Token | difference |
Token ID | 3580 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ット | +0.187 |
fil | +0.184 |
ignore | +0.166 |
fixed | +0.164 |
BAT | +0.163 |
Neg logit contributions | |
uity | -0.180 |
swaps | -0.175 |
risis | -0.174 |
millenn | -0.172 |
anguage | -0.168 |
Token | between |
Token ID | 1022 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
fil | +2.639 |
ット | +2.635 |
ignore | +2.303 |
fixed | +2.247 |
BAT | +2.206 |
Neg logit contributions | |
uity | -4.402 |
millenn | -4.340 |
swaps | -4.337 |
risis | -4.318 |
oute | -4.200 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
fil | +2.640 |
ット | +2.634 |
ignore | +2.345 |
fixed | +2.319 |
BAT | +2.292 |
Neg logit contributions | |
uity | -3.037 |
risis | -2.945 |
swaps | -2.941 |
millenn | -2.922 |
anguage | -2.855 |
Token | raw |
Token ID | 8246 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
fil | +3.719 |
ット | +3.686 |
ignore | +3.298 |
fixed | +3.278 |
BAT | +3.221 |
Neg logit contributions | |
uity | -4.213 |
risis | -4.115 |
millenn | -4.075 |
swaps | -4.058 |
anguage | -3.994 |
Token | and |
Token ID | 290 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
fil | +3.022 |
ット | +2.991 |
ignore | +2.622 |
fixed | +2.587 |
BAT | +2.541 |
Neg logit contributions | |
uity | -4.310 |
risis | -4.230 |
millenn | -4.190 |
swaps | -4.187 |
anguage | -4.095 |
Token | JPEG |
Token ID | 48561 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ット | +2.649 |
fil | +2.643 |
ignore | +2.314 |
fixed | +2.296 |
BAT | +2.261 |
Neg logit contributions | |
uity | -3.684 |
swaps | -3.594 |
risis | -3.592 |
millenn | -3.558 |
anguage | -3.492 |
Token | files |
Token ID | 3696 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
fil | +8.731 |
ット | +7.945 |
fixed | +7.225 |
ignore | +7.216 |
above | +6.970 |
Neg logit contributions | |
uity | -11.855 |
risis | -11.506 |
millenn | -11.443 |
anguage | -11.132 |
aith | -11.030 |
Token | . |
Token ID | 13 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ット | +1.408 |
fil | +1.378 |
ignore | +1.223 |
fixed | +1.203 |
BAT | +1.194 |
Neg logit contributions | |
uity | -1.847 |
swaps | -1.809 |
risis | -1.798 |
millenn | -1.781 |
anguage | -1.744 |
Token | Cur |
Token ID | 4424 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ット | +1.574 |
fil | +1.550 |
ignore | +1.391 |
fixed | +1.370 |
BAT | +1.364 |
Neg logit contributions | |
uity | -1.723 |
swaps | -1.683 |
risis | -1.674 |
millenn | -1.666 |
anguage | -1.622 |
Token | iously |
Token ID | 6819 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ット | +2.253 |
fil | +2.229 |
ignore | +2.051 |
fixed | +2.029 |
BAT | +2.018 |
Neg logit contributions | |
uity | -1.418 |
swaps | -1.390 |
risis | -1.375 |
millenn | -1.373 |
anguage | -1.326 |
Token | , |
Token ID | 11 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ット | +1.420 |
fil | +1.387 |
ignore | +1.216 |
fixed | +1.194 |
BAT | +1.184 |
Neg logit contributions | |
uity | -2.172 |
swaps | -2.130 |
risis | -2.119 |
millenn | -2.100 |
anguage | -2.060 |
Token | from |
Token ID | 422 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ット | +0.880 |
fil | +0.859 |
ignore | +0.764 |
fixed | +0.752 |
BAT | +0.748 |
Neg logit contributions | |
uity | -1.132 |
swaps | -1.110 |
risis | -1.101 |
millenn | -1.088 |
anguage | -1.068 |
Token | build |
Token ID | 1382 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
uity | +0.050 |
swaps | +0.049 |
risis | +0.048 |
millenn | +0.048 |
oute | +0.047 |
Neg logit contributions | |
ット | -0.045 |
fil | -0.044 |
ignore | -0.040 |
fixed | -0.039 |
BAT | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
fil | +5.703 |
ット | +5.643 |
ignore | +5.052 |
fixed | +4.704 |
content | +4.621 |
Neg logit contributions | |
uity | -9.751 |
millenn | -9.499 |
swaps | -9.486 |
risis | -9.452 |
anguage | -9.294 |
Token | boot |
Token ID | 18769 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
fil | +8.836 |
ット | +8.741 |
ignore | +8.151 |
fixed | +7.995 |
BAT | +7.950 |
Neg logit contributions | |
uity | -5.306 |
millenn | -5.221 |
swaps | -5.204 |
risis | -5.071 |
anguage | -4.913 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
fil | +3.960 |
ット | +3.932 |
ignore | +3.491 |
fixed | +3.303 |
BAT | +3.255 |
Neg logit contributions | |
uity | -6.267 |
risis | -6.152 |
millenn | -6.139 |
swaps | -6.075 |
anguage | -5.995 |
Token | project |
Token ID | 1628 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ット | +1.584 |
fil | +1.556 |
ignore | +1.384 |
fixed | +1.355 |
BAT | +1.341 |
Neg logit contributions | |
uity | -2.059 |
risis | -2.009 |
swaps | -2.005 |
millenn | -1.991 |
anguage | -1.950 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
fil | +7.368 |
ット | +7.169 |
ignore | +6.458 |
fixed | +5.954 |
content | +5.852 |
Neg logit contributions | |
uity | -12.989 |
risis | -12.678 |
anguage | -12.572 |
millenn | -12.550 |
swaps | -12.514 |
Token | cl |
Token ID | 565 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
ット | +4.171 |
fil | +4.171 |
ignore | +3.737 |
fixed | +3.656 |
BAT | +3.554 |
Neg logit contributions | |
uity | -4.811 |
swaps | -4.732 |
millenn | -4.718 |
risis | -4.670 |
anguage | -4.531 |
Token | j |
Token ID | 73 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
uity | +0.222 |
swaps | +0.217 |
risis | +0.217 |
anguage | +0.212 |
millenn | +0.212 |
Neg logit contributions | |
ット | -0.108 |
fil | -0.104 |
ignore | -0.087 |
fixed | -0.086 |
BAT | -0.086 |
Token | files |
Token ID | 3696 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ット | +3.028 |
fil | +3.016 |
ignore | +2.658 |
fixed | +2.559 |
above | +2.506 |
Neg logit contributions | |
uity | -4.804 |
millenn | -4.698 |
risis | -4.694 |
swaps | -4.659 |
anguage | -4.574 |
Token | . |
Token ID | 13 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ット | +0.548 |
fil | +0.534 |
ignore | +0.474 |
fixed | +0.466 |
BAT | +0.465 |
Neg logit contributions | |
uity | -0.722 |
swaps | -0.708 |
risis | -0.702 |
millenn | -0.694 |
anguage | -0.682 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
uity | +0.220 |
swaps | +0.216 |
risis | +0.215 |
millenn | +0.210 |
anguage | +0.208 |
Neg logit contributions | |
ット | -0.174 |
fil | -0.170 |
ignore | -0.151 |
BAT | -0.149 |
fixed | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
uity | +1.799 |
risis | +1.759 |
swaps | +1.750 |
oute | +1.688 |
ּ | +1.673 |
Neg logit contributions | |
ット | -1.660 |
fil | -1.609 |
fixed | -1.450 |
ignore | -1.446 |
BAT | -1.421 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
uity | +0.524 |
swaps | +0.509 |
risis | +0.507 |
oute | +0.490 |
ּ | +0.486 |
Neg logit contributions | |
ット | -0.454 |
fil | -0.435 |
ignore | -0.390 |
fixed | -0.386 |
BAT | -0.383 |
Token | Just |
Token ID | 5703 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
uity | +0.982 |
risis | +0.954 |
swaps | +0.947 |
oute | +0.924 |
ּ | +0.916 |
Neg logit contributions | |
ット | -0.913 |
fil | -0.876 |
ignore | -0.787 |
fixed | -0.784 |
HMS | -0.783 |
Token | like |
Token ID | 588 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
uity | +0.205 |
swaps | +0.202 |
risis | +0.199 |
millenn | +0.196 |
anguage | +0.193 |
Neg logit contributions | |
ット | -0.170 |
fil | -0.165 |
fixed | -0.146 |
ignore | -0.146 |
BAT | -0.146 |
Token | 1915 |
Token ID | 32062 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ット | +0.783 |
fil | +0.764 |
ignore | +0.685 |
fixed | +0.676 |
BAT | +0.671 |
Neg logit contributions | |
uity | -0.895 |
swaps | -0.877 |
risis | -0.870 |
millenn | -0.860 |
anguage | -0.842 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
fil | +8.827 |
ット | +8.356 |
ignore | +7.463 |
above | +7.461 |
HMS | +7.391 |
Neg logit contributions | |
millenn | -11.127 |
uity | -11.001 |
aith | -10.675 |
anguage | -10.670 |
ancial | -10.590 |
Token | Just |
Token ID | 2329 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ット | +0.666 |
fil | +0.652 |
ignore | +0.583 |
fixed | +0.574 |
BAT | +0.569 |
Neg logit contributions | |
uity | -0.803 |
swaps | -0.785 |
risis | -0.781 |
millenn | -0.772 |
anguage | -0.756 |
Token | like |
Token ID | 588 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
uity | +1.337 |
swaps | +1.318 |
risis | +1.300 |
millenn | +1.281 |
oute | +1.261 |
Neg logit contributions | |
ット | -1.135 |
fil | -1.114 |
ignore | -0.983 |
BAT | -0.980 |
fixed | -0.978 |
Token | 1988 |
Token ID | 12122 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
uity | +0.231 |
swaps | +0.227 |
risis | +0.224 |
millenn | +0.222 |
anguage | +0.217 |
Neg logit contributions | |
ット | -0.207 |
fil | -0.202 |
ignore | -0.181 |
fixed | -0.179 |
BAT | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ット | +1.651 |
fil | +1.623 |
ignore | +1.426 |
fixed | +1.400 |
BAT | +1.389 |
Neg logit contributions | |
uity | -2.350 |
swaps | -2.304 |
risis | -2.285 |
millenn | -2.280 |
anguage | -2.233 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ット | +1.224 |
fil | +1.208 |
ignore | +1.069 |
fixed | +1.048 |
BAT | +1.041 |
Neg logit contributions | |
uity | -1.682 |
millenn | -1.666 |
swaps | -1.652 |
risis | -1.641 |
anguage | -1.603 |
Token | The |
Token ID | 464 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ット | +1.163 |
fil | +1.141 |
ignore | +0.994 |
fixed | +0.974 |
BAT | +0.963 |
Neg logit contributions | |
uity | -1.942 |
swaps | -1.907 |
risis | -1.897 |
millenn | -1.885 |
anguage | -1.846 |
Token | query |
Token ID | 12405 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ット | +1.287 |
fil | +1.263 |
ignore | +1.134 |
fixed | +1.116 |
BAT | +1.108 |
Neg logit contributions | |
uity | -1.432 |
swaps | -1.399 |
risis | -1.393 |
millenn | -1.379 |
anguage | -1.348 |
Token | below |
Token ID | 2174 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ット | +1.734 |
fil | +1.720 |
ignore | +1.527 |
fixed | +1.500 |
above | +1.489 |
Neg logit contributions | |
uity | -2.124 |
risis | -2.077 |
millenn | -2.061 |
swaps | -2.057 |
anguage | -2.003 |
Token | identifies |
Token ID | 21079 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
swaps | +1.488 |
uity | +1.486 |
risis | +1.426 |
oute | +1.384 |
millenn | +1.377 |
Neg logit contributions | |
ット | -2.037 |
fil | -1.968 |
ignore | -1.814 |
BAT | -1.798 |
fixed | -1.792 |
Token | project |
Token ID | 1628 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ット | +0.195 |
fil | +0.191 |
ignore | +0.172 |
fixed | +0.170 |
BAT | +0.169 |
Neg logit contributions | |
uity | -0.213 |
swaps | -0.209 |
risis | -0.207 |
millenn | -0.205 |
anguage | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
fil | +7.422 |
ット | +7.325 |
ignore | +6.586 |
fixed | +6.193 |
content | +6.149 |
Neg logit contributions | |
uity | -12.148 |
risis | -11.842 |
millenn | -11.819 |
anguage | -11.532 |
swaps | -11.474 |
Token | cl |
Token ID | 565 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
fil | +4.367 |
ット | +4.342 |
ignore | +3.888 |
fixed | +3.813 |
above | +3.698 |
Neg logit contributions | |
uity | -5.282 |
swaps | -5.180 |
millenn | -5.151 |
risis | -5.121 |
anguage | -4.965 |
Token | j |
Token ID | 73 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ット | +0.032 |
fil | +0.031 |
ignore | +0.026 |
fixed | +0.025 |
BAT | +0.025 |
Neg logit contributions | |
uity | -0.070 |
swaps | -0.068 |
risis | -0.068 |
millenn | -0.067 |
anguage | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ット | +3.252 |
fil | +3.213 |
ignore | +2.849 |
fixed | +2.753 |
above | +2.699 |
Neg logit contributions | |
uity | -4.782 |
risis | -4.665 |
millenn | -4.647 |
swaps | -4.601 |
anguage | -4.504 |
Token | build |
Token ID | 1382 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ット | +2.187 |
fil | +2.165 |
ignore | +1.931 |
fixed | +1.879 |
BAT | +1.857 |
Neg logit contributions | |
uity | -2.891 |
risis | -2.822 |
millenn | -2.803 |
swaps | -2.801 |
anguage | -2.740 |
Token | install |
Token ID | 2721 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ット | +3.880 |
fil | +3.823 |
ignore | +3.416 |
BAT | +3.334 |
fixed | +3.313 |
Neg logit contributions | |
uity | -4.919 |
millenn | -4.839 |
risis | -4.817 |
swaps | -4.786 |
anguage | -4.691 |
Token | -- |
Token ID | 1377 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
uity | +1.865 |
swaps | +1.841 |
risis | +1.809 |
millenn | +1.776 |
anguage | +1.764 |
Neg logit contributions | |
ット | -1.562 |
fil | -1.514 |
ignore | -1.345 |
fixed | -1.335 |
BAT | -1.312 |
Token | Open |
Token ID | 4946 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ット | +1.404 |
fil | +1.379 |
ignore | +1.242 |
fixed | +1.216 |
BAT | +1.211 |
Neg logit contributions | |
uity | -1.658 |
swaps | -1.620 |
risis | -1.613 |
millenn | -1.602 |
anguage | -1.560 |
Token | the |
Token ID | 262 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ット | +1.157 |
fil | +1.134 |
ignore | +1.018 |
fixed | +1.003 |
BAT | +0.996 |
Neg logit contributions | |
uity | -1.302 |
swaps | -1.273 |
risis | -1.265 |
millenn | -1.252 |
anguage | -1.224 |
Token | The |
Token ID | 383 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ット | +1.766 |
fil | +1.733 |
ignore | +1.550 |
fixed | +1.527 |
BAT | +1.517 |
Neg logit contributions | |
uity | -2.062 |
swaps | -2.019 |
risis | -2.007 |
millenn | -1.987 |
anguage | -1.942 |
Token | Stan |
Token ID | 32140 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ット | +2.822 |
fil | +2.786 |
ignore | +2.414 |
BAT | +2.369 |
fixed | +2.363 |
Neg logit contributions | |
uity | -4.491 |
swaps | -4.444 |
risis | -4.372 |
millenn | -4.362 |
anguage | -4.274 |
Token | ley |
Token ID | 1636 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
fil | +2.617 |
ット | +1.804 |
above | +1.566 |
ignore | +1.540 |
sel | +1.468 |
Neg logit contributions | |
millenn | -18.582 |
ccording | -17.304 |
swaps | -17.271 |
livest | -17.105 |
uity | -16.637 |
Token | Par |
Token ID | 10044 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ット | +2.953 |
fil | +2.887 |
ignore | +2.495 |
fixed | +2.457 |
BAT | +2.445 |
Neg logit contributions | |
uity | -4.855 |
swaps | -4.772 |
risis | -4.728 |
millenn | -4.706 |
anguage | -4.609 |
Token | ad |
Token ID | 324 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
fil | +5.601 |
ット | +4.834 |
ignore | +4.653 |
above | +4.635 |
content | +4.617 |
Neg logit contributions | |
millenn | -9.903 |
livest | -9.198 |
swaps | -9.121 |
ּ | -9.090 |
ccording | -8.989 |
Token | ox |
Token ID | 1140 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ット | +2.028 |
fil | +2.024 |
ignore | +1.793 |
fixed | +1.752 |
above | +1.737 |
Neg logit contributions | |
millenn | -3.074 |
swaps | -2.968 |
uity | -2.943 |
risis | -2.894 |
livest | -2.879 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ット | +5.180 |
fil | +5.065 |
ignore | +4.557 |
fixed | +4.404 |
BAT | +4.339 |
Neg logit contributions | |
uity | -7.218 |
millenn | -7.186 |
swaps | -7.137 |
risis | -7.131 |
ancial | -6.936 |
Token | 's |
Token ID | 338 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
uity | +2.627 |
swaps | +2.589 |
risis | +2.550 |
millenn | +2.459 |
anguage | +2.440 |
Neg logit contributions | |
ット | -3.270 |
fil | -3.204 |
ignore | -2.924 |
BAT | -2.882 |
fixed | -2.880 |
Token | no |
Token ID | 645 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
uity | +1.804 |
swaps | +1.758 |
risis | +1.723 |
millenn | +1.702 |
oute | +1.666 |
Neg logit contributions | |
ット | -2.065 |
fil | -2.009 |
ignore | -1.835 |
BAT | -1.796 |
fixed | -1.790 |
Token | connection |
Token ID | 4637 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
ット | +0.821 |
fil | +0.808 |
ignore | +0.735 |
fixed | +0.727 |
BAT | +0.722 |
Neg logit contributions | |
uity | -0.694 |
swaps | -0.675 |
risis | -0.672 |
millenn | -0.664 |
anguage | -0.648 |
Token | between |
Token ID | 1022 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
uity | +3.006 |
swaps | +2.954 |
risis | +2.922 |
millenn | +2.853 |
oute | +2.845 |
Neg logit contributions | |
ット | -1.527 |
fil | -1.440 |
ignore | -1.244 |
fixed | -1.204 |
BAT | -1.194 |
Token | the |
Token ID | 262 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ット | +0.903 |
fil | +0.895 |
ignore | +0.801 |
fixed | +0.788 |
BAT | +0.785 |
Neg logit contributions | |
uity | -1.004 |
swaps | -0.979 |
risis | -0.978 |
millenn | -0.970 |
anguage | -0.949 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
fil | +2.255 |
ット | +2.254 |
ignore | +2.033 |
fixed | +2.001 |
BAT | +1.996 |
Neg logit contributions | |
uity | -2.132 |
risis | -2.077 |
swaps | -2.061 |
millenn | -2.056 |
anguage | -2.021 |
Token | and |
Token ID | 290 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
fil | +7.512 |
ット | +7.201 |
ignore | +6.498 |
HMS | +6.378 |
BAT | +6.367 |
Neg logit contributions | |
uity | -11.361 |
millenn | -11.321 |
risis | -11.305 |
livest | -10.960 |
swaps | -10.885 |
Token | the |
Token ID | 262 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ット | +1.104 |
fil | +1.096 |
ignore | +0.982 |
fixed | +0.967 |
BAT | +0.963 |
Neg logit contributions | |
uity | -1.197 |
risis | -1.167 |
swaps | -1.167 |
millenn | -1.158 |
anguage | -1.132 |
Token | decision |
Token ID | 2551 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ット | +1.955 |
fil | +1.951 |
ignore | +1.763 |
fixed | +1.738 |
BAT | +1.733 |
Neg logit contributions | |
uity | -1.818 |
risis | -1.770 |
swaps | -1.761 |
millenn | -1.752 |
anguage | -1.721 |
Token | : |
Token ID | 25 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
fil | +3.032 |
ット | +3.011 |
ignore | +2.664 |
fixed | +2.589 |
BAT | +2.584 |
Neg logit contributions | |
uity | -4.623 |
millenn | -4.527 |
risis | -4.524 |
swaps | -4.470 |
anguage | -4.409 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ット | +1.674 |
fil | +1.663 |
ignore | +1.469 |
fixed | +1.443 |
BAT | +1.440 |
Neg logit contributions | |
uity | -2.269 |
swaps | -2.228 |
risis | -2.223 |
millenn | -2.214 |
anguage | -2.157 |
Token | iper |
Token ID | 9346 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
fil | +5.127 |
ット | +4.834 |
ignore | +4.291 |
fixed | +4.239 |
sweet | +4.104 |
Neg logit contributions | |
swaps | -9.420 |
millenn | -9.369 |
uity | -9.308 |
risis | -9.166 |
ּ | -9.067 |
Token | branches |
Token ID | 13737 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
uity | +1.027 |
swaps | +1.001 |
risis | +0.991 |
millenn | +0.979 |
oute | +0.973 |
Neg logit contributions | |
ット | -0.841 |
fil | -0.806 |
ignore | -0.727 |
fixed | -0.717 |
BAT | -0.715 |
Token | ( |
Token ID | 357 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ット | +0.882 |
fil | +0.861 |
ignore | +0.763 |
fixed | +0.750 |
BAT | +0.745 |
Neg logit contributions | |
uity | -1.202 |
swaps | -1.178 |
risis | -1.171 |
millenn | -1.159 |
anguage | -1.136 |
Token | this |
Token ID | 5661 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
ット | +1.499 |
fil | +1.476 |
ignore | +1.304 |
fixed | +1.281 |
BAT | +1.266 |
Neg logit contributions | |
uity | -2.109 |
swaps | -2.069 |
risis | -2.058 |
millenn | -2.044 |
anguage | -1.998 |
Token | is |
Token ID | 318 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
uity | +2.394 |
swaps | +2.392 |
risis | +2.255 |
millenn | +2.233 |
oute | +2.179 |
Neg logit contributions | |
ット | -3.741 |
fil | -3.588 |
ignore | -3.327 |
BAT | -3.309 |
fixed | -3.300 |
Token | Jun |
Token ID | 7653 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
uity | +1.741 |
swaps | +1.708 |
risis | +1.665 |
millenn | +1.662 |
oute | +1.634 |
Neg logit contributions | |
ット | -1.660 |
fil | -1.593 |
ignore | -1.461 |
fixed | -1.434 |
BAT | -1.432 |
Token | iper |
Token ID | 9346 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
fil | +9.398 |
ット | +9.037 |
ignore | +8.517 |
fixed | +8.098 |
sweet | +8.006 |
Neg logit contributions | |
swaps | -9.503 |
millenn | -9.311 |
risis | -9.131 |
uity | -9.112 |
anguage | -9.055 |
Token | us |
Token ID | 385 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ット | +0.047 |
fil | +0.046 |
ignore | +0.041 |
fixed | +0.041 |
BAT | +0.041 |
Neg logit contributions | |
uity | -0.055 |
swaps | -0.053 |
risis | -0.053 |
millenn | -0.052 |
oute | -0.051 |
Token | commun |
Token ID | 1316 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ット | +3.228 |
fil | +3.226 |
ignore | +2.857 |
fixed | +2.800 |
HMS | +2.774 |
Neg logit contributions | |
uity | -3.792 |
swaps | -3.711 |
risis | -3.707 |
millenn | -3.660 |
anguage | -3.614 |
Token | is |
Token ID | 271 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
uity | +4.809 |
risis | +4.623 |
oute | +4.589 |
swaps | +4.468 |
aith | +4.419 |
Neg logit contributions | |
ット | -5.089 |
fil | -4.733 |
BAT | -4.484 |
Boss | -4.442 |
ignore | -4.439 |
Token | , |
Token ID | 837 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ット | +0.243 |
fil | +0.235 |
ignore | +0.209 |
BAT | +0.205 |
fixed | +0.205 |
Neg logit contributions | |
uity | -0.348 |
swaps | -0.340 |
risis | -0.337 |
millenn | -0.334 |
oute | -0.329 |
Token | v |
Token ID | 410 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
uity | +1.104 |
swaps | +1.086 |
risis | +1.073 |
millenn | +1.053 |
oute | +1.038 |
Neg logit contributions | |
ット | -0.921 |
fil | -0.891 |
ignore | -0.798 |
BAT | -0.783 |
fixed | -0.781 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ット | +2.145 |
fil | +2.128 |
ignore | +1.817 |
fixed | +1.787 |
BAT | +1.777 |
Neg logit contributions | |
uity | -4.080 |
millenn | -4.059 |
swaps | -4.035 |
risis | -3.981 |
anguage | -3.918 |
Token | . |
Token ID | 13 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
ット | +1.108 |
fil | +1.087 |
ignore | +0.960 |
fixed | +0.948 |
BAT | +0.937 |
Neg logit contributions | |
uity | -1.534 |
swaps | -1.503 |
risis | -1.496 |
millenn | -1.491 |
anguage | -1.453 |
Token | 7 |
Token ID | 22 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ット | +1.987 |
fil | +1.953 |
ignore | +1.668 |
fixed | +1.640 |
BAT | +1.635 |
Neg logit contributions | |
millenn | -3.701 |
uity | -3.700 |
swaps | -3.655 |
risis | -3.620 |
anguage | -3.556 |
Token | ( |
Token ID | 357 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ット | +2.034 |
fil | +2.004 |
ignore | +1.762 |
fixed | +1.759 |
BAT | +1.725 |
Neg logit contributions | |
uity | -2.837 |
millenn | -2.790 |
swaps | -2.777 |
risis | -2.770 |
anguage | -2.688 |
Token | Product |
Token ID | 15667 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ット | +1.524 |
fil | +1.502 |
ignore | +1.325 |
fixed | +1.309 |
BAT | +1.290 |
Neg logit contributions | |
uity | -2.176 |
swaps | -2.140 |
risis | -2.121 |
millenn | -2.117 |
anguage | -2.062 |
Token | is |
Token ID | 318 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ット | +8.905 |
fil | +8.786 |
ignore | +7.856 |
HMS | +7.739 |
fixed | +7.692 |
Neg logit contributions | |
millenn | -9.762 |
uity | -9.438 |
risis | -9.316 |
swaps | -9.139 |
aith | -9.063 |
Token | delivered |
Token ID | 6793 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ット | +1.540 |
fil | +1.510 |
ignore | +1.360 |
fixed | +1.345 |
BAT | +1.334 |
Neg logit contributions | |
uity | -1.593 |
swaps | -1.556 |
risis | -1.548 |
millenn | -1.535 |
anguage | -1.495 |
Token | as |
Token ID | 355 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ット | +0.560 |
fil | +0.548 |
ignore | +0.488 |
fixed | +0.480 |
BAT | +0.477 |
Neg logit contributions | |
uity | -0.708 |
swaps | -0.693 |
risis | -0.690 |
millenn | -0.682 |
anguage | -0.668 |
Token | a |
Token ID | 257 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
ット | +4.001 |
fil | +3.989 |
fixed | +3.549 |
ignore | +3.499 |
HMS | +3.445 |
Neg logit contributions | |
uity | -5.042 |
millenn | -4.982 |
risis | -4.936 |
swaps | -4.931 |
anguage | -4.798 |
Token | direct |
Token ID | 1277 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
ット | +3.089 |
fil | +3.023 |
fixed | +2.703 |
ignore | +2.692 |
BAT | +2.679 |
Neg logit contributions | |
uity | -3.667 |
millenn | -3.589 |
risis | -3.588 |
swaps | -3.587 |
anguage | -3.498 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
uity | +0.021 |
swaps | +0.020 |
risis | +0.020 |
millenn | +0.020 |
oute | +0.019 |
Neg logit contributions | |
ット | -0.020 |
fil | -0.020 |
ignore | -0.018 |
BAT | -0.017 |
fixed | -0.017 |
Token | there |
Token ID | 612 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ット | +3.180 |
fil | +3.162 |
ignore | +2.818 |
fixed | +2.793 |
HMS | +2.749 |
Neg logit contributions | |
uity | -3.827 |
risis | -3.752 |
swaps | -3.721 |
millenn | -3.713 |
anguage | -3.642 |
Token | aren |
Token ID | 3588 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
uity | +0.842 |
swaps | +0.826 |
risis | +0.816 |
millenn | +0.797 |
oute | +0.779 |
Neg logit contributions | |
ット | -1.031 |
fil | -1.007 |
ignore | -0.922 |
BAT | -0.907 |
fixed | -0.903 |
Token | 't |
Token ID | 470 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ット | +1.714 |
fil | +1.700 |
ignore | +1.470 |
fixed | +1.437 |
BAT | +1.418 |
Neg logit contributions | |
millenn | -3.126 |
uity | -3.070 |
swaps | -3.031 |
risis | -3.022 |
anguage | -2.966 |
Token | any |
Token ID | 597 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ット | +0.532 |
fil | +0.520 |
ignore | +0.465 |
BAT | +0.457 |
fixed | +0.457 |
Neg logit contributions | |
uity | -0.608 |
swaps | -0.598 |
risis | -0.590 |
millenn | -0.583 |
anguage | -0.570 |
Token | lawsuits |
Token ID | 17785 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ット | +2.058 |
fil | +2.027 |
ignore | +1.827 |
fixed | +1.804 |
BAT | +1.783 |
Neg logit contributions | |
uity | -2.150 |
risis | -2.089 |
swaps | -2.087 |
millenn | -2.069 |
anguage | -2.026 |
Token | coming |
Token ID | 2406 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
fil | +9.021 |
ット | +8.820 |
ignore | +8.272 |
fixed | +8.202 |
HMS | +8.089 |
Neg logit contributions | |
millenn | -9.276 |
risis | -9.024 |
uity | -8.989 |
anguage | -8.871 |
ancial | -8.702 |
Token | out |
Token ID | 503 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ット | +1.939 |
fil | +1.908 |
ignore | +1.700 |
fixed | +1.667 |
BAT | +1.654 |
Neg logit contributions | |
uity | -2.510 |
swaps | -2.456 |
risis | -2.450 |
millenn | -2.445 |
anguage | -2.386 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ット | +0.458 |
fil | +0.445 |
ignore | +0.396 |
fixed | +0.389 |
BAT | +0.387 |
Neg logit contributions | |
uity | -0.583 |
swaps | -0.572 |
risis | -0.566 |
millenn | -0.558 |
oute | -0.548 |
Token | but |
Token ID | 475 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
uity | +1.064 |
swaps | +1.053 |
risis | +1.029 |
millenn | +1.011 |
oute | +0.997 |
Neg logit contributions | |
ット | -0.952 |
fil | -0.916 |
ignore | -0.815 |
BAT | -0.807 |
fixed | -0.801 |
Token | this |
Token ID | 428 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ット | +1.282 |
fil | +1.252 |
ignore | +1.117 |
fixed | +1.100 |
BAT | +1.095 |
Neg logit contributions | |
uity | -1.533 |
swaps | -1.505 |
risis | -1.490 |
millenn | -1.474 |
anguage | -1.441 |
Token | & |
Token ID | 1222 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ット | +0.169 |
fil | +0.165 |
ignore | +0.146 |
fixed | +0.144 |
BAT | +0.143 |
Neg logit contributions | |
uity | -0.236 |
swaps | -0.231 |
risis | -0.230 |
millenn | -0.228 |
anguage | -0.223 |
Token | Sc |
Token ID | 1446 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
uity | +0.710 |
swaps | +0.693 |
risis | +0.686 |
millenn | +0.674 |
oute | +0.663 |
Neg logit contributions | |
ット | -0.723 |
fil | -0.706 |
ignore | -0.640 |
fixed | -0.632 |
BAT | -0.629 |
Token | af |
Token ID | 1878 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
uity | +3.490 |
risis | +3.403 |
anguage | +3.274 |
aith | +3.273 |
oute | +3.265 |
Neg logit contributions | |
ット | -3.223 |
fil | -2.957 |
HMS | -2.708 |
BAT | -2.688 |
ignore | -2.685 |
Token | etta |
Token ID | 15253 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
uity | +2.677 |
risis | +2.612 |
swaps | +2.554 |
ancial | +2.500 |
oute | +2.488 |
Neg logit contributions | |
ット | -2.625 |
fil | -2.511 |
BAT | -2.316 |
fixed | -2.291 |
Boss | -2.283 |
Token | ( |
Token ID | 357 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ット | +2.837 |
fil | +2.789 |
ignore | +2.424 |
fixed | +2.337 |
HMS | +2.296 |
Neg logit contributions | |
uity | -4.656 |
swaps | -4.568 |
risis | -4.555 |
millenn | -4.495 |
anguage | -4.445 |
Token | 2011 |
Token ID | 9804 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ット | +2.898 |
fil | +2.898 |
ignore | +2.513 |
fixed | +2.433 |
above | +2.432 |
Neg logit contributions | |
millenn | -5.207 |
uity | -5.170 |
swaps | -5.132 |
risis | -5.028 |
livest | -4.959 |
Token | ). |
Token ID | 737 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
fil | +5.091 |
ット | +4.795 |
ignore | +3.913 |
fixed | +3.821 |
HMS | +3.755 |
Neg logit contributions | |
millenn | -13.147 |
uity | -13.096 |
swaps | -13.000 |
risis | -12.847 |
ancial | -12.720 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ット | +0.847 |
fil | +0.830 |
ignore | +0.744 |
fixed | +0.734 |
BAT | +0.729 |
Neg logit contributions | |
uity | -0.963 |
swaps | -0.941 |
risis | -0.935 |
millenn | -0.920 |
anguage | -0.903 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
ット | +0.613 |
fil | +0.599 |
ignore | +0.532 |
fixed | +0.524 |
BAT | +0.520 |
Neg logit contributions | |
uity | -0.796 |
swaps | -0.779 |
risis | -0.775 |
millenn | -0.764 |
anguage | -0.751 |
Token | I |
Token ID | 40 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ット | +0.085 |
fil | +0.083 |
ignore | +0.074 |
fixed | +0.073 |
BAT | +0.072 |
Neg logit contributions | |
uity | -0.099 |
swaps | -0.097 |
risis | -0.097 |
millenn | -0.094 |
oute | -0.093 |
Token | should |
Token ID | 815 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ット | +2.108 |
fil | +2.075 |
ignore | +1.870 |
fixed | +1.843 |
BAT | +1.824 |
Neg logit contributions | |
uity | -2.221 |
swaps | -2.172 |
risis | -2.157 |
millenn | -2.150 |
anguage | -2.090 |
Token | it |
Token ID | 340 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
uity | +2.175 |
swaps | +2.152 |
risis | +2.102 |
millenn | +2.058 |
ּ | +2.035 |
Neg logit contributions | |
ット | -1.929 |
fil | -1.816 |
fixed | -1.637 |
BAT | -1.630 |
ignore | -1.628 |
Token | both |
Token ID | 1111 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
uity | +0.266 |
swaps | +0.261 |
risis | +0.258 |
millenn | +0.255 |
anguage | +0.249 |
Neg logit contributions | |
ット | -0.283 |
fil | -0.277 |
ignore | -0.251 |
fixed | -0.248 |
BAT | -0.247 |
Token | drives |
Token ID | 10182 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
uity | +0.176 |
swaps | +0.173 |
risis | +0.171 |
millenn | +0.168 |
anguage | +0.164 |
Neg logit contributions | |
ット | -0.210 |
fil | -0.205 |
ignore | -0.187 |
fixed | -0.185 |
BAT | -0.184 |
Token | home |
Token ID | 1363 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
uity | +1.773 |
swaps | +1.737 |
risis | +1.710 |
millenn | +1.685 |
ּ | +1.659 |
Neg logit contributions | |
ット | -1.832 |
fil | -1.755 |
ignore | -1.582 |
fixed | -1.582 |
BAT | -1.559 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
uity | +1.011 |
swaps | +0.989 |
risis | +0.982 |
millenn | +0.964 |
anguage | +0.949 |
Neg logit contributions | |
ット | -0.975 |
fil | -0.936 |
ignore | -0.846 |
fixed | -0.844 |
BAT | -0.831 |
Token | pain |
Token ID | 2356 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ット | +1.385 |
fil | +1.366 |
ignore | +1.224 |
fixed | +1.206 |
BAT | +1.200 |
Neg logit contributions | |
uity | -1.514 |
swaps | -1.480 |
risis | -1.472 |
millenn | -1.459 |
anguage | -1.427 |
Token | of |
Token ID | 286 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
fil | +7.508 |
ット | +7.073 |
ignore | +6.338 |
fixed | +6.248 |
BAT | +6.171 |
Neg logit contributions | |
millenn | -10.467 |
swaps | -10.442 |
uity | -10.399 |
risis | -10.241 |
livest | -10.112 |
Token | heart |
Token ID | 2612 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ット | +1.273 |
fil | +1.256 |
ignore | +1.129 |
fixed | +1.105 |
BAT | +1.098 |
Neg logit contributions | |
uity | -1.408 |
swaps | -1.375 |
risis | -1.367 |
millenn | -1.354 |
anguage | -1.327 |
Token | break |
Token ID | 9032 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ット | +0.460 |
fil | +0.447 |
ignore | +0.386 |
fixed | +0.378 |
BAT | +0.374 |
Neg logit contributions | |
uity | -0.842 |
swaps | -0.827 |
risis | -0.823 |
millenn | -0.815 |
anguage | -0.801 |
Token | and |
Token ID | 290 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ット | +1.168 |
fil | +1.139 |
ignore | +1.014 |
fixed | +0.998 |
BAT | +0.992 |
Neg logit contributions | |
uity | -1.484 |
swaps | -1.454 |
risis | -1.445 |
millenn | -1.427 |
anguage | -1.400 |
Token | reminds |
Token ID | 17603 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ット | +2.470 |
fil | +2.463 |
ignore | +2.244 |
fixed | +2.207 |
BAT | +2.188 |
Neg logit contributions | |
uity | -2.082 |
risis | -2.013 |
millenn | -2.006 |
swaps | -2.004 |
anguage | -1.949 |
Token | implying |
Token ID | 30253 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
uity | +0.719 |
swaps | +0.707 |
risis | +0.696 |
millenn | +0.685 |
anguage | +0.671 |
Neg logit contributions | |
ット | -0.657 |
fil | -0.635 |
ignore | -0.569 |
fixed | -0.561 |
BAT | -0.561 |
Token | that |
Token ID | 326 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
uity | +3.390 |
swaps | +3.329 |
risis | +3.248 |
millenn | +3.179 |
oute | +3.142 |
Neg logit contributions | |
ット | -3.618 |
fil | -3.459 |
ignore | -3.140 |
fixed | -3.112 |
BAT | -3.083 |
Token | the |
Token ID | 262 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
uity | +0.240 |
swaps | +0.236 |
risis | +0.233 |
millenn | +0.230 |
oute | +0.225 |
Neg logit contributions | |
ット | -0.232 |
fil | -0.224 |
ignore | -0.203 |
fixed | -0.200 |
BAT | -0.199 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
ット | +0.932 |
fil | +0.914 |
ignore | +0.825 |
fixed | +0.813 |
BAT | +0.808 |
Neg logit contributions | |
uity | -0.961 |
swaps | -0.939 |
risis | -0.932 |
millenn | -0.922 |
anguage | -0.901 |
Token | was |
Token ID | 373 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
ット | +0.183 |
fil | +0.179 |
ignore | +0.162 |
fixed | +0.160 |
BAT | +0.160 |
Neg logit contributions | |
uity | -0.169 |
swaps | -0.165 |
risis | -0.163 |
millenn | -0.161 |
anguage | -0.157 |
Token | boiling |
Token ID | 24372 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ット | +0.304 |
fil | +0.296 |
ignore | +0.268 |
fixed | +0.263 |
BAT | +0.262 |
Neg logit contributions | |
uity | -0.317 |
swaps | -0.310 |
risis | -0.307 |
millenn | -0.303 |
oute | -0.296 |
Token | a |
Token ID | 257 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
fil | +7.289 |
ット | +7.082 |
HMS | +6.632 |
ignore | +6.406 |
fixed | +6.308 |
Neg logit contributions | |
uity | -10.435 |
millenn | -10.290 |
risis | -10.244 |
swaps | -10.000 |
anguage | -9.869 |
Token | soup |
Token ID | 17141 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ット | +2.068 |
fil | +2.051 |
ignore | +1.839 |
fixed | +1.812 |
BAT | +1.802 |
Neg logit contributions | |
uity | -2.166 |
swaps | -2.116 |
risis | -2.101 |
millenn | -2.088 |
anguage | -2.045 |
Token | pot |
Token ID | 1787 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
fil | +3.065 |
ット | +3.051 |
ignore | +2.716 |
fixed | +2.697 |
above | +2.616 |
Neg logit contributions | |
uity | -3.755 |
millenn | -3.720 |
swaps | -3.675 |
risis | -3.651 |
urches | -3.543 |
Token | full |
Token ID | 1336 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
uity | +0.875 |
swaps | +0.856 |
risis | +0.850 |
millenn | +0.829 |
oute | +0.823 |
Neg logit contributions | |
ット | -0.705 |
fil | -0.685 |
ignore | -0.610 |
BAT | -0.603 |
fixed | -0.598 |
Token | of |
Token ID | 286 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ット | +0.201 |
fil | +0.196 |
ignore | +0.176 |
fixed | +0.173 |
BAT | +0.172 |
Neg logit contributions | |
uity | -0.242 |
swaps | -0.237 |
risis | -0.235 |
millenn | -0.233 |
anguage | -0.227 |
Token | pay |
Token ID | 1414 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
uity | +0.845 |
swaps | +0.837 |
risis | +0.807 |
oute | +0.786 |
millenn | +0.784 |
Neg logit contributions | |
ット | -0.913 |
fil | -0.892 |
ignore | -0.809 |
fixed | -0.797 |
BAT | -0.794 |
Token | up |
Token ID | 510 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
uity | +0.007 |
swaps | +0.007 |
risis | +0.007 |
millenn | +0.007 |
oute | +0.007 |
Neg logit contributions | |
ット | -0.007 |
fil | -0.007 |
ignore | -0.007 |
fixed | -0.006 |
BAT | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
uity | +2.178 |
swaps | +2.130 |
risis | +2.094 |
oute | +2.014 |
anguage | +2.002 |
Neg logit contributions | |
ット | -1.834 |
fil | -1.775 |
ignore | -1.591 |
fixed | -1.559 |
BAT | -1.558 |
Token | settle |
Token ID | 12259 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
uity | +0.503 |
swaps | +0.493 |
risis | +0.485 |
millenn | +0.476 |
oute | +0.467 |
Neg logit contributions | |
ット | -0.534 |
fil | -0.521 |
ignore | -0.473 |
fixed | -0.464 |
BAT | -0.462 |
Token | a |
Token ID | 257 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
ット | +3.970 |
fil | +3.936 |
ignore | +3.515 |
BAT | +3.502 |
fixed | +3.484 |
Neg logit contributions | |
uity | -4.381 |
risis | -4.302 |
millenn | -4.301 |
swaps | -4.228 |
anguage | -4.225 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ット | +3.532 |
fil | +3.508 |
BAT | +3.212 |
ignore | +3.210 |
fixed | +3.194 |
Neg logit contributions | |
uity | -2.209 |
risis | -2.138 |
millenn | -2.125 |
swaps | -2.114 |
anguage | -2.102 |
Token | stemming |
Token ID | 34807 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
fil | +6.919 |
ット | +6.763 |
HMS | +6.205 |
ignore | +5.969 |
BAT | +5.903 |
Neg logit contributions | |
uity | -10.706 |
risis | -10.692 |
millenn | -10.582 |
anguage | -10.494 |
livest | -10.478 |
Token | from |
Token ID | 422 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ット | +2.200 |
fil | +2.194 |
ignore | +1.882 |
BAT | +1.835 |
HMS | +1.834 |
Neg logit contributions | |
millenn | -4.059 |
uity | -4.019 |
risis | -3.960 |
anguage | -3.915 |
livest | -3.881 |
Token | a |
Token ID | 257 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ット | +0.714 |
fil | +0.702 |
ignore | +0.629 |
fixed | +0.620 |
BAT | +0.618 |
Neg logit contributions | |
uity | -0.781 |
swaps | -0.762 |
risis | -0.760 |
millenn | -0.752 |
anguage | -0.735 |
Token | disastrous |
Token ID | 20756 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ット | +0.802 |
fil | +0.791 |
ignore | +0.714 |
fixed | +0.704 |
BAT | +0.703 |
Neg logit contributions | |
uity | -0.786 |
swaps | -0.765 |
risis | -0.763 |
millenn | -0.755 |
anguage | -0.739 |
Token | raid |
Token ID | 9513 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ット | +0.685 |
fil | +0.672 |
ignore | +0.608 |
fixed | +0.599 |
BAT | +0.595 |
Neg logit contributions | |
uity | -0.673 |
swaps | -0.659 |
risis | -0.654 |
millenn | -0.646 |
anguage | -0.630 |
Token | from |
Token ID | 422 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
uity | +2.782 |
swaps | +2.723 |
risis | +2.699 |
millenn | +2.641 |
oute | +2.621 |
Neg logit contributions | |
ット | -2.383 |
fil | -2.314 |
ignore | -2.064 |
fixed | -2.041 |
BAT | -2.031 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
uity | +1.190 |
swaps | +1.163 |
risis | +1.154 |
millenn | +1.138 |
anguage | +1.111 |
Neg logit contributions | |
ット | -1.222 |
fil | -1.195 |
ignore | -1.082 |
fixed | -1.071 |
BAT | -1.062 |
Token | W |
Token ID | 370 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
uity | +0.339 |
swaps | +0.331 |
risis | +0.328 |
millenn | +0.323 |
anguage | +0.313 |
Neg logit contributions | |
ット | -0.429 |
fil | -0.420 |
ignore | -0.384 |
fixed | -0.380 |
BAT | -0.378 |
Token | ob |
Token ID | 672 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
uity | +0.854 |
swaps | +0.833 |
risis | +0.831 |
millenn | +0.817 |
anguage | +0.801 |
Neg logit contributions | |
ット | -0.851 |
fil | -0.831 |
ignore | -0.750 |
fixed | -0.742 |
BAT | -0.732 |
Token | urn |
Token ID | 700 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
uity | +0.498 |
swaps | +0.425 |
risis | +0.394 |
millenn | +0.354 |
oute | +0.318 |
Neg logit contributions | |
ット | -4.043 |
fil | -3.943 |
ignore | -3.767 |
fixed | -3.752 |
HMS | -3.719 |
Token | Superior |
Token ID | 22953 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ット | +0.698 |
fil | +0.686 |
ignore | +0.620 |
fixed | +0.611 |
BAT | +0.607 |
Neg logit contributions | |
uity | -0.680 |
swaps | -0.664 |
risis | -0.660 |
millenn | -0.653 |
anguage | -0.637 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
fil | +9.401 |
ット | +9.305 |
HMS | +8.594 |
ignore | +8.422 |
Clown | +8.274 |
Neg logit contributions | |
uity | -7.958 |
swaps | -7.892 |
millenn | -7.838 |
risis | -7.722 |
ּ | -7.678 |
Token | offices |
Token ID | 9730 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
fil | +4.967 |
ット | +4.957 |
ignore | +4.468 |
HMS | +4.392 |
above | +4.354 |
Neg logit contributions | |
uity | -5.497 |
swaps | -5.354 |
risis | -5.315 |
millenn | -5.298 |
livest | -5.139 |
Token | to |
Token ID | 284 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ット | +0.938 |
fil | +0.927 |
ignore | +0.832 |
fixed | +0.819 |
BAT | +0.811 |
Neg logit contributions | |
uity | -1.028 |
swaps | -1.004 |
risis | -0.999 |
millenn | -0.994 |
anguage | -0.967 |
Token | inform |
Token ID | 4175 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
ット | +1.132 |
fil | +1.120 |
ignore | +1.014 |
fixed | +0.990 |
HMS | +0.986 |
Neg logit contributions | |
uity | -1.137 |
risis | -1.106 |
swaps | -1.106 |
millenn | -1.096 |
anguage | -1.069 |
Token | immigration |
Token ID | 6272 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
uity | +3.023 |
swaps | +2.953 |
risis | +2.910 |
millenn | +2.860 |
anguage | +2.811 |
Neg logit contributions | |
ット | -3.044 |
fil | -2.922 |
ignore | -2.660 |
fixed | -2.649 |
BAT | -2.627 |
Token | This |
Token ID | 770 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ット | +0.846 |
fil | +0.830 |
ignore | +0.746 |
fixed | +0.735 |
BAT | +0.730 |
Neg logit contributions | |
uity | -0.924 |
swaps | -0.904 |
risis | -0.899 |
millenn | -0.892 |
anguage | -0.870 |
Token | was |
Token ID | 373 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
uity | +0.427 |
swaps | +0.415 |
risis | +0.412 |
millenn | +0.407 |
anguage | +0.396 |
Neg logit contributions | |
ット | -0.546 |
fil | -0.537 |
ignore | -0.491 |
fixed | -0.485 |
BAT | -0.482 |
Token | proved |
Token ID | 8302 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
uity | +1.783 |
swaps | +1.735 |
risis | +1.719 |
millenn | +1.694 |
anguage | +1.665 |
Neg logit contributions | |
ット | -1.609 |
fil | -1.578 |
ignore | -1.421 |
BAT | -1.392 |
fixed | -1.388 |
Token | by |
Token ID | 416 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
uity | +2.108 |
swaps | +2.065 |
risis | +2.048 |
millenn | +2.010 |
ּ | +1.993 |
Neg logit contributions | |
ット | -1.677 |
fil | -1.632 |
ignore | -1.448 |
fixed | -1.422 |
BAT | -1.413 |
Token | Leonard |
Token ID | 20131 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
uity | +1.863 |
swaps | +1.831 |
risis | +1.799 |
millenn | +1.781 |
oute | +1.762 |
Neg logit contributions | |
ット | -1.735 |
fil | -1.681 |
ignore | -1.520 |
fixed | -1.495 |
BAT | -1.493 |
Token | Klein |
Token ID | 22864 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
uity | +1.822 |
swaps | +1.773 |
risis | +1.753 |
millenn | +1.725 |
oute | +1.700 |
Neg logit contributions | |
ット | -1.766 |
fil | -1.719 |
ignore | -1.555 |
fixed | -1.541 |
BAT | -1.530 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
fil | +8.039 |
ット | +7.824 |
ignore | +7.105 |
above | +6.888 |
fixed | +6.815 |
Neg logit contributions | |
millenn | -9.729 |
swaps | -9.593 |
uity | -9.522 |
risis | -9.415 |
urches | -9.156 |
Token | in |
Token ID | 287 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ット | +2.959 |
fil | +2.943 |
ignore | +2.605 |
fixed | +2.531 |
above | +2.500 |
Neg logit contributions | |
uity | -3.886 |
swaps | -3.830 |
millenn | -3.801 |
risis | -3.794 |
anguage | -3.663 |
Token | 1979 |
Token ID | 13521 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ット | +1.429 |
fil | +1.403 |
ignore | +1.256 |
fixed | +1.234 |
BAT | +1.228 |
Neg logit contributions | |
uity | -1.600 |
swaps | -1.566 |
risis | -1.555 |
millenn | -1.544 |
anguage | -1.504 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ット | +3.637 |
fil | +3.616 |
ignore | +3.165 |
fixed | +3.100 |
above | +3.080 |
Neg logit contributions | |
uity | -5.326 |
swaps | -5.274 |
millenn | -5.267 |
risis | -5.188 |
anguage | -5.067 |
Token | unfortunately |
Token ID | 12716 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ット | +0.653 |
fil | +0.640 |
ignore | +0.572 |
fixed | +0.563 |
BAT | +0.559 |
Neg logit contributions | |
uity | -0.785 |
swaps | -0.768 |
risis | -0.764 |
millenn | -0.755 |
anguage | -0.739 |
Token | 1 |
Token ID | 16 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
ット | +1.004 |
fil | +0.982 |
ignore | +0.850 |
fixed | +0.832 |
BAT | +0.827 |
Neg logit contributions | |
uity | -1.764 |
swaps | -1.737 |
millenn | -1.731 |
risis | -1.724 |
anguage | -1.684 |
Token | million |
Token ID | 1510 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
uity | +0.271 |
swaps | +0.264 |
risis | +0.261 |
millenn | +0.257 |
anguage | +0.251 |
Neg logit contributions | |
ット | -0.257 |
fil | -0.252 |
ignore | -0.227 |
fixed | -0.224 |
BAT | -0.222 |
Token | and |
Token ID | 290 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ット | +0.140 |
fil | +0.137 |
ignore | +0.122 |
fixed | +0.119 |
BAT | +0.119 |
Neg logit contributions | |
uity | -0.188 |
swaps | -0.184 |
risis | -0.182 |
millenn | -0.180 |
anguage | -0.176 |
Token | settled |
Token ID | 10282 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
uity | +0.769 |
swaps | +0.757 |
risis | +0.741 |
millenn | +0.734 |
oute | +0.717 |
Neg logit contributions | |
ット | -0.802 |
fil | -0.785 |
ignore | -0.712 |
BAT | -0.697 |
fixed | -0.697 |
Token | the |
Token ID | 262 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
ット | +1.510 |
fil | +1.474 |
ignore | +1.312 |
fixed | +1.296 |
BAT | +1.287 |
Neg logit contributions | |
uity | -2.034 |
risis | -1.993 |
millenn | -1.990 |
swaps | -1.987 |
anguage | -1.948 |
Token | suit |
Token ID | 6050 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ット | +2.494 |
fil | +2.457 |
ignore | +2.239 |
fixed | +2.226 |
BAT | +2.208 |
Neg logit contributions | |
uity | -1.991 |
risis | -1.936 |
millenn | -1.928 |
swaps | -1.926 |
anguage | -1.898 |
Token | on |
Token ID | 319 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ット | +6.484 |
fil | +6.455 |
fixed | +5.899 |
ignore | +5.877 |
HMS | +5.863 |
Neg logit contributions | |
millenn | -10.803 |
anguage | -10.320 |
risis | -10.280 |
livest | -10.206 |
uity | -10.147 |
Token | condition |
Token ID | 4006 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ット | +0.433 |
fil | +0.425 |
ignore | +0.384 |
fixed | +0.379 |
BAT | +0.376 |
Neg logit contributions | |
uity | -0.434 |
swaps | -0.423 |
risis | -0.421 |
millenn | -0.416 |
anguage | -0.407 |
Token | of |
Token ID | 286 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
uity | +3.732 |
swaps | +3.689 |
risis | +3.552 |
millenn | +3.523 |
oute | +3.494 |
Neg logit contributions | |
ット | -4.037 |
fil | -3.948 |
ignore | -3.611 |
fixed | -3.506 |
BAT | -3.503 |
Token | his |
Token ID | 465 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
uity | +1.528 |
swaps | +1.500 |
risis | +1.464 |
millenn | +1.457 |
oute | +1.420 |
Neg logit contributions | |
ット | -1.664 |
fil | -1.630 |
ignore | -1.480 |
fixed | -1.456 |
BAT | -1.452 |
Token | ret |
Token ID | 1005 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ット | +0.589 |
fil | +0.580 |
ignore | +0.525 |
fixed | +0.518 |
BAT | +0.514 |
Neg logit contributions | |
uity | -0.554 |
risis | -0.542 |
swaps | -0.539 |
millenn | -0.532 |
anguage | -0.524 |
Token | describing |
Token ID | 12059 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
fil | +2.265 |
ット | +2.262 |
ignore | +1.985 |
fixed | +1.963 |
BAT | +1.909 |
Neg logit contributions | |
uity | -3.263 |
millenn | -3.226 |
risis | -3.202 |
swaps | -3.187 |
anguage | -3.106 |
Token | own |
Token ID | 898 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ット | +0.322 |
fil | +0.314 |
ignore | +0.283 |
fixed | +0.278 |
BAT | +0.278 |
Neg logit contributions | |
uity | -0.355 |
swaps | -0.349 |
risis | -0.345 |
millenn | -0.341 |
anguage | -0.334 |
Token | backgrounds |
Token ID | 19063 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ット | +4.282 |
fil | +4.253 |
ignore | +3.770 |
fixed | +3.733 |
HMS | +3.707 |
Neg logit contributions | |
uity | -4.810 |
millenn | -4.722 |
risis | -4.717 |
swaps | -4.662 |
anguage | -4.564 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ット | +0.051 |
fil | +0.050 |
ignore | +0.044 |
fixed | +0.043 |
BAT | +0.043 |
Neg logit contributions | |
uity | -0.067 |
swaps | -0.066 |
risis | -0.065 |
millenn | -0.064 |
anguage | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
uity | +0.399 |
swaps | +0.392 |
risis | +0.385 |
millenn | +0.382 |
oute | +0.372 |
Neg logit contributions | |
ット | -0.377 |
fil | -0.366 |
ignore | -0.331 |
BAT | -0.326 |
fixed | -0.326 |
Token | projects |
Token ID | 4493 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ット | +1.165 |
fil | +1.145 |
ignore | +1.034 |
fixed | +1.020 |
BAT | +1.013 |
Neg logit contributions | |
uity | -1.163 |
swaps | -1.135 |
risis | -1.130 |
millenn | -1.118 |
anguage | -1.091 |
Token | we |
Token ID | 356 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
fil | +7.125 |
ット | +6.991 |
fixed | +6.389 |
HMS | +6.365 |
ignore | +6.186 |
Neg logit contributions | |
millenn | -10.224 |
uity | -10.191 |
risis | -10.090 |
anguage | -9.951 |
livest | -9.804 |
Token | were |
Token ID | 547 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
uity | +0.085 |
swaps | +0.083 |
risis | +0.082 |
millenn | +0.079 |
oute | +0.079 |
Neg logit contributions | |
ット | -0.095 |
fil | -0.092 |
ignore | -0.084 |
BAT | -0.083 |
fixed | -0.083 |
Token | working |
Token ID | 1762 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
uity | +1.336 |
swaps | +1.317 |
risis | +1.272 |
millenn | +1.243 |
oute | +1.232 |
Neg logit contributions | |
ット | -1.777 |
fil | -1.721 |
ignore | -1.600 |
BAT | -1.558 |
fixed | -1.557 |
Token | on |
Token ID | 319 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ット | +1.443 |
fil | +1.411 |
ignore | +1.257 |
fixed | +1.234 |
BAT | +1.227 |
Neg logit contributions | |
uity | -1.816 |
swaps | -1.780 |
risis | -1.766 |
millenn | -1.743 |
anguage | -1.710 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
ット | +0.759 |
fil | +0.741 |
ignore | +0.658 |
fixed | +0.645 |
BAT | +0.642 |
Neg logit contributions | |
uity | -1.010 |
swaps | -0.990 |
risis | -0.983 |
millenn | -0.970 |
anguage | -0.952 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
uity | +1.037 |
swaps | +1.018 |
risis | +1.006 |
millenn | +0.979 |
oute | +0.975 |
Neg logit contributions | |
ット | -0.841 |
fil | -0.818 |
ignore | -0.730 |
BAT | -0.727 |
fixed | -0.714 |
Token | Its |
Token ID | 6363 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ット | +1.006 |
fil | +0.986 |
ignore | +0.885 |
fixed | +0.872 |
BAT | +0.867 |
Neg logit contributions | |
uity | -1.114 |
swaps | -1.090 |
risis | -1.082 |
millenn | -1.070 |
anguage | -1.047 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ット | +1.199 |
fil | +1.177 |
ignore | +1.056 |
fixed | +1.041 |
BAT | +1.031 |
Neg logit contributions | |
uity | -1.336 |
swaps | -1.303 |
risis | -1.299 |
millenn | -1.286 |
anguage | -1.257 |
Token | range |
Token ID | 2837 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ット | +0.037 |
fil | +0.036 |
ignore | +0.033 |
fixed | +0.032 |
BAT | +0.032 |
Neg logit contributions | |
uity | -0.043 |
swaps | -0.042 |
risis | -0.042 |
millenn | -0.041 |
anguage | -0.040 |
Token | is |
Token ID | 318 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
uity | +0.968 |
swaps | +0.946 |
risis | +0.935 |
millenn | +0.920 |
anguage | +0.897 |
Neg logit contributions | |
ット | -1.254 |
fil | -1.235 |
ignore | -1.130 |
fixed | -1.116 |
BAT | -1.111 |
Token | [- |
Token ID | 25915 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ット | +0.636 |
fil | +0.623 |
ignore | +0.558 |
fixed | +0.550 |
BAT | +0.545 |
Neg logit contributions | |
uity | -0.741 |
swaps | -0.724 |
risis | -0.720 |
millenn | -0.714 |
anguage | -0.697 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
fil | +4.773 |
ット | +4.582 |
fixed | +4.066 |
ignore | +4.031 |
above | +3.717 |
Neg logit contributions | |
millenn | -13.065 |
swaps | -12.661 |
uity | -12.592 |
risis | -12.498 |
livest | -12.297 |
Token | , |
Token ID | 11 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
ット | +3.651 |
fil | +3.596 |
ignore | +3.070 |
fixed | +3.037 |
BAT | +2.959 |
Neg logit contributions | |
uity | -6.443 |
swaps | -6.320 |
risis | -6.281 |
millenn | -6.234 |
anguage | -6.197 |
Token | + |
Token ID | 10 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ット | +2.760 |
fil | +2.720 |
ignore | +2.451 |
fixed | +2.423 |
BAT | +2.369 |
Neg logit contributions | |
uity | -3.069 |
swaps | -2.992 |
risis | -2.983 |
millenn | -2.981 |
anguage | -2.887 |
Token | 1 |
Token ID | 16 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
fil | +2.582 |
ット | +2.490 |
ignore | +2.191 |
fixed | +2.097 |
above | +1.960 |
Neg logit contributions | |
millenn | -7.758 |
uity | -7.344 |
swaps | -7.328 |
livest | -7.298 |
risis | -7.262 |
Token | ], |
Token ID | 4357 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ット | +1.779 |
fil | +1.739 |
ignore | +1.500 |
fixed | +1.471 |
BAT | +1.441 |
Neg logit contributions | |
uity | -3.184 |
swaps | -3.116 |
risis | -3.108 |
millenn | -3.090 |
anguage | -3.029 |
Token | detail |
Token ID | 3703 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
uity | +0.418 |
swaps | +0.410 |
risis | +0.407 |
millenn | +0.402 |
oute | +0.393 |
Neg logit contributions | |
ット | -0.401 |
fil | -0.391 |
ignore | -0.354 |
fixed | -0.350 |
BAT | -0.347 |
Token | by |
Token ID | 416 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
uity | +1.001 |
swaps | +0.979 |
risis | +0.974 |
millenn | +0.958 |
anguage | +0.945 |
Neg logit contributions | |
ット | -0.766 |
fil | -0.744 |
ignore | -0.664 |
fixed | -0.654 |
BAT | -0.648 |
Token | B |
Token ID | 347 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
uity | +2.248 |
swaps | +2.206 |
risis | +2.174 |
millenn | +2.156 |
oute | +2.108 |
Neg logit contributions | |
ット | -2.201 |
fil | -2.139 |
ignore | -1.931 |
fixed | -1.915 |
BAT | -1.898 |
Token | ode |
Token ID | 1098 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
uity | +2.312 |
risis | +2.236 |
swaps | +2.215 |
oute | +2.179 |
millenn | +2.151 |
Neg logit contributions | |
ット | -2.443 |
fil | -2.353 |
ignore | -2.145 |
fixed | -2.144 |
BAT | -2.104 |
Token | ( |
Token ID | 357 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ット | +0.432 |
fil | +0.424 |
ignore | +0.373 |
fixed | +0.367 |
BAT | +0.364 |
Neg logit contributions | |
uity | -0.606 |
swaps | -0.594 |
risis | -0.591 |
millenn | -0.585 |
anguage | -0.574 |
Token | 1945 |
Token ID | 41931 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ット | +2.334 |
fil | +2.313 |
ignore | +2.013 |
fixed | +1.966 |
BAT | +1.954 |
Neg logit contributions | |
uity | -3.790 |
swaps | -3.748 |
millenn | -3.740 |
risis | -3.685 |
anguage | -3.612 |
Token | ) |
Token ID | 8 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
fil | +5.485 |
ット | +5.353 |
ignore | +4.468 |
above | +4.365 |
fixed | +4.345 |
Neg logit contributions | |
millenn | -12.154 |
uity | -11.806 |
swaps | -11.763 |
risis | -11.505 |
ancial | -11.497 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ット | +1.722 |
fil | +1.688 |
ignore | +1.496 |
fixed | +1.465 |
BAT | +1.452 |
Neg logit contributions | |
uity | -2.287 |
swaps | -2.246 |
risis | -2.228 |
millenn | -2.224 |
anguage | -2.163 |
Token | is |
Token ID | 318 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ット | +0.658 |
fil | +0.645 |
ignore | +0.583 |
fixed | +0.574 |
BAT | +0.571 |
Neg logit contributions | |
uity | -0.657 |
swaps | -0.642 |
risis | -0.637 |
millenn | -0.630 |
anguage | -0.615 |
Token | encaps |
Token ID | 32652 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
uity | +0.471 |
swaps | +0.461 |
risis | +0.453 |
millenn | +0.450 |
anguage | +0.440 |
Neg logit contributions | |
ット | -0.439 |
fil | -0.427 |
ignore | -0.387 |
BAT | -0.378 |
fixed | -0.378 |
Token | ulated |
Token ID | 4817 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
fil | +1.964 |
ット | +1.960 |
fixed | +1.752 |
ignore | +1.748 |
BAT | +1.697 |
Neg logit contributions | |
millenn | -2.136 |
uity | -2.131 |
swaps | -2.131 |
risis | -2.085 |
livest | -2.037 |
Token | binary |
Token ID | 13934 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
ット | +1.832 |
fil | +1.799 |
ignore | +1.618 |
fixed | +1.591 |
BAT | +1.576 |
Neg logit contributions | |
uity | -2.019 |
risis | -1.965 |
swaps | -1.961 |
millenn | -1.946 |
anguage | -1.901 |
Token | format |
Token ID | 5794 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ット | +0.287 |
fil | +0.281 |
ignore | +0.252 |
fixed | +0.248 |
BAT | +0.246 |
Neg logit contributions | |
uity | -0.327 |
swaps | -0.320 |
risis | -0.318 |
millenn | -0.315 |
anguage | -0.308 |
Token | does |
Token ID | 857 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
uity | +1.044 |
swaps | +1.024 |
risis | +1.003 |
millenn | +0.987 |
anguage | +0.963 |
Neg logit contributions | |
ット | -1.402 |
fil | -1.372 |
ignore | -1.257 |
fixed | -1.242 |
BAT | -1.240 |
Token | not |
Token ID | 407 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ット | +0.311 |
fil | +0.305 |
ignore | +0.275 |
fixed | +0.271 |
BAT | +0.270 |
Neg logit contributions | |
uity | -0.306 |
swaps | -0.299 |
risis | -0.297 |
millenn | -0.293 |
anguage | -0.287 |
Token | support |
Token ID | 1104 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
uity | +0.429 |
swaps | +0.421 |
risis | +0.416 |
anguage | +0.400 |
oute | +0.400 |
Neg logit contributions | |
ット | -0.411 |
fil | -0.400 |
ignore | -0.358 |
BAT | -0.357 |
Boss | -0.355 |
Token | version |
Token ID | 2196 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
ット | +0.992 |
fil | +0.972 |
ignore | +0.873 |
fixed | +0.860 |
BAT | +0.855 |
Neg logit contributions | |
uity | -1.088 |
swaps | -1.064 |
risis | -1.057 |
millenn | -1.046 |
anguage | -1.022 |
Token | ing |
Token ID | 278 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
fil | +9.078 |
ット | +8.981 |
ignore | +7.934 |
fixed | +7.840 |
above | +7.680 |
Neg logit contributions | |
millenn | -8.380 |
uity | -8.328 |
risis | -8.283 |
anguage | -8.218 |
ancial | -8.081 |
Token | . |
Token ID | 13 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
ット | +2.947 |
fil | +2.913 |
ignore | +2.588 |
fixed | +2.547 |
HMS | +2.489 |
Neg logit contributions | |
uity | -3.921 |
risis | -3.831 |
millenn | -3.825 |
swaps | -3.787 |
anguage | -3.730 |
Token | The |
Token ID | 383 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ット | +1.885 |
fil | +1.854 |
ignore | +1.664 |
fixed | +1.636 |
BAT | +1.620 |
Neg logit contributions | |
uity | -2.371 |
swaps | -2.310 |
risis | -2.307 |
millenn | -2.304 |
anguage | -2.242 |
Token | way |
Token ID | 835 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ット | +1.152 |
fil | +1.130 |
ignore | +1.016 |
fixed | +1.001 |
BAT | +0.994 |
Neg logit contributions | |
uity | -1.249 |
swaps | -1.220 |
risis | -1.213 |
millenn | -1.201 |
anguage | -1.174 |
Token | this |
Token ID | 428 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ット | +4.038 |
fil | +4.030 |
fixed | +3.562 |
ignore | +3.533 |
HMS | +3.434 |
Neg logit contributions | |
uity | -5.733 |
risis | -5.643 |
millenn | -5.618 |
anguage | -5.513 |
swaps | -5.489 |
Token | administration |
Token ID | 3662 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
uity | +2.588 |
swaps | +2.514 |
risis | +2.470 |
millenn | +2.455 |
ancial | +2.349 |
Neg logit contributions | |
ット | -3.375 |
fil | -3.297 |
ignore | -3.019 |
fixed | -2.999 |
BAT | -2.976 |
Token | . |
Token ID | 13 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
uity | +1.765 |
swaps | +1.735 |
risis | +1.715 |
millenn | +1.670 |
anguage | +1.653 |
Neg logit contributions | |
ット | -1.408 |
fil | -1.365 |
ignore | -1.220 |
fixed | -1.202 |
BAT | -1.197 |
Token | Sub |
Token ID | 3834 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
uity | +0.297 |
swaps | +0.289 |
risis | +0.288 |
millenn | +0.282 |
anguage | +0.277 |
Neg logit contributions | |
ット | -0.309 |
fil | -0.303 |
ignore | -0.275 |
fixed | -0.271 |
BAT | -0.269 |
Token | sequently |
Token ID | 20415 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
uity | +1.505 |
swaps | +1.462 |
risis | +1.452 |
millenn | +1.404 |
oute | +1.394 |
Neg logit contributions | |
ット | -1.732 |
fil | -1.677 |
ignore | -1.538 |
BAT | -1.519 |
fixed | -1.508 |
Token | , |
Token ID | 11 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
uity | +1.863 |
swaps | +1.826 |
risis | +1.811 |
millenn | +1.791 |
oute | +1.751 |
Neg logit contributions | |
ット | -1.338 |
fil | -1.307 |
ignore | -1.159 |
fixed | -1.137 |
BAT | -1.136 |
Token | Elijah |
Token ID | 38646 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
uity | +0.143 |
swaps | +0.139 |
risis | +0.138 |
millenn | +0.136 |
anguage | +0.132 |
Neg logit contributions | |
ット | -0.184 |
fil | -0.181 |
ignore | -0.165 |
fixed | -0.163 |
BAT | -0.162 |
Token | Cummings |
Token ID | 38154 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
uity | +11.471 |
swaps | +11.314 |
oute | +10.828 |
risis | +10.694 |
azer | +10.426 |
Neg logit contributions | |
ット | -11.904 |
fil | -11.452 |
fixed | -11.062 |
ignore | -10.788 |
intention | -10.704 |
Token | , |
Token ID | 11 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
uity | +1.483 |
swaps | +1.458 |
risis | +1.446 |
millenn | +1.412 |
anguage | +1.392 |
Neg logit contributions | |
ット | -1.167 |
fil | -1.131 |
ignore | -1.015 |
fixed | -1.002 |
BAT | -0.989 |
Token | the |
Token ID | 262 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ット | +0.854 |
fil | +0.841 |
ignore | +0.751 |
fixed | +0.739 |
BAT | +0.738 |
Neg logit contributions | |
uity | -0.949 |
swaps | -0.927 |
risis | -0.919 |
millenn | -0.918 |
anguage | -0.894 |
Token | ranking |
Token ID | 12759 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ット | +2.151 |
fil | +2.142 |
ignore | +1.899 |
BAT | +1.884 |
fixed | +1.867 |
Neg logit contributions | |
uity | -2.198 |
millenn | -2.134 |
swaps | -2.131 |
risis | -2.114 |
anguage | -2.074 |
Token | member |
Token ID | 2888 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ット | +1.842 |
fil | +1.830 |
ignore | +1.653 |
fixed | +1.644 |
BAT | +1.634 |
Neg logit contributions | |
uity | -1.407 |
swaps | -1.361 |
risis | -1.356 |
millenn | -1.350 |
anguage | -1.316 |
Token | fel |
Token ID | 10756 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ット | +1.361 |
fil | +1.348 |
ignore | +1.215 |
fixed | +1.190 |
BAT | +1.189 |
Neg logit contributions | |
uity | -1.394 |
swaps | -1.354 |
risis | -1.353 |
millenn | -1.330 |
anguage | -1.315 |
Token | |
Token ID | 3907 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
uity | +3.415 |
swaps | +3.327 |
risis | +3.311 |
aith | +3.201 |
anguage | +3.163 |
Neg logit contributions | |
ット | -4.002 |
fil | -3.795 |
fixed | -3.548 |
ignore | -3.506 |
HMS | -3.490 |
Token | low |
Token ID | 9319 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
uity | +2.423 |
risis | +2.330 |
ancial | +2.293 |
swaps | +2.291 |
anguage | +2.273 |
Neg logit contributions | |
ット | -2.483 |
fil | -2.310 |
HMS | -2.136 |
ignore | -2.111 |
fixed | -2.109 |
Token | Demo |
Token ID | 34588 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
uity | +1.333 |
swaps | +1.305 |
risis | +1.295 |
millenn | +1.278 |
anguage | +1.249 |
Neg logit contributions | |
ット | -1.258 |
fil | -1.225 |
ignore | -1.105 |
fixed | -1.096 |
BAT | -1.087 |
Token | |
Token ID | 3907 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
uity | +0.585 |
swaps | +0.571 |
risis | +0.568 |
millenn | +0.557 |
oute | +0.544 |
Neg logit contributions | |
ット | -0.665 |
fil | -0.651 |
ignore | -0.593 |
fixed | -0.587 |
BAT | -0.582 |
Token | cr |
Token ID | 6098 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
uity | +5.352 |
risis | +5.097 |
oute | +4.985 |
aith | +4.864 |
swaps | +4.842 |
Neg logit contributions | |
ット | -7.433 |
HMS | -6.909 |
fil | -6.819 |
Mermaid | -6.494 |
fixed | -6.475 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
uity | +10.819 |
risis | +10.352 |
oute | +10.218 |
aith | +10.051 |
swaps | +9.924 |
Neg logit contributions | |
ット | -8.942 |
fil | -8.165 |
fixed | -7.951 |
HMS | -7.678 |
ignore | -7.668 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
uity | +3.866 |
swaps | +3.797 |
risis | +3.762 |
millenn | +3.660 |
ּ | +3.641 |
Neg logit contributions | |
ット | -3.325 |
fil | -3.193 |
fixed | -2.890 |
BAT | -2.842 |
ignore | -2.838 |
Token | At |
Token ID | 1629 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ット | +0.689 |
fil | +0.678 |
ignore | +0.611 |
fixed | +0.599 |
BAT | +0.599 |
Neg logit contributions | |
uity | -0.717 |
swaps | -0.701 |
risis | -0.696 |
millenn | -0.694 |
anguage | -0.676 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
uity | +3.678 |
swaps | +3.626 |
risis | +3.579 |
millenn | +3.513 |
oute | +3.455 |
Neg logit contributions | |
ット | -3.711 |
fil | -3.551 |
ignore | -3.236 |
fixed | -3.226 |
BAT | -3.174 |
Token | party |
Token ID | 2151 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
swaps | +3.720 |
uity | +3.711 |
risis | +3.609 |
millenn | +3.576 |
oute | +3.485 |
Neg logit contributions | |
ット | -4.135 |
fil | -3.887 |
ignore | -3.596 |
fixed | -3.577 |
BAT | -3.496 |
Token | on |
Token ID | 319 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
uity | +0.497 |
swaps | +0.489 |
risis | +0.481 |
millenn | +0.476 |
oute | +0.464 |
Neg logit contributions | |
ット | -0.539 |
fil | -0.526 |
ignore | -0.476 |
fixed | -0.471 |
BAT | -0.470 |
Token | foreign |
Token ID | 3215 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ット | +0.554 |
fil | +0.546 |
ignore | +0.493 |
fixed | +0.487 |
BAT | +0.482 |
Neg logit contributions | |
uity | -0.547 |
swaps | -0.532 |
risis | -0.531 |
millenn | -0.523 |
anguage | -0.514 |
Token | policy |
Token ID | 2450 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
uity | +0.362 |
swaps | +0.353 |
risis | +0.347 |
millenn | +0.342 |
anguage | +0.330 |
Neg logit contributions | |
ット | -0.663 |
fil | -0.653 |
ignore | -0.604 |
fixed | -0.598 |
BAT | -0.597 |
Token | -- |
Token ID | 1377 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
uity | +1.815 |
swaps | +1.799 |
risis | +1.769 |
millenn | +1.761 |
oute | +1.709 |
Neg logit contributions | |
ット | -1.427 |
fil | -1.383 |
ignore | -1.221 |
BAT | -1.210 |
fixed | -1.208 |
Token | another |
Token ID | 1194 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
uity | +1.848 |
swaps | +1.822 |
risis | +1.778 |
millenn | +1.763 |
oute | +1.729 |
Neg logit contributions | |
ット | -1.821 |
fil | -1.763 |
ignore | -1.581 |
BAT | -1.574 |
fixed | -1.572 |
Token | Carter |
Token ID | 10831 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
uity | +2.518 |
swaps | +2.481 |
millenn | +2.423 |
risis | +2.418 |
oute | +2.327 |
Neg logit contributions | |
ット | -2.845 |
fil | -2.730 |
ignore | -2.491 |
fixed | -2.452 |
BAT | -2.442 |
Token | weak |
Token ID | 4939 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
uity | +10.145 |
risis | +9.545 |
swaps | +9.462 |
citizenship | +9.281 |
oute | +9.279 |
Neg logit contributions | |
ット | -9.337 |
fil | -8.976 |
BAT | -8.220 |
HMS | -7.986 |
ignore | -7.943 |
Token | point |
Token ID | 966 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uity | +1.389 |
swaps | +1.345 |
risis | +1.342 |
millenn | +1.315 |
anguage | +1.290 |
Neg logit contributions | |
ット | -1.486 |
fil | -1.447 |
ignore | -1.315 |
fixed | -1.296 |
BAT | -1.292 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
uity | +4.753 |
swaps | +4.671 |
risis | +4.569 |
ּ | +4.430 |
oute | +4.389 |
Neg logit contributions | |
ット | -4.184 |
fil | -4.003 |
BAT | -3.577 |
ignore | -3.506 |
Boss | -3.483 |
Token | Obama |
Token ID | 2486 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
uity | +3.859 |
swaps | +3.819 |
risis | +3.720 |
millenn | +3.654 |
oute | +3.585 |
Neg logit contributions | |
ット | -5.184 |
fil | -4.993 |
BAT | -4.597 |
ignore | -4.534 |
fixed | -4.533 |
Token | also |
Token ID | 635 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
swaps | +4.292 |
uity | +4.224 |
risis | +3.952 |
urches | +3.822 |
citizenship | +3.793 |
Neg logit contributions | |
ット | -5.692 |
fil | -5.427 |
BAT | -5.022 |
ignore | -4.986 |
fixed | -4.893 |
Token | Leave |
Token ID | 35087 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ット | +1.000 |
fil | +0.984 |
ignore | +0.887 |
fixed | +0.878 |
BAT | +0.868 |
Neg logit contributions | |
uity | -1.032 |
swaps | -1.016 |
millenn | -1.010 |
risis | -1.006 |
anguage | -0.974 |
Token | a |
Token ID | 257 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
uity | +1.217 |
swaps | +1.200 |
risis | +1.180 |
millenn | +1.167 |
anguage | +1.143 |
Neg logit contributions | |
ット | -1.139 |
fil | -1.113 |
ignore | -1.006 |
BAT | -0.990 |
fixed | -0.986 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ット | +0.011 |
fil | +0.011 |
ignore | +0.010 |
fixed | +0.010 |
BAT | +0.010 |
Neg logit contributions | |
uity | -0.015 |
swaps | -0.015 |
risis | -0.015 |
millenn | -0.015 |
anguage | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
uity | +4.717 |
swaps | +4.635 |
risis | +4.570 |
anguage | +4.444 |
oute | +4.428 |
Neg logit contributions | |
ット | -3.655 |
fil | -3.471 |
ignore | -3.108 |
BAT | -3.045 |
fixed | -3.025 |
Token | By |
Token ID | 3886 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uity | +2.750 |
risis | +2.669 |
swaps | +2.637 |
oute | +2.590 |
anguage | +2.566 |
Neg logit contributions | |
ット | -2.384 |
fil | -2.260 |
ignore | -2.034 |
HMS | -2.032 |
fixed | -1.984 |
Token | Dominic |
Token ID | 36401 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
uity | +3.604 |
swaps | +3.512 |
risis | +3.484 |
millenn | +3.441 |
oute | +3.350 |
Neg logit contributions | |
ット | -3.481 |
fil | -3.356 |
ignore | -3.053 |
fixed | -3.010 |
BAT | -2.998 |
Token | Laurie |
Token ID | 40811 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
uity | +9.412 |
swaps | +9.030 |
risis | +8.905 |
oute | +8.894 |
aith | +8.804 |
Neg logit contributions | |
ット | -9.316 |
fil | -8.829 |
fixed | -8.272 |
ignore | -8.089 |
BAT | -7.890 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
uity | +0.089 |
swaps | +0.087 |
risis | +0.087 |
millenn | +0.085 |
anguage | +0.084 |
Neg logit contributions | |
ット | -0.073 |
fil | -0.071 |
ignore | -0.064 |
fixed | -0.063 |
BAT | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ット | +0.074 |
fil | +0.072 |
ignore | +0.064 |
fixed | +0.064 |
BAT | +0.063 |
Neg logit contributions | |
uity | -0.091 |
swaps | -0.088 |
risis | -0.088 |
oute | -0.085 |
ּ | -0.084 |
Token | Europe |
Token ID | 16112 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
uity | +0.078 |
risis | +0.076 |
swaps | +0.076 |
millenn | +0.074 |
anguage | +0.073 |
Neg logit contributions | |
ット | -0.069 |
fil | -0.067 |
ignore | -0.060 |
fixed | -0.059 |
HMS | -0.059 |
Token | business |
Token ID | 1597 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
uity | +2.309 |
swaps | +2.280 |
risis | +2.268 |
millenn | +2.198 |
anguage | +2.154 |
Neg logit contributions | |
ット | -2.509 |
fil | -2.459 |
ignore | -2.233 |
fixed | -2.216 |
BAT | -2.187 |
Token | Arab |
Token ID | 4498 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
uity | +0.342 |
swaps | +0.337 |
risis | +0.332 |
millenn | +0.328 |
anguage | +0.319 |
Neg logit contributions | |
ット | -0.366 |
fil | -0.357 |
ignore | -0.325 |
fixed | -0.320 |
BAT | -0.319 |
Token | League |
Token ID | 4041 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
swaps | +3.520 |
uity | +3.479 |
risis | +3.455 |
oute | +3.294 |
anguage | +3.264 |
Neg logit contributions | |
ット | -4.334 |
fil | -4.209 |
ignore | -3.912 |
BAT | -3.875 |
fixed | -3.850 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
uity | +0.816 |
swaps | +0.801 |
risis | +0.791 |
millenn | +0.778 |
anguage | +0.764 |
Neg logit contributions | |
ット | -0.904 |
fil | -0.884 |
ignore | -0.800 |
fixed | -0.792 |
BAT | -0.790 |
Token | Organisation |
Token ID | 30801 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uity | +0.900 |
swaps | +0.884 |
risis | +0.873 |
millenn | +0.862 |
anguage | +0.840 |
Neg logit contributions | |
ット | -0.944 |
fil | -0.916 |
ignore | -0.831 |
fixed | -0.820 |
BAT | -0.819 |
Token | of |
Token ID | 286 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
uity | +0.627 |
swaps | +0.618 |
risis | +0.612 |
millenn | +0.606 |
anguage | +0.589 |
Neg logit contributions | |
ット | -0.534 |
fil | -0.520 |
ignore | -0.468 |
fixed | -0.458 |
BAT | -0.456 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
uity | +1.302 |
swaps | +1.274 |
risis | +1.274 |
millenn | +1.237 |
oute | +1.221 |
Neg logit contributions | |
ット | -1.517 |
fil | -1.468 |
ignore | -1.347 |
BAT | -1.336 |
fixed | -1.323 |
Token | Co |
Token ID | 1766 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
uity | +7.457 |
swaps | +6.968 |
risis | +6.623 |
oute | +6.542 |
aith | +6.473 |
Neg logit contributions | |
ット | -12.105 |
fil | -11.472 |
Boss | -11.245 |
BAT | -11.219 |
ignore | -11.208 |
Token | - |
Token ID | 12 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ット | +1.349 |
fil | +1.315 |
ignore | +1.128 |
fixed | +1.104 |
BAT | +1.093 |
Neg logit contributions | |
uity | -2.557 |
swaps | -2.513 |
risis | -2.499 |
millenn | -2.479 |
anguage | -2.435 |
Token | operation |
Token ID | 27184 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uity | +1.888 |
risis | +1.847 |
swaps | +1.847 |
millenn | +1.820 |
anguage | +1.781 |
Neg logit contributions | |
ット | -1.371 |
fil | -1.298 |
ignore | -1.194 |
BAT | -1.156 |
fixed | -1.143 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
uity | +0.434 |
swaps | +0.426 |
risis | +0.423 |
millenn | +0.417 |
anguage | +0.408 |
Neg logit contributions | |
ット | -0.410 |
fil | -0.401 |
ignore | -0.361 |
fixed | -0.357 |
BAT | -0.354 |
Token | Gulf |
Token ID | 12108 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
uity | +0.648 |
swaps | +0.636 |
risis | +0.627 |
millenn | +0.616 |
anguage | +0.604 |
Neg logit contributions | |
ット | -0.643 |
fil | -0.623 |
ignore | -0.567 |
fixed | -0.557 |
BAT | -0.556 |
Token | radical |
Token ID | 7702 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
ット | +0.666 |
fil | +0.654 |
ignore | +0.596 |
fixed | +0.588 |
BAT | +0.585 |
Neg logit contributions | |
uity | -0.562 |
swaps | -0.548 |
risis | -0.543 |
millenn | -0.537 |
anguage | -0.523 |
Token | Islamists |
Token ID | 34434 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uity | +1.814 |
swaps | +1.779 |
millenn | +1.740 |
risis | +1.740 |
oute | +1.686 |
Neg logit contributions | |
ット | -2.067 |
fil | -2.010 |
ignore | -1.841 |
fixed | -1.822 |
BAT | -1.814 |
Token | ( |
Token ID | 357 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
uity | +4.361 |
swaps | +4.341 |
risis | +4.180 |
oute | +4.063 |
livest | +4.053 |
Neg logit contributions | |
ット | -4.565 |
fil | -4.273 |
BAT | -3.942 |
ignore | -3.931 |
Boss | -3.873 |
Token | wh |
Token ID | 1929 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ット | +0.304 |
fil | +0.294 |
ignore | +0.260 |
fixed | +0.255 |
BAT | +0.253 |
Neg logit contributions | |
uity | -0.446 |
swaps | -0.436 |
risis | -0.434 |
millenn | -0.430 |
anguage | -0.422 |
Token | om |
Token ID | 296 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
uity | +3.367 |
swaps | +3.233 |
risis | +3.226 |
anguage | +3.084 |
oute | +3.081 |
Neg logit contributions | |
ット | -4.373 |
fil | -4.221 |
BAT | -3.881 |
fixed | -3.833 |
ignore | -3.818 |
Token | Carter |
Token ID | 10831 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ット | +0.574 |
fil | +0.567 |
ignore | +0.521 |
fixed | +0.515 |
BAT | +0.510 |
Neg logit contributions | |
uity | -0.389 |
swaps | -0.376 |
risis | -0.375 |
millenn | -0.369 |
anguage | -0.360 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
swaps | +9.478 |
uity | +9.270 |
citizenship | +8.508 |
risis | +8.409 |
oute | +8.322 |
Neg logit contributions | |
ット | -9.798 |
fil | -8.762 |
BAT | -8.545 |
Boss | -8.207 |
Fish | -8.095 |
Token | of |
Token ID | 286 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
uity | +3.827 |
swaps | +3.804 |
risis | +3.659 |
millenn | +3.648 |
oute | +3.514 |
Neg logit contributions | |
ット | -4.696 |
fil | -4.420 |
ignore | -4.153 |
BAT | -4.061 |
fixed | -4.045 |
Token | as |
Token ID | 355 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
uity | +2.975 |
swaps | +2.947 |
risis | +2.868 |
millenn | +2.866 |
oute | +2.812 |
Neg logit contributions | |
ット | -2.520 |
fil | -2.418 |
ignore | -2.172 |
BAT | -2.153 |
fixed | -2.148 |
Token | " |
Token ID | 366 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
ット | +1.529 |
fil | +1.521 |
ignore | +1.355 |
fixed | +1.342 |
BAT | +1.335 |
Neg logit contributions | |
uity | -1.657 |
risis | -1.615 |
swaps | -1.611 |
millenn | -1.585 |
anguage | -1.569 |
Token | re |
Token ID | 260 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
fil | +2.082 |
ット | +2.065 |
ignore | +1.834 |
fixed | +1.821 |
BAT | +1.794 |
Neg logit contributions | |
uity | -2.635 |
swaps | -2.600 |
risis | -2.569 |
millenn | -2.560 |
anguage | -2.507 |
Token | The |
Token ID | 383 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
uity | +3.104 |
risis | +2.986 |
swaps | +2.959 |
ּ | +2.844 |
oute | +2.842 |
Neg logit contributions | |
ット | -3.208 |
fil | -3.057 |
ignore | -2.849 |
fixed | -2.844 |
above | -2.729 |
Token | year |
Token ID | 614 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
uity | +0.730 |
swaps | +0.716 |
risis | +0.707 |
millenn | +0.702 |
oute | +0.679 |
Neg logit contributions | |
ット | -0.824 |
fil | -0.800 |
ignore | -0.735 |
fixed | -0.724 |
BAT | -0.717 |
Token | of |
Token ID | 286 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ット | +2.976 |
fil | +2.948 |
ignore | +2.572 |
HMS | +2.530 |
BAT | +2.528 |
Neg logit contributions | |
uity | -3.850 |
swaps | -3.799 |
risis | -3.788 |
millenn | -3.744 |
anguage | -3.695 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
uity | +1.264 |
swaps | +1.235 |
risis | +1.223 |
millenn | +1.202 |
oute | +1.178 |
Neg logit contributions | |
ット | -1.206 |
fil | -1.167 |
ignore | -1.062 |
fixed | -1.049 |
BAT | -1.036 |
Token | first |
Token ID | 717 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
uity | +0.901 |
swaps | +0.890 |
risis | +0.878 |
millenn | +0.866 |
oute | +0.846 |
Neg logit contributions | |
ット | -0.884 |
fil | -0.861 |
ignore | -0.784 |
fixed | -0.771 |
BAT | -0.763 |
Token | lunar |
Token ID | 25572 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
uity | +3.956 |
swaps | +3.906 |
risis | +3.858 |
millenn | +3.808 |
oute | +3.706 |
Neg logit contributions | |
ット | -3.794 |
fil | -3.634 |
ignore | -3.369 |
fixed | -3.332 |
BAT | -3.303 |
Token | landing |
Token ID | 9581 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
swaps | +8.297 |
uity | +8.048 |
risis | +7.922 |
citizenship | +7.544 |
oute | +7.505 |
Neg logit contributions | |
ット | -10.506 |
fil | -10.006 |
sweet | -9.487 |
ignore | -9.422 |
BAT | -9.328 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
uity | +3.996 |
swaps | +3.972 |
risis | +3.870 |
oute | +3.752 |
millenn | +3.699 |
Neg logit contributions | |
ット | -3.651 |
fil | -3.445 |
ignore | -3.116 |
BAT | -3.100 |
fixed | -3.046 |
Token |
|
Token ID | 198 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
uity | +1.360 |
risis | +1.323 |
swaps | +1.319 |
millenn | +1.277 |
oute | +1.266 |
Neg logit contributions | |
ット | -1.181 |
fil | -1.142 |
ignore | -1.033 |
fixed | -1.025 |
BAT | -1.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
uity | +0.329 |
swaps | +0.320 |
risis | +0.318 |
oute | +0.307 |
ּ | +0.305 |
Neg logit contributions | |
ット | -0.281 |
fil | -0.270 |
ignore | -0.242 |
fixed | -0.239 |
BAT | -0.237 |
Token | SP |
Token ID | 4303 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
uity | +0.499 |
risis | +0.487 |
swaps | +0.485 |
millenn | +0.472 |
oute | +0.469 |
Neg logit contributions | |
ット | -0.384 |
fil | -0.371 |
ignore | -0.331 |
fixed | -0.326 |
HMS | -0.320 |
Token | in |
Token ID | 287 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ット | +0.858 |
fil | +0.836 |
ignore | +0.756 |
fixed | +0.744 |
BAT | +0.739 |
Neg logit contributions | |
uity | -0.905 |
swaps | -0.889 |
risis | -0.878 |
millenn | -0.870 |
anguage | -0.849 |
Token | Gr |
Token ID | 1902 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
ット | +1.109 |
fil | +1.086 |
ignore | +0.976 |
fixed | +0.961 |
BAT | +0.954 |
Neg logit contributions | |
uity | -1.238 |
swaps | -1.212 |
risis | -1.204 |
millenn | -1.191 |
anguage | -1.164 |
Token | ims |
Token ID | 12078 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
uity | +2.663 |
risis | +2.589 |
swaps | +2.534 |
oute | +2.521 |
aith | +2.502 |
Neg logit contributions | |
ット | -2.841 |
fil | -2.682 |
ignore | -2.442 |
BAT | -2.435 |
fixed | -2.434 |
Token | by |
Token ID | 1525 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
ット | +1.221 |
fil | +1.219 |
ignore | +1.063 |
fixed | +1.049 |
BAT | +1.034 |
Neg logit contributions | |
uity | -1.810 |
swaps | -1.784 |
millenn | -1.770 |
risis | -1.769 |
anguage | -1.724 |
Token | an |
Token ID | 281 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ット | +0.256 |
fil | +0.251 |
ignore | +0.224 |
fixed | +0.221 |
BAT | +0.219 |
Neg logit contributions | |
uity | -0.308 |
swaps | -0.302 |
risis | -0.299 |
millenn | -0.296 |
anguage | -0.290 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
uity | +0.581 |
swaps | +0.569 |
risis | +0.566 |
millenn | +0.557 |
anguage | +0.545 |
Neg logit contributions | |
ット | -0.567 |
fil | -0.555 |
ignore | -0.501 |
BAT | -0.497 |
fixed | -0.494 |
Token | Cultural |
Token ID | 23897 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uity | +8.445 |
swaps | +8.343 |
citizenship | +8.197 |
millenn | +8.186 |
aith | +8.161 |
Neg logit contributions | |
ット | -9.628 |
fil | -9.279 |
ignore | -8.551 |
fixed | -8.536 |
BAT | -8.420 |
Token | Centre |
Token ID | 9072 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
uity | +3.723 |
swaps | +3.684 |
risis | +3.623 |
millenn | +3.548 |
oute | +3.471 |
Neg logit contributions | |
ット | -3.414 |
fil | -3.326 |
ignore | -3.023 |
fixed | -2.974 |
BAT | -2.916 |
Token | was |
Token ID | 373 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
uity | +1.191 |
swaps | +1.175 |
risis | +1.154 |
millenn | +1.136 |
anguage | +1.105 |
Neg logit contributions | |
ット | -1.482 |
fil | -1.437 |
ignore | -1.320 |
fixed | -1.296 |
BAT | -1.291 |
Token | fire |
Token ID | 2046 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uity | +0.646 |
swaps | +0.637 |
risis | +0.627 |
millenn | +0.617 |
anguage | +0.604 |
Neg logit contributions | |
ット | -0.612 |
fil | -0.592 |
ignore | -0.539 |
BAT | -0.525 |
fixed | -0.525 |
Token | bomb |
Token ID | 27657 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
uity | +0.320 |
swaps | +0.312 |
risis | +0.304 |
millenn | +0.286 |
anguage | +0.276 |
Neg logit contributions | |
ット | -0.844 |
fil | -0.822 |
ignore | -0.773 |
Boss | -0.760 |
fixed | -0.756 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
uity | +0.848 |
swaps | +0.833 |
risis | +0.825 |
millenn | +0.802 |
oute | +0.798 |
Neg logit contributions | |
ット | -0.704 |
fil | -0.687 |
ignore | -0.617 |
fixed | -0.604 |
BAT | -0.599 |
Token | of |
Token ID | 286 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
uity | +3.885 |
swaps | +3.768 |
risis | +3.725 |
ּ | +3.633 |
oute | +3.599 |
Neg logit contributions | |
ット | -4.015 |
fil | -3.834 |
ignore | -3.590 |
fixed | -3.493 |
BAT | -3.473 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
uity | +1.375 |
swaps | +1.363 |
risis | +1.340 |
ּ | +1.298 |
oute | +1.287 |
Neg logit contributions | |
ット | -1.305 |
fil | -1.259 |
ignore | -1.158 |
fixed | -1.136 |
BAT | -1.109 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
uity | +0.341 |
swaps | +0.335 |
risis | +0.333 |
millenn | +0.329 |
anguage | +0.323 |
Neg logit contributions | |
ット | -0.191 |
fil | -0.185 |
ignore | -0.160 |
fixed | -0.157 |
BAT | -0.155 |
Token | : |
Token ID | 25 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
uity | +0.039 |
swaps | +0.038 |
risis | +0.038 |
millenn | +0.038 |
anguage | +0.036 |
Neg logit contributions | |
ット | -0.047 |
fil | -0.046 |
ignore | -0.042 |
fixed | -0.041 |
BAT | -0.041 |
Token | Carly |
Token ID | 35982 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
uity | +1.985 |
risis | +1.961 |
swaps | +1.950 |
millenn | +1.869 |
ּ | +1.863 |
Neg logit contributions | |
ット | -1.802 |
fil | -1.756 |
ignore | -1.609 |
fixed | -1.594 |
BAT | -1.552 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
uity | +6.189 |
swaps | +6.184 |
risis | +5.892 |
millenn | +5.661 |
oute | +5.606 |
Neg logit contributions | |
ット | -12.274 |
fil | -11.522 |
ignore | -11.060 |
fixed | -10.905 |
BAT | -10.725 |
Token | 's |
Token ID | 338 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
uity | +2.406 |
swaps | +2.404 |
risis | +2.343 |
millenn | +2.293 |
oute | +2.231 |
Neg logit contributions | |
ット | -2.631 |
fil | -2.543 |
ignore | -2.322 |
fixed | -2.305 |
BAT | -2.290 |
Token | political |
Token ID | 1964 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
uity | +2.000 |
swaps | +1.989 |
risis | +1.956 |
millenn | +1.931 |
oute | +1.868 |
Neg logit contributions | |
ット | -2.287 |
fil | -2.227 |
ignore | -2.043 |
fixed | -2.016 |
BAT | -2.005 |
Token | career |
Token ID | 3451 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
uity | +1.769 |
swaps | +1.742 |
risis | +1.711 |
millenn | +1.692 |
oute | +1.640 |
Neg logit contributions | |
ット | -2.210 |
fil | -2.147 |
ignore | -1.968 |
fixed | -1.952 |
BAT | -1.939 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
uity | +2.121 |
swaps | +2.088 |
risis | +2.073 |
millenn | +2.009 |
oute | +1.958 |
Neg logit contributions | |
ット | -2.818 |
fil | -2.761 |
ignore | -2.547 |
fixed | -2.520 |
BAT | -2.494 |
Token | � |
Token ID | 247 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
uity | +0.969 |
swaps | +0.917 |
risis | +0.912 |
millenn | +0.910 |
ּ | +0.872 |
Neg logit contributions | |
ット | -2.117 |
fil | -2.088 |
ignore | -1.934 |
BAT | -1.920 |
HMS | -1.919 |
Token | ve |
Token ID | 303 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
uity | +0.867 |
swaps | +0.845 |
risis | +0.844 |
millenn | +0.831 |
oute | +0.817 |
Neg logit contributions | |
ット | -0.693 |
fil | -0.671 |
ignore | -0.598 |
BAT | -0.589 |
fixed | -0.588 |
Token | said |
Token ID | 531 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
ット | +0.781 |
fil | +0.766 |
ignore | +0.690 |
fixed | +0.680 |
BAT | +0.675 |
Neg logit contributions | |
uity | -0.828 |
swaps | -0.810 |
risis | -0.804 |
millenn | -0.795 |
anguage | -0.778 |
Token | for |
Token ID | 329 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ット | +2.183 |
fil | +2.155 |
ignore | +1.926 |
fixed | +1.878 |
BAT | +1.864 |
Neg logit contributions | |
uity | -2.808 |
risis | -2.748 |
swaps | -2.737 |
millenn | -2.735 |
anguage | -2.656 |
Token | a |
Token ID | 257 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ット | +1.068 |
fil | +1.051 |
ignore | +0.957 |
fixed | +0.945 |
BAT | +0.938 |
Neg logit contributions | |
uity | -0.903 |
swaps | -0.880 |
risis | -0.874 |
millenn | -0.863 |
anguage | -0.842 |
Token | couple |
Token ID | 3155 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
uity | +2.335 |
swaps | +2.274 |
risis | +2.256 |
millenn | +2.248 |
ּ | +2.158 |
Neg logit contributions | |
ット | -2.472 |
fil | -2.392 |
ignore | -2.189 |
fixed | -2.148 |
BAT | -2.134 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
swaps | +7.953 |
uity | +7.759 |
millenn | +7.482 |
risis | +7.332 |
ּ | +7.291 |
Neg logit contributions | |
ット | -10.219 |
fil | -9.628 |
ignore | -9.033 |
BAT | -8.833 |
HMS | -8.827 |
Token | years |
Token ID | 812 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
swaps | +3.858 |
uity | +3.741 |
millenn | +3.646 |
risis | +3.619 |
oute | +3.434 |
Neg logit contributions | |
ット | -6.762 |
fil | -6.502 |
ignore | -6.019 |
BAT | -5.973 |
fixed | -5.969 |
Token | I |
Token ID | 314 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ット | +0.106 |
fil | +0.103 |
ignore | +0.092 |
fixed | +0.091 |
BAT | +0.090 |
Neg logit contributions | |
uity | -0.128 |
swaps | -0.125 |
risis | -0.124 |
millenn | -0.123 |
anguage | -0.121 |
Token | would |
Token ID | 561 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ット | +1.513 |
fil | +1.489 |
ignore | +1.353 |
fixed | +1.330 |
BAT | +1.320 |
Neg logit contributions | |
uity | -1.423 |
swaps | -1.390 |
risis | -1.380 |
millenn | -1.378 |
anguage | -1.334 |
Token | love |
Token ID | 1842 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
uity | +2.392 |
swaps | +2.341 |
risis | +2.319 |
ּ | +2.257 |
oute | +2.242 |
Neg logit contributions | |
ット | -2.215 |
fil | -2.144 |
fixed | -1.922 |
BAT | -1.907 |
ignore | -1.902 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ット | +0.588 |
fil | +0.574 |
ignore | +0.518 |
fixed | +0.509 |
BAT | +0.505 |
Neg logit contributions | |
uity | -0.645 |
swaps | -0.633 |
risis | -0.627 |
millenn | -0.606 |
oute | -0.605 |
Token | of |
Token ID | 286 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
uity | +1.743 |
swaps | +1.694 |
risis | +1.676 |
ּ | +1.624 |
oute | +1.613 |
Neg logit contributions | |
ット | -1.682 |
fil | -1.614 |
ignore | -1.467 |
fixed | -1.450 |
BAT | -1.450 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
uity | +1.553 |
swaps | +1.528 |
risis | +1.496 |
aith | +1.452 |
oute | +1.436 |
Neg logit contributions | |
ット | -1.726 |
fil | -1.654 |
ignore | -1.529 |
fixed | -1.520 |
BAT | -1.480 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
uity | +0.404 |
swaps | +0.397 |
risis | +0.392 |
oute | +0.382 |
ּ | +0.380 |
Neg logit contributions | |
ット | -0.237 |
fil | -0.228 |
ignore | -0.200 |
fixed | -0.197 |
BAT | -0.191 |
Token | : |
Token ID | 25 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
uity | +0.615 |
swaps | +0.597 |
risis | +0.593 |
ּ | +0.564 |
oute | +0.564 |
Neg logit contributions | |
ット | -0.815 |
fil | -0.792 |
ignore | -0.728 |
fixed | -0.720 |
BAT | -0.716 |
Token | Carly |
Token ID | 35982 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
uity | +1.547 |
swaps | +1.507 |
risis | +1.506 |
oute | +1.418 |
ּ | +1.410 |
Neg logit contributions | |
ット | -2.059 |
fil | -2.023 |
ignore | -1.877 |
fixed | -1.861 |
BAT | -1.813 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
swaps | +3.344 |
uity | +3.338 |
risis | +2.904 |
oute | +2.628 |
citizenship | +2.539 |
Neg logit contributions | |
ット | -14.829 |
fil | -13.921 |
fixed | -13.476 |
ignore | -13.427 |
BAT | -13.333 |
Token | 's |
Token ID | 338 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
uity | +2.173 |
swaps | +2.158 |
risis | +2.106 |
oute | +2.011 |
citizenship | +1.987 |
Neg logit contributions | |
ット | -2.320 |
fil | -2.210 |
ignore | -2.021 |
fixed | -2.005 |
BAT | -1.999 |
Token | political |
Token ID | 1964 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
uity | +1.445 |
swaps | +1.414 |
risis | +1.390 |
citizenship | +1.311 |
oute | +1.299 |
Neg logit contributions | |
ット | -2.772 |
fil | -2.671 |
ignore | -2.495 |
fixed | -2.464 |
BAT | -2.464 |
Token | career |
Token ID | 3451 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
uity | +1.720 |
swaps | +1.653 |
risis | +1.637 |
millenn | +1.546 |
citizenship | +1.543 |
Neg logit contributions | |
ット | -3.028 |
fil | -2.926 |
ignore | -2.714 |
fixed | -2.702 |
BAT | -2.665 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
uity | +2.587 |
swaps | +2.481 |
risis | +2.479 |
oute | +2.256 |
urches | +2.250 |
Neg logit contributions | |
ット | -6.054 |
fil | -5.939 |
fixed | -5.615 |
ignore | -5.611 |
BAT | -5.465 |
Token | � |
Token ID | 447 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
uity | +1.538 |
risis | +1.492 |
swaps | +1.483 |
millenn | +1.438 |
oute | +1.438 |
Neg logit contributions | |
ット | -1.484 |
fil | -1.441 |
ignore | -1.306 |
fixed | -1.285 |
HMS | -1.283 |
Token | � |
Token ID | 250 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ット | +2.393 |
fil | +2.350 |
ignore | +2.165 |
fixed | +2.139 |
BAT | +2.132 |
Neg logit contributions | |
uity | -1.630 |
swaps | -1.596 |
millenn | -1.592 |
risis | -1.574 |
anguage | -1.520 |
Token | But |
Token ID | 1537 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
uity | +1.850 |
risis | +1.789 |
swaps | +1.785 |
oute | +1.737 |
millenn | +1.721 |
Neg logit contributions | |
ット | -1.729 |
fil | -1.679 |
ignore | -1.516 |
fixed | -1.493 |
HMS | -1.488 |
Token | in |
Token ID | 287 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
uity | +0.778 |
swaps | +0.762 |
risis | +0.756 |
millenn | +0.745 |
oute | +0.728 |
Neg logit contributions | |
ット | -0.725 |
fil | -0.708 |
ignore | -0.638 |
fixed | -0.629 |
BAT | -0.626 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
uity | +0.856 |
swaps | +0.842 |
risis | +0.833 |
millenn | +0.820 |
oute | +0.803 |
Neg logit contributions | |
ット | -0.859 |
fil | -0.838 |
ignore | -0.763 |
fixed | -0.752 |
BAT | -0.748 |
Token | couple |
Token ID | 3155 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
uity | +3.255 |
swaps | +3.220 |
risis | +3.185 |
millenn | +3.134 |
oute | +3.064 |
Neg logit contributions | |
ット | -3.980 |
fil | -3.833 |
ignore | -3.558 |
fixed | -3.492 |
HMS | -3.442 |
Token | of |
Token ID | 286 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
swaps | +8.036 |
uity | +7.829 |
millenn | +7.802 |
risis | +7.682 |
ּ | +7.541 |
Neg logit contributions | |
ット | -9.929 |
fil | -9.427 |
ignore | -9.133 |
fixed | -8.831 |
HMS | -8.794 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
swaps | +4.418 |
uity | +4.285 |
risis | +4.191 |
millenn | +4.136 |
oute | +4.108 |
Neg logit contributions | |
ット | -7.269 |
fil | -6.929 |
ignore | -6.548 |
fixed | -6.491 |
BAT | -6.355 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
uity | +5.000 |
swaps | +4.903 |
risis | +4.813 |
oute | +4.758 |
ּ | +4.712 |
Neg logit contributions | |
ット | -4.192 |
fil | -4.084 |
ignore | -3.668 |
fixed | -3.663 |
BAT | -3.600 |
Token | we |
Token ID | 356 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
uity | +0.737 |
swaps | +0.720 |
risis | +0.714 |
millenn | +0.705 |
oute | +0.688 |
Neg logit contributions | |
ット | -0.720 |
fil | -0.705 |
ignore | -0.637 |
fixed | -0.628 |
BAT | -0.624 |
Token | have |
Token ID | 423 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
uity | +0.857 |
swaps | +0.830 |
risis | +0.830 |
millenn | +0.806 |
anguage | +0.793 |
Neg logit contributions | |
ット | -1.031 |
fil | -1.012 |
ignore | -0.922 |
fixed | -0.916 |
BAT | -0.906 |
Token | 2003 |
Token ID | 5816 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
uity | +0.925 |
swaps | +0.915 |
risis | +0.905 |
millenn | +0.892 |
anguage | +0.872 |
Neg logit contributions | |
ット | -0.803 |
fil | -0.779 |
ignore | -0.703 |
fixed | -0.693 |
BAT | -0.685 |
Token | , |
Token ID | 11 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
ット | +2.563 |
fil | +2.543 |
ignore | +2.206 |
fixed | +2.154 |
BAT | +2.147 |
Neg logit contributions | |
uity | -3.953 |
millenn | -3.878 |
swaps | -3.872 |
risis | -3.847 |
oute | -3.766 |
Token | when |
Token ID | 618 |
Feature activation | -9.50e-03 |
Pos logit contributions | |
uity | +0.250 |
swaps | +0.246 |
risis | +0.244 |
millenn | +0.241 |
anguage | +0.236 |
Neg logit contributions | |
ット | -0.212 |
fil | -0.206 |
ignore | -0.185 |
fixed | -0.183 |
BAT | -0.181 |
Token | the |
Token ID | 262 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
uity | +0.034 |
swaps | +0.033 |
risis | +0.033 |
millenn | +0.033 |
anguage | +0.032 |
Neg logit contributions | |
ット | -0.031 |
fil | -0.031 |
ignore | -0.028 |
fixed | -0.027 |
BAT | -0.027 |
Token | National |
Token ID | 2351 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
uity | +0.991 |
swaps | +0.978 |
risis | +0.958 |
millenn | +0.939 |
oute | +0.914 |
Neg logit contributions | |
ット | -1.315 |
fil | -1.282 |
ignore | -1.176 |
fixed | -1.161 |
Boss | -1.150 |
Token | Slave |
Token ID | 38795 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
uity | +0.290 |
swaps | +0.286 |
risis | +0.283 |
millenn | +0.274 |
anguage | +0.271 |
Neg logit contributions | |
ット | -0.290 |
fil | -0.282 |
ignore | -0.256 |
fixed | -0.252 |
Boss | -0.248 |
Token | Memorial |
Token ID | 14861 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
uity | +8.451 |
risis | +8.231 |
swaps | +8.206 |
citizenship | +7.967 |
ancial | +7.951 |
Neg logit contributions | |
ット | -9.988 |
fil | -9.030 |
ignore | -8.712 |
above | -8.562 |
BAT | -8.306 |
Token | Act |
Token ID | 2191 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
uity | +3.026 |
swaps | +2.957 |
risis | +2.897 |
anguage | +2.812 |
millenn | +2.803 |
Neg logit contributions | |
ット | -3.461 |
fil | -3.334 |
ignore | -3.075 |
fixed | -3.040 |
Boss | -2.991 |
Token | was |
Token ID | 373 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
uity | +0.090 |
swaps | +0.088 |
risis | +0.087 |
millenn | +0.086 |
anguage | +0.084 |
Neg logit contributions | |
ット | -0.090 |
fil | -0.087 |
ignore | -0.079 |
fixed | -0.078 |
BAT | -0.078 |
Token | introduced |
Token ID | 5495 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
uity | +1.843 |
swaps | +1.816 |
risis | +1.770 |
millenn | +1.716 |
anguage | +1.703 |
Neg logit contributions | |
ット | -1.963 |
fil | -1.882 |
ignore | -1.747 |
Boss | -1.716 |
fixed | -1.706 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
uity | +2.080 |
swaps | +2.057 |
risis | +2.031 |
millenn | +1.969 |
anguage | +1.965 |
Neg logit contributions | |
ット | -1.687 |
fil | -1.630 |
ignore | -1.462 |
fixed | -1.449 |
Boss | -1.438 |
Token | of |
Token ID | 286 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ット | +0.452 |
fil | +0.444 |
ignore | +0.395 |
fixed | +0.387 |
BAT | +0.385 |
Neg logit contributions | |
uity | -0.577 |
swaps | -0.565 |
risis | -0.562 |
millenn | -0.558 |
anguage | -0.545 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
uity | +0.675 |
swaps | +0.656 |
risis | +0.652 |
millenn | +0.645 |
anguage | +0.628 |
Neg logit contributions | |
ット | -0.873 |
fil | -0.860 |
ignore | -0.786 |
fixed | -0.776 |
BAT | -0.772 |
Token | welfare |
Token ID | 9490 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
uity | +1.930 |
swaps | +1.894 |
risis | +1.860 |
millenn | +1.820 |
oute | +1.768 |
Neg logit contributions | |
ット | -2.903 |
fil | -2.832 |
ignore | -2.617 |
fixed | -2.587 |
Boss | -2.562 |
Token | state |
Token ID | 1181 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
uity | +2.640 |
swaps | +2.590 |
risis | +2.531 |
millenn | +2.458 |
ּ | +2.417 |
Neg logit contributions | |
ット | -3.614 |
fil | -3.487 |
ignore | -3.228 |
BAT | -3.198 |
fixed | -3.191 |
Token | since |
Token ID | 1201 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ット | +0.035 |
fil | +0.034 |
ignore | +0.030 |
fixed | +0.030 |
BAT | +0.029 |
Neg logit contributions | |
uity | -0.047 |
swaps | -0.046 |
risis | -0.046 |
millenn | -0.045 |
anguage | -0.044 |
Token | LB |
Token ID | 22199 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
uity | +1.681 |
swaps | +1.644 |
risis | +1.627 |
millenn | +1.605 |
anguage | +1.558 |
Neg logit contributions | |
ット | -2.123 |
fil | -2.082 |
ignore | -1.904 |
fixed | -1.883 |
BAT | -1.874 |
Token | J |
Token ID | 41 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
uity | +8.041 |
risis | +7.997 |
swaps | +7.937 |
aith | +7.888 |
citizenship | +7.602 |
Neg logit contributions | |
ット | -10.044 |
fil | -8.904 |
ignore | -8.773 |
fixed | -8.706 |
BAT | -8.618 |
Token | .) |
Token ID | 2014 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
uity | +1.096 |
swaps | +1.071 |
risis | +1.063 |
millenn | +1.045 |
ּ | +1.026 |
Neg logit contributions | |
ット | -0.874 |
fil | -0.852 |
ignore | -0.765 |
fixed | -0.751 |
BAT | -0.750 |
Token | What |
Token ID | 1867 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ット | +0.172 |
fil | +0.168 |
ignore | +0.152 |
fixed | +0.150 |
BAT | +0.149 |
Neg logit contributions | |
uity | -0.168 |
swaps | -0.164 |
risis | -0.163 |
millenn | -0.161 |
anguage | -0.157 |
Token | I |
Token ID | 314 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ット | +2.009 |
fil | +1.994 |
ignore | +1.805 |
fixed | +1.775 |
BAT | +1.752 |
Neg logit contributions | |
uity | -1.995 |
swaps | -1.944 |
risis | -1.938 |
millenn | -1.917 |
anguage | -1.891 |
Token | want |
Token ID | 765 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ット | +1.439 |
fil | +1.413 |
ignore | +1.270 |
fixed | +1.246 |
BAT | +1.236 |
Neg logit contributions | |
uity | -1.678 |
swaps | -1.645 |
risis | -1.630 |
millenn | -1.621 |
anguage | -1.583 |
Token | India |
Token ID | 3794 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
uity | +1.119 |
swaps | +1.094 |
risis | +1.090 |
millenn | +1.051 |
anguage | +1.037 |
Neg logit contributions | |
ット | -1.128 |
fil | -1.101 |
ignore | -1.002 |
fixed | -0.988 |
BAT | -0.968 |
Token | ` |
Token ID | 63 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ット | +1.476 |
fil | +1.452 |
ignore | +1.315 |
fixed | +1.299 |
BAT | +1.291 |
Neg logit contributions | |
uity | -1.374 |
swaps | -1.333 |
risis | -1.331 |
millenn | -1.321 |
anguage | -1.287 |
Token | s |
Token ID | 82 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
uity | +3.735 |
swaps | +3.685 |
risis | +3.681 |
ּ | +3.580 |
oute | +3.550 |
Neg logit contributions | |
ット | -3.416 |
fil | -3.291 |
ignore | -3.038 |
BAT | -3.006 |
fixed | -2.919 |
Token | two |
Token ID | 734 |
Feature activation | +6.66e-03 |
Pos logit contributions | |
uity | +1.002 |
swaps | +0.996 |
risis | +0.978 |
millenn | +0.961 |
oute | +0.931 |
Neg logit contributions | |
ット | -1.125 |
fil | -1.100 |
ignore | -1.001 |
fixed | -0.984 |
BAT | -0.977 |
Token | prominent |
Token ID | 9208 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ット | +0.022 |
fil | +0.022 |
ignore | +0.020 |
fixed | +0.019 |
BAT | +0.019 |
Neg logit contributions | |
uity | -0.023 |
swaps | -0.023 |
risis | -0.023 |
millenn | -0.023 |
oute | -0.022 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ット | +0.909 |
fil | +0.894 |
ignore | +0.814 |
fixed | +0.804 |
BAT | +0.799 |
Neg logit contributions | |
uity | -0.763 |
swaps | -0.743 |
risis | -0.738 |
millenn | -0.729 |
anguage | -0.711 |
Token | hel |
Token ID | 932 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
uity | +7.574 |
swaps | +7.559 |
millenn | +7.176 |
aith | +7.146 |
citizenship | +7.124 |
Neg logit contributions | |
ット | -10.085 |
fil | -9.533 |
fixed | -9.097 |
ignore | -8.984 |
BAT | -8.978 |
Token | pl |
Token ID | 489 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ット | +0.460 |
fil | +0.446 |
ignore | +0.398 |
fixed | +0.391 |
BAT | +0.387 |
Neg logit contributions | |
uity | -0.609 |
swaps | -0.594 |
risis | -0.592 |
millenn | -0.584 |
anguage | -0.574 |
Token | ines |
Token ID | 1127 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
fil | +0.271 |
ット | +0.269 |
ignore | +0.240 |
BAT | +0.231 |
above | +0.230 |
Neg logit contributions | |
millenn | -0.400 |
uity | -0.398 |
swaps | -0.392 |
risis | -0.388 |
ּ | -0.379 |
Token | are |
Token ID | 389 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
uity | +3.389 |
risis | +3.354 |
swaps | +3.345 |
millenn | +3.232 |
anguage | +3.215 |
Neg logit contributions | |
ット | -3.065 |
fil | -2.939 |
ignore | -2.648 |
BAT | -2.609 |
fixed | -2.609 |
Token | discouraging |
Token ID | 48001 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
uity | +0.518 |
swaps | +0.509 |
risis | +0.504 |
millenn | +0.496 |
anguage | +0.485 |
Neg logit contributions | |
ット | -0.515 |
fil | -0.501 |
ignore | -0.455 |
fixed | -0.447 |
BAT | -0.446 |
Token | � |
Token ID | 247 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ット | +0.949 |
fil | +0.933 |
ignore | +0.861 |
fixed | +0.853 |
BAT | +0.848 |
Neg logit contributions | |
uity | -0.581 |
swaps | -0.564 |
risis | -0.559 |
millenn | -0.553 |
anguage | -0.533 |
Token | commitment |
Token ID | 7901 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
uity | +0.458 |
swaps | +0.447 |
risis | +0.446 |
millenn | +0.437 |
anguage | +0.433 |
Neg logit contributions | |
ット | -0.396 |
fil | -0.385 |
ignore | -0.345 |
fixed | -0.340 |
BAT | -0.339 |
Token | to |
Token ID | 284 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
uity | +3.702 |
swaps | +3.678 |
risis | +3.668 |
ּ | +3.542 |
anguage | +3.516 |
Neg logit contributions | |
ット | -3.113 |
fil | -2.996 |
ignore | -2.681 |
fixed | -2.669 |
BAT | -2.607 |
Token | a |
Token ID | 257 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
uity | +1.136 |
swaps | +1.117 |
risis | +1.098 |
millenn | +1.087 |
anguage | +1.060 |
Neg logit contributions | |
ット | -1.067 |
fil | -1.030 |
ignore | -0.926 |
fixed | -0.916 |
BAT | -0.908 |
Token | conservative |
Token ID | 5940 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
uity | +2.590 |
swaps | +2.545 |
risis | +2.515 |
millenn | +2.473 |
aith | +2.411 |
Neg logit contributions | |
ット | -2.818 |
fil | -2.713 |
ignore | -2.492 |
fixed | -2.422 |
Boss | -2.408 |
Token | lifestyle |
Token ID | 12263 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
uity | +5.573 |
swaps | +5.388 |
millenn | +5.287 |
citizenship | +5.235 |
aith | +5.226 |
Neg logit contributions | |
ット | -6.897 |
fil | -6.455 |
BAT | -5.972 |
fixed | -5.964 |
ignore | -5.943 |
Token | , |
Token ID | 11 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
swaps | +8.762 |
uity | +8.575 |
risis | +8.405 |
ּ | +8.294 |
urches | +8.173 |
Neg logit contributions | |
ット | -8.766 |
fil | -8.319 |
ignore | -7.404 |
fixed | -7.387 |
BAT | -7.368 |
Token | Mr |
Token ID | 1770 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
uity | +2.964 |
swaps | +2.928 |
risis | +2.899 |
millenn | +2.835 |
anguage | +2.785 |
Neg logit contributions | |
ット | -3.156 |
fil | -3.043 |
ignore | -2.766 |
fixed | -2.763 |
BAT | -2.718 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
uity | +3.028 |
swaps | +2.945 |
risis | +2.935 |
millenn | +2.852 |
oute | +2.841 |
Neg logit contributions | |
ット | -3.084 |
fil | -2.989 |
ignore | -2.710 |
BAT | -2.686 |
fixed | -2.684 |
Token | Lu |
Token ID | 6026 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
uity | +2.576 |
swaps | +2.510 |
risis | +2.503 |
millenn | +2.438 |
oute | +2.412 |
Neg logit contributions | |
ット | -2.635 |
fil | -2.563 |
ignore | -2.329 |
fixed | -2.304 |
BAT | -2.286 |
Token | ce |
Token ID | 344 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
uity | +1.151 |
swaps | +1.127 |
risis | +1.119 |
millenn | +1.104 |
oute | +1.078 |
Neg logit contributions | |
ット | -0.986 |
fil | -0.956 |
ignore | -0.857 |
fixed | -0.849 |
BAT | -0.841 |
Token | Story |
Token ID | 11605 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
uity | +1.292 |
risis | +1.255 |
swaps | +1.247 |
oute | +1.215 |
anguage | +1.209 |
Neg logit contributions | |
ット | -1.117 |
fil | -1.072 |
ignore | -0.962 |
HMS | -0.949 |
fixed | -0.943 |
Token | highlights |
Token ID | 11330 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
uity | +0.876 |
swaps | +0.863 |
risis | +0.852 |
millenn | +0.841 |
oute | +0.819 |
Neg logit contributions | |
ット | -1.031 |
fil | -1.008 |
ignore | -0.921 |
fixed | -0.908 |
BAT | -0.905 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
uity | +6.839 |
risis | +6.640 |
swaps | +6.518 |
oute | +6.290 |
ּ | +6.263 |
Neg logit contributions | |
ット | -7.298 |
fil | -7.050 |
ignore | -6.597 |
fixed | -6.533 |
intention | -6.217 |
Token | of |
Token ID | 286 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
uity | +4.324 |
swaps | +4.265 |
risis | +4.129 |
millenn | +4.073 |
oute | +4.018 |
Neg logit contributions | |
ット | -4.198 |
fil | -4.111 |
ignore | -3.750 |
BAT | -3.714 |
fixed | -3.667 |
Token | Defense |
Token ID | 5947 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uity | +0.740 |
swaps | +0.719 |
risis | +0.712 |
millenn | +0.700 |
anguage | +0.680 |
Neg logit contributions | |
ット | -1.092 |
fil | -1.076 |
ignore | -0.991 |
fixed | -0.978 |
BAT | -0.973 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
uity | +3.014 |
swaps | +3.009 |
risis | +2.889 |
millenn | +2.835 |
oute | +2.799 |
Neg logit contributions | |
ット | -4.141 |
fil | -4.007 |
ignore | -3.658 |
fixed | -3.632 |
BAT | -3.627 |
Token | Hag |
Token ID | 21375 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
uity | +8.952 |
swaps | +8.709 |
aith | +8.459 |
urches | +8.306 |
risis | +8.291 |
Neg logit contributions | |
fil | -9.180 |
ット | -9.012 |
ignore | -7.832 |
BAT | -7.800 |
fixed | -7.670 |
Token | el |
Token ID | 417 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
ット | +0.146 |
fil | +0.142 |
ignore | +0.126 |
fixed | +0.124 |
BAT | +0.123 |
Neg logit contributions | |
uity | -0.197 |
swaps | -0.193 |
risis | -0.192 |
millenn | -0.189 |
anguage | -0.186 |
Token | will |
Token ID | 481 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
uity | +2.869 |
swaps | +2.851 |
risis | +2.762 |
millenn | +2.654 |
oute | +2.640 |
Neg logit contributions | |
ット | -3.711 |
fil | -3.578 |
ignore | -3.273 |
fixed | -3.249 |
BAT | -3.248 |
Token | step |
Token ID | 2239 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
uity | +2.577 |
swaps | +2.526 |
risis | +2.494 |
oute | +2.404 |
anguage | +2.371 |
Neg logit contributions | |
ット | -3.068 |
fil | -2.951 |
fixed | -2.683 |
BAT | -2.672 |
ignore | -2.659 |
Token | down |
Token ID | 866 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ット | +0.514 |
fil | +0.503 |
ignore | +0.446 |
fixed | +0.440 |
BAT | +0.437 |
Neg logit contributions | |
uity | -0.669 |
swaps | -0.655 |
risis | -0.652 |
millenn | -0.643 |
anguage | -0.631 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ット | +0.786 |
fil | +0.768 |
ignore | +0.679 |
fixed | +0.667 |
BAT | +0.662 |
Neg logit contributions | |
uity | -1.097 |
swaps | -1.075 |
risis | -1.069 |
millenn | -1.059 |
anguage | -1.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
ット | +1.257 |
fil | +1.231 |
ignore | +1.090 |
fixed | +1.072 |
BAT | +1.063 |
Neg logit contributions | |
uity | -1.681 |
swaps | -1.649 |
risis | -1.635 |
millenn | -1.626 |
anguage | -1.593 |
Token | WASHINGTON |
Token ID | 21793 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
uity | +1.803 |
risis | +1.751 |
swaps | +1.736 |
oute | +1.697 |
anguage | +1.685 |
Neg logit contributions | |
ット | -1.562 |
fil | -1.491 |
ignore | -1.342 |
HMS | -1.329 |
fixed | -1.311 |
Token | — |
Token ID | 851 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
uity | +2.255 |
swaps | +2.208 |
risis | +2.198 |
millenn | +2.127 |
ּ | +2.099 |
Neg logit contributions | |
ット | -1.996 |
fil | -1.928 |
ignore | -1.741 |
fixed | -1.726 |
Boss | -1.672 |
Token | A |
Token ID | 317 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
uity | +0.451 |
swaps | +0.440 |
risis | +0.437 |
millenn | +0.427 |
oute | +0.418 |
Neg logit contributions | |
ット | -0.507 |
fil | -0.498 |
ignore | -0.453 |
fixed | -0.448 |
BAT | -0.443 |
Token | Cy |
Token ID | 5934 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
uity | +0.289 |
swaps | +0.280 |
risis | +0.279 |
millenn | +0.276 |
anguage | +0.269 |
Neg logit contributions | |
ット | -0.357 |
fil | -0.352 |
ignore | -0.321 |
fixed | -0.317 |
BAT | -0.316 |
Token | gn |
Token ID | 4593 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
uity | +10.053 |
swaps | +9.842 |
risis | +9.596 |
oute | +9.514 |
millenn | +9.407 |
Neg logit contributions | |
ット | -8.013 |
fil | -6.989 |
ignore | -6.702 |
HMS | -6.608 |
fixed | -6.476 |
Token | us |
Token ID | 385 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
uity | +4.119 |
risis | +3.868 |
swaps | +3.755 |
anguage | +3.690 |
oute | +3.678 |
Neg logit contributions | |
ット | -6.261 |
fil | -6.189 |
BAT | -5.746 |
fixed | -5.730 |
ignore | -5.702 |
Token | cargo |
Token ID | 15892 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
uity | +0.562 |
swaps | +0.552 |
risis | +0.545 |
millenn | +0.539 |
oute | +0.524 |
Neg logit contributions | |
ット | -0.556 |
fil | -0.545 |
ignore | -0.493 |
fixed | -0.486 |
BAT | -0.483 |
Token | mission |
Token ID | 4365 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
swaps | +4.808 |
uity | +4.750 |
risis | +4.688 |
oute | +4.580 |
aith | +4.527 |
Neg logit contributions | |
ット | -5.655 |
fil | -5.388 |
BAT | -5.035 |
ignore | -4.961 |
fixed | -4.922 |
Token | to |
Token ID | 284 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
uity | +1.694 |
swaps | +1.685 |
risis | +1.633 |
millenn | +1.598 |
oute | +1.592 |
Neg logit contributions | |
ット | -1.653 |
fil | -1.599 |
ignore | -1.444 |
BAT | -1.420 |
fixed | -1.419 |
Token | Mohammad |
Token ID | 29674 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
uity | +0.124 |
swaps | +0.122 |
risis | +0.121 |
millenn | +0.119 |
anguage | +0.116 |
Neg logit contributions | |
ット | -0.134 |
fil | -0.132 |
ignore | -0.120 |
fixed | -0.118 |
BAT | -0.118 |
Token | School |
Token ID | 3961 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ット | +0.525 |
fil | +0.514 |
ignore | +0.464 |
fixed | +0.457 |
BAT | +0.454 |
Neg logit contributions | |
uity | -0.544 |
swaps | -0.532 |
risis | -0.528 |
millenn | -0.522 |
anguage | -0.510 |
Token | teaching |
Token ID | 7743 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ット | +1.149 |
fil | +1.132 |
ignore | +1.021 |
fixed | +1.008 |
BAT | +1.000 |
Neg logit contributions | |
uity | -1.138 |
swaps | -1.109 |
risis | -1.104 |
millenn | -1.091 |
anguage | -1.066 |
Token | " |
Token ID | 366 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ット | +0.914 |
fil | +0.901 |
ignore | +0.810 |
fixed | +0.800 |
BAT | +0.794 |
Neg logit contributions | |
uity | -0.948 |
swaps | -0.923 |
risis | -0.921 |
millenn | -0.909 |
anguage | -0.889 |
Token | a |
Token ID | 64 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ット | +1.470 |
fil | +1.469 |
ignore | +1.301 |
fixed | +1.287 |
BAT | +1.266 |
Neg logit contributions | |
uity | -1.878 |
swaps | -1.849 |
risis | -1.829 |
millenn | -1.825 |
anguage | -1.774 |
Token | Qur |
Token ID | 17599 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
uity | +0.625 |
swaps | +0.610 |
risis | +0.606 |
millenn | +0.599 |
anguage | +0.584 |
Neg logit contributions | |
ット | -0.688 |
fil | -0.675 |
ignore | -0.614 |
fixed | -0.605 |
BAT | -0.602 |
Token | ' |
Token ID | 6 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
uity | +7.905 |
oute | +7.593 |
risis | +7.554 |
swaps | +7.337 |
aith | +7.284 |
Neg logit contributions | |
ット | -9.833 |
fil | -9.430 |
BAT | -8.767 |
Boss | -8.674 |
HMS | -8.615 |
Token | an |
Token ID | 272 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
uity | +7.814 |
oute | +7.694 |
risis | +7.511 |
anguage | +7.429 |
ּ | +7.403 |
Neg logit contributions | |
ット | -7.750 |
fil | -7.175 |
HMS | -6.614 |
BAT | -6.536 |
fixed | -6.494 |
Token | - |
Token ID | 12 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
uity | +6.221 |
swaps | +6.072 |
millenn | +6.015 |
anguage | +5.963 |
risis | +5.928 |
Neg logit contributions | |
ット | -5.007 |
fil | -4.673 |
Boss | -4.219 |
ignore | -4.204 |
BAT | -4.183 |
Token | guided |
Token ID | 23657 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
uity | +3.292 |
risis | +3.195 |
swaps | +3.190 |
millenn | +3.149 |
anguage | +3.114 |
Neg logit contributions | |
ット | -2.570 |
fil | -2.404 |
ignore | -2.170 |
BAT | -2.140 |
fixed | -2.136 |
Token | journey |
Token ID | 7002 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
uity | +1.563 |
swaps | +1.536 |
risis | +1.512 |
millenn | +1.504 |
anguage | +1.463 |
Neg logit contributions | |
ット | -1.884 |
fil | -1.812 |
ignore | -1.662 |
fixed | -1.641 |
BAT | -1.636 |
Token | . |
Token ID | 13 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ット | +0.374 |
fil | +0.366 |
ignore | +0.325 |
fixed | +0.319 |
BAT | +0.317 |
Neg logit contributions | |
uity | -0.503 |
swaps | -0.493 |
risis | -0.490 |
millenn | -0.485 |
anguage | -0.476 |
Token | 5 |
Token ID | 20 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ット | +0.243 |
fil | +0.237 |
ignore | +0.208 |
fixed | +0.205 |
BAT | +0.203 |
Neg logit contributions | |
uity | -0.357 |
swaps | -0.350 |
risis | -0.348 |
millenn | -0.343 |
anguage | -0.338 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
uity | +2.134 |
swaps | +2.095 |
risis | +2.092 |
millenn | +2.049 |
anguage | +2.012 |
Neg logit contributions | |
ット | -1.810 |
fil | -1.775 |
ignore | -1.588 |
BAT | -1.568 |
fixed | -1.561 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
uity | +0.544 |
swaps | +0.529 |
risis | +0.527 |
oute | +0.508 |
ּ | +0.505 |
Neg logit contributions | |
ット | -0.481 |
fil | -0.461 |
ignore | -0.414 |
fixed | -0.410 |
BAT | -0.406 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
uity | +0.957 |
swaps | +0.935 |
risis | +0.934 |
millenn | +0.906 |
oute | +0.904 |
Neg logit contributions | |
ット | -0.676 |
fil | -0.655 |
ignore | -0.582 |
fixed | -0.568 |
BAT | -0.563 |
Token | Barb |
Token ID | 10593 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
uity | +4.573 |
swaps | +4.519 |
risis | +4.465 |
oute | +4.320 |
aith | +4.314 |
Neg logit contributions | |
ット | -5.526 |
fil | -5.252 |
ignore | -4.946 |
Boss | -4.852 |
BAT | -4.836 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
uity | +8.793 |
oute | +8.024 |
risis | +7.979 |
aith | +7.949 |
swaps | +7.766 |
Neg logit contributions | |
ット | -9.457 |
fil | -8.709 |
ignore | -8.606 |
BAT | -8.439 |
fixed | -8.258 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uity | +3.953 |
risis | +3.864 |
swaps | +3.863 |
millenn | +3.741 |
oute | +3.696 |
Neg logit contributions | |
ット | -3.567 |
fil | -3.472 |
ignore | -3.136 |
BAT | -3.136 |
fixed | -3.098 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
uity | +0.450 |
swaps | +0.437 |
risis | +0.436 |
oute | +0.420 |
ּ | +0.417 |
Neg logit contributions | |
ット | -0.395 |
fil | -0.378 |
ignore | -0.339 |
fixed | -0.336 |
BAT | -0.333 |
Token | 128 |
Token ID | 12762 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
uity | +1.080 |
swaps | +1.056 |
risis | +1.055 |
millenn | +1.029 |
oute | +1.026 |
Neg logit contributions | |
ット | -0.715 |
fil | -0.689 |
ignore | -0.607 |
BAT | -0.599 |
fixed | -0.594 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
uity | +2.832 |
swaps | +2.761 |
risis | +2.758 |
millenn | +2.692 |
anguage | +2.646 |
Neg logit contributions | |
ット | -2.350 |
fil | -2.291 |
ignore | -2.061 |
BAT | -2.033 |
fixed | -2.019 |
Token | US |
Token ID | 1294 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
uity | +1.438 |
swaps | +1.408 |
risis | +1.389 |
millenn | +1.349 |
oute | +1.326 |
Neg logit contributions | |
ット | -1.670 |
fil | -1.622 |
Boss | -1.496 |
ignore | -1.492 |
BAT | -1.466 |
Token | GS |
Token ID | 14313 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
uity | +1.390 |
swaps | +1.368 |
risis | +1.360 |
millenn | +1.335 |
oute | +1.316 |
Neg logit contributions | |
ット | -0.907 |
fil | -0.884 |
ignore | -0.777 |
fixed | -0.762 |
Boss | -0.758 |
Token | Earth |
Token ID | 3668 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ット | +2.541 |
fil | +2.497 |
ignore | +2.203 |
fixed | +2.171 |
BAT | +2.149 |
Neg logit contributions | |
uity | -3.546 |
swaps | -3.471 |
risis | -3.449 |
millenn | -3.432 |
anguage | -3.361 |
Token | Explorer |
Token ID | 19142 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ット | +0.709 |
fil | +0.697 |
ignore | +0.630 |
fixed | +0.621 |
BAT | +0.616 |
Neg logit contributions | |
uity | -0.702 |
swaps | -0.686 |
risis | -0.682 |
millenn | -0.675 |
anguage | -0.659 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
uity | +0.391 |
swaps | +0.382 |
risis | +0.380 |
oute | +0.372 |
millenn | +0.369 |
Neg logit contributions | |
ット | -0.343 |
fil | -0.329 |
ignore | -0.301 |
Boss | -0.295 |
fixed | -0.295 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
uity | +0.556 |
swaps | +0.539 |
risis | +0.537 |
millenn | +0.512 |
anguage | +0.510 |
Neg logit contributions | |
ット | -0.685 |
fil | -0.669 |
ignore | -0.613 |
fixed | -0.602 |
Boss | -0.601 |
Token | by |
Token ID | 416 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ット | +4.143 |
fil | +4.091 |
fixed | +3.489 |
above | +3.482 |
ignore | +3.409 |
Neg logit contributions | |
uity | -7.769 |
risis | -7.566 |
millenn | -7.480 |
swaps | -7.449 |
anguage | -7.357 |
Token | Holl |
Token ID | 11806 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
uity | +1.316 |
swaps | +1.284 |
risis | +1.268 |
millenn | +1.229 |
oute | +1.222 |
Neg logit contributions | |
ット | -1.309 |
fil | -1.270 |
ignore | -1.151 |
fixed | -1.137 |
BAT | -1.128 |
Token | i |
Token ID | 72 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
uity | +0.250 |
swaps | +0.243 |
risis | +0.242 |
millenn | +0.239 |
anguage | +0.235 |
Neg logit contributions | |
ット | -0.253 |
fil | -0.247 |
ignore | -0.223 |
fixed | -0.221 |
BAT | -0.220 |
Token | R |
Token ID | 371 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ット | +3.834 |
fil | +3.817 |
ignore | +3.430 |
fixed | +3.370 |
HMS | +3.353 |
Neg logit contributions | |
uity | -3.782 |
millenn | -3.737 |
swaps | -3.719 |
risis | -3.695 |
livest | -3.578 |
Token | ie |
Token ID | 494 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
uity | +1.082 |
risis | +1.049 |
swaps | +1.048 |
anguage | +1.017 |
oute | +1.015 |
Neg logit contributions | |
ット | -1.162 |
fil | -1.121 |
ignore | -1.015 |
fixed | -1.009 |
BAT | -1.004 |
Token | NA |
Token ID | 4535 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ット | +3.944 |
fil | +3.884 |
ignore | +3.487 |
BAT | +3.466 |
HMS | +3.442 |
Neg logit contributions | |
uity | -4.921 |
millenn | -4.844 |
swaps | -4.801 |
risis | -4.773 |
anguage | -4.737 |
Token | K |
Token ID | 42 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ット | +2.523 |
fil | +2.458 |
BAT | +2.056 |
ignore | +2.027 |
fixed | +2.014 |
Neg logit contributions | |
uity | -5.499 |
millenn | -5.434 |
swaps | -5.407 |
risis | -5.373 |
anguage | -5.281 |
Token | ES |
Token ID | 1546 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ット | +3.973 |
fil | +3.921 |
ignore | +3.527 |
BAT | +3.473 |
HMS | +3.455 |
Neg logit contributions | |
uity | -5.173 |
millenn | -5.107 |
swaps | -5.047 |
risis | -5.006 |
anguage | -4.959 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ット | +2.047 |
fil | +2.014 |
ignore | +1.780 |
BAT | +1.745 |
fixed | +1.740 |
Neg logit contributions | |
uity | -2.924 |
swaps | -2.868 |
risis | -2.852 |
millenn | -2.848 |
anguage | -2.786 |
Token | We |
Token ID | 775 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
ット | +0.983 |
fil | +0.964 |
ignore | +0.863 |
fixed | +0.849 |
BAT | +0.846 |
Neg logit contributions | |
uity | -1.147 |
swaps | -1.123 |
risis | -1.115 |
millenn | -1.109 |
anguage | -1.083 |
Token | surprised |
Token ID | 6655 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
uity | +0.338 |
swaps | +0.331 |
risis | +0.328 |
millenn | +0.320 |
oute | +0.314 |
Neg logit contributions | |
ット | -0.339 |
fil | -0.331 |
ignore | -0.298 |
fixed | -0.294 |
BAT | -0.294 |
Token | at |
Token ID | 379 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
fil | +4.651 |
ット | +4.639 |
ignore | +4.127 |
HMS | +4.073 |
fixed | +3.991 |
Neg logit contributions | |
uity | -6.161 |
risis | -6.068 |
millenn | -6.009 |
anguage | -5.964 |
swaps | -5.954 |
Token | least |
Token ID | 1551 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
uity | +0.607 |
swaps | +0.592 |
risis | +0.586 |
millenn | +0.578 |
oute | +0.566 |
Neg logit contributions | |
ット | -0.571 |
fil | -0.558 |
ignore | -0.504 |
fixed | -0.498 |
BAT | -0.495 |
Token | two |
Token ID | 734 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ット | +1.777 |
fil | +1.745 |
ignore | +1.565 |
fixed | +1.541 |
BAT | +1.528 |
Neg logit contributions | |
uity | -2.038 |
swaps | -1.990 |
risis | -1.984 |
millenn | -1.965 |
anguage | -1.923 |
Token | big |
Token ID | 1263 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
uity | +0.676 |
swaps | +0.666 |
risis | +0.652 |
millenn | +0.650 |
oute | +0.633 |
Neg logit contributions | |
ット | -0.568 |
fil | -0.551 |
ignore | -0.492 |
fixed | -0.487 |
BAT | -0.484 |
Token | suck |
Token ID | 10110 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ット | +0.876 |
fil | +0.860 |
ignore | +0.772 |
fixed | +0.760 |
BAT | +0.753 |
Neg logit contributions | |
uity | -0.992 |
swaps | -0.969 |
risis | -0.967 |
millenn | -0.956 |
anguage | -0.938 |
Token | deviation |
Token ID | 28833 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ット | +4.016 |
fil | +4.000 |
ignore | +3.624 |
fixed | +3.610 |
BAT | +3.487 |
Neg logit contributions | |
uity | -3.621 |
risis | -3.577 |
swaps | -3.555 |
millenn | -3.505 |
anguage | -3.499 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
ット | +3.856 |
fil | +3.842 |
fixed | +3.359 |
ignore | +3.326 |
BAT | +3.249 |
Neg logit contributions | |
uity | -5.778 |
millenn | -5.745 |
risis | -5.731 |
swaps | -5.587 |
anguage | -5.536 |
Token |
|
Token ID | 198 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ット | +1.205 |
fil | +1.181 |
ignore | +1.056 |
fixed | +1.040 |
BAT | +1.032 |
Neg logit contributions | |
uity | -1.427 |
swaps | -1.397 |
risis | -1.388 |
millenn | -1.375 |
anguage | -1.345 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ット | +1.252 |
fil | +1.234 |
ignore | +1.092 |
fixed | +1.073 |
BAT | +1.065 |
Neg logit contributions | |
uity | -1.700 |
millenn | -1.674 |
swaps | -1.669 |
risis | -1.659 |
anguage | -1.618 |
Token | float |
Token ID | 22468 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ット | +0.573 |
fil | +0.557 |
ignore | +0.497 |
fixed | +0.488 |
BAT | +0.485 |
Neg logit contributions | |
uity | -0.706 |
swaps | -0.690 |
risis | -0.686 |
millenn | -0.676 |
anguage | -0.665 |
Token | Part |
Token ID | 2142 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ット | +0.481 |
fil | +0.470 |
ignore | +0.422 |
fixed | +0.415 |
BAT | +0.413 |
Neg logit contributions | |
uity | -0.545 |
swaps | -0.533 |
risis | -0.529 |
millenn | -0.524 |
anguage | -0.512 |
Token | icle |
Token ID | 1548 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
fil | +6.697 |
ット | +6.696 |
ignore | +6.068 |
fixed | +6.068 |
Boss | +5.929 |
Neg logit contributions | |
swaps | -5.286 |
millenn | -5.225 |
risis | -5.206 |
uity | -5.168 |
urches | -5.085 |
Token | :: |
Token ID | 3712 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ット | +0.560 |
fil | +0.549 |
ignore | +0.494 |
fixed | +0.487 |
BAT | +0.484 |
Neg logit contributions | |
uity | -0.603 |
swaps | -0.590 |
risis | -0.586 |
millenn | -0.580 |
anguage | -0.567 |
Token | Get |
Token ID | 3855 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
uity | +1.033 |
swaps | +1.011 |
risis | +1.002 |
millenn | +0.990 |
oute | +0.971 |
Neg logit contributions | |
ット | -0.797 |
fil | -0.768 |
ignore | -0.680 |
HMS | -0.668 |
BAT | -0.667 |
Token | Mass |
Token ID | 20273 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ット | +0.688 |
fil | +0.677 |
ignore | +0.622 |
fixed | +0.614 |
BAT | +0.612 |
Neg logit contributions | |
uity | -0.469 |
swaps | -0.454 |
risis | -0.451 |
millenn | -0.445 |
anguage | -0.431 |
Token | ( |
Token ID | 7 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
uity | +1.190 |
swaps | +1.168 |
risis | +1.158 |
millenn | +1.147 |
anguage | +1.118 |
Neg logit contributions | |
ット | -0.888 |
fil | -0.864 |
ignore | -0.768 |
BAT | -0.755 |
fixed | -0.749 |
Token | just |
Token ID | 655 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ット | +1.061 |
fil | +1.052 |
ignore | +0.945 |
fixed | +0.930 |
BAT | +0.923 |
Neg logit contributions | |
uity | -1.105 |
risis | -1.074 |
millenn | -1.072 |
swaps | -1.071 |
anguage | -1.043 |
Token | caring |
Token ID | 18088 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
uity | +0.329 |
swaps | +0.322 |
risis | +0.316 |
millenn | +0.309 |
oute | +0.303 |
Neg logit contributions | |
ット | -0.429 |
fil | -0.419 |
ignore | -0.383 |
fixed | -0.379 |
BAT | -0.378 |
Token | for |
Token ID | 329 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
fil | +2.214 |
ット | +2.212 |
ignore | +1.954 |
fixed | +1.932 |
BAT | +1.916 |
Neg logit contributions | |
uity | -2.909 |
swaps | -2.840 |
millenn | -2.838 |
risis | -2.832 |
anguage | -2.757 |
Token | those |
Token ID | 883 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ット | +1.395 |
fil | +1.371 |
ignore | +1.221 |
fixed | +1.204 |
BAT | +1.193 |
Neg logit contributions | |
uity | -1.713 |
swaps | -1.673 |
risis | -1.667 |
millenn | -1.651 |
anguage | -1.618 |
Token | who |
Token ID | 508 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ット | +0.117 |
fil | +0.113 |
ignore | +0.102 |
fixed | +0.100 |
BAT | +0.100 |
Neg logit contributions | |
uity | -0.131 |
swaps | -0.129 |
risis | -0.127 |
millenn | -0.126 |
anguage | -0.123 |
Token | suffer |
Token ID | 8659 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ット | +0.724 |
fil | +0.712 |
ignore | +0.645 |
fixed | +0.636 |
BAT | +0.632 |
Neg logit contributions | |
uity | -0.685 |
swaps | -0.669 |
risis | -0.664 |
millenn | -0.659 |
anguage | -0.642 |
Token | from |
Token ID | 422 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
fil | +4.605 |
ット | +4.542 |
ignore | +4.126 |
above | +4.052 |
fixed | +4.042 |
Neg logit contributions | |
uity | -5.036 |
millenn | -4.900 |
anguage | -4.806 |
risis | -4.801 |
swaps | -4.791 |
Token | the |
Token ID | 262 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
ット | +1.957 |
fil | +1.942 |
ignore | +1.742 |
fixed | +1.722 |
HMS | +1.705 |
Neg logit contributions | |
uity | -1.990 |
swaps | -1.923 |
risis | -1.921 |
millenn | -1.910 |
anguage | -1.876 |
Token | cold |
Token ID | 4692 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ット | +0.285 |
fil | +0.278 |
ignore | +0.254 |
fixed | +0.250 |
BAT | +0.249 |
Neg logit contributions | |
uity | -0.258 |
swaps | -0.253 |
risis | -0.251 |
millenn | -0.248 |
anguage | -0.241 |
Token | winter |
Token ID | 7374 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
fil | +3.986 |
ット | +3.942 |
fixed | +3.483 |
ignore | +3.468 |
above | +3.411 |
Neg logit contributions | |
uity | -4.494 |
millenn | -4.411 |
risis | -4.358 |
swaps | -4.346 |
anguage | -4.262 |
Token | on |
Token ID | 319 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
fil | +3.228 |
ット | +3.197 |
ignore | +2.874 |
fixed | +2.849 |
above | +2.797 |
Neg logit contributions | |
uity | -3.317 |
millenn | -3.235 |
risis | -3.233 |
swaps | -3.218 |
anguage | -3.148 |
Token | prove |
Token ID | 5879 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ット | +0.485 |
fil | +0.469 |
ignore | +0.424 |
fixed | +0.420 |
BAT | +0.415 |
Neg logit contributions | |
uity | -0.514 |
swaps | -0.504 |
risis | -0.498 |
millenn | -0.488 |
anguage | -0.479 |
Token | art |
Token ID | 1242 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
uity | +1.134 |
swaps | +1.111 |
risis | +1.096 |
millenn | +1.085 |
anguage | +1.066 |
Neg logit contributions | |
ット | -1.083 |
fil | -1.044 |
ignore | -0.951 |
fixed | -0.935 |
BAT | -0.926 |
Token | is |
Token ID | 318 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
fil | +3.178 |
ット | +3.168 |
ignore | +2.868 |
fixed | +2.834 |
BAT | +2.808 |
Neg logit contributions | |
uity | -2.820 |
millenn | -2.734 |
risis | -2.733 |
swaps | -2.724 |
oute | -2.656 |
Token | stronger |
Token ID | 7387 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
uity | +1.352 |
swaps | +1.324 |
risis | +1.301 |
millenn | +1.285 |
anguage | +1.259 |
Neg logit contributions | |
ット | -1.424 |
fil | -1.376 |
ignore | -1.256 |
BAT | -1.230 |
fixed | -1.223 |
Token | than |
Token ID | 621 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
uity | +0.751 |
swaps | +0.735 |
risis | +0.730 |
millenn | +0.718 |
anguage | +0.705 |
Neg logit contributions | |
ット | -0.850 |
fil | -0.826 |
ignore | -0.753 |
fixed | -0.743 |
BAT | -0.738 |
Token | war |
Token ID | 1175 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ット | +0.865 |
fil | +0.847 |
ignore | +0.768 |
fixed | +0.757 |
BAT | +0.752 |
Neg logit contributions | |
uity | -0.837 |
swaps | -0.817 |
risis | -0.811 |
millenn | -0.801 |
anguage | -0.783 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
fil | +4.156 |
ット | +4.075 |
ignore | +3.591 |
fixed | +3.533 |
BAT | +3.475 |
Neg logit contributions | |
uity | -6.059 |
millenn | -5.989 |
swaps | -5.934 |
risis | -5.910 |
oute | -5.862 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
ット | +0.455 |
fil | +0.445 |
ignore | +0.396 |
fixed | +0.390 |
BAT | +0.386 |
Neg logit contributions | |
uity | -0.586 |
swaps | -0.574 |
risis | -0.571 |
millenn | -0.564 |
anguage | -0.553 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
uity | +0.185 |
swaps | +0.180 |
risis | +0.180 |
oute | +0.173 |
ּ | +0.172 |
Neg logit contributions | |
ット | -0.159 |
fil | -0.152 |
ignore | -0.137 |
fixed | -0.135 |
BAT | -0.134 |
Token | Throughout |
Token ID | 26797 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
uity | +1.008 |
risis | +0.981 |
swaps | +0.972 |
anguage | +0.946 |
oute | +0.942 |
Neg logit contributions | |
ット | -0.837 |
fil | -0.794 |
ignore | -0.720 |
HMS | -0.711 |
fixed | -0.708 |
Token | history |
Token ID | 2106 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
uity | +2.928 |
swaps | +2.902 |
risis | +2.900 |
millenn | +2.831 |
oute | +2.761 |
Neg logit contributions | |
ット | -2.913 |
fil | -2.779 |
ignore | -2.578 |
BAT | -2.524 |
fixed | -2.520 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ット | +0.560 |
fil | +0.545 |
ignore | +0.485 |
fixed | +0.478 |
BAT | +0.474 |
Neg logit contributions | |
uity | -0.710 |
swaps | -0.694 |
risis | -0.690 |
millenn | -0.672 |
oute | -0.666 |
Token | nothing |
Token ID | 22366 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
uity | +0.672 |
risis | +0.655 |
swaps | +0.653 |
millenn | +0.636 |
oute | +0.633 |
Neg logit contributions | |
ット | -0.530 |
fil | -0.509 |
ignore | -0.451 |
fixed | -0.447 |
HMS | -0.445 |
Token | will |
Token ID | 481 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
uity | +2.226 |
swaps | +2.191 |
risis | +2.167 |
millenn | +2.098 |
ּ | +2.069 |
Neg logit contributions | |
ット | -2.678 |
fil | -2.617 |
ignore | -2.403 |
BAT | -2.357 |
HMS | -2.328 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
uity | +0.410 |
swaps | +0.399 |
risis | +0.396 |
millenn | +0.386 |
anguage | +0.380 |
Neg logit contributions | |
ット | -0.490 |
fil | -0.478 |
ignore | -0.435 |
BAT | -0.429 |
fixed | -0.429 |
Token | ( |
Token ID | 357 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
uity | +1.711 |
swaps | +1.684 |
risis | +1.662 |
millenn | +1.600 |
anguage | +1.598 |
Neg logit contributions | |
ット | -1.388 |
fil | -1.340 |
ignore | -1.189 |
BAT | -1.175 |
fixed | -1.158 |
Token | in |
Token ID | 259 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ット | +1.241 |
fil | +1.217 |
ignore | +1.068 |
fixed | +1.047 |
BAT | +1.037 |
Neg logit contributions | |
uity | -1.916 |
swaps | -1.881 |
risis | -1.868 |
millenn | -1.857 |
anguage | -1.817 |
Token | terms |
Token ID | 2846 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ット | +2.271 |
fil | +2.269 |
ignore | +1.999 |
fixed | +1.972 |
BAT | +1.937 |
Neg logit contributions | |
uity | -2.788 |
swaps | -2.723 |
risis | -2.711 |
millenn | -2.707 |
anguage | -2.637 |
Token | of |
Token ID | 286 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ット | +0.124 |
fil | +0.121 |
ignore | +0.108 |
fixed | +0.106 |
BAT | +0.106 |
Neg logit contributions | |
uity | -0.151 |
swaps | -0.147 |
risis | -0.146 |
millenn | -0.144 |
anguage | -0.142 |
Token | visible |
Token ID | 7424 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
uity | +1.309 |
swaps | +1.292 |
risis | +1.274 |
millenn | +1.258 |
anguage | +1.224 |
Neg logit contributions | |
ット | -1.310 |
fil | -1.271 |
ignore | -1.148 |
BAT | -1.133 |
fixed | -1.129 |
Token | catast |
Token ID | 14911 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
uity | +2.209 |
swaps | +2.170 |
risis | +2.146 |
millenn | +2.108 |
anguage | +2.059 |
Neg logit contributions | |
ット | -2.265 |
fil | -2.202 |
ignore | -2.009 |
fixed | -1.976 |
BAT | -1.973 |
Token | rop |
Token ID | 1773 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
uity | +0.769 |
risis | +0.734 |
swaps | +0.728 |
millenn | +0.688 |
anguage | +0.678 |
Neg logit contributions | |
ット | -1.768 |
fil | -1.738 |
ignore | -1.616 |
BAT | -1.603 |
fixed | -1.602 |
Token | reducing |
Token ID | 8868 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
uity | +0.893 |
swaps | +0.882 |
risis | +0.873 |
millenn | +0.858 |
oute | +0.837 |
Neg logit contributions | |
ット | -0.835 |
fil | -0.810 |
ignore | -0.730 |
fixed | -0.721 |
BAT | -0.717 |
Token | street |
Token ID | 4675 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ット | +0.869 |
fil | +0.856 |
ignore | +0.771 |
fixed | +0.760 |
BAT | +0.754 |
Neg logit contributions | |
uity | -0.898 |
swaps | -0.872 |
risis | -0.869 |
millenn | -0.863 |
anguage | -0.845 |
Token | homelessness |
Token ID | 28822 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ット | +1.509 |
fil | +1.492 |
ignore | +1.347 |
fixed | +1.324 |
BAT | +1.304 |
Neg logit contributions | |
uity | -1.513 |
swaps | -1.472 |
risis | -1.465 |
millenn | -1.461 |
anguage | -1.432 |
Token | is |
Token ID | 318 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
uity | +1.712 |
swaps | +1.682 |
risis | +1.669 |
millenn | +1.608 |
ּ | +1.596 |
Neg logit contributions | |
ット | -2.151 |
fil | -2.100 |
ignore | -1.915 |
fixed | -1.902 |
BAT | -1.897 |
Token | a |
Token ID | 257 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
uity | +1.045 |
swaps | +1.020 |
risis | +1.014 |
millenn | +0.999 |
anguage | +0.976 |
Neg logit contributions | |
ット | -1.045 |
fil | -1.022 |
ignore | -0.927 |
fixed | -0.911 |
BAT | -0.906 |
Token | better |
Token ID | 1365 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ット | +0.218 |
fil | +0.214 |
ignore | +0.195 |
fixed | +0.192 |
BAT | +0.191 |
Neg logit contributions | |
uity | -0.189 |
swaps | -0.184 |
risis | -0.183 |
millenn | -0.181 |
anguage | -0.177 |
Token | measure |
Token ID | 3953 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
uity | +0.622 |
swaps | +0.609 |
risis | +0.603 |
millenn | +0.595 |
anguage | +0.578 |
Neg logit contributions | |
ット | -0.707 |
fil | -0.693 |
ignore | -0.632 |
fixed | -0.621 |
BAT | -0.619 |
Token | of |
Token ID | 286 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
uity | +1.376 |
swaps | +1.345 |
risis | +1.341 |
millenn | +1.312 |
anguage | +1.298 |
Neg logit contributions | |
ット | -1.239 |
fil | -1.211 |
ignore | -1.087 |
fixed | -1.072 |
BAT | -1.063 |
Token | success |
Token ID | 1943 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ット | +0.729 |
fil | +0.718 |
ignore | +0.646 |
fixed | +0.637 |
BAT | +0.633 |
Neg logit contributions | |
uity | -0.746 |
swaps | -0.727 |
risis | -0.722 |
millenn | -0.716 |
anguage | -0.701 |
Token | than |
Token ID | 621 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ット | +2.308 |
fil | +2.290 |
ignore | +2.059 |
fixed | +2.027 |
BAT | +2.016 |
Neg logit contributions | |
uity | -2.491 |
swaps | -2.433 |
millenn | -2.417 |
risis | -2.412 |
anguage | -2.340 |
Token | reducing |
Token ID | 8868 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ット | +1.053 |
fil | +1.040 |
ignore | +0.939 |
fixed | +0.927 |
BAT | +0.919 |
Neg logit contributions | |
uity | -1.046 |
swaps | -1.017 |
risis | -1.012 |
millenn | -1.004 |
anguage | -0.983 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ット | +2.251 |
fil | +2.218 |
ignore | +1.969 |
BAT | +1.928 |
fixed | +1.926 |
Neg logit contributions | |
uity | -2.919 |
swaps | -2.869 |
risis | -2.864 |
millenn | -2.855 |
anguage | -2.775 |
Token | The |
Token ID | 464 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
uity | +1.679 |
risis | +1.631 |
swaps | +1.618 |
oute | +1.580 |
anguage | +1.571 |
Neg logit contributions | |
ット | -1.456 |
fil | -1.392 |
ignore | -1.251 |
HMS | -1.237 |
fixed | -1.224 |
Token | divers |
Token ID | 15070 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ット | +0.097 |
fil | +0.095 |
ignore | +0.086 |
fixed | +0.085 |
BAT | +0.084 |
Neg logit contributions | |
uity | -0.094 |
swaps | -0.092 |
risis | -0.091 |
millenn | -0.090 |
anguage | -0.088 |
Token | found |
Token ID | 1043 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
uity | +1.103 |
swaps | +1.069 |
risis | +1.064 |
millenn | +1.038 |
anguage | +1.023 |
Neg logit contributions | |
ット | -1.032 |
fil | -1.007 |
ignore | -0.907 |
fixed | -0.900 |
BAT | -0.897 |
Token | her |
Token ID | 607 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
uity | +2.828 |
swaps | +2.792 |
risis | +2.732 |
millenn | +2.695 |
oute | +2.635 |
Neg logit contributions | |
ット | -2.490 |
fil | -2.432 |
ignore | -2.219 |
fixed | -2.161 |
BAT | -2.159 |
Token | on |
Token ID | 319 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
uity | +0.818 |
swaps | +0.810 |
risis | +0.795 |
millenn | +0.788 |
oute | +0.766 |
Neg logit contributions | |
ット | -0.691 |
fil | -0.672 |
ignore | -0.602 |
fixed | -0.588 |
BAT | -0.586 |
Token | a |
Token ID | 257 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ット | +0.799 |
fil | +0.786 |
ignore | +0.710 |
fixed | +0.701 |
BAT | +0.696 |
Neg logit contributions | |
uity | -0.787 |
swaps | -0.768 |
risis | -0.764 |
millenn | -0.755 |
anguage | -0.738 |
Token | ledge |
Token ID | 35614 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
uity | +0.807 |
swaps | +0.793 |
risis | +0.784 |
millenn | +0.776 |
oute | +0.757 |
Neg logit contributions | |
ット | -0.855 |
fil | -0.836 |
ignore | -0.759 |
fixed | -0.746 |
BAT | -0.742 |
Token | , |
Token ID | 11 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
uity | +1.141 |
swaps | +1.124 |
risis | +1.112 |
millenn | +1.089 |
oute | +1.075 |
Neg logit contributions | |
ット | -0.918 |
fil | -0.889 |
ignore | -0.796 |
BAT | -0.779 |
fixed | -0.775 |
Token | her |
Token ID | 607 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
uity | +0.255 |
swaps | +0.250 |
risis | +0.248 |
millenn | +0.244 |
anguage | +0.239 |
Neg logit contributions | |
ット | -0.234 |
fil | -0.228 |
ignore | -0.205 |
fixed | -0.201 |
BAT | -0.201 |
Token | skull |
Token ID | 14511 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ット | +2.386 |
fil | +2.360 |
ignore | +2.118 |
fixed | +2.101 |
BAT | +2.084 |
Neg logit contributions | |
uity | -2.545 |
risis | -2.490 |
swaps | -2.465 |
millenn | -2.448 |
anguage | -2.419 |
Token | perceived |
Token ID | 11067 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ット | +1.411 |
fil | +1.387 |
ignore | +1.252 |
fixed | +1.234 |
BAT | +1.225 |
Neg logit contributions | |
uity | -1.426 |
swaps | -1.393 |
risis | -1.384 |
millenn | -1.373 |
anguage | -1.338 |
Token | humanity |
Token ID | 9265 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
uity | +1.959 |
swaps | +1.924 |
risis | +1.895 |
millenn | +1.876 |
anguage | +1.824 |
Neg logit contributions | |
ット | -1.855 |
fil | -1.796 |
ignore | -1.634 |
fixed | -1.607 |
BAT | -1.599 |
Token | in |
Token ID | 287 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
uity | +1.476 |
swaps | +1.451 |
risis | +1.438 |
millenn | +1.399 |
anguage | +1.388 |
Neg logit contributions | |
ット | -1.236 |
fil | -1.200 |
ignore | -1.075 |
fixed | -1.056 |
BAT | -1.054 |
Token | my |
Token ID | 616 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
uity | +1.510 |
swaps | +1.483 |
risis | +1.467 |
millenn | +1.450 |
anguage | +1.418 |
Neg logit contributions | |
ット | -1.423 |
fil | -1.380 |
ignore | -1.257 |
fixed | -1.237 |
BAT | -1.230 |
Token | youth |
Token ID | 6205 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
ット | +1.214 |
fil | +1.196 |
ignore | +1.076 |
fixed | +1.062 |
BAT | +1.055 |
Neg logit contributions | |
uity | -1.224 |
swaps | -1.193 |
risis | -1.188 |
millenn | -1.172 |
anguage | -1.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ット | +1.367 |
fil | +1.352 |
ignore | +1.192 |
fixed | +1.167 |
BAT | +1.152 |
Neg logit contributions | |
uity | -1.924 |
swaps | -1.884 |
risis | -1.871 |
millenn | -1.862 |
anguage | -1.821 |
Token | � |
Token ID | 447 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ット | +0.043 |
fil | +0.042 |
ignore | +0.038 |
fixed | +0.037 |
BAT | +0.037 |
Neg logit contributions | |
uity | -0.049 |
swaps | -0.048 |
risis | -0.048 |
millenn | -0.047 |
anguage | -0.046 |
Token | � |
Token ID | 251 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ット | +1.090 |
fil | +1.073 |
ignore | +0.994 |
fixed | +0.984 |
BAT | +0.979 |
Neg logit contributions | |
uity | -0.601 |
swaps | -0.582 |
risis | -0.577 |
millenn | -0.571 |
anguage | -0.549 |
Token | King |
Token ID | 2677 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ット | +0.701 |
fil | +0.684 |
ignore | +0.611 |
fixed | +0.601 |
BAT | +0.598 |
Neg logit contributions | |
uity | -0.864 |
swaps | -0.846 |
risis | -0.841 |
millenn | -0.831 |
anguage | -0.815 |
Token | said |
Token ID | 531 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ット | +3.065 |
fil | +3.063 |
ignore | +2.748 |
fixed | +2.693 |
above | +2.666 |
Neg logit contributions | |
uity | -3.178 |
swaps | -3.081 |
millenn | -3.075 |
risis | -3.073 |
anguage | -2.982 |
Token | via |
Token ID | 2884 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ット | +0.319 |
fil | +0.311 |
ignore | +0.277 |
fixed | +0.272 |
BAT | +0.271 |
Neg logit contributions | |
uity | -0.416 |
swaps | -0.407 |
risis | -0.404 |
millenn | -0.399 |
anguage | -0.392 |
Token | of |
Token ID | 286 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
uity | +2.301 |
swaps | +2.245 |
risis | +2.218 |
oute | +2.146 |
ּ | +2.123 |
Neg logit contributions | |
ット | -2.134 |
fil | -2.039 |
ignore | -1.841 |
fixed | -1.829 |
BAT | -1.813 |
Token | a |
Token ID | 257 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
uity | +0.919 |
swaps | +0.897 |
risis | +0.890 |
millenn | +0.878 |
anguage | +0.854 |
Neg logit contributions | |
ット | -1.113 |
fil | -1.092 |
ignore | -0.997 |
fixed | -0.985 |
BAT | -0.978 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
uity | +1.186 |
swaps | +1.161 |
risis | +1.151 |
millenn | +1.137 |
oute | +1.107 |
Neg logit contributions | |
ット | -1.306 |
fil | -1.277 |
ignore | -1.163 |
fixed | -1.148 |
BAT | -1.137 |
Token | corruption |
Token ID | 9253 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
fil | +2.809 |
ット | +2.790 |
ignore | +2.551 |
BAT | +2.528 |
fixed | +2.508 |
Neg logit contributions | |
uity | -1.870 |
millenn | -1.789 |
risis | -1.782 |
swaps | -1.777 |
anguage | -1.760 |
Token | scandal |
Token ID | 10731 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
uity | +0.651 |
swaps | +0.635 |
risis | +0.628 |
millenn | +0.615 |
oute | +0.595 |
Neg logit contributions | |
ット | -1.005 |
fil | -0.987 |
ignore | -0.911 |
fixed | -0.901 |
BAT | -0.896 |
Token | in |
Token ID | 287 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ット | +0.740 |
fil | +0.723 |
ignore | +0.649 |
fixed | +0.639 |
BAT | +0.635 |
Neg logit contributions | |
uity | -0.846 |
swaps | -0.829 |
risis | -0.821 |
millenn | -0.810 |
anguage | -0.794 |
Token | which |
Token ID | 543 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
uity | +0.942 |
swaps | +0.927 |
risis | +0.915 |
millenn | +0.900 |
anguage | +0.878 |
Neg logit contributions | |
ット | -1.008 |
fil | -0.983 |
ignore | -0.894 |
fixed | -0.882 |
BAT | -0.874 |
Token | instances |
Token ID | 10245 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ット | +0.329 |
fil | +0.324 |
ignore | +0.293 |
fixed | +0.288 |
BAT | +0.287 |
Neg logit contributions | |
uity | -0.325 |
swaps | -0.317 |
risis | -0.315 |
millenn | -0.312 |
anguage | -0.305 |
Token | of |
Token ID | 286 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ット | +1.018 |
fil | +0.999 |
ignore | +0.887 |
fixed | +0.874 |
BAT | +0.866 |
Neg logit contributions | |
uity | -1.282 |
swaps | -1.255 |
risis | -1.251 |
millenn | -1.240 |
anguage | -1.215 |
Token | Lif |
Token ID | 21073 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ット | +0.896 |
fil | +0.890 |
ignore | +0.810 |
fixed | +0.798 |
BAT | +0.797 |
Neg logit contributions | |
uity | -0.755 |
risis | -0.733 |
swaps | -0.729 |
millenn | -0.726 |
anguage | -0.710 |
Token | eline |
Token ID | 4470 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
uity | +2.158 |
risis | +2.026 |
swaps | +1.935 |
oute | +1.823 |
anguage | +1.813 |
Neg logit contributions | |
ット | -4.887 |
fil | -4.596 |
HMS | -4.392 |
BAT | -4.337 |
ignore | -4.329 |
Token | as |
Token ID | 355 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ット | +1.435 |
fil | +1.415 |
ignore | +1.265 |
fixed | +1.243 |
BAT | +1.233 |
Neg logit contributions | |
uity | -1.693 |
swaps | -1.654 |
risis | -1.645 |
millenn | -1.633 |
anguage | -1.602 |
Token | a |
Token ID | 257 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
fil | +3.950 |
ット | +3.934 |
ignore | +3.508 |
fixed | +3.484 |
BAT | +3.473 |
Neg logit contributions | |
uity | -4.191 |
risis | -4.083 |
swaps | -4.081 |
millenn | -4.025 |
anguage | -4.018 |
Token | U |
Token ID | 471 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ット | +1.870 |
fil | +1.857 |
ignore | +1.665 |
BAT | +1.654 |
fixed | +1.651 |
Neg logit contributions | |
uity | -1.715 |
swaps | -1.671 |
risis | -1.665 |
millenn | -1.636 |
anguage | -1.622 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ット | +0.458 |
fil | +0.451 |
ignore | +0.398 |
fixed | +0.392 |
BAT | +0.389 |
Neg logit contributions | |
uity | -0.637 |
swaps | -0.624 |
risis | -0.620 |
millenn | -0.616 |
anguage | -0.603 |
Token | S |
Token ID | 50 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
uity | +3.926 |
swaps | +3.814 |
risis | +3.777 |
ּ | +3.775 |
citizenship | +3.623 |
Neg logit contributions | |
ット | -5.960 |
fil | -5.807 |
ignore | -5.382 |
fixed | -5.270 |
HMS | -5.217 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
uity | +3.203 |
swaps | +3.128 |
risis | +3.115 |
millenn | +3.061 |
anguage | +3.002 |
Neg logit contributions | |
ット | -2.573 |
fil | -2.492 |
ignore | -2.222 |
fixed | -2.187 |
BAT | -2.175 |
Token | Senator |
Token ID | 8962 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uity | +3.123 |
swaps | +3.014 |
millenn | +3.013 |
risis | +2.990 |
citizenship | +2.888 |
Neg logit contributions | |
ット | -5.506 |
fil | -5.351 |
ignore | -5.017 |
fixed | -4.931 |
Boss | -4.902 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
uity | +0.489 |
swaps | +0.479 |
risis | +0.477 |
millenn | +0.470 |
anguage | +0.460 |
Neg logit contributions | |
ット | -0.358 |
fil | -0.348 |
ignore | -0.311 |
fixed | -0.306 |
BAT | -0.302 |
Token | he |
Token ID | 339 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
uity | +0.773 |
swaps | +0.754 |
risis | +0.749 |
millenn | +0.738 |
anguage | +0.715 |
Neg logit contributions | |
ット | -0.916 |
fil | -0.895 |
ignore | -0.818 |
fixed | -0.810 |
BAT | -0.803 |
Token | is |
Token ID | 318 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
uity | +1.197 |
swaps | +1.172 |
risis | +1.157 |
millenn | +1.125 |
anguage | +1.104 |
Neg logit contributions | |
ット | -1.517 |
fil | -1.489 |
ignore | -1.361 |
fixed | -1.347 |
BAT | -1.342 |
Token | fully |
Token ID | 3938 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ット | +1.133 |
fil | +1.115 |
ignore | +1.005 |
fixed | +0.992 |
BAT | +0.986 |
Neg logit contributions | |
uity | -1.145 |
swaps | -1.119 |
risis | -1.113 |
millenn | -1.098 |
anguage | -1.076 |
Token | attack |
Token ID | 1368 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
uity | +1.712 |
swaps | +1.696 |
risis | +1.638 |
millenn | +1.614 |
oute | +1.592 |
Neg logit contributions | |
ット | -2.174 |
fil | -2.093 |
ignore | -1.926 |
fixed | -1.908 |
BAT | -1.905 |
Token | last |
Token ID | 938 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ット | +0.062 |
fil | +0.061 |
ignore | +0.054 |
fixed | +0.053 |
BAT | +0.052 |
Neg logit contributions | |
uity | -0.082 |
swaps | -0.081 |
risis | -0.080 |
millenn | -0.079 |
anguage | -0.078 |
Token | month |
Token ID | 1227 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
uity | +1.246 |
swaps | +1.229 |
risis | +1.204 |
millenn | +1.183 |
oute | +1.139 |
Neg logit contributions | |
ット | -1.669 |
fil | -1.613 |
ignore | -1.490 |
fixed | -1.469 |
BAT | -1.468 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ット | +1.854 |
fil | +1.830 |
ignore | +1.606 |
fixed | +1.574 |
BAT | +1.561 |
Neg logit contributions | |
uity | -2.672 |
swaps | -2.614 |
millenn | -2.610 |
risis | -2.608 |
anguage | -2.541 |
Token |
|
Token ID | 198 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
uity | +0.927 |
swaps | +0.904 |
risis | +0.902 |
millenn | +0.871 |
oute | +0.865 |
Neg logit contributions | |
ット | -0.851 |
fil | -0.831 |
ignore | -0.751 |
fixed | -0.741 |
BAT | -0.729 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
uity | +1.565 |
risis | +1.513 |
swaps | +1.512 |
oute | +1.456 |
ּ | +1.452 |
Neg logit contributions | |
ット | -1.430 |
fil | -1.364 |
ignore | -1.229 |
fixed | -1.217 |
BAT | -1.201 |
Token | � |
Token ID | 447 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
uity | +1.637 |
risis | +1.584 |
swaps | +1.572 |
oute | +1.527 |
ּ | +1.517 |
Neg logit contributions | |
ット | -1.632 |
fil | -1.564 |
ignore | -1.419 |
HMS | -1.413 |
fixed | -1.396 |
Token | � |
Token ID | 250 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ット | +1.800 |
fil | +1.773 |
ignore | +1.655 |
fixed | +1.640 |
BAT | +1.627 |
Neg logit contributions | |
uity | -0.786 |
swaps | -0.759 |
risis | -0.749 |
millenn | -0.733 |
anguage | -0.708 |
Token | One |
Token ID | 3198 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
uity | +1.441 |
swaps | +1.405 |
risis | +1.404 |
millenn | +1.372 |
anguage | +1.355 |
Neg logit contributions | |
ット | -1.208 |
fil | -1.177 |
ignore | -1.055 |
fixed | -1.039 |
BAT | -1.036 |
Token | day |
Token ID | 1110 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ット | +1.339 |
fil | +1.329 |
ignore | +1.191 |
fixed | +1.176 |
BAT | +1.167 |
Neg logit contributions | |
uity | -1.361 |
swaps | -1.321 |
risis | -1.319 |
millenn | -1.309 |
anguage | -1.290 |
Token | they |
Token ID | 484 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
uity | +4.029 |
swaps | +3.959 |
risis | +3.885 |
millenn | +3.803 |
oute | +3.741 |
Neg logit contributions | |
ット | -4.127 |
fil | -3.944 |
ignore | -3.605 |
fixed | -3.593 |
BAT | -3.548 |
Token | / |
Token ID | 14 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
ット | +0.559 |
fil | +0.542 |
ignore | +0.466 |
fixed | +0.454 |
BAT | +0.451 |
Neg logit contributions | |
uity | -1.088 |
swaps | -1.069 |
risis | -1.063 |
millenn | -1.054 |
anguage | -1.036 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
uity | +2.572 |
swaps | +2.508 |
risis | +2.506 |
millenn | +2.460 |
oute | +2.418 |
Neg logit contributions | |
ット | -1.608 |
fil | -1.453 |
ignore | -1.319 |
Boss | -1.300 |
HMS | -1.299 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ット | +0.893 |
fil | +0.874 |
ignore | +0.774 |
fixed | +0.762 |
BAT | +0.756 |
Neg logit contributions | |
uity | -1.200 |
swaps | -1.176 |
risis | -1.169 |
millenn | -1.158 |
anguage | -1.135 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
uity | +1.312 |
swaps | +1.283 |
risis | +1.279 |
ּ | +1.239 |
oute | +1.236 |
Neg logit contributions | |
ット | -0.903 |
fil | -0.860 |
ignore | -0.769 |
fixed | -0.753 |
BAT | -0.743 |
Token | - |
Token ID | 12 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uity | +0.234 |
swaps | +0.230 |
risis | +0.228 |
millenn | +0.226 |
anguage | +0.222 |
Neg logit contributions | |
ット | -0.165 |
fil | -0.161 |
ignore | -0.142 |
fixed | -0.139 |
BAT | -0.139 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ット | +0.324 |
fil | +0.317 |
ignore | +0.280 |
fixed | +0.275 |
BAT | +0.273 |
Neg logit contributions | |
uity | -0.447 |
swaps | -0.438 |
risis | -0.436 |
millenn | -0.432 |
anguage | -0.423 |
Token | . |
Token ID | 13 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
uity | +1.461 |
swaps | +1.438 |
risis | +1.417 |
millenn | +1.394 |
anguage | +1.372 |
Neg logit contributions | |
ット | -1.144 |
fil | -1.102 |
ignore | -0.991 |
BAT | -0.973 |
fixed | -0.963 |
Token | 8 |
Token ID | 23 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
uity | +2.070 |
swaps | +2.021 |
risis | +2.014 |
oute | +1.941 |
ּ | +1.936 |
Neg logit contributions | |
ット | -1.477 |
fil | -1.395 |
ignore | -1.253 |
fixed | -1.222 |
BAT | -1.221 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
uity | +3.114 |
swaps | +3.085 |
risis | +3.018 |
millenn | +2.987 |
anguage | +2.941 |
Neg logit contributions | |
ット | -2.194 |
fil | -2.092 |
ignore | -1.895 |
BAT | -1.838 |
Boss | -1.835 |
Token | , |
Token ID | 11 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ット | +0.548 |
fil | +0.534 |
ignore | +0.476 |
fixed | +0.467 |
BAT | +0.464 |
Neg logit contributions | |
uity | -0.706 |
swaps | -0.692 |
risis | -0.686 |
millenn | -0.680 |
anguage | -0.666 |
Token | compared |
Token ID | 3688 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
uity | +1.568 |
swaps | +1.556 |
risis | +1.507 |
millenn | +1.492 |
oute | +1.468 |
Neg logit contributions | |
ット | -1.403 |
fil | -1.351 |
ignore | -1.224 |
BAT | -1.200 |
fixed | -1.194 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ット | +1.072 |
fil | +1.050 |
ignore | +0.924 |
fixed | +0.909 |
BAT | +0.902 |
Neg logit contributions | |
uity | -1.521 |
swaps | -1.490 |
risis | -1.485 |
millenn | -1.473 |
anguage | -1.443 |
Token |
|
Token ID | 198 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ット | +0.944 |
fil | +0.924 |
ignore | +0.827 |
fixed | +0.814 |
BAT | +0.808 |
Neg logit contributions | |
uity | -1.128 |
swaps | -1.104 |
risis | -1.097 |
millenn | -1.085 |
anguage | -1.062 |
Token |
|
Token ID | 198 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ット | +0.192 |
fil | +0.186 |
ignore | +0.166 |
fixed | +0.164 |
BAT | +0.163 |
Neg logit contributions | |
uity | -0.235 |
swaps | -0.230 |
risis | -0.229 |
oute | -0.221 |
anguage | -0.219 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
uity | +0.170 |
swaps | +0.165 |
risis | +0.165 |
millenn | +0.161 |
oute | +0.160 |
Neg logit contributions | |
ット | -0.135 |
fil | -0.130 |
ignore | -0.116 |
fixed | -0.114 |
HMS | -0.113 |
Token | by |
Token ID | 416 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ット | +1.388 |
fil | +1.362 |
ignore | +1.222 |
fixed | +1.205 |
BAT | +1.195 |
Neg logit contributions | |
uity | -1.481 |
swaps | -1.443 |
risis | -1.439 |
millenn | -1.420 |
anguage | -1.394 |
Token | John |
Token ID | 1757 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
uity | +2.290 |
swaps | +2.252 |
risis | +2.204 |
millenn | +2.181 |
anguage | +2.129 |
Neg logit contributions | |
ット | -2.177 |
fil | -2.095 |
ignore | -1.911 |
fixed | -1.888 |
BAT | -1.866 |
Token | Fore |
Token ID | 4558 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
uity | +1.589 |
swaps | +1.549 |
risis | +1.535 |
millenn | +1.495 |
oute | +1.485 |
Neg logit contributions | |
ット | -1.593 |
fil | -1.552 |
ignore | -1.415 |
fixed | -1.395 |
BAT | -1.391 |
Token | man |
Token ID | 805 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
uity | +4.424 |
risis | +4.322 |
swaps | +4.226 |
oute | +4.195 |
anguage | +4.162 |
Neg logit contributions | |
ット | -3.189 |
fil | -2.898 |
BAT | -2.654 |
ignore | -2.623 |
HMS | -2.617 |
Token | This |
Token ID | 770 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
uity | +1.332 |
swaps | +1.299 |
risis | +1.282 |
millenn | +1.264 |
oute | +1.246 |
Neg logit contributions | |
ット | -1.043 |
fil | -1.002 |
ignore | -0.904 |
fixed | -0.895 |
BAT | -0.890 |
Token | sequence |
Token ID | 8379 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
uity | +0.493 |
swaps | +0.483 |
risis | +0.478 |
millenn | +0.471 |
oute | +0.460 |
Neg logit contributions | |
ット | -0.462 |
fil | -0.451 |
ignore | -0.407 |
fixed | -0.400 |
BAT | -0.399 |
Token | takes |
Token ID | 2753 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
swaps | +1.993 |
uity | +1.921 |
risis | +1.848 |
oute | +1.777 |
urches | +1.705 |
Neg logit contributions | |
ット | -4.634 |
fil | -4.451 |
BAT | -4.187 |
ignore | -4.176 |
fixed | -4.146 |
Token | 1 |
Token ID | 352 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
uity | +0.906 |
swaps | +0.879 |
risis | +0.870 |
millenn | +0.828 |
oute | +0.820 |
Neg logit contributions | |
ット | -1.741 |
fil | -1.710 |
ignore | -1.584 |
fixed | -1.571 |
BAT | -1.563 |
Token | AL |
Token ID | 8355 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ット | +2.412 |
fil | +2.385 |
ignore | +2.058 |
HMS | +2.016 |
fixed | +2.016 |
Neg logit contributions | |
uity | -3.943 |
millenn | -3.869 |
swaps | -3.862 |
risis | -3.843 |
anguage | -3.795 |
Token | READ |
Token ID | 15675 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
uity | +3.889 |
swaps | +3.887 |
risis | +3.875 |
millenn | +3.780 |
oute | +3.767 |
Neg logit contributions | |
ット | -3.558 |
fil | -3.456 |
ignore | -3.104 |
fixed | -3.017 |
intention | -2.972 |
Token | Y |
Token ID | 56 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
swaps | +4.242 |
uity | +4.164 |
risis | +4.063 |
millenn | +3.944 |
ּ | +3.920 |
Neg logit contributions | |
ット | -5.550 |
fil | -5.291 |
ignore | -4.921 |
fixed | -4.857 |
intention | -4.724 |
Token | COMP |
Token ID | 24301 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
uity | +2.372 |
swaps | +2.347 |
risis | +2.292 |
millenn | +2.245 |
oute | +2.225 |
Neg logit contributions | |
ット | -2.076 |
fil | -1.988 |
ignore | -1.786 |
fixed | -1.760 |
BAT | -1.746 |
Token | ET |
Token ID | 2767 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ット | +1.203 |
fil | +1.182 |
ignore | +1.039 |
BAT | +1.028 |
fixed | +1.019 |
Neg logit contributions | |
uity | -1.735 |
swaps | -1.702 |
millenn | -1.687 |
risis | -1.687 |
anguage | -1.653 |
Token | ED |
Token ID | 1961 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
uity | +1.588 |
swaps | +1.542 |
risis | +1.539 |
millenn | +1.511 |
oute | +1.481 |
Neg logit contributions | |
ット | -1.322 |
fil | -1.287 |
ignore | -1.155 |
fixed | -1.131 |
above | -1.111 |
Token | : |
Token ID | 25 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
uity | +1.115 |
swaps | +1.098 |
risis | +1.087 |
millenn | +1.061 |
oute | +1.051 |
Neg logit contributions | |
ット | -0.871 |
fil | -0.843 |
ignore | -0.749 |
fixed | -0.742 |
Boss | -0.727 |
Token | at |
Token ID | 379 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
uity | +0.416 |
swaps | +0.408 |
risis | +0.403 |
millenn | +0.396 |
anguage | +0.387 |
Neg logit contributions | |
ット | -0.396 |
fil | -0.388 |
ignore | -0.348 |
fixed | -0.344 |
BAT | -0.342 |
Token | Arizona |
Token ID | 7943 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
uity | +3.124 |
swaps | +3.086 |
risis | +3.042 |
ּ | +2.921 |
oute | +2.902 |
Neg logit contributions | |
ット | -3.246 |
fil | -3.119 |
ignore | -2.837 |
fixed | -2.804 |
Boss | -2.783 |
Token | Cardinals |
Token ID | 18071 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ット | +0.210 |
fil | +0.205 |
ignore | +0.182 |
fixed | +0.179 |
BAT | +0.177 |
Neg logit contributions | |
uity | -0.281 |
swaps | -0.276 |
risis | -0.274 |
millenn | -0.271 |
anguage | -0.266 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
uity | +0.076 |
swaps | +0.074 |
risis | +0.074 |
millenn | +0.073 |
anguage | +0.071 |
Neg logit contributions | |
ット | -0.074 |
fil | -0.072 |
ignore | -0.065 |
fixed | -0.064 |
BAT | -0.063 |
Token | social |
Token ID | 1919 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ット | +0.866 |
fil | +0.853 |
ignore | +0.774 |
fixed | +0.765 |
BAT | +0.761 |
Neg logit contributions | |
uity | -0.764 |
swaps | -0.744 |
risis | -0.740 |
millenn | -0.732 |
anguage | -0.713 |
Token | justice |
Token ID | 5316 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
uity | +3.453 |
swaps | +3.424 |
risis | +3.298 |
millenn | +3.254 |
anguage | +3.237 |
Neg logit contributions | |
ット | -4.451 |
fil | -4.236 |
ignore | -3.894 |
Boss | -3.834 |
BAT | -3.833 |
Token | issue |
Token ID | 2071 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
uity | +0.716 |
swaps | +0.700 |
risis | +0.693 |
millenn | +0.683 |
anguage | +0.665 |
Neg logit contributions | |
ット | -0.978 |
fil | -0.953 |
ignore | -0.874 |
fixed | -0.864 |
BAT | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ット | +0.249 |
fil | +0.241 |
ignore | +0.215 |
fixed | +0.210 |
BAT | +0.210 |
Neg logit contributions | |
uity | -0.313 |
swaps | -0.307 |
risis | -0.305 |
millenn | -0.300 |
anguage | -0.295 |
Token | Athe |
Token ID | 27751 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
uity | +1.521 |
swaps | +1.482 |
risis | +1.476 |
ּ | +1.420 |
oute | +1.410 |
Neg logit contributions | |
ット | -1.486 |
fil | -1.443 |
ignore | -1.297 |
fixed | -1.294 |
BAT | -1.272 |
Token | ists |
Token ID | 1023 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
uity | +3.815 |
swaps | +3.508 |
risis | +3.469 |
anguage | +3.319 |
urches | +3.234 |
Neg logit contributions | |
ット | -10.774 |
fil | -10.447 |
HMS | -9.921 |
BAT | -9.834 |
sweet | -9.788 |
Token | are |
Token ID | 389 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
uity | +2.741 |
swaps | +2.679 |
risis | +2.657 |
millenn | +2.548 |
anguage | +2.547 |
Neg logit contributions | |
ット | -2.752 |
fil | -2.643 |
BAT | -2.385 |
fixed | -2.374 |
Boss | -2.354 |
Token | oppressed |
Token ID | 25765 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ット | +1.036 |
fil | +1.013 |
ignore | +0.913 |
fixed | +0.899 |
BAT | +0.894 |
Neg logit contributions | |
uity | -1.084 |
swaps | -1.061 |
risis | -1.052 |
millenn | -1.042 |
anguage | -1.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ット | +3.460 |
fil | +3.434 |
ignore | +3.023 |
fixed | +2.965 |
BAT | +2.928 |
Neg logit contributions | |
uity | -5.365 |
risis | -5.207 |
millenn | -5.195 |
swaps | -5.184 |
oute | -5.093 |
Token | persecuted |
Token ID | 37501 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ット | +0.949 |
fil | +0.924 |
ignore | +0.821 |
fixed | +0.810 |
BAT | +0.809 |
Neg logit contributions | |
uity | -1.156 |
swaps | -1.135 |
risis | -1.123 |
millenn | -1.109 |
anguage | -1.087 |
Token | is |
Token ID | 318 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
ット | +0.037 |
fil | +0.036 |
ignore | +0.033 |
fixed | +0.033 |
BAT | +0.032 |
Neg logit contributions | |
uity | -0.031 |
swaps | -0.030 |
risis | -0.030 |
millenn | -0.029 |
anguage | -0.028 |
Token | now |
Token ID | 783 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
uity | +0.031 |
swaps | +0.030 |
risis | +0.030 |
millenn | +0.029 |
anguage | +0.029 |
Neg logit contributions | |
ット | -0.032 |
fil | -0.031 |
ignore | -0.028 |
fixed | -0.028 |
BAT | -0.027 |
Token | an |
Token ID | 281 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
ット | +0.743 |
fil | +0.729 |
ignore | +0.658 |
fixed | +0.649 |
BAT | +0.645 |
Neg logit contributions | |
uity | -0.752 |
swaps | -0.734 |
risis | -0.730 |
millenn | -0.722 |
anguage | -0.705 |
Token | adviser |
Token ID | 12534 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ット | +3.013 |
fil | +2.966 |
ignore | +2.668 |
HMS | +2.654 |
fixed | +2.618 |
Neg logit contributions | |
uity | -3.005 |
risis | -2.939 |
swaps | -2.937 |
millenn | -2.933 |
anguage | -2.864 |
Token | to |
Token ID | 284 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ット | +1.285 |
fil | +1.261 |
ignore | +1.108 |
fixed | +1.086 |
BAT | +1.077 |
Neg logit contributions | |
uity | -1.895 |
swaps | -1.856 |
risis | -1.849 |
millenn | -1.840 |
anguage | -1.797 |
Token | Lib |
Token ID | 7980 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ット | +0.157 |
fil | +0.154 |
ignore | +0.139 |
fixed | +0.137 |
BAT | +0.136 |
Neg logit contributions | |
uity | -0.155 |
swaps | -0.151 |
risis | -0.150 |
millenn | -0.149 |
anguage | -0.145 |
Token | Dem |
Token ID | 1897 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
uity | +6.088 |
swaps | +5.664 |
risis | +5.437 |
oute | +5.221 |
aith | +5.106 |
Neg logit contributions | |
ット | -10.729 |
fil | -10.266 |
ignore | -9.773 |
HMS | -9.575 |
fixed | -9.484 |
Token | party |
Token ID | 2151 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
uity | +3.893 |
swaps | +3.840 |
risis | +3.742 |
millenn | +3.664 |
aith | +3.580 |
Neg logit contributions | |
ット | -4.968 |
fil | -4.831 |
ignore | -4.477 |
fixed | -4.463 |
BAT | -4.393 |
Token | leader |
Token ID | 3554 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
uity | +2.169 |
swaps | +2.124 |
risis | +2.096 |
millenn | +2.068 |
anguage | +1.999 |
Neg logit contributions | |
ット | -2.560 |
fil | -2.504 |
ignore | -2.285 |
fixed | -2.266 |
BAT | -2.248 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
uity | +3.188 |
swaps | +3.114 |
risis | +3.102 |
millenn | +3.034 |
anguage | +2.972 |
Neg logit contributions | |
ット | -3.196 |
fil | -3.113 |
ignore | -2.823 |
fixed | -2.788 |
BAT | -2.771 |
Token | Far |
Token ID | 6755 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
uity | +2.262 |
risis | +1.985 |
swaps | +1.889 |
oute | +1.791 |
anguage | +1.739 |
Neg logit contributions | |
ット | -9.640 |
fil | -9.414 |
ignore | -8.886 |
BAT | -8.714 |
fixed | -8.714 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
uity | +0.732 |
swaps | +0.717 |
risis | +0.712 |
millenn | +0.695 |
oute | +0.687 |
Neg logit contributions | |
ット | -0.623 |
fil | -0.602 |
ignore | -0.546 |
fixed | -0.537 |
BAT | -0.534 |
Token | 116 |
Token ID | 18298 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ット | +2.938 |
fil | +2.921 |
ignore | +2.500 |
fixed | +2.463 |
BAT | +2.380 |
Neg logit contributions | |
uity | -5.675 |
millenn | -5.655 |
swaps | -5.622 |
risis | -5.570 |
anguage | -5.492 |
Token | ] |
Token ID | 60 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ット | +1.852 |
fil | +1.822 |
ignore | +1.593 |
fixed | +1.568 |
BAT | +1.540 |
Neg logit contributions | |
uity | -2.825 |
millenn | -2.781 |
swaps | -2.780 |
risis | -2.767 |
anguage | -2.691 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ット | +0.939 |
fil | +0.922 |
ignore | +0.832 |
fixed | +0.820 |
BAT | +0.816 |
Neg logit contributions | |
uity | -0.933 |
swaps | -0.912 |
risis | -0.905 |
millenn | -0.903 |
anguage | -0.878 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
uity | +0.775 |
swaps | +0.751 |
risis | +0.750 |
oute | +0.724 |
ּ | +0.718 |
Neg logit contributions | |
ット | -0.672 |
fil | -0.645 |
ignore | -0.579 |
fixed | -0.572 |
BAT | -0.568 |
Token | Following |
Token ID | 14291 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
uity | +1.606 |
risis | +1.559 |
swaps | +1.539 |
oute | +1.511 |
aith | +1.486 |
Neg logit contributions | |
ット | -1.409 |
fil | -1.342 |
ignore | -1.214 |
HMS | -1.208 |
fixed | -1.187 |
Token | the |
Token ID | 262 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
swaps | +6.930 |
uity | +6.739 |
risis | +6.692 |
oute | +6.502 |
citizenship | +6.467 |
Neg logit contributions | |
ット | -8.562 |
fil | -8.184 |
ignore | -7.632 |
fixed | -7.476 |
Boss | -7.448 |
Token | season |
Token ID | 1622 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
uity | +1.841 |
swaps | +1.840 |
risis | +1.814 |
millenn | +1.760 |
oute | +1.734 |
Neg logit contributions | |
ット | -2.026 |
fil | -1.968 |
ignore | -1.787 |
fixed | -1.773 |
Boss | -1.746 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ット | +1.066 |
fil | +1.042 |
ignore | +0.928 |
fixed | +0.913 |
BAT | +0.907 |
Neg logit contributions | |
uity | -1.354 |
swaps | -1.327 |
risis | -1.319 |
millenn | -1.305 |
anguage | -1.277 |
Token | O |
Token ID | 440 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
uity | +0.579 |
swaps | +0.567 |
risis | +0.561 |
millenn | +0.550 |
oute | +0.538 |
Neg logit contributions | |
ット | -0.655 |
fil | -0.641 |
ignore | -0.585 |
fixed | -0.577 |
BAT | -0.574 |
Token | ka |
Token ID | 4914 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ット | +1.118 |
fil | +1.092 |
ignore | +0.961 |
fixed | +0.944 |
BAT | +0.936 |
Neg logit contributions | |
uity | -1.643 |
swaps | -1.611 |
risis | -1.602 |
millenn | -1.587 |
anguage | -1.556 |
Token | s |
Token ID | 82 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
uity | +1.402 |
swaps | +1.369 |
risis | +1.363 |
millenn | +1.340 |
anguage | +1.326 |
Neg logit contributions | |
ット | -1.105 |
fil | -1.074 |
ignore | -0.964 |
BAT | -0.946 |
fixed | -0.942 |
Token | first |
Token ID | 717 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
uity | +1.884 |
swaps | +1.861 |
risis | +1.832 |
millenn | +1.806 |
oute | +1.765 |
Neg logit contributions | |
ット | -2.010 |
fil | -1.958 |
ignore | -1.781 |
fixed | -1.763 |
BAT | -1.751 |
Token | legal |
Token ID | 2742 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
uity | +3.180 |
swaps | +3.121 |
risis | +3.080 |
millenn | +3.046 |
anguage | +2.976 |
Neg logit contributions | |
ット | -3.233 |
fil | -3.151 |
ignore | -2.862 |
BAT | -2.833 |
fixed | -2.831 |
Token | same |
Token ID | 976 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ット | +1.807 |
fil | +1.799 |
ignore | +1.617 |
fixed | +1.600 |
BAT | +1.580 |
Neg logit contributions | |
uity | -1.789 |
risis | -1.739 |
swaps | -1.723 |
millenn | -1.722 |
oute | -1.674 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
uity | +3.347 |
swaps | +3.297 |
risis | +3.253 |
millenn | +3.209 |
citizenship | +3.168 |
Neg logit contributions | |
ット | -2.012 |
fil | -1.920 |
ignore | -1.700 |
BAT | -1.678 |
fixed | -1.655 |
Token | sex |
Token ID | 8044 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
uity | +5.208 |
risis | +5.065 |
swaps | +5.055 |
citizenship | +4.939 |
aith | +4.933 |
Neg logit contributions | |
ット | -2.721 |
fil | -2.453 |
HMS | -2.212 |
BAT | -2.144 |
ignore | -2.118 |
Token | marriage |
Token ID | 4845 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
swaps | +4.929 |
citizenship | +4.842 |
uity | +4.547 |
risis | +4.489 |
aith | +4.423 |
Neg logit contributions | |
ット | -11.520 |
fil | -11.144 |
BAT | -10.494 |
above | -10.390 |
ignore | -10.354 |
Token | , |
Token ID | 11 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
swaps | +5.170 |
uity | +5.092 |
risis | +4.917 |
citizenship | +4.903 |
ּ | +4.617 |
Neg logit contributions | |
ット | -7.749 |
fil | -7.387 |
BAT | -6.789 |
Boss | -6.785 |
fixed | -6.759 |
Token | which |
Token ID | 543 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
uity | +2.964 |
swaps | +2.930 |
risis | +2.884 |
millenn | +2.830 |
anguage | +2.791 |
Neg logit contributions | |
ット | -2.813 |
fil | -2.710 |
ignore | -2.449 |
fixed | -2.435 |
Boss | -2.418 |
Token | was |
Token ID | 373 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
uity | +1.886 |
swaps | +1.864 |
risis | +1.825 |
millenn | +1.800 |
oute | +1.751 |
Neg logit contributions | |
ット | -2.279 |
fil | -2.221 |
ignore | -2.020 |
fixed | -2.002 |
BAT | -1.997 |
Token | recognized |
Token ID | 8018 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
uity | +2.882 |
swaps | +2.820 |
risis | +2.756 |
millenn | +2.716 |
anguage | +2.670 |
Neg logit contributions | |
ット | -3.137 |
fil | -3.012 |
ignore | -2.786 |
fixed | -2.732 |
Boss | -2.720 |
Token | at |
Token ID | 379 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ット | +0.540 |
fil | +0.530 |
ignore | +0.474 |
fixed | +0.464 |
BAT | +0.462 |
Neg logit contributions | |
uity | -0.651 |
swaps | -0.638 |
risis | -0.633 |
millenn | -0.629 |
anguage | -0.615 |
Token | a |
Token ID | 257 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
uity | +4.095 |
swaps | +4.021 |
risis | +3.976 |
millenn | +3.890 |
oute | +3.818 |
Neg logit contributions | |
ット | -4.344 |
fil | -4.141 |
ignore | -3.808 |
fixed | -3.790 |
BAT | -3.711 |
Token | Women |
Token ID | 6926 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uity | +2.304 |
swaps | +2.253 |
risis | +2.235 |
millenn | +2.199 |
oute | +2.115 |
Neg logit contributions | |
ット | -3.289 |
fil | -3.199 |
ignore | -2.959 |
fixed | -2.926 |
BAT | -2.892 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
uity | +4.457 |
risis | +4.351 |
swaps | +4.272 |
millenn | +4.187 |
aith | +4.169 |
Neg logit contributions | |
ット | -4.345 |
fil | -4.141 |
ignore | -3.838 |
fixed | -3.822 |
HMS | -3.713 |
Token | Aerospace |
Token ID | 43226 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
uity | +3.906 |
risis | +3.823 |
swaps | +3.763 |
ancial | +3.625 |
aith | +3.598 |
Neg logit contributions | |
ット | -4.125 |
fil | -3.932 |
ignore | -3.768 |
fixed | -3.609 |
BAT | -3.590 |
Token | breakfast |
Token ID | 12607 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
uity | +3.456 |
swaps | +3.364 |
risis | +3.361 |
millenn | +3.289 |
anguage | +3.219 |
Neg logit contributions | |
ット | -3.774 |
fil | -3.635 |
ignore | -3.326 |
fixed | -3.280 |
BAT | -3.260 |
Token | at |
Token ID | 379 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
uity | +7.261 |
swaps | +7.054 |
risis | +6.969 |
anguage | +6.765 |
millenn | +6.708 |
Neg logit contributions | |
ット | -7.090 |
fil | -6.708 |
fixed | -6.266 |
BAT | -6.167 |
ignore | -6.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
uity | +4.249 |
swaps | +4.120 |
risis | +4.117 |
millenn | +3.935 |
oute | +3.935 |
Neg logit contributions | |
ット | -4.549 |
fil | -4.401 |
ignore | -4.016 |
fixed | -3.996 |
BAT | -3.925 |
Token | US |
Token ID | 1294 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
uity | +3.128 |
swaps | +3.052 |
risis | +3.028 |
millenn | +2.939 |
oute | +2.891 |
Neg logit contributions | |
ット | -3.759 |
fil | -3.637 |
ignore | -3.337 |
fixed | -3.311 |
Boss | -3.265 |
Token | Capitol |
Token ID | 13241 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
uity | +1.127 |
swaps | +1.104 |
risis | +1.097 |
millenn | +1.081 |
anguage | +1.058 |
Neg logit contributions | |
ット | -1.041 |
fil | -1.018 |
ignore | -0.917 |
fixed | -0.903 |
BAT | -0.890 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
uity | +1.213 |
swaps | +1.187 |
risis | +1.180 |
millenn | +1.162 |
anguage | +1.139 |
Neg logit contributions | |
ット | -1.046 |
fil | -1.020 |
ignore | -0.917 |
fixed | -0.905 |
BAT | -0.895 |