Token | � |
Token ID | 251 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Sabha | +0.059 |
bane | +0.052 |
conn | +0.042 |
ader | +0.037 |
Uz | +0.036 |
Neg logit contributions | |
beard | -0.093 |
�� | -0.089 |
netflix | -0.087 |
姫 | -0.084 |
Noir | -0.084 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
Sabha | +0.184 |
bane | +0.169 |
conn | +0.144 |
ader | +0.131 |
Loading | +0.130 |
Neg logit contributions | |
beard | -0.183 |
�� | -0.171 |
netflix | -0.170 |
姫 | -0.162 |
Noir | -0.160 |
Token | Image |
Token ID | 5159 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
beard | +0.225 |
netflix | +0.208 |
�� | +0.208 |
姫 | +0.195 |
Noir | +0.193 |
Neg logit contributions | |
Sabha | -0.282 |
bane | -0.261 |
conn | -0.226 |
ader | -0.208 |
Uz | -0.207 |
Token | copyright |
Token ID | 6634 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Sabha | +2.462 |
bane | +2.248 |
conn | +1.872 |
Loading | +1.681 |
ader | +1.668 |
Neg logit contributions | |
beard | -2.939 |
�� | -2.804 |
netflix | -2.768 |
姫 | -2.635 |
Noir | -2.590 |
Token | publicity |
Token ID | 19403 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Sabha | +4.893 |
bane | +4.437 |
conn | +3.807 |
Pix | +3.538 |
Uz | +3.517 |
Neg logit contributions | |
beard | -4.739 |
�� | -4.531 |
netflix | -4.376 |
姫 | -4.213 |
Noir | -4.042 |
Token | Image |
Token ID | 7412 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Sabha | +5.221 |
bane | +4.887 |
conn | +4.233 |
Pix | +3.864 |
ader | +3.813 |
Neg logit contributions | |
beard | -4.895 |
�� | -4.707 |
netflix | -4.556 |
姫 | -4.381 |
Noir | -4.259 |
Token | caption |
Token ID | 8305 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Sabha | +5.917 |
bane | +4.974 |
conn | +3.155 |
Pix | +2.829 |
ader | +2.818 |
Neg logit contributions | |
�� | -18.058 |
beard | -16.489 |
姫 | -15.956 |
netflix | -15.920 |
Noir | -15.133 |
Token | The |
Token ID | 383 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Sabha | +2.827 |
bane | +2.611 |
conn | +2.249 |
Uz | +2.074 |
ader | +2.064 |
Neg logit contributions | |
beard | -2.395 |
�� | -2.273 |
netflix | -2.215 |
姫 | -2.102 |
Noir | -2.043 |
Token | Greeks |
Token ID | 25059 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
beard | +0.128 |
�� | +0.119 |
netflix | +0.119 |
姫 | +0.111 |
Noir | +0.111 |
Neg logit contributions | |
Sabha | -0.153 |
bane | -0.142 |
conn | -0.123 |
ader | -0.112 |
Loading | -0.112 |
Token | were |
Token ID | 547 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Sabha | +0.501 |
bane | +0.462 |
conn | +0.400 |
ader | +0.365 |
Loading | +0.364 |
Neg logit contributions | |
beard | -0.439 |
netflix | -0.407 |
�� | -0.406 |
姫 | -0.383 |
Noir | -0.381 |
Token | totally |
Token ID | 6635 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Sabha | +2.168 |
bane | +2.009 |
conn | +1.736 |
ader | +1.589 |
Loading | +1.580 |
Neg logit contributions | |
beard | -1.832 |
�� | -1.703 |
netflix | -1.694 |
姫 | -1.598 |
Noir | -1.581 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
beard | +1.817 |
netflix | +1.668 |
�� | +1.646 |
Noir | +1.570 |
姫 | +1.559 |
Neg logit contributions | |
Sabha | -2.233 |
bane | -2.066 |
conn | -1.801 |
ader | -1.638 |
Loading | -1.631 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
Sabha | +1.081 |
bane | +1.001 |
conn | +0.861 |
ader | +0.786 |
Loading | +0.781 |
Neg logit contributions | |
beard | -0.964 |
�� | -0.900 |
netflix | -0.894 |
姫 | -0.845 |
Noir | -0.836 |
Token | Image |
Token ID | 5159 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
beard | +0.618 |
netflix | +0.571 |
�� | +0.567 |
姫 | +0.533 |
Noir | +0.526 |
Neg logit contributions | |
Sabha | -0.774 |
bane | -0.715 |
conn | -0.619 |
ader | -0.570 |
Uz | -0.568 |
Token | copyright |
Token ID | 6634 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Sabha | +2.434 |
bane | +2.223 |
conn | +1.848 |
Loading | +1.660 |
ader | +1.644 |
Neg logit contributions | |
beard | -2.929 |
�� | -2.797 |
netflix | -2.761 |
姫 | -2.630 |
Noir | -2.583 |
Token | AP |
Token ID | 3486 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Sabha | +4.696 |
bane | +4.261 |
conn | +3.655 |
Pix | +3.390 |
Uz | +3.373 |
Neg logit contributions | |
beard | -4.536 |
�� | -4.331 |
netflix | -4.190 |
姫 | -4.030 |
Noir | -3.875 |
Token | Image |
Token ID | 7412 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Sabha | +7.097 |
bane | +6.581 |
conn | +5.606 |
Pix | +5.093 |
Uz | +5.077 |
Neg logit contributions | |
beard | -8.966 |
�� | -8.936 |
netflix | -8.532 |
姫 | -8.288 |
Noir | -8.089 |
Token | caption |
Token ID | 8305 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Sabha | +5.735 |
bane | +4.890 |
conn | +3.126 |
ader | +2.823 |
Pix | +2.726 |
Neg logit contributions | |
�� | -18.062 |
beard | -16.489 |
netflix | -15.985 |
姫 | -15.903 |
Noir | -15.063 |
Token | Peace |
Token ID | 12689 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
Sabha | +3.780 |
bane | +3.472 |
conn | +2.972 |
Uz | +2.767 |
Pix | +2.723 |
Neg logit contributions | |
beard | -3.386 |
�� | -3.250 |
netflix | -3.149 |
姫 | -2.990 |
Noir | -2.901 |
Token | talks |
Token ID | 6130 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Sabha | +4.978 |
bane | +4.533 |
conn | +3.917 |
ader | +3.532 |
Pix | +3.468 |
Neg logit contributions | |
beard | -5.054 |
�� | -4.780 |
netflix | -4.735 |
姫 | -4.492 |
Noir | -4.432 |
Token | between |
Token ID | 1022 |
Feature activation | -1.57e-03 |
Pos logit contributions | |
Sabha | +3.435 |
bane | +3.167 |
conn | +2.671 |
ader | +2.448 |
Uz | +2.418 |
Neg logit contributions | |
beard | -3.463 |
�� | -3.265 |
netflix | -3.210 |
姫 | -3.069 |
Noir | -3.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
beard | +0.013 |
�� | +0.012 |
netflix | +0.012 |
姫 | +0.011 |
Noir | +0.011 |
Neg logit contributions | |
Sabha | -0.011 |
bane | -0.010 |
conn | -0.009 |
ader | -0.008 |
Loading | -0.008 |
Token | an |
Token ID | 281 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Sabha | +0.358 |
bane | +0.331 |
conn | +0.286 |
Loading | +0.259 |
ader | +0.258 |
Neg logit contributions | |
beard | -0.326 |
�� | -0.302 |
netflix | -0.301 |
姫 | -0.286 |
Noir | -0.284 |
Token | ATK |
Token ID | 24526 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
Sabha | +2.284 |
bane | +2.110 |
conn | +1.808 |
ader | +1.650 |
Uz | +1.639 |
Neg logit contributions | |
beard | -2.097 |
�� | -1.953 |
netflix | -1.948 |
姫 | -1.839 |
Noir | -1.820 |
Token | 0 |
Token ID | 657 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
Sabha | +0.516 |
bane | +0.474 |
conn | +0.412 |
Loading | +0.373 |
ader | +0.371 |
Neg logit contributions | |
beard | -0.459 |
netflix | -0.423 |
�� | -0.422 |
姫 | -0.399 |
Noir | -0.397 |
Token | / |
Token ID | 14 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Sabha | +7.041 |
bane | +6.531 |
conn | +5.410 |
Uz | +5.054 |
ader | +4.987 |
Neg logit contributions | |
beard | -7.638 |
�� | -7.309 |
netflix | -7.264 |
姫 | -6.983 |
Noir | -6.754 |
Token | DEF |
Token ID | 32988 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Sabha | +4.113 |
bane | +3.854 |
conn | +3.355 |
Loading | +3.107 |
Uz | +3.068 |
Neg logit contributions | |
beard | -3.298 |
�� | -3.097 |
netflix | -3.066 |
姫 | -2.848 |
Noir | -2.835 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Sabha | +1.944 |
bane | +1.793 |
conn | +1.546 |
ader | +1.406 |
Loading | +1.400 |
Neg logit contributions | |
beard | -1.738 |
�� | -1.614 |
netflix | -1.608 |
姫 | -1.518 |
Noir | -1.505 |
Token | Zombie |
Token ID | 14609 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Sabha | +9.369 |
bane | +8.963 |
conn | +7.038 |
Uz | +6.746 |
Pix | +6.651 |
Neg logit contributions | |
beard | -12.148 |
�� | -11.861 |
netflix | -11.829 |
姫 | -11.484 |
Noir | -10.795 |
Token | - |
Token ID | 12 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
Sabha | +2.033 |
bane | +1.887 |
conn | +1.621 |
ader | +1.485 |
Uz | +1.476 |
Neg logit contributions | |
beard | -1.761 |
�� | -1.648 |
netflix | -1.635 |
姫 | -1.547 |
Noir | -1.523 |
Token | type |
Token ID | 4906 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Sabha | +4.222 |
bane | +3.989 |
conn | +3.401 |
Loading | +3.113 |
Creat | +3.073 |
Neg logit contributions | |
beard | -3.994 |
�� | -3.795 |
netflix | -3.753 |
姫 | -3.568 |
Noir | -3.546 |
Token | � |
Token ID | 564 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Sabha | +3.914 |
bane | +3.642 |
conn | +3.112 |
Uz | +2.884 |
ader | +2.859 |
Neg logit contributions | |
beard | -3.456 |
�� | -3.249 |
netflix | -3.234 |
姫 | -3.075 |
Noir | -2.990 |
Token | � |
Token ID | 250 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Sabha | +2.474 |
bane | +2.305 |
conn | +1.968 |
ader | +1.812 |
Loading | +1.801 |
Neg logit contributions | |
beard | -2.258 |
netflix | -2.109 |
�� | -2.066 |
姫 | -1.973 |
Noir | -1.963 |
Token | would |
Token ID | 561 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
Sabha | +1.126 |
bane | +1.041 |
conn | +0.893 |
ader | +0.814 |
Loading | +0.808 |
Neg logit contributions | |
beard | -1.043 |
�� | -0.968 |
netflix | -0.967 |
姫 | -0.910 |
Noir | -0.910 |
Token | be |
Token ID | 307 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Sabha | +0.045 |
bane | +0.042 |
conn | +0.036 |
ader | +0.033 |
Loading | +0.032 |
Neg logit contributions | |
beard | -0.043 |
�� | -0.040 |
netflix | -0.040 |
姫 | -0.038 |
Noir | -0.038 |
Token | unveiled |
Token ID | 18475 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Sabha | +0.215 |
bane | +0.200 |
conn | +0.176 |
ader | +0.161 |
Uz | +0.159 |
Neg logit contributions | |
beard | -0.165 |
�� | -0.152 |
netflix | -0.151 |
Noir | -0.143 |
姫 | -0.141 |
Token | before |
Token ID | 878 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Sabha | +1.575 |
bane | +1.454 |
conn | +1.246 |
ader | +1.134 |
Loading | +1.127 |
Neg logit contributions | |
beard | -1.474 |
�� | -1.374 |
netflix | -1.369 |
姫 | -1.294 |
Noir | -1.283 |
Token | Holy |
Token ID | 7439 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Sabha | +2.022 |
bane | +1.852 |
conn | +1.564 |
ader | +1.411 |
Loading | +1.402 |
Neg logit contributions | |
beard | -2.181 |
�� | -2.047 |
netflix | -2.037 |
姫 | -1.935 |
Noir | -1.915 |
Token | ro |
Token ID | 305 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Sabha | +3.653 |
bane | +3.285 |
conn | +2.879 |
ader | +2.594 |
Loading | +2.581 |
Neg logit contributions | |
beard | -3.620 |
�� | -3.518 |
netflix | -3.402 |
姫 | -3.240 |
Noir | -3.164 |
Token | od |
Token ID | 375 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
Sabha | +7.557 |
bane | +7.302 |
conn | +5.642 |
ader | +5.429 |
Uz | +4.960 |
Neg logit contributions | |
beard | -13.090 |
�� | -12.833 |
netflix | -12.747 |
姫 | -12.014 |
Noir | -11.970 |
Token | goes |
Token ID | 2925 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Sabha | +4.206 |
bane | +3.843 |
conn | +3.299 |
Loading | +2.993 |
ader | +2.979 |
Neg logit contributions | |
beard | -3.852 |
�� | -3.633 |
netflix | -3.604 |
姫 | -3.392 |
Noir | -3.308 |
Token | into |
Token ID | 656 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Sabha | +1.430 |
bane | +1.321 |
conn | +1.127 |
ader | +1.017 |
Loading | +1.010 |
Neg logit contributions | |
beard | -1.431 |
�� | -1.331 |
netflix | -1.330 |
姫 | -1.258 |
Noir | -1.253 |
Token | summer |
Token ID | 3931 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
beard | +0.787 |
�� | +0.725 |
netflix | +0.719 |
Noir | +0.695 |
姫 | +0.679 |
Neg logit contributions | |
Sabha | -0.853 |
bane | -0.819 |
conn | -0.696 |
ader | -0.642 |
Loading | -0.628 |
Token | recess |
Token ID | 28836 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Sabha | +0.074 |
bane | +0.067 |
conn | +0.050 |
ader | +0.044 |
Uz | +0.042 |
Neg logit contributions | |
beard | -0.153 |
netflix | -0.145 |
�� | -0.144 |
Noir | -0.139 |
姫 | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Sabha | +0.432 |
bane | +0.398 |
conn | +0.338 |
ader | +0.307 |
Uz | +0.305 |
Neg logit contributions | |
beard | -0.440 |
�� | -0.413 |
netflix | -0.409 |
姫 | -0.388 |
Noir | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
Sabha | +1.615 |
bane | +1.482 |
conn | +1.264 |
ader | +1.147 |
Loading | +1.140 |
Neg logit contributions | |
beard | -1.567 |
netflix | -1.451 |
�� | -1.417 |
姫 | -1.366 |
Noir | -1.366 |
Token | Image |
Token ID | 5159 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Sabha | +0.357 |
bane | +0.330 |
conn | +0.286 |
ader | +0.262 |
Uz | +0.260 |
Neg logit contributions | |
beard | -0.291 |
netflix | -0.269 |
�� | -0.268 |
姫 | -0.253 |
Noir | -0.250 |
Token | copyright |
Token ID | 6634 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Sabha | +2.512 |
bane | +2.284 |
conn | +1.896 |
Loading | +1.698 |
Uz | +1.698 |
Neg logit contributions | |
beard | -3.074 |
�� | -2.950 |
netflix | -2.879 |
姫 | -2.762 |
Noir | -2.711 |
Token | AFP |
Token ID | 8916 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Sabha | +5.782 |
bane | +5.130 |
conn | +4.331 |
Uz | +4.075 |
Pix | +4.042 |
Neg logit contributions | |
beard | -6.596 |
�� | -6.342 |
netflix | -6.093 |
姫 | -5.879 |
Noir | -5.658 |
Token | Image |
Token ID | 7412 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Sabha | +6.139 |
bane | +5.668 |
conn | +4.827 |
Pix | +4.360 |
Uz | +4.336 |
Neg logit contributions | |
beard | -7.576 |
�� | -7.399 |
netflix | -7.115 |
姫 | -6.906 |
Noir | -6.727 |
Token | caption |
Token ID | 8305 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Sabha | +5.457 |
bane | +4.804 |
conn | +3.280 |
ader | +2.946 |
Pix | +2.817 |
Neg logit contributions | |
�� | -16.284 |
beard | -14.820 |
姫 | -14.283 |
netflix | -14.187 |
Noir | -13.508 |
Token | The |
Token ID | 383 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
Sabha | +2.743 |
bane | +2.524 |
conn | +2.152 |
Uz | +1.969 |
ader | +1.965 |
Neg logit contributions | |
beard | -2.640 |
�� | -2.491 |
netflix | -2.457 |
姫 | -2.318 |
Noir | -2.283 |
Token | Kurds |
Token ID | 23880 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Sabha | +0.397 |
bane | +0.366 |
conn | +0.311 |
ader | +0.280 |
Loading | +0.279 |
Neg logit contributions | |
beard | -0.410 |
�� | -0.383 |
netflix | -0.382 |
姫 | -0.361 |
Noir | -0.360 |
Token | ' |
Token ID | 6 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
beard | +1.183 |
netflix | +1.092 |
�� | +1.071 |
姫 | +1.026 |
Noir | +1.017 |
Neg logit contributions | |
Sabha | -1.374 |
bane | -1.270 |
conn | -1.112 |
Loading | -1.025 |
ader | -1.003 |
Token | push |
Token ID | 4574 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
beard | +0.232 |
�� | +0.214 |
netflix | +0.213 |
姫 | +0.201 |
Noir | +0.201 |
Neg logit contributions | |
Sabha | -0.272 |
bane | -0.254 |
conn | -0.220 |
Loading | -0.201 |
ader | -0.201 |
Token | .: |
Token ID | 11207 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Sabha | +1.304 |
bane | +1.207 |
conn | +1.041 |
ader | +0.951 |
Loading | +0.945 |
Neg logit contributions | |
beard | -1.133 |
�� | -1.052 |
netflix | -1.048 |
姫 | -0.989 |
Noir | -0.980 |
Token | If |
Token ID | 1002 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
beard | +0.401 |
netflix | +0.369 |
�� | +0.365 |
Noir | +0.345 |
姫 | +0.345 |
Neg logit contributions | |
Sabha | -0.484 |
bane | -0.448 |
conn | -0.387 |
ader | -0.355 |
Loading | -0.350 |
Token | you |
Token ID | 345 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Sabha | +4.649 |
bane | +4.223 |
conn | +3.630 |
Creat | +3.362 |
Loading | +3.360 |
Neg logit contributions | |
beard | -5.188 |
�� | -4.995 |
netflix | -4.751 |
姫 | -4.675 |
Noir | -4.588 |
Token | � |
Token ID | 447 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Sabha | +2.875 |
bane | +2.677 |
conn | +2.259 |
ader | +2.072 |
Loading | +2.063 |
Neg logit contributions | |
beard | -2.903 |
�� | -2.761 |
netflix | -2.702 |
姫 | -2.566 |
Noir | -2.559 |
Token | � |
Token ID | 247 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Sabha | +1.790 |
bane | +1.643 |
conn | +1.398 |
ader | +1.263 |
Loading | +1.257 |
Neg logit contributions | |
beard | -1.826 |
�� | -1.709 |
netflix | -1.698 |
姫 | -1.610 |
Noir | -1.595 |
Token | re |
Token ID | 260 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Sabha | +0.837 |
bane | +0.760 |
conn | +0.641 |
Uz | +0.576 |
Loading | +0.574 |
Neg logit contributions | |
beard | -0.962 |
netflix | -0.899 |
�� | -0.886 |
姫 | -0.845 |
Noir | -0.842 |
Token | using |
Token ID | 1262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Sabha | +9.115 |
bane | +8.428 |
conn | +7.004 |
Loading | +6.525 |
Pix | +6.420 |
Neg logit contributions | |
�� | -11.071 |
beard | -10.613 |
netflix | -10.184 |
姫 | -10.075 |
Noir | -9.584 |
Token | this |
Token ID | 428 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Sabha | +7.347 |
bane | +6.742 |
conn | +5.527 |
ader | +4.878 |
Loading | +4.853 |
Neg logit contributions | |
�� | -11.161 |
beard | -10.533 |
姫 | -10.150 |
netflix | -10.104 |
Noir | -9.502 |
Token | information |
Token ID | 1321 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Sabha | +6.769 |
bane | +6.269 |
conn | +5.488 |
Loading | +5.167 |
ader | +5.089 |
Neg logit contributions | |
�� | -4.939 |
beard | -4.864 |
netflix | -4.559 |
姫 | -4.361 |
Noir | -4.166 |
Token | on |
Token ID | 319 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Sabha | +1.664 |
bane | +1.542 |
conn | +1.334 |
ader | +1.217 |
Loading | +1.209 |
Neg logit contributions | |
beard | -1.418 |
netflix | -1.309 |
�� | -1.294 |
姫 | -1.229 |
Noir | -1.223 |
Token | your |
Token ID | 534 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Sabha | +3.052 |
bane | +2.758 |
conn | +2.236 |
ader | +2.000 |
Loading | +1.982 |
Neg logit contributions | |
beard | -4.334 |
�� | -4.228 |
netflix | -4.108 |
姫 | -3.956 |
Noir | -3.872 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Sabha | +1.971 |
bane | +1.808 |
conn | +1.525 |
Loading | +1.371 |
Uz | +1.368 |
Neg logit contributions | |
beard | -2.181 |
�� | -2.075 |
netflix | -2.045 |
姫 | -1.947 |
Noir | -1.918 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Sabha | +1.877 |
bane | +1.724 |
conn | +1.467 |
ader | +1.331 |
Uz | +1.322 |
Neg logit contributions | |
beard | -1.857 |
netflix | -1.721 |
�� | -1.701 |
姫 | -1.627 |
Noir | -1.621 |
Token | B |
Token ID | 33 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Sabha | +1.871 |
bane | +1.738 |
conn | +1.511 |
ader | +1.388 |
Loading | +1.379 |
Neg logit contributions | |
beard | -1.460 |
�� | -1.349 |
netflix | -1.344 |
姫 | -1.263 |
Noir | -1.250 |
Token | earing |
Token ID | 6648 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
Sabha | +2.999 |
bane | +2.800 |
conn | +2.411 |
ader | +2.227 |
Loading | +2.208 |
Neg logit contributions | |
beard | -2.669 |
�� | -2.509 |
netflix | -2.490 |
姫 | -2.366 |
Noir | -2.331 |
Token | : |
Token ID | 25 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
beard | +0.193 |
netflix | +0.172 |
�� | +0.164 |
Noir | +0.163 |
姫 | +0.159 |
Neg logit contributions | |
Sabha | -0.294 |
bane | -0.276 |
conn | -0.243 |
ader | -0.225 |
Uz | -0.222 |
Token | Size |
Token ID | 12849 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Sabha | +0.514 |
bane | +0.478 |
conn | +0.418 |
ader | +0.384 |
Loading | +0.382 |
Neg logit contributions | |
beard | -0.384 |
�� | -0.352 |
netflix | -0.352 |
姫 | -0.330 |
Noir | -0.329 |
Token | C |
Token ID | 327 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Sabha | +8.944 |
bane | +8.091 |
conn | +6.464 |
Uz | +6.141 |
Pix | +6.121 |
Neg logit contributions | |
beard | -10.508 |
�� | -10.455 |
netflix | -10.240 |
姫 | -9.891 |
fman | -8.961 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Sabha | +0.081 |
bane | +0.074 |
conn | +0.063 |
ader | +0.057 |
Loading | +0.057 |
Neg logit contributions | |
beard | -0.081 |
�� | -0.075 |
netflix | -0.075 |
姫 | -0.071 |
Noir | -0.070 |
Token | Y |
Token ID | 575 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Sabha | +2.591 |
bane | +2.358 |
conn | +1.931 |
Uz | +1.728 |
ader | +1.725 |
Neg logit contributions | |
beard | -3.426 |
�� | -3.254 |
netflix | -3.225 |
姫 | -3.094 |
Noir | -3.022 |
Token | YR |
Token ID | 38162 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
beard | +2.586 |
netflix | +2.327 |
�� | +2.307 |
Noir | +2.216 |
姫 | +2.183 |
Neg logit contributions | |
Sabha | -2.882 |
bane | -2.679 |
conn | -2.298 |
Loading | -2.089 |
Uz | -2.062 |
Token | DS |
Token ID | 17400 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Sabha | +3.873 |
bane | +3.589 |
conn | +3.050 |
ader | +2.808 |
Uz | +2.785 |
Neg logit contributions | |
beard | -3.649 |
�� | -3.421 |
netflix | -3.412 |
姫 | -3.202 |
Noir | -3.168 |
Token |
|
Token ID | 198 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Sabha | +0.948 |
bane | +0.870 |
conn | +0.733 |
Loading | +0.656 |
Uz | +0.656 |
Neg logit contributions | |
beard | -1.104 |
�� | -1.048 |
netflix | -1.038 |
姫 | -0.981 |
Noir | -0.972 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Sabha | +2.516 |
bane | +2.313 |
conn | +1.966 |
ader | +1.779 |
Loading | +1.767 |
Neg logit contributions | |
beard | -2.575 |
�� | -2.406 |
netflix | -2.398 |
姫 | -2.274 |
Noir | -2.255 |
Token | B |
Token ID | 33 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Sabha | +1.611 |
bane | +1.494 |
conn | +1.209 |
Loading | +1.110 |
Creat | +1.058 |
Neg logit contributions | |
beard | -2.329 |
�� | -2.256 |
netflix | -2.239 |
姫 | -2.128 |
Noir | -2.117 |
Token | earing |
Token ID | 6648 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Sabha | +2.997 |
bane | +2.771 |
conn | +2.408 |
Uz | +2.200 |
ader | +2.200 |
Neg logit contributions | |
beard | -2.415 |
�� | -2.219 |
netflix | -2.218 |
姫 | -2.074 |
Noir | -2.069 |
Token | : |
Token ID | 25 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
beard | +1.045 |
netflix | +0.916 |
Noir | +0.865 |
姫 | +0.843 |
EVA | +0.820 |
Neg logit contributions | |
Sabha | -1.735 |
bane | -1.608 |
conn | -1.427 |
Uz | -1.320 |
ader | -1.320 |
Token | Size |
Token ID | 12849 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
beard | +0.025 |
�� | +0.023 |
netflix | +0.022 |
姫 | +0.021 |
Noir | +0.020 |
Neg logit contributions | |
Sabha | -0.045 |
bane | -0.042 |
conn | -0.037 |
ader | -0.035 |
Uz | -0.035 |
Token | C |
Token ID | 327 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Sabha | +8.500 |
bane | +7.628 |
conn | +6.164 |
Uz | +5.908 |
Pix | +5.824 |
Neg logit contributions | |
beard | -10.748 |
netflix | -10.344 |
�� | -10.298 |
姫 | -9.928 |
Noir | -9.079 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
beard | +1.998 |
�� | +1.869 |
netflix | +1.850 |
姫 | +1.757 |
Noir | +1.745 |
Neg logit contributions | |
Sabha | -2.141 |
bane | -1.975 |
conn | -1.698 |
ader | -1.540 |
Loading | -1.536 |
Token | Center |
Token ID | 3337 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Sabha | +0.127 |
bane | +0.118 |
conn | +0.102 |
ader | +0.093 |
Loading | +0.093 |
Neg logit contributions | |
beard | -0.107 |
�� | -0.099 |
netflix | -0.098 |
姫 | -0.093 |
Noir | -0.093 |
Token | Tr |
Token ID | 833 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
Sabha | +3.727 |
bane | +3.461 |
conn | +2.967 |
ader | +2.706 |
Uz | +2.692 |
Neg logit contributions | |
beard | -3.319 |
�� | -3.129 |
netflix | -3.122 |
姫 | -2.954 |
Noir | -2.878 |
Token | ac |
Token ID | 330 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Sabha | +0.550 |
bane | +0.511 |
conn | +0.443 |
ader | +0.404 |
Loading | +0.404 |
Neg logit contributions | |
beard | -0.444 |
�� | -0.411 |
netflix | -0.410 |
姫 | -0.384 |
Noir | -0.382 |
Token | two |
Token ID | 734 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
Sabha | +0.083 |
bane | +0.077 |
conn | +0.066 |
ader | +0.060 |
Loading | +0.060 |
Neg logit contributions | |
beard | -0.072 |
�� | -0.067 |
netflix | -0.066 |
姫 | -0.063 |
Noir | -0.062 |
Token | of |
Token ID | 286 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Sabha | +0.247 |
bane | +0.228 |
conn | +0.196 |
ader | +0.179 |
Loading | +0.179 |
Neg logit contributions | |
beard | -0.219 |
�� | -0.203 |
netflix | -0.202 |
姫 | -0.191 |
Noir | -0.190 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
beard | +0.694 |
�� | +0.640 |
netflix | +0.640 |
姫 | +0.601 |
Noir | +0.599 |
Neg logit contributions | |
Sabha | -0.841 |
bane | -0.781 |
conn | -0.676 |
ader | -0.618 |
Loading | -0.617 |
Token | iconic |
Token ID | 14133 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
beard | +0.785 |
�� | +0.723 |
netflix | +0.720 |
Noir | +0.682 |
姫 | +0.675 |
Neg logit contributions | |
Sabha | -0.949 |
bane | -0.884 |
conn | -0.764 |
ader | -0.700 |
Loading | -0.698 |
Token | Ts |
Token ID | 13146 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
beard | +0.107 |
�� | +0.099 |
netflix | +0.098 |
姫 | +0.092 |
Noir | +0.092 |
Neg logit contributions | |
Sabha | -0.133 |
bane | -0.124 |
conn | -0.108 |
ader | -0.099 |
Loading | -0.098 |
Token | av |
Token ID | 615 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Sabha | +4.642 |
bane | +4.334 |
conn | +3.727 |
ader | +3.464 |
Uz | +3.452 |
Neg logit contributions | |
beard | -3.845 |
�� | -3.651 |
netflix | -3.595 |
姫 | -3.414 |
Noir | -3.313 |
Token | o |
Token ID | 78 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Sabha | +8.954 |
bane | +8.461 |
conn | +6.953 |
ader | +6.767 |
Pix | +6.352 |
Neg logit contributions | |
beard | -10.350 |
�� | -10.195 |
netflix | -9.820 |
姫 | -9.375 |
Noir | -8.912 |
Token | super |
Token ID | 2208 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Sabha | +1.399 |
bane | +1.296 |
conn | +1.122 |
ader | +1.028 |
Uz | +1.021 |
Neg logit contributions | |
beard | -1.168 |
�� | -1.085 |
netflix | -1.080 |
姫 | -1.017 |
Noir | -1.005 |
Token | t |
Token ID | 256 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
beard | +1.636 |
�� | +1.476 |
netflix | +1.464 |
姫 | +1.363 |
Noir | +1.343 |
Neg logit contributions | |
Sabha | -2.787 |
bane | -2.598 |
conn | -2.300 |
Loading | -2.143 |
ader | -2.139 |
Token | us |
Token ID | 385 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
beard | +0.852 |
netflix | +0.785 |
�� | +0.782 |
姫 | +0.736 |
Noir | +0.728 |
Neg logit contributions | |
Sabha | -1.033 |
bane | -0.955 |
conn | -0.821 |
Loading | -0.756 |
ader | -0.752 |
Token | kers |
Token ID | 15949 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Sabha | +4.812 |
bane | +4.568 |
conn | +4.002 |
ader | +3.784 |
Uz | +3.676 |
Neg logit contributions | |
beard | -2.902 |
�� | -2.738 |
netflix | -2.628 |
姫 | -2.474 |
Noir | -2.399 |
Token | om |
Token ID | 296 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Sabha | +1.543 |
bane | +1.435 |
conn | +1.249 |
ader | +1.142 |
Loading | +1.138 |
Neg logit contributions | |
beard | -1.264 |
�� | -1.183 |
netflix | -1.166 |
姫 | -1.103 |
Noir | -1.091 |
Token | g |
Token ID | 70 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Sabha | +2.233 |
bane | +2.074 |
conn | +1.792 |
ader | +1.640 |
Loading | +1.624 |
Neg logit contributions | |
beard | -1.920 |
�� | -1.806 |
netflix | -1.779 |
姫 | -1.684 |
Noir | -1.664 |
Token | its |
Token ID | 896 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
beard | +2.885 |
netflix | +2.652 |
�� | +2.574 |
姫 | +2.462 |
Noir | +2.431 |
Neg logit contributions | |
Sabha | -3.151 |
bane | -2.865 |
conn | -2.441 |
Uz | -2.272 |
Pix | -2.265 |
Token | amb |
Token ID | 4131 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Sabha | +3.007 |
bane | +2.820 |
conn | +2.437 |
ader | +2.239 |
Loading | +2.202 |
Neg logit contributions | |
beard | -2.480 |
�� | -2.356 |
netflix | -2.307 |
姫 | -2.186 |
Noir | -2.163 |
Token | ry |
Token ID | 563 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Sabha | +7.661 |
bane | +7.279 |
conn | +6.274 |
ader | +6.015 |
Loading | +5.658 |
Neg logit contributions | |
�� | -6.252 |
beard | -6.195 |
netflix | -5.953 |
姫 | -5.673 |
Noir | -5.487 |
Token | / |
Token ID | 14 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Sabha | +1.853 |
bane | +1.718 |
conn | +1.475 |
ader | +1.347 |
Loading | +1.331 |
Neg logit contributions | |
beard | -1.695 |
�� | -1.587 |
netflix | -1.575 |
姫 | -1.495 |
Noir | -1.476 |
Token | status |
Token ID | 13376 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Sabha | +6.596 |
bane | +5.877 |
conn | +4.882 |
Creat | +4.186 |
ader | +4.142 |
Neg logit contributions | |
beard | -12.421 |
�� | -12.393 |
netflix | -11.563 |
姫 | -11.390 |
Noir | -11.320 |
Token | / |
Token ID | 14 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
Sabha | +2.865 |
bane | +2.647 |
conn | +2.259 |
ader | +2.048 |
Loading | +2.036 |
Neg logit contributions | |
beard | -2.845 |
�� | -2.694 |
netflix | -2.652 |
姫 | -2.517 |
Noir | -2.493 |
Token | 9 |
Token ID | 24 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Sabha | +7.721 |
bane | +7.452 |
conn | +6.558 |
ader | +6.035 |
Loading | +6.025 |
Neg logit contributions | |
�� | -6.042 |
beard | -5.942 |
netflix | -5.525 |
Noir | -5.210 |
姫 | -5.205 |
Token | 175 |
Token ID | 17430 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Sabha | +2.592 |
bane | +2.432 |
conn | +2.144 |
ader | +1.986 |
Loading | +1.975 |
Neg logit contributions | |
beard | -1.684 |
�� | -1.567 |
netflix | -1.539 |
姫 | -1.437 |
Noir | -1.422 |
Token | 669 |
Token ID | 36657 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Sabha | +1.710 |
bane | +1.598 |
conn | +1.401 |
ader | +1.294 |
Loading | +1.287 |
Neg logit contributions | |
beard | -1.182 |
�� | -1.095 |
netflix | -1.084 |
姫 | -1.014 |
Noir | -1.002 |
Token | December |
Token ID | 3426 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
beard | +0.723 |
netflix | +0.673 |
Noir | +0.657 |
�� | +0.653 |
姫 | +0.646 |
Neg logit contributions | |
Sabha | -0.701 |
bane | -0.651 |
conn | -0.553 |
Loading | -0.493 |
Pix | -0.491 |
Token | 13 |
Token ID | 1511 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
beard | +1.040 |
netflix | +0.939 |
Noir | +0.904 |
Hulk | +0.846 |
heels | +0.843 |
Neg logit contributions | |
Sabha | -1.660 |
bane | -1.584 |
conn | -1.382 |
Loading | -1.269 |
Pix | -1.267 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
beard | +1.119 |
netflix | +1.001 |
Noir | +0.942 |
姫 | +0.928 |
EVA | +0.914 |
Neg logit contributions | |
Sabha | -1.426 |
bane | -1.307 |
conn | -1.135 |
Uz | -1.050 |
ader | -1.046 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Sabha | +2.749 |
bane | +2.536 |
conn | +2.152 |
ader | +1.955 |
Loading | +1.931 |
Neg logit contributions | |
beard | -2.810 |
netflix | -2.613 |
�� | -2.600 |
姫 | -2.472 |
Noir | -2.460 |
Token | boys |
Token ID | 13202 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
beard | +0.324 |
netflix | +0.289 |
�� | +0.281 |
姫 | +0.265 |
Noir | +0.259 |
Neg logit contributions | |
Sabha | -0.597 |
bane | -0.553 |
conn | -0.491 |
Uz | -0.460 |
Pix | -0.459 |
Token | beware |
Token ID | 40600 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Sabha | +0.918 |
bane | +0.839 |
conn | +0.707 |
ader | +0.634 |
Loading | +0.631 |
Neg logit contributions | |
beard | -1.042 |
�� | -0.976 |
netflix | -0.973 |
姫 | -0.925 |
Noir | -0.919 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Sabha | +7.441 |
bane | +6.942 |
conn | +5.457 |
ader | +5.087 |
Pix | +5.054 |
Neg logit contributions | |
beard | -11.124 |
�� | -10.953 |
姫 | -10.233 |
netflix | -10.228 |
EVA | -9.871 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Sabha | +0.986 |
bane | +0.900 |
conn | +0.770 |
ader | +0.703 |
Uz | +0.702 |
Neg logit contributions | |
beard | -0.916 |
netflix | -0.844 |
�� | -0.806 |
Noir | -0.793 |
姫 | -0.786 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Sabha | +0.988 |
bane | +0.918 |
conn | +0.790 |
ader | +0.723 |
Loading | +0.719 |
Neg logit contributions | |
beard | -0.866 |
�� | -0.808 |
netflix | -0.802 |
姫 | -0.757 |
Noir | -0.750 |
Token | : |
Token ID | 25 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
beard | +4.174 |
netflix | +3.439 |
Noir | +3.177 |
Hulk | +3.096 |
TG | +3.006 |
Neg logit contributions | |
Sabha | -9.369 |
bane | -8.589 |
conn | -7.805 |
Uz | -7.338 |
ader | -7.137 |
Token | j |
Token ID | 474 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
beard | +0.899 |
netflix | +0.833 |
�� | +0.833 |
Noir | +0.786 |
姫 | +0.786 |
Neg logit contributions | |
Sabha | -0.969 |
bane | -0.895 |
conn | -0.770 |
ader | -0.699 |
Loading | -0.698 |
Token | ] |
Token ID | 60 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Sabha | +2.888 |
bane | +2.586 |
conn | +2.084 |
ader | +1.856 |
Uz | +1.848 |
Neg logit contributions | |
beard | -4.589 |
�� | -4.452 |
netflix | -4.405 |
姫 | -4.158 |
heels | -4.116 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Sabha | +1.215 |
bane | +1.124 |
conn | +0.969 |
ader | +0.885 |
Loading | +0.879 |
Neg logit contributions | |
beard | -1.068 |
�� | -0.992 |
netflix | -0.989 |
姫 | -0.933 |
Noir | -0.926 |
Token |
|
Token ID | 198 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
beard | +0.910 |
netflix | +0.823 |
Noir | +0.778 |
姫 | +0.761 |
Hulk | +0.750 |
Neg logit contributions | |
Sabha | -1.074 |
bane | -0.978 |
conn | -0.841 |
ader | -0.775 |
Uz | -0.771 |
Token | Mus |
Token ID | 10694 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
beard | +0.409 |
netflix | +0.377 |
�� | +0.372 |
姫 | +0.354 |
Noir | +0.349 |
Neg logit contributions | |
Sabha | -0.497 |
bane | -0.457 |
conn | -0.396 |
ader | -0.363 |
Uz | -0.362 |
Token | ics |
Token ID | 873 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Sabha | +1.667 |
bane | +1.487 |
conn | +1.161 |
ader | +0.995 |
Loading | +0.971 |
Neg logit contributions | |
beard | -3.059 |
�� | -2.919 |
netflix | -2.893 |
姫 | -2.784 |
Noir | -2.753 |
Token | c |
Token ID | 66 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Sabha | +1.926 |
bane | +1.780 |
conn | +1.527 |
ader | +1.395 |
Uz | +1.389 |
Neg logit contributions | |
beard | -1.723 |
�� | -1.619 |
netflix | -1.602 |
姫 | -1.516 |
Noir | -1.487 |
Token | apes |
Token ID | 7916 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Sabha | +10.462 |
bane | +9.524 |
conn | +7.986 |
ader | +7.934 |
Uz | +7.372 |
Neg logit contributions | |
�� | -9.081 |
beard | -9.026 |
netflix | -8.313 |
姫 | -8.259 |
EVA | -7.643 |
Token | from |
Token ID | 422 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Sabha | +0.966 |
bane | +0.894 |
conn | +0.770 |
ader | +0.703 |
Loading | +0.699 |
Neg logit contributions | |
beard | -0.852 |
�� | -0.794 |
netflix | -0.789 |
姫 | -0.745 |
Noir | -0.737 |
Token | M |
Token ID | 337 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Sabha | +1.804 |
bane | +1.663 |
conn | +1.415 |
ader | +1.290 |
Uz | +1.284 |
Neg logit contributions | |
beard | -1.757 |
�� | -1.648 |
netflix | -1.630 |
姫 | -1.549 |
Noir | -1.525 |
Token | oom |
Token ID | 4207 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
beard | +1.816 |
�� | +1.724 |
netflix | +1.715 |
姫 | +1.648 |
Noir | +1.635 |
Neg logit contributions | |
Sabha | -1.042 |
bane | -0.930 |
conn | -0.731 |
ader | -0.634 |
Loading | -0.624 |
Token | in |
Token ID | 259 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Sabha | +1.021 |
bane | +0.916 |
conn | +0.721 |
ader | +0.626 |
Uz | +0.611 |
Neg logit contributions | |
beard | -1.781 |
�� | -1.721 |
netflix | -1.676 |
姫 | -1.638 |
Noir | -1.598 |
Token | ! |
Token ID | 0 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
beard | +1.270 |
netflix | +1.162 |
Noir | +1.084 |
heels | +1.062 |
姫 | +1.059 |
Neg logit contributions | |
Sabha | -1.618 |
bane | -1.491 |
conn | -1.294 |
Uz | -1.195 |
Loading | -1.176 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Sabha | +3.153 |
bane | +2.905 |
conn | +2.412 |
ader | +2.165 |
Uz | +2.160 |
Neg logit contributions | |
beard | -3.645 |
�� | -3.499 |
netflix | -3.445 |
姫 | -3.288 |
Noir | -3.218 |
Token | Image |
Token ID | 5159 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
beard | +0.437 |
netflix | +0.403 |
�� | +0.401 |
姫 | +0.377 |
Noir | +0.372 |
Neg logit contributions | |
Sabha | -0.549 |
bane | -0.508 |
conn | -0.440 |
ader | -0.405 |
Uz | -0.403 |
Token | copyright |
Token ID | 6634 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Sabha | +2.349 |
bane | +2.147 |
conn | +1.787 |
Loading | +1.605 |
ader | +1.592 |
Neg logit contributions | |
beard | -2.804 |
�� | -2.674 |
netflix | -2.640 |
姫 | -2.516 |
Noir | -2.471 |
Token | ESA |
Token ID | 42212 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Sabha | +4.753 |
bane | +4.316 |
conn | +3.702 |
Pix | +3.438 |
Uz | +3.416 |
Neg logit contributions | |
beard | -4.602 |
�� | -4.398 |
netflix | -4.249 |
姫 | -4.094 |
Noir | -3.931 |
Token | Image |
Token ID | 7412 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Sabha | +2.748 |
bane | +2.547 |
conn | +2.189 |
Pix | +1.995 |
ader | +1.980 |
Neg logit contributions | |
beard | -2.693 |
�� | -2.587 |
netflix | -2.532 |
姫 | -2.410 |
Noir | -2.360 |
Token | caption |
Token ID | 8305 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
Sabha | +5.295 |
bane | +4.574 |
conn | +3.069 |
ader | +2.810 |
Pix | +2.635 |
Neg logit contributions | |
�� | -14.202 |
beard | -13.274 |
netflix | -12.837 |
姫 | -12.771 |
Noir | -12.250 |
Token | Go |
Token ID | 1514 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Sabha | +0.033 |
bane | +0.030 |
conn | +0.026 |
ader | +0.024 |
Loading | +0.024 |
Neg logit contributions | |
beard | -0.027 |
�� | -0.025 |
netflix | -0.025 |
姫 | -0.023 |
Noir | -0.023 |
Token | ce |
Token ID | 344 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
beard | +1.637 |
�� | +1.516 |
netflix | +1.513 |
姫 | +1.422 |
Noir | +1.412 |
Neg logit contributions | |
Sabha | -1.971 |
bane | -1.829 |
conn | -1.580 |
ader | -1.440 |
Uz | -1.435 |
Token | uses |
Token ID | 3544 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
beard | +1.204 |
netflix | +1.114 |
�� | +1.113 |
姫 | +1.052 |
Noir | +1.049 |
Neg logit contributions | |
Sabha | -1.343 |
bane | -1.234 |
conn | -1.060 |
Loading | -0.969 |
ader | -0.965 |
Token | an |
Token ID | 281 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
beard | +0.409 |
�� | +0.380 |
netflix | +0.379 |
姫 | +0.357 |
Noir | +0.354 |
Neg logit contributions | |
Sabha | -0.461 |
bane | -0.426 |
conn | -0.367 |
ader | -0.335 |
Loading | -0.333 |
Token | " |
Token ID | 1 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
beard | +1.560 |
netflix | +1.370 |
Noir | +1.237 |
姫 | +1.187 |
EVA | +1.186 |
Neg logit contributions | |
Sabha | -2.963 |
bane | -2.681 |
conn | -2.360 |
Uz | -2.279 |
Pix | -2.230 |
Token | & |
Token ID | 1222 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Sabha | +2.424 |
bane | +2.227 |
conn | +1.916 |
ader | +1.731 |
Loading | +1.713 |
Neg logit contributions | |
beard | -2.589 |
�� | -2.411 |
netflix | -2.390 |
姫 | -2.304 |
Noir | -2.251 |
Token | ] |
Token ID | 60 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Sabha | +0.276 |
bane | +0.250 |
conn | +0.209 |
ader | +0.184 |
Loading | +0.183 |
Neg logit contributions | |
beard | -0.388 |
�� | -0.368 |
netflix | -0.366 |
姫 | -0.352 |
Noir | -0.345 |
Token | @ |
Token ID | 31 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Sabha | +3.503 |
bane | +3.231 |
conn | +2.742 |
Loading | +2.336 |
ader | +2.311 |
Neg logit contributions | |
beard | -5.949 |
�� | -5.803 |
netflix | -5.754 |
姫 | -5.614 |
Noir | -5.449 |
Token | index |
Token ID | 9630 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Sabha | +6.076 |
bane | +5.775 |
conn | +5.164 |
Loading | +4.683 |
ader | +4.596 |
Neg logit contributions | |
beard | -5.208 |
�� | -4.887 |
姫 | -4.760 |
netflix | -4.735 |
Noir | -4.535 |
Token | State |
Token ID | 9012 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Sabha | +6.613 |
bane | +6.254 |
conn | +5.451 |
Loading | +5.093 |
Creat | +4.892 |
Neg logit contributions | |
�� | -10.361 |
beard | -10.171 |
netflix | -9.663 |
姫 | -9.337 |
heels | -9.281 |
Token | < |
Token ID | 1279 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Sabha | +7.808 |
bane | +7.388 |
conn | +6.500 |
Loading | +5.726 |
Creat | +5.638 |
Neg logit contributions | |
beard | -9.848 |
�� | -9.510 |
姫 | -9.098 |
netflix | -8.999 |
heels | -8.762 |
Token | | |
Token ID | 91 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Sabha | +3.881 |
bane | +3.673 |
conn | +3.137 |
Loading | +2.835 |
ader | +2.761 |
Neg logit contributions | |
beard | -4.925 |
�� | -4.692 |
netflix | -4.687 |
姫 | -4.539 |
Noir | -4.374 |
Token | { |
Token ID | 90 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
Sabha | +3.139 |
bane | +2.953 |
conn | +2.498 |
Loading | +2.259 |
ader | +2.182 |
Neg logit contributions | |
beard | -4.219 |
�� | -3.980 |
netflix | -3.960 |
姫 | -3.779 |
Noir | -3.757 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Sabha | +0.652 |
bane | +0.606 |
conn | +0.529 |
ader | +0.487 |
Loading | +0.484 |
Neg logit contributions | |
beard | -0.486 |
�� | -0.448 |
netflix | -0.446 |
姫 | -0.419 |
Noir | -0.414 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
beard | +3.190 |
�� | +2.973 |
netflix | +2.965 |
姫 | +2.799 |
Noir | +2.780 |
Neg logit contributions | |
Sabha | -3.363 |
bane | -3.091 |
conn | -2.648 |
ader | -2.402 |
Loading | -2.393 |
Token | arg |
Token ID | 1822 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Sabha | +3.980 |
bane | +3.741 |
conn | +3.243 |
ader | +3.108 |
Uz | +3.013 |
Neg logit contributions | |
beard | -3.133 |
�� | -2.926 |
netflix | -2.886 |
姫 | -2.795 |
Noir | -2.660 |
Token | parse |
Token ID | 29572 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Sabha | +4.573 |
bane | +4.309 |
conn | +3.663 |
ader | +3.315 |
Loading | +3.279 |
Neg logit contributions | |
beard | -4.804 |
�� | -4.669 |
netflix | -4.432 |
姫 | -4.294 |
Noir | -4.260 |
Token | import |
Token ID | 1330 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Sabha | +3.737 |
bane | +3.232 |
conn | +2.392 |
ader | +2.105 |
Uz | +2.000 |
Neg logit contributions | |
beard | -8.471 |
�� | -8.414 |
姫 | -8.049 |
netflix | -7.969 |
Noir | -7.673 |
Token | im |
Token ID | 545 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Sabha | +4.429 |
bane | +3.997 |
conn | +3.267 |
ader | +2.920 |
Pix | +2.846 |
Neg logit contributions | |
beard | -6.583 |
�� | -6.426 |
netflix | -6.214 |
姫 | -6.108 |
Noir | -5.877 |
Token | utils |
Token ID | 26791 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
Sabha | +2.078 |
bane | +1.919 |
conn | +1.660 |
Uz | +1.524 |
ader | +1.518 |
Neg logit contributions | |
beard | -1.676 |
netflix | -1.550 |
�� | -1.534 |
姫 | -1.452 |
Noir | -1.428 |
Token | import |
Token ID | 1330 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Sabha | +4.134 |
bane | +3.612 |
conn | +2.656 |
ader | +2.288 |
Uz | +2.208 |
Neg logit contributions | |
�� | -9.893 |
beard | -9.842 |
姫 | -9.409 |
netflix | -9.276 |
Noir | -8.863 |
Token | c |
Token ID | 269 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
Sabha | +5.035 |
bane | +4.487 |
conn | +3.509 |
ader | +2.890 |
Pix | +2.788 |
Neg logit contributions | |
beard | -13.117 |
�� | -12.404 |
姫 | -12.350 |
netflix | -12.221 |
Noir | -11.912 |
Token | v |
Token ID | 85 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
beard | +0.565 |
netflix | +0.520 |
Noir | +0.477 |
�� | +0.476 |
姫 | +0.475 |
Neg logit contributions | |
Sabha | -0.649 |
bane | -0.581 |
conn | -0.497 |
Uz | -0.469 |
Pix | -0.459 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
beard | +2.004 |
netflix | +1.849 |
Noir | +1.684 |
姫 | +1.653 |
lap | +1.633 |
Neg logit contributions | |
Sabha | -3.319 |
bane | -2.988 |
conn | -2.680 |
Uz | -2.513 |
Pix | -2.493 |
Token | # |
Token ID | 1303 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Sabha | +0.178 |
bane | +0.163 |
conn | +0.138 |
ader | +0.128 |
Loading | +0.124 |
Neg logit contributions | |
beard | -0.206 |
�� | -0.194 |
netflix | -0.191 |
姫 | -0.187 |
Noir | -0.180 |
Token | construct |
Token ID | 5678 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Sabha | +5.156 |
bane | +4.719 |
conn | +4.086 |
ader | +3.722 |
Creat | +3.651 |
Neg logit contributions | |
beard | -5.487 |
netflix | -5.208 |
�� | -5.154 |
姫 | -4.964 |
Noir | -4.778 |
Token | If |
Token ID | 1002 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
beard | +0.401 |
netflix | +0.369 |
�� | +0.365 |
Noir | +0.345 |
姫 | +0.345 |
Neg logit contributions | |
Sabha | -0.484 |
bane | -0.448 |
conn | -0.387 |
ader | -0.355 |
Loading | -0.350 |
Token | you |
Token ID | 345 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Sabha | +4.649 |
bane | +4.223 |
conn | +3.630 |
Creat | +3.362 |
Loading | +3.360 |
Neg logit contributions | |
beard | -5.188 |
�� | -4.995 |
netflix | -4.751 |
姫 | -4.675 |
Noir | -4.588 |
Token | � |
Token ID | 447 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Sabha | +2.875 |
bane | +2.677 |
conn | +2.259 |
ader | +2.072 |
Loading | +2.063 |
Neg logit contributions | |
beard | -2.903 |
�� | -2.761 |
netflix | -2.702 |
姫 | -2.566 |
Noir | -2.559 |
Token | � |
Token ID | 247 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Sabha | +1.790 |
bane | +1.643 |
conn | +1.398 |
ader | +1.263 |
Loading | +1.257 |
Neg logit contributions | |
beard | -1.826 |
�� | -1.709 |
netflix | -1.698 |
姫 | -1.610 |
Noir | -1.595 |
Token | re |
Token ID | 260 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Sabha | +0.837 |
bane | +0.760 |
conn | +0.641 |
Uz | +0.576 |
Loading | +0.574 |
Neg logit contributions | |
beard | -0.962 |
netflix | -0.899 |
�� | -0.886 |
姫 | -0.845 |
Noir | -0.842 |
Token | using |
Token ID | 1262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Sabha | +9.115 |
bane | +8.428 |
conn | +7.004 |
Loading | +6.525 |
Pix | +6.420 |
Neg logit contributions | |
�� | -11.071 |
beard | -10.613 |
netflix | -10.184 |
姫 | -10.075 |
Noir | -9.584 |
Token | this |
Token ID | 428 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Sabha | +7.347 |
bane | +6.742 |
conn | +5.527 |
ader | +4.878 |
Loading | +4.853 |
Neg logit contributions | |
�� | -11.161 |
beard | -10.533 |
姫 | -10.150 |
netflix | -10.104 |
Noir | -9.502 |
Token | information |
Token ID | 1321 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Sabha | +6.769 |
bane | +6.269 |
conn | +5.488 |
Loading | +5.167 |
ader | +5.089 |
Neg logit contributions | |
�� | -4.939 |
beard | -4.864 |
netflix | -4.559 |
姫 | -4.361 |
Noir | -4.166 |
Token | on |
Token ID | 319 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Sabha | +1.664 |
bane | +1.542 |
conn | +1.334 |
ader | +1.217 |
Loading | +1.209 |
Neg logit contributions | |
beard | -1.418 |
netflix | -1.309 |
�� | -1.294 |
姫 | -1.229 |
Noir | -1.223 |
Token | your |
Token ID | 534 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Sabha | +3.052 |
bane | +2.758 |
conn | +2.236 |
ader | +2.000 |
Loading | +1.982 |
Neg logit contributions | |
beard | -4.334 |
�� | -4.228 |
netflix | -4.108 |
姫 | -3.956 |
Noir | -3.872 |
Token | website |
Token ID | 3052 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Sabha | +2.493 |
bane | +2.310 |
conn | +1.990 |
ader | +1.820 |
Loading | +1.810 |
Neg logit contributions | |
beard | -2.161 |
�� | -2.019 |
netflix | -2.002 |
姫 | -1.891 |
Noir | -1.869 |
Token | pops |
Token ID | 26384 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Sabha | +1.062 |
bane | +0.985 |
conn | +0.853 |
ader | +0.782 |
Loading | +0.777 |
Neg logit contributions | |
beard | -0.878 |
�� | -0.815 |
netflix | -0.810 |
姫 | -0.764 |
Noir | -0.755 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Sabha | +2.082 |
bane | +1.947 |
conn | +1.635 |
ader | +1.517 |
Pix | +1.489 |
Neg logit contributions | |
beard | -2.059 |
�� | -1.950 |
netflix | -1.904 |
姫 | -1.830 |
Noir | -1.775 |
Token | distortions |
Token ID | 47876 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
Sabha | +0.155 |
bane | +0.143 |
conn | +0.123 |
ader | +0.112 |
Loading | +0.111 |
Neg logit contributions | |
beard | -0.142 |
�� | -0.132 |
netflix | -0.131 |
姫 | -0.124 |
Noir | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
beard | +0.014 |
�� | +0.013 |
netflix | +0.013 |
姫 | +0.013 |
Noir | +0.012 |
Neg logit contributions | |
Sabha | -0.014 |
bane | -0.013 |
conn | -0.011 |
ader | -0.010 |
Loading | -0.010 |
Token | lights |
Token ID | 7588 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Sabha | +0.536 |
bane | +0.496 |
conn | +0.426 |
ader | +0.389 |
Loading | +0.386 |
Neg logit contributions | |
beard | -0.483 |
�� | -0.450 |
netflix | -0.448 |
姫 | -0.423 |
Noir | -0.419 |
Token | ab |
Token ID | 397 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Sabha | +2.901 |
bane | +2.706 |
conn | +2.231 |
ader | +2.067 |
Loading | +2.029 |
Neg logit contributions | |
beard | -3.087 |
�� | -2.922 |
netflix | -2.854 |
姫 | -2.758 |
Noir | -2.690 |
Token | ers |
Token ID | 364 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Sabha | +5.836 |
bane | +5.084 |
conn | +3.861 |
ader | +3.605 |
Pix | +3.386 |
Neg logit contributions | |
beard | -12.212 |
�� | -12.118 |
netflix | -11.469 |
姫 | -10.925 |
Hulk | -10.730 |
Token | — |
Token ID | 960 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Sabha | +1.555 |
bane | +1.460 |
conn | +1.199 |
ader | +1.108 |
Pix | +1.089 |
Neg logit contributions | |
beard | -1.726 |
�� | -1.635 |
netflix | -1.605 |
姫 | -1.537 |
Noir | -1.511 |
Token | stuff |
Token ID | 41094 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Sabha | +1.289 |
bane | +1.205 |
conn | +1.062 |
ader | +0.984 |
Loading | +0.980 |
Neg logit contributions | |
beard | -0.807 |
�� | -0.738 |
netflix | -0.735 |
姫 | -0.683 |
Noir | -0.675 |
Token | that |
Token ID | 326 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Sabha | +1.038 |
bane | +0.960 |
conn | +0.825 |
ader | +0.753 |
Loading | +0.748 |
Neg logit contributions | |
beard | -0.929 |
�� | -0.866 |
netflix | -0.861 |
姫 | -0.814 |
Noir | -0.805 |
Token | 's |
Token ID | 338 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Sabha | +2.029 |
bane | +1.876 |
conn | +1.612 |
ader | +1.469 |
Loading | +1.460 |
Neg logit contributions | |
beard | -1.839 |
�� | -1.712 |
netflix | -1.705 |
姫 | -1.610 |
Noir | -1.597 |
Token | ent |
Token ID | 298 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
beard | +1.209 |
netflix | +1.144 |
�� | +1.109 |
Noir | +1.059 |
姫 | +1.048 |
Neg logit contributions | |
Sabha | -1.027 |
bane | -0.887 |
conn | -0.756 |
Loading | -0.690 |
Uz | -0.685 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Sabha | +2.902 |
bane | +2.701 |
conn | +2.296 |
ader | +2.123 |
Uz | +2.113 |
Neg logit contributions | |
beard | -2.657 |
�� | -2.506 |
netflix | -2.497 |
姫 | -2.350 |
Noir | -2.309 |
Token | � |
Token ID | 447 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Sabha | +2.214 |
bane | +2.049 |
conn | +1.746 |
ader | +1.599 |
Uz | +1.593 |
Neg logit contributions | |
beard | -2.039 |
�� | -1.908 |
netflix | -1.896 |
姫 | -1.794 |
Noir | -1.765 |
Token | � |
Token ID | 251 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Sabha | +0.328 |
bane | +0.300 |
conn | +0.260 |
ader | +0.235 |
Uz | +0.233 |
Neg logit contributions | |
beard | -0.300 |
�� | -0.282 |
netflix | -0.276 |
姫 | -0.262 |
Noir | -0.260 |
Token | John |
Token ID | 1757 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Sabha | +2.372 |
bane | +2.196 |
conn | +1.872 |
ader | +1.708 |
Uz | +1.696 |
Neg logit contributions | |
beard | -2.276 |
�� | -2.137 |
netflix | -2.125 |
姫 | -2.007 |
Noir | -1.986 |
Token | Mc |
Token ID | 1982 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Sabha | +3.628 |
bane | +3.346 |
conn | +2.856 |
ader | +2.627 |
Uz | +2.614 |
Neg logit contributions | |
beard | -3.243 |
�� | -3.044 |
netflix | -3.042 |
姫 | -2.869 |
Noir | -2.810 |
Token | |
Token ID | 3907 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Sabha | +7.536 |
bane | +7.036 |
conn | +5.468 |
Uz | +5.021 |
Loading | +4.891 |
Neg logit contributions | |
beard | -10.152 |
�� | -10.002 |
netflix | -9.781 |
姫 | -9.429 |
Noir | -9.022 |
Token | C |
Token ID | 34 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Sabha | +0.618 |
bane | +0.571 |
conn | +0.495 |
ader | +0.453 |
Uz | +0.449 |
Neg logit contributions | |
beard | -0.520 |
�� | -0.479 |
netflix | -0.477 |
姫 | -0.452 |
Noir | -0.446 |
Token | ain |
Token ID | 391 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Sabha | +5.893 |
bane | +5.697 |
conn | +4.817 |
ader | +4.651 |
Creat | +4.314 |
Neg logit contributions | |
�� | -4.574 |
beard | -4.538 |
netflix | -4.410 |
姫 | -4.254 |
Noir | -4.028 |
Token | told |
Token ID | 1297 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Sabha | +3.261 |
bane | +3.028 |
conn | +2.576 |
ader | +2.379 |
Uz | +2.351 |
Neg logit contributions | |
beard | -3.043 |
�� | -2.891 |
netflix | -2.884 |
姫 | -2.718 |
Noir | -2.653 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
beard | +1.118 |
�� | +1.037 |
netflix | +1.035 |
Noir | +0.983 |
姫 | +0.979 |
Neg logit contributions | |
Sabha | -1.159 |
bane | -1.066 |
conn | -0.917 |
Loading | -0.829 |
ader | -0.827 |
Token | * |
Token ID | 1635 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
beard | +0.572 |
�� | +0.527 |
netflix | +0.524 |
姫 | +0.491 |
Noir | +0.487 |
Neg logit contributions | |
Sabha | -0.783 |
bane | -0.730 |
conn | -0.636 |
ader | -0.586 |
Loading | -0.583 |
Token | FROM |
Token ID | 16034 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
beard | +1.661 |
�� | +1.492 |
netflix | +1.483 |
姫 | +1.357 |
Noir | +1.337 |
Neg logit contributions | |
Sabha | -3.508 |
bane | -3.303 |
conn | -2.949 |
ader | -2.759 |
Loading | -2.747 |
Token | [ |
Token ID | 685 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
Sabha | +1.451 |
bane | +1.337 |
conn | +1.166 |
ader | +1.057 |
Loading | +1.056 |
Neg logit contributions | |
beard | -1.299 |
�� | -1.218 |
netflix | -1.203 |
姫 | -1.147 |
Noir | -1.124 |
Token | big |
Token ID | 1263 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
Sabha | +2.720 |
bane | +2.517 |
conn | +2.190 |
ader | +1.990 |
Loading | +1.975 |
Neg logit contributions | |
beard | -2.410 |
�� | -2.276 |
netflix | -2.240 |
姫 | -2.143 |
Noir | -2.095 |
Token | query |
Token ID | 22766 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Sabha | +0.105 |
bane | +0.098 |
conn | +0.086 |
Uz | +0.082 |
Pix | +0.080 |
Neg logit contributions | |
beard | -0.063 |
netflix | -0.057 |
�� | -0.054 |
姫 | -0.052 |
Noir | -0.052 |
Token | - |
Token ID | 532 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
beard | +2.932 |
�� | +2.735 |
netflix | +2.730 |
姫 | +2.581 |
Noir | +2.561 |
Neg logit contributions | |
Sabha | -3.008 |
bane | -2.773 |
conn | -2.365 |
ader | -2.145 |
Loading | -2.132 |
Token | public |
Token ID | 1171 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Sabha | +7.387 |
bane | +6.463 |
conn | +5.612 |
ader | +4.882 |
Loading | +4.841 |
Neg logit contributions | |
beard | -10.028 |
�� | -9.751 |
netflix | -9.358 |
姫 | -9.204 |
Noir | -8.810 |
Token | - |
Token ID | 532 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Sabha | +0.318 |
bane | +0.288 |
conn | +0.247 |
ader | +0.223 |
Loading | +0.221 |
Neg logit contributions | |
beard | -0.344 |
�� | -0.326 |
netflix | -0.321 |
姫 | -0.306 |
Noir | -0.302 |
Token | data |
Token ID | 1366 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
Sabha | +7.985 |
bane | +7.237 |
conn | +6.641 |
Loading | +6.040 |
ader | +6.016 |
Neg logit contributions | |
beard | -6.789 |
�� | -6.705 |
netflix | -6.315 |
姫 | -6.140 |
Noir | -5.803 |
Token | : |
Token ID | 1058 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
beard | +0.367 |
�� | +0.330 |
netflix | +0.321 |
姫 | +0.295 |
Noir | +0.287 |
Neg logit contributions | |
Sabha | -0.868 |
bane | -0.819 |
conn | -0.739 |
ader | -0.692 |
Loading | -0.691 |
Token | github |
Token ID | 33084 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Sabha | +3.868 |
bane | +3.524 |
conn | +3.014 |
ader | +2.677 |
Loading | +2.626 |
Neg logit contributions | |
beard | -4.711 |
�� | -4.536 |
netflix | -4.386 |
姫 | -4.325 |
Noir | -4.169 |
Token | that |
Token ID | 326 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
Sabha | +1.607 |
bane | +1.483 |
conn | +1.270 |
ader | +1.155 |
Loading | +1.148 |
Neg logit contributions | |
beard | -1.512 |
�� | -1.408 |
netflix | -1.404 |
姫 | -1.328 |
Noir | -1.317 |
Token | found |
Token ID | 1043 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
Sabha | +0.648 |
bane | +0.602 |
conn | +0.520 |
ader | +0.472 |
Loading | +0.472 |
Neg logit contributions | |
beard | -0.547 |
netflix | -0.504 |
�� | -0.498 |
Noir | -0.476 |
姫 | -0.474 |
Token | 43 |
Token ID | 5946 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Sabha | +0.753 |
bane | +0.695 |
conn | +0.594 |
ader | +0.541 |
Loading | +0.537 |
Neg logit contributions | |
beard | -0.716 |
�� | -0.670 |
netflix | -0.666 |
姫 | -0.630 |
Noir | -0.623 |
Token | percent |
Token ID | 1411 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Sabha | +3.215 |
bane | +2.772 |
conn | +2.288 |
Uz | +1.976 |
ader | +1.948 |
Neg logit contributions | |
beard | -5.402 |
netflix | -5.220 |
�� | -5.142 |
姫 | -4.974 |
Noir | -4.849 |
Token | had |
Token ID | 550 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Sabha | +3.018 |
bane | +2.712 |
conn | +2.255 |
Uz | +2.071 |
Loading | +2.003 |
Neg logit contributions | |
beard | -3.980 |
�� | -3.863 |
netflix | -3.770 |
姫 | -3.626 |
Noir | -3.582 |
Token | never |
Token ID | 1239 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Sabha | +6.640 |
bane | +6.015 |
conn | +5.009 |
Uz | +4.688 |
Loading | +4.489 |
Neg logit contributions | |
beard | -8.353 |
�� | -8.240 |
netflix | -7.815 |
姫 | -7.665 |
EVA | -7.367 |
Token | heard |
Token ID | 2982 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Sabha | +5.961 |
bane | +5.115 |
conn | +3.950 |
Uz | +3.503 |
ader | +3.496 |
Neg logit contributions | |
beard | -11.606 |
�� | -11.554 |
netflix | -10.984 |
姫 | -10.729 |
EVA | -10.622 |
Token | of |
Token ID | 286 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Sabha | +2.481 |
bane | +2.249 |
conn | +1.820 |
ader | +1.652 |
Uz | +1.641 |
Neg logit contributions | |
beard | -3.353 |
�� | -3.212 |
netflix | -3.120 |
姫 | -2.981 |
Noir | -2.971 |
Token | Pelosi |
Token ID | 29611 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Sabha | +3.140 |
bane | +2.876 |
conn | +2.432 |
ader | +2.222 |
Uz | +2.215 |
Neg logit contributions | |
beard | -3.192 |
�� | -3.016 |
netflix | -2.964 |
姫 | -2.812 |
Noir | -2.768 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Sabha | +1.130 |
bane | +1.046 |
conn | +0.901 |
ader | +0.821 |
Loading | +0.819 |
Neg logit contributions | |
beard | -0.991 |
netflix | -0.917 |
�� | -0.914 |
姫 | -0.865 |
Noir | -0.860 |
Token | while |
Token ID | 981 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
Sabha | +2.250 |
bane | +2.080 |
conn | +1.790 |
ader | +1.634 |
Loading | +1.624 |
Neg logit contributions | |
beard | -2.007 |
�� | -1.869 |
netflix | -1.860 |
姫 | -1.757 |
Noir | -1.740 |
Token | ales |
Token ID | 2040 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
beard | +3.259 |
netflix | +2.919 |
�� | +2.885 |
姫 | +2.749 |
Noir | +2.739 |
Neg logit contributions | |
Sabha | -4.084 |
bane | -3.687 |
conn | -3.164 |
Loading | -2.950 |
Pix | -2.935 |
Token | in |
Token ID | 287 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Sabha | +1.360 |
bane | +1.251 |
conn | +1.043 |
ader | +0.940 |
Uz | +0.931 |
Neg logit contributions | |
beard | -1.609 |
�� | -1.512 |
netflix | -1.509 |
姫 | -1.435 |
Noir | -1.423 |
Token | com |
Token ID | 401 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Sabha | +0.146 |
bane | +0.135 |
conn | +0.114 |
ader | +0.104 |
Loading | +0.103 |
Neg logit contributions | |
beard | -0.149 |
�� | -0.140 |
netflix | -0.139 |
姫 | -0.132 |
Noir | -0.131 |
Token | |
Token ID | 3907 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Sabha | +1.569 |
bane | +1.432 |
conn | +1.181 |
ader | +1.048 |
Loading | +1.037 |
Neg logit contributions | |
beard | -2.070 |
�� | -1.959 |
netflix | -1.948 |
姫 | -1.860 |
Noir | -1.844 |
Token | par |
Token ID | 1845 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
beard | +6.784 |
netflix | +6.123 |
fman | +5.673 |
heels | +5.645 |
Noir | +5.605 |
Neg logit contributions | |
Sabha | -8.145 |
bane | -7.009 |
conn | -6.136 |
Loading | -5.854 |
Uz | -5.764 |
Token | |
Token ID | 3907 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
beard | +6.503 |
netflix | +6.054 |
Noir | +5.698 |
�� | +5.651 |
heels | +5.571 |
Neg logit contributions | |
Sabha | -7.133 |
bane | -6.559 |
conn | -5.338 |
Loading | -5.264 |
Uz | -4.842 |
Token | is |
Token ID | 271 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
beard | +9.614 |
netflix | +8.716 |
�� | +8.311 |
tie | +8.138 |
fman | +8.072 |
Neg logit contributions | |
Sabha | -10.808 |
bane | -9.069 |
Loading | -7.638 |
conn | -7.634 |
Uz | -7.529 |
Token | |
Token ID | 3907 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
beard | +3.854 |
netflix | +3.589 |
�� | +3.558 |
Noir | +3.429 |
姫 | +3.406 |
Neg logit contributions | |
Sabha | -3.526 |
bane | -3.150 |
conn | -2.646 |
Loading | -2.434 |
Uz | -2.387 |
Token | on |
Token ID | 261 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
beard | +4.687 |
netflix | +4.231 |
�� | +4.200 |
姫 | +3.918 |
Noir | +3.858 |
Neg logit contributions | |
Sabha | -6.223 |
bane | -5.628 |
conn | -4.954 |
Loading | -4.650 |
Uz | -4.608 |
Token | to |
Token ID | 284 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
beard | +1.966 |
netflix | +1.816 |
�� | +1.814 |
姫 | +1.723 |
Noir | +1.720 |
Neg logit contributions | |
Sabha | -2.100 |
bane | -1.916 |
conn | -1.650 |
Loading | -1.503 |
ader | -1.484 |
Token | this |
Token ID | 428 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
beard | +2.783 |
netflix | +2.558 |
�� | +2.551 |
Noir | +2.438 |
姫 | +2.429 |
Neg logit contributions | |
Sabha | -3.116 |
bane | -2.857 |
conn | -2.502 |
Loading | -2.252 |
ader | -2.249 |
Token | Industries |
Token ID | 20171 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
beard | +0.494 |
�� | +0.455 |
netflix | +0.453 |
姫 | +0.423 |
Noir | +0.419 |
Neg logit contributions | |
Sabha | -0.712 |
bane | -0.664 |
conn | -0.582 |
ader | -0.537 |
Loading | -0.535 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
beard | +0.891 |
�� | +0.829 |
netflix | +0.828 |
姫 | +0.789 |
Noir | +0.782 |
Neg logit contributions | |
Sabha | -0.856 |
bane | -0.788 |
conn | -0.666 |
ader | -0.603 |
Loading | -0.600 |
Token | and |
Token ID | 290 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
beard | +1.741 |
netflix | +1.619 |
�� | +1.611 |
Noir | +1.521 |
姫 | +1.512 |
Neg logit contributions | |
Sabha | -1.931 |
bane | -1.800 |
conn | -1.536 |
Loading | -1.401 |
ader | -1.399 |
Token | other |
Token ID | 584 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
beard | +0.305 |
�� | +0.283 |
netflix | +0.282 |
Noir | +0.267 |
姫 | +0.266 |
Neg logit contributions | |
Sabha | -0.336 |
bane | -0.313 |
conn | -0.267 |
ader | -0.243 |
Loading | -0.243 |
Token | coal |
Token ID | 5655 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
beard | +2.831 |
netflix | +2.537 |
�� | +2.535 |
Noir | +2.438 |
heels | +2.411 |
Neg logit contributions | |
Sabha | -3.848 |
bane | -3.668 |
conn | -3.136 |
Loading | -2.928 |
ader | -2.909 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
beard | +1.944 |
netflix | +1.763 |
�� | +1.723 |
姫 | +1.645 |
Noir | +1.641 |
Neg logit contributions | |
Sabha | -2.350 |
bane | -2.183 |
conn | -1.888 |
Loading | -1.739 |
ader | -1.726 |
Token | oil |
Token ID | 3056 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
beard | +6.625 |
netflix | +6.086 |
heels | +5.750 |
�� | +5.678 |
Noir | +5.480 |
Neg logit contributions | |
Sabha | -12.466 |
bane | -12.019 |
conn | -10.758 |
ader | -9.965 |
Loading | -9.802 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
beard | +2.893 |
�� | +2.702 |
netflix | +2.689 |
姫 | +2.543 |
Noir | +2.522 |
Neg logit contributions | |
Sabha | -3.003 |
bane | -2.765 |
conn | -2.366 |
ader | -2.147 |
Loading | -2.136 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
beard | +6.205 |
netflix | +5.960 |
�� | +5.782 |
Noir | +5.429 |
heels | +5.426 |
Neg logit contributions | |
Sabha | -9.105 |
bane | -8.355 |
conn | -7.316 |
Loading | -6.876 |
ader | -6.719 |
Token | gas |
Token ID | 3623 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
beard | +5.320 |
netflix | +4.896 |
�� | +4.746 |
heels | +4.704 |
Noir | +4.593 |
Neg logit contributions | |
Sabha | -9.640 |
bane | -9.002 |
conn | -7.965 |
ader | -7.329 |
Loading | -7.306 |
Token | corporations |
Token ID | 10225 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
beard | +1.990 |
netflix | +1.781 |
�� | +1.754 |
Noir | +1.683 |
姫 | +1.671 |
Neg logit contributions | |
Sabha | -2.631 |
bane | -2.467 |
conn | -2.114 |
ader | -1.959 |
Loading | -1.951 |
Token | PH |
Token ID | 11909 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Sabha | +0.623 |
bane | +0.574 |
conn | +0.485 |
ader | +0.444 |
Uz | +0.436 |
Neg logit contributions | |
beard | -0.641 |
netflix | -0.593 |
�� | -0.583 |
姫 | -0.569 |
Noir | -0.562 |
Token | _ |
Token ID | 62 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
beard | +0.179 |
netflix | +0.163 |
姫 | +0.154 |
Noir | +0.152 |
�� | +0.152 |
Neg logit contributions | |
Sabha | -0.243 |
bane | -0.225 |
conn | -0.196 |
Uz | -0.180 |
ader | -0.180 |
Token | BL |
Token ID | 9148 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
beard | +2.474 |
netflix | +2.115 |
EVA | +1.991 |
姫 | +1.985 |
Noir | +1.958 |
Neg logit contributions | |
Sabha | -5.307 |
bane | -4.877 |
conn | -4.415 |
Uz | -4.157 |
ader | -4.153 |
Token | ACK |
Token ID | 8120 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
beard | +2.404 |
netflix | +1.985 |
EVA | +1.922 |
Noir | +1.896 |
TG | +1.896 |
Neg logit contributions | |
Sabha | -5.557 |
bane | -5.166 |
conn | -4.648 |
Uz | -4.360 |
Pix | -4.296 |
Token | H |
Token ID | 39 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
beard | +3.666 |
EVA | +2.931 |
netflix | +2.929 |
TG | +2.860 |
Hulk | +2.850 |
Neg logit contributions | |
Sabha | -6.212 |
bane | -5.784 |
conn | -5.021 |
Uz | -4.849 |
ader | -4.833 |
Token | AT |
Token ID | 1404 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
beard | +1.127 |
netflix | +0.979 |
�� | +0.943 |
Noir | +0.931 |
姫 | +0.926 |
Neg logit contributions | |
Sabha | -1.816 |
bane | -1.679 |
conn | -1.481 |
Uz | -1.386 |
Pix | -1.356 |
Token | , |
Token ID | 837 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
beard | +4.628 |
netflix | +3.561 |
Noir | +3.185 |
Hulk | +3.119 |
EVA | +3.047 |
Neg logit contributions | |
Sabha | -14.883 |
bane | -13.757 |
conn | -12.500 |
tremend | -12.236 |
ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ | -12.125 |
Token | rect |
Token ID | 13621 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Sabha | +0.062 |
bane | +0.056 |
conn | +0.046 |
ader | +0.041 |
Loading | +0.040 |
Neg logit contributions | |
beard | -0.086 |
�� | -0.081 |
netflix | -0.081 |
姫 | -0.077 |
Noir | -0.077 |
Token | K |
Token ID | 42 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
beard | +4.298 |
netflix | +3.688 |
EVA | +3.568 |
姫 | +3.339 |
lap | +3.305 |
Neg logit contributions | |
Sabha | -10.480 |
bane | -9.695 |
conn | -8.686 |
Uz | -8.406 |
Pix | -8.172 |
Token | ernel |
Token ID | 7948 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Sabha | +4.799 |
bane | +4.551 |
conn | +4.123 |
ader | +3.912 |
Loading | +3.870 |
Neg logit contributions | |
beard | -1.581 |
�� | -1.416 |
netflix | -1.353 |
姫 | -1.235 |
Noir | -1.186 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
beard | +1.549 |
netflix | +1.325 |
Noir | +1.189 |
姫 | +1.145 |
Hulk | +1.090 |
Neg logit contributions | |
Sabha | -4.305 |
bane | -4.019 |
conn | -3.597 |
Uz | -3.438 |
ader | -3.411 |
Token |
|
Token ID | 198 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
beard | +0.435 |
netflix | +0.401 |
�� | +0.396 |
Noir | +0.381 |
姫 | +0.380 |
Neg logit contributions | |
Sabha | -0.481 |
bane | -0.445 |
conn | -0.383 |
ader | -0.348 |
Loading | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
beard | +0.374 |
netflix | +0.340 |
Noir | +0.321 |
姫 | +0.316 |
�� | +0.312 |
Neg logit contributions | |
Sabha | -0.434 |
bane | -0.394 |
conn | -0.339 |
Uz | -0.312 |
ader | -0.309 |
Token | Also |
Token ID | 7583 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
beard | +0.204 |
netflix | +0.188 |
�� | +0.187 |
姫 | +0.177 |
Noir | +0.175 |
Neg logit contributions | |
Sabha | -0.240 |
bane | -0.221 |
conn | -0.190 |
ader | -0.174 |
Uz | -0.173 |
Token | in |
Token ID | 287 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
Sabha | +1.771 |
bane | +1.637 |
conn | +1.391 |
Loading | +1.268 |
ader | +1.265 |
Neg logit contributions | |
beard | -1.718 |
�� | -1.619 |
netflix | -1.609 |
姫 | -1.515 |
Noir | -1.493 |
Token | Energy |
Token ID | 6682 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
beard | +0.055 |
�� | +0.051 |
netflix | +0.051 |
Noir | +0.048 |
姫 | +0.048 |
Neg logit contributions | |
Sabha | -0.057 |
bane | -0.053 |
conn | -0.045 |
ader | -0.041 |
Loading | -0.040 |
Token | & |
Token ID | 1222 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Sabha | +0.355 |
bane | +0.329 |
conn | +0.283 |
ader | +0.259 |
Loading | +0.256 |
Neg logit contributions | |
beard | -0.314 |
netflix | -0.290 |
�� | -0.290 |
姫 | -0.274 |
Noir | -0.273 |
Token | Environment |
Token ID | 9344 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
beard | +8.621 |
Noir | +8.130 |
�� | +7.768 |
姫 | +7.720 |
Hulk | +7.676 |
Neg logit contributions | |
Sabha | -9.998 |
bane | -9.113 |
conn | -7.723 |
ader | -7.050 |
Loading | -6.988 |
Token | : |
Token ID | 25 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
beard | +3.930 |
netflix | +3.589 |
�� | +3.517 |
Noir | +3.438 |
姫 | +3.380 |
Neg logit contributions | |
Sabha | -4.629 |
bane | -4.307 |
conn | -3.791 |
ader | -3.400 |
Loading | -3.376 |
Token |
|
Token ID | 198 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
beard | +2.182 |
netflix | +2.030 |
�� | +2.029 |
姫 | +1.923 |
Noir | +1.914 |
Neg logit contributions | |
Sabha | -2.143 |
bane | -1.976 |
conn | -1.680 |
ader | -1.518 |
Loading | -1.502 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Sabha | +0.430 |
bane | +0.393 |
conn | +0.335 |
ader | +0.307 |
Uz | +0.306 |
Neg logit contributions | |
beard | -0.395 |
netflix | -0.362 |
�� | -0.345 |
Noir | -0.341 |
姫 | -0.340 |
Token | Nearly |
Token ID | 27927 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Sabha | +0.114 |
bane | +0.105 |
conn | +0.091 |
ader | +0.083 |
Uz | +0.082 |
Neg logit contributions | |
beard | -0.099 |
�� | -0.092 |
netflix | -0.092 |
姫 | -0.086 |
Noir | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
beard | +2.180 |
netflix | +1.978 |
�� | +1.959 |
Noir | +1.876 |
姫 | +1.849 |
Neg logit contributions | |
Sabha | -2.644 |
bane | -2.444 |
conn | -2.133 |
Loading | -1.933 |
ader | -1.929 |
Token |
|
Token ID | 198 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
beard | +0.806 |
netflix | +0.734 |
�� | +0.729 |
Noir | +0.702 |
姫 | +0.693 |
Neg logit contributions | |
Sabha | -1.053 |
bane | -0.973 |
conn | -0.854 |
ader | -0.781 |
Loading | -0.775 |
Token |
|
Token ID | 198 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
beard | +0.519 |
netflix | +0.470 |
Noir | +0.446 |
姫 | +0.438 |
�� | +0.432 |
Neg logit contributions | |
Sabha | -0.610 |
bane | -0.554 |
conn | -0.476 |
ader | -0.437 |
Uz | -0.435 |
Token | Remember |
Token ID | 16676 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
beard | +0.587 |
netflix | +0.537 |
�� | +0.532 |
姫 | +0.504 |
Noir | +0.496 |
Neg logit contributions | |
Sabha | -0.774 |
bane | -0.710 |
conn | -0.616 |
ader | -0.568 |
Uz | -0.565 |
Token | Na |
Token ID | 11013 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
beard | +0.027 |
�� | +0.026 |
netflix | +0.025 |
姫 | +0.024 |
Noir | +0.024 |
Neg logit contributions | |
Sabha | -0.029 |
bane | -0.027 |
conn | -0.023 |
ader | -0.021 |
Loading | -0.021 |
Token | V |
Token ID | 53 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
beard | +2.365 |
�� | +2.133 |
netflix | +2.064 |
姫 | +1.981 |
Noir | +1.964 |
Neg logit contributions | |
Sabha | -3.210 |
bane | -2.954 |
conn | -2.542 |
Pix | -2.343 |
Uz | -2.340 |
Token | or |
Token ID | 273 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
beard | +5.016 |
Noir | +4.421 |
Hulk | +4.184 |
lap | +4.020 |
roll | +3.882 |
Neg logit contributions | |
Sabha | -12.869 |
bane | -12.327 |
conn | -10.572 |
Creat | -10.077 |
Uz | -10.076 |
Token | ro |
Token ID | 305 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
beard | +2.081 |
Noir | +1.894 |
netflix | +1.889 |
姫 | +1.838 |
�� | +1.806 |
Neg logit contributions | |
Sabha | -3.120 |
bane | -2.949 |
conn | -2.460 |
Loading | -2.351 |
Uz | -2.343 |
Token | Bowman |
Token ID | 38774 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Sabha | +0.432 |
bane | +0.406 |
conn | +0.348 |
ader | +0.319 |
Loading | +0.312 |
Neg logit contributions | |
beard | -0.359 |
�� | -0.325 |
netflix | -0.323 |
姫 | -0.311 |
Noir | -0.304 |
Token | at |
Token ID | 379 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
beard | +1.389 |
�� | +1.265 |
netflix | +1.253 |
Noir | +1.191 |
姫 | +1.186 |
Neg logit contributions | |
Sabha | -1.638 |
bane | -1.499 |
conn | -1.313 |
ader | -1.191 |
Loading | -1.187 |
Token | the |
Token ID | 262 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
beard | +0.996 |
�� | +0.924 |
netflix | +0.914 |
Noir | +0.871 |
姫 | +0.866 |
Neg logit contributions | |
Sabha | -1.045 |
bane | -0.954 |
conn | -0.819 |
ader | -0.747 |
Loading | -0.744 |
Token | if |
Token ID | 611 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Sabha | +0.785 |
bane | +0.723 |
conn | +0.617 |
ader | +0.559 |
Loading | +0.555 |
Neg logit contributions | |
beard | -0.783 |
�� | -0.734 |
netflix | -0.729 |
姫 | -0.693 |
Noir | -0.684 |
Token | you |
Token ID | 345 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
Sabha | +1.496 |
bane | +1.379 |
conn | +1.176 |
ader | +1.067 |
Uz | +1.060 |
Neg logit contributions | |
beard | -1.500 |
�� | -1.408 |
netflix | -1.398 |
姫 | -1.330 |
Noir | -1.308 |
Token | 're |
Token ID | 821 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Sabha | +0.572 |
bane | +0.525 |
conn | +0.452 |
ader | +0.410 |
Loading | +0.408 |
Neg logit contributions | |
beard | -0.538 |
�� | -0.501 |
netflix | -0.500 |
姫 | -0.472 |
Noir | -0.469 |
Token | really |
Token ID | 1107 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
Sabha | +1.450 |
bane | +1.344 |
conn | +1.165 |
ader | +1.067 |
Loading | +1.060 |
Neg logit contributions | |
beard | -1.191 |
�� | -1.104 |
netflix | -1.099 |
姫 | -1.033 |
Noir | -1.026 |
Token | f |
Token ID | 277 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
beard | +0.333 |
�� | +0.307 |
netflix | +0.306 |
Noir | +0.288 |
姫 | +0.284 |
Neg logit contributions | |
Sabha | -0.396 |
bane | -0.365 |
conn | -0.317 |
ader | -0.289 |
Loading | -0.286 |
Token | **** |
Token ID | 2466 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Sabha | +0.213 |
bane | +0.197 |
conn | +0.169 |
ader | +0.153 |
Loading | +0.152 |
Neg logit contributions | |
beard | -0.201 |
�� | -0.188 |
netflix | -0.187 |
姫 | -0.177 |
Noir | -0.175 |
Token | d |
Token ID | 67 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
beard | +7.967 |
netflix | +7.089 |
�� | +6.805 |
heels | +6.704 |
dash | +6.666 |
Neg logit contributions | |
Sabha | -10.774 |
bane | -9.592 |
conn | -8.414 |
Uz | -8.085 |
Creat | -7.803 |
Token | . |
Token ID | 13 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Sabha | +0.665 |
bane | +0.611 |
conn | +0.520 |
ader | +0.471 |
Loading | +0.468 |
Neg logit contributions | |
beard | -0.677 |
�� | -0.631 |
netflix | -0.630 |
姫 | -0.596 |
Noir | -0.592 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Sabha | +0.622 |
bane | +0.575 |
conn | +0.499 |
ader | +0.457 |
Loading | +0.454 |
Neg logit contributions | |
beard | -0.514 |
netflix | -0.475 |
�� | -0.474 |
姫 | -0.445 |
Noir | -0.444 |
Token |
|
Token ID | 198 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Sabha | +2.595 |
bane | +2.388 |
conn | +2.028 |
ader | +1.833 |
Loading | +1.822 |
Neg logit contributions | |
beard | -2.685 |
�� | -2.524 |
netflix | -2.504 |
姫 | -2.378 |
Noir | -2.354 |
Token | Let |
Token ID | 5756 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
Sabha | +2.464 |
bane | +2.314 |
conn | +2.011 |
Loading | +1.856 |
ader | +1.846 |
Neg logit contributions | |
beard | -1.926 |
�� | -1.809 |
netflix | -1.775 |
姫 | -1.684 |
Noir | -1.662 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Sabha | +1.884 |
bane | +1.742 |
conn | +1.496 |
ader | +1.358 |
Loading | +1.350 |
Neg logit contributions | |
beard | -1.742 |
�� | -1.621 |
netflix | -1.610 |
姫 | -1.524 |
Noir | -1.514 |
Token | base |
Token ID | 2779 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Sabha | +1.211 |
bane | +1.125 |
conn | +0.970 |
ader | +0.886 |
Loading | +0.884 |
Neg logit contributions | |
beard | -1.026 |
�� | -0.952 |
netflix | -0.945 |
姫 | -0.890 |
Noir | -0.887 |
Token | case |
Token ID | 1339 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
beard | +1.005 |
�� | +0.924 |
netflix | +0.915 |
Noir | +0.868 |
姫 | +0.860 |
Neg logit contributions | |
Sabha | -1.157 |
bane | -1.070 |
conn | -0.923 |
ader | -0.833 |
Loading | -0.832 |
Token | if |
Token ID | 611 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
beard | +0.569 |
netflix | +0.523 |
�� | +0.521 |
Noir | +0.497 |
姫 | +0.490 |
Neg logit contributions | |
Sabha | -0.628 |
bane | -0.584 |
conn | -0.499 |
ader | -0.450 |
Loading | -0.450 |
Token | ( |
Token ID | 357 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
beard | +1.477 |
�� | +1.377 |
netflix | +1.369 |
Noir | +1.293 |
姫 | +1.289 |
Neg logit contributions | |
Sabha | -1.495 |
bane | -1.373 |
conn | -1.168 |
ader | -1.046 |
Loading | -1.038 |
Token | parts |
Token ID | 3354 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
beard | +5.325 |
netflix | +4.859 |
�� | +4.786 |
Noir | +4.594 |
姫 | +4.515 |
Neg logit contributions | |
Sabha | -5.814 |
bane | -5.217 |
conn | -4.416 |
Loading | -4.061 |
Uz | -3.955 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
beard | +6.756 |
�� | +5.944 |
netflix | +5.942 |
Noir | +5.648 |
lap | +5.535 |
Neg logit contributions | |
Sabha | -11.242 |
bane | -10.656 |
conn | -9.186 |
ader | -8.483 |
Uz | -8.468 |
Token | Any |
Token ID | 7149 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
beard | +2.135 |
netflix | +1.918 |
�� | +1.857 |
Noir | +1.760 |
姫 | +1.740 |
Neg logit contributions | |
Sabha | -3.339 |
bane | -3.083 |
conn | -2.690 |
ader | -2.505 |
Uz | -2.503 |
Token | ( |
Token ID | 7 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
beard | +2.214 |
�� | +2.059 |
netflix | +2.047 |
姫 | +1.952 |
Noir | +1.919 |
Neg logit contributions | |
Sabha | -2.345 |
bane | -2.161 |
conn | -1.834 |
Uz | -1.684 |
ader | -1.666 |
Token | Is |
Token ID | 1148 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
beard | +1.303 |
�� | +1.198 |
netflix | +1.196 |
姫 | +1.121 |
Noir | +1.121 |
Neg logit contributions | |
Sabha | -1.560 |
bane | -1.439 |
conn | -1.238 |
ader | -1.134 |
Loading | -1.132 |
Token | Not |
Token ID | 3673 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Sabha | +0.596 |
bane | +0.555 |
conn | +0.484 |
ader | +0.446 |
Loading | +0.442 |
Neg logit contributions | |
beard | -0.440 |
�� | -0.406 |
netflix | -0.404 |
姫 | -0.379 |
Noir | -0.376 |
Token | said |
Token ID | 531 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
beard | +0.905 |
netflix | +0.829 |
Noir | +0.782 |
heels | +0.778 |
姫 | +0.769 |
Neg logit contributions | |
Sabha | -0.980 |
bane | -0.889 |
conn | -0.768 |
Loading | -0.697 |
ader | -0.691 |
Token | she |
Token ID | 673 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
Sabha | +2.823 |
bane | +2.598 |
conn | +2.220 |
ader | +2.014 |
Loading | +1.993 |
Neg logit contributions | |
beard | -2.820 |
�� | -2.678 |
netflix | -2.626 |
姫 | -2.501 |
Noir | -2.468 |
Token | risked |
Token ID | 42179 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Sabha | +0.346 |
bane | +0.320 |
conn | +0.273 |
ader | +0.248 |
Loading | +0.247 |
Neg logit contributions | |
beard | -0.342 |
netflix | -0.318 |
�� | -0.314 |
姫 | -0.297 |
Noir | -0.297 |
Token | severe |
Token ID | 6049 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
beard | +3.556 |
netflix | +2.969 |
Noir | +2.956 |
heels | +2.911 |
�� | +2.832 |
Neg logit contributions | |
Sabha | -6.041 |
bane | -5.724 |
conn | -5.257 |
Loading | -4.767 |
ader | -4.765 |
Token | infection |
Token ID | 10280 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Sabha | +0.598 |
bane | +0.556 |
conn | +0.487 |
ader | +0.457 |
Loading | +0.452 |
Neg logit contributions | |
beard | -0.383 |
netflix | -0.348 |
�� | -0.332 |
Noir | -0.319 |
姫 | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
beard | +1.506 |
netflix | +1.405 |
Noir | +1.291 |
姫 | +1.261 |
Hulk | +1.259 |
Neg logit contributions | |
Sabha | -1.821 |
bane | -1.675 |
conn | -1.461 |
Loading | -1.334 |
ader | -1.329 |
Token | scar |
Token ID | 10153 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
beard | +6.825 |
netflix | +6.344 |
Hulk | +5.675 |
heels | +5.587 |
scient | +5.454 |
Neg logit contributions | |
Sabha | -10.810 |
bane | -10.175 |
conn | -9.287 |
Creat | -8.703 |
Loading | -8.520 |
Token | ring |
Token ID | 1806 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
beard | +3.108 |
netflix | +2.768 |
heels | +2.438 |
Noir | +2.419 |
Hulk | +2.419 |
Neg logit contributions | |
Sabha | -4.959 |
bane | -4.479 |
conn | -4.054 |
Uz | -3.829 |
Creat | -3.723 |
Token | if |
Token ID | 611 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
beard | +3.010 |
netflix | +2.737 |
�� | +2.631 |
Noir | +2.558 |
姫 | +2.519 |
Neg logit contributions | |
Sabha | -3.658 |
bane | -3.404 |
conn | -2.961 |
Loading | -2.722 |
ader | -2.699 |
Token | she |
Token ID | 673 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
Sabha | +1.885 |
bane | +1.740 |
conn | +1.490 |
ader | +1.355 |
Loading | +1.346 |
Neg logit contributions | |
beard | -1.766 |
netflix | -1.641 |
�� | -1.627 |
姫 | -1.544 |
Noir | -1.535 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
beard | +0.596 |
netflix | +0.545 |
Noir | +0.498 |
姫 | +0.496 |
�� | +0.495 |
Neg logit contributions | |
Sabha | -0.835 |
bane | -0.764 |
conn | -0.668 |
Loading | -0.612 |
ader | -0.610 |
Token | } |
Token ID | 1782 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
beard | +1.368 |
netflix | +1.267 |
�� | +1.266 |
Noir | +1.196 |
姫 | +1.170 |
Neg logit contributions | |
Sabha | -1.605 |
bane | -1.482 |
conn | -1.274 |
ader | -1.166 |
Loading | -1.160 |
Token | Catch |
Token ID | 25750 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
beard | +1.210 |
netflix | +1.118 |
�� | +1.118 |
Noir | +1.054 |
姫 | +1.033 |
Neg logit contributions | |
Sabha | -1.431 |
bane | -1.324 |
conn | -1.138 |
ader | -1.044 |
Loading | -1.037 |
Token | { |
Token ID | 1391 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
beard | +2.372 |
netflix | +2.227 |
Noir | +2.141 |
�� | +2.063 |
Hulk | +1.995 |
Neg logit contributions | |
Sabha | -3.149 |
bane | -2.861 |
conn | -2.510 |
Uz | -2.281 |
ader | -2.272 |
Token | Write |
Token ID | 19430 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Sabha | +1.827 |
bane | +1.681 |
conn | +1.333 |
Pix | +1.125 |
ader | +1.124 |
Neg logit contributions | |
beard | -3.334 |
�� | -3.148 |
姫 | -3.127 |
netflix | -3.106 |
heels | -2.958 |
Token | - |
Token ID | 12 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
beard | +2.672 |
netflix | +2.417 |
Noir | +2.279 |
EVA | +2.180 |
Hulk | +2.173 |
Neg logit contributions | |
Sabha | -4.066 |
bane | -3.676 |
conn | -3.207 |
Uz | -3.034 |
ader | -2.994 |
Token | Warning |
Token ID | 20361 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
beard | +3.971 |
netflix | +3.628 |
Noir | +3.417 |
EVA | +3.393 |
Delete | +3.380 |
Neg logit contributions | |
Sabha | -4.838 |
bane | -4.256 |
conn | -3.549 |
Pix | -3.450 |
Uz | -3.437 |
Token | - |
Token ID | 532 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
beard | +6.030 |
netflix | +5.644 |
Noir | +5.551 |
Hulk | +5.245 |
Delete | +4.803 |
Neg logit contributions | |
Sabha | -11.523 |
bane | -10.440 |
conn | -9.350 |
Uz | -8.726 |
ader | -8.624 |
Token | Message |
Token ID | 12837 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
beard | +0.925 |
netflix | +0.837 |
Noir | +0.794 |
�� | +0.790 |
姫 | +0.774 |
Neg logit contributions | |
Sabha | -1.199 |
bane | -1.090 |
conn | -0.940 |
Uz | -0.883 |
Pix | -0.868 |
Token | " |
Token ID | 366 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
beard | +3.374 |
netflix | +3.169 |
�� | +3.090 |
Noir | +2.962 |
姫 | +2.837 |
Neg logit contributions | |
Sabha | -4.233 |
bane | -3.921 |
conn | -3.348 |
Uz | -3.101 |
ader | -3.076 |
Token | F |
Token ID | 37 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Sabha | +3.825 |
bane | +3.515 |
conn | +3.035 |
Loading | +2.888 |
ader | +2.729 |
Neg logit contributions | |
beard | -4.420 |
�� | -4.237 |
netflix | -4.134 |
姫 | -4.061 |
Noir | -3.878 |
Token | ailed |
Token ID | 6255 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
beard | +0.694 |
netflix | +0.593 |
�� | +0.491 |
Noir | +0.452 |
lap | +0.435 |
Neg logit contributions | |
Sabha | -2.972 |
bane | -2.791 |
conn | -2.524 |
Pix | -2.451 |
Uz | -2.441 |
Token | comet |
Token ID | 31733 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
beard | +1.016 |
netflix | +0.938 |
�� | +0.938 |
Noir | +0.884 |
姫 | +0.877 |
Neg logit contributions | |
Sabha | -1.172 |
bane | -1.091 |
conn | -0.937 |
Loading | -0.854 |
ader | -0.853 |
Token | 107 |
Token ID | 16226 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
beard | +2.097 |
netflix | +1.929 |
�� | +1.894 |
Noir | +1.849 |
heels | +1.773 |
Neg logit contributions | |
Sabha | -2.360 |
bane | -2.186 |
conn | -1.860 |
Loading | -1.698 |
ader | -1.694 |
Token | P |
Token ID | 47 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
beard | +2.327 |
�� | +2.126 |
netflix | +2.118 |
Noir | +2.027 |
姫 | +2.010 |
Neg logit contributions | |
Sabha | -2.547 |
bane | -2.351 |
conn | -2.027 |
ader | -1.837 |
Uz | -1.824 |
Token | / |
Token ID | 14 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
beard | +0.531 |
�� | +0.495 |
netflix | +0.493 |
姫 | +0.467 |
Noir | +0.463 |
Neg logit contributions | |
Sabha | -0.553 |
bane | -0.510 |
conn | -0.436 |
ader | -0.396 |
Loading | -0.394 |
Token | Wilson |
Token ID | 37349 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Sabha | +0.101 |
bane | +0.093 |
conn | +0.080 |
ader | +0.073 |
Loading | +0.073 |
Neg logit contributions | |
beard | -0.089 |
�� | -0.083 |
netflix | -0.082 |
姫 | -0.078 |
Noir | -0.077 |
Token | – |
Token ID | 1906 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
beard | +1.775 |
�� | +1.656 |
netflix | +1.647 |
姫 | +1.567 |
Noir | +1.563 |
Neg logit contributions | |
Sabha | -1.570 |
bane | -1.437 |
conn | -1.202 |
ader | -1.083 |
Loading | -1.081 |
Token | Har |
Token ID | 13587 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
beard | +6.707 |
netflix | +5.738 |
EVA | +5.364 |
�� | +5.336 |
Noir | +5.282 |
Neg logit contributions | |
Sabha | -11.415 |
bane | -10.553 |
conn | -9.274 |
Pix | -8.945 |
Uz | -8.808 |
Token | rington |
Token ID | 24833 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
beard | +1.629 |
netflix | +1.502 |
Noir | +1.417 |
�� | +1.413 |
姫 | +1.398 |
Neg logit contributions | |
Sabha | -1.400 |
bane | -1.200 |
conn | -0.985 |
Uz | -0.972 |
Loading | -0.945 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Sabha | +0.399 |
bane | +0.369 |
conn | +0.317 |
ader | +0.288 |
Loading | +0.287 |
Neg logit contributions | |
beard | -0.365 |
�� | -0.338 |
netflix | -0.338 |
姫 | -0.319 |
Noir | -0.317 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
beard | +0.717 |
netflix | +0.654 |
�� | +0.648 |
Noir | +0.620 |
姫 | +0.616 |
Neg logit contributions | |
Sabha | -0.925 |
bane | -0.858 |
conn | -0.746 |
ader | -0.684 |
Loading | -0.679 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
beard | +1.220 |
netflix | +1.099 |
Noir | +1.041 |
姫 | +1.014 |
Hulk | +1.005 |
Neg logit contributions | |
Sabha | -1.479 |
bane | -1.344 |
conn | -1.156 |
Uz | -1.067 |
ader | -1.066 |
Token | Ga |
Token ID | 12822 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
beard | +0.927 |
�� | +0.843 |
netflix | +0.836 |
Noir | +0.780 |
姫 | +0.774 |
Neg logit contributions | |
Sabha | -1.536 |
bane | -1.434 |
conn | -1.268 |
Loading | -1.175 |
ader | -1.169 |
Token | ussian |
Token ID | 31562 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Sabha | +2.738 |
bane | +2.558 |
conn | +2.242 |
ader | +2.076 |
Loading | +2.061 |
Neg logit contributions | |
beard | -1.872 |
�� | -1.727 |
netflix | -1.712 |
姫 | -1.603 |
Noir | -1.583 |
Token | Bl |
Token ID | 3629 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
beard | +2.574 |
netflix | +2.266 |
Noir | +2.191 |
姫 | +1.984 |
Hulk | +1.980 |
Neg logit contributions | |
Sabha | -6.569 |
bane | -6.053 |
conn | -5.587 |
Uz | -5.180 |
ader | -5.133 |
Token | ur |
Token ID | 333 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
beard | +0.575 |
netflix | +0.526 |
Noir | +0.491 |
�� | +0.490 |
姫 | +0.471 |
Neg logit contributions | |
Sabha | -0.808 |
bane | -0.746 |
conn | -0.655 |
Uz | -0.608 |
Loading | -0.605 |
Token | ( |
Token ID | 357 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
beard | +2.489 |
netflix | +2.278 |
Noir | +2.153 |
姫 | +2.101 |
EVA | +2.079 |
Neg logit contributions | |
Sabha | -2.687 |
bane | -2.419 |
conn | -2.080 |
Uz | -1.933 |
ader | -1.908 |
Token | gray |
Token ID | 12768 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
beard | +2.249 |
netflix | +1.959 |
Noir | +1.902 |
Hulk | +1.845 |
heels | +1.824 |
Neg logit contributions | |
Sabha | -5.950 |
bane | -5.479 |
conn | -4.926 |
Loading | -4.756 |
Uz | -4.690 |
Token | , |
Token ID | 837 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
beard | +4.753 |
netflix | +3.827 |
Hulk | +3.150 |
Noir | +3.148 |
dash | +2.891 |
Neg logit contributions | |
Sabha | -13.540 |
bane | -12.357 |
conn | -10.919 |
Uz | -10.861 |
assadors | -10.548 |
Token | ( |
Token ID | 357 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
beard | +3.983 |
netflix | +3.732 |
Noir | +3.514 |
heels | +3.506 |
Hulk | +3.432 |
Neg logit contributions | |
Sabha | -5.010 |
bane | -4.634 |
conn | -3.880 |
Loading | -3.622 |
Uz | -3.568 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
beard | +3.577 |
netflix | +3.398 |
heels | +3.040 |
Noir | +2.991 |
Hulk | +2.857 |
Neg logit contributions | |
Sabha | -5.967 |
bane | -5.439 |
conn | -4.877 |
Uz | -4.479 |
Loading | -4.475 |
Token | , |
Token ID | 837 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
beard | +4.417 |
netflix | +3.588 |
Noir | +3.206 |
Hulk | +3.178 |
TG | +2.963 |
Neg logit contributions | |
Sabha | -12.726 |
bane | -11.620 |
conn | -10.304 |
��� | -10.135 |
Uz | -10.134 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
beard | +2.683 |
netflix | +2.499 |
Noir | +2.285 |
heels | +2.259 |
Hulk | +2.175 |
Neg logit contributions | |
Sabha | -4.229 |
bane | -3.936 |
conn | -3.453 |
Loading | -3.189 |
Uz | -3.168 |
Token | full |
Token ID | 1336 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Sabha | +0.405 |
bane | +0.376 |
conn | +0.326 |
Loading | +0.298 |
ader | +0.298 |
Neg logit contributions | |
beard | -0.334 |
�� | -0.308 |
netflix | -0.307 |
Noir | -0.290 |
姫 | -0.289 |
Token | value |
Token ID | 1988 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
Sabha | +1.338 |
bane | +1.239 |
conn | +1.071 |
ader | +0.980 |
Loading | +0.976 |
Neg logit contributions | |
beard | -1.134 |
�� | -1.050 |
netflix | -1.045 |
姫 | -0.984 |
Noir | -0.979 |
Token | in |
Token ID | 287 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Sabha | +0.712 |
bane | +0.654 |
conn | +0.556 |
ader | +0.501 |
Loading | +0.499 |
Neg logit contributions | |
beard | -0.743 |
�� | -0.694 |
netflix | -0.693 |
姫 | -0.656 |
Noir | -0.654 |
Token | their |
Token ID | 511 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
beard | +1.991 |
�� | +1.830 |
netflix | +1.817 |
Noir | +1.751 |
姫 | +1.711 |
Neg logit contributions | |
Sabha | -2.401 |
bane | -2.228 |
conn | -1.950 |
Loading | -1.777 |
ader | -1.765 |
Token | gold |
Token ID | 3869 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
beard | +0.257 |
�� | +0.237 |
netflix | +0.236 |
Noir | +0.225 |
姫 | +0.224 |
Neg logit contributions | |
Sabha | -0.288 |
bane | -0.266 |
conn | -0.231 |
Loading | -0.210 |
ader | -0.210 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
beard | +0.355 |
netflix | +0.328 |
�� | +0.327 |
Noir | +0.311 |
姫 | +0.310 |
Neg logit contributions | |
Sabha | -0.378 |
bane | -0.348 |
conn | -0.299 |
Loading | -0.273 |
ader | -0.271 |
Token | silver |
Token ID | 8465 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
beard | +6.080 |
Noir | +5.566 |
heels | +5.508 |
姫 | +5.448 |
�� | +5.440 |
Neg logit contributions | |
Sabha | -11.069 |
bane | -10.017 |
conn | -9.377 |
Loading | -8.477 |
ader | -8.472 |
Token | coins |
Token ID | 10796 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
beard | +1.637 |
netflix | +1.494 |
�� | +1.481 |
Noir | +1.443 |
姫 | +1.424 |
Neg logit contributions | |
Sabha | -1.812 |
bane | -1.672 |
conn | -1.442 |
Loading | -1.322 |
ader | -1.302 |
Token | , |
Token ID | 11 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
beard | +1.250 |
netflix | +1.156 |
�� | +1.143 |
Noir | +1.090 |
姫 | +1.083 |
Neg logit contributions | |
Sabha | -1.375 |
bane | -1.266 |
conn | -1.095 |
Loading | -0.997 |
ader | -0.992 |
Token | they |
Token ID | 484 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
beard | +0.635 |
netflix | +0.584 |
�� | +0.582 |
Noir | +0.553 |
姫 | +0.550 |
Neg logit contributions | |
Sabha | -0.724 |
bane | -0.670 |
conn | -0.582 |
ader | -0.528 |
Loading | -0.527 |
Token | merely |
Token ID | 6974 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
beard | +0.748 |
netflix | +0.682 |
�� | +0.662 |
Noir | +0.638 |
姫 | +0.632 |
Neg logit contributions | |
Sabha | -0.968 |
bane | -0.886 |
conn | -0.782 |
Loading | -0.724 |
ader | -0.713 |
Token | of |
Token ID | 286 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
beard | +1.756 |
netflix | +1.616 |
�� | +1.607 |
Noir | +1.532 |
姫 | +1.529 |
Neg logit contributions | |
Sabha | -1.874 |
bane | -1.716 |
conn | -1.475 |
Loading | -1.344 |
Uz | -1.330 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
beard | +2.070 |
�� | +1.915 |
netflix | +1.903 |
Noir | +1.837 |
姫 | +1.798 |
Neg logit contributions | |
Sabha | -2.225 |
bane | -2.053 |
conn | -1.764 |
Loading | -1.599 |
ader | -1.584 |
Token | University |
Token ID | 2059 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
beard | +2.071 |
�� | +1.905 |
netflix | +1.897 |
Noir | +1.825 |
姫 | +1.786 |
Neg logit contributions | |
Sabha | -2.322 |
bane | -2.157 |
conn | -1.855 |
Loading | -1.692 |
ader | -1.677 |
Token | of |
Token ID | 286 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Sabha | +2.414 |
bane | +2.205 |
conn | +1.852 |
ader | +1.663 |
Loading | +1.650 |
Neg logit contributions | |
beard | -2.742 |
netflix | -2.555 |
�� | -2.527 |
姫 | -2.421 |
Noir | -2.419 |
Token | Gu |
Token ID | 1962 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Sabha | +5.111 |
bane | +4.601 |
conn | +3.956 |
Uz | +3.682 |
Pix | +3.567 |
Neg logit contributions | |
beard | -5.502 |
�� | -5.355 |
netflix | -5.260 |
姫 | -4.943 |
heels | -4.723 |
Token | el |
Token ID | 417 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Sabha | +2.503 |
bane | +2.313 |
conn | +1.965 |
Loading | +1.815 |
Uz | +1.795 |
Neg logit contributions | |
beard | -2.244 |
netflix | -2.086 |
�� | -2.042 |
Noir | -1.953 |
姫 | -1.942 |
Token | ph |
Token ID | 746 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
beard | +8.156 |
netflix | +7.487 |
imov | +7.146 |
dash | +7.009 |
Noir | +6.985 |
Neg logit contributions | |
Sabha | -9.619 |
bane | -8.022 |
Loading | -7.160 |
Creat | -6.683 |
conn | -6.576 |
Token | in |
Token ID | 287 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
beard | +1.480 |
netflix | +1.370 |
�� | +1.363 |
姫 | +1.304 |
Noir | +1.302 |
Neg logit contributions | |
Sabha | -1.502 |
bane | -1.379 |
conn | -1.172 |
ader | -1.062 |
Loading | -1.057 |
Token | Ontario |
Token ID | 10553 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
beard | +1.606 |
netflix | +1.486 |
�� | +1.480 |
Noir | +1.459 |
姫 | +1.408 |
Neg logit contributions | |
Sabha | -1.378 |
bane | -1.271 |
conn | -1.046 |
Loading | -0.964 |
ader | -0.951 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
beard | +1.172 |
�� | +1.105 |
netflix | +1.091 |
姫 | +1.033 |
Noir | +1.020 |
Neg logit contributions | |
Sabha | -1.164 |
bane | -1.072 |
conn | -0.918 |
ader | -0.829 |
Loading | -0.822 |
Token | Canada |
Token ID | 3340 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
beard | +1.424 |
netflix | +1.327 |
�� | +1.323 |
Noir | +1.274 |
姫 | +1.265 |
Neg logit contributions | |
Sabha | -1.205 |
bane | -1.103 |
conn | -0.920 |
ader | -0.825 |
Loading | -0.813 |
Token | as |
Token ID | 292 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
beard | +0.255 |
netflix | +0.233 |
�� | +0.232 |
姫 | +0.218 |
Noir | +0.215 |
Neg logit contributions | |
Sabha | -0.332 |
bane | -0.305 |
conn | -0.265 |
Uz | -0.245 |
ader | -0.243 |
Token | d |
Token ID | 67 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
beard | +3.478 |
netflix | +3.186 |
�� | +3.124 |
Noir | +2.999 |
姫 | +2.941 |
Neg logit contributions | |
Sabha | -3.962 |
bane | -3.516 |
conn | -3.069 |
Uz | -2.830 |
Loading | -2.794 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Sabha | +2.921 |
bane | +2.739 |
conn | +2.354 |
ader | +2.173 |
Uz | +2.139 |
Neg logit contributions | |
beard | -2.408 |
�� | -2.252 |
netflix | -2.229 |
姫 | -2.116 |
Noir | -2.077 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Sabha | +1.491 |
bane | +1.363 |
conn | +1.163 |
ader | +1.057 |
Uz | +1.053 |
Neg logit contributions | |
beard | -1.439 |
netflix | -1.329 |
�� | -1.299 |
姫 | -1.251 |
Noir | -1.250 |
Token | Gu |
Token ID | 8205 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Sabha | +1.571 |
bane | +1.461 |
conn | +1.270 |
ader | +1.167 |
Loading | +1.160 |
Neg logit contributions | |
beard | -1.228 |
�� | -1.138 |
netflix | -1.131 |
姫 | -1.064 |
Noir | -1.053 |
Token | M |
Token ID | 44 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
beard | +2.902 |
netflix | +2.689 |
�� | +2.639 |
Noir | +2.533 |
姫 | +2.494 |
Neg logit contributions | |
Sabha | -3.409 |
bane | -3.121 |
conn | -2.650 |
Uz | -2.443 |
Pix | -2.436 |
Token | ih |
Token ID | 4449 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
beard | +7.797 |
姫 | +7.210 |
�� | +6.970 |
netflix | +6.772 |
dash | +6.769 |
Neg logit contributions | |
Sabha | -9.360 |
bane | -8.100 |
conn | -7.124 |
Pix | -6.587 |
Uz | -6.554 |
Token | o |
Token ID | 78 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
beard | +4.096 |
�� | +3.738 |
netflix | +3.642 |
Noir | +3.562 |
姫 | +3.456 |
Neg logit contributions | |
Sabha | -5.584 |
bane | -5.041 |
conn | -4.396 |
Loading | -4.025 |
Uz | -3.999 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
beard | +2.226 |
�� | +2.041 |
netflix | +2.030 |
Noir | +1.955 |
姫 | +1.949 |
Neg logit contributions | |
Sabha | -2.459 |
bane | -2.241 |
conn | -1.929 |
Loading | -1.761 |
ader | -1.751 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
beard | +1.905 |
netflix | +1.692 |
Noir | +1.599 |
Hulk | +1.560 |
姫 | +1.546 |
Neg logit contributions | |
Sabha | -2.459 |
bane | -2.211 |
conn | -1.905 |
Uz | -1.782 |
ader | -1.766 |
Token | The |
Token ID | 464 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
beard | +1.941 |
netflix | +1.780 |
�� | +1.762 |
姫 | +1.666 |
Noir | +1.645 |
Neg logit contributions | |
Sabha | -2.403 |
bane | -2.171 |
conn | -1.884 |
Uz | -1.745 |
ader | -1.725 |
Token | t |
Token ID | 83 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
beard | +3.190 |
�� | +2.916 |
netflix | +2.905 |
姫 | +2.706 |
Noir | +2.688 |
Neg logit contributions | |
Sabha | -4.482 |
bane | -4.132 |
conn | -3.581 |
ader | -3.321 |
Uz | -3.316 |
Token | ] |
Token ID | 60 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
beard | +0.562 |
�� | +0.534 |
netflix | +0.531 |
姫 | +0.509 |
Noir | +0.501 |
Neg logit contributions | |
Sabha | -0.417 |
bane | -0.378 |
conn | -0.312 |
ader | -0.278 |
Uz | -0.272 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Sabha | +2.132 |
bane | +1.986 |
conn | +1.703 |
ader | +1.562 |
Loading | +1.548 |
Neg logit contributions | |
beard | -1.947 |
netflix | -1.823 |
�� | -1.813 |
姫 | -1.720 |
Noir | -1.682 |
Token | string |
Token ID | 4731 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
beard | +0.402 |
�� | +0.372 |
netflix | +0.370 |
姫 | +0.348 |
Noir | +0.342 |
Neg logit contributions | |
Sabha | -0.548 |
bane | -0.509 |
conn | -0.445 |
ader | -0.411 |
Loading | -0.408 |
Token | " |
Token ID | 366 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
beard | +1.573 |
�� | +1.470 |
netflix | +1.464 |
姫 | +1.394 |
Noir | +1.372 |
Neg logit contributions | |
Sabha | -1.597 |
bane | -1.472 |
conn | -1.260 |
ader | -1.143 |
Loading | -1.135 |
Token | set |
Token ID | 2617 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
beard | +0.795 |
�� | +0.717 |
netflix | +0.711 |
姫 | +0.652 |
Noir | +0.644 |
Neg logit contributions | |
Sabha | -1.675 |
bane | -1.582 |
conn | -1.413 |
ader | -1.320 |
Loading | -1.314 |
Token | " |
Token ID | 366 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
beard | +7.116 |
netflix | +6.222 |
Noir | +5.833 |
�� | +5.827 |
姫 | +5.531 |
Neg logit contributions | |
Sabha | -10.699 |
bane | -9.595 |
conn | -8.406 |
ader | -7.785 |
Loading | -7.759 |
Token | or |
Token ID | 393 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
Sabha | +2.070 |
bane | +1.932 |
conn | +1.666 |
ader | +1.520 |
Uz | +1.512 |
Neg logit contributions | |
beard | -1.850 |
�� | -1.732 |
netflix | -1.726 |
姫 | -1.633 |
Noir | -1.609 |
Token | " |
Token ID | 366 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Sabha | +0.660 |
bane | +0.612 |
conn | +0.524 |
ader | +0.475 |
Loading | +0.473 |
Neg logit contributions | |
beard | -0.643 |
�� | -0.600 |
netflix | -0.597 |
姫 | -0.566 |
Noir | -0.558 |
Token | se |
Token ID | 325 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Sabha | +0.877 |
bane | +0.820 |
conn | +0.714 |
ader | +0.654 |
Loading | +0.650 |
Neg logit contributions | |
beard | -0.691 |
�� | -0.645 |
netflix | -0.638 |
姫 | -0.604 |
Noir | -0.593 |
Token | " |
Token ID | 366 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
beard | +2.904 |
�� | +2.648 |
netflix | +2.646 |
Noir | +2.482 |
姫 | +2.428 |
Neg logit contributions | |
Sabha | -4.324 |
bane | -3.981 |
conn | -3.482 |
ader | -3.231 |
Loading | -3.218 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Sabha | +2.499 |
bane | +2.296 |
conn | +1.953 |
ader | +1.768 |
Loading | +1.755 |
Neg logit contributions | |
beard | -2.534 |
netflix | -2.358 |
�� | -2.356 |
姫 | -2.235 |
Noir | -2.217 |
Token | President |
Token ID | 10364 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
Sabha | +1.707 |
bane | +1.594 |
conn | +1.383 |
Loading | +1.270 |
ader | +1.261 |
Neg logit contributions | |
beard | -1.424 |
�� | -1.340 |
netflix | -1.315 |
姫 | -1.245 |
Noir | -1.237 |
Token | Rodrigo |
Token ID | 46198 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
beard | +0.399 |
�� | +0.370 |
netflix | +0.367 |
姫 | +0.349 |
Noir | +0.348 |
Neg logit contributions | |
Sabha | -0.397 |
bane | -0.366 |
conn | -0.311 |
ader | -0.282 |
Loading | -0.279 |
Token | Duterte |
Token ID | 25763 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
Sabha | +1.193 |
bane | +1.095 |
conn | +0.926 |
Loading | +0.830 |
ader | +0.829 |
Neg logit contributions | |
beard | -1.325 |
netflix | -1.235 |
�� | -1.220 |
Noir | -1.177 |
姫 | -1.167 |
Token | had |
Token ID | 550 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Sabha | +0.641 |
bane | +0.592 |
conn | +0.508 |
ader | +0.462 |
Loading | +0.460 |
Neg logit contributions | |
beard | -0.596 |
�� | -0.553 |
netflix | -0.552 |
姫 | -0.522 |
Noir | -0.519 |
Token | nothing |
Token ID | 2147 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
beard | +1.592 |
netflix | +1.473 |
�� | +1.442 |
Noir | +1.398 |
姫 | +1.366 |
Neg logit contributions | |
Sabha | -1.906 |
bane | -1.777 |
conn | -1.539 |
ader | -1.406 |
Loading | -1.401 |
Token | but |
Token ID | 475 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
beard | +7.450 |
�� | +6.948 |
netflix | +6.605 |
Noir | +6.468 |
heels | +6.354 |
Neg logit contributions | |
Sabha | -9.700 |
bane | -8.903 |
conn | -7.927 |
Loading | -7.260 |
Pix | -7.158 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
beard | +4.407 |
netflix | +3.871 |
�� | +3.736 |
heels | +3.722 |
Hulk | +3.631 |
Neg logit contributions | |
Sabha | -7.327 |
bane | -6.791 |
conn | -6.091 |
ader | -5.641 |
Loading | -5.635 |
Token | words |
Token ID | 2456 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
beard | +1.237 |
netflix | +1.104 |
�� | +1.090 |
Noir | +1.004 |
heels | +0.989 |
Neg logit contributions | |
Sabha | -2.489 |
bane | -2.309 |
conn | -2.062 |
Loading | -1.967 |
ader | -1.933 |
Token | for |
Token ID | 329 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
beard | +2.366 |
netflix | +2.174 |
�� | +2.153 |
Noir | +2.047 |
姫 | +2.031 |
Neg logit contributions | |
Sabha | -2.796 |
bane | -2.578 |
conn | -2.245 |
Loading | -2.048 |
ader | -2.038 |
Token | Japan |
Token ID | 2869 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
Sabha | +0.147 |
bane | +0.136 |
conn | +0.116 |
ader | +0.106 |
Loading | +0.105 |
Neg logit contributions | |
beard | -0.139 |
�� | -0.130 |
netflix | -0.129 |
姫 | -0.122 |
Noir | -0.121 |
Token | voices |
Token ID | 10839 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
beard | +0.226 |
netflix | +0.192 |
�� | +0.188 |
姫 | +0.176 |
Noir | +0.176 |
Neg logit contributions | |
Sabha | -0.598 |
bane | -0.568 |
conn | -0.514 |
Loading | -0.483 |
ader | -0.479 |
Token | in |
Token ID | 287 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
Sabha | +5.700 |
bane | +5.303 |
conn | +4.234 |
Loading | +3.706 |
ader | +3.696 |
Neg logit contributions | |
�� | -9.365 |
beard | -8.987 |
netflix | -8.599 |
姫 | -8.311 |
Noir | -8.139 |
Token | his |
Token ID | 465 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Sabha | +0.294 |
bane | +0.273 |
conn | +0.242 |
Loading | +0.222 |
Uz | +0.222 |
Neg logit contributions | |
beard | -0.198 |
netflix | -0.178 |
�� | -0.173 |
Noir | -0.167 |
姫 | -0.164 |
Token | or |
Token ID | 393 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
Sabha | +0.351 |
bane | +0.322 |
conn | +0.278 |
Loading | +0.254 |
Uz | +0.251 |
Neg logit contributions | |
beard | -0.321 |
netflix | -0.294 |
�� | -0.282 |
Noir | -0.277 |
heels | -0.274 |
Token | her |
Token ID | 607 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Sabha | +0.647 |
bane | +0.595 |
conn | +0.509 |
Loading | +0.458 |
Uz | +0.454 |
Neg logit contributions | |
beard | -0.671 |
netflix | -0.621 |
�� | -0.598 |
Noir | -0.589 |
heels | -0.586 |
Token | head |
Token ID | 1182 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
beard | +2.284 |
heels | +1.909 |
netflix | +1.872 |
Noir | +1.745 |
Hulk | +1.724 |
Neg logit contributions | |
Sabha | -5.171 |
bane | -4.784 |
conn | -4.408 |
Loading | -4.159 |
Uz | -4.024 |
Token | , |
Token ID | 11 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
beard | +5.924 |
netflix | +4.863 |
Hulk | +4.598 |
Noir | +4.585 |
TG | +4.459 |
Neg logit contributions | |
Sabha | -11.577 |
bane | -10.282 |
conn | -9.336 |
tremend | -9.323 |
��� | -9.121 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
beard | +4.310 |
netflix | +3.868 |
Noir | +3.605 |
Hulk | +3.543 |
heels | +3.424 |
Neg logit contributions | |
Sabha | -6.535 |
bane | -5.951 |
conn | -5.284 |
Uz | -4.904 |
ader | -4.856 |
Token | must |
Token ID | 1276 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
beard | +0.874 |
netflix | +0.791 |
Noir | +0.752 |
�� | +0.748 |
heels | +0.735 |
Neg logit contributions | |
Sabha | -1.076 |
bane | -0.996 |
conn | -0.858 |
ader | -0.792 |
Uz | -0.789 |
Token | roll |
Token ID | 4836 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
beard | +2.421 |
roll | +1.985 |
netflix | +1.853 |
heels | +1.588 |
Hulk | +1.584 |
Neg logit contributions | |
Sabha | -11.354 |
bane | -10.728 |
conn | -9.748 |
Loading | -9.408 |
Uz | -9.276 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
beard | +3.160 |
netflix | +2.850 |
Noir | +2.699 |
heels | +2.687 |
Hulk | +2.586 |
Neg logit contributions | |
Sabha | -4.395 |
bane | -4.054 |
conn | -3.536 |
Uz | -3.279 |
Loading | -3.229 |
Token | ce |
Token ID | 344 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
beard | +3.186 |
netflix | +2.911 |
�� | +2.892 |
姫 | +2.694 |
Noir | +2.682 |
Neg logit contributions | |
Sabha | -3.772 |
bane | -3.399 |
conn | -2.929 |
Uz | -2.729 |
Loading | -2.703 |
Token | ives |
Token ID | 1083 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
beard | +0.552 |
netflix | +0.505 |
�� | +0.502 |
姫 | +0.471 |
Noir | +0.470 |
Neg logit contributions | |
Sabha | -0.705 |
bane | -0.649 |
conn | -0.565 |
Loading | -0.520 |
Uz | -0.518 |
Token | from |
Token ID | 422 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
beard | +1.524 |
netflix | +1.394 |
�� | +1.382 |
Noir | +1.322 |
姫 | +1.316 |
Neg logit contributions | |
Sabha | -1.759 |
bane | -1.615 |
conn | -1.416 |
Loading | -1.294 |
ader | -1.278 |
Token | his |
Token ID | 465 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
beard | +0.640 |
�� | +0.594 |
netflix | +0.592 |
姫 | +0.560 |
Noir | +0.558 |
Neg logit contributions | |
Sabha | -0.693 |
bane | -0.640 |
conn | -0.551 |
ader | -0.500 |
Loading | -0.499 |
Token | fel |
Token ID | 10756 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Sabha | +2.654 |
bane | +2.446 |
conn | +2.084 |
ader | +1.902 |
Uz | +1.892 |
Neg logit contributions | |
beard | -2.538 |
�� | -2.383 |
netflix | -2.371 |
姫 | -2.246 |
Noir | -2.208 |
Token | |
Token ID | 3907 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
beard | +1.560 |
netflix | +1.451 |
�� | +1.412 |
Noir | +1.368 |
姫 | +1.356 |
Neg logit contributions | |
Sabha | -1.386 |
bane | -1.241 |
conn | -1.041 |
Loading | -0.949 |
Pix | -0.918 |
Token | low |
Token ID | 9319 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
beard | +7.684 |
netflix | +7.247 |
fman | +6.626 |
lap | +6.524 |
imov | +6.504 |
Neg logit contributions | |
Sabha | -10.004 |
bane | -8.562 |
Uz | -7.087 |
Pix | -6.953 |
Loading | -6.919 |
Token | Demo |
Token ID | 34588 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
beard | +0.273 |
netflix | +0.253 |
�� | +0.253 |
姫 | +0.241 |
Noir | +0.239 |
Neg logit contributions | |
Sabha | -0.264 |
bane | -0.243 |
conn | -0.207 |
Loading | -0.188 |
ader | -0.185 |
Token | |
Token ID | 3907 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Sabha | +1.799 |
bane | +1.637 |
conn | +1.357 |
ader | +1.206 |
Loading | +1.196 |
Neg logit contributions | |
beard | -2.300 |
�� | -2.167 |
netflix | -2.159 |
姫 | -2.059 |
Noir | -2.043 |
Token | cr |
Token ID | 6098 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
beard | +5.960 |
netflix | +5.200 |
�� | +5.068 |
姫 | +4.903 |
lap | +4.881 |
Neg logit contributions | |
Sabha | -6.229 |
bane | -5.415 |
conn | -4.644 |
Uz | -4.433 |
Loading | -4.289 |
Token | ats |
Token ID | 1381 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
beard | +0.571 |
netflix | +0.523 |
�� | +0.520 |
姫 | +0.494 |
Noir | +0.494 |
Neg logit contributions | |
Sabha | -0.712 |
bane | -0.656 |
conn | -0.573 |
Loading | -0.524 |
Uz | -0.517 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
beard | +2.194 |
netflix | +1.940 |
Noir | +1.839 |
Hulk | +1.775 |
姫 | +1.764 |
Neg logit contributions | |
Sabha | -2.978 |
bane | -2.692 |
conn | -2.368 |
Uz | -2.205 |
ader | -2.186 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
beard | +0.960 |
netflix | +0.862 |
Noir | +0.823 |
姫 | +0.806 |
�� | +0.805 |
Neg logit contributions | |
Sabha | -1.408 |
bane | -1.319 |
conn | -1.163 |
ader | -1.074 |
Loading | -1.062 |
Token | at |
Token ID | 379 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Sabha | +1.957 |
bane | +1.777 |
conn | +1.469 |
ader | +1.302 |
Loading | +1.291 |
Neg logit contributions | |
beard | -2.566 |
�� | -2.416 |
netflix | -2.409 |
姫 | -2.299 |
Noir | -2.282 |
Token | 2 |
Token ID | 362 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
beard | +2.590 |
netflix | +2.285 |
Noir | +2.224 |
Hulk | +2.134 |
heels | +2.126 |
Neg logit contributions | |
Sabha | -3.673 |
bane | -3.367 |
conn | -3.017 |
Loading | -2.772 |
ader | -2.752 |
Token | : |
Token ID | 25 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
beard | +3.156 |
netflix | +2.689 |
Noir | +2.476 |
Hulk | +2.415 |
lap | +2.357 |
Neg logit contributions | |
Sabha | -6.281 |
bane | -5.710 |
conn | -5.078 |
Uz | -4.839 |
ader | -4.768 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
beard | +3.620 |
netflix | +3.064 |
Noir | +2.847 |
Hulk | +2.835 |
TG | +2.824 |
Neg logit contributions | |
Sabha | -6.466 |
bane | -5.820 |
conn | -5.143 |
Uz | -4.864 |
ader | -4.849 |
Token | am |
Token ID | 321 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
beard | +6.106 |
netflix | +5.649 |
�� | +5.274 |
lap | +4.971 |
姫 | +4.863 |
Neg logit contributions | |
Sabha | -11.430 |
bane | -10.280 |
conn | -9.102 |
Uz | -8.834 |
Pix | -8.729 |
Token | PST |
Token ID | 28220 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
beard | +2.740 |
netflix | +2.394 |
Noir | +2.377 |
姫 | +2.303 |
Hulk | +2.225 |
Neg logit contributions | |
Sabha | -7.422 |
bane | -6.927 |
conn | -6.208 |
ader | -5.891 |
Loading | -5.781 |
Token |
|
Token ID | 198 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
Sabha | +1.618 |
bane | +1.505 |
conn | +1.247 |
ader | +1.109 |
Loading | +1.108 |
Neg logit contributions | |
beard | -1.973 |
�� | -1.878 |
netflix | -1.853 |
姫 | -1.761 |
Noir | -1.751 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-04 |
Pos logit contributions | |
beard | +0.377 |
netflix | +0.343 |
Noir | +0.323 |
姫 | +0.318 |
�� | +0.315 |
Neg logit contributions | |
Sabha | -0.436 |
bane | -0.397 |
conn | -0.340 |
ader | -0.313 |
Uz | -0.313 |
Token | Do |
Token ID | 5211 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Sabha | +0.007 |
bane | +0.006 |
conn | +0.006 |
ader | +0.005 |
Loading | +0.005 |
Neg logit contributions | |
beard | -0.005 |
�� | -0.005 |
netflix | -0.005 |
姫 | -0.004 |
Noir | -0.004 |
Token | refinery |
Token ID | 44133 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
beard | +0.978 |
�� | +0.909 |
netflix | +0.902 |
Noir | +0.855 |
姫 | +0.844 |
Neg logit contributions | |
Sabha | -1.166 |
bane | -1.086 |
conn | -0.935 |
ader | -0.858 |
Loading | -0.856 |
Token | business |
Token ID | 1597 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
Sabha | +0.863 |
bane | +0.799 |
conn | +0.689 |
ader | +0.630 |
Loading | +0.626 |
Neg logit contributions | |
beard | -0.749 |
�� | -0.697 |
netflix | -0.693 |
姫 | -0.654 |
Noir | -0.648 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
beard | +0.545 |
�� | +0.505 |
netflix | +0.504 |
姫 | +0.475 |
Noir | +0.474 |
Neg logit contributions | |
Sabha | -0.622 |
bane | -0.579 |
conn | -0.497 |
ader | -0.453 |
Loading | -0.453 |
Token | Ser |
Token ID | 2930 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
Sabha | +0.386 |
bane | +0.357 |
conn | +0.308 |
ader | +0.282 |
Loading | +0.280 |
Neg logit contributions | |
beard | -0.334 |
�� | -0.309 |
netflix | -0.309 |
姫 | -0.292 |
Noir | -0.290 |
Token | hi |
Token ID | 5303 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
beard | +0.667 |
netflix | +0.621 |
�� | +0.615 |
Noir | +0.584 |
姫 | +0.583 |
Neg logit contributions | |
Sabha | -0.621 |
bane | -0.569 |
conn | -0.480 |
ader | -0.435 |
Loading | -0.435 |
Token | y |
Token ID | 88 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
beard | +2.636 |
netflix | +2.316 |
Noir | +2.202 |
imov | +2.120 |
姫 | +2.116 |
Neg logit contributions | |
Sabha | -3.854 |
bane | -3.541 |
conn | -3.170 |
Loading | -2.893 |
Pix | -2.852 |
Token | Kaz |
Token ID | 16385 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
beard | +7.192 |
netflix | +6.637 |
�� | +6.630 |
Noir | +6.534 |
姫 | +6.401 |
Neg logit contributions | |
Sabha | -9.768 |
bane | -9.175 |
conn | -8.084 |
Loading | -7.606 |
ader | -7.339 |
Token | arov |
Token ID | 42737 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
beard | +0.241 |
netflix | +0.209 |
�� | +0.199 |
Noir | +0.183 |
姫 | +0.182 |
Neg logit contributions | |
Sabha | -0.609 |
bane | -0.569 |
conn | -0.516 |
Loading | -0.486 |
Uz | -0.483 |
Token | is |
Token ID | 318 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
beard | +0.999 |
netflix | +0.922 |
�� | +0.922 |
姫 | +0.877 |
Noir | +0.869 |
Neg logit contributions | |
Sabha | -1.089 |
bane | -1.008 |
conn | -0.865 |
Loading | -0.789 |
ader | -0.787 |
Token | former |
Token ID | 1966 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Sabha | +0.549 |
bane | +0.506 |
conn | +0.432 |
ader | +0.393 |
Uz | +0.391 |
Neg logit contributions | |
beard | -0.532 |
�� | -0.497 |
netflix | -0.495 |
姫 | -0.468 |
Noir | -0.463 |
Token | head |
Token ID | 1182 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
beard | +1.809 |
�� | +1.656 |
netflix | +1.642 |
Noir | +1.552 |
姫 | +1.525 |
Neg logit contributions | |
Sabha | -2.688 |
bane | -2.533 |
conn | -2.207 |
Loading | -2.054 |
ader | -2.042 |
Token | going |
Token ID | 1016 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Sabha | +0.901 |
bane | +0.840 |
conn | +0.730 |
ader | +0.671 |
Loading | +0.663 |
Neg logit contributions | |
beard | -0.706 |
�� | -0.651 |
netflix | -0.648 |
Noir | -0.605 |
姫 | -0.604 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Sabha | +1.300 |
bane | +1.168 |
conn | +0.992 |
ader | +0.903 |
Loading | +0.894 |
Neg logit contributions | |
beard | -1.477 |
�� | -1.403 |
netflix | -1.371 |
姫 | -1.331 |
Noir | -1.301 |
Token | have |
Token ID | 423 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
Sabha | +1.895 |
bane | +1.757 |
conn | +1.520 |
ader | +1.392 |
Loading | +1.383 |
Neg logit contributions | |
beard | -1.581 |
�� | -1.468 |
netflix | -1.461 |
姫 | -1.376 |
Noir | -1.363 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Sabha | +0.629 |
bane | +0.579 |
conn | +0.494 |
ader | +0.448 |
Loading | +0.445 |
Neg logit contributions | |
beard | -0.620 |
�� | -0.580 |
netflix | -0.577 |
姫 | -0.548 |
Noir | -0.541 |
Token | paraph |
Token ID | 38624 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Sabha | +1.348 |
bane | +1.249 |
conn | +1.083 |
ader | +0.990 |
Loading | +0.989 |
Neg logit contributions | |
beard | -1.119 |
netflix | -1.031 |
�� | -1.031 |
姫 | -0.969 |
Noir | -0.964 |
Token | rase |
Token ID | 22789 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Sabha | +2.970 |
bane | +2.762 |
conn | +2.382 |
ader | +2.186 |
Loading | +2.144 |
Neg logit contributions | |
beard | -2.600 |
�� | -2.502 |
netflix | -2.402 |
姫 | -2.332 |
Noir | -2.257 |
Token | here |
Token ID | 994 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Sabha | +6.939 |
bane | +6.183 |
conn | +5.108 |
Uz | +4.870 |
ader | +4.795 |
Neg logit contributions | |
beard | -6.914 |
�� | -6.790 |
netflix | -6.520 |
姫 | -6.257 |
EVA | -6.051 |
Token | — |
Token ID | 851 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Sabha | +1.752 |
bane | +1.616 |
conn | +1.387 |
ader | +1.269 |
Loading | +1.260 |
Neg logit contributions | |
beard | -1.553 |
�� | -1.455 |
netflix | -1.444 |
姫 | -1.363 |
Noir | -1.347 |
Token | that |
Token ID | 326 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
Sabha | +0.447 |
bane | +0.413 |
conn | +0.353 |
ader | +0.321 |
Loading | +0.319 |
Neg logit contributions | |
beard | -0.426 |
�� | -0.397 |
netflix | -0.397 |
姫 | -0.375 |
Noir | -0.373 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Sabha | +0.291 |
bane | +0.269 |
conn | +0.231 |
ader | +0.211 |
Loading | +0.209 |
Neg logit contributions | |
beard | -0.261 |
�� | -0.242 |
netflix | -0.242 |
姫 | -0.228 |
Noir | -0.227 |
Token | reason |
Token ID | 1738 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
beard | +0.326 |
�� | +0.301 |
netflix | +0.301 |
Noir | +0.283 |
姫 | +0.281 |
Neg logit contributions | |
Sabha | -0.387 |
bane | -0.362 |
conn | -0.311 |
Loading | -0.284 |
ader | -0.283 |
Token | the |
Token ID | 262 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
beard | +2.773 |
�� | +2.511 |
netflix | +2.494 |
Noir | +2.398 |
heels | +2.371 |
Neg logit contributions | |
Sabha | -3.439 |
bane | -3.198 |
conn | -2.773 |
Loading | -2.521 |
ader | -2.516 |
Token | spotlight |
Token ID | 17838 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
beard | +1.079 |
�� | +0.988 |
netflix | +0.978 |
Noir | +0.923 |
heels | +0.910 |
Neg logit contributions | |
Sabha | -1.461 |
bane | -1.364 |
conn | -1.192 |
Loading | -1.089 |
ader | -1.084 |
Token | , |
Token ID | 11 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
Sabha | +2.803 |
bane | +2.588 |
conn | +2.202 |
ader | +2.009 |
Uz | +1.985 |
Neg logit contributions | |
beard | -2.731 |
�� | -2.564 |
netflix | -2.551 |
姫 | -2.419 |
Noir | -2.388 |
Token | as |
Token ID | 355 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Sabha | +0.581 |
bane | +0.536 |
conn | +0.460 |
ader | +0.418 |
Loading | +0.417 |
Neg logit contributions | |
beard | -0.541 |
�� | -0.502 |
netflix | -0.502 |
姫 | -0.472 |
Noir | -0.471 |
Token | Mark |
Token ID | 2940 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
beard | +0.893 |
netflix | +0.827 |
�� | +0.825 |
Noir | +0.777 |
姫 | +0.772 |
Neg logit contributions | |
Sabha | -1.049 |
bane | -0.976 |
conn | -0.839 |
Loading | -0.764 |
ader | -0.763 |
Token | Hal |
Token ID | 11023 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
Sabha | +0.998 |
bane | +0.926 |
conn | +0.795 |
Loading | +0.720 |
ader | +0.715 |
Neg logit contributions | |
beard | -0.927 |
�� | -0.855 |
netflix | -0.854 |
Noir | -0.807 |
姫 | -0.806 |
Token | per |
Token ID | 525 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
Sabha | +6.645 |
bane | +6.345 |
conn | +5.402 |
ader | +5.066 |
Pix | +4.779 |
Neg logit contributions | |
�� | -6.544 |
beard | -6.428 |
姫 | -6.185 |
netflix | -6.174 |
Noir | -5.887 |
Token | in |
Token ID | 259 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
beard | +6.196 |
netflix | +5.723 |
�� | +5.713 |
姫 | +5.530 |
Noir | +5.443 |
Neg logit contributions | |
Sabha | -4.883 |
bane | -4.339 |
conn | -3.609 |
Uz | -3.238 |
Pix | -3.128 |
Token | pointed |
Token ID | 6235 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
beard | +1.746 |
netflix | +1.594 |
�� | +1.589 |
Noir | +1.531 |
姫 | +1.512 |
Neg logit contributions | |
Sabha | -1.975 |
bane | -1.817 |
conn | -1.567 |
Loading | -1.428 |
ader | -1.416 |
Token | out |
Token ID | 503 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
beard | +0.288 |
netflix | +0.263 |
�� | +0.260 |
Noir | +0.247 |
姫 | +0.243 |
Neg logit contributions | |
Sabha | -0.351 |
bane | -0.326 |
conn | -0.285 |
ader | -0.260 |
Loading | -0.260 |
Token | recently |
Token ID | 2904 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
beard | +1.709 |
netflix | +1.578 |
�� | +1.573 |
姫 | +1.496 |
Noir | +1.493 |
Neg logit contributions | |
Sabha | -1.813 |
bane | -1.678 |
conn | -1.444 |
ader | -1.307 |
Loading | -1.301 |
Token | - |
Token ID | 12 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
Sabha | +0.925 |
bane | +0.852 |
conn | +0.726 |
ader | +0.660 |
Loading | +0.655 |
Neg logit contributions | |
beard | -0.914 |
�� | -0.856 |
netflix | -0.852 |
姫 | -0.803 |
Noir | -0.795 |
Token | a |
Token ID | 64 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Sabha | +6.432 |
bane | +6.041 |
conn | +5.275 |
ader | +4.878 |
Loading | +4.751 |
Neg logit contributions | |
beard | -5.350 |
�� | -5.145 |
netflix | -5.090 |
姫 | -4.725 |
Noir | -4.687 |
Token | ] |
Token ID | 60 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Sabha | +1.526 |
bane | +1.399 |
conn | +1.183 |
ader | +1.066 |
Loading | +1.059 |
Neg logit contributions | |
beard | -1.647 |
�� | -1.543 |
netflix | -1.537 |
姫 | -1.460 |
Noir | -1.448 |
Token | p |
Token ID | 79 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Sabha | +1.856 |
bane | +1.725 |
conn | +1.490 |
ader | +1.366 |
Loading | +1.353 |
Neg logit contributions | |
beard | -1.566 |
�� | -1.458 |
netflix | -1.451 |
姫 | -1.367 |
Noir | -1.354 |
Token | yr |
Token ID | 2417 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
Sabha | +0.910 |
bane | +0.832 |
conn | +0.693 |
ader | +0.621 |
Loading | +0.612 |
Neg logit contributions | |
beard | -1.121 |
�� | -1.057 |
netflix | -1.053 |
姫 | -1.004 |
Noir | -0.993 |
Token | id |
Token ID | 312 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Sabha | +0.333 |
bane | +0.307 |
conn | +0.264 |
Loading | +0.241 |
ader | +0.240 |
Neg logit contributions | |
beard | -0.296 |
�� | -0.275 |
netflix | -0.274 |
姫 | -0.259 |
Noir | -0.257 |
Token | in |
Token ID | 259 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Sabha | +6.353 |
bane | +6.028 |
conn | +5.088 |
ader | +4.774 |
Loading | +4.495 |
Neg logit contributions | |
beard | -6.614 |
�� | -6.387 |
netflix | -6.203 |
姫 | -5.994 |
Noir | -5.815 |
Token | - |
Token ID | 12 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
Sabha | +2.185 |
bane | +2.028 |
conn | +1.747 |
ader | +1.607 |
Loading | +1.587 |
Neg logit contributions | |
beard | -1.862 |
�� | -1.738 |
netflix | -1.727 |
姫 | -1.633 |
Noir | -1.606 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Sabha | +0.475 |
bane | +0.441 |
conn | +0.384 |
ader | +0.353 |
Loading | +0.351 |
Neg logit contributions | |
beard | -0.365 |
�� | -0.337 |
netflix | -0.335 |
姫 | -0.314 |
Noir | -0.312 |
Token | - |
Token ID | 12 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
beard | +1.167 |
�� | +1.082 |
netflix | +1.073 |
姫 | +1.020 |
Noir | +1.014 |
Neg logit contributions | |
Sabha | -1.310 |
bane | -1.208 |
conn | -1.047 |
ader | -0.950 |
Loading | -0.949 |
Token | amine |
Token ID | 9862 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Sabha | +2.652 |
bane | +2.500 |
conn | +2.189 |
ader | +2.037 |
Loading | +2.004 |
Neg logit contributions | |
beard | -1.775 |
�� | -1.645 |
netflix | -1.643 |
姫 | -1.536 |
Noir | -1.512 |
Token | his |
Token ID | 465 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Sabha | +5.271 |
bane | +4.868 |
conn | +4.097 |
Uz | +3.823 |
ader | +3.771 |
Neg logit contributions | |
beard | -5.116 |
�� | -4.957 |
netflix | -4.821 |
姫 | -4.654 |
EVA | -4.337 |
Token | ex |
Token ID | 409 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Sabha | +4.542 |
bane | +4.186 |
conn | +3.586 |
Uz | +3.282 |
ader | +3.274 |
Neg logit contributions | |
beard | -4.198 |
�� | -3.998 |
netflix | -3.919 |
姫 | -3.767 |
Noir | -3.630 |
Token | - |
Token ID | 12 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
Sabha | +1.002 |
bane | +0.928 |
conn | +0.797 |
ader | +0.726 |
Uz | +0.718 |
Neg logit contributions | |
beard | -0.952 |
�� | -0.890 |
netflix | -0.882 |
姫 | -0.840 |
Noir | -0.828 |
Token | wife |
Token ID | 22095 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Sabha | +0.691 |
bane | +0.637 |
conn | +0.550 |
ader | +0.504 |
Uz | +0.503 |
Neg logit contributions | |
beard | -0.583 |
netflix | -0.537 |
�� | -0.533 |
姫 | -0.502 |
Noir | -0.497 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Sabha | +0.822 |
bane | +0.759 |
conn | +0.651 |
ader | +0.592 |
Loading | +0.588 |
Neg logit contributions | |
beard | -0.771 |
�� | -0.718 |
netflix | -0.715 |
姫 | -0.676 |
Noir | -0.671 |
Token | 33 |
Token ID | 4747 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Sabha | +3.172 |
bane | +2.928 |
conn | +2.516 |
ader | +2.305 |
Uz | +2.304 |
Neg logit contributions | |
beard | -2.779 |
�� | -2.614 |
netflix | -2.585 |
姫 | -2.449 |
Noir | -2.387 |
Token | - |
Token ID | 12 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Sabha | +6.503 |
bane | +5.932 |
conn | +4.901 |
Uz | +4.564 |
ader | +4.459 |
Neg logit contributions | |
beard | -7.895 |
�� | -7.725 |
netflix | -7.567 |
姫 | -7.209 |
Noir | -6.801 |
Token | year |
Token ID | 1941 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Sabha | +3.385 |
bane | +3.139 |
conn | +2.721 |
ader | +2.496 |
Loading | +2.481 |
Neg logit contributions | |
beard | -2.742 |
�� | -2.534 |
netflix | -2.529 |
姫 | -2.377 |
Noir | -2.354 |
Token | - |
Token ID | 12 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
Sabha | +2.976 |
bane | +2.747 |
conn | +2.355 |
ader | +2.145 |
Loading | +2.131 |
Neg logit contributions | |
beard | -2.766 |
�� | -2.594 |
netflix | -2.571 |
姫 | -2.435 |
Noir | -2.406 |
Token | old |
Token ID | 727 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Sabha | +0.587 |
bane | +0.535 |
conn | +0.462 |
Uz | +0.428 |
ader | +0.423 |
Neg logit contributions | |
beard | -0.482 |
netflix | -0.439 |
�� | -0.421 |
姫 | -0.408 |
Noir | -0.406 |
Token | Z |
Token ID | 1168 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Sabha | +2.643 |
bane | +2.437 |
conn | +2.101 |
Uz | +1.944 |
ader | +1.929 |
Neg logit contributions | |
beard | -2.215 |
�� | -2.087 |
netflix | -2.065 |
姫 | -1.957 |
Noir | -1.886 |
Token | subway |
Token ID | 19612 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Sabha | +0.897 |
bane | +0.833 |
conn | +0.720 |
Loading | +0.662 |
ader | +0.659 |
Neg logit contributions | |
beard | -0.742 |
�� | -0.682 |
netflix | -0.681 |
Noir | -0.645 |
姫 | -0.642 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
beard | +2.050 |
netflix | +1.837 |
�� | +1.827 |
Noir | +1.761 |
姫 | +1.731 |
Neg logit contributions | |
Sabha | -2.925 |
bane | -2.771 |
conn | -2.414 |
Loading | -2.233 |
ader | -2.187 |
Token | killing |
Token ID | 5170 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
beard | +1.397 |
netflix | +1.299 |
�� | +1.259 |
Noir | +1.252 |
heels | +1.221 |
Neg logit contributions | |
Sabha | -1.178 |
bane | -1.100 |
conn | -0.930 |
Loading | -0.810 |
ader | -0.799 |
Token | 12 |
Token ID | 1105 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
beard | +0.327 |
netflix | +0.301 |
�� | +0.299 |
Noir | +0.284 |
姫 | +0.280 |
Neg logit contributions | |
Sabha | -0.362 |
bane | -0.336 |
conn | -0.290 |
Loading | -0.262 |
ader | -0.262 |
Token | people |
Token ID | 661 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Sabha | +3.226 |
bane | +2.934 |
conn | +2.497 |
Uz | +2.256 |
ader | +2.255 |
Neg logit contributions | |
beard | -3.532 |
�� | -3.347 |
netflix | -3.337 |
姫 | -3.178 |
Noir | -3.127 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Sabha | +1.974 |
bane | +1.825 |
conn | +1.572 |
ader | +1.440 |
Uz | +1.429 |
Neg logit contributions | |
beard | -1.725 |
�� | -1.616 |
netflix | -1.601 |
姫 | -1.514 |
Noir | -1.495 |
Token | sending |
Token ID | 7216 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Sabha | +7.637 |
bane | +7.030 |
conn | +5.924 |
ader | +5.549 |
Loading | +5.472 |
Neg logit contributions | |
beard | -7.598 |
�� | -7.566 |
netflix | -7.314 |
姫 | -7.176 |
Noir | -6.812 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Sabha | +0.499 |
bane | +0.463 |
conn | +0.399 |
ader | +0.363 |
Loading | +0.361 |
Neg logit contributions | |
beard | -0.438 |
netflix | -0.404 |
�� | -0.403 |
Noir | -0.378 |
姫 | -0.377 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Sabha | +3.213 |
bane | +2.954 |
conn | +2.526 |
ader | +2.318 |
Uz | +2.312 |
Neg logit contributions | |
beard | -3.035 |
�� | -2.877 |
netflix | -2.845 |
姫 | -2.724 |
Noir | -2.662 |
Token | 500 |
Token ID | 4059 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Sabha | +2.240 |
bane | +2.072 |
conn | +1.764 |
ader | +1.606 |
Loading | +1.592 |
Neg logit contributions | |
beard | -2.254 |
�� | -2.124 |
netflix | -2.095 |
姫 | -1.996 |
Noir | -1.980 |
Token | to |
Token ID | 284 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Sabha | +3.562 |
bane | +3.289 |
conn | +2.839 |
Uz | +2.625 |
ader | +2.606 |
Neg logit contributions | |
beard | -3.112 |
�� | -2.953 |
netflix | -2.903 |
姫 | -2.783 |
Noir | -2.694 |
Token | it |
Token ID | 340 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Sabha | +2.462 |
bane | +2.281 |
conn | +1.964 |
ader | +1.792 |
Loading | +1.780 |
Neg logit contributions | |
beard | -2.180 |
�� | -2.025 |
netflix | -2.018 |
姫 | -1.904 |
Noir | -1.889 |
Token | raises |
Token ID | 12073 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Sabha | +1.648 |
bane | +1.528 |
conn | +1.318 |
Loading | +1.199 |
ader | +1.199 |
Neg logit contributions | |
beard | -1.448 |
netflix | -1.333 |
�� | -1.330 |
姫 | -1.262 |
Noir | -1.255 |
Token | interest |
Token ID | 1393 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
beard | +0.676 |
�� | +0.613 |
netflix | +0.609 |
Noir | +0.582 |
heels | +0.574 |
Neg logit contributions | |
Sabha | -0.884 |
bane | -0.836 |
conn | -0.729 |
Loading | -0.662 |
ader | -0.660 |
Token | rates |
Token ID | 3965 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Sabha | +2.214 |
bane | +2.064 |
conn | +1.833 |
ader | +1.711 |
Uz | +1.707 |
Neg logit contributions | |
beard | -1.255 |
�� | -1.164 |
netflix | -1.150 |
姫 | -1.055 |
Noir | -1.039 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Sabha | +4.939 |
bane | +4.459 |
conn | +3.784 |
ader | +3.505 |
Uz | +3.452 |
Neg logit contributions | |
beard | -4.795 |
�� | -4.676 |
netflix | -4.533 |
姫 | -4.284 |
Noir | -4.163 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Sabha | +1.771 |
bane | +1.617 |
conn | +1.346 |
ader | +1.218 |
Pix | +1.203 |
Neg logit contributions | |
beard | -2.099 |
�� | -2.007 |
netflix | -1.960 |
姫 | -1.884 |
Noir | -1.835 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Sabha | +1.220 |
bane | +1.120 |
conn | +0.955 |
ader | +0.869 |
Uz | +0.867 |
Neg logit contributions | |
beard | -1.139 |
netflix | -1.050 |
�� | -1.005 |
Noir | -0.989 |
姫 | -0.984 |
Token | First |
Token ID | 5962 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Sabha | +2.517 |
bane | +2.342 |
conn | +2.028 |
Loading | +1.856 |
ader | +1.855 |
Neg logit contributions | |
beard | -2.127 |
�� | -1.997 |
netflix | -1.968 |
姫 | -1.861 |
Noir | -1.845 |
Token | rise |
Token ID | 4485 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
beard | +0.630 |
netflix | +0.550 |
�� | +0.550 |
姫 | +0.515 |
Noir | +0.506 |
Neg logit contributions | |
Sabha | -1.259 |
bane | -1.187 |
conn | -1.062 |
ader | -0.988 |
Uz | -0.984 |
Token | ? |
Token ID | 30 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Sabha | +0.197 |
bane | +0.181 |
conn | +0.154 |
ader | +0.140 |
Loading | +0.139 |
Neg logit contributions | |
beard | -0.201 |
�� | -0.188 |
netflix | -0.187 |
姫 | -0.178 |
Noir | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Sabha | +2.035 |
bane | +1.866 |
conn | +1.555 |
ader | +1.409 |
Uz | +1.406 |
Neg logit contributions | |
beard | -2.412 |
�� | -2.306 |
netflix | -2.259 |
姫 | -2.169 |
Noir | -2.118 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
beard | +0.237 |
�� | +0.218 |
netflix | +0.217 |
姫 | +0.205 |
Noir | +0.204 |
Neg logit contributions | |
Sabha | -0.315 |
bane | -0.294 |
conn | -0.254 |
ader | -0.234 |
Loading | -0.234 |
Token | Sk |
Token ID | 3661 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
beard | +1.125 |
netflix | +1.024 |
�� | +1.022 |
Noir | +0.980 |
姫 | +0.963 |
Neg logit contributions | |
Sabha | -1.437 |
bane | -1.337 |
conn | -1.162 |
Loading | -1.068 |
ader | -1.066 |
Token | var |
Token ID | 7785 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
Sabha | +5.444 |
bane | +5.077 |
conn | +4.410 |
ader | +4.096 |
Loading | +3.992 |
Neg logit contributions | |
beard | -4.449 |
�� | -4.233 |
netflix | -4.132 |
姫 | -3.963 |
Noir | -3.858 |
Token | la |
Token ID | 5031 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
beard | +0.549 |
netflix | +0.507 |
�� | +0.507 |
Noir | +0.477 |
姫 | +0.477 |
Neg logit contributions | |
Sabha | -0.586 |
bane | -0.540 |
conn | -0.463 |
Loading | -0.423 |
ader | -0.418 |
Token | made |
Token ID | 925 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
beard | +0.730 |
�� | +0.680 |
netflix | +0.675 |
Noir | +0.642 |
姫 | +0.641 |
Neg logit contributions | |
Sabha | -0.761 |
bane | -0.705 |
conn | -0.599 |
Loading | -0.544 |
ader | -0.543 |
Token | it |
Token ID | 340 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Sabha | +0.309 |
bane | +0.284 |
conn | +0.242 |
ader | +0.219 |
Loading | +0.218 |
Neg logit contributions | |
beard | -0.311 |
�� | -0.289 |
netflix | -0.289 |
姫 | -0.274 |
Noir | -0.273 |
Token | clear |
Token ID | 1598 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Sabha | +2.419 |
bane | +2.227 |
conn | +1.890 |
ader | +1.713 |
Loading | +1.698 |
Neg logit contributions | |
beard | -2.480 |
�� | -2.323 |
netflix | -2.313 |
姫 | -2.194 |
Noir | -2.172 |
Token | that |
Token ID | 326 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
beard | +1.178 |
netflix | +1.092 |
�� | +1.088 |
姫 | +1.037 |
Noir | +1.028 |
Neg logit contributions | |
Sabha | -1.255 |
bane | -1.161 |
conn | -0.989 |
Loading | -0.904 |
ader | -0.902 |
Token | Good |
Token ID | 4599 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
beard | +0.429 |
�� | +0.398 |
netflix | +0.398 |
姫 | +0.377 |
Noir | +0.375 |
Neg logit contributions | |
Sabha | -0.460 |
bane | -0.424 |
conn | -0.362 |
ader | -0.330 |
Loading | -0.329 |
Token | � |
Token ID | 447 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Sabha | +0.646 |
bane | +0.597 |
conn | +0.512 |
ader | +0.468 |
Loading | +0.467 |
Neg logit contributions | |
beard | -0.567 |
�� | -0.525 |
netflix | -0.521 |
姫 | -0.495 |
Noir | -0.490 |
Token | � |
Token ID | 247 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
beard | +0.734 |
�� | +0.693 |
netflix | +0.664 |
姫 | +0.638 |
Noir | +0.627 |
Neg logit contributions | |
Sabha | -0.824 |
bane | -0.750 |
conn | -0.656 |
Uz | -0.596 |
Loading | -0.586 |
Token | in |
Token ID | 287 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Sabha | +0.572 |
bane | +0.529 |
conn | +0.455 |
ader | +0.415 |
Loading | +0.413 |
Neg logit contributions | |
beard | -0.510 |
�� | -0.475 |
netflix | -0.473 |
姫 | -0.446 |
Noir | -0.442 |
Token | the |
Token ID | 262 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
Sabha | +2.025 |
bane | +1.852 |
conn | +1.552 |
ader | +1.415 |
Uz | +1.408 |
Neg logit contributions | |
beard | -2.164 |
�� | -2.056 |
netflix | -2.046 |
姫 | -1.944 |
Noir | -1.907 |
Token | wings |
Token ID | 12098 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
beard | +0.482 |
�� | +0.449 |
netflix | +0.447 |
姫 | +0.422 |
Noir | +0.422 |
Neg logit contributions | |
Sabha | -0.486 |
bane | -0.451 |
conn | -0.384 |
ader | -0.347 |
Loading | -0.347 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
beard | +1.890 |
�� | +1.721 |
netflix | +1.702 |
姫 | +1.618 |
Noir | +1.611 |
Neg logit contributions | |
Sabha | -2.110 |
bane | -1.942 |
conn | -1.683 |
Uz | -1.535 |
Loading | -1.530 |
Token | stage |
Token ID | 3800 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
beard | +0.803 |
netflix | +0.731 |
�� | +0.728 |
Noir | +0.692 |
heels | +0.687 |
Neg logit contributions | |
Sabha | -0.971 |
bane | -0.903 |
conn | -0.786 |
ader | -0.712 |
Loading | -0.708 |
Token | right |
Token ID | 826 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
beard | +0.634 |
�� | +0.574 |
netflix | +0.571 |
姫 | +0.534 |
Noir | +0.532 |
Neg logit contributions | |
Sabha | -0.941 |
bane | -0.881 |
conn | -0.779 |
Loading | -0.713 |
ader | -0.712 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
Sabha | +4.398 |
bane | +4.026 |
conn | +3.396 |
ader | +3.171 |
Uz | +3.092 |
Neg logit contributions | |
beard | -4.267 |
netflix | -4.107 |
�� | -4.091 |
姫 | -3.822 |
Noir | -3.769 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
beard | +0.302 |
�� | +0.277 |
netflix | +0.277 |
Noir | +0.262 |
姫 | +0.261 |
Neg logit contributions | |
Sabha | -0.333 |
bane | -0.309 |
conn | -0.266 |
ader | -0.240 |
Loading | -0.240 |
Token | said |
Token ID | 531 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Sabha | +0.033 |
bane | +0.031 |
conn | +0.026 |
ader | +0.023 |
Loading | +0.023 |
Neg logit contributions | |
beard | -0.036 |
�� | -0.033 |
netflix | -0.033 |
姫 | -0.031 |
Noir | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Sabha | +2.490 |
bane | +2.292 |
conn | +1.976 |
ader | +1.814 |
Uz | +1.799 |
Neg logit contributions | |
beard | -2.218 |
�� | -2.089 |
netflix | -2.076 |
姫 | -1.959 |
Noir | -1.913 |
Token | Each |
Token ID | 5501 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
beard | +0.930 |
netflix | +0.861 |
�� | +0.841 |
Noir | +0.816 |
姫 | +0.813 |
Neg logit contributions | |
Sabha | -1.069 |
bane | -0.987 |
conn | -0.855 |
ader | -0.772 |
Loading | -0.767 |
Token | It |
Token ID | 632 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
Sabha | +0.566 |
bane | +0.522 |
conn | +0.452 |
ader | +0.413 |
Loading | +0.409 |
Neg logit contributions | |
beard | -0.492 |
netflix | -0.452 |
�� | -0.444 |
Noir | -0.430 |
姫 | -0.427 |
Token | was |
Token ID | 373 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Sabha | +0.789 |
bane | +0.727 |
conn | +0.626 |
ader | +0.569 |
Loading | +0.569 |
Neg logit contributions | |
beard | -0.705 |
netflix | -0.652 |
�� | -0.650 |
姫 | -0.614 |
Noir | -0.612 |
Token | a |
Token ID | 257 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Sabha | +1.287 |
bane | +1.192 |
conn | +1.032 |
ader | +0.941 |
Loading | +0.936 |
Neg logit contributions | |
beard | -1.110 |
�� | -1.023 |
netflix | -1.023 |
姫 | -0.964 |
Noir | -0.958 |
Token | different |
Token ID | 1180 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
Sabha | +3.093 |
bane | +2.871 |
conn | +2.491 |
ader | +2.291 |
Loading | +2.274 |
Neg logit contributions | |
beard | -2.469 |
�� | -2.303 |
netflix | -2.285 |
姫 | -2.157 |
Noir | -2.121 |
Token | story |
Token ID | 1621 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Sabha | +3.054 |
bane | +2.842 |
conn | +2.482 |
ader | +2.300 |
Uz | +2.280 |
Neg logit contributions | |
beard | -2.204 |
�� | -2.048 |
netflix | -2.031 |
姫 | -1.913 |
Noir | -1.873 |
Token | in |
Token ID | 287 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Sabha | +1.972 |
bane | +1.810 |
conn | +1.528 |
ader | +1.392 |
Uz | +1.377 |
Neg logit contributions | |
beard | -2.050 |
�� | -1.939 |
netflix | -1.918 |
姫 | -1.820 |
Noir | -1.796 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Sabha | +2.446 |
bane | +2.246 |
conn | +1.896 |
ader | +1.713 |
Uz | +1.701 |
Neg logit contributions | |
beard | -2.585 |
�� | -2.437 |
netflix | -2.417 |
姫 | -2.300 |
Noir | -2.261 |
Token | U |
Token ID | 471 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Sabha | +2.186 |
bane | +2.012 |
conn | +1.714 |
ader | +1.554 |
Loading | +1.543 |
Neg logit contributions | |
beard | -2.179 |
�� | -2.037 |
netflix | -2.028 |
姫 | -1.922 |
Noir | -1.905 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Sabha | +2.238 |
bane | +2.075 |
conn | +1.806 |
Uz | +1.659 |
ader | +1.659 |
Neg logit contributions | |
beard | -1.668 |
netflix | -1.524 |
�� | -1.488 |
姫 | -1.419 |
Noir | -1.412 |
Token | S |
Token ID | 50 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
beard | +0.743 |
�� | +0.688 |
netflix | +0.686 |
姫 | +0.644 |
Noir | +0.634 |
Neg logit contributions | |
Sabha | -1.057 |
bane | -0.984 |
conn | -0.864 |
ader | -0.796 |
Loading | -0.795 |
Token | .: |
Token ID | 11207 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Sabha | +2.335 |
bane | +2.149 |
conn | +1.828 |
ader | +1.708 |
Loading | +1.642 |
Neg logit contributions | |
beard | -2.245 |
�� | -2.089 |
netflix | -2.081 |
姫 | -1.989 |
Noir | -1.956 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Sabha | +0.792 |
bane | +0.731 |
conn | +0.624 |
ader | +0.566 |
Loading | +0.564 |
Neg logit contributions | |
beard | -0.772 |
netflix | -0.717 |
�� | -0.716 |
姫 | -0.679 |
Noir | -0.673 |
Token | more |
Token ID | 517 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
beard | +0.901 |
netflix | +0.823 |
�� | +0.816 |
Noir | +0.779 |
姫 | +0.774 |
Neg logit contributions | |
Sabha | -1.032 |
bane | -0.962 |
conn | -0.825 |
ader | -0.758 |
Loading | -0.751 |
Token | costs |
Token ID | 3484 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
beard | +3.436 |
netflix | +3.095 |
�� | +3.041 |
Noir | +2.977 |
heels | +2.961 |
Neg logit contributions | |
Sabha | -3.568 |
bane | -3.370 |
conn | -2.850 |
ader | -2.650 |
Loading | -2.635 |
Token | than |
Token ID | 621 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
beard | +0.224 |
netflix | +0.207 |
�� | +0.204 |
姫 | +0.195 |
Noir | +0.195 |
Neg logit contributions | |
Sabha | -0.241 |
bane | -0.224 |
conn | -0.192 |
ader | -0.175 |
Loading | -0.174 |
Token | paying |
Token ID | 5989 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
Sabha | +0.104 |
bane | +0.097 |
conn | +0.083 |
ader | +0.076 |
Loading | +0.076 |
Neg logit contributions | |
beard | -0.089 |
netflix | -0.082 |
�� | -0.081 |
Noir | -0.077 |
姫 | -0.076 |
Token | in |
Token ID | 287 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
beard | +0.014 |
netflix | +0.013 |
�� | +0.013 |
Noir | +0.012 |
姫 | +0.012 |
Neg logit contributions | |
Sabha | -0.016 |
bane | -0.015 |
conn | -0.013 |
ader | -0.011 |
Loading | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Sabha | +2.951 |
bane | +2.726 |
conn | +2.352 |
ader | +2.138 |
Uz | +2.128 |
Neg logit contributions | |
beard | -2.642 |
�� | -2.481 |
netflix | -2.453 |
姫 | -2.333 |
Noir | -2.289 |
Token | cases |
Token ID | 2663 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
beard | +0.107 |
netflix | +0.097 |
�� | +0.096 |
Noir | +0.091 |
姫 | +0.091 |
Neg logit contributions | |
Sabha | -0.158 |
bane | -0.148 |
conn | -0.129 |
ader | -0.120 |
Loading | -0.119 |
Token | more |
Token ID | 517 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Sabha | +3.449 |
bane | +3.151 |
conn | +2.696 |
ader | +2.431 |
Uz | +2.423 |
Neg logit contributions | |
beard | -3.508 |
�� | -3.341 |
netflix | -3.279 |
姫 | -3.131 |
Noir | -3.058 |
Token | than |
Token ID | 621 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Sabha | +1.093 |
bane | +1.007 |
conn | +0.857 |
ader | +0.777 |
Loading | +0.773 |
Neg logit contributions | |
beard | -1.091 |
�� | -1.018 |
netflix | -1.015 |
姫 | -0.961 |
Noir | -0.954 |
Token | $ |
Token ID | 720 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Sabha | +2.211 |
bane | +2.042 |
conn | +1.760 |
ader | +1.605 |
Loading | +1.596 |
Neg logit contributions | |
beard | -1.966 |
�� | -1.835 |
netflix | -1.823 |
姫 | -1.724 |
Noir | -1.702 |
Token | � |
Token ID | 447 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
beard | +0.693 |
�� | +0.650 |
netflix | +0.647 |
姫 | +0.617 |
Noir | +0.611 |
Neg logit contributions | |
Sabha | -0.600 |
bane | -0.548 |
conn | -0.460 |
ader | -0.413 |
Loading | -0.410 |
Token | � |
Token ID | 247 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
beard | +1.915 |
�� | +1.797 |
netflix | +1.721 |
姫 | +1.649 |
Noir | +1.628 |
Neg logit contributions | |
Sabha | -2.295 |
bane | -2.080 |
conn | -1.827 |
Uz | -1.685 |
Pix | -1.660 |
Token | m |
Token ID | 76 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
beard | +1.826 |
netflix | +1.664 |
�� | +1.658 |
姫 | +1.573 |
Noir | +1.550 |
Neg logit contributions | |
Sabha | -2.346 |
bane | -2.171 |
conn | -1.891 |
Loading | -1.736 |
Uz | -1.733 |
Token | a |
Token ID | 257 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
beard | +1.445 |
�� | +1.325 |
netflix | +1.325 |
Noir | +1.240 |
姫 | +1.219 |
Neg logit contributions | |
Sabha | -1.927 |
bane | -1.795 |
conn | -1.568 |
ader | -1.452 |
Loading | -1.424 |
Token | social |
Token ID | 1919 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Sabha | +2.277 |
bane | +2.110 |
conn | +1.829 |
ader | +1.674 |
Loading | +1.663 |
Neg logit contributions | |
beard | -1.891 |
�� | -1.759 |
netflix | -1.747 |
姫 | -1.647 |
Noir | -1.631 |
Token | worker |
Token ID | 8383 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
beard | +1.242 |
netflix | +1.139 |
�� | +1.137 |
Noir | +1.080 |
姫 | +1.074 |
Neg logit contributions | |
Sabha | -1.631 |
bane | -1.516 |
conn | -1.292 |
Loading | -1.217 |
Uz | -1.205 |
Token | ! |
Token ID | 0 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
beard | +1.973 |
netflix | +1.811 |
�� | +1.811 |
Noir | +1.720 |
姫 | +1.717 |
Neg logit contributions | |
Sabha | -2.200 |
bane | -2.037 |
conn | -1.756 |
ader | -1.593 |
Loading | -1.584 |
Token | � |
Token ID | 447 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
beard | +0.153 |
�� | +0.142 |
netflix | +0.142 |
姫 | +0.134 |
Noir | +0.133 |
Neg logit contributions | |
Sabha | -0.164 |
bane | -0.152 |
conn | -0.130 |
ader | -0.118 |
Loading | -0.117 |
Token | � |
Token ID | 251 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
beard | +0.160 |
�� | +0.149 |
netflix | +0.148 |
姫 | +0.140 |
Noir | +0.139 |
Neg logit contributions | |
Sabha | -0.173 |
bane | -0.160 |
conn | -0.137 |
ader | -0.125 |
Loading | -0.124 |
Token | she |
Token ID | 673 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
Sabha | +1.120 |
bane | +1.035 |
conn | +0.889 |
ader | +0.810 |
Loading | +0.806 |
Neg logit contributions | |
beard | -1.027 |
�� | -0.958 |
netflix | -0.953 |
姫 | -0.900 |
Noir | -0.892 |
Token | yelled |
Token ID | 22760 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Sabha | +0.237 |
bane | +0.218 |
conn | +0.185 |
ader | +0.166 |
Loading | +0.166 |
Neg logit contributions | |
beard | -0.245 |
�� | -0.228 |
netflix | -0.228 |
姫 | -0.217 |
Noir | -0.215 |
Token | 98 |
Token ID | 9661 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
beard | +1.166 |
netflix | +1.068 |
�� | +1.039 |
Noir | +1.018 |
姫 | +0.995 |
Neg logit contributions | |
Sabha | -1.207 |
bane | -1.123 |
conn | -0.946 |
ader | -0.859 |
Loading | -0.848 |
Token | 59 |
Token ID | 3270 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
beard | +0.570 |
netflix | +0.515 |
�� | +0.498 |
姫 | +0.485 |
Noir | +0.480 |
Neg logit contributions | |
Sabha | -0.778 |
bane | -0.717 |
conn | -0.623 |
ader | -0.575 |
Uz | -0.573 |
Token | 64 |
Token ID | 2414 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
beard | +0.599 |
netflix | +0.542 |
�� | +0.525 |
Noir | +0.508 |
姫 | +0.507 |
Neg logit contributions | |
Sabha | -0.811 |
bane | -0.745 |
conn | -0.649 |
ader | -0.599 |
Uz | -0.595 |
Token | x |
Token ID | 2124 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Sabha | +2.872 |
bane | +2.621 |
conn | +2.190 |
ader | +1.957 |
Loading | +1.942 |
Neg logit contributions | |
beard | -3.452 |
�� | -3.247 |
netflix | -3.234 |
姫 | -3.080 |
Noir | -3.055 |
Token | . |
Token ID | 13 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Sabha | +0.655 |
bane | +0.605 |
conn | +0.526 |
Uz | +0.486 |
ader | +0.485 |
Neg logit contributions | |
beard | -0.473 |
netflix | -0.428 |
�� | -0.409 |
Noir | -0.398 |
姫 | -0.396 |
Token | x |
Token ID | 87 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
Sabha | +2.224 |
bane | +2.029 |
conn | +1.685 |
ader | +1.498 |
Loading | +1.486 |
Neg logit contributions | |
beard | -2.835 |
�� | -2.686 |
netflix | -2.663 |
姫 | -2.544 |
Noir | -2.521 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Sabha | +0.548 |
bane | +0.506 |
conn | +0.441 |
Uz | +0.406 |
ader | +0.406 |
Neg logit contributions | |
beard | -0.396 |
netflix | -0.360 |
�� | -0.345 |
Noir | -0.335 |
姫 | -0.331 |
Token | x |
Token ID | 87 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Sabha | +2.062 |
bane | +1.875 |
conn | +1.558 |
ader | +1.387 |
Loading | +1.376 |
Neg logit contributions | |
beard | -2.581 |
�� | -2.424 |
netflix | -2.420 |
姫 | -2.305 |
Noir | -2.289 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
beard | +0.101 |
netflix | +0.092 |
�� | +0.089 |
姫 | +0.085 |
Noir | +0.085 |
Neg logit contributions | |
Sabha | -0.143 |
bane | -0.132 |
conn | -0.114 |
Uz | -0.107 |
Pix | -0.106 |
Token | 128 |
Token ID | 12762 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
beard | +0.203 |
netflix | +0.181 |
�� | +0.180 |
姫 | +0.165 |
Noir | +0.161 |
Neg logit contributions | |
Sabha | -0.382 |
bane | -0.356 |
conn | -0.312 |
Uz | -0.296 |
Pix | -0.293 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
beard | +0.939 |
netflix | +0.858 |
�� | +0.837 |
Noir | +0.819 |
姫 | +0.804 |
Neg logit contributions | |
Sabha | -1.002 |
bane | -0.928 |
conn | -0.788 |
ader | -0.716 |
Loading | -0.707 |
Token | Lap |
Token ID | 26944 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
Sabha | +0.031 |
bane | +0.029 |
conn | +0.026 |
Uz | +0.024 |
ader | +0.024 |
Neg logit contributions | |
beard | -0.017 |
�� | -0.015 |
netflix | -0.015 |
姫 | -0.014 |
Noir | -0.014 |
Token | eral |
Token ID | 1691 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Sabha | +0.442 |
bane | +0.395 |
conn | +0.326 |
Uz | +0.298 |
Loading | +0.291 |
Neg logit contributions | |
beard | -0.600 |
netflix | -0.554 |
�� | -0.544 |
Noir | -0.529 |
姫 | -0.523 |
Token | also |
Token ID | 635 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
beard | +1.771 |
netflix | +1.634 |
�� | +1.595 |
Noir | +1.566 |
姫 | +1.542 |
Neg logit contributions | |
Sabha | -1.931 |
bane | -1.780 |
conn | -1.518 |
Loading | -1.400 |
ader | -1.371 |
Token | reached |
Token ID | 4251 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
beard | +0.246 |
netflix | +0.227 |
�� | +0.222 |
Noir | +0.216 |
姫 | +0.213 |
Neg logit contributions | |
Sabha | -0.285 |
bane | -0.262 |
conn | -0.225 |
Loading | -0.208 |
ader | -0.205 |
Token | some |
Token ID | 617 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
beard | +0.457 |
netflix | +0.423 |
�� | +0.422 |
Noir | +0.397 |
姫 | +0.397 |
Neg logit contributions | |
Sabha | -0.526 |
bane | -0.488 |
conn | -0.420 |
ader | -0.384 |
Loading | -0.382 |
Token | unsettling |
Token ID | 38192 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
Sabha | +1.346 |
bane | +1.243 |
conn | +1.063 |
ader | +0.970 |
Loading | +0.963 |
Neg logit contributions | |
beard | -1.263 |
netflix | -1.169 |
�� | -1.169 |
Noir | -1.103 |
姫 | -1.102 |
Token | conclusions |
Token ID | 13242 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Sabha | +0.336 |
bane | +0.315 |
conn | +0.279 |
Loading | +0.257 |
ader | +0.257 |
Neg logit contributions | |
beard | -0.197 |
netflix | -0.178 |
�� | -0.176 |
Noir | -0.165 |
姫 | -0.163 |
Token | in |
Token ID | 287 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
beard | +1.706 |
netflix | +1.561 |
�� | +1.517 |
Noir | +1.462 |
姫 | +1.446 |
Neg logit contributions | |
Sabha | -2.242 |
bane | -2.086 |
conn | -1.830 |
Loading | -1.677 |
ader | -1.663 |
Token | her |
Token ID | 607 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
beard | +0.484 |
netflix | +0.451 |
�� | +0.446 |
Noir | +0.426 |
姫 | +0.421 |
Neg logit contributions | |
Sabha | -0.503 |
bane | -0.466 |
conn | -0.398 |
ader | -0.361 |
Loading | -0.359 |
Token | interviews |
Token ID | 9299 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
beard | +1.904 |
netflix | +1.738 |
�� | +1.718 |
Noir | +1.660 |
heels | +1.637 |
Neg logit contributions | |
Sabha | -2.468 |
bane | -2.287 |
conn | -1.999 |
Loading | -1.848 |
ader | -1.837 |
Token | with |
Token ID | 351 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
beard | +2.917 |
netflix | +2.678 |
�� | +2.608 |
Noir | +2.531 |
姫 | +2.495 |
Neg logit contributions | |
Sabha | -3.500 |
bane | -3.263 |
conn | -2.792 |
Loading | -2.588 |
ader | -2.555 |
Token | get |
Token ID | 651 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
beard | +0.406 |
�� | +0.376 |
netflix | +0.373 |
姫 | +0.353 |
Noir | +0.350 |
Neg logit contributions | |
Sabha | -0.509 |
bane | -0.472 |
conn | -0.409 |
Loading | -0.376 |
ader | -0.375 |
Token | some |
Token ID | 617 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
Sabha | +0.380 |
bane | +0.351 |
conn | +0.301 |
ader | +0.274 |
Loading | +0.272 |
Neg logit contributions | |
beard | -0.354 |
�� | -0.329 |
netflix | -0.328 |
姫 | -0.310 |
Noir | -0.308 |
Token | upgrades |
Token ID | 16608 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
Sabha | +0.273 |
bane | +0.253 |
conn | +0.219 |
ader | +0.200 |
Loading | +0.199 |
Neg logit contributions | |
beard | -0.229 |
�� | -0.211 |
netflix | -0.210 |
姫 | -0.199 |
Noir | -0.198 |
Token | for |
Token ID | 329 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
beard | +0.258 |
�� | +0.239 |
netflix | +0.239 |
姫 | +0.225 |
Noir | +0.224 |
Neg logit contributions | |
Sabha | -0.283 |
bane | -0.262 |
conn | -0.225 |
ader | -0.205 |
Loading | -0.204 |
Token | Australia |
Token ID | 4505 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Sabha | +1.908 |
bane | +1.753 |
conn | +1.488 |
ader | +1.355 |
Uz | +1.345 |
Neg logit contributions | |
beard | -1.911 |
�� | -1.783 |
netflix | -1.780 |
姫 | -1.683 |
Noir | -1.652 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Sabha | +2.695 |
bane | +2.470 |
conn | +2.114 |
ader | +1.919 |
Loading | +1.905 |
Neg logit contributions | |
beard | -2.606 |
�� | -2.431 |
netflix | -2.429 |
姫 | -2.303 |
Noir | -2.269 |
Token |
|
Token ID | 198 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
beard | +0.901 |
netflix | +0.836 |
�� | +0.825 |
Noir | +0.791 |
姫 | +0.788 |
Neg logit contributions | |
Sabha | -1.032 |
bane | -0.956 |
conn | -0.822 |
ader | -0.754 |
Loading | -0.741 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
beard | +0.600 |
netflix | +0.547 |
Noir | +0.515 |
姫 | +0.507 |
Hulk | +0.496 |
Neg logit contributions | |
Sabha | -0.711 |
bane | -0.647 |
conn | -0.555 |
Uz | -0.513 |
ader | -0.511 |
Token | � |
Token ID | 447 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
beard | +0.958 |
netflix | +0.898 |
�� | +0.897 |
姫 | +0.855 |
Noir | +0.846 |
Neg logit contributions | |
Sabha | -0.805 |
bane | -0.733 |
conn | -0.610 |
ader | -0.547 |
Uz | -0.542 |
Token | � |
Token ID | 250 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
beard | +0.855 |
�� | +0.809 |
netflix | +0.795 |
姫 | +0.758 |
Noir | +0.753 |
Neg logit contributions | |
Sabha | -0.803 |
bane | -0.728 |
conn | -0.619 |
ader | -0.556 |
Uz | -0.552 |
Token | Especially |
Token ID | 48464 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Sabha | +2.116 |
bane | +1.963 |
conn | +1.699 |
ader | +1.555 |
Loading | +1.549 |
Neg logit contributions | |
beard | -1.771 |
�� | -1.647 |
netflix | -1.636 |
姫 | -1.543 |
Noir | -1.527 |
Token | panel |
Token ID | 6103 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
beard | +0.365 |
�� | +0.335 |
netflix | +0.334 |
姫 | +0.313 |
Noir | +0.312 |
Neg logit contributions | |
Sabha | -0.514 |
bane | -0.481 |
conn | -0.420 |
ader | -0.388 |
Loading | -0.387 |
Token | events |
Token ID | 2995 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Sabha | +0.092 |
bane | +0.085 |
conn | +0.074 |
ader | +0.067 |
Loading | +0.067 |
Neg logit contributions | |
beard | -0.081 |
�� | -0.075 |
netflix | -0.074 |
姫 | -0.070 |
Noir | -0.070 |
Token | will |
Token ID | 481 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
beard | +1.228 |
netflix | +1.138 |
�� | +1.126 |
Noir | +1.070 |
姫 | +1.067 |
Neg logit contributions | |
Sabha | -1.447 |
bane | -1.347 |
conn | -1.176 |
Loading | -1.075 |
ader | -1.062 |
Token | take |
Token ID | 1011 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
beard | +2.041 |
netflix | +1.859 |
�� | +1.848 |
姫 | +1.756 |
Noir | +1.734 |
Neg logit contributions | |
Sabha | -2.646 |
bane | -2.474 |
conn | -2.165 |
Loading | -2.003 |
Uz | -1.972 |
Token | place |
Token ID | 1295 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
beard | +2.340 |
�� | +1.997 |
netflix | +1.993 |
Noir | +1.865 |
姫 | +1.851 |
Neg logit contributions | |
Sabha | -5.849 |
bane | -5.654 |
conn | -5.125 |
Loading | -4.782 |
Uz | -4.719 |
Token | on |
Token ID | 319 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
beard | +2.381 |
netflix | +2.210 |
�� | +2.126 |
Noir | +2.099 |
姫 | +2.095 |
Neg logit contributions | |
Sabha | -2.810 |
bane | -2.619 |
conn | -2.306 |
Loading | -2.070 |
ader | -2.062 |
Token | Feb |
Token ID | 3158 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Sabha | +0.638 |
bane | +0.592 |
conn | +0.512 |
ader | +0.469 |
Loading | +0.466 |
Neg logit contributions | |
beard | -0.535 |
�� | -0.497 |
netflix | -0.495 |
姫 | -0.466 |
Noir | -0.462 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
beard | +0.773 |
netflix | +0.697 |
�� | +0.676 |
Noir | +0.656 |
姫 | +0.646 |
Neg logit contributions | |
Sabha | -1.112 |
bane | -1.032 |
conn | -0.907 |
Uz | -0.836 |
Loading | -0.831 |
Token | 25 |
Token ID | 1679 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
beard | +2.831 |
netflix | +2.513 |
Noir | +2.488 |
姫 | +2.340 |
Hulk | +2.326 |
Neg logit contributions | |
Sabha | -3.708 |
bane | -3.401 |
conn | -3.019 |
ader | -2.752 |
Loading | -2.718 |
Token | - |
Token ID | 12 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
beard | +0.898 |
netflix | +0.831 |
�� | +0.828 |
姫 | +0.790 |
Noir | +0.784 |
Neg logit contributions | |
Sabha | -0.989 |
bane | -0.913 |
conn | -0.786 |
ader | -0.714 |
Loading | -0.712 |
Token | 26 |
Token ID | 2075 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Sabha | +0.217 |
bane | +0.202 |
conn | +0.179 |
ader | +0.166 |
Uz | +0.164 |
Neg logit contributions | |
beard | -0.138 |
netflix | -0.125 |
�� | -0.124 |
姫 | -0.117 |
Noir | -0.115 |
Token | ( |
Token ID | 357 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Sabha | +1.064 |
bane | +0.982 |
conn | +0.840 |
ader | +0.761 |
Loading | +0.757 |
Neg logit contributions | |
beard | -1.009 |
netflix | -0.937 |
�� | -0.937 |
姫 | -0.887 |
Noir | -0.882 |
Token | CB |
Token ID | 23199 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Sabha | +2.256 |
bane | +2.066 |
conn | +1.742 |
ader | +1.567 |
Loading | +1.556 |
Neg logit contributions | |
beard | -2.501 |
�� | -2.345 |
netflix | -2.336 |
姫 | -2.220 |
Noir | -2.202 |
Token | PP |
Token ID | 10246 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
beard | +0.219 |
netflix | +0.193 |
�� | +0.181 |
姫 | +0.176 |
Noir | +0.171 |
Neg logit contributions | |
Sabha | -0.589 |
bane | -0.548 |
conn | -0.496 |
Uz | -0.468 |
ader | -0.467 |
Token | ) |
Token ID | 8 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
beard | +0.263 |
�� | +0.243 |
netflix | +0.243 |
姫 | +0.228 |
Noir | +0.226 |
Neg logit contributions | |
Sabha | -0.307 |
bane | -0.285 |
conn | -0.247 |
ader | -0.225 |
Loading | -0.224 |
Token | offered |
Token ID | 4438 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
beard | +0.238 |
netflix | +0.220 |
�� | +0.217 |
姫 | +0.208 |
Noir | +0.208 |
Neg logit contributions | |
Sabha | -0.269 |
bane | -0.249 |
conn | -0.213 |
Loading | -0.193 |
ader | -0.193 |
Token | further |
Token ID | 2252 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
beard | +0.359 |
�� | +0.333 |
netflix | +0.333 |
Noir | +0.315 |
姫 | +0.314 |
Neg logit contributions | |
Sabha | -0.373 |
bane | -0.345 |
conn | -0.295 |
ader | -0.265 |
Loading | -0.264 |
Token | analysis |
Token ID | 3781 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
beard | +3.992 |
netflix | +3.577 |
heels | +3.573 |
Noir | +3.540 |
�� | +3.533 |
Neg logit contributions | |
Sabha | -5.846 |
bane | -5.550 |
conn | -4.853 |
ader | -4.399 |
Loading | -4.341 |
Token | : |
Token ID | 25 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
beard | +1.378 |
netflix | +1.262 |
�� | +1.238 |
Noir | +1.195 |
姫 | +1.179 |
Neg logit contributions | |
Sabha | -1.593 |
bane | -1.466 |
conn | -1.271 |
ader | -1.150 |
Loading | -1.146 |
Token |
|
Token ID | 198 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
beard | +1.352 |
�� | +1.265 |
netflix | +1.256 |
姫 | +1.193 |
Noir | +1.180 |
Neg logit contributions | |
Sabha | -1.346 |
bane | -1.239 |
conn | -1.057 |
ader | -0.958 |
Loading | -0.951 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Sabha | +0.035 |
bane | +0.032 |
conn | +0.027 |
ader | +0.025 |
Uz | +0.025 |
Neg logit contributions | |
beard | -0.031 |
netflix | -0.028 |
Noir | -0.027 |
�� | -0.026 |
姫 | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Sabha | +0.195 |
bane | +0.181 |
conn | +0.157 |
ader | +0.144 |
Uz | +0.143 |
Neg logit contributions | |
beard | -0.156 |
netflix | -0.144 |
�� | -0.144 |
姫 | -0.135 |
Noir | -0.133 |
Token | The |
Token ID | 464 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
beard | +0.892 |
netflix | +0.825 |
�� | +0.805 |
姫 | +0.767 |
Noir | +0.759 |
Neg logit contributions | |
Sabha | -1.132 |
bane | -1.037 |
conn | -0.898 |
ader | -0.825 |
Uz | -0.824 |
Token | first |
Token ID | 717 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
beard | +0.969 |
netflix | +0.897 |
�� | +0.893 |
Noir | +0.848 |
姫 | +0.833 |
Neg logit contributions | |
Sabha | -1.182 |
bane | -1.097 |
conn | -0.946 |
ader | -0.865 |
Loading | -0.861 |
Token | Destiny |
Token ID | 17886 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
beard | +0.858 |
netflix | +0.791 |
�� | +0.787 |
Noir | +0.740 |
姫 | +0.737 |
Neg logit contributions | |
Sabha | -1.077 |
bane | -1.003 |
conn | -0.868 |
ader | -0.793 |
Loading | -0.788 |
Token | game |
Token ID | 983 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
beard | +1.768 |
netflix | +1.626 |
�� | +1.604 |
Noir | +1.531 |
姫 | +1.499 |
Neg logit contributions | |
Sabha | -2.448 |
bane | -2.274 |
conn | -1.989 |
ader | -1.827 |
Loading | -1.816 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
beard | +2.083 |
netflix | +1.921 |
�� | +1.894 |
Noir | +1.822 |
姫 | +1.782 |
Neg logit contributions | |
Sabha | -2.292 |
bane | -2.114 |
conn | -1.823 |
ader | -1.658 |
Loading | -1.645 |
Token | its |
Token ID | 663 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
Sabha | +0.022 |
bane | +0.021 |
conn | +0.018 |
ader | +0.016 |
Loading | +0.016 |
Neg logit contributions | |
beard | -0.019 |
�� | -0.018 |
netflix | -0.018 |
姫 | -0.017 |
Noir | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
beard | +4.608 |
netflix | +4.254 |
�� | +4.116 |
Noir | +4.106 |
heels | +4.053 |
Neg logit contributions | |
Sabha | -5.205 |
bane | -4.860 |
conn | -4.176 |
Loading | -3.763 |
ader | -3.732 |
Token | major |
Token ID | 22478 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Sabha | +0.860 |
bane | +0.800 |
conn | +0.691 |
ader | +0.633 |
Loading | +0.630 |
Neg logit contributions | |
beard | -0.727 |
�� | -0.679 |
netflix | -0.672 |
姫 | -0.636 |
Noir | -0.629 |
Token | downloadable |
Token ID | 41496 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
beard | +2.345 |
netflix | +2.168 |
�� | +2.104 |
Noir | +2.019 |
姫 | +1.984 |
Neg logit contributions | |
Sabha | -3.258 |
bane | -3.039 |
conn | -2.653 |
Loading | -2.444 |
ader | -2.427 |
Token | content |
Token ID | 2695 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
beard | +2.990 |
netflix | +2.722 |
�� | +2.601 |
Noir | +2.497 |
heels | +2.447 |
Neg logit contributions | |
Sabha | -5.304 |
bane | -4.941 |
conn | -4.412 |
Loading | -4.068 |
ader | -4.050 |
Token | expansion |
Token ID | 7118 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
beard | +3.580 |
netflix | +3.300 |
�� | +3.152 |
Noir | +3.102 |
heels | +3.030 |
Neg logit contributions | |
Sabha | -5.336 |
bane | -4.951 |
conn | -4.370 |
ader | -4.006 |
Loading | -3.996 |
Token | informed |
Token ID | 7981 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
beard | +2.070 |
netflix | +1.910 |
�� | +1.896 |
姫 | +1.820 |
Noir | +1.815 |
Neg logit contributions | |
Sabha | -2.351 |
bane | -2.178 |
conn | -1.845 |
ader | -1.698 |
Loading | -1.677 |
Token | her |
Token ID | 607 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
beard | +1.810 |
netflix | +1.711 |
�� | +1.696 |
Noir | +1.603 |
姫 | +1.590 |
Neg logit contributions | |
Sabha | -1.938 |
bane | -1.797 |
conn | -1.545 |
Loading | -1.389 |
ader | -1.386 |
Token | that |
Token ID | 326 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Sabha | +1.232 |
bane | +1.136 |
conn | +0.971 |
ader | +0.881 |
Loading | +0.876 |
Neg logit contributions | |
beard | -1.193 |
�� | -1.112 |
netflix | -1.109 |
姫 | -1.050 |
Noir | -1.041 |
Token | her |
Token ID | 607 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
beard | +1.177 |
netflix | +1.103 |
�� | +1.096 |
Noir | +1.035 |
姫 | +1.027 |
Neg logit contributions | |
Sabha | -1.314 |
bane | -1.221 |
conn | -1.050 |
ader | -0.950 |
Loading | -0.944 |
Token | original |
Token ID | 2656 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
beard | +1.601 |
netflix | +1.469 |
�� | +1.454 |
Noir | +1.381 |
heels | +1.363 |
Neg logit contributions | |
Sabha | -2.098 |
bane | -1.964 |
conn | -1.710 |
Loading | -1.560 |
ader | -1.555 |
Token | flight |
Token ID | 5474 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
beard | +3.213 |
netflix | +2.959 |
�� | +2.894 |
Noir | +2.762 |
heels | +2.732 |
Neg logit contributions | |
Sabha | -4.999 |
bane | -4.718 |
conn | -4.130 |
Loading | -3.791 |
ader | -3.768 |
Token | was |
Token ID | 373 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
beard | +4.709 |
netflix | +4.251 |
�� | +4.220 |
heels | +4.104 |
Noir | +4.069 |
Neg logit contributions | |
Sabha | -5.861 |
bane | -5.403 |
conn | -4.763 |
ader | -4.251 |
Pix | -4.215 |
Token | full |
Token ID | 1336 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
beard | +4.297 |
netflix | +3.957 |
�� | +3.808 |
Noir | +3.757 |
heels | +3.619 |
Neg logit contributions | |
Sabha | -6.459 |
bane | -5.964 |
conn | -5.381 |
ader | -4.840 |
Creat | -4.807 |
Token | and |
Token ID | 290 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
beard | +2.897 |
netflix | +2.661 |
�� | +2.615 |
姫 | +2.501 |
Noir | +2.488 |
Neg logit contributions | |
Sabha | -3.351 |
bane | -3.084 |
conn | -2.680 |
ader | -2.474 |
Pix | -2.426 |
Token | she |
Token ID | 673 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
beard | +0.511 |
netflix | +0.477 |
�� | +0.476 |
Noir | +0.447 |
姫 | +0.443 |
Neg logit contributions | |
Sabha | -0.573 |
bane | -0.530 |
conn | -0.459 |
ader | -0.415 |
Loading | -0.411 |
Token | wouldn |
Token ID | 3636 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
beard | +1.664 |
netflix | +1.533 |
�� | +1.495 |
姫 | +1.440 |
Noir | +1.437 |
Neg logit contributions | |
Sabha | -1.983 |
bane | -1.819 |
conn | -1.585 |
Loading | -1.444 |
Creat | -1.435 |
Token | b |
Token ID | 65 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
beard | +5.835 |
netflix | +5.448 |
Noir | +5.083 |
�� | +4.879 |
姫 | +4.865 |
Neg logit contributions | |
Sabha | -6.735 |
bane | -6.092 |
conn | -5.318 |
Uz | -4.914 |
Loading | -4.802 |
Token | ose |
Token ID | 577 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
beard | +3.467 |
netflix | +3.261 |
�� | +3.159 |
Noir | +2.972 |
Hulk | +2.812 |
Neg logit contributions | |
Sabha | -6.686 |
bane | -6.127 |
conn | -5.482 |
Uz | -5.075 |
ader | -5.008 |
Token | - |
Token ID | 532 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Sabha | +0.083 |
bane | +0.077 |
conn | +0.066 |
ader | +0.059 |
Loading | +0.059 |
Neg logit contributions | |
beard | -0.082 |
�� | -0.077 |
netflix | -0.076 |
姫 | -0.072 |
Noir | -0.072 |
Token | Message |
Token ID | 12837 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Sabha | +1.716 |
bane | +1.594 |
conn | +1.370 |
Loading | +1.250 |
ader | +1.244 |
Neg logit contributions | |
beard | -1.631 |
�� | -1.527 |
netflix | -1.513 |
姫 | -1.442 |
Noir | -1.413 |
Token | " |
Token ID | 366 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
beard | +4.736 |
�� | +4.462 |
netflix | +4.455 |
Noir | +4.206 |
姫 | +4.075 |
Neg logit contributions | |
Sabha | -5.774 |
bane | -5.342 |
conn | -4.559 |
ader | -4.176 |
Loading | -4.147 |
Token | Screen |
Token ID | 23901 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Sabha | +4.375 |
bane | +4.079 |
conn | +3.577 |
Loading | +3.362 |
ader | +3.265 |
Neg logit contributions | |
beard | -3.758 |
�� | -3.557 |
netflix | -3.484 |
姫 | -3.349 |
Noir | -3.239 |
Token | resolution |
Token ID | 6323 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
beard | +4.489 |
netflix | +4.054 |
Noir | +3.986 |
�� | +3.943 |
姫 | +3.725 |
Neg logit contributions | |
Sabha | -5.453 |
bane | -5.094 |
conn | -4.442 |
Uz | -4.047 |
ader | -3.918 |
Token | is |
Token ID | 318 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
beard | +1.131 |
netflix | +1.048 |
�� | +1.021 |
Noir | +0.994 |
姫 | +0.969 |
Neg logit contributions | |
Sabha | -1.333 |
bane | -1.228 |
conn | -1.067 |
ader | -0.963 |
Uz | -0.960 |
Token | set |
Token ID | 900 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
beard | +3.844 |
netflix | +3.552 |
Noir | +3.460 |
�� | +3.337 |
姫 | +3.226 |
Neg logit contributions | |
Sabha | -4.906 |
bane | -4.541 |
conn | -4.017 |
ader | -3.539 |
Uz | -3.521 |
Token | to |
Token ID | 284 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
beard | +3.046 |
netflix | +2.832 |
Noir | +2.694 |
�� | +2.666 |
姫 | +2.574 |
Neg logit contributions | |
Sabha | -3.643 |
bane | -3.367 |
conn | -2.896 |
Uz | -2.633 |
ader | -2.625 |
Token | $ |
Token ID | 720 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
beard | +3.407 |
netflix | +3.138 |
�� | +3.040 |
Noir | +3.035 |
姫 | +2.895 |
Neg logit contributions | |
Sabha | -4.028 |
bane | -3.740 |
conn | -3.199 |
ader | -2.887 |
Loading | -2.847 |
Token | pl |
Token ID | 489 |
Feature activation | +2.89e-03 |
Pos logit contributions | |
Sabha | +2.668 |
bane | +2.484 |
conn | +2.179 |
ader | +2.019 |
Loading | +2.006 |
Neg logit contributions | |
beard | -1.814 |
netflix | -1.659 |
�� | -1.650 |
姫 | -1.546 |
Noir | -1.531 |
Token | i |
Token ID | 72 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
Sabha | +0.025 |
bane | +0.023 |
conn | +0.020 |
Uz | +0.018 |
Loading | +0.018 |
Neg logit contributions | |
beard | -0.019 |
netflix | -0.018 |
�� | -0.017 |
Noir | -0.017 |
姫 | -0.017 |
Token | Live |
Token ID | 7547 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
beard | +0.253 |
netflix | +0.234 |
�� | +0.234 |
姫 | +0.222 |
Noir | +0.221 |
Neg logit contributions | |
Sabha | -0.284 |
bane | -0.264 |
conn | -0.227 |
ader | -0.207 |
Loading | -0.205 |
Token | will |
Token ID | 481 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
beard | +2.443 |
netflix | +2.246 |
�� | +2.202 |
Noir | +2.148 |
姫 | +2.093 |
Neg logit contributions | |
Sabha | -2.743 |
bane | -2.567 |
conn | -2.213 |
Loading | -2.003 |
ader | -2.002 |
Token | have |
Token ID | 423 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
beard | +1.660 |
netflix | +1.537 |
�� | +1.512 |
Noir | +1.427 |
姫 | +1.426 |
Neg logit contributions | |
Sabha | -1.993 |
bane | -1.848 |
conn | -1.602 |
Loading | -1.477 |
ader | -1.459 |
Token | more |
Token ID | 517 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
beard | +1.425 |
netflix | +1.331 |
�� | +1.322 |
Noir | +1.254 |
姫 | +1.246 |
Neg logit contributions | |
Sabha | -1.582 |
bane | -1.482 |
conn | -1.273 |
ader | -1.151 |
Loading | -1.146 |
Token | success |
Token ID | 1943 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
beard | +4.680 |
netflix | +4.345 |
heels | +4.140 |
Noir | +4.120 |
�� | +4.070 |
Neg logit contributions | |
Sabha | -5.306 |
bane | -5.110 |
conn | -4.393 |
Loading | -4.017 |
ader | -3.968 |
Token | with |
Token ID | 351 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
beard | +4.931 |
netflix | +4.582 |
Noir | +4.325 |
heels | +4.297 |
�� | +4.284 |
Neg logit contributions | |
Sabha | -5.366 |
bane | -5.134 |
conn | -4.349 |
Loading | -3.932 |
ader | -3.893 |
Token | its |
Token ID | 663 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
beard | +1.072 |
netflix | +1.003 |
�� | +0.998 |
Noir | +0.944 |
姫 | +0.942 |
Neg logit contributions | |
Sabha | -1.148 |
bane | -1.070 |
conn | -0.916 |
ader | -0.828 |
Loading | -0.826 |
Token | Indian |
Token ID | 3942 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
beard | +1.605 |
netflix | +1.484 |
�� | +1.471 |
Noir | +1.414 |
姫 | +1.387 |
Neg logit contributions | |
Sabha | -1.841 |
bane | -1.723 |
conn | -1.487 |
Loading | -1.350 |
ader | -1.345 |
Token | viewership |
Token ID | 48347 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
beard | +1.634 |
netflix | +1.513 |
�� | +1.505 |
Noir | +1.451 |
姫 | +1.410 |
Neg logit contributions | |
Sabha | -1.917 |
bane | -1.800 |
conn | -1.542 |
Loading | -1.416 |
ader | -1.408 |