Token | � |
Token ID | 247 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ado | +1.942 |
ャ | +1.893 |
asted | +1.746 |
asting | +1.722 |
ality | +1.677 |
Neg logit contributions | |
hen | -2.286 |
ource | -2.284 |
lime | -2.219 |
IFT | -2.173 |
RIP | -2.170 |
Token | s |
Token ID | 82 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ado | +1.426 |
ャ | +1.379 |
asting | +1.335 |
asted | +1.333 |
ality | +1.303 |
Neg logit contributions | |
ource | -1.299 |
hen | -1.270 |
IFT | -1.259 |
lime | -1.255 |
RIP | -1.244 |
Token | little |
Token ID | 1310 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ado | +0.817 |
ャ | +0.813 |
asting | +0.744 |
asted | +0.741 |
ality | +0.735 |
Neg logit contributions | |
hen | -0.975 |
ource | -0.955 |
lime | -0.940 |
RIP | -0.934 |
IFT | -0.933 |
Token | change |
Token ID | 1487 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ado | +1.465 |
ャ | +1.402 |
ality | +1.295 |
asting | +1.293 |
asted | +1.281 |
Neg logit contributions | |
hen | -1.901 |
ource | -1.860 |
IFT | -1.823 |
lime | -1.816 |
RIP | -1.812 |
Token | in |
Token ID | 287 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
hen | +0.879 |
ource | +0.852 |
lime | +0.839 |
IFT | +0.835 |
RIP | +0.831 |
Neg logit contributions | |
ado | -0.648 |
ャ | -0.640 |
asting | -0.586 |
asted | -0.582 |
ality | -0.577 |
Token | ton |
Token ID | 5680 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ado | +0.169 |
ャ | +0.166 |
asting | +0.154 |
asted | +0.152 |
ality | +0.150 |
Neg logit contributions | |
hen | -0.217 |
ource | -0.212 |
lime | -0.209 |
RIP | -0.207 |
IFT | -0.206 |
Token | al |
Token ID | 282 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ality | +9.946 |
ado | +8.165 |
asting | +8.081 |
ャ | +7.970 |
asted | +7.683 |
Neg logit contributions | |
RIP | -14.305 |
ource | -14.239 |
cius | -13.774 |
hen | -13.577 |
IFT | -13.531 |
Token | / |
Token ID | 14 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ado | +0.843 |
ャ | +0.829 |
asting | +0.757 |
ality | +0.753 |
asted | +0.745 |
Neg logit contributions | |
hen | -1.368 |
ource | -1.350 |
lime | -1.325 |
RIP | -1.308 |
IFT | -1.300 |
Token | spect |
Token ID | 4443 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
hen | +0.037 |
ource | +0.037 |
IFT | +0.036 |
lime | +0.036 |
RIP | +0.035 |
Neg logit contributions | |
ャ | -0.042 |
ado | -0.041 |
asting | -0.039 |
asted | -0.039 |
ality | -0.039 |
Token | ral |
Token ID | 1373 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
hen | +0.345 |
ource | +0.338 |
IFT | +0.333 |
lime | +0.329 |
RIP | +0.326 |
Neg logit contributions | |
ado | -0.362 |
ャ | -0.356 |
asting | -0.338 |
ality | -0.336 |
asted | -0.332 |
Token | response |
Token ID | 2882 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
hen | +2.301 |
ource | +2.228 |
lime | +2.191 |
IFT | +2.178 |
ordinary | +2.163 |
Neg logit contributions | |
ado | -1.527 |
ャ | -1.510 |
asting | -1.370 |
asted | -1.364 |
ality | -1.328 |
Token | , |
Token ID | 11 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ado | +2.157 |
ャ | +2.121 |
ality | +1.858 |
asting | +1.857 |
asted | +1.835 |
Neg logit contributions | |
hen | -3.696 |
ource | -3.597 |
RIP | -3.550 |
lime | -3.543 |
IFT | -3.535 |
Token | the |
Token ID | 262 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
ado | +1.188 |
ャ | +1.166 |
asting | +1.074 |
asted | +1.061 |
ality | +1.054 |
Neg logit contributions | |
hen | -1.454 |
ource | -1.421 |
lime | -1.401 |
RIP | -1.386 |
IFT | -1.385 |
Token | pian |
Token ID | 43923 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ado | +1.981 |
ャ | +1.925 |
asting | +1.775 |
asted | +1.755 |
ality | +1.746 |
Neg logit contributions | |
hen | -2.637 |
ource | -2.594 |
lime | -2.547 |
IFT | -2.525 |
RIP | -2.515 |
Token | ist |
Token ID | 396 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ado | +2.156 |
asted | +2.131 |
asting | +2.128 |
ality | +2.064 |
ャ | +2.041 |
Neg logit contributions | |
hen | -3.883 |
RIP | -3.836 |
IFT | -3.826 |
ource | -3.810 |
lime | -3.740 |
Token | 's |
Token ID | 338 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ado | +2.510 |
ャ | +2.505 |
ality | +2.230 |
asting | +2.209 |
asted | +2.148 |
Neg logit contributions | |
hen | -3.841 |
ource | -3.778 |
RIP | -3.760 |
IFT | -3.743 |
lime | -3.740 |
Token | disagreement |
Token ID | 25800 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ado | +5.129 |
ャ | +4.849 |
ality | +4.377 |
asting | +4.345 |
asted | +4.242 |
Neg logit contributions | |
hen | -6.901 |
ource | -6.749 |
lime | -6.727 |
RIP | -6.726 |
cius | -6.674 |
Token | with |
Token ID | 351 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ado | +7.019 |
ャ | +6.905 |
ality | +6.672 |
asted | +5.960 |
asting | +5.908 |
Neg logit contributions | |
RIP | -12.523 |
ource | -12.341 |
IFT | -12.244 |
hen | -12.194 |
ordinary | -11.962 |
Token | � |
Token ID | 564 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ado | +4.592 |
ャ | +4.507 |
asting | +4.138 |
asted | +4.069 |
ality | +4.032 |
Neg logit contributions | |
hen | -6.409 |
ource | -6.384 |
RIP | -6.274 |
lime | -6.251 |
IFT | -6.240 |
Token | � |
Token ID | 250 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
hen | +0.796 |
ource | +0.765 |
lime | +0.747 |
IFT | +0.740 |
ordinary | +0.733 |
Neg logit contributions | |
ado | -0.931 |
ャ | -0.925 |
asting | -0.860 |
asted | -0.857 |
ality | -0.842 |
Token | This |
Token ID | 1212 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ado | +0.795 |
ャ | +0.795 |
asting | +0.742 |
asted | +0.740 |
ality | +0.725 |
Neg logit contributions | |
hen | -0.776 |
ource | -0.763 |
IFT | -0.739 |
lime | -0.738 |
RIP | -0.729 |
Token | version |
Token ID | 2196 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ado | +2.009 |
ャ | +1.969 |
asted | +1.778 |
asting | +1.778 |
ality | +1.769 |
Neg logit contributions | |
hen | -2.717 |
ource | -2.673 |
RIP | -2.621 |
IFT | -2.615 |
lime | -2.600 |
Token | The |
Token ID | 383 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ado | +0.993 |
ャ | +0.989 |
asting | +0.894 |
asted | +0.882 |
ality | +0.882 |
Neg logit contributions | |
hen | -1.271 |
ource | -1.246 |
lime | -1.229 |
IFT | -1.215 |
cius | -1.214 |
Token | sax |
Token ID | 46909 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ado | +1.168 |
ャ | +1.139 |
asting | +1.045 |
asted | +1.036 |
ality | +1.034 |
Neg logit contributions | |
hen | -1.525 |
ource | -1.490 |
lime | -1.466 |
IFT | -1.452 |
RIP | -1.448 |
Token | ophon |
Token ID | 48982 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ado | +1.392 |
ャ | +1.380 |
asting | +1.306 |
asted | +1.295 |
ality | +1.286 |
Neg logit contributions | |
hen | -1.027 |
ource | -0.990 |
IFT | -0.968 |
lime | -0.968 |
RIP | -0.958 |
Token | ist |
Token ID | 396 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ado | +2.979 |
ャ | +2.892 |
asting | +2.835 |
asted | +2.781 |
ality | +2.740 |
Neg logit contributions | |
hen | -5.203 |
RIP | -5.065 |
ource | -5.048 |
IFT | -5.043 |
lime | -5.027 |
Token | 's |
Token ID | 338 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ado | +2.521 |
ャ | +2.477 |
ality | +2.231 |
asting | +2.211 |
asted | +2.161 |
Neg logit contributions | |
hen | -3.654 |
RIP | -3.596 |
ource | -3.588 |
IFT | -3.575 |
lime | -3.556 |
Token | disagreement |
Token ID | 25800 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ado | +4.662 |
ャ | +4.377 |
ality | +3.989 |
asting | +3.953 |
asted | +3.873 |
Neg logit contributions | |
hen | -6.213 |
RIP | -6.057 |
ource | -6.056 |
lime | -6.030 |
IFT | -5.989 |
Token | with |
Token ID | 351 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ado | +7.291 |
ャ | +7.054 |
ality | +6.845 |
asted | +6.137 |
asting | +6.065 |
Neg logit contributions | |
RIP | -12.310 |
IFT | -11.997 |
ource | -11.981 |
hen | -11.929 |
expensive | -11.767 |
Token | � |
Token ID | 564 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ado | +4.555 |
ャ | +4.481 |
asting | +4.050 |
asted | +4.005 |
ality | +3.962 |
Neg logit contributions | |
hen | -6.760 |
ource | -6.720 |
RIP | -6.630 |
lime | -6.585 |
IFT | -6.578 |
Token | � |
Token ID | 250 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
hen | +0.627 |
ource | +0.603 |
lime | +0.589 |
IFT | +0.583 |
ordinary | +0.578 |
Neg logit contributions | |
ado | -0.731 |
ャ | -0.725 |
asting | -0.675 |
asted | -0.673 |
ality | -0.661 |
Token | During |
Token ID | 7191 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
hen | +0.245 |
ource | +0.239 |
lime | +0.232 |
IFT | +0.231 |
RIP | +0.228 |
Neg logit contributions | |
ado | -0.253 |
ャ | -0.252 |
asting | -0.234 |
asted | -0.234 |
ality | -0.230 |
Token | these |
Token ID | 777 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ado | +2.545 |
ャ | +2.516 |
asted | +2.297 |
asting | +2.290 |
ality | +2.248 |
Neg logit contributions | |
hen | -3.344 |
ource | -3.313 |
IFT | -3.248 |
RIP | -3.245 |
lime | -3.237 |
Token | the |
Token ID | 262 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ado | +1.623 |
ャ | +1.596 |
asted | +1.475 |
asting | +1.463 |
ality | +1.434 |
Neg logit contributions | |
hen | -2.143 |
ource | -2.096 |
IFT | -2.068 |
cius | -2.036 |
lime | -2.022 |
Token | fresh |
Token ID | 4713 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
hen | +1.548 |
ource | +1.497 |
lime | +1.468 |
IFT | +1.461 |
ordinary | +1.445 |
Neg logit contributions | |
ado | -1.297 |
ャ | -1.280 |
asting | -1.177 |
asted | -1.173 |
ality | -1.148 |
Token | citrus |
Token ID | 35405 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
hen | +0.504 |
ource | +0.493 |
IFT | +0.484 |
RIP | +0.481 |
lime | +0.479 |
Neg logit contributions | |
ado | -0.253 |
ャ | -0.250 |
asting | -0.223 |
asted | -0.222 |
ality | -0.218 |
Token | aroma |
Token ID | 31242 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
hen | +4.028 |
ource | +3.866 |
lime | +3.833 |
IFT | +3.765 |
ordinary | +3.740 |
Neg logit contributions | |
ado | -3.072 |
ャ | -3.046 |
asting | -2.772 |
asted | -2.755 |
ality | -2.673 |
Token | from |
Token ID | 422 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ado | +1.036 |
ャ | +1.012 |
asting | +0.925 |
asted | +0.924 |
ality | +0.921 |
Neg logit contributions | |
hen | -1.582 |
ource | -1.557 |
IFT | -1.523 |
lime | -1.517 |
ordinary | -1.510 |
Token | Amar |
Token ID | 44291 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ado | +1.073 |
ャ | +1.047 |
asted | +0.993 |
asting | +0.992 |
ality | +0.948 |
Neg logit contributions | |
hen | -1.278 |
ource | -1.238 |
IFT | -1.219 |
lime | -1.207 |
RIP | -1.205 |
Token | illo |
Token ID | 16111 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ality | +7.948 |
asted | +7.802 |
asting | +7.735 |
aste | +7.632 |
ado | +7.602 |
Neg logit contributions | |
IFT | -11.161 |
cases | -11.137 |
ource | -11.090 |
ordinary | -11.017 |
RIP | -10.944 |
Token | hops |
Token ID | 29438 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ado | +1.750 |
ャ | +1.681 |
asted | +1.597 |
asting | +1.585 |
ality | +1.536 |
Neg logit contributions | |
hen | -2.537 |
ource | -2.470 |
IFT | -2.430 |
ordinary | -2.411 |
RIP | -2.403 |
Token | ; |
Token ID | 26 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ado | +0.959 |
ャ | +0.935 |
asting | +0.865 |
asted | +0.860 |
ality | +0.842 |
Neg logit contributions | |
hen | -1.556 |
ource | -1.522 |
IFT | -1.501 |
RIP | -1.490 |
lime | -1.490 |
Token | something |
Token ID | 1223 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ado | +2.701 |
ャ | +2.615 |
asted | +2.519 |
asting | +2.503 |
ality | +2.430 |
Neg logit contributions | |
hen | -2.891 |
ource | -2.883 |
IFT | -2.817 |
cius | -2.807 |
RIP | -2.787 |
Token | lic |
Token ID | 3476 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
ado | +0.538 |
ャ | +0.526 |
asted | +0.489 |
asting | +0.485 |
ality | +0.481 |
Neg logit contributions | |
hen | -0.675 |
ource | -0.664 |
IFT | -0.653 |
cius | -0.642 |
lime | -0.641 |
Token | built |
Token ID | 3170 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ado | +0.640 |
ャ | +0.623 |
asting | +0.589 |
asted | +0.589 |
ality | +0.576 |
Neg logit contributions | |
hen | -0.664 |
ource | -0.640 |
lime | -0.633 |
ordinary | -0.627 |
IFT | -0.626 |
Token | by |
Token ID | 416 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
hen | +3.418 |
ource | +3.297 |
lime | +3.225 |
IFT | +3.200 |
ordinary | +3.176 |
Neg logit contributions | |
ado | -2.757 |
ャ | -2.738 |
asting | -2.503 |
asted | -2.491 |
ality | -2.426 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
hen | +1.580 |
ource | +1.527 |
lime | +1.503 |
IFT | +1.489 |
ordinary | +1.481 |
Neg logit contributions | |
ado | -1.253 |
ャ | -1.232 |
asting | -1.140 |
asted | -1.134 |
ality | -1.106 |
Token | construction |
Token ID | 5103 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ado | +3.104 |
ャ | +2.968 |
asting | +2.854 |
asted | +2.833 |
ality | +2.787 |
Neg logit contributions | |
hen | -3.449 |
ource | -3.384 |
RIP | -3.355 |
lime | -3.318 |
cius | -3.292 |
Token | company |
Token ID | 1664 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ado | +1.816 |
ャ | +1.744 |
asting | +1.670 |
asted | +1.660 |
ality | +1.645 |
Neg logit contributions | |
hen | -1.888 |
lime | -1.812 |
ource | -1.811 |
cius | -1.789 |
ordinary | -1.788 |
Token | Od |
Token ID | 10529 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ado | +0.499 |
ャ | +0.478 |
asting | +0.447 |
asted | +0.447 |
ality | +0.436 |
Neg logit contributions | |
hen | -0.720 |
ource | -0.699 |
lime | -0.694 |
IFT | -0.686 |
ordinary | -0.685 |
Token | eb |
Token ID | 1765 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ality | +7.832 |
aste | +7.789 |
asting | +7.783 |
ado | +7.588 |
asted | +7.533 |
Neg logit contributions | |
RIP | -10.090 |
IFT | -10.004 |
cases | -9.869 |
ource | -9.707 |
ordinary | -9.646 |
Token | re |
Token ID | 260 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ado | +1.527 |
ャ | +1.485 |
asting | +1.440 |
asted | +1.438 |
ality | +1.406 |
Neg logit contributions | |
hen | -1.217 |
ource | -1.199 |
IFT | -1.159 |
lime | -1.142 |
RIP | -1.125 |
Token | cht |
Token ID | 21474 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ado | +1.060 |
ャ | +1.030 |
asting | +1.008 |
asted | +0.998 |
ality | +0.973 |
Neg logit contributions | |
hen | -0.923 |
ource | -0.920 |
lime | -0.906 |
IFT | -0.898 |
RIP | -0.896 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ado | +0.745 |
ャ | +0.714 |
asting | +0.669 |
asted | +0.666 |
ality | +0.661 |
Neg logit contributions | |
hen | -1.230 |
ource | -1.195 |
lime | -1.189 |
ordinary | -1.180 |
IFT | -1.176 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-04 |
Pos logit contributions | |
hen | +0.696 |
ource | +0.673 |
lime | +0.663 |
IFT | +0.657 |
ordinary | +0.652 |
Neg logit contributions | |
ado | -0.578 |
ャ | -0.572 |
asting | -0.527 |
asted | -0.524 |
ality | -0.514 |
Token | � |
Token ID | 447 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hen | +0.287 |
ource | +0.281 |
IFT | +0.274 |
lime | +0.274 |
ordinary | +0.271 |
Neg logit contributions | |
ado | -0.220 |
ャ | -0.217 |
asting | -0.199 |
asted | -0.198 |
ality | -0.194 |
Token | � |
Token ID | 251 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
hen | +2.630 |
ource | +2.513 |
lime | +2.460 |
IFT | +2.441 |
ordinary | +2.418 |
Neg logit contributions | |
ado | -3.137 |
ャ | -3.109 |
asting | -2.902 |
asted | -2.889 |
ality | -2.842 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
hen | +2.633 |
ource | +2.545 |
lime | +2.496 |
IFT | +2.480 |
ordinary | +2.459 |
Neg logit contributions | |
ado | -2.272 |
ャ | -2.249 |
asting | -2.073 |
asted | -2.064 |
ality | -2.020 |
Token | fighter |
Token ID | 10543 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hen | +0.511 |
ource | +0.501 |
lime | +0.488 |
IFT | +0.486 |
RIP | +0.482 |
Neg logit contributions | |
ado | -0.424 |
ャ | -0.418 |
asting | -0.384 |
asted | -0.382 |
ality | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ado | +2.810 |
ャ | +2.757 |
ality | +2.511 |
asting | +2.507 |
asted | +2.491 |
Neg logit contributions | |
hen | -3.155 |
ource | -3.123 |
IFT | -3.032 |
RIP | -3.013 |
lime | -2.987 |
Token | Antonio |
Token ID | 11366 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
ャ | +1.141 |
ado | +1.139 |
asting | +1.041 |
asted | +1.033 |
ality | +1.020 |
Neg logit contributions | |
hen | -1.280 |
ource | -1.279 |
lime | -1.243 |
IFT | -1.236 |
cius | -1.221 |
Token | Ellison |
Token ID | 33601 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ado | +7.997 |
ャ | +7.248 |
ality | +7.177 |
asting | +7.088 |
asted | +7.081 |
Neg logit contributions | |
IFT | -10.488 |
lime | -10.431 |
RIP | -10.282 |
ource | -10.266 |
hen | -10.263 |
Token | , |
Token ID | 11 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ado | +1.337 |
ャ | +1.317 |
asting | +1.189 |
asted | +1.183 |
ality | +1.157 |
Neg logit contributions | |
hen | -2.138 |
ource | -2.101 |
IFT | -2.073 |
lime | -2.070 |
RIP | -2.041 |
Token | says |
Token ID | 1139 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ado | +1.560 |
ャ | +1.540 |
asting | +1.423 |
asted | +1.419 |
ality | +1.400 |
Neg logit contributions | |
ource | -1.583 |
hen | -1.575 |
IFT | -1.540 |
lime | -1.529 |
cius | -1.513 |
Token | quietly |
Token ID | 12703 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
hen | +0.625 |
ource | +0.611 |
lime | +0.600 |
IFT | +0.597 |
RIP | +0.592 |
Neg logit contributions | |
ado | -0.421 |
ャ | -0.414 |
asting | -0.376 |
asted | -0.374 |
ality | -0.370 |
Token | , |
Token ID | 11 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ado | +0.694 |
ャ | +0.684 |
asting | +0.617 |
ality | +0.615 |
asted | +0.612 |
Neg logit contributions | |
hen | -1.136 |
ource | -1.117 |
lime | -1.094 |
IFT | -1.088 |
RIP | -1.085 |
Token | to |
Token ID | 1462 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
hen | +2.009 |
ource | +1.970 |
IFT | +1.925 |
lime | +1.918 |
cius | +1.909 |
Neg logit contributions | |
ado | -1.220 |
ャ | -1.205 |
asting | -1.103 |
asted | -1.097 |
ality | -1.068 |
Token | guide |
Token ID | 5698 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
hen | +1.615 |
ource | +1.560 |
lime | +1.525 |
IFT | +1.516 |
RIP | +1.501 |
Neg logit contributions | |
ado | -1.560 |
ャ | -1.545 |
asting | -1.435 |
asted | -1.428 |
ality | -1.401 |
Token | for |
Token ID | 329 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
hen | +5.457 |
ource | +5.189 |
lime | +5.128 |
IFT | +5.063 |
ordinary | +5.053 |
Neg logit contributions | |
ado | -5.437 |
ャ | -5.387 |
asted | -4.997 |
asting | -4.982 |
ality | -4.842 |
Token | hosting |
Token ID | 13662 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
hen | +0.844 |
ource | +0.819 |
lime | +0.804 |
IFT | +0.796 |
RIP | +0.793 |
Neg logit contributions | |
ado | -0.775 |
ャ | -0.768 |
asting | -0.714 |
asted | -0.710 |
ality | -0.695 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
hen | +1.388 |
ource | +1.345 |
lime | +1.320 |
IFT | +1.306 |
RIP | +1.300 |
Neg logit contributions | |
ado | -1.238 |
ャ | -1.222 |
asting | -1.132 |
asted | -1.125 |
ality | -1.104 |
Token | Ton |
Token ID | 16859 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ャ | +0.494 |
ado | +0.494 |
asting | +0.450 |
asted | +0.447 |
ality | +0.441 |
Neg logit contributions | |
hen | -0.579 |
ource | -0.571 |
lime | -0.561 |
IFT | -0.556 |
cius | -0.551 |
Token | ally |
Token ID | 453 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ality | +8.472 |
ado | +8.362 |
ャ | +8.021 |
asted | +7.877 |
asting | +7.822 |
Neg logit contributions | |
RIP | -10.105 |
ource | -9.802 |
IFT | -9.680 |
hen | -9.653 |
ordinary | -9.639 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ado | +0.374 |
ャ | +0.373 |
asting | +0.337 |
asted | +0.336 |
ality | +0.327 |
Neg logit contributions | |
hen | -0.539 |
ource | -0.529 |
lime | -0.517 |
IFT | -0.514 |
RIP | -0.513 |
Token | it |
Token ID | 340 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
hen | +0.273 |
ource | +0.269 |
lime | +0.261 |
IFT | +0.260 |
RIP | +0.257 |
Neg logit contributions | |
ado | -0.297 |
ャ | -0.293 |
asting | -0.274 |
asted | -0.273 |
ality | -0.268 |
Token | � |
Token ID | 447 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ado | +0.667 |
ャ | +0.663 |
asting | +0.603 |
asted | +0.600 |
ality | +0.590 |
Neg logit contributions | |
hen | -0.897 |
ource | -0.879 |
lime | -0.857 |
IFT | -0.855 |
RIP | -0.851 |
Token | � |
Token ID | 247 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
ado | +1.472 |
ャ | +1.438 |
asted | +1.326 |
asting | +1.311 |
ality | +1.275 |
Neg logit contributions | |
ource | -1.586 |
hen | -1.582 |
lime | -1.532 |
cius | -1.512 |
IFT | -1.500 |
Token | Gold |
Token ID | 3561 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
hen | +1.867 |
ource | +1.814 |
IFT | +1.764 |
lime | +1.763 |
ordinary | +1.745 |
Neg logit contributions | |
ado | -1.692 |
ャ | -1.675 |
asting | -1.546 |
asted | -1.541 |
ality | -1.513 |
Token | , |
Token ID | 11 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
hen | +2.067 |
ource | +2.009 |
IFT | +1.964 |
lime | +1.962 |
RIP | +1.941 |
Neg logit contributions | |
ado | -1.600 |
ャ | -1.583 |
asting | -1.454 |
asted | -1.451 |
ality | -1.421 |
Token | Gold |
Token ID | 3561 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
hen | +1.166 |
ource | +1.132 |
IFT | +1.107 |
lime | +1.105 |
RIP | +1.092 |
Neg logit contributions | |
ado | -0.902 |
ャ | -0.892 |
asting | -0.817 |
asted | -0.814 |
ality | -0.798 |
Token | – |
Token ID | 784 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
ado | +0.130 |
ャ | +0.129 |
asting | +0.118 |
asted | +0.117 |
ality | +0.115 |
Neg logit contributions | |
hen | -0.175 |
ource | -0.171 |
lime | -0.167 |
IFT | -0.166 |
RIP | -0.165 |
Token | A |
Token ID | 317 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
hen | +2.077 |
ource | +2.008 |
lime | +1.973 |
IFT | +1.956 |
ordinary | +1.939 |
Neg logit contributions | |
ado | -1.764 |
ャ | -1.744 |
asting | -1.606 |
asted | -1.599 |
ality | -1.567 |
Token | Ton |
Token ID | 16859 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
hen | +0.485 |
ource | +0.471 |
lime | +0.461 |
IFT | +0.457 |
RIP | +0.455 |
Neg logit contributions | |
ャ | -0.433 |
ado | -0.432 |
asting | -0.395 |
asted | -0.394 |
ality | -0.385 |
Token | of |
Token ID | 286 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ality | +9.174 |
ado | +9.044 |
ャ | +8.928 |
asted | +8.708 |
asting | +8.571 |
Neg logit contributions | |
RIP | -8.694 |
IFT | -8.445 |
ource | -8.311 |
hen | -8.088 |
ordinary | -8.047 |
Token | Gold |
Token ID | 3561 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
hen | +1.013 |
ource | +0.987 |
lime | +0.964 |
IFT | +0.964 |
RIP | +0.955 |
Neg logit contributions | |
ado | -0.800 |
ャ | -0.785 |
asted | -0.725 |
asting | -0.724 |
ality | -0.707 |
Token | � |
Token ID | 447 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
hen | +1.267 |
ource | +1.229 |
lime | +1.201 |
IFT | +1.200 |
RIP | +1.190 |
Neg logit contributions | |
ado | -1.007 |
ャ | -0.994 |
asting | -0.912 |
asted | -0.909 |
ality | -0.894 |
Token | � |
Token ID | 251 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
hen | +1.875 |
ource | +1.811 |
lime | +1.772 |
IFT | +1.753 |
ordinary | +1.738 |
Neg logit contributions | |
ado | -1.875 |
ャ | -1.857 |
asting | -1.715 |
asted | -1.709 |
ality | -1.678 |
Token | - |
Token ID | 12 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
hen | +1.395 |
ource | +1.351 |
lime | +1.324 |
IFT | +1.316 |
ordinary | +1.306 |
Neg logit contributions | |
ado | -1.130 |
ャ | -1.121 |
asting | -1.027 |
asted | -1.021 |
ality | -1.002 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ado | +2.777 |
ャ | +2.675 |
asting | +2.479 |
ality | +2.476 |
asted | +2.438 |
Neg logit contributions | |
hen | -3.134 |
lime | -3.089 |
ource | -3.057 |
RIP | -3.054 |
IFT | -3.039 |
Token | � |
Token ID | 447 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ado | +1.006 |
ャ | +0.989 |
asting | +0.898 |
ality | +0.893 |
asted | +0.886 |
Neg logit contributions | |
hen | -1.381 |
ource | -1.348 |
lime | -1.343 |
RIP | -1.334 |
IFT | -1.328 |
Token | � |
Token ID | 247 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ado | +0.432 |
ャ | +0.423 |
asting | +0.392 |
asted | +0.392 |
ality | +0.383 |
Neg logit contributions | |
hen | -0.448 |
ource | -0.439 |
lime | -0.431 |
IFT | -0.423 |
cius | -0.421 |
Token | s |
Token ID | 82 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ado | +1.626 |
ャ | +1.604 |
asting | +1.516 |
asted | +1.506 |
ality | +1.502 |
Neg logit contributions | |
hen | -1.489 |
ource | -1.459 |
IFT | -1.449 |
RIP | -1.435 |
lime | -1.421 |
Token | reported |
Token ID | 2098 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ado | +1.078 |
ャ | +1.031 |
asting | +0.961 |
ality | +0.949 |
asted | +0.945 |
Neg logit contributions | |
hen | -1.353 |
ource | -1.306 |
lime | -1.303 |
IFT | -1.289 |
RIP | -1.285 |
Token | revenue |
Token ID | 6426 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
ado | +0.523 |
ャ | +0.505 |
asting | +0.463 |
asted | +0.459 |
ality | +0.458 |
Neg logit contributions | |
hen | -0.739 |
ource | -0.714 |
lime | -0.709 |
RIP | -0.704 |
IFT | -0.703 |
Token | also |
Token ID | 635 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ado | +7.268 |
ality | +6.584 |
ャ | +6.421 |
aste | +5.919 |
asted | +5.893 |
Neg logit contributions | |
hen | -10.816 |
RIP | -10.733 |
lime | -10.662 |
IFT | -10.559 |
cius | -10.474 |
Token | leaves |
Token ID | 5667 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
ado | +0.585 |
ャ | +0.570 |
ality | +0.518 |
asting | +0.516 |
asted | +0.516 |
Neg logit contributions | |
hen | -0.835 |
ource | -0.805 |
IFT | -0.804 |
RIP | -0.804 |
lime | -0.800 |
Token | out |
Token ID | 503 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
hen | +0.262 |
ource | +0.253 |
lime | +0.252 |
IFT | +0.250 |
RIP | +0.248 |
Neg logit contributions | |
ado | -0.236 |
ャ | -0.232 |
asting | -0.213 |
asted | -0.212 |
ality | -0.211 |
Token | royalty |
Token ID | 29359 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ado | +0.983 |
ャ | +0.953 |
ality | +0.871 |
asting | +0.870 |
asted | +0.866 |
Neg logit contributions | |
hen | -1.131 |
lime | -1.094 |
ource | -1.091 |
RIP | -1.081 |
IFT | -1.078 |
Token | payments |
Token ID | 7524 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
hen | +2.393 |
ource | +2.313 |
lime | +2.273 |
IFT | +2.258 |
ordinary | +2.242 |
Neg logit contributions | |
ado | -1.785 |
ャ | -1.766 |
asting | -1.614 |
asted | -1.606 |
ality | -1.569 |
Token | of |
Token ID | 286 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hen | +0.801 |
ource | +0.781 |
lime | +0.765 |
IFT | +0.763 |
RIP | +0.758 |
Neg logit contributions | |
ado | -0.578 |
ャ | -0.569 |
asting | -0.519 |
asted | -0.514 |
ality | -0.511 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
hen | +0.545 |
ource | +0.529 |
lime | +0.519 |
IFT | +0.515 |
RIP | +0.515 |
Neg logit contributions | |
ado | -0.475 |
ャ | -0.470 |
asting | -0.434 |
asted | -0.432 |
ality | -0.425 |
Token | Christian |
Token ID | 4302 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ado | +0.306 |
ャ | +0.303 |
asting | +0.279 |
asted | +0.277 |
ality | +0.274 |
Neg logit contributions | |
hen | -0.359 |
ource | -0.347 |
lime | -0.343 |
RIP | -0.342 |
IFT | -0.341 |
Token | doctrine |
Token ID | 13115 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ado | +0.573 |
ャ | +0.560 |
asting | +0.523 |
asted | +0.518 |
ality | +0.513 |
Neg logit contributions | |
hen | -0.693 |
ource | -0.671 |
lime | -0.665 |
RIP | -0.662 |
IFT | -0.660 |
Token | ; |
Token ID | 26 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
ado | +1.235 |
ャ | +1.218 |
ality | +1.119 |
asting | +1.118 |
asted | +1.098 |
Neg logit contributions | |
hen | -1.840 |
ource | -1.796 |
lime | -1.770 |
IFT | -1.765 |
RIP | -1.760 |
Token | Od |
Token ID | 10529 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ado | +1.933 |
ャ | +1.904 |
asting | +1.767 |
asted | +1.754 |
ality | +1.744 |
Neg logit contributions | |
hen | -2.474 |
ource | -2.467 |
RIP | -2.411 |
IFT | -2.408 |
lime | -2.394 |
Token | ys |
Token ID | 893 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
asting | +7.098 |
ado | +6.966 |
ality | +6.836 |
asted | +6.811 |
aste | +6.735 |
Neg logit contributions | |
IFT | -10.666 |
RIP | -10.423 |
lime | -10.023 |
cases | -9.863 |
expensive | -9.764 |
Token | se |
Token ID | 325 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ado | +1.635 |
ャ | +1.620 |
asting | +1.546 |
asted | +1.542 |
ality | +1.520 |
Neg logit contributions | |
hen | -1.715 |
ource | -1.689 |
IFT | -1.673 |
ordinary | -1.646 |
RIP | -1.644 |
Token | us |
Token ID | 385 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
hen | +3.339 |
ource | +3.143 |
lime | +3.039 |
ordinary | +2.996 |
IFT | +2.973 |
Neg logit contributions | |
ado | -4.890 |
ャ | -4.884 |
asted | -4.503 |
asting | -4.498 |
ality | -4.399 |
Token | tied |
Token ID | 8165 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ado | +0.632 |
ャ | +0.622 |
asting | +0.574 |
asted | +0.571 |
ality | +0.564 |
Neg logit contributions | |
hen | -0.796 |
ource | -0.777 |
IFT | -0.771 |
lime | -0.763 |
RIP | -0.762 |
Token | to |
Token ID | 284 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
ado | +1.330 |
ャ | +1.300 |
ality | +1.208 |
asted | +1.207 |
asting | +1.199 |
Neg logit contributions | |
hen | -1.462 |
ource | -1.438 |
IFT | -1.424 |
RIP | -1.411 |
lime | -1.407 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ado | +0.710 |
ャ | +0.695 |
asting | +0.630 |
asted | +0.628 |
ality | +0.627 |
Neg logit contributions | |
hen | -1.045 |
ource | -1.014 |
lime | -1.004 |
IFT | -0.994 |
RIP | -0.992 |
Token | Merc |
Token ID | 12185 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ャ | +1.461 |
ado | +1.439 |
asting | +1.305 |
asted | +1.303 |
ality | +1.297 |
Neg logit contributions | |
hen | -1.843 |
ource | -1.812 |
cius | -1.781 |
lime | -1.779 |
IFT | -1.757 |
Token | enaries |
Token ID | 30216 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ado | +0.504 |
ャ | +0.500 |
asting | +0.475 |
asted | +0.473 |
ality | +0.460 |
Neg logit contributions | |
hen | -0.357 |
ource | -0.344 |
lime | -0.339 |
IFT | -0.337 |
RIP | -0.332 |
Token | have |
Token ID | 423 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
hen | +3.527 |
ource | +3.410 |
lime | +3.346 |
IFT | +3.319 |
ordinary | +3.294 |
Neg logit contributions | |
ado | -2.798 |
ャ | -2.777 |
asting | -2.542 |
asted | -2.529 |
ality | -2.474 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
hen | +0.073 |
ource | +0.071 |
lime | +0.070 |
IFT | +0.069 |
RIP | +0.069 |
Neg logit contributions | |
ado | -0.065 |
ャ | -0.064 |
asted | -0.059 |
asting | -0.059 |
ality | -0.058 |
Token | ton |
Token ID | 5680 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ado | +0.695 |
ャ | +0.695 |
asted | +0.633 |
asting | +0.633 |
ality | +0.621 |
Neg logit contributions | |
hen | -0.880 |
ource | -0.860 |
lime | -0.846 |
IFT | -0.839 |
RIP | -0.838 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ャ | +6.909 |
ado | +6.746 |
ality | +6.582 |
asted | +6.074 |
asting | +6.018 |
Neg logit contributions | |
hen | -10.872 |
ource | -10.737 |
ordinary | -10.649 |
RIP | -10.566 |
IFT | -10.520 |
Token | great |
Token ID | 1049 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
hen | +0.358 |
ource | +0.347 |
lime | +0.340 |
IFT | +0.337 |
RIP | +0.337 |
Neg logit contributions | |
ado | -0.305 |
ャ | -0.302 |
asting | -0.278 |
asted | -0.278 |
ality | -0.273 |
Token | � |
Token ID | 564 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ado | +1.848 |
ャ | +1.843 |
ality | +1.688 |
asted | +1.684 |
asting | +1.682 |
Neg logit contributions | |
hen | -2.020 |
ource | -1.970 |
RIP | -1.927 |
cius | -1.924 |
lime | -1.909 |
Token | � |
Token ID | 247 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
hen | +2.989 |
ource | +2.870 |
lime | +2.810 |
IFT | +2.786 |
ordinary | +2.762 |
Neg logit contributions | |
ado | -3.311 |
ャ | -3.281 |
asting | -3.053 |
asted | -3.041 |
ality | -2.986 |
Token | jack |
Token ID | 19650 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
hen | +1.541 |
ource | +1.499 |
IFT | +1.449 |
lime | +1.447 |
cius | +1.437 |
Neg logit contributions | |
ャ | -1.608 |
ado | -1.606 |
asting | -1.493 |
asted | -1.490 |
ality | -1.475 |
Token | Tampa |
Token ID | 15528 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
hen | +3.992 |
ource | +3.839 |
lime | +3.752 |
IFT | +3.730 |
ordinary | +3.719 |
Neg logit contributions | |
ado | -3.167 |
ャ | -3.137 |
asting | -2.850 |
asted | -2.841 |
ality | -2.791 |
Token | � |
Token ID | 447 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ャ | +0.999 |
ado | +0.990 |
asting | +0.921 |
asted | +0.908 |
ality | +0.876 |
Neg logit contributions | |
hen | -1.357 |
ource | -1.313 |
lime | -1.300 |
IFT | -1.293 |
RIP | -1.292 |
Token | � |
Token ID | 247 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
hen | +2.710 |
ource | +2.605 |
lime | +2.551 |
IFT | +2.529 |
ordinary | +2.507 |
Neg logit contributions | |
ado | -2.921 |
ャ | -2.895 |
asting | -2.690 |
asted | -2.679 |
ality | -2.630 |
Token | s |
Token ID | 82 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
hen | +0.301 |
ource | +0.291 |
IFT | +0.285 |
lime | +0.283 |
ordinary | +0.279 |
Neg logit contributions | |
ャ | -0.344 |
ado | -0.343 |
asting | -0.322 |
asted | -0.320 |
ality | -0.313 |
Token | Jake |
Token ID | 14757 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
hen | +0.193 |
ource | +0.187 |
lime | +0.184 |
IFT | +0.183 |
RIP | +0.181 |
Neg logit contributions | |
ado | -0.151 |
ャ | -0.149 |
asting | -0.137 |
asted | -0.136 |
ality | -0.133 |
Token | Od |
Token ID | 10529 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ado | +2.658 |
ャ | +2.609 |
asting | +2.502 |
asted | +2.430 |
ality | +2.353 |
Neg logit contributions | |
IFT | -4.120 |
hen | -4.107 |
lime | -4.080 |
RIP | -4.073 |
ordinary | -4.033 |
Token | or |
Token ID | 273 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ado | +5.968 |
ality | +5.913 |
asted | +5.753 |
asting | +5.731 |
aste | +5.428 |
Neg logit contributions | |
IFT | -11.369 |
RIP | -11.351 |
lime | -11.248 |
IFIC | -10.994 |
ordinary | -10.893 |
Token | izz |
Token ID | 6457 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ado | +2.566 |
ャ | +2.528 |
asted | +2.390 |
asting | +2.251 |
aste | +2.243 |
Neg logit contributions | |
hen | -5.641 |
ource | -5.626 |
IFT | -5.509 |
lime | -5.507 |
ordinary | -5.507 |
Token | i |
Token ID | 72 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ado | +1.983 |
ャ | +1.949 |
asting | +1.777 |
ality | +1.725 |
asted | +1.711 |
Neg logit contributions | |
hen | -4.262 |
ource | -4.250 |
IFT | -4.205 |
lime | -4.197 |
cius | -4.158 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ado | +0.697 |
ャ | +0.696 |
asting | +0.623 |
asted | +0.620 |
ality | +0.608 |
Neg logit contributions | |
hen | -1.140 |
ource | -1.117 |
lime | -1.099 |
IFT | -1.094 |
RIP | -1.087 |
Token | San |
Token ID | 2986 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ado | +0.462 |
ャ | +0.456 |
asting | +0.426 |
asted | +0.425 |
ality | +0.410 |
Neg logit contributions | |
hen | -0.553 |
ource | -0.540 |
lime | -0.532 |
IFT | -0.530 |
RIP | -0.522 |
Token | There |
Token ID | 1858 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ャ | +0.605 |
ado | +0.597 |
asting | +0.556 |
asted | +0.552 |
ality | +0.549 |
Neg logit contributions | |
hen | -0.554 |
ource | -0.548 |
lime | -0.537 |
cius | -0.535 |
ordinary | -0.524 |
Token | � |
Token ID | 447 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ado | +2.303 |
ャ | +2.215 |
asted | +2.060 |
ality | +2.059 |
asting | +2.059 |
Neg logit contributions | |
ource | -3.346 |
hen | -3.341 |
lime | -3.289 |
RIP | -3.289 |
IFT | -3.271 |
Token | � |
Token ID | 247 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
ado | +0.294 |
ャ | +0.286 |
asted | +0.264 |
asting | +0.263 |
ality | +0.254 |
Neg logit contributions | |
hen | -0.317 |
ource | -0.314 |
lime | -0.305 |
IFT | -0.300 |
cius | -0.299 |
Token | s |
Token ID | 82 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
hen | +0.150 |
ource | +0.149 |
lime | +0.145 |
RIP | +0.144 |
IFT | +0.143 |
Neg logit contributions | |
ado | -0.157 |
ャ | -0.152 |
asted | -0.145 |
asting | -0.144 |
ality | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ado | +0.537 |
ャ | +0.528 |
asting | +0.487 |
asted | +0.486 |
ality | +0.479 |
Neg logit contributions | |
hen | -0.601 |
ource | -0.587 |
lime | -0.579 |
RIP | -0.576 |
IFT | -0.575 |
Token | ton |
Token ID | 5680 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
ado | +0.104 |
ャ | +0.104 |
asting | +0.095 |
asted | +0.094 |
ality | +0.092 |
Neg logit contributions | |
hen | -0.126 |
ource | -0.123 |
lime | -0.121 |
IFT | -0.120 |
RIP | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
ado | +7.101 |
ャ | +6.884 |
ality | +6.740 |
asting | +6.196 |
asted | +6.112 |
Neg logit contributions | |
hen | -10.505 |
ource | -10.416 |
RIP | -10.266 |
cius | -10.251 |
IFT | -10.245 |
Token | discover |
Token ID | 7073 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
ado | +0.215 |
ャ | +0.212 |
asting | +0.196 |
asted | +0.195 |
ality | +0.186 |
Neg logit contributions | |
hen | -0.329 |
ource | -0.321 |
lime | -0.317 |
cius | -0.313 |
RIP | -0.313 |
Token | in |
Token ID | 287 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
hen | +2.751 |
ource | +2.661 |
lime | +2.614 |
IFT | +2.592 |
ordinary | +2.574 |
Neg logit contributions | |
ado | -2.050 |
ャ | -2.031 |
asting | -1.855 |
asted | -1.846 |
ality | -1.799 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
hen | +2.507 |
ource | +2.422 |
lime | +2.374 |
IFT | +2.363 |
RIP | +2.338 |
Neg logit contributions | |
ado | -2.283 |
ャ | -2.258 |
asting | -2.088 |
asted | -2.075 |
ality | -2.038 |
Token | New |
Token ID | 968 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
hen | +0.575 |
ource | +0.557 |
lime | +0.547 |
IFT | +0.546 |
cius | +0.543 |
Neg logit contributions | |
ado | -0.519 |
ャ | -0.508 |
asting | -0.472 |
asted | -0.468 |
ality | -0.457 |
Token | ][ |
Token ID | 7131 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
hen | +0.246 |
ource | +0.238 |
lime | +0.236 |
ordinary | +0.232 |
IFT | +0.231 |
Neg logit contributions | |
ado | -0.203 |
ャ | -0.202 |
asting | -0.185 |
asted | -0.184 |
ality | -0.181 |
Token | [ |
Token ID | 58 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
hen | +2.755 |
ource | +2.653 |
lime | +2.603 |
IFT | +2.584 |
ordinary | +2.559 |
Neg logit contributions | |
ado | -2.504 |
ャ | -2.475 |
asting | -2.286 |
asted | -2.277 |
ality | -2.227 |
Token | i |
Token ID | 72 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
hen | +0.406 |
ource | +0.394 |
lime | +0.386 |
IFT | +0.383 |
ordinary | +0.382 |
Neg logit contributions | |
ado | -0.293 |
ャ | -0.289 |
asting | -0.264 |
asted | -0.263 |
ality | -0.257 |
Token | ] |
Token ID | 60 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ado | +1.863 |
ャ | +1.846 |
asted | +1.694 |
asting | +1.693 |
ality | +1.646 |
Neg logit contributions | |
hen | -2.411 |
lime | -2.341 |
ource | -2.340 |
RIP | -2.311 |
ordinary | -2.305 |
Token | ], |
Token ID | 4357 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ado | +0.655 |
ャ | +0.650 |
asting | +0.599 |
asted | +0.594 |
ality | +0.584 |
Neg logit contributions | |
hen | -0.734 |
ource | -0.708 |
lime | -0.703 |
ordinary | -0.692 |
RIP | -0.690 |
Token | Inter |
Token ID | 4225 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ado | +0.289 |
ャ | +0.286 |
asting | +0.263 |
asted | +0.261 |
ality | +0.258 |
Neg logit contributions | |
hen | -0.332 |
ource | -0.320 |
lime | -0.315 |
ordinary | -0.312 |
IFT | -0.311 |
Token | section |
Token ID | 5458 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ャ | +8.840 |
ado | +8.722 |
ality | +8.699 |
asting | +8.266 |
iqueness | +8.259 |
Neg logit contributions | |
ource | -8.110 |
hen | -7.741 |
IFIC | -7.701 |
RIP | -7.676 |
IFT | -7.621 |
Token | [ |
Token ID | 58 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ado | +3.182 |
ャ | +3.160 |
ality | +3.014 |
asting | +2.880 |
asted | +2.842 |
Neg logit contributions | |
hen | -4.882 |
lime | -4.769 |
ource | -4.765 |
ordinary | -4.751 |
cius | -4.730 |
Token | nn |
Token ID | 20471 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ado | +0.717 |
ャ | +0.716 |
asting | +0.661 |
asted | +0.657 |
ality | +0.650 |
Neg logit contributions | |
hen | -0.699 |
ource | -0.676 |
lime | -0.660 |
ordinary | -0.653 |
IFT | -0.653 |
Token | [ |
Token ID | 58 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ado | +2.320 |
ャ | +2.289 |
asting | +2.086 |
asted | +2.083 |
ality | +2.046 |
Neg logit contributions | |
hen | -3.599 |
ource | -3.476 |
lime | -3.451 |
ordinary | -3.428 |
IFT | -3.412 |
Token | Keys |
Token ID | 40729 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ャ | +2.365 |
ado | +2.362 |
asting | +2.213 |
asted | +2.204 |
ality | +2.188 |
Neg logit contributions | |
hen | -1.539 |
ource | -1.488 |
cius | -1.429 |
lime | -1.421 |
ordinary | -1.419 |
Token | death |
Token ID | 1918 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
hen | +1.044 |
ource | +1.015 |
lime | +0.995 |
IFT | +0.990 |
RIP | +0.982 |
Neg logit contributions | |
ado | -0.857 |
ャ | -0.840 |
asting | -0.778 |
asted | -0.773 |
ality | -0.757 |
Token | of |
Token ID | 286 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ado | +0.879 |
ャ | +0.856 |
asting | +0.790 |
ality | +0.787 |
asted | +0.783 |
Neg logit contributions | |
hen | -1.260 |
ource | -1.235 |
IFT | -1.209 |
lime | -1.200 |
ordinary | -1.200 |
Token | his |
Token ID | 465 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
hen | +1.464 |
ource | +1.411 |
lime | +1.380 |
IFT | +1.370 |
ordinary | +1.356 |
Neg logit contributions | |
ado | -1.588 |
ャ | -1.565 |
asting | -1.461 |
asted | -1.456 |
ality | -1.429 |
Token | young |
Token ID | 1862 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ado | +0.594 |
ャ | +0.571 |
asting | +0.530 |
asted | +0.527 |
ality | +0.516 |
Neg logit contributions | |
hen | -0.843 |
ource | -0.828 |
lime | -0.814 |
IFT | -0.812 |
RIP | -0.800 |
Token | daughter |
Token ID | 4957 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ado | +2.310 |
ャ | +2.182 |
asting | +2.058 |
asted | +2.057 |
ality | +2.025 |
Neg logit contributions | |
hen | -3.445 |
ource | -3.427 |
IFT | -3.363 |
lime | -3.343 |
cius | -3.322 |
Token | Olivia |
Token ID | 33911 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
ado | +0.053 |
ャ | +0.051 |
asted | +0.047 |
asting | +0.047 |
ality | +0.046 |
Neg logit contributions | |
hen | -0.069 |
ource | -0.067 |
lime | -0.066 |
IFT | -0.066 |
ordinary | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ado | +7.846 |
ャ | +7.486 |
asted | +7.373 |
ality | +7.258 |
asting | +7.194 |
Neg logit contributions | |
ource | -9.104 |
IFT | -9.028 |
lime | -9.008 |
cius | -9.008 |
hen | -8.972 |
Token | the |
Token ID | 262 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
ado | +1.153 |
ャ | +1.122 |
asting | +1.055 |
asted | +1.046 |
ality | +1.038 |
Neg logit contributions | |
hen | -1.172 |
ource | -1.143 |
lime | -1.120 |
IFT | -1.117 |
ordinary | -1.104 |
Token | struggles |
Token ID | 12766 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hen | +3.055 |
ource | +2.953 |
lime | +2.905 |
IFT | +2.883 |
ordinary | +2.866 |
Neg logit contributions | |
ado | -2.090 |
ャ | -2.072 |
asting | -1.881 |
asted | -1.873 |
ality | -1.822 |
Token | of |
Token ID | 286 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ado | +0.837 |
ャ | +0.810 |
asting | +0.761 |
asted | +0.757 |
ality | +0.755 |
Neg logit contributions | |
hen | -1.043 |
ource | -1.023 |
IFT | -0.998 |
lime | -0.997 |
ordinary | -0.990 |
Token | his |
Token ID | 465 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
hen | +1.321 |
ource | +1.267 |
lime | +1.239 |
IFT | +1.227 |
ordinary | +1.215 |
Neg logit contributions | |
ado | -1.638 |
ャ | -1.622 |
asting | -1.518 |
asted | -1.512 |
ality | -1.487 |
Token | , |
Token ID | 837 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
ado | +3.224 |
ャ | +3.174 |
asted | +2.841 |
asting | +2.835 |
ality | +2.799 |
Neg logit contributions | |
hen | -6.123 |
cius | -6.117 |
lime | -6.090 |
ource | -6.048 |
IFT | -6.031 |
Token | c |
Token ID | 269 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
ado | +1.764 |
ャ | +1.689 |
asting | +1.521 |
asted | +1.513 |
ality | +1.488 |
Neg logit contributions | |
hen | -3.277 |
ource | -3.187 |
IFT | -3.183 |
lime | -3.159 |
RIP | -3.151 |
Token | v |
Token ID | 85 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
hen | +1.911 |
ource | +1.828 |
lime | +1.783 |
IFT | +1.761 |
ordinary | +1.756 |
Neg logit contributions | |
ado | -2.238 |
ャ | -2.220 |
asting | -2.062 |
asted | -2.052 |
ality | -2.011 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
hen | +0.852 |
ource | +0.822 |
lime | +0.807 |
IFT | +0.803 |
ordinary | +0.794 |
Neg logit contributions | |
ado | -0.840 |
ャ | -0.833 |
asting | -0.770 |
asted | -0.769 |
ality | -0.758 |
Token | . |
Token ID | 764 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
ado | +1.357 |
ャ | +1.339 |
asting | +1.228 |
asted | +1.228 |
ality | +1.214 |
Neg logit contributions | |
hen | -2.034 |
ource | -1.983 |
lime | -1.973 |
cius | -1.957 |
IFT | -1.954 |
Token | MOR |
Token ID | 35208 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ado | +1.445 |
ャ | +1.414 |
asting | +1.262 |
asted | +1.250 |
ality | +1.232 |
Neg logit contributions | |
hen | -2.823 |
ource | -2.748 |
lime | -2.699 |
IFT | -2.675 |
ordinary | -2.664 |
Token | PH |
Token ID | 11909 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ャ | +6.842 |
ality | +6.355 |
ado | +5.957 |
asted | +5.872 |
ALLY | +5.840 |
Neg logit contributions | |
cius | -10.252 |
achev | -9.911 |
lime | -9.906 |
expensive | -9.653 |
hen | -9.646 |
Token | _ |
Token ID | 62 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ャ | +2.479 |
ado | +2.351 |
asting | +2.210 |
asted | +2.202 |
ality | +2.195 |
Neg logit contributions | |
hen | -4.529 |
cius | -4.494 |
lime | -4.439 |
ource | -4.435 |
achev | -4.377 |
Token | BL |
Token ID | 9148 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
ャ | +0.289 |
ado | +0.282 |
asting | +0.256 |
asted | +0.255 |
ality | +0.249 |
Neg logit contributions | |
hen | -0.497 |
ource | -0.483 |
cius | -0.475 |
lime | -0.475 |
ordinary | -0.469 |
Token | ACK |
Token ID | 8120 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ado | +0.188 |
ャ | +0.188 |
asted | +0.174 |
asting | +0.174 |
ality | +0.168 |
Neg logit contributions | |
hen | -0.256 |
ource | -0.250 |
lime | -0.247 |
cius | -0.245 |
ordinary | -0.242 |
Token | H |
Token ID | 39 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ャ | +1.351 |
ado | +1.344 |
asted | +1.249 |
asting | +1.241 |
ality | +1.225 |
Neg logit contributions | |
hen | -1.182 |
ource | -1.173 |
cius | -1.170 |
lime | -1.166 |
ordinary | -1.131 |
Token | number |
Token ID | 1271 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
ado | +0.347 |
ャ | +0.340 |
asting | +0.316 |
asted | +0.312 |
ality | +0.308 |
Neg logit contributions | |
hen | -0.438 |
ource | -0.420 |
lime | -0.419 |
IFT | -0.412 |
RIP | -0.412 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
hen | +0.206 |
ource | +0.199 |
lime | +0.195 |
IFT | +0.194 |
ordinary | +0.192 |
Neg logit contributions | |
ado | -0.160 |
ャ | -0.158 |
asting | -0.145 |
asted | -0.145 |
ality | -0.140 |
Token | benchmarks |
Token ID | 31747 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
hen | +0.314 |
lime | +0.298 |
ource | +0.297 |
IFT | +0.290 |
RIP | +0.290 |
Neg logit contributions | |
ado | -0.368 |
ャ | -0.359 |
asting | -0.339 |
asted | -0.335 |
ality | -0.333 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
hen | +0.605 |
ource | +0.586 |
lime | +0.579 |
IFT | +0.573 |
RIP | +0.571 |
Neg logit contributions | |
ado | -0.431 |
ャ | -0.424 |
asting | -0.389 |
ality | -0.385 |
asted | -0.385 |
Token | including |
Token ID | 1390 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
hen | +0.568 |
ource | +0.552 |
lime | +0.543 |
IFT | +0.538 |
RIP | +0.535 |
Neg logit contributions | |
ado | -0.491 |
ャ | -0.481 |
asting | -0.449 |
asted | -0.444 |
ality | -0.442 |
Token | revenue |
Token ID | 6426 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
hen | +0.513 |
ource | +0.495 |
lime | +0.491 |
IFT | +0.484 |
RIP | +0.483 |
Neg logit contributions | |
ado | -0.401 |
ャ | -0.394 |
asting | -0.365 |
asted | -0.362 |
ality | -0.356 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ado | +6.143 |
ality | +5.917 |
ャ | +5.803 |
asting | +5.397 |
asted | +5.313 |
Neg logit contributions | |
hen | -10.666 |
lime | -10.534 |
RIP | -10.463 |
ource | -10.451 |
IFT | -10.401 |
Token | profit |
Token ID | 7630 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ado | +2.744 |
ャ | +2.578 |
asting | +2.498 |
ality | +2.470 |
asted | +2.427 |
Neg logit contributions | |
hen | -4.113 |
lime | -4.045 |
ource | -3.986 |
RIP | -3.963 |
IFT | -3.940 |
Token | growth |
Token ID | 3349 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ado | +2.316 |
ャ | +2.196 |
ality | +2.061 |
asting | +2.031 |
asted | +1.995 |
Neg logit contributions | |
hen | -3.913 |
ource | -3.833 |
lime | -3.785 |
IFT | -3.747 |
RIP | -3.735 |
Token | , |
Token ID | 11 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ado | +2.554 |
ャ | +2.428 |
ality | +2.287 |
asting | +2.235 |
asted | +2.199 |
Neg logit contributions | |
hen | -4.486 |
ource | -4.350 |
lime | -4.345 |
RIP | -4.303 |
ordinary | -4.268 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ado | +1.328 |
ャ | +1.283 |
asting | +1.219 |
ality | +1.201 |
asted | +1.194 |
Neg logit contributions | |
hen | -1.628 |
ource | -1.574 |
lime | -1.571 |
IFT | -1.551 |
RIP | -1.546 |
Token | ime |
Token ID | 524 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
hen | +3.799 |
ource | +3.655 |
lime | +3.584 |
IFT | +3.556 |
ordinary | +3.530 |
Neg logit contributions | |
ado | -3.001 |
ャ | -2.968 |
asting | -2.721 |
asted | -2.708 |
ality | -2.650 |
Token | la |
Token ID | 8591 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ado | +0.517 |
ャ | +0.506 |
asting | +0.465 |
asted | +0.462 |
ality | +0.456 |
Neg logit contributions | |
hen | -0.634 |
ource | -0.622 |
IFT | -0.611 |
lime | -0.608 |
RIP | -0.607 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ado | +0.616 |
ャ | +0.611 |
asting | +0.561 |
asted | +0.558 |
ality | +0.547 |
Neg logit contributions | |
hen | -0.720 |
ource | -0.702 |
IFT | -0.690 |
lime | -0.689 |
RIP | -0.682 |
Token | � |
Token ID | 247 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
hen | +2.892 |
ource | +2.780 |
lime | +2.724 |
IFT | +2.702 |
ordinary | +2.680 |
Neg logit contributions | |
ado | -2.963 |
ャ | -2.936 |
asting | -2.723 |
asted | -2.712 |
ality | -2.662 |
Token | ist |
Token ID | 396 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
hen | +1.657 |
ource | +1.602 |
lime | +1.570 |
IFT | +1.562 |
ordinary | +1.548 |
Neg logit contributions | |
ado | -1.448 |
ャ | -1.433 |
asting | -1.320 |
asted | -1.314 |
ality | -1.289 |
Token | Mond |
Token ID | 27328 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ado | +1.342 |
ャ | +1.316 |
asting | +1.223 |
asted | +1.215 |
ality | +1.201 |
Neg logit contributions | |
hen | -1.417 |
ource | -1.401 |
IFT | -1.380 |
lime | -1.371 |
RIP | -1.371 |
Token | y |
Token ID | 88 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
ado | +9.059 |
ャ | +8.955 |
aste | +8.481 |
ality | +8.468 |
asting | +8.317 |
Neg logit contributions | |
ource | -7.414 |
RIP | -7.392 |
IFT | -7.347 |
hen | -7.298 |
ordinary | -7.250 |
Token | ? |
Token ID | 30 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ado | +1.835 |
ャ | +1.819 |
asting | +1.659 |
asted | +1.655 |
ality | +1.642 |
Neg logit contributions | |
hen | -2.182 |
ource | -2.143 |
IFT | -2.100 |
lime | -2.097 |
RIP | -2.091 |
Token | We |
Token ID | 775 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
hen | +2.379 |
ource | +2.299 |
lime | +2.258 |
IFT | +2.242 |
ordinary | +2.225 |
Neg logit contributions | |
ado | -1.883 |
ャ | -1.863 |
asting | -1.708 |
asted | -1.700 |
ality | -1.663 |
Token | did |
Token ID | 750 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ado | +0.966 |
ャ | +0.949 |
asting | +0.881 |
asted | +0.878 |
ality | +0.856 |
Neg logit contributions | |
hen | -1.116 |
ource | -1.096 |
lime | -1.076 |
IFT | -1.069 |
RIP | -1.067 |
Token | ; |
Token ID | 26 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ado | +1.365 |
ャ | +1.331 |
asting | +1.241 |
asted | +1.239 |
ality | +1.201 |
Neg logit contributions | |
hen | -1.605 |
ource | -1.570 |
lime | -1.542 |
IFT | -1.542 |
ordinary | -1.529 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
hen | +3.056 |
ource | +2.949 |
lime | +2.898 |
IFT | +2.879 |
ordinary | +2.860 |
Neg logit contributions | |
ado | -2.136 |
ャ | -2.122 |
asting | -1.922 |
asted | -1.919 |
ality | -1.863 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
hen | +1.068 |
ource | +1.041 |
lime | +1.023 |
IFT | +1.013 |
ordinary | +1.005 |
Neg logit contributions | |
ado | -0.853 |
ャ | -0.848 |
asting | -0.778 |
asted | -0.772 |
ality | -0.758 |
Token | Ill |
Token ID | 21478 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
hen | +0.898 |
ource | +0.876 |
lime | +0.850 |
IFT | +0.841 |
cius | +0.841 |
Neg logit contributions | |
ャ | -1.027 |
ado | -1.023 |
asting | -0.957 |
asted | -0.955 |
ality | -0.943 |
Token | ustration |
Token ID | 44027 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ado | +2.460 |
ャ | +2.314 |
asting | +2.219 |
ality | +2.210 |
asted | +2.204 |
Neg logit contributions | |
hen | -2.934 |
ource | -2.833 |
lime | -2.816 |
IFT | -2.784 |
ordinary | -2.749 |
Token | by |
Token ID | 416 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ado | +2.205 |
ャ | +2.123 |
asting | +1.954 |
asted | +1.944 |
ality | +1.923 |
Neg logit contributions | |
hen | -3.600 |
lime | -3.515 |
ource | -3.472 |
IFT | -3.471 |
cius | -3.460 |
Token | Allison |
Token ID | 33461 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ado | +1.192 |
ャ | +1.167 |
asting | +1.083 |
asted | +1.078 |
ality | +1.058 |
Neg logit contributions | |
hen | -1.488 |
ource | -1.452 |
lime | -1.439 |
IFT | -1.433 |
ordinary | -1.416 |
Token | Br |
Token ID | 1709 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
ado | +6.980 |
ャ | +6.874 |
asting | +6.678 |
asted | +6.619 |
ality | +6.483 |
Neg logit contributions | |
IFT | -9.258 |
RIP | -9.203 |
hen | -9.189 |
lime | -9.146 |
cius | -9.033 |
Token | uns |
Token ID | 13271 |
Feature activation | +2.89e-03 |
Pos logit contributions | |
ado | +2.391 |
asting | +2.365 |
asted | +2.360 |
ャ | +2.287 |
aste | +2.286 |
Neg logit contributions | |
hen | -2.152 |
IFT | -2.138 |
RIP | -2.098 |
lime | -2.088 |
ource | -2.061 |
Token |
|
Token ID | 198 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ado | +0.007 |
ャ | +0.007 |
asting | +0.007 |
asted | +0.007 |
ality | +0.007 |
Neg logit contributions | |
hen | -0.008 |
ource | -0.008 |
IFT | -0.008 |
lime | -0.008 |
ordinary | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ado | +1.327 |
ャ | +1.326 |
asting | +1.212 |
asted | +1.209 |
ality | +1.198 |
Neg logit contributions | |
hen | -1.844 |
ource | -1.805 |
lime | -1.782 |
cius | -1.773 |
IFT | -1.759 |
Token | In |
Token ID | 818 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ャ | +0.816 |
ado | +0.804 |
asting | +0.757 |
asted | +0.755 |
ality | +0.752 |
Neg logit contributions | |
hen | -0.753 |
ource | -0.746 |
lime | -0.723 |
cius | -0.722 |
IFT | -0.706 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ado | +3.052 |
ャ | +3.004 |
asted | +2.766 |
ality | +2.747 |
asting | +2.710 |
Neg logit contributions | |
hen | -5.038 |
lime | -5.025 |
ource | -5.016 |
RIP | -4.974 |
IFT | -4.930 |
Token | for |
Token ID | 329 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ado | +0.539 |
ャ | +0.531 |
asting | +0.488 |
asted | +0.484 |
ality | +0.475 |
Neg logit contributions | |
hen | -0.742 |
ource | -0.727 |
lime | -0.718 |
IFT | -0.710 |
RIP | -0.707 |
Token | example |
Token ID | 1672 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ado | +0.342 |
ャ | +0.333 |
asting | +0.312 |
asted | +0.311 |
ality | +0.304 |
Neg logit contributions | |
hen | -0.446 |
ource | -0.437 |
lime | -0.434 |
IFT | -0.426 |
RIP | -0.425 |
Token | in |
Token ID | 287 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
hen | +0.376 |
ource | +0.365 |
lime | +0.360 |
IFT | +0.356 |
RIP | +0.355 |
Neg logit contributions | |
ado | -0.286 |
ャ | -0.283 |
asting | -0.259 |
asted | -0.259 |
ality | -0.253 |
Token | a |
Token ID | 257 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ado | +0.641 |
ャ | +0.631 |
asting | +0.587 |
asted | +0.586 |
ality | +0.573 |
Neg logit contributions | |
hen | -0.748 |
ource | -0.730 |
lime | -0.718 |
RIP | -0.710 |
IFT | -0.710 |
Token | Manhattan |
Token ID | 13458 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
ado | +1.434 |
ャ | +1.402 |
asting | +1.306 |
asted | +1.299 |
ality | +1.269 |
Neg logit contributions | |
hen | -1.763 |
ource | -1.737 |
lime | -1.716 |
IFT | -1.690 |
RIP | -1.680 |
Token | style |
Token ID | 3918 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
ado | +6.995 |
ャ | +6.735 |
ality | +6.483 |
asting | +6.403 |
asted | +6.402 |
Neg logit contributions | |
ource | -9.534 |
lime | -9.532 |
RIP | -9.433 |
hen | -9.411 |
IFT | -9.348 |
Token | city |
Token ID | 1748 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ado | +2.287 |
ャ | +2.201 |
asting | +2.059 |
asted | +2.048 |
ality | +2.041 |
Neg logit contributions | |
hen | -3.098 |
ource | -3.069 |
lime | -3.038 |
IFT | -3.005 |
RIP | -2.983 |
Token | . |
Token ID | 13 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ado | +4.827 |
ャ | +4.776 |
ality | +4.409 |
asted | +4.269 |
asting | +4.268 |
Neg logit contributions | |
hen | -8.257 |
lime | -8.236 |
ource | -8.231 |
IFT | -8.099 |
RIP | -8.094 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ado | +1.433 |
ャ | +1.421 |
asting | +1.309 |
asted | +1.302 |
ality | +1.275 |
Neg logit contributions | |
hen | -1.834 |
ource | -1.791 |
lime | -1.789 |
IFT | -1.756 |
cius | -1.751 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ado | +1.041 |
ャ | +1.030 |
asting | +0.951 |
asted | +0.948 |
ality | +0.938 |
Neg logit contributions | |
hen | -1.437 |
ource | -1.405 |
lime | -1.390 |
cius | -1.381 |
IFT | -1.377 |
Token | ua |
Token ID | 6413 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ado | +1.384 |
ャ | +1.373 |
asting | +1.314 |
asted | +1.307 |
ality | +1.291 |
Neg logit contributions | |
hen | -1.403 |
IFT | -1.358 |
lime | -1.353 |
ource | -1.351 |
ordinary | -1.337 |
Token | , |
Token ID | 11 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
hen | +3.635 |
ource | +3.494 |
lime | +3.394 |
IFT | +3.368 |
ordinary | +3.362 |
Neg logit contributions | |
ado | -2.579 |
ャ | -2.543 |
asting | -2.296 |
asted | -2.294 |
ality | -2.200 |
Token | New |
Token ID | 968 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
hen | +1.315 |
ource | +1.275 |
lime | +1.259 |
IFT | +1.243 |
ordinary | +1.226 |
Neg logit contributions | |
ado | -1.534 |
ャ | -1.514 |
asting | -1.408 |
ality | -1.398 |
asted | -1.398 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ado | +1.702 |
ャ | +1.689 |
ality | +1.550 |
asting | +1.531 |
asted | +1.530 |
Neg logit contributions | |
hen | -2.113 |
ource | -2.036 |
lime | -2.034 |
IFT | -2.030 |
RIP | -2.015 |
Token | . |
Token ID | 13 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
hen | +1.364 |
ource | +1.320 |
lime | +1.281 |
IFT | +1.270 |
ordinary | +1.265 |
Neg logit contributions | |
ado | -0.997 |
ャ | -0.981 |
asted | -0.888 |
asting | -0.888 |
ality | -0.848 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
hen | +0.235 |
ource | +0.228 |
lime | +0.226 |
IFT | +0.224 |
ordinary | +0.221 |
Neg logit contributions | |
ado | -0.195 |
ャ | -0.194 |
asting | -0.177 |
asted | -0.176 |
ality | -0.174 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
hen | +5.516 |
ource | +4.998 |
ordinary | +4.337 |
book | +4.276 |
cases | +4.244 |
Neg logit contributions | |
ャ | -16.723 |
destro | -16.570 |
ado | -16.507 |
oun | -15.941 |
asting | -15.607 |
Token | 6 |
Token ID | 718 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
hen | +4.401 |
ource | +4.197 |
lime | +3.984 |
ordinary | +3.973 |
IFT | +3.925 |
Neg logit contributions | |
ャ | -4.706 |
ado | -4.616 |
asting | -4.276 |
asted | -4.254 |
ality | -4.073 |
Token | of |
Token ID | 286 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
hen | +2.983 |
ource | +2.846 |
lime | +2.766 |
ordinary | +2.752 |
IFT | +2.743 |
Neg logit contributions | |
ado | -2.595 |
ャ | -2.552 |
asting | -2.347 |
asted | -2.339 |
ality | -2.242 |
Token | 15 |
Token ID | 1315 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
hen | +2.609 |
ource | +2.417 |
ordinary | +2.349 |
IFT | +2.343 |
lime | +2.343 |
Neg logit contributions | |
ado | -3.602 |
ャ | -3.579 |
asting | -3.325 |
asted | -3.302 |
ality | -3.248 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
hen | +1.045 |
ource | +0.973 |
lime | +0.934 |
IFT | +0.921 |
ordinary | +0.915 |
Neg logit contributions | |
ado | -2.450 |
ャ | -2.432 |
asting | -2.305 |
asted | -2.297 |
ality | -2.261 |
Token | in |
Token ID | 287 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
hen | +2.802 |
ource | +2.714 |
lime | +2.653 |
IFT | +2.639 |
ordinary | +2.616 |
Neg logit contributions | |
ado | -2.121 |
ャ | -2.099 |
asting | -1.917 |
asted | -1.910 |
ality | -1.864 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
hen | +3.590 |
ource | +3.429 |
lime | +3.343 |
IFT | +3.315 |
ordinary | +3.283 |
Neg logit contributions | |
ャ | -3.639 |
ado | -3.625 |
asting | -3.327 |
asted | -3.311 |
ality | -3.268 |
Token | , |
Token ID | 11 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ado | +1.685 |
ャ | +1.655 |
asting | +1.500 |
asted | +1.478 |
ality | +1.463 |
Neg logit contributions | |
hen | -2.923 |
ource | -2.845 |
lime | -2.830 |
IFT | -2.812 |
RIP | -2.789 |
Token | California |
Token ID | 3442 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
hen | +2.344 |
ource | +2.230 |
lime | +2.170 |
IFT | +2.151 |
ordinary | +2.134 |
Neg logit contributions | |
ado | -2.959 |
ャ | -2.941 |
asting | -2.736 |
asted | -2.735 |
ality | -2.682 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
hen | +5.633 |
ource | +5.409 |
IFT | +5.171 |
lime | +5.165 |
RIP | +5.139 |
Neg logit contributions | |
ado | -4.688 |
ャ | -4.604 |
asted | -4.192 |
asting | -4.177 |
ality | -3.994 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
hen | +0.406 |
ource | +0.394 |
lime | +0.389 |
IFT | +0.386 |
ordinary | +0.381 |
Neg logit contributions | |
ado | -0.340 |
ャ | -0.336 |
asting | -0.308 |
asted | -0.307 |
ality | -0.301 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hen | +5.402 |
ource | +4.829 |
ordinary | +4.282 |
book | +4.174 |
cases | +4.103 |
Neg logit contributions | |
destro | -16.564 |
ャ | -16.528 |
ado | -16.252 |
oun | -15.836 |
asting | -15.464 |
Token | 12 |
Token ID | 1105 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
hen | +3.609 |
ource | +3.429 |
lime | +3.347 |
ordinary | +3.331 |
RIP | +3.216 |
Neg logit contributions | |
ャ | -4.585 |
ado | -4.542 |
asting | -4.211 |
asted | -4.104 |
iqueness | -4.064 |
Token | of |
Token ID | 286 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
hen | +1.325 |
ource | +1.275 |
lime | +1.249 |
IFT | +1.239 |
ordinary | +1.235 |
Neg logit contributions | |
ado | -1.043 |
ャ | -1.031 |
asting | -0.944 |
asted | -0.940 |
ality | -0.911 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
hen | +1.752 |
ource | +1.638 |
ordinary | +1.589 |
lime | +1.587 |
IFT | +1.587 |
Neg logit contributions | |
ado | -2.331 |
ャ | -2.319 |
asting | -2.153 |
asted | -2.141 |
ality | -2.104 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
hen | +0.617 |
ource | +0.579 |
lime | +0.558 |
IFT | +0.551 |
ordinary | +0.544 |
Neg logit contributions | |
ado | -1.397 |
ャ | -1.387 |
asting | -1.314 |
asted | -1.310 |
ality | -1.292 |
Token | os |
Token ID | 418 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
hen | +5.828 |
ource | +5.448 |
lime | +5.232 |
pres | +5.191 |
ordinary | +5.184 |
Neg logit contributions | |
ャ | -7.766 |
ado | -7.680 |
asted | -6.899 |
asting | -6.862 |
ality | -6.803 |
Token | Hills |
Token ID | 14379 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
hen | +2.508 |
ource | +2.433 |
lime | +2.400 |
IFT | +2.385 |
ordinary | +2.365 |
Neg logit contributions | |
ado | -1.623 |
ャ | -1.603 |
asting | -1.454 |
asted | -1.447 |
ality | -1.418 |
Token | , |
Token ID | 11 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
hen | +1.073 |
ource | +1.042 |
lime | +1.031 |
IFT | +1.025 |
ordinary | +1.017 |
Neg logit contributions | |
ado | -0.651 |
ャ | -0.645 |
asting | -0.583 |
asted | -0.577 |
ality | -0.566 |
Token | California |
Token ID | 3442 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hen | +1.765 |
ource | +1.720 |
lime | +1.698 |
IFT | +1.686 |
RIP | +1.659 |
Neg logit contributions | |
ado | -2.003 |
ャ | -1.976 |
asting | -1.847 |
asted | -1.831 |
ality | -1.819 |
Token | . |
Token ID | 13 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
hen | +3.931 |
ource | +3.778 |
lime | +3.657 |
IFT | +3.655 |
ordinary | +3.644 |
Neg logit contributions | |
ado | -3.096 |
ャ | -3.034 |
asted | -2.750 |
asting | -2.730 |
ality | -2.607 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
hen | +0.240 |
ource | +0.233 |
lime | +0.231 |
IFT | +0.229 |
cius | +0.226 |
Neg logit contributions | |
ado | -0.199 |
ャ | -0.197 |
asting | -0.180 |
asted | -0.180 |
ality | -0.177 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hen | +5.567 |
ource | +5.004 |
ordinary | +4.533 |
book | +4.337 |
cases | +4.322 |
Neg logit contributions | |
ャ | -16.129 |
destro | -15.944 |
ado | -15.834 |
oun | -15.280 |
asting | -15.025 |
Token | 14 |
Token ID | 1478 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
hen | +3.729 |
ource | +3.568 |
lime | +3.443 |
ordinary | +3.392 |
IFT | +3.390 |
Neg logit contributions | |
ャ | -4.477 |
ado | -4.444 |
asting | -4.040 |
asted | -3.991 |
ality | -3.965 |
Token | of |
Token ID | 286 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
hen | +0.884 |
ource | +0.854 |
lime | +0.838 |
IFT | +0.832 |
ordinary | +0.827 |
Neg logit contributions | |
ado | -0.671 |
ャ | -0.664 |
asting | -0.607 |
asted | -0.604 |
ality | -0.589 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
hen | +1.800 |
ource | +1.685 |
lime | +1.633 |
ordinary | +1.632 |
IFT | +1.630 |
Neg logit contributions | |
ado | -2.382 |
ャ | -2.369 |
asting | -2.202 |
asted | -2.189 |
ality | -2.149 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
hen | +0.197 |
ource | +0.187 |
lime | +0.182 |
IFT | +0.180 |
ordinary | +0.176 |
Neg logit contributions | |
ado | -0.424 |
ャ | -0.421 |
asting | -0.399 |
asted | -0.398 |
ality | -0.394 |
Token | Mor |
Token ID | 3461 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
hen | +0.650 |
ource | +0.632 |
lime | +0.622 |
IFT | +0.618 |
ordinary | +0.614 |
Neg logit contributions | |
ado | -0.545 |
ャ | -0.533 |
asting | -0.500 |
asted | -0.498 |
ality | -0.483 |
Token | aga |
Token ID | 8126 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ado | +3.136 |
ality | +3.067 |
ャ | +2.956 |
asting | +2.947 |
asted | +2.931 |
Neg logit contributions | |
IFT | -5.984 |
ource | -5.918 |
ordinary | -5.873 |
lime | -5.825 |
RIP | -5.821 |
Token | , |
Token ID | 11 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
hen | +4.127 |
ource | +3.954 |
lime | +3.870 |
ordinary | +3.833 |
IFT | +3.820 |
Neg logit contributions | |
ado | -2.918 |
ャ | -2.871 |
asting | -2.598 |
asted | -2.586 |
ality | -2.508 |
Token | California |
Token ID | 3442 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hen | +1.503 |
ource | +1.458 |
lime | +1.435 |
IFT | +1.427 |
ordinary | +1.408 |
Neg logit contributions | |
ado | -1.678 |
ャ | -1.658 |
asting | -1.552 |
asted | -1.540 |
ality | -1.523 |
Token | . |
Token ID | 13 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
hen | +4.609 |
ource | +4.415 |
lime | +4.281 |
IFT | +4.270 |
ordinary | +4.241 |
Neg logit contributions | |
ado | -3.703 |
ャ | -3.623 |
asted | -3.280 |
asting | -3.256 |
ality | -3.113 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ado | +0.017 |
ャ | +0.017 |
asting | +0.015 |
asted | +0.015 |
ality | +0.015 |
Neg logit contributions | |
hen | -0.021 |
ource | -0.020 |
lime | -0.020 |
IFT | -0.020 |
cius | -0.020 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hen | +5.547 |
ource | +4.998 |
ordinary | +4.490 |
book | +4.291 |
cases | +4.288 |
Neg logit contributions | |
ャ | -16.067 |
destro | -15.985 |
ado | -15.796 |
oun | -15.320 |
asting | -15.033 |
Token | 13 |
Token ID | 1511 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
hen | +3.816 |
ource | +3.622 |
lime | +3.493 |
IFT | +3.477 |
ordinary | +3.433 |
Neg logit contributions | |
ado | -4.688 |
ャ | -4.663 |
asting | -4.293 |
asted | -4.267 |
ality | -4.180 |
Token | of |
Token ID | 286 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
ado | +0.952 |
ャ | +0.944 |
asting | +0.860 |
asted | +0.856 |
ality | +0.854 |
Neg logit contributions | |
hen | -1.412 |
ource | -1.380 |
lime | -1.365 |
IFT | -1.359 |
cius | -1.352 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
hen | +1.873 |
ource | +1.749 |
ordinary | +1.696 |
lime | +1.694 |
IFT | +1.692 |
Neg logit contributions | |
ado | -2.494 |
ャ | -2.481 |
asting | -2.306 |
asted | -2.291 |
ality | -2.250 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
hen | +0.568 |
ource | +0.533 |
lime | +0.515 |
IFT | +0.508 |
ordinary | +0.501 |
Neg logit contributions | |
ado | -1.272 |
ャ | -1.263 |
asting | -1.197 |
asted | -1.193 |
ality | -1.177 |
Token | in |
Token ID | 287 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ado | +1.396 |
ャ | +1.353 |
asting | +1.272 |
asted | +1.234 |
ality | +1.222 |
Neg logit contributions | |
lime | -2.115 |
hen | -2.096 |
ource | -2.096 |
IFT | -2.061 |
ordinary | -2.036 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hen | +0.969 |
ource | +0.947 |
lime | +0.936 |
IFT | +0.925 |
ordinary | +0.920 |
Neg logit contributions | |
ado | -0.888 |
ャ | -0.866 |
asting | -0.814 |
asted | -0.809 |
ality | -0.788 |
Token | , |
Token ID | 11 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
hen | +0.644 |
ource | +0.628 |
lime | +0.623 |
IFT | +0.620 |
RIP | +0.611 |
Neg logit contributions | |
ado | -0.374 |
ャ | -0.369 |
asting | -0.336 |
asted | -0.331 |
ality | -0.326 |
Token | California |
Token ID | 3442 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
hen | +1.343 |
ource | +1.300 |
lime | +1.283 |
IFT | +1.271 |
ordinary | +1.254 |
Neg logit contributions | |
ado | -1.538 |
ャ | -1.520 |
asting | -1.427 |
asted | -1.414 |
ality | -1.398 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
hen | +4.684 |
ource | +4.482 |
IFT | +4.334 |
ordinary | +4.323 |
lime | +4.321 |
Neg logit contributions | |
ado | -3.839 |
ャ | -3.718 |
asted | -3.386 |
asting | -3.379 |
ality | -3.232 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
ado | +0.370 |
ャ | +0.366 |
asting | +0.334 |
asted | +0.332 |
ality | +0.328 |
Neg logit contributions | |
hen | -0.449 |
ource | -0.436 |
lime | -0.434 |
IFT | -0.429 |
cius | -0.424 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
hen | +5.606 |
ource | +5.054 |
ordinary | +4.513 |
IFT | +4.349 |
book | +4.341 |
Neg logit contributions | |
ャ | -15.885 |
destro | -15.839 |
ado | -15.603 |
oun | -15.130 |
asting | -14.832 |
Token | 10 |
Token ID | 838 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
hen | +3.376 |
ource | +3.288 |
IFT | +3.081 |
ordinary | +3.071 |
lime | +3.061 |
Neg logit contributions | |
ャ | -5.279 |
ado | -5.193 |
asting | -4.872 |
asted | -4.853 |
iqueness | -4.733 |
Token | of |
Token ID | 286 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ado | +2.031 |
ャ | +2.013 |
ality | +1.847 |
asting | +1.833 |
asted | +1.817 |
Neg logit contributions | |
hen | -3.351 |
ource | -3.294 |
cius | -3.282 |
lime | -3.281 |
IFT | -3.260 |
Token | 15 |
Token ID | 1315 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
hen | +1.927 |
ource | +1.797 |
ordinary | +1.742 |
lime | +1.739 |
IFT | +1.738 |
Neg logit contributions | |
ado | -2.583 |
ャ | -2.569 |
asting | -2.387 |
asted | -2.374 |
ality | -2.329 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
hen | +0.925 |
ource | +0.863 |
lime | +0.828 |
IFT | +0.816 |
ordinary | +0.811 |
Neg logit contributions | |
ado | -2.157 |
ャ | -2.142 |
asting | -2.029 |
asted | -2.022 |
ality | -1.991 |
Token | in |
Token ID | 287 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ado | +0.979 |
ャ | +0.944 |
asting | +0.884 |
asted | +0.856 |
ality | +0.855 |
Neg logit contributions | |
hen | -1.450 |
ource | -1.440 |
lime | -1.440 |
IFT | -1.416 |
RIP | -1.400 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
hen | +0.899 |
ource | +0.881 |
lime | +0.872 |
IFT | +0.864 |
ordinary | +0.859 |
Neg logit contributions | |
ado | -0.831 |
ャ | -0.812 |
asting | -0.765 |
asted | -0.758 |
ality | -0.740 |
Token | , |
Token ID | 11 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
hen | +0.858 |
ource | +0.834 |
lime | +0.825 |
IFT | +0.820 |
ordinary | +0.812 |
Neg logit contributions | |
ado | -0.521 |
ャ | -0.515 |
asting | -0.466 |
asted | -0.461 |
ality | -0.452 |
Token | California |
Token ID | 3442 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
hen | +1.345 |
ource | +1.318 |
lime | +1.312 |
IFT | +1.300 |
ordinary | +1.274 |
Neg logit contributions | |
ado | -1.491 |
ャ | -1.469 |
asting | -1.373 |
asted | -1.356 |
ality | -1.352 |
Token | . |
Token ID | 13 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
hen | +3.150 |
ource | +3.021 |
lime | +2.916 |
IFT | +2.915 |
ordinary | +2.905 |
Neg logit contributions | |
ado | -2.448 |
ャ | -2.394 |
asted | -2.171 |
asting | -2.167 |
ality | -2.069 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ado | +0.135 |
ャ | +0.133 |
asting | +0.122 |
asted | +0.121 |
ality | +0.120 |
Neg logit contributions | |
hen | -0.161 |
ource | -0.156 |
lime | -0.155 |
IFT | -0.154 |
cius | -0.152 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hen | +5.459 |
ource | +4.920 |
ordinary | +4.354 |
IFT | +4.225 |
book | +4.184 |
Neg logit contributions | |
ャ | -15.914 |
destro | -15.806 |
ado | -15.660 |
oun | -15.175 |
asting | -14.930 |
Token | 9 |
Token ID | 860 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
hen | +3.461 |
ource | +3.327 |
IFT | +3.202 |
ordinary | +3.171 |
lime | +3.158 |
Neg logit contributions | |
ャ | -4.950 |
ado | -4.908 |
asting | -4.620 |
asted | -4.589 |
ality | -4.469 |
Token | of |
Token ID | 286 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
hen | +0.223 |
ource | +0.216 |
lime | +0.213 |
IFT | +0.211 |
ordinary | +0.209 |
Neg logit contributions | |
ado | -0.162 |
ャ | -0.161 |
asting | -0.147 |
asted | -0.146 |
ality | -0.144 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
hen | +1.103 |
ource | +1.045 |
lime | +1.016 |
IFT | +1.011 |
ordinary | +1.007 |
Neg logit contributions | |
ado | -1.390 |
ャ | -1.380 |
asting | -1.286 |
asted | -1.279 |
ality | -1.256 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
hen | +0.822 |
ource | +0.768 |
lime | +0.737 |
IFT | +0.727 |
ordinary | +0.721 |
Neg logit contributions | |
ado | -1.901 |
ャ | -1.888 |
asting | -1.789 |
asted | -1.783 |
ality | -1.756 |
Token | Garden |
Token ID | 11652 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
hen | +1.209 |
ource | +1.174 |
lime | +1.157 |
IFT | +1.150 |
ordinary | +1.139 |
Neg logit contributions | |
ado | -1.006 |
ャ | -0.988 |
asting | -0.919 |
asted | -0.915 |
ality | -0.892 |
Token | Grove |
Token ID | 24144 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ado | +0.679 |
ャ | +0.665 |
asting | +0.627 |
asted | +0.627 |
ality | +0.624 |
Neg logit contributions | |
hen | -0.751 |
IFT | -0.728 |
ource | -0.726 |
lime | -0.715 |
RIP | -0.714 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hen | +3.927 |
ource | +3.792 |
lime | +3.704 |
IFT | +3.669 |
ordinary | +3.661 |
Neg logit contributions | |
ado | -2.629 |
ャ | -2.598 |
asting | -2.346 |
asted | -2.340 |
ality | -2.275 |
Token | California |
Token ID | 3442 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hen | +0.952 |
ource | +0.933 |
lime | +0.927 |
IFT | +0.918 |
ordinary | +0.906 |
Neg logit contributions | |
ado | -1.036 |
ャ | -1.020 |
asting | -0.956 |
asted | -0.944 |
ality | -0.939 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
hen | +3.205 |
ource | +3.083 |
lime | +2.989 |
IFT | +2.984 |
RIP | +2.969 |
Neg logit contributions | |
ado | -2.453 |
ャ | -2.406 |
asted | -2.175 |
asting | -2.164 |
ality | -2.075 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ado | +0.077 |
ャ | +0.076 |
asting | +0.070 |
asted | +0.069 |
ality | +0.069 |
Neg logit contributions | |
hen | -0.093 |
ource | -0.090 |
lime | -0.089 |
IFT | -0.089 |
cius | -0.088 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
hen | +5.574 |
ource | +4.991 |
ordinary | +4.536 |
book | +4.330 |
cases | +4.310 |
Neg logit contributions | |
ャ | -15.799 |
destro | -15.640 |
ado | -15.550 |
oun | -14.950 |
asting | -14.733 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
hen | +3.316 |
ource | +3.076 |
IFT | +3.011 |
ordinary | +2.976 |
lime | +2.949 |
Neg logit contributions | |
ャ | -5.044 |
ado | -5.021 |
asting | -4.632 |
asted | -4.601 |
iqueness | -4.558 |
Token | of |
Token ID | 286 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
hen | +0.125 |
ource | +0.121 |
lime | +0.120 |
IFT | +0.119 |
cius | +0.118 |
Neg logit contributions | |
ado | -0.089 |
ャ | -0.088 |
asting | -0.081 |
asted | -0.080 |
ality | -0.079 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
hen | +2.434 |
ource | +2.283 |
ordinary | +2.215 |
lime | +2.210 |
IFT | +2.200 |
Neg logit contributions | |
ado | -3.188 |
ャ | -3.169 |
asting | -2.945 |
asted | -2.922 |
ality | -2.873 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
hen | +1.370 |
ource | +1.325 |
lime | +1.305 |
IFT | +1.295 |
ordinary | +1.284 |
Neg logit contributions | |
ado | -1.106 |
ャ | -1.095 |
asting | -1.007 |
asted | -1.003 |
ality | -0.981 |
Token | Tiff |
Token ID | 35775 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
hen | +0.941 |
ource | +0.915 |
lime | +0.901 |
IFT | +0.896 |
ordinary | +0.890 |
Neg logit contributions | |
ado | -0.793 |
ャ | -0.780 |
asting | -0.726 |
asted | -0.721 |
ality | -0.703 |
Token | in |
Token ID | 259 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ado | +3.676 |
asting | +3.528 |
asted | +3.503 |
ャ | +3.477 |
aste | +3.421 |
Neg logit contributions | |
hen | -3.367 |
IFT | -3.339 |
ource | -3.327 |
RIP | -3.299 |
lime | -3.224 |
Token | , |
Token ID | 11 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
hen | +0.738 |
ource | +0.718 |
lime | +0.709 |
IFT | +0.705 |
ordinary | +0.699 |
Neg logit contributions | |
ado | -0.451 |
ャ | -0.445 |
asting | -0.403 |
asted | -0.400 |
ality | -0.392 |
Token | Iowa |
Token ID | 9406 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
hen | +1.153 |
ource | +1.115 |
lime | +1.098 |
IFT | +1.089 |
ordinary | +1.079 |
Neg logit contributions | |
ado | -1.321 |
ャ | -1.302 |
asting | -1.218 |
asted | -1.210 |
ality | -1.195 |
Token | . |
Token ID | 13 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ado | +0.928 |
ャ | +0.918 |
asting | +0.838 |
asted | +0.829 |
ality | +0.819 |
Neg logit contributions | |
hen | -1.607 |
ource | -1.568 |
lime | -1.553 |
IFT | -1.544 |
ordinary | -1.525 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
ado | +1.106 |
ャ | +1.100 |
asting | +1.001 |
asted | +0.997 |
ality | +0.980 |
Neg logit contributions | |
hen | -1.436 |
ource | -1.402 |
lime | -1.396 |
IFT | -1.389 |
cius | -1.369 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
hen | +5.177 |
ource | +4.866 |
ordinary | +4.048 |
RIP | +4.035 |
IFT | +4.000 |
Neg logit contributions | |
ャ | -15.735 |
ado | -15.597 |
destro | -15.518 |
oun | -15.046 |
asting | -14.642 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
hen | +4.087 |
ource | +3.960 |
IFT | +3.848 |
ordinary | +3.827 |
lime | +3.774 |
Neg logit contributions | |
ャ | -4.256 |
ado | -4.244 |
asting | -3.925 |
asted | -3.878 |
ality | -3.774 |
Token | of |
Token ID | 286 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
ado | +0.042 |
ャ | +0.042 |
asting | +0.038 |
asted | +0.038 |
ality | +0.038 |
Neg logit contributions | |
hen | -0.060 |
ource | -0.058 |
lime | -0.058 |
IFT | -0.057 |
cius | -0.057 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
hen | +1.796 |
ource | +1.695 |
lime | +1.653 |
IFT | +1.642 |
ordinary | +1.636 |
Neg logit contributions | |
ado | -2.291 |
ャ | -2.273 |
asting | -2.115 |
asted | -2.103 |
ality | -2.070 |
Token | Photos |
Token ID | 9434 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
hen | +0.755 |
ource | +0.711 |
lime | +0.689 |
IFT | +0.680 |
ordinary | +0.668 |
Neg logit contributions | |
ado | -1.667 |
ャ | -1.657 |
asting | -1.569 |
asted | -1.564 |
ality | -1.545 |
Token | on |
Token ID | 319 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ado | +0.666 |
ャ | +0.656 |
ality | +0.600 |
asting | +0.596 |
asted | +0.593 |
Neg logit contributions | |
hen | -0.898 |
ource | -0.887 |
IFT | -0.863 |
lime | -0.861 |
RIP | -0.858 |
Token | Women |
Token ID | 6926 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
hen | +3.413 |
ource | +3.248 |
lime | +3.167 |
ordinary | +3.150 |
IFT | +3.138 |
Neg logit contributions | |
ado | -4.285 |
ャ | -4.274 |
asting | -3.968 |
asted | -3.954 |
ality | -3.876 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hen | +2.284 |
ource | +2.215 |
lime | +2.186 |
IFT | +2.164 |
ordinary | +2.150 |
Neg logit contributions | |
ado | -1.575 |
ャ | -1.549 |
asting | -1.416 |
asted | -1.407 |
ality | -1.380 |
Token | politics |
Token ID | 4819 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
hen | +3.232 |
ource | +3.114 |
lime | +3.056 |
IFT | +3.031 |
ordinary | +3.005 |
Neg logit contributions | |
ado | -3.044 |
ャ | -3.013 |
asting | -2.787 |
asted | -2.774 |
ality | -2.720 |
Token | . |
Token ID | 13 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
hen | +2.989 |
ource | +2.893 |
lime | +2.835 |
IFT | +2.821 |
ordinary | +2.800 |
Neg logit contributions | |
ado | -2.067 |
ャ | -2.052 |
asting | -1.862 |
asted | -1.854 |
ality | -1.804 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
hen | +1.864 |
ource | +1.800 |
lime | +1.768 |
IFT | +1.755 |
ordinary | +1.741 |
Neg logit contributions | |
ado | -1.548 |
ャ | -1.532 |
asting | -1.408 |
asted | -1.401 |
ality | -1.372 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
hen | +5.416 |
ource | +4.975 |
ordinary | +4.338 |
RIP | +4.293 |
cases | +4.246 |
Neg logit contributions | |
ャ | -15.421 |
ado | -15.246 |
destro | -14.943 |
asting | -14.481 |
oun | -14.364 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
hen | +4.172 |
ource | +3.987 |
ordinary | +3.830 |
lime | +3.817 |
IFT | +3.816 |
Neg logit contributions | |
ado | -4.386 |
ャ | -4.377 |
asting | -4.123 |
asted | -4.091 |
ality | -3.945 |
Token | of |
Token ID | 286 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ado | +0.607 |
ャ | +0.601 |
asting | +0.548 |
asted | +0.544 |
ality | +0.540 |
Neg logit contributions | |
hen | -0.879 |
ource | -0.856 |
lime | -0.846 |
IFT | -0.841 |
cius | -0.835 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
hen | +1.649 |
ource | +1.551 |
lime | +1.507 |
IFT | +1.503 |
ordinary | +1.499 |
Neg logit contributions | |
ado | -2.138 |
ャ | -2.122 |
asting | -1.976 |
asted | -1.965 |
ality | -1.931 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
hen | +0.779 |
ource | +0.729 |
lime | +0.702 |
IFT | +0.692 |
ordinary | +0.685 |
Neg logit contributions | |
ado | -1.780 |
ャ | -1.767 |
asting | -1.674 |
asted | -1.669 |
ality | -1.645 |
Token | January |
Token ID | 3269 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
hen | +0.163 |
ource | +0.159 |
lime | +0.157 |
IFT | +0.155 |
RIP | +0.154 |
Neg logit contributions | |
ado | -0.130 |
ャ | -0.127 |
asting | -0.117 |
asted | -0.117 |
ality | -0.116 |
Token | 20 |
Token ID | 1160 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
hen | +2.815 |
ource | +2.676 |
lime | +2.611 |
ordinary | +2.587 |
IFT | +2.585 |
Neg logit contributions | |
ado | -2.923 |
ャ | -2.902 |
asting | -2.677 |
asted | -2.664 |
ality | -2.585 |
Token | , |
Token ID | 11 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ado | +0.010 |
ャ | +0.009 |
asting | +0.009 |
asted | +0.009 |
ality | +0.008 |
Neg logit contributions | |
hen | -0.016 |
ource | -0.016 |
lime | -0.016 |
IFT | -0.016 |
ordinary | -0.015 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
hen | +1.480 |
ource | +1.433 |
lime | +1.404 |
IFT | +1.394 |
ordinary | +1.377 |
Neg logit contributions | |
ado | -1.542 |
ャ | -1.523 |
asting | -1.425 |
asted | -1.417 |
ality | -1.389 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ado | +0.178 |
ャ | +0.176 |
asting | +0.159 |
asted | +0.158 |
ality | +0.154 |
Neg logit contributions | |
hen | -0.269 |
ource | -0.260 |
lime | -0.255 |
IFT | -0.253 |
ordinary | -0.252 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
ado | +0.429 |
ャ | +0.426 |
asting | +0.389 |
asted | +0.387 |
ality | +0.382 |
Neg logit contributions | |
hen | -0.534 |
ource | -0.521 |
lime | -0.518 |
IFT | -0.513 |
cius | -0.507 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
hen | +5.259 |
ource | +4.766 |
ordinary | +4.164 |
RIP | +4.090 |
book | +4.069 |
Neg logit contributions | |
ャ | -15.293 |
ado | -15.063 |
destro | -14.972 |
oun | -14.363 |
asting | -14.285 |
Token | 8 |
Token ID | 807 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
hen | +3.591 |
ource | +3.453 |
lime | +3.337 |
ordinary | +3.312 |
IFT | +3.264 |
Neg logit contributions | |
ャ | -4.151 |
ado | -4.134 |
asting | -3.843 |
asted | -3.790 |
ality | -3.725 |
Token | of |
Token ID | 286 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ado | +1.923 |
ャ | +1.914 |
ality | +1.746 |
asting | +1.736 |
asted | +1.718 |
Neg logit contributions | |
hen | -3.142 |
ource | -3.095 |
lime | -3.082 |
cius | -3.079 |
IFT | -3.064 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
hen | +0.701 |
ource | +0.668 |
lime | +0.652 |
IFT | +0.647 |
ordinary | +0.643 |
Neg logit contributions | |
ado | -0.855 |
ャ | -0.848 |
asting | -0.790 |
asted | -0.787 |
ality | -0.773 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
hen | +0.622 |
ource | +0.583 |
lime | +0.563 |
IFT | +0.555 |
ordinary | +0.548 |
Neg logit contributions | |
ado | -1.405 |
ャ | -1.396 |
asting | -1.322 |
asted | -1.318 |
ality | -1.300 |
Token | in |
Token ID | 287 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
ado | +1.798 |
ャ | +1.735 |
asting | +1.634 |
asted | +1.573 |
ality | +1.551 |
Neg logit contributions | |
lime | -2.813 |
hen | -2.803 |
ource | -2.785 |
IFT | -2.758 |
RIP | -2.724 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
hen | +0.263 |
ource | +0.256 |
lime | +0.253 |
IFT | +0.251 |
RIP | +0.250 |
Neg logit contributions | |
ado | -0.233 |
ャ | -0.228 |
asting | -0.214 |
asted | -0.213 |
ality | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ado | +2.041 |
ャ | +2.005 |
asting | +1.829 |
asted | +1.776 |
ality | +1.769 |
Neg logit contributions | |
hen | -3.746 |
ource | -3.674 |
lime | -3.657 |
IFT | -3.639 |
RIP | -3.607 |
Token | California |
Token ID | 3442 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
hen | +1.626 |
ource | +1.584 |
lime | +1.561 |
IFT | +1.548 |
RIP | +1.529 |
Neg logit contributions | |
ado | -1.858 |
ャ | -1.830 |
asting | -1.715 |
asted | -1.695 |
ality | -1.681 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
hen | +3.800 |
ource | +3.629 |
lime | +3.528 |
IFT | +3.519 |
ordinary | +3.505 |
Neg logit contributions | |
ado | -2.940 |
ャ | -2.880 |
asted | -2.626 |
asting | -2.607 |
ality | -2.497 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
ado | +0.869 |
ャ | +0.857 |
asting | +0.782 |
asted | +0.777 |
ality | +0.766 |
Neg logit contributions | |
hen | -1.079 |
ource | -1.052 |
lime | -1.047 |
IFT | -1.036 |
cius | -1.023 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
hen | +5.195 |
ource | +4.747 |
ordinary | +4.162 |
IFT | +4.058 |
RIP | +4.057 |
Neg logit contributions | |
ャ | -15.200 |
destro | -14.948 |
ado | -14.939 |
oun | -14.311 |
asting | -14.219 |
Token | 11 |
Token ID | 1367 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
hen | +3.518 |
ource | +3.326 |
IFT | +3.147 |
ordinary | +3.138 |
RIP | +3.135 |
Neg logit contributions | |
ャ | -4.238 |
ado | -4.087 |
asting | -3.840 |
asted | -3.803 |
ality | -3.671 |
Token | of |
Token ID | 286 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
ado | +1.767 |
ャ | +1.751 |
ality | +1.599 |
asting | +1.589 |
asted | +1.576 |
Neg logit contributions | |
hen | -2.815 |
ource | -2.765 |
lime | -2.744 |
cius | -2.738 |
IFT | -2.732 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
hen | +1.190 |
ource | +1.123 |
lime | +1.092 |
IFT | +1.088 |
ordinary | +1.085 |
Neg logit contributions | |
ado | -1.516 |
ャ | -1.505 |
asting | -1.401 |
asted | -1.394 |
ality | -1.369 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
hen | +0.605 |
ource | +0.567 |
lime | +0.548 |
IFT | +0.540 |
ordinary | +0.533 |
Neg logit contributions | |
ado | -1.366 |
ャ | -1.356 |
asting | -1.285 |
asted | -1.281 |
ality | -1.263 |
Token | In |
Token ID | 818 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
hen | +0.786 |
ource | +0.768 |
lime | +0.745 |
IFT | +0.745 |
cius | +0.735 |
Neg logit contributions | |
ャ | -0.884 |
ado | -0.880 |
asting | -0.821 |
asted | -0.819 |
ality | -0.814 |
Token | the |
Token ID | 262 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
hen | +2.963 |
ource | +2.858 |
lime | +2.805 |
IFT | +2.783 |
ordinary | +2.763 |
Neg logit contributions | |
ado | -2.531 |
ャ | -2.505 |
asting | -2.304 |
asted | -2.294 |
ality | -2.246 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
hen | +2.232 |
ource | +2.155 |
lime | +2.119 |
IFT | +2.101 |
ordinary | +2.081 |
Neg logit contributions | |
ado | -1.990 |
ャ | -1.970 |
asting | -1.818 |
asted | -1.808 |
ality | -1.772 |
Token | film |
Token ID | 2646 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
hen | +0.857 |
ource | +0.835 |
lime | +0.818 |
IFT | +0.814 |
RIP | +0.802 |
Neg logit contributions | |
ado | -0.781 |
ャ | -0.770 |
asting | -0.712 |
asted | -0.708 |
ality | -0.696 |
Token | The |
Token ID | 383 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
hen | +2.135 |
ource | +2.061 |
lime | +2.024 |
IFT | +2.008 |
ordinary | +1.994 |
Neg logit contributions | |
ado | -1.773 |
ャ | -1.755 |
asting | -1.613 |
asted | -1.605 |
ality | -1.571 |
Token | Secret |
Token ID | 3943 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ado | +0.817 |
ャ | +0.813 |
asting | +0.752 |
asted | +0.748 |
ality | +0.739 |
Neg logit contributions | |
hen | -0.998 |
ource | -0.988 |
lime | -0.963 |
IFT | -0.957 |
RIP | -0.953 |
Token | Life |
Token ID | 5155 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
hen | +10.316 |
ource | +9.641 |
ordinary | +9.623 |
pres | +9.417 |
lime | +9.326 |
Neg logit contributions | |
ado | -9.207 |
ャ | -9.172 |
asting | -8.245 |
asted | -8.059 |
aste | -7.768 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
hen | +2.511 |
ource | +2.401 |
lime | +2.365 |
IFT | +2.318 |
ordinary | +2.311 |
Neg logit contributions | |
ado | -2.225 |
ャ | -2.217 |
asting | -2.048 |
asted | -2.025 |
ality | -1.960 |
Token | Walter |
Token ID | 15819 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
hen | +3.184 |
ource | +2.987 |
lime | +2.936 |
IFT | +2.923 |
ordinary | +2.912 |
Neg logit contributions | |
ado | -4.220 |
ャ | -4.185 |
asting | -3.892 |
asted | -3.852 |
ality | -3.838 |
Token | M |
Token ID | 337 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ado | +0.458 |
ャ | +0.456 |
asting | +0.410 |
asted | +0.402 |
ality | +0.394 |
Neg logit contributions | |
hen | -0.773 |
ource | -0.761 |
lime | -0.751 |
cius | -0.746 |
IFT | -0.743 |
Token | itty |
Token ID | 9760 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
hen | +0.407 |
ource | +0.386 |
lime | +0.375 |
IFT | +0.371 |
ordinary | +0.367 |
Neg logit contributions | |
ado | -0.734 |
ャ | -0.728 |
asting | -0.687 |
asted | -0.685 |
ality | -0.675 |
Token | be |
Token ID | 307 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
hen | +0.292 |
ource | +0.286 |
lime | +0.283 |
RIP | +0.281 |
IFT | +0.281 |
Neg logit contributions | |
ado | -0.158 |
ャ | -0.152 |
asting | -0.141 |
asted | -0.139 |
ality | -0.136 |
Token | used |
Token ID | 973 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
hen | +1.472 |
ource | +1.433 |
lime | +1.408 |
IFT | +1.380 |
RIP | +1.379 |
Neg logit contributions | |
ado | -1.628 |
ャ | -1.596 |
asting | -1.489 |
asted | -1.487 |
ality | -1.468 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
hen | +2.250 |
ource | +2.177 |
lime | +2.139 |
IFT | +2.125 |
ordinary | +2.109 |
Neg logit contributions | |
ado | -1.659 |
ャ | -1.640 |
asting | -1.498 |
asted | -1.490 |
ality | -1.458 |
Token | highlight |
Token ID | 7238 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ado | +0.307 |
ャ | +0.300 |
asting | +0.280 |
asted | +0.277 |
ality | +0.268 |
Neg logit contributions | |
hen | -0.475 |
ource | -0.462 |
lime | -0.459 |
RIP | -0.454 |
IFT | -0.453 |
Token | or |
Token ID | 393 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
hen | +3.953 |
ource | +3.802 |
lime | +3.701 |
IFT | +3.683 |
ordinary | +3.663 |
Neg logit contributions | |
ado | -3.750 |
ャ | -3.739 |
asting | -3.449 |
asted | -3.432 |
ality | -3.351 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ado | +1.953 |
ャ | +1.887 |
asting | +1.783 |
asted | +1.765 |
ality | +1.711 |
Neg logit contributions | |
hen | -3.035 |
lime | -2.934 |
ource | -2.932 |
RIP | -2.897 |
IFT | -2.895 |
Token | something |
Token ID | 1223 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
hen | +9.629 |
ource | +9.195 |
ordinary | +8.833 |
IFT | +8.684 |
cases | +8.613 |
Neg logit contributions | |
ャ | -9.260 |
ado | -9.018 |
asting | -8.530 |
asted | -8.403 |
aste | -8.131 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
hen | +0.029 |
ource | +0.028 |
lime | +0.028 |
IFT | +0.028 |
RIP | +0.028 |
Neg logit contributions | |
ado | -0.019 |
ャ | -0.019 |
asting | -0.017 |
asted | -0.017 |
ality | -0.017 |
Token | If |
Token ID | 1002 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ado | +0.347 |
ャ | +0.345 |
asting | +0.315 |
asted | +0.312 |
ality | +0.309 |
Neg logit contributions | |
hen | -0.422 |
ource | -0.412 |
lime | -0.405 |
IFT | -0.400 |
cius | -0.397 |
Token | a |
Token ID | 257 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
hen | +0.720 |
ource | +0.697 |
lime | +0.684 |
IFT | +0.678 |
RIP | +0.675 |
Neg logit contributions | |
ado | -0.743 |
ャ | -0.732 |
asting | -0.680 |
asted | -0.677 |
ality | -0.669 |
Token | map |
Token ID | 3975 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ado | +1.426 |
ャ | +1.396 |
asting | +1.283 |
asted | +1.271 |
ality | +1.251 |
Neg logit contributions | |
hen | -2.026 |
ource | -1.968 |
lime | -1.958 |
IFT | -1.937 |
RIP | -1.922 |
Token | s |
Token ID | 82 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ャ | +1.836 |
ado | +1.831 |
asting | +1.698 |
asted | +1.694 |
ality | +1.674 |
Neg logit contributions | |
hen | -1.613 |
ource | -1.580 |
IFT | -1.534 |
RIP | -1.517 |
lime | -1.516 |
Token | third |
Token ID | 2368 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ado | +0.717 |
ャ | +0.701 |
asting | +0.647 |
asted | +0.639 |
ality | +0.634 |
Neg logit contributions | |
hen | -0.899 |
ource | -0.883 |
lime | -0.864 |
RIP | -0.851 |
IFT | -0.849 |
Token | policy |
Token ID | 2450 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ado | +0.955 |
ャ | +0.945 |
ality | +0.860 |
asting | +0.855 |
asted | +0.838 |
Neg logit contributions | |
hen | -1.232 |
ource | -1.190 |
lime | -1.169 |
RIP | -1.167 |
cius | -1.164 |
Token | is |
Token ID | 318 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
hen | +1.451 |
ource | +1.407 |
lime | +1.384 |
IFT | +1.373 |
ordinary | +1.365 |
Neg logit contributions | |
ado | -0.971 |
ャ | -0.958 |
asting | -0.869 |
asted | -0.864 |
ality | -0.851 |
Token | to |
Token ID | 284 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
hen | +0.371 |
ource | +0.363 |
lime | +0.354 |
IFT | +0.351 |
ordinary | +0.349 |
Neg logit contributions | |
ado | -0.299 |
ャ | -0.294 |
asting | -0.270 |
asted | -0.268 |
ality | -0.265 |
Token | disguise |
Token ID | 27487 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ado | +1.847 |
ャ | +1.786 |
asting | +1.696 |
asted | +1.686 |
ality | +1.601 |
Neg logit contributions | |
hen | -2.980 |
ource | -2.914 |
lime | -2.897 |
RIP | -2.861 |
IFT | -2.846 |
Token | the |
Token ID | 262 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
hen | +8.859 |
ordinary | +8.380 |
ource | +8.280 |
IFT | +8.239 |
pres | +8.043 |
Neg logit contributions | |
ャ | -9.555 |
ado | -9.525 |
asting | -8.906 |
asted | -8.840 |
iqueness | -8.515 |
Token | first |
Token ID | 717 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hen | +2.794 |
ource | +2.698 |
lime | +2.648 |
IFT | +2.630 |
ordinary | +2.611 |
Neg logit contributions | |
ado | -2.307 |
ャ | -2.283 |
asting | -2.098 |
asted | -2.089 |
ality | -2.042 |
Token | two |
Token ID | 734 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
hen | +4.667 |
ource | +4.515 |
lime | +4.429 |
IFT | +4.412 |
ordinary | +4.367 |
Neg logit contributions | |
ado | -3.456 |
ャ | -3.433 |
asting | -3.146 |
asted | -3.135 |
ality | -2.992 |
Token | in |
Token ID | 287 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
hen | +0.528 |
ource | +0.513 |
lime | +0.502 |
IFT | +0.497 |
RIP | +0.496 |
Neg logit contributions | |
ado | -0.450 |
ャ | -0.445 |
asting | -0.407 |
asted | -0.405 |
ality | -0.405 |
Token | words |
Token ID | 2456 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
hen | +2.886 |
ource | +2.792 |
lime | +2.733 |
IFT | +2.710 |
RIP | +2.694 |
Neg logit contributions | |
ado | -2.677 |
ャ | -2.642 |
asting | -2.449 |
asted | -2.437 |
ality | -2.390 |
Token | arrest |
Token ID | 3251 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ado | +1.913 |
ャ | +1.814 |
asting | +1.699 |
asted | +1.676 |
ality | +1.655 |
Neg logit contributions | |
ource | -3.709 |
hen | -3.672 |
IFT | -3.594 |
lime | -3.587 |
cius | -3.548 |
Token | warrant |
Token ID | 8084 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
hen | +0.834 |
ource | +0.811 |
lime | +0.797 |
IFT | +0.791 |
ordinary | +0.786 |
Neg logit contributions | |
ado | -0.535 |
ャ | -0.526 |
asting | -0.478 |
asted | -0.475 |
ality | -0.466 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ado | +0.831 |
ャ | +0.806 |
ality | +0.750 |
asting | +0.741 |
asted | +0.728 |
Neg logit contributions | |
hen | -1.415 |
ource | -1.396 |
lime | -1.372 |
RIP | -1.353 |
ordinary | -1.353 |
Token |
|
Token ID | 198 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
hen | +0.104 |
ource | +0.101 |
lime | +0.099 |
IFT | +0.098 |
ordinary | +0.097 |
Neg logit contributions | |
ado | -0.084 |
ャ | -0.084 |
asting | -0.077 |
asted | -0.077 |
ality | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
hen | +0.156 |
ource | +0.152 |
lime | +0.149 |
IFT | +0.148 |
cius | +0.147 |
Neg logit contributions | |
ado | -0.123 |
ャ | -0.122 |
asting | -0.112 |
asted | -0.112 |
ality | -0.110 |
Token | Wiki |
Token ID | 32603 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
hen | +0.150 |
ource | +0.148 |
lime | +0.144 |
cius | +0.144 |
IFT | +0.142 |
Neg logit contributions | |
ャ | -0.165 |
ado | -0.163 |
asting | -0.154 |
asted | -0.154 |
ality | -0.153 |
Token | Leaks |
Token ID | 17874 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
hen | +5.086 |
lime | +4.095 |
ource | +4.004 |
IFT | +3.999 |
ordinary | +3.927 |
Neg logit contributions | |
ャ | -14.379 |
ado | -13.846 |
asting | -13.188 |
asted | -13.123 |
iqueness | -12.921 |
Token | pr |
Token ID | 778 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
hen | +4.909 |
ource | +4.734 |
lime | +4.616 |
IFT | +4.572 |
ordinary | +4.545 |
Neg logit contributions | |
ado | -4.415 |
ャ | -4.412 |
asting | -4.052 |
asted | -4.032 |
ality | -3.948 |
Token | ides |
Token ID | 1460 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
hen | +3.223 |
ource | +3.044 |
lime | +2.936 |
ordinary | +2.895 |
IFT | +2.893 |
Neg logit contributions | |
ado | -5.675 |
ャ | -5.647 |
asting | -5.275 |
asted | -5.240 |
ality | -5.163 |
Token | itself |
Token ID | 2346 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hen | +1.147 |
ource | +1.099 |
lime | +1.087 |
IFT | +1.076 |
RIP | +1.061 |
Neg logit contributions | |
ado | -1.558 |
ャ | -1.544 |
asting | -1.457 |
asted | -1.453 |
ality | -1.436 |
Token | as |
Token ID | 355 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
hen | +0.773 |
ource | +0.744 |
lime | +0.729 |
IFT | +0.722 |
ordinary | +0.717 |
Neg logit contributions | |
ado | -0.698 |
ャ | -0.689 |
asted | -0.636 |
asting | -0.636 |
ality | -0.617 |
Token | girls |
Token ID | 4813 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
ado | +1.594 |
ャ | +1.553 |
asting | +1.435 |
asted | +1.428 |
ality | +1.389 |
Neg logit contributions | |
hen | -1.727 |
ource | -1.692 |
lime | -1.668 |
RIP | -1.660 |
IFT | -1.651 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hen | +0.163 |
ource | +0.158 |
lime | +0.156 |
IFT | +0.155 |
RIP | +0.155 |
Neg logit contributions | |
ado | -0.107 |
ャ | -0.106 |
asted | -0.095 |
asting | -0.095 |
ality | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
hen | +0.520 |
ource | +0.506 |
lime | +0.495 |
IFT | +0.493 |
RIP | +0.490 |
Neg logit contributions | |
ado | -0.503 |
ャ | -0.495 |
asting | -0.457 |
asted | -0.456 |
ality | -0.453 |
Token | attempt |
Token ID | 2230 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ado | +0.126 |
ャ | +0.123 |
asting | +0.113 |
asted | +0.112 |
ality | +0.112 |
Neg logit contributions | |
hen | -0.157 |
ource | -0.153 |
lime | -0.150 |
RIP | -0.150 |
IFT | -0.149 |
Token | to |
Token ID | 284 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ado | +0.631 |
ャ | +0.623 |
asting | +0.567 |
asted | +0.564 |
ality | +0.558 |
Neg logit contributions | |
hen | -0.919 |
ource | -0.895 |
IFT | -0.880 |
lime | -0.877 |
RIP | -0.873 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ado | +2.065 |
ャ | +1.992 |
asting | +1.879 |
asted | +1.872 |
ality | +1.821 |
Neg logit contributions | |
hen | -3.084 |
ource | -2.988 |
RIP | -2.982 |
lime | -2.969 |
IFT | -2.952 |
Token | or |
Token ID | 393 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
hen | +9.620 |
ordinary | +9.132 |
ource | +8.962 |
lime | +8.856 |
cases | +8.680 |
Neg logit contributions | |
ャ | -8.808 |
ado | -8.634 |
asting | -8.131 |
asted | -7.955 |
iqueness | -7.483 |
Token | overcome |
Token ID | 10980 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ado | +0.560 |
ャ | +0.546 |
asting | +0.504 |
asted | +0.500 |
ality | +0.489 |
Neg logit contributions | |
hen | -0.871 |
ource | -0.843 |
lime | -0.834 |
IFT | -0.832 |
RIP | -0.830 |
Token | nature |
Token ID | 3450 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
hen | +1.402 |
ource | +1.358 |
lime | +1.332 |
IFT | +1.323 |
RIP | +1.313 |
Neg logit contributions | |
ado | -1.197 |
ャ | -1.181 |
asting | -1.088 |
asted | -1.084 |
ality | -1.066 |
Token | by |
Token ID | 416 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
hen | +2.433 |
ource | +2.351 |
lime | +2.312 |
IFT | +2.293 |
ordinary | +2.279 |
Neg logit contributions | |
ado | -1.765 |
ャ | -1.747 |
asting | -1.594 |
asted | -1.586 |
ality | -1.546 |
Token | training |
Token ID | 3047 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
hen | +1.063 |
ource | +1.028 |
lime | +1.010 |
IFT | +1.003 |
RIP | +0.999 |
Neg logit contributions | |
ado | -0.931 |
ャ | -0.912 |
asting | -0.847 |
asted | -0.839 |
ality | -0.828 |
Token | � |
Token ID | 447 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
hen | +1.856 |
ource | +1.792 |
lime | +1.761 |
IFT | +1.749 |
ordinary | +1.737 |
Neg logit contributions | |
ado | -1.431 |
ャ | -1.416 |
asting | -1.297 |
asted | -1.291 |
ality | -1.261 |
Token | � |
Token ID | 247 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
hen | +0.660 |
ource | +0.644 |
lime | +0.629 |
IFT | +0.622 |
ordinary | +0.617 |
Neg logit contributions | |
ado | -0.654 |
ャ | -0.647 |
asting | -0.598 |
asted | -0.597 |
ality | -0.584 |
Token | s |
Token ID | 82 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
hen | +0.095 |
ource | +0.093 |
IFT | +0.090 |
lime | +0.090 |
RIP | +0.090 |
Neg logit contributions | |
ado | -0.083 |
ャ | -0.082 |
asting | -0.077 |
asted | -0.076 |
ality | -0.076 |
Token | apartment |
Token ID | 7962 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
hen | +1.538 |
ource | +1.493 |
lime | +1.466 |
IFT | +1.457 |
ordinary | +1.446 |
Neg logit contributions | |
ado | -1.101 |
ャ | -1.082 |
asting | -0.992 |
asted | -0.987 |
ality | -0.966 |
Token | and |
Token ID | 290 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ado | +3.495 |
ャ | +3.302 |
ality | +3.092 |
asting | +3.000 |
asted | +2.972 |
Neg logit contributions | |
hen | -5.967 |
ource | -5.794 |
cius | -5.774 |
RIP | -5.705 |
lime | -5.675 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ado | +0.861 |
ャ | +0.824 |
asting | +0.782 |
asted | +0.775 |
ality | +0.755 |
Neg logit contributions | |
hen | -1.312 |
ource | -1.273 |
lime | -1.261 |
IFT | -1.252 |
cius | -1.247 |
Token | under |
Token ID | 739 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
hen | +9.661 |
ource | +9.006 |
ordinary | +8.863 |
IFT | +8.753 |
lime | +8.705 |
Neg logit contributions | |
ャ | -9.018 |
ado | -8.879 |
asting | -8.228 |
asted | -8.172 |
iqueness | -7.720 |
Token | his |
Token ID | 465 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
hen | +4.555 |
ource | +4.344 |
lime | +4.279 |
IFT | +4.224 |
ordinary | +4.219 |
Neg logit contributions | |
ャ | -4.508 |
ado | -4.507 |
asting | -4.152 |
asted | -4.121 |
ality | -4.040 |
Token | bed |
Token ID | 3996 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
hen | +0.992 |
ource | +0.966 |
IFT | +0.945 |
lime | +0.945 |
cius | +0.936 |
Neg logit contributions | |
ado | -0.741 |
ャ | -0.722 |
asting | -0.666 |
asted | -0.664 |
ality | -0.649 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
hen | +2.214 |
ource | +2.144 |
lime | +2.107 |
IFT | +2.093 |
ordinary | +2.079 |
Neg logit contributions | |
ado | -1.532 |
ャ | -1.513 |
asting | -1.378 |
asted | -1.370 |
ality | -1.339 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
hen | +1.124 |
ource | +1.092 |
lime | +1.072 |
IFT | +1.065 |
RIP | +1.056 |
Neg logit contributions | |
ado | -0.881 |
ャ | -0.866 |
asting | -0.799 |
asted | -0.793 |
ality | -0.781 |
Token | f |
Token ID | 69 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ado | +0.103 |
ャ | +0.100 |
asting | +0.095 |
asted | +0.094 |
ality | +0.093 |
Neg logit contributions | |
hen | -0.096 |
ource | -0.093 |
IFT | -0.092 |
lime | -0.092 |
RIP | -0.090 |
Token | 736 |
Token ID | 49150 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
hen | +1.352 |
ource | +1.300 |
lime | +1.277 |
IFT | +1.270 |
RIP | +1.249 |
Neg logit contributions | |
ado | -1.517 |
ャ | -1.493 |
asting | -1.402 |
asted | -1.395 |
ality | -1.368 |
Token | 79 |
Token ID | 3720 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ado | +0.824 |
ャ | +0.804 |
asting | +0.759 |
asted | +0.753 |
ality | +0.744 |
Neg logit contributions | |
hen | -0.850 |
ource | -0.825 |
IFT | -0.816 |
lime | -0.812 |
RIP | -0.802 |
Token | — |
Token ID | 851 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
hen | +1.568 |
ource | +1.516 |
lime | +1.485 |
IFT | +1.482 |
ordinary | +1.460 |
Neg logit contributions | |
ado | -1.526 |
ャ | -1.501 |
asting | -1.398 |
asted | -1.391 |
ality | -1.365 |
Token | / |
Token ID | 14 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ado | +1.713 |
ャ | +1.699 |
asting | +1.565 |
asted | +1.545 |
ality | +1.529 |
Neg logit contributions | |
hen | -2.013 |
ource | -1.956 |
IFT | -1.933 |
lime | -1.917 |
ordinary | -1.900 |
Token | hide |
Token ID | 24717 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
hen | +1.517 |
ource | +1.454 |
lime | +1.417 |
IFT | +1.417 |
ordinary | +1.390 |
Neg logit contributions | |
ado | -2.021 |
ャ | -2.009 |
asting | -1.883 |
asted | -1.875 |
ality | -1.851 |
Token | ports |
Token ID | 3742 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
hen | +9.231 |
ource | +8.902 |
lime | +8.729 |
ordinary | +8.586 |
RIP | +8.517 |
Neg logit contributions | |
ado | -8.500 |
ャ | -8.462 |
asting | -7.728 |
asted | -7.715 |
ality | -7.438 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
hen | +1.562 |
ource | +1.504 |
lime | +1.483 |
IFT | +1.477 |
ordinary | +1.464 |
Neg logit contributions | |
ado | -1.323 |
ャ | -1.307 |
asting | -1.205 |
asted | -1.199 |
ality | -1.180 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
hen | +0.469 |
ource | +0.455 |
lime | +0.448 |
IFT | +0.444 |
ordinary | +0.440 |
Neg logit contributions | |
ado | -0.375 |
ャ | -0.371 |
asting | -0.342 |
asted | -0.340 |
ality | -0.334 |
Token | 022 |
Token ID | 44087 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ado | +0.858 |
ャ | +0.840 |
asting | +0.792 |
asted | +0.789 |
ality | +0.780 |
Neg logit contributions | |
hen | -0.836 |
ource | -0.814 |
IFT | -0.802 |
lime | -0.798 |
cius | -0.783 |
Token | be |
Token ID | 1350 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
hen | +0.609 |
ource | +0.588 |
IFT | +0.579 |
lime | +0.578 |
RIP | +0.569 |
Neg logit contributions | |
ado | -0.592 |
ャ | -0.581 |
asting | -0.546 |
asted | -0.543 |
ality | -0.534 |
Token | Ambassador |
Token ID | 20656 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ado | +2.782 |
ャ | +2.748 |
asting | +2.575 |
asted | +2.553 |
ality | +2.518 |
Neg logit contributions | |
hen | -3.399 |
ource | -3.287 |
lime | -3.211 |
cius | -3.205 |
RIP | -3.160 |
Token | Susan |
Token ID | 14919 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ado | +0.674 |
ャ | +0.664 |
asting | +0.614 |
asted | +0.609 |
ality | +0.603 |
Neg logit contributions | |
hen | -0.900 |
ource | -0.869 |
lime | -0.853 |
IFT | -0.851 |
RIP | -0.849 |
Token | Rice |
Token ID | 13823 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ado | +0.874 |
ャ | +0.863 |
asting | +0.791 |
asted | +0.788 |
ality | +0.774 |
Neg logit contributions | |
hen | -1.617 |
ource | -1.562 |
IFT | -1.543 |
lime | -1.543 |
RIP | -1.537 |
Token | , |
Token ID | 11 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ado | +0.754 |
ャ | +0.748 |
asting | +0.675 |
asted | +0.670 |
ality | +0.658 |
Neg logit contributions | |
hen | -1.221 |
ource | -1.190 |
lime | -1.173 |
IFT | -1.165 |
ordinary | -1.162 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ado | +1.240 |
ャ | +1.221 |
asting | +1.128 |
asted | +1.116 |
ality | +1.092 |
Neg logit contributions | |
hen | -1.697 |
ource | -1.654 |
lime | -1.631 |
IFT | -1.613 |
ordinary | -1.604 |
Token | Special |
Token ID | 6093 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
ado | +0.670 |
ャ | +0.658 |
asting | +0.613 |
asted | +0.611 |
ality | +0.596 |
Neg logit contributions | |
hen | -0.837 |
ource | -0.812 |
lime | -0.804 |
IFT | -0.793 |
ordinary | -0.788 |
Token | Assistant |
Token ID | 15286 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
hen | +8.576 |
ordinary | +8.020 |
ource | +7.898 |
lime | +7.877 |
pres | +7.710 |
Neg logit contributions | |
ャ | -9.437 |
ado | -9.252 |
asting | -8.459 |
asted | -8.448 |
ality | -8.230 |
Token | Samantha |
Token ID | 34778 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
hen | +3.952 |
ource | +3.818 |
lime | +3.725 |
ordinary | +3.682 |
IFT | +3.674 |
Neg logit contributions | |
ado | -3.381 |
ャ | -3.350 |
asted | -3.067 |
asting | -3.062 |
ality | -2.940 |
Token | Power |
Token ID | 4333 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
hen | +2.661 |
ource | +2.585 |
lime | +2.533 |
IFT | +2.519 |
ordinary | +2.508 |
Neg logit contributions | |
ado | -1.677 |
ャ | -1.648 |
asting | -1.481 |
asted | -1.470 |
ality | -1.429 |
Token | ), |
Token ID | 828 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
hen | +3.173 |
ource | +3.069 |
lime | +3.017 |
IFT | +2.996 |
ordinary | +2.972 |
Neg logit contributions | |
ado | -2.154 |
ャ | -2.130 |
asting | -1.932 |
asted | -1.923 |
ality | -1.872 |
Token | has |
Token ID | 468 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ado | +0.011 |
ャ | +0.010 |
asting | +0.010 |
asted | +0.010 |
ality | +0.010 |
Neg logit contributions | |
hen | -0.014 |
ource | -0.014 |
IFT | -0.013 |
lime | -0.013 |
cius | -0.013 |
Token | M |
Token ID | 44 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
hen | +0.066 |
ource | +0.066 |
cius | +0.063 |
lime | +0.063 |
IFT | +0.062 |
Neg logit contributions | |
ャ | -0.076 |
ado | -0.076 |
asted | -0.072 |
asting | -0.071 |
ality | -0.070 |
Token | ord |
Token ID | 585 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ado | +4.158 |
ャ | +4.073 |
asting | +4.018 |
asted | +4.012 |
aste | +3.912 |
Neg logit contributions | |
hen | -0.985 |
lime | -0.926 |
ource | -0.909 |
IFT | -0.872 |
RIP | -0.863 |
Token | ica |
Token ID | 3970 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ado | +5.431 |
ality | +5.277 |
asted | +5.177 |
asting | +5.147 |
aste | +5.120 |
Neg logit contributions | |
IFT | -7.126 |
hen | -7.066 |
RIP | -6.996 |
ource | -6.821 |
lime | -6.694 |
Token | is |
Token ID | 318 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
hen | +3.361 |
ource | +3.240 |
lime | +3.184 |
IFT | +3.160 |
ordinary | +3.143 |
Neg logit contributions | |
ado | -2.506 |
ャ | -2.478 |
asting | -2.269 |
asted | -2.255 |
ality | -2.202 |
Token | the |
Token ID | 262 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
hen | +2.373 |
ource | +2.297 |
lime | +2.248 |
IFT | +2.231 |
ordinary | +2.207 |
Neg logit contributions | |
ado | -2.222 |
ャ | -2.193 |
asting | -2.035 |
asted | -2.026 |
ality | -1.985 |
Token | fastest |
Token ID | 14162 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
hen | +2.379 |
ource | +2.310 |
lime | +2.269 |
IFT | +2.250 |
RIP | +2.230 |
Neg logit contributions | |
ado | -1.717 |
ャ | -1.689 |
asting | -1.544 |
asted | -1.536 |
ality | -1.501 |
Token | back |
Token ID | 736 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
hen | +9.019 |
ource | +8.491 |
ordinary | +8.300 |
lime | +8.252 |
IFT | +8.143 |
Neg logit contributions | |
ャ | -8.712 |
ado | -8.637 |
asting | -7.925 |
asted | -7.881 |
aste | -7.677 |
Token | we |
Token ID | 356 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hen | +5.623 |
ource | +5.386 |
lime | +5.297 |
IFT | +5.241 |
ordinary | +5.227 |
Neg logit contributions | |
ado | -4.776 |
ャ | -4.743 |
asting | -4.346 |
asted | -4.338 |
ality | -4.175 |
Token | � |
Token ID | 447 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
hen | +3.737 |
ource | +3.577 |
lime | +3.507 |
IFT | +3.476 |
ordinary | +3.460 |
Neg logit contributions | |
ado | -3.321 |
ャ | -3.298 |
asting | -3.017 |
asted | -2.995 |
ality | -2.941 |
Token | � |
Token ID | 247 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
hen | +1.098 |
ource | +1.069 |
lime | +1.047 |
IFT | +1.029 |
ordinary | +1.023 |
Neg logit contributions | |
ado | -1.105 |
ャ | -1.087 |
asting | -1.004 |
asted | -1.004 |
ality | -0.981 |
Token | ve |
Token ID | 303 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ado | +1.274 |
ャ | +1.261 |
asted | +1.212 |
asting | +1.203 |
ality | +1.173 |
Neg logit contributions | |
hen | -1.079 |
IFT | -1.076 |
ource | -1.064 |
lime | -1.043 |
RIP | -1.038 |
Token | Berg |
Token ID | 24626 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
ado | +0.904 |
ャ | +0.876 |
asting | +0.825 |
asted | +0.816 |
ality | +0.794 |
Neg logit contributions | |
hen | -1.143 |
ource | -1.118 |
lime | -1.095 |
IFT | -1.088 |
cius | -1.077 |
Token | man |
Token ID | 805 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ado | +0.203 |
ャ | +0.202 |
asting | +0.189 |
asted | +0.189 |
ality | +0.185 |
Neg logit contributions | |
hen | -0.204 |
ource | -0.200 |
IFT | -0.197 |
cius | -0.196 |
lime | -0.195 |
Token | esque |
Token ID | 28939 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ado | +1.073 |
ャ | +1.058 |
asting | +0.981 |
asted | +0.971 |
ality | +0.948 |
Neg logit contributions | |
hen | -1.384 |
ource | -1.366 |
lime | -1.334 |
IFT | -1.331 |
cius | -1.317 |
Token | chamber |
Token ID | 11847 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ado | +2.551 |
ャ | +2.486 |
asting | +2.329 |
asted | +2.302 |
ality | +2.272 |
Neg logit contributions | |
hen | -3.180 |
ource | -3.144 |
lime | -3.070 |
IFT | -3.047 |
cius | -3.032 |
Token | piece |
Token ID | 3704 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ado | +1.316 |
ャ | +1.288 |
asting | +1.199 |
asted | +1.186 |
ality | +1.179 |
Neg logit contributions | |
hen | -1.568 |
ource | -1.560 |
IFT | -1.512 |
lime | -1.508 |
RIP | -1.502 |
Token | Inter |
Token ID | 4225 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ado | +2.250 |
ャ | +2.154 |
asting | +2.004 |
asted | +1.996 |
ality | +1.995 |
Neg logit contributions | |
hen | -3.147 |
ource | -3.132 |
lime | -3.061 |
cius | -3.050 |
IFT | -3.026 |
Token | iors |
Token ID | 12706 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ado | +4.792 |
ality | +4.731 |
ャ | +4.684 |
asted | +4.577 |
asting | +4.556 |
Neg logit contributions | |
ource | -9.254 |
IFT | -9.085 |
hen | -8.978 |
RIP | -8.826 |
lime | -8.735 |
Token | as |
Token ID | 355 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ado | +1.127 |
ャ | +1.093 |
asting | +0.993 |
asted | +0.990 |
ality | +0.981 |
Neg logit contributions | |
hen | -1.640 |
ource | -1.599 |
lime | -1.583 |
IFT | -1.567 |
cius | -1.559 |
Token | a |
Token ID | 257 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
hen | +1.100 |
ource | +1.069 |
lime | +1.048 |
IFT | +1.039 |
RIP | +1.029 |
Neg logit contributions | |
ado | -1.012 |
ャ | -0.993 |
asting | -0.922 |
asted | -0.918 |
ality | -0.901 |
Token | film |
Token ID | 2646 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
hen | +0.323 |
ource | +0.314 |
lime | +0.308 |
IFT | +0.306 |
RIP | +0.303 |
Neg logit contributions | |
ado | -0.251 |
ャ | -0.246 |
asting | -0.226 |
asted | -0.225 |
ality | -0.220 |
Token | that |
Token ID | 326 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
hen | +1.402 |
ource | +1.357 |
lime | +1.333 |
IFT | +1.324 |
ordinary | +1.314 |
Neg logit contributions | |
ado | -1.057 |
ャ | -1.045 |
asting | -0.956 |
asted | -0.951 |
ality | -0.930 |
Token | , |
Token ID | 11 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
ado | +1.354 |
ャ | +1.308 |
asting | +1.193 |
ality | +1.181 |
asted | +1.179 |
Neg logit contributions | |
hen | -1.906 |
ource | -1.852 |
lime | -1.831 |
RIP | -1.818 |
IFT | -1.816 |
Token | Trump |
Token ID | 1301 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ado | +1.828 |
ャ | +1.792 |
asting | +1.632 |
ality | +1.626 |
asted | +1.610 |
Neg logit contributions | |
hen | -2.009 |
ource | -1.945 |
lime | -1.944 |
RIP | -1.929 |
IFT | -1.921 |
Token | � |
Token ID | 447 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ado | +1.744 |
ャ | +1.699 |
asting | +1.559 |
asted | +1.544 |
ality | +1.526 |
Neg logit contributions | |
hen | -2.160 |
lime | -2.084 |
RIP | -2.077 |
ource | -2.074 |
IFT | -2.052 |
Token | � |
Token ID | 247 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ado | +1.873 |
ャ | +1.820 |
asted | +1.688 |
asting | +1.673 |
ality | +1.627 |
Neg logit contributions | |
hen | -2.125 |
ource | -2.110 |
lime | -2.063 |
cius | -2.029 |
IFT | -2.018 |
Token | s |
Token ID | 82 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
ado | +3.317 |
ャ | +3.270 |
asting | +3.054 |
asted | +3.023 |
ality | +2.983 |
Neg logit contributions | |
hen | -3.151 |
ource | -3.015 |
RIP | -3.011 |
IFT | -2.985 |
lime | -2.968 |
Token | revenue |
Token ID | 6426 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
ado | +2.090 |
ャ | +1.989 |
asting | +1.836 |
asted | +1.813 |
ality | +1.810 |
Neg logit contributions | |
hen | -2.931 |
lime | -2.812 |
ource | -2.807 |
RIP | -2.803 |
IFT | -2.787 |
Token | in |
Token ID | 287 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ado | +6.636 |
ャ | +6.111 |
ality | +5.866 |
asted | +5.626 |
asting | +5.416 |
Neg logit contributions | |
hen | -9.602 |
RIP | -9.451 |
lime | -9.439 |
cius | -9.313 |
ource | -9.301 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ado | +1.110 |
ャ | +1.086 |
asting | +1.005 |
ality | +0.998 |
asted | +0.993 |
Neg logit contributions | |
hen | -1.276 |
ource | -1.246 |
lime | -1.244 |
RIP | -1.235 |
IFT | -1.233 |
Token | and |
Token ID | 290 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ado | +2.345 |
ャ | +2.268 |
asted | +2.055 |
ality | +2.031 |
asting | +2.025 |
Neg logit contributions | |
hen | -3.706 |
ource | -3.622 |
lime | -3.604 |
RIP | -3.580 |
IFT | -3.555 |
Token | early |
Token ID | 1903 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
ado | +2.303 |
ャ | +2.247 |
ality | +2.091 |
asting | +2.077 |
asted | +2.051 |
Neg logit contributions | |
hen | -2.561 |
lime | -2.515 |
ource | -2.486 |
IFT | -2.472 |
RIP | -2.459 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
hen | +2.599 |
ource | +2.496 |
lime | +2.442 |
IFT | +2.423 |
ordinary | +2.403 |
Neg logit contributions | |
ado | -2.839 |
ャ | -2.813 |
asting | -2.616 |
asted | -2.607 |
ality | -2.556 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ado | +0.710 |
ャ | +0.695 |
asting | +0.630 |
asted | +0.628 |
ality | +0.627 |
Neg logit contributions | |
hen | -1.045 |
ource | -1.014 |
lime | -1.004 |
IFT | -0.994 |
RIP | -0.992 |
Token | Merc |
Token ID | 12185 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ャ | +1.461 |
ado | +1.439 |
asting | +1.305 |
asted | +1.303 |
ality | +1.297 |
Neg logit contributions | |
hen | -1.843 |
ource | -1.812 |
cius | -1.781 |
lime | -1.779 |
IFT | -1.757 |
Token | enaries |
Token ID | 30216 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ado | +0.504 |
ャ | +0.500 |
asting | +0.475 |
asted | +0.473 |
ality | +0.460 |
Neg logit contributions | |
hen | -0.357 |
ource | -0.344 |
lime | -0.339 |
IFT | -0.337 |
RIP | -0.332 |
Token | have |
Token ID | 423 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
hen | +3.527 |
ource | +3.410 |
lime | +3.346 |
IFT | +3.319 |
ordinary | +3.294 |
Neg logit contributions | |
ado | -2.798 |
ャ | -2.777 |
asting | -2.542 |
asted | -2.529 |
ality | -2.474 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
hen | +0.073 |
ource | +0.071 |
lime | +0.070 |
IFT | +0.069 |
RIP | +0.069 |
Neg logit contributions | |
ado | -0.065 |
ャ | -0.064 |
asted | -0.059 |
asting | -0.059 |
ality | -0.058 |
Token | ton |
Token ID | 5680 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ado | +0.695 |
ャ | +0.695 |
asted | +0.633 |
asting | +0.633 |
ality | +0.621 |
Neg logit contributions | |
hen | -0.880 |
ource | -0.860 |
lime | -0.846 |
IFT | -0.839 |
RIP | -0.838 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ャ | +6.909 |
ado | +6.746 |
ality | +6.582 |
asted | +6.074 |
asting | +6.018 |
Neg logit contributions | |
hen | -10.872 |
ource | -10.737 |
ordinary | -10.649 |
RIP | -10.566 |
IFT | -10.520 |
Token | great |
Token ID | 1049 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
hen | +0.358 |
ource | +0.347 |
lime | +0.340 |
IFT | +0.337 |
RIP | +0.337 |
Neg logit contributions | |
ado | -0.305 |
ャ | -0.302 |
asting | -0.278 |
asted | -0.278 |
ality | -0.273 |
Token | � |
Token ID | 564 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ado | +1.848 |
ャ | +1.843 |
ality | +1.688 |
asted | +1.684 |
asting | +1.682 |
Neg logit contributions | |
hen | -2.020 |
ource | -1.970 |
RIP | -1.927 |
cius | -1.924 |
lime | -1.909 |
Token | � |
Token ID | 247 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
hen | +2.989 |
ource | +2.870 |
lime | +2.810 |
IFT | +2.786 |
ordinary | +2.762 |
Neg logit contributions | |
ado | -3.311 |
ャ | -3.281 |
asting | -3.053 |
asted | -3.041 |
ality | -2.986 |
Token | jack |
Token ID | 19650 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
hen | +1.541 |
ource | +1.499 |
IFT | +1.449 |
lime | +1.447 |
cius | +1.437 |
Neg logit contributions | |
ャ | -1.608 |
ado | -1.606 |
asting | -1.493 |
asted | -1.490 |
ality | -1.475 |
Token | and |
Token ID | 392 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
hen | +0.162 |
ource | +0.160 |
IFT | +0.156 |
cius | +0.153 |
RIP | +0.152 |
Neg logit contributions | |
ャ | -0.223 |
ado | -0.222 |
asting | -0.212 |
asted | -0.211 |
ality | -0.210 |
Token | - |
Token ID | 12 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ado | +0.528 |
ャ | +0.527 |
asting | +0.486 |
asted | +0.484 |
ality | +0.471 |
Neg logit contributions | |
hen | -0.728 |
ource | -0.713 |
IFT | -0.698 |
lime | -0.697 |
RIP | -0.692 |
Token | white |
Token ID | 11186 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
hen | +2.031 |
ource | +1.954 |
lime | +1.888 |
IFT | +1.886 |
RIP | +1.858 |
Neg logit contributions | |
ado | -2.902 |
ャ | -2.890 |
asting | -2.715 |
asted | -2.708 |
ality | -2.659 |
Token | photos |
Token ID | 5205 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ado | +2.339 |
ャ | +2.272 |
asting | +2.138 |
ality | +2.116 |
asted | +2.103 |
Neg logit contributions | |
hen | -2.434 |
ource | -2.411 |
IFT | -2.322 |
cius | -2.318 |
lime | -2.318 |
Token | of |
Token ID | 286 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
hen | +0.929 |
ource | +0.902 |
lime | +0.886 |
IFT | +0.881 |
ordinary | +0.875 |
Neg logit contributions | |
ado | -0.647 |
ャ | -0.641 |
asting | -0.585 |
asted | -0.580 |
ality | -0.570 |
Token | urban |
Token ID | 7876 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
hen | +0.133 |
ource | +0.130 |
lime | +0.127 |
IFT | +0.127 |
RIP | +0.126 |
Neg logit contributions | |
ado | -0.119 |
ャ | -0.117 |
asting | -0.109 |
asted | -0.109 |
ality | -0.107 |
Token | life |
Token ID | 1204 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ado | +6.142 |
ャ | +5.945 |
ality | +5.685 |
asting | +5.406 |
asted | +5.328 |
Neg logit contributions | |
ource | -7.381 |
hen | -7.318 |
cius | -7.139 |
RIP | -7.041 |
lime | -7.030 |
Token | . |
Token ID | 13 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
ado | +1.538 |
ャ | +1.517 |
ality | +1.364 |
asting | +1.362 |
asted | +1.347 |
Neg logit contributions | |
hen | -2.421 |
ource | -2.387 |
lime | -2.343 |
IFT | -2.340 |
RIP | -2.313 |
Token | The |
Token ID | 383 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ado | +0.148 |
ャ | +0.147 |
asting | +0.135 |
asted | +0.134 |
ality | +0.132 |
Neg logit contributions | |
hen | -0.179 |
ource | -0.176 |
lime | -0.172 |
IFT | -0.171 |
cius | -0.171 |
Token | influence |
Token ID | 4588 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
hen | +0.344 |
ource | +0.334 |
lime | +0.327 |
IFT | +0.323 |
RIP | +0.321 |
Neg logit contributions | |
ado | -0.348 |
ャ | -0.340 |
asting | -0.319 |
asted | -0.317 |
ality | -0.312 |
Token | is |
Token ID | 318 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
hen | +0.904 |
ource | +0.888 |
IFT | +0.865 |
lime | +0.865 |
RIP | +0.858 |
Neg logit contributions | |
ado | -0.662 |
ャ | -0.647 |
ality | -0.591 |
asting | -0.590 |
asted | -0.588 |
Token | competitive |
Token ID | 7606 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ado | +0.243 |
ャ | +0.238 |
asting | +0.221 |
asted | +0.219 |
ality | +0.215 |
Neg logit contributions | |
hen | -0.295 |
ource | -0.284 |
lime | -0.281 |
IFT | -0.280 |
RIP | -0.278 |
Token | bids |
Token ID | 27837 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ado | +3.832 |
ャ | +3.642 |
ality | +3.472 |
asting | +3.461 |
asted | +3.400 |
Neg logit contributions | |
hen | -4.614 |
ource | -4.468 |
IFT | -4.426 |
lime | -4.387 |
cius | -4.373 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ado | +1.450 |
ャ | +1.417 |
asting | +1.297 |
ality | +1.296 |
asted | +1.279 |
Neg logit contributions | |
hen | -2.149 |
ource | -2.076 |
RIP | -2.074 |
IFT | -2.064 |
lime | -2.056 |
Token | an |
Token ID | 281 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ado | +0.355 |
ャ | +0.347 |
asting | +0.321 |
asted | +0.319 |
ality | +0.315 |
Neg logit contributions | |
hen | -0.449 |
ource | -0.435 |
lime | -0.431 |
IFT | -0.428 |
RIP | -0.424 |
Token | expensive |
Token ID | 5789 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ado | +1.122 |
ャ | +1.080 |
asted | +1.009 |
asting | +1.008 |
ality | +1.005 |
Neg logit contributions | |
hen | -1.421 |
ource | -1.371 |
lime | -1.370 |
IFT | -1.345 |
RIP | -1.332 |
Token | inter |
Token ID | 987 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ado | +0.934 |
ャ | +0.910 |
asting | +0.840 |
asted | +0.834 |
ality | +0.828 |
Neg logit contributions | |
hen | -1.219 |
ource | -1.174 |
lime | -1.164 |
IFT | -1.159 |
RIP | -1.148 |
Token | - |
Token ID | 12 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ャ | +5.946 |
asting | +5.726 |
ality | +5.683 |
ado | +5.573 |
asted | +5.544 |
Neg logit contributions | |
hen | -7.055 |
IFT | -6.837 |
RIP | -6.786 |
ource | -6.692 |
cius | -6.670 |
Token | is |
Token ID | 271 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
hen | +0.995 |
ource | +0.956 |
lime | +0.936 |
IFT | +0.935 |
RIP | +0.925 |
Neg logit contributions | |
ado | -1.017 |
ャ | -1.015 |
asting | -0.948 |
asted | -0.942 |
ality | -0.932 |
Token | land |
Token ID | 1044 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
hen | +2.798 |
ource | +2.679 |
lime | +2.649 |
IFT | +2.636 |
ordinary | +2.618 |
Neg logit contributions | |
ado | -2.729 |
ャ | -2.719 |
asting | -2.529 |
asted | -2.515 |
ality | -2.478 |
Token | under |
Token ID | 739 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ado | +0.178 |
ャ | +0.175 |
asting | +0.161 |
asted | +0.160 |
ality | +0.158 |
Neg logit contributions | |
hen | -0.218 |
ource | -0.211 |
lime | -0.207 |
IFT | -0.206 |
RIP | -0.204 |
Token | sea |
Token ID | 8583 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hen | +2.409 |
ource | +2.300 |
lime | +2.243 |
IFT | +2.221 |
ordinary | +2.199 |
Neg logit contributions | |
ado | -3.357 |
ャ | -3.328 |
asting | -3.116 |
asted | -3.106 |
ality | -3.056 |
Token | the |
Token ID | 262 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
hen | +3.419 |
ource | +3.288 |
lime | +3.229 |
IFT | +3.204 |
ordinary | +3.177 |
Neg logit contributions | |
ado | -3.142 |
ャ | -3.114 |
asting | -2.875 |
asted | -2.860 |
ality | -2.801 |
Token | only |
Token ID | 691 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
hen | +2.648 |
ource | +2.558 |
lime | +2.513 |
IFT | +2.495 |
ordinary | +2.478 |
Neg logit contributions | |
ado | -2.035 |
ャ | -2.013 |
asting | -1.842 |
asted | -1.833 |
ality | -1.793 |
Token | democracy |
Token ID | 7996 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
hen | +5.866 |
ource | +5.607 |
ordinary | +5.545 |
IFT | +5.488 |
lime | +5.455 |
Neg logit contributions | |
ado | -5.005 |
ャ | -4.988 |
asted | -4.594 |
asting | -4.582 |
ality | -4.340 |
Token | in |
Token ID | 287 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
hen | +1.646 |
ource | +1.596 |
lime | +1.575 |
IFT | +1.565 |
RIP | +1.549 |
Neg logit contributions | |
ado | -1.268 |
ャ | -1.250 |
asting | -1.146 |
asted | -1.138 |
ality | -1.133 |
Token | the |
Token ID | 262 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
hen | +2.903 |
ource | +2.789 |
lime | +2.736 |
IFT | +2.718 |
ordinary | +2.703 |
Neg logit contributions | |
ado | -2.542 |
ャ | -2.519 |
asting | -2.316 |
asted | -2.304 |
ality | -2.255 |
Token | Middle |
Token ID | 6046 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
hen | +2.354 |
ource | +2.266 |
lime | +2.221 |
IFT | +2.207 |
ordinary | +2.189 |
Neg logit contributions | |
ado | -2.168 |
ャ | -2.148 |
asting | -1.983 |
asted | -1.975 |
ality | -1.936 |
Token | East |
Token ID | 3687 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ャ | +1.447 |
ado | +1.438 |
asting | +1.326 |
asted | +1.324 |
ality | +1.315 |
Neg logit contributions | |
hen | -2.360 |
ource | -2.353 |
lime | -2.322 |
RIP | -2.321 |
IFT | -2.268 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
ado | +0.535 |
ャ | +0.534 |
asting | +0.484 |
ality | +0.483 |
asted | +0.481 |
Neg logit contributions | |
hen | -0.734 |
ource | -0.720 |
lime | -0.711 |
IFT | -0.700 |
RIP | -0.699 |
Token | A |
Token ID | 317 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
hen | +1.618 |
ource | +1.565 |
lime | +1.536 |
IFT | +1.522 |
ordinary | +1.506 |
Neg logit contributions | |
ado | -1.488 |
ャ | -1.478 |
asting | -1.362 |
asted | -1.356 |
ality | -1.332 |
Token | land |
Token ID | 1956 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
hen | +1.143 |
ource | +1.108 |
lime | +1.088 |
IFT | +1.079 |
RIP | +1.072 |
Neg logit contributions | |
ado | -0.984 |
ャ | -0.982 |
asting | -0.902 |
asted | -0.896 |
ality | -0.881 |
Token | where |
Token ID | 810 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
hen | +1.772 |
ource | +1.717 |
lime | +1.684 |
IFT | +1.674 |
ordinary | +1.663 |
Neg logit contributions | |
ado | -1.476 |
ャ | -1.462 |
asting | -1.343 |
asted | -1.337 |
ality | -1.316 |
Token | , |
Token ID | 837 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ado | +0.702 |
ャ | +0.697 |
asting | +0.628 |
asted | +0.626 |
ality | +0.610 |
Neg logit contributions | |
hen | -1.080 |
ource | -1.051 |
lime | -1.044 |
cius | -1.032 |
IFT | -1.030 |
Token | c |
Token ID | 269 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ado | +2.641 |
ャ | +2.453 |
asting | +2.219 |
asted | +2.184 |
ality | +2.153 |
Neg logit contributions | |
hen | -5.617 |
IFT | -5.582 |
RIP | -5.497 |
ource | -5.496 |
lime | -5.478 |
Token | v |
Token ID | 85 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
hen | +0.990 |
ource | +0.953 |
lime | +0.935 |
IFT | +0.929 |
RIP | +0.918 |
Neg logit contributions | |
ado | -1.101 |
ャ | -1.091 |
asting | -1.017 |
asted | -1.014 |
ality | -0.997 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ado | +0.310 |
ャ | +0.308 |
asting | +0.284 |
asted | +0.284 |
ality | +0.282 |
Neg logit contributions | |
hen | -0.338 |
ource | -0.328 |
lime | -0.323 |
IFT | -0.322 |
cius | -0.321 |
Token | . |
Token ID | 764 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ado | +2.114 |
ャ | +2.085 |
asting | +1.917 |
asted | +1.916 |
ality | +1.902 |
Neg logit contributions | |
hen | -3.383 |
ource | -3.306 |
lime | -3.305 |
cius | -3.290 |
IFT | -3.265 |
Token | COL |
Token ID | 20444 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ado | +2.924 |
ャ | +2.835 |
asting | +2.625 |
ality | +2.608 |
asted | +2.574 |
Neg logit contributions | |
hen | -3.569 |
ource | -3.496 |
lime | -3.409 |
RIP | -3.368 |
IFT | -3.362 |
Token | OR |
Token ID | 1581 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ado | +3.959 |
ャ | +3.934 |
asting | +3.767 |
asted | +3.708 |
ality | +3.692 |
Neg logit contributions | |
hen | -4.287 |
lime | -4.206 |
ource | -4.196 |
cius | -4.182 |
achev | -4.031 |
Token | _ |
Token ID | 62 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ャ | +3.250 |
ado | +3.115 |
asting | +2.872 |
ality | +2.864 |
asted | +2.827 |
Neg logit contributions | |
hen | -6.177 |
cius | -6.142 |
ource | -6.078 |
lime | -6.071 |
achev | -5.981 |
Token | B |
Token ID | 33 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ャ | +0.030 |
ado | +0.029 |
asting | +0.027 |
asted | +0.027 |
ality | +0.027 |
Neg logit contributions | |
hen | -0.037 |
ource | -0.037 |
lime | -0.036 |
cius | -0.036 |
ordinary | -0.035 |
Token | GR |
Token ID | 10761 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ャ | +2.813 |
ado | +2.810 |
asting | +2.669 |
asted | +2.668 |
ality | +2.580 |
Neg logit contributions | |
hen | -2.225 |
ource | -2.130 |
cius | -2.115 |
lime | -2.094 |
cases | -2.055 |
Token | 2 |
Token ID | 17 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ado | +0.627 |
ャ | +0.627 |
asting | +0.578 |
asted | +0.578 |
ality | +0.565 |
Neg logit contributions | |
hen | -0.667 |
ource | -0.647 |
lime | -0.637 |
cius | -0.632 |
ordinary | -0.625 |
Token | those |
Token ID | 883 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
hen | +1.298 |
ource | +1.252 |
lime | +1.229 |
IFT | +1.216 |
RIP | +1.212 |
Neg logit contributions | |
ado | -1.282 |
ャ | -1.268 |
asting | -1.176 |
asted | -1.170 |
ality | -1.153 |
Token | who |
Token ID | 508 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
hen | +2.194 |
ource | +2.112 |
lime | +2.072 |
IFT | +2.052 |
ordinary | +2.032 |
Neg logit contributions | |
ado | -2.284 |
ャ | -2.261 |
asting | -2.097 |
asted | -2.089 |
ality | -2.055 |
Token | are |
Token ID | 389 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
hen | +2.180 |
ource | +2.103 |
lime | +2.063 |
IFT | +2.048 |
ordinary | +2.033 |
Neg logit contributions | |
ado | -1.896 |
ャ | -1.878 |
asting | -1.730 |
asted | -1.722 |
ality | -1.686 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
hen | +1.689 |
ource | +1.642 |
lime | +1.614 |
IFT | +1.602 |
RIP | +1.597 |
Neg logit contributions | |
ado | -1.109 |
ャ | -1.094 |
asting | -0.987 |
asted | -0.982 |
ality | -0.966 |
Token | When |
Token ID | 1649 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
ャ | +0.705 |
ado | +0.700 |
asting | +0.631 |
ality | +0.628 |
asted | +0.625 |
Neg logit contributions | |
hen | -0.914 |
ource | -0.898 |
lime | -0.887 |
cius | -0.873 |
IFT | -0.872 |
Token | Trudeau |
Token ID | 17524 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
hen | +2.411 |
ource | +2.322 |
lime | +2.281 |
IFT | +2.258 |
RIP | +2.239 |
Neg logit contributions | |
ado | -2.482 |
ャ | -2.451 |
asting | -2.276 |
asted | -2.265 |
ality | -2.230 |
Token | chose |
Token ID | 7690 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ado | +0.800 |
ャ | +0.785 |
asted | +0.728 |
asting | +0.725 |
ality | +0.711 |
Neg logit contributions | |
hen | -0.923 |
ource | -0.900 |
lime | -0.890 |
IFT | -0.882 |
RIP | -0.873 |
Token | St |
Token ID | 520 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
hen | +0.738 |
ource | +0.713 |
lime | +0.700 |
IFT | +0.696 |
RIP | +0.690 |
Neg logit contributions | |
ado | -0.650 |
ャ | -0.641 |
asting | -0.592 |
asted | -0.591 |
ality | -0.579 |
Token | é |
Token ID | 2634 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ado | +1.425 |
ャ | +1.382 |
asting | +1.322 |
asted | +1.303 |
ality | +1.264 |
Neg logit contributions | |
hen | -1.758 |
ource | -1.721 |
lime | -1.688 |
RIP | -1.677 |
IFT | -1.667 |
Token | ph |
Token ID | 746 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
ado | +0.554 |
ャ | +0.543 |
asting | +0.505 |
asted | +0.499 |
ality | +0.492 |
Neg logit contributions | |
hen | -0.507 |
ource | -0.493 |
IFT | -0.490 |
RIP | -0.485 |
lime | -0.483 |
Token | ane |
Token ID | 1531 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ado | +0.090 |
ャ | +0.088 |
asting | +0.084 |
asted | +0.083 |
ality | +0.082 |
Neg logit contributions | |
hen | -0.081 |
ource | -0.078 |
IFT | -0.077 |
lime | -0.076 |
RIP | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ado | +4.106 |
ャ | +4.029 |
ality | +3.760 |
asting | +3.659 |
asted | +3.589 |
Neg logit contributions | |
hen | -5.846 |
RIP | -5.822 |
lime | -5.640 |
IFT | -5.619 |
ource | -5.602 |
Token | as |
Token ID | 355 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ado | +1.188 |
ャ | +1.165 |
asting | +1.078 |
asted | +1.075 |
ality | +1.071 |
Neg logit contributions | |
hen | -1.310 |
ource | -1.276 |
lime | -1.251 |
RIP | -1.247 |
IFT | -1.243 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
hen | +1.602 |
ource | +1.551 |
lime | +1.525 |
IFT | +1.513 |
RIP | +1.502 |
Neg logit contributions | |
ado | -1.581 |
ャ | -1.559 |
asting | -1.444 |
asted | -1.440 |
ality | -1.422 |
Token | top |
Token ID | 1353 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
hen | +0.090 |
ource | +0.087 |
lime | +0.086 |
RIP | +0.085 |
IFT | +0.085 |
Neg logit contributions | |
ado | -0.077 |
ャ | -0.076 |
asting | -0.070 |
asted | -0.070 |
ality | -0.068 |
Token | political |
Token ID | 1964 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
hen | +1.174 |
ource | +1.136 |
lime | +1.115 |
RIP | +1.105 |
IFT | +1.103 |
Neg logit contributions | |
ado | -1.109 |
ャ | -1.092 |
asting | -1.011 |
asted | -1.002 |
ality | -1.001 |
Token | and |
Token ID | 290 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
hen | +1.547 |
ource | +1.501 |
lime | +1.474 |
IFT | +1.458 |
RIP | +1.451 |
Neg logit contributions | |
ado | -1.376 |
ャ | -1.351 |
asting | -1.247 |
asted | -1.237 |
ality | -1.227 |
Token | executive |
Token ID | 4640 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ado | +1.067 |
ャ | +1.043 |
asting | +0.956 |
ality | +0.951 |
asted | +0.945 |
Neg logit contributions | |
hen | -1.440 |
ource | -1.400 |
lime | -1.387 |
RIP | -1.369 |
IFT | -1.356 |
Token | office |
Token ID | 2607 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
hen | +0.953 |
ource | +0.919 |
lime | +0.899 |
IFT | +0.887 |
RIP | +0.885 |
Neg logit contributions | |
ado | -1.090 |
ャ | -1.079 |
asting | -1.004 |
asted | -0.998 |
ality | -0.992 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ado | +1.917 |
ャ | +1.906 |
ality | +1.815 |
asting | +1.792 |
asted | +1.778 |
Neg logit contributions | |
hen | -0.871 |
ource | -0.823 |
lime | -0.821 |
RIP | -0.797 |
IFT | -0.787 |
Token | cities |
Token ID | 4736 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
hen | +0.563 |
ource | +0.547 |
lime | +0.540 |
RIP | +0.536 |
IFT | +0.532 |
Neg logit contributions | |
ado | -0.495 |
ャ | -0.486 |
asting | -0.451 |
asted | -0.451 |
ality | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ado | +2.536 |
ャ | +2.505 |
ality | +2.241 |
asting | +2.215 |
asted | +2.213 |
Neg logit contributions | |
hen | -4.382 |
lime | -4.241 |
RIP | -4.228 |
ource | -4.225 |
IFT | -4.193 |
Token | Local |
Token ID | 14565 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ャ | +0.985 |
ado | +0.981 |
asted | +0.931 |
asting | +0.926 |
ality | +0.916 |
Neg logit contributions | |
hen | -0.833 |
ource | -0.816 |
cius | -0.795 |
lime | -0.791 |
IFT | -0.780 |
Token | tourist |
Token ID | 18473 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
hen | +2.054 |
ource | +1.980 |
lime | +1.939 |
IFT | +1.926 |
RIP | +1.907 |
Neg logit contributions | |
ado | -2.068 |
ャ | -2.044 |
asting | -1.897 |
asted | -1.891 |
ality | -1.860 |
Token | site |
Token ID | 2524 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
hen | +1.241 |
ource | +1.205 |
lime | +1.185 |
IFT | +1.173 |
RIP | +1.165 |
Neg logit contributions | |
ado | -1.083 |
ャ | -1.054 |
asting | -0.988 |
asted | -0.980 |
ality | -0.962 |
Token | Fort |
Token ID | 6401 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
hen | +3.951 |
ource | +3.808 |
lime | +3.734 |
IFT | +3.703 |
ordinary | +3.677 |
Neg logit contributions | |
ado | -3.159 |
ャ | -3.139 |
asting | -2.866 |
asted | -2.849 |
ality | -2.783 |
Token | de |
Token ID | 390 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ado | +0.977 |
ャ | +0.948 |
asting | +0.900 |
ality | +0.893 |
asted | +0.892 |
Neg logit contributions | |
hen | -1.118 |
ource | -1.105 |
IFT | -1.095 |
RIP | -1.093 |
lime | -1.091 |
Token | Bre |
Token ID | 3719 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
hen | +4.138 |
ource | +3.985 |
lime | +3.909 |
IFT | +3.857 |
ordinary | +3.838 |
Neg logit contributions | |
ado | -3.189 |
ャ | -3.173 |
asting | -2.884 |
asted | -2.872 |
ality | -2.806 |
Token | gan |
Token ID | 1030 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ado | +1.255 |
ャ | +1.202 |
asting | +1.183 |
asted | +1.175 |
ality | +1.158 |
Neg logit contributions | |
IFT | -1.286 |
ource | -1.280 |
hen | -1.279 |
lime | -1.266 |
RIP | -1.264 |
Token | con |
Token ID | 1102 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ado | +0.545 |
ャ | +0.532 |
asted | +0.501 |
asting | +0.499 |
ality | +0.491 |
Neg logit contributions | |
hen | -0.669 |
ource | -0.658 |
IFT | -0.651 |
lime | -0.649 |
RIP | -0.643 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hen | +0.767 |
ource | +0.750 |
IFT | +0.739 |
lime | +0.739 |
RIP | +0.728 |
Neg logit contributions | |
ado | -0.635 |
ャ | -0.629 |
asting | -0.588 |
asted | -0.585 |
ality | -0.575 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
hen | +0.444 |
ource | +0.436 |
lime | +0.430 |
IFT | +0.427 |
cius | +0.420 |
Neg logit contributions | |
ado | -0.405 |
ャ | -0.397 |
asting | -0.372 |
asted | -0.372 |
ality | -0.364 |
Token | former |
Token ID | 1966 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
hen | +0.617 |
ource | +0.602 |
lime | +0.596 |
IFT | +0.587 |
RIP | +0.585 |
Neg logit contributions | |
ado | -0.477 |
ャ | -0.471 |
asting | -0.434 |
asted | -0.433 |
ality | -0.419 |
Token | our |
Token ID | 674 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ado | +0.898 |
ャ | +0.866 |
asting | +0.806 |
asted | +0.806 |
ality | +0.792 |
Neg logit contributions | |
hen | -1.045 |
ource | -1.013 |
lime | -0.992 |
IFT | -0.985 |
cius | -0.981 |
Token | own |
Token ID | 898 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ado | +0.758 |
ャ | +0.733 |
asting | +0.670 |
asted | +0.664 |
ality | +0.653 |
Neg logit contributions | |
hen | -1.110 |
ource | -1.078 |
lime | -1.063 |
IFT | -1.055 |
RIP | -1.048 |
Token | investigation |
Token ID | 3645 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
hen | +2.166 |
ource | +2.079 |
lime | +2.023 |
IFT | +2.005 |
ordinary | +2.002 |
Neg logit contributions | |
ado | -2.589 |
ャ | -2.587 |
asting | -2.403 |
asted | -2.400 |
ality | -2.349 |
Token | that |
Token ID | 326 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ado | +1.865 |
ャ | +1.804 |
ality | +1.674 |
asted | +1.645 |
asting | +1.643 |
Neg logit contributions | |
hen | -2.427 |
lime | -2.370 |
ource | -2.357 |
IFT | -2.335 |
RIP | -2.315 |
Token | at |
Token ID | 379 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
hen | +1.001 |
ource | +0.972 |
lime | +0.954 |
IFT | +0.946 |
RIP | +0.938 |
Neg logit contributions | |
ado | -0.876 |
ャ | -0.857 |
asting | -0.793 |
asted | -0.792 |
ality | -0.781 |
Token | least |
Token ID | 1551 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ado | +2.041 |
ャ | +1.946 |
asted | +1.853 |
asting | +1.840 |
aste | +1.756 |
Neg logit contributions | |
hen | -2.580 |
ource | -2.561 |
lime | -2.536 |
IFT | -2.533 |
cius | -2.497 |
Token | two |
Token ID | 734 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
ado | +0.119 |
ャ | +0.115 |
asted | +0.108 |
asting | +0.108 |
ality | +0.107 |
Neg logit contributions | |
hen | -0.116 |
ource | -0.114 |
lime | -0.113 |
IFT | -0.112 |
RIP | -0.111 |
Token | City |
Token ID | 2254 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
hen | +0.020 |
ource | +0.019 |
lime | +0.019 |
IFT | +0.019 |
RIP | +0.019 |
Neg logit contributions | |
ado | -0.019 |
ャ | -0.018 |
asted | -0.017 |
asting | -0.017 |
ality | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ado | +1.174 |
ャ | +1.165 |
ality | +1.060 |
asting | +1.056 |
asted | +1.055 |
Neg logit contributions | |
hen | -1.366 |
ource | -1.329 |
lime | -1.310 |
IFT | -1.303 |
RIP | -1.296 |
Token | Miami |
Token ID | 8437 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
hen | +3.955 |
ource | +3.810 |
lime | +3.708 |
IFT | +3.677 |
ordinary | +3.653 |
Neg logit contributions | |
ャ | -4.084 |
ado | -4.058 |
asting | -3.745 |
asted | -3.743 |
ality | -3.640 |
Token | officers |
Token ID | 3790 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ado | +3.526 |
ャ | +3.447 |
ality | +3.261 |
asted | +3.260 |
asting | +3.249 |
Neg logit contributions | |
hen | -3.005 |
ource | -2.956 |
lime | -2.899 |
cius | -2.846 |
IFT | -2.843 |
Token | they |
Token ID | 484 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
hen | +2.709 |
ource | +2.589 |
lime | +2.516 |
IFT | +2.501 |
ordinary | +2.478 |
Neg logit contributions | |
ado | -3.495 |
ャ | -3.484 |
asting | -3.248 |
asted | -3.236 |
ality | -3.167 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
hen | +1.444 |
ource | +1.398 |
lime | +1.375 |
IFT | +1.366 |
ordinary | +1.356 |
Neg logit contributions | |
ado | -0.994 |
ャ | -0.984 |
asting | -0.894 |
asted | -0.890 |
ality | -0.868 |
Token | working |
Token ID | 1762 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
hen | +0.296 |
ource | +0.285 |
lime | +0.283 |
RIP | +0.280 |
IFT | +0.277 |
Neg logit contributions | |
ado | -0.306 |
ャ | -0.299 |
asting | -0.281 |
asted | -0.279 |
ality | -0.278 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ado | +2.982 |
ャ | +2.826 |
ality | +2.651 |
asted | +2.603 |
asting | +2.589 |
Neg logit contributions | |
hen | -4.434 |
lime | -4.415 |
ource | -4.394 |
RIP | -4.394 |
cius | -4.300 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ado | +0.629 |
ャ | +0.614 |
asting | +0.571 |
asted | +0.561 |
ality | +0.558 |
Neg logit contributions | |
hen | -0.844 |
ource | -0.826 |
lime | -0.816 |
IFT | -0.804 |
RIP | -0.804 |
Token | their |
Token ID | 511 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
ado | +0.583 |
ャ | +0.572 |
asting | +0.534 |
asted | +0.530 |
ality | +0.526 |
Neg logit contributions | |
hen | -0.638 |
ource | -0.617 |
lime | -0.614 |
IFT | -0.604 |
RIP | -0.602 |
Token | annual |
Token ID | 5079 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
hen | +0.077 |
ource | +0.074 |
lime | +0.074 |
IFT | +0.072 |
RIP | +0.072 |
Neg logit contributions | |
ado | -0.060 |
ャ | -0.059 |
asting | -0.054 |
asted | -0.054 |
ality | -0.053 |
Token | pensions |
Token ID | 27581 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ado | +1.976 |
ャ | +1.928 |
ality | +1.783 |
asting | +1.770 |
asted | +1.757 |
Neg logit contributions | |
hen | -2.474 |
ource | -2.410 |
lime | -2.380 |
RIP | -2.345 |
IFT | -2.343 |
Token | will |
Token ID | 481 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
ado | +1.350 |
ャ | +1.316 |
asting | +1.231 |
ality | +1.224 |
asted | +1.224 |
Neg logit contributions | |
hen | -1.764 |
ource | -1.702 |
lime | -1.696 |
RIP | -1.681 |
IFT | -1.670 |
Token | be |
Token ID | 307 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ado | +1.442 |
ャ | +1.425 |
asted | +1.314 |
asting | +1.307 |
ality | +1.268 |
Neg logit contributions | |
hen | -3.026 |
ource | -2.951 |
lime | -2.939 |
RIP | -2.933 |
IFT | -2.908 |
Token | higher |
Token ID | 2440 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ado | +0.866 |
ャ | +0.843 |
asting | +0.766 |
asted | +0.765 |
ality | +0.754 |
Neg logit contributions | |
hen | -1.395 |
ource | -1.379 |
lime | -1.371 |
cius | -1.343 |
RIP | -1.335 |
Token | s |
Token ID | 82 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ado | +0.545 |
ャ | +0.544 |
asting | +0.506 |
ality | +0.501 |
asted | +0.499 |
Neg logit contributions | |
hen | -0.498 |
ource | -0.488 |
IFT | -0.482 |
RIP | -0.478 |
lime | -0.471 |
Token | the |
Token ID | 262 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
hen | +0.131 |
ource | +0.129 |
lime | +0.126 |
IFT | +0.124 |
RIP | +0.124 |
Neg logit contributions | |
ado | -0.125 |
ャ | -0.123 |
asting | -0.113 |
asted | -0.113 |
ality | -0.112 |
Token | condition |
Token ID | 4006 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
ado | +0.095 |
ャ | +0.094 |
asting | +0.086 |
asted | +0.085 |
ality | +0.085 |
Neg logit contributions | |
hen | -0.109 |
ource | -0.106 |
lime | -0.105 |
IFT | -0.104 |
RIP | -0.103 |
Token | of |
Token ID | 286 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ado | +1.488 |
ャ | +1.473 |
ality | +1.385 |
asting | +1.326 |
asted | +1.295 |
Neg logit contributions | |
hen | -2.216 |
ource | -2.182 |
lime | -2.158 |
IFT | -2.142 |
RIP | -2.131 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
hen | +0.696 |
ource | +0.678 |
lime | +0.666 |
IFT | +0.659 |
RIP | +0.655 |
Neg logit contributions | |
ado | -0.687 |
ャ | -0.676 |
asting | -0.628 |
asted | -0.622 |
ality | -0.617 |
Token | small |
Token ID | 1402 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hen | +0.641 |
ource | +0.623 |
lime | +0.613 |
IFT | +0.607 |
RIP | +0.603 |
Neg logit contributions | |
ado | -0.663 |
ャ | -0.651 |
asting | -0.604 |
asted | -0.601 |
ality | -0.592 |
Token | nation |
Token ID | 3277 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
hen | +4.725 |
ource | +4.549 |
lime | +4.474 |
IFT | +4.432 |
ordinary | +4.424 |
Neg logit contributions | |
ado | -3.636 |
ャ | -3.603 |
asting | -3.304 |
asted | -3.280 |
ality | -3.187 |
Token | . |
Token ID | 13 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
ャ | +1.442 |
ado | +1.436 |
ality | +1.329 |
asting | +1.289 |
asted | +1.288 |
Neg logit contributions | |
hen | -2.245 |
ource | -2.223 |
IFT | -2.188 |
lime | -2.182 |
RIP | -2.170 |
Token | It |
Token ID | 632 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
hen | +0.258 |
ource | +0.252 |
lime | +0.249 |
IFT | +0.245 |
RIP | +0.243 |
Neg logit contributions | |
ャ | -0.211 |
ado | -0.210 |
asting | -0.190 |
asted | -0.189 |
ality | -0.188 |
Token | � |
Token ID | 447 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ado | +0.012 |
ャ | +0.012 |
asting | +0.011 |
asted | +0.011 |
ality | +0.011 |
Neg logit contributions | |
hen | -0.018 |
ource | -0.017 |
IFT | -0.017 |
lime | -0.017 |
RIP | -0.017 |
Token | � |
Token ID | 247 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
ado | +1.536 |
ャ | +1.501 |
asted | +1.374 |
asting | +1.368 |
aste | +1.328 |
Neg logit contributions | |
ource | -1.727 |
hen | -1.716 |
lime | -1.673 |
RIP | -1.646 |
cius | -1.641 |
Token | aerial |
Token ID | 17789 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ado | +1.227 |
ャ | +1.183 |
asting | +1.111 |
asted | +1.107 |
ality | +1.087 |
Neg logit contributions | |
hen | -1.808 |
ource | -1.765 |
IFT | -1.746 |
lime | -1.739 |
cius | -1.722 |
Token | view |
Token ID | 1570 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
ado | +1.278 |
ャ | +1.239 |
asting | +1.148 |
asted | +1.136 |
ality | +1.102 |
Neg logit contributions | |
hen | -2.250 |
ource | -2.168 |
lime | -2.146 |
RIP | -2.144 |
IFT | -2.137 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
hen | +0.013 |
ource | +0.013 |
lime | +0.013 |
IFT | +0.013 |
ordinary | +0.013 |
Neg logit contributions | |
ado | -0.008 |
ャ | -0.008 |
asting | -0.007 |
asted | -0.007 |
ality | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ado | +0.669 |
ャ | +0.666 |
asting | +0.614 |
asted | +0.611 |
ality | +0.598 |
Neg logit contributions | |
hen | -0.858 |
ource | -0.836 |
IFT | -0.822 |
lime | -0.820 |
RIP | -0.812 |
Token | place |
Token ID | 1295 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
ado | +0.289 |
ャ | +0.287 |
asting | +0.264 |
asted | +0.262 |
ality | +0.256 |
Neg logit contributions | |
hen | -0.408 |
ource | -0.395 |
lime | -0.391 |
IFT | -0.390 |
RIP | -0.386 |
Token | can |
Token ID | 460 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ャ | +0.194 |
ado | +0.194 |
asting | +0.180 |
asted | +0.179 |
ality | +0.177 |
Neg logit contributions | |
hen | -0.214 |
ource | -0.206 |
IFT | -0.204 |
lime | -0.202 |
RIP | -0.201 |
Token | be |
Token ID | 307 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
hen | +1.785 |
ource | +1.737 |
lime | +1.709 |
IFT | +1.696 |
ordinary | +1.691 |
Neg logit contributions | |
ado | -0.739 |
ャ | -0.725 |
asting | -0.631 |
asted | -0.625 |
ality | -0.602 |
Token | explored |
Token ID | 18782 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
hen | +1.992 |
ource | +1.915 |
lime | +1.879 |
IFT | +1.870 |
ordinary | +1.849 |
Neg logit contributions | |
ado | -1.862 |
ャ | -1.840 |
asting | -1.703 |
asted | -1.700 |
ality | -1.665 |
Token | in |
Token ID | 287 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
hen | +0.185 |
ource | +0.179 |
lime | +0.176 |
IFT | +0.175 |
ordinary | +0.174 |
Neg logit contributions | |
ado | -0.142 |
ャ | -0.140 |
asting | -0.129 |
asted | -0.128 |
ality | -0.125 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
hen | +0.961 |
ource | +0.928 |
lime | +0.908 |
IFT | +0.899 |
ordinary | +0.892 |
Neg logit contributions | |
ado | -0.857 |
ャ | -0.850 |
asting | -0.781 |
asted | -0.779 |
ality | -0.760 |
Token | D |
Token ID | 35 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
hen | +0.132 |
ource | +0.127 |
lime | +0.126 |
IFT | +0.124 |
cius | +0.123 |
Neg logit contributions | |
ado | -0.147 |
ャ | -0.146 |
asting | -0.137 |
asted | -0.136 |
ality | -0.134 |
Token | quarter |
Token ID | 3860 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
hen | +0.863 |
ource | +0.835 |
lime | +0.816 |
IFT | +0.809 |
cius | +0.802 |
Neg logit contributions | |
ado | -0.858 |
ャ | -0.840 |
asting | -0.782 |
asted | -0.779 |
ality | -0.772 |
Token | highlighted |
Token ID | 14537 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ado | +1.266 |
ャ | +1.232 |
asted | +1.138 |
ality | +1.135 |
asting | +1.131 |
Neg logit contributions | |
hen | -1.452 |
ource | -1.429 |
RIP | -1.392 |
cius | -1.391 |
IFT | -1.391 |
Token | what |
Token ID | 644 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
hen | +1.656 |
ource | +1.598 |
lime | +1.562 |
IFT | +1.548 |
RIP | +1.542 |
Neg logit contributions | |
ado | -1.550 |
ャ | -1.526 |
asting | -1.420 |
asted | -1.417 |
ality | -1.389 |
Token | was |
Token ID | 373 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
hen | +1.609 |
ource | +1.571 |
lime | +1.537 |
IFT | +1.525 |
RIP | +1.518 |
Neg logit contributions | |
ado | -1.256 |
ャ | -1.229 |
asting | -1.137 |
asted | -1.135 |
ality | -1.110 |
Token | then |
Token ID | 788 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
hen | +0.983 |
ource | +0.958 |
lime | +0.929 |
IFT | +0.928 |
cius | +0.925 |
Neg logit contributions | |
ado | -0.758 |
ャ | -0.738 |
asting | -0.682 |
asted | -0.680 |
ality | -0.668 |
Token | the |
Token ID | 262 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
hen | +1.645 |
ource | +1.594 |
lime | +1.547 |
IFT | +1.547 |
RIP | +1.541 |
Neg logit contributions | |
ado | -1.524 |
ャ | -1.491 |
asting | -1.383 |
asted | -1.382 |
ality | -1.357 |
Token | second |
Token ID | 1218 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hen | +1.346 |
ource | +1.310 |
lime | +1.282 |
RIP | +1.270 |
IFT | +1.269 |
Neg logit contributions | |
ado | -1.123 |
ャ | -1.099 |
asting | -1.015 |
asted | -1.010 |
ality | -0.989 |
Token | - |
Token ID | 12 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
hen | +2.013 |
ource | +1.955 |
lime | +1.917 |
IFT | +1.900 |
RIP | +1.893 |
Neg logit contributions | |
ado | -1.562 |
ャ | -1.523 |
asting | -1.403 |
asted | -1.397 |
ality | -1.376 |
Token | best |
Token ID | 13466 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
hen | +2.129 |
ource | +2.070 |
lime | +2.005 |
IFT | +2.000 |
RIP | +1.982 |
Neg logit contributions | |
ado | -2.281 |
ャ | -2.246 |
asting | -2.101 |
asted | -2.093 |
ality | -2.064 |
Token | rushing |
Token ID | 15795 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
hen | +4.841 |
ource | +4.659 |
lime | +4.555 |
IFT | +4.554 |
ordinary | +4.542 |
Neg logit contributions | |
ャ | -3.746 |
ado | -3.692 |
asting | -3.361 |
asted | -3.360 |
ality | -3.253 |
Token | game |
Token ID | 983 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
hen | +0.187 |
ource | +0.181 |
lime | +0.179 |
IFT | +0.177 |
RIP | +0.176 |
Neg logit contributions | |
ado | -0.122 |
ャ | -0.119 |
asting | -0.109 |
asted | -0.108 |
ality | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
hen | +0.046 |
ource | +0.045 |
lime | +0.044 |
IFT | +0.043 |
RIP | +0.043 |
Neg logit contributions | |
ado | -0.039 |
ャ | -0.039 |
asting | -0.036 |
asted | -0.036 |
ality | -0.035 |
Token | whole |
Token ID | 2187 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
hen | +0.057 |
ource | +0.056 |
lime | +0.055 |
IFT | +0.055 |
RIP | +0.054 |
Neg logit contributions | |
ado | -0.039 |
ャ | -0.039 |
asting | -0.035 |
asted | -0.035 |
ality | -0.035 |
Token | other |
Token ID | 584 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ado | +2.072 |
ャ | +2.030 |
asting | +1.872 |
asted | +1.846 |
ality | +1.839 |
Neg logit contributions | |
hen | -2.754 |
ource | -2.700 |
lime | -2.663 |
RIP | -2.645 |
cius | -2.643 |
Token | league |
Token ID | 4652 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
hen | +1.953 |
ource | +1.891 |
lime | +1.858 |
IFT | +1.842 |
RIP | +1.833 |
Neg logit contributions | |
ado | -1.532 |
ャ | -1.511 |
asting | -1.386 |
asted | -1.376 |
ality | -1.357 |
Token | of |
Token ID | 286 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ado | +2.351 |
ャ | +2.321 |
ality | +2.152 |
asting | +2.095 |
asted | +2.054 |
Neg logit contributions | |
hen | -3.791 |
ource | -3.732 |
RIP | -3.684 |
lime | -3.679 |
IFT | -3.666 |
Token | pretending |
Token ID | 23662 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
hen | +2.115 |
ource | +2.035 |
lime | +1.992 |
IFT | +1.976 |
ordinary | +1.958 |
Neg logit contributions | |
ado | -2.229 |
ャ | -2.208 |
asting | -2.051 |
asted | -2.042 |
ality | -2.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
hen | +6.261 |
ource | +5.930 |
ordinary | +5.845 |
lime | +5.841 |
IFT | +5.773 |
Neg logit contributions | |
ャ | -5.046 |
ado | -4.997 |
asting | -4.585 |
asted | -4.539 |
aste | -4.289 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
hen | +0.153 |
ource | +0.150 |
lime | +0.148 |
IFT | +0.146 |
cius | +0.145 |
Neg logit contributions | |
ado | -0.128 |
ャ | -0.128 |
asting | -0.117 |
asted | -0.117 |
ality | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ado | +0.363 |
ャ | +0.360 |
asting | +0.331 |
asted | +0.330 |
ality | +0.325 |
Neg logit contributions | |
hen | -0.479 |
ource | -0.465 |
lime | -0.460 |
IFT | -0.456 |
cius | -0.455 |
Token | R |
Token ID | 49 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ado | +0.541 |
ャ | +0.538 |
asting | +0.500 |
asted | +0.498 |
ality | +0.491 |
Neg logit contributions | |
hen | -0.539 |
ource | -0.523 |
lime | -0.511 |
ordinary | -0.505 |
IFT | -0.502 |
Token | USE |
Token ID | 19108 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ado | +0.241 |
ャ | +0.239 |
asting | +0.231 |
asted | +0.230 |
ality | +0.228 |
Neg logit contributions | |
hen | -0.033 |
ource | -0.028 |
lime | -0.026 |
IFT | -0.024 |
ordinary | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ャ | +2.205 |
ado | +2.180 |
ality | +2.068 |
asted | +2.018 |
asting | +1.997 |
Neg logit contributions | |
ource | -2.951 |
hen | -2.946 |
RIP | -2.904 |
lime | -2.885 |
IFT | -2.878 |
Token | he |
Token ID | 339 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
hen | +0.358 |
ource | +0.349 |
lime | +0.342 |
IFT | +0.339 |
RIP | +0.335 |
Neg logit contributions | |
ado | -0.362 |
ャ | -0.354 |
asting | -0.331 |
asted | -0.329 |
ality | -0.327 |
Token | will |
Token ID | 481 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ado | +0.210 |
ャ | +0.205 |
asting | +0.190 |
asted | +0.189 |
ality | +0.188 |
Neg logit contributions | |
hen | -0.271 |
ource | -0.265 |
IFT | -0.261 |
lime | -0.260 |
RIP | -0.258 |
Token | recover |
Token ID | 8551 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ado | +1.227 |
ャ | +1.188 |
asting | +1.122 |
asted | +1.117 |
ality | +1.076 |
Neg logit contributions | |
hen | -1.984 |
ource | -1.928 |
lime | -1.919 |
IFT | -1.907 |
RIP | -1.890 |
Token | and |
Token ID | 290 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
hen | +2.436 |
ource | +2.347 |
lime | +2.300 |
IFT | +2.286 |
ordinary | +2.272 |
Neg logit contributions | |
ado | -1.976 |
ャ | -1.960 |
asting | -1.795 |
asted | -1.783 |
ality | -1.738 |
Token | become |
Token ID | 1716 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
hen | +0.756 |
ource | +0.734 |
lime | +0.723 |
IFT | +0.719 |
RIP | +0.712 |
Neg logit contributions | |
ado | -0.567 |
ャ | -0.556 |
asting | -0.514 |
asted | -0.512 |
ality | -0.501 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
hen | +6.618 |
ource | +6.281 |
IFT | +6.139 |
lime | +6.138 |
ordinary | +6.094 |
Neg logit contributions | |
ado | -6.314 |
ャ | -6.253 |
asting | -5.710 |
asted | -5.642 |
ality | -5.519 |
Token | productive |
Token ID | 12973 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
hen | +4.078 |
ource | +3.933 |
lime | +3.849 |
IFT | +3.826 |
ordinary | +3.810 |
Neg logit contributions | |
ado | -3.437 |
ャ | -3.405 |
asting | -3.114 |
asted | -3.097 |
ality | -3.026 |
Token | person |
Token ID | 1048 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
hen | +0.979 |
ource | +0.949 |
lime | +0.938 |
IFT | +0.927 |
RIP | +0.922 |
Neg logit contributions | |
ado | -0.766 |
ャ | -0.746 |
asting | -0.700 |
asted | -0.699 |
ality | -0.689 |
Token | again |
Token ID | 757 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
hen | +1.677 |
ource | +1.629 |
lime | +1.604 |
IFT | +1.593 |
RIP | +1.581 |
Neg logit contributions | |
ado | -1.180 |
ャ | -1.169 |
asting | -1.069 |
asted | -1.062 |
ality | -1.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
hen | +2.332 |
ource | +2.263 |
lime | +2.226 |
IFT | +2.213 |
RIP | +2.195 |
Neg logit contributions | |
ado | -1.569 |
ャ | -1.551 |
asting | -1.412 |
asted | -1.403 |
ality | -1.378 |
Token | event |
Token ID | 1785 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
hen | +1.231 |
ource | +1.190 |
lime | +1.173 |
IFT | +1.159 |
RIP | +1.153 |
Neg logit contributions | |
ado | -1.011 |
ャ | -0.990 |
asting | -0.919 |
asted | -0.910 |
ality | -0.894 |
Token | . |
Token ID | 13 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
hen | +2.895 |
ource | +2.799 |
lime | +2.749 |
IFT | +2.730 |
ordinary | +2.711 |
Neg logit contributions | |
ado | -2.140 |
ャ | -2.118 |
asting | -1.933 |
asted | -1.924 |
ality | -1.876 |
Token | That |
Token ID | 1320 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hen | +2.388 |
ource | +2.299 |
lime | +2.253 |
IFT | +2.237 |
ordinary | +2.218 |
Neg logit contributions | |
ado | -2.269 |
ャ | -2.247 |
asting | -2.078 |
asted | -2.070 |
ality | -2.028 |
Token | 's |
Token ID | 338 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
hen | +1.961 |
ource | +1.896 |
lime | +1.859 |
IFT | +1.850 |
RIP | +1.835 |
Neg logit contributions | |
ado | -1.606 |
ャ | -1.583 |
asting | -1.456 |
asted | -1.447 |
ality | -1.427 |
Token | the |
Token ID | 262 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
hen | +0.947 |
ource | +0.917 |
lime | +0.899 |
IFT | +0.890 |
RIP | +0.882 |
Neg logit contributions | |
ado | -0.938 |
ャ | -0.917 |
asting | -0.857 |
asted | -0.852 |
ality | -0.841 |
Token | only |
Token ID | 691 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
hen | +1.880 |
ource | +1.819 |
lime | +1.787 |
IFT | +1.774 |
ordinary | +1.758 |
Neg logit contributions | |
ado | -1.463 |
ャ | -1.444 |
asting | -1.325 |
asted | -1.317 |
ality | -1.291 |
Token | way |
Token ID | 835 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
hen | +4.887 |
ource | +4.702 |
ordinary | +4.558 |
lime | +4.497 |
IFT | +4.495 |
Neg logit contributions | |
ャ | -6.580 |
ado | -6.472 |
asted | -6.094 |
asting | -6.065 |
aste | -5.881 |
Token | we |
Token ID | 356 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
hen | +0.635 |
ource | +0.614 |
lime | +0.604 |
IFT | +0.600 |
cius | +0.597 |
Neg logit contributions | |
ado | -0.631 |
ャ | -0.616 |
ality | -0.574 |
asting | -0.573 |
asted | -0.566 |
Token | can |
Token ID | 460 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hen | +1.851 |
ource | +1.781 |
lime | +1.744 |
IFT | +1.730 |
ordinary | +1.715 |
Neg logit contributions | |
ado | -1.942 |
ャ | -1.923 |
asting | -1.787 |
asted | -1.780 |
ality | -1.748 |
Token | really |
Token ID | 1107 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hen | +4.183 |
ource | +4.048 |
lime | +3.943 |
IFT | +3.932 |
ordinary | +3.925 |
Neg logit contributions | |
ャ | -2.877 |
ado | -2.822 |
asting | -2.466 |
asted | -2.453 |
ality | -2.415 |
Token | continue |
Token ID | 2555 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
hen | +1.881 |
ource | +1.824 |
lime | +1.790 |
IFT | +1.780 |
ordinary | +1.770 |
Neg logit contributions | |
ado | -1.202 |
ャ | -1.196 |
asting | -1.071 |
asted | -1.065 |
ality | -1.040 |
Token | - |
Token ID | 532 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
hen | +1.087 |
ource | +1.052 |
lime | +1.034 |
IFT | +1.023 |
ordinary | +1.016 |
Neg logit contributions | |
ado | -0.925 |
ャ | -0.917 |
asting | -0.843 |
asted | -0.839 |
ality | -0.824 |
Token | 307 |
Token ID | 38369 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
hen | +1.028 |
ource | +0.998 |
lime | +0.990 |
IFT | +0.978 |
ordinary | +0.970 |
Neg logit contributions | |
ado | -0.804 |
ャ | -0.791 |
asting | -0.726 |
asted | -0.718 |
ality | -0.706 |
Token | . |
Token ID | 764 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
hen | +1.610 |
ource | +1.554 |
lime | +1.524 |
IFT | +1.514 |
ordinary | +1.504 |
Neg logit contributions | |
ado | -1.284 |
ャ | -1.270 |
asting | -1.164 |
asted | -1.158 |
ality | -1.132 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
hen | +0.016 |
ource | +0.016 |
lime | +0.016 |
IFT | +0.015 |
cius | +0.015 |
Neg logit contributions | |
ado | -0.013 |
ャ | -0.013 |
asting | -0.012 |
asted | -0.012 |
ality | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
hen | +0.069 |
ource | +0.067 |
lime | +0.066 |
IFT | +0.066 |
cius | +0.065 |
Neg logit contributions | |
ado | -0.055 |
ャ | -0.055 |
asting | -0.050 |
asted | -0.050 |
ality | -0.049 |
Token | Google |
Token ID | 11708 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ャ | +0.047 |
ado | +0.047 |
asting | +0.045 |
asted | +0.045 |
ality | +0.044 |
Neg logit contributions | |
hen | -0.021 |
ource | -0.021 |
cius | -0.020 |
lime | -0.020 |
ordinary | -0.020 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
hen | +3.600 |
ource | +3.362 |
ordinary | +3.106 |
IFT | +3.050 |
lime | +3.031 |
Neg logit contributions | |
ado | -7.642 |
ャ | -7.558 |
asting | -7.109 |
asted | -7.071 |
ality | -7.018 |
Token | Crossref |
Token ID | 23613 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
hen | +1.207 |
ource | +1.166 |
lime | +1.133 |
IFT | +1.130 |
ordinary | +1.116 |
Neg logit contributions | |
ado | -1.230 |
ャ | -1.222 |
asting | -1.134 |
asted | -1.131 |
ality | -1.099 |
Token | | |
Token ID | 930 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
hen | +0.035 |
ource | +0.034 |
lime | +0.033 |
IFT | +0.033 |
ordinary | +0.032 |
Neg logit contributions | |
ado | -0.026 |
ャ | -0.026 |
asting | -0.024 |
asted | -0.024 |
ality | -0.023 |
Token | Medline |
Token ID | 34582 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
hen | +1.822 |
ource | +1.752 |
lime | +1.707 |
IFT | +1.701 |
ordinary | +1.682 |
Neg logit contributions | |
ado | -1.960 |
ャ | -1.941 |
asting | -1.808 |
asted | -1.803 |
ality | -1.764 |
Token | | |
Token ID | 930 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
hen | +0.212 |
ource | +0.205 |
lime | +0.201 |
IFT | +0.200 |
RIP | +0.198 |
Neg logit contributions | |
ado | -0.154 |
ャ | -0.153 |
asting | -0.140 |
asted | -0.139 |
ality | -0.134 |
Token | — |
Token ID | 851 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
hen | +2.482 |
ource | +2.407 |
lime | +2.375 |
IFT | +2.361 |
ordinary | +2.343 |
Neg logit contributions | |
ado | -1.597 |
ャ | -1.587 |
asting | -1.434 |
asted | -1.424 |
ality | -1.388 |
Token | I |
Token ID | 314 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
hen | +0.455 |
ource | +0.443 |
lime | +0.436 |
IFT | +0.433 |
ordinary | +0.427 |
Neg logit contributions | |
ado | -0.391 |
ャ | -0.385 |
asting | -0.357 |
asted | -0.354 |
ality | -0.347 |
Token | hope |
Token ID | 2911 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
hen | +1.595 |
ource | +1.541 |
lime | +1.513 |
IFT | +1.503 |
ordinary | +1.492 |
Neg logit contributions | |
ado | -1.213 |
ャ | -1.204 |
asting | -1.098 |
asted | -1.093 |
ality | -1.068 |
Token | you |
Token ID | 345 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
ado | +0.149 |
ャ | +0.145 |
asting | +0.135 |
asted | +0.134 |
ality | +0.134 |
Neg logit contributions | |
hen | -0.143 |
ource | -0.139 |
IFT | -0.138 |
lime | -0.137 |
ordinary | -0.134 |
Token | can |
Token ID | 460 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hen | +2.610 |
ource | +2.517 |
lime | +2.466 |
IFT | +2.445 |
ordinary | +2.429 |
Neg logit contributions | |
ado | -2.221 |
ャ | -2.212 |
asting | -2.022 |
asted | -2.012 |
ality | -1.971 |
Token | change |
Token ID | 1487 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
hen | +3.933 |
ource | +3.805 |
lime | +3.711 |
IFT | +3.691 |
ordinary | +3.664 |
Neg logit contributions | |
ャ | -2.501 |
ado | -2.470 |
asting | -2.186 |
asted | -2.177 |
ality | -2.133 |
Token | your |
Token ID | 534 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
hen | +6.896 |
ource | +6.498 |
lime | +6.302 |
ordinary | +6.255 |
IFT | +6.222 |
Neg logit contributions | |
ャ | -7.902 |
ado | -7.793 |
asting | -7.243 |
asted | -7.200 |
ality | -6.986 |
Token | mind |
Token ID | 2000 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
hen | +3.344 |
ource | +3.209 |
lime | +3.134 |
IFT | +3.107 |
ordinary | +3.092 |
Neg logit contributions | |
ado | -3.604 |
ャ | -3.586 |
asting | -3.331 |
asted | -3.324 |
ality | -3.253 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
hen | +2.003 |
ource | +1.937 |
lime | +1.903 |
IFT | +1.891 |
ordinary | +1.876 |
Neg logit contributions | |
ado | -1.630 |
ャ | -1.611 |
asting | -1.481 |
asted | -1.474 |
ality | -1.448 |
Token | Look |
Token ID | 6803 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
hen | +2.232 |
ource | +2.158 |
lime | +2.120 |
IFT | +2.104 |
ordinary | +2.083 |
Neg logit contributions | |
ado | -1.979 |
ャ | -1.961 |
asting | -1.808 |
asted | -1.799 |
ality | -1.764 |
Token | forward |
Token ID | 2651 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
hen | +5.871 |
ource | +5.641 |
lime | +5.499 |
IFT | +5.462 |
ordinary | +5.438 |
Neg logit contributions | |
ado | -4.179 |
ャ | -4.141 |
asting | -3.746 |
asted | -3.734 |
ality | -3.611 |