iences | -8.458 |
Token | 46 |
Token ID | 3510 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
unts | +2.346 |
olas | +2.334 |
llo | +2.276 |
uria | +2.096 |
inant | +2.065 |
Neg logit contributions | |
su | -2.415 |
ements | -2.196 |
��� | -2.129 |
iences | -2.101 |
ruciating | -2.059 |
Token | 99 |
Token ID | 2079 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
olas | +1.424 |
unts | +1.420 |
llo | +1.384 |
uria | +1.280 |
inant | +1.269 |
Neg logit contributions | |
su | -1.446 |
ements | -1.299 |
iences | -1.234 |
��� | -1.223 |
mingham | -1.215 |
Token | I |
Token ID | 314 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
su | +1.842 |
ements | +1.568 |
iences | +1.468 |
ement | +1.467 |
Stronghold | +1.461 |
Neg logit contributions | |
unts | -2.222 |
olas | -2.185 |
llo | -2.105 |
ngth | -2.049 |
uria | -2.016 |
Token | caught |
Token ID | 4978 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
olas | +2.593 |
unts | +2.563 |
llo | +2.510 |
inant | +2.354 |
uria | +2.349 |
Neg logit contributions | |
su | -1.898 |
ements | -1.673 |
iences | -1.557 |
ement | -1.516 |
mingham | -1.510 |
Token | her |
Token ID | 607 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
su | +0.307 |
ements | +0.265 |
ement | +0.243 |
iences | +0.242 |
mingham | +0.239 |
Neg logit contributions | |
olas | -0.427 |
unts | -0.424 |
llo | -0.410 |
ngth | -0.392 |
uria | -0.391 |
Token | re |
Token ID | 302 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
llo | +4.367 |
unts | +4.337 |
olas | +4.233 |
uria | +3.850 |
inant | +3.789 |
Neg logit contributions | |
su | -7.023 |
��� | -6.543 |
ements | -6.441 |
iences | -6.308 |
ruciating | -6.160 |
Token | - |
Token ID | 12 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
olas | +2.006 |
unts | +1.998 |
llo | +1.949 |
uria | +1.799 |
inant | +1.785 |
Neg logit contributions | |
su | -2.304 |
ements | -2.072 |
iences | -1.975 |
��� | -1.950 |
mingham | -1.932 |
Token | en |
Token ID | 268 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
olas | +5.023 |
unts | +4.968 |
llo | +4.807 |
uria | +4.347 |
inant | +4.318 |
Neg logit contributions | |
��� | -10.267 |
su | -9.472 |
ements | -9.105 |
ruciating | -9.076 |
者 | -9.013 |
Token | acting |
Token ID | 27362 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
olas | +4.078 |
unts | +3.751 |
llo | +3.451 |
inant | +3.107 |
uria | +2.821 |
Neg logit contributions | |
��� | -15.984 |
su | -14.804 |
ements | -14.656 |
者 | -14.397 |
Stronghold | -14.249 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
su | +1.018 |
ements | +0.865 |
ement | +0.796 |
iences | +0.785 |
mingham | +0.781 |
Neg logit contributions | |
olas | -1.491 |
unts | -1.482 |
llo | -1.427 |
ngth | -1.385 |
uria | -1.372 |
Token | double |
Token ID | 4274 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
olas | +2.481 |
unts | +2.474 |
llo | +2.404 |
inant | +2.187 |
uria | +2.174 |
Neg logit contributions | |
su | -3.772 |
ements | -3.454 |
iences | -3.330 |
��� | -3.329 |
mingham | -3.261 |
Token | - |
Token ID | 12 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
olas | +3.517 |
unts | +3.514 |
llo | +3.459 |
inant | +3.099 |
uria | +3.078 |
Neg logit contributions | |
su | -4.726 |
��� | -4.385 |
ements | -4.326 |
iences | -4.240 |
ruciating | -4.136 |
Token | sl |
Token ID | 6649 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
olas | +4.833 |
unts | +4.673 |
llo | +4.596 |
inant | +4.136 |
uria | +3.999 |
Neg logit contributions | |
��� | -7.385 |
su | -7.030 |
ruciating | -6.794 |
ements | -6.639 |
Pradesh | -6.632 |
Token | party |
Token ID | 2151 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
olas | +0.167 |
unts | +0.166 |
llo | +0.161 |
uria | +0.151 |
inant | +0.150 |
Neg logit contributions | |
su | -0.146 |
ements | -0.129 |
iences | -0.120 |
mingham | -0.119 |
ement | -0.119 |
Token | interest |
Token ID | 1393 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
olas | +2.579 |
unts | +2.575 |
llo | +2.501 |
uria | +2.324 |
inant | +2.273 |
Neg logit contributions | |
su | -2.514 |
ements | -2.226 |
mingham | -2.123 |
iences | -2.115 |
��� | -2.064 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
su | +0.459 |
ements | +0.406 |
iences | +0.382 |
mingham | +0.376 |
ement | +0.375 |
Neg logit contributions | |
olas | -0.481 |
unts | -0.478 |
llo | -0.464 |
uria | -0.435 |
inant | -0.431 |
Token | not |
Token ID | 407 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
su | +1.953 |
ements | +1.697 |
ement | +1.568 |
iences | +1.561 |
Priv | +1.540 |
Neg logit contributions | |
olas | -2.501 |
unts | -2.481 |
llo | -2.407 |
ngth | -2.296 |
uria | -2.293 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
su | +1.420 |
ements | +1.242 |
iences | +1.152 |
ement | +1.145 |
mingham | +1.128 |
Neg logit contributions | |
olas | -1.751 |
unts | -1.735 |
llo | -1.684 |
uria | -1.600 |
inant | -1.591 |
Token | national |
Token ID | 2260 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
unts | +2.848 |
olas | +2.805 |
llo | +2.738 |
inant | +2.533 |
uria | +2.518 |
Neg logit contributions | |
su | -2.564 |
ements | -2.225 |
mingham | -2.110 |
iences | -2.105 |
��� | -2.066 |
Token | interest |
Token ID | 1393 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
unts | +7.591 |
llo | +7.234 |
olas | +7.232 |
inant | +6.390 |
uria | +6.169 |
Neg logit contributions | |
su | -11.030 |
��� | -10.746 |
ements | -10.300 |
mingham | -9.890 |
ruciating | -9.798 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
olas | +0.713 |
unts | +0.710 |
llo | +0.690 |
uria | +0.638 |
inant | +0.632 |
Neg logit contributions | |
su | -0.825 |
ements | -0.742 |
iences | -0.704 |
mingham | -0.696 |
��� | -0.691 |
Token |
|
Token ID | 198 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
olas | +2.707 |
unts | +2.704 |
llo | +2.681 |
uria | +2.386 |
inant | +2.338 |
Neg logit contributions | |
su | -3.047 |
ements | -2.755 |
��� | -2.709 |
iences | -2.673 |
mingham | -2.623 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
olas | +1.084 |
unts | +1.077 |
llo | +1.042 |
uria | +0.982 |
inant | +0.976 |
Neg logit contributions | |
su | -1.035 |
ements | -0.913 |
iences | -0.857 |
ement | -0.849 |
mingham | -0.843 |
Token | " |
Token ID | 1 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
su | +0.195 |
ements | +0.174 |
iences | +0.164 |
ement | +0.162 |
mingham | +0.161 |
Neg logit contributions | |
olas | -0.192 |
unts | -0.190 |
llo | -0.185 |
uria | -0.172 |
inant | -0.172 |
Token | dialog |
Token ID | 17310 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
olas | +2.209 |
unts | +2.208 |
llo | +2.140 |
uria | +2.007 |
inant | +1.991 |
Neg logit contributions | |
su | -2.034 |
ements | -1.791 |
iences | -1.695 |
mingham | -1.669 |
ement | -1.659 |
Token | or |
Token ID | 393 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
olas | +3.656 |
unts | +3.574 |
llo | +3.520 |
uria | +3.262 |
inant | +3.195 |
Neg logit contributions | |
su | -3.677 |
ements | -3.235 |
mingham | -3.155 |
Priv | -3.086 |
��� | -3.082 |
Token | on |
Token ID | 319 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
olas | +0.512 |
unts | +0.511 |
llo | +0.496 |
uria | +0.474 |
inant | +0.469 |
Neg logit contributions | |
su | -0.302 |
ements | -0.255 |
iences | -0.234 |
ement | -0.230 |
mingham | -0.230 |
Token | om |
Token ID | 296 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
olas | +3.618 |
unts | +3.525 |
llo | +3.396 |
uria | +3.241 |
inant | +3.161 |
Neg logit contributions | |
su | -3.391 |
ements | -3.044 |
Priv | -3.019 |
mingham | -2.984 |
��� | -2.973 |
Token | at |
Token ID | 265 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
su | +4.053 |
ements | +3.608 |
ement | +3.360 |
iences | +3.326 |
atom | +3.260 |
Neg logit contributions | |
olas | -4.388 |
llo | -4.361 |
unts | -4.328 |
uria | -3.941 |
ngth | -3.936 |
Token | op |
Token ID | 404 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
su | +7.503 |
ements | +6.468 |
iences | +6.215 |
mingham | +6.201 |
ynam | +6.125 |
Neg logit contributions | |
unts | -10.455 |
llo | -10.205 |
ngth | -10.023 |
olas | -9.805 |
inant | -9.588 |
Token | o |
Token ID | 78 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
su | +7.823 |
ements | +5.941 |
olitan | +5.572 |
ement | +5.149 |
iences | +4.989 |
Neg logit contributions | |
unts | -18.557 |
olas | -17.418 |
ngth | -17.226 |
llo | -17.208 |
inant | -17.119 |
Token | etic |
Token ID | 5139 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
su | +5.212 |
ements | +4.827 |
ement | +4.565 |
iences | +4.486 |
ynam | +4.065 |
Neg logit contributions | |
llo | -7.158 |
olas | -7.100 |
unts | -7.018 |
ngth | -6.874 |
uria | -6.701 |
Token | words |
Token ID | 2456 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
su | +2.593 |
ements | +2.277 |
iences | +2.116 |
ement | +2.104 |
mingham | +2.056 |
Neg logit contributions | |
olas | -3.183 |
unts | -3.169 |
llo | -3.073 |
uria | -2.918 |
ngth | -2.903 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
su | +1.318 |
ements | +1.159 |
iences | +1.084 |
ement | +1.076 |
mingham | +1.063 |
Neg logit contributions | |
olas | -1.459 |
unts | -1.451 |
llo | -1.404 |
uria | -1.326 |
inant | -1.317 |
Token | People |
Token ID | 4380 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
su | +0.392 |
ements | +0.344 |
iences | +0.321 |
ement | +0.318 |
mingham | +0.316 |
Neg logit contributions | |
olas | -0.458 |
unts | -0.455 |
llo | -0.441 |
uria | -0.417 |
inant | -0.414 |
Token | t |
Token ID | 83 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
su | +0.103 |
ements | +0.093 |
iences | +0.087 |
ement | +0.086 |
mingham | +0.086 |
Neg logit contributions | |
olas | -0.106 |
unts | -0.105 |
llo | -0.102 |
uria | -0.096 |
inant | -0.095 |
Token | ay |
Token ID | 323 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
olas | +0.419 |
unts | +0.415 |
llo | +0.400 |
uria | +0.373 |
inant | +0.370 |
Neg logit contributions | |
su | -0.532 |
ements | -0.478 |
iences | -0.452 |
ement | -0.449 |
mingham | -0.446 |
Token | l |
Token ID | 75 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
su | +3.694 |
ements | +3.252 |
ement | +3.050 |
iences | +3.043 |
Priv | +3.004 |
Neg logit contributions | |
olas | -3.387 |
unts | -3.361 |
llo | -3.231 |
inant | -3.072 |
uria | -3.045 |
Token | ort |
Token ID | 419 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
su | +4.326 |
ements | +3.741 |
ement | +3.508 |
iences | +3.479 |
mingham | +3.447 |
Neg logit contributions | |
unts | -4.760 |
olas | -4.710 |
llo | -4.571 |
inant | -4.398 |
ngth | -4.365 |
Token | ot |
Token ID | 313 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
su | +8.515 |
ements | +7.477 |
ement | +7.133 |
iences | +6.941 |
mingham | +6.865 |
Neg logit contributions | |
olas | -6.896 |
unts | -6.878 |
llo | -6.549 |
inant | -6.340 |
ngth | -6.293 |
Token | ft |
Token ID | 701 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
su | +8.355 |
ements | +7.274 |
ement | +6.887 |
iences | +6.781 |
mingham | +6.728 |
Neg logit contributions | |
unts | -6.708 |
olas | -6.608 |
ngth | -6.142 |
llo | -6.088 |
inant | -6.086 |
Token | w |
Token ID | 86 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
su | +11.524 |
ements | +9.388 |
ement | +9.073 |
iences | +9.002 |
mingham | +8.757 |
Neg logit contributions | |
olas | -10.307 |
unts | -10.178 |
inant | -9.896 |
llo | -9.830 |
ngth | -9.538 |
Token | > |
Token ID | 29 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
su | +6.765 |
ements | +5.781 |
iences | +5.514 |
ement | +5.406 |
mingham | +5.345 |
Neg logit contributions | |
olas | -6.606 |
unts | -6.511 |
llo | -6.355 |
inant | -6.189 |
uria | -6.011 |
Token | loving |
Token ID | 14442 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
olas | +3.138 |
unts | +3.087 |
llo | +3.057 |
uria | +2.815 |
inant | +2.776 |
Neg logit contributions | |
su | -2.745 |
ements | -2.462 |
iences | -2.336 |
mingham | -2.281 |
ynam | -2.263 |
Token | this |
Token ID | 428 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
olas | +1.851 |
unts | +1.840 |
llo | +1.790 |
uria | +1.658 |
inant | +1.649 |
Neg logit contributions | |
su | -1.572 |
ements | -1.400 |
iences | -1.312 |
mingham | -1.295 |
Priv | -1.281 |
Token | meme |
Token ID | 25336 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
su | +0.855 |
ements | +0.748 |
iences | +0.698 |
ement | +0.690 |
mingham | +0.686 |
Neg logit contributions | |
olas | -1.021 |
unts | -1.015 |
llo | -0.984 |
uria | -0.930 |
inant | -0.925 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
olas | +2.009 |
unts | +1.994 |
llo | +1.925 |
uria | +1.834 |
inant | +1.784 |
Neg logit contributions | |
su | -2.274 |
ements | -2.069 |
iences | -1.968 |
��� | -1.963 |
mingham | -1.939 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
olas | +0.307 |
unts | +0.304 |
llo | +0.297 |
uria | +0.276 |
inant | +0.273 |
Neg logit contributions | |
su | -0.295 |
ements | -0.262 |
iences | -0.246 |
ement | -0.244 |
mingham | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
su | +0.044 |
ements | +0.038 |
ement | +0.035 |
iences | +0.035 |
Priv | +0.035 |
Neg logit contributions | |
olas | -0.050 |
unts | -0.049 |
llo | -0.047 |
ngth | -0.046 |
uria | -0.045 |
Token | US |
Token ID | 2937 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
olas | +0.813 |
unts | +0.807 |
llo | +0.785 |
uria | +0.731 |
inant | +0.729 |
Neg logit contributions | |
su | -0.765 |
ements | -0.682 |
iences | -0.640 |
ement | -0.635 |
mingham | -0.630 |
Token | AT |
Token ID | 1404 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
su | +2.466 |
ements | +2.167 |
ement | +2.014 |
iences | +2.008 |
Priv | +1.975 |
Neg logit contributions | |
olas | -2.804 |
unts | -2.791 |
llo | -2.711 |
uria | -2.558 |
inant | -2.546 |
Token | OD |
Token ID | 3727 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
su | +2.702 |
ements | +2.377 |
ement | +2.203 |
iences | +2.185 |
mingham | +2.157 |
Neg logit contributions | |
olas | -3.081 |
unts | -3.038 |
llo | -2.944 |
uria | -2.802 |
inant | -2.757 |
Token | AY |
Token ID | 4792 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
su | +4.323 |
ements | +2.195 |
ynam | +1.864 |
ement | +1.807 |
atom | +1.767 |
Neg logit contributions | |
olas | -18.558 |
unts | -18.210 |
ngth | -17.412 |
llo | -17.291 |
inant | -17.280 |
Token | OP |
Token ID | 13349 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
su | +2.154 |
ements | +1.855 |
iences | +1.759 |
ement | +1.720 |
Pradesh | +1.709 |
Neg logit contributions | |
olas | -2.442 |
unts | -2.431 |
llo | -2.341 |
uria | -2.254 |
ngth | -2.215 |
Token | IN |
Token ID | 1268 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
olas | +0.385 |
unts | +0.381 |
llo | +0.362 |
uria | +0.328 |
inant | +0.324 |
Neg logit contributions | |
su | -0.790 |
ements | -0.723 |
iences | -0.692 |
ement | -0.687 |
mingham | -0.684 |
Token | ION |
Token ID | 2849 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
su | +4.786 |
ements | +4.337 |
iences | +4.100 |
ement | +4.077 |
Priv | +3.984 |
Neg logit contributions | |
olas | -3.730 |
unts | -3.712 |
llo | -3.550 |
ngth | -3.368 |
uria | -3.360 |
Token | About |
Token ID | 7994 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
su | +1.450 |
ements | +1.281 |
iences | +1.201 |
ement | +1.190 |
mingham | +1.182 |
Neg logit contributions | |
olas | -1.531 |
unts | -1.527 |
llo | -1.470 |
uria | -1.390 |
inant | -1.379 |
Token | x |
Token ID | 2124 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
su | +0.846 |
ements | +0.702 |
ement | +0.644 |
Priv | +0.636 |
iences | +0.632 |
Neg logit contributions | |
olas | -1.451 |
unts | -1.445 |
llo | -1.393 |
ngth | -1.357 |
uria | -1.344 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
su | +2.383 |
ements | +1.998 |
Priv | +1.882 |
ement | +1.871 |
mingham | +1.802 |
Neg logit contributions | |
olas | -3.031 |
unts | -2.984 |
ngth | -2.925 |
llo | -2.832 |
inant | -2.778 |
Token | x |
Token ID | 87 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
olas | +2.212 |
unts | +2.196 |
llo | +2.138 |
uria | +2.007 |
inant | +1.985 |
Neg logit contributions | |
su | -2.076 |
ements | -1.852 |
iences | -1.750 |
��� | -1.736 |
ement | -1.716 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
olas | +1.249 |
unts | +1.241 |
llo | +1.200 |
uria | +1.129 |
inant | +1.121 |
Neg logit contributions | |
su | -1.248 |
ements | -1.106 |
iences | -1.040 |
ement | -1.030 |
mingham | -1.023 |
Token | x |
Token ID | 87 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
olas | +0.558 |
unts | +0.555 |
llo | +0.536 |
uria | +0.508 |
ngth | +0.507 |
Neg logit contributions | |
su | -0.482 |
ements | -0.420 |
iences | -0.390 |
ement | -0.389 |
mingham | -0.384 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
su | +4.007 |
ements | +3.348 |
ement | +3.145 |
Priv | +3.113 |
atom | +2.908 |
Neg logit contributions | |
olas | -5.722 |
unts | -5.587 |
ngth | -5.517 |
llo | -5.195 |
inant | -5.193 |
Token | 120 |
Token ID | 10232 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
su | +6.403 |
ements | +4.801 |
Priv | +4.401 |
ement | +4.262 |
poor | +3.930 |
Neg logit contributions | |
olas | -16.559 |
unts | -16.079 |
ngth | -15.325 |
inant | -15.240 |
uria | -15.120 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
olas | +1.066 |
unts | +1.064 |
llo | +1.040 |
uria | +0.970 |
inant | +0.970 |
Neg logit contributions | |
su | -0.859 |
ements | -0.750 |
iences | -0.698 |
ement | -0.688 |
mingham | -0.686 |
Token | 25 |
Token ID | 1495 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
unts | +1.485 |
olas | +1.481 |
llo | +1.442 |
uria | +1.340 |
inant | +1.329 |
Neg logit contributions | |
su | -1.380 |
ements | -1.229 |
iences | -1.167 |
��� | -1.158 |
mingham | -1.143 |
Token | 290 |
Token ID | 24369 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
su | +0.542 |
ements | +0.477 |
iences | +0.446 |
mingham | +0.439 |
ement | +0.439 |
Neg logit contributions | |
olas | -0.660 |
unts | -0.657 |
llo | -0.639 |
uria | -0.602 |
inant | -0.597 |
Token | x |
Token ID | 2124 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
olas | +0.370 |
unts | +0.368 |
llo | +0.358 |
uria | +0.341 |
inant | +0.339 |
Neg logit contributions | |
su | -0.237 |
ements | -0.202 |
iences | -0.185 |
ement | -0.184 |
mingham | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
su | +1.494 |
ements | +1.304 |
iences | +1.212 |
ement | +1.204 |
mingham | +1.187 |
Neg logit contributions | |
olas | -1.805 |
unts | -1.793 |
llo | -1.743 |
uria | -1.649 |
inant | -1.641 |
Token | densely |
Token ID | 42255 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
su | +2.403 |
ements | +2.094 |
ement | +1.956 |
iences | +1.945 |
mingham | +1.914 |
Neg logit contributions | |
olas | -2.729 |
unts | -2.678 |
llo | -2.614 |
uria | -2.476 |
inant | -2.456 |
Token | forest |
Token ID | 8222 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
olas | +0.142 |
unts | +0.142 |
llo | +0.138 |
uria | +0.130 |
inant | +0.129 |
Neg logit contributions | |
su | -0.101 |
ements | -0.088 |
iences | -0.081 |
mingham | -0.080 |
Priv | -0.080 |
Token | ed |
Token ID | 276 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
unts | +3.180 |
olas | +3.176 |
llo | +3.041 |
inant | +2.733 |
uria | +2.690 |
Neg logit contributions | |
su | -6.831 |
ements | -6.526 |
iences | -6.346 |
��� | -6.275 |
Priv | -6.266 |
Token | landscape |
Token ID | 10747 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
su | +2.861 |
ements | +2.442 |
ement | +2.293 |
iences | +2.251 |
Pradesh | +2.248 |
Neg logit contributions | |
olas | -3.627 |
unts | -3.564 |
llo | -3.479 |
uria | -3.320 |
ngth | -3.312 |
Token | inter |
Token ID | 987 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
su | +1.799 |
ements | +1.564 |
iences | +1.462 |
ement | +1.455 |
mingham | +1.428 |
Neg logit contributions | |
olas | -2.060 |
unts | -2.044 |
llo | -1.982 |
uria | -1.873 |
inant | -1.868 |
Token | l |
Token ID | 75 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
su | +8.522 |
ements | +6.197 |
ement | +5.901 |
ynam | +5.786 |
iences | +5.690 |
Neg logit contributions | |
unts | -13.631 |
ngth | -13.231 |
olas | -13.108 |
llo | -12.840 |
uria | -12.729 |
Token | aced |
Token ID | 2286 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
su | +7.502 |
ements | +6.382 |
ynam | +6.156 |
ement | +6.041 |
iences | +5.917 |
Neg logit contributions | |
olas | -5.782 |
unts | -5.771 |
llo | -5.726 |
ngth | -5.704 |
uria | -5.313 |
Token | with |
Token ID | 351 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
su | +4.866 |
ements | +4.231 |
ement | +3.960 |
iences | +3.953 |
Pradesh | +3.869 |
Neg logit contributions | |
olas | -5.676 |
unts | -5.645 |
llo | -5.489 |
uria | -5.174 |
ngth | -5.157 |
Token | c |
Token ID | 269 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
su | +0.829 |
ements | +0.729 |
iences | +0.682 |
ement | +0.675 |
mingham | +0.671 |
Neg logit contributions | |
olas | -0.929 |
unts | -0.923 |
llo | -0.894 |
uria | -0.844 |
inant | -0.838 |
Token | ree |
Token ID | 631 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
olas | +0.508 |
unts | +0.508 |
llo | +0.485 |
uria | +0.448 |
inant | +0.444 |
Neg logit contributions | |
su | -0.675 |
ements | -0.601 |
iences | -0.582 |
��� | -0.579 |
Priv | -0.577 |
Token | " |
Token ID | 366 |
Feature activation | -2.54e-04 |
Pos logit contributions | |
su | +1.401 |
ements | +1.190 |
Priv | +1.114 |
ement | +1.095 |
Pradesh | +1.072 |
Neg logit contributions | |
olas | -2.077 |
unts | -2.058 |
llo | -1.970 |
ngth | -1.935 |
inant | -1.919 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
su | +0.003 |
ements | +0.002 |
iences | +0.002 |
ement | +0.002 |
mingham | +0.002 |
Neg logit contributions | |
olas | -0.003 |
unts | -0.003 |
llo | -0.003 |
uria | -0.003 |
inant | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
su | +2.992 |
ements | +2.533 |
ement | +2.354 |
Stronghold | +2.284 |
Priv | +2.269 |
Neg logit contributions | |
olas | -4.234 |
ngth | -4.137 |
unts | -4.120 |
llo | -3.968 |
inant | -3.936 |
Token | 01 |
Token ID | 486 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
su | +0.215 |
ements | +0.187 |
iences | +0.174 |
ement | +0.173 |
Priv | +0.172 |
Neg logit contributions | |
olas | -0.250 |
unts | -0.247 |
llo | -0.239 |
uria | -0.227 |
inant | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
su | +2.252 |
ements | +1.899 |
ement | +1.770 |
Priv | +1.756 |
Stronghold | +1.712 |
Neg logit contributions | |
olas | -2.900 |
unts | -2.838 |
ngth | -2.811 |
llo | -2.700 |
inant | -2.680 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
su | +1.190 |
ements | +1.019 |
Priv | +0.955 |
ement | +0.941 |
iences | +0.925 |
Neg logit contributions | |
olas | -1.460 |
unts | -1.437 |
llo | -1.383 |
ngth | -1.381 |
inant | -1.340 |
Token | "] |
Token ID | 8973 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
su | +7.903 |
ements | +6.097 |
Stronghold | +5.987 |
Olivier | +5.740 |
者 | +5.642 |
Neg logit contributions | |
ngth | -14.622 |
unts | -13.995 |
olas | -13.708 |
uria | -13.222 |
inant | -13.168 |
Token | [ |
Token ID | 685 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
su | +3.706 |
Stronghold | +2.866 |
Priv | +2.823 |
ements | +2.821 |
ement | +2.707 |
Neg logit contributions | |
ngth | -8.214 |
olas | -7.876 |
unts | -7.731 |
uria | -7.669 |
llo | -7.553 |
Token | Round |
Token ID | 22685 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
su | +5.533 |
Priv | +4.472 |
ements | +4.397 |
ement | +4.287 |
iences | +4.184 |
Neg logit contributions | |
olas | -8.296 |
llo | -7.984 |
ngth | -7.823 |
unts | -7.776 |
uria | -7.740 |
Token | " |
Token ID | 366 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
su | +6.981 |
ements | +4.989 |
ement | +4.708 |
Priv | +4.442 |
者 | +4.306 |
Neg logit contributions | |
ngth | -14.757 |
unts | -14.410 |
olas | -13.844 |
inant | -13.804 |
llo | -13.764 |
Token | 11 |
Token ID | 1157 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
su | +0.540 |
ements | +0.476 |
iences | +0.447 |
ement | +0.442 |
mingham | +0.439 |
Neg logit contributions | |
olas | -0.580 |
unts | -0.576 |
llo | -0.558 |
uria | -0.526 |
inant | -0.522 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
olas | +0.190 |
unts | +0.188 |
llo | +0.184 |
uria | +0.171 |
inant | +0.170 |
Neg logit contributions | |
su | -0.186 |
ements | -0.166 |
iences | -0.156 |
mingham | -0.154 |
ement | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
su | +2.800 |
ements | +2.410 |
iences | +2.247 |
ement | +2.225 |
Stronghold | +2.192 |
Neg logit contributions | |
unts | -3.687 |
olas | -3.684 |
llo | -3.549 |
uria | -3.391 |
inant | -3.381 |
Token | st |
Token ID | 336 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
su | +2.401 |
ements | +2.095 |
iences | +1.951 |
ement | +1.948 |
mingham | +1.915 |
Neg logit contributions | |
olas | -2.745 |
unts | -2.733 |
llo | -2.628 |
uria | -2.507 |
ngth | -2.490 |
Token | on |
Token ID | 261 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
su | +4.988 |
ements | +4.451 |
ement | +4.165 |
iences | +4.110 |
ynam | +4.037 |
Neg logit contributions | |
olas | -4.688 |
unts | -4.662 |
llo | -4.536 |
uria | -4.329 |
inant | -4.293 |
Token | ework |
Token ID | 6433 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
olas | +0.520 |
unts | +0.517 |
llo | +0.502 |
uria | +0.477 |
inant | +0.475 |
Neg logit contributions | |
su | -0.346 |
ements | -0.293 |
iences | -0.276 |
mingham | -0.271 |
Pradesh | -0.268 |
Token | a |
Token ID | 257 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
su | +3.374 |
ements | +2.928 |
ement | +2.734 |
iences | +2.709 |
Stronghold | +2.620 |
Neg logit contributions | |
unts | -4.221 |
olas | -4.209 |
llo | -4.033 |
inant | -3.859 |
uria | -3.853 |
Token | light |
Token ID | 1657 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
su | +8.460 |
ements | +7.024 |
guid | +6.872 |
ement | +6.813 |
Stronghold | +6.652 |
Neg logit contributions | |
olas | -12.458 |
unts | -11.630 |
llo | -11.558 |
ngth | -11.398 |
uria | -11.356 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
su | +7.784 |
ement | +6.540 |
ements | +6.423 |
mingham | +6.216 |
Stronghold | +6.161 |
Neg logit contributions | |
olas | -9.762 |
unts | -9.482 |
llo | -9.319 |
ngth | -8.948 |
inant | -8.849 |
Token | m |
Token ID | 285 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
su | +2.206 |
ements | +1.918 |
iences | +1.790 |
ement | +1.776 |
mingham | +1.750 |
Neg logit contributions | |
olas | -2.681 |
unts | -2.674 |
llo | -2.582 |
uria | -2.459 |
inant | -2.440 |
Token | ott |
Token ID | 1252 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
su | +6.666 |
ements | +5.824 |
ement | +5.777 |
iences | +5.374 |
ynam | +5.298 |
Neg logit contributions | |
olas | -5.919 |
unts | -5.911 |
llo | -5.795 |
uria | -5.526 |
inant | -5.506 |
Token | led |
Token ID | 992 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
su | +1.392 |
ements | +1.235 |
iences | +1.162 |
ement | +1.155 |
mingham | +1.145 |
Neg logit contributions | |
olas | -1.325 |
unts | -1.317 |
llo | -1.272 |
uria | -1.195 |
inant | -1.186 |
Token | eker |
Token ID | 28233 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
olas | +2.048 |
unts | +2.033 |
llo | +1.975 |
uria | +1.849 |
inant | +1.827 |
Neg logit contributions | |
su | -2.027 |
ements | -1.787 |
iences | -1.715 |
Pradesh | -1.694 |
mingham | -1.687 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
su | +2.267 |
ements | +1.997 |
iences | +1.874 |
ement | +1.857 |
mingham | +1.842 |
Neg logit contributions | |
olas | -2.417 |
unts | -2.401 |
llo | -2.325 |
uria | -2.192 |
inant | -2.178 |
Token |
|
Token ID | 198 |
Feature activation | -7.49e-05 |
Pos logit contributions | |
olas | +0.301 |
unts | +0.299 |
llo | +0.288 |
ngth | +0.275 |
uria | +0.274 |
Neg logit contributions | |
su | -0.273 |
ements | -0.239 |
ement | -0.222 |
iences | -0.222 |
Priv | -0.220 |
Token | Ph |
Token ID | 2725 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
su | +0.001 |
ements | +0.001 |
iences | +0.001 |
mingham | +0.001 |
ement | +0.001 |
Neg logit contributions | |
olas | -0.001 |
unts | -0.001 |
llo | -0.001 |
uria | -0.001 |
inant | -0.001 |
Token | yt |
Token ID | 20760 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
olas | +2.697 |
unts | +2.650 |
llo | +2.521 |
uria | +2.378 |
inant | +2.307 |
Neg logit contributions | |
su | -4.267 |
ements | -3.945 |
��� | -3.921 |
Priv | -3.809 |
者 | -3.764 |
Token | ot |
Token ID | 313 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
su | +6.656 |
ements | +5.802 |
ement | +5.501 |
mingham | +5.457 |
ynam | +5.427 |
Neg logit contributions | |
unts | -5.984 |
olas | -5.809 |
llo | -5.634 |
ngth | -5.464 |
inant | -5.408 |
Token | itan |
Token ID | 18642 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
su | +11.608 |
ements | +10.217 |
ement | +9.908 |
Stronghold | +9.829 |
atom | +9.571 |
Neg logit contributions | |
unts | -9.697 |
olas | -9.262 |
ngth | -8.884 |
llo | -8.525 |
inant | -8.329 |
Token | vs |
Token ID | 3691 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
su | +4.662 |
ements | +4.107 |
Stronghold | +3.871 |
ement | +3.867 |
iences | +3.826 |
Neg logit contributions | |
olas | -4.752 |
unts | -4.698 |
llo | -4.558 |
inant | -4.307 |
uria | -4.250 |
Token | Torch |
Token ID | 34868 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
su | +2.203 |
ements | +1.945 |
iences | +1.823 |
ement | +1.813 |
mingham | +1.792 |
Neg logit contributions | |
olas | -2.239 |
unts | -2.222 |
llo | -2.148 |
uria | -2.024 |
inant | -2.015 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
olas | +0.456 |
unts | +0.454 |
llo | +0.437 |
uria | +0.415 |
inant | +0.411 |
Neg logit contributions | |
su | -0.448 |
ements | -0.401 |
iences | -0.376 |
Priv | -0.374 |
ement | -0.373 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
su | +2.399 |
ements | +2.120 |
iences | +1.982 |
ement | +1.976 |
mingham | +1.952 |
Neg logit contributions | |
olas | -2.450 |
unts | -2.429 |
llo | -2.347 |
uria | -2.215 |
inant | -2.207 |
Token | 01 |
Token ID | 486 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
su | +0.215 |
ements | +0.187 |
iences | +0.174 |
ement | +0.173 |
Priv | +0.172 |
Neg logit contributions | |
olas | -0.250 |
unts | -0.247 |
llo | -0.239 |
uria | -0.227 |
inant | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
su | +2.252 |
ements | +1.899 |
ement | +1.770 |
Priv | +1.756 |
Stronghold | +1.712 |
Neg logit contributions | |
olas | -2.900 |
unts | -2.838 |
ngth | -2.811 |
llo | -2.700 |
inant | -2.680 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
su | +1.190 |
ements | +1.019 |
Priv | +0.955 |
ement | +0.941 |
iences | +0.925 |
Neg logit contributions | |
olas | -1.460 |
unts | -1.437 |
llo | -1.383 |
ngth | -1.381 |
inant | -1.340 |
Token | "] |
Token ID | 8973 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
su | +7.903 |
ements | +6.097 |
Stronghold | +5.987 |
Olivier | +5.740 |
者 | +5.642 |
Neg logit contributions | |
ngth | -14.622 |
unts | -13.995 |
olas | -13.708 |
uria | -13.222 |
inant | -13.168 |
Token | [ |
Token ID | 685 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
su | +3.706 |
Stronghold | +2.866 |
Priv | +2.823 |
ements | +2.821 |
ement | +2.707 |
Neg logit contributions | |
ngth | -8.214 |
olas | -7.876 |
unts | -7.731 |
uria | -7.669 |
llo | -7.553 |
Token | Round |
Token ID | 22685 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
su | +5.533 |
Priv | +4.472 |
ements | +4.397 |
ement | +4.287 |
iences | +4.184 |
Neg logit contributions | |
olas | -8.296 |
llo | -7.984 |
ngth | -7.823 |
unts | -7.776 |
uria | -7.740 |
Token | " |
Token ID | 366 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
su | +6.981 |
ements | +4.989 |
ement | +4.708 |
Priv | +4.442 |
者 | +4.306 |
Neg logit contributions | |
ngth | -14.757 |
unts | -14.410 |
olas | -13.844 |
inant | -13.804 |
llo | -13.764 |
Token | 11 |
Token ID | 1157 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
su | +0.540 |
ements | +0.476 |
iences | +0.447 |
ement | +0.442 |
mingham | +0.439 |
Neg logit contributions | |
olas | -0.580 |
unts | -0.576 |
llo | -0.558 |
uria | -0.526 |
inant | -0.522 |
Token | "] |
Token ID | 8973 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
su | +4.149 |
ements | +3.567 |
ement | +3.335 |
Priv | +3.310 |
iences | +3.295 |
Neg logit contributions | |
olas | -4.443 |
unts | -4.389 |
llo | -4.249 |
ngth | -4.109 |
inant | -4.091 |
Token | [ |
Token ID | 685 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
su | +3.761 |
ements | +2.880 |
Priv | +2.796 |
Stronghold | +2.715 |
ement | +2.708 |
Neg logit contributions | |
ngth | -7.534 |
olas | -7.458 |
unts | -7.404 |
uria | -7.104 |
inant | -7.078 |
Token | White |
Token ID | 12256 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
su | +4.903 |
ements | +4.005 |
Priv | +3.898 |
iences | +3.760 |
ement | +3.707 |
Neg logit contributions | |
olas | -6.852 |
llo | -6.735 |
ngth | -6.653 |
unts | -6.610 |
uria | -6.575 |
Token | that |
Token ID | 326 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
su | +3.040 |
ements | +2.590 |
iences | +2.442 |
ement | +2.409 |
Stronghold | +2.375 |
Neg logit contributions | |
olas | -3.941 |
unts | -3.888 |
llo | -3.792 |
uria | -3.654 |
inant | -3.616 |
Token | means |
Token ID | 1724 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
su | +2.375 |
ements | +2.068 |
iences | +1.939 |
ement | +1.926 |
mingham | +1.896 |
Neg logit contributions | |
olas | -2.711 |
unts | -2.672 |
llo | -2.606 |
uria | -2.462 |
inant | -2.440 |
Token | that |
Token ID | 326 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
su | +1.436 |
ements | +1.243 |
iences | +1.165 |
ement | +1.147 |
mingham | +1.137 |
Neg logit contributions | |
olas | -1.784 |
unts | -1.768 |
llo | -1.722 |
uria | -1.639 |
inant | -1.624 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
su | +3.506 |
ements | +2.976 |
iences | +2.815 |
ement | +2.771 |
Stronghold | +2.742 |
Neg logit contributions | |
olas | -4.544 |
unts | -4.444 |
llo | -4.371 |
uria | -4.215 |
ngth | -4.182 |
Token | mat |
Token ID | 2603 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
su | +3.512 |
ements | +3.031 |
iences | +2.831 |
ement | +2.783 |
Priv | +2.755 |
Neg logit contributions | |
olas | -4.546 |
unts | -4.461 |
llo | -4.362 |
uria | -4.191 |
ngth | -4.184 |
Token | ri |
Token ID | 380 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
unts | +1.956 |
olas | +1.954 |
llo | +1.857 |
inant | +1.771 |
uria | +1.757 |
Neg logit contributions | |
su | -1.972 |
ements | -1.759 |
Priv | -1.687 |
mingham | -1.676 |
��� | -1.664 |
Token | archs |
Token ID | 34592 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
su | +7.413 |
ements | +6.079 |
iences | +5.476 |
atom | +5.453 |
ement | +5.423 |
Neg logit contributions | |
unts | -13.405 |
olas | -13.229 |
llo | -12.799 |
inant | -12.710 |
ngth | -12.584 |
Token | are |
Token ID | 389 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
su | +0.590 |
ements | +0.519 |
iences | +0.485 |
ement | +0.480 |
mingham | +0.478 |
Neg logit contributions | |
olas | -0.662 |
unts | -0.658 |
llo | -0.638 |
uria | -0.601 |
inant | -0.598 |
Token | great |
Token ID | 1049 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
su | +2.540 |
ements | +2.199 |
iences | +2.029 |
ement | +2.029 |
mingham | +1.999 |
Neg logit contributions | |
olas | -3.040 |
unts | -2.979 |
llo | -2.917 |
uria | -2.782 |
ngth | -2.776 |
Token | cooks |
Token ID | 38383 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
su | +0.439 |
ements | +0.385 |
iences | +0.359 |
ement | +0.356 |
mingham | +0.354 |
Neg logit contributions | |
olas | -0.525 |
unts | -0.525 |
llo | -0.507 |
uria | -0.477 |
inant | -0.475 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
unts | +2.647 |
olas | +2.618 |
llo | +2.532 |
uria | +2.350 |
inant | +2.347 |
Neg logit contributions | |
su | -2.723 |
ements | -2.473 |
��� | -2.349 |
iences | -2.325 |
mingham | -2.309 |
Token | s |
Token ID | 82 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
su | +0.550 |
ements | +0.495 |
iences | +0.469 |
mingham | +0.464 |
ement | +0.463 |
Neg logit contributions | |
olas | -0.481 |
unts | -0.478 |
llo | -0.461 |
uria | -0.430 |
inant | -0.425 |
Token | -- |
Token ID | 1377 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
su | +5.536 |
ements | +4.805 |
Priv | +4.607 |
ement | +4.489 |
iences | +4.442 |
Neg logit contributions | |
unts | -6.200 |
olas | -6.179 |
llo | -6.014 |
inant | -5.746 |
uria | -5.666 |
Token | key |
Token ID | 2539 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
su | +3.144 |
ements | +2.724 |
iences | +2.561 |
ement | +2.536 |
Priv | +2.536 |
Neg logit contributions | |
olas | -3.332 |
unts | -3.312 |
llo | -3.220 |
inant | -3.017 |
uria | -3.007 |
Token | < |
Token ID | 1279 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
su | +0.338 |
ements | +0.297 |
iences | +0.278 |
ement | +0.275 |
mingham | +0.274 |
Neg logit contributions | |
olas | -0.382 |
unts | -0.378 |
llo | -0.367 |
uria | -0.347 |
inant | -0.344 |
Token | Access |
Token ID | 15457 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
olas | +2.342 |
unts | +2.333 |
llo | +2.249 |
uria | +2.134 |
inant | +2.099 |
Neg logit contributions | |
su | -2.215 |
ements | -2.026 |
iences | -1.900 |
mingham | -1.891 |
��� | -1.880 |
Token | Key |
Token ID | 7383 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
su | +5.826 |
ements | +5.076 |
Priv | +4.927 |
ement | +4.808 |
iences | +4.792 |
Neg logit contributions | |
unts | -6.161 |
olas | -6.126 |
llo | -5.840 |
inant | -5.504 |
uria | -5.502 |
Token | ID |
Token ID | 4522 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
su | +9.409 |
Priv | +7.754 |
guid | +7.698 |
ements | +7.653 |
Stronghold | +7.597 |
Neg logit contributions | |
olas | -11.455 |
unts | -11.390 |
llo | -10.914 |
inant | -10.172 |
uria | -9.945 |
Token | > |
Token ID | 29 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
su | +7.972 |
ements | +6.625 |
Priv | +6.417 |
Stronghold | +6.307 |
iences | +6.273 |
Neg logit contributions | |
olas | -9.898 |
unts | -9.692 |
llo | -9.218 |
inant | -8.807 |
uria | -8.789 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
su | +1.102 |
ements | +0.974 |
iences | +0.913 |
ement | +0.904 |
mingham | +0.899 |
Neg logit contributions | |
olas | -1.163 |
unts | -1.156 |
llo | -1.119 |
uria | -1.054 |
inant | -1.046 |
Token | secret |
Token ID | 21078 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
su | +3.907 |
ements | +3.374 |
iences | +3.176 |
Priv | +3.164 |
ement | +3.151 |
Neg logit contributions | |
olas | -3.909 |
unts | -3.863 |
llo | -3.769 |
inant | -3.525 |
ngth | -3.504 |
Token | < |
Token ID | 1279 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
su | +0.832 |
ements | +0.747 |
iences | +0.708 |
ement | +0.699 |
mingham | +0.696 |
Neg logit contributions | |
olas | -0.732 |
unts | -0.725 |
llo | -0.699 |
uria | -0.656 |
inant | -0.649 |
Token |
|
Token ID | 198 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
su | +1.458 |
ements | +1.242 |
ement | +1.158 |
Priv | +1.150 |
iences | +1.128 |
Neg logit contributions | |
olas | -1.820 |
unts | -1.800 |
ngth | -1.728 |
llo | -1.709 |
uria | -1.665 |
Token | The |
Token ID | 464 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
olas | +0.504 |
unts | +0.501 |
llo | +0.489 |
uria | +0.454 |
inant | +0.454 |
Neg logit contributions | |
su | -0.475 |
ements | -0.423 |
iences | -0.399 |
mingham | -0.393 |
ement | -0.391 |
Token | issue |
Token ID | 2071 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
olas | +0.063 |
unts | +0.063 |
llo | +0.061 |
uria | +0.057 |
inant | +0.057 |
Neg logit contributions | |
su | -0.055 |
ements | -0.048 |
iences | -0.046 |
ement | -0.045 |
mingham | -0.045 |
Token | has |
Token ID | 468 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
olas | +0.328 |
unts | +0.326 |
llo | +0.317 |
uria | +0.297 |
inant | +0.296 |
Neg logit contributions | |
su | -0.314 |
ements | -0.279 |
iences | -0.262 |
mingham | -0.260 |
ement | -0.259 |
Token | become |
Token ID | 1716 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
su | +1.841 |
ements | +1.606 |
iences | +1.502 |
ement | +1.491 |
Priv | +1.469 |
Neg logit contributions | |
olas | -2.158 |
unts | -2.146 |
llo | -2.070 |
uria | -1.965 |
ngth | -1.962 |
Token | front |
Token ID | 2166 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
su | +1.758 |
ements | +1.520 |
iences | +1.416 |
ement | +1.403 |
mingham | +1.391 |
Neg logit contributions | |
olas | -2.211 |
unts | -2.210 |
llo | -2.132 |
uria | -2.023 |
ngth | -2.019 |
Token | - |
Token ID | 12 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
su | +7.601 |
ements | +6.135 |
Pradesh | +6.007 |
iences | +5.883 |
ement | +5.778 |
Neg logit contributions | |
unts | -12.715 |
olas | -12.450 |
llo | -12.197 |
uria | -11.946 |
ngth | -11.711 |
Token | page |
Token ID | 7700 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
su | +8.551 |
ements | +7.269 |
atom | +6.865 |
iences | +6.856 |
ement | +6.841 |
Neg logit contributions | |
unts | -7.685 |
olas | -7.512 |
llo | -7.286 |
uria | -7.022 |
ngth | -6.824 |
Token | news |
Token ID | 1705 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
su | +0.760 |
ements | +0.687 |
iences | +0.652 |
ement | +0.647 |
mingham | +0.645 |
Neg logit contributions | |
olas | -0.532 |
unts | -0.527 |
llo | -0.508 |
uria | -0.471 |
inant | -0.467 |
Token | since |
Token ID | 1201 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
su | +2.351 |
ements | +2.040 |
iences | +1.922 |
ement | +1.900 |
mingham | +1.874 |
Neg logit contributions | |
olas | -2.796 |
unts | -2.795 |
llo | -2.688 |
uria | -2.539 |
ngth | -2.533 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
olas | +1.265 |
unts | +1.251 |
llo | +1.222 |
uria | +1.136 |
inant | +1.130 |
Neg logit contributions | |
su | -1.192 |
ements | -1.056 |
iences | -0.998 |
mingham | -0.985 |
ement | -0.985 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
olas | +1.171 |
unts | +1.167 |
llo | +1.129 |
uria | +1.065 |
inant | +1.054 |
Neg logit contributions | |
su | -1.101 |
ements | -0.968 |
iences | -0.913 |
mingham | -0.905 |
ement | -0.893 |
Token | art |
Token ID | 1242 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
olas | +0.155 |
unts | +0.154 |
llo | +0.149 |
uria | +0.142 |
inant | +0.141 |
Neg logit contributions | |
su | -0.128 |
ements | -0.113 |
iences | -0.105 |
mingham | -0.104 |
ement | -0.103 |
Token | are |
Token ID | 389 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
olas | +5.931 |
unts | +5.881 |
llo | +5.698 |
uria | +5.570 |
inant | +5.328 |
Neg logit contributions | |
su | -5.585 |
ements | -4.994 |
��� | -4.813 |
mingham | -4.700 |
ruciating | -4.609 |
Token | often |
Token ID | 1690 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
su | +1.313 |
ements | +1.142 |
iences | +1.061 |
ement | +1.050 |
mingham | +1.038 |
Neg logit contributions | |
olas | -1.675 |
unts | -1.664 |
llo | -1.617 |
uria | -1.532 |
inant | -1.523 |
Token | closely |
Token ID | 7173 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
su | +1.527 |
ements | +1.329 |
iences | +1.235 |
ement | +1.225 |
mingham | +1.209 |
Neg logit contributions | |
olas | -1.908 |
unts | -1.894 |
llo | -1.840 |
uria | -1.742 |
inant | -1.734 |
Token | inter |
Token ID | 987 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
su | +4.229 |
ements | +3.529 |
ement | +3.244 |
iences | +3.242 |
ynam | +3.201 |
Neg logit contributions | |
olas | -5.917 |
unts | -5.858 |
llo | -5.668 |
ngth | -5.613 |
uria | -5.466 |
Token | ming |
Token ID | 2229 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
su | +8.464 |
ements | +6.513 |
ynam | +6.275 |
iences | +6.022 |
ement | +6.007 |
Neg logit contributions | |
unts | -11.822 |
olas | -11.617 |
ngth | -11.483 |
llo | -11.210 |
uria | -11.162 |
Token | led |
Token ID | 992 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
su | +2.427 |
ements | +2.148 |
iences | +2.022 |
ement | +1.998 |
mingham | +1.952 |
Neg logit contributions | |
olas | -2.442 |
unts | -2.433 |
llo | -2.352 |
uria | -2.256 |
ngth | -2.251 |
Token | as |
Token ID | 355 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
su | +1.031 |
ements | +0.907 |
iences | +0.849 |
ement | +0.841 |
mingham | +0.835 |
Neg logit contributions | |
olas | -1.141 |
unts | -1.134 |
llo | -1.098 |
uria | -1.036 |
inant | -1.029 |
Token | new |
Token ID | 649 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
olas | +0.358 |
unts | +0.356 |
llo | +0.344 |
uria | +0.326 |
inant | +0.323 |
Neg logit contributions | |
su | -0.298 |
ements | -0.261 |
iences | -0.243 |
mingham | -0.242 |
ement | -0.241 |
Token | values |
Token ID | 3815 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
su | +2.898 |
ements | +2.541 |
iences | +2.372 |
ement | +2.329 |
Priv | +2.290 |
Neg logit contributions | |
olas | -3.679 |
unts | -3.663 |
llo | -3.557 |
uria | -3.391 |
ngth | -3.377 |
Token | a |
Token ID | 257 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
su | +1.557 |
ements | +1.360 |
iences | +1.268 |
ement | +1.255 |
mingham | +1.246 |
Neg logit contributions | |
olas | -1.897 |
unts | -1.885 |
llo | -1.829 |
uria | -1.730 |
inant | -1.719 |
Token | neo |
Token ID | 19102 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
su | +3.012 |
ements | +2.591 |
ement | +2.410 |
iences | +2.382 |
Priv | +2.351 |
Neg logit contributions | |
olas | -3.974 |
unts | -3.884 |
llo | -3.776 |
uria | -3.636 |
ngth | -3.628 |
Token | - |
Token ID | 12 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
su | +1.444 |
ements | +1.288 |
iences | +1.219 |
ement | +1.204 |
mingham | +1.203 |
Neg logit contributions | |
olas | -1.315 |
unts | -1.307 |
llo | -1.262 |
uria | -1.182 |
inant | -1.176 |
Token | A |
Token ID | 32 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
su | +4.438 |
ements | +3.831 |
Priv | +3.588 |
iences | +3.588 |
ement | +3.558 |
Neg logit contributions | |
olas | -4.501 |
unts | -4.476 |
llo | -4.328 |
ngth | -4.100 |
uria | -4.099 |
Token | rist |
Token ID | 1585 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
su | +0.915 |
ements | +0.826 |
iences | +0.784 |
ement | +0.779 |
mingham | +0.775 |
Neg logit contributions | |
olas | -0.639 |
unts | -0.633 |
llo | -0.608 |
uria | -0.563 |
inant | -0.559 |
Token | ot |
Token ID | 313 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
su | +3.540 |
ements | +3.114 |
iences | +2.889 |
ement | +2.875 |
ynam | +2.804 |
Neg logit contributions | |
unts | -4.383 |
olas | -4.313 |
llo | -4.201 |
uria | -3.984 |
ngth | -3.982 |
Token | el |
Token ID | 417 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
su | +5.542 |
ements | +4.138 |
ement | +3.769 |
iences | +3.599 |
ynam | +3.592 |
Neg logit contributions | |
unts | -15.069 |
olas | -14.837 |
ngth | -14.785 |
llo | -14.064 |
inant | -14.046 |
Token | ian |
Token ID | 666 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
su | +6.427 |
ements | +5.602 |
ement | +5.325 |
iences | +5.262 |
ynam | +5.124 |
Neg logit contributions | |
unts | -7.651 |
olas | -7.550 |
llo | -7.270 |
ngth | -7.182 |
uria | -6.836 |
Token | approach |
Token ID | 3164 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
su | +3.667 |
ements | +3.083 |
ement | +2.873 |
iences | +2.788 |
ynam | +2.786 |
Neg logit contributions | |
olas | -5.489 |
unts | -5.438 |
llo | -5.235 |
ngth | -5.132 |
uria | -5.055 |
Token | which |
Token ID | 543 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
su | +2.519 |
ements | +2.196 |
ement | +2.042 |
iences | +2.031 |
Priv | +1.993 |
Neg logit contributions | |
olas | -2.968 |
unts | -2.962 |
llo | -2.849 |
uria | -2.703 |
inant | -2.687 |
Token | she |
Token ID | 673 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
su | +0.184 |
ements | +0.161 |
iences | +0.150 |
ement | +0.149 |
mingham | +0.148 |
Neg logit contributions | |
olas | -0.215 |
unts | -0.214 |
llo | -0.208 |
uria | -0.196 |
inant | -0.195 |
Token | single |
Token ID | 2060 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
su | +2.579 |
ements | +2.260 |
ement | +2.106 |
iences | +2.095 |
mingham | +2.063 |
Neg logit contributions | |
olas | -3.038 |
unts | -2.978 |
llo | -2.906 |
uria | -2.764 |
ngth | -2.755 |
Token | bill |
Token ID | 2855 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
su | +2.016 |
ements | +1.775 |
ement | +1.651 |
iences | +1.648 |
mingham | +1.627 |
Neg logit contributions | |
olas | -2.301 |
unts | -2.277 |
llo | -2.202 |
uria | -2.089 |
ngth | -2.071 |
Token | into |
Token ID | 656 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
su | +2.165 |
ements | +1.886 |
ement | +1.749 |
iences | +1.739 |
Priv | +1.717 |
Neg logit contributions | |
olas | -2.704 |
unts | -2.684 |
llo | -2.593 |
ngth | -2.462 |
inant | -2.459 |
Token | law |
Token ID | 1099 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
su | +2.858 |
ements | +2.581 |
iences | +2.448 |
ement | +2.437 |
mingham | +2.421 |
Neg logit contributions | |
olas | -1.972 |
unts | -1.954 |
llo | -1.879 |
uria | -1.739 |
inant | -1.728 |
Token | limiting |
Token ID | 15637 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
su | +3.829 |
ements | +3.346 |
ement | +3.125 |
Priv | +3.040 |
iences | +3.020 |
Neg logit contributions | |
olas | -4.945 |
unts | -4.894 |
llo | -4.718 |
ngth | -4.511 |
inant | -4.505 |
Token | the |
Token ID | 262 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
su | +4.714 |
ements | +3.966 |
ement | +3.622 |
iences | +3.498 |
Priv | +3.483 |
Neg logit contributions | |
olas | -7.615 |
unts | -7.513 |
llo | -7.381 |
ngth | -7.271 |
inant | -7.071 |
Token | use |
Token ID | 779 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
su | +7.958 |
ements | +6.575 |
ement | +6.249 |
blanket | +5.974 |
Priv | +5.897 |
Neg logit contributions | |
olas | -11.674 |
llo | -11.664 |
unts | -11.566 |
ngth | -11.277 |
uria | -10.721 |
Token | or |
Token ID | 393 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
su | +4.603 |
ements | +3.962 |
iences | +3.693 |
ement | +3.678 |
Priv | +3.603 |
Neg logit contributions | |
unts | -6.280 |
olas | -6.268 |
llo | -6.102 |
uria | -5.790 |
ngth | -5.714 |
Token | purchase |
Token ID | 5001 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
su | +5.288 |
ements | +4.462 |
ement | +4.185 |
iences | +4.142 |
mingham | +4.001 |
Neg logit contributions | |
olas | -7.827 |
unts | -7.789 |
llo | -7.671 |
ngth | -7.413 |
inant | -7.262 |
Token | of |
Token ID | 286 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
su | +3.641 |
ements | +3.184 |
ement | +2.960 |
iences | +2.951 |
mingham | +2.874 |
Neg logit contributions | |
olas | -4.737 |
unts | -4.732 |
llo | -4.586 |
uria | -4.320 |
ngth | -4.303 |
Token | guns |
Token ID | 6541 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
su | +4.877 |
ements | +4.033 |
ement | +3.781 |
Priv | +3.687 |
iences | +3.670 |
Neg logit contributions | |
unts | -7.367 |
olas | -7.288 |
llo | -7.255 |
ngth | -7.086 |
uria | -6.852 |
Token | tendency |
Token ID | 13542 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
su | +1.464 |
ements | +1.275 |
iences | +1.184 |
ement | +1.177 |
mingham | +1.159 |
Neg logit contributions | |
olas | -1.835 |
unts | -1.812 |
llo | -1.768 |
uria | -1.677 |
inant | -1.660 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
su | +1.328 |
ements | +1.170 |
iences | +1.098 |
ement | +1.083 |
mingham | +1.083 |
Neg logit contributions | |
olas | -1.444 |
unts | -1.432 |
llo | -1.391 |
uria | -1.310 |
inant | -1.300 |
Token | look |
Token ID | 804 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
su | +1.136 |
ements | +0.990 |
iences | +0.920 |
ement | +0.915 |
mingham | +0.905 |
Neg logit contributions | |
olas | -1.386 |
unts | -1.375 |
llo | -1.335 |
uria | -1.268 |
inant | -1.257 |
Token | to |
Token ID | 284 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
olas | +0.842 |
unts | +0.835 |
llo | +0.812 |
inant | +0.758 |
uria | +0.758 |
Neg logit contributions | |
su | -0.769 |
ements | -0.679 |
iences | -0.643 |
mingham | -0.636 |
ement | -0.633 |
Token | Ant |
Token ID | 3738 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
su | +0.275 |
ements | +0.240 |
iences | +0.225 |
ement | +0.222 |
mingham | +0.222 |
Neg logit contributions | |
olas | -0.327 |
unts | -0.325 |
llo | -0.315 |
uria | -0.297 |
inant | -0.295 |
Token | wan |
Token ID | 8149 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
su | +1.499 |
ements | +1.322 |
iences | +1.241 |
mingham | +1.224 |
ement | +1.224 |
Neg logit contributions | |
olas | -1.614 |
unts | -1.598 |
llo | -1.549 |
uria | -1.463 |
inant | -1.451 |
Token | Good |
Token ID | 4599 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
su | +6.731 |
Stevenson | +5.397 |
ements | +5.393 |
ement | +5.208 |
ruciating | +4.877 |
Neg logit contributions | |
olas | -13.388 |
unts | -13.196 |
llo | -12.856 |
ngth | -12.816 |
uria | -12.261 |
Token | ley |
Token ID | 1636 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
su | +3.317 |
ements | +2.922 |
ement | +2.791 |
iences | +2.755 |
mingham | +2.723 |
Neg logit contributions | |
unts | -2.894 |
olas | -2.881 |
llo | -2.769 |
ngth | -2.664 |
inant | -2.619 |
Token | in |
Token ID | 287 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
su | +0.432 |
ements | +0.381 |
iences | +0.357 |
mingham | +0.352 |
ement | +0.351 |
Neg logit contributions | |
olas | -0.485 |
unts | -0.481 |
llo | -0.468 |
uria | -0.441 |
inant | -0.438 |
Token | key |
Token ID | 1994 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
su | +0.208 |
ements | +0.182 |
iences | +0.170 |
ement | +0.169 |
mingham | +0.168 |
Neg logit contributions | |
olas | -0.250 |
unts | -0.249 |
llo | -0.241 |
uria | -0.227 |
inant | -0.226 |
Token | moments |
Token ID | 7188 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
olas | +1.260 |
unts | +1.257 |
llo | +1.224 |
uria | +1.146 |
inant | +1.136 |
Neg logit contributions | |
su | -1.079 |
ements | -0.942 |
iences | -0.884 |
ement | -0.876 |
mingham | -0.874 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
su | +4.111 |
ements | +3.256 |
Priv | +3.050 |
ement | +3.046 |
Stronghold | +2.798 |
Neg logit contributions | |
ngth | -6.824 |
olas | -6.698 |
unts | -6.534 |
inant | -6.257 |
uria | -6.186 |
Token | Contract |
Token ID | 45845 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
su | +5.704 |
Priv | +4.810 |
ements | +4.757 |
ement | +4.394 |
iences | +4.314 |
Neg logit contributions | |
olas | -6.494 |
unts | -6.437 |
llo | -6.190 |
ngth | -6.161 |
uria | -6.095 |
Token | : |
Token ID | 25 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
su | +3.494 |
ements | +3.039 |
iences | +2.841 |
ement | +2.833 |
Stronghold | +2.783 |
Neg logit contributions | |
unts | -3.980 |
olas | -3.970 |
llo | -3.830 |
uria | -3.616 |
ngth | -3.589 |
Token | A |
Token ID | 317 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
su | +1.983 |
ements | +1.754 |
iences | +1.641 |
ement | +1.634 |
Priv | +1.615 |
Neg logit contributions | |
olas | -2.049 |
unts | -2.034 |
llo | -1.967 |
uria | -1.864 |
inant | -1.849 |
Token | three |
Token ID | 1115 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
su | +2.219 |
ements | +1.942 |
iences | +1.838 |
ement | +1.832 |
Priv | +1.806 |
Neg logit contributions | |
olas | -2.280 |
unts | -2.237 |
llo | -2.181 |
uria | -2.069 |
inant | -2.034 |
Token | - |
Token ID | 12 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
su | +5.930 |
ements | +5.182 |
ement | +4.932 |
iences | +4.736 |
Priv | +4.711 |
Neg logit contributions | |
olas | -7.127 |
unts | -6.890 |
llo | -6.680 |
uria | -6.528 |
ngth | -6.505 |
Token | year |
Token ID | 1941 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
su | +7.927 |
ements | +6.063 |
Priv | +5.719 |
ement | +5.691 |
ooo | +5.386 |
Neg logit contributions | |
olas | -12.573 |
unts | -12.082 |
llo | -11.978 |
ngth | -11.932 |
uria | -11.711 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
su | +3.401 |
ements | +2.987 |
ement | +2.795 |
iences | +2.778 |
Priv | +2.743 |
Neg logit contributions | |
olas | -3.784 |
unts | -3.749 |
llo | -3.619 |
uria | -3.460 |
ngth | -3.429 |
Token | $ |
Token ID | 720 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
su | +3.674 |
ements | +3.296 |
iences | +3.081 |
ement | +3.073 |
Priv | +3.039 |
Neg logit contributions | |
olas | -3.257 |
unts | -3.206 |
llo | -3.086 |
uria | -2.927 |
ngth | -2.914 |
Token | 15 |
Token ID | 1314 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
su | +3.389 |
ements | +2.804 |
Priv | +2.707 |
ement | +2.604 |
iences | +2.545 |
Neg logit contributions | |
olas | -4.332 |
unts | -4.275 |
ngth | -4.127 |
llo | -4.054 |
uria | -4.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
su | +4.731 |
ements | +4.043 |
ement | +3.760 |
iences | +3.701 |
Priv | +3.694 |
Neg logit contributions | |
olas | -5.997 |
unts | -5.952 |
llo | -5.741 |
uria | -5.532 |
inant | -5.411 |
Token | for |
Token ID | 329 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
su | +0.714 |
ements | +0.628 |
iences | +0.590 |
ement | +0.582 |
mingham | +0.581 |
Neg logit contributions | |
olas | -0.791 |
unts | -0.784 |
llo | -0.762 |
uria | -0.718 |
inant | -0.713 |
Token | Ad |
Token ID | 1215 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
su | +2.930 |
ements | +2.577 |
ement | +2.369 |
iences | +2.359 |
mingham | +2.321 |
Neg logit contributions | |
unts | -3.449 |
olas | -3.438 |
llo | -3.332 |
uria | -3.151 |
ngth | -3.128 |
Token | ew |
Token ID | 413 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
su | +1.055 |
ements | +0.941 |
iences | +0.885 |
ement | +0.877 |
mingham | +0.873 |
Neg logit contributions | |
olas | -0.992 |
unts | -0.982 |
llo | -0.950 |
uria | -0.894 |
inant | -0.885 |
Token | ale |
Token ID | 1000 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
su | +7.753 |
ement | +6.605 |
ements | +6.588 |
olitan | +6.198 |
Stevenson | +6.177 |
Neg logit contributions | |
ngth | -8.042 |
unts | -7.887 |
olas | -7.755 |
llo | -7.320 |
uria | -7.125 |
Token | Om |
Token ID | 16543 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
su | +2.724 |
ements | +2.373 |
ement | +2.218 |
Stevenson | +2.093 |
Stronghold | +2.088 |
Neg logit contributions | |
olas | -4.177 |
unts | -4.169 |
llo | -3.966 |
ngth | -3.852 |
uria | -3.843 |
Token | ot |
Token ID | 313 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
su | +4.598 |
ements | +3.842 |
ement | +3.792 |
atom | +3.697 |
ooo | +3.592 |
Neg logit contributions | |
ngth | -4.132 |
unts | -4.047 |
llo | -4.010 |
olas | -3.887 |
inant | -3.808 |
Token | osh |
Token ID | 3768 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
su | +11.355 |
ements | +9.965 |
ement | +9.724 |
ynam | +9.560 |
ooo | +9.467 |
Neg logit contributions | |
ngth | -8.064 |
unts | -7.740 |
ftime | -7.228 |
olas | -7.054 |
llo | -7.013 |
Token | o |
Token ID | 78 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
su | +5.001 |
ements | +4.306 |
ement | +4.154 |
Pradesh | +4.094 |
iences | +4.074 |
Neg logit contributions | |
olas | -4.942 |
llo | -4.804 |
unts | -4.798 |
ngth | -4.569 |
inant | -4.449 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
su | +3.386 |
ements | +2.926 |
ement | +2.745 |
iences | +2.716 |
mingham | +2.690 |
Neg logit contributions | |
olas | -3.932 |
unts | -3.925 |
llo | -3.759 |
uria | -3.552 |
ngth | -3.546 |
Token | Aaron |
Token ID | 12139 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
su | +1.191 |
ements | +1.047 |
iences | +0.981 |
ement | +0.971 |
mingham | +0.965 |
Neg logit contributions | |
olas | -1.329 |
unts | -1.320 |
llo | -1.279 |
uria | -1.207 |
inant | -1.199 |
Token | Hans |
Token ID | 13071 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
olas | +0.730 |
unts | +0.722 |
llo | +0.703 |
uria | +0.663 |
inant | +0.647 |
Neg logit contributions | |
su | -0.684 |
ements | -0.606 |
Priv | -0.575 |
iences | -0.573 |
��� | -0.565 |
Token | aggressive |
Token ID | 8361 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
olas | +0.778 |
unts | +0.766 |
llo | +0.749 |
uria | +0.708 |
inant | +0.701 |
Neg logit contributions | |
su | -0.613 |
ements | -0.537 |
iences | -0.502 |
mingham | -0.493 |
ement | -0.492 |
Token | , |
Token ID | 11 |
Feature activation | +4.85e-03 |
Pos logit contributions | |
su | +3.536 |
ements | +3.066 |
ement | +2.865 |
Stronghold | +2.798 |
Priv | +2.793 |
Neg logit contributions | |
olas | -4.089 |
unts | -4.042 |
llo | -3.872 |
ngth | -3.726 |
inant | -3.703 |
Token | arguably |
Token ID | 15242 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
olas | +0.061 |
unts | +0.061 |
llo | +0.059 |
uria | +0.056 |
inant | +0.055 |
Neg logit contributions | |
su | -0.051 |
ements | -0.045 |
iences | -0.042 |
mingham | -0.041 |
ement | -0.041 |
Token | un |
Token ID | 555 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
unts | +1.072 |
olas | +1.065 |
llo | +1.039 |
uria | +0.978 |
inant | +0.967 |
Neg logit contributions | |
su | -0.908 |
ements | -0.810 |
iences | -0.766 |
mingham | -0.747 |
ement | -0.743 |
Token | pat |
Token ID | 8071 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
su | +0.474 |
ements | +0.423 |
iences | +0.398 |
ement | +0.393 |
mingham | +0.392 |
Neg logit contributions | |
olas | -0.502 |
unts | -0.499 |
llo | -0.483 |
uria | -0.455 |
inant | -0.452 |
Token | ri |
Token ID | 380 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
su | +0.910 |
ements | +0.810 |
iences | +0.765 |
ement | +0.759 |
mingham | +0.752 |
Neg logit contributions | |
olas | -0.805 |
unts | -0.799 |
llo | -0.771 |
uria | -0.723 |
ngth | -0.715 |
Token | otic |
Token ID | 6210 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
su | +7.047 |
ements | +5.413 |
atom | +5.320 |
ement | +5.265 |
ynam | +5.136 |
Neg logit contributions | |
unts | -12.868 |
olas | -12.405 |
llo | -12.356 |
ngth | -11.893 |
uria | -11.694 |
Token | pattern |
Token ID | 3912 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
su | +0.572 |
ements | +0.504 |
iences | +0.475 |
ement | +0.467 |
mingham | +0.466 |
Neg logit contributions | |
olas | -0.628 |
unts | -0.624 |
llo | -0.605 |
uria | -0.571 |
inant | -0.566 |
Token | of |
Token ID | 286 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
su | +2.304 |
ements | +2.007 |
ement | +1.866 |
iences | +1.853 |
mingham | +1.833 |
Neg logit contributions | |
olas | -2.705 |
unts | -2.695 |
llo | -2.606 |
uria | -2.465 |
inant | -2.448 |
Token | tax |
Token ID | 1687 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
su | +1.687 |
ements | +1.486 |
iences | +1.385 |
ement | +1.379 |
Priv | +1.363 |
Neg logit contributions | |
olas | -1.841 |
unts | -1.822 |
llo | -1.770 |
uria | -1.671 |
inant | -1.663 |
Token | - |
Token ID | 12 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
olas | +0.317 |
unts | +0.316 |
llo | +0.306 |
uria | +0.291 |
inant | +0.287 |
Neg logit contributions | |
su | -0.277 |
ements | -0.243 |
iences | -0.230 |
mingham | -0.226 |
ement | -0.225 |
Token | fel |
Token ID | 10756 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
unts | +3.370 |
olas | +3.321 |
llo | +3.237 |
inant | +3.012 |
uria | +2.969 |
Neg logit contributions | |
su | -3.008 |
ements | -2.668 |
iences | -2.571 |
mingham | -2.519 |
ynam | -2.485 |
Token | |
Token ID | 3907 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
su | +1.530 |
ements | +1.363 |
iences | +1.288 |
ement | +1.278 |
mingham | +1.270 |
Neg logit contributions | |
olas | -1.334 |
unts | -1.325 |
llo | -1.278 |
uria | -1.195 |
inant | -1.185 |
Token | low |
Token ID | 9319 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
unts | +5.161 |
olas | +5.053 |
llo | +4.702 |
inant | +4.625 |
uria | +4.545 |
Neg logit contributions | |
��� | -5.579 |
su | -5.573 |
Stronghold | -5.176 |
Pradesh | -5.094 |
ements | -5.024 |
Token | Demo |
Token ID | 34588 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
unts | +1.089 |
olas | +1.087 |
llo | +1.049 |
inant | +0.976 |
uria | +0.972 |
Neg logit contributions | |
su | -1.084 |
ements | -0.961 |
iences | -0.913 |
mingham | -0.909 |
Priv | -0.895 |
Token | |
Token ID | 3907 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
su | +3.035 |
ements | +2.621 |
ement | +2.472 |
iences | +2.469 |
Priv | +2.468 |
Neg logit contributions | |
unts | -2.958 |
olas | -2.921 |
llo | -2.765 |
ngth | -2.673 |
uria | -2.664 |
Token | cr |
Token ID | 6098 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
su | +4.470 |
ements | +3.241 |
iences | +3.062 |
ement | +2.928 |
Priv | +2.866 |
Neg logit contributions | |
olas | -9.213 |
unts | -9.133 |
ngth | -8.993 |
uria | -8.881 |
ftime | -8.800 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
su | +9.837 |
atom | +7.912 |
ements | +7.776 |
mingham | +7.698 |
ement | +7.593 |
Neg logit contributions | |
ngth | -9.681 |
olas | -9.655 |
unts | -9.489 |
llo | -9.232 |
inant | -8.809 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
su | +2.155 |
ements | +1.891 |
iences | +1.769 |
ement | +1.767 |
mingham | +1.739 |
Neg logit contributions | |
olas | -2.343 |
unts | -2.329 |
llo | -2.254 |
uria | -2.129 |
inant | -2.113 |
Token | At |
Token ID | 1629 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
olas | +0.112 |
unts | +0.111 |
llo | +0.108 |
uria | +0.101 |
inant | +0.101 |
Neg logit contributions | |
su | -0.101 |
ements | -0.090 |
iences | -0.084 |
mingham | -0.083 |
ement | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
olas | +1.731 |
unts | +1.704 |
llo | +1.666 |
uria | +1.548 |
inant | +1.548 |
Neg logit contributions | |
su | -1.539 |
ements | -1.379 |
iences | -1.300 |
mingham | -1.291 |
ynam | -1.266 |
Token | party |
Token ID | 2151 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
llo | +5.183 |
olas | +5.175 |
unts | +5.118 |
inant | +4.625 |
uria | +4.527 |
Neg logit contributions | |
su | -5.152 |
ements | -4.686 |
iences | -4.532 |
mingham | -4.419 |
ement | -4.385 |
Token | about |
Token ID | 546 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
olas | +0.384 |
unts | +0.381 |
llo | +0.372 |
uria | +0.346 |
inant | +0.342 |
Neg logit contributions | |
su | -0.371 |
ements | -0.328 |
iences | -0.310 |
mingham | -0.307 |
ement | -0.303 |
Token | faithful |
Token ID | 17074 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
unts | +1.763 |
olas | +1.755 |
llo | +1.694 |
uria | +1.584 |
inant | +1.550 |
Neg logit contributions | |
su | -1.544 |
ements | -1.359 |
iences | -1.284 |
mingham | -1.259 |
ement | -1.255 |
Token | slaves |
Token ID | 13384 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
su | +0.034 |
ements | +0.030 |
iences | +0.028 |
ement | +0.027 |
mingham | +0.027 |
Neg logit contributions | |
unts | -0.043 |
olas | -0.043 |
llo | -0.042 |
uria | -0.040 |
inant | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
unts | +1.512 |
olas | +1.503 |
llo | +1.456 |
uria | +1.368 |
inant | +1.350 |
Neg logit contributions | |
su | -1.425 |
ements | -1.270 |
iences | -1.202 |
mingham | -1.179 |
Priv | -1.166 |
Token | d |
Token ID | 288 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
unts | +3.925 |
olas | +3.867 |
llo | +3.709 |
uria | +3.447 |
inant | +3.366 |
Neg logit contributions | |
su | -3.394 |
ements | -2.970 |
iences | -2.815 |
Pradesh | -2.795 |
��� | -2.792 |
Token | oting |
Token ID | 10720 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
unts | +2.888 |
olas | +2.880 |
llo | +2.743 |
inant | +2.566 |
uria | +2.562 |
Neg logit contributions | |
su | -2.936 |
��� | -2.603 |
ements | -2.569 |
Pradesh | -2.503 |
Priv | -2.502 |
Token | masters |
Token ID | 18159 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
unts | +5.305 |
olas | +4.972 |
llo | +4.908 |
uria | +4.363 |
inant | +4.311 |
Neg logit contributions | |
su | -4.961 |
ements | -4.313 |
��� | -4.256 |
mingham | -4.192 |
Pradesh | -4.152 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
unts | +1.555 |
olas | +1.552 |
llo | +1.495 |
uria | +1.404 |
inant | +1.388 |
Neg logit contributions | |
su | -1.583 |
ements | -1.408 |
iences | -1.336 |
mingham | -1.316 |
Priv | -1.301 |
Token | New |
Token ID | 968 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
olas | +2.197 |
unts | +2.181 |
llo | +2.147 |
uria | +1.978 |
inant | +1.946 |
Neg logit contributions | |
su | -2.030 |
ements | -1.807 |
iences | -1.715 |
mingham | -1.673 |
��� | -1.670 |
Token | research |
Token ID | 2267 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
su | +3.558 |
ements | +3.077 |
iences | +2.840 |
ement | +2.796 |
Priv | +2.759 |
Neg logit contributions | |
unts | -4.939 |
olas | -4.919 |
llo | -4.728 |
inant | -4.556 |
uria | -4.540 |
Token | has |
Token ID | 468 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
olas | +1.514 |
unts | +1.501 |
llo | +1.466 |
uria | +1.371 |
inant | +1.363 |
Neg logit contributions | |
su | -1.456 |
ements | -1.277 |
iences | -1.215 |
mingham | -1.196 |
ement | -1.193 |
Token | with |
Token ID | 351 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
unts | +3.500 |
olas | +3.423 |
llo | +3.399 |
inant | +3.094 |
uria | +3.062 |
Neg logit contributions | |
su | -4.164 |
ements | -3.695 |
��� | -3.540 |
iences | -3.521 |
mingham | -3.485 |
Token | family |
Token ID | 1641 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
unts | +3.120 |
olas | +3.074 |
llo | +2.957 |
inant | +2.748 |
uria | +2.677 |
Neg logit contributions | |
su | -3.130 |
ements | -2.759 |
mingham | -2.652 |
iences | -2.619 |
��� | -2.594 |
Token | ," |
Token ID | 553 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
unts | +3.230 |
olas | +3.204 |
llo | +3.091 |
uria | +2.872 |
inant | +2.846 |
Neg logit contributions | |
su | -3.644 |
ements | -3.235 |
��� | -3.121 |
iences | -3.057 |
Priv | -3.029 |
Token | Walker |
Token ID | 10120 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
olas | +2.587 |
llo | +2.472 |
unts | +2.447 |
uria | +2.212 |
inant | +2.162 |
Neg logit contributions | |
su | -3.636 |
ements | -3.328 |
Priv | -3.151 |
iences | -3.142 |
ement | -3.102 |
Token | told |
Token ID | 1297 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
olas | +0.535 |
unts | +0.530 |
llo | +0.521 |
uria | +0.487 |
inant | +0.480 |
Neg logit contributions | |
su | -0.465 |
ements | -0.412 |
iences | -0.387 |
Priv | -0.381 |
mingham | -0.378 |
Token | Triple |
Token ID | 19817 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
unts | +2.795 |
olas | +2.789 |
llo | +2.740 |
uria | +2.537 |
inant | +2.524 |
Neg logit contributions | |
su | -2.432 |
ements | -2.158 |
iences | -2.037 |
Priv | -1.988 |
Pradesh | -1.985 |
Token | M |
Token ID | 337 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
llo | +5.390 |
unts | +5.388 |
olas | +5.287 |
inant | +4.860 |
uria | +4.791 |
Neg logit contributions | |
su | -4.893 |
ements | -4.362 |
iences | -4.249 |
Priv | -4.083 |
��� | -4.083 |
Token | . |
Token ID | 13 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
olas | +0.488 |
unts | +0.486 |
llo | +0.472 |
uria | +0.442 |
inant | +0.439 |
Neg logit contributions | |
su | -0.487 |
ements | -0.434 |
iences | -0.408 |
ement | -0.401 |
mingham | -0.399 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
olas | +0.924 |
unts | +0.907 |
llo | +0.899 |
uria | +0.824 |
inant | +0.812 |
Neg logit contributions | |
su | -0.995 |
ements | -0.898 |
iences | -0.850 |
Stronghold | -0.835 |
Pradesh | -0.834 |
Token |
|
Token ID | 198 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
olas | +2.045 |
unts | +2.034 |
llo | +1.986 |
uria | +1.844 |
inant | +1.821 |
Neg logit contributions | |
su | -2.117 |
ements | -1.897 |
iences | -1.803 |
��� | -1.798 |
mingham | -1.765 |
Token | " |
Token ID | 1 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
olas | +1.065 |
unts | +1.048 |
llo | +1.034 |
uria | +0.950 |
inant | +0.948 |
Neg logit contributions | |
su | -1.112 |
ements | -1.002 |
iences | -0.949 |
��� | -0.935 |
mingham | -0.934 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
unts | +3.752 |
olas | +3.745 |
llo | +3.663 |
inant | +3.373 |
uria | +3.339 |
Neg logit contributions | |
su | -3.974 |
ements | -3.568 |
iences | -3.372 |
��� | -3.349 |
Priv | -3.339 |
Token | and |
Token ID | 290 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
olas | +3.865 |
unts | +3.844 |
llo | +3.731 |
uria | +3.469 |
inant | +3.432 |
Neg logit contributions | |
su | -3.758 |
ements | -3.346 |
��� | -3.206 |
iences | -3.189 |
Priv | -3.140 |
Token | we |
Token ID | 356 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
su | +0.876 |
ements | +0.766 |
iences | +0.715 |
ement | +0.708 |
mingham | +0.702 |
Neg logit contributions | |
olas | -1.040 |
unts | -1.034 |
llo | -1.002 |
uria | -0.949 |
inant | -0.942 |
Token | are |
Token ID | 389 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
su | +1.773 |
ements | +1.547 |
iences | +1.445 |
ement | +1.438 |
mingham | +1.419 |
Neg logit contributions | |
olas | -2.036 |
unts | -2.018 |
llo | -1.952 |
uria | -1.858 |
ngth | -1.843 |
Token | only |
Token ID | 691 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
olas | +0.602 |
unts | +0.599 |
llo | +0.581 |
uria | +0.545 |
inant | +0.542 |
Neg logit contributions | |
su | -0.522 |
ements | -0.460 |
iences | -0.435 |
ement | -0.425 |
mingham | -0.423 |
Token | six |
Token ID | 2237 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
su | +0.035 |
ements | +0.031 |
iences | +0.029 |
ement | +0.029 |
mingham | +0.029 |
Neg logit contributions | |
olas | -0.041 |
unts | -0.041 |
llo | -0.040 |
uria | -0.038 |
inant | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
unts | +4.638 |
olas | +4.586 |
llo | +4.455 |
uria | +4.021 |
inant | +3.841 |
Neg logit contributions | |
su | -6.973 |
��� | -6.176 |
ements | -6.147 |
iences | -5.996 |
Priv | -5.931 |
Token | seven |
Token ID | 3598 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
olas | +4.050 |
unts | +4.038 |
llo | +3.935 |
uria | +3.621 |
inant | +3.610 |
Neg logit contributions | |
su | -3.960 |
ements | -3.508 |
iences | -3.348 |
��� | -3.332 |
Priv | -3.304 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
unts | +5.563 |
olas | +5.404 |
llo | +5.283 |
uria | +4.803 |
inant | +4.632 |
Neg logit contributions | |
su | -7.364 |
��� | -6.650 |
ements | -6.399 |
iences | -6.306 |
Priv | -6.255 |
Token | eight |
Token ID | 3624 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
olas | +4.528 |
unts | +4.477 |
llo | +4.352 |
uria | +3.979 |
inant | +3.963 |
Neg logit contributions | |
su | -4.162 |
ements | -3.641 |
iences | -3.510 |
��� | -3.452 |
Priv | -3.424 |
Token | points |
Token ID | 2173 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
unts | +4.446 |
olas | +4.333 |
llo | +4.207 |
uria | +3.832 |
inant | +3.709 |
Neg logit contributions | |
su | -6.478 |
��� | -5.748 |
ements | -5.693 |
iences | -5.543 |
Priv | -5.533 |
Token | alternative |
Token ID | 5559 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
unts | +2.522 |
olas | +2.510 |
llo | +2.453 |
inant | +2.284 |
uria | +2.273 |
Neg logit contributions | |
su | -2.277 |
ements | -1.999 |
iences | -1.893 |
mingham | -1.871 |
ement | -1.848 |
Token | was |
Token ID | 373 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
unts | +3.911 |
olas | +3.868 |
llo | +3.812 |
uria | +3.506 |
inant | +3.477 |
Neg logit contributions | |
su | -4.431 |
ements | -4.009 |
iences | -3.836 |
mingham | -3.772 |
Priv | -3.682 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
su | +0.084 |
ements | +0.074 |
iences | +0.069 |
ement | +0.069 |
mingham | +0.068 |
Neg logit contributions | |
olas | -0.094 |
unts | -0.094 |
llo | -0.091 |
uria | -0.085 |
inant | -0.085 |
Token | bill |
Token ID | 2855 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
su | +0.111 |
ements | +0.097 |
iences | +0.091 |
ement | +0.090 |
mingham | +0.090 |
Neg logit contributions | |
olas | -0.127 |
unts | -0.127 |
llo | -0.123 |
uria | -0.116 |
inant | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
olas | +0.829 |
unts | +0.823 |
llo | +0.803 |
uria | +0.754 |
inant | +0.749 |
Neg logit contributions | |
su | -0.723 |
ements | -0.636 |
iences | -0.597 |
mingham | -0.590 |
ement | -0.585 |
Token | would |
Token ID | 561 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
olas | +3.025 |
unts | +3.025 |
llo | +2.950 |
uria | +2.714 |
inant | +2.689 |
Neg logit contributions | |
su | -3.120 |
ements | -2.744 |
iences | -2.632 |
mingham | -2.625 |
ynam | -2.567 |
Token | have |
Token ID | 423 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
unts | +4.764 |
olas | +4.718 |
llo | +4.647 |
inant | +4.262 |
uria | +4.055 |
Neg logit contributions | |
su | -5.303 |
ements | -4.793 |
iences | -4.652 |
mingham | -4.532 |
Pradesh | -4.529 |
Token | restored |
Token ID | 15032 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
olas | +1.588 |
unts | +1.584 |
llo | +1.545 |
uria | +1.435 |
inant | +1.428 |
Neg logit contributions | |
su | -1.402 |
ements | -1.236 |
iences | -1.179 |
mingham | -1.155 |
ement | -1.136 |
Token | the |
Token ID | 262 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
unts | +1.658 |
olas | +1.645 |
llo | +1.607 |
uria | +1.494 |
inant | +1.482 |
Neg logit contributions | |
su | -1.464 |
ements | -1.276 |
iences | -1.216 |
mingham | -1.201 |
ement | -1.181 |
Token | program |
Token ID | 1430 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
unts | +1.033 |
olas | +1.031 |
llo | +0.998 |
uria | +0.934 |
inant | +0.932 |
Neg logit contributions | |
su | -0.921 |
ements | -0.806 |
iences | -0.762 |
mingham | -0.748 |
ement | -0.745 |
Token | � |
Token ID | 447 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
olas | +1.640 |
unts | +1.629 |
llo | +1.587 |
uria | +1.484 |
inant | +1.475 |
Neg logit contributions | |
su | -1.565 |
ements | -1.404 |
iences | -1.317 |
mingham | -1.300 |
ement | -1.289 |
Token | - |
Token ID | 12 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
olas | +2.016 |
unts | +2.007 |
llo | +1.945 |
uria | +1.828 |
inant | +1.759 |
Neg logit contributions | |
su | -2.554 |
ements | -2.259 |
mingham | -2.183 |
iences | -2.177 |
Pradesh | -2.164 |
Token | wheel |
Token ID | 22001 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
su | +1.368 |
ements | +1.196 |
iences | +1.119 |
ement | +1.108 |
mingham | +1.100 |
Neg logit contributions | |
olas | -1.539 |
unts | -1.527 |
llo | -1.482 |
uria | -1.395 |
inant | -1.391 |
Token | drive |
Token ID | 3708 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
su | +3.222 |
ements | +2.749 |
iences | +2.583 |
ement | +2.548 |
ynam | +2.539 |
Neg logit contributions | |
olas | -4.113 |
unts | -4.111 |
llo | -3.996 |
ngth | -3.766 |
inant | -3.745 |
Token | with |
Token ID | 351 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
unts | +2.863 |
olas | +2.808 |
llo | +2.738 |
uria | +2.554 |
inant | +2.514 |
Neg logit contributions | |
su | -2.864 |
ements | -2.599 |
ement | -2.407 |
mingham | -2.403 |
Priv | -2.398 |
Token | durable |
Token ID | 20923 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
olas | +1.441 |
unts | +1.431 |
llo | +1.392 |
uria | +1.302 |
inant | +1.295 |
Neg logit contributions | |
su | -1.225 |
ements | -1.083 |
iences | -1.011 |
ement | -1.000 |
mingham | -0.994 |
Token | , |
Token ID | 11 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
olas | +4.049 |
unts | +3.974 |
llo | +3.921 |
uria | +3.651 |
inant | +3.574 |
Neg logit contributions | |
su | -3.734 |
ements | -3.335 |
iences | -3.164 |
mingham | -3.139 |
��� | -3.129 |
Token | mechanical |
Token ID | 12370 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
olas | +6.251 |
unts | +6.179 |
llo | +6.116 |
uria | +5.701 |
inant | +5.533 |
Neg logit contributions | |
su | -5.339 |
ements | -4.890 |
iences | -4.614 |
��� | -4.554 |
Pradesh | -4.494 |
Token | - |
Token ID | 12 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
olas | +4.673 |
unts | +4.634 |
llo | +4.539 |
uria | +4.280 |
inant | +4.117 |
Neg logit contributions | |
su | -4.191 |
ements | -3.774 |
iences | -3.598 |
��� | -3.596 |
mingham | -3.544 |
Token | locking |
Token ID | 48331 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
olas | +5.088 |
unts | +5.066 |
llo | +4.869 |
uria | +4.769 |
inant | +4.587 |
Neg logit contributions | |
su | -3.981 |
ements | -3.796 |
Pradesh | -3.723 |
��� | -3.682 |
iences | -3.617 |
Token | four |
Token ID | 1440 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
olas | +3.946 |
unts | +3.942 |
llo | +3.824 |
uria | +3.573 |
inant | +3.477 |
Neg logit contributions | |
su | -3.562 |
ements | -3.150 |
iences | -2.993 |
��� | -2.973 |
mingham | -2.960 |
Token | - |
Token ID | 12 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
su | +0.489 |
ements | +0.436 |
iences | +0.412 |
mingham | +0.407 |
ement | +0.406 |
Neg logit contributions | |
olas | -0.449 |
unts | -0.446 |
llo | -0.431 |
uria | -0.402 |
inant | -0.399 |
Token | name |
Token ID | 1438 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
olas | +1.387 |
unts | +1.381 |
llo | +1.335 |
uria | +1.253 |
inant | +1.248 |
Neg logit contributions | |
su | -1.219 |
ements | -1.080 |
iences | -1.011 |
ement | -0.999 |
mingham | -0.994 |
Token | associated |
Token ID | 3917 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
su | +1.340 |
ements | +1.174 |
iences | +1.096 |
ement | +1.086 |
mingham | +1.078 |
Neg logit contributions | |
olas | -1.548 |
unts | -1.540 |
llo | -1.489 |
uria | -1.410 |
inant | -1.399 |
Token | with |
Token ID | 351 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
su | +1.627 |
ements | +1.445 |
iences | +1.360 |
ement | +1.345 |
mingham | +1.338 |
Neg logit contributions | |
olas | -1.604 |
unts | -1.590 |
llo | -1.542 |
uria | -1.447 |
inant | -1.441 |
Token | a |
Token ID | 257 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
su | +0.775 |
ements | +0.678 |
iences | +0.632 |
ement | +0.625 |
mingham | +0.621 |
Neg logit contributions | |
olas | -0.945 |
unts | -0.939 |
llo | -0.911 |
uria | -0.861 |
inant | -0.856 |
Token | case |
Token ID | 1339 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
unts | +1.074 |
olas | +1.069 |
llo | +1.041 |
uria | +0.972 |
inant | +0.968 |
Neg logit contributions | |
su | -0.930 |
ements | -0.827 |
iences | -0.777 |
mingham | -0.759 |
ement | -0.758 |
Token | like |
Token ID | 588 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
su | +0.912 |
ements | +0.804 |
iences | +0.753 |
ement | +0.743 |
mingham | +0.739 |
Neg logit contributions | |
olas | -1.022 |
unts | -1.015 |
llo | -0.985 |
uria | -0.929 |
inant | -0.923 |
Token | this |
Token ID | 428 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
olas | +2.826 |
unts | +2.802 |
llo | +2.728 |
uria | +2.525 |
inant | +2.514 |
Neg logit contributions | |
su | -2.831 |
ements | -2.551 |
iences | -2.399 |
ement | -2.341 |
Priv | -2.339 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
su | +1.341 |
ements | +1.186 |
iences | +1.114 |
ement | +1.102 |
mingham | +1.095 |
Neg logit contributions | |
olas | -1.388 |
unts | -1.378 |
llo | -1.334 |
uria | -1.256 |
inant | -1.248 |
Token | and |
Token ID | 290 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
olas | +2.332 |
unts | +2.306 |
llo | +2.275 |
inant | +2.065 |
uria | +2.054 |
Neg logit contributions | |
su | -2.641 |
ements | -2.387 |
iences | -2.259 |
mingham | -2.220 |
ynam | -2.212 |
Token | they |
Token ID | 484 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
olas | +0.411 |
unts | +0.408 |
llo | +0.396 |
uria | +0.372 |
inant | +0.371 |
Neg logit contributions | |
su | -0.352 |
ements | -0.310 |
iences | -0.289 |
ement | -0.286 |
mingham | -0.285 |
Token | quickly |
Token ID | 2952 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
su | +1.118 |
ements | +0.983 |
iences | +0.923 |
ement | +0.916 |
mingham | +0.907 |
Neg logit contributions | |
olas | -1.178 |
unts | -1.170 |
llo | -1.131 |
uria | -1.070 |
inant | -1.059 |
Token | well |
Token ID | 4053 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
su | +1.694 |
ements | +1.485 |
iences | +1.394 |
ement | +1.383 |
Priv | +1.369 |
Neg logit contributions | |
olas | -1.767 |
unts | -1.756 |
llo | -1.699 |
uria | -1.603 |
inant | -1.589 |
Token | known |
Token ID | 1900 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
olas | +1.160 |
unts | +1.149 |
llo | +1.122 |
uria | +1.039 |
inant | +1.037 |
Neg logit contributions | |
su | -1.158 |
ements | -1.042 |
iences | -0.985 |
mingham | -0.969 |
ement | -0.963 |
Token | or |
Token ID | 393 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
olas | +0.455 |
unts | +0.450 |
llo | +0.439 |
uria | +0.412 |
inant | +0.411 |
Neg logit contributions | |
su | -0.409 |
ements | -0.364 |
iences | -0.340 |
mingham | -0.336 |
ement | -0.336 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
olas | +0.561 |
unts | +0.559 |
llo | +0.542 |
uria | +0.508 |
inant | +0.506 |
Neg logit contributions | |
su | -0.495 |
ements | -0.439 |
iences | -0.410 |
mingham | -0.407 |
ement | -0.406 |
Token | ), |
Token ID | 828 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
olas | +2.352 |
unts | +2.321 |
llo | +2.247 |
inant | +2.087 |
uria | +2.086 |
Neg logit contributions | |
su | -2.823 |
ements | -2.594 |
iences | -2.448 |
mingham | -2.448 |
��� | -2.418 |
Token | I |
Token ID | 314 |
Feature activation | -6.93e-03 |
Pos logit contributions | |
olas | +1.507 |
unts | +1.487 |
llo | +1.458 |
inant | +1.357 |
uria | +1.352 |
Neg logit contributions | |
su | -1.442 |
ements | -1.292 |
iences | -1.210 |
mingham | -1.204 |
ement | -1.197 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
su | +0.082 |
ements | +0.073 |
iences | +0.069 |
ement | +0.068 |
mingham | +0.068 |
Neg logit contributions | |
olas | -0.079 |
unts | -0.078 |
llo | -0.076 |
uria | -0.071 |
inant | -0.070 |
Token | 't |
Token ID | 470 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
su | +2.466 |
ements | +2.096 |
ement | +1.954 |
Priv | +1.945 |
iences | +1.902 |
Neg logit contributions | |
olas | -2.765 |
unts | -2.710 |
ngth | -2.634 |
llo | -2.566 |
inant | -2.511 |
Token | count |
Token ID | 954 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
olas | +0.617 |
unts | +0.617 |
llo | +0.602 |
inant | +0.567 |
uria | +0.564 |
Neg logit contributions | |
su | -0.420 |
ements | -0.368 |
iences | -0.340 |
ement | -0.333 |
mingham | -0.332 |
Token | it |
Token ID | 340 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
su | +1.877 |
ements | +1.635 |
iences | +1.521 |
ement | +1.511 |
mingham | +1.492 |
Neg logit contributions | |
olas | -2.286 |
unts | -2.271 |
llo | -2.201 |
uria | -2.089 |
inant | -2.071 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
su | +2.272 |
ements | +1.977 |
iences | +1.844 |
ement | +1.842 |
mingham | +1.817 |
Neg logit contributions | |
olas | -2.598 |
unts | -2.587 |
llo | -2.499 |
uria | -2.363 |
ngth | -2.349 |
Token | for |
Token ID | 329 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
unts | +3.373 |
olas | +3.348 |
llo | +3.258 |
uria | +3.153 |
inant | +3.012 |
Neg logit contributions | |
su | -3.825 |
ements | -3.507 |
��� | -3.315 |
mingham | -3.289 |
Priv | -3.272 |
Token | fuel |
Token ID | 5252 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
su | +1.396 |
ements | +1.181 |
iences | +1.081 |
ement | +1.067 |
mingham | +1.057 |
Neg logit contributions | |
olas | -2.365 |
unts | -2.353 |
llo | -2.292 |
uria | -2.184 |
inant | -2.172 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
unts | +1.962 |
olas | +1.951 |
llo | +1.889 |
uria | +1.825 |
inant | +1.758 |
Neg logit contributions | |
su | -2.158 |
ements | -1.940 |
��� | -1.831 |
iences | -1.816 |
Priv | -1.807 |
Token | Inter |
Token ID | 4225 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
su | +0.295 |
ements | +0.259 |
iences | +0.243 |
ement | +0.240 |
mingham | +0.239 |
Neg logit contributions | |
olas | -0.331 |
unts | -0.329 |
llo | -0.318 |
uria | -0.300 |
inant | -0.298 |
Token | mitt |
Token ID | 20124 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
su | +2.544 |
ements | +2.150 |
iences | +1.990 |
ement | +1.961 |
mingham | +1.910 |
Neg logit contributions | |
olas | -4.188 |
unts | -4.171 |
llo | -4.058 |
uria | -3.867 |
inant | -3.837 |
Token | ent |
Token ID | 298 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
su | +4.477 |
ements | +4.033 |
ement | +3.819 |
iences | +3.796 |
ynam | +3.660 |
Neg logit contributions | |
unts | -4.006 |
olas | -4.002 |
llo | -3.826 |
ngth | -3.684 |
uria | -3.613 |
Token | fasting |
Token ID | 24845 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
su | +0.128 |
ements | +0.114 |
iences | +0.108 |
ement | +0.107 |
Priv | +0.106 |
Neg logit contributions | |
olas | -0.112 |
unts | -0.111 |
llo | -0.108 |
uria | -0.101 |
inant | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
olas | +1.350 |
unts | +1.346 |
llo | +1.303 |
uria | +1.219 |
inant | +1.209 |
Neg logit contributions | |
su | -1.359 |
ements | -1.205 |
iences | -1.137 |
Priv | -1.123 |
mingham | -1.122 |
Token | spending |
Token ID | 4581 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
su | +2.418 |
ements | +2.102 |
ement | +1.951 |
iences | +1.951 |
mingham | +1.924 |
Neg logit contributions | |
olas | -2.911 |
unts | -2.894 |
llo | -2.808 |
uria | -2.648 |
inant | -2.635 |
Token | more |
Token ID | 517 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
unts | +1.848 |
olas | +1.843 |
llo | +1.787 |
uria | +1.672 |
inant | +1.653 |
Neg logit contributions | |
su | -1.741 |
ements | -1.524 |
iences | -1.441 |
Priv | -1.417 |
mingham | -1.412 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
unts | +1.695 |
olas | +1.679 |
llo | +1.649 |
uria | +1.524 |
ngth | +1.523 |
Neg logit contributions | |
su | -1.908 |
ements | -1.706 |
iences | -1.615 |
ynam | -1.594 |
Priv | -1.586 |
Token | dealing |
Token ID | 7219 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
su | +5.768 |
ements | +4.988 |
ement | +4.606 |
Pradesh | +4.570 |
iences | +4.470 |
Neg logit contributions | |
olas | -7.881 |
unts | -7.665 |
llo | -7.493 |
ngth | -7.305 |
inant | -7.195 |
Token | with |
Token ID | 351 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
su | +2.299 |
ements | +2.035 |
iences | +1.913 |
ement | +1.895 |
mingham | +1.883 |
Neg logit contributions | |
olas | -2.313 |
unts | -2.297 |
llo | -2.223 |
uria | -2.091 |
inant | -2.076 |
Token | transport |
Token ID | 4839 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
su | +1.228 |
ements | +1.070 |
iences | +0.995 |
ement | +0.985 |
mingham | +0.976 |
Neg logit contributions | |
olas | -1.559 |
unts | -1.549 |
llo | -1.504 |
uria | -1.424 |
inant | -1.416 |
Token | departments |
Token ID | 13346 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
su | +2.546 |
ements | +2.192 |
iences | +2.031 |
ement | +2.025 |
mingham | +1.980 |
Neg logit contributions | |
olas | -3.598 |
unts | -3.570 |
llo | -3.450 |
uria | -3.286 |
inant | -3.277 |
Token | , |
Token ID | 11 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
su | +1.069 |
ements | +0.943 |
iences | +0.885 |
ement | +0.873 |
mingham | +0.873 |
Neg logit contributions | |
olas | -1.130 |
unts | -1.125 |
llo | -1.089 |
uria | -1.027 |
inant | -1.020 |
Token | Ministry |
Token ID | 9475 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
olas | +0.966 |
unts | +0.960 |
llo | +0.930 |
uria | +0.882 |
inant | +0.873 |
Neg logit contributions | |
su | -0.849 |
ements | -0.745 |
iences | -0.701 |
mingham | -0.692 |
ement | -0.686 |
Token | of |
Token ID | 286 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
olas | +1.249 |
unts | +1.229 |
llo | +1.194 |
uria | +1.141 |
inant | +1.125 |
Neg logit contributions | |
su | -1.257 |
ements | -1.105 |
iences | -1.054 |
mingham | -1.041 |
Stronghold | -1.028 |
Token | Road |
Token ID | 5567 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
su | +2.644 |
ements | +2.340 |
iences | +2.187 |
ement | +2.172 |
mingham | +2.143 |
Neg logit contributions | |
olas | -3.008 |
unts | -2.974 |
llo | -2.887 |
uria | -2.727 |
ngth | -2.714 |
Token | Transport |
Token ID | 19940 |
Feature activation | +8.07e-03 |
Pos logit contributions | |
su | +1.804 |
ements | +1.510 |
iences | +1.370 |
ement | +1.350 |
mingham | +1.339 |
Neg logit contributions | |
olas | -3.356 |
unts | -3.339 |
llo | -3.257 |
uria | -3.110 |
inant | -3.092 |
Token | & |
Token ID | 1222 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
olas | +0.098 |
unts | +0.097 |
llo | +0.094 |
uria | +0.089 |
inant | +0.088 |
Neg logit contributions | |
su | -0.089 |
ements | -0.078 |
iences | -0.074 |
mingham | -0.073 |
ement | -0.072 |
Token | High |
Token ID | 3334 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
olas | +0.247 |
unts | +0.246 |
llo | +0.241 |
uria | +0.229 |
inant | +0.224 |
Neg logit contributions | |
su | -0.195 |
ements | -0.170 |
iences | -0.159 |
ement | -0.156 |
mingham | -0.156 |
Token | not |
Token ID | 407 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
su | +0.429 |
ements | +0.375 |
iences | +0.351 |
ement | +0.346 |
mingham | +0.344 |
Neg logit contributions | |
olas | -0.521 |
unts | -0.518 |
llo | -0.502 |
uria | -0.475 |
inant | -0.470 |
Token | doing |
Token ID | 1804 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
olas | +0.073 |
unts | +0.073 |
llo | +0.071 |
uria | +0.067 |
inant | +0.066 |
Neg logit contributions | |
su | -0.064 |
ements | -0.056 |
iences | -0.053 |
ement | -0.052 |
mingham | -0.052 |
Token | more |
Token ID | 517 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
olas | +2.751 |
unts | +2.723 |
llo | +2.645 |
uria | +2.428 |
inant | +2.397 |
Neg logit contributions | |
su | -3.046 |
ements | -2.733 |
iences | -2.598 |
Pradesh | -2.553 |
��� | -2.544 |
Token | to |
Token ID | 284 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
su | +2.473 |
ements | +2.147 |
ement | +1.988 |
iences | +1.984 |
Priv | +1.983 |
Neg logit contributions | |
olas | -3.032 |
unts | -2.997 |
llo | -2.872 |
uria | -2.762 |
inant | -2.759 |
Token | distance |
Token ID | 5253 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
su | +1.795 |
ements | +1.576 |
ement | +1.452 |
iences | +1.450 |
mingham | +1.428 |
Neg logit contributions | |
olas | -2.237 |
unts | -2.203 |
llo | -2.145 |
uria | -2.053 |
ngth | -2.040 |
Token | the |
Token ID | 262 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
unts | +1.879 |
olas | +1.861 |
llo | +1.810 |
uria | +1.678 |
inant | +1.635 |
Neg logit contributions | |
su | -1.760 |
ements | -1.544 |
iences | -1.472 |
��� | -1.441 |
Pradesh | -1.427 |
Token | UK |
Token ID | 3482 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
olas | +0.091 |
unts | +0.091 |
llo | +0.088 |
uria | +0.083 |
inant | +0.082 |
Neg logit contributions | |
su | -0.079 |
ements | -0.069 |
iences | -0.066 |
ement | -0.064 |
mingham | -0.064 |
Token | from |
Token ID | 422 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
unts | +2.178 |
olas | +2.172 |
llo | +2.097 |
uria | +1.982 |
inant | +1.929 |
Neg logit contributions | |
su | -2.625 |
ements | -2.370 |
iences | -2.271 |
��� | -2.261 |
mingham | -2.219 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
su | +0.911 |
ements | +0.799 |
iences | +0.749 |
ement | +0.736 |
mingham | +0.732 |
Neg logit contributions | |
olas | -1.102 |
unts | -1.096 |
llo | -1.061 |
uria | -1.004 |
inant | -0.993 |
Token | EU |
Token ID | 4576 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
su | +1.881 |
ements | +1.652 |
iences | +1.532 |
ement | +1.530 |
mingham | +1.512 |
Neg logit contributions | |
olas | -2.125 |
unts | -2.111 |
llo | -2.043 |
uria | -1.935 |
ngth | -1.929 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
olas | +0.130 |
unts | +0.129 |
llo | +0.125 |
uria | +0.118 |
inant | +0.117 |
Neg logit contributions | |
su | -0.124 |
ements | -0.110 |
iences | -0.104 |
ement | -0.102 |
mingham | -0.102 |
Token | whipping |
Token ID | 44637 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
olas | +0.004 |
unts | +0.004 |
llo | +0.004 |
uria | +0.004 |
inant | +0.004 |
Neg logit contributions | |
su | -0.003 |
ements | -0.003 |
iences | -0.003 |
mingham | -0.003 |
ement | -0.003 |
Token | boys |
Token ID | 6510 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
su | +2.661 |
ements | +2.339 |
iences | +2.175 |
ement | +2.173 |
mingham | +2.129 |
Neg logit contributions | |
olas | -2.987 |
unts | -2.981 |
llo | -2.893 |
uria | -2.752 |
ngth | -2.749 |
Token | . |
Token ID | 13 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
su | +2.699 |
ements | +2.372 |
iences | +2.228 |
ement | +2.213 |
mingham | +2.184 |
Neg logit contributions | |
olas | -2.936 |
unts | -2.905 |
llo | -2.833 |
uria | -2.668 |
ngth | -2.646 |
Token | Washington |
Token ID | 2669 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
olas | +4.602 |
unts | +4.587 |
llo | +4.479 |
inant | +4.126 |
uria | +4.119 |
Neg logit contributions | |
su | -4.182 |
ements | -3.759 |
��� | -3.622 |
iences | -3.566 |
ement | -3.485 |
Token | , |
Token ID | 11 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
su | +3.471 |
ements | +3.004 |
iences | +2.812 |
ement | +2.804 |
mingham | +2.777 |
Neg logit contributions | |
unts | -4.069 |
olas | -4.069 |
llo | -3.905 |
ngth | -3.728 |
inant | -3.726 |
Token | DC |
Token ID | 6257 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
olas | +1.317 |
unts | +1.314 |
llo | +1.297 |
uria | +1.221 |
inant | +1.206 |
Neg logit contributions | |
su | -0.643 |
ements | -0.539 |
iences | -0.491 |
ement | -0.476 |
mingham | -0.475 |
Token | : |
Token ID | 1058 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
su | +4.048 |
ements | +3.419 |
ement | +3.153 |
iences | +3.135 |
Priv | +3.092 |
Neg logit contributions | |
unts | -6.270 |
olas | -6.159 |
llo | -5.987 |
ngth | -5.750 |
uria | -5.735 |
Token | Hemisphere |
Token ID | 42811 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
su | +1.387 |
ements | +1.224 |
iences | +1.146 |
ement | +1.138 |
Priv | +1.128 |
Neg logit contributions | |
olas | -1.457 |
unts | -1.446 |
llo | -1.399 |
uria | -1.323 |
inant | -1.313 |
Token | Publishing |
Token ID | 23499 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
olas | +1.652 |
unts | +1.611 |
llo | +1.580 |
uria | +1.468 |
inant | +1.436 |
Neg logit contributions | |
su | -1.906 |
ements | -1.718 |
iences | -1.619 |
mingham | -1.597 |
ement | -1.591 |
Token | . |
Token ID | 764 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
su | +1.475 |
ements | +1.300 |
iences | +1.220 |
ement | +1.210 |
mingham | +1.196 |
Neg logit contributions | |
olas | -1.560 |
unts | -1.553 |
llo | -1.500 |
uria | -1.417 |
inant | -1.410 |
Token |
|
Token ID | 198 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
su | +0.541 |
ements | +0.481 |
iences | +0.453 |
ement | +0.448 |
mingham | +0.444 |
Neg logit contributions | |
olas | -0.547 |
unts | -0.542 |
llo | -0.526 |
uria | -0.494 |
inant | -0.490 |
Token | for |
Token ID | 329 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
olas | +1.063 |
unts | +1.049 |
llo | +1.011 |
uria | +0.950 |
inant | +0.941 |
Neg logit contributions | |
su | -1.012 |
ements | -0.897 |
iences | -0.845 |
Priv | -0.841 |
mingham | -0.840 |
Token | rare |
Token ID | 4071 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
olas | +0.058 |
unts | +0.057 |
llo | +0.055 |
uria | +0.052 |
inant | +0.052 |
Neg logit contributions | |
su | -0.048 |
ements | -0.042 |
iences | -0.040 |
mingham | -0.039 |
ement | -0.039 |
Token | fossil |
Token ID | 12584 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
su | +2.652 |
ements | +2.314 |
ement | +2.139 |
iences | +2.134 |
mingham | +2.079 |
Neg logit contributions | |
olas | -3.356 |
unts | -3.354 |
llo | -3.241 |
uria | -3.090 |
ngth | -3.085 |
Token | remains |
Token ID | 3793 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
olas | +2.053 |
unts | +2.009 |
llo | +1.950 |
uria | +1.834 |
inant | +1.813 |
Neg logit contributions | |
su | -1.871 |
ements | -1.656 |
iences | -1.568 |
mingham | -1.567 |
Priv | -1.567 |
Token | of |
Token ID | 286 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
olas | +0.667 |
unts | +0.659 |
llo | +0.640 |
uria | +0.603 |
inant | +0.598 |
Neg logit contributions | |
su | -0.617 |
ements | -0.545 |
iences | -0.514 |
mingham | -0.513 |
Priv | -0.507 |
Token | endemic |
Token ID | 42560 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
su | +0.456 |
ements | +0.399 |
iences | +0.371 |
ement | +0.366 |
mingham | +0.366 |
Neg logit contributions | |
olas | -0.574 |
unts | -0.569 |
llo | -0.552 |
uria | -0.521 |
inant | -0.519 |
Token | mammals |
Token ID | 23426 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
su | +2.961 |
ements | +2.530 |
ement | +2.332 |
iences | +2.328 |
Pradesh | +2.262 |
Neg logit contributions | |
olas | -4.094 |
unts | -4.081 |
llo | -3.968 |
uria | -3.819 |
ngth | -3.813 |
Token | to |
Token ID | 284 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
su | +3.834 |
ements | +3.264 |
ement | +3.051 |
iences | +3.043 |
Stronghold | +2.935 |
Neg logit contributions | |
olas | -4.824 |
unts | -4.800 |
llo | -4.672 |
ngth | -4.487 |
uria | -4.434 |
Token | investigate |
Token ID | 9161 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
su | +3.493 |
ements | +3.010 |
ement | +2.783 |
iences | +2.772 |
mingham | +2.730 |
Neg logit contributions | |
olas | -4.834 |
unts | -4.810 |
llo | -4.699 |
uria | -4.492 |
ngth | -4.491 |
Token | how |
Token ID | 703 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
olas | +0.963 |
unts | +0.955 |
llo | +0.921 |
uria | +0.875 |
inant | +0.866 |
Neg logit contributions | |
su | -0.831 |
ements | -0.733 |
iences | -0.687 |
mingham | -0.684 |
Priv | -0.674 |
Token | these |
Token ID | 777 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
su | +2.191 |
ements | +1.895 |
iences | +1.765 |
ement | +1.745 |
Priv | +1.711 |
Neg logit contributions | |
olas | -2.829 |
unts | -2.817 |
llo | -2.738 |
uria | -2.599 |
inant | -2.596 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
su | +2.900 |
ements | +2.508 |
iences | +2.340 |
ement | +2.305 |
ynam | +2.259 |
Neg logit contributions | |
olas | -3.905 |
unts | -3.880 |
llo | -3.753 |
uria | -3.600 |
inant | -3.568 |
Token | game |
Token ID | 983 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
su | +2.713 |
ements | +2.342 |
iences | +2.189 |
ement | +2.171 |
ynam | +2.123 |
Neg logit contributions | |
olas | -3.526 |
unts | -3.485 |
llo | -3.363 |
uria | -3.223 |
ngth | -3.205 |
Token | � |
Token ID | 447 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
su | +1.632 |
ements | +1.466 |
iences | +1.386 |
ement | +1.374 |
mingham | +1.369 |
Neg logit contributions | |
olas | -1.313 |
unts | -1.303 |
llo | -1.257 |
uria | -1.172 |
inant | -1.161 |
Token | � |
Token ID | 247 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
olas | +0.813 |
unts | +0.807 |
llo | +0.782 |
uria | +0.725 |
inant | +0.718 |
Neg logit contributions | |
su | -1.036 |
ements | -0.933 |
iences | -0.883 |
ement | -0.875 |
mingham | -0.871 |
Token | s |
Token ID | 82 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
su | +3.334 |
ements | +2.914 |
iences | +2.754 |
ement | +2.743 |
ynam | +2.686 |
Neg logit contributions | |
olas | -3.246 |
unts | -3.214 |
llo | -3.090 |
uria | -2.925 |
inant | -2.906 |
Token | new |
Token ID | 649 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
su | +5.404 |
ements | +4.611 |
ement | +4.387 |
iences | +4.364 |
ynam | +4.282 |
Neg logit contributions | |
olas | -6.632 |
unts | -6.582 |
llo | -6.258 |
ngth | -6.120 |
inant | -6.067 |
Token | online |
Token ID | 2691 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
su | +5.214 |
ements | +4.491 |
ement | +4.254 |
iences | +4.236 |
ynam | +4.169 |
Neg logit contributions | |
olas | -6.384 |
unts | -6.297 |
llo | -5.986 |
ngth | -5.830 |
uria | -5.768 |
Token | multiplayer |
Token ID | 16913 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
su | +2.586 |
ements | +2.191 |
iences | +2.025 |
ement | +2.025 |
Stronghold | +1.976 |
Neg logit contributions | |
olas | -4.064 |
unts | -4.000 |
llo | -3.869 |
ngth | -3.726 |
uria | -3.722 |
Token | mode |
Token ID | 4235 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
su | +0.077 |
ements | +0.069 |
iences | +0.064 |
ement | +0.064 |
mingham | +0.064 |
Neg logit contributions | |
olas | -0.077 |
unts | -0.076 |
llo | -0.074 |
uria | -0.069 |
inant | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
olas | +0.473 |
unts | +0.472 |
llo | +0.460 |
uria | +0.429 |
inant | +0.427 |
Neg logit contributions | |
su | -0.467 |
ements | -0.417 |
iences | -0.389 |
mingham | -0.387 |
ement | -0.386 |
Token | players |
Token ID | 1938 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
su | +1.426 |
ements | +1.242 |
iences | +1.159 |
ement | +1.147 |
mingham | +1.134 |
Neg logit contributions | |
olas | -1.758 |
unts | -1.744 |
llo | -1.694 |
uria | -1.604 |
inant | -1.595 |
Token | : |
Token ID | 25 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
olas | +0.703 |
unts | +0.699 |
llo | +0.673 |
uria | +0.636 |
inant | +0.634 |
Neg logit contributions | |
su | -0.677 |
ements | -0.596 |
iences | -0.558 |
ement | -0.556 |
mingham | -0.550 |
Token | Da |
Token ID | 9637 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
olas | +0.251 |
unts | +0.250 |
llo | +0.242 |
uria | +0.227 |
inant | +0.225 |
Neg logit contributions | |
su | -0.238 |
ements | -0.210 |
iences | -0.199 |
ement | -0.195 |
mingham | -0.195 |
Token | ar |
Token ID | 283 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
unts | +5.125 |
olas | +5.108 |
llo | +4.871 |
uria | +4.644 |
ngth | +4.528 |
Neg logit contributions | |
su | -4.973 |
ements | -4.489 |
��� | -4.334 |
Priv | -4.253 |
iences | -4.249 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
olas | +3.203 |
unts | +3.144 |
llo | +3.052 |
uria | +2.949 |
ngth | +2.835 |
Neg logit contributions | |
su | -2.952 |
ements | -2.661 |
iences | -2.521 |
Priv | -2.497 |
者 | -2.445 |
Token | avan |
Token ID | 12421 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
su | +0.198 |
ements | +0.176 |
iences | +0.166 |
ement | +0.164 |
mingham | +0.163 |
Neg logit contributions | |
olas | -0.196 |
unts | -0.194 |
llo | -0.188 |
uria | -0.177 |
inant | -0.174 |
Token | am |
Token ID | 321 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
su | +2.433 |
ements | +2.127 |
iences | +1.995 |
ement | +1.992 |
mingham | +1.966 |
Neg logit contributions | |
olas | -2.555 |
unts | -2.541 |
llo | -2.455 |
inant | -2.312 |
uria | -2.306 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
su | +2.651 |
ements | +2.303 |
iences | +2.163 |
ement | +2.158 |
mingham | +2.136 |
Neg logit contributions | |
olas | -2.852 |
unts | -2.831 |
llo | -2.742 |
inant | -2.581 |
uria | -2.574 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
su | +2.374 |
ements | +2.074 |
iences | +1.938 |
ement | +1.923 |
Pradesh | +1.908 |
Neg logit contributions | |
olas | -2.718 |
unts | -2.695 |
llo | -2.613 |
uria | -2.470 |
inant | -2.457 |
Token | 36 |
Token ID | 4570 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
su | +0.108 |
ements | +0.096 |
iences | +0.090 |
mingham | +0.088 |
ement | +0.088 |
Neg logit contributions | |
olas | -0.120 |
unts | -0.119 |
llo | -0.115 |
uria | -0.108 |
inant | -0.108 |
Token | 13 |
Token ID | 1485 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
su | +1.713 |
ements | +1.482 |
iences | +1.379 |
ement | +1.378 |
Priv | +1.373 |
Neg logit contributions | |
olas | -1.980 |
unts | -1.958 |
llo | -1.885 |
ngth | -1.808 |
uria | -1.800 |
Token | 45 |
Token ID | 2231 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
olas | +1.342 |
unts | +1.333 |
llo | +1.295 |
uria | +1.203 |
inant | +1.192 |
Neg logit contributions | |
su | -1.373 |
ements | -1.238 |
iences | -1.168 |
��� | -1.161 |
mingham | -1.149 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
olas | +2.028 |
unts | +2.021 |
llo | +1.976 |
uria | +1.859 |
inant | +1.822 |
Neg logit contributions | |
su | -2.118 |
ements | -1.885 |
��� | -1.800 |
iences | -1.794 |
mingham | -1.774 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
su | +1.955 |
ements | +1.725 |
iences | +1.618 |
ement | +1.602 |
mingham | +1.592 |
Neg logit contributions | |
olas | -2.074 |
unts | -2.060 |
llo | -1.995 |
uria | -1.880 |
inant | -1.866 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
su | +0.307 |
ements | +0.266 |
ement | +0.247 |
iences | +0.245 |
Priv | +0.244 |
Neg logit contributions | |
olas | -0.353 |
unts | -0.350 |
llo | -0.335 |
ngth | -0.327 |
uria | -0.321 |
Token | Judge |
Token ID | 29511 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
su | +3.039 |
ements | +2.596 |
Priv | +2.464 |
ement | +2.418 |
iences | +2.391 |
Neg logit contributions | |
olas | -3.515 |
unts | -3.492 |
llo | -3.324 |
ngth | -3.239 |
uria | -3.209 |
Token | Meyer |
Token ID | 23975 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
olas | +0.547 |
unts | +0.541 |
llo | +0.531 |
uria | +0.498 |
inant | +0.489 |
Neg logit contributions | |
su | -0.531 |
ements | -0.471 |
iences | -0.445 |
mingham | -0.440 |
Priv | -0.435 |
Token | told |
Token ID | 1297 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
olas | +0.694 |
unts | +0.688 |
llo | +0.673 |
uria | +0.633 |
inant | +0.628 |
Neg logit contributions | |
su | -0.571 |
ements | -0.499 |
iences | -0.468 |
mingham | -0.460 |
ement | -0.458 |
Token | the |
Token ID | 262 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
su | +3.165 |
ements | +2.751 |
iences | +2.563 |
ement | +2.545 |
mingham | +2.525 |
Neg logit contributions | |
olas | -3.579 |
unts | -3.563 |
llo | -3.405 |
inant | -3.271 |
uria | -3.261 |
Token | court |
Token ID | 2184 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
su | +1.498 |
ements | +1.267 |
iences | +1.161 |
ement | +1.153 |
mingham | +1.141 |
Neg logit contributions | |
olas | -2.352 |
unts | -2.328 |
llo | -2.255 |
uria | -2.169 |
ngth | -2.156 |
Token | he |
Token ID | 339 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
su | +1.342 |
ements | +1.180 |
iences | +1.104 |
ement | +1.094 |
mingham | +1.086 |
Neg logit contributions | |
olas | -1.481 |
unts | -1.473 |
llo | -1.424 |
uria | -1.346 |
inant | -1.337 |
Token | reviewed |
Token ID | 11765 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
olas | +1.890 |
unts | +1.883 |
llo | +1.833 |
uria | +1.711 |
inant | +1.675 |
Neg logit contributions | |
su | -1.862 |
ements | -1.640 |
iences | -1.565 |
mingham | -1.555 |
Priv | -1.543 |
Token | court |
Token ID | 2184 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
su | +2.944 |
ements | +2.544 |
ement | +2.347 |
iences | +2.345 |
Priv | +2.307 |
Neg logit contributions | |
olas | -3.672 |
unts | -3.645 |
llo | -3.513 |
inant | -3.373 |
ngth | -3.366 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
olas | +3.485 |
unts | +3.437 |
llo | +3.364 |
uria | +3.145 |
inant | +3.106 |
Neg logit contributions | |
su | -3.172 |
ements | -2.893 |
iences | -2.725 |
mingham | -2.698 |
Priv | -2.659 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
su | +0.145 |
ements | +0.130 |
iences | +0.123 |
mingham | +0.121 |
ement | +0.121 |
Neg logit contributions | |
olas | -0.140 |
unts | -0.139 |
llo | -0.135 |
uria | -0.126 |
inant | -0.125 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
su | +1.251 |
ements | +1.093 |
iences | +1.019 |
ement | +1.013 |
Priv | +1.001 |
Neg logit contributions | |
olas | -1.421 |
unts | -1.409 |
llo | -1.364 |
uria | -1.291 |
inant | -1.286 |
Token | 125 |
Token ID | 11623 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
su | +1.321 |
ements | +1.156 |
iences | +1.084 |
ement | +1.076 |
mingham | +1.064 |
Neg logit contributions | |
olas | -1.420 |
unts | -1.411 |
llo | -1.363 |
uria | -1.287 |
inant | -1.281 |
Token | K |
Token ID | 509 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
olas | +0.067 |
unts | +0.066 |
llo | +0.064 |
uria | +0.060 |
inant | +0.060 |
Neg logit contributions | |
su | -0.064 |
ements | -0.057 |
iences | -0.053 |
mingham | -0.053 |
ement | -0.053 |
Token | W |
Token ID | 370 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
su | +1.152 |
ements | +1.012 |
iences | +0.947 |
ement | +0.939 |
mingham | +0.931 |
Neg logit contributions | |
olas | -1.270 |
unts | -1.262 |
llo | -1.223 |
uria | -1.153 |
inant | -1.147 |
Token | – |
Token ID | 1906 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
su | +6.638 |
ements | +5.107 |
ement | +4.952 |
Pradesh | +4.805 |
ynam | +4.787 |
Neg logit contributions | |
olas | -10.274 |
unts | -10.245 |
llo | -9.942 |
inant | -9.702 |
ngth | -9.458 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
su | +4.185 |
ements | +3.489 |
ement | +3.272 |
iences | +3.198 |
ynam | +3.183 |
Neg logit contributions | |
olas | -5.227 |
unts | -5.200 |
llo | -5.015 |
inant | -4.819 |
ngth | -4.783 |
Token | m |
Token ID | 285 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
olas | +0.728 |
unts | +0.724 |
llo | +0.703 |
uria | +0.662 |
inant | +0.656 |
Neg logit contributions | |
su | -0.675 |
ements | -0.603 |
iences | -0.567 |
mingham | -0.559 |
ement | -0.555 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
su | +4.446 |
ements | +3.746 |
ement | +3.525 |
iences | +3.458 |
ynam | +3.436 |
Neg logit contributions | |
unts | -5.207 |
olas | -5.181 |
llo | -5.038 |
inant | -4.801 |
uria | -4.767 |
Token | ( |
Token ID | 357 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
su | +3.653 |
ements | +3.087 |
ement | +2.913 |
iences | +2.863 |
ynam | +2.862 |
Neg logit contributions | |
olas | -4.420 |
unts | -4.409 |
llo | -4.247 |
inant | -4.027 |
uria | -4.022 |
Token | as |
Token ID | 355 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
su | +0.286 |
ements | +0.253 |
iences | +0.238 |
ement | +0.234 |
mingham | +0.234 |
Neg logit contributions | |
olas | -0.308 |
unts | -0.307 |
llo | -0.297 |
uria | -0.280 |
inant | -0.279 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
olas | +1.773 |
unts | +1.752 |
llo | +1.694 |
uria | +1.604 |
ngth | +1.589 |
Neg logit contributions | |
su | -1.738 |
ements | -1.569 |
iences | -1.475 |
Priv | -1.445 |
ement | -1.438 |
Token | route |
Token ID | 6339 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
unts | +1.455 |
olas | +1.448 |
llo | +1.408 |
uria | +1.322 |
inant | +1.316 |
Neg logit contributions | |
su | -1.278 |
ements | -1.141 |
iences | -1.075 |
ement | -1.049 |
Priv | -1.049 |
Token | runner |
Token ID | 17490 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
su | +0.734 |
ements | +0.611 |
iences | +0.554 |
ement | +0.550 |
mingham | +0.544 |
Neg logit contributions | |
olas | -1.334 |
unts | -1.326 |
llo | -1.290 |
uria | -1.232 |
inant | -1.225 |
Token | , |
Token ID | 11 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
su | +0.796 |
ements | +0.707 |
iences | +0.665 |
ement | +0.655 |
mingham | +0.654 |
Neg logit contributions | |
olas | -0.806 |
unts | -0.805 |
llo | -0.779 |
uria | -0.734 |
inant | -0.729 |
Token | T |
Token ID | 309 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
olas | +0.866 |
unts | +0.857 |
llo | +0.824 |
uria | +0.754 |
ngth | +0.745 |
Neg logit contributions | |
su | -1.331 |
ements | -1.219 |
iences | -1.169 |
mingham | -1.151 |
ement | -1.147 |
Token | read |
Token ID | 961 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
su | +6.130 |
ements | +4.454 |
ynam | +4.332 |
ement | +4.246 |
mingham | +4.065 |
Neg logit contributions | |
olas | -10.379 |
unts | -10.372 |
ngth | -9.975 |
llo | -9.969 |
inant | -9.597 |
Token | well |
Token ID | 4053 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
su | +4.886 |
ements | +3.940 |
ement | +3.685 |
mingham | +3.530 |
ynam | +3.421 |
Neg logit contributions | |
olas | -7.381 |
unts | -7.297 |
inant | -6.922 |
ngth | -6.890 |
llo | -6.851 |
Token | doesn |
Token ID | 1595 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
su | +2.204 |
ements | +1.901 |
iences | +1.769 |
ement | +1.764 |
mingham | +1.731 |
Neg logit contributions | |
olas | -2.701 |
unts | -2.676 |
llo | -2.593 |
uria | -2.465 |
inant | -2.450 |
Token | � |
Token ID | 447 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
su | +1.850 |
ements | +1.591 |
ement | +1.484 |
iences | +1.472 |
Priv | +1.466 |
Neg logit contributions | |
olas | -2.103 |
unts | -2.061 |
llo | -1.980 |
ngth | -1.946 |
uria | -1.915 |
Token | � |
Token ID | 247 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
su | +2.158 |
ements | +1.910 |
iences | +1.807 |
ement | +1.800 |
mingham | +1.784 |
Neg logit contributions | |
olas | -1.800 |
unts | -1.785 |
llo | -1.684 |
ngth | -1.616 |
inant | -1.602 |
Token | to |
Token ID | 284 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
su | +3.512 |
ements | +3.068 |
ement | +2.857 |
iences | +2.834 |
Priv | +2.789 |
Neg logit contributions | |
olas | -4.208 |
unts | -4.206 |
llo | -4.048 |
uria | -3.851 |
inant | -3.821 |
Token | research |
Token ID | 2267 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
su | +1.247 |
ements | +1.089 |
iences | +1.017 |
ement | +1.004 |
mingham | +0.995 |
Neg logit contributions | |
olas | -1.526 |
unts | -1.515 |
llo | -1.469 |
uria | -1.395 |
inant | -1.383 |
Token | and |
Token ID | 290 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
su | +1.228 |
ements | +1.074 |
iences | +1.001 |
ement | +0.991 |
mingham | +0.982 |
Neg logit contributions | |
olas | -1.461 |
unts | -1.454 |
llo | -1.408 |
uria | -1.334 |
inant | -1.323 |
Token | promote |
Token ID | 7719 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
olas | +0.929 |
unts | +0.920 |
llo | +0.895 |
uria | +0.839 |
inant | +0.835 |
Neg logit contributions | |
su | -0.906 |
ements | -0.806 |
iences | -0.754 |
ement | -0.747 |
mingham | -0.744 |
Token | Anat |
Token ID | 28880 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
su | +0.395 |
ements | +0.349 |
iences | +0.328 |
ement | +0.324 |
mingham | +0.323 |
Neg logit contributions | |
olas | -0.436 |
unts | -0.432 |
llo | -0.420 |
uria | -0.394 |
inant | -0.394 |
Token | ab |
Token ID | 397 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
su | +3.711 |
ements | +3.295 |
ement | +3.112 |
iences | +3.098 |
mingham | +3.043 |
Neg logit contributions | |
unts | -3.206 |
olas | -3.152 |
llo | -3.062 |
inant | -2.890 |
uria | -2.829 |
Token | loc |
Token ID | 17946 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
su | +9.421 |
ements | +8.024 |
ynam | +7.960 |
atom | +7.919 |
ement | +7.875 |
Neg logit contributions | |
unts | -8.001 |
llo | -7.930 |
olas | -7.725 |
ngth | -7.369 |
ftime | -7.278 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
su | +3.998 |
ements | +3.439 |
ement | +3.252 |
iences | +3.206 |
mingham | +3.181 |
Neg logit contributions | |
unts | -4.296 |
olas | -4.277 |
llo | -4.100 |
ngth | -3.878 |
inant | -3.864 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
olas | +0.159 |
unts | +0.158 |
llo | +0.154 |
uria | +0.145 |
inant | +0.143 |
Neg logit contributions | |
su | -0.143 |
ements | -0.127 |
iences | -0.119 |
ement | -0.117 |
mingham | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
su | +1.958 |
ements | +1.644 |
Priv | +1.534 |
ement | +1.530 |
mingham | +1.472 |
Neg logit contributions | |
olas | -2.598 |
unts | -2.569 |
ngth | -2.506 |
llo | -2.432 |
inant | -2.386 |
Token | Nevertheless |
Token ID | 29011 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
su | +0.638 |
ements | +0.554 |
iences | +0.515 |
ement | +0.512 |
Priv | +0.510 |
Neg logit contributions | |
olas | -0.769 |
unts | -0.764 |
llo | -0.739 |
uria | -0.702 |
inant | -0.697 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
olas | +2.001 |
unts | +1.987 |
llo | +1.932 |
uria | +1.817 |
inant | +1.789 |
Neg logit contributions | |
su | -1.786 |
ements | -1.602 |
iences | -1.511 |
mingham | -1.492 |
Priv | -1.478 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
su | +0.534 |
ements | +0.475 |
iences | +0.447 |
ement | +0.441 |
mingham | +0.440 |
Neg logit contributions | |
olas | -0.536 |
unts | -0.532 |
llo | -0.515 |
uria | -0.484 |
inant | -0.481 |
Token | 708 |
Token ID | 32583 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
su | +2.793 |
ements | +2.404 |
ement | +2.244 |
Priv | +2.218 |
iences | +2.216 |
Neg logit contributions | |
olas | -3.243 |
unts | -3.199 |
llo | -3.086 |
ngth | -2.992 |
uria | -2.962 |
Token | W |
Token ID | 370 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
olas | +0.344 |
unts | +0.342 |
llo | +0.331 |
uria | +0.311 |
inant | +0.308 |
Neg logit contributions | |
su | -0.329 |
ements | -0.294 |
iences | -0.276 |
mingham | -0.273 |
ement | -0.273 |
Token | m |
Token ID | 285 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
su | +5.751 |
ements | +4.706 |
ement | +4.533 |
ynam | +4.479 |
Pradesh | +4.441 |
Neg logit contributions | |
olas | -6.416 |
unts | -6.353 |
llo | -6.303 |
inant | -5.967 |
uria | -5.894 |
Token | – |
Token ID | 1906 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
su | +3.859 |
ements | +3.271 |
ement | +3.076 |
iences | +3.004 |
ynam | +2.989 |
Neg logit contributions | |
unts | -4.603 |
olas | -4.598 |
llo | -4.472 |
inant | -4.269 |
uria | -4.243 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
su | +6.912 |
ements | +5.614 |
ement | +5.358 |
atom | +5.078 |
ynam | +5.055 |
Neg logit contributions | |
olas | -8.787 |
unts | -8.774 |
llo | -8.363 |
inant | -8.248 |
ngth | -8.174 |
Token | at |
Token ID | 379 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
su | +3.431 |
ements | +2.940 |
ement | +2.758 |
iences | +2.731 |
ynam | +2.720 |
Neg logit contributions | |
olas | -3.940 |
unts | -3.922 |
llo | -3.777 |
uria | -3.583 |
inant | -3.579 |
Token | CO |
Token ID | 7375 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
olas | +0.086 |
unts | +0.085 |
llo | +0.083 |
uria | +0.078 |
inant | +0.077 |
Neg logit contributions | |
su | -0.071 |
ements | -0.063 |
iences | -0.059 |
mingham | -0.058 |
Priv | -0.058 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
su | +2.722 |
ements | +2.351 |
iences | +2.178 |
ement | +2.172 |
mingham | +2.137 |
Neg logit contributions | |
olas | -3.416 |
unts | -3.386 |
llo | -3.275 |
inant | -3.114 |
uria | -3.099 |
Token | doubling |
Token ID | 26862 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
su | +1.460 |
ements | +1.279 |
iences | +1.194 |
ement | +1.188 |
mingham | +1.171 |
Neg logit contributions | |
olas | -1.618 |
unts | -1.606 |
llo | -1.554 |
uria | -1.467 |
inant | -1.461 |
Token | In |
Token ID | 554 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
olas | +1.554 |
unts | +1.543 |
llo | +1.505 |
uria | +1.404 |
inant | +1.397 |
Neg logit contributions | |
su | -1.327 |
ements | -1.174 |
iences | -1.111 |
mingham | -1.096 |
ynam | -1.082 |
Token | fact |
Token ID | 1109 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
olas | +2.397 |
unts | +2.366 |
llo | +2.274 |
uria | +2.129 |
inant | +2.085 |
Neg logit contributions | |
su | -2.641 |
ements | -2.365 |
iences | -2.267 |
mingham | -2.245 |
ement | -2.226 |
Token | , |
Token ID | 11 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
olas | +1.832 |
unts | +1.799 |
llo | +1.749 |
uria | +1.631 |
inant | +1.628 |
Neg logit contributions | |
su | -2.062 |
ements | -1.851 |
iences | -1.742 |
mingham | -1.718 |
ement | -1.709 |
Token | Washington |
Token ID | 2669 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
olas | +0.796 |
unts | +0.789 |
llo | +0.762 |
uria | +0.718 |
inant | +0.715 |
Neg logit contributions | |
su | -0.710 |
ements | -0.625 |
iences | -0.587 |
mingham | -0.581 |
ement | -0.578 |
Token | was |
Token ID | 373 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
su | +2.370 |
ements | +2.083 |
iences | +1.947 |
ement | +1.943 |
Priv | +1.914 |
Neg logit contributions | |
olas | -2.598 |
unts | -2.579 |
llo | -2.496 |
uria | -2.352 |
inant | -2.348 |
Token | cogn |
Token ID | 8866 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
olas | +0.662 |
unts | +0.660 |
llo | +0.639 |
uria | +0.604 |
inant | +0.597 |
Neg logit contributions | |
su | -0.572 |
ements | -0.502 |
iences | -0.475 |
mingham | -0.466 |
ement | -0.463 |
Token | iz |
Token ID | 528 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
su | +5.160 |
ements | +4.187 |
ement | +3.878 |
iences | +3.677 |
ynam | +3.551 |
Neg logit contributions | |
unts | -10.606 |
olas | -10.377 |
llo | -10.339 |
ngth | -10.070 |
uria | -10.025 |
Token | ant |
Token ID | 415 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
su | +2.643 |
ements | +2.360 |
ement | +2.261 |
iences | +2.247 |
mingham | +2.188 |
Neg logit contributions | |
olas | -1.901 |
unts | -1.887 |
llo | -1.804 |
ngth | -1.713 |
uria | -1.708 |
Token | of |
Token ID | 286 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
olas | +2.910 |
llo | +2.807 |
unts | +2.806 |
ngth | +2.564 |
inant | +2.564 |
Neg logit contributions | |
su | -3.180 |
ements | -2.818 |
mingham | -2.711 |
iences | -2.707 |
��� | -2.698 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
olas | +3.182 |
unts | +3.156 |
llo | +2.993 |
inant | +2.851 |
uria | +2.832 |
Neg logit contributions | |
su | -2.954 |
ements | -2.591 |
mingham | -2.487 |
iences | -2.466 |
��� | -2.455 |
Token | fact |
Token ID | 1109 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
unts | +3.144 |
olas | +3.130 |
llo | +2.981 |
inant | +2.830 |
uria | +2.809 |
Neg logit contributions | |
su | -2.947 |
ements | -2.589 |
mingham | -2.481 |
iences | -2.472 |
��� | -2.435 |