Token | equipped |
Token ID | 10911 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Kinnikuman | +0.588 |
scale | +0.561 |
�� | +0.527 |
cially | +0.519 |
utton | +0.509 |
Neg logit contributions | |
anan | -0.739 |
lie | -0.713 |
pell | -0.707 |
condem | -0.705 |
fug | -0.700 |
Token | with |
Token ID | 351 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Kinnikuman | +1.145 |
scale | +1.089 |
�� | +1.009 |
cially | +1.009 |
utton | +0.968 |
Neg logit contributions | |
anan | -1.621 |
pell | -1.568 |
lie | -1.558 |
condem | -1.557 |
fug | -1.543 |
Token | AMD |
Token ID | 10324 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Kinnikuman | +2.517 |
scale | +2.413 |
�� | +2.270 |
cially | +2.235 |
utton | +2.192 |
Neg logit contributions | |
anan | -3.096 |
lie | -2.987 |
pell | -2.975 |
condem | -2.955 |
fug | -2.925 |
Token | 's |
Token ID | 338 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Kinnikuman | +0.810 |
scale | +0.776 |
�� | +0.731 |
cially | +0.718 |
utton | +0.704 |
Neg logit contributions | |
anan | -0.991 |
lie | -0.958 |
pell | -0.952 |
condem | -0.947 |
fug | -0.939 |
Token | 28 |
Token ID | 2579 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
Kinnikuman | +0.702 |
scale | +0.673 |
�� | +0.634 |
cially | +0.626 |
utton | +0.615 |
Neg logit contributions | |
anan | -0.783 |
lie | -0.758 |
pell | -0.751 |
condem | -0.747 |
fug | -0.745 |
Token | nm |
Token ID | 21533 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Kinnikuman | +0.314 |
scale | +0.282 |
�� | +0.253 |
cially | +0.251 |
utton | +0.241 |
Neg logit contributions | |
anan | -0.815 |
lie | -0.796 |
pell | -0.793 |
condem | -0.787 |
fug | -0.785 |
Token | Radeon |
Token ID | 13082 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Kinnikuman | +6.714 |
scale | +6.559 |
�� | +6.270 |
cially | +5.971 |
utton | +5.750 |
Neg logit contributions | |
anan | -7.408 |
lie | -7.058 |
condem | -7.015 |
pell | -7.007 |
fug | -6.805 |
Token | HD |
Token ID | 5572 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Kinnikuman | +1.640 |
scale | +1.552 |
�� | +1.434 |
cially | +1.380 |
utton | +1.325 |
Neg logit contributions | |
anan | -3.476 |
lie | -3.381 |
pell | -3.370 |
condem | -3.364 |
fug | -3.334 |
Token | 78 |
Token ID | 8699 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Kinnikuman | +0.436 |
scale | +0.421 |
�� | +0.400 |
cially | +0.388 |
utton | +0.382 |
Neg logit contributions | |
anan | -0.478 |
lie | -0.460 |
pell | -0.459 |
condem | -0.457 |
fug | -0.452 |
Token | 70 |
Token ID | 2154 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Kinnikuman | +1.827 |
scale | +1.750 |
�� | +1.669 |
cially | +1.655 |
utton | +1.625 |
Neg logit contributions | |
anan | -1.488 |
lie | -1.432 |
pell | -1.420 |
condem | -1.394 |
fug | -1.390 |
Token | GPU |
Token ID | 11362 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
Kinnikuman | +2.580 |
scale | +2.495 |
�� | +2.359 |
cially | +2.307 |
utton | +2.268 |
Neg logit contributions | |
anan | -2.826 |
lie | -2.719 |
pell | -2.707 |
condem | -2.695 |
fug | -2.672 |
Token | Op |
Token ID | 18257 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
anan | +1.154 |
lie | +1.124 |
pell | +1.104 |
fug | +1.083 |
condem | +1.083 |
Neg logit contributions | |
Kinnikuman | -1.043 |
scale | -0.987 |
�� | -0.949 |
cially | -0.931 |
utton | -0.908 |
Token | Sick |
Token ID | 32181 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
Kinnikuman | +1.055 |
scale | +1.009 |
�� | +0.949 |
cially | +0.934 |
utton | +0.916 |
Neg logit contributions | |
anan | -1.296 |
lie | -1.253 |
pell | -1.244 |
condem | -1.238 |
fug | -1.229 |
Token | - |
Token ID | 12 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Kinnikuman | +4.609 |
scale | +4.501 |
�� | +4.253 |
cially | +4.091 |
utton | +4.082 |
Neg logit contributions | |
anan | -4.597 |
condem | -4.488 |
fug | -4.400 |
pell | -4.399 |
lie | -4.388 |
Token | Ant |
Token ID | 13217 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Kinnikuman | +0.836 |
scale | +0.801 |
�� | +0.756 |
cially | +0.745 |
utton | +0.730 |
Neg logit contributions | |
anan | -0.947 |
lie | -0.915 |
pell | -0.907 |
condem | -0.902 |
fug | -0.895 |
Token | s |
Token ID | 82 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
Kinnikuman | +0.919 |
scale | +0.887 |
�� | +0.838 |
cially | +0.829 |
utton | +0.815 |
Neg logit contributions | |
anan | -0.863 |
lie | -0.830 |
pell | -0.824 |
condem | -0.821 |
fug | -0.814 |
Token | Dad |
Token ID | 17415 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
Kinnikuman | +2.754 |
scale | +2.652 |
�� | +2.504 |
cially | +2.476 |
utton | +2.442 |
Neg logit contributions | |
anan | -2.770 |
condem | -2.657 |
lie | -2.636 |
pell | -2.619 |
fug | -2.615 |
Token | A |
Token ID | 317 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Kinnikuman | +6.430 |
scale | +6.298 |
�� | +5.882 |
cially | +5.801 |
cade | +5.752 |
Neg logit contributions | |
anan | -6.828 |
condem | -6.788 |
fug | -6.659 |
pell | -6.505 |
lie | -6.494 |
Token | Rob |
Token ID | 3851 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Kinnikuman | +1.216 |
scale | +1.173 |
�� | +1.114 |
cially | +1.105 |
utton | +1.088 |
Neg logit contributions | |
anan | -0.972 |
condem | -0.934 |
lie | -0.934 |
pell | -0.926 |
fug | -0.919 |
Token | ber |
Token ID | 527 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
anan | +0.961 |
lie | +0.920 |
pell | +0.909 |
condem | +0.894 |
fug | +0.887 |
Neg logit contributions | |
Kinnikuman | -1.261 |
scale | -1.209 |
�� | -1.158 |
cially | -1.145 |
utton | -1.115 |
Token | - |
Token ID | 12 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Kinnikuman | +1.142 |
scale | +1.097 |
�� | +1.039 |
cially | +1.025 |
utton | +1.006 |
Neg logit contributions | |
anan | -1.142 |
lie | -1.101 |
pell | -1.092 |
condem | -1.085 |
fug | -1.077 |
Token | 08 |
Token ID | 2919 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Kinnikuman | +0.164 |
scale | +0.156 |
�� | +0.149 |
cially | +0.146 |
utton | +0.143 |
Neg logit contributions | |
anan | -0.183 |
lie | -0.177 |
pell | -0.175 |
condem | -0.173 |
fug | -0.172 |
Token | K |
Token ID | 42 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Kinnikuman | +0.518 |
scale | +0.491 |
�� | +0.469 |
cially | +0.459 |
utton | +0.450 |
Neg logit contributions | |
anan | -0.520 |
lie | -0.503 |
pell | -0.497 |
condem | -0.490 |
fug | -0.488 |
Token | ch |
Token ID | 354 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Kinnikuman | +2.466 |
scale | +2.396 |
�� | +2.246 |
cially | +2.228 |
utton | +2.191 |
Neg logit contributions | |
anan | -2.526 |
lie | -2.428 |
condem | -2.422 |
pell | -2.420 |
fug | -2.395 |
Token | — |
Token ID | 851 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
anan | +0.232 |
lie | +0.227 |
pell | +0.221 |
fug | +0.219 |
condem | +0.218 |
Neg logit contributions | |
Kinnikuman | -0.243 |
scale | -0.229 |
�� | -0.221 |
cially | -0.215 |
utton | -0.211 |
Token | Dr |
Token ID | 1583 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
anan | +0.716 |
lie | +0.686 |
pell | +0.677 |
condem | +0.677 |
fug | +0.671 |
Neg logit contributions | |
Kinnikuman | -0.777 |
scale | -0.751 |
�� | -0.715 |
cially | -0.702 |
utton | -0.694 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Kinnikuman | +1.975 |
scale | +1.903 |
�� | +1.789 |
cially | +1.786 |
utton | +1.768 |
Neg logit contributions | |
anan | -1.890 |
condem | -1.839 |
pell | -1.832 |
lie | -1.830 |
fug | -1.807 |
Token | Jill |
Token ID | 22772 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
Kinnikuman | +0.765 |
scale | +0.737 |
�� | +0.700 |
cially | +0.691 |
utton | +0.679 |
Neg logit contributions | |
anan | -0.694 |
lie | -0.667 |
pell | -0.660 |
condem | -0.655 |
fug | -0.650 |
Token | Stein |
Token ID | 15215 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Kinnikuman | +5.158 |
scale | +4.707 |
�� | +4.261 |
cially | +4.182 |
utton | +4.074 |
Neg logit contributions | |
condem | -8.421 |
lie | -8.402 |
fug | -8.361 |
anan | -8.306 |
pell | -8.143 |
Token | � |
Token ID | 8582 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Kinnikuman | +1.413 |
scale | +1.361 |
�� | +1.293 |
cially | +1.278 |
utton | +1.256 |
Neg logit contributions | |
anan | -1.217 |
lie | -1.169 |
pell | -1.162 |
condem | -1.157 |
fug | -1.148 |
Token | � |
Token ID | 234 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
anan | +0.143 |
lie | +0.138 |
pell | +0.137 |
condem | +0.136 |
fug | +0.135 |
Neg logit contributions | |
Kinnikuman | -0.119 |
scale | -0.114 |
cially | -0.105 |
�� | -0.105 |
utton | -0.103 |
Token | � |
Token ID | 119 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Kinnikuman | +0.288 |
scale | +0.273 |
�� | +0.254 |
cially | +0.249 |
utton | +0.243 |
Neg logit contributions | |
anan | -0.468 |
lie | -0.454 |
pell | -0.451 |
condem | -0.449 |
fug | -0.446 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
anan | +0.870 |
lie | +0.838 |
pell | +0.826 |
condem | +0.820 |
fug | +0.812 |
Neg logit contributions | |
Kinnikuman | -1.024 |
scale | -0.984 |
�� | -0.937 |
cially | -0.924 |
utton | -0.911 |
Token | able |
Token ID | 540 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Kinnikuman | +1.966 |
scale | +1.865 |
cially | +1.636 |
�� | +1.607 |
utton | +1.588 |
Neg logit contributions | |
anan | -4.717 |
condem | -4.589 |
lie | -4.535 |
pell | -4.512 |
fug | -4.475 |
Token | version |
Token ID | 2196 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Kinnikuman | +0.674 |
scale | +0.645 |
�� | +0.604 |
cially | +0.597 |
utton | +0.586 |
Neg logit contributions | |
anan | -0.815 |
lie | -0.786 |
pell | -0.782 |
condem | -0.780 |
fug | -0.770 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Kinnikuman | +1.900 |
scale | +1.824 |
cially | +1.697 |
utton | +1.675 |
cade | +1.659 |
Neg logit contributions | |
anan | -2.392 |
condem | -2.310 |
lie | -2.293 |
pell | -2.292 |
fug | -2.284 |
Token | Rob |
Token ID | 14350 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
Kinnikuman | +1.179 |
scale | +1.132 |
�� | +1.061 |
cially | +1.047 |
utton | +1.026 |
Neg logit contributions | |
anan | -1.416 |
lie | -1.368 |
pell | -1.360 |
condem | -1.357 |
fug | -1.345 |
Token | C |
Token ID | 327 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
anan | +3.990 |
lie | +3.875 |
pell | +3.794 |
condem | +3.726 |
fug | +3.708 |
Neg logit contributions | |
Kinnikuman | -3.594 |
scale | -3.401 |
�� | -3.324 |
cially | -3.174 |
utton | -3.078 |
Token | estern |
Token ID | 3330 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
Kinnikuman | +2.318 |
scale | +2.249 |
�� | +2.111 |
cially | +2.097 |
utton | +2.091 |
Neg logit contributions | |
anan | -2.278 |
condem | -2.199 |
lie | -2.197 |
pell | -2.178 |
fug | -2.168 |
Token | ino |
Token ID | 2879 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
scale | +4.107 |
Kinnikuman | +4.056 |
cially | +3.949 |
cade | +3.846 |
�� | +3.725 |
Neg logit contributions | |
anan | -9.093 |
condem | -9.037 |
fug | -9.028 |
pell | -8.940 |
lie | -8.739 |
Token | hosts |
Token ID | 11453 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
anan | +1.371 |
lie | +1.331 |
condem | +1.316 |
pell | +1.304 |
fug | +1.289 |
Neg logit contributions | |
Kinnikuman | -1.560 |
scale | -1.510 |
�� | -1.426 |
cially | -1.408 |
utton | -1.386 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Kinnikuman | +0.782 |
scale | +0.749 |
�� | +0.705 |
cially | +0.695 |
utton | +0.681 |
Neg logit contributions | |
anan | -0.917 |
lie | -0.886 |
pell | -0.880 |
condem | -0.875 |
fug | -0.868 |
Token | jam |
Token ID | 16853 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
anan | +0.695 |
lie | +0.669 |
pell | +0.662 |
condem | +0.660 |
fug | +0.656 |
Neg logit contributions | |
Kinnikuman | -0.874 |
scale | -0.845 |
�� | -0.804 |
cially | -0.793 |
utton | -0.784 |
Token | packed |
Token ID | 11856 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Kinnikuman | +0.917 |
scale | +0.888 |
�� | +0.846 |
cially | +0.838 |
utton | +0.825 |
Neg logit contributions | |
anan | -0.654 |
lie | -0.625 |
pell | -0.618 |
condem | -0.616 |
fug | -0.608 |
Token | Flynn |
Token ID | 14654 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Kinnikuman | +0.688 |
scale | +0.661 |
�� | +0.645 |
cially | +0.628 |
utton | +0.618 |
Neg logit contributions | |
anan | -0.433 |
lie | -0.415 |
pell | -0.411 |
fug | -0.404 |
condem | -0.395 |
Token | announced |
Token ID | 3414 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Kinnikuman | +0.613 |
scale | +0.589 |
�� | +0.558 |
cially | +0.550 |
utton | +0.540 |
Neg logit contributions | |
anan | -0.617 |
lie | -0.595 |
pell | -0.590 |
condem | -0.586 |
fug | -0.582 |
Token | that |
Token ID | 326 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
Kinnikuman | +2.296 |
scale | +2.191 |
�� | +2.018 |
cially | +2.009 |
utton | +1.968 |
Neg logit contributions | |
anan | -3.342 |
lie | -3.222 |
condem | -3.204 |
pell | -3.203 |
fug | -3.165 |
Token | Jen |
Token ID | 13364 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
Kinnikuman | +0.539 |
scale | +0.515 |
�� | +0.483 |
cially | +0.474 |
utton | +0.464 |
Neg logit contributions | |
anan | -0.742 |
lie | -0.721 |
pell | -0.715 |
condem | -0.711 |
fug | -0.707 |
Token | was |
Token ID | 373 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Kinnikuman | +0.695 |
scale | +0.669 |
�� | +0.632 |
cially | +0.624 |
utton | +0.616 |
Neg logit contributions | |
anan | -0.665 |
lie | -0.642 |
condem | -0.636 |
pell | -0.635 |
fug | -0.627 |
Token | pregnant |
Token ID | 10423 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
Kinnikuman | +1.767 |
scale | +1.696 |
�� | +1.603 |
cially | +1.581 |
utton | +1.552 |
Neg logit contributions | |
anan | -1.855 |
lie | -1.790 |
pell | -1.776 |
condem | -1.765 |
fug | -1.752 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Kinnikuman | +5.407 |
scale | +5.087 |
cially | +4.759 |
�� | +4.724 |
utton | +4.689 |
Neg logit contributions | |
anan | -7.606 |
condem | -7.418 |
fug | -7.290 |
pell | -7.280 |
lie | -7.254 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Kinnikuman | +1.108 |
scale | +1.063 |
�� | +1.019 |
cially | +0.997 |
utton | +0.979 |
Neg logit contributions | |
anan | -1.187 |
lie | -1.153 |
pell | -1.135 |
condem | -1.118 |
fug | -1.117 |
Token | and |
Token ID | 290 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
anan | +1.393 |
lie | +1.350 |
pell | +1.334 |
condem | +1.325 |
fug | +1.313 |
Neg logit contributions | |
Kinnikuman | -1.516 |
scale | -1.458 |
�� | -1.386 |
cially | -1.359 |
utton | -1.338 |
Token | his |
Token ID | 465 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Kinnikuman | +0.623 |
scale | +0.596 |
�� | +0.561 |
cially | +0.552 |
utton | +0.541 |
Neg logit contributions | |
anan | -0.764 |
lie | -0.739 |
pell | -0.733 |
condem | -0.729 |
fug | -0.724 |
Token | wife |
Token ID | 3656 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
anan | +1.033 |
lie | +1.012 |
pell | +1.002 |
fug | +0.989 |
condem | +0.977 |
Neg logit contributions | |
Kinnikuman | -1.236 |
scale | -1.193 |
�� | -1.146 |
cially | -1.126 |
utton | -1.110 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
anan | +0.264 |
lie | +0.256 |
pell | +0.254 |
condem | +0.253 |
fug | +0.252 |
Neg logit contributions | |
Kinnikuman | -0.254 |
scale | -0.245 |
�� | -0.232 |
cially | -0.229 |
utton | -0.226 |
Token | brands |
Token ID | 11394 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Kinnikuman | +0.467 |
scale | +0.448 |
�� | +0.421 |
cially | +0.415 |
utton | +0.409 |
Neg logit contributions | |
anan | -0.521 |
lie | -0.506 |
pell | -0.499 |
condem | -0.494 |
fug | -0.493 |
Token | through |
Token ID | 832 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Kinnikuman | +1.052 |
scale | +1.009 |
�� | +0.953 |
cially | +0.940 |
utton | +0.922 |
Neg logit contributions | |
anan | -1.127 |
lie | -1.085 |
pell | -1.077 |
condem | -1.071 |
fug | -1.061 |
Token | its |
Token ID | 663 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
anan | +1.112 |
lie | +1.082 |
pell | +1.072 |
fug | +1.060 |
condem | +1.052 |
Neg logit contributions | |
Kinnikuman | -1.094 |
scale | -1.048 |
�� | -1.016 |
cially | -0.989 |
utton | -0.973 |
Token | Philip |
Token ID | 14576 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Kinnikuman | +1.806 |
scale | +1.743 |
�� | +1.658 |
cially | +1.638 |
utton | +1.610 |
Neg logit contributions | |
anan | -1.468 |
lie | -1.408 |
pell | -1.396 |
condem | -1.386 |
fug | -1.373 |
Token | Morris |
Token ID | 14433 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
Kinnikuman | +1.331 |
scale | +1.264 |
�� | +1.171 |
cially | +1.150 |
utton | +1.122 |
Neg logit contributions | |
anan | -2.194 |
lie | -2.125 |
pell | -2.118 |
condem | -2.110 |
fug | -2.095 |
Token | USA |
Token ID | 4916 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Kinnikuman | +6.710 |
scale | +6.479 |
�� | +6.219 |
cially | +6.157 |
cade | +5.996 |
Neg logit contributions | |
anan | -6.249 |
lie | -5.924 |
pell | -5.917 |
condem | -5.904 |
fug | -5.786 |
Token | unit |
Token ID | 4326 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
anan | +0.212 |
lie | +0.204 |
pell | +0.202 |
condem | +0.201 |
fug | +0.200 |
Neg logit contributions | |
Kinnikuman | -0.272 |
scale | -0.260 |
�� | -0.247 |
cially | -0.245 |
utton | -0.242 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
anan | +0.286 |
lie | +0.277 |
pell | +0.275 |
condem | +0.272 |
fug | +0.272 |
Neg logit contributions | |
Kinnikuman | -0.292 |
scale | -0.280 |
�� | -0.267 |
cially | -0.264 |
utton | -0.259 |
Token | plunged |
Token ID | 31460 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
anan | +0.265 |
lie | +0.258 |
pell | +0.252 |
condem | +0.252 |
fug | +0.251 |
Neg logit contributions | |
Kinnikuman | -0.320 |
scale | -0.309 |
�� | -0.296 |
cially | -0.291 |
utton | -0.286 |
Token | more |
Token ID | 517 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
anan | +0.697 |
lie | +0.675 |
pell | +0.671 |
condem | +0.664 |
fug | +0.662 |
Neg logit contributions | |
Kinnikuman | -0.711 |
scale | -0.679 |
�� | -0.656 |
cially | -0.638 |
utton | -0.626 |
Token | www |
Token ID | 2503 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
lie | +1.529 |
anan | +1.507 |
pell | +1.408 |
fug | +1.236 |
sen | +1.150 |
Neg logit contributions | |
Kinnikuman | -4.154 |
�� | -3.983 |
scale | -3.724 |
ザ | -3.698 |
utton | -3.659 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
anan | +0.429 |
lie | +0.423 |
pell | +0.411 |
fug | +0.395 |
Gott | +0.366 |
Neg logit contributions | |
Kinnikuman | -0.611 |
�� | -0.588 |
scale | -0.573 |
cially | -0.549 |
utton | -0.540 |
Token | bel |
Token ID | 6667 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Kinnikuman | +0.834 |
scale | +0.793 |
�� | +0.763 |
cially | +0.746 |
utton | +0.731 |
Neg logit contributions | |
anan | -0.820 |
lie | -0.794 |
pell | -0.785 |
condem | -0.772 |
fug | -0.768 |
Token | fast |
Token ID | 7217 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
anan | +0.476 |
lie | +0.460 |
pell | +0.447 |
fug | +0.431 |
condem | +0.409 |
Neg logit contributions | |
Kinnikuman | -0.700 |
�� | -0.651 |
scale | -0.642 |
cially | -0.609 |
ザ | -0.605 |
Token | te |
Token ID | 660 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
anan | +0.066 |
lie | +0.058 |
pell | +0.055 |
fug | +0.049 |
condem | +0.045 |
Neg logit contributions | |
Kinnikuman | -0.386 |
scale | -0.368 |
�� | -0.366 |
cially | -0.355 |
utton | -0.351 |
Token | legraph |
Token ID | 16606 |
Feature activation | +9.34e+00 |
Pos logit contributions | |
anan | +0.697 |
lie | +0.673 |
pell | +0.663 |
fug | +0.630 |
condem | +0.599 |
Neg logit contributions | |
Kinnikuman | -0.728 |
�� | -0.672 |
scale | -0.657 |
ザ | -0.619 |
cially | -0.616 |
Token | . |
Token ID | 13 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
scale | +5.855 |
Kinnikuman | +5.754 |
cially | +5.242 |
utton | +5.217 |
cade | +5.215 |
Neg logit contributions | |
condem | -7.637 |
anan | -7.125 |
fug | -6.912 |
pell | -6.818 |
prosec | -6.715 |
Token | co |
Token ID | 1073 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Kinnikuman | +0.080 |
�� | +0.076 |
scale | +0.075 |
cially | +0.072 |
utton | +0.072 |
Neg logit contributions | |
anan | -0.049 |
lie | -0.048 |
pell | -0.047 |
fug | -0.044 |
condem | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
Kinnikuman | +1.946 |
scale | +1.869 |
�� | +1.791 |
cially | +1.756 |
utton | +1.727 |
Neg logit contributions | |
anan | -1.649 |
lie | -1.587 |
pell | -1.571 |
condem | -1.545 |
fug | -1.544 |
Token | uk |
Token ID | 2724 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Kinnikuman | +0.852 |
scale | +0.812 |
�� | +0.801 |
cially | +0.765 |
utton | +0.755 |
Neg logit contributions | |
anan | -0.571 |
lie | -0.548 |
pell | -0.535 |
fug | -0.519 |
condem | -0.493 |
Token | / |
Token ID | 14 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
Kinnikuman | +0.402 |
scale | +0.384 |
�� | +0.383 |
cially | +0.368 |
utton | +0.361 |
Neg logit contributions | |
anan | -0.251 |
lie | -0.243 |
pell | -0.237 |
fug | -0.227 |
condem | -0.218 |
Token | musical |
Token ID | 10530 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Kinnikuman | +3.130 |
scale | +3.027 |
�� | +2.817 |
cially | +2.793 |
utton | +2.746 |
Neg logit contributions | |
anan | -3.308 |
lie | -3.180 |
condem | -3.158 |
pell | -3.155 |
fug | -3.078 |
Token | interpretations |
Token ID | 26146 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
anan | +0.625 |
lie | +0.603 |
fug | +0.599 |
pell | +0.598 |
condem | +0.593 |
Neg logit contributions | |
Kinnikuman | -0.765 |
scale | -0.734 |
�� | -0.706 |
cially | -0.694 |
utton | -0.685 |
Token | of |
Token ID | 286 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Kinnikuman | +1.241 |
scale | +1.185 |
�� | +1.103 |
cially | +1.093 |
utton | +1.066 |
Neg logit contributions | |
anan | -1.631 |
lie | -1.575 |
pell | -1.561 |
condem | -1.557 |
fug | -1.542 |
Token | the |
Token ID | 262 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
Kinnikuman | +0.350 |
scale | +0.337 |
�� | +0.319 |
cially | +0.314 |
utton | +0.309 |
Neg logit contributions | |
anan | -0.373 |
lie | -0.361 |
pell | -0.358 |
condem | -0.355 |
fug | -0.354 |
Token | M |
Token ID | 337 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Kinnikuman | +0.468 |
scale | +0.450 |
�� | +0.425 |
cially | +0.419 |
utton | +0.410 |
Neg logit contributions | |
anan | -0.566 |
lie | -0.548 |
pell | -0.545 |
fug | -0.542 |
condem | -0.540 |
Token | oom |
Token ID | 4207 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
Kinnikuman | +1.572 |
scale | +1.501 |
�� | +1.418 |
cially | +1.393 |
utton | +1.363 |
Neg logit contributions | |
anan | -1.874 |
lie | -1.814 |
pell | -1.800 |
condem | -1.784 |
fug | -1.775 |
Token | ins |
Token ID | 1040 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
Kinnikuman | +7.013 |
scale | +7.008 |
utton | +6.435 |
cially | +6.389 |
cade | +6.375 |
Neg logit contributions | |
condem | -5.692 |
anan | -5.660 |
fug | -5.521 |
lie | -5.488 |
pell | -5.446 |
Token | have |
Token ID | 423 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
anan | +0.045 |
lie | +0.044 |
pell | +0.044 |
fug | +0.043 |
condem | +0.043 |
Neg logit contributions | |
Kinnikuman | -0.042 |
scale | -0.040 |
�� | -0.039 |
cially | -0.038 |
utton | -0.037 |
Token | been |
Token ID | 587 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Kinnikuman | +0.143 |
scale | +0.137 |
�� | +0.130 |
cially | +0.127 |
utton | +0.126 |
Neg logit contributions | |
anan | -0.148 |
lie | -0.143 |
pell | -0.142 |
condem | -0.142 |
fug | -0.141 |
Token | made |
Token ID | 925 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Kinnikuman | +0.645 |
scale | +0.621 |
�� | +0.589 |
cially | +0.579 |
utton | +0.571 |
Neg logit contributions | |
anan | -0.627 |
lie | -0.604 |
pell | -0.600 |
condem | -0.597 |
fug | -0.593 |
Token | for |
Token ID | 329 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
anan | +1.229 |
lie | +1.194 |
pell | +1.192 |
fug | +1.182 |
condem | +1.172 |
Neg logit contributions | |
Kinnikuman | -1.224 |
scale | -1.174 |
�� | -1.126 |
cially | -1.098 |
utton | -1.087 |
Token | is |
Token ID | 318 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
Kinnikuman | +1.624 |
scale | +1.564 |
�� | +1.459 |
cially | +1.457 |
utton | +1.427 |
Neg logit contributions | |
anan | -1.767 |
lie | -1.696 |
pell | -1.678 |
condem | -1.675 |
fug | -1.655 |
Token | determined |
Token ID | 5295 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Kinnikuman | +0.052 |
scale | +0.050 |
�� | +0.048 |
cially | +0.047 |
utton | +0.046 |
Neg logit contributions | |
anan | -0.047 |
lie | -0.045 |
pell | -0.045 |
condem | -0.045 |
fug | -0.045 |
Token | by |
Token ID | 416 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
anan | +0.853 |
lie | +0.821 |
pell | +0.815 |
condem | +0.811 |
fug | +0.803 |
Neg logit contributions | |
Kinnikuman | -0.839 |
scale | -0.808 |
�� | -0.763 |
cially | -0.754 |
utton | -0.739 |
Token | how |
Token ID | 703 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
anan | +0.484 |
lie | +0.469 |
pell | +0.467 |
condem | +0.464 |
fug | +0.463 |
Neg logit contributions | |
Kinnikuman | -0.415 |
scale | -0.394 |
�� | -0.377 |
cially | -0.367 |
utton | -0.359 |
Token | the |
Token ID | 262 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
anan | +1.799 |
pell | +1.737 |
fug | +1.735 |
lie | +1.730 |
condem | +1.729 |
Neg logit contributions | |
Kinnikuman | -1.977 |
scale | -1.907 |
�� | -1.841 |
utton | -1.767 |
cially | -1.766 |
Token | carc |
Token ID | 36756 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
Kinnikuman | +0.326 |
scale | +0.310 |
�� | +0.294 |
cially | +0.287 |
utton | +0.280 |
Neg logit contributions | |
anan | -0.429 |
lie | -0.416 |
condem | -0.415 |
pell | -0.414 |
fug | -0.413 |
Token | ass |
Token ID | 562 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Kinnikuman | +7.092 |
scale | +7.014 |
cially | +6.532 |
cade | +6.444 |
utton | +6.418 |
Neg logit contributions | |
anan | -5.629 |
condem | -5.550 |
fug | -5.500 |
lie | -5.365 |
pell | -5.117 |
Token | is |
Token ID | 318 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Kinnikuman | +2.272 |
scale | +2.184 |
�� | +2.061 |
cially | +2.036 |
utton | +1.998 |
Neg logit contributions | |
anan | -2.351 |
lie | -2.264 |
pell | -2.246 |
condem | -2.233 |
fug | -2.215 |
Token | scored |
Token ID | 7781 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Kinnikuman | +1.357 |
scale | +1.304 |
�� | +1.236 |
cially | +1.218 |
utton | +1.197 |
Neg logit contributions | |
anan | -1.329 |
lie | -1.281 |
pell | -1.271 |
condem | -1.263 |
fug | -1.253 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Kinnikuman | +0.936 |
scale | +0.901 |
�� | +0.853 |
cially | +0.842 |
utton | +0.827 |
Neg logit contributions | |
anan | -0.910 |
lie | -0.876 |
pell | -0.868 |
condem | -0.864 |
fug | -0.856 |
Token | things |
Token ID | 1243 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Kinnikuman | +0.738 |
scale | +0.709 |
�� | +0.673 |
cially | +0.663 |
utton | +0.651 |
Neg logit contributions | |
anan | -0.727 |
lie | -0.702 |
pell | -0.696 |
condem | -0.692 |
fug | -0.688 |
Token | books |
Token ID | 3835 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Kinnikuman | +1.095 |
scale | +1.055 |
�� | +1.005 |
cially | +0.989 |
utton | +0.975 |
Neg logit contributions | |
anan | -0.979 |
lie | -0.945 |
pell | -0.933 |
condem | -0.931 |
fug | -0.923 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
anan | +1.265 |
lie | +1.244 |
pell | +1.220 |
condem | +1.203 |
fug | +1.191 |
Neg logit contributions | |
Kinnikuman | -1.348 |
scale | -1.283 |
�� | -1.237 |
cially | -1.203 |
utton | -1.186 |
Token | D |
Token ID | 360 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Kinnikuman | +0.069 |
scale | +0.066 |
�� | +0.065 |
cially | +0.063 |
utton | +0.062 |
Neg logit contributions | |
anan | -0.075 |
lie | -0.074 |
pell | -0.071 |
fug | -0.070 |
condem | -0.069 |
Token | ines |
Token ID | 1127 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Kinnikuman | +0.763 |
scale | +0.704 |
�� | +0.649 |
cially | +0.627 |
utton | +0.602 |
Neg logit contributions | |
anan | -1.724 |
lie | -1.681 |
pell | -1.668 |
condem | -1.654 |
fug | -1.649 |
Token | h |
Token ID | 71 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Kinnikuman | +0.777 |
�� | +0.723 |
scale | +0.722 |
cially | +0.679 |
utton | +0.678 |
Neg logit contributions | |
anan | -0.573 |
lie | -0.558 |
pell | -0.548 |
fug | -0.529 |
condem | -0.514 |
Token | Sham |
Token ID | 27957 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
Kinnikuman | +0.445 |
scale | +0.429 |
�� | +0.410 |
cially | +0.402 |
utton | +0.395 |
Neg logit contributions | |
anan | -0.423 |
lie | -0.407 |
pell | -0.403 |
condem | -0.399 |
fug | -0.397 |
Token | d |
Token ID | 67 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
scale | +6.759 |
Kinnikuman | +6.613 |
utton | +6.246 |
cade | +6.146 |
cially | +6.131 |
Neg logit contributions | |
condem | -5.608 |
anan | -5.533 |
fug | -5.392 |
lie | -5.294 |
pell | -5.159 |
Token | as |
Token ID | 292 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Kinnikuman | +2.578 |
scale | +2.505 |
�� | +2.395 |
cially | +2.375 |
utton | +2.344 |
Neg logit contributions | |
anan | -1.484 |
lie | -1.411 |
pell | -1.398 |
condem | -1.392 |
fug | -1.374 |
Token | ani |
Token ID | 3216 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Kinnikuman | +0.167 |
scale | +0.160 |
�� | +0.154 |
cially | +0.151 |
utton | +0.148 |
Neg logit contributions | |
anan | -0.124 |
lie | -0.119 |
pell | -0.118 |
condem | -0.115 |
fug | -0.114 |
Token | : |
Token ID | 25 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
anan | +0.019 |
lie | +0.018 |
pell | +0.018 |
condem | +0.017 |
fug | +0.017 |
Neg logit contributions | |
Kinnikuman | -0.021 |
scale | -0.020 |
�� | -0.019 |
cially | -0.019 |
utton | -0.018 |
Token | It |
Token ID | 632 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
anan | +0.228 |
lie | +0.222 |
pell | +0.216 |
fug | +0.215 |
condem | +0.210 |
Neg logit contributions | |
Kinnikuman | -0.209 |
scale | -0.201 |
�� | -0.198 |
cially | -0.191 |
utton | -0.190 |
Token | But |
Token ID | 1537 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Kinnikuman | +0.706 |
scale | +0.662 |
�� | +0.637 |
cially | +0.616 |
utton | +0.604 |
Neg logit contributions | |
anan | -0.912 |
lie | -0.891 |
pell | -0.877 |
fug | -0.860 |
condem | -0.857 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Kinnikuman | +0.515 |
scale | +0.492 |
�� | +0.472 |
cially | +0.459 |
utton | +0.451 |
Neg logit contributions | |
anan | -0.536 |
lie | -0.519 |
pell | -0.514 |
condem | -0.512 |
fug | -0.510 |
Token | people |
Token ID | 661 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
anan | +0.119 |
lie | +0.115 |
condem | +0.114 |
pell | +0.114 |
fug | +0.113 |
Neg logit contributions | |
Kinnikuman | -0.126 |
scale | -0.121 |
�� | -0.116 |
cially | -0.114 |
utton | -0.112 |
Token | scoring |
Token ID | 9689 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Kinnikuman | +0.158 |
scale | +0.151 |
�� | +0.145 |
cially | +0.141 |
utton | +0.139 |
Neg logit contributions | |
anan | -0.167 |
lie | -0.162 |
pell | -0.161 |
condem | -0.161 |
fug | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Kinnikuman | +2.170 |
scale | +2.082 |
�� | +1.952 |
cially | +1.935 |
utton | +1.894 |
Neg logit contributions | |
anan | -2.491 |
lie | -2.403 |
pell | -2.382 |
condem | -2.370 |
fug | -2.347 |
Token | carc |
Token ID | 36756 |
Feature activation | +8.97e+00 |
Pos logit contributions | |
Kinnikuman | +1.016 |
scale | +0.975 |
�� | +0.926 |
cially | +0.909 |
utton | +0.892 |
Neg logit contributions | |
anan | -1.082 |
lie | -1.047 |
pell | -1.039 |
condem | -1.034 |
fug | -1.031 |
Token | asses |
Token ID | 13978 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
scale | +7.137 |
Kinnikuman | +7.113 |
cially | +6.676 |
cade | +6.577 |
utton | +6.553 |
Neg logit contributions | |
condem | -5.351 |
anan | -5.215 |
fug | -5.112 |
lie | -4.988 |
pell | -4.855 |
Token | are |
Token ID | 389 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Kinnikuman | +2.748 |
scale | +2.674 |
cially | +2.489 |
�� | +2.470 |
utton | +2.424 |
Neg logit contributions | |
anan | -3.052 |
lie | -2.912 |
pell | -2.886 |
condem | -2.883 |
fug | -2.853 |
Token | employees |
Token ID | 4409 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
anan | +1.282 |
fug | +1.253 |
condem | +1.250 |
lie | +1.248 |
pell | +1.245 |
Neg logit contributions | |
Kinnikuman | -1.476 |
scale | -1.420 |
�� | -1.356 |
utton | -1.320 |
cially | -1.308 |
Token | of |
Token ID | 286 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
Kinnikuman | +1.163 |
scale | +1.117 |
�� | +1.040 |
cially | +1.035 |
utton | +1.009 |
Neg logit contributions | |
anan | -1.450 |
lie | -1.400 |
pell | -1.385 |
condem | -1.382 |
fug | -1.369 |
Token | the |
Token ID | 262 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Kinnikuman | +0.647 |
scale | +0.619 |
�� | +0.587 |
cially | +0.576 |
utton | +0.566 |
Neg logit contributions | |
anan | -0.725 |
lie | -0.702 |
pell | -0.696 |
condem | -0.692 |
fug | -0.688 |
Token | official |
Token ID | 1743 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
Kinnikuman | +1.594 |
scale | +1.487 |
�� | +1.421 |
cially | +1.347 |
utton | +1.326 |
Neg logit contributions | |
anan | -2.557 |
lie | -2.477 |
fug | -2.441 |
pell | -2.439 |
condem | -2.420 |
Token | statement |
Token ID | 2643 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Kinnikuman | +5.182 |
scale | +5.057 |
cially | +4.816 |
�� | +4.736 |
utton | +4.694 |
Neg logit contributions | |
anan | -3.615 |
condem | -3.424 |
pell | -3.393 |
lie | -3.374 |
fug | -3.329 |
Token | soon |
Token ID | 2582 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Kinnikuman | +2.179 |
scale | +2.095 |
�� | +1.990 |
cially | +1.953 |
utton | +1.923 |
Neg logit contributions | |
anan | -2.177 |
lie | -2.100 |
pell | -2.084 |
condem | -2.068 |
fug | -2.054 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Kinnikuman | +1.623 |
scale | +1.549 |
�� | +1.526 |
cially | +1.467 |
utton | +1.447 |
Neg logit contributions | |
anan | -1.274 |
lie | -1.234 |
pell | -1.215 |
fug | -1.186 |
condem | -1.162 |
Token | As |
Token ID | 1081 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Kinnikuman | +0.804 |
scale | +0.761 |
�� | +0.704 |
cially | +0.697 |
utton | +0.681 |
Neg logit contributions | |
anan | -1.119 |
lie | -1.085 |
pell | -1.080 |
condem | -1.077 |
fug | -1.066 |
Token | well |
Token ID | 880 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
Kinnikuman | +0.274 |
scale | +0.253 |
�� | +0.248 |
utton | +0.229 |
ザ | +0.228 |
Neg logit contributions | |
anan | -0.378 |
lie | -0.369 |
pell | -0.369 |
fug | -0.363 |
condem | -0.351 |
Token | as |
Token ID | 355 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
Kinnikuman | +4.576 |
scale | +4.503 |
cially | +4.132 |
utton | +3.951 |
cade | +3.869 |
Neg logit contributions | |
condem | -7.980 |
anan | -7.773 |
pell | -7.523 |
lie | -7.437 |
fug | -7.435 |
Token | updates |
Token ID | 5992 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Kinnikuman | +2.409 |
scale | +2.289 |
�� | +2.119 |
cially | +2.092 |
utton | +2.039 |
Neg logit contributions | |
anan | -3.790 |
lie | -3.670 |
condem | -3.645 |
pell | -3.643 |
fug | -3.598 |
Token | regarding |
Token ID | 5115 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Kinnikuman | +2.172 |
scale | +2.084 |
�� | +1.981 |
cially | +1.948 |
utton | +1.915 |
Neg logit contributions | |
anan | -2.124 |
lie | -2.050 |
pell | -2.033 |
condem | -2.018 |
fug | -2.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Kinnikuman | +3.258 |
scale | +3.168 |
cially | +2.897 |
utton | +2.830 |
�� | +2.817 |
Neg logit contributions | |
anan | -4.374 |
condem | -4.294 |
pell | -4.193 |
lie | -4.188 |
fug | -4.117 |
Token | future |
Token ID | 2003 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Kinnikuman | +2.006 |
scale | +1.918 |
�� | +1.865 |
cially | +1.808 |
utton | +1.785 |
Neg logit contributions | |
anan | -1.658 |
lie | -1.611 |
pell | -1.587 |
fug | -1.582 |
condem | -1.564 |
Token | estation |
Token ID | 27364 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Kinnikuman | +0.444 |
scale | +0.423 |
�� | +0.414 |
cially | +0.402 |
utton | +0.390 |
Neg logit contributions | |
anan | -0.324 |
lie | -0.313 |
pell | -0.309 |
fug | -0.297 |
condem | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
anan | +0.869 |
lie | +0.839 |
pell | +0.838 |
condem | +0.829 |
fug | +0.829 |
Neg logit contributions | |
Kinnikuman | -0.979 |
scale | -0.938 |
�� | -0.909 |
cially | -0.886 |
utton | -0.872 |
Token | The |
Token ID | 383 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
anan | +0.280 |
lie | +0.271 |
pell | +0.267 |
fug | +0.265 |
condem | +0.264 |
Neg logit contributions | |
Kinnikuman | -0.265 |
scale | -0.254 |
�� | -0.244 |
cially | -0.238 |
utton | -0.233 |
Token | 39 |
Token ID | 5014 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
anan | +0.051 |
lie | +0.049 |
pell | +0.048 |
condem | +0.048 |
fug | +0.048 |
Neg logit contributions | |
Kinnikuman | -0.057 |
scale | -0.055 |
�� | -0.053 |
cially | -0.052 |
utton | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
Kinnikuman | +0.251 |
scale | +0.243 |
�� | +0.231 |
cially | +0.226 |
utton | +0.222 |
Neg logit contributions | |
anan | -0.254 |
lie | -0.244 |
condem | -0.242 |
pell | -0.242 |
fug | -0.237 |
Token | year |
Token ID | 1941 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
scale | +2.370 |
Kinnikuman | +2.343 |
�� | +2.053 |
utton | +2.032 |
cially | +2.021 |
Neg logit contributions | |
anan | -3.955 |
condem | -3.828 |
lie | -3.794 |
pell | -3.789 |
fug | -3.787 |
Token | - |
Token ID | 12 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Kinnikuman | +5.690 |
scale | +5.478 |
cially | +5.125 |
�� | +5.043 |
utton | +4.879 |
Neg logit contributions | |
anan | -6.749 |
condem | -6.515 |
lie | -6.384 |
pell | -6.351 |
fug | -6.113 |
Token | old |
Token ID | 727 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
Kinnikuman | +0.887 |
scale | +0.789 |
�� | +0.753 |
cially | +0.699 |
utton | +0.674 |
Neg logit contributions | |
anan | -2.410 |
lie | -2.367 |
pell | -2.344 |
fug | -2.304 |
condem | -2.279 |
Token | Australian |
Token ID | 6638 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Kinnikuman | +3.879 |
scale | +3.728 |
�� | +3.514 |
cially | +3.483 |
cade | +3.405 |
Neg logit contributions | |
anan | -3.972 |
lie | -3.831 |
pell | -3.816 |
condem | -3.756 |
fug | -3.685 |
Token | , |
Token ID | 11 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Kinnikuman | +1.473 |
scale | +1.415 |
�� | +1.341 |
cially | +1.323 |
utton | +1.300 |
Neg logit contributions | |
anan | -1.441 |
lie | -1.388 |
pell | -1.377 |
condem | -1.368 |
fug | -1.359 |
Token | who |
Token ID | 508 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
anan | +0.470 |
fug | +0.451 |
pell | +0.451 |
lie | +0.450 |
condem | +0.448 |
Neg logit contributions | |
Kinnikuman | -0.452 |
scale | -0.437 |
�� | -0.413 |
cially | -0.407 |
utton | -0.398 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
anan | +0.401 |
lie | +0.386 |
pell | +0.385 |
condem | +0.383 |
fug | +0.380 |
Neg logit contributions | |
Kinnikuman | -0.356 |
scale | -0.341 |
�� | -0.321 |
cially | -0.317 |
utton | -0.311 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
anan | +0.557 |
lie | +0.556 |
pell | +0.538 |
fug | +0.520 |
Lawyers | +0.487 |
Neg logit contributions | |
Kinnikuman | -0.658 |
�� | -0.639 |
scale | -0.609 |
cially | -0.589 |
utton | -0.577 |
Token | The |
Token ID | 464 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
anan | +0.223 |
lie | +0.219 |
pell | +0.214 |
fug | +0.209 |
condem | +0.207 |
Neg logit contributions | |
Kinnikuman | -0.180 |
scale | -0.168 |
�� | -0.163 |
cially | -0.158 |
utton | -0.154 |
Token | 89 |
Token ID | 9919 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
anan | +0.266 |
lie | +0.259 |
condem | +0.254 |
pell | +0.253 |
fug | +0.253 |
Neg logit contributions | |
Kinnikuman | -0.277 |
scale | -0.265 |
�� | -0.253 |
cially | -0.250 |
utton | -0.244 |
Token | - |
Token ID | 12 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Kinnikuman | +1.119 |
scale | +1.085 |
�� | +1.024 |
cially | +1.001 |
utton | +0.992 |
Neg logit contributions | |
anan | -1.124 |
condem | -1.076 |
pell | -1.067 |
lie | -1.065 |
fug | -1.048 |
Token | year |
Token ID | 1941 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
scale | +1.795 |
Kinnikuman | +1.788 |
�� | +1.464 |
cially | +1.462 |
utton | +1.451 |
Neg logit contributions | |
anan | -4.479 |
condem | -4.384 |
fug | -4.323 |
pell | -4.305 |
lie | -4.234 |
Token | - |
Token ID | 12 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Kinnikuman | +5.763 |
scale | +5.570 |
cially | +5.202 |
�� | +5.122 |
utton | +4.990 |
Neg logit contributions | |
anan | -6.612 |
condem | -6.416 |
lie | -6.261 |
pell | -6.238 |
fug | -6.103 |
Token | old |
Token ID | 727 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
Kinnikuman | +0.836 |
scale | +0.744 |
�� | +0.713 |
cially | +0.661 |
utton | +0.637 |
Neg logit contributions | |
anan | -2.238 |
lie | -2.200 |
pell | -2.177 |
fug | -2.133 |
condem | -2.107 |
Token | said |
Token ID | 531 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Kinnikuman | +3.660 |
scale | +3.527 |
�� | +3.341 |
cially | +3.299 |
cade | +3.228 |
Neg logit contributions | |
anan | -3.637 |
pell | -3.498 |
lie | -3.481 |
condem | -3.418 |
fug | -3.411 |
Token | : |
Token ID | 25 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
anan | +0.303 |
lie | +0.294 |
pell | +0.291 |
condem | +0.289 |
fug | +0.289 |
Neg logit contributions | |
Kinnikuman | -0.328 |
scale | -0.314 |
�� | -0.301 |
cially | -0.296 |
utton | -0.291 |
Token | � |
Token ID | 564 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
anan | +1.122 |
lie | +1.078 |
pell | +1.073 |
condem | +1.068 |
fug | +1.058 |
Neg logit contributions | |
Kinnikuman | -1.045 |
scale | -1.004 |
�� | -0.947 |
cially | -0.934 |
utton | -0.916 |
Token | 8 |
Token ID | 23 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
anan | +0.240 |
lie | +0.231 |
pell | +0.229 |
condem | +0.228 |
fug | +0.226 |
Neg logit contributions | |
Kinnikuman | -0.232 |
scale | -0.223 |
�� | -0.211 |
cially | -0.208 |
utton | -0.204 |
Token | rating |
Token ID | 7955 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Kinnikuman | +1.686 |
scale | +1.633 |
�� | +1.540 |
cially | +1.527 |
utton | +1.512 |
Neg logit contributions | |
anan | -1.383 |
lie | -1.321 |
pell | -1.313 |
condem | -1.295 |
fug | -1.286 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Kinnikuman | +1.659 |
scale | +1.596 |
�� | +1.491 |
cially | +1.483 |
utton | +1.459 |
Neg logit contributions | |
anan | -1.741 |
lie | -1.674 |
pell | -1.658 |
condem | -1.648 |
fug | -1.633 |
Token | The |
Token ID | 383 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Kinnikuman | +0.987 |
scale | +0.952 |
�� | +0.904 |
cially | +0.893 |
utton | +0.877 |
Neg logit contributions | |
anan | -0.868 |
lie | -0.835 |
pell | -0.828 |
condem | -0.822 |
fug | -0.816 |
Token | Bastard |
Token ID | 47209 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
anan | +0.621 |
lie | +0.599 |
pell | +0.590 |
condem | +0.585 |
fug | +0.584 |
Neg logit contributions | |
Kinnikuman | -0.640 |
scale | -0.619 |
�� | -0.590 |
cially | -0.580 |
utton | -0.567 |
Token | Execution |
Token ID | 37497 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Kinnikuman | +2.753 |
scale | +2.605 |
�� | +2.435 |
cially | +2.394 |
cade | +2.369 |
Neg logit contributions | |
anan | -3.398 |
condem | -3.275 |
pell | -3.270 |
lie | -3.268 |
fug | -3.215 |
Token | er |
Token ID | 263 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Kinnikuman | +3.391 |
scale | +3.201 |
�� | +2.871 |
cade | +2.702 |
cially | +2.697 |
Neg logit contributions | |
anan | -8.888 |
lie | -8.595 |
condem | -8.585 |
pell | -8.545 |
fug | -8.416 |
Token | premiered |
Token ID | 44119 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Kinnikuman | +2.555 |
scale | +2.449 |
�� | +2.314 |
cially | +2.284 |
utton | +2.236 |
Neg logit contributions | |
anan | -2.604 |
lie | -2.515 |
pell | -2.500 |
condem | -2.473 |
fug | -2.453 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Kinnikuman | +0.124 |
scale | +0.119 |
�� | +0.113 |
cially | +0.111 |
utton | +0.109 |
Neg logit contributions | |
anan | -0.131 |
lie | -0.127 |
pell | -0.125 |
condem | -0.125 |
fug | -0.124 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
anan | +0.708 |
lie | +0.680 |
pell | +0.673 |
condem | +0.671 |
fug | +0.667 |
Neg logit contributions | |
Kinnikuman | -0.775 |
scale | -0.740 |
�� | -0.712 |
cially | -0.702 |
utton | -0.685 |
Token | . |
Token ID | 13 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Kinnikuman | +1.445 |
scale | +1.396 |
�� | +1.326 |
utton | +1.304 |
cially | +1.302 |
Neg logit contributions | |
anan | -1.506 |
lie | -1.465 |
pell | -1.447 |
condem | -1.432 |
fug | -1.428 |
Token | Monday |
Token ID | 3321 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Kinnikuman | +0.390 |
scale | +0.375 |
�� | +0.359 |
cially | +0.354 |
utton | +0.347 |
Neg logit contributions | |
anan | -0.331 |
lie | -0.320 |
pell | -0.317 |
condem | -0.314 |
fug | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
anan | +1.812 |
lie | +1.733 |
pell | +1.712 |
condem | +1.691 |
fug | +1.685 |
Neg logit contributions | |
Kinnikuman | -2.746 |
scale | -2.646 |
�� | -2.537 |
cially | -2.503 |
utton | -2.451 |
Token | The |
Token ID | 464 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Kinnikuman | +0.186 |
scale | +0.179 |
�� | +0.172 |
cially | +0.168 |
utton | +0.165 |
Neg logit contributions | |
anan | -0.204 |
lie | -0.198 |
pell | -0.194 |
condem | -0.192 |
fug | -0.192 |
Token | 68 |
Token ID | 8257 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
anan | +0.365 |
lie | +0.351 |
condem | +0.346 |
pell | +0.345 |
fug | +0.345 |
Neg logit contributions | |
Kinnikuman | -0.466 |
scale | -0.449 |
�� | -0.428 |
cially | -0.423 |
utton | -0.417 |
Token | - |
Token ID | 12 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Kinnikuman | +1.283 |
scale | +1.240 |
�� | +1.174 |
cially | +1.147 |
utton | +1.121 |
Neg logit contributions | |
anan | -1.467 |
lie | -1.406 |
pell | -1.399 |
condem | -1.394 |
fug | -1.360 |
Token | year |
Token ID | 1941 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
Kinnikuman | +2.252 |
scale | +2.172 |
�� | +1.926 |
cially | +1.917 |
utton | +1.867 |
Neg logit contributions | |
anan | -4.659 |
condem | -4.524 |
lie | -4.511 |
pell | -4.494 |
fug | -4.468 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Kinnikuman | +5.123 |
scale | +4.970 |
cially | +4.590 |
�� | +4.528 |
utton | +4.311 |
Neg logit contributions | |
anan | -6.843 |
condem | -6.571 |
pell | -6.470 |
lie | -6.426 |
fug | -6.292 |
Token | old |
Token ID | 727 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Kinnikuman | +0.986 |
scale | +0.888 |
�� | +0.826 |
cially | +0.778 |
utton | +0.750 |
Neg logit contributions | |
anan | -2.770 |
lie | -2.711 |
pell | -2.690 |
fug | -2.650 |
condem | -2.639 |
Token | woman |
Token ID | 2415 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Kinnikuman | +4.077 |
scale | +3.909 |
�� | +3.697 |
cially | +3.671 |
cade | +3.578 |
Neg logit contributions | |
anan | -3.930 |
lie | -3.823 |
pell | -3.811 |
condem | -3.702 |
fug | -3.666 |
Token | , |
Token ID | 11 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
Kinnikuman | +0.297 |
scale | +0.286 |
�� | +0.270 |
cially | +0.267 |
utton | +0.263 |
Neg logit contributions | |
anan | -0.294 |
lie | -0.283 |
pell | -0.281 |
condem | -0.280 |
fug | -0.278 |
Token | Man |
Token ID | 1869 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Kinnikuman | +0.490 |
scale | +0.470 |
�� | +0.445 |
cially | +0.438 |
utton | +0.431 |
Neg logit contributions | |
anan | -0.512 |
lie | -0.493 |
pell | -0.489 |
condem | -0.487 |
fug | -0.483 |
Token | � |
Token ID | 251 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Kinnikuman | +0.579 |
scale | +0.547 |
�� | +0.518 |
cially | +0.499 |
utton | +0.489 |
Neg logit contributions | |
anan | -0.891 |
lie | -0.863 |
pell | -0.857 |
condem | -0.853 |
fug | -0.845 |
Token | said |
Token ID | 531 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Kinnikuman | +0.873 |
scale | +0.823 |
�� | +0.790 |
cially | +0.775 |
utton | +0.761 |
Neg logit contributions | |
anan | -0.896 |
lie | -0.867 |
pell | -0.858 |
fug | -0.850 |
condem | -0.850 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Kinnikuman | +1.101 |
scale | +1.058 |
�� | +0.999 |
cially | +0.986 |
utton | +0.967 |
Neg logit contributions | |
anan | -1.145 |
lie | -1.105 |
pell | -1.097 |
condem | -1.090 |
fug | -1.080 |
Token | 82 |
Token ID | 9415 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
anan | +0.775 |
lie | +0.749 |
pell | +0.734 |
condem | +0.734 |
fug | +0.732 |
Neg logit contributions | |
Kinnikuman | -0.860 |
scale | -0.819 |
�� | -0.789 |
cially | -0.776 |
utton | -0.760 |
Token | - |
Token ID | 12 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
Kinnikuman | +1.596 |
scale | +1.579 |
�� | +1.469 |
cially | +1.436 |
utton | +1.419 |
Neg logit contributions | |
anan | -1.804 |
condem | -1.758 |
pell | -1.750 |
lie | -1.747 |
fug | -1.699 |
Token | year |
Token ID | 1941 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
Kinnikuman | +1.991 |
scale | +1.885 |
�� | +1.723 |
cially | +1.693 |
utton | +1.646 |
Neg logit contributions | |
anan | -3.880 |
lie | -3.771 |
pell | -3.750 |
condem | -3.743 |
fug | -3.715 |
Token | - |
Token ID | 12 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Kinnikuman | +5.625 |
scale | +5.484 |
cially | +5.084 |
�� | +4.999 |
utton | +4.902 |
Neg logit contributions | |
anan | -6.460 |
condem | -6.305 |
lie | -6.141 |
pell | -6.090 |
fug | -5.978 |
Token | old |
Token ID | 727 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
Kinnikuman | +0.667 |
scale | +0.589 |
�� | +0.577 |
cially | +0.529 |
utton | +0.511 |
Neg logit contributions | |
anan | -1.719 |
lie | -1.693 |
pell | -1.675 |
fug | -1.634 |
condem | -1.605 |
Token | grandmother |
Token ID | 18410 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Kinnikuman | +3.610 |
scale | +3.494 |
�� | +3.277 |
cially | +3.256 |
cade | +3.165 |
Neg logit contributions | |
anan | -3.551 |
lie | -3.428 |
pell | -3.422 |
condem | -3.359 |
fug | -3.335 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Kinnikuman | +1.712 |
scale | +1.642 |
�� | +1.543 |
cially | +1.524 |
utton | +1.494 |
Neg logit contributions | |
anan | -1.879 |
lie | -1.813 |
pell | -1.800 |
condem | -1.788 |
fug | -1.774 |
Token | � |
Token ID | 564 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
anan | +0.122 |
lie | +0.118 |
pell | +0.117 |
fug | +0.115 |
condem | +0.115 |
Neg logit contributions | |
Kinnikuman | -0.118 |
scale | -0.112 |
�� | -0.108 |
cially | -0.106 |
utton | -0.104 |
Token | www |
Token ID | 2503 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
lie | +1.607 |
anan | +1.512 |
pell | +1.357 |
fug | +1.274 |
sen | +1.202 |
Neg logit contributions | |
Kinnikuman | -4.471 |
�� | -4.339 |
ザ | -4.061 |
utton | -4.057 |
scale | -3.973 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
anan | +0.228 |
lie | +0.224 |
pell | +0.217 |
fug | +0.211 |
condem | +0.197 |
Neg logit contributions | |
Kinnikuman | -0.318 |
�� | -0.306 |
scale | -0.300 |
cially | -0.287 |
utton | -0.283 |
Token | bel |
Token ID | 6667 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Kinnikuman | +0.229 |
scale | +0.213 |
�� | +0.213 |
cially | +0.203 |
utton | +0.201 |
Neg logit contributions | |
anan | -0.208 |
lie | -0.203 |
pell | -0.199 |
condem | -0.192 |
fug | -0.191 |
Token | fast |
Token ID | 7217 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
anan | +1.881 |
lie | +1.781 |
pell | +1.727 |
condem | +1.649 |
fug | +1.641 |
Neg logit contributions | |
Kinnikuman | -2.810 |
�� | -2.639 |
scale | -2.618 |
cade | -2.499 |
ザ | -2.462 |
Token | te |
Token ID | 660 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
anan | +0.235 |
lie | +0.204 |
pell | +0.196 |
fug | +0.181 |
condem | +0.169 |
Neg logit contributions | |
Kinnikuman | -1.480 |
scale | -1.420 |
�� | -1.404 |
cially | -1.355 |
utton | -1.354 |
Token | legraph |
Token ID | 16606 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
anan | +1.370 |
pell | +1.293 |
lie | +1.265 |
fug | +1.240 |
condem | +1.204 |
Neg logit contributions | |
Kinnikuman | -1.511 |
�� | -1.382 |
scale | -1.372 |
utton | -1.290 |
ザ | -1.271 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
scale | +5.469 |
Kinnikuman | +5.406 |
cially | +4.947 |
utton | +4.907 |
cade | +4.897 |
Neg logit contributions | |
condem | -6.939 |
anan | -6.542 |
fug | -6.320 |
pell | -6.230 |
lie | -6.131 |
Token | co |
Token ID | 1073 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
anan | +0.159 |
lie | +0.153 |
pell | +0.152 |
fug | +0.145 |
condem | +0.138 |
Neg logit contributions | |
Kinnikuman | -0.262 |
�� | -0.248 |
scale | -0.247 |
utton | -0.235 |
cially | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
Kinnikuman | +1.536 |
scale | +1.474 |
�� | +1.416 |
cially | +1.385 |
utton | +1.362 |
Neg logit contributions | |
anan | -1.289 |
lie | -1.241 |
pell | -1.227 |
fug | -1.206 |
condem | -1.205 |
Token | uk |
Token ID | 2724 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
anan | +0.033 |
lie | +0.031 |
pell | +0.031 |
fug | +0.030 |
condem | +0.029 |
Neg logit contributions | |
Kinnikuman | -0.050 |
scale | -0.048 |
�� | -0.047 |
cially | -0.045 |
utton | -0.045 |
Token | / |
Token ID | 14 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
anan | +0.432 |
lie | +0.423 |
pell | +0.409 |
fug | +0.393 |
condem | +0.375 |
Neg logit contributions | |
Kinnikuman | -0.725 |
�� | -0.695 |
scale | -0.695 |
cially | -0.666 |
utton | -0.656 |
Token | one |
Token ID | 530 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Kinnikuman | +1.345 |
scale | +1.293 |
�� | +1.223 |
cially | +1.207 |
utton | +1.186 |
Neg logit contributions | |
anan | -1.306 |
lie | -1.258 |
pell | -1.248 |
condem | -1.240 |
fug | -1.229 |
Token | - |
Token ID | 12 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Kinnikuman | +0.312 |
scale | +0.300 |
�� | +0.285 |
cially | +0.282 |
utton | +0.277 |
Neg logit contributions | |
anan | -0.287 |
lie | -0.276 |
pell | -0.273 |
condem | -0.272 |
fug | -0.270 |
Token | story |
Token ID | 13571 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Kinnikuman | +1.081 |
scale | +1.034 |
�� | +0.962 |
cially | +0.948 |
utton | +0.929 |
Neg logit contributions | |
anan | -1.498 |
lie | -1.450 |
pell | -1.441 |
condem | -1.436 |
fug | -1.425 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Kinnikuman | +1.192 |
scale | +1.146 |
�� | +1.084 |
cially | +1.069 |
utton | +1.051 |
Neg logit contributions | |
anan | -1.140 |
lie | -1.096 |
pell | -1.088 |
condem | -1.081 |
fug | -1.071 |
Token | c |
Token ID | 269 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
anan | +1.063 |
lie | +1.026 |
fug | +1.026 |
condem | +1.022 |
pell | +1.015 |
Neg logit contributions | |
Kinnikuman | -1.121 |
scale | -1.069 |
�� | -1.042 |
cially | -1.027 |
utton | -1.000 |
Token | rescent |
Token ID | 26505 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Kinnikuman | +1.914 |
scale | +1.818 |
�� | +1.722 |
cially | +1.689 |
utton | +1.649 |
Neg logit contributions | |
anan | -2.349 |
lie | -2.271 |
pell | -2.250 |
condem | -2.231 |
fug | -2.217 |
Token | - |
Token ID | 12 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Kinnikuman | +5.655 |
scale | +5.621 |
�� | +5.126 |
cially | +5.080 |
utton | +4.998 |
Neg logit contributions | |
anan | -6.261 |
pell | -6.035 |
condem | -5.998 |
lie | -5.951 |
fug | -5.782 |
Token | shaped |
Token ID | 16760 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Kinnikuman | +0.582 |
scale | +0.523 |
�� | +0.509 |
cially | +0.487 |
utton | +0.472 |
Neg logit contributions | |
anan | -1.145 |
lie | -1.126 |
pell | -1.110 |
fug | -1.100 |
condem | -1.097 |
Token | Kent |
Token ID | 8758 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Kinnikuman | +1.520 |
scale | +1.457 |
�� | +1.374 |
cially | +1.353 |
utton | +1.332 |
Neg logit contributions | |
anan | -1.516 |
lie | -1.454 |
pell | -1.445 |
condem | -1.436 |
fug | -1.420 |
Token | uck |
Token ID | 1347 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Kinnikuman | +1.597 |
scale | +1.521 |
�� | +1.443 |
cially | +1.419 |
utton | +1.382 |
Neg logit contributions | |
anan | -1.833 |
lie | -1.772 |
pell | -1.757 |
fug | -1.732 |
condem | -1.727 |
Token | Kn |
Token ID | 6102 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Kinnikuman | +1.861 |
scale | +1.795 |
�� | +1.704 |
cially | +1.680 |
utton | +1.657 |
Neg logit contributions | |
anan | -1.522 |
lie | -1.450 |
pell | -1.446 |
condem | -1.438 |
fug | -1.423 |
Token | Ed |
Token ID | 1717 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Kinnikuman | +0.337 |
scale | +0.324 |
�� | +0.307 |
cially | +0.304 |
utton | +0.297 |
Neg logit contributions | |
anan | -0.350 |
lie | -0.340 |
pell | -0.336 |
fug | -0.333 |
condem | -0.333 |
Token | Ge |
Token ID | 10082 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
anan | +0.278 |
lie | +0.272 |
pell | +0.267 |
fug | +0.262 |
condem | +0.261 |
Neg logit contributions | |
Kinnikuman | -0.275 |
scale | -0.262 |
�� | -0.255 |
cially | -0.249 |
utton | -0.241 |
Token | in |
Token ID | 259 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Kinnikuman | +1.598 |
scale | +1.535 |
�� | +1.454 |
cially | +1.435 |
utton | +1.408 |
Neg logit contributions | |
anan | -1.562 |
lie | -1.505 |
pell | -1.493 |
condem | -1.483 |
fug | -1.472 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Kinnikuman | +0.694 |
scale | +0.666 |
�� | +0.630 |
cially | +0.621 |
utton | +0.610 |
Neg logit contributions | |
anan | -0.718 |
lie | -0.693 |
pell | -0.687 |
condem | -0.683 |
fug | -0.678 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Kinnikuman | +1.302 |
scale | +1.246 |
�� | +1.173 |
cially | +1.155 |
utton | +1.133 |
Neg logit contributions | |
anan | -1.554 |
lie | -1.502 |
pell | -1.491 |
condem | -1.483 |
fug | -1.472 |
Token | cannibal |
Token ID | 39904 |
Feature activation | +8.51e+00 |
Pos logit contributions | |
Kinnikuman | +2.136 |
scale | +2.052 |
�� | +1.947 |
cially | +1.914 |
utton | +1.888 |
Neg logit contributions | |
anan | -1.967 |
lie | -1.881 |
pell | -1.873 |
condem | -1.858 |
fug | -1.831 |
Token | istic |
Token ID | 2569 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
Kinnikuman | +5.934 |
scale | +5.722 |
�� | +5.301 |
utton | +5.187 |
cially | +5.141 |
Neg logit contributions | |
anan | -6.005 |
pell | -5.745 |
lie | -5.700 |
condem | -5.611 |
fug | -5.394 |
Token | serial |
Token ID | 11389 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Kinnikuman | +4.355 |
scale | +4.177 |
�� | +3.931 |
utton | +3.859 |
cially | +3.810 |
Neg logit contributions | |
anan | -4.091 |
pell | -3.862 |
lie | -3.832 |
condem | -3.812 |
fug | -3.693 |
Token | killer |
Token ID | 11868 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
Kinnikuman | +0.942 |
scale | +0.897 |
�� | +0.836 |
cially | +0.822 |
utton | +0.803 |
Neg logit contributions | |
anan | -1.398 |
lie | -1.355 |
pell | -1.346 |
condem | -1.339 |
fug | -1.330 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Kinnikuman | +2.707 |
scale | +2.616 |
�� | +2.444 |
cially | +2.393 |
utton | +2.377 |
Neg logit contributions | |
anan | -2.854 |
lie | -2.722 |
pell | -2.703 |
condem | -2.691 |
fug | -2.640 |
Token | Real |
Token ID | 6416 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Kinnikuman | +1.191 |
scale | +1.140 |
�� | +1.100 |
cially | +1.073 |
utton | +1.048 |
Neg logit contributions | |
anan | -1.331 |
lie | -1.301 |
pell | -1.278 |
fug | -1.256 |
condem | -1.255 |
Token | & |
Token ID | 1222 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Kinnikuman | +1.690 |
scale | +1.623 |
�� | +1.540 |
cially | +1.519 |
utton | +1.490 |
Neg logit contributions | |
anan | -1.647 |
lie | -1.588 |
pell | -1.577 |
condem | -1.564 |
fug | -1.553 |
Token | 40 |
Token ID | 2319 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
anan | +0.713 |
lie | +0.694 |
pell | +0.686 |
condem | +0.681 |
fug | +0.679 |
Neg logit contributions | |
Kinnikuman | -0.729 |
scale | -0.694 |
�� | -0.661 |
cially | -0.651 |
utton | -0.639 |
Token | pl |
Token ID | 458 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
anan | +0.897 |
lie | +0.868 |
pell | +0.862 |
condem | +0.855 |
fug | +0.851 |
Neg logit contributions | |
Kinnikuman | -0.803 |
scale | -0.764 |
�� | -0.724 |
cially | -0.708 |
utton | -0.695 |
Token | ows |
Token ID | 1666 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
anan | +2.662 |
lie | +2.503 |
fug | +2.462 |
pell | +2.458 |
condem | +2.410 |
Neg logit contributions | |
Kinnikuman | -2.494 |
scale | -2.301 |
�� | -2.258 |
cially | -2.223 |
ザ | -2.135 |
Token | in |
Token ID | 287 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Kinnikuman | +0.286 |
scale | +0.273 |
�� | +0.261 |
cially | +0.257 |
utton | +0.252 |
Neg logit contributions | |
anan | -0.260 |
lie | -0.253 |
pell | -0.251 |
condem | -0.247 |
fug | -0.245 |
Token | ATL |
Token ID | 41051 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
anan | +1.289 |
lie | +1.254 |
pell | +1.237 |
condem | +1.228 |
fug | +1.228 |
Neg logit contributions | |
Kinnikuman | -1.213 |
scale | -1.159 |
�� | -1.107 |
cially | -1.094 |
utton | -1.058 |
Token | proper |
Token ID | 1774 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
anan | +6.609 |
pell | +6.530 |
lie | +6.507 |
fug | +6.355 |
condem | +6.270 |
Neg logit contributions | |
Kinnikuman | -6.431 |
scale | -6.049 |
�� | -5.801 |
cially | -5.746 |
ixon | -5.536 |
Token | ), |
Token ID | 828 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
anan | +1.850 |
lie | +1.821 |
pell | +1.811 |
condem | +1.758 |
fug | +1.754 |
Neg logit contributions | |
Kinnikuman | -1.832 |
scale | -1.736 |
�� | -1.664 |
cially | -1.639 |
utton | -1.591 |
Token | so |
Token ID | 523 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
anan | +0.369 |
lie | +0.359 |
fug | +0.356 |
pell | +0.355 |
condem | +0.352 |
Neg logit contributions | |
Kinnikuman | -0.332 |
scale | -0.313 |
�� | -0.301 |
cially | -0.292 |
utton | -0.288 |
Token | the |
Token ID | 262 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Kinnikuman | +1.640 |
scale | +1.570 |
�� | +1.484 |
cially | +1.455 |
utton | +1.431 |
Neg logit contributions | |
anan | -1.903 |
lie | -1.839 |
pell | -1.824 |
condem | -1.808 |
fug | -1.806 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
anan | +0.448 |
lie | +0.431 |
fug | +0.428 |
pell | +0.427 |
condem | +0.426 |
Neg logit contributions | |
Kinnikuman | -0.469 |
scale | -0.447 |
�� | -0.429 |
cially | -0.421 |
utton | -0.413 |
Token | to |
Token ID | 284 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
anan | +0.404 |
lie | +0.389 |
pell | +0.386 |
condem | +0.379 |
fug | +0.379 |
Neg logit contributions | |
Kinnikuman | -0.454 |
scale | -0.438 |
�� | -0.419 |
cially | -0.410 |
utton | -0.404 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
anan | +1.459 |
lie | +1.417 |
pell | +1.403 |
condem | +1.391 |
fug | +1.386 |
Neg logit contributions | |
Kinnikuman | -1.405 |
scale | -1.329 |
�� | -1.272 |
cially | -1.254 |
cade | -1.223 |
Token | end |
Token ID | 886 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
anan | +0.182 |
lie | +0.178 |
pell | +0.176 |
condem | +0.175 |
fug | +0.175 |
Neg logit contributions | |
Kinnikuman | -0.146 |
scale | -0.139 |
�� | -0.131 |
cially | -0.129 |
utton | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
anan | +0.225 |
lie | +0.217 |
pell | +0.215 |
condem | +0.212 |
fug | +0.211 |
Neg logit contributions | |
Kinnikuman | -0.270 |
scale | -0.258 |
�� | -0.247 |
cially | -0.244 |
utton | -0.240 |
Token | then |
Token ID | 788 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
anan | +0.544 |
lie | +0.531 |
pell | +0.525 |
fug | +0.523 |
condem | +0.521 |
Neg logit contributions | |
Kinnikuman | -0.526 |
scale | -0.507 |
�� | -0.488 |
cially | -0.473 |
utton | -0.465 |
Token | come |
Token ID | 1282 |
Feature activation | -9.30e+00 |
Pos logit contributions | |
Kinnikuman | +0.066 |
scale | +0.062 |
�� | +0.060 |
cially | +0.058 |
utton | +0.057 |
Neg logit contributions | |
anan | -0.081 |
lie | -0.078 |
pell | -0.077 |
condem | -0.077 |
fug | -0.077 |
Token | back |
Token ID | 736 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
lie | +6.584 |
anan | +6.474 |
fug | +6.437 |
condem | +6.345 |
pell | +6.263 |
Neg logit contributions | |
Kinnikuman | -6.187 |
scale | -5.686 |
�� | -5.677 |
ザ | -5.469 |
ixon | -5.343 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
anan | +2.215 |
lie | +2.170 |
pell | +2.144 |
fug | +2.114 |
condem | +2.096 |
Neg logit contributions | |
Kinnikuman | -2.664 |
scale | -2.581 |
�� | -2.485 |
cially | -2.406 |
cade | -2.391 |
Token | click |
Token ID | 3904 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anan | +1.269 |
lie | +1.237 |
condem | +1.211 |
fug | +1.210 |
pell | +1.208 |
Neg logit contributions | |
Kinnikuman | -1.254 |
scale | -1.184 |
�� | -1.151 |
cially | -1.121 |
utton | -1.100 |
Token | on |
Token ID | 319 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Kinnikuman | +0.791 |
scale | +0.762 |
�� | +0.726 |
cially | +0.713 |
utton | +0.702 |
Neg logit contributions | |
anan | -0.754 |
lie | -0.728 |
pell | -0.722 |
condem | -0.717 |
fug | -0.712 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
anan | +0.254 |
lie | +0.246 |
pell | +0.244 |
condem | +0.242 |
fug | +0.241 |
Neg logit contributions | |
Kinnikuman | -0.231 |
scale | -0.222 |
�� | -0.210 |
cially | -0.206 |
utton | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Kinnikuman | +3.595 |
scale | +3.490 |
�� | +3.252 |
cially | +3.245 |
utton | +3.168 |
Neg logit contributions | |
anan | -4.338 |
condem | -4.154 |
lie | -4.148 |
pell | -4.104 |
fug | -4.072 |
Token | they |
Token ID | 484 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Kinnikuman | +0.927 |
scale | +0.884 |
�� | +0.836 |
cially | +0.822 |
utton | +0.805 |
Neg logit contributions | |
anan | -1.036 |
lie | -1.003 |
pell | -0.995 |
condem | -0.984 |
fug | -0.984 |
Token | may |
Token ID | 743 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
anan | +1.085 |
lie | +1.062 |
pell | +1.043 |
condem | +1.039 |
fug | +1.036 |
Neg logit contributions | |
Kinnikuman | -1.191 |
scale | -1.129 |
�� | -1.086 |
cially | -1.050 |
utton | -1.036 |
Token | well |
Token ID | 880 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
anan | +0.093 |
lie | +0.092 |
pell | +0.090 |
condem | +0.090 |
fug | +0.090 |
Neg logit contributions | |
Kinnikuman | -0.094 |
scale | -0.088 |
�� | -0.086 |
cially | -0.083 |
utton | -0.081 |
Token | also |
Token ID | 635 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anan | +0.710 |
lie | +0.703 |
condem | +0.689 |
pell | +0.688 |
fug | +0.685 |
Neg logit contributions | |
Kinnikuman | -0.757 |
scale | -0.701 |
�� | -0.686 |
cially | -0.660 |
utton | -0.649 |
Token | owe |
Token ID | 19059 |
Feature activation | -8.99e+00 |
Pos logit contributions | |
anan | +0.701 |
lie | +0.693 |
pell | +0.682 |
condem | +0.679 |
fug | +0.674 |
Neg logit contributions | |
Kinnikuman | -0.750 |
scale | -0.704 |
�� | -0.682 |
cially | -0.663 |
utton | -0.650 |
Token | history |
Token ID | 2106 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anan | +5.894 |
pell | +5.755 |
lie | +5.742 |
fug | +5.736 |
condem | +5.509 |
Neg logit contributions | |
Kinnikuman | -6.551 |
scale | -6.079 |
�� | -5.954 |
cade | -5.742 |
ザ | -5.727 |
Token | and |
Token ID | 290 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
anan | +1.418 |
pell | +1.357 |
lie | +1.353 |
condem | +1.338 |
fug | +1.332 |
Neg logit contributions | |
Kinnikuman | -1.314 |
scale | -1.254 |
�� | -1.194 |
cially | -1.172 |
utton | -1.152 |
Token | their |
Token ID | 511 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
anan | +1.018 |
lie | +0.978 |
pell | +0.971 |
condem | +0.968 |
fug | +0.967 |
Neg logit contributions | |
Kinnikuman | -1.091 |
scale | -1.041 |
�� | -0.976 |
cially | -0.968 |
utton | -0.959 |
Token | party |
Token ID | 2151 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anan | +1.373 |
lie | +1.328 |
fug | +1.327 |
pell | +1.327 |
condem | +1.321 |
Neg logit contributions | |
Kinnikuman | -1.243 |
scale | -1.187 |
�� | -1.115 |
cially | -1.098 |
utton | -1.085 |
Token | a |
Token ID | 257 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
anan | +1.420 |
lie | +1.369 |
pell | +1.359 |
condem | +1.349 |
fug | +1.344 |
Neg logit contributions | |
Kinnikuman | -1.304 |
scale | -1.238 |
�� | -1.176 |
cially | -1.153 |
utton | -1.144 |
Token | serious |
Token ID | 2726 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
Kinnikuman | +0.840 |
scale | +0.802 |
�� | +0.755 |
cially | +0.739 |
utton | +0.724 |
Neg logit contributions | |
anan | -1.103 |
lie | -1.072 |
pell | -1.065 |
condem | -1.060 |
fug | -1.055 |
Token | injuries |
Token ID | 6821 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
Kinnikuman | +0.678 |
scale | +0.651 |
�� | +0.621 |
cially | +0.611 |
utton | +0.600 |
Neg logit contributions | |
anan | -0.600 |
lie | -0.580 |
pell | -0.573 |
condem | -0.572 |
fug | -0.567 |
Token | in |
Token ID | 287 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Kinnikuman | +0.028 |
scale | +0.027 |
�� | +0.025 |
cially | +0.025 |
utton | +0.024 |
Neg logit contributions | |
anan | -0.031 |
lie | -0.030 |
pell | -0.029 |
condem | -0.029 |
fug | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Kinnikuman | +0.014 |
scale | +0.014 |
�� | +0.013 |
cially | +0.013 |
utton | +0.012 |
Neg logit contributions | |
anan | -0.016 |
lie | -0.015 |
pell | -0.015 |
condem | -0.015 |
fug | -0.015 |
Token | rally |
Token ID | 7903 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
Kinnikuman | +0.538 |
scale | +0.520 |
�� | +0.497 |
cially | +0.491 |
utton | +0.484 |
Neg logit contributions | |
anan | -0.381 |
lie | -0.364 |
pell | -0.361 |
condem | -0.358 |
fug | -0.355 |
Token | crash |
Token ID | 7014 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
anan | +2.260 |
condem | +2.213 |
lie | +2.205 |
fug | +2.179 |
pell | +2.178 |
Neg logit contributions | |
Kinnikuman | -2.616 |
scale | -2.461 |
�� | -2.417 |
cially | -2.328 |
utton | -2.265 |
Token | last |
Token ID | 938 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
anan | +5.706 |
pell | +5.668 |
lie | +5.658 |
condem | +5.656 |
fug | +5.605 |
Neg logit contributions | |
Kinnikuman | -6.390 |
�� | -6.320 |
scale | -6.179 |
ザ | -5.798 |
cially | -5.707 |
Token | weekend |
Token ID | 5041 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
Kinnikuman | +1.044 |
scale | +1.008 |
�� | +0.952 |
cially | +0.950 |
utton | +0.929 |
Neg logit contributions | |
anan | -0.867 |
lie | -0.825 |
pell | -0.821 |
condem | -0.815 |
fug | -0.805 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
anan | +2.443 |
lie | +2.371 |
pell | +2.339 |
condem | +2.325 |
fug | +2.303 |
Neg logit contributions | |
Kinnikuman | -3.025 |
scale | -2.910 |
�� | -2.825 |
cially | -2.719 |
utton | -2.657 |
Token | Michael |
Token ID | 3899 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
anan | +0.123 |
lie | +0.120 |
pell | +0.117 |
fug | +0.116 |
condem | +0.116 |
Neg logit contributions | |
Kinnikuman | -0.117 |
scale | -0.113 |
�� | -0.109 |
cially | -0.106 |
utton | -0.103 |
Token | Sch |
Token ID | 3059 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
anan | +0.190 |
lie | +0.185 |
pell | +0.183 |
condem | +0.181 |
fug | +0.181 |
Neg logit contributions | |
Kinnikuman | -0.150 |
scale | -0.143 |
�� | -0.135 |
cially | -0.132 |
utton | -0.130 |
Token | Lords |
Token ID | 18651 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Kinnikuman | +0.446 |
scale | +0.432 |
�� | +0.414 |
cially | +0.410 |
utton | +0.404 |
Neg logit contributions | |
anan | -0.255 |
lie | -0.242 |
pell | -0.240 |
condem | -0.237 |
fug | -0.235 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
anan | +1.245 |
lie | +1.205 |
pell | +1.198 |
condem | +1.174 |
fug | +1.164 |
Neg logit contributions | |
Kinnikuman | -1.960 |
scale | -1.884 |
�� | -1.819 |
cially | -1.773 |
utton | -1.761 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
anan | +2.382 |
lie | +2.326 |
pell | +2.323 |
condem | +2.322 |
fug | +2.251 |
Neg logit contributions | |
Kinnikuman | -2.909 |
scale | -2.815 |
�� | -2.724 |
cially | -2.611 |
utton | -2.603 |
Token |
|
Token ID | 198 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
anan | +0.560 |
lie | +0.540 |
pell | +0.539 |
condem | +0.538 |
fug | +0.532 |
Neg logit contributions | |
Kinnikuman | -0.452 |
scale | -0.431 |
�� | -0.403 |
cially | -0.400 |
utton | -0.391 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
anan | +0.570 |
lie | +0.565 |
pell | +0.548 |
fug | +0.532 |
Lawyers | +0.499 |
Neg logit contributions | |
Kinnikuman | -0.677 |
�� | -0.661 |
scale | -0.626 |
cially | -0.604 |
utton | -0.595 |
Token | Hel |
Token ID | 12621 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
anan | +0.606 |
lie | +0.590 |
pell | +0.579 |
fug | +0.563 |
condem | +0.559 |
Neg logit contributions | |
Kinnikuman | -0.598 |
scale | -0.565 |
�� | -0.546 |
cially | -0.528 |
utton | -0.523 |
Token | ena |
Token ID | 8107 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
anan | +4.064 |
pell | +3.868 |
lie | +3.799 |
fug | +3.233 |
condem | +3.229 |
Neg logit contributions | |
Kinnikuman | -8.262 |
�� | -7.892 |
scale | -7.775 |
cially | -7.330 |
cade | -7.294 |
Token | Kennedy |
Token ID | 10401 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
anan | +2.672 |
lie | +2.601 |
pell | +2.579 |
fug | +2.501 |
condem | +2.480 |
Neg logit contributions | |
Kinnikuman | -2.720 |
scale | -2.671 |
�� | -2.576 |
cially | -2.476 |
utton | -2.414 |
Token | QC |
Token ID | 36070 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
anan | +0.687 |
lie | +0.662 |
pell | +0.656 |
condem | +0.651 |
fug | +0.644 |
Neg logit contributions | |
Kinnikuman | -0.711 |
scale | -0.682 |
�� | -0.645 |
cially | -0.636 |
utton | -0.624 |
Token | suggested |
Token ID | 5220 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
anan | +0.061 |
lie | +0.058 |
pell | +0.058 |
condem | +0.057 |
fug | +0.057 |
Neg logit contributions | |
Kinnikuman | -0.061 |
scale | -0.059 |
�� | -0.056 |
cially | -0.055 |
utton | -0.054 |
Token | collecting |
Token ID | 13157 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
anan | +1.501 |
lie | +1.456 |
pell | +1.448 |
condem | +1.440 |
fug | +1.439 |
Neg logit contributions | |
Kinnikuman | -1.463 |
scale | -1.406 |
�� | -1.346 |
cially | -1.301 |
utton | -1.289 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Kinnikuman | +1.175 |
scale | +1.125 |
�� | +1.068 |
cially | +1.048 |
utton | +1.032 |
Neg logit contributions | |
anan | -1.151 |
lie | -1.112 |
pell | -1.100 |
condem | -1.091 |
fug | -1.088 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anan | +1.056 |
lie | +1.052 |
pell | +1.027 |
fug | +1.000 |
Gott | +0.932 |
Neg logit contributions | |
Kinnikuman | -1.271 |
�� | -1.233 |
scale | -1.170 |
cially | -1.131 |
utton | -1.116 |
Token | – |
Token ID | 1906 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
anan | +0.827 |
lie | +0.808 |
pell | +0.796 |
fug | +0.780 |
condem | +0.778 |
Neg logit contributions | |
Kinnikuman | -0.762 |
scale | -0.711 |
�� | -0.686 |
cially | -0.671 |
utton | -0.656 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
anan | +1.479 |
lie | +1.436 |
pell | +1.415 |
fug | +1.408 |
condem | +1.404 |
Neg logit contributions | |
Kinnikuman | -1.463 |
scale | -1.401 |
�� | -1.343 |
cially | -1.321 |
utton | -1.288 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
lie | +1.200 |
anan | +1.200 |
pell | +1.169 |
fug | +1.133 |
Gott | +1.058 |
Neg logit contributions | |
Kinnikuman | -1.453 |
�� | -1.410 |
scale | -1.340 |
cially | -1.297 |
utton | -1.279 |
Token | ont |
Token ID | 756 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
anan | +1.266 |
lie | +1.235 |
pell | +1.214 |
fug | +1.187 |
condem | +1.179 |
Neg logit contributions | |
Kinnikuman | -1.251 |
scale | -1.174 |
�� | -1.137 |
cially | -1.111 |
utton | -1.089 |
Token | ological |
Token ID | 2770 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
anan | +6.042 |
lie | +5.983 |
pell | +5.827 |
fug | +5.679 |
condem | +5.676 |
Neg logit contributions | |
Kinnikuman | -5.838 |
scale | -5.401 |
�� | -5.122 |
utton | -5.010 |
cade | -4.940 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
anan | +1.107 |
lie | +1.077 |
fug | +1.059 |
pell | +1.059 |
condem | +1.055 |
Neg logit contributions | |
Kinnikuman | -1.197 |
scale | -1.135 |
�� | -1.082 |
cially | -1.059 |
utton | -1.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
anan | +1.025 |
lie | +1.020 |
pell | +0.996 |
fug | +0.965 |
Gott | +0.901 |
Neg logit contributions | |
Kinnikuman | -1.219 |
�� | -1.173 |
scale | -1.119 |
cially | -1.080 |
utton | -1.067 |
Token | – |
Token ID | 1906 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
anan | +1.192 |
lie | +1.160 |
pell | +1.141 |
condem | +1.115 |
fug | +1.114 |
Neg logit contributions | |
Kinnikuman | -1.220 |
scale | -1.142 |
�� | -1.109 |
cially | -1.084 |
utton | -1.062 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
anan | +1.899 |
lie | +1.840 |
pell | +1.820 |
condem | +1.810 |
fug | +1.806 |
Neg logit contributions | |
Kinnikuman | -1.815 |
scale | -1.732 |
�� | -1.644 |
cially | -1.621 |
utton | -1.588 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Kinnikuman | +1.367 |
scale | +1.303 |
�� | +1.227 |
cially | +1.207 |
utton | +1.187 |
Neg logit contributions | |
anan | -1.612 |
lie | -1.559 |
pell | -1.543 |
condem | -1.542 |
fug | -1.522 |
Token | model |
Token ID | 2746 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Kinnikuman | +0.178 |
scale | +0.172 |
�� | +0.163 |
cially | +0.161 |
utton | +0.158 |
Neg logit contributions | |
anan | -0.161 |
lie | -0.155 |
pell | -0.154 |
condem | -0.153 |
fug | -0.152 |
Token | of |
Token ID | 286 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Kinnikuman | +1.767 |
scale | +1.696 |
�� | +1.602 |
cially | +1.581 |
utton | +1.551 |
Neg logit contributions | |
anan | -1.843 |
lie | -1.780 |
pell | -1.765 |
condem | -1.753 |
fug | -1.738 |
Token | Pont |
Token ID | 26345 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Kinnikuman | +0.213 |
scale | +0.205 |
�� | +0.195 |
cially | +0.192 |
utton | +0.188 |
Neg logit contributions | |
anan | -0.217 |
lie | -0.209 |
pell | -0.208 |
condem | -0.207 |
fug | -0.206 |
Token | iac |
Token ID | 9607 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
anan | +1.351 |
lie | +1.298 |
pell | +1.293 |
fug | +1.261 |
condem | +1.260 |
Neg logit contributions | |
Kinnikuman | -1.032 |
scale | -0.978 |
�� | -0.927 |
cially | -0.905 |
utton | -0.882 |
Token | GT |
Token ID | 7963 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
Kinnikuman | +1.004 |
scale | +0.965 |
�� | +0.915 |
cially | +0.903 |
utton | +0.887 |
Neg logit contributions | |
anan | -0.963 |
lie | -0.927 |
pell | -0.920 |
condem | -0.914 |
fug | -0.906 |
Token | O |
Token ID | 46 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
anan | +5.652 |
fug | +5.451 |
pell | +5.436 |
lie | +5.428 |
condem | +5.402 |
Neg logit contributions | |
Kinnikuman | -5.955 |
scale | -5.673 |
cially | -5.513 |
�� | -5.299 |
utton | -5.213 |
Token | sold |
Token ID | 2702 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Kinnikuman | +1.102 |
scale | +1.059 |
�� | +1.003 |
cially | +0.990 |
utton | +0.972 |
Neg logit contributions | |
anan | -1.073 |
lie | -1.034 |
pell | -1.025 |
condem | -1.019 |
fug | -1.010 |
Token | from |
Token ID | 422 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Kinnikuman | +1.106 |
scale | +1.061 |
�� | +1.003 |
cially | +0.988 |
utton | +0.970 |
Neg logit contributions | |
anan | -1.176 |
lie | -1.136 |
pell | -1.126 |
condem | -1.119 |
fug | -1.111 |
Token | 1969 |
Token ID | 16450 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anan | +0.603 |
lie | +0.582 |
pell | +0.581 |
condem | +0.571 |
fug | +0.570 |
Neg logit contributions | |
Kinnikuman | -0.612 |
scale | -0.591 |
�� | -0.568 |
cially | -0.557 |
utton | -0.543 |
Token | till |
Token ID | 10597 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
anan | +0.754 |
lie | +0.727 |
pell | +0.719 |
condem | +0.711 |
fug | +0.711 |
Neg logit contributions | |
Kinnikuman | -0.801 |
scale | -0.767 |
�� | -0.736 |
cially | -0.721 |
utton | -0.707 |
Token | an |
Token ID | 281 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
anan | +0.532 |
lie | +0.517 |
pell | +0.513 |
fug | +0.510 |
condem | +0.510 |
Neg logit contributions | |
Kinnikuman | -0.414 |
scale | -0.398 |
�� | -0.375 |
cially | -0.370 |
cade | -0.361 |
Token | incompetent |
Token ID | 33840 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Kinnikuman | +0.928 |
scale | +0.895 |
�� | +0.849 |
cially | +0.839 |
cade | +0.824 |
Neg logit contributions | |
anan | -0.898 |
lie | -0.865 |
pell | -0.855 |
condem | -0.855 |
fug | -0.850 |
Token | fool |
Token ID | 9192 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Kinnikuman | +1.382 |
scale | +1.329 |
�� | +1.259 |
cially | +1.242 |
utton | +1.223 |
Neg logit contributions | |
anan | -1.294 |
lie | -1.244 |
pell | -1.235 |
condem | -1.226 |
fug | -1.215 |
Token | . |
Token ID | 13 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
Kinnikuman | +1.974 |
scale | +1.903 |
�� | +1.793 |
cially | +1.771 |
utton | +1.746 |
Neg logit contributions | |
anan | -1.942 |
lie | -1.870 |
pell | -1.855 |
condem | -1.846 |
fug | -1.830 |
Token | Even |
Token ID | 3412 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Kinnikuman | +0.607 |
scale | +0.585 |
�� | +0.563 |
cially | +0.550 |
utton | +0.539 |
Neg logit contributions | |
anan | -0.658 |
lie | -0.637 |
pell | -0.628 |
fug | -0.620 |
condem | -0.618 |
Token | GT |
Token ID | 7963 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
Kinnikuman | +0.486 |
scale | +0.468 |
�� | +0.444 |
cially | +0.436 |
utton | +0.427 |
Neg logit contributions | |
anan | -0.527 |
lie | -0.510 |
pell | -0.505 |
condem | -0.504 |
fug | -0.502 |
Token | did |
Token ID | 750 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
anan | +5.761 |
fug | +5.555 |
lie | +5.414 |
pell | +5.374 |
condem | +5.283 |
Neg logit contributions | |
Kinnikuman | -5.917 |
scale | -5.738 |
cially | -5.522 |
�� | -5.495 |
utton | -5.234 |
Token | a |
Token ID | 257 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
anan | +0.654 |
lie | +0.633 |
pell | +0.629 |
condem | +0.627 |
fug | +0.621 |
Neg logit contributions | |
Kinnikuman | -0.692 |
scale | -0.663 |
�� | -0.639 |
cially | -0.619 |
cade | -0.611 |
Token | better |
Token ID | 1365 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
anan | +1.708 |
lie | +1.634 |
condem | +1.622 |
pell | +1.622 |
fug | +1.619 |
Neg logit contributions | |
Kinnikuman | -2.146 |
scale | -2.069 |
�� | -1.986 |
cially | -1.949 |
utton | -1.920 |
Token | job |
Token ID | 1693 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
anan | +1.663 |
lie | +1.593 |
pell | +1.589 |
condem | +1.585 |
fug | +1.559 |
Neg logit contributions | |
Kinnikuman | -2.759 |
scale | -2.664 |
�� | -2.607 |
cially | -2.544 |
cade | -2.502 |
Token | at |
Token ID | 379 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anan | +1.968 |
pell | +1.911 |
condem | +1.906 |
lie | +1.894 |
fug | +1.878 |
Neg logit contributions | |
Kinnikuman | -1.858 |
scale | -1.784 |
�� | -1.725 |
cially | -1.675 |
utton | -1.653 |
Token | Leicester |
Token ID | 29224 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Kinnikuman | +0.055 |
scale | +0.053 |
�� | +0.050 |
cially | +0.049 |
utton | +0.048 |
Neg logit contributions | |
anan | -0.056 |
lie | -0.054 |
pell | -0.054 |
condem | -0.054 |
fug | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Kinnikuman | +1.610 |
scale | +1.536 |
�� | +1.435 |
cially | +1.417 |
utton | +1.391 |
Neg logit contributions | |
anan | -2.095 |
lie | -2.025 |
pell | -2.011 |
condem | -2.008 |
fug | -1.986 |
Token | the |
Token ID | 262 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
anan | +0.412 |
lie | +0.397 |
pell | +0.394 |
condem | +0.392 |
fug | +0.388 |
Neg logit contributions | |
Kinnikuman | -0.419 |
scale | -0.403 |
�� | -0.381 |
cially | -0.376 |
utton | -0.370 |
Token | European |
Token ID | 3427 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
anan | +0.005 |
lie | +0.004 |
pell | +0.004 |
condem | +0.004 |
fug | +0.004 |
Neg logit contributions | |
Kinnikuman | -0.005 |
scale | -0.005 |
�� | -0.005 |
cially | -0.005 |
utton | -0.005 |
Token | Rugby |
Token ID | 26244 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
anan | +2.933 |
lie | +2.849 |
fug | +2.784 |
pell | +2.780 |
condem | +2.752 |
Neg logit contributions | |
Kinnikuman | -3.980 |
scale | -3.811 |
�� | -3.625 |
cially | -3.623 |
utton | -3.531 |
Token | Champions |
Token ID | 6662 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
anan | +0.238 |
lie | +0.226 |
pell | +0.224 |
condem | +0.222 |
fug | +0.219 |
Neg logit contributions | |
Kinnikuman | -0.408 |
scale | -0.395 |
�� | -0.379 |
cially | -0.375 |
utton | -0.369 |
Token | Cup |
Token ID | 5454 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
pell | +3.258 |
anan | +3.239 |
fug | +3.200 |
lie | +3.134 |
lender | +2.781 |
Neg logit contributions | |
Kinnikuman | -8.395 |
scale | -7.959 |
ザ | -7.830 |
�� | -7.822 |
ixon | -7.647 |
Token | at |
Token ID | 379 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
anan | +2.395 |
lie | +2.323 |
pell | +2.288 |
fug | +2.281 |
condem | +2.248 |
Neg logit contributions | |
Kinnikuman | -2.888 |
scale | -2.768 |
�� | -2.636 |
cially | -2.626 |
utton | -2.554 |
Token | Wel |
Token ID | 22268 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Kinnikuman | +1.409 |
scale | +1.353 |
�� | +1.276 |
cially | +1.270 |
utton | +1.250 |
Neg logit contributions | |
anan | -1.245 |
lie | -1.185 |
pell | -1.182 |
condem | -1.180 |
fug | -1.170 |
Token | ford |
Token ID | 3841 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
anan | +0.663 |
lie | +0.651 |
pell | +0.638 |
fug | +0.607 |
condem | +0.582 |
Neg logit contributions | |
Kinnikuman | -0.977 |
�� | -0.922 |
scale | -0.902 |
cially | -0.855 |
ザ | -0.847 |
Token | Road |
Token ID | 5567 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Kinnikuman | +1.021 |
scale | +0.980 |
�� | +0.945 |
cially | +0.925 |
utton | +0.907 |
Neg logit contributions | |
anan | -0.921 |
lie | -0.888 |
pell | -0.875 |
fug | -0.862 |
condem | -0.862 |
Token | 160 |
Token ID | 13454 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
anan | +0.293 |
lie | +0.285 |
pell | +0.282 |
fug | +0.278 |
condem | +0.276 |
Neg logit contributions | |
Kinnikuman | -0.283 |
scale | -0.269 |
�� | -0.261 |
cially | -0.256 |
utton | -0.251 |
Token | Texture |
Token ID | 44409 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
anan | +1.476 |
lie | +1.450 |
pell | +1.424 |
fug | +1.402 |
condem | +1.387 |
Neg logit contributions | |
Kinnikuman | -1.571 |
scale | -1.481 |
�� | -1.464 |
cially | -1.429 |
utton | -1.400 |
Token | fill |
Token ID | 6070 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
pell | +0.562 |
anan | +0.556 |
fug | +0.544 |
lie | +0.541 |
condem | +0.519 |
Neg logit contributions | |
Kinnikuman | -0.621 |
�� | -0.589 |
scale | -0.582 |
cade | -0.564 |
utton | -0.556 |
Token | - |
Token ID | 12 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
anan | +0.598 |
lie | +0.579 |
pell | +0.577 |
fug | +0.565 |
condem | +0.562 |
Neg logit contributions | |
Kinnikuman | -0.790 |
scale | -0.752 |
�� | -0.736 |
cially | -0.722 |
utton | -0.706 |
Token | rate |
Token ID | 4873 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
anan | +0.607 |
lie | +0.600 |
pell | +0.589 |
fug | +0.570 |
condem | +0.567 |
Neg logit contributions | |
Kinnikuman | -0.748 |
scale | -0.699 |
�� | -0.691 |
cially | -0.668 |
cade | -0.658 |
Token | GT |
Token ID | 7963 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
Kinnikuman | +0.368 |
scale | +0.350 |
�� | +0.338 |
cially | +0.331 |
utton | +0.324 |
Neg logit contributions | |
anan | -0.362 |
lie | -0.351 |
pell | -0.347 |
condem | -0.344 |
fug | -0.343 |
Token | / |
Token ID | 14 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
anan | +5.495 |
pell | +5.391 |
lie | +5.345 |
fug | +5.299 |
condem | +5.063 |
Neg logit contributions | |
Kinnikuman | -6.045 |
cially | -5.728 |
scale | -5.591 |
�� | -5.581 |
cade | -5.402 |
Token | s |
Token ID | 82 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
anan | +0.552 |
lie | +0.530 |
pell | +0.525 |
condem | +0.514 |
fug | +0.513 |
Neg logit contributions | |
Kinnikuman | -0.772 |
scale | -0.735 |
�� | -0.713 |
cially | -0.707 |
utton | -0.690 |
Token | 72 |
Token ID | 7724 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
anan | +0.159 |
lie | +0.155 |
pell | +0.153 |
condem | +0.151 |
fug | +0.151 |
Neg logit contributions | |
Kinnikuman | -0.172 |
scale | -0.165 |
�� | -0.158 |
cially | -0.156 |
utton | -0.152 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
Kinnikuman | +1.578 |
scale | +1.520 |
�� | +1.439 |
cially | +1.419 |
utton | +1.397 |
Neg logit contributions | |
anan | -1.491 |
lie | -1.436 |
pell | -1.423 |
condem | -1.417 |
fug | -1.404 |
Token | / |
Token ID | 14 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
anan | +3.531 |
pell | +3.463 |
lie | +3.440 |
fug | +3.389 |
condem | +3.256 |
Neg logit contributions | |
Kinnikuman | -6.199 |
scale | -5.924 |
cially | -5.836 |
�� | -5.756 |
cade | -5.629 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
anan | +2.571 |
lie | +2.485 |
pell | +2.462 |
condem | +2.441 |
fug | +2.430 |
Neg logit contributions | |
Kinnikuman | -2.502 |
scale | -2.398 |
�� | -2.271 |
cially | -2.237 |
utton | -2.195 |
Token | it |
Token ID | 340 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
anan | +1.104 |
lie | +1.068 |
fug | +1.062 |
pell | +1.062 |
condem | +1.056 |
Neg logit contributions | |
Kinnikuman | -1.086 |
scale | -1.037 |
�� | -1.002 |
cially | -0.974 |
utton | -0.950 |
Token | � |
Token ID | 447 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Kinnikuman | +0.164 |
scale | +0.158 |
�� | +0.151 |
cially | +0.148 |
utton | +0.146 |
Neg logit contributions | |
anan | -0.141 |
lie | -0.136 |
pell | -0.135 |
condem | -0.134 |
fug | -0.133 |
Token | � |
Token ID | 247 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
anan | +0.532 |
pell | +0.520 |
lie | +0.515 |
fug | +0.509 |
condem | +0.496 |
Neg logit contributions | |
Kinnikuman | -0.416 |
scale | -0.397 |
cially | -0.366 |
cade | -0.361 |
utton | -0.361 |
Token | s |
Token ID | 82 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Kinnikuman | +0.123 |
scale | +0.118 |
�� | +0.115 |
cially | +0.112 |
utton | +0.111 |
Neg logit contributions | |
anan | -0.057 |
lie | -0.054 |
pell | -0.054 |
condem | -0.052 |
fug | -0.052 |
Token | worth |
Token ID | 2861 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
Kinnikuman | +0.083 |
scale | +0.080 |
�� | +0.076 |
cially | +0.075 |
utton | +0.073 |
Neg logit contributions | |
anan | -0.075 |
lie | -0.072 |
pell | -0.072 |
condem | -0.072 |
fug | -0.072 |
Token | it |
Token ID | 340 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
anan | +5.089 |
pell | +4.873 |
condem | +4.852 |
fug | +4.846 |
lie | +4.836 |
Neg logit contributions | |
Kinnikuman | -6.187 |
scale | -5.937 |
�� | -5.703 |
cially | -5.649 |
ザ | -5.533 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
anan | +1.427 |
lie | +1.382 |
pell | +1.374 |
fug | +1.352 |
condem | +1.348 |
Neg logit contributions | |
Kinnikuman | -1.656 |
scale | -1.585 |
�� | -1.522 |
cially | -1.492 |
utton | -1.462 |
Token | � |
Token ID | 447 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
anan | +1.154 |
lie | +1.128 |
pell | +1.106 |
fug | +1.089 |
condem | +1.078 |
Neg logit contributions | |
Kinnikuman | -1.130 |
scale | -1.091 |
�� | -1.058 |
cially | -1.030 |
utton | -1.009 |
Token | � |
Token ID | 251 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Kinnikuman | +0.014 |
scale | +0.013 |
�� | +0.012 |
cially | +0.012 |
utton | +0.011 |
Neg logit contributions | |
anan | -0.023 |
lie | -0.022 |
pell | -0.022 |
condem | -0.022 |
fug | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
anan | +0.140 |
lie | +0.135 |
pell | +0.134 |
condem | +0.133 |
fug | +0.132 |
Neg logit contributions | |
Kinnikuman | -0.127 |
scale | -0.122 |
�� | -0.115 |
cially | -0.114 |
utton | -0.111 |
Token | Treasury |
Token ID | 13419 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
anan | +0.615 |
lie | +0.598 |
pell | +0.589 |
fug | +0.581 |
condem | +0.581 |
Neg logit contributions | |
Kinnikuman | -0.628 |
scale | -0.605 |
�� | -0.578 |
cially | -0.567 |
utton | -0.556 |
Token | will |
Token ID | 481 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Kinnikuman | +0.157 |
scale | +0.151 |
�� | +0.144 |
cially | +0.141 |
utton | +0.139 |
Neg logit contributions | |
anan | -0.145 |
lie | -0.140 |
pell | -0.139 |
condem | -0.138 |
fug | -0.137 |
Token | run |
Token ID | 1057 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Kinnikuman | +0.916 |
scale | +0.874 |
�� | +0.831 |
cially | +0.816 |
utton | +0.803 |
Neg logit contributions | |
anan | -0.954 |
lie | -0.924 |
pell | -0.918 |
condem | -0.910 |
fug | -0.905 |
Token | out |
Token ID | 503 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
Kinnikuman | +0.988 |
scale | +0.943 |
�� | +0.871 |
cially | +0.862 |
utton | +0.836 |
Neg logit contributions | |
anan | -1.716 |
lie | -1.663 |
pell | -1.650 |
condem | -1.650 |
fug | -1.630 |
Token | of |
Token ID | 286 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
anan | +0.764 |
lie | +0.735 |
condem | +0.731 |
pell | +0.729 |
fug | +0.721 |
Neg logit contributions | |
Kinnikuman | -0.530 |
scale | -0.510 |
�� | -0.474 |
cially | -0.469 |
utton | -0.457 |
Token | borrowed |
Token ID | 22546 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
anan | +2.158 |
lie | +2.107 |
pell | +2.100 |
fug | +2.088 |
condem | +2.078 |
Neg logit contributions | |
Kinnikuman | -3.243 |
scale | -3.115 |
�� | -2.997 |
cially | -2.901 |
utton | -2.894 |
Token | money |
Token ID | 1637 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
anan | +3.706 |
lie | +3.591 |
pell | +3.560 |
fug | +3.538 |
condem | +3.462 |
Neg logit contributions | |
Kinnikuman | -7.761 |
scale | -7.457 |
�� | -7.227 |
cially | -7.087 |
ザ | -6.977 |
Token | by |
Token ID | 416 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anan | +0.465 |
lie | +0.450 |
pell | +0.447 |
condem | +0.443 |
fug | +0.441 |
Neg logit contributions | |
Kinnikuman | -0.485 |
scale | -0.465 |
�� | -0.443 |
cially | -0.436 |
utton | -0.428 |
Token | Oct |
Token ID | 2556 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
anan | +1.247 |
lie | +1.209 |
pell | +1.201 |
condem | +1.195 |
fug | +1.186 |
Neg logit contributions | |
Kinnikuman | -1.488 |
scale | -1.424 |
�� | -1.368 |
cially | -1.340 |
utton | -1.321 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
anan | +2.683 |
lie | +2.590 |
pell | +2.557 |
fug | +2.522 |
condem | +2.521 |
Neg logit contributions | |
Kinnikuman | -3.191 |
scale | -3.067 |
�� | -2.914 |
cially | -2.877 |
utton | -2.822 |
Token | 17 |
Token ID | 1596 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
anan | +0.182 |
lie | +0.177 |
pell | +0.175 |
fug | +0.173 |
condem | +0.173 |
Neg logit contributions | |
Kinnikuman | -0.194 |
scale | -0.186 |
�� | -0.176 |
cially | -0.174 |
utton | -0.170 |
Token | � |
Token ID | 247 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
anan | +0.876 |
pell | +0.857 |
lie | +0.845 |
fug | +0.839 |
condem | +0.816 |
Neg logit contributions | |
Kinnikuman | -0.717 |
scale | -0.694 |
cially | -0.644 |
cade | -0.631 |
utton | -0.631 |
Token | s |
Token ID | 82 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
anan | +0.290 |
lie | +0.277 |
pell | +0.272 |
condem | +0.264 |
fug | +0.261 |
Neg logit contributions | |
Kinnikuman | -0.639 |
scale | -0.613 |
�� | -0.599 |
cially | -0.588 |
utton | -0.580 |
Token | been |
Token ID | 587 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
anan | +0.014 |
lie | +0.014 |
pell | +0.014 |
condem | +0.013 |
fug | +0.013 |
Neg logit contributions | |
Kinnikuman | -0.020 |
scale | -0.020 |
�� | -0.019 |
cially | -0.019 |
utton | -0.018 |
Token | made |
Token ID | 925 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Kinnikuman | +0.966 |
scale | +0.933 |
�� | +0.880 |
cially | +0.868 |
utton | +0.858 |
Neg logit contributions | |
anan | -0.953 |
lie | -0.921 |
pell | -0.915 |
condem | -0.912 |
fug | -0.907 |
Token | since |
Token ID | 1201 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
anan | +1.253 |
pell | +1.227 |
lie | +1.223 |
fug | +1.215 |
condem | +1.211 |
Neg logit contributions | |
Kinnikuman | -1.226 |
scale | -1.183 |
�� | -1.142 |
cially | -1.109 |
utton | -1.096 |
Token | owes |
Token ID | 29264 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
anan | +0.321 |
lie | +0.312 |
pell | +0.308 |
condem | +0.305 |
fug | +0.303 |
Neg logit contributions | |
Kinnikuman | -0.316 |
scale | -0.308 |
�� | -0.294 |
cially | -0.288 |
utton | -0.284 |
Token | something |
Token ID | 1223 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
anan | +5.816 |
pell | +5.591 |
lie | +5.579 |
fug | +5.559 |
condem | +5.321 |
Neg logit contributions | |
Kinnikuman | -5.405 |
scale | -5.318 |
cially | -4.971 |
�� | -4.970 |
utton | -4.876 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
anan | +2.908 |
lie | +2.783 |
pell | +2.767 |
fug | +2.723 |
condem | +2.719 |
Neg logit contributions | |
Kinnikuman | -3.617 |
scale | -3.483 |
�� | -3.315 |
cially | -3.290 |
utton | -3.247 |
Token | Annie |
Token ID | 25860 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
anan | +1.240 |
lie | +1.199 |
pell | +1.186 |
fug | +1.174 |
condem | +1.169 |
Neg logit contributions | |
Kinnikuman | -1.118 |
scale | -1.079 |
�� | -1.033 |
cially | -1.009 |
cade | -0.991 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Kinnikuman | +0.297 |
scale | +0.286 |
�� | +0.273 |
cially | +0.270 |
utton | +0.265 |
Neg logit contributions | |
anan | -0.211 |
lie | -0.200 |
pell | -0.199 |
condem | -0.199 |
fug | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Kinnikuman | +1.388 |
scale | +1.336 |
�� | +1.263 |
cially | +1.245 |
utton | +1.224 |
Neg logit contributions | |
anan | -1.376 |
lie | -1.326 |
condem | -1.314 |
pell | -1.314 |
fug | -1.297 |
Token | - |
Token ID | 12 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
Kinnikuman | +1.806 |
scale | +1.746 |
�� | +1.616 |
cially | +1.605 |
cade | +1.575 |
Neg logit contributions | |
anan | -1.866 |
lie | -1.797 |
condem | -1.785 |
pell | -1.775 |
fug | -1.756 |
Token | Author |
Token ID | 13838 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Kinnikuman | +0.453 |
scale | +0.432 |
�� | +0.411 |
cially | +0.404 |
utton | +0.396 |
Neg logit contributions | |
anan | -0.491 |
lie | -0.475 |
pell | -0.472 |
condem | -0.468 |
fug | -0.464 |
Token | itarian |
Token ID | 8353 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
anan | +2.034 |
lie | +1.985 |
pell | +1.961 |
condem | +1.955 |
fug | +1.953 |
Neg logit contributions | |
Kinnikuman | -1.183 |
scale | -1.102 |
�� | -1.070 |
cially | -1.007 |
utton | -0.999 |
Token | Movement |
Token ID | 15477 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Kinnikuman | +2.354 |
scale | +2.248 |
�� | +2.094 |
cially | +2.066 |
utton | +2.038 |
Neg logit contributions | |
anan | -2.611 |
lie | -2.512 |
pell | -2.511 |
condem | -2.509 |
fug | -2.474 |
Token | ( |
Token ID | 357 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Kinnikuman | +0.534 |
scale | +0.513 |
�� | +0.485 |
cially | +0.478 |
utton | +0.470 |
Neg logit contributions | |
anan | -0.552 |
lie | -0.532 |
pell | -0.528 |
condem | -0.525 |
fug | -0.521 |
Token | AK |
Token ID | 10206 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
anan | +1.365 |
lie | +1.288 |
pell | +1.284 |
condem | +1.266 |
fug | +1.257 |
Neg logit contributions | |
Kinnikuman | -1.655 |
scale | -1.577 |
�� | -1.517 |
cially | -1.493 |
utton | -1.464 |
Token | ) |
Token ID | 8 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
anan | +5.510 |
lie | +5.176 |
pell | +5.063 |
fug | +4.933 |
condem | +4.920 |
Neg logit contributions | |
Kinnikuman | -5.895 |
scale | -5.672 |
�� | -5.472 |
cially | -5.354 |
utton | -5.258 |
Token | in |
Token ID | 287 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
anan | +1.669 |
lie | +1.601 |
pell | +1.599 |
fug | +1.586 |
condem | +1.585 |
Neg logit contributions | |
Kinnikuman | -1.677 |
scale | -1.610 |
�� | -1.550 |
cially | -1.526 |
utton | -1.502 |
Token | relation |
Token ID | 8695 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
anan | +0.156 |
lie | +0.150 |
pell | +0.148 |
condem | +0.147 |
fug | +0.146 |
Neg logit contributions | |
Kinnikuman | -0.194 |
scale | -0.188 |
�� | -0.179 |
cially | -0.177 |
utton | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Kinnikuman | +1.968 |
scale | +1.893 |
�� | +1.821 |
cially | +1.781 |
utton | +1.757 |
Neg logit contributions | |
anan | -1.565 |
lie | -1.502 |
pell | -1.485 |
condem | -1.465 |
fug | -1.463 |
Token | the |
Token ID | 262 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
anan | +0.183 |
lie | +0.177 |
pell | +0.176 |
condem | +0.175 |
fug | +0.175 |
Neg logit contributions | |
Kinnikuman | -0.171 |
scale | -0.164 |
�� | -0.157 |
cially | -0.153 |
utton | -0.151 |
Token | Finland |
Token ID | 17837 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Kinnikuman | +1.363 |
scale | +1.309 |
�� | +1.239 |
cially | +1.222 |
utton | +1.200 |
Neg logit contributions | |
anan | -1.376 |
lie | -1.327 |
pell | -1.316 |
condem | -1.308 |
fug | -1.299 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Kinnikuman | +0.739 |
scale | +0.710 |
�� | +0.675 |
cially | +0.665 |
utton | +0.654 |
Neg logit contributions | |
anan | -0.701 |
lie | -0.676 |
pell | -0.670 |
condem | -0.665 |
fug | -0.661 |
Token |
|
Token ID | 198 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Kinnikuman | +0.361 |
scale | +0.346 |
�� | +0.331 |
cially | +0.324 |
utton | +0.319 |
Neg logit contributions | |
anan | -0.388 |
lie | -0.376 |
pell | -0.371 |
condem | -0.367 |
fug | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
anan | +0.334 |
lie | +0.331 |
pell | +0.323 |
fug | +0.312 |
Gott | +0.291 |
Neg logit contributions | |
Kinnikuman | -0.390 |
�� | -0.377 |
scale | -0.362 |
cially | -0.348 |
utton | -0.343 |
Token | Sa |
Token ID | 33890 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
anan | +0.136 |
lie | +0.134 |
pell | +0.131 |
fug | +0.128 |
condem | +0.126 |
Neg logit contributions | |
Kinnikuman | -0.114 |
scale | -0.106 |
�� | -0.103 |
cially | -0.100 |
utton | -0.099 |
Token | arak |
Token ID | 30447 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
anan | +0.819 |
pell | +0.749 |
lie | +0.740 |
fug | +0.720 |
condem | +0.681 |
Neg logit contributions | |
Kinnikuman | -1.638 |
scale | -1.558 |
�� | -1.535 |
cially | -1.472 |
ザ | -1.454 |
Token | k |
Token ID | 74 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
anan | +4.063 |
lie | +3.970 |
pell | +3.844 |
sen | +3.257 |
fug | +3.231 |
Neg logit contributions | |
Kinnikuman | -7.654 |
�� | -7.306 |
ザ | -6.971 |
scale | -6.901 |
cially | -6.735 |
Token | ala |
Token ID | 6081 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
anan | +2.320 |
lie | +2.246 |
pell | +2.168 |
fug | +1.990 |
lender | +1.877 |
Neg logit contributions | |
Kinnikuman | -2.856 |
�� | -2.716 |
scale | -2.658 |
ザ | -2.587 |
cially | -2.536 |
Token | , |
Token ID | 11 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
anan | +0.215 |
lie | +0.205 |
condem | +0.205 |
pell | +0.204 |
fug | +0.202 |
Neg logit contributions | |
Kinnikuman | -0.243 |
scale | -0.233 |
�� | -0.222 |
cially | -0.218 |
utton | -0.215 |
Token | 28 |
Token ID | 2579 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
anan | +0.583 |
lie | +0.557 |
pell | +0.556 |
condem | +0.554 |
fug | +0.552 |
Neg logit contributions | |
Kinnikuman | -0.540 |
scale | -0.518 |
�� | -0.492 |
cially | -0.481 |
utton | -0.474 |
Token | , |
Token ID | 11 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
Kinnikuman | +1.274 |
scale | +1.226 |
�� | +1.143 |
cially | +1.126 |
utton | +1.105 |
Neg logit contributions | |
anan | -1.546 |
condem | -1.483 |
lie | -1.470 |
pell | -1.470 |
fug | -1.442 |
Token | guilty |
Token ID | 6717 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Kinnikuman | +0.641 |
scale | +0.623 |
�� | +0.596 |
cially | +0.591 |
utton | +0.584 |
Neg logit contributions | |
anan | -0.338 |
lie | -0.320 |
pell | -0.316 |
condem | -0.313 |
fug | -0.309 |
Token | of |
Token ID | 286 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
anan | +0.175 |
lie | +0.169 |
pell | +0.168 |
condem | +0.166 |
fug | +0.165 |
Neg logit contributions | |
Kinnikuman | -0.181 |
scale | -0.174 |
�� | -0.165 |
cially | -0.163 |
utton | -0.160 |
Token | driving |
Token ID | 5059 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
anan | +1.495 |
fug | +1.461 |
pell | +1.455 |
lie | +1.450 |
condem | +1.433 |
Neg logit contributions | |
Kinnikuman | -2.335 |
scale | -2.242 |
�� | -2.196 |
cially | -2.133 |
utton | -2.073 |
Token | drunk |
Token ID | 10785 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
anan | +0.465 |
lie | +0.450 |
pell | +0.447 |
fug | +0.444 |
condem | +0.442 |
Neg logit contributions | |
Kinnikuman | -0.458 |
scale | -0.438 |
�� | -0.418 |
cially | -0.408 |
utton | -0.401 |
Token | and |
Token ID | 290 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
anan | +0.564 |
lie | +0.550 |
pell | +0.543 |
fug | +0.538 |
condem | +0.536 |
Neg logit contributions | |
Kinnikuman | -0.581 |
scale | -0.550 |
�� | -0.532 |
cially | -0.517 |
utton | -0.505 |
Token | crashing |
Token ID | 21899 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
anan | +1.147 |
fug | +1.120 |
lie | +1.100 |
condem | +1.100 |
pell | +1.092 |
Neg logit contributions | |
Kinnikuman | -1.720 |
scale | -1.653 |
�� | -1.602 |
cially | -1.564 |
utton | -1.536 |
Token | into |
Token ID | 656 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
anan | +5.445 |
lie | +5.435 |
fug | +5.377 |
pell | +5.356 |
condem | +5.206 |
Neg logit contributions | |
Kinnikuman | -5.597 |
�� | -5.426 |
scale | -5.331 |
ザ | -4.957 |
utton | -4.947 |
Token | a |
Token ID | 257 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
anan | +2.381 |
lie | +2.316 |
pell | +2.314 |
fug | +2.302 |
condem | +2.271 |
Neg logit contributions | |
Kinnikuman | -2.234 |
scale | -2.154 |
�� | -2.085 |
cially | -2.026 |
utton | -1.953 |
Token | car |
Token ID | 1097 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
anan | +0.883 |
pell | +0.846 |
lie | +0.844 |
condem | +0.838 |
fug | +0.837 |
Neg logit contributions | |
Kinnikuman | -1.111 |
scale | -1.071 |
�� | -1.033 |
cially | -1.012 |
utton | -0.990 |
Token | killing |
Token ID | 5170 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
anan | +0.561 |
lie | +0.547 |
pell | +0.539 |
fug | +0.534 |
condem | +0.533 |
Neg logit contributions | |
Kinnikuman | -0.600 |
scale | -0.572 |
�� | -0.560 |
cially | -0.537 |
utton | -0.526 |
Token | Dec |
Token ID | 4280 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Kinnikuman | +0.232 |
scale | +0.223 |
�� | +0.215 |
cially | +0.210 |
utton | +0.205 |
Neg logit contributions | |
anan | -0.227 |
lie | -0.220 |
pell | -0.218 |
condem | -0.215 |
fug | -0.215 |
Token | say |
Token ID | 910 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
anan | +0.260 |
lie | +0.250 |
pell | +0.247 |
condem | +0.246 |
fug | +0.244 |
Neg logit contributions | |
Kinnikuman | -0.351 |
scale | -0.336 |
�� | -0.324 |
cially | -0.318 |
utton | -0.313 |
Token | is |
Token ID | 318 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Kinnikuman | +1.332 |
scale | +1.280 |
�� | +1.189 |
cially | +1.186 |
utton | +1.161 |
Neg logit contributions | |
anan | -1.465 |
lie | -1.414 |
pell | -1.401 |
condem | -1.398 |
fug | -1.379 |
Token | that |
Token ID | 326 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
anan | +1.245 |
lie | +1.213 |
pell | +1.200 |
fug | +1.191 |
condem | +1.186 |
Neg logit contributions | |
Kinnikuman | -0.882 |
scale | -0.837 |
�� | -0.804 |
cially | -0.776 |
cade | -0.758 |
Token | they |
Token ID | 484 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
anan | +1.133 |
lie | +1.100 |
fug | +1.088 |
pell | +1.080 |
condem | +1.071 |
Neg logit contributions | |
Kinnikuman | -1.198 |
scale | -1.159 |
�� | -1.120 |
cially | -1.091 |
cade | -1.075 |
Token | were |
Token ID | 547 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
anan | +1.585 |
lie | +1.562 |
pell | +1.526 |
condem | +1.525 |
fug | +1.523 |
Neg logit contributions | |
Kinnikuman | -1.593 |
scale | -1.505 |
�� | -1.464 |
cially | -1.395 |
utton | -1.389 |
Token | redu |
Token ID | 2027 |
Feature activation | -8.05e+00 |
Pos logit contributions | |
anan | +1.587 |
lie | +1.541 |
pell | +1.535 |
fug | +1.532 |
condem | +1.527 |
Neg logit contributions | |
Kinnikuman | -1.804 |
scale | -1.728 |
�� | -1.654 |
cially | -1.607 |
utton | -1.594 |
Token | ctive |
Token ID | 14070 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
pell | +5.433 |
anan | +5.336 |
lie | +5.147 |
fug | +5.022 |
condem | +4.718 |
Neg logit contributions | |
Kinnikuman | -6.099 |
�� | -5.534 |
scale | -5.372 |
utton | -5.099 |
ebus | -5.083 |
Token | and |
Token ID | 290 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
anan | +1.927 |
lie | +1.897 |
fug | +1.877 |
pell | +1.853 |
condem | +1.850 |
Neg logit contributions | |
Kinnikuman | -2.160 |
scale | -2.062 |
�� | -2.016 |
cially | -1.954 |
cade | -1.918 |
Token | unilateral |
Token ID | 37095 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Kinnikuman | +0.550 |
scale | +0.529 |
�� | +0.503 |
cially | +0.496 |
utton | +0.488 |
Neg logit contributions | |
anan | -0.493 |
lie | -0.474 |
pell | -0.471 |
condem | -0.468 |
fug | -0.466 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Kinnikuman | +0.848 |
scale | +0.815 |
�� | +0.776 |
cially | +0.764 |
utton | +0.750 |
Neg logit contributions | |
anan | -0.795 |
lie | -0.767 |
pell | -0.759 |
condem | -0.755 |
fug | -0.750 |
Token | The |
Token ID | 383 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
anan | +0.074 |
lie | +0.072 |
pell | +0.070 |
fug | +0.070 |
condem | +0.069 |
Neg logit contributions | |
Kinnikuman | -0.069 |
scale | -0.067 |
�� | -0.066 |
cially | -0.063 |
utton | -0.062 |
Token | � |
Token ID | 247 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Kinnikuman | +0.402 |
scale | +0.382 |
cially | +0.348 |
�� | +0.344 |
utton | +0.337 |
Neg logit contributions | |
anan | -0.675 |
lie | -0.654 |
pell | -0.651 |
condem | -0.647 |
fug | -0.646 |
Token | s |
Token ID | 82 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Kinnikuman | +0.371 |
scale | +0.356 |
�� | +0.338 |
cially | +0.332 |
utton | +0.324 |
Neg logit contributions | |
anan | -0.386 |
lie | -0.373 |
pell | -0.370 |
condem | -0.366 |
fug | -0.364 |
Token | final |
Token ID | 2457 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
anan | +0.330 |
lie | +0.317 |
pell | +0.315 |
condem | +0.312 |
fug | +0.310 |
Neg logit contributions | |
Kinnikuman | -0.387 |
scale | -0.373 |
�� | -0.355 |
cially | -0.350 |
utton | -0.344 |
Token | European |
Token ID | 3427 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
anan | +0.377 |
lie | +0.362 |
pell | +0.359 |
condem | +0.355 |
fug | +0.353 |
Neg logit contributions | |
Kinnikuman | -0.467 |
scale | -0.450 |
�� | -0.430 |
cially | -0.423 |
utton | -0.415 |
Token | Rugby |
Token ID | 26244 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
anan | +3.141 |
lie | +3.093 |
pell | +3.027 |
fug | +3.020 |
condem | +2.976 |
Neg logit contributions | |
Kinnikuman | -4.172 |
scale | -3.991 |
�� | -3.816 |
cially | -3.794 |
utton | -3.698 |
Token | Champions |
Token ID | 6662 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
anan | +0.103 |
lie | +0.099 |
pell | +0.098 |
condem | +0.098 |
fug | +0.097 |
Neg logit contributions | |
Kinnikuman | -0.121 |
scale | -0.116 |
�� | -0.110 |
cially | -0.109 |
utton | -0.108 |
Token | Cup |
Token ID | 5454 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
anan | +3.757 |
lie | +3.756 |
pell | +3.624 |
fug | +3.500 |
condem | +3.417 |
Neg logit contributions | |
Kinnikuman | -7.396 |
scale | -7.053 |
�� | -6.764 |
ザ | -6.759 |
cially | -6.750 |
Token | pool |
Token ID | 5933 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
anan | +2.350 |
lie | +2.266 |
pell | +2.226 |
fug | +2.209 |
condem | +2.200 |
Neg logit contributions | |
Kinnikuman | -3.025 |
scale | -2.882 |
�� | -2.740 |
cially | -2.716 |
utton | -2.667 |
Token | match |
Token ID | 2872 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
anan | +1.143 |
lie | +1.113 |
pell | +1.079 |
fug | +1.075 |
condem | +1.068 |
Neg logit contributions | |
Kinnikuman | -1.429 |
scale | -1.358 |
�� | -1.305 |
cially | -1.290 |
utton | -1.257 |
Token | at |
Token ID | 379 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
anan | +1.004 |
lie | +0.969 |
pell | +0.959 |
condem | +0.940 |
fug | +0.939 |
Neg logit contributions | |
Kinnikuman | -1.290 |
scale | -1.239 |
�� | -1.194 |
cially | -1.166 |
utton | -1.148 |
Token | Wel |
Token ID | 22268 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Kinnikuman | +1.378 |
scale | +1.325 |
�� | +1.246 |
cially | +1.237 |
utton | +1.215 |
Neg logit contributions | |
anan | -1.384 |
lie | -1.333 |
pell | -1.323 |
condem | -1.317 |
fug | -1.308 |
Token | make |
Token ID | 787 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Kinnikuman | +0.391 |
scale | +0.376 |
�� | +0.360 |
cially | +0.353 |
utton | +0.347 |
Neg logit contributions | |
anan | -0.370 |
lie | -0.360 |
pell | -0.355 |
condem | -0.354 |
fug | -0.352 |
Token | a |
Token ID | 257 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
anan | +0.915 |
lie | +0.889 |
pell | +0.880 |
fug | +0.875 |
condem | +0.869 |
Neg logit contributions | |
Kinnikuman | -0.829 |
scale | -0.799 |
�� | -0.768 |
cially | -0.751 |
cade | -0.735 |
Token | scene |
Token ID | 3715 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
anan | +0.422 |
lie | +0.413 |
fug | +0.406 |
pell | +0.406 |
condem | +0.405 |
Neg logit contributions | |
Kinnikuman | -0.427 |
scale | -0.409 |
�� | -0.392 |
cially | -0.384 |
utton | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
anan | +0.090 |
lie | +0.087 |
pell | +0.086 |
fug | +0.085 |
condem | +0.085 |
Neg logit contributions | |
Kinnikuman | -0.095 |
scale | -0.091 |
�� | -0.087 |
cially | -0.085 |
utton | -0.084 |
Token | ( |
Token ID | 357 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
anan | +0.208 |
lie | +0.203 |
fug | +0.198 |
pell | +0.198 |
condem | +0.195 |
Neg logit contributions | |
Kinnikuman | -0.189 |
scale | -0.182 |
�� | -0.177 |
cially | -0.172 |
utton | -0.169 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
anan | +1.087 |
lie | +1.069 |
pell | +1.041 |
fug | +1.039 |
condem | +1.028 |
Neg logit contributions | |
Kinnikuman | -0.951 |
scale | -0.890 |
�� | -0.870 |
cially | -0.844 |
utton | -0.832 |
Token | � |
Token ID | 447 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anan | +6.556 |
lie | +6.516 |
fug | +6.243 |
pell | +6.213 |
condem | +6.027 |
Neg logit contributions | |
Kinnikuman | -4.625 |
scale | -4.215 |
�� | -4.167 |
cade | -3.893 |
cially | -3.868 |
Token | � |
Token ID | 247 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
anan | +0.852 |
lie | +0.824 |
pell | +0.823 |
condem | +0.814 |
fug | +0.811 |
Neg logit contributions | |
Kinnikuman | -0.588 |
scale | -0.561 |
cially | -0.515 |
�� | -0.514 |
utton | -0.504 |
Token | t |
Token ID | 83 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Kinnikuman | +0.173 |
scale | +0.165 |
�� | +0.158 |
cially | +0.155 |
utton | +0.152 |
Neg logit contributions | |
anan | -0.157 |
lie | -0.152 |
pell | -0.150 |
condem | -0.148 |
fug | -0.147 |
Token | get |
Token ID | 651 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
lie | +2.462 |
anan | +2.447 |
pell | +2.397 |
fug | +2.396 |
condem | +2.394 |
Neg logit contributions | |
Kinnikuman | -2.891 |
scale | -2.765 |
�� | -2.703 |
cially | -2.662 |
utton | -2.572 |
Token | so |
Token ID | 523 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
anan | +0.019 |
lie | +0.018 |
pell | +0.018 |
condem | +0.018 |
fug | +0.018 |
Neg logit contributions | |
Kinnikuman | -0.022 |
scale | -0.021 |
�� | -0.020 |
cially | -0.020 |
utton | -0.020 |
Token | Adapt |
Token ID | 48003 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Kinnikuman | +0.068 |
scale | +0.064 |
�� | +0.062 |
cially | +0.060 |
utton | +0.059 |
Neg logit contributions | |
anan | -0.084 |
lie | -0.082 |
pell | -0.081 |
fug | -0.079 |
condem | -0.078 |
Token | ed |
Token ID | 276 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
anan | +3.173 |
lie | +3.121 |
pell | +3.099 |
fug | +3.063 |
condem | +3.054 |
Neg logit contributions | |
Kinnikuman | -1.684 |
scale | -1.559 |
�� | -1.447 |
cially | -1.408 |
cade | -1.397 |
Token | from |
Token ID | 422 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anan | +0.952 |
lie | +0.925 |
pell | +0.917 |
fug | +0.911 |
condem | +0.909 |
Neg logit contributions | |
Kinnikuman | -0.734 |
scale | -0.702 |
�� | -0.662 |
cially | -0.652 |
utton | -0.637 |
Token | the |
Token ID | 262 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
anan | +1.398 |
lie | +1.353 |
pell | +1.338 |
fug | +1.324 |
condem | +1.317 |
Neg logit contributions | |
Kinnikuman | -1.337 |
scale | -1.288 |
�� | -1.223 |
cially | -1.215 |
utton | -1.179 |
Token | forthcoming |
Token ID | 21220 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
anan | +0.625 |
lie | +0.604 |
pell | +0.596 |
fug | +0.593 |
condem | +0.591 |
Neg logit contributions | |
Kinnikuman | -0.642 |
scale | -0.622 |
�� | -0.592 |
cially | -0.586 |
utton | -0.573 |
Token | book |
Token ID | 1492 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
anan | +1.929 |
lie | +1.871 |
pell | +1.842 |
fug | +1.836 |
condem | +1.816 |
Neg logit contributions | |
Kinnikuman | -2.038 |
scale | -1.977 |
�� | -1.891 |
cially | -1.876 |
utton | -1.838 |
Token | Future |
Token ID | 10898 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
anan | +5.380 |
lie | +5.338 |
pell | +5.145 |
fug | +5.128 |
condem | +4.962 |
Neg logit contributions | |
Kinnikuman | -5.446 |
scale | -5.190 |
cially | -5.125 |
�� | -5.077 |
utton | -4.948 |
Token | Crimes |
Token ID | 32655 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
Kinnikuman | +1.254 |
scale | +1.203 |
�� | +1.132 |
cially | +1.114 |
utton | +1.094 |
Neg logit contributions | |
anan | -1.430 |
lie | -1.379 |
pell | -1.371 |
condem | -1.365 |
fug | -1.352 |
Token | : |
Token ID | 25 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
anan | +0.666 |
lie | +0.647 |
pell | +0.643 |
condem | +0.634 |
fug | +0.632 |
Neg logit contributions | |
Kinnikuman | -0.720 |
scale | -0.688 |
�� | -0.657 |
cially | -0.651 |
utton | -0.638 |
Token | Everything |
Token ID | 11391 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
anan | +0.332 |
lie | +0.321 |
pell | +0.316 |
fug | +0.315 |
condem | +0.314 |
Neg logit contributions | |
Kinnikuman | -0.314 |
scale | -0.302 |
�� | -0.288 |
cially | -0.285 |
utton | -0.278 |
Token | Is |
Token ID | 1148 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
Kinnikuman | +0.854 |
scale | +0.819 |
�� | +0.773 |
cially | +0.763 |
utton | +0.750 |
Neg logit contributions | |
anan | -0.860 |
lie | -0.828 |
pell | -0.823 |
condem | -0.818 |
fug | -0.810 |
Token | may |
Token ID | 743 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Kinnikuman | +1.092 |
scale | +1.049 |
�� | +0.993 |
cially | +0.980 |
utton | +0.963 |
Neg logit contributions | |
anan | -1.088 |
lie | -1.048 |
pell | -1.040 |
condem | -1.033 |
fug | -1.025 |
Token | well |
Token ID | 880 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Kinnikuman | +1.481 |
scale | +1.429 |
�� | +1.334 |
cially | +1.321 |
utton | +1.297 |
Neg logit contributions | |
anan | -1.804 |
lie | -1.732 |
pell | -1.724 |
condem | -1.715 |
fug | -1.699 |
Token | be |
Token ID | 307 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Kinnikuman | +0.493 |
scale | +0.470 |
�� | +0.442 |
cially | +0.435 |
utton | +0.425 |
Neg logit contributions | |
anan | -0.624 |
lie | -0.605 |
pell | -0.601 |
condem | -0.598 |
fug | -0.594 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Kinnikuman | +1.095 |
scale | +1.049 |
�� | +0.991 |
cially | +0.977 |
utton | +0.957 |
Neg logit contributions | |
anan | -1.205 |
lie | -1.163 |
pell | -1.154 |
condem | -1.145 |
fug | -1.135 |
Token | as |
Token ID | 355 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
anan | +0.857 |
lie | +0.832 |
pell | +0.824 |
fug | +0.822 |
condem | +0.817 |
Neg logit contributions | |
Kinnikuman | -0.816 |
scale | -0.783 |
�� | -0.751 |
cially | -0.733 |
utton | -0.717 |
Token | consensus |
Token ID | 11529 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
Kinnikuman | +0.109 |
scale | +0.106 |
�� | +0.100 |
cially | +0.098 |
utton | +0.097 |
Neg logit contributions | |
anan | -0.115 |
lie | -0.112 |
pell | -0.111 |
fug | -0.110 |
condem | -0.110 |
Token | opinion |
Token ID | 4459 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Kinnikuman | +3.691 |
scale | +3.552 |
�� | +3.369 |
cially | +3.314 |
cade | +3.252 |
Neg logit contributions | |
anan | -3.776 |
lie | -3.643 |
pell | -3.609 |
condem | -3.584 |
fug | -3.536 |
Token | has |
Token ID | 468 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Kinnikuman | +1.657 |
scale | +1.591 |
�� | +1.506 |
cially | +1.485 |
utton | +1.458 |
Neg logit contributions | |
anan | -1.686 |
lie | -1.626 |
pell | -1.613 |
condem | -1.604 |
fug | -1.591 |
Token | it |
Token ID | 340 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Kinnikuman | +1.898 |
scale | +1.809 |
�� | +1.704 |
cially | +1.687 |
utton | +1.638 |
Neg logit contributions | |
anan | -2.240 |
lie | -2.164 |
pell | -2.137 |
condem | -2.133 |
fug | -2.107 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Kinnikuman | +1.545 |
scale | +1.477 |
�� | +1.389 |
cially | +1.374 |
utton | +1.335 |
Neg logit contributions | |
anan | -1.869 |
condem | -1.779 |
pell | -1.773 |
lie | -1.772 |
fug | -1.740 |
Token | a |
Token ID | 257 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
anan | +0.938 |
lie | +0.912 |
pell | +0.901 |
fug | +0.900 |
condem | +0.900 |
Neg logit contributions | |
Kinnikuman | -0.872 |
scale | -0.837 |
�� | -0.790 |
cially | -0.778 |
utton | -0.766 |
Token | to |
Token ID | 284 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
anan | +0.207 |
lie | +0.201 |
pell | +0.199 |
condem | +0.197 |
fug | +0.197 |
Neg logit contributions | |
Kinnikuman | -0.211 |
scale | -0.201 |
�� | -0.191 |
cially | -0.190 |
utton | -0.186 |
Token | its |
Token ID | 663 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Kinnikuman | +0.360 |
scale | +0.342 |
�� | +0.326 |
cially | +0.323 |
utton | +0.317 |
Neg logit contributions | |
anan | -0.356 |
lie | -0.343 |
pell | -0.341 |
condem | -0.337 |
fug | -0.334 |
Token | slate |
Token ID | 27589 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
Kinnikuman | +1.719 |
scale | +1.651 |
�� | +1.555 |
cially | +1.531 |
utton | +1.498 |
Neg logit contributions | |
anan | -1.934 |
lie | -1.868 |
pell | -1.852 |
condem | -1.840 |
fug | -1.822 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Kinnikuman | +1.666 |
scale | +1.599 |
�� | +1.482 |
cially | +1.459 |
utton | +1.435 |
Neg logit contributions | |
anan | -2.214 |
lie | -2.140 |
pell | -2.124 |
condem | -2.118 |
fug | -2.094 |
Token | In |
Token ID | 554 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Kinnikuman | +0.420 |
scale | +0.402 |
�� | +0.390 |
cially | +0.379 |
utton | +0.372 |
Neg logit contributions | |
anan | -0.464 |
lie | -0.453 |
pell | -0.444 |
fug | -0.437 |
condem | -0.436 |
Token | honor |
Token ID | 7522 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
anan | +0.011 |
lie | +0.011 |
pell | +0.011 |
condem | +0.011 |
fug | +0.011 |
Neg logit contributions | |
Kinnikuman | -0.011 |
scale | -0.011 |
�� | -0.010 |
cially | -0.010 |
utton | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Kinnikuman | +3.894 |
scale | +3.722 |
�� | +3.471 |
cially | +3.428 |
utton | +3.354 |
Neg logit contributions | |
anan | -5.271 |
lie | -5.106 |
pell | -5.073 |
condem | -5.063 |
fug | -5.012 |
Token | its |
Token ID | 663 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Kinnikuman | +1.433 |
scale | +1.373 |
�� | +1.292 |
cially | +1.271 |
utton | +1.247 |
Neg logit contributions | |
anan | -1.688 |
lie | -1.632 |
pell | -1.619 |
condem | -1.612 |
fug | -1.598 |
Token | premiere |
Token ID | 19245 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Kinnikuman | +2.037 |
scale | +1.957 |
�� | +1.849 |
cially | +1.822 |
utton | +1.790 |
Neg logit contributions | |
anan | -2.101 |
lie | -2.025 |
pell | -2.008 |
condem | -1.997 |
fug | -1.979 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Kinnikuman | +0.406 |
scale | +0.389 |
�� | +0.369 |
cially | +0.363 |
utton | +0.358 |
Neg logit contributions | |
anan | -0.397 |
lie | -0.382 |
pell | -0.377 |
condem | -0.376 |
fug | -0.374 |
Token | of |
Token ID | 286 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
anan | +0.841 |
lie | +0.808 |
condem | +0.807 |
pell | +0.798 |
fug | +0.796 |
Neg logit contributions | |
Kinnikuman | -0.777 |
scale | -0.743 |
�� | -0.711 |
cially | -0.695 |
utton | -0.684 |
Token | health |
Token ID | 1535 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
anan | +0.003 |
lie | +0.003 |
pell | +0.003 |
fug | +0.003 |
condem | +0.003 |
Neg logit contributions | |
Kinnikuman | -0.004 |
scale | -0.004 |
�� | -0.004 |
cially | -0.004 |
utton | -0.004 |
Token | risks |
Token ID | 7476 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Kinnikuman | +3.909 |
scale | +3.879 |
�� | +3.614 |
cially | +3.607 |
utton | +3.539 |
Neg logit contributions | |
anan | -2.865 |
lie | -2.715 |
pell | -2.701 |
condem | -2.663 |
fug | -2.631 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Kinnikuman | +1.870 |
scale | +1.809 |
�� | +1.689 |
cially | +1.670 |
utton | +1.633 |
Neg logit contributions | |
anan | -2.120 |
lie | -2.036 |
pell | -2.020 |
condem | -2.014 |
fug | -1.986 |
Token | the |
Token ID | 262 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Kinnikuman | +0.886 |
scale | +0.844 |
�� | +0.808 |
cially | +0.793 |
utton | +0.778 |
Neg logit contributions | |
anan | -0.853 |
lie | -0.825 |
pell | -0.816 |
condem | -0.812 |
fug | -0.810 |
Token | crisis |
Token ID | 4902 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Kinnikuman | +0.523 |
scale | +0.500 |
�� | +0.479 |
cially | +0.472 |
utton | +0.463 |
Neg logit contributions | |
anan | -0.467 |
lie | -0.452 |
pell | -0.447 |
condem | -0.444 |
fug | -0.444 |
Token | at |
Token ID | 379 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Kinnikuman | +0.719 |
scale | +0.685 |
�� | +0.655 |
cially | +0.640 |
utton | +0.634 |
Neg logit contributions | |
anan | -0.719 |
lie | -0.698 |
pell | -0.689 |
condem | -0.688 |
fug | -0.684 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Kinnikuman | +3.358 |
scale | +3.286 |
�� | +2.995 |
cially | +2.983 |
utton | +2.949 |
Neg logit contributions | |
anan | -4.084 |
condem | -3.930 |
pell | -3.898 |
lie | -3.868 |
fug | -3.832 |
Token | Fukushima |
Token ID | 34170 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
Kinnikuman | +2.578 |
scale | +2.482 |
�� | +2.333 |
cially | +2.299 |
utton | +2.257 |
Neg logit contributions | |
anan | -2.897 |
lie | -2.792 |
pell | -2.774 |
condem | -2.761 |
fug | -2.731 |
Token | plant |
Token ID | 4618 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Kinnikuman | +2.559 |
scale | +2.499 |
�� | +2.328 |
cially | +2.272 |
utton | +2.224 |
Neg logit contributions | |
anan | -3.496 |
lie | -3.381 |
pell | -3.368 |
condem | -3.351 |
fug | -3.303 |
Token | has |
Token ID | 468 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Kinnikuman | +1.502 |
scale | +1.438 |
�� | +1.362 |
cially | +1.341 |
utton | +1.319 |
Neg logit contributions | |
anan | -1.581 |
lie | -1.528 |
pell | -1.514 |
condem | -1.507 |
fug | -1.496 |
Token | worsened |
Token ID | 44838 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Kinnikuman | +0.924 |
scale | +0.884 |
�� | +0.838 |
cially | +0.823 |
utton | +0.813 |
Neg logit contributions | |
anan | -0.948 |
lie | -0.915 |
pell | -0.908 |
condem | -0.906 |
fug | -0.898 |
Token | think |
Token ID | 892 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
anan | +0.460 |
lie | +0.451 |
pell | +0.446 |
condem | +0.446 |
fug | +0.441 |
Neg logit contributions | |
Kinnikuman | -0.474 |
scale | -0.447 |
�� | -0.433 |
cially | -0.421 |
utton | -0.411 |
Token | there |
Token ID | 612 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Kinnikuman | +2.769 |
scale | +2.658 |
�� | +2.489 |
cially | +2.471 |
utton | +2.406 |
Neg logit contributions | |
anan | -3.149 |
lie | -3.033 |
pell | -3.009 |
condem | -2.983 |
fug | -2.953 |
Token | will |
Token ID | 481 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
Kinnikuman | +0.692 |
scale | +0.664 |
�� | +0.628 |
cially | +0.618 |
utton | +0.607 |
Neg logit contributions | |
anan | -0.730 |
lie | -0.705 |
pell | -0.698 |
condem | -0.695 |
fug | -0.690 |
Token | be |
Token ID | 307 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Kinnikuman | +2.101 |
scale | +2.036 |
�� | +1.886 |
cially | +1.864 |
utton | +1.822 |
Neg logit contributions | |
anan | -2.706 |
pell | -2.588 |
lie | -2.580 |
condem | -2.563 |
fug | -2.541 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Kinnikuman | +2.581 |
scale | +2.479 |
�� | +2.310 |
cially | +2.289 |
utton | +2.233 |
Neg logit contributions | |
anan | -3.193 |
lie | -3.075 |
pell | -3.056 |
condem | -3.029 |
fug | -3.000 |
Token | division |
Token ID | 7297 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
Kinnikuman | +0.982 |
scale | +0.944 |
�� | +0.900 |
cially | +0.885 |
utton | +0.874 |
Neg logit contributions | |
anan | -0.858 |
lie | -0.829 |
pell | -0.820 |
condem | -0.818 |
fug | -0.812 |
Token | of |
Token ID | 286 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Kinnikuman | +4.063 |
scale | +3.978 |
cially | +3.663 |
�� | +3.630 |
cade | +3.535 |
Neg logit contributions | |
anan | -5.047 |
lie | -4.820 |
pell | -4.775 |
condem | -4.757 |
fug | -4.689 |
Token | Syria |
Token ID | 4392 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Kinnikuman | +1.603 |
scale | +1.544 |
�� | +1.466 |
cially | +1.447 |
utton | +1.423 |
Neg logit contributions | |
anan | -1.432 |
lie | -1.377 |
pell | -1.366 |
condem | -1.357 |
fug | -1.345 |
Token | ," |
Token ID | 553 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
anan | +0.115 |
lie | +0.112 |
pell | +0.111 |
fug | +0.110 |
condem | +0.110 |
Neg logit contributions | |
Kinnikuman | -0.119 |
scale | -0.112 |
�� | -0.109 |
cially | -0.105 |
utton | -0.105 |
Token | he |
Token ID | 339 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
Kinnikuman | +0.759 |
scale | +0.724 |
�� | +0.681 |
cially | +0.669 |
utton | +0.655 |
Neg logit contributions | |
anan | -1.006 |
lie | -0.975 |
pell | -0.968 |
condem | -0.962 |
fug | -0.956 |
Token | said |
Token ID | 531 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
Kinnikuman | +0.477 |
scale | +0.460 |
�� | +0.437 |
cially | +0.432 |
utton | +0.425 |
Neg logit contributions | |
anan | -0.400 |
lie | -0.384 |
pell | -0.381 |
condem | -0.378 |
fug | -0.375 |
Token | ) |
Token ID | 8 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
anan | +2.078 |
lie | +2.001 |
pell | +1.984 |
fug | +1.918 |
condem | +1.899 |
Neg logit contributions | |
Kinnikuman | -2.998 |
scale | -2.898 |
�� | -2.783 |
cially | -2.760 |
utton | -2.698 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
anan | +2.361 |
lie | +2.269 |
pell | +2.263 |
fug | +2.239 |
condem | +2.178 |
Neg logit contributions | |
Kinnikuman | -2.788 |
scale | -2.687 |
�� | -2.591 |
cially | -2.519 |
utton | -2.496 |
Token |
|
Token ID | 198 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
anan | +0.876 |
lie | +0.868 |
pell | +0.846 |
fug | +0.816 |
Gott | +0.764 |
Neg logit contributions | |
Kinnikuman | -1.050 |
�� | -1.025 |
scale | -0.966 |
cially | -0.936 |
utton | -0.917 |
Token | Lu |
Token ID | 25596 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
anan | +0.594 |
lie | +0.578 |
pell | +0.572 |
fug | +0.557 |
condem | +0.555 |
Neg logit contributions | |
Kinnikuman | -0.546 |
scale | -0.518 |
�� | -0.498 |
cially | -0.483 |
utton | -0.475 |
Token | is |
Token ID | 271 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
Kinnikuman | +0.264 |
scale | +0.252 |
�� | +0.234 |
cially | +0.231 |
utton | +0.225 |
Neg logit contributions | |
anan | -0.397 |
lie | -0.385 |
pell | -0.383 |
condem | -0.382 |
fug | -0.379 |
Token | Moreno |
Token ID | 43269 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
anan | +0.641 |
lie | +0.616 |
pell | +0.611 |
condem | +0.607 |
fug | +0.602 |
Neg logit contributions | |
Kinnikuman | -0.720 |
scale | -0.693 |
�� | -0.659 |
cially | -0.650 |
utton | -0.639 |
Token | is |
Token ID | 318 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Kinnikuman | +3.999 |
scale | +3.768 |
cially | +3.570 |
�� | +3.522 |
utton | +3.482 |
Neg logit contributions | |
anan | -4.722 |
lie | -4.615 |
condem | -4.608 |
pell | -4.506 |
fug | -4.462 |
Token | Research |
Token ID | 4992 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Kinnikuman | +0.510 |
scale | +0.489 |
�� | +0.462 |
cially | +0.454 |
utton | +0.445 |
Neg logit contributions | |
anan | -0.576 |
lie | -0.556 |
pell | -0.553 |
condem | -0.548 |
fug | -0.545 |
Token | Professor |
Token ID | 8129 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
anan | +1.412 |
lie | +1.385 |
pell | +1.357 |
fug | +1.342 |
condem | +1.327 |
Neg logit contributions | |
Kinnikuman | -1.600 |
scale | -1.531 |
�� | -1.472 |
cially | -1.427 |
utton | -1.413 |
Token | at |
Token ID | 379 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Kinnikuman | +0.947 |
scale | +0.907 |
�� | +0.849 |
cially | +0.840 |
utton | +0.821 |
Neg logit contributions | |
anan | -1.164 |
lie | -1.123 |
pell | -1.117 |
condem | -1.115 |
fug | -1.103 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Kinnikuman | +1.951 |
scale | +1.862 |
cially | +1.727 |
�� | +1.726 |
utton | +1.694 |
Neg logit contributions | |
anan | -2.186 |
condem | -2.103 |
pell | -2.090 |
lie | -2.089 |
fug | -2.064 |
Token | on |
Token ID | 319 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anan | +0.901 |
lie | +0.873 |
pell | +0.863 |
condem | +0.850 |
fug | +0.849 |
Neg logit contributions | |
Kinnikuman | -1.021 |
scale | -0.972 |
�� | -0.931 |
cially | -0.913 |
utton | -0.904 |
Token | : |
Token ID | 25 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Kinnikuman | +1.220 |
scale | +1.170 |
�� | +1.103 |
cially | +1.090 |
utton | +1.067 |
Neg logit contributions | |
anan | -1.324 |
lie | -1.278 |
pell | -1.267 |
condem | -1.262 |
fug | -1.250 |
Token |
|
Token ID | 198 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
anan | +0.334 |
lie | +0.321 |
pell | +0.320 |
condem | +0.318 |
fug | +0.317 |
Neg logit contributions | |
Kinnikuman | -0.322 |
scale | -0.307 |
�� | -0.294 |
cially | -0.289 |
utton | -0.283 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
anan | +0.332 |
lie | +0.327 |
pell | +0.320 |
fug | +0.310 |
Gott | +0.288 |
Neg logit contributions | |
Kinnikuman | -0.378 |
�� | -0.363 |
scale | -0.349 |
cially | -0.337 |
utton | -0.331 |
Token | Trans |
Token ID | 8291 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
anan | +0.190 |
lie | +0.185 |
pell | +0.183 |
fug | +0.180 |
condem | +0.179 |
Neg logit contributions | |
Kinnikuman | -0.160 |
scale | -0.150 |
�� | -0.144 |
cially | -0.141 |
utton | -0.139 |
Token | actions |
Token ID | 4658 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
anan | +2.209 |
lie | +2.154 |
pell | +2.144 |
fug | +2.091 |
condem | +2.048 |
Neg logit contributions | |
Kinnikuman | -2.762 |
scale | -2.585 |
�� | -2.531 |
cially | -2.440 |
utton | -2.427 |
Token | in |
Token ID | 287 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Kinnikuman | +1.745 |
scale | +1.680 |
�� | +1.580 |
cially | +1.565 |
utton | +1.536 |
Neg logit contributions | |
anan | -1.802 |
lie | -1.737 |
pell | -1.720 |
condem | -1.713 |
fug | -1.695 |
Token | database |
Token ID | 6831 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Kinnikuman | +0.773 |
scale | +0.742 |
�� | +0.702 |
cially | +0.692 |
utton | +0.679 |
Neg logit contributions | |
anan | -0.822 |
lie | -0.794 |
pell | -0.788 |
condem | -0.782 |
fug | -0.777 |
Token | systems |
Token ID | 3341 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
anan | +1.019 |
lie | +0.976 |
pell | +0.974 |
condem | +0.970 |
fug | +0.968 |
Neg logit contributions | |
Kinnikuman | -1.146 |
scale | -1.089 |
�� | -1.056 |
cially | -1.036 |
utton | -1.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anan | +0.831 |
lie | +0.808 |
pell | +0.807 |
fug | +0.795 |
condem | +0.794 |
Neg logit contributions | |
Kinnikuman | -0.866 |
scale | -0.827 |
�� | -0.801 |
cially | -0.780 |
utton | -0.767 |
Token |
|
Token ID | 198 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
anan | +0.711 |
lie | +0.705 |
pell | +0.686 |
fug | +0.661 |
Gott | +0.621 |
Neg logit contributions | |
Kinnikuman | -0.846 |
�� | -0.822 |
scale | -0.777 |
cially | -0.754 |
utton | -0.740 |
Token | Tom |
Token ID | 13787 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
anan | +1.164 |
lie | +1.136 |
pell | +1.110 |
condem | +1.085 |
fug | +1.084 |
Neg logit contributions | |
Kinnikuman | -1.128 |
scale | -1.067 |
�� | -1.029 |
cially | -1.009 |
utton | -0.981 |
Token | Ret |
Token ID | 4990 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
anan | +0.250 |
lie | +0.243 |
pell | +0.240 |
condem | +0.238 |
fug | +0.236 |
Neg logit contributions | |
Kinnikuman | -0.186 |
scale | -0.177 |
�� | -0.167 |
cially | -0.164 |
utton | -0.160 |
Token | ired |
Token ID | 1202 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
Kinnikuman | +0.756 |
scale | +0.718 |
�� | +0.679 |
cially | +0.665 |
utton | +0.648 |
Neg logit contributions | |
anan | -0.970 |
lie | -0.942 |
pell | -0.934 |
condem | -0.924 |
fug | -0.917 |
Token | - |
Token ID | 12 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
Kinnikuman | +4.191 |
scale | +4.044 |
�� | +3.811 |
cially | +3.703 |
cade | +3.655 |
Neg logit contributions | |
anan | -4.758 |
condem | -4.683 |
fug | -4.580 |
pell | -4.578 |
lie | -4.553 |
Token | 08 |
Token ID | 2919 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Kinnikuman | +0.418 |
scale | +0.398 |
�� | +0.379 |
cially | +0.372 |
utton | +0.364 |
Neg logit contributions | |
anan | -0.468 |
lie | -0.453 |
pell | -0.448 |
condem | -0.443 |
fug | -0.440 |
Token | Election |
Token ID | 14219 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
anan | +0.247 |
lie | +0.240 |
pell | +0.238 |
condem | +0.237 |
fug | +0.235 |
Neg logit contributions | |
Kinnikuman | -0.159 |
scale | -0.151 |
�� | -0.141 |
cially | -0.138 |
utton | -0.135 |
Token | - |
Token ID | 12 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Kinnikuman | +2.731 |
scale | +2.619 |
�� | +2.490 |
cially | +2.411 |
utton | +2.382 |
Neg logit contributions | |
anan | -3.020 |
condem | -2.952 |
lie | -2.899 |
pell | -2.898 |
fug | -2.884 |
Token | F |
Token ID | 37 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
anan | +0.281 |
lie | +0.273 |
pell | +0.269 |
condem | +0.264 |
fug | +0.263 |
Neg logit contributions | |
Kinnikuman | -0.254 |
scale | -0.241 |
�� | -0.231 |
cially | -0.226 |
utton | -0.221 |
Token | inger |
Token ID | 3889 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
Kinnikuman | +3.263 |
scale | +3.182 |
�� | +2.980 |
cially | +2.973 |
utton | +2.934 |
Neg logit contributions | |
anan | -3.132 |
pell | -3.016 |
condem | -3.006 |
lie | -3.003 |
fug | -2.976 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Kinnikuman | +3.265 |
scale | +3.176 |
�� | +2.984 |
cially | +2.959 |
cade | +2.900 |
Neg logit contributions | |
anan | -3.318 |
condem | -3.160 |
lie | -3.154 |
pell | -3.128 |
fug | -3.120 |
Token | Tech |
Token ID | 9634 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Kinnikuman | +1.627 |
scale | +1.568 |
�� | +1.479 |
cially | +1.459 |
utton | +1.433 |
Neg logit contributions | |
anan | -1.645 |
lie | -1.582 |
condem | -1.573 |
pell | -1.572 |
fug | -1.555 |
Token | if |
Token ID | 611 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Kinnikuman | +0.928 |
scale | +0.883 |
�� | +0.836 |
cially | +0.819 |
utton | +0.803 |
Neg logit contributions | |
anan | -1.158 |
lie | -1.122 |
pell | -1.118 |
condem | -1.111 |
fug | -1.107 |
Token | I |
Token ID | 314 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Kinnikuman | +0.528 |
scale | +0.505 |
�� | +0.479 |
cially | +0.471 |
utton | +0.464 |
Neg logit contributions | |
anan | -0.548 |
lie | -0.530 |
pell | -0.526 |
condem | -0.523 |
fug | -0.521 |
Token | 'm |
Token ID | 1101 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
anan | +0.269 |
lie | +0.263 |
condem | +0.260 |
pell | +0.259 |
fug | +0.258 |
Neg logit contributions | |
Kinnikuman | -0.236 |
scale | -0.223 |
�� | -0.214 |
cially | -0.208 |
utton | -0.203 |
Token | making |
Token ID | 1642 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
anan | +0.371 |
lie | +0.359 |
condem | +0.359 |
pell | +0.358 |
fug | +0.355 |
Neg logit contributions | |
Kinnikuman | -0.412 |
scale | -0.397 |
�� | -0.375 |
cially | -0.369 |
utton | -0.366 |
Token | news |
Token ID | 1705 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Kinnikuman | +0.284 |
scale | +0.271 |
�� | +0.256 |
cially | +0.253 |
utton | +0.248 |
Neg logit contributions | |
anan | -0.311 |
lie | -0.300 |
pell | -0.299 |
fug | -0.298 |
condem | -0.297 |
Token | here |
Token ID | 994 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Kinnikuman | +1.587 |
scale | +1.514 |
�� | +1.432 |
cially | +1.409 |
utton | +1.384 |
Neg logit contributions | |
anan | -1.783 |
lie | -1.726 |
pell | -1.713 |
condem | -1.702 |
fug | -1.693 |
Token | ," |
Token ID | 553 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Kinnikuman | +0.448 |
scale | +0.426 |
�� | +0.405 |
cially | +0.398 |
utton | +0.391 |
Neg logit contributions | |
anan | -0.459 |
lie | -0.444 |
pell | -0.443 |
condem | -0.436 |
fug | -0.436 |
Token | National |
Token ID | 2351 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Kinnikuman | +1.200 |
scale | +1.155 |
�� | +1.096 |
cially | +1.082 |
utton | +1.063 |
Neg logit contributions | |
anan | -1.099 |
lie | -1.057 |
pell | -1.048 |
condem | -1.042 |
fug | -1.033 |
Token | Review |
Token ID | 6602 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Kinnikuman | +1.408 |
scale | +1.353 |
�� | +1.280 |
cially | +1.263 |
utton | +1.240 |
Neg logit contributions | |
anan | -1.413 |
lie | -1.362 |
pell | -1.351 |
condem | -1.343 |
fug | -1.333 |
Token | 's |
Token ID | 338 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Kinnikuman | +0.216 |
scale | +0.208 |
�� | +0.197 |
cially | +0.195 |
utton | +0.190 |
Neg logit contributions | |
anan | -0.192 |
lie | -0.184 |
pell | -0.182 |
condem | -0.182 |
fug | -0.180 |
Token | Jonah |
Token ID | 45447 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Kinnikuman | +0.214 |
scale | +0.207 |
�� | +0.196 |
cially | +0.194 |
utton | +0.191 |
Neg logit contributions | |
anan | -0.183 |
lie | -0.177 |
pell | -0.175 |
condem | -0.173 |
fug | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Kinnikuman | +0.775 |
scale | +0.748 |
�� | +0.703 |
cially | +0.695 |
utton | +0.681 |
Neg logit contributions | |
anan | -0.855 |
lie | -0.822 |
condem | -0.815 |
pell | -0.812 |
fug | -0.805 |
Token | Pages |
Token ID | 28221 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Kinnikuman | +0.338 |
scale | +0.324 |
�� | +0.309 |
cially | +0.303 |
utton | +0.297 |
Neg logit contributions | |
anan | -0.359 |
pell | -0.347 |
lie | -0.347 |
condem | -0.341 |
fug | -0.341 |
Token | and |
Token ID | 290 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
anan | +1.448 |
pell | +1.425 |
lie | +1.404 |
condem | +1.394 |
fug | +1.386 |
Neg logit contributions | |
Kinnikuman | -1.547 |
scale | -1.470 |
�� | -1.426 |
cially | -1.398 |
utton | -1.357 |
Token | company |
Token ID | 1664 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
anan | +0.062 |
lie | +0.060 |
pell | +0.060 |
condem | +0.059 |
fug | +0.059 |
Neg logit contributions | |
Kinnikuman | -0.056 |
scale | -0.054 |
�� | -0.051 |
cially | -0.050 |
utton | -0.049 |
Token | have |
Token ID | 423 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Kinnikuman | +0.400 |
scale | +0.383 |
�� | +0.363 |
cially | +0.357 |
utton | +0.352 |
Neg logit contributions | |
anan | -0.430 |
lie | -0.417 |
pell | -0.416 |
condem | -0.412 |
fug | -0.410 |
Token | undergone |
Token ID | 29900 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
anan | +0.186 |
lie | +0.179 |
pell | +0.179 |
condem | +0.179 |
fug | +0.178 |
Neg logit contributions | |
Kinnikuman | -0.186 |
scale | -0.178 |
�� | -0.169 |
cially | -0.166 |
utton | -0.165 |
Token | an |
Token ID | 281 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Kinnikuman | +0.978 |
scale | +0.938 |
�� | +0.888 |
cially | +0.876 |
utton | +0.861 |
Neg logit contributions | |
anan | -1.019 |
lie | -0.985 |
pell | -0.978 |
condem | -0.971 |
fug | -0.965 |
Token | extensive |
Token ID | 7667 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Kinnikuman | +1.397 |
scale | +1.332 |
�� | +1.253 |
cially | +1.234 |
utton | +1.210 |
Neg logit contributions | |
anan | -1.776 |
lie | -1.720 |
pell | -1.707 |
condem | -1.699 |
fug | -1.688 |
Token | Apple |
Token ID | 4196 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Kinnikuman | +2.207 |
scale | +2.141 |
�� | +2.014 |
cially | +1.986 |
utton | +1.950 |
Neg logit contributions | |
anan | -2.007 |
lie | -1.922 |
pell | -1.898 |
condem | -1.891 |
fug | -1.867 |
Token | Script |
Token ID | 7391 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Kinnikuman | +0.569 |
scale | +0.544 |
�� | +0.516 |
cially | +0.509 |
utton | +0.499 |
Neg logit contributions | |
anan | -0.594 |
lie | -0.575 |
pell | -0.570 |
condem | -0.567 |
fug | -0.563 |
Token | ectomy |
Token ID | 42505 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
anan | +1.877 |
pell | +1.861 |
lie | +1.847 |
condem | +1.842 |
fug | +1.825 |
Neg logit contributions | |
Kinnikuman | -1.946 |
scale | -1.816 |
cially | -1.738 |
�� | -1.733 |
utton | -1.702 |
Token | How |
Token ID | 2437 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
anan | +0.419 |
lie | +0.413 |
pell | +0.406 |
fug | +0.395 |
condem | +0.391 |
Neg logit contributions | |
Kinnikuman | -0.341 |
scale | -0.316 |
�� | -0.307 |
cially | -0.298 |
utton | -0.292 |
Token | will |
Token ID | 481 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
anan | +2.289 |
lie | +2.203 |
pell | +2.192 |
condem | +2.176 |
fug | +2.173 |
Neg logit contributions | |
Kinnikuman | -2.716 |
scale | -2.595 |
�� | -2.532 |
cially | -2.446 |
utton | -2.444 |
Token | you |
Token ID | 345 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Kinnikuman | +0.921 |
scale | +0.887 |
�� | +0.840 |
cially | +0.830 |
utton | +0.814 |
Neg logit contributions | |
anan | -0.864 |
lie | -0.830 |
pell | -0.822 |
condem | -0.818 |
fug | -0.810 |
Token | build |
Token ID | 1382 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Kinnikuman | +0.913 |
scale | +0.872 |
�� | +0.826 |
cially | +0.813 |
utton | +0.798 |
Neg logit contributions | |
anan | -1.015 |
lie | -0.983 |
pell | -0.977 |
condem | -0.970 |
fug | -0.964 |
Token | suspense |
Token ID | 43527 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
anan | +0.407 |
lie | +0.395 |
pell | +0.394 |
fug | +0.390 |
condem | +0.389 |
Neg logit contributions | |
Kinnikuman | -0.399 |
scale | -0.377 |
�� | -0.363 |
cially | -0.356 |
utton | -0.350 |
Token | and |
Token ID | 290 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Kinnikuman | +0.171 |
scale | +0.162 |
�� | +0.155 |
cially | +0.152 |
utton | +0.150 |
Neg logit contributions | |
anan | -0.178 |
lie | -0.174 |
pell | -0.172 |
fug | -0.170 |
condem | -0.170 |
Token | dread |
Token ID | 15157 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Kinnikuman | +0.429 |
scale | +0.412 |
�� | +0.394 |
cially | +0.389 |
utton | +0.383 |
Neg logit contributions | |
anan | -0.337 |
lie | -0.325 |
pell | -0.321 |
condem | -0.320 |
fug | -0.318 |
Token | ? |
Token ID | 30 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
lie | +2.752 |
anan | +2.745 |
pell | +2.694 |
fug | +2.660 |
condem | +2.573 |
Neg logit contributions | |
Kinnikuman | -2.778 |
scale | -2.505 |
�� | -2.500 |
cially | -2.434 |
utton | -2.368 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Kinnikuman | +0.278 |
scale | +0.267 |
�� | +0.251 |
cially | +0.248 |
utton | +0.243 |
Neg logit contributions | |
anan | -0.311 |
lie | -0.301 |
pell | -0.298 |
condem | -0.297 |
fug | -0.294 |
Token |
|
Token ID | 198 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
anan | +0.148 |
lie | +0.146 |
pell | +0.143 |
fug | +0.139 |
condem | +0.131 |
Neg logit contributions | |
Kinnikuman | -0.164 |
�� | -0.157 |
scale | -0.153 |
cially | -0.146 |
utton | -0.144 |
Token | S |
Token ID | 50 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
anan | +0.398 |
lie | +0.393 |
pell | +0.385 |
fug | +0.375 |
condem | +0.369 |
Neg logit contributions | |
Kinnikuman | -0.327 |
scale | -0.301 |
�� | -0.296 |
cially | -0.286 |
utton | -0.280 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
anan | +0.622 |
lie | +0.613 |
pell | +0.597 |
fug | +0.575 |
Gott | +0.532 |
Neg logit contributions | |
Kinnikuman | -0.898 |
�� | -0.866 |
scale | -0.837 |
cially | -0.807 |
utton | -0.798 |
Token | x |
Token ID | 87 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
lie | +1.410 |
anan | +1.408 |
pell | +1.357 |
fug | +1.289 |
sen | +1.231 |
Neg logit contributions | |
Kinnikuman | -1.568 |
�� | -1.515 |
scale | -1.376 |
cially | -1.359 |
utton | -1.342 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
anan | +0.621 |
lie | +0.612 |
pell | +0.594 |
fug | +0.572 |
Gott | +0.528 |
Neg logit contributions | |
Kinnikuman | -0.886 |
�� | -0.852 |
scale | -0.825 |
cially | -0.793 |
utton | -0.784 |
Token | x |
Token ID | 87 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
lie | +1.097 |
anan | +1.097 |
pell | +1.053 |
fug | +1.002 |
sen | +0.955 |
Neg logit contributions | |
Kinnikuman | -1.188 |
�� | -1.137 |
scale | -1.049 |
cially | -1.026 |
utton | -1.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
anan | +0.373 |
lie | +0.365 |
pell | +0.354 |
fug | +0.340 |
condem | +0.315 |
Neg logit contributions | |
Kinnikuman | -0.524 |
�� | -0.499 |
scale | -0.485 |
cially | -0.468 |
utton | -0.460 |
Token | 117 |
Token ID | 17657 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
anan | +1.128 |
lie | +1.117 |
pell | +1.100 |
fug | +1.078 |
condem | +1.048 |
Neg logit contributions | |
Kinnikuman | -0.561 |
�� | -0.471 |
scale | -0.467 |
cially | -0.440 |
cade | -0.436 |
Token | 11 |
Token ID | 1367 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
anan | +0.026 |
lie | +0.025 |
pell | +0.025 |
fug | +0.024 |
condem | +0.024 |
Neg logit contributions | |
Kinnikuman | -0.028 |
scale | -0.026 |
�� | -0.026 |
cially | -0.025 |
utton | -0.024 |
Token | 0000 |
Token ID | 2388 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
anan | +0.451 |
lie | +0.443 |
pell | +0.433 |
fug | +0.419 |
condem | +0.417 |
Neg logit contributions | |
Kinnikuman | -0.386 |
scale | -0.363 |
�� | -0.360 |
cially | -0.345 |
utton | -0.332 |
Token | 8 |
Token ID | 23 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
anan | +0.060 |
lie | +0.058 |
pell | +0.057 |
fug | +0.057 |
condem | +0.057 |
Neg logit contributions | |
Kinnikuman | -0.061 |
scale | -0.058 |
�� | -0.056 |
cially | -0.055 |
utton | -0.054 |
Token | x |
Token ID | 2124 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Kinnikuman | +0.248 |
scale | +0.234 |
�� | +0.230 |
cially | +0.222 |
utton | +0.216 |
Neg logit contributions | |
anan | -0.280 |
lie | -0.272 |
pell | -0.269 |
fug | -0.268 |
condem | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
anan | +0.762 |
lie | +0.749 |
pell | +0.730 |
fug | +0.700 |
Gott | +0.647 |
Neg logit contributions | |
Kinnikuman | -1.111 |
�� | -1.073 |
scale | -1.030 |
cially | -0.997 |
utton | -0.982 |
Token | make |
Token ID | 787 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Kinnikuman | +1.073 |
scale | +1.024 |
�� | +0.967 |
cially | +0.950 |
utton | +0.930 |
Neg logit contributions | |
anan | -1.296 |
lie | -1.254 |
pell | -1.245 |
condem | -1.238 |
fug | -1.230 |
Token | a |
Token ID | 257 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
Kinnikuman | +0.709 |
scale | +0.678 |
�� | +0.639 |
cially | +0.630 |
utton | +0.617 |
Neg logit contributions | |
anan | -0.832 |
lie | -0.805 |
pell | -0.798 |
condem | -0.794 |
fug | -0.788 |
Token | big |
Token ID | 1263 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Kinnikuman | +0.039 |
scale | +0.037 |
�� | +0.036 |
cially | +0.035 |
utton | +0.035 |
Neg logit contributions | |
anan | -0.027 |
lie | -0.026 |
pell | -0.026 |
condem | -0.026 |
fug | -0.026 |
Token | mistake |
Token ID | 7457 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Kinnikuman | +0.196 |
scale | +0.189 |
�� | +0.181 |
cially | +0.179 |
utton | +0.176 |
Neg logit contributions | |
anan | -0.126 |
lie | -0.120 |
pell | -0.119 |
condem | -0.117 |
fug | -0.117 |
Token | inside |
Token ID | 2641 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Kinnikuman | +1.528 |
scale | +1.472 |
�� | +1.378 |
cially | +1.366 |
utton | +1.339 |
Neg logit contributions | |
anan | -1.675 |
lie | -1.615 |
pell | -1.600 |
condem | -1.596 |
fug | -1.579 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Kinnikuman | +0.290 |
scale | +0.277 |
�� | +0.261 |
cially | +0.258 |
utton | +0.252 |
Neg logit contributions | |
anan | -0.328 |
lie | -0.316 |
pell | -0.316 |
condem | -0.313 |
fug | -0.312 |
Token | init |
Token ID | 2315 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
anan | +0.089 |
condem | +0.085 |
lie | +0.085 |
pell | +0.085 |
fug | +0.085 |
Neg logit contributions | |
Kinnikuman | -0.084 |
scale | -0.080 |
�� | -0.075 |
cially | -0.074 |
utton | -0.073 |
Token | .* |
Token ID | 15885 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
anan | +0.435 |
lie | +0.418 |
pell | +0.415 |
fug | +0.412 |
condem | +0.411 |
Neg logit contributions | |
Kinnikuman | -0.417 |
scale | -0.397 |
�� | -0.378 |
cially | -0.370 |
utton | -0.361 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
anan | +0.217 |
lie | +0.209 |
pell | +0.208 |
fug | +0.206 |
condem | +0.205 |
Neg logit contributions | |
Kinnikuman | -0.238 |
scale | -0.225 |
�� | -0.217 |
cially | -0.213 |
utton | -0.207 |
Token | rc |
Token ID | 6015 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Kinnikuman | +0.310 |
scale | +0.289 |
�� | +0.275 |
cially | +0.272 |
utton | +0.263 |
Neg logit contributions | |
anan | -0.392 |
lie | -0.380 |
pell | -0.375 |
fug | -0.373 |
condem | -0.372 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
anan | +1.105 |
lie | +1.071 |
pell | +1.057 |
fug | +1.050 |
condem | +1.041 |
Neg logit contributions | |
Kinnikuman | -1.561 |
scale | -1.464 |
�� | -1.429 |
cially | -1.396 |
cade | -1.367 |
Token | despite |
Token ID | 3805 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Kinnikuman | +0.428 |
scale | +0.410 |
�� | +0.390 |
cially | +0.383 |
utton | +0.377 |
Neg logit contributions | |
anan | -0.485 |
lie | -0.471 |
pell | -0.467 |
fug | -0.466 |
condem | -0.463 |
Token | his |
Token ID | 465 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
anan | +0.096 |
lie | +0.093 |
pell | +0.093 |
condem | +0.092 |
fug | +0.092 |
Neg logit contributions | |
Kinnikuman | -0.082 |
scale | -0.078 |
�� | -0.074 |
cially | -0.073 |
utton | -0.072 |
Token | best |
Token ID | 1266 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
Kinnikuman | +0.385 |
scale | +0.371 |
�� | +0.353 |
cially | +0.348 |
utton | +0.343 |
Neg logit contributions | |
anan | -0.343 |
lie | -0.330 |
pell | -0.329 |
condem | -0.327 |
fug | -0.326 |
Token | efforts |
Token ID | 4040 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
anan | +2.269 |
pell | +2.169 |
lie | +2.167 |
fug | +2.148 |
condem | +2.085 |
Neg logit contributions | |
Kinnikuman | -3.538 |
scale | -3.417 |
�� | -3.289 |
cially | -3.268 |
cade | -3.201 |
Token | , |
Token ID | 11 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
anan | +2.315 |
pell | +2.219 |
lie | +2.208 |
fug | +2.199 |
condem | +2.160 |
Neg logit contributions | |
Kinnikuman | -2.500 |
scale | -2.413 |
�� | -2.315 |
cially | -2.273 |
utton | -2.233 |
Token | the |
Token ID | 262 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
anan | +0.458 |
lie | +0.445 |
pell | +0.442 |
fug | +0.440 |
condem | +0.437 |
Neg logit contributions | |
Kinnikuman | -0.400 |
scale | -0.384 |
�� | -0.366 |
cially | -0.358 |
utton | -0.350 |
Token | life |
Token ID | 1204 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
anan | +0.385 |
fug | +0.372 |
lie | +0.372 |
pell | +0.368 |
condem | +0.366 |
Neg logit contributions | |
Kinnikuman | -0.407 |
scale | -0.391 |
�� | -0.375 |
cially | -0.369 |
utton | -0.361 |
Token | could |
Token ID | 714 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
anan | +0.070 |
lie | +0.068 |
fug | +0.067 |
pell | +0.067 |
condem | +0.066 |
Neg logit contributions | |
Kinnikuman | -0.060 |
scale | -0.057 |
�� | -0.055 |
cially | -0.054 |
utton | -0.053 |
Token | never |
Token ID | 1239 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Kinnikuman | +1.657 |
scale | +1.597 |
�� | +1.518 |
cially | +1.499 |
utton | +1.475 |
Neg logit contributions | |
anan | -1.407 |
lie | -1.351 |
pell | -1.340 |
condem | -1.331 |
fug | -1.319 |
Token | quite |
Token ID | 2407 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
anan | +0.009 |
lie | +0.009 |
pell | +0.009 |
condem | +0.008 |
fug | +0.008 |
Neg logit contributions | |
Kinnikuman | -0.009 |
scale | -0.008 |
�� | -0.008 |
cially | -0.008 |
utton | -0.008 |
Token | match |
Token ID | 2872 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Kinnikuman | +0.547 |
scale | +0.523 |
�� | +0.498 |
cially | +0.490 |
utton | +0.481 |
Neg logit contributions | |
anan | -0.561 |
lie | -0.544 |
pell | -0.539 |
condem | -0.535 |
fug | -0.533 |
Token | Every |
Token ID | 3887 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
anan | +0.432 |
lie | +0.423 |
pell | +0.416 |
fug | +0.408 |
condem | +0.399 |
Neg logit contributions | |
Kinnikuman | -0.407 |
scale | -0.397 |
�� | -0.385 |
cially | -0.375 |
utton | -0.366 |
Token | day |
Token ID | 1110 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Kinnikuman | +3.500 |
scale | +3.383 |
�� | +3.197 |
cially | +3.172 |
utton | +3.126 |
Neg logit contributions | |
anan | -2.905 |
lie | -2.794 |
condem | -2.765 |
pell | -2.763 |
fug | -2.710 |
Token | , |
Token ID | 11 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Kinnikuman | +0.094 |
scale | +0.091 |
�� | +0.087 |
cially | +0.085 |
utton | +0.083 |
Neg logit contributions | |
anan | -0.093 |
lie | -0.090 |
pell | -0.090 |
fug | -0.089 |
condem | -0.089 |
Token | someone |
Token ID | 2130 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
anan | +0.408 |
lie | +0.397 |
pell | +0.394 |
fug | +0.392 |
condem | +0.385 |
Neg logit contributions | |
Kinnikuman | -0.407 |
scale | -0.394 |
�� | -0.379 |
cially | -0.370 |
utton | -0.362 |
Token | else |
Token ID | 2073 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
anan | +2.442 |
pell | +2.358 |
fug | +2.334 |
lie | +2.333 |
condem | +2.319 |
Neg logit contributions | |
Kinnikuman | -2.632 |
scale | -2.545 |
�� | -2.461 |
utton | -2.372 |
cially | -2.370 |
Token | in |
Token ID | 287 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Kinnikuman | +0.186 |
scale | +0.179 |
�� | +0.170 |
cially | +0.167 |
utton | +0.164 |
Neg logit contributions | |
anan | -0.185 |
lie | -0.178 |
pell | -0.177 |
condem | -0.176 |
fug | -0.175 |
Token | charge |
Token ID | 3877 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
anan | +1.029 |
lie | +1.001 |
pell | +0.993 |
fug | +0.977 |
condem | +0.973 |
Neg logit contributions | |
Kinnikuman | -0.926 |
scale | -0.890 |
�� | -0.850 |
cially | -0.827 |
utton | -0.810 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Kinnikuman | +1.501 |
scale | +1.439 |
�� | +1.352 |
cially | +1.337 |
utton | +1.309 |
Neg logit contributions | |
anan | -1.710 |
lie | -1.653 |
pell | -1.639 |
condem | -1.631 |
fug | -1.617 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
anan | +0.079 |
lie | +0.077 |
pell | +0.077 |
fug | +0.075 |
condem | +0.075 |
Neg logit contributions | |
Kinnikuman | -0.077 |
scale | -0.074 |
�� | -0.071 |
cially | -0.069 |
utton | -0.068 |
Token | tune |
Token ID | 14009 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anan | +0.736 |
pell | +0.712 |
lie | +0.712 |
fug | +0.706 |
condem | +0.693 |
Neg logit contributions | |
Kinnikuman | -0.803 |
scale | -0.774 |
�� | -0.737 |
cially | -0.731 |
utton | -0.712 |
Token | age |
Token ID | 496 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
anan | +0.802 |
pell | +0.772 |
lie | +0.769 |
fug | +0.761 |
condem | +0.755 |
Neg logit contributions | |
Kinnikuman | -0.822 |
scale | -0.777 |
�� | -0.753 |
cially | -0.741 |
utton | -0.726 |
Token | you |
Token ID | 5832 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
anan | +1.128 |
lie | +1.113 |
pell | +1.091 |
fug | +1.066 |
condem | +1.064 |
Neg logit contributions | |
Kinnikuman | -1.106 |
scale | -1.019 |
�� | -0.998 |
cially | -0.976 |
utton | -0.952 |
Token | actually |
Token ID | 1682 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
anan | +0.124 |
lie | +0.121 |
pell | +0.120 |
fug | +0.118 |
condem | +0.118 |
Neg logit contributions | |
Kinnikuman | -0.127 |
scale | -0.120 |
�� | -0.115 |
cially | -0.112 |
utton | -0.111 |
Token | can |
Token ID | 460 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
anan | +1.139 |
lie | +1.134 |
pell | +1.125 |
condem | +1.105 |
fug | +1.104 |
Neg logit contributions | |
Kinnikuman | -1.139 |
scale | -1.076 |
�� | -1.028 |
cially | -1.006 |
cade | -0.989 |
Token | , |
Token ID | 11 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
Kinnikuman | +0.596 |
scale | +0.569 |
�� | +0.549 |
cially | +0.539 |
utton | +0.531 |
Neg logit contributions | |
anan | -0.439 |
lie | -0.425 |
pell | -0.422 |
condem | -0.415 |
fug | -0.414 |
Token | but |
Token ID | 475 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
anan | +0.653 |
lie | +0.642 |
pell | +0.641 |
fug | +0.634 |
condem | +0.623 |
Neg logit contributions | |
Kinnikuman | -0.648 |
scale | -0.610 |
�� | -0.598 |
cially | -0.574 |
utton | -0.570 |
Token | it |
Token ID | 340 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
anan | +1.117 |
lie | +1.091 |
pell | +1.086 |
fug | +1.076 |
condem | +1.058 |
Neg logit contributions | |
Kinnikuman | -1.147 |
scale | -1.091 |
�� | -1.058 |
cially | -1.020 |
utton | -1.020 |
Token | � |
Token ID | 447 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anan | +0.419 |
lie | +0.406 |
pell | +0.405 |
condem | +0.396 |
fug | +0.395 |
Neg logit contributions | |
Kinnikuman | -0.418 |
scale | -0.397 |
�� | -0.382 |
cially | -0.371 |
utton | -0.364 |
Token | � |
Token ID | 247 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
anan | +0.876 |
pell | +0.852 |
lie | +0.845 |
fug | +0.834 |
condem | +0.820 |
Neg logit contributions | |
Kinnikuman | -0.687 |
scale | -0.661 |
cially | -0.613 |
cade | -0.604 |
utton | -0.600 |
Token | s |
Token ID | 82 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
anan | +0.123 |
lie | +0.117 |
pell | +0.116 |
condem | +0.113 |
fug | +0.113 |
Neg logit contributions | |
Kinnikuman | -0.256 |
scale | -0.246 |
�� | -0.239 |
cially | -0.235 |
utton | -0.232 |
Token | not |
Token ID | 407 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
anan | +0.446 |
lie | +0.431 |
pell | +0.431 |
fug | +0.427 |
condem | +0.424 |
Neg logit contributions | |
Kinnikuman | -0.483 |
scale | -0.461 |
�� | -0.441 |
cially | -0.432 |
utton | -0.425 |
Token | much |
Token ID | 881 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Kinnikuman | +1.080 |
scale | +1.035 |
�� | +0.983 |
cially | +0.965 |
utton | +0.951 |
Neg logit contributions | |
anan | -1.075 |
lie | -1.043 |
pell | -1.039 |
condem | -1.028 |
fug | -1.025 |
Token | millions |
Token ID | 5242 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Kinnikuman | +0.221 |
scale | +0.212 |
�� | +0.202 |
cially | +0.198 |
utton | +0.194 |
Neg logit contributions | |
anan | -0.220 |
lie | -0.214 |
pell | -0.211 |
condem | -0.210 |
fug | -0.209 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
anan | +2.137 |
lie | +2.087 |
pell | +2.082 |
fug | +2.041 |
condem | +2.038 |
Neg logit contributions | |
Kinnikuman | -1.864 |
scale | -1.780 |
�� | -1.714 |
cially | -1.671 |
utton | -1.628 |
Token | pounds |
Token ID | 8059 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
anan | +0.554 |
lie | +0.534 |
pell | +0.531 |
fug | +0.519 |
condem | +0.515 |
Neg logit contributions | |
Kinnikuman | -0.937 |
scale | -0.900 |
�� | -0.871 |
cially | -0.859 |
cade | -0.843 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
anan | +2.627 |
lie | +2.598 |
pell | +2.591 |
fug | +2.533 |
condem | +2.512 |
Neg logit contributions | |
Kinnikuman | -2.927 |
scale | -2.790 |
�� | -2.745 |
cially | -2.651 |
ザ | -2.602 |
Token | this |
Token ID | 428 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
anan | +0.027 |
lie | +0.027 |
pell | +0.026 |
condem | +0.026 |
fug | +0.026 |
Neg logit contributions | |
Kinnikuman | -0.024 |
scale | -0.023 |
�� | -0.022 |
cially | -0.022 |
utton | -0.021 |
Token | helped |
Token ID | 4193 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
anan | +0.526 |
lie | +0.510 |
condem | +0.506 |
fug | +0.504 |
pell | +0.500 |
Neg logit contributions | |
Kinnikuman | -0.553 |
scale | -0.529 |
�� | -0.508 |
cially | -0.494 |
utton | -0.489 |
Token | support |
Token ID | 1104 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
anan | +3.791 |
lie | +3.760 |
condem | +3.705 |
fug | +3.693 |
pell | +3.690 |
Neg logit contributions | |
Kinnikuman | -3.972 |
scale | -3.839 |
�� | -3.798 |
cade | -3.585 |
ixon | -3.532 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Kinnikuman | +0.892 |
scale | +0.855 |
�� | +0.810 |
cially | +0.793 |
utton | +0.777 |
Neg logit contributions | |
anan | -0.988 |
lie | -0.958 |
pell | -0.951 |
condem | -0.941 |
fug | -0.939 |
Token | staging |
Token ID | 29475 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
Kinnikuman | +0.850 |
scale | +0.816 |
�� | +0.779 |
cially | +0.767 |
utton | +0.749 |
Neg logit contributions | |
anan | -0.794 |
lie | -0.770 |
pell | -0.760 |
condem | -0.756 |
fug | -0.755 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Kinnikuman | +1.971 |
scale | +1.886 |
�� | +1.757 |
cially | +1.731 |
cade | +1.699 |
Neg logit contributions | |
anan | -2.804 |
lie | -2.705 |
pell | -2.704 |
condem | -2.698 |
fug | -2.667 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Kinnikuman | +1.364 |
scale | +1.309 |
�� | +1.233 |
cially | +1.217 |
utton | +1.195 |
Neg logit contributions | |
anan | -1.515 |
lie | -1.461 |
pell | -1.451 |
condem | -1.444 |
fug | -1.430 |
Token | to |
Token ID | 284 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
anan | +1.807 |
pell | +1.776 |
lie | +1.775 |
fug | +1.747 |
condem | +1.736 |
Neg logit contributions | |
Kinnikuman | -1.854 |
scale | -1.767 |
�� | -1.732 |
cially | -1.650 |
cade | -1.625 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
anan | +0.231 |
lie | +0.223 |
pell | +0.221 |
condem | +0.220 |
fug | +0.218 |
Neg logit contributions | |
Kinnikuman | -0.263 |
scale | -0.249 |
�� | -0.241 |
cially | -0.235 |
utton | -0.232 |
Token | banks |
Token ID | 6341 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Kinnikuman | +0.158 |
scale | +0.151 |
�� | +0.146 |
cially | +0.143 |
utton | +0.141 |
Neg logit contributions | |
anan | -0.122 |
lie | -0.118 |
condem | -0.117 |
pell | -0.116 |
fug | -0.115 |
Token | on |
Token ID | 319 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
anan | +1.279 |
pell | +1.255 |
lie | +1.254 |
fug | +1.227 |
condem | +1.227 |
Neg logit contributions | |
Kinnikuman | -1.252 |
scale | -1.187 |
�� | -1.154 |
cially | -1.114 |
utton | -1.094 |
Token | their |
Token ID | 511 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anan | +0.028 |
lie | +0.027 |
pell | +0.027 |
condem | +0.027 |
fug | +0.027 |
Neg logit contributions | |
Kinnikuman | -0.026 |
scale | -0.025 |
�� | -0.024 |
cially | -0.023 |
utton | -0.023 |
Token | lending |
Token ID | 20983 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
Kinnikuman | +0.899 |
scale | +0.867 |
�� | +0.830 |
cially | +0.818 |
utton | +0.806 |
Neg logit contributions | |
anan | -0.650 |
lie | -0.624 |
pell | -0.618 |
condem | -0.614 |
fug | -0.608 |
Token | for |
Token ID | 329 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
fug | +3.831 |
anan | +3.807 |
lie | +3.804 |
condem | +3.725 |
lender | +3.668 |
Neg logit contributions | |
Kinnikuman | -5.555 |
�� | -5.360 |
scale | -5.248 |
cade | -5.086 |
ザ | -5.051 |
Token | investment |
Token ID | 4896 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
anan | +0.733 |
lie | +0.716 |
pell | +0.704 |
condem | +0.701 |
fug | +0.697 |
Neg logit contributions | |
Kinnikuman | -0.872 |
scale | -0.831 |
�� | -0.802 |
cially | -0.780 |
cade | -0.774 |
Token | properties |
Token ID | 6608 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
anan | +1.007 |
lie | +0.985 |
condem | +0.966 |
fug | +0.964 |
pell | +0.961 |
Neg logit contributions | |
Kinnikuman | -1.126 |
scale | -1.073 |
�� | -1.038 |
cially | -1.002 |
cade | -0.993 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
anan | +1.829 |
lie | +1.796 |
pell | +1.788 |
fug | +1.746 |
condem | +1.740 |
Neg logit contributions | |
Kinnikuman | -1.959 |
scale | -1.856 |
�� | -1.820 |
cially | -1.740 |
utton | -1.716 |
Token | it |
Token ID | 340 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
anan | +1.429 |
lie | +1.383 |
pell | +1.368 |
condem | +1.364 |
fug | +1.360 |
Neg logit contributions | |
Kinnikuman | -1.532 |
scale | -1.457 |
�� | -1.412 |
cially | -1.360 |
utton | -1.351 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Kinnikuman | +0.765 |
scale | +0.736 |
�� | +0.698 |
cially | +0.687 |
utton | +0.676 |
Neg logit contributions | |
anan | -0.736 |
lie | -0.709 |
pell | -0.704 |
condem | -0.698 |
fug | -0.693 |
Token | � |
Token ID | 447 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
Kinnikuman | +0.487 |
scale | +0.467 |
�� | +0.440 |
cially | +0.433 |
utton | +0.424 |
Neg logit contributions | |
anan | -0.560 |
lie | -0.542 |
pell | -0.538 |
condem | -0.534 |
fug | -0.530 |
Token | � |
Token ID | 251 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Kinnikuman | +0.455 |
scale | +0.429 |
�� | +0.403 |
cially | +0.389 |
utton | +0.380 |
Neg logit contributions | |
anan | -0.762 |
lie | -0.740 |
pell | -0.734 |
condem | -0.730 |
fug | -0.725 |
Token | Lat |
Token ID | 5476 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Kinnikuman | +0.833 |
scale | +0.801 |
�� | +0.757 |
cially | +0.748 |
utton | +0.735 |
Neg logit contributions | |
anan | -0.833 |
lie | -0.801 |
pell | -0.796 |
condem | -0.791 |
fug | -0.786 |
Token | end |
Token ID | 437 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
anan | +1.528 |
lie | +1.516 |
pell | +1.461 |
fug | +1.401 |
condem | +1.343 |
Neg logit contributions | |
Kinnikuman | -1.727 |
�� | -1.601 |
scale | -1.550 |
ザ | -1.471 |
utton | -1.449 |
Token | res |
Token ID | 411 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
anan | +0.471 |
lie | +0.460 |
pell | +0.452 |
fug | +0.433 |
condem | +0.415 |
Neg logit contributions | |
Kinnikuman | -0.704 |
�� | -0.663 |
scale | -0.655 |
cially | -0.626 |
ザ | -0.625 |
Token | se |
Token ID | 325 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
lie | +2.431 |
anan | +2.376 |
pell | +2.298 |
sen | +2.036 |
fug | +2.009 |
Neg logit contributions | |
Kinnikuman | -4.687 |
�� | -4.516 |
ザ | -4.175 |
scale | -4.156 |
utton | -4.016 |
Token | said |
Token ID | 531 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
anan | +0.702 |
lie | +0.674 |
pell | +0.667 |
condem | +0.664 |
fug | +0.656 |
Neg logit contributions | |
Kinnikuman | -0.834 |
scale | -0.802 |
�� | -0.763 |
cially | -0.751 |
utton | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
anan | +0.945 |
lie | +0.907 |
pell | +0.901 |
condem | +0.894 |
fug | +0.890 |
Neg logit contributions | |
Kinnikuman | -1.030 |
scale | -0.992 |
�� | -0.941 |
cially | -0.931 |
utton | -0.915 |
Token |
|
Token ID | 198 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
anan | +1.286 |
lie | +1.246 |
pell | +1.232 |
condem | +1.222 |
fug | +1.216 |
Neg logit contributions | |
Kinnikuman | -1.187 |
scale | -1.137 |
�� | -1.080 |
cially | -1.059 |
utton | -1.039 |
Token |
|
Token ID | 198 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
anan | +0.531 |
lie | +0.528 |
pell | +0.515 |
fug | +0.498 |
Gott | +0.465 |
Neg logit contributions | |
Kinnikuman | -0.613 |
�� | -0.591 |
scale | -0.568 |
cially | -0.546 |
utton | -0.536 |
Token | automatically |
Token ID | 6338 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Kinnikuman | +0.113 |
scale | +0.106 |
�� | +0.103 |
cially | +0.100 |
utton | +0.099 |
Neg logit contributions | |
anan | -0.123 |
lie | -0.121 |
pell | -0.120 |
fug | -0.118 |
condem | -0.118 |
Token | begin |
Token ID | 2221 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
anan | +1.874 |
pell | +1.844 |
lie | +1.841 |
fug | +1.822 |
condem | +1.811 |
Neg logit contributions | |
Kinnikuman | -1.791 |
scale | -1.635 |
�� | -1.625 |
cially | -1.579 |
utton | -1.556 |
Token | another |
Token ID | 1194 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
anan | +2.874 |
pell | +2.791 |
fug | +2.765 |
lie | +2.757 |
condem | +2.750 |
Neg logit contributions | |
Kinnikuman | -3.450 |
scale | -3.270 |
�� | -3.149 |
utton | -3.095 |
cially | -3.080 |
Token | drawing |
Token ID | 8263 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
anan | +0.752 |
lie | +0.731 |
pell | +0.729 |
fug | +0.724 |
condem | +0.723 |
Neg logit contributions | |
Kinnikuman | -0.787 |
scale | -0.748 |
�� | -0.722 |
cially | -0.707 |
utton | -0.698 |
Token | or |
Token ID | 393 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
anan | +0.869 |
lie | +0.845 |
pell | +0.844 |
fug | +0.835 |
condem | +0.831 |
Neg logit contributions | |
Kinnikuman | -0.880 |
scale | -0.835 |
�� | -0.809 |
cially | -0.790 |
utton | -0.774 |
Token | poem |
Token ID | 21247 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
anan | +0.572 |
lie | +0.550 |
pell | +0.546 |
condem | +0.542 |
fug | +0.540 |
Neg logit contributions | |
Kinnikuman | -0.656 |
scale | -0.631 |
�� | -0.601 |
cially | -0.593 |
utton | -0.583 |
Token | shortly |
Token ID | 8972 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
anan | +3.170 |
pell | +3.129 |
fug | +3.104 |
lie | +3.103 |
condem | +3.020 |
Neg logit contributions | |
Kinnikuman | -3.750 |
�� | -3.557 |
scale | -3.550 |
cially | -3.371 |
utton | -3.358 |
Token | after |
Token ID | 706 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
anan | +2.040 |
lie | +2.010 |
pell | +1.998 |
fug | +1.977 |
condem | +1.963 |
Neg logit contributions | |
Kinnikuman | -1.914 |
scale | -1.825 |
�� | -1.768 |
cially | -1.687 |
utton | -1.676 |
Token | finishing |
Token ID | 12848 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
anan | +1.577 |
lie | +1.549 |
pell | +1.540 |
condem | +1.533 |
fug | +1.525 |
Neg logit contributions | |
Kinnikuman | -1.667 |
scale | -1.590 |
�� | -1.551 |
cially | -1.500 |
utton | -1.478 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
anan | +0.248 |
pell | +0.241 |
lie | +0.240 |
fug | +0.236 |
condem | +0.236 |
Neg logit contributions | |
Kinnikuman | -0.259 |
scale | -0.247 |
�� | -0.237 |
cially | -0.231 |
utton | -0.229 |
Token | first |
Token ID | 717 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
anan | +1.291 |
fug | +1.262 |
pell | +1.254 |
lie | +1.251 |
condem | +1.240 |
Neg logit contributions | |
Kinnikuman | -1.642 |
scale | -1.560 |
�� | -1.515 |
cially | -1.481 |
utton | -1.469 |
Token | positive |
Token ID | 24561 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Kinnikuman | +1.508 |
scale | +1.480 |
�� | +1.387 |
cially | +1.376 |
utton | +1.354 |
Neg logit contributions | |
anan | -1.382 |
lie | -1.319 |
pell | -1.314 |
condem | -1.305 |
fug | -1.291 |
Token | , |
Token ID | 11 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Kinnikuman | +1.308 |
scale | +1.260 |
�� | +1.193 |
cially | +1.177 |
utton | +1.157 |
Neg logit contributions | |
anan | -1.290 |
lie | -1.240 |
pell | -1.230 |
condem | -1.225 |
fug | -1.212 |
Token | � |
Token ID | 447 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
anan | +0.410 |
lie | +0.403 |
pell | +0.397 |
fug | +0.397 |
condem | +0.396 |
Neg logit contributions | |
Kinnikuman | -0.426 |
scale | -0.405 |
�� | -0.389 |
cially | -0.381 |
cade | -0.375 |
Token | � |
Token ID | 251 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Kinnikuman | +0.006 |
scale | +0.006 |
�� | +0.005 |
cially | +0.005 |
utton | +0.005 |
Neg logit contributions | |
anan | -0.011 |
lie | -0.010 |
pell | -0.010 |
condem | -0.010 |
fug | -0.010 |
Token | says |
Token ID | 1139 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
anan | +0.175 |
lie | +0.171 |
pell | +0.169 |
condem | +0.167 |
fug | +0.167 |
Neg logit contributions | |
Kinnikuman | -0.163 |
scale | -0.155 |
�� | -0.148 |
cially | -0.145 |
utton | -0.142 |
Token | Wong |
Token ID | 27247 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
Kinnikuman | +2.678 |
scale | +2.585 |
�� | +2.429 |
cially | +2.414 |
utton | +2.377 |
Neg logit contributions | |
anan | -2.565 |
lie | -2.461 |
pell | -2.452 |
condem | -2.442 |
fug | -2.424 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
anan | +3.139 |
lie | +3.031 |
pell | +2.944 |
condem | +2.902 |
fug | +2.882 |
Neg logit contributions | |
Kinnikuman | -3.759 |
scale | -3.579 |
�� | -3.483 |
cially | -3.395 |
utton | -3.334 |
Token | � |
Token ID | 564 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Kinnikuman | +0.689 |
scale | +0.659 |
�� | +0.627 |
cially | +0.614 |
utton | +0.603 |
Neg logit contributions | |
anan | -0.780 |
lie | -0.758 |
pell | -0.749 |
condem | -0.742 |
fug | -0.738 |
Token | � |
Token ID | 250 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Kinnikuman | +0.767 |
scale | +0.726 |
�� | +0.670 |
cially | +0.659 |
utton | +0.642 |
Neg logit contributions | |
anan | -1.338 |
lie | -1.301 |
pell | -1.292 |
condem | -1.287 |
fug | -1.279 |
Token | Those |
Token ID | 9627 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
Kinnikuman | +0.201 |
scale | +0.186 |
�� | +0.178 |
cially | +0.171 |
utton | +0.168 |
Neg logit contributions | |
anan | -0.317 |
lie | -0.312 |
pell | -0.307 |
fug | -0.303 |
condem | -0.302 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
anan | +0.598 |
lie | +0.581 |
condem | +0.576 |
fug | +0.573 |
pell | +0.573 |
Neg logit contributions | |
Kinnikuman | -0.611 |
scale | -0.580 |
�� | -0.559 |
cially | -0.544 |
utton | -0.536 |