Token | S |
Token ID | 311 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
chery | +0.762 |
xual | +0.736 |
apper | +0.719 |
�� | +0.706 |
urrency | +0.697 |
Neg logit contributions | |
Nept | -0.527 |
mir | -0.514 |
Reaction | -0.499 |
Boe | -0.484 |
Gret | -0.467 |
Token | Mr |
Token ID | 1770 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
chery | +0.572 |
xual | +0.550 |
apper | +0.534 |
�� | +0.525 |
urrency | +0.516 |
Neg logit contributions | |
Nept | -0.519 |
mir | -0.511 |
Reaction | -0.496 |
Boe | -0.484 |
Gret | -0.469 |
Token | á |
Token ID | 6557 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
Nept | +0.787 |
mir | +0.783 |
Reaction | +0.753 |
Boe | +0.736 |
Gret | +0.706 |
Neg logit contributions | |
chery | -0.862 |
xual | -0.830 |
apper | -0.807 |
�� | -0.801 |
urrency | -0.782 |
Token | z |
Token ID | 89 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
Nept | +1.363 |
mir | +1.357 |
Reaction | +1.302 |
Boe | +1.275 |
Gret | +1.232 |
Neg logit contributions | |
chery | -1.460 |
xual | -1.416 |
apper | -1.378 |
�� | -1.363 |
urrency | -1.335 |
Token | ( |
Token ID | 357 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
Nept | +0.982 |
mir | +0.973 |
Reaction | +0.933 |
Boe | +0.913 |
Gret | +0.879 |
Neg logit contributions | |
chery | -1.308 |
xual | -1.265 |
apper | -1.229 |
�� | -1.215 |
urrency | -1.196 |
Token | Mich |
Token ID | 11180 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
chery | +0.790 |
xual | +0.766 |
apper | +0.745 |
�� | +0.734 |
urrency | +0.724 |
Neg logit contributions | |
Nept | -0.547 |
mir | -0.537 |
Reaction | -0.519 |
Boe | -0.505 |
Gret | -0.486 |
Token | l |
Token ID | 75 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
mir | +5.063 |
Nept | +4.874 |
Boe | +4.758 |
Reaction | +4.748 |
Gret | +4.449 |
Neg logit contributions | |
chery | -5.938 |
xual | -5.863 |
�� | -5.723 |
apper | -5.539 |
urrency | -5.413 |
Token | í |
Token ID | 8836 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
chery | +0.635 |
xual | +0.612 |
apper | +0.595 |
�� | +0.585 |
urrency | +0.576 |
Neg logit contributions | |
Nept | -0.548 |
mir | -0.538 |
Reaction | -0.522 |
Boe | -0.508 |
Gret | -0.492 |
Token | k |
Token ID | 74 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
mir | +2.340 |
Nept | +2.339 |
Reaction | +2.202 |
Boe | +2.171 |
Gret | +2.138 |
Neg logit contributions | |
chery | -2.505 |
xual | -2.484 |
apper | -2.384 |
�� | -2.357 |
urrency | -2.330 |
Token | 41 |
Token ID | 6073 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Nept | +0.699 |
mir | +0.690 |
Reaction | +0.662 |
Boe | +0.650 |
Gret | +0.622 |
Neg logit contributions | |
chery | -0.964 |
xual | -0.943 |
apper | -0.907 |
�� | -0.905 |
urrency | -0.886 |
Token | ), |
Token ID | 828 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Nept | +0.602 |
mir | +0.591 |
Reaction | +0.572 |
Boe | +0.558 |
Gret | +0.540 |
Neg logit contributions | |
chery | -0.775 |
xual | -0.748 |
apper | -0.727 |
�� | -0.716 |
urrency | -0.707 |
Token | Dis |
Token ID | 3167 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
Nept | +0.584 |
mir | +0.571 |
Reaction | +0.557 |
Boe | +0.537 |
Gret | +0.518 |
Neg logit contributions | |
chery | -0.889 |
xual | -0.859 |
apper | -0.842 |
�� | -0.827 |
urrency | -0.817 |
Token | pat |
Token ID | 8071 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
Nept | +1.108 |
mir | +1.100 |
Reaction | +1.070 |
Boe | +1.045 |
Gret | +1.021 |
Neg logit contributions | |
chery | -0.723 |
xual | -0.687 |
apper | -0.656 |
�� | -0.647 |
urrency | -0.628 |
Token | ches |
Token ID | 2052 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
chery | +0.001 |
xual | +0.001 |
apper | +0.001 |
�� | +0.001 |
urrency | +0.001 |
Neg logit contributions | |
Nept | -0.002 |
mir | -0.002 |
Reaction | -0.002 |
Boe | -0.002 |
Gret | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
chery | +0.894 |
xual | +0.859 |
apper | +0.838 |
�� | +0.823 |
urrency | +0.811 |
Neg logit contributions | |
Nept | -0.783 |
mir | -0.768 |
Reaction | -0.749 |
Boe | -0.728 |
Gret | -0.707 |
Token | the |
Token ID | 262 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
chery | +0.274 |
xual | +0.264 |
apper | +0.258 |
�� | +0.254 |
urrency | +0.251 |
Neg logit contributions | |
Nept | -0.194 |
mir | -0.189 |
Reaction | -0.184 |
Boe | -0.178 |
Gret | -0.172 |
Token | Evangel |
Token ID | 27834 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Nept | +0.112 |
mir | +0.109 |
Reaction | +0.107 |
Boe | +0.102 |
Gret | +0.099 |
Neg logit contributions | |
chery | -0.177 |
xual | -0.172 |
apper | -0.168 |
�� | -0.166 |
urrency | -0.163 |
Token | ical |
Token ID | 605 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
mir | +3.579 |
Nept | +3.499 |
Reaction | +3.437 |
Boe | +3.232 |
Gret | +3.028 |
Neg logit contributions | |
chery | -7.505 |
xual | -7.434 |
�� | -7.150 |
apper | -6.979 |
urrency | -6.885 |
Token | Youth |
Token ID | 17582 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Nept | +2.070 |
Reaction | +2.053 |
mir | +2.033 |
Boe | +1.932 |
Gret | +1.853 |
Neg logit contributions | |
chery | -3.009 |
xual | -2.912 |
apper | -2.831 |
�� | -2.813 |
urrency | -2.776 |
Token | Movement |
Token ID | 15477 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Nept | +0.190 |
mir | +0.187 |
Reaction | +0.183 |
Boe | +0.176 |
Gret | +0.171 |
Neg logit contributions | |
chery | -0.231 |
xual | -0.223 |
apper | -0.217 |
�� | -0.215 |
urrency | -0.211 |
Token | � |
Token ID | 447 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Nept | +0.299 |
mir | +0.294 |
Reaction | +0.287 |
Boe | +0.277 |
Gret | +0.269 |
Neg logit contributions | |
chery | -0.368 |
xual | -0.355 |
apper | -0.346 |
�� | -0.340 |
urrency | -0.336 |
Token | � |
Token ID | 251 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
chery | +0.308 |
xual | +0.295 |
apper | +0.286 |
�� | +0.278 |
urrency | +0.275 |
Neg logit contributions | |
Nept | -0.303 |
mir | -0.298 |
Reaction | -0.291 |
Boe | -0.284 |
Gret | -0.275 |
Token | , |
Token ID | 11 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
Nept | +0.036 |
mir | +0.035 |
Reaction | +0.034 |
Boe | +0.033 |
Gret | +0.032 |
Neg logit contributions | |
chery | -0.053 |
xual | -0.051 |
apper | -0.050 |
�� | -0.049 |
urrency | -0.049 |
Token | in |
Token ID | 287 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
chery | +0.116 |
xual | +0.112 |
apper | +0.109 |
�� | +0.108 |
urrency | +0.105 |
Neg logit contributions | |
Nept | -0.113 |
mir | -0.109 |
Reaction | -0.107 |
Boe | -0.105 |
Gret | -0.102 |
Token | contrast |
Token ID | 6273 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Nept | +0.074 |
mir | +0.072 |
Reaction | +0.070 |
Boe | +0.068 |
Gret | +0.066 |
Neg logit contributions | |
chery | -0.094 |
xual | -0.091 |
apper | -0.088 |
�� | -0.087 |
urrency | -0.086 |
Token | with |
Token ID | 351 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
chery | +0.500 |
xual | +0.478 |
apper | +0.463 |
�� | +0.451 |
urrency | +0.444 |
Neg logit contributions | |
Nept | -0.589 |
mir | -0.581 |
Reaction | -0.566 |
Boe | -0.553 |
Gret | -0.536 |
Token | traditional |
Token ID | 4569 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Nept | +0.093 |
mir | +0.090 |
Reaction | +0.088 |
Boe | +0.086 |
Gret | +0.083 |
Neg logit contributions | |
chery | -0.116 |
xual | -0.112 |
apper | -0.109 |
�� | -0.107 |
urrency | -0.105 |
Token | Protestant |
Token ID | 25310 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
chery | +0.709 |
xual | +0.685 |
apper | +0.670 |
�� | +0.658 |
urrency | +0.652 |
Neg logit contributions | |
Nept | -0.422 |
mir | -0.410 |
Reaction | -0.397 |
Boe | -0.385 |
Gret | -0.369 |
Token | sects |
Token ID | 48027 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Nept | +4.278 |
mir | +4.075 |
Reaction | +4.046 |
Boe | +3.970 |
Gret | +3.794 |
Neg logit contributions | |
chery | -6.755 |
xual | -6.457 |
apper | -6.213 |
urrency | -6.137 |
assic | -6.049 |
Token | like |
Token ID | 588 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
Nept | +2.244 |
mir | +2.201 |
Reaction | +2.128 |
Boe | +2.071 |
Gret | +2.016 |
Neg logit contributions | |
chery | -2.803 |
xual | -2.715 |
apper | -2.661 |
�� | -2.602 |
urrency | -2.582 |
Token | Lutheran |
Token ID | 43772 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
chery | +0.156 |
xual | +0.151 |
apper | +0.147 |
�� | +0.144 |
urrency | +0.143 |
Neg logit contributions | |
Nept | -0.098 |
mir | -0.095 |
Reaction | -0.093 |
Boe | -0.090 |
Gret | -0.086 |
Token | ism |
Token ID | 1042 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Nept | +2.433 |
mir | +2.371 |
Reaction | +2.316 |
Boe | +2.252 |
Gret | +2.157 |
Neg logit contributions | |
chery | -3.432 |
xual | -3.303 |
apper | -3.193 |
urrency | -3.129 |
�� | -3.121 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Nept | +1.673 |
mir | +1.639 |
Reaction | +1.586 |
Boe | +1.541 |
Gret | +1.491 |
Neg logit contributions | |
chery | -2.221 |
xual | -2.143 |
apper | -2.098 |
�� | -2.049 |
urrency | -2.035 |
Token | to |
Token ID | 284 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
Nept | +0.502 |
mir | +0.496 |
Reaction | +0.479 |
Boe | +0.466 |
Gret | +0.452 |
Neg logit contributions | |
chery | -0.601 |
xual | -0.586 |
apper | -0.570 |
�� | -0.558 |
urrency | -0.549 |
Token | perform |
Token ID | 1620 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
chery | +0.053 |
xual | +0.051 |
apper | +0.050 |
�� | +0.049 |
urrency | +0.048 |
Neg logit contributions | |
Nept | -0.051 |
mir | -0.050 |
Reaction | -0.049 |
Boe | -0.048 |
Gret | -0.046 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Nept | +0.211 |
mir | +0.207 |
Reaction | +0.199 |
Boe | +0.193 |
Gret | +0.186 |
Neg logit contributions | |
chery | -0.310 |
xual | -0.301 |
apper | -0.294 |
�� | -0.289 |
urrency | -0.285 |
Token | Mars |
Token ID | 43725 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
chery | +1.933 |
xual | +1.847 |
apper | +1.818 |
�� | +1.772 |
urrency | +1.753 |
Neg logit contributions | |
Nept | -1.531 |
mir | -1.480 |
Reaction | -1.452 |
Boe | -1.413 |
Gret | -1.362 |
Token | Rock |
Token ID | 4631 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
chery | +0.141 |
xual | +0.136 |
apper | +0.132 |
�� | +0.130 |
urrency | +0.127 |
Neg logit contributions | |
Nept | -0.119 |
mir | -0.117 |
Reaction | -0.114 |
Boe | -0.110 |
Gret | -0.107 |
Token | Tou |
Token ID | 23359 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Nept | +0.981 |
mir | +0.963 |
Reaction | +0.942 |
Boe | +0.903 |
Gret | +0.883 |
Neg logit contributions | |
chery | -1.210 |
xual | -1.178 |
apper | -1.147 |
�� | -1.136 |
urrency | -1.113 |
Token | ched |
Token ID | 1740 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
mir | +6.761 |
Nept | +6.618 |
Reaction | +6.465 |
Boe | +6.341 |
Gret | +6.239 |
Neg logit contributions | |
xual | -3.801 |
�� | -3.748 |
apper | -3.737 |
chery | -3.730 |
urrency | -3.639 |
Token | by |
Token ID | 416 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Nept | +0.552 |
mir | +0.538 |
Reaction | +0.529 |
Boe | +0.510 |
Gret | +0.494 |
Neg logit contributions | |
chery | -0.714 |
xual | -0.694 |
�� | -0.675 |
apper | -0.672 |
urrency | -0.655 |
Token | NASA |
Token ID | 8884 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
Nept | +1.347 |
mir | +1.301 |
Reaction | +1.298 |
Boe | +1.244 |
Gret | +1.207 |
Neg logit contributions | |
chery | -1.746 |
xual | -1.686 |
apper | -1.636 |
�� | -1.630 |
urrency | -1.590 |
Token | Curiosity |
Token ID | 39736 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Nept | +1.240 |
mir | +1.205 |
Reaction | +1.201 |
Boe | +1.136 |
Gret | +1.110 |
Neg logit contributions | |
chery | -1.717 |
xual | -1.684 |
�� | -1.622 |
apper | -1.611 |
urrency | -1.588 |
Token | has |
Token ID | 468 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Nept | +0.219 |
mir | +0.214 |
Reaction | +0.213 |
Boe | +0.203 |
Gret | +0.197 |
Neg logit contributions | |
chery | -0.268 |
xual | -0.260 |
apper | -0.251 |
�� | -0.250 |
urrency | -0.245 |
Token | ching |
Token ID | 10813 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
chery | +0.237 |
xual | +0.228 |
apper | +0.222 |
�� | +0.217 |
urrency | +0.214 |
Neg logit contributions | |
Nept | -0.232 |
mir | -0.229 |
Reaction | -0.222 |
Boe | -0.217 |
Gret | -0.211 |
Token | need |
Token ID | 761 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Nept | +0.246 |
mir | +0.241 |
Reaction | +0.235 |
Boe | +0.228 |
Gret | +0.221 |
Neg logit contributions | |
chery | -0.294 |
xual | -0.283 |
apper | -0.275 |
�� | -0.270 |
urrency | -0.267 |
Token | that |
Token ID | 326 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
chery | +1.595 |
xual | +1.528 |
apper | +1.486 |
�� | +1.450 |
urrency | +1.430 |
Neg logit contributions | |
Nept | -1.634 |
mir | -1.599 |
Reaction | -1.561 |
Boe | -1.523 |
Gret | -1.479 |
Token | has |
Token ID | 468 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Nept | +0.227 |
mir | +0.222 |
Reaction | +0.216 |
Boe | +0.210 |
Gret | +0.204 |
Neg logit contributions | |
chery | -0.276 |
xual | -0.267 |
apper | -0.261 |
�� | -0.255 |
urrency | -0.252 |
Token | her |
Token ID | 607 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
chery | +0.491 |
xual | +0.471 |
apper | +0.459 |
�� | +0.448 |
urrency | +0.441 |
Neg logit contributions | |
Nept | -0.546 |
mir | -0.536 |
Reaction | -0.523 |
Boe | -0.511 |
Gret | -0.498 |
Token | sob |
Token ID | 27355 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
Nept | +0.826 |
mir | +0.811 |
Reaction | +0.791 |
Boe | +0.770 |
Gret | +0.750 |
Neg logit contributions | |
chery | -0.913 |
xual | -0.879 |
apper | -0.856 |
�� | -0.841 |
urrency | -0.830 |
Token | bing |
Token ID | 4623 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
mir | +4.084 |
Nept | +4.081 |
Reaction | +3.862 |
Boe | +3.743 |
Gret | +3.646 |
Neg logit contributions | |
chery | -6.664 |
xual | -6.660 |
apper | -6.337 |
�� | -6.264 |
urrency | -6.186 |
Token | in |
Token ID | 287 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Nept | +0.556 |
mir | +0.545 |
Reaction | +0.530 |
Boe | +0.517 |
Gret | +0.502 |
Neg logit contributions | |
chery | -0.626 |
xual | -0.603 |
apper | -0.586 |
�� | -0.578 |
urrency | -0.568 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
Nept | +0.229 |
mir | +0.224 |
Reaction | +0.219 |
Boe | +0.213 |
Gret | +0.207 |
Neg logit contributions | |
chery | -0.249 |
xual | -0.240 |
apper | -0.233 |
�� | -0.229 |
urrency | -0.226 |
Token | hospital |
Token ID | 4436 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Nept | +0.058 |
mir | +0.057 |
Reaction | +0.056 |
Boe | +0.054 |
Gret | +0.053 |
Neg logit contributions | |
chery | -0.065 |
xual | -0.062 |
apper | -0.060 |
�� | -0.059 |
urrency | -0.058 |
Token | corridors |
Token ID | 32807 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Nept | +1.698 |
mir | +1.674 |
Reaction | +1.624 |
Boe | +1.578 |
Gret | +1.542 |
Neg logit contributions | |
chery | -2.006 |
xual | -1.949 |
apper | -1.877 |
�� | -1.868 |
urrency | -1.827 |
Token | desires |
Token ID | 15997 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
Nept | +0.358 |
mir | +0.350 |
Reaction | +0.340 |
Boe | +0.332 |
Gret | +0.322 |
Neg logit contributions | |
chery | -0.408 |
xual | -0.393 |
apper | -0.384 |
�� | -0.376 |
urrency | -0.370 |
Token | , |
Token ID | 11 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
chery | +0.076 |
xual | +0.074 |
apper | +0.072 |
�� | +0.071 |
urrency | +0.070 |
Neg logit contributions | |
Nept | -0.061 |
mir | -0.060 |
Reaction | -0.058 |
Boe | -0.056 |
Gret | -0.055 |
Token | in |
Token ID | 287 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
chery | +0.129 |
xual | +0.125 |
apper | +0.122 |
�� | +0.120 |
urrency | +0.118 |
Neg logit contributions | |
Nept | -0.107 |
mir | -0.105 |
Reaction | -0.102 |
Boe | -0.099 |
Gret | -0.096 |
Token | moments |
Token ID | 7188 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Nept | +0.007 |
mir | +0.007 |
Reaction | +0.007 |
Boe | +0.007 |
Gret | +0.006 |
Neg logit contributions | |
chery | -0.008 |
xual | -0.008 |
apper | -0.008 |
�� | -0.008 |
urrency | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
chery | +0.340 |
xual | +0.326 |
apper | +0.317 |
�� | +0.309 |
urrency | +0.305 |
Neg logit contributions | |
Nept | -0.356 |
mir | -0.349 |
Reaction | -0.341 |
Boe | -0.332 |
Gret | -0.323 |
Token | sob |
Token ID | 27355 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
chery | +0.523 |
xual | +0.504 |
apper | +0.491 |
�� | +0.481 |
urrency | +0.474 |
Neg logit contributions | |
Nept | -0.528 |
mir | -0.517 |
Reaction | -0.505 |
Boe | -0.492 |
Gret | -0.479 |
Token | ri |
Token ID | 380 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Nept | +3.186 |
mir | +3.184 |
Reaction | +3.000 |
Boe | +2.796 |
Gret | +2.632 |
Neg logit contributions | |
xual | -7.557 |
chery | -7.435 |
�� | -7.282 |
apper | -7.252 |
urrency | -6.996 |
Token | ety |
Token ID | 2963 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Nept | +0.075 |
mir | +0.072 |
Reaction | +0.068 |
Boe | +0.064 |
Gret | +0.060 |
Neg logit contributions | |
chery | -0.241 |
xual | -0.235 |
apper | -0.231 |
�� | -0.227 |
urrency | -0.225 |
Token | I |
Token ID | 314 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
Nept | +0.776 |
mir | +0.760 |
Reaction | +0.736 |
Boe | +0.715 |
Gret | +0.693 |
Neg logit contributions | |
chery | -1.009 |
xual | -0.977 |
apper | -0.957 |
�� | -0.937 |
urrency | -0.928 |
Token | knew |
Token ID | 2993 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Nept | +0.125 |
mir | +0.123 |
Reaction | +0.119 |
Boe | +0.116 |
Gret | +0.113 |
Neg logit contributions | |
chery | -0.126 |
xual | -0.122 |
apper | -0.118 |
�� | -0.116 |
urrency | -0.114 |
Token | that |
Token ID | 326 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
chery | +1.226 |
xual | +1.178 |
apper | +1.147 |
�� | +1.123 |
urrency | +1.106 |
Neg logit contributions | |
Nept | -1.242 |
mir | -1.217 |
Reaction | -1.187 |
Boe | -1.160 |
Gret | -1.127 |
Token | brain |
Token ID | 3632 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Nept | +1.746 |
mir | +1.711 |
Reaction | +1.677 |
Boe | +1.631 |
Gret | +1.579 |
Neg logit contributions | |
chery | -2.124 |
xual | -2.071 |
apper | -2.016 |
�� | -1.984 |
urrency | -1.935 |
Token | tissue |
Token ID | 10712 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Nept | +1.058 |
mir | +1.041 |
Reaction | +1.016 |
Boe | +0.985 |
Gret | +0.956 |
Neg logit contributions | |
chery | -1.206 |
xual | -1.171 |
apper | -1.136 |
�� | -1.111 |
urrency | -1.095 |
Token | , |
Token ID | 11 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
Nept | +1.758 |
mir | +1.725 |
Reaction | +1.662 |
Boe | +1.604 |
Gret | +1.554 |
Neg logit contributions | |
chery | -2.869 |
xual | -2.797 |
apper | -2.744 |
�� | -2.717 |
urrency | -2.664 |
Token | like |
Token ID | 588 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Nept | +0.098 |
mir | +0.096 |
Reaction | +0.094 |
Boe | +0.092 |
Gret | +0.089 |
Neg logit contributions | |
chery | -0.101 |
xual | -0.098 |
apper | -0.095 |
�� | -0.093 |
urrency | -0.092 |
Token | multiple |
Token ID | 3294 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
chery | +0.195 |
xual | +0.188 |
apper | +0.183 |
�� | +0.180 |
urrency | +0.177 |
Neg logit contributions | |
Nept | -0.154 |
mir | -0.151 |
Reaction | -0.147 |
Boe | -0.143 |
Gret | -0.138 |
Token | sclerosis |
Token ID | 46225 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Nept | +0.567 |
mir | +0.553 |
Reaction | +0.539 |
Boe | +0.524 |
Gret | +0.503 |
Neg logit contributions | |
chery | -0.808 |
xual | -0.788 |
apper | -0.765 |
�� | -0.748 |
urrency | -0.742 |
Token | ." |
Token ID | 526 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Nept | +3.634 |
mir | +3.551 |
Reaction | +3.473 |
Boe | +3.350 |
Gret | +3.214 |
Neg logit contributions | |
chery | -6.405 |
xual | -6.205 |
�� | -6.161 |
apper | -6.126 |
urrency | -6.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Nept | +0.215 |
mir | +0.210 |
Reaction | +0.201 |
Boe | +0.196 |
Gret | +0.189 |
Neg logit contributions | |
chery | -0.268 |
xual | -0.256 |
apper | -0.251 |
�� | -0.243 |
urrency | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
mir | +0.253 |
Nept | +0.250 |
Reaction | +0.241 |
Boe | +0.234 |
Gret | +0.226 |
Neg logit contributions | |
chery | -0.397 |
xual | -0.397 |
�� | -0.386 |
apper | -0.379 |
urrency | -0.369 |
Token | There |
Token ID | 1858 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
mir | +0.248 |
Nept | +0.248 |
Reaction | +0.238 |
Boe | +0.231 |
Gret | +0.225 |
Neg logit contributions | |
chery | -0.302 |
xual | -0.297 |
apper | -0.284 |
�� | -0.281 |
urrency | -0.277 |
Token | have |
Token ID | 423 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
chery | +0.882 |
xual | +0.845 |
apper | +0.826 |
�� | +0.805 |
urrency | +0.797 |
Neg logit contributions | |
Nept | -0.784 |
mir | -0.764 |
Reaction | -0.747 |
Boe | -0.727 |
Gret | -0.703 |
Token | in |
Token ID | 287 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
chery | +0.444 |
xual | +0.427 |
apper | +0.416 |
�� | +0.407 |
urrency | +0.401 |
Neg logit contributions | |
Nept | -0.413 |
mir | -0.405 |
Reaction | -0.394 |
Boe | -0.384 |
Gret | -0.373 |
Token | California |
Token ID | 3442 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
Nept | +0.130 |
mir | +0.127 |
Reaction | +0.124 |
Boe | +0.121 |
Gret | +0.117 |
Neg logit contributions | |
chery | -0.161 |
xual | -0.157 |
apper | -0.152 |
�� | -0.149 |
urrency | -0.147 |
Token | � |
Token ID | 447 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
Nept | +0.081 |
mir | +0.079 |
Reaction | +0.077 |
Boe | +0.075 |
Gret | +0.072 |
Neg logit contributions | |
chery | -0.110 |
xual | -0.106 |
apper | -0.103 |
�� | -0.101 |
urrency | -0.100 |
Token | � |
Token ID | 247 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
chery | +0.013 |
xual | +0.012 |
apper | +0.012 |
�� | +0.012 |
urrency | +0.011 |
Neg logit contributions | |
Nept | -0.012 |
mir | -0.011 |
Reaction | -0.011 |
Boe | -0.011 |
Gret | -0.010 |
Token | s |
Token ID | 82 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
chery | +0.098 |
xual | +0.094 |
apper | +0.092 |
�� | +0.090 |
urrency | +0.089 |
Neg logit contributions | |
Nept | -0.078 |
mir | -0.077 |
Reaction | -0.074 |
Boe | -0.072 |
Gret | -0.070 |
Token | Sierra |
Token ID | 17559 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
chery | +0.008 |
xual | +0.008 |
apper | +0.008 |
�� | +0.007 |
urrency | +0.007 |
Neg logit contributions | |
Nept | -0.007 |
mir | -0.007 |
Reaction | -0.006 |
Boe | -0.006 |
Gret | -0.006 |
Token | Nevada |
Token ID | 12087 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Nept | +3.586 |
mir | +3.586 |
Reaction | +3.477 |
Boe | +3.425 |
Gret | +3.340 |
Neg logit contributions | |
xual | -6.348 |
chery | -6.347 |
�� | -6.085 |
apper | -6.066 |
urrency | -5.962 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
Nept | +1.387 |
mir | +1.351 |
Reaction | +1.316 |
Boe | +1.277 |
Gret | +1.241 |
Neg logit contributions | |
chery | -1.861 |
xual | -1.808 |
apper | -1.759 |
�� | -1.730 |
urrency | -1.714 |
Token | Dan |
Token ID | 6035 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
chery | +0.010 |
xual | +0.010 |
apper | +0.010 |
�� | +0.010 |
urrency | +0.010 |
Neg logit contributions | |
Nept | -0.007 |
mir | -0.007 |
Reaction | -0.006 |
Boe | -0.006 |
Gret | -0.006 |
Token | K |
Token ID | 509 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Nept | +0.790 |
mir | +0.778 |
Reaction | +0.751 |
Boe | +0.740 |
Gret | +0.712 |
Neg logit contributions | |
chery | -1.037 |
xual | -1.013 |
apper | -0.982 |
�� | -0.967 |
urrency | -0.953 |
Token | oe |
Token ID | 2577 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Nept | +0.219 |
mir | +0.218 |
Reaction | +0.210 |
Boe | +0.206 |
Gret | +0.199 |
Neg logit contributions | |
chery | -0.229 |
xual | -0.221 |
apper | -0.212 |
�� | -0.211 |
urrency | -0.205 |
Token | same |
Token ID | 976 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Nept | +0.190 |
mir | +0.187 |
Reaction | +0.181 |
Boe | +0.176 |
Gret | +0.171 |
Neg logit contributions | |
chery | -0.232 |
xual | -0.224 |
apper | -0.219 |
�� | -0.216 |
urrency | -0.213 |
Token | year |
Token ID | 614 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Nept | +1.342 |
mir | +1.309 |
Reaction | +1.277 |
Boe | +1.240 |
Gret | +1.214 |
Neg logit contributions | |
chery | -1.688 |
xual | -1.641 |
apper | -1.583 |
�� | -1.582 |
urrency | -1.555 |
Token | , |
Token ID | 11 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
chery | +0.094 |
xual | +0.091 |
apper | +0.089 |
�� | +0.087 |
urrency | +0.086 |
Neg logit contributions | |
Nept | -0.070 |
mir | -0.068 |
Reaction | -0.066 |
Boe | -0.065 |
Gret | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
chery | +0.127 |
xual | +0.123 |
apper | +0.119 |
�� | +0.118 |
urrency | +0.117 |
Neg logit contributions | |
Nept | -0.100 |
mir | -0.097 |
Reaction | -0.095 |
Boe | -0.093 |
Gret | -0.090 |
Token | American |
Token ID | 1605 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
chery | +0.212 |
xual | +0.204 |
apper | +0.198 |
�� | +0.195 |
urrency | +0.193 |
Neg logit contributions | |
Nept | -0.187 |
mir | -0.181 |
Reaction | -0.178 |
Boe | -0.173 |
Gret | -0.168 |
Token | Psychiatric |
Token ID | 46404 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
chery | +0.445 |
xual | +0.431 |
apper | +0.421 |
�� | +0.415 |
urrency | +0.411 |
Neg logit contributions | |
Nept | -0.241 |
mir | -0.234 |
Reaction | -0.227 |
Boe | -0.218 |
Gret | -0.210 |
Token | Association |
Token ID | 5396 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Nept | +2.253 |
Reaction | +2.190 |
mir | +2.092 |
Boe | +1.811 |
Gret | +1.764 |
Neg logit contributions | |
chery | -7.660 |
xual | -7.571 |
�� | -7.423 |
urrency | -7.169 |
apper | -7.121 |
Token | removed |
Token ID | 4615 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Nept | +1.837 |
mir | +1.782 |
Reaction | +1.760 |
Boe | +1.713 |
Gret | +1.681 |
Neg logit contributions | |
chery | -1.709 |
xual | -1.654 |
�� | -1.604 |
apper | -1.585 |
urrency | -1.553 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
chery | +0.204 |
xual | +0.196 |
apper | +0.191 |
�� | +0.187 |
urrency | +0.185 |
Neg logit contributions | |
Nept | -0.187 |
mir | -0.183 |
Reaction | -0.179 |
Boe | -0.174 |
Gret | -0.169 |
Token | from |
Token ID | 422 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Nept | +1.352 |
mir | +1.328 |
Reaction | +1.291 |
Boe | +1.260 |
Gret | +1.218 |
Neg logit contributions | |
chery | -1.551 |
xual | -1.492 |
apper | -1.458 |
�� | -1.444 |
urrency | -1.417 |
Token | its |
Token ID | 663 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
chery | +0.486 |
xual | +0.467 |
apper | +0.456 |
�� | +0.446 |
urrency | +0.440 |
Neg logit contributions | |
Nept | -0.430 |
mir | -0.421 |
Reaction | -0.410 |
Boe | -0.399 |
Gret | -0.387 |
Token | Louis |
Token ID | 5593 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Nept | +0.337 |
mir | +0.330 |
Reaction | +0.322 |
Boe | +0.314 |
Gret | +0.304 |
Neg logit contributions | |
chery | -0.326 |
xual | -0.311 |
apper | -0.305 |
�� | -0.296 |
urrency | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
chery | +1.347 |
xual | +1.296 |
apper | +1.267 |
�� | +1.240 |
urrency | +1.221 |
Neg logit contributions | |
Nept | -1.140 |
mir | -1.112 |
Reaction | -1.077 |
Boe | -1.044 |
Gret | -1.014 |
Token | has |
Token ID | 468 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Nept | +0.133 |
mir | +0.130 |
Reaction | +0.128 |
Boe | +0.125 |
Gret | +0.121 |
Neg logit contributions | |
chery | -0.160 |
xual | -0.154 |
apper | -0.150 |
�� | -0.147 |
urrency | -0.144 |
Token | also |
Token ID | 635 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
chery | +0.332 |
xual | +0.320 |
apper | +0.308 |
�� | +0.304 |
urrency | +0.296 |
Neg logit contributions | |
Nept | -0.378 |
mir | -0.368 |
Reaction | -0.359 |
Boe | -0.357 |
Gret | -0.345 |
Token | studied |
Token ID | 9713 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
chery | +0.017 |
xual | +0.017 |
apper | +0.016 |
�� | +0.016 |
urrency | +0.015 |
Neg logit contributions | |
Nept | -0.020 |
mir | -0.020 |
Reaction | -0.019 |
Boe | -0.019 |
Gret | -0.019 |
Token | schizophrenia |
Token ID | 22794 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Nept | +1.134 |
mir | +1.111 |
Reaction | +1.094 |
Boe | +1.061 |
Gret | +1.033 |
Neg logit contributions | |
chery | -1.229 |
xual | -1.183 |
apper | -1.148 |
�� | -1.134 |
urrency | -1.117 |
Token | using |
Token ID | 1262 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
mir | +4.315 |
Nept | +4.281 |
Reaction | +4.153 |
Boe | +4.066 |
Gret | +3.861 |
Neg logit contributions | |
chery | -5.408 |
xual | -5.200 |
�� | -5.130 |
apper | -5.051 |
urrency | -4.971 |
Token | computer |
Token ID | 3644 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Nept | +0.038 |
mir | +0.038 |
Reaction | +0.037 |
Boe | +0.036 |
Gret | +0.035 |
Neg logit contributions | |
chery | -0.042 |
xual | -0.041 |
apper | -0.040 |
�� | -0.039 |
urrency | -0.039 |
Token | models |
Token ID | 4981 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
chery | +0.645 |
xual | +0.622 |
apper | +0.599 |
�� | +0.589 |
urrency | +0.578 |
Neg logit contributions | |
Nept | -0.681 |
mir | -0.672 |
Reaction | -0.655 |
Boe | -0.640 |
Gret | -0.623 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Nept | +0.162 |
mir | +0.160 |
Reaction | +0.154 |
Boe | +0.151 |
Gret | +0.146 |
Neg logit contributions | |
chery | -0.204 |
xual | -0.197 |
apper | -0.192 |
�� | -0.190 |
urrency | -0.187 |
Token | " |
Token ID | 366 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Nept | +0.133 |
mir | +0.129 |
Reaction | +0.125 |
Boe | +0.121 |
Gret | +0.116 |
Neg logit contributions | |
chery | -0.212 |
xual | -0.205 |
apper | -0.201 |
�� | -0.197 |
urrency | -0.195 |
Token | it |
Token ID | 340 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
chery | +0.360 |
xual | +0.347 |
apper | +0.339 |
�� | +0.333 |
urrency | +0.329 |
Neg logit contributions | |
Nept | -0.280 |
mir | -0.274 |
Reaction | -0.266 |
Boe | -0.258 |
Gret | -0.250 |
Token | so |
Token ID | 523 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Nept | +0.975 |
mir | +0.958 |
Reaction | +0.933 |
Boe | +0.899 |
Gret | +0.876 |
Neg logit contributions | |
chery | -1.173 |
xual | -1.132 |
apper | -1.106 |
�� | -1.098 |
urrency | -1.076 |
Token | you |
Token ID | 345 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
chery | +2.098 |
xual | +2.010 |
apper | +1.956 |
�� | +1.908 |
urrency | +1.883 |
Neg logit contributions | |
Nept | -2.037 |
mir | -1.995 |
Reaction | -1.948 |
Boe | -1.902 |
Gret | -1.840 |
Token | don |
Token ID | 836 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Nept | +1.105 |
mir | +1.083 |
Reaction | +1.055 |
Boe | +1.017 |
Gret | +1.000 |
Neg logit contributions | |
chery | -1.213 |
xual | -1.177 |
�� | -1.150 |
apper | -1.145 |
urrency | -1.112 |
Token | 't |
Token ID | 470 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
mir | +0.281 |
Nept | +0.279 |
Reaction | +0.265 |
Boe | +0.256 |
Gret | +0.249 |
Neg logit contributions | |
chery | -0.541 |
xual | -0.539 |
�� | -0.527 |
apper | -0.517 |
urrency | -0.507 |
Token | ejac |
Token ID | 39426 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
chery | +0.252 |
xual | +0.242 |
apper | +0.235 |
�� | +0.231 |
urrency | +0.227 |
Neg logit contributions | |
Nept | -0.256 |
mir | -0.251 |
Reaction | -0.245 |
Boe | -0.239 |
Gret | -0.232 |
Token | ulate |
Token ID | 5039 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
mir | +4.344 |
Nept | +4.242 |
Reaction | +4.112 |
Boe | +3.975 |
Gret | +3.816 |
Neg logit contributions | |
chery | -5.302 |
�� | -5.222 |
xual | -5.106 |
apper | -4.977 |
urrency | -4.805 |
Token | soon |
Token ID | 2582 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Nept | +0.845 |
mir | +0.828 |
Reaction | +0.801 |
Boe | +0.779 |
Gret | +0.757 |
Neg logit contributions | |
chery | -1.087 |
xual | -1.050 |
apper | -1.028 |
�� | -1.020 |
urrency | -0.995 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
chery | +0.356 |
xual | +0.343 |
apper | +0.334 |
�� | +0.327 |
urrency | +0.323 |
Neg logit contributions | |
Nept | -0.289 |
mir | -0.283 |
Reaction | -0.275 |
Boe | -0.267 |
Gret | -0.258 |
Token | So |
Token ID | 1406 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Nept | +0.198 |
mir | +0.191 |
Reaction | +0.187 |
Boe | +0.180 |
Gret | +0.174 |
Neg logit contributions | |
chery | -0.327 |
xual | -0.317 |
apper | -0.310 |
�� | -0.306 |
urrency | -0.301 |
Token | you |
Token ID | 345 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
chery | +1.279 |
xual | +1.233 |
apper | +1.205 |
�� | +1.182 |
urrency | +1.167 |
Neg logit contributions | |
Nept | -1.019 |
mir | -0.997 |
Reaction | -0.967 |
Boe | -0.940 |
Gret | -0.912 |
Token | � |
Token ID | 447 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Nept | +0.210 |
mir | +0.205 |
Reaction | +0.200 |
Boe | +0.195 |
Gret | +0.189 |
Neg logit contributions | |
chery | -0.262 |
xual | -0.253 |
apper | -0.248 |
�� | -0.243 |
urrency | -0.240 |
Token | � |
Token ID | 247 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Nept | +0.424 |
mir | +0.419 |
Reaction | +0.408 |
Boe | +0.395 |
Gret | +0.384 |
Neg logit contributions | |
chery | -0.493 |
xual | -0.474 |
apper | -0.461 |
�� | -0.447 |
urrency | -0.446 |
Token | 48 |
Token ID | 4764 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
chery | +0.204 |
xual | +0.197 |
apper | +0.193 |
�� | +0.189 |
urrency | +0.187 |
Neg logit contributions | |
Nept | -0.155 |
mir | -0.152 |
Reaction | -0.147 |
Boe | -0.143 |
Gret | -0.138 |
Token | points |
Token ID | 2173 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Nept | +0.782 |
mir | +0.770 |
Reaction | +0.745 |
Boe | +0.726 |
Gret | +0.706 |
Neg logit contributions | |
chery | -0.911 |
xual | -0.880 |
apper | -0.857 |
�� | -0.837 |
urrency | -0.830 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Nept | +0.349 |
mir | +0.343 |
Reaction | +0.332 |
Boe | +0.324 |
Gret | +0.319 |
Neg logit contributions | |
chery | -0.431 |
xual | -0.420 |
apper | -0.405 |
�� | -0.403 |
urrency | -0.395 |
Token | McF |
Token ID | 38222 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Nept | +0.154 |
mir | +0.151 |
Reaction | +0.147 |
Boe | +0.144 |
Gret | +0.140 |
Neg logit contributions | |
chery | -0.189 |
xual | -0.185 |
�� | -0.179 |
apper | -0.179 |
urrency | -0.174 |
Token | adden |
Token ID | 38014 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
mir | +4.829 |
Nept | +4.705 |
Reaction | +4.641 |
Boe | +4.487 |
Gret | +4.268 |
Neg logit contributions | |
chery | -4.722 |
xual | -4.700 |
�� | -4.584 |
urrency | -4.193 |
apper | -4.172 |
Token | only |
Token ID | 691 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Nept | +0.502 |
mir | +0.498 |
Reaction | +0.484 |
Boe | +0.472 |
Gret | +0.461 |
Neg logit contributions | |
chery | -0.578 |
xual | -0.566 |
apper | -0.546 |
�� | -0.541 |
urrency | -0.531 |
Token | accounted |
Token ID | 17830 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Nept | +0.178 |
mir | +0.177 |
Reaction | +0.171 |
Boe | +0.168 |
Gret | +0.165 |
Neg logit contributions | |
chery | -0.189 |
xual | -0.186 |
apper | -0.180 |
�� | -0.179 |
urrency | -0.175 |
Token | for |
Token ID | 329 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
chery | +0.593 |
xual | +0.575 |
apper | +0.558 |
�� | +0.552 |
urrency | +0.542 |
Neg logit contributions | |
Nept | -0.497 |
mir | -0.487 |
Reaction | -0.472 |
Boe | -0.461 |
Gret | -0.446 |
Token | one |
Token ID | 530 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
Nept | +1.075 |
mir | +1.041 |
Reaction | +1.029 |
Boe | +1.003 |
Gret | +0.976 |
Neg logit contributions | |
chery | -1.495 |
xual | -1.465 |
�� | -1.429 |
apper | -1.419 |
urrency | -1.386 |
Token | folk |
Token ID | 15504 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Nept | +1.513 |
mir | +1.472 |
Reaction | +1.454 |
Boe | +1.411 |
Gret | +1.382 |
Neg logit contributions | |
chery | -1.681 |
xual | -1.641 |
apper | -1.566 |
�� | -1.554 |
urrency | -1.511 |
Token | festival |
Token ID | 10876 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
chery | +1.749 |
xual | +1.691 |
apper | +1.626 |
�� | +1.598 |
urrency | +1.571 |
Neg logit contributions | |
Nept | -1.854 |
mir | -1.826 |
Reaction | -1.778 |
Boe | -1.733 |
Gret | -1.690 |
Token | kicks |
Token ID | 17364 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
chery | +2.130 |
xual | +2.047 |
apper | +1.999 |
�� | +1.955 |
urrency | +1.932 |
Neg logit contributions | |
Nept | -1.791 |
mir | -1.755 |
Reaction | -1.706 |
Boe | -1.659 |
Gret | -1.605 |
Token | off |
Token ID | 572 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
chery | +1.675 |
xual | +1.625 |
apper | +1.567 |
�� | +1.531 |
urrency | +1.517 |
Neg logit contributions | |
Nept | -1.487 |
mir | -1.453 |
Reaction | -1.419 |
Boe | -1.386 |
Gret | -1.345 |
Token | in |
Token ID | 287 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
chery | +0.495 |
xual | +0.483 |
apper | +0.462 |
�� | +0.458 |
urrency | +0.451 |
Neg logit contributions | |
Nept | -0.442 |
mir | -0.432 |
Reaction | -0.424 |
Boe | -0.416 |
Gret | -0.402 |
Token | Munich |
Token ID | 22418 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
Nept | +0.364 |
mir | +0.353 |
Reaction | +0.347 |
Boe | +0.339 |
Gret | +0.331 |
Neg logit contributions | |
chery | -0.434 |
xual | -0.425 |
apper | -0.406 |
�� | -0.401 |
urrency | -0.394 |
Token | - |
Token ID | 532 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Nept | +3.989 |
mir | +3.969 |
Reaction | +3.821 |
Boe | +3.807 |
Gret | +3.677 |
Neg logit contributions | |
chery | -5.520 |
xual | -5.497 |
�� | -5.277 |
apper | -5.196 |
urrency | -5.124 |
Token | which |
Token ID | 543 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Nept | +0.272 |
mir | +0.267 |
Reaction | +0.262 |
Boe | +0.255 |
Gret | +0.247 |
Neg logit contributions | |
chery | -0.309 |
xual | -0.300 |
apper | -0.288 |
�� | -0.287 |
urrency | -0.280 |
Token | goes |
Token ID | 2925 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Nept | +0.467 |
mir | +0.456 |
Reaction | +0.444 |
Boe | +0.437 |
Gret | +0.424 |
Neg logit contributions | |
chery | -0.533 |
xual | -0.518 |
apper | -0.501 |
�� | -0.497 |
urrency | -0.484 |
Token | from |
Token ID | 422 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Nept | +0.233 |
mir | +0.225 |
Reaction | +0.221 |
Boe | +0.219 |
Gret | +0.211 |
Neg logit contributions | |
chery | -0.240 |
xual | -0.231 |
apper | -0.223 |
�� | -0.220 |
urrency | -0.216 |
Token | September |
Token ID | 2693 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Nept | +0.041 |
mir | +0.040 |
Reaction | +0.040 |
Boe | +0.039 |
Gret | +0.037 |
Neg logit contributions | |
chery | -0.050 |
xual | -0.048 |
apper | -0.047 |
�� | -0.046 |
urrency | -0.045 |
Token | achieved |
Token ID | 8793 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Nept | +0.557 |
mir | +0.543 |
Reaction | +0.535 |
Boe | +0.525 |
Gret | +0.509 |
Neg logit contributions | |
chery | -0.504 |
xual | -0.483 |
apper | -0.471 |
�� | -0.460 |
urrency | -0.451 |
Token | representation |
Token ID | 10552 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Nept | +1.476 |
mir | +1.438 |
Reaction | +1.416 |
Boe | +1.378 |
Gret | +1.339 |
Neg logit contributions | |
chery | -1.513 |
xual | -1.460 |
apper | -1.424 |
�� | -1.402 |
urrency | -1.371 |
Token | in |
Token ID | 287 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
chery | +2.254 |
xual | +2.149 |
apper | +2.086 |
�� | +2.017 |
urrency | +2.003 |
Neg logit contributions | |
Nept | -2.598 |
mir | -2.554 |
Reaction | -2.501 |
Boe | -2.433 |
Gret | -2.364 |
Token | Australian |
Token ID | 6638 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Nept | +0.471 |
mir | +0.458 |
Reaction | +0.450 |
Boe | +0.439 |
Gret | +0.425 |
Neg logit contributions | |
chery | -0.546 |
xual | -0.525 |
apper | -0.513 |
�� | -0.501 |
urrency | -0.494 |
Token | par |
Token ID | 1582 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
chery | +1.353 |
xual | +1.302 |
apper | +1.270 |
�� | +1.242 |
urrency | +1.228 |
Neg logit contributions | |
Nept | -1.122 |
mir | -1.098 |
Reaction | -1.070 |
Boe | -1.040 |
Gret | -1.006 |
Token | liam |
Token ID | 5058 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Nept | +0.250 |
mir | +0.241 |
Reaction | +0.231 |
Boe | +0.222 |
Gret | +0.214 |
Neg logit contributions | |
chery | -0.537 |
xual | -0.523 |
apper | -0.509 |
�� | -0.505 |
urrency | -0.498 |
Token | ents |
Token ID | 658 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
mir | +3.480 |
Nept | +3.222 |
Reaction | +3.083 |
Boe | +3.072 |
Gret | +2.892 |
Neg logit contributions | |
chery | -6.168 |
xual | -6.156 |
�� | -6.057 |
apper | -5.814 |
urrency | -5.698 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Nept | +0.143 |
mir | +0.140 |
Reaction | +0.136 |
Boe | +0.132 |
Gret | +0.128 |
Neg logit contributions | |
chery | -0.181 |
xual | -0.174 |
apper | -0.170 |
�� | -0.167 |
urrency | -0.165 |
Token | mostly |
Token ID | 4632 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
Nept | +0.162 |
mir | +0.158 |
Reaction | +0.155 |
Boe | +0.151 |
Gret | +0.147 |
Neg logit contributions | |
chery | -0.169 |
xual | -0.163 |
apper | -0.159 |
�� | -0.157 |
urrency | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Nept | +0.012 |
mir | +0.012 |
Reaction | +0.011 |
Boe | +0.011 |
Gret | +0.011 |
Neg logit contributions | |
chery | -0.012 |
xual | -0.012 |
apper | -0.012 |
�� | -0.011 |
urrency | -0.011 |
Token | upper |
Token ID | 6727 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Nept | +0.492 |
mir | +0.480 |
Reaction | +0.471 |
Boe | +0.458 |
Gret | +0.445 |
Neg logit contributions | |
chery | -0.543 |
xual | -0.521 |
apper | -0.508 |
�� | -0.497 |
urrency | -0.490 |
Token | diagnosed |
Token ID | 14641 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
chery | +0.023 |
xual | +0.022 |
apper | +0.021 |
�� | +0.021 |
urrency | +0.021 |
Neg logit contributions | |
Nept | -0.019 |
mir | -0.018 |
Reaction | -0.018 |
Boe | -0.017 |
Gret | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Nept | +1.191 |
mir | +1.161 |
Reaction | +1.143 |
Boe | +1.120 |
Gret | +1.087 |
Neg logit contributions | |
chery | -1.248 |
xual | -1.210 |
apper | -1.174 |
�� | -1.150 |
urrency | -1.134 |
Token | with |
Token ID | 351 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Nept | +0.665 |
mir | +0.652 |
Reaction | +0.639 |
Boe | +0.623 |
Gret | +0.604 |
Neg logit contributions | |
chery | -0.655 |
xual | -0.634 |
apper | -0.614 |
�� | -0.606 |
urrency | -0.591 |
Token | foreign |
Token ID | 3215 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Nept | +0.135 |
mir | +0.131 |
Reaction | +0.128 |
Boe | +0.125 |
Gret | +0.121 |
Neg logit contributions | |
chery | -0.166 |
xual | -0.161 |
apper | -0.156 |
�� | -0.153 |
urrency | -0.151 |
Token | accent |
Token ID | 18702 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
chery | +0.500 |
xual | +0.477 |
apper | +0.465 |
�� | +0.452 |
urrency | +0.445 |
Neg logit contributions | |
Nept | -0.564 |
mir | -0.555 |
Reaction | -0.542 |
Boe | -0.530 |
Gret | -0.516 |
Token | syndrome |
Token ID | 14027 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
chery | +1.927 |
xual | +1.850 |
apper | +1.807 |
�� | +1.767 |
urrency | +1.750 |
Neg logit contributions | |
Nept | -1.443 |
mir | -1.405 |
Reaction | -1.362 |
Boe | -1.319 |
Gret | -1.281 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Nept | +3.832 |
mir | +3.793 |
Reaction | +3.694 |
Boe | +3.622 |
Gret | +3.474 |
Neg logit contributions | |
chery | -5.722 |
xual | -5.557 |
�� | -5.470 |
apper | -5.465 |
urrency | -5.332 |
Token | a |
Token ID | 257 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Nept | +0.046 |
mir | +0.045 |
Reaction | +0.044 |
Boe | +0.043 |
Gret | +0.041 |
Neg logit contributions | |
chery | -0.052 |
xual | -0.050 |
apper | -0.049 |
�� | -0.048 |
urrency | -0.047 |
Token | rare |
Token ID | 4071 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
chery | +0.396 |
xual | +0.382 |
apper | +0.372 |
�� | +0.365 |
urrency | +0.361 |
Neg logit contributions | |
Nept | -0.303 |
mir | -0.296 |
Reaction | -0.288 |
Boe | -0.279 |
Gret | -0.270 |
Token | neurological |
Token ID | 30232 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Nept | +0.926 |
mir | +0.909 |
Reaction | +0.888 |
Boe | +0.867 |
Gret | +0.834 |
Neg logit contributions | |
chery | -1.115 |
xual | -1.087 |
apper | -1.050 |
�� | -1.032 |
urrency | -1.015 |
Token | disorder |
Token ID | 8967 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Nept | +1.192 |
mir | +1.163 |
Reaction | +1.146 |
Boe | +1.109 |
Gret | +1.074 |
Neg logit contributions | |
chery | -1.555 |
xual | -1.525 |
apper | -1.461 |
�� | -1.446 |
urrency | -1.418 |
Token | a |
Token ID | 257 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Nept | +0.225 |
mir | +0.219 |
Reaction | +0.214 |
Boe | +0.209 |
Gret | +0.202 |
Neg logit contributions | |
chery | -0.251 |
xual | -0.244 |
apper | -0.236 |
�� | -0.233 |
urrency | -0.227 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
chery | +0.558 |
xual | +0.536 |
apper | +0.522 |
�� | +0.510 |
urrency | +0.504 |
Neg logit contributions | |
Nept | -0.523 |
mir | -0.513 |
Reaction | -0.499 |
Boe | -0.486 |
Gret | -0.472 |
Token | condition |
Token ID | 4006 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Nept | +0.189 |
mir | +0.186 |
Reaction | +0.181 |
Boe | +0.176 |
Gret | +0.171 |
Neg logit contributions | |
chery | -0.209 |
xual | -0.201 |
apper | -0.195 |
�� | -0.192 |
urrency | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Nept | +1.673 |
mir | +1.641 |
Reaction | +1.608 |
Boe | +1.566 |
Gret | +1.517 |
Neg logit contributions | |
chery | -1.875 |
xual | -1.807 |
apper | -1.756 |
�� | -1.752 |
urrency | -1.707 |
Token | an |
Token ID | 281 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
chery | +0.702 |
xual | +0.675 |
apper | +0.658 |
�� | +0.645 |
urrency | +0.635 |
Neg logit contributions | |
Nept | -0.645 |
mir | -0.631 |
Reaction | -0.616 |
Boe | -0.600 |
Gret | -0.582 |
Token | autos |
Token ID | 44619 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
chery | +1.163 |
xual | +1.118 |
apper | +1.087 |
�� | +1.065 |
urrency | +1.050 |
Neg logit contributions | |
Nept | -1.073 |
mir | -1.051 |
Reaction | -1.024 |
Boe | -0.998 |
Gret | -0.967 |
Token | omal |
Token ID | 18048 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
mir | +3.768 |
Nept | +3.644 |
Reaction | +3.581 |
Boe | +3.413 |
Gret | +3.296 |
Neg logit contributions | |
chery | -5.696 |
�� | -5.625 |
xual | -5.573 |
apper | -5.386 |
urrency | -5.264 |
Token | dominant |
Token ID | 11410 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Nept | +0.142 |
mir | +0.140 |
Reaction | +0.137 |
Boe | +0.133 |
Gret | +0.128 |
Neg logit contributions | |
chery | -0.181 |
xual | -0.174 |
apper | -0.170 |
�� | -0.168 |
urrency | -0.165 |
Token | palm |
Token ID | 18057 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
Nept | +1.022 |
mir | +0.999 |
Reaction | +0.977 |
Boe | +0.950 |
Gret | +0.915 |
Neg logit contributions | |
chery | -1.365 |
xual | -1.315 |
apper | -1.281 |
�� | -1.267 |
urrency | -1.249 |
Token | opl |
Token ID | 20106 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
Nept | +0.044 |
mir | +0.044 |
Reaction | +0.043 |
Boe | +0.041 |
Gret | +0.040 |
Neg logit contributions | |
chery | -0.054 |
xual | -0.053 |
�� | -0.051 |
apper | -0.050 |
urrency | -0.050 |
Token | ant |
Token ID | 415 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
chery | +1.054 |
xual | +1.002 |
�� | +0.971 |
apper | +0.960 |
urrency | +0.928 |
Neg logit contributions | |
Nept | -1.265 |
mir | -1.261 |
Reaction | -1.226 |
Boe | -1.196 |
Gret | -1.159 |
Token | ups |
Token ID | 4739 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
mir | +0.056 |
Nept | +0.056 |
Reaction | +0.054 |
Boe | +0.052 |
Gret | +0.051 |
Neg logit contributions | |
chery | -0.054 |
xual | -0.052 |
apper | -0.050 |
�� | -0.050 |
urrency | -0.048 |
Token | closely |
Token ID | 7173 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
chery | +2.008 |
xual | +1.929 |
apper | +1.877 |
�� | +1.838 |
urrency | +1.810 |
Neg logit contributions | |
Nept | -1.986 |
mir | -1.949 |
Reaction | -1.901 |
Boe | -1.852 |
Gret | -1.799 |
Token | resemble |
Token ID | 22464 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Nept | +0.140 |
mir | +0.138 |
Reaction | +0.134 |
Boe | +0.131 |
Gret | +0.127 |
Neg logit contributions | |
chery | -0.140 |
xual | -0.135 |
apper | -0.130 |
�� | -0.129 |
urrency | -0.126 |
Token | symptoms |
Token ID | 7460 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
chery | +0.246 |
xual | +0.238 |
apper | +0.231 |
�� | +0.227 |
urrency | +0.224 |
Neg logit contributions | |
Nept | -0.210 |
mir | -0.205 |
Reaction | -0.201 |
Boe | -0.196 |
Gret | -0.190 |
Token | of |
Token ID | 286 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Nept | +2.406 |
mir | +2.340 |
Reaction | +2.309 |
Boe | +2.239 |
Gret | +2.208 |
Neg logit contributions | |
chery | -2.581 |
xual | -2.488 |
�� | -2.416 |
apper | -2.414 |
urrency | -2.377 |
Token | schizophrenia |
Token ID | 22794 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
chery | +0.297 |
xual | +0.288 |
apper | +0.280 |
�� | +0.275 |
urrency | +0.272 |
Neg logit contributions | |
Nept | -0.228 |
mir | -0.222 |
Reaction | -0.218 |
Boe | -0.211 |
Gret | -0.204 |
Token | called |
Token ID | 1444 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Nept | +3.727 |
mir | +3.664 |
Reaction | +3.589 |
Boe | +3.449 |
Gret | +3.333 |
Neg logit contributions | |
chery | -5.722 |
xual | -5.559 |
�� | -5.389 |
apper | -5.374 |
urrency | -5.315 |
Token | derail |
Token ID | 33749 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
chery | +0.340 |
xual | +0.327 |
apper | +0.319 |
�� | +0.313 |
urrency | +0.310 |
Neg logit contributions | |
Nept | -0.267 |
mir | -0.261 |
Reaction | -0.255 |
Boe | -0.247 |
Gret | -0.239 |
Token | ment |
Token ID | 434 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Nept | +0.442 |
mir | +0.435 |
Reaction | +0.425 |
Boe | +0.411 |
Gret | +0.398 |
Neg logit contributions | |
chery | -0.487 |
xual | -0.467 |
apper | -0.457 |
�� | -0.446 |
urrency | -0.441 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Nept | +1.068 |
mir | +1.041 |
Reaction | +1.025 |
Boe | +0.979 |
Gret | +0.942 |
Neg logit contributions | |
chery | -1.629 |
xual | -1.560 |
apper | -1.534 |
�� | -1.515 |
urrency | -1.494 |
Token | delusion |
Token ID | 40969 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Nept | +0.390 |
mir | +0.381 |
Reaction | +0.375 |
Boe | +0.363 |
Gret | +0.352 |
Neg logit contributions | |
chery | -0.439 |
xual | -0.425 |
apper | -0.413 |
�� | -0.405 |
urrency | -0.401 |
Token | Friends |
Token ID | 14213 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
chery | +0.787 |
xual | +0.758 |
apper | +0.734 |
�� | +0.720 |
urrency | +0.708 |
Neg logit contributions | |
Nept | -0.790 |
mir | -0.773 |
Reaction | -0.755 |
Boe | -0.738 |
Gret | -0.717 |
Token | of |
Token ID | 286 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Nept | +1.392 |
mir | +1.367 |
Reaction | +1.333 |
Boe | +1.301 |
Gret | +1.266 |
Neg logit contributions | |
chery | -1.383 |
xual | -1.330 |
apper | -1.291 |
�� | -1.264 |
urrency | -1.247 |
Token | the |
Token ID | 262 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
chery | +0.046 |
xual | +0.045 |
apper | +0.043 |
�� | +0.043 |
urrency | +0.042 |
Neg logit contributions | |
Nept | -0.038 |
mir | -0.037 |
Reaction | -0.036 |
Boe | -0.035 |
Gret | -0.034 |
Token | Earth |
Token ID | 3668 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Nept | +0.116 |
mir | +0.114 |
Reaction | +0.112 |
Boe | +0.109 |
Gret | +0.107 |
Neg logit contributions | |
chery | -0.101 |
xual | -0.097 |
apper | -0.094 |
�� | -0.092 |
urrency | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
chery | +0.586 |
xual | +0.564 |
apper | +0.551 |
�� | +0.539 |
urrency | +0.533 |
Neg logit contributions | |
Nept | -0.477 |
mir | -0.467 |
Reaction | -0.454 |
Boe | -0.441 |
Gret | -0.427 |
Token | Sierra |
Token ID | 17559 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Nept | +0.057 |
mir | +0.056 |
Reaction | +0.054 |
Boe | +0.053 |
Gret | +0.051 |
Neg logit contributions | |
chery | -0.077 |
xual | -0.074 |
apper | -0.072 |
�� | -0.071 |
urrency | -0.070 |
Token | Club |
Token ID | 6289 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
Nept | +3.288 |
mir | +3.253 |
Reaction | +3.176 |
Boe | +3.066 |
Gret | +2.962 |
Neg logit contributions | |
chery | -6.126 |
xual | -5.985 |
�� | -5.813 |
apper | -5.782 |
urrency | -5.690 |
Token | , |
Token ID | 11 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
chery | +0.083 |
xual | +0.080 |
apper | +0.078 |
�� | +0.076 |
urrency | +0.076 |
Neg logit contributions | |
Nept | -0.067 |
mir | -0.065 |
Reaction | -0.063 |
Boe | -0.061 |
Gret | -0.059 |
Token | Natural |
Token ID | 12068 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Nept | +0.012 |
mir | +0.012 |
Reaction | +0.011 |
Boe | +0.011 |
Gret | +0.011 |
Neg logit contributions | |
chery | -0.016 |
xual | -0.016 |
apper | -0.015 |
�� | -0.015 |
urrency | -0.015 |
Token | Resources |
Token ID | 13864 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
chery | +1.011 |
xual | +0.975 |
apper | +0.954 |
�� | +0.936 |
urrency | +0.925 |
Neg logit contributions | |
Nept | -0.684 |
mir | -0.668 |
Reaction | -0.647 |
Boe | -0.627 |
Gret | -0.604 |
Token | Defense |
Token ID | 5947 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Nept | +0.949 |
mir | +0.930 |
Reaction | +0.912 |
Boe | +0.873 |
Gret | +0.850 |
Neg logit contributions | |
chery | -1.411 |
xual | -1.372 |
apper | -1.334 |
�� | -1.319 |
urrency | -1.297 |
Token | , |
Token ID | 11 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
Nept | +0.258 |
mir | +0.252 |
Reaction | +0.244 |
Boe | +0.237 |
Gret | +0.229 |
Neg logit contributions | |
chery | -0.371 |
xual | -0.359 |
apper | -0.351 |
�� | -0.345 |
urrency | -0.341 |
Token | seemingly |
Token ID | 9775 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
chery | +0.091 |
xual | +0.088 |
apper | +0.086 |
�� | +0.084 |
urrency | +0.083 |
Neg logit contributions | |
Nept | -0.092 |
mir | -0.091 |
Reaction | -0.088 |
Boe | -0.087 |
Gret | -0.084 |
Token | ve |
Token ID | 1569 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Nept | +2.094 |
mir | +2.078 |
Reaction | +2.008 |
Boe | +1.982 |
Gret | +1.943 |
Neg logit contributions | |
chery | -1.889 |
xual | -1.861 |
apper | -1.807 |
�� | -1.794 |
urrency | -1.747 |
Token | ered |
Token ID | 1068 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
chery | +0.390 |
xual | +0.375 |
apper | +0.368 |
�� | +0.361 |
urrency | +0.356 |
Neg logit contributions | |
Nept | -0.350 |
mir | -0.344 |
Reaction | -0.333 |
Boe | -0.325 |
Gret | -0.315 |
Token | into |
Token ID | 656 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Nept | +0.215 |
mir | +0.210 |
Reaction | +0.205 |
Boe | +0.201 |
Gret | +0.196 |
Neg logit contributions | |
chery | -0.232 |
xual | -0.225 |
apper | -0.218 |
�� | -0.216 |
urrency | -0.212 |
Token | sch |
Token ID | 5513 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Nept | +0.244 |
mir | +0.240 |
Reaction | +0.234 |
Boe | +0.228 |
Gret | +0.222 |
Neg logit contributions | |
chery | -0.268 |
xual | -0.259 |
apper | -0.252 |
�� | -0.248 |
urrency | -0.244 |
Token | lock |
Token ID | 5354 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
mir | +3.422 |
Nept | +3.315 |
Reaction | +3.182 |
Boe | +3.088 |
Gret | +2.908 |
Neg logit contributions | |
chery | -5.895 |
xual | -5.784 |
�� | -5.689 |
apper | -5.514 |
urrency | -5.441 |
Token | - |
Token ID | 12 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
chery | +0.258 |
xual | +0.248 |
apper | +0.242 |
�� | +0.237 |
urrency | +0.234 |
Neg logit contributions | |
Nept | -0.229 |
mir | -0.225 |
Reaction | -0.219 |
Boe | -0.212 |
Gret | -0.206 |
Token | me |
Token ID | 1326 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Nept | +0.215 |
mir | +0.212 |
Reaction | +0.205 |
Boe | +0.199 |
Gret | +0.193 |
Neg logit contributions | |
chery | -0.251 |
xual | -0.243 |
apper | -0.236 |
�� | -0.232 |
urrency | -0.228 |
Token | ister |
Token ID | 1694 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
chery | +0.988 |
xual | +0.955 |
apper | +0.935 |
�� | +0.918 |
urrency | +0.905 |
Neg logit contributions | |
Nept | -0.692 |
mir | -0.677 |
Reaction | -0.656 |
Boe | -0.637 |
Gret | -0.615 |
Token | William |
Token ID | 3977 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
Nept | +1.672 |
mir | +1.644 |
Reaction | +1.603 |
Boe | +1.561 |
Gret | +1.516 |
Neg logit contributions | |
chery | -1.961 |
xual | -1.898 |
apper | -1.863 |
�� | -1.832 |
urrency | -1.812 |
Token | might |
Token ID | 44092 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
chery | +1.125 |
xual | +1.083 |
apper | +1.053 |
�� | +1.035 |
urrency | +1.018 |
Neg logit contributions | |
Nept | -1.005 |
mir | -0.993 |
Reaction | -0.961 |
Boe | -0.935 |
Gret | -0.907 |
Token | be |
Token ID | 307 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Nept | +0.593 |
mir | +0.584 |
Reaction | +0.565 |
Boe | +0.551 |
Gret | +0.535 |
Neg logit contributions | |
chery | -0.627 |
xual | -0.606 |
apper | -0.588 |
�� | -0.583 |
urrency | -0.571 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
chery | +0.804 |
xual | +0.775 |
apper | +0.754 |
�� | +0.739 |
urrency | +0.729 |
Neg logit contributions | |
Nept | -0.743 |
mir | -0.728 |
Reaction | -0.709 |
Boe | -0.692 |
Gret | -0.671 |
Token | cause |
Token ID | 2728 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
chery | +0.201 |
xual | +0.194 |
apper | +0.189 |
�� | +0.186 |
urrency | +0.183 |
Neg logit contributions | |
Nept | -0.172 |
mir | -0.169 |
Reaction | -0.165 |
Boe | -0.160 |
Gret | -0.155 |
Token | of |
Token ID | 286 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Nept | +0.232 |
mir | +0.225 |
Reaction | +0.222 |
Boe | +0.216 |
Gret | +0.209 |
Neg logit contributions | |
chery | -0.229 |
xual | -0.220 |
apper | -0.214 |
�� | -0.207 |
urrency | -0.204 |
Token | schizophrenia |
Token ID | 22794 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
chery | +0.339 |
xual | +0.327 |
apper | +0.318 |
�� | +0.313 |
urrency | +0.309 |
Neg logit contributions | |
Nept | -0.265 |
mir | -0.260 |
Reaction | -0.253 |
Boe | -0.245 |
Gret | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Nept | +3.502 |
mir | +3.478 |
Reaction | +3.374 |
Boe | +3.220 |
Gret | +3.105 |
Neg logit contributions | |
chery | -5.689 |
xual | -5.557 |
apper | -5.413 |
�� | -5.384 |
urrency | -5.328 |
Token | They |
Token ID | 1119 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Nept | +0.026 |
mir | +0.025 |
Reaction | +0.025 |
Boe | +0.024 |
Gret | +0.023 |
Neg logit contributions | |
chery | -0.036 |
xual | -0.035 |
apper | -0.034 |
�� | -0.034 |
urrency | -0.033 |
Token | have |
Token ID | 423 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Nept | +0.032 |
mir | +0.031 |
Reaction | +0.030 |
Boe | +0.030 |
Gret | +0.029 |
Neg logit contributions | |
chery | -0.030 |
xual | -0.029 |
apper | -0.028 |
�� | -0.028 |
urrency | -0.027 |
Token | dubbed |
Token ID | 17494 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Nept | +0.379 |
mir | +0.365 |
Reaction | +0.356 |
Boe | +0.355 |
Gret | +0.342 |
Neg logit contributions | |
chery | -0.363 |
xual | -0.351 |
apper | -0.340 |
�� | -0.334 |
urrency | -0.328 |
Token | this |
Token ID | 428 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
chery | +0.293 |
xual | +0.281 |
apper | +0.274 |
�� | +0.267 |
urrency | +0.264 |
Neg logit contributions | |
Nept | -0.295 |
mir | -0.290 |
Reaction | -0.283 |
Boe | -0.276 |
Gret | -0.268 |
Token | with |
Token ID | 351 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
Nept | +0.064 |
mir | +0.063 |
Reaction | +0.062 |
Boe | +0.060 |
Gret | +0.058 |
Neg logit contributions | |
chery | -0.069 |
xual | -0.066 |
apper | -0.064 |
�� | -0.064 |
urrency | -0.062 |
Token | traces |
Token ID | 20675 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Nept | +0.060 |
mir | +0.058 |
Reaction | +0.057 |
Boe | +0.055 |
Gret | +0.054 |
Neg logit contributions | |
chery | -0.076 |
xual | -0.074 |
apper | -0.071 |
�� | -0.070 |
urrency | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
chery | +1.616 |
xual | +1.545 |
apper | +1.501 |
�� | +1.456 |
urrency | +1.440 |
Neg logit contributions | |
Nept | -1.765 |
mir | -1.734 |
Reaction | -1.697 |
Boe | -1.652 |
Gret | -1.600 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
chery | +0.094 |
xual | +0.091 |
apper | +0.089 |
�� | +0.088 |
urrency | +0.086 |
Neg logit contributions | |
Nept | -0.072 |
mir | -0.069 |
Reaction | -0.067 |
Boe | -0.066 |
Gret | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Nept | +0.020 |
mir | +0.019 |
Reaction | +0.019 |
Boe | +0.018 |
Gret | +0.018 |
Neg logit contributions | |
chery | -0.022 |
xual | -0.021 |
apper | -0.021 |
�� | -0.021 |
urrency | -0.020 |
Token | Cyr |
Token ID | 40399 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
chery | +0.452 |
xual | +0.434 |
apper | +0.425 |
�� | +0.419 |
urrency | +0.410 |
Neg logit contributions | |
Nept | -0.381 |
mir | -0.373 |
Reaction | -0.362 |
Boe | -0.351 |
Gret | -0.340 |
Token | ill |
Token ID | 359 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
chery | +7.759 |
xual | +7.249 |
apper | +7.242 |
urrency | +6.909 |
axy | +6.757 |
Neg logit contributions | |
Nept | -7.942 |
mir | -7.599 |
Reaction | -7.566 |
Boe | -7.248 |
Gret | -7.165 |
Token | ic |
Token ID | 291 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Nept | +0.623 |
mir | +0.605 |
Reaction | +0.585 |
Boe | +0.570 |
Gret | +0.559 |
Neg logit contributions | |
chery | -0.676 |
xual | -0.654 |
apper | -0.628 |
�� | -0.623 |
urrency | -0.607 |
Token | found |
Token ID | 1043 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
chery | +0.222 |
xual | +0.214 |
apper | +0.207 |
�� | +0.205 |
urrency | +0.198 |
Neg logit contributions | |
Nept | -0.222 |
mir | -0.217 |
Reaction | -0.213 |
Boe | -0.207 |
Gret | -0.201 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
chery | +0.277 |
xual | +0.267 |
apper | +0.259 |
�� | +0.256 |
urrency | +0.248 |
Neg logit contributions | |
Nept | -0.303 |
mir | -0.298 |
Reaction | -0.290 |
Boe | -0.284 |
Gret | -0.277 |
Token | their |
Token ID | 511 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
Nept | +0.163 |
mir | +0.158 |
Reaction | +0.155 |
Boe | +0.151 |
Gret | +0.147 |
Neg logit contributions | |
chery | -0.200 |
xual | -0.194 |
apper | -0.188 |
�� | -0.185 |
urrency | -0.181 |
Token | this |
Token ID | 428 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
Nept | +0.778 |
mir | +0.757 |
Reaction | +0.751 |
Boe | +0.719 |
Gret | +0.705 |
Neg logit contributions | |
chery | -0.797 |
xual | -0.770 |
apper | -0.742 |
�� | -0.739 |
urrency | -0.719 |
Token | post |
Token ID | 1281 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Nept | +0.080 |
mir | +0.078 |
Reaction | +0.076 |
Boe | +0.073 |
Gret | +0.072 |
Neg logit contributions | |
chery | -0.085 |
xual | -0.082 |
apper | -0.079 |
�� | -0.079 |
urrency | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
chery | +0.288 |
xual | +0.278 |
apper | +0.272 |
�� | +0.268 |
urrency | +0.264 |
Neg logit contributions | |
Nept | -0.213 |
mir | -0.209 |
Reaction | -0.203 |
Boe | -0.197 |
Gret | -0.190 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Nept | +0.008 |
mir | +0.008 |
Reaction | +0.008 |
Boe | +0.008 |
Gret | +0.007 |
Neg logit contributions | |
chery | -0.012 |
xual | -0.012 |
apper | -0.012 |
�� | -0.012 |
urrency | -0.011 |
Token | THE |
Token ID | 10970 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
chery | +2.190 |
xual | +2.088 |
apper | +2.060 |
�� | +2.004 |
urrency | +1.985 |
Neg logit contributions | |
Nept | -1.734 |
mir | -1.671 |
Reaction | -1.644 |
Boe | -1.600 |
Gret | -1.541 |
Token | BALL |
Token ID | 46433 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
Nept | +0.070 |
mir | +0.068 |
Reaction | +0.066 |
Boe | +0.064 |
Gret | +0.062 |
Neg logit contributions | |
chery | -0.089 |
xual | -0.086 |
apper | -0.084 |
�� | -0.082 |
urrency | -0.081 |
Token | OT |
Token ID | 2394 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
chery | +6.601 |
xual | +6.323 |
apper | +6.296 |
�� | +6.061 |
urrency | +6.054 |
Neg logit contributions | |
Nept | -5.158 |
mir | -5.018 |
Reaction | -4.802 |
Boe | -4.742 |
Gret | -4.514 |
Token | FOR |
Token ID | 7473 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
chery | +2.208 |
xual | +2.124 |
apper | +2.076 |
�� | +2.033 |
urrency | +2.009 |
Neg logit contributions | |
Nept | -1.729 |
mir | -1.689 |
Reaction | -1.642 |
Boe | -1.595 |
Gret | -1.543 |
Token | industrial |
Token ID | 7593 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Nept | +0.231 |
mir | +0.225 |
Reaction | +0.220 |
Boe | +0.213 |
Gret | +0.206 |
Neg logit contributions | |
chery | -0.310 |
xual | -0.301 |
apper | -0.291 |
�� | -0.287 |
urrency | -0.283 |
Token | action |
Token ID | 2223 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
Nept | +0.979 |
mir | +0.946 |
Reaction | +0.940 |
Boe | +0.909 |
Gret | +0.891 |
Neg logit contributions | |
chery | -0.892 |
xual | -0.860 |
apper | -0.817 |
�� | -0.805 |
urrency | -0.779 |
Token | among |
Token ID | 1871 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Nept | +0.027 |
mir | +0.026 |
Reaction | +0.025 |
Boe | +0.024 |
Gret | +0.024 |
Neg logit contributions | |
chery | -0.029 |
xual | -0.028 |
apper | -0.027 |
�� | -0.027 |
urrency | -0.026 |
Token | as |
Token ID | 355 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
chery | +1.336 |
xual | +1.294 |
apper | +1.257 |
�� | +1.251 |
urrency | +1.219 |
Neg logit contributions | |
Nept | -1.092 |
mir | -1.067 |
Reaction | -1.040 |
Boe | -1.011 |
Gret | -0.986 |
Token | representatives |
Token ID | 10826 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
chery | +0.904 |
xual | +0.868 |
apper | +0.845 |
�� | +0.829 |
urrency | +0.817 |
Neg logit contributions | |
Nept | -0.827 |
mir | -0.809 |
Reaction | -0.789 |
Boe | -0.769 |
Gret | -0.746 |
Token | from |
Token ID | 422 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
chery | +0.668 |
xual | +0.639 |
apper | +0.624 |
�� | +0.602 |
urrency | +0.597 |
Neg logit contributions | |
Nept | -0.667 |
mir | -0.652 |
Reaction | -0.638 |
Boe | -0.618 |
Gret | -0.597 |
Token | club |
Token ID | 3430 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
chery | +0.399 |
xual | +0.383 |
apper | +0.373 |
�� | +0.366 |
urrency | +0.361 |
Neg logit contributions | |
Nept | -0.345 |
mir | -0.337 |
Reaction | -0.329 |
Boe | -0.320 |
Gret | -0.310 |
Token | sponsors |
Token ID | 18073 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
chery | +0.329 |
xual | +0.317 |
apper | +0.307 |
�� | +0.301 |
urrency | +0.296 |
Neg logit contributions | |
Nept | -0.323 |
mir | -0.317 |
Reaction | -0.309 |
Boe | -0.301 |
Gret | -0.292 |
Token | Wong |
Token ID | 27247 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
chery | +0.022 |
xual | +0.021 |
apper | +0.020 |
�� | +0.020 |
urrency | +0.020 |
Neg logit contributions | |
Nept | -0.017 |
mir | -0.017 |
Reaction | -0.016 |
Boe | -0.016 |
Gret | -0.015 |
Token | a |
Token ID | 64 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
chery | +5.828 |
xual | +5.531 |
apper | +5.465 |
�� | +5.278 |
urrency | +5.266 |
Neg logit contributions | |
Nept | -5.782 |
mir | -5.626 |
Reaction | -5.497 |
Boe | -5.297 |
Gret | -5.237 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Nept | +0.484 |
mir | +0.473 |
Reaction | +0.463 |
Boe | +0.449 |
Gret | +0.434 |
Neg logit contributions | |
chery | -0.649 |
xual | -0.627 |
apper | -0.612 |
�� | -0.602 |
urrency | -0.593 |
Token | com |
Token ID | 785 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Nept | +0.195 |
mir | +0.192 |
Reaction | +0.186 |
Boe | +0.180 |
Gret | +0.174 |
Neg logit contributions | |
chery | -0.270 |
xual | -0.260 |
apper | -0.254 |
�� | -0.250 |
urrency | -0.246 |
Token | . |
Token ID | 13 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
chery | +0.402 |
xual | +0.387 |
apper | +0.378 |
�� | +0.371 |
urrency | +0.366 |
Neg logit contributions | |
Nept | -0.311 |
mir | -0.304 |
Reaction | -0.296 |
Boe | -0.287 |
Gret | -0.277 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Nept | +0.049 |
mir | +0.048 |
Reaction | +0.047 |
Boe | +0.045 |
Gret | +0.044 |
Neg logit contributions | |
chery | -0.069 |
xual | -0.066 |
apper | -0.065 |
�� | -0.064 |
urrency | -0.063 |
Token | In |
Token ID | 554 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Nept | +0.037 |
mir | +0.036 |
Reaction | +0.036 |
Boe | +0.034 |
Gret | +0.033 |
Neg logit contributions | |
chery | -0.055 |
xual | -0.053 |
apper | -0.052 |
�� | -0.051 |
urrency | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
Nept | +0.242 |
mir | +0.236 |
Reaction | +0.230 |
Boe | +0.223 |
Gret | +0.215 |
Neg logit contributions | |
chery | -0.337 |
xual | -0.325 |
apper | -0.318 |
�� | -0.313 |
urrency | -0.308 |
Token | face |
Token ID | 1986 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Nept | +0.108 |
mir | +0.105 |
Reaction | +0.103 |
Boe | +0.100 |
Gret | +0.097 |
Neg logit contributions | |
chery | -0.136 |
xual | -0.131 |
apper | -0.127 |
�� | -0.126 |
urrency | -0.123 |
Token | of |
Token ID | 286 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
chery | +0.741 |
xual | +0.722 |
�� | +0.704 |
apper | +0.701 |
urrency | +0.679 |
Neg logit contributions | |
Nept | -0.685 |
mir | -0.679 |
Reaction | -0.660 |
Boe | -0.641 |
Gret | -0.627 |
Token | these |
Token ID | 777 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
chery | +0.132 |
xual | +0.127 |
apper | +0.124 |
�� | +0.122 |
urrency | +0.120 |
Neg logit contributions | |
Nept | -0.138 |
mir | -0.134 |
Reaction | -0.132 |
Boe | -0.129 |
Gret | -0.125 |
Token | discrim |
Token ID | 6534 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
chery | +0.137 |
xual | +0.133 |
apper | +0.129 |
�� | +0.127 |
urrency | +0.125 |
Neg logit contributions | |
Nept | -0.137 |
mir | -0.134 |
Reaction | -0.131 |
Boe | -0.128 |
Gret | -0.124 |
Token | inations |
Token ID | 7352 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
chery | +6.170 |
xual | +5.711 |
apper | +5.692 |
urrency | +5.578 |
axy | +5.462 |
Neg logit contributions | |
Nept | -5.395 |
mir | -5.150 |
Reaction | -5.097 |
Boe | -4.940 |
Gret | -4.803 |
Token | , |
Token ID | 11 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
Nept | +0.391 |
mir | +0.380 |
Reaction | +0.371 |
Boe | +0.363 |
Gret | +0.348 |
Neg logit contributions | |
chery | -0.524 |
xual | -0.502 |
apper | -0.494 |
�� | -0.488 |
urrency | -0.479 |
Token | it |
Token ID | 340 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
chery | +0.099 |
xual | +0.094 |
apper | +0.091 |
�� | +0.091 |
urrency | +0.088 |
Neg logit contributions | |
Nept | -0.132 |
mir | -0.129 |
Reaction | -0.127 |
Boe | -0.125 |
Gret | -0.121 |
Token | is |
Token ID | 318 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Nept | +0.376 |
mir | +0.370 |
Reaction | +0.358 |
Boe | +0.348 |
Gret | +0.340 |
Neg logit contributions | |
chery | -0.449 |
xual | -0.434 |
apper | -0.425 |
�� | -0.420 |
urrency | -0.409 |
Token | currently |
Token ID | 3058 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Nept | +0.209 |
mir | +0.204 |
Reaction | +0.200 |
Boe | +0.195 |
Gret | +0.190 |
Neg logit contributions | |
chery | -0.217 |
xual | -0.211 |
apper | -0.205 |
�� | -0.203 |
urrency | -0.199 |
Token | country |
Token ID | 1499 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Nept | +0.131 |
mir | +0.128 |
Reaction | +0.125 |
Boe | +0.121 |
Gret | +0.117 |
Neg logit contributions | |
chery | -0.158 |
xual | -0.152 |
apper | -0.148 |
�� | -0.145 |
urrency | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
chery | +0.419 |
xual | +0.402 |
apper | +0.393 |
�� | +0.384 |
urrency | +0.379 |
Neg logit contributions | |
Nept | -0.398 |
mir | -0.391 |
Reaction | -0.381 |
Boe | -0.370 |
Gret | -0.360 |
Token | � |
Token ID | 447 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
Nept | +0.085 |
mir | +0.084 |
Reaction | +0.081 |
Boe | +0.079 |
Gret | +0.077 |
Neg logit contributions | |
chery | -0.090 |
xual | -0.087 |
apper | -0.085 |
�� | -0.083 |
urrency | -0.082 |
Token | � |
Token ID | 251 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Nept | +0.076 |
mir | +0.074 |
Reaction | +0.073 |
Boe | +0.071 |
Gret | +0.069 |
Neg logit contributions | |
chery | -0.078 |
xual | -0.075 |
apper | -0.072 |
�� | -0.071 |
urrency | -0.070 |
Token | said |
Token ID | 531 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
Nept | +0.657 |
mir | +0.644 |
Reaction | +0.624 |
Boe | +0.608 |
Gret | +0.593 |
Neg logit contributions | |
chery | -0.843 |
xual | -0.818 |
apper | -0.796 |
�� | -0.784 |
urrency | -0.774 |
Token | Wong |
Token ID | 27247 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
Nept | +0.003 |
mir | +0.003 |
Reaction | +0.003 |
Boe | +0.003 |
Gret | +0.003 |
Neg logit contributions | |
chery | -0.002 |
xual | -0.001 |
apper | -0.001 |
�� | -0.001 |
urrency | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
chery | +6.095 |
xual | +5.806 |
apper | +5.709 |
�� | +5.662 |
urrency | +5.478 |
Neg logit contributions | |
Nept | -5.066 |
mir | -4.915 |
Reaction | -4.824 |
Boe | -4.642 |
Gret | -4.493 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Nept | +0.373 |
mir | +0.365 |
Reaction | +0.356 |
Boe | +0.344 |
Gret | +0.333 |
Neg logit contributions | |
chery | -0.509 |
xual | -0.492 |
apper | -0.481 |
�� | -0.471 |
urrency | -0.466 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
mir | +0.272 |
Nept | +0.270 |
Reaction | +0.259 |
Boe | +0.251 |
Gret | +0.244 |
Neg logit contributions | |
chery | -0.427 |
xual | -0.426 |
�� | -0.414 |
apper | -0.407 |
urrency | -0.396 |
Token | He |
Token ID | 1544 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Nept | +0.281 |
mir | +0.281 |
Reaction | +0.268 |
Boe | +0.260 |
Gret | +0.252 |
Neg logit contributions | |
chery | -0.376 |
xual | -0.370 |
apper | -0.356 |
�� | -0.350 |
urrency | -0.346 |
Token | wants |
Token ID | 3382 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Nept | +0.162 |
mir | +0.159 |
Reaction | +0.152 |
Boe | +0.150 |
Gret | +0.146 |
Neg logit contributions | |
chery | -0.196 |
xual | -0.189 |
apper | -0.186 |
�� | -0.182 |
urrency | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
Nept | +0.632 |
mir | +0.624 |
Reaction | +0.596 |
Boe | +0.580 |
Gret | +0.562 |
Neg logit contributions | |
chery | -0.961 |
xual | -0.934 |
apper | -0.914 |
�� | -0.899 |
urrency | -0.885 |
Token | � |
Token ID | 447 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
chery | +0.094 |
xual | +0.090 |
apper | +0.088 |
�� | +0.086 |
urrency | +0.085 |
Neg logit contributions | |
Nept | -0.084 |
mir | -0.083 |
Reaction | -0.081 |
Boe | -0.078 |
Gret | -0.076 |
Token | � |
Token ID | 247 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
chery | +0.348 |
xual | +0.334 |
apper | +0.325 |
�� | +0.316 |
urrency | +0.313 |
Neg logit contributions | |
Nept | -0.326 |
mir | -0.320 |
Reaction | -0.312 |
Boe | -0.304 |
Gret | -0.295 |
Token | � |
Token ID | 564 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
chery | +0.507 |
xual | +0.489 |
apper | +0.476 |
�� | +0.466 |
urrency | +0.459 |
Neg logit contributions | |
Nept | -0.454 |
mir | -0.446 |
Reaction | -0.435 |
Boe | -0.422 |
Gret | -0.410 |
Token | � |
Token ID | 251 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
chery | +0.163 |
xual | +0.156 |
apper | +0.151 |
�� | +0.146 |
urrency | +0.145 |
Neg logit contributions | |
Nept | -0.191 |
mir | -0.188 |
Reaction | -0.184 |
Boe | -0.180 |
Gret | -0.175 |
Token | Wong |
Token ID | 27247 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
Nept | +0.960 |
mir | +0.951 |
Reaction | +0.920 |
Boe | +0.892 |
Gret | +0.871 |
Neg logit contributions | |
chery | -1.129 |
xual | -1.095 |
apper | -1.060 |
�� | -1.051 |
urrency | -1.026 |
Token | said |
Token ID | 531 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
chery | +5.960 |
xual | +5.666 |
apper | +5.578 |
�� | +5.463 |
urrency | +5.384 |
Neg logit contributions | |
Nept | -5.190 |
mir | -5.002 |
Reaction | -4.966 |
Boe | -4.745 |
Gret | -4.613 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Nept | +0.106 |
mir | +0.103 |
Reaction | +0.100 |
Boe | +0.097 |
Gret | +0.093 |
Neg logit contributions | |
chery | -0.161 |
xual | -0.156 |
apper | -0.152 |
�� | -0.150 |
urrency | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
Nept | +0.276 |
mir | +0.270 |
Reaction | +0.263 |
Boe | +0.254 |
Gret | +0.246 |
Neg logit contributions | |
chery | -0.382 |
xual | -0.369 |
apper | -0.361 |
�� | -0.354 |
urrency | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
mir | +0.047 |
Nept | +0.047 |
Reaction | +0.045 |
Boe | +0.043 |
Gret | +0.042 |
Neg logit contributions | |
chery | -0.072 |
xual | -0.071 |
�� | -0.069 |
apper | -0.068 |
urrency | -0.066 |
Token | The |
Token ID | 464 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
chery | +0.015 |
xual | +0.015 |
apper | +0.014 |
�� | +0.014 |
urrency | +0.014 |
Neg logit contributions | |
Nept | -0.011 |
mir | -0.011 |
Reaction | -0.011 |
Boe | -0.010 |
Gret | -0.010 |
Token | social |
Token ID | 1919 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Nept | +0.055 |
mir | +0.054 |
Reaction | +0.053 |
Boe | +0.051 |
Gret | +0.050 |
Neg logit contributions | |
chery | -0.053 |
xual | -0.051 |
apper | -0.050 |
�� | -0.049 |
urrency | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Nept | +0.807 |
mir | +0.792 |
Reaction | +0.772 |
Boe | +0.746 |
Gret | +0.721 |
Neg logit contributions | |
chery | -1.077 |
xual | -1.038 |
apper | -1.012 |
�� | -0.999 |
urrency | -0.981 |
Token | public |
Token ID | 1171 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
chery | +0.214 |
xual | +0.206 |
apper | +0.200 |
�� | +0.199 |
urrency | +0.193 |
Neg logit contributions | |
Nept | -0.208 |
mir | -0.202 |
Reaction | -0.199 |
Boe | -0.195 |
Gret | -0.188 |
Token | opinions |
Token ID | 9317 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
Nept | +0.219 |
mir | +0.215 |
Reaction | +0.214 |
Boe | +0.206 |
Gret | +0.199 |
Neg logit contributions | |
chery | -0.202 |
xual | -0.193 |
apper | -0.186 |
�� | -0.186 |
urrency | -0.181 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
chery | +1.199 |
xual | +1.152 |
apper | +1.123 |
�� | +1.102 |
urrency | +1.082 |
Neg logit contributions | |
Nept | -1.200 |
mir | -1.180 |
Reaction | -1.151 |
Boe | -1.122 |
Gret | -1.090 |
Token | pun |
Token ID | 4000 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
chery | +0.319 |
xual | +0.304 |
apper | +0.294 |
�� | +0.291 |
urrency | +0.283 |
Neg logit contributions | |
Nept | -0.398 |
mir | -0.389 |
Reaction | -0.384 |
Boe | -0.376 |
Gret | -0.365 |
Token | ks |
Token ID | 591 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
chery | +6.567 |
xual | +6.243 |
apper | +6.174 |
urrency | +5.969 |
�� | +5.924 |
Neg logit contributions | |
Nept | -4.056 |
mir | -3.902 |
Reaction | -3.799 |
Boe | -3.668 |
Gret | -3.520 |
Token | have |
Token ID | 423 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Nept | +0.212 |
mir | +0.211 |
Reaction | +0.204 |
Boe | +0.198 |
Gret | +0.192 |
Neg logit contributions | |
chery | -0.227 |
xual | -0.217 |
apper | -0.215 |
�� | -0.212 |
urrency | -0.206 |
Token | not |
Token ID | 407 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Nept | +0.399 |
mir | +0.393 |
Reaction | +0.382 |
Boe | +0.376 |
Gret | +0.366 |
Neg logit contributions | |
chery | -0.338 |
xual | -0.329 |
apper | -0.318 |
�� | -0.313 |
urrency | -0.304 |
Token | entirely |
Token ID | 5000 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
chery | +0.447 |
xual | +0.433 |
apper | +0.415 |
�� | +0.414 |
urrency | +0.400 |
Neg logit contributions | |
Nept | -0.549 |
mir | -0.541 |
Reaction | -0.525 |
Boe | -0.517 |
Gret | -0.502 |
Token | stepped |
Token ID | 10764 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
Nept | +2.067 |
mir | +2.051 |
Boe | +1.970 |
Reaction | +1.958 |
Gret | +1.884 |
Neg logit contributions | |
chery | -1.735 |
xual | -1.722 |
�� | -1.662 |
apper | -1.606 |
urrency | -1.575 |
Token | potato |
Token ID | 21219 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
Nept | +1.151 |
mir | +1.126 |
Reaction | +1.090 |
Boe | +1.065 |
Gret | +1.027 |
Neg logit contributions | |
chery | -1.240 |
xual | -1.211 |
apper | -1.151 |
�� | -1.132 |
urrency | -1.112 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
chery | +0.214 |
xual | +0.207 |
apper | +0.201 |
�� | +0.199 |
urrency | +0.195 |
Neg logit contributions | |
Nept | -0.191 |
mir | -0.188 |
Reaction | -0.182 |
Boe | -0.177 |
Gret | -0.172 |
Token | � |
Token ID | 447 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
chery | +0.180 |
xual | +0.175 |
apper | +0.170 |
�� | +0.166 |
urrency | +0.165 |
Neg logit contributions | |
Nept | -0.164 |
mir | -0.161 |
Reaction | -0.157 |
Boe | -0.153 |
Gret | -0.149 |
Token | � |
Token ID | 251 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
chery | +0.320 |
xual | +0.306 |
apper | +0.298 |
�� | +0.292 |
urrency | +0.286 |
Neg logit contributions | |
Nept | -0.357 |
mir | -0.350 |
Reaction | -0.341 |
Boe | -0.333 |
Gret | -0.324 |
Token | says |
Token ID | 1139 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Nept | +0.580 |
mir | +0.568 |
Reaction | +0.553 |
Boe | +0.541 |
Gret | +0.527 |
Neg logit contributions | |
chery | -0.616 |
xual | -0.594 |
apper | -0.577 |
�� | -0.567 |
urrency | -0.559 |
Token | Wong |
Token ID | 27247 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
chery | +0.654 |
xual | +0.617 |
apper | +0.594 |
�� | +0.574 |
urrency | +0.563 |
Neg logit contributions | |
Nept | -1.149 |
mir | -1.132 |
Reaction | -1.110 |
Boe | -1.089 |
Gret | -1.065 |
Token | . |
Token ID | 13 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
chery | +5.633 |
xual | +5.381 |
apper | +5.298 |
�� | +5.246 |
urrency | +5.075 |
Neg logit contributions | |
Nept | -4.608 |
mir | -4.493 |
Reaction | -4.426 |
Boe | -4.230 |
Gret | -4.083 |
Token | � |
Token ID | 564 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
Nept | +0.087 |
mir | +0.084 |
Reaction | +0.082 |
Boe | +0.080 |
Gret | +0.077 |
Neg logit contributions | |
chery | -0.122 |
xual | -0.118 |
apper | -0.115 |
�� | -0.113 |
urrency | -0.111 |
Token | � |
Token ID | 250 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Nept | +0.068 |
mir | +0.067 |
Reaction | +0.065 |
Boe | +0.064 |
Gret | +0.062 |
Neg logit contributions | |
chery | -0.052 |
xual | -0.049 |
apper | -0.048 |
�� | -0.047 |
urrency | -0.046 |
Token | You |
Token ID | 1639 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
chery | +0.471 |
xual | +0.457 |
apper | +0.443 |
�� | +0.436 |
urrency | +0.430 |
Neg logit contributions | |
Nept | -0.362 |
mir | -0.357 |
Reaction | -0.345 |
Boe | -0.334 |
Gret | -0.324 |
Token | � |
Token ID | 447 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
Nept | +1.049 |
mir | +1.032 |
Reaction | +0.999 |
Boe | +0.965 |
Gret | +0.948 |
Neg logit contributions | |
chery | -1.133 |
xual | -1.105 |
apper | -1.068 |
�� | -1.053 |
urrency | -1.035 |
Token | to |
Token ID | 284 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
chery | +1.316 |
xual | +1.246 |
apper | +1.205 |
�� | +1.173 |
urrency | +1.156 |
Neg logit contributions | |
Nept | -1.565 |
mir | -1.541 |
Reaction | -1.503 |
Boe | -1.469 |
Gret | -1.429 |
Token | hard |
Token ID | 1327 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
chery | +0.185 |
xual | +0.177 |
apper | +0.172 |
�� | +0.170 |
urrency | +0.166 |
Neg logit contributions | |
Nept | -0.192 |
mir | -0.188 |
Reaction | -0.184 |
Boe | -0.179 |
Gret | -0.174 |
Token | en |
Token ID | 268 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Nept | +0.512 |
mir | +0.506 |
Reaction | +0.489 |
Boe | +0.475 |
Gret | +0.454 |
Neg logit contributions | |
chery | -0.738 |
xual | -0.710 |
apper | -0.696 |
�� | -0.686 |
urrency | -0.677 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Nept | +1.064 |
mir | +1.032 |
Reaction | +1.016 |
Boe | +0.988 |
Gret | +0.952 |
Neg logit contributions | |
chery | -1.240 |
xual | -1.190 |
apper | -1.158 |
�� | -1.149 |
urrency | -1.130 |
Token | young |
Token ID | 1862 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
chery | +0.184 |
xual | +0.177 |
apper | +0.171 |
�� | +0.169 |
urrency | +0.166 |
Neg logit contributions | |
Nept | -0.186 |
mir | -0.181 |
Reaction | -0.178 |
Boe | -0.173 |
Gret | -0.168 |
Token | pun |
Token ID | 4000 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
chery | +1.639 |
xual | +1.573 |
apper | +1.532 |
�� | +1.498 |
urrency | +1.477 |
Neg logit contributions | |
Nept | -1.574 |
mir | -1.543 |
Reaction | -1.505 |
Boe | -1.466 |
Gret | -1.423 |
Token | ks |
Token ID | 591 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
chery | +6.322 |
xual | +5.994 |
apper | +5.975 |
urrency | +5.700 |
�� | +5.681 |
Neg logit contributions | |
Nept | -4.106 |
mir | -3.941 |
Reaction | -3.877 |
Boe | -3.716 |
Gret | -3.593 |
Token | ' |
Token ID | 6 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
Nept | +0.222 |
mir | +0.217 |
Reaction | +0.212 |
Boe | +0.206 |
Gret | +0.198 |
Neg logit contributions | |
chery | -0.274 |
xual | -0.262 |
apper | -0.257 |
�� | -0.255 |
urrency | -0.250 |
Token | resolve |
Token ID | 10568 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
Nept | +0.143 |
mir | +0.138 |
Reaction | +0.137 |
Boe | +0.133 |
Gret | +0.128 |
Neg logit contributions | |
chery | -0.149 |
xual | -0.143 |
apper | -0.139 |
�� | -0.138 |
urrency | -0.135 |
Token | ; |
Token ID | 26 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Nept | +1.203 |
mir | +1.182 |
Reaction | +1.148 |
Boe | +1.113 |
Gret | +1.077 |
Neg logit contributions | |
chery | -1.458 |
xual | -1.400 |
apper | -1.376 |
�� | -1.366 |
urrency | -1.333 |
Token | many |
Token ID | 867 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
chery | +1.299 |
xual | +1.248 |
apper | +1.217 |
�� | +1.195 |
urrency | +1.177 |
Neg logit contributions | |
Nept | -1.194 |
mir | -1.167 |
Reaction | -1.140 |
Boe | -1.110 |
Gret | -1.077 |
Token | infections |
Token ID | 16079 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
chery | +0.090 |
xual | +0.087 |
apper | +0.085 |
�� | +0.083 |
urrency | +0.082 |
Neg logit contributions | |
Nept | -0.067 |
mir | -0.065 |
Reaction | -0.064 |
Boe | -0.062 |
Gret | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Nept | +2.025 |
mir | +1.996 |
Reaction | +1.926 |
Boe | +1.884 |
Gret | +1.824 |
Neg logit contributions | |
chery | -2.518 |
xual | -2.421 |
apper | -2.375 |
�� | -2.350 |
urrency | -2.308 |
Token | In |
Token ID | 554 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Nept | +0.157 |
mir | +0.153 |
Reaction | +0.150 |
Boe | +0.145 |
Gret | +0.140 |
Neg logit contributions | |
chery | -0.230 |
xual | -0.223 |
apper | -0.218 |
�� | -0.214 |
urrency | -0.211 |
Token | Saskatchewan |
Token ID | 31346 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
Nept | +0.380 |
mir | +0.371 |
Reaction | +0.360 |
Boe | +0.350 |
Gret | +0.339 |
Neg logit contributions | |
chery | -0.517 |
xual | -0.502 |
apper | -0.489 |
�� | -0.477 |
urrency | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
chery | +0.143 |
xual | +0.138 |
apper | +0.135 |
�� | +0.133 |
urrency | +0.131 |
Neg logit contributions | |
Nept | -0.104 |
mir | -0.102 |
Reaction | -0.099 |
Boe | -0.096 |
Gret | -0.092 |
Token | Wong |
Token ID | 27247 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
chery | +0.236 |
xual | +0.228 |
apper | +0.222 |
�� | +0.218 |
urrency | +0.215 |
Neg logit contributions | |
Nept | -0.216 |
mir | -0.212 |
Reaction | -0.207 |
Boe | -0.202 |
Gret | -0.195 |
Token | is |
Token ID | 318 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
chery | +5.593 |
xual | +5.301 |
apper | +5.210 |
�� | +5.086 |
urrency | +5.030 |
Neg logit contributions | |
Nept | -4.710 |
mir | -4.575 |
Reaction | -4.497 |
Boe | -4.290 |
Gret | -4.156 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Nept | +0.099 |
mir | +0.097 |
Reaction | +0.094 |
Boe | +0.092 |
Gret | +0.090 |
Neg logit contributions | |
chery | -0.097 |
xual | -0.094 |
apper | -0.091 |
�� | -0.089 |
urrency | -0.088 |
Token | by |
Token ID | 416 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Nept | +0.252 |
mir | +0.247 |
Reaction | +0.240 |
Boe | +0.235 |
Gret | +0.228 |
Neg logit contributions | |
chery | -0.275 |
xual | -0.266 |
apper | -0.259 |
�� | -0.254 |
urrency | -0.251 |
Token | policy |
Token ID | 2450 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Nept | +1.193 |
mir | +1.166 |
Reaction | +1.140 |
Boe | +1.119 |
Gret | +1.082 |
Neg logit contributions | |
chery | -1.328 |
xual | -1.292 |
apper | -1.252 |
�� | -1.220 |
urrency | -1.216 |
Token | failures |
Token ID | 15536 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
chery | +0.325 |
xual | +0.313 |
apper | +0.304 |
�� | +0.297 |
urrency | +0.293 |
Neg logit contributions | |
Nept | -0.334 |
mir | -0.328 |
Reaction | -0.320 |
Boe | -0.312 |
Gret | -0.303 |
Token | incor |
Token ID | 5970 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
chery | +0.767 |
xual | +0.742 |
apper | +0.718 |
�� | +0.704 |
urrency | +0.695 |
Neg logit contributions | |
Nept | -0.754 |
mir | -0.740 |
Reaction | -0.723 |
Boe | -0.704 |
Gret | -0.686 |
Token | rupt |
Token ID | 3622 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
chery | +2.306 |
xual | +2.205 |
apper | +2.160 |
�� | +2.096 |
urrency | +2.082 |
Neg logit contributions | |
Nept | -2.123 |
mir | -2.067 |
Reaction | -2.034 |
Boe | -1.978 |
Gret | -1.919 |
Token | ible |
Token ID | 856 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
chery | +0.383 |
xual | +0.363 |
apper | +0.349 |
�� | +0.337 |
urrency | +0.333 |
Neg logit contributions | |
Nept | -0.591 |
mir | -0.582 |
Reaction | -0.570 |
Boe | -0.559 |
Gret | -0.546 |
Token | white |
Token ID | 2330 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
chery | +0.728 |
xual | +0.701 |
apper | +0.679 |
�� | +0.665 |
urrency | +0.658 |
Neg logit contributions | |
Nept | -0.719 |
mir | -0.705 |
Reaction | -0.689 |
Boe | -0.672 |
Gret | -0.654 |
Token | - |
Token ID | 12 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Nept | +0.988 |
mir | +0.982 |
Reaction | +0.947 |
Boe | +0.939 |
Gret | +0.907 |
Neg logit contributions | |
chery | -0.968 |
xual | -0.925 |
apper | -0.902 |
�� | -0.881 |
urrency | -0.877 |
Token | collar |
Token ID | 37676 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
chery | +0.206 |
xual | +0.195 |
apper | +0.188 |
�� | +0.186 |
urrency | +0.181 |
Neg logit contributions | |
Nept | -0.306 |
mir | -0.304 |
Reaction | -0.295 |
Boe | -0.290 |
Gret | -0.283 |
Token | division |
Token ID | 7297 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
chery | +4.864 |
xual | +4.627 |
apper | +4.543 |
�� | +4.359 |
urrency | +4.292 |
Neg logit contributions | |
Nept | -5.341 |
mir | -5.239 |
Reaction | -5.063 |
Boe | -4.963 |
Gret | -4.805 |
Token | has |
Token ID | 468 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Nept | +0.440 |
mir | +0.434 |
Reaction | +0.423 |
Boe | +0.409 |
Gret | +0.402 |
Neg logit contributions | |
chery | -0.461 |
xual | -0.447 |
apper | -0.434 |
�� | -0.428 |
urrency | -0.421 |
Token | leaked |
Token ID | 14109 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
chery | +0.145 |
xual | +0.140 |
apper | +0.136 |
�� | +0.132 |
urrency | +0.131 |
Neg logit contributions | |
Nept | -0.166 |
mir | -0.164 |
Reaction | -0.160 |
Boe | -0.157 |
Gret | -0.153 |
Token | sensitive |
Token ID | 8564 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
chery | +1.903 |
xual | +1.815 |
apper | +1.770 |
�� | +1.723 |
urrency | +1.698 |
Neg logit contributions | |
Nept | -2.074 |
mir | -2.037 |
Reaction | -1.988 |
Boe | -1.939 |
Gret | -1.884 |
Token | details |
Token ID | 3307 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
chery | +0.834 |
xual | +0.794 |
apper | +0.761 |
�� | +0.742 |
urrency | +0.727 |
Neg logit contributions | |
Nept | -1.329 |
mir | -1.307 |
Reaction | -1.282 |
Boe | -1.257 |
Gret | -1.228 |
Token | respect |
Token ID | 2461 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
Nept | +0.108 |
mir | +0.105 |
Reaction | +0.103 |
Boe | +0.101 |
Gret | +0.098 |
Neg logit contributions | |
chery | -0.102 |
xual | -0.098 |
apper | -0.095 |
�� | -0.094 |
urrency | -0.092 |
Token | of |
Token ID | 286 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
chery | +0.142 |
xual | +0.136 |
apper | +0.133 |
�� | +0.131 |
urrency | +0.128 |
Neg logit contributions | |
Nept | -0.130 |
mir | -0.127 |
Reaction | -0.124 |
Boe | -0.120 |
Gret | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
chery | +0.321 |
xual | +0.308 |
apper | +0.300 |
�� | +0.295 |
urrency | +0.290 |
Neg logit contributions | |
Nept | -0.304 |
mir | -0.296 |
Reaction | -0.290 |
Boe | -0.283 |
Gret | -0.274 |
Token | more |
Token ID | 517 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
chery | +0.075 |
xual | +0.072 |
apper | +0.069 |
�� | +0.069 |
urrency | +0.067 |
Neg logit contributions | |
Nept | -0.079 |
mir | -0.076 |
Reaction | -0.075 |
Boe | -0.074 |
Gret | -0.071 |
Token | extreme |
Token ID | 3257 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
chery | +1.569 |
xual | +1.501 |
apper | +1.463 |
�� | +1.424 |
urrency | +1.408 |
Neg logit contributions | |
Nept | -1.550 |
mir | -1.527 |
Reaction | -1.485 |
Boe | -1.448 |
Gret | -1.405 |
Token | pun |
Token ID | 4000 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Nept | +2.549 |
Reaction | +2.445 |
mir | +2.422 |
Boe | +2.370 |
Gret | +2.293 |
Neg logit contributions | |
chery | -2.587 |
xual | -2.457 |
�� | -2.437 |
apper | -2.393 |
urrency | -2.332 |
Token | ks |
Token ID | 591 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
chery | +6.312 |
xual | +5.989 |
apper | +5.951 |
urrency | +5.720 |
�� | +5.685 |
Neg logit contributions | |
Nept | -3.973 |
mir | -3.818 |
Reaction | -3.750 |
Boe | -3.616 |
Gret | -3.476 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Nept | +0.405 |
mir | +0.396 |
Reaction | +0.384 |
Boe | +0.374 |
Gret | +0.362 |
Neg logit contributions | |
chery | -0.542 |
xual | -0.522 |
apper | -0.512 |
�� | -0.510 |
urrency | -0.497 |
Token | return |
Token ID | 1441 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
Nept | +0.183 |
mir | +0.177 |
Reaction | +0.174 |
Boe | +0.169 |
Gret | +0.164 |
Neg logit contributions | |
chery | -0.226 |
xual | -0.218 |
apper | -0.212 |
�� | -0.209 |
urrency | -0.206 |
Token | for |
Token ID | 329 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
Nept | +1.120 |
mir | +1.097 |
Reaction | +1.066 |
Boe | +1.035 |
Gret | +1.001 |
Neg logit contributions | |
chery | -1.412 |
xual | -1.360 |
apper | -1.328 |
�� | -1.302 |
urrency | -1.285 |
Token | having |
Token ID | 1719 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Nept | +1.263 |
mir | +1.217 |
Reaction | +1.201 |
Boe | +1.170 |
Gret | +1.135 |
Neg logit contributions | |
chery | -1.341 |
xual | -1.306 |
�� | -1.274 |
apper | -1.263 |
urrency | -1.226 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Nept | +0.810 |
mir | +0.789 |
Reaction | +0.769 |
Boe | +0.748 |
Gret | +0.732 |
Neg logit contributions | |
chery | -1.118 |
xual | -1.089 |
apper | -1.057 |
�� | -1.048 |
urrency | -1.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
chery | +0.246 |
xual | +0.239 |
apper | +0.232 |
�� | +0.229 |
urrency | +0.226 |
Neg logit contributions | |
Nept | -0.186 |
mir | -0.181 |
Reaction | -0.177 |
Boe | -0.172 |
Gret | -0.167 |
Token | singer |
Token ID | 14015 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
chery | +0.282 |
xual | +0.271 |
apper | +0.263 |
�� | +0.259 |
urrency | +0.255 |
Neg logit contributions | |
Nept | -0.254 |
mir | -0.248 |
Reaction | -0.242 |
Boe | -0.235 |
Gret | -0.229 |
Token | with |
Token ID | 351 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
chery | +2.895 |
xual | +2.761 |
apper | +2.697 |
�� | +2.605 |
urrency | +2.575 |
Neg logit contributions | |
Nept | -3.020 |
mir | -2.967 |
Reaction | -2.898 |
Boe | -2.824 |
Gret | -2.727 |
Token | a |
Token ID | 257 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
chery | +0.038 |
xual | +0.036 |
apper | +0.035 |
�� | +0.035 |
urrency | +0.034 |
Neg logit contributions | |
Nept | -0.035 |
mir | -0.034 |
Reaction | -0.033 |
Boe | -0.032 |
Gret | -0.031 |
Token | bal |
Token ID | 3652 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
chery | +0.217 |
xual | +0.208 |
apper | +0.202 |
�� | +0.198 |
urrency | +0.195 |
Neg logit contributions | |
Nept | -0.215 |
mir | -0.210 |
Reaction | -0.205 |
Boe | -0.200 |
Gret | -0.194 |
Token | acl |
Token ID | 37779 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
chery | +3.817 |
xual | +3.560 |
apper | +3.556 |
urrency | +3.295 |
�� | +3.255 |
Neg logit contributions | |
Nept | -6.329 |
mir | -6.161 |
Reaction | -6.158 |
Boe | -5.990 |
Gret | -5.852 |
Token | ava |
Token ID | 4170 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
chery | +1.012 |
xual | +0.938 |
�� | +0.873 |
apper | +0.841 |
urrency | +0.809 |
Neg logit contributions | |
mir | -2.737 |
Nept | -2.732 |
Reaction | -2.670 |
Boe | -2.618 |
Gret | -2.569 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
chery | +1.340 |
xual | +1.288 |
apper | +1.254 |
�� | +1.233 |
urrency | +1.214 |
Neg logit contributions | |
Nept | -1.214 |
mir | -1.189 |
Reaction | -1.158 |
Boe | -1.128 |
Gret | -1.095 |
Token | a |
Token ID | 257 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Nept | +0.243 |
mir | +0.236 |
Reaction | +0.230 |
Boe | +0.225 |
Gret | +0.220 |
Neg logit contributions | |
chery | -0.264 |
xual | -0.256 |
apper | -0.246 |
�� | -0.244 |
urrency | -0.240 |
Token | cowboy |
Token ID | 42966 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
chery | +0.189 |
xual | +0.182 |
apper | +0.176 |
�� | +0.173 |
urrency | +0.170 |
Neg logit contributions | |
Nept | -0.188 |
mir | -0.184 |
Reaction | -0.179 |
Boe | -0.175 |
Gret | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
chery | +0.425 |
xual | +0.407 |
apper | +0.398 |
�� | +0.390 |
urrency | +0.385 |
Neg logit contributions | |
Nept | -0.377 |
mir | -0.368 |
Reaction | -0.360 |
Boe | -0.350 |
Gret | -0.338 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Nept | +0.219 |
mir | +0.213 |
Reaction | +0.210 |
Boe | +0.203 |
Gret | +0.196 |
Neg logit contributions | |
chery | -0.330 |
xual | -0.321 |
apper | -0.313 |
�� | -0.309 |
urrency | -0.304 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
mir | +0.180 |
Nept | +0.179 |
Reaction | +0.172 |
Boe | +0.167 |
Gret | +0.162 |
Neg logit contributions | |
chery | -0.279 |
xual | -0.278 |
�� | -0.270 |
apper | -0.266 |
urrency | -0.258 |
Token | At |
Token ID | 2953 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
mir | +0.136 |
Nept | +0.134 |
Reaction | +0.129 |
Boe | +0.125 |
Gret | +0.121 |
Neg logit contributions | |
chery | -0.183 |
xual | -0.182 |
apper | -0.173 |
�� | -0.172 |
urrency | -0.169 |
Token | a |
Token ID | 257 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Nept | +0.629 |
mir | +0.617 |
Reaction | +0.603 |
Boe | +0.591 |
Gret | +0.573 |
Neg logit contributions | |
chery | -0.681 |
xual | -0.660 |
apper | -0.634 |
�� | -0.622 |
urrency | -0.614 |
Token | curs |
Token ID | 13882 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
chery | +0.337 |
xual | +0.324 |
apper | +0.313 |
�� | +0.306 |
urrency | +0.302 |
Neg logit contributions | |
Nept | -0.378 |
mir | -0.369 |
Reaction | -0.362 |
Boe | -0.354 |
Gret | -0.344 |
Token | ory |
Token ID | 652 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
chery | +6.492 |
xual | +6.205 |
apper | +6.134 |
urrency | +5.989 |
�� | +5.904 |
Neg logit contributions | |
Nept | -3.720 |
mir | -3.504 |
Reaction | -3.422 |
Boe | -3.247 |
Gret | -3.158 |
Token | glance |
Token ID | 16086 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
chery | +0.421 |
xual | +0.408 |
apper | +0.396 |
�� | +0.391 |
urrency | +0.383 |
Neg logit contributions | |
Nept | -0.381 |
mir | -0.372 |
Reaction | -0.364 |
Boe | -0.355 |
Gret | -0.344 |
Token | , |
Token ID | 11 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
chery | +0.077 |
xual | +0.075 |
apper | +0.073 |
�� | +0.072 |
urrency | +0.071 |
Neg logit contributions | |
Nept | -0.056 |
mir | -0.055 |
Reaction | -0.053 |
Boe | -0.051 |
Gret | -0.050 |
Token | this |
Token ID | 428 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
chery | +0.128 |
xual | +0.124 |
apper | +0.121 |
�� | +0.118 |
urrency | +0.116 |
Neg logit contributions | |
Nept | -0.115 |
mir | -0.113 |
Reaction | -0.110 |
Boe | -0.108 |
Gret | -0.105 |
Token | makes |
Token ID | 1838 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
chery | +0.183 |
xual | +0.176 |
apper | +0.171 |
�� | +0.169 |
urrency | +0.165 |
Neg logit contributions | |
Nept | -0.181 |
mir | -0.178 |
Reaction | -0.174 |
Boe | -0.170 |
Gret | -0.165 |
Token | houses |
Token ID | 7777 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Nept | +0.225 |
mir | +0.218 |
Reaction | +0.209 |
Boe | +0.202 |
Gret | +0.193 |
Neg logit contributions | |
chery | -0.456 |
xual | -0.442 |
apper | -0.434 |
�� | -0.426 |
urrency | -0.422 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
chery | +0.094 |
xual | +0.090 |
apper | +0.088 |
�� | +0.087 |
urrency | +0.086 |
Neg logit contributions | |
Nept | -0.070 |
mir | -0.068 |
Reaction | -0.066 |
Boe | -0.064 |
Gret | -0.062 |
Token | combine |
Token ID | 12082 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
chery | +0.016 |
xual | +0.015 |
apper | +0.015 |
�� | +0.014 |
urrency | +0.014 |
Neg logit contributions | |
Nept | -0.016 |
mir | -0.016 |
Reaction | -0.015 |
Boe | -0.015 |
Gret | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
chery | +0.610 |
xual | +0.585 |
apper | +0.570 |
�� | +0.558 |
urrency | +0.549 |
Neg logit contributions | |
Nept | -0.617 |
mir | -0.605 |
Reaction | -0.591 |
Boe | -0.578 |
Gret | -0.560 |
Token | with |
Token ID | 351 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Nept | +0.638 |
mir | +0.631 |
Reaction | +0.608 |
Boe | +0.597 |
Gret | +0.578 |
Neg logit contributions | |
chery | -0.689 |
xual | -0.666 |
apper | -0.647 |
�� | -0.647 |
urrency | -0.626 |
Token | proportional |
Token ID | 27111 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
Nept | +0.151 |
mir | +0.148 |
Reaction | +0.145 |
Boe | +0.142 |
Gret | +0.137 |
Neg logit contributions | |
chery | -0.151 |
xual | -0.146 |
apper | -0.142 |
�� | -0.138 |
urrency | -0.136 |
Token | representation |
Token ID | 10552 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
chery | +2.182 |
xual | +1.942 |
apper | +1.840 |
�� | +1.793 |
urrency | +1.709 |
Neg logit contributions | |
Nept | -7.847 |
mir | -7.648 |
Reaction | -7.535 |
Boe | -7.393 |
Gret | -7.233 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
chery | +2.495 |
xual | +2.407 |
apper | +2.349 |
�� | +2.301 |
urrency | +2.277 |
Neg logit contributions | |
Nept | -1.824 |
mir | -1.783 |
Reaction | -1.731 |
Boe | -1.676 |
Gret | -1.619 |
Token | a |
Token ID | 257 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
Nept | +0.174 |
mir | +0.170 |
Reaction | +0.167 |
Boe | +0.163 |
Gret | +0.158 |
Neg logit contributions | |
chery | -0.198 |
xual | -0.190 |
apper | -0.185 |
�� | -0.181 |
urrency | -0.179 |
Token | system |
Token ID | 1080 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
Nept | +0.082 |
mir | +0.080 |
Reaction | +0.079 |
Boe | +0.077 |
Gret | +0.074 |
Neg logit contributions | |
chery | -0.093 |
xual | -0.089 |
apper | -0.087 |
�� | -0.085 |
urrency | -0.084 |
Token | known |
Token ID | 1900 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Nept | +1.364 |
mir | +1.344 |
Reaction | +1.310 |
Boe | +1.284 |
Gret | +1.258 |
Neg logit contributions | |
chery | -1.284 |
xual | -1.241 |
apper | -1.203 |
�� | -1.188 |
urrency | -1.148 |
Token | and |
Token ID | 290 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
chery | +0.446 |
xual | +0.431 |
apper | +0.420 |
�� | +0.413 |
urrency | +0.406 |
Neg logit contributions | |
Nept | -0.369 |
mir | -0.360 |
Reaction | -0.351 |
Boe | -0.340 |
Gret | -0.330 |
Token | Atmospheric |
Token ID | 41516 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Nept | +0.600 |
mir | +0.583 |
Reaction | +0.574 |
Boe | +0.556 |
Gret | +0.539 |
Neg logit contributions | |
chery | -0.608 |
xual | -0.590 |
apper | -0.569 |
�� | -0.559 |
urrency | -0.550 |
Token | Sciences |
Token ID | 13473 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
chery | +1.754 |
xual | +1.687 |
apper | +1.664 |
urrency | +1.616 |
�� | +1.614 |
Neg logit contributions | |
Nept | -0.898 |
mir | -0.883 |
Reaction | -0.832 |
Boe | -0.813 |
Gret | -0.774 |
Token | ( |
Token ID | 357 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Nept | +0.396 |
mir | +0.388 |
Reaction | +0.375 |
Boe | +0.364 |
Gret | +0.352 |
Neg logit contributions | |
chery | -0.588 |
xual | -0.570 |
apper | -0.555 |
�� | -0.548 |
urrency | -0.541 |
Token | So |
Token ID | 2396 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
chery | +0.972 |
xual | +0.940 |
apper | +0.916 |
�� | +0.900 |
urrency | +0.889 |
Neg logit contributions | |
Nept | -0.705 |
mir | -0.691 |
Reaction | -0.669 |
Boe | -0.650 |
Gret | -0.628 |
Token | MAS |
Token ID | 31180 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
chery | +0.654 |
xual | +0.632 |
apper | +0.609 |
�� | +0.601 |
urrency | +0.596 |
Neg logit contributions | |
Nept | -0.567 |
mir | -0.561 |
Reaction | -0.542 |
Boe | -0.531 |
Gret | -0.515 |
Token | ). |
Token ID | 737 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
chery | +5.316 |
xual | +5.068 |
apper | +4.934 |
�� | +4.780 |
urrency | +4.704 |
Neg logit contributions | |
Nept | -4.706 |
mir | -4.555 |
Reaction | -4.509 |
Boe | -4.410 |
Gret | -4.220 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
chery | +0.554 |
xual | +0.531 |
apper | +0.521 |
�� | +0.510 |
urrency | +0.504 |
Neg logit contributions | |
Nept | -0.417 |
mir | -0.408 |
Reaction | -0.395 |
Boe | -0.384 |
Gret | -0.370 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
mir | +0.346 |
Nept | +0.344 |
Reaction | +0.332 |
Boe | +0.319 |
Gret | +0.310 |
Neg logit contributions | |
chery | -0.541 |
xual | -0.541 |
�� | -0.523 |
apper | -0.516 |
urrency | -0.502 |
Token | � |
Token ID | 447 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Nept | +0.250 |
mir | +0.247 |
Reaction | +0.237 |
Boe | +0.230 |
Gret | +0.223 |
Neg logit contributions | |
chery | -0.346 |
xual | -0.338 |
apper | -0.325 |
�� | -0.321 |
urrency | -0.317 |
Token | � |
Token ID | 250 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Nept | +0.210 |
mir | +0.206 |
Reaction | +0.201 |
Boe | +0.197 |
Gret | +0.191 |
Neg logit contributions | |
chery | -0.185 |
xual | -0.176 |
apper | -0.171 |
�� | -0.168 |
urrency | -0.165 |
Token | is |
Token ID | 318 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
chery | +1.293 |
xual | +1.242 |
apper | +1.209 |
�� | +1.176 |
urrency | +1.167 |
Neg logit contributions | |
Nept | -1.240 |
mir | -1.214 |
Reaction | -1.186 |
Boe | -1.155 |
Gret | -1.119 |
Token | no |
Token ID | 645 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Nept | +0.014 |
mir | +0.014 |
Reaction | +0.013 |
Boe | +0.013 |
Gret | +0.013 |
Neg logit contributions | |
chery | -0.017 |
xual | -0.016 |
apper | -0.016 |
�� | -0.016 |
urrency | -0.016 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
chery | +0.466 |
xual | +0.447 |
�� | +0.434 |
apper | +0.434 |
urrency | +0.423 |
Neg logit contributions | |
Nept | -0.448 |
mir | -0.436 |
Reaction | -0.428 |
Boe | -0.419 |
Gret | -0.406 |
Token | showing |
Token ID | 4478 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
chery | +0.240 |
xual | +0.229 |
apper | +0.225 |
�� | +0.220 |
urrency | +0.217 |
Neg logit contributions | |
Nept | -0.236 |
mir | -0.231 |
Reaction | -0.225 |
Boe | -0.221 |
Gret | -0.214 |
Token | that |
Token ID | 326 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
chery | +0.436 |
xual | +0.418 |
apper | +0.409 |
�� | +0.402 |
urrency | +0.395 |
Neg logit contributions | |
Nept | -0.405 |
mir | -0.394 |
Reaction | -0.387 |
Boe | -0.378 |
Gret | -0.365 |
Token | pun |
Token ID | 4000 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
Nept | +0.281 |
mir | +0.273 |
Reaction | +0.268 |
Boe | +0.261 |
Gret | +0.252 |
Neg logit contributions | |
chery | -0.320 |
xual | -0.308 |
apper | -0.300 |
�� | -0.298 |
urrency | -0.291 |
Token | ks |
Token ID | 591 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
chery | +6.263 |
xual | +5.953 |
apper | +5.893 |
urrency | +5.691 |
�� | +5.639 |
Neg logit contributions | |
Nept | -3.894 |
mir | -3.739 |
Reaction | -3.661 |
Boe | -3.527 |
Gret | -3.371 |
Token | are |
Token ID | 389 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Nept | +0.185 |
mir | +0.182 |
Reaction | +0.178 |
Boe | +0.174 |
Gret | +0.168 |
Neg logit contributions | |
chery | -0.198 |
xual | -0.191 |
apper | -0.186 |
�� | -0.186 |
urrency | -0.181 |
Token | more |
Token ID | 517 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Nept | +0.869 |
mir | +0.847 |
Reaction | +0.832 |
Boe | +0.817 |
Gret | +0.792 |
Neg logit contributions | |
chery | -0.827 |
xual | -0.801 |
apper | -0.781 |
�� | -0.776 |
urrency | -0.759 |
Token | likely |
Token ID | 1884 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
chery | +1.022 |
xual | +0.981 |
apper | +0.953 |
�� | +0.942 |
urrency | +0.922 |
Neg logit contributions | |
Nept | -1.088 |
mir | -1.063 |
Reaction | -1.043 |
Boe | -1.017 |
Gret | -0.987 |
Token | to |
Token ID | 284 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
Nept | +0.405 |
mir | +0.399 |
Reaction | +0.389 |
Boe | +0.381 |
Gret | +0.371 |
Neg logit contributions | |
chery | -0.323 |
xual | -0.308 |
apper | -0.299 |
�� | -0.291 |
urrency | -0.286 |
Token | is |
Token ID | 318 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
chery | +1.934 |
xual | +1.864 |
apper | +1.814 |
�� | +1.783 |
urrency | +1.756 |
Neg logit contributions | |
Nept | -1.660 |
mir | -1.628 |
Reaction | -1.583 |
Boe | -1.543 |
Gret | -1.494 |
Token | one |
Token ID | 530 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Nept | +0.283 |
mir | +0.277 |
Reaction | +0.271 |
Boe | +0.267 |
Gret | +0.259 |
Neg logit contributions | |
chery | -0.288 |
xual | -0.280 |
apper | -0.267 |
�� | -0.265 |
urrency | -0.260 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Nept | +1.444 |
mir | +1.417 |
Reaction | +1.383 |
Boe | +1.347 |
Gret | +1.310 |
Neg logit contributions | |
chery | -1.361 |
xual | -1.300 |
apper | -1.269 |
�� | -1.238 |
urrency | -1.219 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Nept | +0.143 |
mir | +0.140 |
Reaction | +0.137 |
Boe | +0.133 |
Gret | +0.129 |
Neg logit contributions | |
chery | -0.170 |
xual | -0.165 |
apper | -0.159 |
�� | -0.157 |
urrency | -0.154 |
Token | st |
Token ID | 336 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Nept | +0.174 |
mir | +0.170 |
Reaction | +0.166 |
Boe | +0.162 |
Gret | +0.157 |
Neg logit contributions | |
chery | -0.219 |
xual | -0.212 |
apper | -0.205 |
�� | -0.203 |
urrency | -0.199 |
Token | aun |
Token ID | 1942 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
chery | +0.576 |
xual | +0.545 |
apper | +0.523 |
�� | +0.509 |
urrency | +0.497 |
Neg logit contributions | |
Nept | -0.994 |
mir | -0.980 |
Reaction | -0.960 |
Boe | -0.941 |
Gret | -0.920 |
Token | chest |
Token ID | 46713 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
chery | +5.275 |
xual | +4.907 |
apper | +4.879 |
�� | +4.643 |
urrency | +4.622 |
Neg logit contributions | |
Nept | -4.842 |
mir | -4.687 |
Reaction | -4.646 |
Boe | -4.485 |
Gret | -4.314 |
Token | supporters |
Token ID | 5941 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
chery | +0.932 |
xual | +0.894 |
apper | +0.865 |
�� | +0.850 |
urrency | +0.835 |
Neg logit contributions | |
Nept | -0.946 |
mir | -0.925 |
Reaction | -0.910 |
Boe | -0.887 |
Gret | -0.859 |
Token | of |
Token ID | 286 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
Nept | +0.641 |
mir | +0.628 |
Reaction | +0.613 |
Boe | +0.597 |
Gret | +0.580 |
Neg logit contributions | |
chery | -0.600 |
xual | -0.573 |
apper | -0.559 |
�� | -0.545 |
urrency | -0.537 |
Token | Trump |
Token ID | 1301 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
chery | +0.120 |
xual | +0.115 |
apper | +0.111 |
�� | +0.109 |
urrency | +0.108 |
Neg logit contributions | |
Nept | -0.120 |
mir | -0.118 |
Reaction | -0.115 |
Boe | -0.112 |
Gret | -0.109 |
Token | 's |
Token ID | 338 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
chery | +1.492 |
xual | +1.436 |
apper | +1.403 |
�� | +1.373 |
urrency | +1.357 |
Neg logit contributions | |
Nept | -1.197 |
mir | -1.170 |
Reaction | -1.138 |
Boe | -1.105 |
Gret | -1.069 |
Token | 25 |
Token ID | 1679 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Nept | +0.898 |
mir | +0.875 |
Reaction | +0.850 |
Boe | +0.830 |
Gret | +0.811 |
Neg logit contributions | |
chery | -1.316 |
xual | -1.293 |
apper | -1.258 |
�� | -1.258 |
urrency | -1.239 |
Token | to |
Token ID | 284 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Nept | +0.355 |
mir | +0.348 |
Reaction | +0.338 |
Boe | +0.332 |
Gret | +0.322 |
Neg logit contributions | |
chery | -0.354 |
xual | -0.340 |
apper | -0.330 |
�� | -0.324 |
urrency | -0.319 |
Token | 49 |
Token ID | 5125 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
chery | +0.277 |
xual | +0.275 |
apper | +0.264 |
�� | +0.263 |
urrency | +0.259 |
Neg logit contributions | |
Nept | -0.212 |
mir | -0.206 |
Reaction | -0.200 |
Boe | -0.196 |
Gret | -0.193 |
Token | with |
Token ID | 351 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
chery | +0.103 |
xual | +0.100 |
apper | +0.098 |
�� | +0.096 |
urrency | +0.095 |
Neg logit contributions | |
Nept | -0.080 |
mir | -0.079 |
Reaction | -0.076 |
Boe | -0.074 |
Gret | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Nept | +0.140 |
mir | +0.137 |
Reaction | +0.134 |
Boe | +0.130 |
Gret | +0.127 |
Neg logit contributions | |
chery | -0.153 |
xual | -0.148 |
apper | -0.144 |
�� | -0.141 |
urrency | -0.139 |
Token | bachelor |
Token ID | 29384 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
chery | +0.149 |
xual | +0.143 |
apper | +0.139 |
�� | +0.136 |
urrency | +0.135 |
Neg logit contributions | |
Nept | -0.149 |
mir | -0.145 |
Reaction | -0.143 |
Boe | -0.139 |
Gret | -0.136 |
Token | � |
Token ID | 447 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
chery | +5.562 |
xual | +5.236 |
apper | +5.150 |
�� | +4.993 |
urrency | +4.884 |
Neg logit contributions | |
Nept | -4.477 |
mir | -4.333 |
Reaction | -4.262 |
Boe | -4.122 |
Gret | -3.934 |
Token | � |
Token ID | 247 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Nept | +0.124 |
mir | +0.124 |
Reaction | +0.121 |
Boe | +0.117 |
Gret | +0.113 |
Neg logit contributions | |
chery | -0.139 |
xual | -0.133 |
apper | -0.129 |
�� | -0.125 |
urrency | -0.125 |
Token | s |
Token ID | 82 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
chery | +0.291 |
xual | +0.281 |
apper | +0.273 |
�� | +0.269 |
urrency | +0.265 |
Neg logit contributions | |
Nept | -0.241 |
mir | -0.237 |
Reaction | -0.229 |
Boe | -0.223 |
Gret | -0.217 |
Token | degree |
Token ID | 4922 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Nept | +0.023 |
mir | +0.023 |
Reaction | +0.022 |
Boe | +0.021 |
Gret | +0.020 |
Neg logit contributions | |
chery | -0.034 |
xual | -0.033 |
apper | -0.032 |
�� | -0.031 |
urrency | -0.031 |
Token | or |
Token ID | 393 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
chery | +0.529 |
xual | +0.513 |
apper | +0.501 |
�� | +0.493 |
urrency | +0.486 |
Neg logit contributions | |
Nept | -0.404 |
mir | -0.398 |
Reaction | -0.385 |
Boe | -0.373 |
Gret | -0.362 |
Token | so |
Token ID | 523 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Nept | +0.001 |
mir | +0.001 |
Reaction | +0.001 |
Boe | +0.001 |
Gret | +0.001 |
Neg logit contributions | |
chery | -0.001 |
xual | -0.001 |
apper | -0.001 |
�� | -0.001 |
urrency | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
chery | +2.345 |
xual | +2.221 |
apper | +2.199 |
�� | +2.135 |
urrency | +2.104 |
Neg logit contributions | |
Nept | -2.288 |
mir | -2.240 |
Reaction | -2.203 |
Boe | -2.132 |
Gret | -2.068 |
Token | called |
Token ID | 7174 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
chery | +0.296 |
xual | +0.286 |
�� | +0.282 |
apper | +0.275 |
urrency | +0.268 |
Neg logit contributions | |
mir | -0.250 |
Nept | -0.248 |
Reaction | -0.234 |
Boe | -0.229 |
Gret | -0.221 |
Token | white |
Token ID | 2330 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
chery | +0.216 |
xual | +0.209 |
apper | +0.202 |
�� | +0.199 |
urrency | +0.195 |
Neg logit contributions | |
Nept | -0.206 |
mir | -0.202 |
Reaction | -0.197 |
Boe | -0.191 |
Gret | -0.186 |
Token | - |
Token ID | 12 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Nept | +1.060 |
mir | +1.050 |
Reaction | +1.011 |
Boe | +1.001 |
Gret | +0.970 |
Neg logit contributions | |
chery | -1.038 |
xual | -1.002 |
apper | -0.965 |
�� | -0.950 |
urrency | -0.939 |
Token | collar |
Token ID | 37676 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
chery | +0.156 |
xual | +0.148 |
apper | +0.140 |
�� | +0.139 |
urrency | +0.134 |
Neg logit contributions | |
Nept | -0.286 |
mir | -0.285 |
Reaction | -0.276 |
Boe | -0.272 |
Gret | -0.266 |
Token | jobs |
Token ID | 3946 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
chery | +4.965 |
xual | +4.721 |
apper | +4.601 |
�� | +4.436 |
urrency | +4.411 |
Neg logit contributions | |
Nept | -4.955 |
mir | -4.885 |
Reaction | -4.749 |
Boe | -4.637 |
Gret | -4.488 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
chery | +0.535 |
xual | +0.518 |
apper | +0.505 |
�� | +0.496 |
urrency | +0.488 |
Neg logit contributions | |
Nept | -0.470 |
mir | -0.461 |
Reaction | -0.448 |
Boe | -0.435 |
Gret | -0.424 |
Token | In |
Token ID | 554 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Nept | +0.097 |
mir | +0.094 |
Reaction | +0.093 |
Boe | +0.089 |
Gret | +0.087 |
Neg logit contributions | |
chery | -0.141 |
xual | -0.137 |
apper | -0.133 |
�� | -0.132 |
urrency | -0.130 |
Token | fact |
Token ID | 1109 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Nept | +0.232 |
mir | +0.226 |
Reaction | +0.219 |
Boe | +0.212 |
Gret | +0.206 |
Neg logit contributions | |
chery | -0.335 |
xual | -0.325 |
apper | -0.316 |
�� | -0.310 |
urrency | -0.306 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Nept | +0.434 |
mir | +0.422 |
Reaction | +0.409 |
Boe | +0.394 |
Gret | +0.387 |
Neg logit contributions | |
chery | -0.711 |
xual | -0.699 |
apper | -0.678 |
�� | -0.677 |
urrency | -0.657 |
Token | student |
Token ID | 3710 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
chery | +1.198 |
xual | +1.150 |
apper | +1.097 |
�� | +1.089 |
urrency | +1.068 |
Neg logit contributions | |
Nept | -1.561 |
mir | -1.528 |
Reaction | -1.499 |
Boe | -1.475 |
Gret | -1.439 |
Token | who |
Token ID | 508 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Nept | +0.347 |
mir | +0.342 |
Reaction | +0.333 |
Boe | +0.328 |
Gret | +0.321 |
Neg logit contributions | |
chery | -0.331 |
xual | -0.318 |
apper | -0.309 |
�� | -0.309 |
urrency | -0.300 |
Token | argues |
Token ID | 11673 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Nept | +0.040 |
mir | +0.039 |
Reaction | +0.038 |
Boe | +0.037 |
Gret | +0.036 |
Neg logit contributions | |
chery | -0.039 |
xual | -0.038 |
apper | -0.037 |
�� | -0.037 |
urrency | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Nept | +0.491 |
mir | +0.476 |
Reaction | +0.466 |
Boe | +0.462 |
Gret | +0.450 |
Neg logit contributions | |
chery | -0.512 |
xual | -0.496 |
apper | -0.484 |
�� | -0.475 |
urrency | -0.468 |
Token | was |
Token ID | 373 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Nept | +0.356 |
mir | +0.352 |
Reaction | +0.338 |
Boe | +0.335 |
Gret | +0.324 |
Neg logit contributions | |
chery | -0.410 |
xual | -0.398 |
apper | -0.390 |
�� | -0.384 |
urrency | -0.376 |
Token | completely |
Token ID | 3190 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Nept | +0.321 |
mir | +0.313 |
Reaction | +0.305 |
Boe | +0.303 |
Gret | +0.295 |
Neg logit contributions | |
chery | -0.259 |
xual | -0.249 |
apper | -0.244 |
�� | -0.240 |
urrency | -0.235 |
Token | denied |
Token ID | 6699 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Nept | +2.531 |
mir | +2.503 |
Boe | +2.407 |
Reaction | +2.361 |
Gret | +2.324 |
Neg logit contributions | |
chery | -2.580 |
xual | -2.522 |
apper | -2.493 |
�� | -2.435 |
urrency | -2.396 |
Token | his |
Token ID | 465 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Nept | +1.014 |
mir | +0.982 |
Reaction | +0.966 |
Boe | +0.951 |
Gret | +0.923 |
Neg logit contributions | |
chery | -1.101 |
xual | -1.080 |
apper | -1.052 |
�� | -1.041 |
urrency | -1.013 |
Token | right |
Token ID | 826 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Nept | +0.388 |
mir | +0.377 |
Reaction | +0.372 |
Boe | +0.363 |
Gret | +0.352 |
Neg logit contributions | |
chery | -0.418 |
xual | -0.405 |
apper | -0.393 |
�� | -0.386 |
urrency | -0.378 |
Token | to |
Token ID | 284 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
Nept | +1.167 |
mir | +1.161 |
Reaction | +1.127 |
Boe | +1.103 |
Gret | +1.077 |
Neg logit contributions | |
chery | -1.056 |
xual | -1.010 |
apper | -0.992 |
�� | -0.971 |
urrency | -0.950 |
Token | confront |
Token ID | 7239 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
chery | +0.098 |
xual | +0.094 |
apper | +0.092 |
�� | +0.091 |
urrency | +0.089 |
Neg logit contributions | |
Nept | -0.099 |
mir | -0.097 |
Reaction | -0.095 |
Boe | -0.094 |
Gret | -0.091 |
Token | on |
Token ID | 319 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
chery | +0.829 |
xual | +0.793 |
apper | +0.772 |
�� | +0.754 |
urrency | +0.744 |
Neg logit contributions | |
Nept | -0.864 |
mir | -0.848 |
Reaction | -0.827 |
Boe | -0.807 |
Gret | -0.784 |
Token | Ireland |
Token ID | 7517 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
chery | +0.286 |
xual | +0.277 |
apper | +0.268 |
�� | +0.264 |
urrency | +0.256 |
Neg logit contributions | |
Nept | -0.258 |
mir | -0.253 |
Reaction | -0.247 |
Boe | -0.241 |
Gret | -0.234 |
Token | from |
Token ID | 422 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Nept | +0.626 |
mir | +0.614 |
Reaction | +0.598 |
Boe | +0.575 |
Gret | +0.560 |
Neg logit contributions | |
chery | -0.739 |
xual | -0.715 |
apper | -0.696 |
�� | -0.680 |
urrency | -0.667 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
chery | +0.359 |
xual | +0.348 |
apper | +0.337 |
�� | +0.332 |
urrency | +0.325 |
Neg logit contributions | |
Nept | -0.289 |
mir | -0.283 |
Reaction | -0.277 |
Boe | -0.268 |
Gret | -0.259 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
chery | +0.041 |
xual | +0.040 |
apper | +0.038 |
�� | +0.038 |
urrency | +0.037 |
Neg logit contributions | |
Nept | -0.034 |
mir | -0.034 |
Reaction | -0.033 |
Boe | -0.032 |
Gret | -0.031 |
Token | shock |
Token ID | 6380 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
chery | +0.312 |
xual | +0.298 |
apper | +0.289 |
�� | +0.281 |
urrency | +0.276 |
Neg logit contributions | |
Nept | -0.393 |
mir | -0.387 |
Reaction | -0.379 |
Boe | -0.370 |
Gret | -0.360 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
Nept | +2.115 |
mir | +2.114 |
Reaction | +2.032 |
Boe | +1.962 |
Gret | +1.875 |
Neg logit contributions | |
chery | -2.881 |
xual | -2.800 |
apper | -2.721 |
�� | -2.665 |
urrency | -2.643 |
Token | but |
Token ID | 475 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
chery | +0.029 |
xual | +0.028 |
apper | +0.027 |
�� | +0.027 |
urrency | +0.026 |
Neg logit contributions | |
Nept | -0.026 |
mir | -0.026 |
Reaction | -0.025 |
Boe | -0.025 |
Gret | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
chery | +2.926 |
xual | +2.798 |
apper | +2.736 |
�� | +2.660 |
urrency | +2.642 |
Neg logit contributions | |
Nept | -2.686 |
mir | -2.635 |
Reaction | -2.556 |
Boe | -2.494 |
Gret | -2.417 |
Token | is |
Token ID | 318 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Nept | +0.238 |
mir | +0.236 |
Reaction | +0.229 |
Boe | +0.221 |
Gret | +0.215 |
Neg logit contributions | |
chery | -0.251 |
xual | -0.245 |
apper | -0.236 |
�� | -0.233 |
urrency | -0.227 |
Token | going |
Token ID | 1016 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Nept | +0.151 |
mir | +0.150 |
Reaction | +0.145 |
Boe | +0.141 |
Gret | +0.137 |
Neg logit contributions | |
chery | -0.159 |
xual | -0.155 |
apper | -0.150 |
�� | -0.147 |
urrency | -0.144 |
Token | any |
Token ID | 597 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
chery | +0.036 |
xual | +0.035 |
apper | +0.034 |
�� | +0.033 |
urrency | +0.032 |
Neg logit contributions | |
Nept | -0.034 |
mir | -0.033 |
Reaction | -0.033 |
Boe | -0.032 |
Gret | -0.031 |
Token | remedy |
Token ID | 21210 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Nept | +0.015 |
mir | +0.015 |
Reaction | +0.015 |
Boe | +0.014 |
Gret | +0.014 |
Neg logit contributions | |
chery | -0.015 |
xual | -0.014 |
apper | -0.014 |
�� | -0.014 |
urrency | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Nept | +0.640 |
mir | +0.631 |
Reaction | +0.608 |
Boe | +0.589 |
Gret | +0.571 |
Neg logit contributions | |
chery | -0.881 |
xual | -0.851 |
apper | -0.833 |
�� | -0.819 |
urrency | -0.807 |
Token | In |
Token ID | 554 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Nept | +0.133 |
mir | +0.130 |
Reaction | +0.127 |
Boe | +0.123 |
Gret | +0.119 |
Neg logit contributions | |
chery | -0.194 |
xual | -0.189 |
apper | -0.184 |
�� | -0.181 |
urrency | -0.179 |
Token | a |
Token ID | 257 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
Nept | +0.277 |
mir | +0.270 |
Reaction | +0.263 |
Boe | +0.255 |
Gret | +0.247 |
Neg logit contributions | |
chery | -0.387 |
xual | -0.375 |
apper | -0.365 |
�� | -0.359 |
urrency | -0.355 |
Token | series |
Token ID | 2168 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
chery | +0.062 |
xual | +0.060 |
apper | +0.058 |
�� | +0.057 |
urrency | +0.056 |
Neg logit contributions | |
Nept | -0.050 |
mir | -0.049 |
Reaction | -0.048 |
Boe | -0.046 |
Gret | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
mir | +2.067 |
Nept | +2.046 |
Reaction | +1.962 |
Gret | +1.922 |
Boe | +1.919 |
Neg logit contributions | |
chery | -2.458 |
xual | -2.395 |
�� | -2.304 |
apper | -2.296 |
urrency | -2.248 |
Token | stories |
Token ID | 3923 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
chery | +0.093 |
xual | +0.091 |
apper | +0.087 |
�� | +0.086 |
urrency | +0.084 |
Neg logit contributions | |
Nept | -0.090 |
mir | -0.088 |
Reaction | -0.086 |
Boe | -0.083 |
Gret | -0.081 |
Token | entitled |
Token ID | 9080 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
mir | +0.030 |
Nept | +0.030 |
Reaction | +0.029 |
Boe | +0.028 |
Gret | +0.028 |
Neg logit contributions | |
chery | -0.031 |
xual | -0.030 |
apper | -0.029 |
�� | -0.029 |
urrency | -0.028 |
Token | � |
Token ID | 564 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Nept | +0.770 |
mir | +0.751 |
Reaction | +0.738 |
Boe | +0.709 |
Gret | +0.691 |
Neg logit contributions | |
chery | -1.018 |
xual | -0.984 |
apper | -0.961 |
�� | -0.941 |
urrency | -0.932 |
Token | � |
Token ID | 250 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Nept | +0.238 |
mir | +0.235 |
Reaction | +0.229 |
Boe | +0.224 |
Gret | +0.217 |
Neg logit contributions | |
chery | -0.215 |
xual | -0.206 |
apper | -0.200 |
�� | -0.193 |
urrency | -0.192 |
Token | Named |
Token ID | 34441 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
Nept | +0.022 |
mir | +0.021 |
Reaction | +0.021 |
Boe | +0.020 |
Gret | +0.019 |
Neg logit contributions | |
chery | -0.034 |
xual | -0.033 |
apper | -0.032 |
�� | -0.032 |
urrency | -0.031 |
Token | after |
Token ID | 706 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
chery | +1.345 |
xual | +1.295 |
apper | +1.264 |
�� | +1.239 |
urrency | +1.222 |
Neg logit contributions | |
Nept | -1.098 |
mir | -1.075 |
Reaction | -1.046 |
Boe | -1.016 |
Gret | -0.984 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Nept | +0.137 |
mir | +0.134 |
Reaction | +0.131 |
Boe | +0.127 |
Gret | +0.124 |
Neg logit contributions | |
chery | -0.163 |
xual | -0.157 |
apper | -0.152 |
�� | -0.150 |
urrency | -0.147 |
Token | model |
Token ID | 2746 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
chery | +0.289 |
xual | +0.278 |
apper | +0.270 |
�� | +0.266 |
urrency | +0.261 |
Neg logit contributions | |
Nept | -0.257 |
mir | -0.250 |
Reaction | -0.244 |
Boe | -0.238 |
Gret | -0.232 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Nept | +0.098 |
mir | +0.096 |
Reaction | +0.093 |
Boe | +0.092 |
Gret | +0.089 |
Neg logit contributions | |
chery | -0.093 |
xual | -0.089 |
apper | -0.086 |
�� | -0.086 |
urrency | -0.084 |
Token | Pont |
Token ID | 26345 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
chery | +0.487 |
xual | +0.468 |
apper | +0.455 |
�� | +0.447 |
urrency | +0.439 |
Neg logit contributions | |
Nept | -0.452 |
mir | -0.442 |
Reaction | -0.431 |
Boe | -0.421 |
Gret | -0.409 |
Token | iac |
Token ID | 9607 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Nept | +3.615 |
mir | +3.560 |
Reaction | +3.477 |
Boe | +3.407 |
Gret | +3.273 |
Neg logit contributions | |
chery | -4.111 |
xual | -4.061 |
�� | -3.840 |
apper | -3.740 |
urrency | -3.706 |
Token | GT |
Token ID | 7963 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Nept | +0.272 |
mir | +0.265 |
Reaction | +0.259 |
Boe | +0.251 |
Gret | +0.244 |
Neg logit contributions | |
chery | -0.320 |
xual | -0.307 |
apper | -0.298 |
�� | -0.293 |
urrency | -0.288 |
Token | O |
Token ID | 46 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
Nept | +1.566 |
mir | +1.532 |
Reaction | +1.495 |
Boe | +1.457 |
Gret | +1.416 |
Neg logit contributions | |
chery | -1.795 |
xual | -1.720 |
apper | -1.654 |
�� | -1.645 |
urrency | -1.617 |
Token | sold |
Token ID | 2702 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Nept | +1.144 |
mir | +1.106 |
Reaction | +1.089 |
Boe | +1.058 |
Gret | +1.029 |
Neg logit contributions | |
chery | -1.276 |
xual | -1.219 |
apper | -1.182 |
�� | -1.172 |
urrency | -1.150 |
Token | from |
Token ID | 422 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Nept | +0.806 |
mir | +0.798 |
Reaction | +0.764 |
Boe | +0.760 |
Gret | +0.733 |
Neg logit contributions | |
chery | -0.855 |
xual | -0.832 |
apper | -0.802 |
�� | -0.802 |
urrency | -0.777 |
Token | li |
Token ID | 4528 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
mir | +2.428 |
Nept | +2.372 |
Reaction | +2.301 |
Boe | +2.179 |
Gret | +2.131 |
Neg logit contributions | |
chery | -3.632 |
xual | -3.557 |
�� | -3.471 |
apper | -3.408 |
urrency | -3.347 |
Token | > |
Token ID | 29 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Nept | +0.195 |
mir | +0.193 |
Reaction | +0.185 |
Boe | +0.180 |
Gret | +0.174 |
Neg logit contributions | |
chery | -0.332 |
xual | -0.327 |
�� | -0.318 |
apper | -0.314 |
urrency | -0.310 |
Token | |
Token ID | 7359 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Nept | +0.216 |
mir | +0.211 |
Reaction | +0.202 |
Boe | +0.196 |
Gret | +0.188 |
Neg logit contributions | |
chery | -0.371 |
xual | -0.356 |
apper | -0.351 |
�� | -0.343 |
urrency | -0.340 |
Token | ul |
Token ID | 377 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
mir | +2.270 |
Nept | +2.124 |
Reaction | +2.082 |
Boe | +1.995 |
Gret | +1.946 |
Neg logit contributions | |
chery | -3.681 |
�� | -3.678 |
xual | -3.650 |
apper | -3.466 |
urrency | -3.415 |
Token | > |
Token ID | 29 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
chery | +1.373 |
xual | +1.342 |
apper | +1.303 |
�� | +1.299 |
urrency | +1.271 |
Neg logit contributions | |
Nept | -0.875 |
mir | -0.861 |
Reaction | -0.828 |
Boe | -0.803 |
Gret | -0.774 |
Token | |
Token ID | 7359 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Nept | +0.179 |
mir | +0.174 |
Reaction | +0.167 |
Boe | +0.162 |
Gret | +0.156 |
Neg logit contributions | |
chery | -0.297 |
xual | -0.285 |
apper | -0.282 |
�� | -0.275 |
urrency | -0.273 |
Token | body |
Token ID | 2618 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
mir | +2.228 |
Nept | +2.070 |
Reaction | +2.043 |
Boe | +1.953 |
Gret | +1.888 |
Neg logit contributions | |
xual | -3.722 |
chery | -3.684 |
�� | -3.660 |
apper | -3.473 |
urrency | -3.461 |
Token | > |
Token ID | 29 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
chery | +0.075 |
xual | +0.075 |
�� | +0.073 |
apper | +0.072 |
urrency | +0.071 |
Neg logit contributions | |
Nept | -0.044 |
mir | -0.044 |
Reaction | -0.042 |
Boe | -0.041 |
Gret | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Nept | +0.154 |
mir | +0.150 |
Reaction | +0.145 |
Boe | +0.141 |
Gret | +0.136 |
Neg logit contributions | |
chery | -0.219 |
xual | -0.209 |
apper | -0.207 |
�� | -0.202 |
urrency | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
mir | +0.406 |
Nept | +0.400 |
Reaction | +0.386 |
Boe | +0.373 |
Gret | +0.363 |
Neg logit contributions | |
xual | -0.654 |
chery | -0.649 |
�� | -0.636 |
apper | -0.621 |
urrency | -0.604 |
Token | You |
Token ID | 1639 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
mir | +0.341 |
Nept | +0.336 |
Reaction | +0.323 |
Boe | +0.314 |
Gret | +0.303 |
Neg logit contributions | |
chery | -0.450 |
xual | -0.443 |
apper | -0.422 |
�� | -0.421 |
urrency | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Nept | +1.831 |
mir | +1.815 |
Reaction | +1.753 |
Boe | +1.707 |
Gret | +1.667 |
Neg logit contributions | |
chery | -1.850 |
xual | -1.787 |
apper | -1.764 |
�� | -1.734 |
urrency | -1.717 |
Token | or |
Token ID | 393 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
chery | +0.026 |
xual | +0.025 |
apper | +0.025 |
�� | +0.024 |
urrency | +0.024 |
Neg logit contributions | |
Nept | -0.026 |
mir | -0.026 |
Reaction | -0.025 |
Boe | -0.025 |
Gret | -0.024 |
Token | interior |
Token ID | 11087 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Nept | +1.164 |
mir | +1.144 |
Reaction | +1.111 |
Boe | +1.083 |
Gret | +1.049 |
Neg logit contributions | |
chery | -1.289 |
xual | -1.243 |
apper | -1.215 |
�� | -1.183 |
urrency | -1.174 |
Token | ity |
Token ID | 414 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Nept | +0.416 |
mir | +0.408 |
Reaction | +0.396 |
Boe | +0.388 |
Gret | +0.376 |
Neg logit contributions | |
chery | -0.449 |
xual | -0.432 |
apper | -0.421 |
�� | -0.411 |
urrency | -0.407 |
Token | , |
Token ID | 11 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
Nept | +0.016 |
mir | +0.016 |
Reaction | +0.015 |
Boe | +0.015 |
Gret | +0.014 |
Neg logit contributions | |
chery | -0.020 |
xual | -0.019 |
apper | -0.019 |
�� | -0.018 |
urrency | -0.018 |
Token | become |
Token ID | 1716 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
chery | +0.010 |
xual | +0.010 |
apper | +0.010 |
�� | +0.010 |
urrency | +0.009 |
Neg logit contributions | |
Nept | -0.011 |
mir | -0.010 |
Reaction | -0.010 |
Boe | -0.010 |
Gret | -0.010 |
Token | something |
Token ID | 1223 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Nept | +0.938 |
mir | +0.920 |
Reaction | +0.897 |
Boe | +0.881 |
Gret | +0.854 |
Neg logit contributions | |
chery | -0.974 |
xual | -0.949 |
apper | -0.917 |
�� | -0.901 |
urrency | -0.891 |
Token | heartbreaking |
Token ID | 37154 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
chery | +0.944 |
xual | +0.909 |
apper | +0.883 |
�� | +0.863 |
urrency | +0.853 |
Neg logit contributions | |
Nept | -0.952 |
mir | -0.935 |
Reaction | -0.910 |
Boe | -0.890 |
Gret | -0.864 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Nept | +1.078 |
mir | +1.063 |
Reaction | +1.018 |
Boe | +0.992 |
Gret | +0.967 |
Neg logit contributions | |
chery | -1.341 |
xual | -1.297 |
apper | -1.266 |
�� | -1.246 |
urrency | -1.235 |
Token | universal |
Token ID | 10112 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Nept | +0.208 |
mir | +0.205 |
Reaction | +0.199 |
Boe | +0.194 |
Gret | +0.190 |
Neg logit contributions | |
chery | -0.205 |
xual | -0.198 |
apper | -0.192 |
�� | -0.189 |
urrency | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
chery | +0.343 |
xual | +0.332 |
apper | +0.323 |
�� | +0.318 |
urrency | +0.314 |
Neg logit contributions | |
Nept | -0.261 |
mir | -0.256 |
Reaction | -0.248 |
Boe | -0.241 |
Gret | -0.233 |
Token | We |
Token ID | 775 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
chery | +0.088 |
xual | +0.086 |
apper | +0.084 |
�� | +0.083 |
urrency | +0.081 |
Neg logit contributions | |
Nept | -0.058 |
mir | -0.056 |
Reaction | -0.055 |
Boe | -0.053 |
Gret | -0.051 |
Token | were |
Token ID | 547 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
chery | +1.003 |
xual | +0.969 |
apper | +0.933 |
�� | +0.923 |
urrency | +0.902 |
Neg logit contributions | |
Nept | -1.128 |
mir | -1.103 |
Reaction | -1.079 |
Boe | -1.053 |
Gret | -1.028 |
Token | trying |
Token ID | 2111 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Nept | +0.373 |
mir | +0.365 |
Reaction | +0.359 |
Boe | +0.349 |
Gret | +0.343 |
Neg logit contributions | |
chery | -0.376 |
xual | -0.364 |
apper | -0.353 |
�� | -0.348 |
urrency | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Nept | +0.525 |
mir | +0.515 |
Reaction | +0.505 |
Boe | +0.493 |
Gret | +0.480 |
Neg logit contributions | |
chery | -0.414 |
xual | -0.394 |
apper | -0.383 |
�� | -0.372 |
urrency | -0.366 |
Token | avoid |
Token ID | 3368 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
chery | +0.019 |
xual | +0.018 |
�� | +0.018 |
apper | +0.018 |
urrency | +0.017 |
Neg logit contributions | |
Nept | -0.020 |
mir | -0.019 |
Reaction | -0.019 |
Boe | -0.018 |
Gret | -0.018 |
Token | explaining |
Token ID | 11170 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
chery | +0.159 |
xual | +0.153 |
apper | +0.148 |
�� | +0.145 |
urrency | +0.143 |
Neg logit contributions | |
Nept | -0.153 |
mir | -0.150 |
Reaction | -0.146 |
Boe | -0.142 |
Gret | -0.138 |
Token | things |
Token ID | 1243 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Nept | +0.352 |
mir | +0.341 |
Reaction | +0.336 |
Boe | +0.328 |
Gret | +0.319 |
Neg logit contributions | |
chery | -0.369 |
xual | -0.353 |
apper | -0.345 |
�� | -0.341 |
urrency | -0.333 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
chery | +0.192 |
xual | +0.185 |
apper | +0.180 |
�� | +0.179 |
urrency | +0.174 |
Neg logit contributions | |
Nept | -0.186 |
mir | -0.182 |
Reaction | -0.177 |
Boe | -0.174 |
Gret | -0.169 |
Token | But |
Token ID | 887 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
chery | +0.144 |
xual | +0.140 |
apper | +0.137 |
�� | +0.135 |
urrency | +0.133 |
Neg logit contributions | |
Nept | -0.097 |
mir | -0.094 |
Reaction | -0.092 |
Boe | -0.089 |
Gret | -0.086 |
Token | we |
Token ID | 356 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
chery | +1.863 |
xual | +1.796 |
apper | +1.746 |
�� | +1.719 |
urrency | +1.689 |
Neg logit contributions | |
Nept | -1.741 |
mir | -1.700 |
Reaction | -1.663 |
Boe | -1.619 |
Gret | -1.576 |
Token | still |
Token ID | 991 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
chery | +1.078 |
xual | +1.044 |
apper | +1.006 |
�� | +0.998 |
urrency | +0.971 |
Neg logit contributions | |
Nept | -1.207 |
mir | -1.181 |
Reaction | -1.155 |
Boe | -1.125 |
Gret | -1.101 |
Token | of |
Token ID | 286 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
Nept | +0.517 |
mir | +0.506 |
Reaction | +0.493 |
Boe | +0.480 |
Gret | +0.469 |
Neg logit contributions | |
chery | -0.555 |
xual | -0.538 |
apper | -0.521 |
�� | -0.517 |
urrency | -0.506 |
Token | co |
Token ID | 763 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
chery | +0.014 |
xual | +0.014 |
apper | +0.013 |
�� | +0.013 |
urrency | +0.013 |
Neg logit contributions | |
Nept | -0.011 |
mir | -0.011 |
Reaction | -0.011 |
Boe | -0.010 |
Gret | -0.010 |
Token | - |
Token ID | 12 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
chery | +1.087 |
xual | +1.067 |
�� | +1.031 |
apper | +1.017 |
urrency | +0.989 |
Neg logit contributions | |
Nept | -0.862 |
mir | -0.857 |
Reaction | -0.829 |
Boe | -0.807 |
Gret | -0.777 |
Token | op |
Token ID | 404 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
chery | +0.036 |
xual | +0.036 |
�� | +0.035 |
apper | +0.034 |
urrency | +0.033 |
Neg logit contributions | |
mir | -0.024 |
Nept | -0.024 |
Reaction | -0.023 |
Boe | -0.022 |
Gret | -0.021 |
Token | ( |
Token ID | 357 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
chery | +0.932 |
xual | +0.899 |
apper | +0.877 |
�� | +0.860 |
urrency | +0.849 |
Neg logit contributions | |
Nept | -0.744 |
mir | -0.727 |
Reaction | -0.707 |
Boe | -0.687 |
Gret | -0.665 |
Token | 81 |
Token ID | 6659 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
chery | +0.936 |
xual | +0.904 |
apper | +0.873 |
�� | +0.862 |
urrency | +0.842 |
Neg logit contributions | |
Nept | -0.995 |
mir | -0.986 |
Reaction | -0.958 |
Boe | -0.933 |
Gret | -0.909 |
Token | ) |
Token ID | 8 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
Nept | +0.224 |
mir | +0.221 |
Reaction | +0.212 |
Boe | +0.205 |
Gret | +0.199 |
Neg logit contributions | |
chery | -0.350 |
xual | -0.342 |
�� | -0.332 |
apper | -0.332 |
urrency | -0.324 |
Token |
|
Token ID | 198 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
chery | +1.409 |
xual | +1.338 |
apper | +1.319 |
urrency | +1.279 |
�� | +1.278 |
Neg logit contributions | |
Nept | -1.172 |
mir | -1.144 |
Reaction | -1.104 |
Boe | -1.080 |
Gret | -1.040 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
mir | +0.342 |
Nept | +0.340 |
Reaction | +0.328 |
Boe | +0.316 |
Gret | +0.308 |
Neg logit contributions | |
chery | -0.538 |
xual | -0.537 |
�� | -0.525 |
apper | -0.513 |
urrency | -0.500 |
Token | Never |
Token ID | 12295 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Nept | +0.283 |
mir | +0.280 |
Reaction | +0.270 |
Boe | +0.261 |
Gret | +0.253 |
Neg logit contributions | |
chery | -0.400 |
xual | -0.391 |
apper | -0.378 |
�� | -0.374 |
urrency | -0.368 |
Token | lose |
Token ID | 4425 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
chery | +0.378 |
xual | +0.363 |
apper | +0.353 |
�� | +0.346 |
urrency | +0.341 |
Neg logit contributions | |
Nept | -0.366 |
mir | -0.359 |
Reaction | -0.350 |
Boe | -0.341 |
Gret | -0.331 |
Token | have |
Token ID | 423 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
Nept | +0.545 |
mir | +0.541 |
Reaction | +0.527 |
Boe | +0.509 |
Gret | +0.496 |
Neg logit contributions | |
chery | -0.605 |
xual | -0.588 |
apper | -0.568 |
�� | -0.562 |
urrency | -0.551 |
Token | over |
Token ID | 625 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Nept | +0.111 |
mir | +0.111 |
Reaction | +0.107 |
Boe | +0.105 |
Gret | +0.103 |
Neg logit contributions | |
chery | -0.096 |
xual | -0.093 |
apper | -0.089 |
�� | -0.087 |
urrency | -0.086 |
Token | stated |
Token ID | 21989 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
chery | +0.577 |
xual | +0.558 |
apper | +0.539 |
�� | +0.529 |
urrency | +0.522 |
Neg logit contributions | |
Nept | -0.505 |
mir | -0.499 |
Reaction | -0.484 |
Boe | -0.469 |
Gret | -0.456 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
chery | +1.821 |
xual | +1.753 |
apper | +1.709 |
�� | +1.673 |
urrency | +1.650 |
Neg logit contributions | |
Nept | -1.585 |
mir | -1.554 |
Reaction | -1.512 |
Boe | -1.469 |
Gret | -1.427 |
Token | impact |
Token ID | 2928 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
chery | +0.224 |
xual | +0.215 |
apper | +0.208 |
�� | +0.204 |
urrency | +0.200 |
Neg logit contributions | |
Nept | -0.225 |
mir | -0.221 |
Reaction | -0.216 |
Boe | -0.209 |
Gret | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
chery | +0.777 |
xual | +0.748 |
apper | +0.729 |
�� | +0.711 |
urrency | +0.700 |
Neg logit contributions | |
Nept | -0.755 |
mir | -0.743 |
Reaction | -0.722 |
Boe | -0.703 |
Gret | -0.688 |
Token | But |
Token ID | 887 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
chery | +0.013 |
xual | +0.013 |
apper | +0.012 |
�� | +0.012 |
urrency | +0.012 |
Neg logit contributions | |
Nept | -0.009 |
mir | -0.009 |
Reaction | -0.009 |
Boe | -0.008 |
Gret | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
chery | +2.156 |
xual | +2.075 |
apper | +2.024 |
�� | +1.982 |
urrency | +1.957 |
Neg logit contributions | |
Nept | -1.779 |
mir | -1.741 |
Reaction | -1.693 |
Boe | -1.646 |
Gret | -1.593 |
Token | says |
Token ID | 1139 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Nept | +0.499 |
mir | +0.492 |
Reaction | +0.473 |
Boe | +0.463 |
Gret | +0.450 |
Neg logit contributions | |
chery | -0.589 |
xual | -0.570 |
apper | -0.558 |
�� | -0.551 |
urrency | -0.538 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
chery | +0.667 |
xual | +0.642 |
apper | +0.624 |
�� | +0.611 |
urrency | +0.602 |
Neg logit contributions | |
Nept | -0.645 |
mir | -0.633 |
Reaction | -0.617 |
Boe | -0.600 |
Gret | -0.585 |
Token | Russians |
Token ID | 13234 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
chery | +0.065 |
xual | +0.062 |
apper | +0.060 |
�� | +0.060 |
urrency | +0.058 |
Neg logit contributions | |
Nept | -0.053 |
mir | -0.052 |
Reaction | -0.051 |
Boe | -0.049 |
Gret | -0.048 |
Token | I |
Token ID | 40 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
chery | +0.267 |
xual | +0.261 |
apper | +0.251 |
�� | +0.249 |
urrency | +0.244 |
Neg logit contributions | |
Nept | -0.205 |
mir | -0.203 |
Reaction | -0.196 |
Boe | -0.189 |
Gret | -0.184 |
Token | think |
Token ID | 892 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Nept | +0.120 |
mir | +0.119 |
Reaction | +0.113 |
Boe | +0.110 |
Gret | +0.107 |
Neg logit contributions | |
chery | -0.154 |
xual | -0.150 |
apper | -0.146 |
�� | -0.144 |
urrency | -0.142 |
Token | today |
Token ID | 1909 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Nept | +0.473 |
mir | +0.464 |
Reaction | +0.454 |
Boe | +0.439 |
Gret | +0.429 |
Neg logit contributions | |
chery | -0.496 |
xual | -0.481 |
apper | -0.465 |
�� | -0.460 |
urrency | -0.451 |
Token | the |
Token ID | 262 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
chery | +1.851 |
xual | +1.778 |
apper | +1.735 |
�� | +1.698 |
urrency | +1.677 |
Neg logit contributions | |
Nept | -1.587 |
mir | -1.552 |
Reaction | -1.512 |
Boe | -1.470 |
Gret | -1.424 |
Token | team |
Token ID | 1074 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
chery | +0.104 |
xual | +0.100 |
apper | +0.097 |
�� | +0.095 |
urrency | +0.094 |
Neg logit contributions | |
Nept | -0.098 |
mir | -0.096 |
Reaction | -0.094 |
Boe | -0.091 |
Gret | -0.089 |
Token | has |
Token ID | 468 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Nept | +0.437 |
mir | +0.431 |
Reaction | +0.419 |
Boe | +0.403 |
Gret | +0.395 |
Neg logit contributions | |
chery | -0.470 |
xual | -0.457 |
apper | -0.440 |
�� | -0.437 |
urrency | -0.428 |
Token | found |
Token ID | 1043 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
chery | +0.614 |
xual | +0.591 |
apper | +0.571 |
�� | +0.559 |
urrency | +0.550 |
Neg logit contributions | |
Nept | -0.717 |
mir | -0.704 |
Reaction | -0.689 |
Boe | -0.671 |
Gret | -0.654 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
chery | +0.022 |
xual | +0.021 |
apper | +0.021 |
�� | +0.020 |
urrency | +0.020 |
Neg logit contributions | |
Nept | -0.020 |
mir | -0.019 |
Reaction | -0.019 |
Boe | -0.018 |
Gret | -0.018 |
Token | lot |
Token ID | 1256 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
chery | +0.177 |
xual | +0.171 |
apper | +0.166 |
�� | +0.164 |
urrency | +0.161 |
Neg logit contributions | |
Nept | -0.158 |
mir | -0.155 |
Reaction | -0.151 |
Boe | -0.146 |
Gret | -0.143 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
chery | +0.482 |
xual | +0.468 |
apper | +0.454 |
�� | +0.446 |
urrency | +0.436 |
Neg logit contributions | |
Nept | -0.459 |
mir | -0.453 |
Reaction | -0.440 |
Boe | -0.426 |
Gret | -0.415 |
Token | the |
Token ID | 262 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
chery | +0.202 |
xual | +0.196 |
apper | +0.188 |
�� | +0.186 |
urrency | +0.182 |
Neg logit contributions | |
Nept | -0.204 |
mir | -0.201 |
Reaction | -0.196 |
Boe | -0.190 |
Gret | -0.185 |
Token | from |
Token ID | 422 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Nept | +0.569 |
mir | +0.564 |
Reaction | +0.543 |
Boe | +0.534 |
Gret | +0.518 |
Neg logit contributions | |
chery | -0.681 |
xual | -0.658 |
apper | -0.640 |
�� | -0.632 |
urrency | -0.619 |
Token | all |
Token ID | 477 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
chery | +0.299 |
xual | +0.289 |
apper | +0.280 |
�� | +0.275 |
urrency | +0.272 |
Neg logit contributions | |
Nept | -0.247 |
mir | -0.242 |
Reaction | -0.236 |
Boe | -0.230 |
Gret | -0.223 |
Token | Russia |
Token ID | 3284 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
chery | +0.547 |
xual | +0.527 |
apper | +0.506 |
�� | +0.495 |
urrency | +0.486 |
Neg logit contributions | |
Nept | -0.691 |
mir | -0.680 |
Reaction | -0.665 |
Boe | -0.652 |
Gret | -0.635 |
Token | - |
Token ID | 12 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
chery | +0.267 |
xual | +0.257 |
apper | +0.247 |
�� | +0.239 |
urrency | +0.236 |
Neg logit contributions | |
Nept | -0.334 |
mir | -0.330 |
Reaction | -0.322 |
Boe | -0.315 |
Gret | -0.306 |
Token | related |
Token ID | 5363 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
chery | +0.091 |
xual | +0.089 |
apper | +0.087 |
�� | +0.085 |
urrency | +0.084 |
Neg logit contributions | |
Nept | -0.032 |
mir | -0.032 |
Reaction | -0.030 |
Boe | -0.028 |
Gret | -0.027 |
Token | matters |
Token ID | 6067 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
chery | +1.007 |
xual | +0.960 |
apper | +0.923 |
�� | +0.896 |
urrency | +0.878 |
Neg logit contributions | |
Nept | -1.542 |
mir | -1.517 |
Reaction | -1.488 |
Boe | -1.458 |
Gret | -1.425 |
Token | because |
Token ID | 780 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
chery | +1.619 |
xual | +1.558 |
apper | +1.521 |
�� | +1.491 |
urrency | +1.472 |
Neg logit contributions | |
Nept | -1.280 |
mir | -1.251 |
Reaction | -1.216 |
Boe | -1.181 |
Gret | -1.142 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
chery | +0.807 |
xual | +0.777 |
apper | +0.754 |
�� | +0.739 |
urrency | +0.728 |
Neg logit contributions | |
Nept | -0.756 |
mir | -0.741 |
Reaction | -0.722 |
Boe | -0.705 |
Gret | -0.685 |
Token | the |
Token ID | 262 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
chery | +0.248 |
xual | +0.239 |
apper | +0.231 |
�� | +0.226 |
urrency | +0.222 |
Neg logit contributions | |
Nept | -0.241 |
mir | -0.236 |
Reaction | -0.231 |
Boe | -0.226 |
Gret | -0.220 |
Token | S |
Token ID | 311 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Nept | +0.006 |
mir | +0.006 |
Reaction | +0.006 |
Boe | +0.006 |
Gret | +0.006 |
Neg logit contributions | |
chery | -0.007 |
xual | -0.006 |
apper | -0.006 |
�� | -0.006 |
urrency | -0.006 |
Token | IB |
Token ID | 9865 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
chery | +1.309 |
xual | +1.255 |
apper | +1.220 |
�� | +1.193 |
urrency | +1.175 |
Neg logit contributions | |
Nept | -1.348 |
mir | -1.323 |
Reaction | -1.291 |
Boe | -1.259 |
Gret | -1.223 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
chery | +1.132 |
xual | +1.087 |
apper | +1.061 |
�� | +1.044 |
urrency | +1.028 |
Neg logit contributions | |
Nept | -0.976 |
mir | -0.958 |
Reaction | -0.931 |
Boe | -0.908 |
Gret | -0.881 |
Token | likely |
Token ID | 1884 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
chery | +0.031 |
xual | +0.030 |
�� | +0.029 |
apper | +0.029 |
urrency | +0.028 |
Neg logit contributions | |
Nept | -0.028 |
mir | -0.027 |
Reaction | -0.027 |
Boe | -0.026 |
Gret | -0.026 |
Token | courtesy |
Token ID | 12537 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
chery | +0.275 |
xual | +0.268 |
apper | +0.259 |
�� | +0.259 |
urrency | +0.253 |
Neg logit contributions | |
Nept | -0.251 |
mir | -0.246 |
Reaction | -0.239 |
Boe | -0.234 |
Gret | -0.229 |
Token | of |
Token ID | 286 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
chery | +0.423 |
xual | +0.412 |
apper | +0.396 |
�� | +0.395 |
urrency | +0.386 |
Neg logit contributions | |
Nept | -0.397 |
mir | -0.389 |
Reaction | -0.381 |
Boe | -0.371 |
Gret | -0.364 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
chery | +0.380 |
xual | +0.369 |
apper | +0.357 |
�� | +0.353 |
urrency | +0.348 |
Neg logit contributions | |
Nept | -0.283 |
mir | -0.276 |
Reaction | -0.270 |
Boe | -0.262 |
Gret | -0.253 |
Token | hacker |
Token ID | 23385 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
chery | +0.252 |
xual | +0.245 |
apper | +0.237 |
�� | +0.235 |
urrency | +0.231 |
Neg logit contributions | |
Nept | -0.188 |
mir | -0.183 |
Reaction | -0.179 |
Boe | -0.174 |
Gret | -0.169 |
Token | who |
Token ID | 508 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
chery | +2.466 |
xual | +2.342 |
apper | +2.290 |
�� | +2.217 |
urrency | +2.192 |
Neg logit contributions | |
Nept | -2.593 |
mir | -2.550 |
Reaction | -2.472 |
Boe | -2.423 |
Gret | -2.347 |
Token | refers |
Token ID | 10229 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
chery | +0.446 |
xual | +0.433 |
apper | +0.417 |
�� | +0.411 |
urrency | +0.401 |
Neg logit contributions | |
Nept | -0.478 |
mir | -0.469 |
Reaction | -0.456 |
Boe | -0.447 |
Gret | -0.437 |
Token | to |
Token ID | 284 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
chery | +0.508 |
xual | +0.485 |
apper | +0.470 |
�� | +0.459 |
urrency | +0.448 |
Neg logit contributions | |
Nept | -0.683 |
mir | -0.672 |
Reaction | -0.659 |
Boe | -0.643 |
Gret | -0.623 |
Token | himself |
Token ID | 2241 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
chery | +0.543 |
xual | +0.523 |
apper | +0.510 |
�� | +0.501 |
urrency | +0.494 |
Neg logit contributions | |
Nept | -0.420 |
mir | -0.411 |
Reaction | -0.399 |
Boe | -0.388 |
Gret | -0.376 |
Token | as |
Token ID | 355 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Nept | +0.562 |
mir | +0.551 |
Reaction | +0.536 |
Boe | +0.522 |
Gret | +0.506 |
Neg logit contributions | |
chery | -0.639 |
xual | -0.614 |
apper | -0.599 |
�� | -0.586 |
urrency | -0.579 |
Token | upcoming |
Token ID | 7865 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Nept | +0.201 |
mir | +0.195 |
Reaction | +0.191 |
Boe | +0.185 |
Gret | +0.181 |
Neg logit contributions | |
chery | -0.227 |
xual | -0.220 |
apper | -0.212 |
�� | -0.210 |
urrency | -0.205 |
Token | revival |
Token ID | 26624 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
chery | +1.163 |
xual | +1.121 |
apper | +1.091 |
�� | +1.071 |
urrency | +1.056 |
Neg logit contributions | |
Nept | -0.959 |
mir | -0.937 |
Reaction | -0.912 |
Boe | -0.886 |
Gret | -0.860 |
Token | of |
Token ID | 286 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
chery | +1.081 |
xual | +1.035 |
apper | +1.007 |
�� | +0.985 |
urrency | +0.970 |
Neg logit contributions | |
Nept | -1.106 |
mir | -1.084 |
Reaction | -1.058 |
Boe | -1.032 |
Gret | -1.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
chery | +0.423 |
xual | +0.408 |
apper | +0.398 |
�� | +0.391 |
urrency | +0.386 |
Neg logit contributions | |
Nept | -0.317 |
mir | -0.309 |
Reaction | -0.301 |
Boe | -0.292 |
Gret | -0.283 |
Token | historic |
Token ID | 9566 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
chery | +0.078 |
xual | +0.075 |
apper | +0.073 |
�� | +0.072 |
urrency | +0.071 |
Neg logit contributions | |
Nept | -0.068 |
mir | -0.067 |
Reaction | -0.065 |
Boe | -0.063 |
Gret | -0.062 |
Token | Broadway |
Token ID | 20617 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
chery | +0.410 |
xual | +0.396 |
apper | +0.384 |
�� | +0.378 |
urrency | +0.372 |
Neg logit contributions | |
Nept | -0.357 |
mir | -0.349 |
Reaction | -0.340 |
Boe | -0.331 |
Gret | -0.322 |
Token | musical |
Token ID | 10530 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
chery | +1.873 |
xual | +1.770 |
apper | +1.711 |
�� | +1.659 |
urrency | +1.628 |
Neg logit contributions | |
Nept | -2.957 |
mir | -2.909 |
Reaction | -2.851 |
Boe | -2.796 |
Gret | -2.727 |
Token | has |
Token ID | 468 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
chery | +2.956 |
xual | +2.837 |
apper | +2.758 |
�� | +2.680 |
urrency | +2.661 |
Neg logit contributions | |
Nept | -2.699 |
mir | -2.645 |
Reaction | -2.569 |
Boe | -2.503 |
Gret | -2.414 |
Token | gone |
Token ID | 3750 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
chery | +0.414 |
xual | +0.397 |
apper | +0.386 |
�� | +0.382 |
urrency | +0.371 |
Neg logit contributions | |
Nept | -0.470 |
mir | -0.460 |
Reaction | -0.450 |
Boe | -0.443 |
Gret | -0.431 |
Token | missing |
Token ID | 4814 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Nept | +1.208 |
mir | +1.181 |
Reaction | +1.159 |
Boe | +1.145 |
Gret | +1.108 |
Neg logit contributions | |
chery | -1.142 |
xual | -1.122 |
apper | -1.075 |
�� | -1.072 |
urrency | -1.043 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
chery | +0.884 |
xual | +0.855 |
apper | +0.833 |
�� | +0.821 |
urrency | +0.807 |
Neg logit contributions | |
Nept | -0.694 |
mir | -0.682 |
Reaction | -0.661 |
Boe | -0.644 |
Gret | -0.623 |
Token |
|
Token ID | 198 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
chery | +0.123 |
xual | +0.118 |
apper | +0.116 |
�� | +0.113 |
urrency | +0.112 |
Neg logit contributions | |
Nept | -0.093 |
mir | -0.091 |
Reaction | -0.089 |
Boe | -0.086 |
Gret | -0.083 |
Token | The |
Token ID | 464 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
chery | +0.093 |
xual | +0.091 |
apper | +0.088 |
�� | +0.086 |
urrency | +0.085 |
Neg logit contributions | |
Nept | -0.074 |
mir | -0.073 |
Reaction | -0.071 |
Boe | -0.069 |
Gret | -0.067 |
Token | opinions |
Token ID | 9317 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
Nept | +0.162 |
mir | +0.158 |
Reaction | +0.155 |
Boe | +0.150 |
Gret | +0.145 |
Neg logit contributions | |
chery | -0.186 |
xual | -0.179 |
apper | -0.174 |
�� | -0.171 |
urrency | -0.169 |
Token | expressed |
Token ID | 6241 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
chery | +1.171 |
xual | +1.119 |
apper | +1.084 |
�� | +1.060 |
urrency | +1.043 |
Neg logit contributions | |
Nept | -1.400 |
mir | -1.374 |
Reaction | -1.345 |
Boe | -1.315 |
Gret | -1.281 |
Token | are |
Token ID | 389 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
chery | +0.622 |
xual | +0.598 |
apper | +0.580 |
�� | +0.574 |
urrency | +0.561 |
Neg logit contributions | |
Nept | -0.642 |
mir | -0.625 |
Reaction | -0.614 |
Boe | -0.598 |
Gret | -0.582 |
Token | solely |
Token ID | 9944 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Nept | +0.494 |
mir | +0.481 |
Reaction | +0.473 |
Boe | +0.466 |
Gret | +0.454 |
Neg logit contributions | |
chery | -0.457 |
xual | -0.442 |
apper | -0.425 |
�� | -0.420 |
urrency | -0.415 |
Token | those |
Token ID | 883 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
chery | +1.473 |
xual | +1.416 |
apper | +1.384 |
�� | +1.354 |
urrency | +1.337 |
Neg logit contributions | |
Nept | -1.157 |
mir | -1.135 |
Reaction | -1.102 |
Boe | -1.067 |
Gret | -1.030 |
Token | of |
Token ID | 286 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
chery | +0.224 |
xual | +0.216 |
apper | +0.208 |
�� | +0.206 |
urrency | +0.203 |
Neg logit contributions | |
Nept | -0.216 |
mir | -0.214 |
Reaction | -0.207 |
Boe | -0.203 |
Gret | -0.198 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
chery | +0.510 |
xual | +0.491 |
apper | +0.479 |
�� | +0.469 |
urrency | +0.464 |
Neg logit contributions | |
Nept | -0.423 |
mir | -0.414 |
Reaction | -0.403 |
Boe | -0.392 |
Gret | -0.380 |
Token | author |
Token ID | 1772 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
chery | +0.260 |
xual | +0.248 |
apper | +0.241 |
�� | +0.241 |
urrency | +0.237 |
Neg logit contributions | |
Nept | -0.180 |
mir | -0.173 |
Reaction | -0.170 |
Boe | -0.166 |
Gret | -0.159 |
Token | and |
Token ID | 290 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
Nept | +1.524 |
mir | +1.497 |
Reaction | +1.459 |
Boe | +1.428 |
Gret | +1.379 |
Neg logit contributions | |
chery | -1.849 |
xual | -1.781 |
apper | -1.728 |
�� | -1.705 |
urrency | -1.685 |
Token | Corpor |
Token ID | 8422 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Nept | +0.024 |
mir | +0.023 |
Reaction | +0.023 |
Boe | +0.022 |
Gret | +0.021 |
Neg logit contributions | |
chery | -0.036 |
xual | -0.035 |
apper | -0.034 |
�� | -0.034 |
urrency | -0.033 |
Token | ations |
Token ID | 602 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
chery | +0.381 |
xual | +0.367 |
apper | +0.353 |
�� | +0.349 |
urrency | +0.340 |
Neg logit contributions | |
Nept | -0.379 |
mir | -0.372 |
Reaction | -0.363 |
Boe | -0.354 |
Gret | -0.343 |
Token | deserve |
Token ID | 10925 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
chery | +0.564 |
xual | +0.543 |
apper | +0.528 |
�� | +0.518 |
urrency | +0.510 |
Neg logit contributions | |
Nept | -0.555 |
mir | -0.543 |
Reaction | -0.531 |
Boe | -0.517 |
Gret | -0.502 |
Token | subsidies |
Token ID | 16230 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
chery | +0.949 |
xual | +0.910 |
apper | +0.886 |
�� | +0.867 |
urrency | +0.854 |
Neg logit contributions | |
Nept | -0.940 |
mir | -0.922 |
Reaction | -0.900 |
Boe | -0.877 |
Gret | -0.851 |
Token | , |
Token ID | 11 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
chery | +0.190 |
xual | +0.183 |
apper | +0.179 |
�� | +0.176 |
urrency | +0.173 |
Neg logit contributions | |
Nept | -0.163 |
mir | -0.159 |
Reaction | -0.155 |
Boe | -0.151 |
Gret | -0.146 |
Token | but |
Token ID | 475 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Nept | +0.088 |
mir | +0.086 |
Reaction | +0.085 |
Boe | +0.082 |
Gret | +0.080 |
Neg logit contributions | |
chery | -0.092 |
xual | -0.088 |
apper | -0.086 |
�� | -0.085 |
urrency | -0.083 |
Token | people |
Token ID | 661 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
chery | +2.880 |
xual | +2.752 |
apper | +2.679 |
�� | +2.605 |
urrency | +2.585 |
Neg logit contributions | |
Nept | -2.605 |
mir | -2.569 |
Reaction | -2.485 |
Boe | -2.419 |
Gret | -2.342 |
Token | on |
Token ID | 319 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
chery | +0.850 |
xual | +0.821 |
apper | +0.797 |
�� | +0.787 |
urrency | +0.769 |
Neg logit contributions | |
Nept | -0.886 |
mir | -0.869 |
Reaction | -0.849 |
Boe | -0.828 |
Gret | -0.806 |
Token | welfare |
Token ID | 9490 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
chery | +0.062 |
xual | +0.060 |
apper | +0.058 |
�� | +0.057 |
urrency | +0.056 |
Neg logit contributions | |
Nept | -0.052 |
mir | -0.051 |
Reaction | -0.050 |
Boe | -0.049 |
Gret | -0.047 |
Token | need |
Token ID | 761 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Nept | +0.880 |
mir | +0.868 |
Reaction | +0.843 |
Boe | +0.824 |
Gret | +0.802 |
Neg logit contributions | |
chery | -0.938 |
xual | -0.910 |
apper | -0.884 |
�� | -0.876 |
urrency | -0.858 |
Token | to |
Token ID | 284 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
chery | +1.580 |
xual | +1.516 |
apper | +1.475 |
�� | +1.443 |
urrency | +1.422 |
Neg logit contributions | |
Nept | -1.601 |
mir | -1.570 |
Reaction | -1.532 |
Boe | -1.493 |
Gret | -1.451 |
Token | infections |
Token ID | 16079 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
chery | +0.090 |
xual | +0.087 |
apper | +0.085 |
�� | +0.083 |
urrency | +0.082 |
Neg logit contributions | |
Nept | -0.067 |
mir | -0.065 |
Reaction | -0.064 |
Boe | -0.062 |
Gret | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Nept | +2.025 |
mir | +1.996 |
Reaction | +1.926 |
Boe | +1.884 |
Gret | +1.824 |
Neg logit contributions | |
chery | -2.518 |
xual | -2.421 |
apper | -2.375 |
�� | -2.350 |
urrency | -2.308 |
Token | In |
Token ID | 554 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Nept | +0.157 |
mir | +0.153 |
Reaction | +0.150 |
Boe | +0.145 |
Gret | +0.140 |
Neg logit contributions | |
chery | -0.230 |
xual | -0.223 |
apper | -0.218 |
�� | -0.214 |
urrency | -0.211 |
Token | Saskatchewan |
Token ID | 31346 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
Nept | +0.380 |
mir | +0.371 |
Reaction | +0.360 |
Boe | +0.350 |
Gret | +0.339 |
Neg logit contributions | |
chery | -0.517 |
xual | -0.502 |
apper | -0.489 |
�� | -0.477 |
urrency | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
chery | +0.143 |
xual | +0.138 |
apper | +0.135 |
�� | +0.133 |
urrency | +0.131 |
Neg logit contributions | |
Nept | -0.104 |
mir | -0.102 |
Reaction | -0.099 |
Boe | -0.096 |
Gret | -0.092 |
Token | Wong |
Token ID | 27247 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
chery | +0.236 |
xual | +0.228 |
apper | +0.222 |
�� | +0.218 |
urrency | +0.215 |
Neg logit contributions | |
Nept | -0.216 |
mir | -0.212 |
Reaction | -0.207 |
Boe | -0.202 |
Gret | -0.195 |
Token | is |
Token ID | 318 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
chery | +5.593 |
xual | +5.301 |
apper | +5.210 |
�� | +5.086 |
urrency | +5.030 |
Neg logit contributions | |
Nept | -4.710 |
mir | -4.575 |
Reaction | -4.497 |
Boe | -4.290 |
Gret | -4.156 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Nept | +0.099 |
mir | +0.097 |
Reaction | +0.094 |
Boe | +0.092 |
Gret | +0.090 |
Neg logit contributions | |
chery | -0.097 |
xual | -0.094 |
apper | -0.091 |
�� | -0.089 |
urrency | -0.088 |
Token | by |
Token ID | 416 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Nept | +0.252 |
mir | +0.247 |
Reaction | +0.240 |
Boe | +0.235 |
Gret | +0.228 |
Neg logit contributions | |
chery | -0.275 |
xual | -0.266 |
apper | -0.259 |
�� | -0.254 |
urrency | -0.251 |
Token | policy |
Token ID | 2450 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Nept | +1.193 |
mir | +1.166 |
Reaction | +1.140 |
Boe | +1.119 |
Gret | +1.082 |
Neg logit contributions | |
chery | -1.328 |
xual | -1.292 |
apper | -1.252 |
�� | -1.220 |
urrency | -1.216 |
Token | failures |
Token ID | 15536 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
chery | +0.325 |
xual | +0.313 |
apper | +0.304 |
�� | +0.297 |
urrency | +0.293 |
Neg logit contributions | |
Nept | -0.334 |
mir | -0.328 |
Reaction | -0.320 |
Boe | -0.312 |
Gret | -0.303 |
Token | find |
Token ID | 1064 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
chery | +0.026 |
xual | +0.025 |
apper | +0.024 |
�� | +0.024 |
urrency | +0.023 |
Neg logit contributions | |
Nept | -0.021 |
mir | -0.020 |
Reaction | -0.020 |
Boe | -0.020 |
Gret | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
chery | +0.534 |
xual | +0.516 |
apper | +0.499 |
�� | +0.490 |
urrency | +0.484 |
Neg logit contributions | |
Nept | -0.451 |
mir | -0.441 |
Reaction | -0.430 |
Boe | -0.419 |
Gret | -0.406 |
Token | email |
Token ID | 3053 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
chery | +0.314 |
xual | +0.302 |
apper | +0.291 |
�� | +0.288 |
urrency | +0.280 |
Neg logit contributions | |
Nept | -0.300 |
mir | -0.292 |
Reaction | -0.286 |
Boe | -0.280 |
Gret | -0.271 |
Token | of |
Token ID | 286 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
chery | +0.517 |
xual | +0.499 |
apper | +0.486 |
�� | +0.480 |
urrency | +0.472 |
Neg logit contributions | |
Nept | -0.420 |
mir | -0.411 |
Reaction | -0.400 |
Boe | -0.390 |
Gret | -0.377 |
Token | a |
Token ID | 257 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
chery | +0.609 |
xual | +0.587 |
apper | +0.569 |
�� | +0.561 |
urrency | +0.552 |
Neg logit contributions | |
Nept | -0.526 |
mir | -0.513 |
Reaction | -0.502 |
Boe | -0.491 |
Gret | -0.473 |
Token | recru |
Token ID | 8921 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
chery | +0.494 |
xual | +0.475 |
apper | +0.459 |
�� | +0.455 |
urrency | +0.446 |
Neg logit contributions | |
Nept | -0.495 |
mir | -0.482 |
Reaction | -0.473 |
Boe | -0.464 |
Gret | -0.448 |
Token | iter |
Token ID | 2676 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
chery | +4.582 |
xual | +4.362 |
apper | +4.352 |
urrency | +4.101 |
�� | +4.063 |
Neg logit contributions | |
Nept | -4.742 |
mir | -4.584 |
Reaction | -4.526 |
Boe | -4.394 |
Gret | -4.254 |
Token | and |
Token ID | 290 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
Nept | +0.144 |
mir | +0.142 |
Reaction | +0.138 |
Boe | +0.135 |
Gret | +0.131 |
Neg logit contributions | |
chery | -0.159 |
xual | -0.154 |
apper | -0.149 |
�� | -0.148 |
urrency | -0.145 |
Token | send |
Token ID | 3758 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
Nept | +0.105 |
mir | +0.103 |
Reaction | +0.101 |
Boe | +0.099 |
Gret | +0.096 |
Neg logit contributions | |
chery | -0.103 |
xual | -0.100 |
apper | -0.096 |
�� | -0.095 |
urrency | -0.093 |
Token | them |
Token ID | 606 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
Nept | +0.099 |
mir | +0.097 |
Reaction | +0.094 |
Boe | +0.092 |
Gret | +0.089 |
Neg logit contributions | |
chery | -0.128 |
xual | -0.124 |
apper | -0.120 |
�� | -0.118 |
urrency | -0.117 |
Token | a |
Token ID | 257 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
chery | +0.131 |
xual | +0.127 |
apper | +0.123 |
�� | +0.121 |
urrency | +0.119 |
Neg logit contributions | |
Nept | -0.112 |
mir | -0.108 |
Reaction | -0.106 |
Boe | -0.103 |
Gret | -0.100 |
Token | deemed |
Token ID | 10762 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Nept | +0.313 |
mir | +0.306 |
Reaction | +0.299 |
Boe | +0.291 |
Gret | +0.285 |
Neg logit contributions | |
chery | -0.274 |
xual | -0.264 |
apper | -0.255 |
�� | -0.251 |
urrency | -0.247 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
chery | +0.503 |
xual | +0.485 |
apper | +0.471 |
�� | +0.462 |
urrency | +0.454 |
Neg logit contributions | |
Nept | -0.506 |
mir | -0.494 |
Reaction | -0.482 |
Boe | -0.469 |
Gret | -0.458 |
Token | be |
Token ID | 307 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Nept | +0.210 |
mir | +0.206 |
Reaction | +0.200 |
Boe | +0.195 |
Gret | +0.190 |
Neg logit contributions | |
chery | -0.222 |
xual | -0.214 |
apper | -0.208 |
�� | -0.204 |
urrency | -0.201 |
Token | white |
Token ID | 2330 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
chery | +0.433 |
xual | +0.419 |
apper | +0.406 |
�� | +0.399 |
urrency | +0.391 |
Neg logit contributions | |
Nept | -0.434 |
mir | -0.424 |
Reaction | -0.414 |
Boe | -0.403 |
Gret | -0.394 |
Token | - |
Token ID | 12 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Nept | +1.312 |
mir | +1.285 |
Reaction | +1.243 |
Boe | +1.217 |
Gret | +1.182 |
Neg logit contributions | |
chery | -1.467 |
xual | -1.416 |
apper | -1.381 |
�� | -1.354 |
urrency | -1.332 |
Token | collar |
Token ID | 37676 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
mir | +0.358 |
Nept | +0.355 |
Reaction | +0.341 |
Boe | +0.335 |
Gret | +0.328 |
Neg logit contributions | |
chery | -0.209 |
xual | -0.203 |
�� | -0.196 |
apper | -0.192 |
urrency | -0.182 |
Token | jobs |
Token ID | 3946 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
chery | +5.279 |
xual | +5.094 |
apper | +4.920 |
�� | +4.796 |
urrency | +4.747 |
Neg logit contributions | |
Nept | -4.251 |
mir | -4.189 |
Reaction | -4.088 |
Boe | -3.986 |
Gret | -3.825 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
chery | +0.220 |
xual | +0.213 |
apper | +0.208 |
�� | +0.205 |
urrency | +0.202 |
Neg logit contributions | |
Nept | -0.149 |
mir | -0.146 |
Reaction | -0.141 |
Boe | -0.136 |
Gret | -0.132 |
Token | for |
Token ID | 329 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
Nept | +0.195 |
mir | +0.191 |
Reaction | +0.186 |
Boe | +0.181 |
Gret | +0.177 |
Neg logit contributions | |
chery | -0.199 |
xual | -0.193 |
�� | -0.186 |
apper | -0.186 |
urrency | -0.182 |
Token | example |
Token ID | 1672 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Nept | +0.558 |
mir | +0.525 |
Reaction | +0.499 |
Boe | +0.476 |
Gret | +0.448 |
Neg logit contributions | |
chery | -1.891 |
xual | -1.850 |
apper | -1.821 |
�� | -1.800 |
urrency | -1.780 |
Token | , |
Token ID | 11 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
Nept | +2.761 |
mir | +2.660 |
Reaction | +2.600 |
Boe | +2.563 |
Gret | +2.489 |
Neg logit contributions | |
xual | -3.079 |
chery | -3.066 |
�� | -2.956 |
apper | -2.923 |
urrency | -2.871 |
Token | so |
Token ID | 523 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
chery | +0.081 |
xual | +0.078 |
apper | +0.075 |
�� | +0.074 |
urrency | +0.073 |
Neg logit contributions | |
Nept | -0.073 |
mir | -0.071 |
Reaction | -0.069 |
Boe | -0.068 |
Gret | -0.066 |
Token | - |
Token ID | 12 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
chery | +2.332 |
xual | +2.275 |
apper | +2.192 |
�� | +2.179 |
urrency | +2.133 |
Neg logit contributions | |
Nept | -1.936 |
mir | -1.901 |
Reaction | -1.838 |
Boe | -1.799 |
Gret | -1.742 |
Token | called |
Token ID | 7174 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
chery | +0.086 |
xual | +0.084 |
�� | +0.082 |
apper | +0.081 |
urrency | +0.078 |
Neg logit contributions | |
mir | -0.073 |
Nept | -0.072 |
Reaction | -0.069 |
Boe | -0.067 |
Gret | -0.065 |
Token | white |
Token ID | 2330 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
chery | +0.184 |
xual | +0.179 |
apper | +0.174 |
�� | +0.171 |
urrency | +0.169 |
Neg logit contributions | |
Nept | -0.133 |
mir | -0.130 |
Reaction | -0.126 |
Boe | -0.122 |
Gret | -0.118 |
Token | - |
Token ID | 12 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Nept | +1.343 |
mir | +1.316 |
Reaction | +1.281 |
Boe | +1.249 |
Gret | +1.212 |
Neg logit contributions | |
chery | -1.440 |
xual | -1.385 |
apper | -1.348 |
�� | -1.319 |
urrency | -1.301 |
Token | collar |
Token ID | 37676 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
mir | +0.040 |
Nept | +0.039 |
Reaction | +0.038 |
Boe | +0.037 |
Gret | +0.036 |
Neg logit contributions | |
chery | -0.023 |
xual | -0.022 |
�� | -0.022 |
apper | -0.021 |
urrency | -0.020 |
Token | jobs |
Token ID | 3946 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
chery | +4.032 |
xual | +3.783 |
apper | +3.695 |
�� | +3.553 |
urrency | +3.523 |
Neg logit contributions | |
Nept | -5.154 |
mir | -5.074 |
Reaction | -4.972 |
Boe | -4.850 |
Gret | -4.724 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
chery | +0.356 |
xual | +0.344 |
apper | +0.335 |
�� | +0.329 |
urrency | +0.324 |
Neg logit contributions | |
Nept | -0.306 |
mir | -0.301 |
Reaction | -0.292 |
Boe | -0.284 |
Gret | -0.276 |
Token | while |
Token ID | 981 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Nept | +0.031 |
mir | +0.030 |
Reaction | +0.030 |
Boe | +0.029 |
Gret | +0.028 |
Neg logit contributions | |
chery | -0.035 |
xual | -0.034 |
�� | -0.033 |
apper | -0.033 |
urrency | -0.032 |
Token | jobs |
Token ID | 3946 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Nept | +0.484 |
mir | +0.468 |
Reaction | +0.457 |
Boe | +0.446 |
Gret | +0.439 |
Neg logit contributions | |
chery | -0.572 |
xual | -0.557 |
�� | -0.541 |
apper | -0.541 |
urrency | -0.526 |
Token | like |
Token ID | 588 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
chery | +0.336 |
xual | +0.325 |
apper | +0.316 |
�� | +0.312 |
urrency | +0.307 |
Neg logit contributions | |
Nept | -0.347 |
mir | -0.342 |
Reaction | -0.332 |
Boe | -0.323 |
Gret | -0.316 |
Token | incor |
Token ID | 5970 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
chery | +0.767 |
xual | +0.742 |
apper | +0.718 |
�� | +0.704 |
urrency | +0.695 |
Neg logit contributions | |
Nept | -0.754 |
mir | -0.740 |
Reaction | -0.723 |
Boe | -0.704 |
Gret | -0.686 |
Token | rupt |
Token ID | 3622 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
chery | +2.306 |
xual | +2.205 |
apper | +2.160 |
�� | +2.096 |
urrency | +2.082 |
Neg logit contributions | |
Nept | -2.123 |
mir | -2.067 |
Reaction | -2.034 |
Boe | -1.978 |
Gret | -1.919 |
Token | ible |
Token ID | 856 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
chery | +0.383 |
xual | +0.363 |
apper | +0.349 |
�� | +0.337 |
urrency | +0.333 |
Neg logit contributions | |
Nept | -0.591 |
mir | -0.582 |
Reaction | -0.570 |
Boe | -0.559 |
Gret | -0.546 |
Token | white |
Token ID | 2330 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
chery | +0.728 |
xual | +0.701 |
apper | +0.679 |
�� | +0.665 |
urrency | +0.658 |
Neg logit contributions | |
Nept | -0.719 |
mir | -0.705 |
Reaction | -0.689 |
Boe | -0.672 |
Gret | -0.654 |
Token | - |
Token ID | 12 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Nept | +0.988 |
mir | +0.982 |
Reaction | +0.947 |
Boe | +0.939 |
Gret | +0.907 |
Neg logit contributions | |
chery | -0.968 |
xual | -0.925 |
apper | -0.902 |
�� | -0.881 |
urrency | -0.877 |
Token | collar |
Token ID | 37676 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
chery | +0.206 |
xual | +0.195 |
apper | +0.188 |
�� | +0.186 |
urrency | +0.181 |
Neg logit contributions | |
Nept | -0.306 |
mir | -0.304 |
Reaction | -0.295 |
Boe | -0.290 |
Gret | -0.283 |
Token | division |
Token ID | 7297 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
chery | +4.864 |
xual | +4.627 |
apper | +4.543 |
�� | +4.359 |
urrency | +4.292 |
Neg logit contributions | |
Nept | -5.341 |
mir | -5.239 |
Reaction | -5.063 |
Boe | -4.963 |
Gret | -4.805 |
Token | has |
Token ID | 468 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Nept | +0.440 |
mir | +0.434 |
Reaction | +0.423 |
Boe | +0.409 |
Gret | +0.402 |
Neg logit contributions | |
chery | -0.461 |
xual | -0.447 |
apper | -0.434 |
�� | -0.428 |
urrency | -0.421 |
Token | leaked |
Token ID | 14109 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
chery | +0.145 |
xual | +0.140 |
apper | +0.136 |
�� | +0.132 |
urrency | +0.131 |
Neg logit contributions | |
Nept | -0.166 |
mir | -0.164 |
Reaction | -0.160 |
Boe | -0.157 |
Gret | -0.153 |
Token | sensitive |
Token ID | 8564 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
chery | +1.903 |
xual | +1.815 |
apper | +1.770 |
�� | +1.723 |
urrency | +1.698 |
Neg logit contributions | |
Nept | -2.074 |
mir | -2.037 |
Reaction | -1.988 |
Boe | -1.939 |
Gret | -1.884 |
Token | details |
Token ID | 3307 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
chery | +0.834 |
xual | +0.794 |
apper | +0.761 |
�� | +0.742 |
urrency | +0.727 |
Neg logit contributions | |
Nept | -1.329 |
mir | -1.307 |
Reaction | -1.282 |
Boe | -1.257 |
Gret | -1.228 |