Token | G |
Token ID | 38 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
LT | +0.084 |
ofi | +0.084 |
avorite | +0.079 |
/+ | +0.077 |
thel | +0.077 |
Neg logit contributions | |
uits | -0.071 |
| -0.069 |
Hyde | -0.069 |
ulic | -0.067 |
ongo | -0.067 |
Token | ED |
Token ID | 1961 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
uits | +1.019 |
| +0.994 |
Hyde | +0.989 |
ongo | +0.964 |
ulic | +0.961 |
Neg logit contributions | |
ofi | -1.036 |
LT | -1.028 |
avorite | -0.981 |
thel | -0.933 |
/+ | -0.932 |
Token | NET |
Token ID | 30502 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
LT | +3.606 |
ofi | +3.549 |
avorite | +3.271 |
/+ | +3.229 |
thel | +3.188 |
Neg logit contributions | |
uits | -3.754 |
| -3.595 |
Hyde | -3.581 |
ulic | -3.567 |
ongo | -3.539 |
Token | CALL |
Token ID | 42815 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ofi | +1.414 |
LT | +1.407 |
avorite | +1.350 |
/+ | +1.290 |
thel | +1.288 |
Neg logit contributions | |
uits | -1.076 |
| -1.042 |
Hyde | -1.035 |
ongo | -1.007 |
ulic | -1.002 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ofi | +1.682 |
LT | +1.677 |
avorite | +1.568 |
/+ | +1.484 |
thel | +1.477 |
Neg logit contributions | |
uits | -2.407 |
| -2.342 |
Hyde | -2.337 |
ulic | -2.292 |
ongo | -2.290 |
Token | : |
Token ID | 25 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ofi | +1.081 |
LT | +1.066 |
avorite | +1.029 |
thel | +0.963 |
/+ | +0.959 |
Neg logit contributions | |
uits | -1.272 |
| -1.250 |
Hyde | -1.241 |
ongo | -1.209 |
ulic | -1.204 |
Token | 05 |
Token ID | 8870 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
LT | +4.315 |
ofi | +4.189 |
avorite | +3.730 |
/+ | +3.707 |
WP | +3.516 |
Neg logit contributions | |
uits | -11.165 |
ulic | -10.819 |
Hyde | -10.730 |
ongo | -10.613 |
gebra | -10.499 |
Token | 42 |
Token ID | 3682 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
uits | +0.054 |
| +0.053 |
Hyde | +0.053 |
ongo | +0.052 |
ulic | +0.052 |
Neg logit contributions | |
ofi | -0.032 |
LT | -0.032 |
avorite | -0.030 |
thel | -0.028 |
/+ | -0.028 |
Token | z |
Token ID | 89 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
uits | +0.699 |
| +0.683 |
Hyde | +0.680 |
ongo | +0.660 |
ulic | +0.658 |
Neg logit contributions | |
ofi | -0.740 |
LT | -0.732 |
avorite | -0.705 |
thel | -0.668 |
/+ | -0.666 |
Token | SH |
Token ID | 6006 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
uits | +1.224 |
| +1.211 |
Hyde | +1.201 |
AES | +1.164 |
ongo | +1.159 |
Neg logit contributions | |
ofi | -1.252 |
LT | -1.223 |
avorite | -1.208 |
thel | -1.128 |
/+ | -1.116 |
Token | AM |
Token ID | 2390 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
ofi | +1.458 |
LT | +1.447 |
avorite | +1.384 |
/+ | +1.305 |
thel | +1.305 |
Neg logit contributions | |
uits | -1.555 |
| -1.518 |
Hyde | -1.510 |
ongo | -1.470 |
ulic | -1.468 |
Token | G |
Token ID | 38 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
uits | +0.769 |
| +0.752 |
Hyde | +0.746 |
ongo | +0.722 |
ulic | +0.719 |
Neg logit contributions | |
ofi | -0.976 |
LT | -0.965 |
avorite | -0.939 |
thel | -0.888 |
/+ | -0.884 |
Token | ED |
Token ID | 1961 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
uits | +1.555 |
| +1.523 |
Hyde | +1.512 |
ongo | +1.469 |
ulic | +1.463 |
Neg logit contributions | |
ofi | -1.631 |
LT | -1.612 |
avorite | -1.562 |
thel | -1.471 |
/+ | -1.464 |
Token | NET |
Token ID | 30502 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
LT | +3.518 |
ofi | +3.457 |
avorite | +3.198 |
/+ | +3.128 |
thel | +3.082 |
Neg logit contributions | |
uits | -4.114 |
Hyde | -3.945 |
| -3.944 |
ulic | -3.912 |
ongo | -3.888 |
Token | CALL |
Token ID | 42815 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
LT | +0.750 |
ofi | +0.738 |
/+ | +0.689 |
avorite | +0.671 |
thel | +0.669 |
Neg logit contributions | |
uits | -0.643 |
ulic | -0.603 |
ongo | -0.602 |
| -0.602 |
Hyde | -0.602 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
ofi | +1.482 |
LT | +1.471 |
avorite | +1.388 |
/+ | +1.296 |
thel | +1.295 |
Neg logit contributions | |
uits | -2.250 |
| -2.198 |
Hyde | -2.192 |
ongo | -2.145 |
ulic | -2.143 |
Token | : |
Token ID | 25 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
LT | +0.491 |
ofi | +0.488 |
avorite | +0.440 |
/+ | +0.439 |
thel | +0.434 |
Neg logit contributions | |
uits | -0.660 |
Hyde | -0.634 |
| -0.631 |
ulic | -0.629 |
ongo | -0.627 |
Token | 05 |
Token ID | 8870 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
LT | +3.926 |
ofi | +3.818 |
avorite | +3.458 |
/+ | +3.346 |
thel | +3.154 |
Neg logit contributions | |
uits | -11.313 |
ulic | -10.957 |
Hyde | -10.941 |
ongo | -10.777 |
gebra | -10.669 |
Token | 43 |
Token ID | 3559 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ofi | +0.468 |
LT | +0.462 |
avorite | +0.431 |
thel | +0.394 |
/+ | +0.393 |
Neg logit contributions | |
uits | -1.012 |
| -0.994 |
Hyde | -0.991 |
ongo | -0.971 |
ulic | -0.970 |
Token | z |
Token ID | 89 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
uits | +1.205 |
| +1.180 |
Hyde | +1.170 |
ongo | +1.139 |
ulic | +1.131 |
Neg logit contributions | |
ofi | -1.306 |
LT | -1.290 |
avorite | -1.255 |
thel | -1.180 |
/+ | -1.173 |
Token | ST |
Token ID | 3563 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
uits | +1.091 |
| +1.078 |
Hyde | +1.069 |
AES | +1.036 |
ongo | +1.033 |
Neg logit contributions | |
ofi | -1.080 |
LT | -1.057 |
avorite | -1.039 |
thel | -0.970 |
/+ | -0.961 |
Token | OW |
Token ID | 3913 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ofi | +0.583 |
LT | +0.575 |
avorite | +0.555 |
thel | +0.519 |
/+ | +0.516 |
Neg logit contributions | |
uits | -0.690 |
| -0.678 |
Hyde | -0.674 |
ongo | -0.657 |
ulic | -0.653 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
LT | +2.829 |
ofi | +2.784 |
/+ | +2.615 |
thel | +2.490 |
WP | +2.429 |
Neg logit contributions | |
uits | -4.614 |
�� | -4.542 |
Hyde | -4.451 |
ulic | -4.397 |
| -4.394 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
LT | +4.847 |
/+ | +4.594 |
ofi | +4.577 |
thel | +4.139 |
WP | +4.007 |
Neg logit contributions | |
�� | -9.189 |
uits | -8.549 |
�� | -8.522 |
ongo | -8.463 |
naissance | -8.429 |
Token | re |
Token ID | 302 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ofi | +2.900 |
LT | +2.734 |
/+ | +2.577 |
thel | +2.390 |
avorite | +2.168 |
Neg logit contributions | |
�� | -7.595 |
uits | -7.514 |
Hyde | -7.443 |
ongo | -7.339 |
| -7.300 |
Token | - |
Token ID | 12 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
LT | +2.547 |
ofi | +2.538 |
/+ | +2.316 |
thel | +2.259 |
WP | +2.187 |
Neg logit contributions | |
�� | -3.259 |
uits | -3.247 |
Hyde | -3.193 |
| -3.160 |
ulic | -3.149 |
Token | enter |
Token ID | 9255 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ofi | +2.830 |
LT | +2.710 |
/+ | +2.402 |
thel | +2.359 |
WP | +2.160 |
Neg logit contributions | |
�� | -5.610 |
uits | -5.446 |
Hyde | -5.409 |
ulic | -5.294 |
| -5.255 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
LT | +3.881 |
ofi | +3.821 |
/+ | +3.613 |
WP | +3.218 |
thel | +3.180 |
Neg logit contributions | |
�� | -8.744 |
�� | -8.380 |
uits | -8.117 |
ulic | -8.003 |
Hyde | -7.984 |
Token | You |
Token ID | 921 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
LT | +4.293 |
ofi | +4.288 |
/+ | +3.870 |
thel | +3.495 |
WP | +3.341 |
Neg logit contributions | |
�� | -10.364 |
uits | -10.074 |
ulic | -9.764 |
ongo | -9.677 |
| -9.554 |
Token | must |
Token ID | 1276 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ofi | +4.760 |
LT | +4.554 |
/+ | +4.212 |
thel | +3.919 |
avorite | +3.638 |
Neg logit contributions | |
uits | -7.925 |
�� | -7.833 |
Hyde | -7.622 |
ongo | -7.516 |
ulic | -7.424 |
Token | select |
Token ID | 2922 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
ofi | +2.803 |
LT | +2.709 |
/+ | +2.550 |
avorite | +2.434 |
thel | +2.397 |
Neg logit contributions | |
uits | -2.965 |
Hyde | -2.962 |
�� | -2.900 |
| -2.877 |
ulic | -2.861 |
Token | a |
Token ID | 257 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
LT | +3.788 |
ofi | +3.787 |
/+ | +3.454 |
WP | +3.153 |
thel | +3.079 |
Neg logit contributions | |
�� | -5.619 |
ulic | -5.519 |
uits | -5.434 |
Hyde | -5.417 |
| -5.309 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ofi | +2.984 |
LT | +2.878 |
/+ | +2.740 |
WP | +2.604 |
avorite | +2.571 |
Neg logit contributions | |
�� | -3.637 |
uits | -3.631 |
ulic | -3.586 |
Hyde | -3.555 |
| -3.518 |
Token | . |
Token ID | 13 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
LT | +2.672 |
ofi | +2.651 |
/+ | +2.462 |
thel | +2.369 |
WP | +2.287 |
Neg logit contributions | |
uits | -4.341 |
�� | -4.254 |
Hyde | -4.194 |
| -4.144 |
ulic | -4.125 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
LT | +4.774 |
ofi | +4.563 |
/+ | +4.490 |
thel | +4.110 |
WP | +3.958 |
Neg logit contributions | |
�� | -8.999 |
uits | -8.480 |
�� | -8.449 |
ongo | -8.356 |
naissance | -8.298 |
Token | re |
Token ID | 302 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ofi | +3.052 |
LT | +2.836 |
/+ | +2.696 |
thel | +2.515 |
avorite | +2.272 |
Neg logit contributions | |
�� | -7.820 |
uits | -7.769 |
Hyde | -7.669 |
ongo | -7.587 |
| -7.508 |
Token | - |
Token ID | 12 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
LT | +2.378 |
ofi | +2.372 |
/+ | +2.158 |
thel | +2.119 |
WP | +2.041 |
Neg logit contributions | |
uits | -2.978 |
�� | -2.967 |
Hyde | -2.924 |
| -2.892 |
ulic | -2.887 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ofi | +2.722 |
LT | +2.613 |
/+ | +2.303 |
thel | +2.273 |
WP | +2.082 |
Neg logit contributions | |
�� | -5.311 |
uits | -5.184 |
Hyde | -5.145 |
ulic | -5.023 |
| -4.995 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
LT | +3.663 |
ofi | +3.598 |
/+ | +3.363 |
thel | +3.045 |
WP | +3.040 |
Neg logit contributions | |
�� | -7.665 |
�� | -7.269 |
uits | -7.220 |
ulic | -7.098 |
Hyde | -7.080 |
Token | You |
Token ID | 921 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ofi | +4.293 |
LT | +4.291 |
/+ | +3.810 |
thel | +3.507 |
WP | +3.358 |
Neg logit contributions | |
�� | -10.250 |
uits | -9.939 |
ulic | -9.554 |
ongo | -9.538 |
Hyde | -9.433 |
Token | must |
Token ID | 1276 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ofi | +4.863 |
LT | +4.686 |
/+ | +4.324 |
thel | +4.044 |
avorite | +3.743 |
Neg logit contributions | |
uits | -8.006 |
�� | -7.893 |
Hyde | -7.662 |
ongo | -7.542 |
ulic | -7.478 |
Token | select |
Token ID | 2922 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ofi | +3.050 |
LT | +2.953 |
/+ | +2.775 |
avorite | +2.657 |
thel | +2.615 |
Neg logit contributions | |
Hyde | -3.233 |
uits | -3.232 |
�� | -3.168 |
| -3.133 |
ulic | -3.109 |
Token | a |
Token ID | 257 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
LT | +3.784 |
ofi | +3.760 |
/+ | +3.442 |
WP | +3.132 |
thel | +3.101 |
Neg logit contributions | |
�� | -5.477 |
ulic | -5.364 |
uits | -5.348 |
Hyde | -5.302 |
| -5.189 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
ofi | +2.935 |
LT | +2.840 |
/+ | +2.704 |
WP | +2.557 |
avorite | +2.539 |
Neg logit contributions | |
uits | -3.489 |
�� | -3.478 |
ulic | -3.434 |
Hyde | -3.428 |
| -3.352 |
Token | Thank |
Token ID | 10449 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ofi | +4.592 |
LT | +4.537 |
/+ | +4.105 |
avorite | +3.965 |
WP | +3.944 |
Neg logit contributions | |
Hyde | -5.098 |
uits | -4.991 |
�� | -4.952 |
| -4.826 |
ulic | -4.800 |
Token | you |
Token ID | 345 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
LT | +2.434 |
ofi | +2.397 |
/+ | +2.183 |
thel | +2.087 |
WP | +2.035 |
Neg logit contributions | |
uits | -4.512 |
Hyde | -4.347 |
�� | -4.317 |
| -4.315 |
ulic | -4.278 |
Token | for |
Token ID | 329 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ofi | +3.597 |
LT | +3.574 |
/+ | +3.276 |
thel | +3.145 |
WP | +3.011 |
Neg logit contributions | |
uits | -6.035 |
�� | -5.915 |
Hyde | -5.784 |
ulic | -5.642 |
ongo | -5.641 |
Token | signing |
Token ID | 8415 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ofi | +1.827 |
LT | +1.795 |
/+ | +1.606 |
avorite | +1.568 |
thel | +1.566 |
Neg logit contributions | |
uits | -3.298 |
Hyde | -3.239 |
| -3.168 |
�� | -3.137 |
ulic | -3.134 |
Token | up |
Token ID | 510 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
LT | +1.945 |
ofi | +1.925 |
/+ | +1.787 |
thel | +1.719 |
avorite | +1.680 |
Neg logit contributions | |
uits | -2.463 |
�� | -2.393 |
Hyde | -2.386 |
ulic | -2.378 |
| -2.341 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ofi | +0.330 |
LT | +0.328 |
avorite | +0.304 |
/+ | +0.296 |
thel | +0.294 |
Neg logit contributions | |
uits | -0.410 |
Hyde | -0.399 |
| -0.398 |
ulic | -0.389 |
ongo | -0.389 |
Token | For |
Token ID | 1114 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
LT | +3.663 |
ofi | +3.651 |
/+ | +3.453 |
WP | +2.870 |
Luck | +2.785 |
Neg logit contributions | |
uits | -10.925 |
�� | -10.706 |
�� | -10.543 |
ongo | -10.310 |
tymology | -10.188 |
Token | more |
Token ID | 517 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
LT | +3.050 |
ofi | +3.041 |
/+ | +2.715 |
thel | +2.570 |
WP | +2.404 |
Neg logit contributions | |
uits | -6.326 |
�� | -6.242 |
Hyde | -6.215 |
| -6.062 |
ulic | -6.047 |
Token | from |
Token ID | 422 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
LT | +2.980 |
ofi | +2.980 |
/+ | +2.768 |
thel | +2.667 |
WP | +2.582 |
Neg logit contributions | |
uits | -3.513 |
Hyde | -3.446 |
�� | -3.399 |
ulic | -3.380 |
| -3.308 |
Token | The |
Token ID | 383 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
ofi | +0.185 |
LT | +0.183 |
avorite | +0.169 |
thel | +0.164 |
/+ | +0.163 |
Neg logit contributions | |
uits | -0.250 |
Hyde | -0.243 |
| -0.242 |
ongo | -0.238 |
ulic | -0.237 |
Token | Nation |
Token ID | 8741 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ofi | +0.270 |
LT | +0.266 |
/+ | +0.239 |
thel | +0.235 |
avorite | +0.233 |
Neg logit contributions | |
uits | -0.430 |
Hyde | -0.413 |
ulic | -0.411 |
| -0.407 |
ongo | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
LT | +2.507 |
ofi | +2.474 |
/+ | +2.302 |
thel | +2.215 |
WP | +2.148 |
Neg logit contributions | |
uits | -3.955 |
�� | -3.856 |
Hyde | -3.829 |
| -3.774 |
ulic | -3.753 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
LT | +4.749 |
ofi | +4.514 |
/+ | +4.448 |
thel | +4.051 |
Tune | +3.901 |
Neg logit contributions | |
�� | -8.846 |
uits | -8.356 |
ongo | -8.244 |
�� | -8.210 |
naissance | -8.187 |
Token | re |
Token ID | 302 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ofi | +2.885 |
LT | +2.707 |
/+ | +2.547 |
thel | +2.372 |
avorite | +2.184 |
Neg logit contributions | |
�� | -7.120 |
uits | -7.112 |
Hyde | -7.050 |
ongo | -6.927 |
| -6.877 |
Token | - |
Token ID | 12 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
LT | +2.243 |
ofi | +2.240 |
/+ | +2.036 |
thel | +1.998 |
avorite | +1.941 |
Neg logit contributions | |
uits | -2.773 |
�� | -2.739 |
Hyde | -2.726 |
| -2.692 |
ulic | -2.688 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ofi | +2.626 |
LT | +2.529 |
/+ | +2.222 |
thel | +2.210 |
WP | +2.023 |
Neg logit contributions | |
�� | -4.988 |
uits | -4.914 |
Hyde | -4.866 |
ulic | -4.772 |
| -4.720 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
LT | +3.376 |
ofi | +3.369 |
/+ | +3.098 |
thel | +2.844 |
WP | +2.803 |
Neg logit contributions | |
�� | -6.858 |
uits | -6.496 |
�� | -6.455 |
Hyde | -6.399 |
ulic | -6.362 |
Token | You |
Token ID | 921 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
LT | +4.200 |
ofi | +4.185 |
/+ | +3.746 |
thel | +3.383 |
Tee | +3.267 |
Neg logit contributions | |
�� | -10.176 |
uits | -9.859 |
ulic | -9.479 |
ongo | -9.471 |
Hyde | -9.418 |
Token | must |
Token ID | 1276 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ofi | +4.694 |
LT | +4.480 |
/+ | +4.156 |
thel | +3.869 |
avorite | +3.581 |
Neg logit contributions | |
uits | -7.918 |
�� | -7.761 |
Hyde | -7.569 |
ulic | -7.405 |
ongo | -7.390 |
Token | select |
Token ID | 2922 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ofi | +2.779 |
LT | +2.684 |
/+ | +2.531 |
avorite | +2.413 |
thel | +2.372 |
Neg logit contributions | |
Hyde | -3.041 |
uits | -3.017 |
�� | -2.947 |
ulic | -2.917 |
| -2.915 |
Token | a |
Token ID | 257 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ofi | +3.918 |
LT | +3.886 |
/+ | +3.546 |
WP | +3.208 |
thel | +3.181 |
Neg logit contributions | |
�� | -5.695 |
ulic | -5.616 |
uits | -5.559 |
Hyde | -5.558 |
| -5.413 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
ofi | +2.974 |
LT | +2.866 |
/+ | +2.749 |
WP | +2.589 |
avorite | +2.578 |
Neg logit contributions | |
uits | -3.661 |
�� | -3.637 |
ulic | -3.619 |
Hyde | -3.592 |
| -3.489 |
Token | , |
Token ID | 11 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ofi | +0.660 |
LT | +0.657 |
/+ | +0.600 |
thel | +0.592 |
avorite | +0.587 |
Neg logit contributions | |
uits | -0.760 |
Hyde | -0.736 |
| -0.729 |
ulic | -0.723 |
ongo | -0.718 |
Token | involving |
Token ID | 7411 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ofi | +1.774 |
LT | +1.758 |
thel | +1.622 |
/+ | +1.566 |
avorite | +1.530 |
Neg logit contributions | |
uits | -3.970 |
| -3.940 |
ulic | -3.926 |
Hyde | -3.898 |
ongo | -3.841 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
uits | +1.458 |
| +1.432 |
Hyde | +1.420 |
ongo | +1.379 |
ulic | +1.372 |
Neg logit contributions | |
ofi | -1.529 |
LT | -1.510 |
avorite | -1.471 |
thel | -1.375 |
/+ | -1.370 |
Token | entire |
Token ID | 2104 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
uits | +1.486 |
| +1.448 |
Hyde | +1.442 |
ulic | +1.408 |
ongo | +1.405 |
Neg logit contributions | |
ofi | -1.325 |
LT | -1.312 |
avorite | -1.240 |
thel | -1.191 |
/+ | -1.182 |
Token | palm |
Token ID | 18057 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ofi | +0.707 |
LT | +0.685 |
avorite | +0.628 |
/+ | +0.609 |
thel | +0.607 |
Neg logit contributions | |
uits | -1.271 |
Hyde | -1.235 |
| -1.222 |
ongo | -1.207 |
ulic | -1.203 |
Token | opl |
Token ID | 20106 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ofi | +0.521 |
LT | +0.410 |
thel | +0.238 |
/+ | +0.192 |
avorite | +0.147 |
Neg logit contributions | |
Hyde | -5.147 |
uits | -5.127 |
| -5.111 |
�� | -5.068 |
AES | -5.047 |
Token | ant |
Token ID | 415 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ofi | +2.787 |
LT | +2.627 |
/+ | +2.311 |
thel | +2.198 |
WP | +1.590 |
Neg logit contributions | |
�� | -11.307 |
�� | -11.203 |
Hyde | -11.036 |
uits | -10.928 |
vul | -10.657 |
Token | ar |
Token ID | 283 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
ofi | +2.390 |
LT | +2.311 |
thel | +2.043 |
/+ | +2.028 |
avorite | +1.801 |
Neg logit contributions | |
uits | -5.639 |
Hyde | -5.552 |
�� | -5.532 |
AES | -5.429 |
| -5.405 |
Token | surfaces |
Token ID | 16649 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
ofi | +0.017 |
LT | +0.017 |
avorite | +0.016 |
/+ | +0.016 |
thel | +0.015 |
Neg logit contributions | |
uits | -0.015 |
Hyde | -0.014 |
| -0.014 |
ongo | -0.014 |
ulic | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ofi | +0.300 |
LT | +0.299 |
avorite | +0.270 |
/+ | +0.270 |
thel | +0.267 |
Neg logit contributions | |
uits | -0.390 |
Hyde | -0.379 |
| -0.376 |
ulic | -0.371 |
ongo | -0.370 |
Token | Type |
Token ID | 5994 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ofi | +2.051 |
LT | +2.032 |
avorite | +1.931 |
thel | +1.856 |
/+ | +1.849 |
Neg logit contributions | |
uits | -2.026 |
| -1.957 |
Hyde | -1.949 |
ulic | -1.908 |
ongo | -1.903 |
Token | whole |
Token ID | 2187 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ofi | +3.894 |
LT | +3.862 |
avorite | +3.633 |
thel | +3.495 |
/+ | +3.441 |
Neg logit contributions | |
uits | -4.232 |
| -4.125 |
Hyde | -4.044 |
ulic | -3.974 |
ongo | -3.951 |
Token | or |
Token ID | 393 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
ofi | +1.530 |
LT | +1.515 |
avorite | +1.426 |
thel | +1.363 |
/+ | +1.358 |
Neg logit contributions | |
uits | -1.832 |
Hyde | -1.780 |
| -1.777 |
ongo | -1.740 |
ulic | -1.725 |
Token | in |
Token ID | 287 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ofi | +0.571 |
LT | +0.564 |
avorite | +0.544 |
thel | +0.508 |
/+ | +0.507 |
Neg logit contributions | |
uits | -0.681 |
| -0.668 |
Hyde | -0.664 |
ongo | -0.647 |
ulic | -0.642 |
Token | part |
Token ID | 636 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ofi | +1.691 |
LT | +1.671 |
avorite | +1.600 |
thel | +1.509 |
/+ | +1.500 |
Neg logit contributions | |
uits | -1.908 |
| -1.871 |
Hyde | -1.856 |
ongo | -1.811 |
ulic | -1.808 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ofi | +1.878 |
LT | +1.853 |
avorite | +1.772 |
thel | +1.684 |
/+ | +1.675 |
Neg logit contributions | |
uits | -1.947 |
| -1.898 |
Hyde | -1.891 |
ongo | -1.844 |
ulic | -1.837 |
Token | is |
Token ID | 318 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
ofi | +1.795 |
LT | +1.774 |
avorite | +1.683 |
thel | +1.607 |
/+ | +1.590 |
Neg logit contributions | |
uits | -2.099 |
| -2.044 |
Hyde | -2.036 |
ongo | -1.988 |
ulic | -1.986 |
Token | strictly |
Token ID | 14084 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ofi | +6.223 |
LT | +6.019 |
avorite | +5.639 |
thel | +5.615 |
/+ | +5.444 |
Neg logit contributions | |
uits | -7.716 |
| -7.521 |
Hyde | -7.382 |
ulic | -7.286 |
ongo | -7.179 |
Token | prohibited |
Token ID | 12244 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ofi | +3.293 |
LT | +3.226 |
avorite | +3.104 |
thel | +2.967 |
/+ | +2.932 |
Neg logit contributions | |
uits | -3.411 |
| -3.346 |
Hyde | -3.312 |
ulic | -3.233 |
ongo | -3.223 |
Token | without |
Token ID | 1231 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ofi | +3.855 |
LT | +3.831 |
avorite | +3.554 |
/+ | +3.465 |
thel | +3.444 |
Neg logit contributions | |
uits | -4.877 |
Hyde | -4.711 |
| -4.699 |
ongo | -4.625 |
ulic | -4.613 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ofi | +2.597 |
LT | +2.563 |
avorite | +2.470 |
thel | +2.349 |
/+ | +2.315 |
Neg logit contributions | |
uits | -2.486 |
| -2.412 |
Hyde | -2.341 |
ulic | -2.328 |
ongo | -2.311 |
Token | express |
Token ID | 4911 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
ofi | +1.489 |
LT | +1.478 |
avorite | +1.417 |
thel | +1.354 |
/+ | +1.354 |
Neg logit contributions | |
uits | -1.348 |
| -1.307 |
Hyde | -1.288 |
ulic | -1.273 |
ongo | -1.259 |
Token | box |
Token ID | 3091 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
LT | +3.223 |
ofi | +3.194 |
/+ | +3.065 |
thel | +2.992 |
avorite | +2.843 |
Neg logit contributions | |
| -2.607 |
uits | -2.573 |
�� | -2.494 |
Hyde | -2.481 |
ongo | -2.452 |
Token | . |
Token ID | 13 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ofi | +1.351 |
LT | +1.351 |
/+ | +1.217 |
thel | +1.209 |
WP | +1.148 |
Neg logit contributions | |
uits | -1.974 |
| -1.907 |
�� | -1.903 |
Hyde | -1.898 |
ulic | -1.898 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
LT | +3.800 |
ofi | +3.771 |
/+ | +3.639 |
thel | +3.390 |
WP | +3.343 |
Neg logit contributions | |
uits | -3.934 |
�� | -3.864 |
ongo | -3.736 |
| -3.674 |
ulic | -3.662 |
Token | email |
Token ID | 3053 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ofi | +2.761 |
LT | +2.747 |
/+ | +2.600 |
thel | +2.485 |
avorite | +2.466 |
Neg logit contributions | |
uits | -3.033 |
Hyde | -2.979 |
�� | -2.964 |
| -2.952 |
ongo | -2.848 |
Token | address |
Token ID | 2209 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
ofi | +1.584 |
LT | +1.569 |
/+ | +1.481 |
thel | +1.468 |
avorite | +1.435 |
Neg logit contributions | |
uits | -1.250 |
| -1.198 |
Hyde | -1.195 |
�� | -1.180 |
ulic | -1.171 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
LT | +2.829 |
ofi | +2.784 |
/+ | +2.615 |
thel | +2.490 |
WP | +2.429 |
Neg logit contributions | |
uits | -4.614 |
�� | -4.542 |
Hyde | -4.451 |
ulic | -4.397 |
| -4.394 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
LT | +4.847 |
/+ | +4.594 |
ofi | +4.577 |
thel | +4.139 |
WP | +4.007 |
Neg logit contributions | |
�� | -9.189 |
uits | -8.549 |
�� | -8.522 |
ongo | -8.463 |
naissance | -8.429 |
Token | re |
Token ID | 302 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ofi | +2.900 |
LT | +2.734 |
/+ | +2.577 |
thel | +2.390 |
avorite | +2.168 |
Neg logit contributions | |
�� | -7.595 |
uits | -7.514 |
Hyde | -7.443 |
ongo | -7.339 |
| -7.300 |
Token | - |
Token ID | 12 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
LT | +2.547 |
ofi | +2.538 |
/+ | +2.316 |
thel | +2.259 |
WP | +2.187 |
Neg logit contributions | |
�� | -3.259 |
uits | -3.247 |
Hyde | -3.193 |
| -3.160 |
ulic | -3.149 |
Token | enter |
Token ID | 9255 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ofi | +2.830 |
LT | +2.710 |
/+ | +2.402 |
thel | +2.359 |
WP | +2.160 |
Neg logit contributions | |
�� | -5.610 |
uits | -5.446 |
Hyde | -5.409 |
ulic | -5.294 |
| -5.255 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
LT | +3.881 |
ofi | +3.821 |
/+ | +3.613 |
WP | +3.218 |
thel | +3.180 |
Neg logit contributions | |
�� | -8.744 |
�� | -8.380 |
uits | -8.117 |
ulic | -8.003 |
Hyde | -7.984 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ofi | +1.406 |
LT | +1.392 |
avorite | +1.323 |
thel | +1.266 |
/+ | +1.253 |
Neg logit contributions | |
uits | -1.437 |
| -1.394 |
Hyde | -1.377 |
ongo | -1.364 |
ulic | -1.361 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
uits | +0.840 |
| +0.821 |
Hyde | +0.817 |
ongo | +0.791 |
ulic | +0.787 |
Neg logit contributions | |
ofi | -0.929 |
LT | -0.918 |
avorite | -0.892 |
thel | -0.841 |
/+ | -0.838 |
Token | The |
Token ID | 464 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
ofi | +0.111 |
LT | +0.110 |
avorite | +0.106 |
thel | +0.100 |
/+ | +0.100 |
Neg logit contributions | |
uits | -0.108 |
| -0.106 |
Hyde | -0.105 |
ongo | -0.102 |
ulic | -0.102 |
Token | opinions |
Token ID | 9317 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ofi | +0.439 |
LT | +0.434 |
avorite | +0.419 |
thel | +0.396 |
/+ | +0.395 |
Neg logit contributions | |
uits | -0.415 |
| -0.405 |
Hyde | -0.401 |
ongo | -0.391 |
ulic | -0.390 |
Token | expressed |
Token ID | 6241 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ofi | +1.223 |
LT | +1.210 |
avorite | +1.167 |
thel | +1.107 |
/+ | +1.103 |
Neg logit contributions | |
uits | -1.094 |
| -1.068 |
Hyde | -1.063 |
ongo | -1.034 |
ulic | -1.030 |
Token | by |
Token ID | 416 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
ofi | +2.841 |
LT | +2.803 |
avorite | +2.675 |
thel | +2.565 |
/+ | +2.534 |
Neg logit contributions | |
uits | -3.455 |
Hyde | -3.416 |
| -3.358 |
ulic | -3.342 |
ongo | -3.337 |
Token | column |
Token ID | 5721 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ofi | +3.301 |
LT | +3.212 |
avorite | +3.078 |
/+ | +2.887 |
thel | +2.784 |
Neg logit contributions | |
uits | -10.197 |
ulic | -9.953 |
gebra | -9.920 |
ongo | -9.899 |
Hyde | -9.883 |
Token | ists |
Token ID | 1023 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ofi | +1.883 |
LT | +1.864 |
avorite | +1.800 |
/+ | +1.711 |
thel | +1.710 |
Neg logit contributions | |
uits | -1.627 |
| -1.591 |
Hyde | -1.585 |
ongo | -1.535 |
ulic | -1.532 |
Token | are |
Token ID | 389 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
LT | +1.227 |
ofi | +1.224 |
avorite | +1.139 |
/+ | +1.107 |
thel | +1.091 |
Neg logit contributions | |
uits | -1.519 |
Hyde | -1.503 |
ongo | -1.488 |
| -1.479 |
ulic | -1.475 |
Token | their |
Token ID | 511 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ofi | +3.921 |
LT | +3.848 |
avorite | +3.678 |
/+ | +3.599 |
thel | +3.599 |
Neg logit contributions | |
uits | -3.195 |
Hyde | -3.161 |
| -3.127 |
ongo | -3.043 |
ulic | -2.996 |
Token | own |
Token ID | 898 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
LT | +0.179 |
ofi | +0.179 |
avorite | +0.173 |
thel | +0.164 |
/+ | +0.163 |
Neg logit contributions | |
uits | -0.125 |
| -0.122 |
Hyde | -0.120 |
ongo | -0.118 |
ulic | -0.117 |
Token | G |
Token ID | 38 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
uits | +0.677 |
| +0.661 |
Hyde | +0.656 |
ongo | +0.636 |
ulic | +0.633 |
Neg logit contributions | |
ofi | -0.848 |
LT | -0.840 |
avorite | -0.813 |
thel | -0.772 |
/+ | -0.769 |
Token | ED |
Token ID | 1961 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
uits | +1.628 |
| +1.596 |
Hyde | +1.584 |
ongo | +1.538 |
ulic | +1.531 |
Neg logit contributions | |
ofi | -1.725 |
LT | -1.702 |
avorite | -1.657 |
thel | -1.556 |
/+ | -1.547 |
Token | NET |
Token ID | 30502 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
LT | +3.377 |
ofi | +3.317 |
avorite | +3.063 |
/+ | +2.987 |
thel | +2.948 |
Neg logit contributions | |
uits | -4.198 |
| -4.042 |
Hyde | -4.037 |
ulic | -4.007 |
ongo | -3.977 |
Token | CALL |
Token ID | 42815 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
LT | +1.064 |
ofi | +1.040 |
/+ | +0.976 |
WP | +0.946 |
thel | +0.942 |
Neg logit contributions | |
uits | -0.935 |
ulic | -0.878 |
ongo | -0.876 |
| -0.869 |
Hyde | -0.869 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ofi | +1.737 |
LT | +1.731 |
avorite | +1.616 |
/+ | +1.523 |
thel | +1.514 |
Neg logit contributions | |
uits | -2.734 |
| -2.662 |
Hyde | -2.657 |
ulic | -2.607 |
ongo | -2.604 |
Token | : |
Token ID | 25 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
LT | +0.700 |
ofi | +0.691 |
/+ | +0.624 |
thel | +0.614 |
avorite | +0.610 |
Neg logit contributions | |
uits | -0.965 |
Hyde | -0.925 |
ulic | -0.922 |
| -0.918 |
ongo | -0.917 |
Token | 0 |
Token ID | 657 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
LT | +3.522 |
ofi | +3.444 |
avorite | +3.097 |
/+ | +3.021 |
WP | +2.825 |
Neg logit contributions | |
uits | -10.146 |
ulic | -9.820 |
Hyde | -9.804 |
ongo | -9.652 |
| -9.526 |
Token | 551 |
Token ID | 43697 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
LT | +2.577 |
ofi | +2.575 |
avorite | +2.338 |
/+ | +2.273 |
thel | +2.248 |
Neg logit contributions | |
uits | -3.545 |
| -3.414 |
Hyde | -3.412 |
ongo | -3.363 |
ulic | -3.358 |
Token | z |
Token ID | 89 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
uits | +0.414 |
| +0.407 |
Hyde | +0.403 |
ongo | +0.392 |
AES | +0.388 |
Neg logit contributions | |
ofi | -0.461 |
LT | -0.453 |
avorite | -0.445 |
thel | -0.418 |
/+ | -0.414 |
Token | VOL |
Token ID | 38570 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
uits | +2.932 |
| +2.916 |
Hyde | +2.906 |
AES | +2.835 |
ongo | +2.776 |
Neg logit contributions | |
ofi | -2.932 |
avorite | -2.863 |
LT | -2.837 |
thel | -2.641 |
/+ | -2.599 |
Token | UN |
Token ID | 4944 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
LT | +0.328 |
ofi | +0.327 |
avorite | +0.299 |
/+ | +0.286 |
thel | +0.285 |
Neg logit contributions | |
uits | -0.535 |
Hyde | -0.523 |
| -0.522 |
ulic | -0.510 |
ongo | -0.510 |
Token | box |
Token ID | 3091 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
LT | +2.500 |
ofi | +2.486 |
/+ | +2.377 |
thel | +2.325 |
avorite | +2.247 |
Neg logit contributions | |
| -1.911 |
uits | -1.897 |
Hyde | -1.831 |
�� | -1.823 |
ongo | -1.799 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ofi | +1.037 |
LT | +1.034 |
/+ | +0.930 |
thel | +0.928 |
avorite | +0.896 |
Neg logit contributions | |
uits | -1.456 |
| -1.410 |
Hyde | -1.404 |
ulic | -1.395 |
ongo | -1.389 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
LT | +3.365 |
ofi | +3.361 |
/+ | +3.204 |
thel | +3.025 |
WP | +2.946 |
Neg logit contributions | |
uits | -3.373 |
�� | -3.325 |
ongo | -3.194 |
| -3.154 |
ulic | -3.135 |
Token | email |
Token ID | 3053 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ofi | +3.096 |
LT | +3.072 |
/+ | +2.924 |
thel | +2.786 |
avorite | +2.753 |
Neg logit contributions | |
uits | -3.511 |
Hyde | -3.445 |
�� | -3.427 |
| -3.407 |
ongo | -3.288 |
Token | address |
Token ID | 2209 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ofi | +1.086 |
LT | +1.075 |
/+ | +1.009 |
thel | +1.005 |
avorite | +1.000 |
Neg logit contributions | |
uits | -0.807 |
Hyde | -0.774 |
| -0.774 |
ongo | -0.753 |
ulic | -0.753 |
Token | . |
Token ID | 13 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
LT | +2.672 |
ofi | +2.651 |
/+ | +2.462 |
thel | +2.369 |
WP | +2.287 |
Neg logit contributions | |
uits | -4.341 |
�� | -4.254 |
Hyde | -4.194 |
| -4.144 |
ulic | -4.125 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
LT | +4.774 |
ofi | +4.563 |
/+ | +4.490 |
thel | +4.110 |
WP | +3.958 |
Neg logit contributions | |
�� | -8.999 |
uits | -8.480 |
�� | -8.449 |
ongo | -8.356 |
naissance | -8.298 |
Token | re |
Token ID | 302 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ofi | +3.052 |
LT | +2.836 |
/+ | +2.696 |
thel | +2.515 |
avorite | +2.272 |
Neg logit contributions | |
�� | -7.820 |
uits | -7.769 |
Hyde | -7.669 |
ongo | -7.587 |
| -7.508 |
Token | - |
Token ID | 12 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
LT | +2.378 |
ofi | +2.372 |
/+ | +2.158 |
thel | +2.119 |
WP | +2.041 |
Neg logit contributions | |
uits | -2.978 |
�� | -2.967 |
Hyde | -2.924 |
| -2.892 |
ulic | -2.887 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ofi | +2.722 |
LT | +2.613 |
/+ | +2.303 |
thel | +2.273 |
WP | +2.082 |
Neg logit contributions | |
�� | -5.311 |
uits | -5.184 |
Hyde | -5.145 |
ulic | -5.023 |
| -4.995 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
LT | +3.663 |
ofi | +3.598 |
/+ | +3.363 |
thel | +3.045 |
WP | +3.040 |
Neg logit contributions | |
�� | -7.665 |
�� | -7.269 |
uits | -7.220 |
ulic | -7.098 |
Hyde | -7.080 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
LT | +2.572 |
ofi | +2.556 |
/+ | +2.354 |
thel | +2.286 |
WP | +2.205 |
Neg logit contributions | |
uits | -4.085 |
�� | -3.960 |
Hyde | -3.941 |
| -3.892 |
ulic | -3.874 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
LT | +4.697 |
ofi | +4.528 |
/+ | +4.374 |
thel | +4.073 |
WP | +3.914 |
Neg logit contributions | |
�� | -8.327 |
uits | -7.975 |
ongo | -7.839 |
�� | -7.742 |
ulic | -7.737 |
Token | re |
Token ID | 302 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ofi | +2.994 |
LT | +2.812 |
/+ | +2.605 |
thel | +2.485 |
avorite | +2.334 |
Neg logit contributions | |
uits | -7.156 |
�� | -7.071 |
Hyde | -7.058 |
ongo | -6.957 |
ulic | -6.875 |
Token | - |
Token ID | 12 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ofi | +1.985 |
LT | +1.980 |
/+ | +1.793 |
thel | +1.773 |
avorite | +1.741 |
Neg logit contributions | |
uits | -2.389 |
Hyde | -2.341 |
�� | -2.339 |
| -2.317 |
ulic | -2.304 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ofi | +2.495 |
LT | +2.407 |
/+ | +2.112 |
thel | +2.101 |
avorite | +1.967 |
Neg logit contributions | |
�� | -4.537 |
uits | -4.502 |
Hyde | -4.443 |
ulic | -4.343 |
| -4.322 |
Token | . |
Token ID | 13 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
LT | +3.386 |
ofi | +3.363 |
/+ | +3.091 |
thel | +2.853 |
WP | +2.826 |
Neg logit contributions | |
�� | -6.692 |
uits | -6.393 |
�� | -6.313 |
ulic | -6.257 |
Hyde | -6.251 |
Token | You |
Token ID | 921 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ofi | +4.195 |
LT | +4.165 |
/+ | +3.668 |
thel | +3.457 |
WP | +3.253 |
Neg logit contributions | |
�� | -9.505 |
uits | -9.328 |
ongo | -8.980 |
ulic | -8.977 |
Hyde | -8.877 |
Token | must |
Token ID | 1276 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ofi | +4.589 |
LT | +4.441 |
/+ | +4.085 |
thel | +3.859 |
avorite | +3.627 |
Neg logit contributions | |
uits | -7.182 |
�� | -7.017 |
Hyde | -6.869 |
ongo | -6.776 |
ulic | -6.749 |
Token | select |
Token ID | 2922 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ofi | +2.499 |
LT | +2.427 |
/+ | +2.273 |
avorite | +2.206 |
thel | +2.161 |
Neg logit contributions | |
uits | -2.552 |
Hyde | -2.543 |
�� | -2.475 |
| -2.466 |
ulic | -2.445 |
Token | a |
Token ID | 257 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
LT | +3.690 |
ofi | +3.679 |
/+ | +3.354 |
WP | +3.061 |
thel | +3.039 |
Neg logit contributions | |
�� | -5.183 |
ulic | -5.120 |
uits | -5.100 |
Hyde | -5.066 |
| -4.952 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ofi | +2.823 |
LT | +2.734 |
/+ | +2.601 |
avorite | +2.469 |
WP | +2.468 |
Neg logit contributions | |
uits | -3.327 |
�� | -3.283 |
ulic | -3.268 |
Hyde | -3.261 |
| -3.168 |
Token | ON |
Token ID | 6177 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ofi | +2.035 |
LT | +2.030 |
avorite | +1.862 |
/+ | +1.799 |
thel | +1.773 |
Neg logit contributions | |
uits | -2.998 |
| -2.907 |
Hyde | -2.894 |
ulic | -2.869 |
ongo | -2.851 |
Token | ALL |
Token ID | 11096 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ofi | +1.205 |
LT | +1.201 |
avorite | +1.140 |
thel | +1.083 |
/+ | +1.081 |
Neg logit contributions | |
uits | -1.215 |
| -1.185 |
Hyde | -1.178 |
ulic | -1.147 |
ongo | -1.147 |
Token | PERSON |
Token ID | 46740 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
LT | +4.393 |
ofi | +4.360 |
avorite | +4.055 |
/+ | +3.982 |
thel | +3.975 |
Neg logit contributions | |
uits | -3.070 |
| -2.928 |
Hyde | -2.918 |
ulic | -2.895 |
ongo | -2.857 |
Token | EL |
Token ID | 3698 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
LT | +1.223 |
ofi | +1.219 |
avorite | +1.147 |
thel | +1.101 |
/+ | +1.099 |
Neg logit contributions | |
uits | -1.219 |
| -1.186 |
Hyde | -1.177 |
ongo | -1.152 |
ulic | -1.149 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
LT | +1.945 |
ofi | +1.937 |
avorite | +1.791 |
/+ | +1.727 |
thel | +1.717 |
Neg logit contributions | |
uits | -2.499 |
| -2.426 |
Hyde | -2.414 |
ulic | -2.373 |
ongo | -2.366 |
Token | : |
Token ID | 25 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
ofi | +0.822 |
LT | +0.811 |
avorite | +0.781 |
thel | +0.732 |
/+ | +0.729 |
Neg logit contributions | |
uits | -0.966 |
| -0.947 |
Hyde | -0.941 |
ongo | -0.917 |
ulic | -0.914 |
Token | 05 |
Token ID | 8870 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
LT | +3.956 |
ofi | +3.902 |
avorite | +3.509 |
/+ | +3.447 |
thel | +3.283 |
Neg logit contributions | |
uits | -9.609 |
ulic | -9.269 |
Hyde | -9.266 |
ongo | -9.148 |
gebra | -9.028 |
Token | 45 |
Token ID | 2231 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
LT | +1.608 |
ofi | +1.600 |
avorite | +1.477 |
/+ | +1.452 |
thel | +1.419 |
Neg logit contributions | |
uits | -2.028 |
Hyde | -1.959 |
| -1.952 |
ulic | -1.929 |
ongo | -1.923 |
Token | z |
Token ID | 89 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
uits | +0.646 |
| +0.631 |
Hyde | +0.628 |
ongo | +0.610 |
ulic | +0.608 |
Neg logit contributions | |
ofi | -0.682 |
LT | -0.675 |
avorite | -0.650 |
thel | -0.616 |
/+ | -0.614 |
Token | K |
Token ID | 509 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
uits | +1.104 |
| +1.090 |
Hyde | +1.082 |
AES | +1.048 |
ongo | +1.046 |
Neg logit contributions | |
ofi | -1.077 |
LT | -1.054 |
avorite | -1.035 |
thel | -0.966 |
/+ | -0.958 |
Token | USH |
Token ID | 27143 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
ofi | +0.280 |
LT | +0.276 |
avorite | +0.268 |
thel | +0.252 |
/+ | +0.251 |
Neg logit contributions | |
uits | -0.276 |
| -0.270 |
Hyde | -0.268 |
ongo | -0.261 |
ulic | -0.260 |
Token | box |
Token ID | 3091 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
LT | +2.656 |
ofi | +2.619 |
/+ | +2.525 |
thel | +2.445 |
avorite | +2.364 |
Neg logit contributions | |
| -2.112 |
uits | -2.085 |
Hyde | -2.035 |
�� | -2.001 |
ongo | -1.999 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ofi | +1.176 |
LT | +1.173 |
/+ | +1.056 |
thel | +1.052 |
avorite | +1.007 |
Neg logit contributions | |
uits | -1.678 |
| -1.623 |
Hyde | -1.618 |
ulic | -1.607 |
ongo | -1.600 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
LT | +3.154 |
ofi | +3.154 |
/+ | +3.031 |
thel | +2.836 |
WP | +2.763 |
Neg logit contributions | |
uits | -3.184 |
�� | -3.101 |
ongo | -3.025 |
| -2.980 |
ulic | -2.958 |
Token | email |
Token ID | 3053 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
ofi | +2.376 |
LT | +2.356 |
/+ | +2.228 |
thel | +2.142 |
avorite | +2.141 |
Neg logit contributions | |
uits | -2.510 |
Hyde | -2.467 |
| -2.436 |
�� | -2.417 |
ongo | -2.363 |
Token | address |
Token ID | 2209 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ofi | +0.495 |
LT | +0.490 |
/+ | +0.460 |
avorite | +0.459 |
thel | +0.457 |
Neg logit contributions | |
uits | -0.356 |
Hyde | -0.343 |
| -0.342 |
ulic | -0.332 |
ongo | -0.332 |
Token | . |
Token ID | 13 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
LT | +2.507 |
ofi | +2.474 |
/+ | +2.302 |
thel | +2.215 |
WP | +2.148 |
Neg logit contributions | |
uits | -3.955 |
�� | -3.856 |
Hyde | -3.829 |
| -3.774 |
ulic | -3.753 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
LT | +4.749 |
ofi | +4.514 |
/+ | +4.448 |
thel | +4.051 |
Tune | +3.901 |
Neg logit contributions | |
�� | -8.846 |
uits | -8.356 |
ongo | -8.244 |
�� | -8.210 |
naissance | -8.187 |
Token | re |
Token ID | 302 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ofi | +2.885 |
LT | +2.707 |
/+ | +2.547 |
thel | +2.372 |
avorite | +2.184 |
Neg logit contributions | |
�� | -7.120 |
uits | -7.112 |
Hyde | -7.050 |
ongo | -6.927 |
| -6.877 |
Token | - |
Token ID | 12 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
LT | +2.243 |
ofi | +2.240 |
/+ | +2.036 |
thel | +1.998 |
avorite | +1.941 |
Neg logit contributions | |
uits | -2.773 |
�� | -2.739 |
Hyde | -2.726 |
| -2.692 |
ulic | -2.688 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ofi | +2.626 |
LT | +2.529 |
/+ | +2.222 |
thel | +2.210 |
WP | +2.023 |
Neg logit contributions | |
�� | -4.988 |
uits | -4.914 |
Hyde | -4.866 |
ulic | -4.772 |
| -4.720 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
LT | +3.376 |
ofi | +3.369 |
/+ | +3.098 |
thel | +2.844 |
WP | +2.803 |
Neg logit contributions | |
�� | -6.858 |
uits | -6.496 |
�� | -6.455 |
Hyde | -6.399 |
ulic | -6.362 |
Token | G |
Token ID | 38 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
uits | +0.681 |
| +0.664 |
Hyde | +0.660 |
ongo | +0.639 |
ulic | +0.636 |
Neg logit contributions | |
ofi | -0.856 |
LT | -0.847 |
avorite | -0.821 |
thel | -0.779 |
/+ | -0.776 |
Token | ED |
Token ID | 1961 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
uits | +1.917 |
| +1.883 |
Hyde | +1.867 |
ongo | +1.810 |
ulic | +1.801 |
Neg logit contributions | |
ofi | -2.059 |
LT | -2.028 |
avorite | -1.988 |
thel | -1.859 |
/+ | -1.846 |
Token | NET |
Token ID | 30502 |
Feature activation | -4.65e-04 |
Pos logit contributions | |
LT | +3.012 |
ofi | +2.976 |
avorite | +2.758 |
/+ | +2.663 |
thel | +2.638 |
Neg logit contributions | |
uits | -3.805 |
| -3.680 |
Hyde | -3.675 |
ulic | -3.631 |
ongo | -3.608 |
Token | CALL |
Token ID | 42815 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
uits | +0.003 |
| +0.003 |
Hyde | +0.003 |
ongo | +0.003 |
ulic | +0.003 |
Neg logit contributions | |
LT | -0.004 |
ofi | -0.004 |
/+ | -0.003 |
avorite | -0.003 |
thel | -0.003 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ofi | +1.088 |
LT | +1.076 |
avorite | +1.023 |
thel | +0.952 |
/+ | +0.950 |
Neg logit contributions | |
uits | -1.615 |
| -1.583 |
Hyde | -1.576 |
ongo | -1.541 |
ulic | -1.537 |
Token | : |
Token ID | 25 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
uits | +0.282 |
Hyde | +0.273 |
| +0.272 |
ulic | +0.268 |
ongo | +0.268 |
Neg logit contributions | |
ofi | -0.218 |
LT | -0.218 |
avorite | -0.201 |
/+ | -0.195 |
thel | -0.194 |
Token | 05 |
Token ID | 8870 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
LT | +3.176 |
ofi | +3.121 |
avorite | +2.869 |
/+ | +2.683 |
thel | +2.511 |
Neg logit contributions | |
uits | -10.056 |
Hyde | -9.780 |
ulic | -9.730 |
ongo | -9.603 |
| -9.524 |
Token | 50 |
Token ID | 1120 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
ofi | +0.935 |
LT | +0.933 |
avorite | +0.866 |
/+ | +0.824 |
thel | +0.814 |
Neg logit contributions | |
uits | -1.432 |
Hyde | -1.393 |
| -1.392 |
ulic | -1.368 |
ongo | -1.367 |
Token | z |
Token ID | 89 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
uits | +0.521 |
| +0.509 |
Hyde | +0.507 |
ongo | +0.491 |
ulic | +0.491 |
Neg logit contributions | |
ofi | -0.546 |
LT | -0.541 |
avorite | -0.518 |
thel | -0.493 |
/+ | -0.492 |
Token | VOL |
Token ID | 38570 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
uits | +1.422 |
| +1.408 |
Hyde | +1.399 |
AES | +1.358 |
ongo | +1.348 |
Neg logit contributions | |
ofi | -1.365 |
LT | -1.332 |
avorite | -1.316 |
thel | -1.223 |
/+ | -1.211 |
Token | UN |
Token ID | 4944 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uits | +0.264 |
| +0.260 |
Hyde | +0.257 |
ongo | +0.250 |
AES | +0.250 |
Neg logit contributions | |
ofi | -0.233 |
LT | -0.227 |
avorite | -0.226 |
thel | -0.209 |
/+ | -0.206 |
Token | Last |
Token ID | 4586 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ofi | +1.213 |
LT | +1.200 |
avorite | +1.142 |
thel | +1.090 |
/+ | +1.083 |
Neg logit contributions | |
uits | -1.292 |
| -1.253 |
Hyde | -1.248 |
ulic | -1.226 |
ongo | -1.224 |
Token | updated |
Token ID | 6153 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ofi | +1.052 |
LT | +1.035 |
avorite | +0.988 |
/+ | +0.941 |
thel | +0.941 |
Neg logit contributions | |
uits | -1.168 |
Hyde | -1.136 |
| -1.129 |
ulic | -1.111 |
ongo | -1.109 |
Token | on |
Token ID | 319 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ofi | +1.173 |
LT | +1.158 |
avorite | +1.087 |
thel | +1.053 |
/+ | +1.047 |
Neg logit contributions | |
uits | -1.344 |
Hyde | -1.299 |
ulic | -1.282 |
| -1.273 |
ongo | -1.272 |
Token | Sat |
Token ID | 7031 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ofi | +0.099 |
LT | +0.098 |
avorite | +0.091 |
thel | +0.088 |
/+ | +0.088 |
Neg logit contributions | |
uits | -0.120 |
Hyde | -0.115 |
| -0.115 |
ulic | -0.114 |
ongo | -0.113 |
Token | , |
Token ID | 11 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ofi | +2.674 |
LT | +2.601 |
/+ | +2.371 |
thel | +2.365 |
avorite | +2.364 |
Neg logit contributions | |
uits | -3.092 |
Hyde | -3.002 |
| -2.950 |
ulic | -2.933 |
ongo | -2.929 |
Token | 13 |
Token ID | 1511 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
LT | +3.704 |
ofi | +3.638 |
/+ | +3.399 |
thel | +3.237 |
WP | +3.115 |
Neg logit contributions | |
uits | -5.264 |
�� | -5.086 |
ulic | -5.056 |
ongo | -4.992 |
gebra | -4.882 |
Token | Sep |
Token ID | 8621 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
LT | +6.482 |
ofi | +6.382 |
/+ | +5.886 |
thel | +5.765 |
WP | +5.574 |
Neg logit contributions | |
uits | -6.840 |
�� | -6.440 |
ulic | -6.339 |
ongo | -6.304 |
Hyde | -6.123 |
Token | , |
Token ID | 11 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
LT | +2.272 |
ofi | +2.262 |
avorite | +2.053 |
/+ | +2.046 |
thel | +2.019 |
Neg logit contributions | |
uits | -2.711 |
Hyde | -2.596 |
ongo | -2.573 |
| -2.569 |
ulic | -2.562 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
ofi | +0.173 |
LT | +0.172 |
avorite | +0.163 |
thel | +0.155 |
/+ | +0.154 |
Neg logit contributions | |
uits | -0.207 |
| -0.200 |
Hyde | -0.200 |
ulic | -0.197 |
ongo | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ofi | +0.046 |
LT | +0.045 |
avorite | +0.044 |
thel | +0.041 |
/+ | +0.041 |
Neg logit contributions | |
uits | -0.050 |
| -0.048 |
Hyde | -0.048 |
ongo | -0.047 |
ulic | -0.047 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
uits | +0.791 |
| +0.769 |
Hyde | +0.767 |
ulic | +0.751 |
ongo | +0.751 |
Neg logit contributions | |
ofi | -0.669 |
LT | -0.662 |
avorite | -0.632 |
thel | -0.597 |
/+ | -0.596 |
Token | send |
Token ID | 3758 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ofi | +1.041 |
LT | +1.018 |
/+ | +0.953 |
avorite | +0.950 |
thel | +0.938 |
Neg logit contributions | |
uits | -1.047 |
Hyde | -1.035 |
| -1.006 |
ongo | -0.986 |
�� | -0.985 |
Token | you |
Token ID | 345 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
ofi | +1.634 |
LT | +1.624 |
/+ | +1.447 |
avorite | +1.409 |
thel | +1.407 |
Neg logit contributions | |
uits | -2.743 |
Hyde | -2.669 |
| -2.668 |
ulic | -2.645 |
�� | -2.620 |
Token | three |
Token ID | 1115 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
LT | +3.654 |
ofi | +3.651 |
avorite | +3.388 |
thel | +3.356 |
/+ | +3.286 |
Neg logit contributions | |
uits | -5.333 |
Hyde | -5.234 |
| -5.126 |
ulic | -5.089 |
ongo | -5.084 |
Token | meaningful |
Token ID | 11570 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uits | +1.109 |
Hyde | +1.053 |
| +1.051 |
ulic | +1.027 |
ongo | +1.001 |
Neg logit contributions | |
ofi | -2.074 |
LT | -2.058 |
avorite | -1.984 |
thel | -1.924 |
/+ | -1.919 |
Token | actions |
Token ID | 4028 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
uits | +0.309 |
Hyde | +0.301 |
| +0.301 |
ulic | +0.290 |
ongo | +0.289 |
Neg logit contributions | |
ofi | -0.458 |
LT | -0.456 |
avorite | -0.435 |
/+ | -0.422 |
thel | -0.421 |
Token | you |
Token ID | 345 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
ofi | +2.253 |
LT | +2.248 |
/+ | +2.030 |
thel | +1.941 |
WP | +1.890 |
Neg logit contributions | |
uits | -4.186 |
�� | -4.161 |
ulic | -4.119 |
Hyde | -4.105 |
ongo | -4.086 |
Token | can |
Token ID | 460 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
LT | +4.399 |
ofi | +4.221 |
/+ | +3.827 |
thel | +3.731 |
WP | +3.331 |
Neg logit contributions | |
�� | -8.385 |
Hyde | -8.339 |
ongo | -8.262 |
uits | -8.248 |
| -8.049 |
Token | take |
Token ID | 1011 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ofi | +2.622 |
LT | +2.619 |
/+ | +2.371 |
thel | +2.304 |
avorite | +2.160 |
Neg logit contributions | |
uits | -4.099 |
�� | -4.089 |
Hyde | -4.045 |
| -3.918 |
ongo | -3.915 |
Token | each |
Token ID | 1123 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ofi | +2.279 |
LT | +2.242 |
/+ | +2.133 |
avorite | +2.133 |
thel | +2.089 |
Neg logit contributions | |
uits | -2.075 |
Hyde | -2.054 |
| -2.019 |
ulic | -2.009 |
�� | -1.987 |
Token | week |
Token ID | 1285 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
ofi | +1.024 |
LT | +1.017 |
/+ | +0.942 |
thel | +0.940 |
avorite | +0.937 |
Neg logit contributions | |
uits | -0.938 |
Hyde | -0.920 |
| -0.900 |
�� | -0.893 |
ulic | -0.889 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
uits | +0.403 |
| +0.394 |
Hyde | +0.393 |
ongo | +0.383 |
ulic | +0.382 |
Neg logit contributions | |
ofi | -0.336 |
LT | -0.333 |
avorite | -0.315 |
thel | -0.299 |
/+ | -0.299 |
Token | box |
Token ID | 3091 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
LT | +2.312 |
ofi | +2.290 |
/+ | +2.182 |
thel | +2.145 |
avorite | +2.087 |
Neg logit contributions | |
uits | -1.708 |
| -1.704 |
Hyde | -1.649 |
�� | -1.625 |
ongo | -1.623 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ofi | +1.001 |
LT | +0.996 |
/+ | +0.894 |
thel | +0.894 |
avorite | +0.868 |
Neg logit contributions | |
uits | -1.395 |
| -1.349 |
Hyde | -1.347 |
ulic | -1.335 |
ongo | -1.331 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
ofi | +2.865 |
LT | +2.858 |
/+ | +2.699 |
thel | +2.587 |
WP | +2.517 |
Neg logit contributions | |
uits | -2.676 |
�� | -2.579 |
ongo | -2.532 |
ulic | -2.472 |
| -2.459 |
Token | email |
Token ID | 3053 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
ofi | +2.804 |
LT | +2.779 |
/+ | +2.629 |
thel | +2.525 |
avorite | +2.516 |
Neg logit contributions | |
uits | -3.060 |
Hyde | -2.990 |
| -2.944 |
�� | -2.933 |
ongo | -2.863 |
Token | address |
Token ID | 2209 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ofi | +0.755 |
LT | +0.747 |
avorite | +0.700 |
/+ | +0.699 |
thel | +0.698 |
Neg logit contributions | |
uits | -0.543 |
Hyde | -0.521 |
| -0.520 |
ongo | -0.505 |
ulic | -0.505 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
LT | +2.572 |
ofi | +2.556 |
/+ | +2.354 |
thel | +2.286 |
WP | +2.205 |
Neg logit contributions | |
uits | -4.085 |
�� | -3.960 |
Hyde | -3.941 |
| -3.892 |
ulic | -3.874 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
LT | +4.697 |
ofi | +4.528 |
/+ | +4.374 |
thel | +4.073 |
WP | +3.914 |
Neg logit contributions | |
�� | -8.327 |
uits | -7.975 |
ongo | -7.839 |
�� | -7.742 |
ulic | -7.737 |
Token | re |
Token ID | 302 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ofi | +2.994 |
LT | +2.812 |
/+ | +2.605 |
thel | +2.485 |
avorite | +2.334 |
Neg logit contributions | |
uits | -7.156 |
�� | -7.071 |
Hyde | -7.058 |
ongo | -6.957 |
ulic | -6.875 |
Token | - |
Token ID | 12 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ofi | +1.985 |
LT | +1.980 |
/+ | +1.793 |
thel | +1.773 |
avorite | +1.741 |
Neg logit contributions | |
uits | -2.389 |
Hyde | -2.341 |
�� | -2.339 |
| -2.317 |
ulic | -2.304 |
Token | enter |
Token ID | 9255 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ofi | +2.495 |
LT | +2.407 |
/+ | +2.112 |
thel | +2.101 |
avorite | +1.967 |
Neg logit contributions | |
�� | -4.537 |
uits | -4.502 |
Hyde | -4.443 |
ulic | -4.343 |
| -4.322 |
Token | . |
Token ID | 13 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
LT | +3.386 |
ofi | +3.363 |
/+ | +3.091 |
thel | +2.853 |
WP | +2.826 |
Neg logit contributions | |
�� | -6.692 |
uits | -6.393 |
�� | -6.313 |
ulic | -6.257 |
Hyde | -6.251 |
Token | G |
Token ID | 38 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
LT | +1.048 |
ofi | +1.039 |
avorite | +0.955 |
/+ | +0.951 |
thel | +0.940 |
Neg logit contributions | |
uits | -0.932 |
Hyde | -0.895 |
| -0.893 |
ulic | -0.878 |
ongo | -0.876 |
Token | ED |
Token ID | 1961 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
uits | +0.722 |
| +0.704 |
Hyde | +0.701 |
ongo | +0.683 |
ulic | +0.681 |
Neg logit contributions | |
ofi | -0.731 |
LT | -0.726 |
avorite | -0.692 |
thel | -0.659 |
/+ | -0.658 |
Token | NET |
Token ID | 30502 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
LT | +4.138 |
ofi | +4.066 |
avorite | +3.708 |
/+ | +3.700 |
thel | +3.642 |
Neg logit contributions | |
uits | -4.329 |
ulic | -4.119 |
| -4.119 |
Hyde | -4.104 |
ongo | -4.076 |
Token | CALL |
Token ID | 42815 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ofi | +2.107 |
LT | +2.104 |
avorite | +1.999 |
/+ | +1.922 |
thel | +1.914 |
Neg logit contributions | |
uits | -1.671 |
| -1.611 |
Hyde | -1.601 |
ongo | -1.563 |
ulic | -1.556 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ofi | +1.938 |
LT | +1.932 |
avorite | +1.810 |
/+ | +1.725 |
thel | +1.718 |
Neg logit contributions | |
uits | -2.399 |
| -2.330 |
Hyde | -2.323 |
ulic | -2.278 |
ongo | -2.275 |
Token | : |
Token ID | 25 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
ofi | +1.167 |
LT | +1.152 |
avorite | +1.109 |
thel | +1.039 |
/+ | +1.034 |
Neg logit contributions | |
uits | -1.383 |
| -1.357 |
Hyde | -1.349 |
ongo | -1.314 |
ulic | -1.309 |
Token | 05 |
Token ID | 8870 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
LT | +3.637 |
ofi | +3.585 |
avorite | +3.132 |
/+ | +3.124 |
thel | +2.969 |
Neg logit contributions | |
uits | -9.297 |
ulic | -8.984 |
Hyde | -8.953 |
ongo | -8.858 |
gebra | -8.736 |
Token | 41 |
Token ID | 3901 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
| +2.278 |
Hyde | +2.244 |
uits | +2.231 |
AES | +2.165 |
ongo | +2.138 |
Neg logit contributions | |
avorite | -2.340 |
ofi | -2.313 |
LT | -2.205 |
thel | -2.090 |
/+ | -2.021 |
Token | z |
Token ID | 89 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
uits | +1.263 |
| +1.241 |
Hyde | +1.227 |
ongo | +1.196 |
ulic | +1.184 |
Neg logit contributions | |
ofi | -1.391 |
LT | -1.372 |
avorite | -1.346 |
thel | -1.258 |
/+ | -1.249 |
Token | BLACK |
Token ID | 31963 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
uits | +0.519 |
| +0.511 |
Hyde | +0.507 |
ongo | +0.492 |
AES | +0.490 |
Neg logit contributions | |
ofi | -0.507 |
LT | -0.499 |
avorite | -0.486 |
thel | -0.456 |
/+ | -0.453 |
Token | FO |
Token ID | 6080 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
uits | +0.440 |
| +0.433 |
Hyde | +0.431 |
ongo | +0.419 |
AES | +0.417 |
Neg logit contributions | |
ofi | -0.380 |
LT | -0.371 |
avorite | -0.362 |
thel | -0.338 |
/+ | -0.336 |
Token | . |
Token ID | 764 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
| +4.160 |
uits | +4.135 |
Hyde | +4.002 |
ongo | +3.881 |
AES | +3.808 |
Neg logit contributions | |
avorite | -7.655 |
ofi | -7.531 |
LT | -7.357 |
thel | -6.855 |
/+ | -6.796 |
Token | list |
Token ID | 1351 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
uits | +3.198 |
| +3.196 |
Hyde | +3.136 |
AES | +3.025 |
ongo | +2.990 |
Neg logit contributions | |
ofi | -5.421 |
LT | -5.323 |
avorite | -5.235 |
/+ | -4.992 |
thel | -4.962 |
Token | _ |
Token ID | 62 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
| +3.951 |
uits | +3.866 |
Hyde | +3.805 |
AES | +3.678 |
ongo | +3.651 |
Neg logit contributions | |
avorite | -6.493 |
ofi | -6.301 |
LT | -6.104 |
thel | -5.753 |
/+ | -5.638 |
Token | images |
Token ID | 17566 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
uits | +2.526 |
| +2.399 |
ongo | +2.251 |
Hyde | +2.238 |
ulic | +2.183 |
Neg logit contributions | |
ofi | -6.542 |
LT | -6.500 |
avorite | -6.479 |
thel | -6.074 |
/+ | -6.050 |
Token | ( |
Token ID | 357 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
| +3.401 |
uits | +3.352 |
Hyde | +3.279 |
AES | +3.154 |
ongo | +3.128 |
Neg logit contributions | |
avorite | -5.392 |
ofi | -5.354 |
LT | -5.235 |
thel | -4.884 |
/+ | -4.834 |
Token | args |
Token ID | 26498 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
uits | +2.319 |
| +2.289 |
Hyde | +2.279 |
AES | +2.217 |
ongo | +2.214 |
Neg logit contributions | |
ofi | -1.574 |
LT | -1.560 |
avorite | -1.512 |
thel | -1.375 |
/+ | -1.363 |
Token | [ |
Token ID | 685 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
| +7.309 |
uits | +7.069 |
Hyde | +7.058 |
ongo | +6.736 |
AES | +6.651 |
Neg logit contributions | |
ofi | -11.542 |
avorite | -11.282 |
LT | -10.481 |
thel | -10.039 |
/+ | -10.037 |
Token | " |
Token ID | 366 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
uits | +2.880 |
Hyde | +2.876 |
| +2.857 |
AES | +2.775 |
ongo | +2.761 |
Neg logit contributions | |
ofi | -3.456 |
avorite | -3.407 |
LT | -3.363 |
thel | -3.134 |
/+ | -3.105 |
Token | images |
Token ID | 17566 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
uits | +2.623 |
| +2.510 |
Hyde | +2.386 |
ongo | +2.375 |
ulic | +2.280 |
Neg logit contributions | |
ofi | -6.694 |
LT | -6.665 |
avorite | -6.625 |
thel | -6.209 |
/+ | -6.185 |
Token | " |
Token ID | 1 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
uits | +4.398 |
| +4.311 |
Hyde | +4.169 |
ongo | +4.030 |
AES | +3.983 |
Neg logit contributions | |
ofi | -5.822 |
avorite | -5.811 |
LT | -5.666 |
thel | -5.206 |
/+ | -5.113 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
uits | +3.565 |
| +3.542 |
Hyde | +3.476 |
ongo | +3.381 |
AES | +3.369 |
Neg logit contributions | |
ofi | -4.464 |
avorite | -4.398 |
LT | -4.290 |
thel | -3.998 |
/+ | -3.948 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
uits | +0.407 |
| +0.405 |
Hyde | +0.401 |
ongo | +0.387 |
AES | +0.385 |
Neg logit contributions | |
ofi | -0.426 |
LT | -0.421 |
avorite | -0.409 |
thel | -0.384 |
/+ | -0.381 |
Token |
|
Token ID | 198 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
uits | +0.082 |
Hyde | +0.079 |
| +0.078 |
ulic | +0.077 |
ongo | +0.077 |
Neg logit contributions | |
ofi | -0.071 |
LT | -0.071 |
avorite | -0.065 |
/+ | -0.064 |
thel | -0.064 |
Token | Google |
Token ID | 11708 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ofi | +0.226 |
LT | +0.223 |
avorite | +0.212 |
thel | +0.201 |
/+ | +0.200 |
Neg logit contributions | |
uits | -0.262 |
| -0.255 |
Hyde | -0.255 |
ongo | -0.248 |
ulic | -0.247 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ofi | +1.741 |
LT | +1.738 |
/+ | +1.626 |
thel | +1.533 |
WP | +1.521 |
Neg logit contributions | |
uits | -2.417 |
ulic | -2.278 |
Hyde | -2.255 |
ongo | -2.249 |
�� | -2.227 |
Token |
|
Token ID | 198 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
uits | +0.820 |
| +0.812 |
Hyde | +0.804 |
ongo | +0.773 |
AES | +0.771 |
Neg logit contributions | |
ofi | -1.026 |
LT | -1.013 |
avorite | -0.984 |
thel | -0.938 |
/+ | -0.925 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
| +4.250 |
Hyde | +4.085 |
uits | +4.052 |
AES | +3.904 |
ongo | +3.901 |
Neg logit contributions | |
avorite | -5.472 |
ofi | -5.192 |
LT | -5.034 |
thel | -4.702 |
/+ | -4.506 |
Token | Ol |
Token ID | 30098 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
| +7.947 |
ongo | +7.550 |
uits | +7.414 |
Hyde | +7.387 |
ong | +7.080 |
Neg logit contributions | |
avorite | -9.607 |
ofi | -8.515 |
LT | -8.295 |
thel | -8.022 |
/+ | -7.808 |
Token | we |
Token ID | 732 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
ofi | +1.632 |
LT | +1.600 |
avorite | +1.541 |
thel | +1.471 |
/+ | +1.448 |
Neg logit contributions | |
uits | -1.698 |
| -1.667 |
Hyde | -1.662 |
ulic | -1.610 |
AES | -1.610 |
Token | us |
Token ID | 385 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
uits | +0.015 |
Hyde | +0.015 |
| +0.015 |
AES | +0.014 |
ongo | +0.014 |
Neg logit contributions | |
ofi | -0.014 |
LT | -0.014 |
avorite | -0.013 |
thel | -0.013 |
/+ | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
uits | +0.626 |
| +0.610 |
Hyde | +0.607 |
ulic | +0.592 |
ongo | +0.592 |
Neg logit contributions | |
ofi | -0.601 |
LT | -0.595 |
avorite | -0.561 |
/+ | -0.541 |
thel | -0.539 |
Token | D |
Token ID | 360 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
uits | +0.297 |
| +0.286 |
Hyde | +0.283 |
ulic | +0.282 |
ongo | +0.281 |
Neg logit contributions | |
ofi | -0.239 |
LT | -0.237 |
avorite | -0.219 |
/+ | -0.214 |
thel | -0.213 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
ofi | +0.822 |
LT | +0.812 |
avorite | +0.784 |
thel | +0.738 |
/+ | +0.735 |
Neg logit contributions | |
uits | -0.843 |
| -0.826 |
Hyde | -0.821 |
ongo | -0.799 |
ulic | -0.795 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
LT | +0.278 |
ofi | +0.278 |
/+ | +0.252 |
avorite | +0.249 |
thel | +0.249 |
Neg logit contributions | |
uits | -0.329 |
Hyde | -0.317 |
| -0.313 |
ulic | -0.312 |
ongo | -0.309 |
Token | Google |
Token ID | 11708 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
LT | +0.728 |
ofi | +0.728 |
avorite | +0.656 |
/+ | +0.647 |
thel | +0.644 |
Neg logit contributions | |
uits | -0.939 |
Hyde | -0.907 |
| -0.897 |
ulic | -0.887 |
AES | -0.880 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ofi | +1.720 |
LT | +1.711 |
/+ | +1.603 |
thel | +1.513 |
WP | +1.499 |
Neg logit contributions | |
uits | -2.374 |
ulic | -2.235 |
Hyde | -2.215 |
ongo | -2.206 |
�� | -2.183 |
Token |
|
Token ID | 198 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
uits | +0.958 |
| +0.952 |
Hyde | +0.942 |
ongo | +0.907 |
AES | +0.907 |
Neg logit contributions | |
ofi | -1.111 |
LT | -1.096 |
avorite | -1.062 |
thel | -1.013 |
/+ | -0.996 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
| +3.695 |
uits | +3.571 |
Hyde | +3.570 |
ongo | +3.425 |
AES | +3.419 |
Neg logit contributions | |
avorite | -4.519 |
ofi | -4.352 |
LT | -4.232 |
thel | -3.933 |
/+ | -3.795 |
Token | Park |
Token ID | 25478 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
| +7.766 |
ongo | +7.341 |
uits | +7.258 |
Hyde | +7.222 |
ong | +6.890 |
Neg logit contributions | |
avorite | -9.337 |
ofi | -8.329 |
LT | -8.120 |
thel | -7.818 |
/+ | -7.644 |
Token | er |
Token ID | 263 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
uits | +0.609 |
| +0.597 |
Hyde | +0.597 |
ongo | +0.577 |
ulic | +0.572 |
Neg logit contributions | |
ofi | -0.725 |
LT | -0.717 |
avorite | -0.702 |
/+ | -0.657 |
thel | -0.657 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
uits | +0.254 |
| +0.249 |
Hyde | +0.249 |
ongo | +0.241 |
ulic | +0.240 |
Neg logit contributions | |
ofi | -0.270 |
LT | -0.268 |
avorite | -0.261 |
thel | -0.244 |
/+ | -0.244 |
Token | A |
Token ID | 317 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
LT | +1.168 |
ofi | +1.156 |
/+ | +1.057 |
thel | +1.042 |
avorite | +1.038 |
Neg logit contributions | |
uits | -1.407 |
ulic | -1.351 |
ongo | -1.335 |
| -1.335 |
Hyde | -1.309 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ofi | +2.632 |
LT | +2.605 |
avorite | +2.480 |
thel | +2.351 |
/+ | +2.311 |
Neg logit contributions | |
uits | -3.404 |
| -3.339 |
Hyde | -3.311 |
ongo | -3.233 |
AES | -3.219 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
| +1.837 |
uits | +1.829 |
Hyde | +1.792 |
ongo | +1.700 |
ulic | +1.698 |
Neg logit contributions | |
LT | -2.101 |
ofi | -2.093 |
avorite | -2.047 |
thel | -1.922 |
/+ | -1.918 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
uits | +1.036 |
| +1.027 |
Hyde | +1.020 |
ongo | +0.977 |
AES | +0.971 |
Neg logit contributions | |
ofi | -1.125 |
LT | -1.116 |
avorite | -1.082 |
thel | -1.016 |
/+ | -1.013 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
uits | +1.444 |
| +1.428 |
Hyde | +1.416 |
ongo | +1.361 |
AES | +1.358 |
Neg logit contributions | |
ofi | -1.324 |
LT | -1.311 |
avorite | -1.268 |
thel | -1.185 |
/+ | -1.184 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
| +3.983 |
uits | +3.750 |
Hyde | +3.740 |
ongo | +3.456 |
AES | +3.380 |
Neg logit contributions | |
LT | -7.000 |
ofi | -6.927 |
avorite | -6.727 |
/+ | -6.475 |
thel | -6.300 |
Token | Diane |
Token ID | 26542 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
| +2.532 |
uits | +2.497 |
Hyde | +2.496 |
AES | +2.314 |
ongo | +2.272 |
Neg logit contributions | |
LT | -4.783 |
avorite | -4.777 |
ofi | -4.737 |
thel | -4.469 |
/+ | -4.355 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
uits | +2.623 |
| +2.569 |
Hyde | +2.560 |
ongo | +2.402 |
ulic | +2.400 |
Neg logit contributions | |
avorite | -3.982 |
ofi | -3.976 |
LT | -3.960 |
thel | -3.733 |
/+ | -3.612 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Hyde | +7.014 |
uits | +7.003 |
| +6.953 |
ongo | +6.585 |
AES | +6.446 |
Neg logit contributions | |
avorite | -8.465 |
ofi | -8.138 |
LT | -7.995 |
thel | -7.461 |
PDATE | -7.286 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
| +4.837 |
Hyde | +4.705 |
uits | +4.627 |
ongo | +4.553 |
ulic | +4.306 |
Neg logit contributions | |
avorite | -7.647 |
ofi | -7.366 |
LT | -6.918 |
thel | -6.768 |
PDATE | -6.581 |
Token | : |
Token ID | 25 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
uits | +4.261 |
Hyde | +4.133 |
| +4.065 |
ongo | +3.966 |
ulic | +3.807 |
Neg logit contributions | |
ofi | -5.694 |
avorite | -5.675 |
LT | -5.673 |
thel | -5.356 |
/+ | -5.048 |
Token | ' |
Token ID | 705 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
Hyde | +4.707 |
AES | +4.196 |
uits | +4.141 |
| +4.042 |
ongo | +4.020 |
Neg logit contributions | |
avorite | -8.016 |
LT | -7.957 |
ofi | -7.693 |
thel | -7.329 |
WP | -7.082 |
Token | I |
Token ID | 40 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
uits | +5.800 |
Hyde | +5.669 |
| +5.661 |
ongo | +5.486 |
ulic | +5.426 |
Neg logit contributions | |
ofi | -6.316 |
LT | -6.210 |
avorite | -6.139 |
thel | -5.698 |
/+ | -5.692 |
Token | the |
Token ID | 262 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
uits | +1.453 |
| +1.427 |
Hyde | +1.423 |
AES | +1.370 |
ongo | +1.366 |
Neg logit contributions | |
ofi | -1.701 |
LT | -1.678 |
avorite | -1.646 |
thel | -1.539 |
/+ | -1.531 |
Token | old |
Token ID | 1468 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
uits | +0.341 |
| +0.335 |
Hyde | +0.333 |
ongo | +0.322 |
AES | +0.321 |
Neg logit contributions | |
ofi | -0.385 |
LT | -0.380 |
avorite | -0.369 |
thel | -0.349 |
/+ | -0.346 |
Token | D |
Token ID | 360 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ofi | +0.403 |
LT | +0.398 |
avorite | +0.384 |
thel | +0.363 |
/+ | +0.362 |
Neg logit contributions | |
uits | -0.392 |
| -0.384 |
Hyde | -0.381 |
ongo | -0.371 |
ulic | -0.369 |
Token | FW |
Token ID | 24160 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ofi | +1.145 |
LT | +1.134 |
avorite | +1.092 |
thel | +1.032 |
/+ | +1.029 |
Neg logit contributions | |
uits | -1.101 |
| -1.078 |
Hyde | -1.072 |
ongo | -1.040 |
ulic | -1.036 |
Token | I |
Token ID | 40 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
uits | +0.075 |
| +0.073 |
Hyde | +0.073 |
ongo | +0.071 |
ulic | +0.071 |
Neg logit contributions | |
ofi | -0.077 |
LT | -0.076 |
avorite | -0.074 |
thel | -0.069 |
/+ | -0.069 |
Token | ( |
Token ID | 357 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ofi | +0.039 |
LT | +0.039 |
avorite | +0.037 |
thel | +0.035 |
/+ | +0.035 |
Neg logit contributions | |
uits | -0.037 |
| -0.036 |
Hyde | -0.036 |
ongo | -0.035 |
ulic | -0.035 |
Token | Don |
Token ID | 3987 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
| +7.014 |
ongo | +6.988 |
uits | +6.968 |
Hyde | +6.768 |
ulic | +6.616 |
Neg logit contributions | |
ofi | -7.691 |
avorite | -7.416 |
LT | -7.217 |
thel | -6.645 |
/+ | -6.618 |
Token | 't |
Token ID | 470 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
uits | +1.576 |
Hyde | +1.547 |
| +1.536 |
ongo | +1.491 |
ulic | +1.482 |
Neg logit contributions | |
ofi | -1.628 |
LT | -1.617 |
avorite | -1.594 |
thel | -1.475 |
/+ | -1.467 |
Token | F |
Token ID | 376 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
uits | +0.639 |
| +0.627 |
Hyde | +0.624 |
ongo | +0.604 |
ulic | +0.601 |
Neg logit contributions | |
ofi | -0.627 |
LT | -0.618 |
avorite | -0.600 |
thel | -0.563 |
/+ | -0.557 |
Token | --- |
Token ID | 6329 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ofi | +2.329 |
LT | +2.304 |
avorite | +2.217 |
/+ | +2.132 |
thel | +2.120 |
Neg logit contributions | |
uits | -1.699 |
| -1.668 |
Hyde | -1.662 |
ulic | -1.613 |
ongo | -1.593 |
Token | with |
Token ID | 351 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ofi | +0.350 |
LT | +0.346 |
avorite | +0.334 |
thel | +0.314 |
/+ | +0.313 |
Neg logit contributions | |
uits | -0.359 |
| -0.352 |
Hyde | -0.350 |
ongo | -0.340 |
ulic | -0.338 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
uits | +1.385 |
| +1.377 |
Hyde | +1.345 |
ulic | +1.296 |
ongo | +1.288 |
Neg logit contributions | |
ofi | -1.673 |
LT | -1.661 |
avorite | -1.611 |
thel | -1.526 |
/+ | -1.512 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
uits | +0.770 |
Hyde | +0.756 |
| +0.756 |
AES | +0.725 |
ongo | +0.724 |
Neg logit contributions | |
ofi | -0.899 |
LT | -0.892 |
avorite | -0.864 |
thel | -0.814 |
/+ | -0.814 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
uits | +1.770 |
| +1.745 |
Hyde | +1.733 |
ongo | +1.678 |
ulic | +1.669 |
Neg logit contributions | |
ofi | -1.528 |
LT | -1.510 |
avorite | -1.469 |
thel | -1.362 |
/+ | -1.354 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
| +3.383 |
Hyde | +3.214 |
uits | +3.194 |
ongo | +3.024 |
AES | +2.967 |
Neg logit contributions | |
LT | -6.203 |
avorite | -6.098 |
ofi | -6.093 |
/+ | -5.747 |
thel | -5.619 |
Token | Diane |
Token ID | 26542 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
| +2.459 |
uits | +2.434 |
Hyde | +2.419 |
AES | +2.252 |
ongo | +2.229 |
Neg logit contributions | |
LT | -4.517 |
avorite | -4.489 |
ofi | -4.489 |
thel | -4.193 |
/+ | -4.113 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uits | +2.504 |
| +2.472 |
Hyde | +2.451 |
ongo | +2.309 |
ulic | +2.299 |
Neg logit contributions | |
ofi | -3.726 |
LT | -3.717 |
avorite | -3.711 |
thel | -3.479 |
/+ | -3.386 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
Hyde | +6.785 |
uits | +6.728 |
| +6.716 |
ongo | +6.391 |
AES | +6.234 |
Neg logit contributions | |
avorite | -8.066 |
ofi | -7.762 |
LT | -7.665 |
thel | -7.080 |
PDATE | -6.864 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
| +4.807 |
uits | +4.642 |
Hyde | +4.605 |
ongo | +4.547 |
ulic | +4.297 |
Neg logit contributions | |
avorite | -7.263 |
ofi | -7.036 |
LT | -6.682 |
thel | -6.430 |
/+ | -6.267 |
Token | : |
Token ID | 25 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
uits | +4.242 |
Hyde | +4.102 |
| +4.056 |
ongo | +3.968 |
ulic | +3.762 |
Neg logit contributions | |
ofi | -5.704 |
LT | -5.697 |
avorite | -5.644 |
thel | -5.357 |
/+ | -5.033 |
Token | ' |
Token ID | 705 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
Hyde | +4.575 |
AES | +4.098 |
uits | +4.010 |
ongo | +3.916 |
| +3.911 |
Neg logit contributions | |
LT | -7.769 |
avorite | -7.753 |
ofi | -7.504 |
thel | -7.091 |
WP | -6.862 |
Token | I |
Token ID | 40 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
uits | +5.956 |
Hyde | +5.836 |
| +5.823 |
ongo | +5.645 |
ulic | +5.571 |
Neg logit contributions | |
ofi | -6.620 |
LT | -6.494 |
avorite | -6.447 |
/+ | -5.956 |
thel | -5.951 |
Token | partner |
Token ID | 5212 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
uits | +0.930 |
| +0.919 |
Hyde | +0.909 |
ongo | +0.882 |
ulic | +0.867 |
Neg logit contributions | |
ofi | -1.157 |
LT | -1.152 |
avorite | -1.124 |
thel | -1.064 |
/+ | -1.058 |
Token | , |
Token ID | 11 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
uits | +0.499 |
| +0.489 |
Hyde | +0.486 |
ongo | +0.472 |
ulic | +0.469 |
Neg logit contributions | |
ofi | -0.508 |
LT | -0.502 |
avorite | -0.486 |
thel | -0.458 |
/+ | -0.457 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ofi | +0.645 |
LT | +0.641 |
avorite | +0.610 |
thel | +0.581 |
/+ | +0.573 |
Neg logit contributions | |
uits | -0.675 |
| -0.654 |
Hyde | -0.652 |
ulic | -0.640 |
ongo | -0.638 |
Token | National |
Token ID | 2351 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
uits | +0.987 |
| +0.967 |
Hyde | +0.962 |
ongo | +0.935 |
ulic | +0.931 |
Neg logit contributions | |
ofi | -0.971 |
LT | -0.959 |
avorite | -0.926 |
thel | -0.872 |
/+ | -0.869 |
Token | Party |
Token ID | 3615 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
uits | +0.493 |
| +0.482 |
Hyde | +0.479 |
ongo | +0.466 |
ulic | +0.464 |
Neg logit contributions | |
ofi | -0.504 |
LT | -0.499 |
avorite | -0.482 |
thel | -0.454 |
/+ | -0.452 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ofi | +0.457 |
LT | +0.451 |
avorite | +0.434 |
thel | +0.408 |
/+ | +0.406 |
Neg logit contributions | |
uits | -0.512 |
| -0.502 |
Hyde | -0.499 |
ongo | -0.486 |
ulic | -0.485 |
Token | 190 |
Token ID | 19782 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
uits | +5.264 |
| +5.223 |
Hyde | +5.096 |
ongo | +4.926 |
ulic | +4.762 |
Neg logit contributions | |
ofi | -8.952 |
avorite | -8.845 |
LT | -8.255 |
/+ | -8.250 |
thel | -8.005 |
Token | ][ |
Token ID | 7131 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
uits | +2.213 |
| +2.193 |
Hyde | +2.152 |
ongo | +2.109 |
AES | +2.091 |
Neg logit contributions | |
ofi | -2.250 |
LT | -2.220 |
avorite | -2.216 |
thel | -2.028 |
/+ | -1.992 |
Token | 191 |
Token ID | 26492 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
uits | +1.905 |
| +1.872 |
Hyde | +1.840 |
ongo | +1.810 |
AES | +1.778 |
Neg logit contributions | |
ofi | -1.845 |
LT | -1.801 |
avorite | -1.767 |
/+ | -1.657 |
thel | -1.650 |
Token | ] |
Token ID | 60 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
uits | +2.841 |
| +2.824 |
Hyde | +2.752 |
ongo | +2.694 |
AES | +2.681 |
Neg logit contributions | |
ofi | -3.198 |
LT | -3.140 |
avorite | -3.104 |
thel | -2.913 |
/+ | -2.831 |
Token | Within |
Token ID | 12511 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ofi | +0.228 |
LT | +0.226 |
avorite | +0.216 |
thel | +0.203 |
/+ | +0.203 |
Neg logit contributions | |
uits | -0.265 |
| -0.258 |
Hyde | -0.257 |
ongo | -0.251 |
ulic | -0.251 |
Token | д |
Token ID | 43666 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
uits | +0.654 |
| +0.646 |
Hyde | +0.633 |
ongo | +0.611 |
ulic | +0.607 |
Neg logit contributions | |
ofi | -1.038 |
LT | -1.024 |
avorite | -1.005 |
thel | -0.951 |
/+ | -0.949 |
Token | е |
Token ID | 16843 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
ofi | +1.579 |
LT | +1.571 |
avorite | +1.515 |
thel | +1.460 |
/+ | +1.452 |
Neg logit contributions | |
uits | -0.905 |
Hyde | -0.871 |
| -0.870 |
ongo | -0.835 |
ulic | -0.832 |
Token | л |
Token ID | 30143 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
uits | +0.355 |
| +0.346 |
Hyde | +0.340 |
ongo | +0.324 |
ulic | +0.324 |
Neg logit contributions | |
ofi | -0.811 |
LT | -0.800 |
avorite | -0.784 |
thel | -0.748 |
/+ | -0.748 |
Token | е |
Token ID | 16843 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
| +2.216 |
uits | +2.201 |
Hyde | +2.154 |
AES | +2.076 |
ulic | +2.073 |
Neg logit contributions | |
ofi | -3.288 |
LT | -3.217 |
avorite | -3.187 |
/+ | -2.991 |
thel | -2.985 |
Token | н |
Token ID | 22177 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
uits | +2.429 |
| +2.428 |
Hyde | +2.362 |
ulic | +2.296 |
AES | +2.273 |
Neg logit contributions | |
ofi | -4.004 |
LT | -3.894 |
avorite | -3.893 |
/+ | -3.622 |
thel | -3.609 |
Token | и |
Token ID | 18849 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
uits | +1.646 |
| +1.643 |
Hyde | +1.603 |
ongo | +1.534 |
AES | +1.518 |
Neg logit contributions | |
ofi | -3.324 |
LT | -3.271 |
avorite | -3.234 |
/+ | -3.057 |
thel | -3.050 |
Token | я |
Token ID | 40623 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
| +4.922 |
uits | +4.857 |
Hyde | +4.688 |
AES | +4.552 |
ulic | +4.422 |
Neg logit contributions | |
ofi | -8.653 |
avorite | -8.501 |
LT | -8.314 |
/+ | -7.777 |
thel | -7.693 |
Token | � |
Token ID | 141 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
uits | +1.266 |
| +1.258 |
Hyde | +1.233 |
ongo | +1.194 |
ulic | +1.191 |
Neg logit contributions | |
ofi | -1.541 |
LT | -1.511 |
avorite | -1.481 |
thel | -1.390 |
/+ | -1.383 |
Token | � |
Token ID | 227 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
uits | +2.159 |
| +2.122 |
Hyde | +2.107 |
ongo | +2.002 |
AES | +1.975 |
Neg logit contributions | |
ofi | -4.043 |
LT | -4.021 |
avorite | -3.942 |
thel | -3.729 |
/+ | -3.707 |
Token | � |
Token ID | 12466 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
| +1.694 |
uits | +1.688 |
Hyde | +1.650 |
AES | +1.594 |
ongo | +1.594 |
Neg logit contributions | |
ofi | -2.224 |
LT | -2.176 |
avorite | -2.156 |
thel | -2.019 |
/+ | -2.000 |
Token | � |
Token ID | 116 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
uits | +1.168 |
| +1.147 |
Hyde | +1.132 |
ongo | +1.091 |
ulic | +1.076 |
Neg logit contributions | |
ofi | -2.199 |
LT | -2.161 |
avorite | -2.126 |
/+ | -2.020 |
thel | -2.013 |
Token | genius |
Token ID | 15632 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
uits | +0.280 |
| +0.274 |
Hyde | +0.272 |
ongo | +0.264 |
ulic | +0.263 |
Neg logit contributions | |
ofi | -0.299 |
LT | -0.296 |
avorite | -0.286 |
thel | -0.270 |
/+ | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
uits | +0.983 |
| +0.968 |
Hyde | +0.960 |
ongo | +0.933 |
ulic | +0.927 |
Neg logit contributions | |
ofi | -0.932 |
LT | -0.917 |
avorite | -0.890 |
thel | -0.833 |
/+ | -0.829 |
Token |
|
Token ID | 198 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
| +2.085 |
uits | +2.072 |
Hyde | +2.068 |
AES | +1.979 |
ongo | +1.973 |
Neg logit contributions | |
ofi | -1.983 |
LT | -1.943 |
avorite | -1.925 |
thel | -1.759 |
/+ | -1.741 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
uits | +0.263 |
Hyde | +0.254 |
| +0.253 |
ulic | +0.250 |
ongo | +0.248 |
Neg logit contributions | |
ofi | -0.231 |
LT | -0.231 |
avorite | -0.212 |
/+ | -0.209 |
thel | -0.207 |
Token | Our |
Token ID | 5122 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
| +2.460 |
uits | +2.413 |
Hyde | +2.359 |
ongo | +2.347 |
ulic | +2.281 |
Neg logit contributions | |
ofi | -2.062 |
LT | -2.004 |
avorite | -2.003 |
thel | -1.811 |
/+ | -1.808 |
Token | daughter |
Token ID | 4957 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
| +3.181 |
Hyde | +3.112 |
uits | +3.057 |
ongo | +2.943 |
AES | +2.882 |
Neg logit contributions | |
ofi | -4.019 |
LT | -3.971 |
avorite | -3.940 |
thel | -3.615 |
/+ | -3.609 |
Token | is |
Token ID | 318 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
| +6.132 |
Hyde | +5.816 |
uits | +5.758 |
AES | +5.563 |
ongo | +5.533 |
Neg logit contributions | |
avorite | -7.744 |
ofi | -7.434 |
LT | -7.295 |
thel | -6.710 |
/+ | -6.497 |
Token | a |
Token ID | 257 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
uits | +1.950 |
| +1.916 |
Hyde | +1.900 |
ongo | +1.844 |
ulic | +1.832 |
Neg logit contributions | |
ofi | -2.087 |
LT | -2.063 |
avorite | -2.003 |
thel | -1.886 |
/+ | -1.873 |
Token | genius |
Token ID | 15632 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
| +2.836 |
uits | +2.814 |
Hyde | +2.792 |
ongo | +2.716 |
AES | +2.697 |
Neg logit contributions | |
ofi | -2.090 |
LT | -2.055 |
avorite | -2.009 |
thel | -1.851 |
/+ | -1.814 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
| +3.508 |
uits | +3.453 |
Hyde | +3.410 |
AES | +3.300 |
ongo | +3.296 |
Neg logit contributions | |
avorite | -3.598 |
ofi | -3.559 |
LT | -3.447 |
thel | -3.164 |
/+ | -3.073 |
Token | Ye |
Token ID | 11609 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
ofi | +1.926 |
LT | +1.922 |
avorite | +1.799 |
thel | +1.754 |
/+ | +1.739 |
Neg logit contributions | |
uits | -2.213 |
ulic | -2.100 |
| -2.099 |
Hyde | -2.077 |
ongo | -2.076 |
Token | Republican |
Token ID | 3415 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
uits | +1.468 |
Hyde | +1.450 |
| +1.450 |
ongo | +1.398 |
AES | +1.382 |
Neg logit contributions | |
ofi | -1.594 |
LT | -1.570 |
avorite | -1.528 |
/+ | -1.440 |
thel | -1.438 |
Token | nominee |
Token ID | 10429 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
ofi | +0.814 |
LT | +0.805 |
avorite | +0.779 |
thel | +0.732 |
/+ | +0.728 |
Neg logit contributions | |
uits | -0.818 |
| -0.790 |
Hyde | -0.783 |
ulic | -0.776 |
ongo | -0.772 |
Token | Donald |
Token ID | 3759 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
ofi | +0.407 |
LT | +0.401 |
avorite | +0.385 |
thel | +0.364 |
/+ | +0.363 |
Neg logit contributions | |
uits | -0.435 |
| -0.424 |
Hyde | -0.421 |
ongo | -0.413 |
ulic | -0.412 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ofi | +0.064 |
LT | +0.064 |
avorite | +0.061 |
thel | +0.059 |
/+ | +0.059 |
Neg logit contributions | |
uits | -0.047 |
| -0.045 |
Hyde | -0.045 |
ongo | -0.044 |
ulic | -0.044 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
| +3.778 |
Hyde | +3.725 |
uits | +3.702 |
ongo | +3.478 |
AES | +3.461 |
Neg logit contributions | |
LT | -4.689 |
ofi | -4.665 |
avorite | -4.642 |
/+ | -4.332 |
thel | -4.272 |
Token | John |
Token ID | 1757 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
uits | +2.643 |
Hyde | +2.613 |
| +2.582 |
AES | +2.493 |
ongo | +2.486 |
Neg logit contributions | |
ofi | -3.155 |
LT | -3.130 |
avorite | -3.112 |
thel | -2.884 |
/+ | -2.851 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Hyde | +4.626 |
uits | +4.470 |
AES | +4.214 |
| +4.145 |
ulic | +4.000 |
Neg logit contributions | |
avorite | -9.195 |
ofi | -9.075 |
LT | -9.010 |
thel | -8.261 |
/+ | -8.129 |
Token | House |
Token ID | 18102 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
uits | +2.877 |
| +2.862 |
Hyde | +2.845 |
ongo | +2.752 |
ulic | +2.700 |
Neg logit contributions | |
avorite | -3.460 |
ofi | -3.457 |
LT | -3.336 |
thel | -3.128 |
/+ | -3.101 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Hyde | +3.807 |
uits | +3.733 |
| +3.719 |
ongo | +3.707 |
AES | +3.591 |
Neg logit contributions | |
LT | -5.154 |
ofi | -5.150 |
avorite | -5.047 |
thel | -4.790 |
/+ | -4.634 |
Token | believes |
Token ID | 5804 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
uits | +2.242 |
Hyde | +2.198 |
| +2.193 |
ongo | +2.193 |
ulic | +2.124 |
Neg logit contributions | |
ofi | -2.671 |
LT | -2.611 |
avorite | -2.499 |
thel | -2.442 |
/+ | -2.292 |
Token | it |
Token ID | 340 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Hyde | +2.063 |
| +1.992 |
uits | +1.892 |
ulic | +1.878 |
AES | +1.869 |
Neg logit contributions | |
LT | -3.844 |
avorite | -3.844 |
ofi | -3.806 |
thel | -3.658 |
/+ | -3.469 |
Token | ap |
Token ID | 2471 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
ofi | +2.392 |
LT | +2.371 |
avorite | +2.263 |
/+ | +2.047 |
thel | +2.013 |
Neg logit contributions | |
uits | -5.443 |
Hyde | -5.370 |
| -5.312 |
ulic | -5.272 |
ongo | -5.258 |
Token | = |
Token ID | 796 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
uits | +0.542 |
Hyde | +0.526 |
| +0.526 |
ulic | +0.512 |
ongo | +0.511 |
Neg logit contributions | |
ofi | -0.533 |
LT | -0.531 |
avorite | -0.498 |
/+ | -0.479 |
thel | -0.478 |
Token | arg |
Token ID | 1822 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
uits | +0.770 |
| +0.742 |
Hyde | +0.742 |
ongo | +0.715 |
ulic | +0.715 |
Neg logit contributions | |
ofi | -1.269 |
LT | -1.257 |
avorite | -1.211 |
/+ | -1.168 |
thel | -1.165 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
uits | +0.206 |
Hyde | +0.204 |
| +0.202 |
ulic | +0.197 |
ongo | +0.196 |
Neg logit contributions | |
ofi | -0.124 |
LT | -0.123 |
avorite | -0.113 |
/+ | -0.108 |
thel | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
LT | +1.253 |
ofi | +1.236 |
/+ | +1.124 |
thel | +1.096 |
WP | +1.062 |
Neg logit contributions | |
uits | -1.792 |
�� | -1.742 |
Hyde | -1.740 |
| -1.714 |
ulic | -1.711 |
Token | Arg |
Token ID | 28100 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
uits | +1.173 |
| +1.144 |
Hyde | +1.136 |
ongo | +1.101 |
ulic | +1.096 |
Neg logit contributions | |
ofi | -1.502 |
LT | -1.487 |
avorite | -1.441 |
thel | -1.368 |
/+ | -1.363 |
Token | ument |
Token ID | 1713 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
| +3.676 |
uits | +3.624 |
ongo | +3.313 |
Hyde | +3.252 |
ulic | +3.230 |
Neg logit contributions | |
avorite | -9.931 |
ofi | -9.740 |
LT | -9.537 |
thel | -9.063 |
/+ | -8.893 |
Token | Parser |
Token ID | 46677 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
LT | +0.078 |
ofi | +0.077 |
avorite | +0.072 |
/+ | +0.069 |
thel | +0.069 |
Neg logit contributions | |
uits | -0.093 |
Hyde | -0.091 |
| -0.090 |
ongo | -0.089 |
ulic | -0.088 |
Token | () |
Token ID | 3419 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
LT | +0.064 |
ofi | +0.064 |
avorite | +0.059 |
/+ | +0.058 |
thel | +0.058 |
Neg logit contributions | |
uits | -0.062 |
Hyde | -0.060 |
| -0.060 |
ongo | -0.058 |
ulic | -0.058 |
Token | ap |
Token ID | 2471 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ofi | +2.332 |
LT | +2.215 |
/+ | +2.007 |
avorite | +1.956 |
thel | +1.873 |
Neg logit contributions | |
uits | -6.376 |
Hyde | -6.294 |
ulic | -6.239 |
ongo | -6.177 |
�� | -6.117 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
LT | +0.837 |
ofi | +0.834 |
/+ | +0.752 |
thel | +0.738 |
avorite | +0.733 |
Neg logit contributions | |
uits | -1.140 |
Hyde | -1.110 |
| -1.101 |
ulic | -1.086 |
�� | -1.083 |
Token | post |
Token ID | 1281 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
uits | +0.227 |
Hyde | +0.220 |
| +0.216 |
ulic | +0.214 |
ongo | +0.212 |
Neg logit contributions | |
ofi | -0.244 |
LT | -0.243 |
avorite | -0.227 |
/+ | -0.224 |
thel | -0.223 |
Token | is |
Token ID | 318 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
uits | +2.110 |
| +2.082 |
Hyde | +2.051 |
ongo | +2.004 |
ulic | +1.992 |
Neg logit contributions | |
ofi | -1.995 |
LT | -1.978 |
avorite | -1.941 |
thel | -1.789 |
/+ | -1.770 |
Token | ready |
Token ID | 3492 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ofi | +1.532 |
LT | +1.495 |
thel | +1.381 |
avorite | +1.372 |
/+ | +1.367 |
Neg logit contributions | |
uits | -1.541 |
Hyde | -1.473 |
ulic | -1.445 |
| -1.437 |
ongo | -1.436 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
uits | +0.260 |
Hyde | +0.253 |
| +0.252 |
ongo | +0.246 |
ulic | +0.246 |
Neg logit contributions | |
ofi | -0.250 |
LT | -0.248 |
avorite | -0.233 |
/+ | -0.225 |
thel | -0.225 |
Token | enter |
Token ID | 3802 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
uits | +1.050 |
| +1.021 |
Hyde | +1.021 |
ongo | +0.993 |
ulic | +0.992 |
Neg logit contributions | |
ofi | -0.984 |
LT | -0.972 |
avorite | -0.924 |
thel | -0.885 |
/+ | -0.883 |
Token | your |
Token ID | 534 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
ofi | +0.588 |
LT | +0.574 |
avorite | +0.532 |
/+ | +0.524 |
thel | +0.521 |
Neg logit contributions | |
uits | -0.763 |
Hyde | -0.742 |
| -0.732 |
ongo | -0.724 |
ulic | -0.723 |
Token | email |
Token ID | 3053 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
| +4.932 |
uits | +4.641 |
Hyde | +4.527 |
AES | +4.470 |
ongo | +4.419 |
Neg logit contributions | |
avorite | -8.634 |
ofi | -8.485 |
LT | -8.359 |
thel | -7.768 |
/+ | -7.549 |
Token | below |
Token ID | 2174 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
uits | +1.699 |
| +1.663 |
Hyde | +1.649 |
ongo | +1.596 |
ulic | +1.589 |
Neg logit contributions | |
ofi | -2.082 |
LT | -2.059 |
avorite | -1.998 |
thel | -1.889 |
/+ | -1.885 |
Token | . |
Token ID | 13 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
| +3.246 |
uits | +3.193 |
Hyde | +3.126 |
ongo | +3.042 |
AES | +3.025 |
Neg logit contributions | |
avorite | -3.274 |
ofi | -3.243 |
LT | -3.137 |
thel | -2.887 |
/+ | -2.824 |
Token | Notes |
Token ID | 11822 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
uits | +0.341 |
| +0.336 |
Hyde | +0.333 |
ongo | +0.323 |
ulic | +0.322 |
Neg logit contributions | |
ofi | -0.341 |
LT | -0.337 |
avorite | -0.326 |
thel | -0.306 |
/+ | -0.305 |
Token | # |
Token ID | 1303 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
uits | +0.403 |
| +0.397 |
Hyde | +0.393 |
ongo | +0.381 |
ulic | +0.380 |
Neg logit contributions | |
ofi | -0.394 |
LT | -0.389 |
avorite | -0.377 |
thel | -0.354 |
/+ | -0.352 |
Token | app |
Token ID | 598 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ofi | +0.266 |
LT | +0.261 |
avorite | +0.245 |
/+ | +0.229 |
thel | +0.228 |
Neg logit contributions | |
uits | -0.484 |
Hyde | -0.472 |
| -0.472 |
ulic | -0.463 |
ongo | -0.462 |
Token | data |
Token ID | 7890 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
uits | +2.944 |
| +2.916 |
Hyde | +2.806 |
ongo | +2.798 |
ulic | +2.708 |
Neg logit contributions | |
ofi | -4.518 |
LT | -4.486 |
avorite | -4.442 |
/+ | -4.111 |
thel | -4.101 |
Token | _ |
Token ID | 4808 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
| +2.151 |
uits | +2.150 |
Hyde | +2.111 |
AES | +2.029 |
ongo | +2.028 |
Neg logit contributions | |
ofi | -3.001 |
avorite | -2.963 |
LT | -2.945 |
thel | -2.725 |
/+ | -2.694 |
Token | full |
Token ID | 1336 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ofi | +0.683 |
LT | +0.675 |
avorite | +0.654 |
thel | +0.619 |
/+ | +0.617 |
Neg logit contributions | |
uits | -0.586 |
| -0.573 |
Hyde | -0.569 |
ongo | -0.552 |
ulic | -0.549 |
Token | v |
Token ID | 410 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
uits | +1.392 |
| +1.378 |
Hyde | +1.346 |
ongo | +1.313 |
ulic | +1.296 |
Neg logit contributions | |
ofi | -1.658 |
LT | -1.634 |
avorite | -1.584 |
thel | -1.504 |
/+ | -1.496 |
Token | ) |
Token ID | 1267 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
| +2.893 |
uits | +2.878 |
Hyde | +2.808 |
ongo | +2.746 |
ulic | +2.717 |
Neg logit contributions | |
ofi | -3.766 |
avorite | -3.711 |
LT | -3.674 |
thel | -3.428 |
/+ | -3.374 |
Token | { |
Token ID | 1391 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
| +7.116 |
uits | +7.063 |
Hyde | +6.997 |
AES | +6.842 |
ongo | +6.756 |
Neg logit contributions | |
avorite | -6.114 |
ofi | -5.892 |
LT | -5.639 |
thel | -5.315 |
/+ | -5.093 |
Token | v |
Token ID | 410 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
uits | +0.540 |
| +0.531 |
Hyde | +0.527 |
ongo | +0.512 |
ulic | +0.509 |
Neg logit contributions | |
ofi | -0.498 |
LT | -0.492 |
avorite | -0.475 |
thel | -0.446 |
/+ | -0.443 |
Token | . |
Token ID | 764 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
| +4.036 |
Hyde | +3.956 |
uits | +3.841 |
AES | +3.765 |
ongo | +3.749 |
Neg logit contributions | |
avorite | -8.373 |
ofi | -8.132 |
LT | -7.794 |
thel | -7.390 |
/+ | -7.220 |
Token | vertex |
Token ID | 37423 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
uits | +4.585 |
| +4.578 |
Hyde | +4.511 |
AES | +4.362 |
ongo | +4.310 |
Neg logit contributions | |
ofi | -5.051 |
LT | -4.889 |
avorite | -4.886 |
thel | -4.519 |
WP | -4.451 |
Token | . |
Token ID | 764 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
| +3.201 |
Hyde | +3.162 |
uits | +3.147 |
AES | +3.025 |
ongo | +2.990 |
Neg logit contributions | |
ofi | -5.421 |
avorite | -5.407 |
LT | -5.259 |
thel | -4.944 |
/+ | -4.890 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
uits | +0.295 |
Hyde | +0.285 |
| +0.284 |
ulic | +0.279 |
ongo | +0.278 |
Neg logit contributions | |
ofi | -0.261 |
LT | -0.261 |
avorite | -0.240 |
/+ | -0.236 |
thel | -0.235 |
Token | ______ |
Token ID | 25947 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
uits | +0.199 |
| +0.194 |
Hyde | +0.192 |
ongo | +0.185 |
ulic | +0.184 |
Neg logit contributions | |
ofi | -0.336 |
LT | -0.333 |
avorite | -0.324 |
thel | -0.309 |
/+ | -0.308 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ofi | +0.885 |
LT | +0.875 |
avorite | +0.845 |
thel | +0.796 |
/+ | +0.792 |
Neg logit contributions | |
uits | -0.911 |
| -0.892 |
Hyde | -0.887 |
ongo | -0.863 |
ulic | -0.859 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ofi | +0.124 |
LT | +0.124 |
avorite | +0.115 |
/+ | +0.112 |
thel | +0.111 |
Neg logit contributions | |
uits | -0.137 |
Hyde | -0.133 |
| -0.133 |
ulic | -0.130 |
ongo | -0.130 |
Token | X |
Token ID | 55 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ofi | +1.804 |
LT | +1.797 |
avorite | +1.723 |
thel | +1.651 |
/+ | +1.645 |
Neg logit contributions | |
uits | -1.252 |
| -1.213 |
Hyde | -1.211 |
ongo | -1.168 |
ulic | -1.166 |
Token | avier |
Token ID | 19492 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
uits | +2.924 |
| +2.848 |
Hyde | +2.793 |
ongo | +2.758 |
AES | +2.702 |
Neg logit contributions | |
ofi | -3.012 |
avorite | -2.970 |
LT | -2.967 |
/+ | -2.704 |
thel | -2.700 |
Token | Dum |
Token ID | 30933 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Hyde | +4.823 |
| +4.767 |
uits | +4.648 |
AES | +4.566 |
ulic | +4.323 |
Neg logit contributions | |
avorite | -8.096 |
ofi | -8.061 |
LT | -7.974 |
thel | -7.682 |
WP | -7.420 |
Token | us |
Token ID | 385 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
uits | +2.035 |
| +1.989 |
Hyde | +1.970 |
ongo | +1.922 |
ulic | +1.913 |
Neg logit contributions | |
ofi | -2.127 |
LT | -2.103 |
avorite | -2.039 |
thel | -1.919 |
/+ | -1.908 |
Token | que |
Token ID | 4188 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
uits | +2.449 |
| +2.373 |
Hyde | +2.290 |
ongo | +2.205 |
ulic | +2.162 |
Neg logit contributions | |
ofi | -6.341 |
LT | -6.286 |
avorite | -6.233 |
thel | -5.909 |
/+ | -5.860 |
Token | et |
Token ID | 2123 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
| +3.534 |
uits | +3.516 |
Hyde | +3.444 |
AES | +3.336 |
ongo | +3.299 |
Neg logit contributions | |
ofi | -3.751 |
avorite | -3.739 |
LT | -3.660 |
thel | -3.456 |
/+ | -3.323 |
Token | al |
Token ID | 435 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
uits | +1.530 |
| +1.482 |
Hyde | +1.472 |
ongo | +1.420 |
ulic | +1.415 |
Neg logit contributions | |
ofi | -2.593 |
LT | -2.571 |
avorite | -2.488 |
thel | -2.387 |
/+ | -2.383 |
Token | rational |
Token ID | 9377 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
| +2.826 |
uits | +2.810 |
Hyde | +2.738 |
ongo | +2.605 |
AES | +2.603 |
Neg logit contributions | |
ofi | -3.035 |
LT | -3.021 |
avorite | -2.985 |
/+ | -2.742 |
thel | -2.738 |
Token | enough |
Token ID | 1576 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
| +3.586 |
uits | +3.542 |
Hyde | +3.404 |
ongo | +3.348 |
ulic | +3.288 |
Neg logit contributions | |
ofi | -3.816 |
LT | -3.755 |
avorite | -3.740 |
thel | -3.416 |
/+ | -3.407 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
ofi | +0.197 |
LT | +0.195 |
avorite | +0.187 |
thel | +0.177 |
/+ | +0.176 |
Neg logit contributions | |
uits | -0.210 |
| -0.205 |
Hyde | -0.205 |
ongo | -0.199 |
ulic | -0.198 |
Token | � |
Token ID | 447 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
uits | +0.359 |
| +0.348 |
Hyde | +0.347 |
ongo | +0.339 |
ulic | +0.338 |
Neg logit contributions | |
ofi | -0.373 |
LT | -0.370 |
avorite | -0.354 |
thel | -0.337 |
/+ | -0.335 |
Token | � |
Token ID | 251 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ofi | +0.349 |
LT | +0.345 |
avorite | +0.333 |
thel | +0.315 |
/+ | +0.314 |
Neg logit contributions | |
uits | -0.312 |
| -0.305 |
Hyde | -0.303 |
ongo | -0.294 |
ulic | -0.293 |
Token | [ |
Token ID | 58 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
uits | +0.965 |
| +0.954 |
Hyde | +0.944 |
ongo | +0.912 |
ulic | +0.907 |
Neg logit contributions | |
ofi | -1.017 |
LT | -1.003 |
avorite | -0.980 |
thel | -0.917 |
/+ | -0.914 |
Token | 20 |
Token ID | 1238 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
| +4.711 |
uits | +4.412 |
Hyde | +4.350 |
ongo | +4.288 |
cu | +4.038 |
Neg logit contributions | |
avorite | -8.144 |
ofi | -8.034 |
LT | -7.684 |
/+ | -7.377 |
thel | -7.340 |
Token | ] |
Token ID | 60 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
uits | +0.266 |
Hyde | +0.258 |
| +0.257 |
ulic | +0.252 |
ongo | +0.252 |
Neg logit contributions | |
ofi | -0.231 |
LT | -0.229 |
avorite | -0.212 |
/+ | -0.207 |
thel | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
uits | +0.480 |
| +0.467 |
Hyde | +0.465 |
ongo | +0.455 |
ulic | +0.454 |
Neg logit contributions | |
ofi | -0.431 |
LT | -0.427 |
avorite | -0.406 |
thel | -0.385 |
/+ | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
uits | +1.737 |
| +1.709 |
Hyde | +1.694 |
ongo | +1.647 |
ulic | +1.637 |
Neg logit contributions | |
ofi | -1.713 |
LT | -1.690 |
avorite | -1.647 |
thel | -1.538 |
/+ | -1.528 |
Token | So |
Token ID | 2396 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
uits | +1.107 |
| +1.086 |
Hyde | +1.078 |
ongo | +1.049 |
ulic | +1.043 |
Neg logit contributions | |
ofi | -1.119 |
LT | -1.104 |
avorite | -1.070 |
thel | -1.006 |
/+ | -1.003 |
Token | Currency |
Token ID | 20113 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ofi | +1.784 |
LT | +1.760 |
avorite | +1.680 |
/+ | +1.599 |
thel | +1.592 |
Neg logit contributions | |
uits | -1.740 |
| -1.678 |
Hyde | -1.660 |
ongo | -1.627 |
ulic | -1.622 |
Token | Inter |
Token ID | 4225 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
ofi | +1.362 |
LT | +1.350 |
avorite | +1.298 |
thel | +1.249 |
/+ | +1.243 |
Neg logit contributions | |
uits | -0.905 |
| -0.872 |
Hyde | -0.866 |
ulic | -0.840 |
ongo | -0.839 |
Token | change |
Token ID | 3803 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
uits | +0.401 |
Hyde | +0.394 |
| +0.386 |
ulic | +0.378 |
AES | +0.374 |
Neg logit contributions | |
ofi | -0.553 |
LT | -0.546 |
avorite | -0.513 |
thel | -0.505 |
/+ | -0.504 |
Token | ability |
Token ID | 1799 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ofi | +0.974 |
LT | +0.951 |
avorite | +0.882 |
/+ | +0.869 |
thel | +0.866 |
Neg logit contributions | |
uits | -1.133 |
Hyde | -1.098 |
| -1.090 |
ulic | -1.081 |
ongo | -1.071 |
Token | Agreement |
Token ID | 12729 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ofi | +2.027 |
LT | +1.993 |
avorite | +1.884 |
/+ | +1.771 |
thel | +1.769 |
Neg logit contributions | |
uits | -2.910 |
| -2.836 |
Hyde | -2.833 |
ulic | -2.778 |
ongo | -2.774 |
Token | .[ |
Token ID | 3693 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ofi | +0.131 |
LT | +0.129 |
avorite | +0.125 |
thel | +0.118 |
/+ | +0.117 |
Neg logit contributions | |
uits | -0.135 |
| -0.132 |
Hyde | -0.131 |
ongo | -0.128 |
ulic | -0.127 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
| +4.711 |
uits | +4.514 |
Hyde | +4.441 |
ongo | +4.317 |
AES | +4.156 |
Neg logit contributions | |
avorite | -7.986 |
ofi | -7.939 |
LT | -7.643 |
/+ | -7.308 |
thel | -7.248 |
Token | ] |
Token ID | 60 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ofi | +0.794 |
LT | +0.785 |
avorite | +0.759 |
thel | +0.713 |
/+ | +0.709 |
Neg logit contributions | |
uits | -0.841 |
| -0.825 |
Hyde | -0.818 |
ongo | -0.797 |
ulic | -0.794 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ofi | +0.206 |
LT | +0.203 |
avorite | +0.195 |
thel | +0.184 |
/+ | +0.183 |
Neg logit contributions | |
uits | -0.235 |
| -0.230 |
Hyde | -0.229 |
ongo | -0.223 |
ulic | -0.222 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uits | +1.261 |
| +1.236 |
Hyde | +1.228 |
ongo | +1.194 |
ulic | +1.189 |
Neg logit contributions | |
ofi | -1.222 |
LT | -1.208 |
avorite | -1.167 |
thel | -1.097 |
/+ | -1.092 |
Token | $ |
Token ID | 3 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
uits | +0.405 |
| +0.398 |
Hyde | +0.395 |
ongo | +0.385 |
ulic | +0.383 |
Neg logit contributions | |
ofi | -0.367 |
LT | -0.363 |
avorite | -0.350 |
thel | -0.329 |
/+ | -0.327 |
Token | we |
Token ID | 356 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ofi | +0.899 |
LT | +0.890 |
avorite | +0.849 |
thel | +0.808 |
/+ | +0.802 |
Neg logit contributions | |
uits | -0.948 |
| -0.920 |
Hyde | -0.915 |
ulic | -0.898 |
ongo | -0.894 |
Token | can |
Token ID | 460 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ofi | +1.161 |
LT | +1.157 |
avorite | +1.081 |
thel | +1.050 |
/+ | +1.035 |
Neg logit contributions | |
uits | -1.263 |
Hyde | -1.227 |
| -1.207 |
ongo | -1.205 |
ulic | -1.196 |
Token | work |
Token ID | 670 |
Feature activation | -1.22e-05 |
Pos logit contributions | |
ofi | +2.071 |
LT | +2.049 |
avorite | +1.901 |
/+ | +1.876 |
thel | +1.849 |
Neg logit contributions | |
uits | -2.238 |
Hyde | -2.205 |
ongo | -2.157 |
| -2.143 |
�� | -2.123 |
Token | on |
Token ID | 319 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
uits | +0.000 |
| +0.000 |
Hyde | +0.000 |
ongo | +0.000 |
ulic | +0.000 |
Neg logit contributions | |
ofi | -0.000 |
LT | -0.000 |
avorite | -0.000 |
thel | -0.000 |
/+ | -0.000 |
Token | piece |
Token ID | 3704 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ofi | +0.703 |
LT | +0.696 |
avorite | +0.666 |
thel | +0.636 |
/+ | +0.633 |
Neg logit contributions | |
uits | -0.656 |
Hyde | -0.640 |
| -0.639 |
ongo | -0.619 |
ulic | -0.619 |
Token | by |
Token ID | 416 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
ofi | +2.224 |
LT | +2.199 |
avorite | +2.121 |
thel | +2.039 |
/+ | +2.026 |
Neg logit contributions | |
uits | -1.337 |
Hyde | -1.277 |
| -1.275 |
ulic | -1.234 |
ongo | -1.224 |
Token | piece |
Token ID | 3704 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
| +7.390 |
Hyde | +7.239 |
uits | +7.056 |
vul | +6.968 |
AES | +6.947 |
Neg logit contributions | |
avorite | -5.549 |
ofi | -5.281 |
LT | -5.257 |
/+ | -4.526 |
thel | -4.405 |
Token | ." |
Token ID | 526 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
uits | +1.563 |
| +1.543 |
Hyde | +1.507 |
ongo | +1.474 |
ulic | +1.462 |
Neg logit contributions | |
ofi | -1.704 |
LT | -1.685 |
avorite | -1.654 |
/+ | -1.539 |
thel | -1.536 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ofi | +0.205 |
LT | +0.202 |
avorite | +0.196 |
thel | +0.185 |
/+ | +0.184 |
Neg logit contributions | |
uits | -0.198 |
| -0.194 |
Hyde | -0.192 |
ongo | -0.187 |
ulic | -0.186 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
uits | +1.106 |
| +1.078 |
Hyde | +1.075 |
ongo | +1.046 |
ulic | +1.045 |
Neg logit contributions | |
ofi | -1.040 |
LT | -1.031 |
avorite | -0.981 |
thel | -0.934 |
/+ | -0.932 |
Token | She |
Token ID | 3347 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
uits | +0.892 |
| +0.885 |
Hyde | +0.866 |
ongo | +0.854 |
ulic | +0.843 |
Neg logit contributions | |
ofi | -0.846 |
LT | -0.828 |
avorite | -0.823 |
thel | -0.756 |
/+ | -0.754 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
| +2.079 |
uits | +2.064 |
Hyde | +2.023 |
ongo | +1.957 |
AES | +1.953 |
Neg logit contributions | |
avorite | -2.353 |
ofi | -2.347 |
LT | -2.292 |
thel | -2.128 |
/+ | -2.079 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
uits | +1.881 |
| +1.844 |
Hyde | +1.835 |
ongo | +1.792 |
ulic | +1.786 |
Neg logit contributions | |
ofi | -1.400 |
LT | -1.382 |
avorite | -1.323 |
thel | -1.235 |
/+ | -1.230 |
Token | Que |
Token ID | 15681 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
| +0.713 |
uits | +0.692 |
Hyde | +0.584 |
ongo | +0.555 |
AES | +0.489 |
Neg logit contributions | |
ofi | -5.427 |
avorite | -5.366 |
LT | -5.284 |
thel | -5.074 |
/+ | -5.036 |
Token | ers |
Token ID | 364 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
uits | +3.618 |
| +3.477 |
ongo | +3.296 |
ulic | +3.296 |
Hyde | +3.281 |
Neg logit contributions | |
ofi | -4.503 |
avorite | -4.486 |
LT | -4.408 |
thel | -3.982 |
WP | -3.916 |
Token | are |
Token ID | 389 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
| +5.630 |
uits | +5.457 |
Hyde | +5.193 |
AES | +5.012 |
ulic | +4.914 |
Neg logit contributions | |
ofi | -7.163 |
avorite | -7.162 |
LT | -7.058 |
thel | -6.476 |
WP | -6.225 |
Token | Here |
Token ID | 3423 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
| +3.838 |
Hyde | +3.676 |
uits | +3.652 |
AES | +3.401 |
ongo | +3.388 |
Neg logit contributions | |
ofi | -6.081 |
LT | -5.895 |
avorite | -5.891 |
thel | -5.453 |
/+ | -5.403 |
Token | .... |
Token ID | 1106 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
| +4.192 |
uits | +3.906 |
Hyde | +3.744 |
ongo | +3.580 |
AES | +3.263 |
Neg logit contributions | |
ofi | -8.686 |
avorite | -8.472 |
LT | -8.424 |
thel | -7.944 |
WP | -7.880 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
| +2.683 |
uits | +2.641 |
Hyde | +2.622 |
AES | +2.530 |
ongo | +2.473 |
Neg logit contributions | |
ofi | -3.455 |
LT | -3.363 |
avorite | -3.308 |
thel | -3.094 |
/+ | -3.082 |
Token |
|
Token ID | 198 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
| +2.640 |
uits | +2.622 |
Hyde | +2.575 |
ongo | +2.499 |
AES | +2.479 |
Neg logit contributions | |
ofi | -2.912 |
avorite | -2.910 |
LT | -2.839 |
thel | -2.608 |
/+ | -2.561 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
| +3.140 |
uits | +3.126 |
ongo | +3.012 |
Hyde | +3.007 |
ulic | +2.936 |
Neg logit contributions | |
ofi | -3.133 |
avorite | -3.047 |
LT | -3.032 |
/+ | -2.763 |
thel | -2.752 |
Token | : |
Token ID | 25 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
uits | +2.430 |
| +2.426 |
Hyde | +2.380 |
ongo | +2.313 |
AES | +2.299 |
Neg logit contributions | |
ofi | -2.234 |
avorite | -2.198 |
LT | -2.176 |
thel | -1.982 |
/+ | -1.945 |
Token | 0 |
Token ID | 15 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
ofi | +1.923 |
LT | +1.892 |
avorite | +1.817 |
thel | +1.740 |
/+ | +1.726 |
Neg logit contributions | |
uits | -1.519 |
| -1.493 |
Hyde | -1.468 |
ulic | -1.413 |
AES | -1.410 |
Token | king |
Token ID | 3364 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ofi | +0.653 |
LT | +0.647 |
avorite | +0.623 |
thel | +0.589 |
/+ | +0.587 |
Neg logit contributions | |
uits | -0.623 |
| -0.610 |
Hyde | -0.606 |
ongo | -0.589 |
ulic | -0.586 |
Token | [ |
Token ID | 685 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
uits | +1.039 |
| +1.017 |
Hyde | +1.013 |
ongo | +0.984 |
ulic | +0.977 |
Neg logit contributions | |
ofi | -1.068 |
LT | -1.055 |
avorite | -1.031 |
thel | -0.967 |
/+ | -0.962 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
uits | +0.446 |
Hyde | +0.431 |
| +0.430 |
ulic | +0.419 |
ongo | +0.415 |
Neg logit contributions | |
ofi | -0.533 |
LT | -0.531 |
avorite | -0.501 |
/+ | -0.486 |
thel | -0.485 |
Token | : |
Token ID | 25 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
uits | +2.305 |
| +2.299 |
Hyde | +2.258 |
ongo | +2.193 |
AES | +2.182 |
Neg logit contributions | |
ofi | -2.094 |
avorite | -2.077 |
LT | -2.050 |
thel | -1.868 |
/+ | -1.833 |
Token | 47 |
Token ID | 2857 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ofi | +0.054 |
LT | +0.053 |
avorite | +0.051 |
thel | +0.046 |
/+ | +0.046 |
Neg logit contributions | |
uits | -0.093 |
| -0.092 |
Hyde | -0.091 |
ongo | -0.089 |
AES | -0.088 |
Token | ] |
Token ID | 60 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
| +5.584 |
uits | +5.284 |
Hyde | +5.236 |
AES | +5.142 |
ongo | +5.125 |
Neg logit contributions | |
avorite | -7.925 |
ofi | -7.200 |
LT | -6.915 |
PDATE | -6.635 |
thel | -6.531 |
Token | < |
Token ID | 1279 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
uits | +1.431 |
| +1.415 |
Hyde | +1.378 |
AES | +1.304 |
ongo | +1.280 |
Neg logit contributions | |
ofi | -4.559 |
LT | -4.485 |
avorite | -4.471 |
thel | -4.295 |
/+ | -4.243 |
Token | dan |
Token ID | 25604 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
uits | +1.836 |
| +1.792 |
Hyde | +1.762 |
ongo | +1.737 |
ulic | +1.728 |
Neg logit contributions | |
ofi | -1.996 |
LT | -1.974 |
avorite | -1.945 |
/+ | -1.802 |
thel | -1.792 |
Token | ides |
Token ID | 1460 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
uits | +1.064 |
| +1.032 |
Hyde | +1.023 |
ongo | +1.008 |
ulic | +1.001 |
Neg logit contributions | |
ofi | -1.149 |
LT | -1.142 |
avorite | -1.108 |
/+ | -1.041 |
thel | -1.036 |
Token | u |
Token ID | 84 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
uits | +0.175 |
| +0.171 |
Hyde | +0.169 |
ongo | +0.164 |
ulic | +0.164 |
Neg logit contributions | |
ofi | -0.206 |
LT | -0.204 |
avorite | -0.198 |
thel | -0.187 |
/+ | -0.187 |
Token | | |
Token ID | 930 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
uits | +0.815 |
| +0.811 |
Hyde | +0.796 |
ongo | +0.771 |
ulic | +0.769 |
Neg logit contributions | |
ofi | -0.899 |
LT | -0.887 |
avorite | -0.862 |
thel | -0.818 |
/+ | -0.802 |
Token | Medline |
Token ID | 34582 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
ofi | +0.029 |
LT | +0.029 |
avorite | +0.027 |
/+ | +0.027 |
thel | +0.027 |
Neg logit contributions | |
uits | -0.015 |
| -0.014 |
Hyde | -0.014 |
ulic | -0.014 |
ongo | -0.014 |
Token | | |
Token ID | 930 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ofi | +0.471 |
LT | +0.465 |
avorite | +0.450 |
thel | +0.427 |
/+ | +0.423 |
Neg logit contributions | |
uits | -0.417 |
| -0.409 |
Hyde | -0.405 |
ongo | -0.393 |
ulic | -0.392 |
Token | ISI |
Token ID | 22048 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
ofi | +0.995 |
LT | +0.992 |
avorite | +0.933 |
/+ | +0.925 |
thel | +0.918 |
Neg logit contributions | |
uits | -0.541 |
| -0.511 |
Hyde | -0.504 |
ulic | -0.499 |
ongo | -0.494 |
Token |
|
Token ID | 198 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
ofi | +0.471 |
LT | +0.466 |
avorite | +0.450 |
thel | +0.424 |
/+ | +0.423 |
Neg logit contributions | |
uits | -0.463 |
| -0.453 |
Hyde | -0.450 |
ongo | -0.438 |
ulic | -0.436 |
Token |
|
Token ID | 198 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
| +4.526 |
Hyde | +4.330 |
uits | +4.270 |
AES | +4.142 |
ongo | +4.114 |
Neg logit contributions | |
avorite | -5.990 |
ofi | -5.655 |
LT | -5.457 |
thel | -5.135 |
PDATE | -4.970 |
Token | My |
Token ID | 3666 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
| +5.795 |
uits | +5.541 |
ongo | +5.471 |
Hyde | +5.470 |
ulic | +5.253 |
Neg logit contributions | |
avorite | -6.954 |
ofi | -6.647 |
LT | -6.323 |
thel | -6.119 |
/+ | -5.939 |
Token | ers |
Token ID | 364 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
ofi | +0.486 |
LT | +0.481 |
avorite | +0.464 |
thel | +0.438 |
/+ | +0.436 |
Neg logit contributions | |
uits | -0.469 |
| -0.459 |
Hyde | -0.456 |
ongo | -0.443 |
ulic | -0.441 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ofi | +0.705 |
LT | +0.697 |
avorite | +0.674 |
thel | +0.635 |
/+ | +0.633 |
Neg logit contributions | |
uits | -0.690 |
| -0.675 |
Hyde | -0.671 |
ongo | -0.652 |
ulic | -0.650 |
Token | D |
Token ID | 360 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
LT | +1.350 |
ofi | +1.333 |
/+ | +1.223 |
thel | +1.201 |
avorite | +1.181 |
Neg logit contributions | |
uits | -1.638 |
ulic | -1.572 |
ongo | -1.553 |
| -1.548 |
�� | -1.519 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ofi | +1.696 |
LT | +1.676 |
avorite | +1.603 |
thel | +1.511 |
/+ | +1.495 |
Neg logit contributions | |
uits | -2.083 |
| -2.041 |
Hyde | -2.030 |
ongo | -1.978 |
ulic | -1.973 |
Token | all |
Token ID | 477 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
uits | +0.539 |
| +0.529 |
Hyde | +0.525 |
ongo | +0.508 |
ulic | +0.506 |
Neg logit contributions | |
ofi | -0.624 |
LT | -0.618 |
avorite | -0.598 |
thel | -0.566 |
/+ | -0.563 |
Token | protesters |
Token ID | 9584 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
uits | +1.470 |
| +1.463 |
Hyde | +1.439 |
ongo | +1.394 |
AES | +1.378 |
Neg logit contributions | |
ofi | -1.708 |
LT | -1.693 |
avorite | -1.658 |
thel | -1.552 |
/+ | -1.547 |
Token | would |
Token ID | 561 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ofi | +0.245 |
LT | +0.242 |
avorite | +0.231 |
thel | +0.219 |
/+ | +0.218 |
Neg logit contributions | |
uits | -0.264 |
Hyde | -0.257 |
| -0.256 |
ulic | -0.251 |
ongo | -0.251 |
Token | be |
Token ID | 307 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
ofi | +0.795 |
LT | +0.780 |
avorite | +0.742 |
thel | +0.707 |
/+ | +0.698 |
Neg logit contributions | |
uits | -0.973 |
Hyde | -0.946 |
| -0.939 |
ongo | -0.928 |
ulic | -0.918 |
Token | treated |
Token ID | 5716 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ofi | +0.205 |
LT | +0.203 |
avorite | +0.196 |
thel | +0.185 |
/+ | +0.185 |
Neg logit contributions | |
uits | -0.186 |
| -0.183 |
Hyde | -0.181 |
ongo | -0.176 |
ulic | -0.175 |
Token | as |
Token ID | 355 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ofi | +1.510 |
LT | +1.496 |
avorite | +1.436 |
thel | +1.369 |
/+ | +1.358 |
Neg logit contributions | |
uits | -1.376 |
Hyde | -1.338 |
| -1.335 |
ongo | -1.304 |
ulic | -1.294 |
Token | Israeli |
Token ID | 6085 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
ofi | +3.737 |
LT | +3.710 |
avorite | +3.500 |
thel | +3.367 |
/+ | +3.327 |
Neg logit contributions | |
uits | -3.689 |
Hyde | -3.504 |
ulic | -3.503 |
| -3.461 |
ongo | -3.425 |
Token | spies |
Token ID | 28801 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
uits | +0.121 |
| +0.121 |
Hyde | +0.119 |
ongo | +0.115 |
ulic | +0.114 |
Neg logit contributions | |
ofi | -0.128 |
LT | -0.126 |
avorite | -0.123 |
thel | -0.115 |
/+ | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
ofi | +2.007 |
LT | +1.991 |
avorite | +1.882 |
thel | +1.814 |
/+ | +1.790 |
Neg logit contributions | |
uits | -2.218 |
Hyde | -2.178 |
AES | -2.132 |
| -2.125 |
ulic | -2.125 |
Token |
|
Token ID | 198 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ofi | +0.377 |
LT | +0.373 |
avorite | +0.351 |
/+ | +0.338 |
thel | +0.336 |
Neg logit contributions | |
uits | -0.412 |
Hyde | -0.397 |
| -0.396 |
ongo | -0.390 |
ulic | -0.390 |
Token |
|
Token ID | 198 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
uits | +0.280 |
Hyde | +0.271 |
| +0.269 |
ulic | +0.265 |
ongo | +0.264 |
Neg logit contributions | |
ofi | -0.250 |
LT | -0.249 |
avorite | -0.230 |
/+ | -0.225 |
thel | -0.224 |
Token | ind |
Token ID | 521 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ofi | +1.845 |
LT | +1.825 |
avorite | +1.773 |
thel | +1.666 |
/+ | +1.657 |
Neg logit contributions | |
uits | -1.790 |
Hyde | -1.770 |
| -1.751 |
AES | -1.691 |
ulic | -1.669 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
uits | +2.513 |
| +2.487 |
Hyde | +2.449 |
ongo | +2.363 |
ulic | +2.358 |
Neg logit contributions | |
ofi | -2.731 |
LT | -2.693 |
avorite | -2.643 |
/+ | -2.448 |
thel | -2.438 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
uits | +0.303 |
| +0.298 |
Hyde | +0.296 |
ongo | +0.287 |
ulic | +0.286 |
Neg logit contributions | |
ofi | -0.282 |
LT | -0.279 |
avorite | -0.270 |
thel | -0.253 |
/+ | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
LT | +0.222 |
ofi | +0.220 |
avorite | +0.202 |
/+ | +0.200 |
thel | +0.198 |
Neg logit contributions | |
uits | -0.255 |
Hyde | -0.244 |
| -0.243 |
ulic | -0.241 |
ongo | -0.239 |
Token | Dub |
Token ID | 37590 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
uits | +0.313 |
| +0.307 |
Hyde | +0.305 |
ongo | +0.297 |
ulic | +0.295 |
Neg logit contributions | |
ofi | -0.319 |
LT | -0.315 |
avorite | -0.305 |
thel | -0.287 |
/+ | -0.286 |
Token | ov |
Token ID | 709 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
uits | +0.149 |
| +0.145 |
Hyde | +0.144 |
ongo | +0.140 |
ulic | +0.139 |
Neg logit contributions | |
ofi | -0.198 |
LT | -0.196 |
avorite | -0.191 |
thel | -0.181 |
/+ | -0.180 |
Token | ick |
Token ID | 624 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ofi | +4.230 |
LT | +4.150 |
avorite | +3.957 |
/+ | +3.812 |
thel | +3.774 |
Neg logit contributions | |
uits | -3.678 |
| -3.617 |
Hyde | -3.590 |
AES | -3.450 |
ongo | -3.383 |
Token | says |
Token ID | 1139 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
uits | +0.117 |
| +0.114 |
Hyde | +0.114 |
ongo | +0.110 |
ulic | +0.110 |
Neg logit contributions | |
ofi | -0.116 |
LT | -0.115 |
avorite | -0.111 |
thel | -0.104 |
/+ | -0.104 |
Token | he |
Token ID | 339 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
ofi | +0.445 |
LT | +0.439 |
avorite | +0.423 |
thel | +0.400 |
/+ | +0.400 |
Neg logit contributions | |
uits | -0.422 |
| -0.412 |
Hyde | -0.409 |
ongo | -0.399 |
ulic | -0.398 |
Token | thinks |
Token ID | 6834 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
uits | +0.486 |
| +0.476 |
Hyde | +0.473 |
ongo | +0.461 |
ulic | +0.459 |
Neg logit contributions | |
ofi | -0.469 |
LT | -0.463 |
avorite | -0.447 |
thel | -0.421 |
/+ | -0.419 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ofi | +1.466 |
LT | +1.443 |
avorite | +1.383 |
/+ | +1.304 |
thel | +1.303 |
Neg logit contributions | |
uits | -1.509 |
| -1.474 |
Hyde | -1.452 |
ulic | -1.435 |
ongo | -1.433 |
Token | have |
Token ID | 423 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
uits | +0.920 |
| +0.899 |
Hyde | +0.896 |
ongo | +0.872 |
ulic | +0.870 |
Neg logit contributions | |
ofi | -0.880 |
LT | -0.870 |
avorite | -0.836 |
thel | -0.790 |
/+ | -0.786 |
Token | never |
Token ID | 1239 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
uits | +0.687 |
| +0.672 |
Hyde | +0.668 |
ongo | +0.650 |
ulic | +0.648 |
Neg logit contributions | |
ofi | -0.716 |
LT | -0.708 |
avorite | -0.683 |
thel | -0.646 |
/+ | -0.643 |
Token | seen |
Token ID | 1775 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
ofi | +0.137 |
LT | +0.135 |
avorite | +0.129 |
thel | +0.122 |
/+ | +0.120 |
Neg logit contributions | |
uits | -0.199 |
| -0.194 |
Hyde | -0.194 |
ulic | -0.190 |
ongo | -0.190 |
Token | a |
Token ID | 257 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
ofi | +0.400 |
LT | +0.395 |
avorite | +0.382 |
thel | +0.362 |
/+ | +0.361 |
Neg logit contributions | |
uits | -0.358 |
| -0.349 |
Hyde | -0.346 |
ongo | -0.338 |
ulic | -0.337 |
Token | case |
Token ID | 1339 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
uits | +0.214 |
| +0.210 |
Hyde | +0.209 |
ongo | +0.202 |
ulic | +0.202 |
Neg logit contributions | |
ofi | -0.209 |
LT | -0.207 |
avorite | -0.200 |
thel | -0.188 |
/+ | -0.187 |
Token | like |
Token ID | 588 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ofi | +1.027 |
LT | +1.019 |
avorite | +0.972 |
thel | +0.933 |
/+ | +0.921 |
Neg logit contributions | |
uits | -1.088 |
| -1.067 |
Hyde | -1.065 |
ongo | -1.044 |
ulic | -1.041 |
Token | it |
Token ID | 340 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ofi | +3.820 |
LT | +3.717 |
avorite | +3.519 |
thel | +3.406 |
/+ | +3.357 |
Neg logit contributions | |
uits | -3.790 |
| -3.651 |
ulic | -3.643 |
ongo | -3.597 |
Hyde | -3.567 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
ofi | +2.210 |
LT | +2.181 |
avorite | +2.078 |
thel | +1.981 |
/+ | +1.971 |
Neg logit contributions | |
uits | -2.533 |
| -2.468 |
Hyde | -2.461 |
ongo | -2.425 |
ulic | -2.422 |
Token |
|
Token ID | 198 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
uits | +0.298 |
| +0.293 |
Hyde | +0.291 |
ongo | +0.282 |
ulic | +0.280 |
Neg logit contributions | |
ofi | -0.311 |
LT | -0.307 |
avorite | -0.298 |
thel | -0.280 |
/+ | -0.279 |
Token |
|
Token ID | 198 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
uits | +0.268 |
Hyde | +0.259 |
| +0.259 |
ulic | +0.254 |
ongo | +0.253 |
Neg logit contributions | |
ofi | -0.239 |
LT | -0.239 |
avorite | -0.220 |
/+ | -0.216 |
thel | -0.215 |
Token | B |
Token ID | 33 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
uits | +0.546 |
| +0.537 |
Hyde | +0.531 |
ongo | +0.517 |
ulic | +0.513 |
Neg logit contributions | |
ofi | -0.595 |
LT | -0.586 |
avorite | -0.573 |
thel | -0.537 |
/+ | -0.535 |
Token | of |
Token ID | 286 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
ofi | +1.997 |
LT | +1.985 |
avorite | +1.847 |
thel | +1.753 |
/+ | +1.733 |
Neg logit contributions | |
uits | -2.297 |
| -2.226 |
Hyde | -2.223 |
ulic | -2.172 |
ongo | -2.159 |
Token | fish |
Token ID | 5916 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ofi | +0.315 |
LT | +0.310 |
avorite | +0.294 |
thel | +0.269 |
/+ | +0.268 |
Neg logit contributions | |
uits | -0.593 |
| -0.583 |
Hyde | -0.580 |
ongo | -0.568 |
ulic | -0.567 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ofi | +1.070 |
LT | +1.062 |
avorite | +1.006 |
thel | +0.958 |
/+ | +0.951 |
Neg logit contributions | |
uits | -1.201 |
Hyde | -1.176 |
| -1.174 |
ongo | -1.149 |
ulic | -1.142 |
Token | Each |
Token ID | 5501 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ofi | +1.757 |
LT | +1.755 |
avorite | +1.600 |
/+ | +1.575 |
thel | +1.567 |
Neg logit contributions | |
uits | -2.143 |
| -2.053 |
Hyde | -2.043 |
ongo | -2.032 |
ulic | -2.025 |
Token | ST |
Token ID | 3563 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
ofi | +0.195 |
LT | +0.193 |
avorite | +0.186 |
thel | +0.177 |
/+ | +0.177 |
Neg logit contributions | |
uits | -0.158 |
| -0.154 |
Hyde | -0.153 |
ongo | -0.149 |
ulic | -0.148 |
Token | - |
Token ID | 12 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
uits | +0.595 |
| +0.589 |
Hyde | +0.584 |
ongo | +0.564 |
ulic | +0.562 |
Neg logit contributions | |
ofi | -0.657 |
LT | -0.643 |
avorite | -0.632 |
thel | -0.596 |
/+ | -0.594 |
Token | L |
Token ID | 43 |
Feature activation | +9.11e-03 |
Pos logit contributions | |
LT | +2.850 |
ofi | +2.761 |
avorite | +2.424 |
thel | +2.399 |
/+ | +2.343 |
Neg logit contributions | |
uits | -4.947 |
Hyde | -4.837 |
| -4.760 |
AES | -4.692 |
ulic | -4.681 |
Token | has |
Token ID | 468 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
ofi | +0.066 |
LT | +0.065 |
avorite | +0.063 |
thel | +0.059 |
/+ | +0.059 |
Neg logit contributions | |
uits | -0.066 |
| -0.064 |
Hyde | -0.064 |
ongo | -0.062 |
ulic | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ofi | +0.062 |
LT | +0.062 |
avorite | +0.060 |
thel | +0.056 |
/+ | +0.056 |
Neg logit contributions | |
uits | -0.063 |
| -0.062 |
Hyde | -0.061 |
ongo | -0.060 |
ulic | -0.059 |
Token | built |
Token ID | 3170 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ofi | +0.229 |
LT | +0.227 |
avorite | +0.219 |
thel | +0.206 |
/+ | +0.206 |
Neg logit contributions | |
uits | -0.222 |
| -0.218 |
Hyde | -0.216 |
ongo | -0.210 |
ulic | -0.209 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ofi | +0.265 |
LT | +0.262 |
avorite | +0.255 |
thel | +0.241 |
/+ | +0.239 |
Neg logit contributions | |
uits | -0.243 |
| -0.240 |
Hyde | -0.239 |
ongo | -0.230 |
AES | -0.229 |
Token | http |
Token ID | 2638 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ofi | +1.653 |
LT | +1.630 |
avorite | +1.575 |
thel | +1.510 |
/+ | +1.501 |
Neg logit contributions | |
uits | -1.249 |
Hyde | -1.200 |
| -1.200 |
ongo | -1.164 |
ulic | -1.161 |
Token | :// |
Token ID | 1378 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
LT | +1.293 |
ofi | +1.282 |
/+ | +1.165 |
thel | +1.076 |
WP | +1.030 |
Neg logit contributions | |
uits | -3.220 |
Hyde | -3.145 |
�� | -3.132 |
ulic | -3.105 |
ongo | -3.067 |
Token | www |
Token ID | 2503 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ofi | +3.071 |
LT | +2.997 |
avorite | +2.827 |
thel | +2.800 |
/+ | +2.729 |
Neg logit contributions | |
uits | -3.146 |
Hyde | -3.105 |
| -3.049 |
AES | -2.959 |
ulic | -2.929 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ofi | +0.680 |
LT | +0.677 |
/+ | +0.614 |
thel | +0.606 |
avorite | +0.600 |
Neg logit contributions | |
uits | -0.903 |
Hyde | -0.881 |
| -0.872 |
ulic | -0.862 |
�� | -0.858 |
Token | n |
Token ID | 77 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
uits | +0.140 |
Hyde | +0.137 |
| +0.136 |
ongo | +0.129 |
ulic | +0.129 |
Neg logit contributions | |
ofi | -0.236 |
LT | -0.232 |
avorite | -0.225 |
thel | -0.217 |
/+ | -0.216 |
Token | h |
Token ID | 71 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
uits | +0.315 |
| +0.310 |
Hyde | +0.309 |
ongo | +0.298 |
ulic | +0.298 |
Neg logit contributions | |
ofi | -0.295 |
LT | -0.292 |
avorite | -0.279 |
thel | -0.265 |
/+ | -0.263 |
Token | ts |
Token ID | 912 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ofi | +3.324 |
LT | +3.230 |
/+ | +2.980 |
thel | +2.929 |
avorite | +2.918 |
Neg logit contributions | |
Hyde | -5.859 |
| -5.780 |
uits | -5.762 |
�� | -5.725 |
AES | -5.578 |
Token | a |
Token ID | 64 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ofi | +2.173 |
LT | +2.063 |
/+ | +1.959 |
thel | +1.929 |
avorite | +1.914 |
Neg logit contributions | |
Hyde | -2.557 |
uits | -2.528 |
�� | -2.503 |
| -2.502 |
ulic | -2.431 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
LT | +2.165 |
ofi | +2.165 |
/+ | +1.958 |
thel | +1.914 |
WP | +1.842 |
Neg logit contributions | |
uits | -3.241 |
�� | -3.188 |
Hyde | -3.177 |
| -3.115 |
ulic | -3.065 |
Token | dot |
Token ID | 26518 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
ofi | +0.767 |
LT | +0.748 |
avorite | +0.701 |
thel | +0.651 |
/+ | +0.644 |
Neg logit contributions | |
uits | -1.516 |
| -1.489 |
Hyde | -1.488 |
ongo | -1.451 |
ulic | -1.448 |
Token | . |
Token ID | 13 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
ofi | +0.542 |
LT | +0.541 |
/+ | +0.490 |
thel | +0.481 |
avorite | +0.472 |
Neg logit contributions | |
uits | -0.727 |
Hyde | -0.708 |
| -0.701 |
�� | -0.696 |
ulic | -0.694 |
Token | to |
Token ID | 284 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
uits | +0.409 |
| +0.399 |
Hyde | +0.399 |
ulic | +0.387 |
ongo | +0.386 |
Neg logit contributions | |
ofi | -0.354 |
LT | -0.351 |
avorite | -0.332 |
thel | -0.316 |
/+ | -0.316 |
Token | a |
Token ID | 257 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ofi | +1.176 |
LT | +1.162 |
avorite | +1.115 |
thel | +1.050 |
/+ | +1.035 |
Neg logit contributions | |
uits | -1.476 |
Hyde | -1.442 |
| -1.438 |
ongo | -1.402 |
ulic | -1.393 |
Token | close |
Token ID | 1969 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ofi | +0.180 |
LT | +0.178 |
avorite | +0.171 |
thel | +0.162 |
/+ | +0.161 |
Neg logit contributions | |
uits | -0.173 |
| -0.169 |
Hyde | -0.168 |
ongo | -0.163 |
ulic | -0.163 |
Token | examination |
Token ID | 12452 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ofi | +1.627 |
LT | +1.602 |
avorite | +1.518 |
/+ | +1.468 |
thel | +1.456 |
Neg logit contributions | |
uits | -1.583 |
| -1.541 |
Hyde | -1.540 |
ulic | -1.501 |
ongo | -1.489 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ofi | +1.013 |
LT | +1.001 |
avorite | +0.964 |
thel | +0.910 |
/+ | +0.905 |
Neg logit contributions | |
uits | -1.045 |
| -1.022 |
Hyde | -1.019 |
ongo | -0.991 |
ulic | -0.987 |
Token | whether |
Token ID | 1771 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ofi | +0.717 |
LT | +0.705 |
avorite | +0.681 |
thel | +0.645 |
/+ | +0.639 |
Neg logit contributions | |
uits | -0.734 |
| -0.714 |
Hyde | -0.712 |
ulic | -0.698 |
ongo | -0.693 |
Token | Ross |
Token ID | 9847 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ofi | +0.994 |
LT | +0.979 |
avorite | +0.942 |
/+ | +0.894 |
thel | +0.892 |
Neg logit contributions | |
uits | -0.966 |
Hyde | -0.925 |
| -0.924 |
ulic | -0.909 |
ongo | -0.904 |
Token | � |
Token ID | 447 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
uits | +1.115 |
| +1.098 |
Hyde | +1.089 |
ongo | +1.056 |
ulic | +1.050 |
Neg logit contributions | |
ofi | -1.059 |
LT | -1.047 |
avorite | -1.010 |
thel | -0.950 |
/+ | -0.945 |
Token | � |
Token ID | 247 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
ofi | +1.222 |
LT | +1.213 |
avorite | +1.136 |
/+ | +1.114 |
thel | +1.093 |
Neg logit contributions | |
uits | -1.175 |
Hyde | -1.139 |
ulic | -1.121 |
ongo | -1.118 |
| -1.114 |
Token | testimony |
Token ID | 9709 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ofi | +0.484 |
LT | +0.477 |
avorite | +0.460 |
thel | +0.436 |
/+ | +0.434 |
Neg logit contributions | |
uits | -0.488 |
| -0.476 |
Hyde | -0.475 |
ongo | -0.462 |
ulic | -0.459 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ofi | +1.484 |
LT | +1.464 |
avorite | +1.392 |
thel | +1.339 |
/+ | +1.333 |
Neg logit contributions | |
uits | -1.620 |
Hyde | -1.578 |
ulic | -1.570 |
| -1.568 |
ongo | -1.547 |
Token | over |
Token ID | 2502 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
uits | +1.343 |
| +1.343 |
Hyde | +1.326 |
ongo | +1.294 |
ulic | +1.275 |
Neg logit contributions | |
ofi | -1.402 |
LT | -1.400 |
avorite | -1.380 |
/+ | -1.278 |
thel | -1.278 |
Token | and |
Token ID | 290 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
uits | +0.837 |
| +0.832 |
Hyde | +0.813 |
ongo | +0.793 |
ulic | +0.790 |
Neg logit contributions | |
ofi | -0.946 |
LT | -0.939 |
avorite | -0.920 |
thel | -0.859 |
/+ | -0.856 |
Token | at |
Token ID | 379 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
ofi | +0.408 |
LT | +0.402 |
avorite | +0.387 |
thel | +0.367 |
/+ | +0.366 |
Neg logit contributions | |
uits | -0.373 |
| -0.360 |
Hyde | -0.360 |
ongo | -0.350 |
ulic | -0.350 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uits | +0.337 |
| +0.331 |
Hyde | +0.329 |
ongo | +0.320 |
ulic | +0.318 |
Neg logit contributions | |
ofi | -0.342 |
LT | -0.338 |
avorite | -0.327 |
thel | -0.308 |
/+ | -0.307 |
Token | Turkish |
Token ID | 9663 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
ofi | +0.758 |
LT | +0.747 |
avorite | +0.713 |
thel | +0.681 |
/+ | +0.679 |
Neg logit contributions | |
uits | -0.724 |
| -0.698 |
Hyde | -0.692 |
ulic | -0.677 |
ongo | -0.677 |
Token | foreign |
Token ID | 3215 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
ofi | +0.737 |
LT | +0.728 |
avorite | +0.701 |
thel | +0.667 |
/+ | +0.667 |
Neg logit contributions | |
uits | -0.626 |
| -0.603 |
Hyde | -0.600 |
ongo | -0.583 |
ulic | -0.582 |
Token | ministry |
Token ID | 11957 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
uits | +0.462 |
| +0.457 |
Hyde | +0.452 |
ongo | +0.437 |
ulic | +0.435 |
Neg logit contributions | |
ofi | -0.565 |
LT | -0.561 |
avorite | -0.545 |
thel | -0.514 |
/+ | -0.511 |
Token | under |
Token ID | 739 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ofi | +0.694 |
LT | +0.686 |
avorite | +0.658 |
thel | +0.626 |
/+ | +0.623 |
Neg logit contributions | |
uits | -0.673 |
Hyde | -0.651 |
| -0.647 |
ulic | -0.632 |
ongo | -0.632 |
Token | secretary |
Token ID | 7705 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
uits | +2.012 |
| +2.009 |
Hyde | +1.984 |
ongo | +1.919 |
ulic | +1.894 |
Neg logit contributions | |
ofi | -2.274 |
LT | -2.250 |
avorite | -2.201 |
thel | -2.084 |
/+ | -2.084 |
Token | Fer |
Token ID | 12880 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
uits | +0.800 |
| +0.795 |
Hyde | +0.783 |
ongo | +0.754 |
ulic | +0.754 |
Neg logit contributions | |
ofi | -0.807 |
LT | -0.803 |
avorite | -0.782 |
thel | -0.733 |
/+ | -0.727 |
Token | id |
Token ID | 312 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ofi | +0.828 |
LT | +0.821 |
avorite | +0.800 |
thel | +0.767 |
/+ | +0.764 |
Neg logit contributions | |
uits | -0.398 |
| -0.385 |
Hyde | -0.382 |
ongo | -0.365 |
ulic | -0.362 |
Token | aware |
Token ID | 3910 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ofi | +2.089 |
LT | +2.062 |
avorite | +1.960 |
/+ | +1.865 |
thel | +1.863 |
Neg logit contributions | |
uits | -2.219 |
| -2.153 |
Hyde | -2.145 |
ulic | -2.114 |
ongo | -2.105 |
Token | that |
Token ID | 326 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ofi | +2.409 |
LT | +2.373 |
avorite | +2.260 |
thel | +2.137 |
/+ | +2.121 |
Neg logit contributions | |
uits | -2.568 |
Hyde | -2.491 |
| -2.485 |
ulic | -2.430 |
ongo | -2.429 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ofi | +1.511 |
LT | +1.494 |
avorite | +1.436 |
thel | +1.354 |
/+ | +1.351 |
Neg logit contributions | |
uits | -1.479 |
| -1.421 |
Hyde | -1.417 |
ulic | -1.401 |
ongo | -1.393 |
Token | 's |
Token ID | 338 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ofi | +1.082 |
LT | +1.066 |
avorite | +1.015 |
thel | +0.966 |
/+ | +0.961 |
Neg logit contributions | |
uits | -1.194 |
| -1.163 |
Hyde | -1.163 |
ulic | -1.139 |
ongo | -1.132 |
Token | not |
Token ID | 407 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ofi | +0.781 |
LT | +0.772 |
avorite | +0.740 |
thel | +0.706 |
/+ | +0.700 |
Neg logit contributions | |
uits | -0.727 |
| -0.707 |
Hyde | -0.701 |
ulic | -0.693 |
ongo | -0.687 |
Token | an |
Token ID | 281 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
uits | +0.983 |
| +0.964 |
Hyde | +0.961 |
ongo | +0.925 |
AES | +0.925 |
Neg logit contributions | |
ofi | -1.054 |
LT | -1.041 |
avorite | -1.011 |
thel | -0.949 |
/+ | -0.944 |
Token | apples |
Token ID | 22514 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
ofi | +0.281 |
LT | +0.278 |
avorite | +0.269 |
thel | +0.257 |
/+ | +0.256 |
Neg logit contributions | |
uits | -0.207 |
| -0.201 |
Hyde | -0.199 |
ulic | -0.194 |
ongo | -0.193 |
Token | - |
Token ID | 12 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
uits | +0.396 |
| +0.387 |
Hyde | +0.385 |
ongo | +0.374 |
ulic | +0.373 |
Neg logit contributions | |
ofi | -0.404 |
LT | -0.400 |
avorite | -0.386 |
thel | -0.364 |
/+ | -0.363 |
Token | to |
Token ID | 1462 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
uits | +3.315 |
| +3.199 |
ongo | +3.134 |
Hyde | +3.127 |
AES | +3.044 |
Neg logit contributions | |
ofi | -4.395 |
LT | -4.337 |
avorite | -4.213 |
thel | -3.991 |
/+ | -3.938 |
Token | - |
Token ID | 12 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
uits | +2.192 |
| +2.153 |
Hyde | +2.122 |
ongo | +2.066 |
AES | +2.046 |
Neg logit contributions | |
ofi | -2.380 |
LT | -2.350 |
avorite | -2.303 |
thel | -2.142 |
/+ | -2.125 |
Token | app |
Token ID | 1324 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
uits | +3.173 |
| +3.079 |
ongo | +2.965 |
Hyde | +2.916 |
AES | +2.862 |
Neg logit contributions | |
LT | -3.864 |
ofi | -3.859 |
avorite | -3.689 |
/+ | -3.521 |
thel | -3.480 |
Token | s |
Token ID | 82 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
ofi | +0.600 |
LT | +0.594 |
avorite | +0.570 |
thel | +0.544 |
/+ | +0.539 |
Neg logit contributions | |
uits | -0.569 |
| -0.554 |
Hyde | -0.553 |
ulic | -0.537 |
ongo | -0.534 |
Token | oul |
Token ID | 2852 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
uits | +0.321 |
| +0.309 |
Hyde | +0.304 |
ongo | +0.292 |
ulic | +0.288 |
Neg logit contributions | |
ofi | -0.753 |
LT | -0.749 |
avorite | -0.732 |
/+ | -0.700 |
thel | -0.699 |
Token | defence |
Token ID | 9366 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
uits | +1.166 |
| +1.159 |
Hyde | +1.141 |
ongo | +1.104 |
ulic | +1.095 |
Neg logit contributions | |
ofi | -1.102 |
LT | -1.089 |
avorite | -1.066 |
/+ | -0.995 |
thel | -0.990 |
Token | man |
Token ID | 805 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
ofi | +0.099 |
LT | +0.098 |
avorite | +0.095 |
thel | +0.091 |
/+ | +0.090 |
Neg logit contributions | |
uits | -0.066 |
| -0.064 |
Hyde | -0.063 |
ongo | -0.061 |
ulic | -0.061 |
Token | Josh |
Token ID | 8518 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
uits | +0.637 |
| +0.627 |
Hyde | +0.622 |
ongo | +0.603 |
ulic | +0.602 |
Neg logit contributions | |
ofi | -0.584 |
LT | -0.578 |
avorite | -0.562 |
thel | -0.524 |
/+ | -0.522 |
Token | G |
Token ID | 402 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
uits | +0.704 |
Hyde | +0.698 |
| +0.696 |
ongo | +0.670 |
AES | +0.665 |
Neg logit contributions | |
ofi | -0.690 |
LT | -0.679 |
avorite | -0.668 |
thel | -0.619 |
/+ | -0.617 |
Token | org |
Token ID | 2398 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ofi | +1.454 |
LT | +1.445 |
avorite | +1.409 |
thel | +1.364 |
/+ | +1.359 |
Neg logit contributions | |
uits | -0.356 |
| -0.338 |
Hyde | -0.333 |
ongo | -0.306 |
AES | -0.301 |
Token | es |
Token ID | 274 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
uits | +0.333 |
| +0.321 |
Hyde | +0.311 |
ulic | +0.307 |
ongo | +0.304 |
Neg logit contributions | |
LT | -0.558 |
ofi | -0.555 |
avorite | -0.548 |
thel | -0.517 |
/+ | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
uits | +1.458 |
| +1.430 |
Hyde | +1.400 |
ongo | +1.372 |
ulic | +1.364 |
Neg logit contributions | |
LT | -1.587 |
ofi | -1.586 |
avorite | -1.550 |
/+ | -1.463 |
thel | -1.461 |
Token | and |
Token ID | 290 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
uits | +0.311 |
| +0.305 |
Hyde | +0.303 |
ongo | +0.295 |
ulic | +0.293 |
Neg logit contributions | |
ofi | -0.322 |
LT | -0.319 |
avorite | -0.308 |
thel | -0.290 |
/+ | -0.289 |
Token | playoff |
Token ID | 13119 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
uits | +0.608 |
| +0.595 |
Hyde | +0.591 |
ongo | +0.575 |
ulic | +0.572 |
Neg logit contributions | |
ofi | -0.614 |
LT | -0.607 |
avorite | -0.587 |
thel | -0.553 |
/+ | -0.551 |
Token | right |
Token ID | 826 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ofi | +0.196 |
LT | +0.194 |
avorite | +0.187 |
thel | +0.176 |
/+ | +0.176 |
Neg logit contributions | |
uits | -0.204 |
| -0.200 |
Hyde | -0.199 |
ongo | -0.193 |
ulic | -0.192 |
Token | away |
Token ID | 1497 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ofi | +0.862 |
LT | +0.850 |
avorite | +0.809 |
thel | +0.765 |
/+ | +0.756 |
Neg logit contributions | |
uits | -1.153 |
| -1.128 |
Hyde | -1.127 |
ongo | -1.101 |
ulic | -1.100 |
Token | ' |
Token ID | 6 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ofi | +0.729 |
LT | +0.719 |
avorite | +0.681 |
thel | +0.634 |
/+ | +0.630 |
Neg logit contributions | |
uits | -1.214 |
| -1.190 |
Hyde | -1.189 |
ongo | -1.166 |
ulic | -1.160 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
uits | +0.834 |
| +0.830 |
Hyde | +0.820 |
ongo | +0.784 |
AES | +0.779 |
Neg logit contributions | |
ofi | -0.846 |
LT | -0.839 |
avorite | -0.815 |
/+ | -0.761 |
thel | -0.754 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
LT | +0.348 |
ofi | +0.347 |
avorite | +0.315 |
/+ | +0.315 |
thel | +0.311 |
Neg logit contributions | |
uits | -0.401 |
Hyde | -0.387 |
| -0.385 |
ulic | -0.381 |
ongo | -0.379 |
Token | T |
Token ID | 51 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ofi | +0.800 |
LT | +0.793 |
avorite | +0.758 |
thel | +0.715 |
/+ | +0.712 |
Neg logit contributions | |
uits | -0.908 |
| -0.887 |
Hyde | -0.884 |
ongo | -0.861 |
ulic | -0.859 |
Token | ori |
Token ID | 10145 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ofi | +2.796 |
LT | +2.766 |
avorite | +2.692 |
thel | +2.582 |
/+ | +2.569 |
Neg logit contributions | |
uits | -1.414 |
| -1.372 |
Hyde | -1.363 |
ongo | -1.298 |
ulic | -1.296 |
Token | was |
Token ID | 373 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ofi | +1.591 |
LT | +1.569 |
avorite | +1.498 |
thel | +1.422 |
/+ | +1.421 |
Neg logit contributions | |
uits | -1.667 |
| -1.612 |
Hyde | -1.607 |
ongo | -1.577 |
ulic | -1.567 |
Token | eventually |
Token ID | 4191 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
ofi | +1.347 |
LT | +1.334 |
avorite | +1.262 |
thel | +1.209 |
/+ | +1.201 |
Neg logit contributions | |
uits | -1.410 |
| -1.377 |
Hyde | -1.364 |
ulic | -1.341 |
ongo | -1.340 |
Token | taken |
Token ID | 2077 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ofi | +0.034 |
LT | +0.034 |
avorite | +0.032 |
thel | +0.031 |
/+ | +0.030 |
Neg logit contributions | |
uits | -0.034 |
| -0.033 |
Hyde | -0.033 |
ongo | -0.032 |
ulic | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ofi | +2.325 |
LT | +2.323 |
avorite | +2.174 |
thel | +2.103 |
/+ | +2.046 |
Neg logit contributions | |
uits | -2.833 |
| -2.769 |
ulic | -2.753 |
Hyde | -2.749 |
ongo | -2.709 |
Token | 60 |
Token ID | 3126 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
ofi | +0.854 |
LT | +0.840 |
avorite | +0.803 |
/+ | +0.762 |
thel | +0.757 |
Neg logit contributions | |
uits | -1.031 |
| -0.996 |
Hyde | -0.990 |
ongo | -0.976 |
ulic | -0.975 |
Token | percent |
Token ID | 1411 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
uits | +0.406 |
| +0.399 |
Hyde | +0.395 |
ongo | +0.384 |
ulic | +0.382 |
Neg logit contributions | |
ofi | -0.396 |
LT | -0.393 |
avorite | -0.381 |
thel | -0.359 |
/+ | -0.356 |
Token | of |
Token ID | 286 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ofi | +2.136 |
LT | +2.106 |
avorite | +2.026 |
thel | +1.907 |
/+ | +1.895 |
Neg logit contributions | |
uits | -2.261 |
| -2.204 |
Hyde | -2.203 |
ongo | -2.152 |
ulic | -2.134 |
Token | our |
Token ID | 674 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
uits | +0.211 |
| +0.206 |
Hyde | +0.205 |
ongo | +0.199 |
ulic | +0.198 |
Neg logit contributions | |
ofi | -0.230 |
LT | -0.227 |
avorite | -0.220 |
thel | -0.208 |
/+ | -0.207 |
Token | gross |
Token ID | 10319 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
uits | +1.388 |
| +1.368 |
Hyde | +1.358 |
ongo | +1.320 |
ulic | +1.317 |
Neg logit contributions | |
ofi | -1.252 |
LT | -1.237 |
avorite | -1.194 |
thel | -1.122 |
/+ | -1.116 |
Token | domestic |
Token ID | 5928 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ofi | +0.880 |
LT | +0.875 |
avorite | +0.838 |
thel | +0.795 |
/+ | +0.793 |
Neg logit contributions | |
uits | -0.829 |
Hyde | -0.804 |
| -0.803 |
ongo | -0.779 |
ulic | -0.775 |
Token | product |
Token ID | 1720 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
| +3.800 |
Hyde | +3.600 |
uits | +3.575 |
AES | +3.546 |
ongo | +3.446 |
Neg logit contributions | |
avorite | -4.259 |
ofi | -4.230 |
LT | -4.111 |
thel | -3.933 |
/+ | -3.847 |
Token | and |
Token ID | 290 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
| +2.108 |
uits | +2.074 |
Hyde | +2.021 |
ongo | +1.954 |
ulic | +1.942 |
Neg logit contributions | |
ofi | -2.377 |
LT | -2.329 |
avorite | -2.295 |
thel | -2.162 |
/+ | -2.135 |
Token | possess |
Token ID | 8588 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
uits | +1.691 |
| +1.663 |
Hyde | +1.649 |
ongo | +1.594 |
ulic | +1.587 |
Neg logit contributions | |
ofi | -1.709 |
LT | -1.691 |
avorite | -1.638 |
thel | -1.543 |
/+ | -1.533 |
Token | enormous |
Token ID | 9812 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
uits | +0.249 |
| +0.244 |
Hyde | +0.242 |
ongo | +0.236 |
ulic | +0.235 |
Neg logit contributions | |
ofi | -0.258 |
LT | -0.256 |
avorite | -0.247 |
thel | -0.233 |
/+ | -0.232 |
Token | economic |
Token ID | 3034 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uits | +0.297 |
| +0.291 |
Hyde | +0.289 |
ongo | +0.281 |
ulic | +0.280 |
Neg logit contributions | |
ofi | -0.320 |
LT | -0.317 |
avorite | -0.306 |
thel | -0.289 |
/+ | -0.288 |
Token | Each |
Token ID | 5501 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ofi | +0.071 |
LT | +0.070 |
avorite | +0.068 |
thel | +0.063 |
/+ | +0.063 |
Neg logit contributions | |
uits | -0.086 |
| -0.084 |
Hyde | -0.084 |
ongo | -0.081 |
ulic | -0.081 |
Token | other |
Token ID | 847 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
uits | +1.187 |
Hyde | +1.162 |
| +1.159 |
ongo | +1.105 |
AES | +1.092 |
Neg logit contributions | |
ofi | -1.948 |
LT | -1.928 |
avorite | -1.901 |
thel | -1.789 |
/+ | -1.775 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
uits | +0.617 |
| +0.606 |
Hyde | +0.605 |
ongo | +0.586 |
ulic | +0.583 |
Neg logit contributions | |
ofi | -0.545 |
LT | -0.537 |
avorite | -0.525 |
thel | -0.485 |
/+ | -0.483 |
Token | 01 |
Token ID | 486 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
LT | +1.836 |
ofi | +1.813 |
/+ | +1.702 |
WP | +1.664 |
thel | +1.662 |
Neg logit contributions | |
uits | -1.512 |
ulic | -1.447 |
�� | -1.396 |
Hyde | -1.386 |
ongo | -1.367 |
Token | 12 |
Token ID | 1065 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
uits | +1.949 |
| +1.943 |
Hyde | +1.939 |
ongo | +1.796 |
AES | +1.732 |
Neg logit contributions | |
ofi | -5.601 |
avorite | -5.404 |
LT | -5.404 |
thel | -5.174 |
/+ | -5.061 |
Token | O |
Token ID | 440 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
uits | +1.819 |
| +1.789 |
Hyde | +1.780 |
ongo | +1.701 |
AES | +1.691 |
Neg logit contributions | |
ofi | -2.905 |
LT | -2.867 |
avorite | -2.837 |
thel | -2.665 |
/+ | -2.640 |
Token | & |
Token ID | 5 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
uits | +2.427 |
| +2.396 |
Hyde | +2.358 |
ongo | +2.293 |
AES | +2.269 |
Neg logit contributions | |
ofi | -2.748 |
avorite | -2.740 |
LT | -2.695 |
thel | -2.484 |
/+ | -2.433 |
Token | A |
Token ID | 32 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
| +2.577 |
uits | +2.531 |
Hyde | +2.511 |
AES | +2.450 |
ongo | +2.429 |
Neg logit contributions | |
avorite | -2.585 |
ofi | -2.541 |
LT | -2.467 |
thel | -2.287 |
/+ | -2.206 |
Token | - |
Token ID | 12 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
uits | +0.613 |
| +0.596 |
Hyde | +0.594 |
ongo | +0.579 |
ulic | +0.579 |
Neg logit contributions | |
ofi | -0.608 |
LT | -0.604 |
avorite | -0.574 |
/+ | -0.548 |
thel | -0.548 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
uits | +0.013 |
| +0.012 |
Hyde | +0.012 |
ongo | +0.012 |
ulic | +0.012 |
Neg logit contributions | |
ofi | -0.014 |
LT | -0.014 |
avorite | -0.013 |
thel | -0.012 |
/+ | -0.012 |
Token | Saturday |
Token ID | 3909 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
uits | +0.870 |
| +0.855 |
Hyde | +0.853 |
ongo | +0.824 |
ulic | +0.818 |
Neg logit contributions | |
ofi | -1.029 |
LT | -1.016 |
avorite | -0.993 |
thel | -0.933 |
/+ | -0.929 |
Token | you |
Token ID | 345 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
uits | +0.931 |
| +0.918 |
Hyde | +0.915 |
ongo | +0.884 |
ulic | +0.880 |
Neg logit contributions | |
ofi | -0.818 |
LT | -0.809 |
avorite | -0.781 |
thel | -0.730 |
/+ | -0.727 |
Token | drive |
Token ID | 3708 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ofi | +1.326 |
LT | +1.323 |
avorite | +1.266 |
/+ | +1.206 |
thel | +1.194 |
Neg logit contributions | |
uits | -1.222 |
Hyde | -1.186 |
| -1.175 |
ongo | -1.157 |
ulic | -1.146 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ofi | +0.798 |
LT | +0.791 |
avorite | +0.757 |
thel | +0.721 |
/+ | +0.717 |
Neg logit contributions | |
uits | -0.764 |
| -0.744 |
Hyde | -0.741 |
ongo | -0.722 |
ulic | -0.721 |
Token | you |
Token ID | 345 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ofi | +1.735 |
LT | +1.725 |
avorite | +1.639 |
/+ | +1.571 |
thel | +1.556 |
Neg logit contributions | |
uits | -1.851 |
| -1.795 |
Hyde | -1.794 |
ongo | -1.755 |
ulic | -1.743 |
Token | can |
Token ID | 460 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ofi | +0.900 |
LT | +0.894 |
avorite | +0.850 |
thel | +0.801 |
/+ | +0.796 |
Neg logit contributions | |
uits | -1.123 |
Hyde | -1.097 |
| -1.092 |
ongo | -1.068 |
ulic | -1.060 |
Token | even |
Token ID | 772 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ofi | +0.610 |
LT | +0.608 |
avorite | +0.581 |
/+ | +0.554 |
thel | +0.550 |
Neg logit contributions | |
uits | -0.581 |
Hyde | -0.566 |
| -0.563 |
ongo | -0.550 |
ulic | -0.544 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
uits | +0.815 |
| +0.800 |
Hyde | +0.793 |
ongo | +0.770 |
ulic | +0.768 |
Neg logit contributions | |
ofi | -0.825 |
LT | -0.815 |
avorite | -0.787 |
thel | -0.743 |
/+ | -0.738 |
Token | radio |
Token ID | 5243 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ofi | +1.219 |
LT | +1.204 |
avorite | +1.147 |
/+ | +1.097 |
thel | +1.090 |
Neg logit contributions | |
uits | -1.291 |
| -1.256 |
Hyde | -1.251 |
ongo | -1.221 |
ulic | -1.217 |
Token | chatter |
Token ID | 37303 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
uits | +2.410 |
| +2.361 |
Hyde | +2.307 |
ongo | +2.259 |
AES | +2.252 |
Neg logit contributions | |
ofi | -3.063 |
LT | -3.013 |
avorite | -2.980 |
thel | -2.771 |
/+ | -2.734 |
Token | from |
Token ID | 422 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
uits | +0.807 |
| +0.790 |
Hyde | +0.783 |
ongo | +0.762 |
ulic | +0.758 |
Neg logit contributions | |
ofi | -0.852 |
LT | -0.842 |
avorite | -0.816 |
thel | -0.768 |
/+ | -0.764 |
Token | your |
Token ID | 534 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
uits | +0.456 |
| +0.447 |
Hyde | +0.444 |
ongo | +0.431 |
ulic | +0.430 |
Neg logit contributions | |
ofi | -0.476 |
LT | -0.471 |
avorite | -0.455 |
thel | -0.429 |
/+ | -0.427 |
Token | bring |
Token ID | 2222 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ofi | +1.135 |
LT | +1.115 |
avorite | +1.061 |
thel | +1.025 |
/+ | +1.014 |
Neg logit contributions | |
uits | -1.170 |
Hyde | -1.142 |
| -1.116 |
ongo | -1.110 |
ulic | -1.096 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ofi | +2.112 |
LT | +2.061 |
avorite | +1.958 |
thel | +1.878 |
/+ | +1.873 |
Neg logit contributions | |
uits | -2.182 |
Hyde | -2.126 |
| -2.108 |
ulic | -2.075 |
ongo | -2.061 |
Token | problems |
Token ID | 2761 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
ofi | +0.957 |
LT | +0.947 |
avorite | +0.907 |
thel | +0.864 |
/+ | +0.860 |
Neg logit contributions | |
uits | -0.881 |
Hyde | -0.856 |
| -0.855 |
ongo | -0.832 |
ulic | -0.831 |
Token | to |
Token ID | 284 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
uits | +0.692 |
| +0.680 |
Hyde | +0.673 |
ongo | +0.653 |
ulic | +0.651 |
Neg logit contributions | |
ofi | -0.706 |
LT | -0.700 |
avorite | -0.679 |
thel | -0.638 |
/+ | -0.634 |
Token | Congress |
Token ID | 3162 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
ofi | +4.580 |
LT | +4.490 |
avorite | +4.135 |
thel | +4.033 |
/+ | +4.015 |
Neg logit contributions | |
uits | -5.341 |
Hyde | -5.082 |
ulic | -5.052 |
ongo | -5.024 |
| -4.987 |
Token | so |
Token ID | 523 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
uits | +0.198 |
| +0.194 |
Hyde | +0.193 |
ongo | +0.188 |
ulic | +0.187 |
Neg logit contributions | |
ofi | -0.204 |
LT | -0.202 |
avorite | -0.195 |
thel | -0.184 |
/+ | -0.183 |
Token | we |
Token ID | 356 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
| +2.511 |
uits | +2.492 |
Hyde | +2.421 |
AES | +2.361 |
ulic | +2.344 |
Neg logit contributions | |
ofi | -3.153 |
LT | -3.129 |
avorite | -3.125 |
thel | -2.902 |
/+ | -2.879 |
Token | can |
Token ID | 460 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
uits | +0.980 |
| +0.963 |
Hyde | +0.954 |
ongo | +0.928 |
ulic | +0.926 |
Neg logit contributions | |
ofi | -0.914 |
LT | -0.904 |
avorite | -0.873 |
thel | -0.819 |
/+ | -0.816 |
Token | do |
Token ID | 466 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ofi | +0.851 |
LT | +0.837 |
avorite | +0.795 |
thel | +0.767 |
/+ | +0.767 |
Neg logit contributions | |
uits | -0.810 |
Hyde | -0.787 |
| -0.767 |
ongo | -0.766 |
ulic | -0.750 |
Token | that |
Token ID | 326 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ofi | +1.399 |
LT | +1.381 |
avorite | +1.316 |
thel | +1.251 |
/+ | +1.248 |
Neg logit contributions | |
uits | -1.506 |
Hyde | -1.468 |
| -1.463 |
ongo | -1.427 |
ulic | -1.419 |
Token | . |
Token ID | 13 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
ofi | +2.132 |
LT | +2.121 |
avorite | +1.980 |
thel | +1.922 |
/+ | +1.908 |
Neg logit contributions | |
uits | -2.327 |
Hyde | -2.251 |
| -2.197 |
ongo | -2.183 |
ulic | -2.159 |
Token | Joseph |
Token ID | 7212 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ofi | +0.395 |
LT | +0.391 |
avorite | +0.377 |
thel | +0.358 |
/+ | +0.356 |
Neg logit contributions | |
uits | -0.353 |
| -0.343 |
Hyde | -0.339 |
ongo | -0.332 |
ulic | -0.331 |
Token | Stalin |
Token ID | 17482 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ofi | +1.055 |
LT | +1.044 |
avorite | +1.013 |
thel | +0.970 |
/+ | +0.968 |
Neg logit contributions | |
uits | -0.612 |
| -0.595 |
Hyde | -0.587 |
ongo | -0.568 |
ulic | -0.565 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
uits | +0.077 |
| +0.075 |
Hyde | +0.075 |
ongo | +0.073 |
ulic | +0.073 |
Neg logit contributions | |
ofi | -0.077 |
LT | -0.076 |
avorite | -0.074 |
thel | -0.070 |
/+ | -0.069 |
Token | despite |
Token ID | 3805 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
uits | +1.735 |
| +1.711 |
Hyde | +1.697 |
ongo | +1.632 |
ulic | +1.620 |
Neg logit contributions | |
ofi | -2.100 |
LT | -2.080 |
avorite | -2.020 |
thel | -1.905 |
/+ | -1.903 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-04 |
Pos logit contributions | |
uits | +0.538 |
| +0.526 |
Hyde | +0.522 |
ongo | +0.507 |
ulic | +0.505 |
Neg logit contributions | |
ofi | -0.588 |
LT | -0.582 |
avorite | -0.562 |
thel | -0.532 |
/+ | -0.530 |
Token | reservations |
Token ID | 24722 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ofi | +0.001 |
LT | +0.001 |
avorite | +0.001 |
thel | +0.001 |
/+ | +0.001 |
Neg logit contributions | |
uits | -0.001 |
| -0.001 |
Hyde | -0.001 |
ongo | -0.001 |
ulic | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
uits | +1.032 |
| +1.013 |
Hyde | +1.006 |
ongo | +0.975 |
ulic | +0.971 |
Neg logit contributions | |
ofi | -1.106 |
LT | -1.096 |
avorite | -1.062 |
thel | -1.001 |
/+ | -0.997 |
Token | he |
Token ID | 339 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
uits | +0.926 |
| +0.906 |
Hyde | +0.900 |
ongo | +0.874 |
ulic | +0.871 |
Neg logit contributions | |
ofi | -0.986 |
LT | -0.976 |
avorite | -0.942 |
thel | -0.890 |
/+ | -0.887 |
Token | raised |
Token ID | 4376 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uits | +1.591 |
| +1.568 |
Hyde | +1.551 |
ongo | +1.507 |
ulic | +1.498 |
Neg logit contributions | |
ofi | -1.647 |
LT | -1.640 |
avorite | -1.584 |
thel | -1.484 |
/+ | -1.481 |
Token | .[ |
Token ID | 3693 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ofi | +0.725 |
LT | +0.712 |
avorite | +0.681 |
thel | +0.649 |
/+ | +0.646 |
Neg logit contributions | |
uits | -0.755 |
Hyde | -0.735 |
| -0.733 |
ongo | -0.715 |
ulic | -0.714 |
Token | 26 |
Token ID | 2075 |
Feature activation | -4.37e-03 |
Pos logit contributions | |
ofi | +1.584 |
LT | +1.566 |
avorite | +1.492 |
/+ | +1.413 |
thel | +1.408 |
Neg logit contributions | |
uits | -1.902 |
Hyde | -1.855 |
| -1.837 |
ulic | -1.801 |
ongo | -1.798 |
Token | ritch |
Token ID | 46510 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
uits | +0.853 |
| +0.827 |
Hyde | +0.816 |
ongo | +0.796 |
ulic | +0.793 |
Neg logit contributions | |
ofi | -1.274 |
LT | -1.268 |
avorite | -1.230 |
thel | -1.165 |
/+ | -1.160 |
Token | mon |
Token ID | 937 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ofi | +0.372 |
LT | +0.368 |
avorite | +0.356 |
thel | +0.338 |
/+ | +0.337 |
Neg logit contributions | |
uits | -0.318 |
| -0.310 |
Hyde | -0.308 |
ongo | -0.300 |
ulic | -0.298 |
Token | stros |
Token ID | 48288 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
uits | +1.967 |
| +1.906 |
Hyde | +1.888 |
ongo | +1.835 |
ulic | +1.821 |
Neg logit contributions | |
LT | -2.414 |
ofi | -2.397 |
avorite | -2.323 |
thel | -2.176 |
/+ | -2.169 |
Token | ities |
Token ID | 871 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
ofi | +0.504 |
LT | +0.498 |
avorite | +0.479 |
/+ | +0.460 |
thel | +0.457 |
Neg logit contributions | |
uits | -0.374 |
| -0.369 |
Hyde | -0.369 |
ongo | -0.356 |
ulic | -0.354 |
Token | year |
Token ID | 614 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
uits | +0.585 |
| +0.573 |
Hyde | +0.569 |
ongo | +0.553 |
ulic | +0.551 |
Neg logit contributions | |
ofi | -0.613 |
LT | -0.606 |
avorite | -0.585 |
thel | -0.553 |
/+ | -0.550 |
Token | after |
Token ID | 706 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
uits | +1.600 |
| +1.581 |
Hyde | +1.557 |
ongo | +1.514 |
AES | +1.497 |
Neg logit contributions | |
ofi | -1.835 |
LT | -1.818 |
avorite | -1.772 |
thel | -1.658 |
/+ | -1.652 |
Token | year |
Token ID | 614 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
| +3.176 |
Hyde | +3.076 |
uits | +2.942 |
ongo | +2.766 |
AES | +2.723 |
Neg logit contributions | |
LT | -7.773 |
ofi | -7.677 |
avorite | -7.659 |
thel | -7.174 |
/+ | -7.145 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
uits | +2.690 |
| +2.672 |
Hyde | +2.622 |
ongo | +2.513 |
ulic | +2.500 |
Neg logit contributions | |
ofi | -2.846 |
LT | -2.841 |
avorite | -2.780 |
/+ | -2.576 |
thel | -2.570 |
Token | held |
Token ID | 2714 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
uits | +2.211 |
| +2.183 |
Hyde | +2.180 |
ongo | +2.075 |
AES | +2.061 |
Neg logit contributions | |
ofi | -2.431 |
LT | -2.417 |
avorite | -2.352 |
thel | -2.214 |
/+ | -2.189 |
Token | them |
Token ID | 606 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
uits | +2.132 |
Hyde | +2.101 |
| +2.079 |
ongo | +2.007 |
AES | +1.985 |
Neg logit contributions | |
ofi | -2.412 |
LT | -2.408 |
avorite | -2.345 |
thel | -2.202 |
/+ | -2.188 |
Token | at |
Token ID | 379 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
uits | +1.691 |
| +1.652 |
Hyde | +1.645 |
ongo | +1.588 |
ulic | +1.583 |
Neg logit contributions | |
ofi | -1.827 |
LT | -1.813 |
avorite | -1.766 |
/+ | -1.651 |
thel | -1.649 |
Token | Stack |
Token ID | 23881 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
uits | +0.502 |
| +0.491 |
Hyde | +0.490 |
ongo | +0.475 |
ulic | +0.473 |
Neg logit contributions | |
ofi | -0.481 |
LT | -0.475 |
avorite | -0.460 |
thel | -0.431 |
/+ | -0.428 |
Token | pointer |
Token ID | 17562 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
uits | +2.327 |
| +2.300 |
Hyde | +2.290 |
ulic | +2.209 |
ongo | +2.186 |
Neg logit contributions | |
ofi | -3.275 |
LT | -3.254 |
avorite | -3.202 |
thel | -2.995 |
/+ | -2.975 |
Token | + |
Token ID | 1343 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
uits | +1.748 |
| +1.725 |
Hyde | +1.708 |
ongo | +1.657 |
AES | +1.655 |
Neg logit contributions | |
ofi | -1.869 |
LT | -1.849 |
avorite | -1.817 |
thel | -1.683 |
/+ | -1.656 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
uits | +2.905 |
| +2.868 |
Hyde | +2.806 |
ongo | +2.730 |
ulic | +2.706 |
Neg logit contributions | |
ofi | -3.437 |
LT | -3.374 |
avorite | -3.341 |
thel | -3.101 |
/+ | -3.056 |
Token | --+ |
Token ID | 44785 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
uits | +1.172 |
| +1.147 |
Hyde | +1.132 |
ongo | +1.094 |
ulic | +1.091 |
Neg logit contributions | |
ofi | -1.636 |
LT | -1.622 |
avorite | -1.584 |
thel | -1.496 |
/+ | -1.479 |
Token | + |
Token ID | 1343 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
uits | +0.589 |
| +0.582 |
Hyde | +0.574 |
ongo | +0.559 |
AES | +0.555 |
Neg logit contributions | |
ofi | -0.608 |
LT | -0.599 |
avorite | -0.583 |
thel | -0.548 |
/+ | -0.538 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
| +4.434 |
uits | +4.392 |
Hyde | +4.236 |
ongo | +4.100 |
AES | +4.078 |
Neg logit contributions | |
ofi | -5.931 |
avorite | -5.913 |
LT | -5.745 |
thel | -5.350 |
WP | -5.157 |
Token | --+ |
Token ID | 44785 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
uits | +0.970 |
| +0.948 |
Hyde | +0.938 |
ongo | +0.907 |
ulic | +0.904 |
Neg logit contributions | |
ofi | -1.334 |
LT | -1.323 |
avorite | -1.287 |
thel | -1.219 |
/+ | -1.210 |
Token | | |
Token ID | 930 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
ofi | +0.547 |
LT | +0.542 |
avorite | +0.526 |
thel | +0.502 |
/+ | +0.501 |
Neg logit contributions | |
uits | -0.344 |
| -0.334 |
Hyde | -0.332 |
ongo | -0.320 |
ulic | -0.318 |
Token | ... |
Token ID | 2644 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
uits | +0.688 |
| +0.674 |
Hyde | +0.669 |
ongo | +0.650 |
ulic | +0.646 |
Neg logit contributions | |
ofi | -0.749 |
LT | -0.741 |
avorite | -0.718 |
thel | -0.678 |
/+ | -0.674 |
Token | | |
Token ID | 930 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
| +3.091 |
uits | +3.048 |
Hyde | +3.039 |
AES | +3.008 |
ongo | +2.927 |
Neg logit contributions | |
ofi | -5.184 |
avorite | -5.104 |
LT | -5.088 |
thel | -4.807 |
WP | -4.615 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
uits | +0.295 |
Hyde | +0.285 |
| +0.284 |
ulic | +0.279 |
ongo | +0.278 |
Neg logit contributions | |
ofi | -0.261 |
LT | -0.261 |
avorite | -0.240 |
/+ | -0.236 |
thel | -0.235 |
Token | ______ |
Token ID | 25947 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
uits | +0.199 |
| +0.194 |
Hyde | +0.192 |
ongo | +0.185 |
ulic | +0.184 |
Neg logit contributions | |
ofi | -0.336 |
LT | -0.333 |
avorite | -0.324 |
thel | -0.309 |
/+ | -0.308 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ofi | +0.885 |
LT | +0.875 |
avorite | +0.845 |
thel | +0.796 |
/+ | +0.792 |
Neg logit contributions | |
uits | -0.911 |
| -0.892 |
Hyde | -0.887 |
ongo | -0.863 |
ulic | -0.859 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ofi | +0.124 |
LT | +0.124 |
avorite | +0.115 |
/+ | +0.112 |
thel | +0.111 |
Neg logit contributions | |
uits | -0.137 |
Hyde | -0.133 |
| -0.133 |
ulic | -0.130 |
ongo | -0.130 |
Token | X |
Token ID | 55 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ofi | +1.804 |
LT | +1.797 |
avorite | +1.723 |
thel | +1.651 |
/+ | +1.645 |
Neg logit contributions | |
uits | -1.252 |
| -1.213 |
Hyde | -1.211 |
ongo | -1.168 |
ulic | -1.166 |
Token | avier |
Token ID | 19492 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
uits | +2.924 |
| +2.848 |
Hyde | +2.793 |
ongo | +2.758 |
AES | +2.702 |
Neg logit contributions | |
ofi | -3.012 |
avorite | -2.970 |
LT | -2.967 |
/+ | -2.704 |
thel | -2.700 |
Token | Dum |
Token ID | 30933 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Hyde | +4.823 |
| +4.767 |
uits | +4.648 |
AES | +4.566 |
ulic | +4.323 |
Neg logit contributions | |
avorite | -8.096 |
ofi | -8.061 |
LT | -7.974 |
thel | -7.682 |
WP | -7.420 |
Token | us |
Token ID | 385 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
uits | +2.035 |
| +1.989 |
Hyde | +1.970 |
ongo | +1.922 |
ulic | +1.913 |
Neg logit contributions | |
ofi | -2.127 |
LT | -2.103 |
avorite | -2.039 |
thel | -1.919 |
/+ | -1.908 |
Token | que |
Token ID | 4188 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
uits | +2.449 |
| +2.373 |
Hyde | +2.290 |
ongo | +2.205 |
ulic | +2.162 |
Neg logit contributions | |
ofi | -6.341 |
LT | -6.286 |
avorite | -6.233 |
thel | -5.909 |
/+ | -5.860 |
Token | et |
Token ID | 2123 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
| +3.534 |
uits | +3.516 |
Hyde | +3.444 |
AES | +3.336 |
ongo | +3.299 |
Neg logit contributions | |
ofi | -3.751 |
avorite | -3.739 |
LT | -3.660 |
thel | -3.456 |
/+ | -3.323 |
Token | al |
Token ID | 435 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
uits | +1.530 |
| +1.482 |
Hyde | +1.472 |
ongo | +1.420 |
ulic | +1.415 |
Neg logit contributions | |
ofi | -2.593 |
LT | -2.571 |
avorite | -2.488 |
thel | -2.387 |
/+ | -2.383 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ofi | +0.760 |
LT | +0.752 |
avorite | +0.722 |
thel | +0.679 |
/+ | +0.677 |
Neg logit contributions | |
uits | -0.885 |
| -0.866 |
Hyde | -0.862 |
ongo | -0.841 |
ulic | -0.837 |
Token | Fourth |
Token ID | 15692 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ofi | +1.154 |
LT | +1.145 |
avorite | +1.067 |
/+ | +0.988 |
thel | +0.986 |
Neg logit contributions | |
uits | -2.412 |
| -2.354 |
Hyde | -2.346 |
ongo | -2.310 |
ulic | -2.302 |
Token | Div |
Token ID | 4777 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
uits | +1.039 |
| +1.015 |
Hyde | +1.011 |
ongo | +0.979 |
ulic | +0.976 |
Neg logit contributions | |
ofi | -1.058 |
LT | -1.044 |
avorite | -1.015 |
thel | -0.956 |
/+ | -0.947 |
Token | isions |
Token ID | 3279 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
ofi | +0.518 |
LT | +0.513 |
avorite | +0.498 |
thel | +0.475 |
/+ | +0.473 |
Neg logit contributions | |
uits | -0.343 |
| -0.334 |
Hyde | -0.331 |
ongo | -0.320 |
ulic | -0.318 |
Token | all |
Token ID | 477 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
uits | +0.729 |
| +0.715 |
Hyde | +0.710 |
ongo | +0.691 |
ulic | +0.688 |
Neg logit contributions | |
ofi | -0.689 |
LT | -0.681 |
avorite | -0.656 |
thel | -0.618 |
/+ | -0.615 |
Token | at |
Token ID | 379 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
uits | +2.234 |
| +2.208 |
Hyde | +2.172 |
ongo | +2.100 |
ulic | +2.090 |
Neg logit contributions | |
ofi | -2.449 |
LT | -2.447 |
avorite | -2.368 |
/+ | -2.221 |
thel | -2.220 |
Token | once |
Token ID | 1752 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
| +4.351 |
Hyde | +4.347 |
uits | +4.269 |
AES | +4.099 |
ongo | +4.070 |
Neg logit contributions | |
ofi | -6.231 |
LT | -6.154 |
avorite | -6.084 |
thel | -5.769 |
/+ | -5.690 |
Token | on |
Token ID | 319 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
| +3.611 |
uits | +3.604 |
Hyde | +3.508 |
ulic | +3.397 |
ongo | +3.388 |
Neg logit contributions | |
ofi | -3.708 |
LT | -3.681 |
avorite | -3.627 |
thel | -3.359 |
/+ | -3.311 |
Token | S |
Token ID | 311 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
uits | +2.021 |
Hyde | +1.984 |
| +1.981 |
ongo | +1.908 |
ulic | +1.890 |
Neg logit contributions | |
ofi | -2.135 |
LT | -2.111 |
avorite | -2.059 |
thel | -1.928 |
/+ | -1.924 |
Token | oky |
Token ID | 31375 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
uits | +1.898 |
| +1.871 |
Hyde | +1.845 |
ongo | +1.819 |
ulic | +1.801 |
Neg logit contributions | |
ofi | -2.175 |
LT | -2.156 |
avorite | -2.095 |
thel | -1.975 |
/+ | -1.964 |
Token | oku |
Token ID | 11601 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ofi | +0.014 |
LT | +0.014 |
avorite | +0.014 |
thel | +0.013 |
/+ | +0.013 |
Neg logit contributions | |
uits | -0.011 |
| -0.010 |
Hyde | -0.010 |
ongo | -0.010 |
ulic | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
uits | +0.346 |
| +0.339 |
Hyde | +0.337 |
ongo | +0.327 |
ulic | +0.326 |
Neg logit contributions | |
ofi | -0.330 |
LT | -0.326 |
avorite | -0.314 |
thel | -0.295 |
/+ | -0.294 |
Token | game |
Token ID | 983 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
uits | +0.311 |
| +0.305 |
Hyde | +0.303 |
ongo | +0.296 |
ulic | +0.295 |
Neg logit contributions | |
ofi | -0.266 |
LT | -0.263 |
avorite | -0.253 |
thel | -0.237 |
/+ | -0.237 |
Token | , |
Token ID | 11 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
uits | +1.713 |
| +1.680 |
Hyde | +1.664 |
ongo | +1.620 |
ulic | +1.604 |
Neg logit contributions | |
ofi | -1.769 |
LT | -1.754 |
avorite | -1.706 |
thel | -1.593 |
/+ | -1.585 |
Token | Buy |
Token ID | 11763 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
uits | +2.224 |
| +2.194 |
Hyde | +2.192 |
ongo | +2.108 |
AES | +2.097 |
Neg logit contributions | |
ofi | -2.307 |
LT | -2.268 |
avorite | -2.208 |
thel | -2.065 |
/+ | -2.045 |
Token | It |
Token ID | 632 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
uits | +1.167 |
| +1.144 |
Hyde | +1.136 |
ongo | +1.105 |
ulic | +1.096 |
Neg logit contributions | |
ofi | -1.171 |
LT | -1.158 |
avorite | -1.121 |
thel | -1.053 |
/+ | -1.045 |
Token | Here |
Token ID | 3423 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
uits | +2.354 |
| +2.319 |
Hyde | +2.300 |
ongo | +2.234 |
AES | +2.223 |
Neg logit contributions | |
ofi | -2.159 |
LT | -2.106 |
avorite | -2.068 |
thel | -1.918 |
/+ | -1.879 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
| +5.390 |
uits | +5.315 |
Hyde | +5.254 |
AES | +5.014 |
ongo | +4.985 |
Neg logit contributions | |
ofi | -6.016 |
avorite | -5.819 |
LT | -5.672 |
thel | -5.301 |
/+ | -5.083 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
uits | +0.830 |
| +0.817 |
Hyde | +0.811 |
ongo | +0.787 |
ulic | +0.783 |
Neg logit contributions | |
ofi | -0.800 |
LT | -0.789 |
avorite | -0.767 |
thel | -0.717 |
/+ | -0.713 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
LT | +0.475 |
ofi | +0.472 |
/+ | +0.431 |
thel | +0.425 |
avorite | +0.421 |
Neg logit contributions | |
uits | -0.569 |
Hyde | -0.548 |
| -0.541 |
ulic | -0.540 |
ongo | -0.536 |
Token | For |
Token ID | 1890 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
uits | +0.191 |
Hyde | +0.186 |
| +0.186 |
ongo | +0.180 |
ulic | +0.180 |
Neg logit contributions | |
ofi | -0.192 |
LT | -0.191 |
avorite | -0.182 |
thel | -0.174 |
/+ | -0.173 |
Token | backers |
Token ID | 18917 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
uits | +1.540 |
| +1.515 |
Hyde | +1.508 |
ongo | +1.468 |
AES | +1.457 |
Neg logit contributions | |
ofi | -1.487 |
LT | -1.460 |
avorite | -1.413 |
thel | -1.321 |
/+ | -1.309 |