Token | � |
Token ID | 447 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Britann | +2.668 |
politic | +2.589 |
democrat | +2.569 |
shalt | +2.438 |
Anglo | +2.408 |
Neg logit contributions | |
ukong | -2.572 |
specific | -2.536 |
izable | -2.436 |
UAL | -2.425 |
antically | -2.406 |
Token | � |
Token ID | 247 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
specific | +1.892 |
ukong | +1.882 |
UAL | +1.791 |
izable | +1.775 |
antically | +1.746 |
Neg logit contributions | |
Britann | -2.601 |
politic | -2.518 |
democrat | -2.505 |
shalt | -2.398 |
Anglo | -2.360 |
Token | ) |
Token ID | 8 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
specific | +3.372 |
ukong | +3.356 |
izable | +3.217 |
UAL | +3.203 |
antically | +3.142 |
Neg logit contributions | |
Britann | -3.596 |
democrat | -3.483 |
politic | -3.478 |
shalt | -3.283 |
Anglo | -3.234 |
Token | + |
Token ID | 1343 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
specific | +3.567 |
ukong | +3.550 |
izable | +3.411 |
UAL | +3.397 |
antically | +3.344 |
Neg logit contributions | |
Britann | -3.539 |
democrat | -3.414 |
politic | -3.413 |
shalt | -3.215 |
Anglo | -3.175 |
Token | f |
Token ID | 277 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
specific | +3.140 |
ukong | +3.128 |
izable | +3.012 |
UAL | +2.986 |
antically | +2.951 |
Neg logit contributions | |
Britann | -2.848 |
democrat | -2.743 |
politic | -2.742 |
shalt | -2.579 |
Anglo | -2.532 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Britann | +1.019 |
politic | +0.980 |
democrat | +0.972 |
shalt | +0.905 |
Anglo | +0.897 |
Neg logit contributions | |
ukong | -1.547 |
specific | -1.533 |
UAL | -1.484 |
izable | -1.478 |
antically | -1.463 |
Token | ic |
Token ID | 291 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
specific | +7.293 |
izable | +7.055 |
agi | +6.836 |
ual | +6.463 |
antically | +6.343 |
Neg logit contributions | |
Britann | -22.158 |
democrat | -20.988 |
politic | -20.894 |
shalt | -20.734 |
contrace | -20.570 |
Token | ( |
Token ID | 357 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
specific | +1.465 |
ukong | +1.462 |
izable | +1.406 |
UAL | +1.397 |
antically | +1.381 |
Neg logit contributions | |
Britann | -1.416 |
politic | -1.363 |
democrat | -1.360 |
shalt | -1.286 |
Anglo | -1.268 |
Token | t |
Token ID | 83 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
specific | +2.080 |
ukong | +2.067 |
izable | +1.975 |
UAL | +1.956 |
antically | +1.934 |
Neg logit contributions | |
Britann | -2.375 |
politic | -2.298 |
democrat | -2.297 |
shalt | -2.177 |
Anglo | -2.147 |
Token | � |
Token ID | 447 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Britann | +2.477 |
politic | +2.389 |
democrat | +2.382 |
shalt | +2.250 |
Anglo | +2.216 |
Neg logit contributions | |
ukong | -2.656 |
specific | -2.617 |
izable | -2.531 |
UAL | -2.508 |
antically | -2.505 |
Token | � |
Token ID | 247 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
specific | +1.115 |
ukong | +1.114 |
izable | +1.050 |
UAL | +1.050 |
antically | +1.030 |
Neg logit contributions | |
Britann | -1.703 |
politic | -1.653 |
democrat | -1.648 |
shalt | -1.575 |
Anglo | -1.556 |
Token | match |
Token ID | 15699 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ukong | +1.137 |
specific | +1.121 |
izable | +1.067 |
UAL | +1.059 |
antically | +1.046 |
Neg logit contributions | |
Britann | -1.845 |
politic | -1.788 |
democrat | -1.784 |
shalt | -1.708 |
Anglo | -1.693 |
Token | consolation |
Token ID | 45194 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
specific | +5.204 |
ukong | +5.066 |
izable | +4.907 |
UAL | +4.794 |
agi | +4.745 |
Neg logit contributions | |
Britann | -4.731 |
democrat | -4.575 |
politic | -4.535 |
shalt | -4.365 |
Anglo | -4.189 |
Token | rec |
Token ID | 664 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
specific | +4.035 |
ukong | +3.986 |
izable | +3.891 |
agi | +3.815 |
UAL | +3.815 |
Neg logit contributions | |
Britann | -3.167 |
politic | -3.068 |
democrat | -3.065 |
shalt | -2.843 |
Anglo | -2.807 |
Token | eded |
Token ID | 15395 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ukong | +0.137 |
specific | +0.137 |
UAL | +0.131 |
izable | +0.131 |
antically | +0.128 |
Neg logit contributions | |
Britann | -0.142 |
politic | -0.137 |
democrat | -0.137 |
shalt | -0.129 |
Anglo | -0.127 |
Token | when |
Token ID | 618 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ukong | +0.138 |
specific | +0.138 |
izable | +0.133 |
UAL | +0.132 |
antically | +0.131 |
Neg logit contributions | |
Britann | -0.106 |
politic | -0.102 |
democrat | -0.101 |
shalt | -0.095 |
Anglo | -0.094 |
Token | Mal |
Token ID | 4434 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
specific | +1.610 |
ukong | +1.600 |
izable | +1.545 |
UAL | +1.535 |
antically | +1.525 |
Neg logit contributions | |
Britann | -1.201 |
democrat | -1.157 |
politic | -1.156 |
shalt | -1.084 |
Anglo | -1.053 |
Token | br |
Token ID | 1671 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
specific | +11.038 |
agi | +9.928 |
pson | +9.815 |
antically | +9.783 |
izable | +9.730 |
Neg logit contributions | |
Britann | -17.361 |
democrat | -17.047 |
politic | -17.031 |
shalt | -16.577 |
contrace | -16.559 |
Token | an |
Token ID | 272 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
specific | +3.722 |
ukong | +3.661 |
izable | +3.381 |
antically | +3.360 |
agi | +3.356 |
Neg logit contributions | |
Britann | -8.656 |
politic | -8.410 |
democrat | -8.363 |
shalt | -8.238 |
contrace | -8.053 |
Token | que |
Token ID | 4188 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
specific | +5.294 |
ukong | +4.899 |
izable | +4.891 |
nesota | +4.644 |
antically | +4.554 |
Neg logit contributions | |
Britann | -11.087 |
democrat | -10.558 |
politic | -10.451 |
shalt | -10.353 |
contrace | -10.165 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
specific | +4.210 |
ukong | +4.208 |
izable | +4.040 |
UAL | +3.998 |
antically | +3.977 |
Neg logit contributions | |
Britann | -3.274 |
democrat | -3.096 |
politic | -3.087 |
shalt | -2.915 |
Anglo | -2.881 |
Token | excellent |
Token ID | 6275 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
specific | +5.221 |
ukong | +5.109 |
antically | +4.926 |
izable | +4.925 |
UAL | +4.887 |
Neg logit contributions | |
Britann | -4.512 |
democrat | -4.397 |
politic | -4.374 |
shalt | -4.150 |
Anglo | -4.010 |
Token | to |
Token ID | 284 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Britann | +2.335 |
politic | +2.256 |
democrat | +2.239 |
shalt | +2.049 |
Anglo | +2.041 |
Neg logit contributions | |
ukong | -3.734 |
specific | -3.706 |
izable | -3.585 |
UAL | -3.570 |
antically | -3.533 |
Token | employers |
Token ID | 11390 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
Britann | +1.140 |
politic | +1.096 |
democrat | +1.092 |
shalt | +1.014 |
Anglo | +1.010 |
Neg logit contributions | |
ukong | -1.478 |
specific | -1.474 |
izable | -1.418 |
UAL | -1.414 |
antically | -1.398 |
Token | ." |
Token ID | 526 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Britann | +0.296 |
politic | +0.282 |
democrat | +0.281 |
shalt | +0.261 |
Anglo | +0.257 |
Neg logit contributions | |
ukong | -0.468 |
specific | -0.468 |
izable | -0.452 |
UAL | -0.450 |
antically | -0.446 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Britann | +2.247 |
politic | +2.124 |
democrat | +2.120 |
Anglo | +1.967 |
shalt | +1.964 |
Neg logit contributions | |
ukong | -3.384 |
specific | -3.372 |
izable | -3.257 |
UAL | -3.251 |
antically | -3.218 |
Token | MA |
Token ID | 5673 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
specific | +4.838 |
ukong | +4.720 |
UAL | +4.594 |
izable | +4.514 |
antically | +4.420 |
Neg logit contributions | |
Britann | -5.008 |
democrat | -4.794 |
politic | -4.791 |
shalt | -4.558 |
Anglo | -4.490 |
Token | J |
Token ID | 41 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
specific | +5.516 |
ukong | +5.483 |
UAL | +5.420 |
izable | +5.116 |
antically | +5.006 |
Neg logit contributions | |
Britann | -6.551 |
politic | -6.344 |
democrat | -6.259 |
shalt | -5.966 |
Anglo | -5.861 |
Token | UR |
Token ID | 4261 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
UAL | +10.224 |
ukong | +9.828 |
specific | +9.710 |
izable | +8.961 |
AMI | +8.792 |
Neg logit contributions | |
Britann | -17.477 |
politic | -16.429 |
democrat | -16.270 |
shalt | -15.818 |
Anglo | -15.587 |
Token | O |
Token ID | 46 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
UAL | +8.840 |
specific | +8.690 |
ukong | +8.490 |
izable | +8.205 |
agi | +8.103 |
Neg logit contributions | |
Britann | -9.159 |
democrat | -9.149 |
politic | -9.041 |
shalt | -8.475 |
Anglo | -8.275 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ukong | +3.677 |
specific | +3.673 |
UAL | +3.586 |
izable | +3.533 |
antically | +3.498 |
Neg logit contributions | |
Britann | -2.235 |
politic | -2.120 |
democrat | -2.117 |
shalt | -1.981 |
Anglo | -1.931 |
Token | Marshall |
Token ID | 13606 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
specific | +4.757 |
ukong | +4.629 |
UAL | +4.626 |
izable | +4.499 |
antically | +4.380 |
Neg logit contributions | |
Britann | -4.011 |
democrat | -3.921 |
politic | -3.859 |
shalt | -3.695 |
Anglo | -3.554 |
Token | Islands |
Token ID | 12010 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
specific | +5.787 |
ukong | +5.744 |
UAL | +5.741 |
izable | +5.656 |
agi | +5.571 |
Neg logit contributions | |
Britann | -4.748 |
democrat | -4.627 |
politic | -4.577 |
shalt | -4.287 |
Anglo | -4.163 |
Token | that |
Token ID | 326 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
specific | +1.243 |
ukong | +1.242 |
izable | +1.196 |
UAL | +1.189 |
antically | +1.171 |
Neg logit contributions | |
Britann | -1.140 |
politic | -1.093 |
democrat | -1.089 |
shalt | -1.037 |
Anglo | -1.013 |
Token | troubled |
Token ID | 17840 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Britann | +3.111 |
politic | +3.008 |
democrat | +2.999 |
Anglo | +2.790 |
shalt | +2.774 |
Neg logit contributions | |
ukong | -3.839 |
specific | -3.829 |
izable | -3.670 |
UAL | -3.656 |
antically | -3.650 |
Token | state |
Token ID | 1181 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
specific | +2.232 |
ukong | +2.228 |
UAL | +2.153 |
izable | +2.146 |
antically | +2.113 |
Neg logit contributions | |
Britann | -1.667 |
politic | -1.586 |
democrat | -1.581 |
shalt | -1.510 |
Anglo | -1.442 |
Token | fund |
Token ID | 1814 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
specific | +4.953 |
ukong | +4.882 |
UAL | +4.770 |
izable | +4.720 |
agi | +4.641 |
Neg logit contributions | |
Britann | -3.763 |
democrat | -3.577 |
politic | -3.569 |
shalt | -3.390 |
Anglo | -3.251 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Britann | +1.556 |
politic | +1.488 |
democrat | +1.483 |
shalt | +1.390 |
Anglo | +1.380 |
Neg logit contributions | |
ukong | -1.892 |
specific | -1.890 |
izable | -1.815 |
UAL | -1.805 |
antically | -1.793 |
Token | Mal |
Token ID | 15029 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Britann | +2.509 |
democrat | +2.406 |
politic | +2.405 |
shalt | +2.274 |
Anglo | +2.261 |
Neg logit contributions | |
ukong | -2.561 |
specific | -2.550 |
izable | -2.445 |
UAL | -2.417 |
antically | -2.407 |
Token | ays |
Token ID | 592 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
specific | +7.332 |
agi | +7.294 |
UAL | +7.026 |
ukong | +6.921 |
ual | +6.859 |
Neg logit contributions | |
Britann | -19.808 |
democrat | -19.347 |
shalt | -18.864 |
politic | -18.860 |
Anglo | -18.278 |
Token | ia |
Token ID | 544 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
specific | +3.820 |
ukong | +3.673 |
izable | +3.570 |
UAL | +3.569 |
agi | +3.452 |
Neg logit contributions | |
Britann | -11.689 |
politic | -11.541 |
democrat | -11.392 |
shalt | -11.020 |
Anglo | -10.951 |
Token | Development |
Token ID | 7712 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
specific | +8.748 |
ukong | +8.563 |
UAL | +8.386 |
izable | +8.228 |
agi | +8.209 |
Neg logit contributions | |
Britann | -6.806 |
democrat | -6.591 |
politic | -6.561 |
shalt | -6.193 |
artisan | -5.931 |
Token | Ber |
Token ID | 4312 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
ukong | +0.654 |
specific | +0.653 |
izable | +0.629 |
UAL | +0.626 |
antically | +0.620 |
Neg logit contributions | |
Britann | -0.465 |
politic | -0.444 |
democrat | -0.443 |
shalt | -0.414 |
Anglo | -0.408 |
Token | had |
Token ID | 18108 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Britann | +0.291 |
politic | +0.285 |
democrat | +0.284 |
shalt | +0.271 |
Anglo | +0.269 |
Neg logit contributions | |
specific | -0.162 |
ukong | -0.161 |
izable | -0.151 |
UAL | -0.151 |
antically | -0.148 |
Token | as |
Token ID | 355 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
specific | +3.995 |
ukong | +3.937 |
izable | +3.809 |
UAL | +3.777 |
antically | +3.757 |
Neg logit contributions | |
Britann | -3.451 |
politic | -3.308 |
democrat | -3.286 |
shalt | -3.107 |
Anglo | -3.077 |
Token | an |
Token ID | 281 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
specific | +4.483 |
ukong | +4.391 |
izable | +4.242 |
UAL | +4.199 |
antically | +4.173 |
Neg logit contributions | |
Britann | -4.226 |
politic | -4.095 |
democrat | -4.084 |
shalt | -3.816 |
Anglo | -3.813 |
Token | alternative |
Token ID | 5559 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
specific | +5.393 |
ukong | +5.244 |
izable | +5.116 |
UAL | +5.083 |
agi | +5.046 |
Neg logit contributions | |
Britann | -5.200 |
politic | -5.052 |
democrat | -4.962 |
shalt | -4.631 |
Anglo | -4.503 |
Token | to |
Token ID | 284 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
specific | +3.558 |
ukong | +3.542 |
izable | +3.447 |
UAL | +3.397 |
antically | +3.379 |
Neg logit contributions | |
Britann | -2.949 |
politic | -2.826 |
democrat | -2.805 |
shalt | -2.623 |
Anglo | -2.599 |
Token | Kai |
Token ID | 22091 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
specific | +2.995 |
ukong | +2.968 |
izable | +2.855 |
UAL | +2.830 |
antically | +2.808 |
Neg logit contributions | |
Britann | -2.756 |
democrat | -2.650 |
politic | -2.648 |
shalt | -2.494 |
Anglo | -2.461 |
Token | j |
Token ID | 73 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
specific | +4.059 |
ukong | +4.024 |
izable | +3.727 |
agi | +3.716 |
UAL | +3.606 |
Neg logit contributions | |
Britann | -11.413 |
democrat | -11.226 |
politic | -11.203 |
shalt | -10.924 |
Anglo | -10.717 |
Token | us |
Token ID | 385 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
agi | +11.770 |
ukong | +11.677 |
specific | +10.999 |
ual | +10.951 |
izable | +10.918 |
Neg logit contributions | |
Britann | -15.685 |
democrat | -14.952 |
politic | -14.905 |
shalt | -14.733 |
Anglo | -14.153 |
Token | in |
Token ID | 287 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
specific | +9.232 |
ukong | +9.181 |
agi | +8.964 |
UAL | +8.794 |
izable | +8.774 |
Neg logit contributions | |
Britann | -6.551 |
politic | -6.426 |
democrat | -6.355 |
shalt | -5.908 |
Anglo | -5.871 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
specific | +5.794 |
ukong | +5.667 |
izable | +5.457 |
UAL | +5.428 |
antically | +5.365 |
Neg logit contributions | |
Britann | -5.719 |
politic | -5.546 |
democrat | -5.497 |
shalt | -5.266 |
Anglo | -5.072 |
Token | form |
Token ID | 1296 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
specific | +2.084 |
ukong | +2.078 |
izable | +2.000 |
UAL | +1.986 |
antically | +1.971 |
Neg logit contributions | |
Britann | -1.749 |
politic | -1.682 |
democrat | -1.672 |
shalt | -1.575 |
Anglo | -1.540 |
Token | of |
Token ID | 286 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
specific | +5.028 |
ukong | +4.994 |
izable | +4.833 |
UAL | +4.799 |
antically | +4.741 |
Neg logit contributions | |
Britann | -3.556 |
democrat | -3.387 |
politic | -3.382 |
shalt | -3.165 |
Anglo | -3.113 |
Token | ( |
Token ID | 357 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
specific | +2.802 |
ukong | +2.786 |
izable | +2.698 |
UAL | +2.678 |
antically | +2.635 |
Neg logit contributions | |
Britann | -2.294 |
politic | -2.197 |
democrat | -2.195 |
shalt | -2.056 |
Anglo | -2.033 |
Token | t |
Token ID | 83 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
specific | +1.767 |
ukong | +1.762 |
izable | +1.680 |
UAL | +1.671 |
antically | +1.646 |
Neg logit contributions | |
Britann | -2.138 |
politic | -2.069 |
democrat | -2.066 |
shalt | -1.964 |
Anglo | -1.939 |
Token | ) |
Token ID | 8 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Britann | +4.529 |
politic | +4.377 |
democrat | +4.317 |
shalt | +4.101 |
Anglo | +4.056 |
Neg logit contributions | |
ukong | -4.704 |
specific | -4.611 |
nesota | -4.444 |
UAL | -4.405 |
antically | -4.395 |
Token | + |
Token ID | 1343 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ukong | +1.137 |
specific | +1.134 |
izable | +1.091 |
UAL | +1.087 |
antically | +1.076 |
Neg logit contributions | |
Britann | -0.932 |
politic | -0.894 |
democrat | -0.892 |
shalt | -0.838 |
Anglo | -0.826 |
Token | f |
Token ID | 277 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ukong | +1.566 |
specific | +1.565 |
izable | +1.501 |
UAL | +1.493 |
antically | +1.475 |
Neg logit contributions | |
Britann | -1.476 |
politic | -1.421 |
democrat | -1.418 |
shalt | -1.339 |
Anglo | -1.320 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
Britann | +1.461 |
politic | +1.409 |
democrat | +1.403 |
shalt | +1.330 |
Anglo | +1.309 |
Neg logit contributions | |
ukong | -1.566 |
specific | -1.545 |
UAL | -1.489 |
izable | -1.484 |
antically | -1.477 |
Token | ic |
Token ID | 291 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
izable | +14.068 |
specific | +13.990 |
ukong | +13.220 |
agi | +13.080 |
ual | +12.869 |
Neg logit contributions | |
Britann | -13.021 |
politic | -12.245 |
democrat | -11.968 |
shalt | -11.850 |
Anglo | -11.302 |
Token | ( |
Token ID | 357 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
specific | +3.873 |
ukong | +3.836 |
izable | +3.733 |
UAL | +3.687 |
antically | +3.630 |
Neg logit contributions | |
Britann | -3.463 |
politic | -3.326 |
democrat | -3.320 |
shalt | -3.132 |
Anglo | -3.082 |
Token | t |
Token ID | 83 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
specific | +2.143 |
ukong | +2.129 |
izable | +2.029 |
UAL | +2.013 |
antically | +1.977 |
Neg logit contributions | |
Britann | -2.798 |
democrat | -2.707 |
politic | -2.707 |
shalt | -2.577 |
Anglo | -2.540 |
Token | ) |
Token ID | 8 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Britann | +4.861 |
politic | +4.689 |
democrat | +4.599 |
shalt | +4.356 |
Anglo | +4.329 |
Neg logit contributions | |
ukong | -5.562 |
specific | -5.432 |
nesota | -5.255 |
antically | -5.252 |
UAL | -5.247 |
Token | – |
Token ID | 784 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Britann | +0.262 |
politic | +0.252 |
democrat | +0.250 |
shalt | +0.236 |
Anglo | +0.233 |
Neg logit contributions | |
ukong | -0.308 |
specific | -0.306 |
izable | -0.295 |
UAL | -0.294 |
antically | -0.291 |
Token | log |
Token ID | 6404 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
specific | +5.480 |
ukong | +5.385 |
izable | +5.147 |
antically | +5.086 |
UAL | +5.051 |
Neg logit contributions | |
Britann | -6.995 |
democrat | -6.725 |
politic | -6.724 |
shalt | -6.423 |
Anglo | -6.412 |
Token | y |
Token ID | 88 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ukong | +1.412 |
specific | +1.409 |
izable | +1.348 |
UAL | +1.340 |
antically | +1.324 |
Neg logit contributions | |
Britann | -1.599 |
politic | -1.544 |
democrat | -1.541 |
shalt | -1.462 |
Anglo | -1.444 |
Token | a |
Token ID | 257 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
specific | +0.852 |
ukong | +0.852 |
izable | +0.820 |
UAL | +0.816 |
antically | +0.808 |
Neg logit contributions | |
Britann | -0.680 |
democrat | -0.650 |
politic | -0.650 |
shalt | -0.609 |
Anglo | -0.600 |
Token | ma |
Token ID | 17266 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
specific | +2.444 |
ukong | +2.437 |
izable | +2.347 |
UAL | +2.334 |
antically | +2.309 |
Neg logit contributions | |
Britann | -2.071 |
democrat | -1.980 |
politic | -1.973 |
shalt | -1.860 |
Anglo | -1.841 |
Token | |
Token ID | 3907 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ukong | +3.444 |
specific | +3.441 |
izable | +3.325 |
UAL | +3.295 |
antically | +3.271 |
Neg logit contributions | |
Britann | -3.190 |
politic | -3.066 |
democrat | -3.058 |
shalt | -2.870 |
Anglo | -2.833 |
Token | j |
Token ID | 73 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
specific | +6.106 |
ukong | +5.885 |
izable | +5.618 |
agi | +5.609 |
nesota | +5.560 |
Neg logit contributions | |
Britann | -9.587 |
politic | -9.283 |
democrat | -9.166 |
Anglo | -8.931 |
shalt | -8.868 |
Token | or |
Token ID | 273 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
antically | +8.109 |
specific | +8.039 |
izable | +7.909 |
ukong | +7.749 |
ual | +7.700 |
Neg logit contributions | |
Britann | -19.048 |
politic | -18.149 |
democrat | -18.022 |
Anglo | -17.653 |
shalt | -17.546 |
Token | thrust |
Token ID | 14613 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
specific | +8.674 |
ukong | +8.567 |
izable | +8.503 |
agi | +8.371 |
UAL | +8.318 |
Neg logit contributions | |
Britann | -6.870 |
politic | -6.478 |
democrat | -6.461 |
shalt | -6.034 |
Anglo | -5.986 |
Token | of |
Token ID | 286 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Britann | +1.412 |
politic | +1.355 |
democrat | +1.348 |
shalt | +1.259 |
Anglo | +1.233 |
Neg logit contributions | |
ukong | -2.146 |
specific | -2.139 |
izable | -2.069 |
UAL | -2.055 |
antically | -2.038 |
Token | his |
Token ID | 465 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
Britann | +1.062 |
politic | +1.024 |
democrat | +1.019 |
shalt | +0.956 |
Anglo | +0.946 |
Neg logit contributions | |
ukong | -1.290 |
specific | -1.288 |
izable | -1.238 |
UAL | -1.234 |
antically | -1.221 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Britann | +0.022 |
politic | +0.021 |
democrat | +0.021 |
shalt | +0.019 |
Anglo | +0.019 |
Neg logit contributions | |
ukong | -0.027 |
specific | -0.027 |
izable | -0.026 |
UAL | -0.025 |
antically | -0.025 |
Token | could |
Token ID | 714 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
specific | +2.954 |
ukong | +2.952 |
izable | +2.864 |
UAL | +2.834 |
antically | +2.810 |
Neg logit contributions | |
Britann | -2.345 |
democrat | -2.241 |
politic | -2.232 |
shalt | -2.105 |
Anglo | -2.052 |
Token | be |
Token ID | 307 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
ukong | +6.338 |
specific | +6.305 |
izable | +6.144 |
UAL | +6.120 |
antically | +6.102 |
Neg logit contributions | |
Britann | -6.243 |
democrat | -5.809 |
politic | -5.801 |
shalt | -5.607 |
Anglo | -5.493 |
Token | . |
Token ID | 13 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
specific | +4.210 |
ukong | +4.175 |
izable | +4.072 |
UAL | +4.012 |
antically | +3.978 |
Neg logit contributions | |
Britann | -3.099 |
democrat | -2.928 |
politic | -2.920 |
shalt | -2.763 |
Anglo | -2.719 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ukong | +0.377 |
specific | +0.376 |
izable | +0.363 |
UAL | +0.361 |
antically | +0.358 |
Neg logit contributions | |
Britann | -0.264 |
politic | -0.253 |
democrat | -0.252 |
shalt | -0.235 |
Anglo | -0.231 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Britann | +1.239 |
politic | +1.179 |
democrat | +1.171 |
shalt | +1.083 |
Anglo | +1.083 |
Neg logit contributions | |
ukong | -1.947 |
specific | -1.919 |
antically | -1.863 |
izable | -1.861 |
UAL | -1.859 |
Token | Mal |
Token ID | 15029 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
specific | +1.135 |
ukong | +1.132 |
izable | +1.092 |
UAL | +1.091 |
antically | +1.076 |
Neg logit contributions | |
Britann | -0.759 |
politic | -0.726 |
democrat | -0.724 |
shalt | -0.675 |
Anglo | -0.663 |
Token | colm |
Token ID | 18414 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ukong | +6.286 |
specific | +6.239 |
ual | +5.848 |
UAL | +5.816 |
izable | +5.727 |
Neg logit contributions | |
Britann | -19.421 |
democrat | -19.185 |
politic | -19.015 |
shalt | -18.806 |
Anglo | -18.235 |
Token | Grim |
Token ID | 17525 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Britann | +2.153 |
politic | +2.043 |
democrat | +2.039 |
shalt | +1.904 |
Anglo | +1.880 |
Neg logit contributions | |
ukong | -3.067 |
specific | -3.052 |
izable | -2.945 |
UAL | -2.930 |
antically | -2.900 |
Token | ston |
Token ID | 3743 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ukong | +1.150 |
specific | +1.149 |
izable | +1.102 |
UAL | +1.094 |
antically | +1.085 |
Neg logit contributions | |
Britann | -1.022 |
politic | -0.986 |
democrat | -0.984 |
shalt | -0.925 |
Anglo | -0.912 |
Token | , |
Token ID | 11 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Britann | +2.457 |
politic | +2.316 |
democrat | +2.306 |
shalt | +2.115 |
Anglo | +2.077 |
Neg logit contributions | |
ukong | -4.903 |
specific | -4.899 |
izable | -4.744 |
UAL | -4.715 |
antically | -4.700 |
Token | a |
Token ID | 257 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Britann | +2.783 |
politic | +2.659 |
democrat | +2.654 |
Anglo | +2.488 |
shalt | +2.487 |
Neg logit contributions | |
ukong | -3.160 |
specific | -3.121 |
izable | -3.011 |
UAL | -2.988 |
antically | -2.968 |
Token | " |
Token ID | 366 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
specific | +5.151 |
ukong | +5.100 |
izable | +4.963 |
UAL | +4.893 |
agi | +4.791 |
Neg logit contributions | |
Britann | -4.155 |
democrat | -4.023 |
politic | -3.962 |
shalt | -3.774 |
Anglo | -3.625 |
Token | Ant |
Token ID | 13217 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
specific | +1.605 |
ukong | +1.588 |
izable | +1.517 |
UAL | +1.515 |
antically | +1.490 |
Neg logit contributions | |
Britann | -1.878 |
politic | -1.820 |
democrat | -1.815 |
shalt | -1.723 |
Anglo | -1.700 |
Token | ip |
Token ID | 541 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
specific | +7.321 |
ukong | +7.250 |
agi | +6.893 |
izable | +6.834 |
antically | +6.685 |
Neg logit contributions | |
Britann | -7.875 |
politic | -7.618 |
democrat | -7.518 |
shalt | -7.235 |
Anglo | -7.188 |
Token | ov |
Token ID | 709 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ukong | +2.666 |
specific | +2.657 |
izable | +2.516 |
UAL | +2.484 |
antically | +2.471 |
Neg logit contributions | |
Britann | -3.536 |
democrat | -3.426 |
politic | -3.421 |
shalt | -3.267 |
Anglo | -3.224 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ukong | +8.077 |
specific | +8.040 |
agi | +7.792 |
antically | +7.790 |
izable | +7.752 |
Neg logit contributions | |
Britann | -4.355 |
democrat | -4.154 |
politic | -4.098 |
shalt | -3.890 |
Anglo | -3.772 |
Token | Mikhail |
Token ID | 42040 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
specific | +5.047 |
ukong | +4.995 |
izable | +4.834 |
UAL | +4.800 |
antically | +4.744 |
Neg logit contributions | |
Britann | -4.202 |
politic | -4.074 |
democrat | -4.070 |
shalt | -3.866 |
Anglo | -3.708 |
Token | Al |
Token ID | 978 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
agi | +11.675 |
ukong | +11.648 |
specific | +11.536 |
UAL | +11.220 |
izable | +11.130 |
Neg logit contributions | |
Britann | -14.029 |
democrat | -13.233 |
politic | -13.102 |
shalt | -12.791 |
Anglo | -12.299 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ukong | +12.188 |
specific | +11.992 |
izable | +11.842 |
agi | +11.657 |
antically | +11.531 |
Neg logit contributions | |
Britann | -9.015 |
politic | -8.749 |
democrat | -8.612 |
Anglo | -8.125 |
shalt | -8.050 |
Token | [ |
Token ID | 685 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
specific | +6.971 |
ukong | +6.859 |
izable | +6.758 |
UAL | +6.704 |
agi | +6.577 |
Neg logit contributions | |
Britann | -2.975 |
democrat | -2.892 |
politic | -2.806 |
shalt | -2.621 |
Anglo | -2.398 |
Token | Result |
Token ID | 23004 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Result | +2.514 |
specific | +2.321 |
izable | +2.064 |
ukong | +1.960 |
agi | +1.871 |
Neg logit contributions | |
Britann | -14.177 |
democrat | -13.527 |
politic | -13.270 |
shalt | -12.988 |
Anglo | -12.927 |
Token | " |
Token ID | 366 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Britann | +0.570 |
politic | +0.543 |
democrat | +0.543 |
shalt | +0.508 |
Anglo | +0.498 |
Neg logit contributions | |
specific | -0.801 |
ukong | -0.801 |
izable | -0.774 |
UAL | -0.768 |
antically | -0.758 |
Token | Way |
Token ID | 6378 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
specific | +1.414 |
ukong | +1.409 |
izable | +1.358 |
UAL | +1.356 |
antically | +1.330 |
Neg logit contributions | |
Britann | -1.032 |
politic | -0.984 |
democrat | -0.981 |
shalt | -0.918 |
Anglo | -0.901 |
Token | man |
Token ID | 805 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ukong | +0.934 |
specific | +0.932 |
izable | +0.897 |
UAL | +0.894 |
antically | +0.885 |
Neg logit contributions | |
Britann | -0.759 |
politic | -0.728 |
democrat | -0.727 |
shalt | -0.682 |
Anglo | -0.672 |
Token | T |
Token ID | 309 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ukong | +6.343 |
specific | +6.283 |
izable | +5.918 |
UAL | +5.916 |
agi | +5.722 |
Neg logit contributions | |
Britann | -7.245 |
democrat | -7.077 |
politic | -7.025 |
shalt | -6.643 |
Anglo | -6.638 |
Token | isd |
Token ID | 9409 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
Britann | +5.346 |
democrat | +5.211 |
politic | +5.190 |
shalt | +4.994 |
Anglo | +4.884 |
Neg logit contributions | |
ukong | -3.629 |
specific | -3.607 |
UAL | -3.479 |
antically | -3.415 |
nesota | -3.343 |
Token | ale |
Token ID | 1000 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
specific | +1.162 |
ukong | +1.161 |
izable | +1.068 |
UAL | +1.058 |
antically | +1.034 |
Neg logit contributions | |
Britann | -3.209 |
politic | -3.127 |
democrat | -3.122 |
shalt | -3.010 |
Anglo | -2.983 |
Token | National |
Token ID | 2351 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
specific | +2.975 |
ukong | +2.973 |
izable | +2.846 |
UAL | +2.844 |
antically | +2.779 |
Neg logit contributions | |
Britann | -2.532 |
democrat | -2.460 |
politic | -2.456 |
shalt | -2.313 |
Anglo | -2.272 |
Token | Fresh |
Token ID | 20138 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
specific | +13.479 |
ukong | +13.150 |
izable | +12.898 |
ized | +12.181 |
UAL | +12.133 |
Neg logit contributions | |
democrat | -11.841 |
politic | -11.227 |
Britann | -11.036 |
shalt | -10.843 |
contrace | -10.255 |
Token | man |
Token ID | 805 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Britann | +3.628 |
politic | +3.397 |
democrat | +3.382 |
shalt | +3.185 |
Anglo | +3.140 |
Neg logit contributions | |
ukong | -5.144 |
specific | -5.019 |
izable | -4.950 |
antically | -4.926 |
UAL | -4.885 |
Token | of |
Token ID | 286 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ukong | +5.658 |
specific | +5.643 |
izable | +5.388 |
UAL | +5.325 |
antically | +5.215 |
Neg logit contributions | |
Britann | -4.421 |
democrat | -4.370 |
politic | -4.269 |
shalt | -3.999 |
Anglo | -3.932 |
Token | the |
Token ID | 262 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Britann | +0.829 |
politic | +0.792 |
democrat | +0.786 |
Anglo | +0.734 |
shalt | +0.733 |
Neg logit contributions | |
ukong | -1.115 |
specific | -1.111 |
izable | -1.072 |
UAL | -1.069 |
antically | -1.063 |
Token | Week |
Token ID | 6119 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Britann | +1.717 |
politic | +1.659 |
democrat | +1.654 |
shalt | +1.577 |
Anglo | +1.563 |
Neg logit contributions | |
ukong | -1.273 |
specific | -1.271 |
izable | -1.210 |
UAL | -1.203 |
antically | -1.187 |
Token | Besides |
Token ID | 23937 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
specific | +0.651 |
ukong | +0.649 |
izable | +0.621 |
UAL | +0.620 |
antically | +0.610 |
Neg logit contributions | |
Britann | -0.687 |
politic | -0.662 |
democrat | -0.661 |
shalt | -0.627 |
Anglo | -0.618 |
Token | Sh |
Token ID | 911 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
specific | +0.543 |
ukong | +0.542 |
izable | +0.523 |
UAL | +0.520 |
antically | +0.514 |
Neg logit contributions | |
Britann | -0.449 |
democrat | -0.428 |
politic | -0.428 |
shalt | -0.405 |
Anglo | -0.396 |
Token | kind |
Token ID | 11031 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
specific | +2.882 |
ukong | +2.824 |
izable | +2.676 |
antically | +2.563 |
agi | +2.557 |
Neg logit contributions | |
Britann | -5.744 |
democrat | -5.582 |
politic | -5.549 |
shalt | -5.348 |
Anglo | -5.332 |
Token | el |
Token ID | 417 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
specific | +0.434 |
ukong | +0.434 |
izable | +0.410 |
UAL | +0.407 |
antically | +0.401 |
Neg logit contributions | |
Britann | -0.692 |
politic | -0.671 |
democrat | -0.670 |
shalt | -0.641 |
Anglo | -0.634 |
Token | , |
Token ID | 11 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
Britann | +0.055 |
democrat | +0.052 |
politic | +0.052 |
shalt | +0.049 |
Anglo | +0.047 |
Neg logit contributions | |
specific | -0.093 |
ukong | -0.093 |
izable | -0.090 |
UAL | -0.090 |
antically | -0.089 |
Token | Mal |
Token ID | 4434 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Britann | +0.197 |
politic | +0.189 |
democrat | +0.189 |
shalt | +0.177 |
Anglo | +0.175 |
Neg logit contributions | |
ukong | -0.231 |
specific | -0.230 |
izable | -0.221 |
UAL | -0.220 |
antically | -0.218 |
Token | anch |
Token ID | 3702 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
specific | +13.014 |
agi | +12.676 |
ukong | +12.652 |
izable | +12.364 |
antically | +12.198 |
Neg logit contributions | |
Britann | -13.189 |
politic | -12.334 |
shalt | -12.259 |
democrat | -12.194 |
contrace | -12.134 |
Token | ak |
Token ID | 461 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
specific | +3.736 |
ukong | +3.701 |
izable | +3.539 |
agi | +3.465 |
UAL | +3.438 |
Neg logit contributions | |
Britann | -4.728 |
democrat | -4.553 |
politic | -4.536 |
shalt | -4.386 |
Anglo | -4.273 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
specific | +2.277 |
ukong | +2.272 |
izable | +2.182 |
UAL | +2.170 |
antically | +2.156 |
Neg logit contributions | |
Britann | -1.734 |
politic | -1.642 |
democrat | -1.641 |
shalt | -1.562 |
Anglo | -1.516 |
Token | Mak |
Token ID | 15841 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Britann | +0.584 |
politic | +0.561 |
democrat | +0.559 |
shalt | +0.525 |
Anglo | +0.519 |
Neg logit contributions | |
ukong | -0.688 |
specific | -0.687 |
izable | -0.660 |
UAL | -0.658 |
antically | -0.651 |
Token | ovi |
Token ID | 47297 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
specific | +2.636 |
ukong | +2.601 |
izable | +2.376 |
UAL | +2.287 |
agi | +2.285 |
Neg logit contributions | |
Britann | -8.155 |
politic | -7.838 |
democrat | -7.831 |
shalt | -7.645 |
Anglo | -7.555 |
Token | of |
Token ID | 286 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
specific | +5.769 |
ukong | +5.705 |
izable | +5.579 |
UAL | +5.509 |
antically | +5.467 |
Neg logit contributions | |
Britann | -4.310 |
politic | -4.117 |
democrat | -4.083 |
shalt | -3.872 |
Anglo | -3.814 |
Token | each |
Token ID | 1123 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
specific | +3.073 |
ukong | +3.059 |
izable | +2.953 |
UAL | +2.928 |
antically | +2.899 |
Neg logit contributions | |
Britann | -2.716 |
politic | -2.617 |
democrat | -2.606 |
shalt | -2.471 |
Anglo | -2.421 |
Token | pixel |
Token ID | 17465 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
specific | +1.732 |
ukong | +1.731 |
izable | +1.658 |
UAL | +1.641 |
antically | +1.622 |
Neg logit contributions | |
Britann | -1.976 |
politic | -1.909 |
democrat | -1.904 |
shalt | -1.811 |
Anglo | -1.787 |
Token | and |
Token ID | 290 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
specific | +5.583 |
ukong | +5.504 |
izable | +5.388 |
UAL | +5.314 |
antically | +5.295 |
Neg logit contributions | |
Britann | -4.506 |
politic | -4.309 |
democrat | -4.284 |
shalt | -4.061 |
Anglo | -4.017 |
Token | have |
Token ID | 423 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
specific | +2.869 |
ukong | +2.831 |
izable | +2.756 |
UAL | +2.718 |
antically | +2.701 |
Neg logit contributions | |
Britann | -2.457 |
politic | -2.352 |
democrat | -2.331 |
shalt | -2.209 |
Anglo | -2.176 |
Token | j |
Token ID | 474 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
specific | +7.527 |
ukong | +7.380 |
izable | +7.304 |
UAL | +7.026 |
antically | +7.014 |
Neg logit contributions | |
Britann | -8.207 |
politic | -7.834 |
democrat | -7.712 |
shalt | -7.473 |
Anglo | -7.222 |
Token | agg |
Token ID | 9460 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
specific | +9.478 |
ukong | +9.442 |
agi | +9.430 |
izable | +9.214 |
antically | +8.862 |
Neg logit contributions | |
Britann | -16.064 |
politic | -16.003 |
democrat | -15.755 |
shalt | -15.045 |
Anglo | -14.919 |
Token | ies |
Token ID | 444 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
specific | +6.973 |
ukong | +6.961 |
izable | +6.764 |
antically | +6.606 |
agi | +6.588 |
Neg logit contributions | |
Britann | -7.410 |
politic | -7.109 |
democrat | -7.099 |
shalt | -6.810 |
Anglo | -6.666 |
Token | but |
Token ID | 475 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
specific | +7.181 |
ukong | +7.044 |
izable | +6.984 |
UAL | +6.799 |
antically | +6.778 |
Neg logit contributions | |
Britann | -5.916 |
politic | -5.657 |
democrat | -5.523 |
shalt | -5.272 |
Anglo | -5.221 |
Token | I |
Token ID | 314 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Britann | +0.488 |
democrat | +0.469 |
politic | +0.469 |
shalt | +0.440 |
Anglo | +0.433 |
Neg logit contributions | |
ukong | -0.590 |
specific | -0.586 |
izable | -0.564 |
UAL | -0.563 |
antically | -0.557 |
Token | have |
Token ID | 423 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
specific | +1.416 |
ukong | +1.404 |
izable | +1.351 |
UAL | +1.349 |
antically | +1.339 |
Neg logit contributions | |
Britann | -1.000 |
politic | -0.948 |
democrat | -0.944 |
Anglo | -0.880 |
shalt | -0.880 |
Token | carried |
Token ID | 5281 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ukong | +6.198 |
specific | +6.102 |
izable | +5.881 |
antically | +5.833 |
UAL | +5.780 |
Neg logit contributions | |
Britann | -5.302 |
democrat | -5.037 |
politic | -5.012 |
shalt | -4.848 |
Anglo | -4.667 |
Token | on |
Token ID | 319 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Britann | +0.859 |
politic | +0.822 |
democrat | +0.819 |
shalt | +0.763 |
Anglo | +0.754 |
Neg logit contributions | |
ukong | -1.191 |
specific | -1.188 |
izable | -1.145 |
UAL | -1.144 |
antically | -1.127 |
Token | , |
Token ID | 11 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Britann | +0.639 |
politic | +0.612 |
democrat | +0.611 |
shalt | +0.571 |
Anglo | +0.563 |
Neg logit contributions | |
ukong | -0.861 |
specific | -0.859 |
izable | -0.828 |
UAL | -0.825 |
antically | -0.816 |
Token | and |
Token ID | 290 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
specific | +3.778 |
ukong | +3.724 |
izable | +3.603 |
UAL | +3.570 |
antically | +3.569 |
Neg logit contributions | |
Britann | -3.274 |
politic | -3.116 |
democrat | -3.116 |
shalt | -2.945 |
Anglo | -2.910 |
Token | the |
Token ID | 262 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
specific | +1.559 |
ukong | +1.551 |
izable | +1.500 |
UAL | +1.483 |
antically | +1.476 |
Neg logit contributions | |
Britann | -1.240 |
politic | -1.185 |
democrat | -1.184 |
shalt | -1.113 |
Anglo | -1.095 |
Token | US |
Token ID | 1294 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
specific | +2.995 |
ukong | +2.987 |
izable | +2.884 |
UAL | +2.874 |
antically | +2.843 |
Neg logit contributions | |
Britann | -2.488 |
democrat | -2.374 |
politic | -2.372 |
shalt | -2.266 |
Anglo | -2.189 |
Token | world |
Token ID | 995 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
specific | +13.868 |
UAL | +13.701 |
izable | +13.566 |
ukong | +13.416 |
antically | +12.830 |
Neg logit contributions | |
Britann | -12.233 |
politic | -10.802 |
democrat | -10.590 |
shalt | -10.567 |
Anglo | -10.451 |
Token | champions |
Token ID | 7827 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
specific | +9.875 |
ukong | +9.612 |
izable | +9.579 |
UAL | +9.265 |
antically | +9.124 |
Neg logit contributions | |
Britann | -9.109 |
politic | -8.562 |
democrat | -8.387 |
shalt | -8.101 |
Anglo | -7.888 |
Token | T |
Token ID | 309 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
specific | +4.896 |
ukong | +4.886 |
izable | +4.699 |
antically | +4.686 |
UAL | +4.668 |
Neg logit contributions | |
Britann | -3.413 |
democrat | -3.234 |
politic | -3.231 |
shalt | -3.024 |
Anglo | -2.972 |
Token | erence |
Token ID | 1945 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Britann | +7.848 |
politic | +7.757 |
democrat | +7.649 |
Anglo | +7.187 |
shalt | +6.994 |
Neg logit contributions | |
specific | -7.528 |
ukong | -7.233 |
nesota | -7.018 |
izable | -6.997 |
UAL | -6.906 |
Token | Crawford |
Token ID | 24499 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
Britann | +4.272 |
democrat | +4.078 |
politic | +3.984 |
Anglo | +3.965 |
shalt | +3.755 |
Neg logit contributions | |
ukong | -6.117 |
specific | -6.062 |
nesota | -5.784 |
UAL | -5.747 |
ulkan | -5.737 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
specific | +4.277 |
ukong | +4.266 |
izable | +4.101 |
UAL | +4.083 |
antically | +4.037 |
Neg logit contributions | |
Britann | -3.815 |
politic | -3.678 |
democrat | -3.674 |
shalt | -3.458 |
Anglo | -3.397 |
Token | Campbell |
Token ID | 14327 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
specific | +4.558 |
ukong | +4.450 |
izable | +4.259 |
UAL | +4.237 |
antically | +4.208 |
Neg logit contributions | |
Britann | -5.358 |
politic | -5.216 |
democrat | -5.211 |
shalt | -4.992 |
Anglo | -4.838 |
Token | and |
Token ID | 290 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ukong | +2.047 |
specific | +2.046 |
izable | +1.965 |
UAL | +1.954 |
antically | +1.935 |
Neg logit contributions | |
Britann | -1.796 |
politic | -1.725 |
democrat | -1.722 |
shalt | -1.621 |
Anglo | -1.599 |
Token | St |
Token ID | 520 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
specific | +1.094 |
ukong | +1.092 |
izable | +1.049 |
UAL | +1.046 |
antically | +1.035 |
Neg logit contributions | |
Britann | -0.911 |
democrat | -0.877 |
politic | -0.876 |
shalt | -0.824 |
Anglo | -0.805 |
Token | eed |
Token ID | 2308 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Britann | +6.478 |
democrat | +6.134 |
politic | +6.033 |
Anglo | +5.835 |
shalt | +5.763 |
Neg logit contributions | |
specific | -5.185 |
ukong | -5.051 |
izable | -4.897 |
UAL | -4.855 |
antically | -4.795 |
Token | Mal |
Token ID | 4434 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Britann | +5.441 |
politic | +5.164 |
democrat | +5.158 |
Anglo | +4.940 |
shalt | +4.879 |
Neg logit contributions | |
specific | -6.031 |
ukong | -6.030 |
izable | -5.956 |
UAL | -5.775 |
antically | -5.764 |
Token | br |
Token ID | 1671 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
specific | +13.447 |
ukong | +12.732 |
agi | +12.692 |
ual | +12.128 |
antically | +12.106 |
Neg logit contributions | |
politic | -12.601 |
democrat | -12.350 |
Britann | -12.280 |
shalt | -11.571 |
Anglo | -11.112 |
Token | an |
Token ID | 272 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ukong | +4.727 |
specific | +4.575 |
agi | +4.457 |
antically | +4.328 |
izable | +4.293 |
Neg logit contributions | |
Britann | -5.875 |
politic | -5.754 |
democrat | -5.704 |
shalt | -5.395 |
Anglo | -5.342 |
Token | que |
Token ID | 4188 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
specific | +5.877 |
ukong | +5.860 |
izable | +5.631 |
UAL | +5.580 |
agi | +5.578 |
Neg logit contributions | |
Britann | -4.893 |
politic | -4.631 |
democrat | -4.619 |
shalt | -4.369 |
Anglo | -4.259 |
Token | in |
Token ID | 287 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ukong | +0.249 |
specific | +0.248 |
izable | +0.238 |
UAL | +0.238 |
antically | +0.235 |
Neg logit contributions | |
Britann | -0.178 |
politic | -0.171 |
democrat | -0.170 |
shalt | -0.158 |
Anglo | -0.157 |
Token | particular |
Token ID | 1948 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
specific | +4.856 |
ukong | +4.840 |
izable | +4.631 |
UAL | +4.597 |
antically | +4.565 |
Neg logit contributions | |
Britann | -4.464 |
politic | -4.314 |
democrat | -4.313 |
shalt | -4.102 |
Anglo | -3.972 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
specific | +1.212 |
ukong | +1.207 |
izable | +1.170 |
UAL | +1.166 |
antically | +1.154 |
Neg logit contributions | |
Britann | -0.693 |
politic | -0.656 |
democrat | -0.653 |
shalt | -0.607 |
Anglo | -0.593 |
Token | star |
Token ID | 3491 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
ukong | +1.390 |
specific | +1.389 |
izable | +1.334 |
UAL | +1.326 |
antically | +1.310 |
Neg logit contributions | |
Britann | -1.298 |
politic | -1.249 |
democrat | -1.246 |
shalt | -1.178 |
Anglo | -1.160 |
Token | power |
Token ID | 1176 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ukong | +0.406 |
specific | +0.405 |
izable | +0.388 |
UAL | +0.387 |
antically | +0.382 |
Neg logit contributions | |
Britann | -0.418 |
politic | -0.404 |
democrat | -0.403 |
shalt | -0.381 |
Anglo | -0.377 |
Token | , |
Token ID | 11 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
specific | +0.187 |
ukong | +0.187 |
izable | +0.181 |
UAL | +0.181 |
antically | +0.179 |
Neg logit contributions | |
Britann | -0.089 |
politic | -0.084 |
democrat | -0.084 |
shalt | -0.077 |
Anglo | -0.075 |
Token | most |
Token ID | 749 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
specific | +1.824 |
ukong | +1.820 |
izable | +1.751 |
UAL | +1.743 |
antically | +1.724 |
Neg logit contributions | |
Britann | -1.506 |
politic | -1.447 |
democrat | -1.439 |
shalt | -1.357 |
Anglo | -1.334 |
Token | national |
Token ID | 2260 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
specific | +3.999 |
ukong | +3.973 |
izable | +3.857 |
UAL | +3.790 |
antically | +3.735 |
Neg logit contributions | |
Britann | -3.448 |
democrat | -3.316 |
politic | -3.314 |
shalt | -3.136 |
Anglo | -3.052 |
Token | observers |
Token ID | 17984 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
specific | +14.028 |
izable | +13.556 |
ukong | +13.176 |
antically | +12.657 |
ized | +12.506 |
Neg logit contributions | |
Britann | -11.438 |
democrat | -10.651 |
shalt | -10.443 |
politic | -10.231 |
artisan | -9.940 |
Token | wrote |
Token ID | 2630 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
specific | +0.897 |
ukong | +0.887 |
izable | +0.859 |
UAL | +0.853 |
antically | +0.847 |
Neg logit contributions | |
Britann | -0.683 |
democrat | -0.651 |
politic | -0.650 |
shalt | -0.610 |
Anglo | -0.604 |
Token | them |
Token ID | 606 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Britann | +3.337 |
democrat | +3.192 |
politic | +3.141 |
shalt | +2.934 |
Anglo | +2.904 |
Neg logit contributions | |
ukong | -4.760 |
specific | -4.670 |
UAL | -4.561 |
izable | -4.548 |
antically | -4.470 |
Token | off |
Token ID | 572 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
specific | +1.087 |
ukong | +1.079 |
izable | +1.042 |
UAL | +1.035 |
antically | +1.031 |
Neg logit contributions | |
Britann | -0.754 |
democrat | -0.717 |
politic | -0.715 |
shalt | -0.668 |
Anglo | -0.654 |
Token | as |
Token ID | 355 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Britann | +1.029 |
politic | +0.992 |
democrat | +0.988 |
shalt | +0.924 |
Anglo | +0.911 |
Neg logit contributions | |
ukong | -1.316 |
specific | -1.304 |
UAL | -1.261 |
izable | -1.253 |
antically | -1.240 |
Token | ] |
Token ID | 60 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Britann | +0.542 |
politic | +0.519 |
democrat | +0.516 |
shalt | +0.482 |
Anglo | +0.478 |
Neg logit contributions | |
ukong | -0.732 |
specific | -0.726 |
izable | -0.700 |
UAL | -0.698 |
antically | -0.692 |
Token | He |
Token ID | 679 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
specific | +4.465 |
ukong | +4.420 |
UAL | +4.280 |
izable | +4.248 |
nesota | +4.114 |
Neg logit contributions | |
Britann | -3.591 |
democrat | -3.561 |
politic | -3.553 |
shalt | -3.323 |
Anglo | -3.181 |
Token | contributed |
Token ID | 8639 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
specific | +2.424 |
ukong | +2.420 |
izable | +2.322 |
UAL | +2.299 |
antically | +2.271 |
Neg logit contributions | |
Britann | -2.113 |
politic | -2.019 |
democrat | -2.016 |
shalt | -1.917 |
Anglo | -1.898 |
Token | to |
Token ID | 284 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
specific | +4.150 |
ukong | +4.127 |
izable | +3.936 |
antically | +3.916 |
UAL | +3.914 |
Neg logit contributions | |
Britann | -3.847 |
democrat | -3.715 |
politic | -3.705 |
shalt | -3.504 |
Anglo | -3.436 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
specific | +3.296 |
ukong | +3.263 |
UAL | +3.136 |
izable | +3.134 |
antically | +3.048 |
Neg logit contributions | |
Britann | -2.957 |
politic | -2.857 |
democrat | -2.849 |
shalt | -2.715 |
Anglo | -2.637 |
Token | national |
Token ID | 2260 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
specific | +4.509 |
ukong | +4.502 |
izable | +4.338 |
UAL | +4.328 |
antically | +4.192 |
Neg logit contributions | |
Britann | -4.437 |
politic | -4.269 |
democrat | -4.249 |
shalt | -4.122 |
Anglo | -4.000 |
Token | championship |
Token ID | 12184 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
specific | +12.665 |
izable | +12.626 |
ukong | +12.167 |
UAL | +11.801 |
ized | +11.734 |
Neg logit contributions | |
Britann | -11.629 |
democrat | -11.044 |
shalt | -10.906 |
politic | -10.901 |
artisan | -10.467 |
Token | with |
Token ID | 351 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
specific | +1.664 |
ukong | +1.661 |
izable | +1.601 |
UAL | +1.589 |
antically | +1.576 |
Neg logit contributions | |
Britann | -1.556 |
democrat | -1.494 |
politic | -1.492 |
shalt | -1.410 |
Anglo | -1.390 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
specific | +3.648 |
ukong | +3.629 |
UAL | +3.496 |
izable | +3.495 |
antically | +3.419 |
Neg logit contributions | |
Britann | -2.845 |
politic | -2.755 |
democrat | -2.744 |
shalt | -2.613 |
Anglo | -2.505 |
Token | points |
Token ID | 2173 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Britann | +1.032 |
politic | +1.006 |
democrat | +1.003 |
shalt | +0.957 |
Anglo | +0.945 |
Neg logit contributions | |
ukong | -0.742 |
specific | -0.736 |
izable | -0.704 |
UAL | -0.695 |
antically | -0.694 |
Token | , |
Token ID | 11 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
ukong | +0.887 |
specific | +0.886 |
izable | +0.856 |
UAL | +0.850 |
antically | +0.845 |
Neg logit contributions | |
Britann | -0.576 |
politic | -0.547 |
democrat | -0.545 |
shalt | -0.508 |
Anglo | -0.501 |
Token | - |
Token ID | 12 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Britann | +0.404 |
politic | +0.386 |
democrat | +0.383 |
shalt | +0.358 |
Anglo | +0.354 |
Neg logit contributions | |
ukong | -0.573 |
specific | -0.570 |
UAL | -0.549 |
izable | -0.549 |
antically | -0.542 |
Token | footed |
Token ID | 43127 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Britann | +1.183 |
politic | +1.143 |
democrat | +1.135 |
shalt | +1.071 |
Anglo | +1.057 |
Neg logit contributions | |
ukong | -1.266 |
specific | -1.244 |
izable | -1.207 |
UAL | -1.207 |
antically | -1.189 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ukong | +0.650 |
specific | +0.648 |
izable | +0.624 |
UAL | +0.622 |
antically | +0.615 |
Neg logit contributions | |
Britann | -0.501 |
politic | -0.480 |
democrat | -0.479 |
shalt | -0.449 |
Anglo | -0.442 |
Token | past |
Token ID | 1613 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
ukong | +1.165 |
specific | +1.162 |
izable | +1.119 |
UAL | +1.115 |
antically | +1.103 |
Neg logit contributions | |
Britann | -0.903 |
politic | -0.865 |
democrat | -0.864 |
shalt | -0.809 |
Anglo | -0.798 |
Token | Ja |
Token ID | 13790 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
specific | +4.217 |
ukong | +4.169 |
izable | +4.043 |
UAL | +4.014 |
antically | +3.995 |
Neg logit contributions | |
Britann | -3.398 |
democrat | -3.307 |
politic | -3.290 |
shalt | -3.110 |
Anglo | -2.986 |
Token | as |
Token ID | 292 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
specific | +4.846 |
ukong | +4.780 |
agi | +4.612 |
izable | +4.592 |
antically | +4.243 |
Neg logit contributions | |
Britann | -13.431 |
democrat | -12.956 |
politic | -12.927 |
shalt | -12.486 |
Anglo | -12.316 |
Token | kel |
Token ID | 7750 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
specific | +7.309 |
ukong | +7.012 |
izable | +6.839 |
ulkan | +6.806 |
agi | +6.767 |
Neg logit contributions | |
Britann | -18.298 |
politic | -17.797 |
contrace | -17.751 |
democrat | -17.581 |
shalt | -17.453 |
Token | ain |
Token ID | 391 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
specific | +6.352 |
ukong | +6.344 |
agi | +6.066 |
antically | +5.872 |
izable | +5.849 |
Neg logit contributions | |
Britann | -11.137 |
politic | -10.972 |
democrat | -10.786 |
shalt | -10.683 |
contrace | -10.374 |
Token | en |
Token ID | 268 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
specific | +8.213 |
ukong | +7.935 |
izable | +7.526 |
agi | +7.499 |
ual | +7.391 |
Neg logit contributions | |
Britann | -12.507 |
contrace | -12.208 |
politic | -11.956 |
shalt | -11.763 |
democrat | -11.659 |
Token | from |
Token ID | 422 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
specific | +8.455 |
ukong | +8.381 |
izable | +8.138 |
agi | +8.037 |
antically | +7.987 |
Neg logit contributions | |
Britann | -6.237 |
democrat | -6.007 |
politic | -5.985 |
shalt | -5.631 |
Anglo | -5.518 |
Token | just |
Token ID | 655 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
specific | +3.874 |
ukong | +3.873 |
izable | +3.721 |
antically | +3.684 |
UAL | +3.681 |
Neg logit contributions | |
Britann | -3.610 |
democrat | -3.494 |
politic | -3.482 |
shalt | -3.308 |
Anglo | -3.216 |
Token | and |
Token ID | 290 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Britann | +0.744 |
democrat | +0.713 |
politic | +0.713 |
shalt | +0.669 |
Anglo | +0.663 |
Neg logit contributions | |
ukong | -0.872 |
specific | -0.862 |
izable | -0.834 |
UAL | -0.830 |
antically | -0.820 |
Token | presumably |
Token ID | 14572 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
specific | +2.806 |
ukong | +2.783 |
izable | +2.693 |
UAL | +2.672 |
antically | +2.644 |
Neg logit contributions | |
Britann | -2.209 |
politic | -2.117 |
democrat | -2.113 |
shalt | -1.987 |
Anglo | -1.941 |
Token | minim |
Token ID | 10356 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
specific | +5.890 |
ukong | +5.846 |
izable | +5.688 |
UAL | +5.547 |
antically | +5.523 |
Neg logit contributions | |
Britann | -4.559 |
politic | -4.388 |
democrat | -4.362 |
shalt | -4.083 |
artisan | -3.971 |
Token | ise |
Token ID | 786 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
izable | +3.834 |
specific | +3.795 |
ukong | +3.724 |
antically | +3.460 |
agi | +3.295 |
Neg logit contributions | |
Britann | -12.318 |
democrat | -11.992 |
politic | -11.989 |
shalt | -11.651 |
Anglo | -11.439 |
Token | any |
Token ID | 597 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
specific | +6.822 |
ukong | +6.819 |
izable | +6.652 |
UAL | +6.555 |
antically | +6.417 |
Neg logit contributions | |
Britann | -6.285 |
democrat | -6.058 |
shalt | -5.947 |
politic | -5.942 |
artisan | -5.506 |
Token | potential |
Token ID | 2785 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
specific | +8.610 |
ukong | +8.593 |
izable | +8.398 |
UAL | +8.286 |
antically | +8.029 |
Neg logit contributions | |
Britann | -7.769 |
democrat | -7.279 |
shalt | -7.207 |
politic | -7.099 |
artisan | -6.945 |
Token | technical |
Token ID | 6276 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ukong | +13.534 |
izable | +13.452 |
specific | +13.440 |
UAL | +13.116 |
inconsistencies | +12.815 |
Neg logit contributions | |
Britann | -10.591 |
shalt | -9.696 |
democrat | -9.648 |
artisan | -9.605 |
politic | -9.244 |
Token | interference |
Token ID | 14517 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
specific | +6.450 |
ukong | +6.220 |
izable | +6.106 |
UAL | +5.983 |
antically | +5.901 |
Neg logit contributions | |
Britann | -8.202 |
democrat | -7.895 |
politic | -7.755 |
shalt | -7.696 |
artisan | -7.397 |
Token | - |
Token ID | 532 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
specific | +6.828 |
ukong | +6.692 |
UAL | +6.550 |
izable | +6.455 |
antically | +6.377 |
Neg logit contributions | |
Britann | -5.489 |
democrat | -5.239 |
politic | -5.197 |
shalt | -5.020 |
Anglo | -4.736 |
Token | LOC |
Token ID | 37347 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Britann | +0.198 |
politic | +0.190 |
democrat | +0.189 |
shalt | +0.177 |
Anglo | +0.175 |
Neg logit contributions | |
ukong | -0.267 |
specific | -0.266 |
izable | -0.257 |
UAL | -0.255 |
antically | -0.253 |
Token | OG |
Token ID | 7730 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
specific | +6.318 |
ukong | +6.312 |
UAL | +6.182 |
izable | +6.019 |
antically | +5.949 |
Neg logit contributions | |
Britann | -5.701 |
politic | -5.507 |
democrat | -5.456 |
shalt | -5.206 |
Anglo | -5.042 |
Token | ed |
Token ID | 276 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Britann | +0.815 |
politic | +0.778 |
democrat | +0.773 |
shalt | +0.725 |
Anglo | +0.713 |
Neg logit contributions | |
ukong | -1.188 |
specific | -1.182 |
izable | -1.142 |
UAL | -1.137 |
antically | -1.124 |
Token | by |
Token ID | 416 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Britann | +1.251 |
politic | +1.191 |
democrat | +1.183 |
shalt | +1.100 |
Anglo | +1.083 |
Neg logit contributions | |
ukong | -2.109 |
specific | -2.091 |
izable | -2.028 |
UAL | -2.024 |
antically | -2.003 |
Token | che |
Token ID | 1125 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
Britann | +1.962 |
politic | +1.874 |
democrat | +1.870 |
shalt | +1.766 |
Anglo | +1.757 |
Neg logit contributions | |
ukong | -2.238 |
specific | -2.233 |
UAL | -2.151 |
izable | -2.150 |
antically | -2.126 |
Token | wy |
Token ID | 21768 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Britann | +0.265 |
politic | +0.256 |
democrat | +0.256 |
shalt | +0.244 |
Anglo | +0.241 |
Neg logit contributions | |
ukong | -0.194 |
specific | -0.194 |
izable | -0.184 |
UAL | -0.183 |
antically | -0.181 |
Token | caramel |
Token ID | 32913 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
Britann | +3.237 |
politic | +3.071 |
democrat | +3.059 |
shalt | +2.896 |
Anglo | +2.884 |
Neg logit contributions | |
ukong | -4.272 |
specific | -4.266 |
UAL | -4.136 |
izable | -4.104 |
antically | -4.095 |
Token | mal |
Token ID | 6428 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Britann | +0.295 |
politic | +0.284 |
democrat | +0.283 |
shalt | +0.269 |
Anglo | +0.266 |
Neg logit contributions | |
ukong | -0.288 |
specific | -0.287 |
UAL | -0.274 |
izable | -0.273 |
antically | -0.270 |
Token | ts |
Token ID | 912 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
specific | +6.564 |
agi | +6.311 |
izable | +5.926 |
oa | +5.915 |
ual | +5.493 |
Neg logit contributions | |
Britann | -19.118 |
politic | -19.093 |
democrat | -18.909 |
Anglo | -18.533 |
shalt | -17.957 |
Token | with |
Token ID | 351 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Britann | +1.812 |
politic | +1.735 |
democrat | +1.724 |
shalt | +1.619 |
Anglo | +1.581 |
Neg logit contributions | |
ukong | -2.686 |
specific | -2.653 |
izable | -2.568 |
UAL | -2.567 |
antically | -2.532 |
Token | a |
Token ID | 257 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
specific | +3.505 |
ukong | +3.496 |
izable | +3.364 |
UAL | +3.329 |
antically | +3.298 |
Neg logit contributions | |
Britann | -3.213 |
politic | -3.101 |
democrat | -3.091 |
shalt | -2.908 |
Anglo | -2.848 |
Token | bisc |
Token ID | 36228 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
specific | +4.371 |
ukong | +4.356 |
izable | +4.183 |
UAL | +4.158 |
antically | +4.102 |
Neg logit contributions | |
Britann | -4.100 |
politic | -3.945 |
democrat | -3.937 |
shalt | -3.713 |
Anglo | -3.644 |
Token | uity |
Token ID | 14834 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
Britann | +2.734 |
politic | +2.579 |
democrat | +2.556 |
shalt | +2.413 |
Anglo | +2.389 |
Neg logit contributions | |
ukong | -3.180 |
specific | -3.152 |
UAL | -3.048 |
antically | -3.016 |
izable | -3.011 |
Token | d |
Token ID | 67 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
specific | +5.510 |
ukong | +5.477 |
UAL | +5.300 |
agi | +5.262 |
izable | +5.257 |
Neg logit contributions | |
Britann | -4.997 |
politic | -4.812 |
democrat | -4.795 |
shalt | -4.543 |
Anglo | -4.435 |
Token |
|
Token ID | 198 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
ukong | +5.030 |
specific | +4.982 |
UAL | +4.799 |
izable | +4.756 |
agi | +4.736 |
Neg logit contributions | |
Britann | -5.188 |
politic | -5.046 |
democrat | -4.996 |
shalt | -4.741 |
Anglo | -4.650 |
Token |
|
Token ID | 198 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
ukong | +0.245 |
specific | +0.245 |
izable | +0.236 |
UAL | +0.235 |
antically | +0.233 |
Neg logit contributions | |
Britann | -0.174 |
politic | -0.166 |
democrat | -0.166 |
shalt | -0.155 |
Anglo | -0.153 |
Token | Gu |
Token ID | 8205 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
specific | +3.827 |
ukong | +3.789 |
UAL | +3.617 |
izable | +3.606 |
antically | +3.528 |
Neg logit contributions | |
Britann | -4.478 |
politic | -4.336 |
democrat | -4.306 |
shalt | -4.105 |
Anglo | -4.046 |
Token | M |
Token ID | 44 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
ukong | +8.355 |
specific | +8.175 |
izable | +8.098 |
UAL | +8.038 |
agi | +7.811 |
Neg logit contributions | |
Britann | -9.578 |
politic | -9.570 |
democrat | -9.118 |
shalt | -8.855 |
Anglo | -8.604 |
Token | ih |
Token ID | 4449 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
specific | +7.174 |
agi | +7.140 |
ukong | +6.950 |
ual | +6.928 |
oa | +6.826 |
Neg logit contributions | |
Britann | -18.522 |
politic | -17.820 |
shalt | -17.163 |
democrat | -17.096 |
Anglo | -16.512 |
Token | o |
Token ID | 78 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
specific | +9.036 |
agi | +8.986 |
ukong | +8.324 |
UAL | +7.946 |
oa | +7.803 |
Neg logit contributions | |
Britann | -17.593 |
politic | -16.799 |
democrat | -16.747 |
shalt | -16.017 |
abolition | -15.387 |
Token |
|
Token ID | 198 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ukong | +2.668 |
specific | +2.663 |
izable | +2.566 |
UAL | +2.556 |
antically | +2.516 |
Neg logit contributions | |
Britann | -2.159 |
politic | -2.089 |
democrat | -2.076 |
shalt | -1.950 |
Anglo | -1.910 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
specific | +2.069 |
ukong | +2.050 |
izable | +1.984 |
UAL | +1.970 |
antically | +1.933 |
Neg logit contributions | |
Britann | -1.612 |
democrat | -1.546 |
politic | -1.545 |
shalt | -1.459 |
Anglo | -1.417 |
Token | The |
Token ID | 464 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
specific | +4.195 |
ukong | +4.172 |
UAL | +3.959 |
izable | +3.954 |
agi | +3.876 |
Neg logit contributions | |
Britann | -5.021 |
politic | -4.860 |
democrat | -4.827 |
shalt | -4.616 |
Anglo | -4.548 |
Token | Best |
Token ID | 13014 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ukong | +1.444 |
specific | +1.443 |
izable | +1.385 |
UAL | +1.378 |
antically | +1.363 |
Neg logit contributions | |
Britann | -1.331 |
politic | -1.282 |
democrat | -1.279 |
shalt | -1.207 |
Anglo | -1.188 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Britann | +0.793 |
politic | +0.758 |
democrat | +0.756 |
shalt | +0.709 |
Anglo | +0.699 |
Neg logit contributions | |
specific | -1.026 |
ukong | -1.024 |
izable | -0.986 |
UAL | -0.983 |
antically | -0.973 |
Token | see |
Token ID | 766 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ukong | +0.727 |
specific | +0.726 |
izable | +0.696 |
UAL | +0.689 |
antically | +0.686 |
Neg logit contributions | |
Britann | -0.627 |
democrat | -0.588 |
politic | -0.587 |
shalt | -0.559 |
Anglo | -0.551 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
specific | +6.522 |
ukong | +6.316 |
izable | +6.234 |
UAL | +6.123 |
antically | +6.020 |
Neg logit contributions | |
Britann | -6.340 |
democrat | -5.855 |
politic | -5.815 |
shalt | -5.670 |
Anglo | -5.507 |
Token | ACLU |
Token ID | 24381 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
specific | +2.280 |
ukong | +2.268 |
izable | +2.204 |
UAL | +2.192 |
antically | +2.170 |
Neg logit contributions | |
Britann | -1.328 |
politic | -1.245 |
democrat | -1.243 |
shalt | -1.165 |
Anglo | -1.136 |
Token | and |
Token ID | 290 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
ukong | +0.330 |
specific | +0.329 |
izable | +0.317 |
UAL | +0.316 |
antically | +0.312 |
Neg logit contributions | |
Britann | -0.249 |
politic | -0.240 |
democrat | -0.239 |
shalt | -0.224 |
Anglo | -0.220 |
Token | Tea |
Token ID | 15777 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
Britann | +3.610 |
politic | +3.489 |
democrat | +3.486 |
shalt | +3.238 |
Anglo | +3.192 |
Neg logit contributions | |
ukong | -4.854 |
specific | -4.751 |
izable | -4.601 |
UAL | -4.575 |
antically | -4.540 |
Token | Party |
Token ID | 3615 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Britann | +9.561 |
democrat | +8.546 |
politic | +8.493 |
shalt | +7.377 |
Anglo | +7.047 |
Neg logit contributions | |
specific | -21.692 |
nesota | -21.616 |
ukong | -21.575 |
ulkan | -21.355 |
antically | -20.711 |
Token | conservatives |
Token ID | 12471 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Britann | +5.492 |
politic | +5.486 |
democrat | +5.470 |
shalt | +4.963 |
Anglo | +4.942 |
Neg logit contributions | |
ukong | -6.827 |
specific | -6.645 |
UAL | -6.406 |
ulkan | -6.386 |
antically | -6.377 |
Token | in |
Token ID | 287 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
Britann | +2.136 |
politic | +2.103 |
democrat | +2.085 |
shalt | +1.944 |
Anglo | +1.902 |
Neg logit contributions | |
ukong | -2.868 |
specific | -2.844 |
izable | -2.754 |
UAL | -2.729 |
antically | -2.692 |
Token | lock |
Token ID | 5793 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
specific | +2.860 |
ukong | +2.844 |
izable | +2.740 |
UAL | +2.717 |
antically | +2.693 |
Neg logit contributions | |
Britann | -2.658 |
democrat | -2.525 |
politic | -2.521 |
shalt | -2.415 |
Anglo | -2.353 |
Token | step |
Token ID | 9662 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Britann | +4.058 |
politic | +3.957 |
democrat | +3.918 |
shalt | +3.599 |
Anglo | +3.584 |
Neg logit contributions | |
ukong | -5.607 |
specific | -5.486 |
UAL | -5.416 |
izable | -5.277 |
antically | -5.217 |
Token | tower |
Token ID | 10580 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
specific | +4.224 |
ukong | +4.189 |
UAL | +4.060 |
izable | +4.039 |
antically | +3.962 |
Neg logit contributions | |
Britann | -3.032 |
democrat | -2.943 |
politic | -2.942 |
shalt | -2.730 |
Anglo | -2.679 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Britann | +6.655 |
politic | +6.345 |
democrat | +6.273 |
shalt | +5.992 |
Anglo | +5.861 |
Neg logit contributions | |
ukong | -7.676 |
specific | -7.545 |
izable | -7.325 |
ulkan | -7.284 |
antically | -7.281 |
Token | Your |
Token ID | 3406 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Britann | +1.014 |
politic | +0.964 |
democrat | +0.957 |
shalt | +0.903 |
Anglo | +0.895 |
Neg logit contributions | |
ukong | -1.312 |
specific | -1.302 |
izable | -1.259 |
UAL | -1.249 |
antically | -1.243 |
Token | wings |
Token ID | 12098 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Britann | +1.150 |
politic | +1.108 |
democrat | +1.102 |
shalt | +1.042 |
Anglo | +1.028 |
Neg logit contributions | |
ukong | -1.247 |
specific | -1.237 |
izable | -1.190 |
UAL | -1.182 |
antically | -1.174 |
Token | are |
Token ID | 389 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Britann | +4.552 |
politic | +4.456 |
democrat | +4.408 |
shalt | +4.066 |
Anglo | +3.869 |
Neg logit contributions | |
ukong | -9.095 |
specific | -8.987 |
izable | -8.694 |
ulkan | -8.636 |
UAL | -8.622 |
Token | folded |
Token ID | 24650 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Britann | +3.486 |
democrat | +3.362 |
politic | +3.350 |
shalt | +3.066 |
Anglo | +3.042 |
Neg logit contributions | |
ukong | -5.538 |
specific | -5.475 |
izable | -5.291 |
UAL | -5.231 |
antically | -5.229 |
Token | ." |
Token ID | 526 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Britann | +13.127 |
politic | +12.563 |
democrat | +12.296 |
shalt | +11.566 |
Anglo | +11.208 |
Neg logit contributions | |
ukong | -16.247 |
nesota | -15.879 |
specific | -15.786 |
ulkan | -15.588 |
izable | -15.296 |
Token | Well |
Token ID | 3894 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Britann | +0.392 |
politic | +0.374 |
democrat | +0.372 |
shalt | +0.348 |
Anglo | +0.344 |
Neg logit contributions | |
ukong | -0.562 |
specific | -0.560 |
izable | -0.540 |
UAL | -0.538 |
antically | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Britann | +2.917 |
politic | +2.802 |
democrat | +2.760 |
shalt | +2.571 |
Anglo | +2.495 |
Neg logit contributions | |
ukong | -5.571 |
specific | -5.537 |
izable | -5.352 |
UAL | -5.351 |
antically | -5.319 |
Token | he |
Token ID | 339 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
specific | +1.372 |
ukong | +1.365 |
izable | +1.316 |
UAL | +1.309 |
antically | +1.296 |
Neg logit contributions | |
Britann | -1.073 |
democrat | -1.027 |
politic | -1.026 |
shalt | -0.962 |
Anglo | -0.943 |
Token | was |
Token ID | 373 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
specific | +3.685 |
ukong | +3.661 |
izable | +3.537 |
UAL | +3.488 |
antically | +3.467 |
Neg logit contributions | |
Britann | -2.946 |
politic | -2.797 |
democrat | -2.787 |
shalt | -2.621 |
Anglo | -2.605 |
Token | division |
Token ID | 7297 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Britann | +5.117 |
politic | +4.973 |
democrat | +4.830 |
Anglo | +4.516 |
shalt | +4.390 |
Neg logit contributions | |
ukong | -7.603 |
specific | -7.490 |
UAL | -7.245 |
izable | -7.215 |
ulkan | -7.191 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Britann | +1.556 |
politic | +1.499 |
democrat | +1.483 |
shalt | +1.389 |
Anglo | +1.373 |
Neg logit contributions | |
ukong | -2.143 |
specific | -2.122 |
izable | -2.052 |
UAL | -2.046 |
antically | -2.015 |
Token | scrutin |
Token ID | 30441 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Britann | +4.814 |
politic | +4.789 |
democrat | +4.707 |
Anglo | +4.361 |
shalt | +4.325 |
Neg logit contributions | |
ukong | -6.581 |
specific | -6.500 |
UAL | -6.385 |
izable | -6.264 |
ulkan | -6.215 |
Token | ized |
Token ID | 1143 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ukong | +0.291 |
specific | +0.288 |
izable | +0.232 |
UAL | +0.213 |
antically | +0.202 |
Neg logit contributions | |
Britann | -2.763 |
politic | -2.704 |
democrat | -2.703 |
shalt | -2.625 |
Anglo | -2.606 |
Token | the |
Token ID | 262 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
specific | +0.909 |
ukong | +0.906 |
izable | +0.876 |
UAL | +0.869 |
antically | +0.865 |
Neg logit contributions | |
Britann | -0.665 |
democrat | -0.633 |
politic | -0.629 |
shalt | -0.598 |
Anglo | -0.579 |
Token | tea |
Token ID | 8887 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Britann | +2.048 |
politic | +2.002 |
democrat | +1.965 |
Anglo | +1.822 |
shalt | +1.807 |
Neg logit contributions | |
ukong | -2.684 |
specific | -2.671 |
izable | -2.572 |
UAL | -2.567 |
antically | -2.530 |
Token | party |
Token ID | 2151 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
politic | +9.975 |
democrat | +9.668 |
Britann | +9.498 |
shalt | +8.400 |
Anglo | +8.088 |
Neg logit contributions | |
ukong | -19.925 |
specific | -19.582 |
nesota | -19.344 |
ulkan | -19.127 |
imei | -18.682 |
Token | applications |
Token ID | 5479 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
politic | +5.851 |
Britann | +5.788 |
democrat | +5.709 |
Anglo | +5.306 |
shalt | +5.170 |
Neg logit contributions | |
ukong | -7.435 |
specific | -7.228 |
ulkan | -6.988 |
UAL | -6.946 |
izable | -6.920 |
Token | until |
Token ID | 1566 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
Britann | +1.382 |
politic | +1.316 |
democrat | +1.306 |
shalt | +1.200 |
Anglo | +1.188 |
Neg logit contributions | |
ukong | -2.537 |
specific | -2.526 |
izable | -2.441 |
UAL | -2.438 |
antically | -2.409 |
Token | she |
Token ID | 673 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Britann | +2.725 |
politic | +2.685 |
democrat | +2.645 |
Anglo | +2.468 |
shalt | +2.435 |
Neg logit contributions | |
ukong | -3.220 |
specific | -3.196 |
UAL | -3.088 |
izable | -3.065 |
antically | -3.031 |
Token | retired |
Token ID | 9880 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Britann | +1.718 |
politic | +1.678 |
democrat | +1.662 |
shalt | +1.518 |
Anglo | +1.496 |
Neg logit contributions | |
ukong | -2.596 |
specific | -2.585 |
UAL | -2.511 |
izable | -2.490 |
antically | -2.464 |
Token | had |
Token ID | 550 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Britann | +0.396 |
politic | +0.378 |
democrat | +0.377 |
shalt | +0.354 |
Anglo | +0.348 |
Neg logit contributions | |
specific | -0.543 |
ukong | -0.541 |
izable | -0.522 |
UAL | -0.519 |
antically | -0.515 |
Token | never |
Token ID | 1239 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
ukong | +0.538 |
specific | +0.537 |
izable | +0.517 |
UAL | +0.515 |
antically | +0.509 |
Neg logit contributions | |
Britann | -0.444 |
politic | -0.426 |
democrat | -0.425 |
shalt | -0.399 |
Anglo | -0.394 |
Token | heard |
Token ID | 2982 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Britann | +3.450 |
politic | +3.415 |
democrat | +3.355 |
shalt | +3.038 |
Anglo | +3.015 |
Neg logit contributions | |
ukong | -5.091 |
specific | -5.037 |
UAL | -4.923 |
izable | -4.888 |
nesota | -4.794 |
Token | of |
Token ID | 286 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
Britann | +1.362 |
politic | +1.303 |
democrat | +1.293 |
shalt | +1.187 |
Anglo | +1.180 |
Neg logit contributions | |
ukong | -2.241 |
specific | -2.236 |
izable | -2.164 |
UAL | -2.157 |
antically | -2.127 |
Token | the |
Token ID | 262 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Britann | +0.242 |
politic | +0.230 |
democrat | +0.230 |
shalt | +0.215 |
Anglo | +0.210 |
Neg logit contributions | |
specific | -0.357 |
ukong | -0.357 |
izable | -0.344 |
UAL | -0.342 |
antically | -0.339 |
Token | tea |
Token ID | 8887 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
Britann | +2.176 |
politic | +2.090 |
democrat | +2.077 |
Anglo | +1.885 |
shalt | +1.874 |
Neg logit contributions | |
ukong | -4.001 |
specific | -3.996 |
izable | -3.860 |
UAL | -3.840 |
antically | -3.810 |
Token | party |
Token ID | 2151 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
politic | +8.571 |
Britann | +8.511 |
democrat | +8.278 |
shalt | +7.112 |
Anglo | +6.863 |
Neg logit contributions | |
specific | -20.095 |
ukong | -20.049 |
nesota | -19.975 |
ulkan | -19.835 |
ahime | -18.963 |
Token | movement |
Token ID | 3356 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
politic | +5.762 |
Britann | +5.746 |
democrat | +5.702 |
Anglo | +5.175 |
shalt | +5.014 |
Neg logit contributions | |
ukong | -8.033 |
specific | -7.959 |
nesota | -7.703 |
UAL | -7.670 |
antically | -7.623 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Britann | +1.076 |
politic | +1.033 |
democrat | +1.030 |
shalt | +0.952 |
Anglo | +0.944 |
Neg logit contributions | |
ukong | -1.525 |
specific | -1.520 |
izable | -1.468 |
UAL | -1.462 |
antically | -1.449 |
Token | which |
Token ID | 543 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
specific | +1.483 |
ukong | +1.476 |
izable | +1.419 |
UAL | +1.411 |
antically | +1.396 |
Neg logit contributions | |
Britann | -1.355 |
politic | -1.300 |
democrat | -1.297 |
shalt | -1.231 |
Anglo | -1.208 |
Token | was |
Token ID | 373 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Britann | +5.050 |
politic | +4.971 |
democrat | +4.971 |
Anglo | +4.482 |
shalt | +4.417 |
Neg logit contributions | |
ukong | -6.838 |
specific | -6.764 |
izable | -6.626 |
UAL | -6.563 |
nesota | -6.540 |
Token | a |
Token ID | 257 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Britann | +3.391 |
politic | +3.220 |
democrat | +3.219 |
Anglo | +3.059 |
shalt | +2.956 |
Neg logit contributions | |
ukong | -4.099 |
specific | -4.065 |
UAL | -3.921 |
izable | -3.898 |
antically | -3.876 |
Token | soft |
Token ID | 2705 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Britann | +1.517 |
politic | +1.455 |
democrat | +1.451 |
shalt | +1.346 |
Anglo | +1.343 |
Neg logit contributions | |
ukong | -2.027 |
specific | -2.018 |
izable | -1.939 |
UAL | -1.935 |
antically | -1.920 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Britann | +5.564 |
politic | +5.349 |
democrat | +5.332 |
Anglo | +5.018 |
shalt | +4.971 |
Neg logit contributions | |
ukong | -6.668 |
specific | -6.545 |
UAL | -6.348 |
izable | -6.309 |
antically | -6.243 |
Token | dr |
Token ID | 7109 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
Britann | +5.014 |
politic | +4.838 |
democrat | +4.821 |
Anglo | +4.476 |
shalt | +4.403 |
Neg logit contributions | |
ukong | -6.245 |
specific | -5.930 |
UAL | -5.906 |
izable | -5.902 |
nesota | -5.863 |
Token | ink |
Token ID | 676 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Britann | +2.720 |
democrat | +2.660 |
politic | +2.658 |
shalt | +2.475 |
Anglo | +2.458 |
Neg logit contributions | |
specific | -3.359 |
ukong | -3.339 |
UAL | -3.249 |
nesota | -3.192 |
izable | -3.192 |
Token | bott |
Token ID | 3005 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
Britann | +6.999 |
politic | +6.674 |
democrat | +6.661 |
shalt | +6.219 |
Anglo | +6.219 |
Neg logit contributions | |
ukong | -9.079 |
specific | -8.826 |
UAL | -8.675 |
antically | -8.502 |
nesota | -8.488 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Britann | +11.095 |
democrat | +10.451 |
politic | +10.381 |
shalt | +10.374 |
Anglo | +9.715 |
Neg logit contributions | |
ukong | -16.426 |
specific | -15.441 |
nesota | -15.257 |
UAL | -15.034 |
ulkan | -14.940 |
Token | company |
Token ID | 1664 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Britann | +6.522 |
politic | +6.133 |
democrat | +6.106 |
Anglo | +5.689 |
shalt | +5.531 |
Neg logit contributions | |
ukong | -12.455 |
specific | -12.179 |
UAL | -11.932 |
antically | -11.799 |
ulkan | -11.740 |
Token | that |
Token ID | 326 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Britann | +5.022 |
politic | +4.836 |
democrat | +4.787 |
Anglo | +4.456 |
shalt | +4.423 |
Neg logit contributions | |
ukong | -7.698 |
specific | -7.462 |
UAL | -7.263 |
izable | -7.232 |
nesota | -7.143 |
Token | became |
Token ID | 2627 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Britann | +6.185 |
democrat | +6.011 |
politic | +5.956 |
Anglo | +5.453 |
shalt | +5.400 |
Neg logit contributions | |
ukong | -8.804 |
specific | -8.698 |
UAL | -8.479 |
antically | -8.380 |
izable | -8.370 |
Token | one |
Token ID | 530 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Britann | +2.317 |
politic | +2.225 |
democrat | +2.216 |
shalt | +2.078 |
Anglo | +2.056 |
Neg logit contributions | |
ukong | -2.878 |
specific | -2.868 |
izable | -2.759 |
UAL | -2.751 |
antically | -2.719 |
Token | they |
Token ID | 484 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
specific | +3.306 |
ukong | +3.256 |
izable | +3.177 |
UAL | +3.132 |
antically | +3.112 |
Neg logit contributions | |
Britann | -2.722 |
democrat | -2.627 |
politic | -2.555 |
shalt | -2.496 |
Anglo | -2.377 |
Token | held |
Token ID | 2714 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
specific | +1.120 |
ukong | +1.118 |
izable | +1.084 |
antically | +1.067 |
UAL | +1.061 |
Neg logit contributions | |
Britann | -0.864 |
democrat | -0.818 |
politic | -0.809 |
shalt | -0.770 |
Anglo | -0.761 |
Token | up |
Token ID | 510 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
specific | +1.074 |
ukong | +1.072 |
izable | +1.034 |
UAL | +1.024 |
antically | +1.017 |
Neg logit contributions | |
Britann | -0.897 |
democrat | -0.861 |
politic | -0.856 |
shalt | -0.813 |
Anglo | -0.792 |
Token | hundreds |
Token ID | 5179 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ukong | +0.315 |
specific | +0.315 |
izable | +0.302 |
UAL | +0.301 |
antically | +0.298 |
Neg logit contributions | |
Britann | -0.281 |
politic | -0.269 |
democrat | -0.269 |
shalt | -0.254 |
Anglo | -0.250 |
Token | of |
Token ID | 286 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
specific | +1.151 |
ukong | +1.147 |
izable | +1.112 |
UAL | +1.103 |
antically | +1.096 |
Neg logit contributions | |
Britann | -0.795 |
democrat | -0.760 |
politic | -0.753 |
shalt | -0.711 |
Anglo | -0.696 |
Token | tea |
Token ID | 8887 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Britann | +1.480 |
politic | +1.426 |
democrat | +1.406 |
shalt | +1.293 |
Anglo | +1.287 |
Neg logit contributions | |
ukong | -2.447 |
specific | -2.433 |
izable | -2.352 |
UAL | -2.352 |
antically | -2.324 |
Token | party |
Token ID | 2151 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
politic | +9.540 |
Britann | +9.230 |
democrat | +8.723 |
shalt | +8.162 |
Anglo | +7.750 |
Neg logit contributions | |
ukong | -19.570 |
nesota | -18.916 |
specific | -18.710 |
ulkan | -18.247 |
antically | -17.931 |
Token | and |
Token ID | 290 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
politic | +4.534 |
Britann | +4.533 |
democrat | +4.447 |
Anglo | +4.114 |
shalt | +4.085 |
Neg logit contributions | |
ukong | -5.125 |
specific | -4.949 |
UAL | -4.811 |
antically | -4.788 |
nesota | -4.740 |
Token | conservative |
Token ID | 5940 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
Britann | +3.827 |
politic | +3.809 |
democrat | +3.762 |
Anglo | +3.422 |
shalt | +3.381 |
Neg logit contributions | |
ukong | -4.896 |
specific | -4.791 |
izable | -4.648 |
antically | -4.646 |
UAL | -4.637 |
Token | group |
Token ID | 1448 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
Britann | +3.712 |
politic | +3.698 |
democrat | +3.621 |
Anglo | +3.373 |
shalt | +3.323 |
Neg logit contributions | |
ukong | -4.128 |
specific | -4.023 |
UAL | -3.873 |
antically | -3.872 |
izable | -3.850 |
Token | applications |
Token ID | 5479 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
specific | +3.763 |
ukong | +3.693 |
izable | +3.588 |
UAL | +3.550 |
antically | +3.485 |
Neg logit contributions | |
Britann | -3.255 |
democrat | -3.115 |
politic | -3.074 |
shalt | -2.964 |
Anglo | -2.872 |
Token | must |
Token ID | 1276 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Britann | +4.187 |
politic | +4.111 |
democrat | +4.097 |
shalt | +3.794 |
Anglo | +3.621 |
Neg logit contributions | |
ukong | -6.597 |
specific | -6.538 |
UAL | -6.380 |
izable | -6.328 |
nesota | -6.255 |
Token | commit |
Token ID | 4589 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
politic | +9.338 |
democrat | +9.313 |
Britann | +9.210 |
shalt | +8.518 |
Anglo | +8.010 |
Neg logit contributions | |
ukong | -11.476 |
specific | -11.329 |
UAL | -10.951 |
izable | -10.889 |
nesota | -10.781 |
Token | ourselves |
Token ID | 6731 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Britann | +3.522 |
politic | +3.368 |
democrat | +3.348 |
shalt | +3.162 |
Anglo | +3.122 |
Neg logit contributions | |
ukong | -5.096 |
specific | -5.055 |
izable | -4.878 |
UAL | -4.828 |
nesota | -4.799 |
Token | very |
Token ID | 845 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Britann | +3.597 |
politic | +3.524 |
democrat | +3.489 |
shalt | +3.317 |
Anglo | +3.237 |
Neg logit contributions | |
ukong | -4.250 |
specific | -4.165 |
izable | -4.035 |
UAL | -3.999 |
antically | -3.913 |
Token | res |
Token ID | 581 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
politic | +5.763 |
Britann | +5.624 |
democrat | +5.610 |
shalt | +5.345 |
Anglo | +5.115 |
Neg logit contributions | |
ukong | -7.343 |
specific | -7.013 |
izable | -6.985 |
UAL | -6.962 |
ulkan | -6.767 |
Token | olutely |
Token ID | 16780 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Britann | +2.354 |
democrat | +2.265 |
politic | +2.257 |
shalt | +2.135 |
Anglo | +2.060 |
Neg logit contributions | |
ukong | -3.251 |
specific | -3.236 |
UAL | -3.170 |
izable | -3.143 |
nesota | -3.073 |
Token | because |
Token ID | 780 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Britann | +10.392 |
democrat | +10.243 |
politic | +10.220 |
shalt | +9.052 |
Anglo | +9.036 |
Neg logit contributions | |
ukong | -16.917 |
nesota | -16.234 |
specific | -16.048 |
UAL | -15.764 |
izable | -15.763 |
Token | there |
Token ID | 612 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Britann | +4.617 |
politic | +4.397 |
democrat | +4.375 |
Anglo | +3.924 |
shalt | +3.922 |
Neg logit contributions | |
ukong | -9.082 |
specific | -8.951 |
UAL | -8.705 |
antically | -8.695 |
izable | -8.659 |
Token | isn |
Token ID | 2125 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
Britann | +1.653 |
democrat | +1.580 |
politic | +1.573 |
shalt | +1.458 |
Anglo | +1.434 |
Neg logit contributions | |
ukong | -2.543 |
specific | -2.543 |
UAL | -2.462 |
izable | -2.460 |
antically | -2.427 |
Token | � |
Token ID | 447 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ukong | +0.208 |
specific | +0.207 |
izable | +0.201 |
UAL | +0.201 |
antically | +0.199 |
Neg logit contributions | |
Britann | -0.107 |
politic | -0.101 |
democrat | -0.101 |
shalt | -0.093 |
Anglo | -0.092 |
Token | � |
Token ID | 247 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
specific | +2.956 |
ukong | +2.913 |
UAL | +2.797 |
izable | +2.724 |
agi | +2.716 |
Neg logit contributions | |
Britann | -4.908 |
politic | -4.772 |
democrat | -4.720 |
shalt | -4.542 |
Anglo | -4.443 |
Token | companies |
Token ID | 2706 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
specific | +1.077 |
ukong | +1.076 |
izable | +1.038 |
UAL | +1.035 |
antically | +1.024 |
Neg logit contributions | |
Britann | -0.699 |
politic | -0.665 |
democrat | -0.664 |
shalt | -0.619 |
Anglo | -0.606 |
Token | letter |
Token ID | 3850 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
Britann | +1.365 |
politic | +1.308 |
democrat | +1.304 |
shalt | +1.218 |
Anglo | +1.197 |
Neg logit contributions | |
ukong | -1.918 |
specific | -1.914 |
izable | -1.848 |
UAL | -1.839 |
antically | -1.821 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Britann | +3.117 |
politic | +3.029 |
democrat | +2.986 |
shalt | +2.772 |
Anglo | +2.732 |
Neg logit contributions | |
ukong | -4.305 |
specific | -4.222 |
izable | -4.097 |
antically | -4.049 |
UAL | -4.049 |
Token | Sen |
Token ID | 2311 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
Britann | +3.509 |
politic | +3.478 |
democrat | +3.441 |
Anglo | +3.101 |
shalt | +3.099 |
Neg logit contributions | |
ukong | -5.385 |
specific | -5.301 |
izable | -5.156 |
UAL | -5.101 |
antically | -5.095 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Britann | +0.135 |
politic | +0.128 |
democrat | +0.128 |
shalt | +0.120 |
Anglo | +0.118 |
Neg logit contributions | |
specific | -0.177 |
ukong | -0.177 |
izable | -0.171 |
UAL | -0.170 |
antically | -0.168 |
Token | Patty |
Token ID | 42417 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
specific | +0.565 |
ukong | +0.564 |
izable | +0.546 |
UAL | +0.544 |
antically | +0.539 |
Neg logit contributions | |
Britann | -0.324 |
politic | -0.307 |
democrat | -0.307 |
shalt | -0.284 |
Anglo | -0.278 |
Token | Murray |
Token ID | 12164 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Britann | +6.174 |
politic | +6.055 |
democrat | +5.256 |
Anglo | +4.724 |
shalt | +4.639 |
Neg logit contributions | |
ukong | -21.431 |
ulkan | -21.255 |
antically | -21.169 |
nesota | -21.071 |
specific | -20.954 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
specific | +1.639 |
ukong | +1.623 |
izable | +1.570 |
UAL | +1.564 |
antically | +1.544 |
Neg logit contributions | |
Britann | -1.205 |
democrat | -1.143 |
politic | -1.139 |
shalt | -1.076 |
Anglo | -1.058 |
Token | Chair |
Token ID | 9369 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
specific | +0.794 |
ukong | +0.792 |
izable | +0.762 |
UAL | +0.759 |
antically | +0.749 |
Neg logit contributions | |
Britann | -0.669 |
politic | -0.639 |
democrat | -0.638 |
shalt | -0.602 |
Anglo | -0.592 |
Token | , |
Token ID | 11 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Britann | +7.481 |
democrat | +7.382 |
politic | +7.380 |
shalt | +6.680 |
Anglo | +6.627 |
Neg logit contributions | |
ukong | -10.625 |
specific | -10.247 |
izable | -10.150 |
antically | -10.018 |
UAL | -9.984 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Britann | +3.134 |
politic | +3.037 |
democrat | +3.026 |
shalt | +2.776 |
Anglo | +2.768 |
Neg logit contributions | |
ukong | -4.817 |
specific | -4.721 |
izable | -4.584 |
UAL | -4.561 |
antically | -4.540 |
Token | of |
Token ID | 286 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
Britann | +1.036 |
politic | +0.986 |
democrat | +0.985 |
shalt | +0.918 |
Anglo | +0.900 |
Neg logit contributions | |
specific | -1.587 |
ukong | -1.586 |
izable | -1.532 |
UAL | -1.527 |
antically | -1.512 |
Token | faculty |
Token ID | 12829 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Britann | +2.598 |
politic | +2.497 |
democrat | +2.487 |
shalt | +2.302 |
Anglo | +2.300 |
Neg logit contributions | |
ukong | -3.765 |
specific | -3.740 |
izable | -3.597 |
UAL | -3.585 |
antically | -3.559 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Britann | +3.915 |
politic | +3.855 |
democrat | +3.792 |
Anglo | +3.456 |
shalt | +3.395 |
Neg logit contributions | |
ukong | -6.393 |
specific | -6.281 |
izable | -6.056 |
UAL | -6.042 |
nesota | -6.002 |
Token | staff |
Token ID | 3085 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Britann | +4.262 |
politic | +4.127 |
democrat | +4.064 |
Anglo | +3.723 |
shalt | +3.722 |
Neg logit contributions | |
ukong | -6.651 |
specific | -6.519 |
izable | -6.306 |
ulkan | -6.280 |
UAL | -6.252 |
Token | who |
Token ID | 508 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
politic | +5.301 |
Britann | +5.242 |
democrat | +5.115 |
Anglo | +4.693 |
shalt | +4.560 |
Neg logit contributions | |
ukong | -8.223 |
specific | -7.949 |
izable | -7.685 |
ulkan | -7.674 |
UAL | -7.672 |
Token | faithfully |
Token ID | 42353 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Britann | +4.150 |
politic | +4.063 |
democrat | +4.029 |
shalt | +3.743 |
Anglo | +3.651 |
Neg logit contributions | |
ukong | -6.171 |
specific | -6.159 |
UAL | -5.940 |
izable | -5.924 |
antically | -5.837 |
Token | serve |
Token ID | 4691 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
politic | +11.854 |
democrat | +11.691 |
Britann | +11.249 |
shalt | +10.914 |
uphold | +10.586 |
Neg logit contributions | |
specific | -15.551 |
ulkan | -15.392 |
ukong | -15.346 |
nesota | -15.125 |
UAL | -15.053 |
Token | our |
Token ID | 674 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Britann | +4.272 |
politic | +4.107 |
democrat | +4.096 |
Anglo | +3.837 |
shalt | +3.777 |
Neg logit contributions | |
ukong | -5.921 |
specific | -5.841 |
izable | -5.624 |
UAL | -5.573 |
antically | -5.552 |
Token | students |
Token ID | 2444 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Britann | +3.855 |
politic | +3.746 |
democrat | +3.726 |
Anglo | +3.434 |
shalt | +3.353 |
Neg logit contributions | |
ukong | -6.168 |
specific | -6.084 |
izable | -5.871 |
nesota | -5.826 |
UAL | -5.814 |
Token | and |
Token ID | 290 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
Britann | +0.434 |
democrat | +0.413 |
politic | +0.412 |
shalt | +0.385 |
Anglo | +0.377 |
Neg logit contributions | |
specific | -0.661 |
ukong | -0.661 |
izable | -0.638 |
UAL | -0.636 |
antically | -0.630 |
Token | patients |
Token ID | 3871 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
Britann | +2.855 |
politic | +2.745 |
democrat | +2.733 |
shalt | +2.556 |
Anglo | +2.524 |
Neg logit contributions | |
ukong | -3.815 |
specific | -3.798 |
izable | -3.653 |
UAL | -3.630 |
antically | -3.610 |
Token | market |
Token ID | 1910 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Britann | +2.254 |
democrat | +2.183 |
politic | +2.181 |
Anglo | +2.036 |
shalt | +2.028 |
Neg logit contributions | |
ukong | -2.637 |
specific | -2.608 |
UAL | -2.504 |
izable | -2.489 |
antically | -2.488 |
Token | , |
Token ID | 11 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
specific | +0.988 |
ukong | +0.981 |
izable | +0.955 |
UAL | +0.947 |
antically | +0.936 |
Neg logit contributions | |
Britann | -0.661 |
democrat | -0.627 |
politic | -0.627 |
shalt | -0.590 |
Anglo | -0.575 |
Token | which |
Token ID | 543 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
specific | +1.262 |
ukong | +1.248 |
izable | +1.206 |
UAL | +1.197 |
antically | +1.182 |
Neg logit contributions | |
Britann | -1.152 |
politic | -1.103 |
democrat | -1.100 |
shalt | -1.046 |
Anglo | -1.022 |
Token | is |
Token ID | 318 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Britann | +1.587 |
politic | +1.516 |
democrat | +1.512 |
shalt | +1.409 |
Anglo | +1.386 |
Neg logit contributions | |
ukong | -2.343 |
specific | -2.340 |
izable | -2.258 |
UAL | -2.249 |
antically | -2.227 |
Token | the |
Token ID | 262 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Britann | +0.715 |
politic | +0.688 |
democrat | +0.687 |
shalt | +0.650 |
Anglo | +0.641 |
Neg logit contributions | |
ukong | -0.717 |
specific | -0.716 |
izable | -0.686 |
UAL | -0.683 |
antically | -0.675 |
Token | bread |
Token ID | 8509 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
Britann | +1.885 |
democrat | +1.817 |
politic | +1.817 |
shalt | +1.684 |
Anglo | +1.680 |
Neg logit contributions | |
ukong | -2.350 |
specific | -2.323 |
UAL | -2.239 |
izable | -2.230 |
antically | -2.215 |
Token | and |
Token ID | 290 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Britann | +12.134 |
democrat | +11.396 |
politic | +11.191 |
shalt | +10.484 |
Anglo | +10.420 |
Neg logit contributions | |
ukong | -16.631 |
izable | -15.178 |
nesota | -14.765 |
ulkan | -14.755 |
UAL | -14.747 |
Token | butter |
Token ID | 9215 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Britann | +6.521 |
democrat | +6.427 |
politic | +6.253 |
shalt | +6.038 |
Anglo | +5.456 |
Neg logit contributions | |
ukong | -10.965 |
specific | -10.664 |
UAL | -10.517 |
antically | -10.443 |
ulkan | -10.383 |
Token | for |
Token ID | 329 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Britann | +6.078 |
politic | +5.948 |
democrat | +5.945 |
Anglo | +5.469 |
shalt | +5.353 |
Neg logit contributions | |
ukong | -9.794 |
specific | -9.445 |
UAL | -9.243 |
antically | -9.198 |
ulkan | -9.164 |
Token | these |
Token ID | 777 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Britann | +1.570 |
politic | +1.514 |
democrat | +1.511 |
shalt | +1.415 |
Anglo | +1.405 |
Neg logit contributions | |
ukong | -1.813 |
specific | -1.804 |
izable | -1.729 |
UAL | -1.727 |
antically | -1.709 |
Token | guys |
Token ID | 3730 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Britann | +1.586 |
politic | +1.530 |
democrat | +1.528 |
shalt | +1.422 |
Anglo | +1.412 |
Neg logit contributions | |
ukong | -2.070 |
specific | -2.057 |
UAL | -1.974 |
izable | -1.972 |
antically | -1.957 |
Token | ! |
Token ID | 0 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ukong | +2.250 |
specific | +2.245 |
UAL | +2.154 |
izable | +2.153 |
antically | +2.125 |
Neg logit contributions | |
Britann | -1.723 |
politic | -1.648 |
democrat | -1.643 |
shalt | -1.534 |
Anglo | -1.520 |
Token | If |
Token ID | 1002 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
Britann | +5.436 |
politic | +5.074 |
democrat | +5.047 |
shalt | +4.820 |
Anglo | +4.816 |
Neg logit contributions | |
ukong | -7.123 |
specific | -7.081 |
izable | -6.818 |
antically | -6.759 |
nesota | -6.748 |
Token | them |
Token ID | 606 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ukong | +0.144 |
specific | +0.143 |
izable | +0.138 |
UAL | +0.137 |
antically | +0.136 |
Neg logit contributions | |
Britann | -0.118 |
politic | -0.113 |
democrat | -0.113 |
shalt | -0.106 |
Anglo | -0.104 |
Token | wings |
Token ID | 12098 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
specific | +4.956 |
ukong | +4.918 |
UAL | +4.791 |
izable | +4.762 |
antically | +4.728 |
Neg logit contributions | |
Britann | -3.901 |
politic | -3.693 |
democrat | -3.686 |
shalt | -3.481 |
Anglo | -3.391 |
Token | are |
Token ID | 389 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
Britann | +4.551 |
democrat | +4.447 |
politic | +4.407 |
shalt | +4.076 |
Anglo | +3.935 |
Neg logit contributions | |
ukong | -7.279 |
specific | -7.232 |
izable | -6.946 |
UAL | -6.876 |
ulkan | -6.839 |
Token | folded |
Token ID | 24650 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
Britann | +3.229 |
democrat | +3.136 |
politic | +3.112 |
shalt | +2.841 |
Anglo | +2.827 |
Neg logit contributions | |
ukong | -5.014 |
specific | -4.986 |
izable | -4.815 |
UAL | -4.763 |
antically | -4.748 |
Token | and |
Token ID | 290 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
Britann | +11.412 |
democrat | +11.250 |
politic | +10.895 |
shalt | +10.247 |
Anglo | +9.819 |
Neg logit contributions | |
ukong | -15.393 |
specific | -15.169 |
nesota | -15.056 |
ulkan | -14.653 |
izable | -14.618 |
Token | you |
Token ID | 345 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
Britann | +3.638 |
democrat | +3.529 |
politic | +3.523 |
shalt | +3.291 |
Anglo | +3.238 |
Neg logit contributions | |
ukong | -4.590 |
specific | -4.543 |
izable | -4.369 |
UAL | -4.362 |
antically | -4.322 |
Token | 're |
Token ID | 821 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Britann | +0.338 |
politic | +0.322 |
democrat | +0.321 |
shalt | +0.301 |
Anglo | +0.297 |
Neg logit contributions | |
specific | -0.441 |
ukong | -0.441 |
izable | -0.424 |
UAL | -0.422 |
antically | -0.419 |
Token | still |
Token ID | 991 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
specific | +1.104 |
ukong | +1.102 |
izable | +1.055 |
UAL | +1.054 |
antically | +1.045 |
Neg logit contributions | |
Britann | -0.984 |
politic | -0.943 |
democrat | -0.938 |
shalt | -0.890 |
Anglo | -0.872 |
Token | flying |
Token ID | 7348 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Britann | +4.275 |
democrat | +4.188 |
politic | +4.168 |
shalt | +3.882 |
Anglo | +3.857 |
Neg logit contributions | |
ukong | -5.025 |
specific | -4.961 |
izable | -4.807 |
UAL | -4.742 |
nesota | -4.694 |
Token | ding |
Token ID | 12083 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ukong | +4.866 |
specific | +4.760 |
izable | +4.607 |
agi | +4.533 |
antically | +4.435 |
Neg logit contributions | |
Britann | -6.671 |
democrat | -6.485 |
politic | -6.476 |
Anglo | -6.109 |
shalt | -6.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Britann | +0.409 |
politic | +0.387 |
democrat | +0.387 |
shalt | +0.357 |
Anglo | +0.349 |
Neg logit contributions | |
ukong | -0.753 |
specific | -0.752 |
izable | -0.728 |
UAL | -0.725 |
antically | -0.718 |
Token | Robert |
Token ID | 5199 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
specific | +0.111 |
ukong | +0.111 |
izable | +0.108 |
UAL | +0.107 |
antically | +0.106 |
Neg logit contributions | |
Britann | -0.065 |
politic | -0.062 |
democrat | -0.061 |
shalt | -0.057 |
Anglo | -0.055 |
Token | G |
Token ID | 402 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Britann | +3.305 |
politic | +3.097 |
democrat | +3.075 |
Anglo | +2.937 |
shalt | +2.879 |
Neg logit contributions | |
ukong | -4.354 |
specific | -4.313 |
UAL | -4.154 |
izable | -4.139 |
antically | -4.114 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ukong | +1.291 |
specific | +1.283 |
izable | +1.240 |
UAL | +1.235 |
antically | +1.221 |
Neg logit contributions | |
Britann | -1.048 |
politic | -1.006 |
democrat | -1.004 |
shalt | -0.948 |
Anglo | -0.927 |
Token | Bott |
Token ID | 14835 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Britann | +1.303 |
politic | +1.234 |
democrat | +1.230 |
Anglo | +1.151 |
shalt | +1.149 |
Neg logit contributions | |
ukong | -1.723 |
specific | -1.714 |
izable | -1.652 |
UAL | -1.645 |
antically | -1.630 |
Token | oms |
Token ID | 3150 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Britann | +14.883 |
democrat | +14.827 |
politic | +14.759 |
shalt | +13.430 |
Anglo | +13.419 |
Neg logit contributions | |
ukong | -10.852 |
specific | -10.652 |
UAL | -10.497 |
antically | -10.408 |
nesota | -10.221 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Britann | +2.079 |
politic | +1.991 |
democrat | +1.983 |
shalt | +1.851 |
Anglo | +1.827 |
Neg logit contributions | |
ukong | -2.856 |
specific | -2.849 |
izable | -2.747 |
UAL | -2.738 |
antically | -2.713 |
Token | Car |
Token ID | 1879 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Britann | +0.526 |
politic | +0.501 |
democrat | +0.500 |
shalt | +0.462 |
Anglo | +0.451 |
Neg logit contributions | |
ukong | -0.934 |
specific | -0.934 |
izable | -0.903 |
UAL | -0.900 |
antically | -0.891 |
Token | in |
Token ID | 259 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Britann | +3.043 |
democrat | +2.924 |
politic | +2.903 |
Anglo | +2.742 |
shalt | +2.704 |
Neg logit contributions | |
ukong | -2.856 |
specific | -2.839 |
UAL | -2.751 |
izable | -2.703 |
antically | -2.658 |
Token | A |
Token ID | 317 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
ukong | +0.521 |
specific | +0.521 |
izable | +0.502 |
UAL | +0.499 |
antically | +0.494 |
Neg logit contributions | |
Britann | -0.409 |
politic | -0.393 |
democrat | -0.393 |
shalt | -0.368 |
Anglo | -0.361 |
Token | . |
Token ID | 13 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
ukong | +0.124 |
specific | +0.124 |
izable | +0.120 |
UAL | +0.119 |
antically | +0.118 |
Neg logit contributions | |
Britann | -0.086 |
politic | -0.082 |
democrat | -0.082 |
shalt | -0.076 |
Anglo | -0.075 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ukong | +0.331 |
specific | +0.331 |
izable | +0.319 |
UAL | +0.317 |
antically | +0.315 |
Neg logit contributions | |
Britann | -0.235 |
politic | -0.224 |
democrat | -0.224 |
shalt | -0.209 |
Anglo | -0.206 |
Token | called |
Token ID | 1444 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Britann | +3.604 |
democrat | +3.443 |
politic | +3.437 |
shalt | +3.217 |
Anglo | +3.190 |
Neg logit contributions | |
ukong | -4.523 |
specific | -4.482 |
izable | -4.336 |
UAL | -4.322 |
antically | -4.283 |
Token | it |
Token ID | 340 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Britann | +0.172 |
politic | +0.165 |
democrat | +0.165 |
shalt | +0.156 |
Anglo | +0.153 |
Neg logit contributions | |
specific | -0.183 |
ukong | -0.183 |
izable | -0.175 |
UAL | -0.174 |
antically | -0.172 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Britann | +1.949 |
politic | +1.872 |
democrat | +1.870 |
shalt | +1.751 |
Anglo | +1.728 |
Neg logit contributions | |
ukong | -2.417 |
specific | -2.406 |
izable | -2.317 |
UAL | -2.315 |
antically | -2.288 |
Token | Brew |
Token ID | 9702 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Britann | +3.729 |
democrat | +3.579 |
politic | +3.567 |
Anglo | +3.301 |
shalt | +3.298 |
Neg logit contributions | |
ukong | -5.089 |
specific | -5.047 |
UAL | -4.895 |
izable | -4.869 |
antically | -4.833 |
Token | Th |
Token ID | 536 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Britann | +15.191 |
politic | +13.929 |
democrat | +13.817 |
shalt | +13.553 |
Anglo | +13.347 |
Neg logit contributions | |
ukong | -11.309 |
UAL | -11.122 |
nesota | -10.795 |
antically | -10.727 |
specific | -10.550 |
Token | ru |
Token ID | 622 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Britann | +7.195 |
democrat | +6.989 |
politic | +6.859 |
shalt | +6.704 |
Anglo | +6.547 |
Neg logit contributions | |
ukong | -6.714 |
specific | -6.705 |
UAL | -6.623 |
izable | -6.485 |
nesota | -6.352 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Britann | +8.019 |
democrat | +7.523 |
politic | +7.491 |
shalt | +7.334 |
Anglo | +7.186 |
Neg logit contributions | |
ukong | -9.213 |
specific | -8.995 |
UAL | -8.838 |
antically | -8.703 |
izable | -8.689 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Britann | +1.261 |
politic | +1.187 |
democrat | +1.180 |
shalt | +1.107 |
Anglo | +1.105 |
Neg logit contributions | |
ukong | -1.839 |
specific | -1.823 |
izable | -1.762 |
UAL | -1.754 |
antically | -1.749 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Britann | +0.635 |
politic | +0.604 |
democrat | +0.600 |
shalt | +0.558 |
Anglo | +0.556 |
Neg logit contributions | |
ukong | -0.967 |
specific | -0.955 |
izable | -0.928 |
antically | -0.923 |
UAL | -0.921 |
Token | taken |
Token ID | 2077 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ukong | +1.439 |
specific | +1.439 |
izable | +1.379 |
UAL | +1.373 |
antically | +1.357 |
Neg logit contributions | |
Britann | -1.331 |
politic | -1.276 |
democrat | -1.273 |
shalt | -1.208 |
Anglo | -1.186 |
Token | off |
Token ID | 572 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Britann | +2.053 |
politic | +1.985 |
democrat | +1.969 |
Anglo | +1.840 |
shalt | +1.834 |
Neg logit contributions | |
ukong | -2.410 |
specific | -2.379 |
izable | -2.310 |
UAL | -2.299 |
antically | -2.266 |
Token | with |
Token ID | 351 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Britann | +3.304 |
politic | +3.189 |
democrat | +3.162 |
Anglo | +2.908 |
shalt | +2.894 |
Neg logit contributions | |
ukong | -4.756 |
specific | -4.674 |
izable | -4.540 |
UAL | -4.530 |
agi | -4.478 |
Token | his |
Token ID | 465 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
specific | +2.294 |
ukong | +2.284 |
izable | +2.194 |
UAL | +2.186 |
antically | +2.160 |
Neg logit contributions | |
Britann | -2.255 |
politic | -2.169 |
democrat | -2.168 |
shalt | -2.067 |
Anglo | -2.018 |
Token | wings |
Token ID | 12098 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
specific | +0.432 |
ukong | +0.432 |
izable | +0.415 |
UAL | +0.414 |
antically | +0.409 |
Neg logit contributions | |
Britann | -0.351 |
politic | -0.337 |
democrat | -0.336 |
shalt | -0.317 |
Anglo | -0.311 |
Token | folded |
Token ID | 24650 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
Britann | +4.953 |
politic | +4.811 |
democrat | +4.807 |
shalt | +4.366 |
Anglo | +4.288 |
Neg logit contributions | |
ukong | -7.720 |
specific | -7.556 |
izable | -7.363 |
UAL | -7.259 |
nesota | -7.242 |
Token | in |
Token ID | 287 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
Britann | +10.468 |
politic | +10.211 |
democrat | +9.984 |
shalt | +8.904 |
Anglo | +8.834 |
Neg logit contributions | |
ukong | -15.858 |
specific | -15.294 |
nesota | -15.101 |
ulkan | -14.833 |
UAL | -14.712 |
Token | an |
Token ID | 281 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ukong | +0.422 |
specific | +0.421 |
izable | +0.404 |
UAL | +0.402 |
antically | +0.398 |
Neg logit contributions | |
Britann | -0.387 |
politic | -0.372 |
democrat | -0.372 |
shalt | -0.350 |
Anglo | -0.346 |
Token | F |
Token ID | 376 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
specific | +2.612 |
ukong | +2.592 |
izable | +2.500 |
UAL | +2.475 |
antically | +2.446 |
Neg logit contributions | |
Britann | -2.874 |
politic | -2.773 |
democrat | -2.773 |
shalt | -2.639 |
Anglo | -2.560 |
Token | 8 |
Token ID | 23 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
Britann | +2.489 |
politic | +2.421 |
democrat | +2.402 |
shalt | +2.265 |
Anglo | +2.257 |
Neg logit contributions | |
ukong | -2.045 |
specific | -2.009 |
izable | -1.929 |
antically | -1.889 |
UAL | -1.885 |
Token | E |
Token ID | 36 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
ukong | +0.206 |
specific | +0.205 |
izable | +0.197 |
UAL | +0.195 |
antically | +0.194 |
Neg logit contributions | |
Britann | -0.193 |
politic | -0.185 |
democrat | -0.185 |
shalt | -0.174 |
Anglo | -0.172 |
Token | like |
Token ID | 2339 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
specific | +1.506 |
ukong | +1.504 |
izable | +1.430 |
UAL | +1.420 |
antically | +1.402 |
Neg logit contributions | |
Britann | -1.973 |
politic | -1.909 |
democrat | -1.907 |
shalt | -1.817 |
Anglo | -1.795 |
Token | challenges |
Token ID | 6459 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Britann | +0.602 |
politic | +0.583 |
democrat | +0.582 |
shalt | +0.550 |
Anglo | +0.545 |
Neg logit contributions | |
ukong | -0.517 |
specific | -0.514 |
UAL | -0.490 |
izable | -0.490 |
antically | -0.485 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
specific | +4.902 |
ukong | +4.828 |
izable | +4.712 |
UAL | +4.675 |
antically | +4.643 |
Neg logit contributions | |
Britann | -3.066 |
politic | -2.895 |
democrat | -2.888 |
shalt | -2.736 |
Anglo | -2.676 |
Token | During |
Token ID | 5856 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
specific | +1.380 |
ukong | +1.371 |
izable | +1.323 |
UAL | +1.321 |
antically | +1.297 |
Neg logit contributions | |
Britann | -0.989 |
democrat | -0.965 |
politic | -0.963 |
shalt | -0.899 |
Anglo | -0.868 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
specific | +1.253 |
ukong | +1.242 |
izable | +1.197 |
UAL | +1.187 |
antically | +1.173 |
Neg logit contributions | |
Britann | -1.128 |
politic | -1.086 |
democrat | -1.084 |
shalt | -1.031 |
Anglo | -1.004 |
Token | Brew |
Token ID | 9702 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Britann | +2.092 |
politic | +2.008 |
democrat | +2.007 |
shalt | +1.873 |
Anglo | +1.868 |
Neg logit contributions | |
ukong | -2.383 |
specific | -2.368 |
izable | -2.282 |
UAL | -2.276 |
antically | -2.247 |
Token | Th |
Token ID | 536 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Britann | +12.226 |
shalt | +11.019 |
politic | +10.818 |
democrat | +10.784 |
Anglo | +10.493 |
Neg logit contributions | |
ukong | -14.326 |
UAL | -14.077 |
nesota | -14.061 |
izable | -14.028 |
specific | -14.025 |
Token | ru |
Token ID | 622 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Britann | +6.378 |
democrat | +6.309 |
politic | +6.201 |
shalt | +5.973 |
Anglo | +5.784 |
Neg logit contributions | |
ukong | -7.209 |
specific | -7.085 |
izable | -6.956 |
UAL | -6.838 |
nesota | -6.789 |
Token | , |
Token ID | 11 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Britann | +7.311 |
politic | +6.879 |
democrat | +6.849 |
shalt | +6.508 |
Anglo | +6.395 |
Neg logit contributions | |
ukong | -9.315 |
specific | -9.096 |
izable | -8.934 |
UAL | -8.914 |
antically | -8.822 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Britann | +1.144 |
politic | +1.090 |
democrat | +1.087 |
shalt | +1.013 |
Anglo | +0.997 |
Neg logit contributions | |
ukong | -1.727 |
specific | -1.717 |
izable | -1.661 |
UAL | -1.656 |
antically | -1.640 |
Token | imb |
Token ID | 33966 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Britann | +3.949 |
democrat | +3.794 |
politic | +3.791 |
shalt | +3.535 |
Anglo | +3.425 |
Neg logit contributions | |
ukong | -5.020 |
specific | -4.971 |
UAL | -4.841 |
izable | -4.836 |
antically | -4.772 |
Token | 207 |
Token ID | 22745 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Britann | +0.717 |
politic | +0.693 |
democrat | +0.692 |
shalt | +0.660 |
Anglo | +0.653 |
Neg logit contributions | |
ukong | -0.504 |
specific | -0.497 |
izable | -0.476 |
UAL | -0.471 |
antically | -0.467 |
Token | , |
Token ID | 11 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
Britann | +1.638 |
politic | +1.561 |
democrat | +1.554 |
shalt | +1.454 |
Anglo | +1.435 |
Neg logit contributions | |
ukong | -2.234 |
specific | -2.219 |
izable | -2.151 |
UAL | -2.123 |
antically | -2.117 |
Token | your |
Token ID | 534 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Britann | +0.303 |
politic | +0.290 |
democrat | +0.289 |
shalt | +0.272 |
Anglo | +0.268 |
Neg logit contributions | |
ukong | -0.372 |
specific | -0.370 |
izable | -0.357 |
UAL | -0.355 |
antically | -0.352 |
Token | wings |
Token ID | 12098 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Britann | +2.430 |
politic | +2.344 |
democrat | +2.322 |
shalt | +2.195 |
Anglo | +2.187 |
Neg logit contributions | |
ukong | -2.411 |
specific | -2.382 |
izable | -2.292 |
UAL | -2.271 |
antically | -2.257 |
Token | are |
Token ID | 389 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Britann | +5.339 |
politic | +5.249 |
democrat | +5.104 |
shalt | +4.843 |
Anglo | +4.643 |
Neg logit contributions | |
ukong | -8.104 |
specific | -7.977 |
izable | -7.773 |
UAL | -7.674 |
ulkan | -7.658 |
Token | folded |
Token ID | 24650 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Britann | +4.259 |
politic | +4.132 |
democrat | +4.085 |
Anglo | +3.803 |
shalt | +3.800 |
Neg logit contributions | |
ukong | -4.966 |
specific | -4.906 |
izable | -4.742 |
UAL | -4.663 |
nesota | -4.640 |
Token | ." |
Token ID | 526 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Britann | +11.483 |
politic | +11.339 |
democrat | +11.061 |
shalt | +10.174 |
Anglo | +9.988 |
Neg logit contributions | |
ukong | -14.794 |
nesota | -14.438 |
specific | -14.426 |
ulkan | -14.171 |
izable | -13.860 |
Token | Calm |
Token ID | 38280 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Britann | +2.104 |
politic | +1.973 |
democrat | +1.956 |
Anglo | +1.843 |
shalt | +1.829 |
Neg logit contributions | |
ukong | -3.156 |
specific | -3.121 |
izable | -3.028 |
antically | -2.994 |
UAL | -2.993 |
Token | ... |
Token ID | 986 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Britann | +2.110 |
politic | +2.013 |
democrat | +2.008 |
shalt | +1.887 |
Anglo | +1.865 |
Neg logit contributions | |
ukong | -2.645 |
specific | -2.642 |
izable | -2.544 |
UAL | -2.528 |
antically | -2.506 |
Token | matter |
Token ID | 47635 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Britann | +4.678 |
politic | +4.488 |
democrat | +4.486 |
shalt | +4.222 |
Anglo | +4.185 |
Neg logit contributions | |
ukong | -4.683 |
specific | -4.527 |
izable | -4.469 |
UAL | -4.397 |
nesota | -4.395 |
Token | of |
Token ID | 286 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
specific | +8.425 |
izable | +8.048 |
UAL | +8.028 |
ukong | +7.979 |
antically | +7.908 |
Neg logit contributions | |
Britann | -7.218 |
democrat | -6.930 |
politic | -6.768 |
Anglo | -6.471 |
shalt | -6.283 |
Token | " |
Token ID | 366 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Britann | +0.694 |
politic | +0.666 |
democrat | +0.663 |
shalt | +0.621 |
Anglo | +0.613 |
Neg logit contributions | |
ukong | -0.904 |
specific | -0.901 |
izable | -0.868 |
UAL | -0.866 |
antically | -0.855 |
Token | P |
Token ID | 47 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Britann | +1.094 |
politic | +1.056 |
democrat | +1.051 |
shalt | +1.000 |
Anglo | +0.990 |
Neg logit contributions | |
ukong | -0.975 |
specific | -0.966 |
izable | -0.928 |
UAL | -0.920 |
antically | -0.911 |
Token | enny |
Token ID | 11870 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Britann | +3.344 |
democrat | +3.252 |
politic | +3.232 |
shalt | +3.060 |
Anglo | +3.023 |
Neg logit contributions | |
specific | -3.026 |
ukong | -2.966 |
izable | -2.864 |
UAL | -2.830 |
nesota | -2.798 |
Token | roy |
Token ID | 3287 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Britann | +5.285 |
politic | +4.904 |
democrat | +4.816 |
shalt | +4.556 |
Anglo | +4.525 |
Neg logit contributions | |
ukong | -7.561 |
specific | -7.445 |
izable | -7.293 |
UAL | -7.246 |
nesota | -7.200 |
Token | al |
Token ID | 282 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
Britann | +2.791 |
politic | +2.698 |
democrat | +2.697 |
shalt | +2.585 |
Anglo | +2.575 |
Neg logit contributions | |
ukong | -1.365 |
specific | -1.355 |
izable | -1.293 |
UAL | -1.285 |
nesota | -1.238 |
Token | Tea |
Token ID | 15777 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Britann | +0.291 |
politic | +0.278 |
democrat | +0.278 |
shalt | +0.260 |
Anglo | +0.256 |
Neg logit contributions | |
ukong | -0.385 |
specific | -0.385 |
izable | -0.370 |
UAL | -0.369 |
antically | -0.365 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Britann | +12.032 |
politic | +10.623 |
shalt | +10.319 |
democrat | +10.124 |
Anglo | +9.812 |
Neg logit contributions | |
ukong | -15.378 |
nesota | -15.126 |
specific | -14.710 |
antically | -14.504 |
UAL | -14.394 |
Token | as |
Token ID | 355 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
specific | +1.310 |
ukong | +1.306 |
izable | +1.256 |
UAL | +1.250 |
antically | +1.238 |
Neg logit contributions | |
Britann | -1.089 |
politic | -1.042 |
democrat | -1.042 |
shalt | -0.980 |
Anglo | -0.965 |
Token | well |
Token ID | 880 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
specific | +2.710 |
ukong | +2.685 |
izable | +2.588 |
UAL | +2.555 |
antically | +2.552 |
Neg logit contributions | |
Britann | -2.456 |
democrat | -2.367 |
politic | -2.352 |
shalt | -2.228 |
Anglo | -2.184 |
Token | as |
Token ID | 355 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
Britann | +0.314 |
politic | +0.302 |
democrat | +0.302 |
shalt | +0.285 |
Anglo | +0.281 |
Neg logit contributions | |
specific | -0.333 |
ukong | -0.333 |
izable | -0.319 |
UAL | -0.318 |
antically | -0.314 |
Token | women |
Token ID | 1466 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
specific | +3.600 |
ukong | +3.568 |
izable | +3.437 |
antically | +3.410 |
UAL | +3.397 |
Neg logit contributions | |
Britann | -2.908 |
democrat | -2.799 |
politic | -2.767 |
shalt | -2.647 |
Anglo | -2.565 |
Token | his |
Token ID | 465 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Britann | +0.245 |
politic | +0.235 |
democrat | +0.234 |
shalt | +0.220 |
Anglo | +0.219 |
Neg logit contributions | |
ukong | -0.262 |
specific | -0.262 |
izable | -0.251 |
UAL | -0.250 |
antically | -0.247 |
Token | massive |
Token ID | 4858 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Britann | +1.008 |
politic | +0.961 |
democrat | +0.959 |
Anglo | +0.895 |
shalt | +0.892 |
Neg logit contributions | |
ukong | -1.224 |
specific | -1.216 |
izable | -1.169 |
UAL | -1.169 |
antically | -1.149 |
Token | army |
Token ID | 5428 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Britann | +0.723 |
politic | +0.691 |
democrat | +0.690 |
shalt | +0.646 |
Anglo | +0.642 |
Neg logit contributions | |
ukong | -0.889 |
specific | -0.887 |
izable | -0.851 |
UAL | -0.850 |
antically | -0.841 |
Token | across |
Token ID | 1973 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Britann | +1.396 |
politic | +1.330 |
democrat | +1.319 |
shalt | +1.231 |
Anglo | +1.215 |
Neg logit contributions | |
ukong | -2.055 |
specific | -2.038 |
UAL | -1.967 |
izable | -1.966 |
antically | -1.942 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Britann | +3.465 |
democrat | +3.183 |
politic | +3.173 |
Anglo | +3.017 |
shalt | +2.983 |
Neg logit contributions | |
ukong | -4.634 |
specific | -4.590 |
UAL | -4.466 |
izable | -4.438 |
nesota | -4.406 |
Token | stra |
Token ID | 3534 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Britann | +4.708 |
politic | +4.422 |
democrat | +4.327 |
Anglo | +4.176 |
shalt | +4.046 |
Neg logit contributions | |
ukong | -6.572 |
specific | -6.458 |
UAL | -6.293 |
nesota | -6.215 |
izable | -6.174 |
Token | it |
Token ID | 270 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Britann | +11.518 |
politic | +11.228 |
democrat | +10.484 |
shalt | +10.410 |
Anglo | +10.007 |
Neg logit contributions | |
UAL | -14.423 |
nesota | -13.726 |
ukong | -13.371 |
specific | -13.323 |
izable | -12.952 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Britann | +3.608 |
politic | +3.399 |
democrat | +3.340 |
shalt | +3.130 |
Anglo | +3.085 |
Neg logit contributions | |
ukong | -5.463 |
specific | -5.383 |
UAL | -5.230 |
izable | -5.200 |
nesota | -5.165 |
Token | ahead |
Token ID | 4058 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ukong | +0.906 |
specific | +0.904 |
izable | +0.869 |
UAL | +0.865 |
antically | +0.855 |
Neg logit contributions | |
Britann | -0.797 |
politic | -0.766 |
democrat | -0.764 |
shalt | -0.719 |
Anglo | -0.709 |
Token | of |
Token ID | 286 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Britann | +1.082 |
politic | +1.027 |
democrat | +1.022 |
shalt | +0.950 |
Anglo | +0.935 |
Neg logit contributions | |
ukong | -1.765 |
specific | -1.756 |
izable | -1.696 |
UAL | -1.695 |
antically | -1.675 |
Token | his |
Token ID | 465 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
specific | +2.329 |
ukong | +2.320 |
izable | +2.242 |
UAL | +2.223 |
antically | +2.204 |
Neg logit contributions | |
Britann | -1.982 |
politic | -1.923 |
democrat | -1.916 |
shalt | -1.812 |
Anglo | -1.762 |
Token | at |
Token ID | 379 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
specific | +1.526 |
ukong | +1.526 |
izable | +1.471 |
UAL | +1.464 |
antically | +1.450 |
Neg logit contributions | |
Britann | -1.081 |
politic | -1.032 |
democrat | -1.030 |
shalt | -0.962 |
Anglo | -0.947 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ukong | +1.489 |
specific | +1.485 |
izable | +1.422 |
UAL | +1.416 |
antically | +1.398 |
Neg logit contributions | |
Britann | -1.517 |
politic | -1.463 |
democrat | -1.460 |
shalt | -1.380 |
Anglo | -1.363 |
Token | B |
Token ID | 347 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Britann | +0.615 |
politic | +0.592 |
democrat | +0.590 |
shalt | +0.555 |
Anglo | +0.548 |
Neg logit contributions | |
ukong | -0.703 |
specific | -0.699 |
izable | -0.671 |
UAL | -0.670 |
antically | -0.662 |
Token | DP |
Token ID | 6322 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Britann | +1.092 |
democrat | +1.056 |
politic | +1.054 |
shalt | +0.997 |
Anglo | +0.981 |
Neg logit contributions | |
ukong | -1.018 |
specific | -1.014 |
izable | -0.973 |
UAL | -0.966 |
antically | -0.955 |
Token | + |
Token ID | 1343 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
specific | +1.832 |
ukong | +1.828 |
izable | +1.757 |
UAL | +1.744 |
antically | +1.724 |
Neg logit contributions | |
Britann | -1.751 |
politic | -1.685 |
democrat | -1.683 |
shalt | -1.587 |
Anglo | -1.569 |
Token | Bott |
Token ID | 14835 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
ukong | +0.645 |
specific | +0.641 |
izable | +0.616 |
UAL | +0.613 |
antically | +0.607 |
Neg logit contributions | |
Britann | -0.627 |
politic | -0.605 |
democrat | -0.603 |
shalt | -0.570 |
Anglo | -0.562 |
Token | leneck |
Token ID | 43163 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Britann | +9.452 |
politic | +9.318 |
democrat | +9.274 |
shalt | +8.623 |
Anglo | +8.193 |
Neg logit contributions | |
ukong | -15.430 |
nesota | -14.680 |
izable | -14.451 |
antically | -14.201 |
UAL | -14.172 |
Token | Buffer |
Token ID | 47017 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Britann | +0.481 |
politic | +0.464 |
democrat | +0.461 |
shalt | +0.438 |
Anglo | +0.431 |
Neg logit contributions | |
ukong | -0.488 |
specific | -0.485 |
UAL | -0.465 |
izable | -0.463 |
antically | -0.458 |
Token | Size |
Token ID | 12849 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Britann | +4.410 |
politic | +4.245 |
democrat | +4.171 |
shalt | +3.958 |
Anglo | +3.901 |
Neg logit contributions | |
ukong | -4.927 |
specific | -4.785 |
UAL | -4.677 |
nesota | -4.630 |
antically | -4.627 |
Token | point |
Token ID | 966 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ukong | +0.594 |
specific | +0.593 |
izable | +0.570 |
UAL | +0.568 |
antically | +0.562 |
Neg logit contributions | |
Britann | -0.490 |
politic | -0.471 |
democrat | -0.470 |
shalt | -0.441 |
Anglo | -0.435 |
Token | ( |
Token ID | 357 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Britann | +0.574 |
politic | +0.551 |
democrat | +0.550 |
shalt | +0.512 |
Anglo | +0.501 |
Neg logit contributions | |
ukong | -0.826 |
specific | -0.820 |
izable | -0.793 |
UAL | -0.790 |
antically | -0.780 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
specific | +3.063 |
ukong | +3.062 |
izable | +2.982 |
antically | +2.941 |
UAL | +2.914 |
Neg logit contributions | |
Britann | -1.435 |
democrat | -1.326 |
politic | -1.316 |
shalt | -1.246 |
Anglo | -1.208 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
specific | +3.655 |
ukong | +3.574 |
izable | +3.488 |
antically | +3.465 |
UAL | +3.447 |
Neg logit contributions | |
Britann | -2.889 |
democrat | -2.735 |
politic | -2.727 |
shalt | -2.588 |
Anglo | -2.571 |
Token | : |
Token ID | 25 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
specific | +1.487 |
ukong | +1.484 |
izable | +1.421 |
UAL | +1.414 |
antically | +1.405 |
Neg logit contributions | |
Britann | -1.467 |
politic | -1.407 |
democrat | -1.407 |
shalt | -1.332 |
Anglo | -1.315 |
Token | ' |
Token ID | 705 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Britann | +2.974 |
politic | +2.822 |
democrat | +2.776 |
Anglo | +2.476 |
shalt | +2.423 |
Neg logit contributions | |
ukong | -6.371 |
specific | -6.350 |
izable | -6.186 |
UAL | -6.138 |
ulkan | -6.072 |
Token | I |
Token ID | 40 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Britann | +3.897 |
politic | +3.752 |
democrat | +3.668 |
shalt | +3.480 |
Anglo | +3.365 |
Neg logit contributions | |
ukong | -6.033 |
izable | -5.973 |
nesota | -5.966 |
specific | -5.868 |
UAL | -5.830 |
Token | fully |
Token ID | 3938 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Britann | +4.351 |
democrat | +4.134 |
politic | +4.122 |
shalt | +3.938 |
Anglo | +3.722 |
Neg logit contributions | |
ukong | -6.818 |
specific | -6.630 |
izable | -6.565 |
nesota | -6.429 |
ulkan | -6.427 |
Token | expect |
Token ID | 1607 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
politic | +9.705 |
democrat | +8.757 |
Britann | +8.721 |
endorsed | +8.299 |
shalt | +8.203 |
Neg logit contributions | |
ukong | -17.041 |
AMI | -16.953 |
specific | -16.836 |
ahime | -16.814 |
nesota | -16.812 |
Token | ' |
Token ID | 6 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
specific | +1.644 |
ukong | +1.632 |
UAL | +1.583 |
izable | +1.567 |
antically | +1.547 |
Neg logit contributions | |
Britann | -1.541 |
politic | -1.485 |
democrat | -1.480 |
shalt | -1.412 |
Anglo | -1.387 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
specific | +1.168 |
ukong | +1.168 |
izable | +1.129 |
UAL | +1.127 |
antically | +1.111 |
Neg logit contributions | |
Britann | -0.735 |
politic | -0.699 |
democrat | -0.698 |
shalt | -0.654 |
Anglo | -0.633 |
Token | treatment |
Token ID | 3513 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Britann | +4.525 |
democrat | +4.442 |
politic | +4.404 |
shalt | +4.217 |
Anglo | +4.041 |
Neg logit contributions | |
specific | -6.251 |
ukong | -6.206 |
izable | -5.873 |
UAL | -5.871 |
antically | -5.863 |
Token | by |
Token ID | 416 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Britann | +2.358 |
politic | +2.335 |
democrat | +2.318 |
shalt | +2.090 |
Anglo | +2.080 |
Neg logit contributions | |
specific | -4.184 |
ukong | -4.179 |
antically | -4.021 |
agi | -4.015 |
izable | -4.011 |
Token | interviewing |
Token ID | 31481 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
Britann | +0.651 |
politic | +0.629 |
democrat | +0.628 |
shalt | +0.587 |
Anglo | +0.581 |
Neg logit contributions | |
ukong | -0.753 |
specific | -0.746 |
izable | -0.718 |
UAL | -0.715 |
antically | -0.706 |
Token | process |
Token ID | 1429 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
specific | +4.958 |
ukong | +4.788 |
izable | +4.746 |
UAL | +4.697 |
antically | +4.657 |
Neg logit contributions | |
Britann | -3.520 |
politic | -3.289 |
democrat | -3.245 |
shalt | -3.078 |
Anglo | -3.024 |
Token | : |
Token ID | 25 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
specific | +1.932 |
ukong | +1.921 |
izable | +1.867 |
UAL | +1.865 |
antically | +1.841 |
Neg logit contributions | |
Britann | -1.039 |
politic | -0.981 |
democrat | -0.976 |
shalt | -0.895 |
Anglo | -0.884 |
Token |
|
Token ID | 198 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Britann | +1.792 |
democrat | +1.723 |
politic | +1.714 |
shalt | +1.599 |
Anglo | +1.568 |
Neg logit contributions | |
ukong | -2.661 |
specific | -2.639 |
izable | -2.553 |
UAL | -2.545 |
antically | -2.520 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Britann | +2.875 |
politic | +2.732 |
democrat | +2.700 |
Anglo | +2.493 |
shalt | +2.446 |
Neg logit contributions | |
ukong | -5.415 |
specific | -5.241 |
antically | -5.222 |
UAL | -5.148 |
izable | -5.143 |
Token | Interview |
Token ID | 39945 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Britann | +1.594 |
democrat | +1.548 |
politic | +1.546 |
shalt | +1.465 |
Anglo | +1.442 |
Neg logit contributions | |
ukong | -1.444 |
specific | -1.418 |
izable | -1.366 |
UAL | -1.356 |
antically | -1.345 |
Token | preparation |
Token ID | 11824 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
specific | +8.539 |
ukong | +8.194 |
UAL | +8.022 |
izable | +7.969 |
antically | +7.827 |
Neg logit contributions | |
Britann | -7.208 |
politic | -6.837 |
democrat | -6.715 |
Anglo | -6.330 |
shalt | -6.265 |
Token | books |
Token ID | 3835 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
specific | +0.601 |
ukong | +0.598 |
izable | +0.578 |
UAL | +0.575 |
antically | +0.569 |
Neg logit contributions | |
Britann | -0.441 |
politic | -0.421 |
democrat | -0.419 |
shalt | -0.392 |
Anglo | -0.387 |
Token | are |
Token ID | 389 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
Britann | +4.059 |
democrat | +3.923 |
politic | +3.886 |
shalt | +3.646 |
Anglo | +3.487 |
Neg logit contributions | |
ukong | -6.265 |
specific | -6.143 |
UAL | -5.959 |
izable | -5.946 |
antically | -5.904 |
Token | good |
Token ID | 922 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Britann | +3.164 |
democrat | +3.087 |
politic | +3.075 |
shalt | +2.872 |
Anglo | +2.838 |
Neg logit contributions | |
ukong | -3.445 |
specific | -3.381 |
UAL | -3.251 |
izable | -3.241 |
antically | -3.210 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
Britann | +1.622 |
democrat | +1.557 |
politic | +1.551 |
shalt | +1.447 |
Anglo | +1.420 |
Neg logit contributions | |
ukong | -2.379 |
specific | -2.358 |
UAL | -2.273 |
izable | -2.265 |
antically | -2.252 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Britann | +0.185 |
democrat | +0.175 |
politic | +0.175 |
shalt | +0.163 |
Anglo | +0.160 |
Neg logit contributions | |
specific | -0.289 |
ukong | -0.288 |
izable | -0.278 |
UAL | -0.277 |
antically | -0.275 |
Token | opposite |
Token ID | 6697 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
specific | +0.671 |
ukong | +0.670 |
izable | +0.652 |
UAL | +0.650 |
antically | +0.645 |
Neg logit contributions | |
Britann | -0.225 |
politic | -0.208 |
democrat | -0.207 |
shalt | -0.186 |
Anglo | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Britann | +2.651 |
politic | +2.585 |
democrat | +2.565 |
shalt | +2.363 |
Anglo | +2.320 |
Neg logit contributions | |
ukong | -4.243 |
specific | -4.202 |
izable | -4.036 |
UAL | -4.021 |
antically | -3.990 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Britann | +1.742 |
politic | +1.640 |
democrat | +1.626 |
Anglo | +1.525 |
shalt | +1.512 |
Neg logit contributions | |
ukong | -2.591 |
specific | -2.580 |
izable | -2.492 |
antically | -2.475 |
UAL | -2.475 |
Token | The |
Token ID | 464 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
specific | +4.831 |
ukong | +4.712 |
UAL | +4.582 |
izable | +4.507 |
antically | +4.411 |
Neg logit contributions | |
Britann | -4.985 |
democrat | -4.767 |
politic | -4.767 |
shalt | -4.535 |
Anglo | -4.472 |
Token | US |
Token ID | 1294 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ukong | +1.021 |
specific | +1.020 |
izable | +0.982 |
UAL | +0.978 |
antically | +0.968 |
Neg logit contributions | |
Britann | -0.790 |
politic | -0.757 |
democrat | -0.755 |
shalt | -0.710 |
Anglo | -0.696 |
Token | state |
Token ID | 1181 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
UAL | +11.733 |
specific | +11.708 |
ukong | +11.622 |
izable | +11.268 |
antically | +10.970 |
Neg logit contributions | |
Britann | -8.480 |
politic | -7.530 |
democrat | -7.451 |
shalt | -7.190 |
Anglo | -7.167 |
Token | department |
Token ID | 5011 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
specific | +5.630 |
ukong | +5.544 |
UAL | +5.431 |
izable | +5.418 |
antically | +5.273 |
Neg logit contributions | |
Britann | -4.673 |
democrat | -4.304 |
politic | -4.291 |
shalt | -4.104 |
Anglo | -4.066 |
Token | has |
Token ID | 468 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ukong | +1.182 |
specific | +1.180 |
UAL | +1.132 |
izable | +1.130 |
antically | +1.114 |
Neg logit contributions | |
Britann | -0.911 |
democrat | -0.866 |
politic | -0.864 |
shalt | -0.817 |
Anglo | -0.801 |
Token | approved |
Token ID | 6325 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ukong | +0.209 |
specific | +0.209 |
izable | +0.201 |
UAL | +0.200 |
antically | +0.198 |
Neg logit contributions | |
Britann | -0.154 |
democrat | -0.147 |
politic | -0.146 |
shalt | -0.138 |
Anglo | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Britann | +1.642 |
politic | +1.586 |
democrat | +1.582 |
shalt | +1.481 |
Anglo | +1.477 |
Neg logit contributions | |
ukong | -1.754 |
specific | -1.741 |
izable | -1.674 |
UAL | -1.666 |
antically | -1.650 |
Token | my |
Token ID | 616 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
specific | +2.817 |
ukong | +2.751 |
izable | +2.690 |
UAL | +2.678 |
antically | +2.649 |
Neg logit contributions | |
Britann | -2.211 |
politic | -2.108 |
democrat | -2.107 |
shalt | -1.984 |
Anglo | -1.941 |
Token | last |
Token ID | 938 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
specific | +2.586 |
ukong | +2.553 |
izable | +2.487 |
UAL | +2.471 |
antically | +2.442 |
Neg logit contributions | |
Britann | -2.294 |
politic | -2.206 |
democrat | -2.199 |
shalt | -2.086 |
Anglo | -2.035 |
Token | phone |
Token ID | 3072 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
specific | +0.711 |
ukong | +0.706 |
izable | +0.683 |
UAL | +0.680 |
antically | +0.672 |
Neg logit contributions | |
Britann | -0.600 |
politic | -0.577 |
democrat | -0.575 |
shalt | -0.542 |
Anglo | -0.532 |
Token | call |
Token ID | 869 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
Britann | +0.361 |
politic | +0.347 |
democrat | +0.346 |
shalt | +0.327 |
Anglo | +0.323 |
Neg logit contributions | |
ukong | -0.397 |
specific | -0.394 |
izable | -0.378 |
UAL | -0.377 |
antically | -0.372 |
Token | with |
Token ID | 351 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Britann | +0.283 |
politic | +0.269 |
democrat | +0.268 |
shalt | +0.247 |
Anglo | +0.242 |
Neg logit contributions | |
ukong | -0.525 |
specific | -0.525 |
izable | -0.508 |
UAL | -0.506 |
antically | -0.501 |
Token | M |
Token ID | 337 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
specific | +2.390 |
ukong | +2.377 |
izable | +2.301 |
UAL | +2.281 |
antically | +2.262 |
Neg logit contributions | |
Britann | -2.019 |
politic | -1.941 |
democrat | -1.940 |
shalt | -1.839 |
Anglo | -1.790 |
Token | imi |
Token ID | 25236 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ukong | +4.608 |
specific | +4.331 |
izable | +4.228 |
UAL | +4.204 |
antically | +4.144 |
Neg logit contributions | |
Britann | -12.055 |
politic | -11.691 |
democrat | -11.485 |
shalt | -11.402 |
Anglo | -11.147 |
Token | L |
Token ID | 406 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
specific | +6.195 |
ukong | +6.140 |
izable | +6.011 |
antically | +5.946 |
UAL | +5.935 |
Neg logit contributions | |
Britann | -3.380 |
politic | -3.249 |
democrat | -3.243 |
shalt | -2.980 |
Anglo | -2.887 |
Token | eder |
Token ID | 5702 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
Britann | +0.075 |
democrat | +0.072 |
politic | +0.072 |
shalt | +0.066 |
Anglo | +0.064 |
Neg logit contributions | |
ukong | -0.141 |
specific | -0.141 |
UAL | -0.136 |
izable | -0.136 |
antically | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Britann | +0.151 |
politic | +0.142 |
democrat | +0.142 |
shalt | +0.129 |
Anglo | +0.126 |
Neg logit contributions | |
ukong | -0.328 |
specific | -0.327 |
izable | -0.317 |
UAL | -0.316 |
antically | -0.314 |
Token | she |
Token ID | 673 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
specific | +2.609 |
ukong | +2.585 |
izable | +2.509 |
UAL | +2.500 |
antically | +2.479 |
Neg logit contributions | |
Britann | -1.737 |
politic | -1.664 |
democrat | -1.663 |
shalt | -1.551 |
Anglo | -1.515 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
specific | +0.630 |
ukong | +0.630 |
izable | +0.607 |
UAL | +0.605 |
antically | +0.598 |
Neg logit contributions | |
Britann | -0.459 |
politic | -0.441 |
democrat | -0.439 |
shalt | -0.411 |
Anglo | -0.403 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Britann | +1.232 |
politic | +1.173 |
democrat | +1.164 |
Anglo | +1.079 |
shalt | +1.077 |
Neg logit contributions | |
ukong | -1.891 |
specific | -1.866 |
izable | -1.810 |
UAL | -1.807 |
antically | -1.804 |
Token | FR |
Token ID | 10913 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
specific | +1.554 |
ukong | +1.537 |
UAL | +1.480 |
izable | +1.475 |
antically | +1.446 |
Neg logit contributions | |
Britann | -1.624 |
politic | -1.573 |
democrat | -1.565 |
shalt | -1.485 |
Anglo | -1.458 |
Token | OM |
Token ID | 2662 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Britann | +1.032 |
politic | +0.997 |
democrat | +0.997 |
shalt | +0.953 |
Anglo | +0.946 |
Neg logit contributions | |
ukong | -0.759 |
specific | -0.756 |
izable | -0.720 |
UAL | -0.703 |
antically | -0.699 |
Token | THE |
Token ID | 3336 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Britann | +1.197 |
politic | +1.149 |
democrat | +1.148 |
shalt | +1.081 |
Anglo | +1.068 |
Neg logit contributions | |
ukong | -1.362 |
specific | -1.356 |
izable | -1.307 |
UAL | -1.294 |
antically | -1.287 |
Token | AR |
Token ID | 5923 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Britann | +2.754 |
politic | +2.629 |
democrat | +2.619 |
shalt | +2.465 |
Anglo | +2.463 |
Neg logit contributions | |
ukong | -3.122 |
specific | -3.079 |
izable | -2.983 |
antically | -2.942 |
nesota | -2.920 |
Token | CH |
Token ID | 3398 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
UAL | +7.158 |
specific | +7.086 |
ukong | +6.826 |
izable | +6.676 |
agi | +6.398 |
Neg logit contributions | |
Britann | -10.818 |
politic | -10.613 |
democrat | -10.590 |
shalt | -10.079 |
Anglo | -9.822 |
Token | IVE |
Token ID | 9306 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
specific | +3.634 |
ukong | +3.570 |
UAL | +3.527 |
izable | +3.437 |
antically | +3.350 |
Neg logit contributions | |
Britann | -5.664 |
democrat | -5.589 |
politic | -5.583 |
shalt | -5.317 |
Anglo | -5.234 |
Token | : |
Token ID | 25 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Britann | +0.118 |
politic | +0.113 |
democrat | +0.113 |
shalt | +0.106 |
Anglo | +0.104 |
Neg logit contributions | |
specific | -0.160 |
ukong | -0.159 |
UAL | -0.154 |
izable | -0.154 |
antically | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Britann | +1.099 |
politic | +1.045 |
democrat | +1.043 |
shalt | +0.975 |
Anglo | +0.972 |
Neg logit contributions | |
ukong | -1.399 |
specific | -1.391 |
izable | -1.344 |
UAL | -1.334 |
antically | -1.327 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Britann | +1.373 |
politic | +1.304 |
democrat | +1.293 |
Anglo | +1.202 |
shalt | +1.194 |
Neg logit contributions | |
ukong | -2.171 |
specific | -2.136 |
izable | -2.077 |
antically | -2.076 |
UAL | -2.067 |
Token | ured |
Token ID | 1522 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
Britann | +3.409 |
democrat | +3.339 |
politic | +3.276 |
shalt | +2.990 |
Anglo | +2.982 |
Neg logit contributions | |
specific | -4.645 |
ukong | -4.573 |
UAL | -4.451 |
nesota | -4.435 |
antically | -4.417 |
Token | ) |
Token ID | 8 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Britann | +2.792 |
democrat | +2.679 |
politic | +2.678 |
shalt | +2.476 |
Anglo | +2.450 |
Neg logit contributions | |
ukong | -4.268 |
specific | -4.254 |
UAL | -4.120 |
izable | -4.116 |
antically | -4.057 |
Token | would |
Token ID | 561 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ukong | +0.134 |
specific | +0.133 |
izable | +0.128 |
UAL | +0.128 |
antically | +0.127 |
Neg logit contributions | |
Britann | -0.102 |
politic | -0.098 |
democrat | -0.098 |
shalt | -0.092 |
Anglo | -0.090 |
Token | be |
Token ID | 307 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ukong | +3.750 |
specific | +3.696 |
izable | +3.568 |
antically | +3.537 |
UAL | +3.505 |
Neg logit contributions | |
Britann | -3.337 |
democrat | -3.120 |
politic | -3.098 |
shalt | -3.021 |
Anglo | -2.969 |
Token | an |
Token ID | 281 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ukong | +2.443 |
specific | +2.433 |
izable | +2.341 |
UAL | +2.316 |
antically | +2.312 |
Neg logit contributions | |
Britann | -1.986 |
democrat | -1.891 |
politic | -1.875 |
shalt | -1.785 |
Anglo | -1.745 |
Token | al |
Token ID | 435 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
specific | +5.332 |
ukong | +5.248 |
izable | +5.201 |
UAL | +5.084 |
agi | +5.015 |
Neg logit contributions | |
Britann | -4.787 |
democrat | -4.525 |
politic | -4.490 |
shalt | -4.297 |
Anglo | -4.106 |
Token | bat |
Token ID | 8664 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ukong | +3.985 |
specific | +3.894 |
antically | +3.555 |
agi | +3.522 |
izable | +3.493 |
Neg logit contributions | |
Britann | -11.985 |
democrat | -11.659 |
politic | -11.596 |
Anglo | -11.223 |
shalt | -11.009 |
Token | ross |
Token ID | 1214 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
specific | +4.257 |
ukong | +4.183 |
izable | +4.087 |
agi | +3.824 |
antically | +3.712 |
Neg logit contributions | |
Britann | -11.929 |
politic | -11.475 |
democrat | -11.345 |
shalt | -11.077 |
Anglo | -11.014 |
Token | on |
Token ID | 319 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
Britann | +2.866 |
politic | +2.757 |
democrat | +2.730 |
shalt | +2.547 |
Anglo | +2.500 |
Neg logit contributions | |
ukong | -4.365 |
specific | -4.327 |
izable | -4.163 |
UAL | -4.151 |
antically | -4.104 |
Token | Miami |
Token ID | 8437 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Britann | +0.334 |
politic | +0.322 |
democrat | +0.321 |
shalt | +0.300 |
Anglo | +0.297 |
Neg logit contributions | |
ukong | -0.401 |
specific | -0.401 |
izable | -0.385 |
UAL | -0.384 |
antically | -0.380 |
Token | � |
Token ID | 447 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ukong | +6.248 |
specific | +6.207 |
izable | +5.917 |
antically | +5.831 |
UAL | +5.823 |
Neg logit contributions | |
Britann | -5.907 |
democrat | -5.576 |
politic | -5.526 |
Anglo | -5.313 |
shalt | -5.311 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ukong | +0.237 |
specific | +0.237 |
izable | +0.228 |
UAL | +0.227 |
antically | +0.225 |
Neg logit contributions | |
Britann | -0.183 |
politic | -0.175 |
democrat | -0.175 |
shalt | -0.164 |
Anglo | -0.162 |
Token | time |
Token ID | 640 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
Britann | +0.733 |
politic | +0.704 |
democrat | +0.702 |
shalt | +0.660 |
Anglo | +0.651 |
Neg logit contributions | |
ukong | -0.872 |
specific | -0.870 |
izable | -0.836 |
UAL | -0.833 |
antically | -0.824 |
Token | Mid |
Token ID | 7215 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Britann | +0.278 |
politic | +0.264 |
democrat | +0.263 |
shalt | +0.242 |
Anglo | +0.237 |
Neg logit contributions | |
specific | -0.515 |
ukong | -0.515 |
izable | -0.499 |
UAL | -0.497 |
antically | -0.492 |
Token | n |
Token ID | 77 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
specific | +1.640 |
ukong | +1.640 |
izable | +1.549 |
UAL | +1.532 |
antically | +1.514 |
Neg logit contributions | |
Britann | -2.569 |
politic | -2.494 |
democrat | -2.489 |
shalt | -2.384 |
Anglo | -2.355 |
Token | ighter |
Token ID | 4799 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ukong | +10.011 |
specific | +9.580 |
izable | +9.425 |
antically | +9.288 |
agi | +9.248 |
Neg logit contributions | |
Britann | -7.326 |
politic | -7.098 |
democrat | -6.952 |
shalt | -6.775 |
contrace | -6.443 |
Token | was |
Token ID | 373 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
ukong | +0.543 |
specific | +0.543 |
izable | +0.522 |
UAL | +0.520 |
antically | +0.514 |
Neg logit contributions | |
Britann | -0.435 |
politic | -0.417 |
democrat | -0.416 |
shalt | -0.391 |
Anglo | -0.385 |
Token | created |
Token ID | 2727 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Britann | +0.162 |
politic | +0.156 |
democrat | +0.155 |
shalt | +0.146 |
Anglo | +0.144 |
Neg logit contributions | |
ukong | -0.197 |
specific | -0.197 |
izable | -0.190 |
UAL | -0.189 |
antically | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Britann | +1.274 |
politic | +1.209 |
democrat | +1.205 |
shalt | +1.101 |
Anglo | +1.076 |
Neg logit contributions | |
ukong | -2.595 |
specific | -2.589 |
UAL | -2.503 |
izable | -2.501 |
antically | -2.481 |
Token | was |
Token ID | 373 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Britann | +0.486 |
politic | +0.466 |
democrat | +0.465 |
shalt | +0.435 |
Anglo | +0.430 |
Neg logit contributions | |
ukong | -0.633 |
specific | -0.631 |
izable | -0.608 |
UAL | -0.606 |
antically | -0.600 |
Token | sort |
Token ID | 3297 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Britann | +0.093 |
politic | +0.089 |
democrat | +0.089 |
shalt | +0.084 |
Anglo | +0.083 |
Neg logit contributions | |
ukong | -0.103 |
specific | -0.103 |
izable | -0.099 |
UAL | -0.098 |
antically | -0.097 |
Token | of |
Token ID | 286 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Britann | +1.058 |
politic | +1.019 |
democrat | +1.009 |
shalt | +0.928 |
Anglo | +0.918 |
Neg logit contributions | |
ukong | -1.869 |
specific | -1.842 |
UAL | -1.794 |
izable | -1.787 |
antically | -1.778 |
Token |
|
Token ID | 198 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Britann | +2.135 |
democrat | +2.024 |
politic | +2.023 |
shalt | +1.885 |
Anglo | +1.851 |
Neg logit contributions | |
specific | -3.175 |
ukong | -3.172 |
izable | -3.068 |
UAL | -3.051 |
antically | -3.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Britann | +1.469 |
politic | +1.404 |
democrat | +1.387 |
Anglo | +1.284 |
shalt | +1.275 |
Neg logit contributions | |
ukong | -2.404 |
specific | -2.358 |
antically | -2.303 |
izable | -2.300 |
UAL | -2.297 |
Token | shut |
Token ID | 49625 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
specific | +0.860 |
ukong | +0.859 |
izable | +0.823 |
UAL | +0.820 |
antically | +0.811 |
Neg logit contributions | |
Britann | -0.792 |
politic | -0.762 |
democrat | -0.760 |
shalt | -0.717 |
Anglo | -0.707 |
Token | at |
Token ID | 379 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
Britann | +6.099 |
politic | +5.835 |
democrat | +5.775 |
shalt | +5.455 |
Anglo | +5.280 |
Neg logit contributions | |
ukong | -7.342 |
specific | -7.087 |
nesota | -7.072 |
izable | -7.021 |
UAL | -6.996 |
Token | high |
Token ID | 1029 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
specific | +2.650 |
ukong | +2.646 |
izable | +2.544 |
UAL | +2.526 |
antically | +2.504 |
Neg logit contributions | |
Britann | -2.498 |
politic | -2.406 |
democrat | -2.399 |
shalt | -2.270 |
Anglo | -2.232 |
Token | - |
Token ID | 12 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
specific | +2.325 |
ukong | +2.303 |
izable | +2.217 |
UAL | +2.190 |
antically | +2.167 |
Neg logit contributions | |
Britann | -2.991 |
politic | -2.891 |
democrat | -2.889 |
shalt | -2.759 |
Anglo | -2.721 |
Token | speed |
Token ID | 12287 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
specific | +2.551 |
ukong | +2.494 |
izable | +2.373 |
UAL | +2.342 |
antically | +2.329 |
Neg logit contributions | |
Britann | -4.270 |
democrat | -4.150 |
politic | -4.150 |
shalt | -3.971 |
Anglo | -3.938 |
Token | ) |
Token ID | 8 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Britann | +1.059 |
politic | +1.021 |
democrat | +1.017 |
shalt | +0.954 |
Anglo | +0.941 |
Neg logit contributions | |
ukong | -1.240 |
specific | -1.225 |
UAL | -1.178 |
izable | -1.177 |
antically | -1.162 |
Token | and |
Token ID | 290 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
ukong | +1.481 |
specific | +1.477 |
izable | +1.422 |
UAL | +1.417 |
antically | +1.402 |
Neg logit contributions | |
Britann | -1.172 |
politic | -1.124 |
democrat | -1.121 |
shalt | -1.052 |
Anglo | -1.036 |
Token | do |
Token ID | 466 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
specific | +1.968 |
ukong | +1.954 |
izable | +1.894 |
UAL | +1.883 |
antically | +1.856 |
Neg logit contributions | |
Britann | -1.760 |
politic | -1.681 |
democrat | -1.679 |
shalt | -1.580 |
Anglo | -1.565 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Britann | +2.804 |
politic | +2.721 |
democrat | +2.713 |
shalt | +2.499 |
Anglo | +2.484 |
Neg logit contributions | |
ukong | -3.797 |
specific | -3.763 |
UAL | -3.642 |
izable | -3.603 |
antically | -3.565 |
Token | claim |
Token ID | 1624 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Britann | +1.571 |
democrat | +1.508 |
politic | +1.507 |
shalt | +1.402 |
Anglo | +1.375 |
Neg logit contributions | |
ukong | -2.221 |
specific | -2.217 |
izable | -2.140 |
UAL | -2.134 |
antically | -2.108 |
Token | to |
Token ID | 284 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
specific | +6.973 |
ukong | +6.840 |
izable | +6.665 |
antically | +6.611 |
UAL | +6.567 |
Neg logit contributions | |
Britann | -6.586 |
politic | -6.204 |
democrat | -5.984 |
shalt | -5.924 |
Anglo | -5.857 |
Token | be |
Token ID | 307 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Britann | +2.181 |
democrat | +2.135 |
politic | +2.110 |
shalt | +1.946 |
Anglo | +1.913 |
Neg logit contributions | |
ukong | -2.997 |
specific | -2.993 |
UAL | -2.876 |
izable | -2.872 |
antically | -2.837 |
Token | ( |
Token ID | 357 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Britann | +2.110 |
democrat | +2.068 |
politic | +2.043 |
shalt | +1.918 |
Anglo | +1.894 |
Neg logit contributions | |
ukong | -2.216 |
specific | -2.183 |
UAL | -2.095 |
izable | -2.090 |
nesota | -2.052 |
Token | in |
Token ID | 259 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
ukong | +0.062 |
specific | +0.061 |
izable | +0.059 |
UAL | +0.058 |
antically | +0.058 |
Neg logit contributions | |
Britann | -0.075 |
politic | -0.073 |
democrat | -0.073 |
shalt | -0.069 |
Anglo | -0.068 |
Token | theory |
Token ID | 4583 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
specific | +3.898 |
ukong | +3.814 |
izable | +3.713 |
UAL | +3.671 |
antically | +3.632 |
Neg logit contributions | |
Britann | -3.669 |
politic | -3.515 |
democrat | -3.509 |
shalt | -3.373 |
Anglo | -3.262 |
Token | at |
Token ID | 379 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
specific | +0.708 |
ukong | +0.703 |
izable | +0.680 |
UAL | +0.675 |
antically | +0.667 |
Neg logit contributions | |
Britann | -0.692 |
politic | -0.664 |
democrat | -0.663 |
shalt | -0.630 |
Anglo | -0.619 |
Token | least |
Token ID | 1551 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ukong | +0.716 |
specific | +0.716 |
izable | +0.692 |
UAL | +0.689 |
antically | +0.683 |
Neg logit contributions | |
Britann | -0.451 |
politic | -0.429 |
democrat | -0.428 |
shalt | -0.398 |
Anglo | -0.391 |
Token | ) |
Token ID | 8 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
specific | +0.713 |
ukong | +0.709 |
izable | +0.682 |
UAL | +0.678 |
antically | +0.672 |
Neg logit contributions | |
Britann | -0.717 |
politic | -0.688 |
democrat | -0.687 |
shalt | -0.653 |
Anglo | -0.642 |
Token | universal |
Token ID | 10112 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Britann | +0.282 |
democrat | +0.272 |
politic | +0.272 |
shalt | +0.256 |
Anglo | +0.253 |
Neg logit contributions | |
ukong | -0.294 |
specific | -0.292 |
izable | -0.280 |
UAL | -0.279 |
antically | -0.275 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
specific | +3.278 |
ukong | +3.241 |
izable | +3.219 |
UAL | +3.119 |
antically | +3.112 |
Neg logit contributions | |
Britann | -2.194 |
politic | -2.095 |
democrat | -2.056 |
shalt | -1.968 |
Anglo | -1.926 |
Token | aire |
Token ID | 7626 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
specific | +3.119 |
ukong | +3.108 |
izable | +3.006 |
UAL | +2.975 |
antically | +2.936 |
Neg logit contributions | |
Britann | -3.494 |
politic | -3.375 |
democrat | -3.299 |
shalt | -3.211 |
Anglo | -3.129 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Britann | +2.367 |
politic | +2.300 |
democrat | +2.295 |
shalt | +2.112 |
Anglo | +2.100 |
Neg logit contributions | |
ukong | -3.374 |
specific | -3.359 |
izable | -3.223 |
UAL | -3.216 |
antically | -3.196 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
specific | +1.042 |
ukong | +1.038 |
izable | +1.003 |
UAL | +1.000 |
antically | +0.985 |
Neg logit contributions | |
Britann | -0.759 |
democrat | -0.733 |
politic | -0.731 |
shalt | -0.684 |
Anglo | -0.665 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Britann | +0.373 |
politic | +0.356 |
democrat | +0.354 |
shalt | +0.330 |
Anglo | +0.327 |
Neg logit contributions | |
ukong | -0.543 |
specific | -0.539 |
izable | -0.521 |
UAL | -0.519 |
antically | -0.517 |
Token | I |
Token ID | 40 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
specific | +1.775 |
ukong | +1.755 |
UAL | +1.692 |
izable | +1.688 |
antically | +1.654 |
Neg logit contributions | |
Britann | -1.747 |
democrat | -1.682 |
politic | -1.680 |
shalt | -1.591 |
Anglo | -1.561 |
Token | suppose |
Token ID | 11691 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
specific | +0.790 |
ukong | +0.789 |
izable | +0.760 |
UAL | +0.757 |
antically | +0.752 |
Neg logit contributions | |
Britann | -0.535 |
politic | -0.509 |
democrat | -0.508 |
shalt | -0.473 |
Anglo | -0.468 |
Token | one |
Token ID | 530 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
specific | +1.119 |
ukong | +1.115 |
izable | +1.075 |
UAL | +1.066 |
antically | +1.054 |
Neg logit contributions | |
Britann | -0.923 |
democrat | -0.878 |
politic | -0.877 |
shalt | -0.831 |
Anglo | -0.809 |
Token | could |
Token ID | 714 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
specific | +2.230 |
ukong | +2.218 |
izable | +2.146 |
UAL | +2.132 |
antically | +2.100 |
Neg logit contributions | |
Britann | -1.734 |
politic | -1.646 |
democrat | -1.636 |
shalt | -1.543 |
Anglo | -1.512 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
specific | +4.709 |
ukong | +4.692 |
izable | +4.577 |
antically | +4.517 |
UAL | +4.481 |
Neg logit contributions | |
Britann | -4.197 |
democrat | -3.831 |
politic | -3.779 |
shalt | -3.711 |
Anglo | -3.678 |
Token | a |
Token ID | 257 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
specific | +3.176 |
ukong | +3.159 |
UAL | +3.046 |
izable | +3.019 |
antically | +3.014 |
Neg logit contributions | |
Britann | -2.594 |
democrat | -2.472 |
politic | -2.472 |
shalt | -2.354 |
Anglo | -2.281 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
specific | +4.536 |
ukong | +4.522 |
izable | +4.376 |
UAL | +4.342 |
antically | +4.306 |
Neg logit contributions | |
Britann | -3.322 |
politic | -3.129 |
democrat | -3.114 |
shalt | -2.990 |
Anglo | -2.899 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Britann | +0.256 |
politic | +0.245 |
democrat | +0.244 |
shalt | +0.228 |
Anglo | +0.224 |
Neg logit contributions | |
ukong | -0.377 |
specific | -0.375 |
izable | -0.362 |
UAL | -0.361 |
antically | -0.357 |
Token | then |
Token ID | 788 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
specific | +5.125 |
ukong | +4.922 |
izable | +4.836 |
antically | +4.770 |
UAL | +4.765 |
Neg logit contributions | |
Britann | -4.284 |
politic | -4.054 |
democrat | -4.034 |
shalt | -3.812 |
Anglo | -3.794 |
Token | return |
Token ID | 1441 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
specific | +2.786 |
ukong | +2.745 |
izable | +2.664 |
UAL | +2.623 |
antically | +2.614 |
Neg logit contributions | |
Britann | -3.015 |
democrat | -2.887 |
politic | -2.885 |
Anglo | -2.721 |
shalt | -2.713 |
Token | . |
Token ID | 13 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
specific | +5.889 |
ukong | +5.742 |
izable | +5.726 |
UAL | +5.583 |
antically | +5.518 |
Neg logit contributions | |
Britann | -5.765 |
democrat | -5.550 |
politic | -5.522 |
shalt | -5.215 |
Anglo | -5.101 |
Token | To |
Token ID | 1675 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
specific | +3.577 |
ukong | +3.517 |
izable | +3.427 |
UAL | +3.411 |
antically | +3.369 |
Neg logit contributions | |
Britann | -2.684 |
democrat | -2.586 |
politic | -2.583 |
shalt | -2.418 |
Anglo | -2.356 |
Token | demonstrate |
Token ID | 10176 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
Britann | +1.690 |
politic | +1.620 |
democrat | +1.618 |
shalt | +1.488 |
Anglo | +1.466 |
Neg logit contributions | |
ukong | -2.659 |
specific | -2.646 |
izable | -2.557 |
UAL | -2.551 |
antically | -2.523 |
Token | , |
Token ID | 11 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
specific | +4.474 |
ukong | +4.422 |
izable | +4.294 |
UAL | +4.256 |
antically | +4.236 |
Neg logit contributions | |
Britann | -3.646 |
politic | -3.473 |
democrat | -3.427 |
shalt | -3.278 |
Anglo | -3.202 |
Token | here |
Token ID | 994 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
specific | +2.564 |
ukong | +2.552 |
izable | +2.476 |
UAL | +2.447 |
antically | +2.445 |
Neg logit contributions | |
Britann | -1.684 |
politic | -1.606 |
democrat | -1.595 |
shalt | -1.474 |
Anglo | -1.464 |
Token | 's |
Token ID | 338 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Britann | +1.022 |
politic | +0.985 |
democrat | +0.983 |
shalt | +0.931 |
Anglo | +0.916 |
Neg logit contributions | |
ukong | -1.023 |
specific | -1.020 |
izable | -0.980 |
UAL | -0.974 |
antically | -0.962 |
Token | what |
Token ID | 644 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
Britann | +0.241 |
politic | +0.232 |
democrat | +0.232 |
shalt | +0.219 |
Anglo | +0.216 |
Neg logit contributions | |
ukong | -0.237 |
specific | -0.235 |
izable | -0.226 |
UAL | -0.225 |
antically | -0.223 |
Token | the |
Token ID | 262 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ukong | +0.130 |
specific | +0.130 |
izable | +0.124 |
UAL | +0.124 |
antically | +0.123 |
Neg logit contributions | |
Britann | -0.124 |
politic | -0.119 |
democrat | -0.119 |
shalt | -0.112 |
Anglo | -0.111 |
Token | B |
Token ID | 347 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Britann | +2.840 |
politic | +2.742 |
democrat | +2.729 |
shalt | +2.534 |
Anglo | +2.521 |
Neg logit contributions | |
ukong | -3.984 |
specific | -3.926 |
UAL | -3.795 |
izable | -3.774 |
antically | -3.764 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Britann | +2.453 |
politic | +2.413 |
democrat | +2.360 |
shalt | +2.157 |
Anglo | +2.111 |
Neg logit contributions | |
ukong | -4.248 |
specific | -4.183 |
UAL | -4.061 |
izable | -4.057 |
antically | -4.024 |
Token | C |
Token ID | 34 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
Britann | +1.399 |
politic | +1.348 |
democrat | +1.340 |
Anglo | +1.260 |
shalt | +1.254 |
Neg logit contributions | |
ukong | -1.362 |
specific | -1.326 |
izable | -1.296 |
antically | -1.284 |
UAL | -1.262 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ukong | +0.151 |
specific | +0.150 |
izable | +0.145 |
UAL | +0.144 |
antically | +0.143 |
Neg logit contributions | |
Britann | -0.113 |
politic | -0.108 |
democrat | -0.107 |
shalt | -0.101 |
Anglo | -0.099 |
Token | examples |
Token ID | 6096 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
specific | +2.217 |
ukong | +2.201 |
izable | +2.131 |
UAL | +2.116 |
antically | +2.082 |
Neg logit contributions | |
Britann | -1.707 |
democrat | -1.622 |
politic | -1.616 |
shalt | -1.526 |
Anglo | -1.495 |
Token | : |
Token ID | 25 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Britann | +1.584 |
politic | +1.512 |
democrat | +1.511 |
shalt | +1.405 |
Anglo | +1.379 |
Neg logit contributions | |
ukong | -2.396 |
specific | -2.388 |
izable | -2.308 |
UAL | -2.298 |
antically | -2.278 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Britann | +1.984 |
democrat | +1.889 |
politic | +1.879 |
shalt | +1.753 |
Anglo | +1.748 |
Neg logit contributions | |
ukong | -2.633 |
specific | -2.618 |
izable | -2.531 |
UAL | -2.516 |
antically | -2.497 |
Token | 90 |
Token ID | 4101 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
specific | +0.560 |
ukong | +0.559 |
izable | +0.538 |
UAL | +0.536 |
antically | +0.529 |
Neg logit contributions | |
Britann | -0.470 |
politic | -0.451 |
democrat | -0.450 |
shalt | -0.424 |
Anglo | -0.417 |
Token | per |
Token ID | 583 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Britann | +2.586 |
politic | +2.469 |
democrat | +2.463 |
shalt | +2.306 |
Anglo | +2.279 |
Neg logit contributions | |
ukong | -3.381 |
specific | -3.352 |
izable | -3.224 |
UAL | -3.210 |
antically | -3.187 |
Token | cent |
Token ID | 1247 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Britann | +3.410 |
democrat | +3.319 |
politic | +3.263 |
shalt | +2.984 |
Anglo | +2.954 |
Neg logit contributions | |
ukong | -6.287 |
specific | -6.202 |
UAL | -6.034 |
antically | -6.005 |
izable | -5.995 |
Token | reduction |
Token ID | 7741 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Britann | +6.466 |
democrat | +6.357 |
politic | +6.330 |
shalt | +5.961 |
Anglo | +5.928 |
Neg logit contributions | |
ukong | -6.386 |
specific | -6.141 |
antically | -6.042 |
nesota | -5.958 |
ulkan | -5.872 |
Token | and |
Token ID | 290 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Britann | +1.060 |
politic | +1.013 |
democrat | +1.011 |
shalt | +0.942 |
Anglo | +0.927 |
Neg logit contributions | |
ukong | -1.527 |
specific | -1.525 |
izable | -1.473 |
UAL | -1.465 |
antically | -1.451 |
Token | will |
Token ID | 481 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Britann | +2.478 |
politic | +2.377 |
democrat | +2.371 |
shalt | +2.221 |
Anglo | +2.170 |
Neg logit contributions | |
ukong | -3.514 |
specific | -3.508 |
izable | -3.393 |
UAL | -3.381 |
antically | -3.346 |
Token | never |
Token ID | 1239 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
Britann | +0.670 |
politic | +0.637 |
democrat | +0.636 |
shalt | +0.597 |
Anglo | +0.592 |
Neg logit contributions | |
ukong | -0.855 |
specific | -0.851 |
izable | -0.818 |
UAL | -0.813 |
antically | -0.806 |
Token | under |
Token ID | 739 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Britann | +2.994 |
politic | +2.940 |
democrat | +2.906 |
shalt | +2.697 |
Anglo | +2.614 |
Neg logit contributions | |
specific | -4.189 |
ukong | -4.166 |
izable | -4.047 |
UAL | -4.041 |
antically | -3.974 |
Token | value |
Token ID | 8367 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
Britann | +2.143 |
politic | +2.092 |
democrat | +2.074 |
shalt | +1.953 |
Anglo | +1.931 |
Neg logit contributions | |
ukong | -2.076 |
specific | -2.053 |
izable | -2.001 |
UAL | -1.995 |
antically | -1.950 |
Token | that |
Token ID | 326 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
Britann | +0.043 |
politic | +0.041 |
democrat | +0.041 |
shalt | +0.038 |
Anglo | +0.038 |
Neg logit contributions | |
ukong | -0.062 |
specific | -0.062 |
izable | -0.059 |
UAL | -0.059 |
antically | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Britann | +3.391 |
politic | +3.250 |
democrat | +3.246 |
shalt | +3.014 |
Anglo | +2.955 |
Neg logit contributions | |
ukong | -4.839 |
specific | -4.831 |
izable | -4.735 |
UAL | -4.651 |
antically | -4.623 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Britann | +0.804 |
politic | +0.760 |
democrat | +0.754 |
shalt | +0.706 |
Anglo | +0.702 |
Neg logit contributions | |
ukong | -1.220 |
specific | -1.215 |
izable | -1.177 |
UAL | -1.169 |
antically | -1.164 |
Token |
|
Token ID | 198 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Britann | +1.249 |
politic | +1.191 |
democrat | +1.184 |
shalt | +1.094 |
Anglo | +1.093 |
Neg logit contributions | |
ukong | -1.942 |
specific | -1.919 |
izable | -1.861 |
antically | -1.857 |
UAL | -1.857 |
Token | My |
Token ID | 3666 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
specific | +1.454 |
ukong | +1.449 |
izable | +1.385 |
UAL | +1.384 |
antically | +1.361 |
Neg logit contributions | |
Britann | -1.479 |
politic | -1.424 |
democrat | -1.423 |
shalt | -1.345 |
Anglo | -1.327 |
Token | release |
Token ID | 2650 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
specific | +2.640 |
ukong | +2.632 |
izable | +2.523 |
UAL | +2.519 |
antically | +2.487 |
Neg logit contributions | |
Britann | -2.469 |
politic | -2.370 |
democrat | -2.370 |
shalt | -2.239 |
Anglo | -2.201 |
Token | Pelosi |
Token ID | 29611 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Britann | +1.350 |
politic | +1.286 |
democrat | +1.275 |
shalt | +1.193 |
Anglo | +1.179 |
Neg logit contributions | |
ukong | -1.989 |
specific | -1.984 |
izable | -1.920 |
UAL | -1.912 |
antically | -1.890 |
Token |
|
Token ID | 198 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Britann | +5.544 |
politic | +5.369 |
democrat | +5.315 |
shalt | +4.824 |
Anglo | +4.778 |
Neg logit contributions | |
ukong | -9.023 |
specific | -9.020 |
UAL | -8.716 |
izable | -8.702 |
antically | -8.657 |
Token |
|
Token ID | 198 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Britann | +1.769 |
politic | +1.682 |
democrat | +1.659 |
Anglo | +1.542 |
shalt | +1.519 |
Neg logit contributions | |
ukong | -2.964 |
specific | -2.897 |
antically | -2.840 |
UAL | -2.826 |
izable | -2.817 |
Token | In |
Token ID | 818 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
specific | +0.228 |
ukong | +0.227 |
izable | +0.218 |
UAL | +0.217 |
antically | +0.214 |
Neg logit contributions | |
Britann | -0.226 |
politic | -0.217 |
democrat | -0.217 |
shalt | -0.205 |
Anglo | -0.202 |
Token | October |
Token ID | 3267 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
specific | +2.782 |
ukong | +2.755 |
izable | +2.662 |
UAL | +2.625 |
antically | +2.602 |
Neg logit contributions | |
Britann | -2.728 |
democrat | -2.623 |
politic | -2.616 |
shalt | -2.512 |
Anglo | -2.431 |
Token | 2006 |
Token ID | 4793 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Britann | +2.169 |
politic | +2.098 |
democrat | +2.085 |
shalt | +1.975 |
Anglo | +1.965 |
Neg logit contributions | |
ukong | -1.903 |
specific | -1.891 |
izable | -1.808 |
UAL | -1.799 |
antically | -1.786 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Britann | +1.862 |
politic | +1.746 |
democrat | +1.737 |
shalt | +1.558 |
Anglo | +1.533 |
Neg logit contributions | |
ukong | -4.576 |
specific | -4.565 |
izable | -4.431 |
UAL | -4.418 |
antically | -4.385 |
Token | a |
Token ID | 257 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Britann | +0.601 |
politic | +0.574 |
democrat | +0.574 |
shalt | +0.537 |
Anglo | +0.527 |
Neg logit contributions | |
specific | -0.822 |
ukong | -0.822 |
izable | -0.791 |
UAL | -0.788 |
antically | -0.780 |
Token | Newsweek |
Token ID | 39594 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
specific | +2.592 |
ukong | +2.570 |
izable | +2.497 |
UAL | +2.482 |
antically | +2.451 |
Neg logit contributions | |
Britann | -1.887 |
politic | -1.801 |
democrat | -1.800 |
shalt | -1.716 |
Anglo | -1.665 |
Token | poll |
Token ID | 3278 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
specific | +1.930 |
ukong | +1.916 |
UAL | +1.854 |
izable | +1.852 |
antically | +1.817 |
Neg logit contributions | |
Britann | -1.751 |
democrat | -1.688 |
politic | -1.683 |
shalt | -1.602 |
Anglo | -1.565 |
Token | found |
Token ID | 1043 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Britann | +1.071 |
democrat | +1.029 |
politic | +1.029 |
shalt | +0.951 |
Anglo | +0.939 |
Neg logit contributions | |
ukong | -1.452 |
specific | -1.441 |
izable | -1.394 |
UAL | -1.388 |
antically | -1.374 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
specific | +1.028 |
ukong | +1.026 |
izable | +0.994 |
UAL | +0.989 |
antically | +0.980 |
Neg logit contributions | |
Britann | -0.614 |
politic | -0.584 |
democrat | -0.583 |
shalt | -0.540 |
Anglo | -0.530 |
Token | � |
Token ID | 564 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ukong | +0.304 |
specific | +0.303 |
izable | +0.293 |
UAL | +0.291 |
antically | +0.289 |
Neg logit contributions | |
Britann | -0.214 |
politic | -0.205 |
democrat | -0.204 |
shalt | -0.191 |
Anglo | -0.188 |
Token | � |
Token ID | 250 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Britann | +5.149 |
democrat | +4.884 |
politic | +4.859 |
shalt | +4.590 |
Anglo | +4.530 |
Neg logit contributions | |
ukong | -6.218 |
specific | -6.055 |
UAL | -5.884 |
izable | -5.875 |
antically | -5.803 |
Token | I |
Token ID | 40 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Britann | +6.578 |
politic | +6.219 |
democrat | +6.121 |
Anglo | +5.866 |
shalt | +5.795 |
Neg logit contributions | |
ukong | -7.985 |
antically | -7.439 |
specific | -7.375 |
nesota | -7.331 |
ulkan | -7.300 |
Token | believe |
Token ID | 1975 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Britann | +1.308 |
politic | +1.252 |
democrat | +1.251 |
shalt | +1.162 |
Anglo | +1.138 |
Neg logit contributions | |
ukong | -1.970 |
specific | -1.964 |
izable | -1.898 |
UAL | -1.891 |
antically | -1.871 |
Token | that |
Token ID | 326 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Britann | +2.389 |
politic | +2.297 |
democrat | +2.296 |
shalt | +2.147 |
Anglo | +2.122 |
Neg logit contributions | |
ukong | -2.973 |
specific | -2.953 |
izable | -2.842 |
UAL | -2.832 |
antically | -2.805 |
Token | [ |
Token ID | 685 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Britann | +4.352 |
democrat | +4.231 |
politic | +4.201 |
shalt | +3.912 |
Anglo | +3.871 |
Neg logit contributions | |
ukong | -5.514 |
specific | -5.405 |
UAL | -5.223 |
izable | -5.204 |
antically | -5.201 |
Token | there |
Token ID | 8117 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
Britann | +0.102 |
politic | +0.098 |
democrat | +0.098 |
shalt | +0.092 |
Anglo | +0.091 |
Neg logit contributions | |
ukong | -0.108 |
specific | -0.108 |
izable | -0.104 |
UAL | -0.103 |
antically | -0.102 |
Token | ] |
Token ID | 60 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ukong | +0.398 |
specific | +0.397 |
izable | +0.383 |
UAL | +0.381 |
antically | +0.378 |
Neg logit contributions | |
Britann | -0.280 |
politic | -0.268 |
democrat | -0.267 |
shalt | -0.249 |
Anglo | -0.245 |
Token | is |
Token ID | 318 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ukong | +0.950 |
specific | +0.950 |
izable | +0.915 |
UAL | +0.911 |
antically | +0.902 |
Neg logit contributions | |
Britann | -0.686 |
politic | -0.655 |
democrat | -0.654 |
shalt | -0.611 |
Anglo | -0.602 |
Token | this |
Token ID | 428 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Britann | +1.849 |
democrat | +1.815 |
politic | +1.809 |
shalt | +1.692 |
Anglo | +1.678 |
Neg logit contributions | |
ukong | -1.781 |
specific | -1.770 |
UAL | -1.688 |
izable | -1.687 |
antically | -1.682 |
Token | or |
Token ID | 273 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Britann | +5.362 |
politic | +5.261 |
democrat | +5.258 |
Anglo | +4.852 |
shalt | +4.838 |
Neg logit contributions | |
ukong | -4.286 |
specific | -4.264 |
UAL | -4.219 |
izable | -4.086 |
antically | -4.074 |
Token | ak |
Token ID | 461 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
specific | +2.982 |
ukong | +2.972 |
izable | +2.819 |
agi | +2.758 |
UAL | +2.752 |
Neg logit contributions | |
Britann | -3.719 |
democrat | -3.592 |
politic | -3.571 |
shalt | -3.448 |
Anglo | -3.388 |
Token | attributes |
Token ID | 12608 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Britann | +0.290 |
politic | +0.277 |
democrat | +0.276 |
shalt | +0.259 |
Anglo | +0.255 |
Neg logit contributions | |
specific | -0.389 |
ukong | -0.389 |
izable | -0.375 |
UAL | -0.373 |
antically | -0.369 |
Token | Montana |
Token ID | 18311 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Britann | +0.559 |
politic | +0.540 |
democrat | +0.540 |
shalt | +0.503 |
Anglo | +0.502 |
Neg logit contributions | |
ukong | -0.646 |
specific | -0.641 |
UAL | -0.617 |
izable | -0.616 |
antically | -0.610 |
Token | 's |
Token ID | 338 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
specific | +4.949 |
ukong | +4.713 |
UAL | +4.610 |
izable | +4.607 |
antically | +4.483 |
Neg logit contributions | |
Britann | -6.297 |
politic | -5.865 |
democrat | -5.824 |
shalt | -5.688 |
Anglo | -5.549 |
Token | early |
Token ID | 1903 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
specific | +0.885 |
ukong | +0.884 |
izable | +0.840 |
UAL | +0.834 |
antically | +0.821 |
Neg logit contributions | |
Britann | -1.276 |
politic | -1.235 |
democrat | -1.233 |
shalt | -1.178 |
Anglo | -1.164 |
Token | success |
Token ID | 1943 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Britann | +1.193 |
democrat | +1.169 |
politic | +1.167 |
shalt | +1.107 |
Anglo | +1.102 |
Neg logit contributions | |
ukong | -0.757 |
specific | -0.745 |
izable | -0.703 |
UAL | -0.701 |
antically | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Britann | +1.108 |
politic | +1.069 |
democrat | +1.066 |
shalt | +0.988 |
Anglo | +0.975 |
Neg logit contributions | |
ukong | -1.597 |
specific | -1.585 |
izable | -1.531 |
UAL | -1.525 |
antically | -1.512 |
Token | in |
Token ID | 287 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ukong | +1.353 |
specific | +1.351 |
izable | +1.299 |
UAL | +1.293 |
antically | +1.280 |
Neg logit contributions | |
Britann | -1.131 |
politic | -1.086 |
democrat | -1.084 |
shalt | -1.019 |
Anglo | -1.004 |
Token | part |
Token ID | 636 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
specific | +3.075 |
ukong | +3.060 |
izable | +2.957 |
UAL | +2.922 |
antically | +2.890 |
Neg logit contributions | |
Britann | -2.520 |
politic | -2.394 |
democrat | -2.383 |
shalt | -2.275 |
Anglo | -2.208 |
Token | , |
Token ID | 11 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
Britann | +3.326 |
politic | +3.252 |
democrat | +3.234 |
Anglo | +2.892 |
shalt | +2.888 |
Neg logit contributions | |
ukong | -7.028 |
specific | -6.976 |
UAL | -6.760 |
izable | -6.731 |
antically | -6.723 |
Token | looking |
Token ID | 2045 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
specific | +2.960 |
ukong | +2.923 |
izable | +2.823 |
UAL | +2.821 |
antically | +2.787 |
Neg logit contributions | |
Britann | -2.404 |
politic | -2.307 |
democrat | -2.296 |
shalt | -2.162 |
Anglo | -2.132 |
Token | for |
Token ID | 329 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
specific | +1.491 |
ukong | +1.483 |
izable | +1.433 |
UAL | +1.429 |
antically | +1.415 |
Neg logit contributions | |
Britann | -1.023 |
politic | -0.972 |
democrat | -0.972 |
shalt | -0.910 |
Anglo | -0.889 |
Token | people |
Token ID | 661 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
specific | +3.578 |
ukong | +3.552 |
izable | +3.442 |
UAL | +3.402 |
antically | +3.366 |
Neg logit contributions | |
Britann | -3.259 |
politic | -3.129 |
democrat | -3.119 |
shalt | -2.974 |
Anglo | -2.885 |
Token | who |
Token ID | 508 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
specific | +6.241 |
ukong | +5.944 |
izable | +5.914 |
UAL | +5.814 |
antically | +5.806 |
Neg logit contributions | |
Britann | -5.141 |
democrat | -4.890 |
politic | -4.862 |
shalt | -4.658 |
Anglo | -4.496 |
Token | were |
Token ID | 547 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Britann | +0.529 |
politic | +0.507 |
democrat | +0.506 |
shalt | +0.475 |
Anglo | +0.468 |
Neg logit contributions | |
ukong | -0.679 |
specific | -0.679 |
izable | -0.654 |
UAL | -0.650 |
antically | -0.644 |
Token | � |
Token ID | 564 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Britann | +0.140 |
politic | +0.134 |
democrat | +0.134 |
shalt | +0.126 |
Anglo | +0.124 |
Neg logit contributions | |
specific | -0.169 |
ukong | -0.169 |
izable | -0.162 |
UAL | -0.162 |
antically | -0.160 |
Token | � |
Token ID | 250 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Britann | +7.325 |
democrat | +6.890 |
politic | +6.810 |
Anglo | +6.444 |
shalt | +6.337 |
Neg logit contributions | |
ukong | -10.416 |
izable | -10.080 |
specific | -10.040 |
UAL | -9.997 |
ulkan | -9.941 |
Token | lost |
Token ID | 33224 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Britann | +6.915 |
politic | +6.816 |
democrat | +6.758 |
Anglo | +6.375 |
shalt | +6.288 |
Neg logit contributions | |
ukong | -5.565 |
nesota | -5.131 |
izable | -5.086 |
specific | -5.053 |
UAL | -5.052 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Britann | +1.775 |
politic | +1.686 |
democrat | +1.678 |
shalt | +1.542 |
Anglo | +1.521 |
Neg logit contributions | |
ukong | -3.168 |
specific | -3.143 |
izable | -3.039 |
UAL | -3.030 |
antically | -2.996 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
specific | +1.717 |
ukong | +1.714 |
izable | +1.656 |
UAL | +1.649 |
antically | +1.635 |
Neg logit contributions | |
Britann | -1.098 |
politic | -1.046 |
democrat | -1.043 |
shalt | -0.972 |
Anglo | -0.953 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
specific | +1.160 |
ukong | +1.157 |
izable | +1.122 |
UAL | +1.117 |
antically | +1.109 |
Neg logit contributions | |
Britann | -0.644 |
democrat | -0.610 |
politic | -0.610 |
shalt | -0.565 |
Anglo | -0.550 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
specific | +3.365 |
ukong | +3.336 |
UAL | +3.246 |
izable | +3.223 |
antically | +3.190 |
Neg logit contributions | |
Britann | -2.398 |
politic | -2.259 |
democrat | -2.258 |
shalt | -2.135 |
Anglo | -2.089 |
Token |
|
Token ID | 198 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
specific | +1.914 |
ukong | +1.900 |
UAL | +1.837 |
izable | +1.836 |
antically | +1.803 |
Neg logit contributions | |
Britann | -1.354 |
democrat | -1.319 |
politic | -1.312 |
shalt | -1.232 |
Anglo | -1.180 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Britann | +0.019 |
politic | +0.018 |
democrat | +0.018 |
shalt | +0.017 |
Anglo | +0.017 |
Neg logit contributions | |
ukong | -0.028 |
specific | -0.027 |
izable | -0.027 |
UAL | -0.026 |
antically | -0.026 |
Token | 1994 |
Token ID | 22666 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
specific | +1.730 |
ukong | +1.713 |
UAL | +1.650 |
izable | +1.646 |
antically | +1.615 |
Neg logit contributions | |
Britann | -1.641 |
politic | -1.579 |
democrat | -1.579 |
shalt | -1.493 |
Anglo | -1.464 |
Token | Roger |
Token ID | 13637 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Britann | +0.251 |
politic | +0.240 |
democrat | +0.240 |
shalt | +0.224 |
Anglo | +0.220 |
Neg logit contributions | |
ukong | -0.354 |
specific | -0.354 |
izable | -0.341 |
UAL | -0.340 |
antically | -0.337 |
Token | Po |
Token ID | 7695 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Britann | +2.733 |
politic | +2.573 |
democrat | +2.553 |
Anglo | +2.405 |
shalt | +2.393 |
Neg logit contributions | |
ukong | -3.518 |
specific | -3.492 |
izable | -3.369 |
UAL | -3.347 |
antically | -3.306 |
Token | isson |
Token ID | 30927 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Britann | +10.877 |
democrat | +10.506 |
politic | +10.261 |
Anglo | +9.702 |
shalt | +9.694 |
Neg logit contributions | |
UAL | -9.196 |
specific | -8.971 |
ukong | -8.923 |
antically | -8.524 |
izable | -8.467 |
Token | admits |
Token ID | 15534 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Britann | +0.614 |
politic | +0.587 |
democrat | +0.585 |
shalt | +0.546 |
Anglo | +0.539 |
Neg logit contributions | |
ukong | -0.855 |
specific | -0.853 |
izable | -0.821 |
UAL | -0.819 |
antically | -0.812 |
Token | to |
Token ID | 284 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
specific | +1.311 |
ukong | +1.307 |
izable | +1.259 |
UAL | +1.252 |
antically | +1.240 |
Neg logit contributions | |
Britann | -1.102 |
democrat | -1.053 |
politic | -1.052 |
shalt | -0.995 |
Anglo | -0.973 |
Token | fabric |
Token ID | 9664 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
specific | +1.152 |
ukong | +1.150 |
izable | +1.102 |
UAL | +1.098 |
antically | +1.087 |
Neg logit contributions | |
Britann | -1.056 |
democrat | -1.012 |
politic | -1.012 |
shalt | -0.959 |
Anglo | -0.940 |
Token | ating |
Token ID | 803 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
Britann | +2.387 |
politic | +2.304 |
democrat | +2.285 |
shalt | +2.140 |
Anglo | +2.137 |
Neg logit contributions | |
ukong | -2.442 |
specific | -2.423 |
izable | -2.302 |
nesota | -2.279 |
UAL | -2.273 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
specific | +0.594 |
ukong | +0.593 |
izable | +0.572 |
UAL | +0.570 |
antically | +0.564 |
Neg logit contributions | |
Britann | -0.406 |
politic | -0.389 |
democrat | -0.389 |
shalt | -0.361 |
Anglo | -0.355 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Britann | +1.503 |
politic | +1.431 |
democrat | +1.416 |
Anglo | +1.314 |
shalt | +1.305 |
Neg logit contributions | |
ukong | -2.491 |
specific | -2.444 |
antically | -2.392 |
izable | -2.376 |
UAL | -2.375 |
Token | With |
Token ID | 3152 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
specific | +1.584 |
ukong | +1.576 |
izable | +1.510 |
UAL | +1.505 |
antically | +1.480 |
Neg logit contributions | |
Britann | -1.644 |
politic | -1.590 |
democrat | -1.586 |
shalt | -1.498 |
Anglo | -1.479 |
Token | love |
Token ID | 1842 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
specific | +0.691 |
ukong | +0.691 |
izable | +0.666 |
UAL | +0.663 |
antically | +0.657 |
Neg logit contributions | |
Britann | -0.519 |
politic | -0.497 |
democrat | -0.496 |
shalt | -0.465 |
Anglo | -0.456 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Britann | +5.765 |
politic | +5.404 |
democrat | +5.364 |
shalt | +5.124 |
Anglo | +4.961 |
Neg logit contributions | |
ukong | -8.144 |
specific | -8.094 |
izable | -7.774 |
UAL | -7.729 |
nesota | -7.681 |
Token | light |
Token ID | 1657 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Britann | +4.406 |
democrat | +4.221 |
politic | +4.198 |
shalt | +3.944 |
Anglo | +3.814 |
Neg logit contributions | |
ukong | -7.921 |
specific | -7.796 |
izable | -7.510 |
UAL | -7.474 |
antically | -7.438 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Britann | +8.528 |
politic | +7.722 |
democrat | +7.641 |
shalt | +7.492 |
Anglo | +7.281 |
Neg logit contributions | |
ukong | -13.047 |
specific | -12.926 |
izable | -12.410 |
UAL | -12.352 |
antically | -12.346 |
Token |
|
Token ID | 198 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Britann | +4.421 |
politic | +4.067 |
democrat | +3.965 |
Anglo | +3.864 |
Lyndon | +3.503 |
Neg logit contributions | |
ukong | -11.063 |
antically | -10.830 |
nesota | -10.603 |
ulkan | -10.571 |
specific | -10.539 |
Token | George |
Token ID | 20191 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Britann | +2.879 |
democrat | +2.739 |
politic | +2.737 |
shalt | +2.598 |
Anglo | +2.572 |
Neg logit contributions | |
ukong | -3.080 |
specific | -3.048 |
izable | -2.943 |
UAL | -2.927 |
antically | -2.909 |
Token |
|
Token ID | 198 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Britann | +1.074 |
politic | +1.030 |
democrat | +1.028 |
shalt | +0.960 |
Anglo | +0.944 |
Neg logit contributions | |
ukong | -1.476 |
specific | -1.473 |
izable | -1.420 |
UAL | -1.415 |
antically | -1.401 |
Token |
|
Token ID | 198 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
Britann | +1.844 |
politic | +1.756 |
democrat | +1.729 |
Anglo | +1.611 |
shalt | +1.595 |
Neg logit contributions | |
ukong | -3.145 |
specific | -3.071 |
antically | -3.016 |
UAL | -2.996 |
izable | -2.992 |
Token | as |
Token ID | 355 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
specific | +4.535 |
ukong | +4.475 |
izable | +4.326 |
antically | +4.311 |
UAL | +4.294 |
Neg logit contributions | |
Britann | -3.621 |
politic | -3.458 |
democrat | -3.456 |
shalt | -3.239 |
Anglo | -3.205 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
specific | +4.389 |
ukong | +4.377 |
izable | +4.231 |
UAL | +4.179 |
antically | +4.160 |
Neg logit contributions | |
Britann | -3.901 |
democrat | -3.781 |
politic | -3.777 |
shalt | -3.559 |
Anglo | -3.486 |
Token | t |
Token ID | 256 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ukong | +1.175 |
specific | +1.175 |
izable | +1.133 |
UAL | +1.125 |
antically | +1.115 |
Neg logit contributions | |
Britann | -0.933 |
politic | -0.897 |
democrat | -0.896 |
shalt | -0.843 |
Anglo | -0.827 |
Token | umbling |
Token ID | 14739 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Britann | +6.637 |
democrat | +6.236 |
politic | +6.198 |
shalt | +5.934 |
Anglo | +5.850 |
Neg logit contributions | |
specific | -5.523 |
ukong | -5.445 |
nesota | -5.320 |
izable | -5.305 |
UAL | -5.233 |
Token | and |
Token ID | 290 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
Britann | +2.335 |
politic | +2.210 |
democrat | +2.203 |
shalt | +2.060 |
Anglo | +2.024 |
Neg logit contributions | |
specific | -3.393 |
ukong | -3.388 |
UAL | -3.266 |
izable | -3.252 |
antically | -3.219 |
Token | rolling |
Token ID | 10708 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ukong | +0.162 |
specific | +0.162 |
izable | +0.155 |
UAL | +0.154 |
antically | +0.152 |
Neg logit contributions | |
Britann | -0.154 |
politic | -0.148 |
democrat | -0.148 |
shalt | -0.139 |
Anglo | -0.137 |
Token | iceberg |
Token ID | 34849 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Britann | +8.045 |
politic | +7.524 |
democrat | +7.411 |
shalt | +7.202 |
Anglo | +6.916 |
Neg logit contributions | |
specific | -10.059 |
ukong | -10.031 |
UAL | -9.665 |
izable | -9.504 |
antically | -9.460 |
Token | pushes |
Token ID | 20070 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
Britann | +1.370 |
politic | +1.323 |
democrat | +1.318 |
shalt | +1.247 |
Anglo | +1.224 |
Neg logit contributions | |
ukong | -1.381 |
specific | -1.375 |
izable | -1.315 |
UAL | -1.312 |
antically | -1.293 |
Token | water |
Token ID | 1660 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ukong | +0.441 |
specific | +0.440 |
izable | +0.424 |
UAL | +0.422 |
antically | +0.418 |
Neg logit contributions | |
Britann | -0.340 |
politic | -0.326 |
democrat | -0.325 |
shalt | -0.305 |
Anglo | -0.300 |
Token | out |
Token ID | 503 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
specific | +1.047 |
ukong | +1.047 |
izable | +1.009 |
UAL | +1.005 |
antically | +0.996 |
Neg logit contributions | |
Britann | -0.769 |
politic | -0.735 |
democrat | -0.734 |
shalt | -0.686 |
Anglo | -0.676 |
Token | wards |
Token ID | 2017 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Britann | +0.195 |
politic | +0.186 |
democrat | +0.186 |
shalt | +0.173 |
Anglo | +0.170 |
Neg logit contributions | |
ukong | -0.293 |
specific | -0.292 |
izable | -0.282 |
UAL | -0.281 |
antically | -0.278 |
Token | home |
Token ID | 1363 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
Britann | +2.257 |
politic | +2.169 |
democrat | +2.157 |
shalt | +1.988 |
Anglo | +1.987 |
Neg logit contributions | |
ukong | -3.308 |
specific | -3.301 |
izable | -3.175 |
UAL | -3.165 |
antically | -3.133 |
Token | of |
Token ID | 286 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Britann | +0.235 |
democrat | +0.224 |
politic | +0.224 |
shalt | +0.209 |
Anglo | +0.205 |
Neg logit contributions | |
specific | -0.350 |
ukong | -0.350 |
izable | -0.337 |
UAL | -0.336 |
antically | -0.334 |
Token | Nikki |
Token ID | 34108 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Britann | +6.137 |
politic | +6.056 |
democrat | +5.982 |
Anglo | +5.565 |
shalt | +5.417 |
Neg logit contributions | |
ukong | -8.194 |
specific | -8.064 |
UAL | -7.829 |
izable | -7.768 |
agi | -7.688 |
Token | J |
Token ID | 449 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Britann | +2.963 |
politic | +2.826 |
democrat | +2.812 |
shalt | +2.635 |
Anglo | +2.631 |
Neg logit contributions | |
ukong | -3.829 |
specific | -3.806 |
UAL | -3.675 |
izable | -3.659 |
antically | -3.614 |
Token | oly |
Token ID | 3366 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
ukong | +7.140 |
specific | +7.058 |
izable | +6.979 |
agi | +6.963 |
ulkan | +6.732 |
Neg logit contributions | |
Britann | -6.945 |
democrat | -6.748 |
politic | -6.718 |
shalt | -6.391 |
Anglo | -6.264 |
Token | burned |
Token ID | 11544 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Britann | +2.643 |
politic | +2.533 |
democrat | +2.529 |
shalt | +2.362 |
Anglo | +2.327 |
Neg logit contributions | |
ukong | -3.419 |
specific | -3.414 |
izable | -3.297 |
UAL | -3.285 |
antically | -3.247 |
Token | down |
Token ID | 866 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Britann | +6.234 |
politic | +6.010 |
democrat | +5.805 |
Anglo | +5.415 |
shalt | +5.384 |
Neg logit contributions | |
specific | -11.831 |
ukong | -11.828 |
UAL | -11.565 |
izable | -11.483 |
nesota | -11.430 |
Token | in |
Token ID | 287 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
Britann | +3.414 |
politic | +3.280 |
democrat | +3.238 |
shalt | +3.006 |
Anglo | +2.989 |
Neg logit contributions | |
ukong | -5.550 |
specific | -5.537 |
izable | -5.362 |
UAL | -5.348 |
antically | -5.270 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Britann | +0.239 |
politic | +0.230 |
democrat | +0.229 |
shalt | +0.215 |
Anglo | +0.213 |
Neg logit contributions | |
ukong | -0.259 |
specific | -0.258 |
izable | -0.248 |
UAL | -0.247 |
antically | -0.244 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Britann | +0.042 |
democrat | +0.039 |
politic | +0.039 |
shalt | +0.036 |
Anglo | +0.035 |
Neg logit contributions | |
ukong | -0.091 |
specific | -0.091 |
izable | -0.088 |
UAL | -0.087 |
antically | -0.087 |
Token | killing |
Token ID | 5170 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
specific | +0.517 |
ukong | +0.515 |
izable | +0.497 |
UAL | +0.493 |
antically | +0.489 |
Neg logit contributions | |
Britann | -0.397 |
democrat | -0.379 |
politic | -0.379 |
shalt | -0.356 |
Anglo | -0.349 |