Token |
|
Token ID | 198 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
iatus | +0.974 |
AST | +0.848 |
maj | +0.847 |
Ast | +0.820 |
代 | +0.811 |
Neg logit contributions | |
psychiat | -0.777 |
nesota | -0.730 |
ieft | -0.725 |
olkien | -0.720 |
harassing | -0.718 |
Token | pur |
Token ID | 14225 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
iatus | +0.486 |
AST | +0.416 |
maj | +0.415 |
Ast | +0.399 |
代 | +0.396 |
Neg logit contributions | |
psychiat | -0.472 |
nesota | -0.453 |
ieft | -0.452 |
olkien | -0.448 |
harassing | -0.445 |
Token | ak |
Token ID | 461 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
iatus | +0.534 |
AST | +0.457 |
maj | +0.456 |
Ast | +0.439 |
代 | +0.435 |
Neg logit contributions | |
psychiat | -0.506 |
nesota | -0.485 |
ieft | -0.482 |
olkien | -0.478 |
harassing | -0.476 |
Token | ushi |
Token ID | 17731 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
iatus | +0.868 |
maj | +0.738 |
AST | +0.738 |
Ast | +0.709 |
代 | +0.702 |
Neg logit contributions | |
psychiat | -0.880 |
nesota | -0.846 |
ieft | -0.841 |
olkien | -0.834 |
harassing | -0.830 |
Token | Profile |
Token ID | 13118 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
iatus | +1.753 |
maj | +1.496 |
AST | +1.494 |
Ast | +1.440 |
代 | +1.419 |
Neg logit contributions | |
psychiat | -1.786 |
nesota | -1.718 |
ieft | -1.701 |
olkien | -1.691 |
harassing | -1.677 |
Token | Joined |
Token ID | 16709 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
iatus | +2.395 |
AST | +2.021 |
maj | +1.995 |
Ast | +1.932 |
� | +1.876 |
Neg logit contributions | |
psychiat | -3.470 |
nesota | -3.379 |
ieft | -3.333 |
olkien | -3.326 |
harassing | -3.277 |
Token | August |
Token ID | 2932 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
iatus | +5.021 |
AST | +4.511 |
Ast | +4.436 |
maj | +4.399 |
� | +4.247 |
Neg logit contributions | |
psychiat | -5.426 |
olkien | -5.231 |
nesota | -5.202 |
ieft | -5.125 |
harassing | -4.934 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
iatus | +2.712 |
AST | +2.359 |
maj | +2.320 |
Ast | +2.288 |
Toast | +2.225 |
Neg logit contributions | |
psychiat | -2.633 |
nesota | -2.515 |
olkien | -2.502 |
ieft | -2.472 |
harassing | -2.449 |
Token | United |
Token ID | 1578 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
iatus | +2.791 |
AST | +2.458 |
maj | +2.425 |
Ast | +2.384 |
Toast | +2.335 |
Neg logit contributions | |
psychiat | -2.245 |
nesota | -2.129 |
olkien | -2.121 |
ieft | -2.102 |
harassing | -2.076 |
Token | States |
Token ID | 1829 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
iatus | +4.094 |
AST | +3.550 |
maj | +3.535 |
Ast | +3.466 |
Toast | +3.417 |
Neg logit contributions | |
psychiat | -3.466 |
nesota | -3.294 |
olkien | -3.274 |
ieft | -3.262 |
harassing | -3.227 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
iatus | +3.712 |
AST | +3.235 |
maj | +3.184 |
Ast | +3.126 |
� | +3.051 |
Neg logit contributions | |
psychiat | -3.771 |
nesota | -3.593 |
olkien | -3.579 |
ieft | -3.549 |
harassing | -3.504 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +0.675 |
maj | +0.593 |
AST | +0.592 |
Ast | +0.575 |
代 | +0.569 |
Neg logit contributions | |
psychiat | -0.443 |
nesota | -0.421 |
ieft | -0.419 |
olkien | -0.415 |
harassing | -0.411 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
iatus | +0.947 |
maj | +0.819 |
AST | +0.815 |
Ast | +0.789 |
代 | +0.776 |
Neg logit contributions | |
psychiat | -0.857 |
nesota | -0.824 |
ieft | -0.819 |
olkien | -0.816 |
harassing | -0.802 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
iatus | +2.611 |
Ast | +1.951 |
AST | +1.931 |
maj | +1.866 |
Toast | +1.824 |
Neg logit contributions | |
psychiat | -5.663 |
olkien | -5.446 |
nesota | -5.394 |
ieft | -5.388 |
harassing | -5.310 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +4.803 |
Ast | +4.188 |
maj | +4.065 |
Romance | +3.936 |
AST | +3.920 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.162 |
olkien | -4.083 |
ieft | -4.048 |
uman | -3.752 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
iatus | +4.976 |
maj | +4.368 |
AST | +4.348 |
Ast | +4.283 |
Romance | +4.189 |
Neg logit contributions | |
psychiat | -3.901 |
olkien | -3.630 |
nesota | -3.609 |
ieft | -3.593 |
harassing | -3.543 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
iatus | +4.269 |
maj | +3.611 |
AST | +3.595 |
Ast | +3.508 |
代 | +3.456 |
Neg logit contributions | |
psychiat | -4.465 |
nesota | -4.284 |
olkien | -4.227 |
ieft | -4.218 |
harassing | -4.195 |
Token | : |
Token ID | 25 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
iatus | +4.295 |
AST | +3.494 |
Ast | +3.440 |
maj | +3.404 |
Toast | +3.244 |
Neg logit contributions | |
psychiat | -6.142 |
nesota | -5.870 |
ieft | -5.824 |
olkien | -5.816 |
harassing | -5.598 |
Token | ' |
Token ID | 705 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
iatus | +2.299 |
AST | +1.946 |
maj | +1.943 |
Ast | +1.871 |
代 | +1.842 |
Neg logit contributions | |
psychiat | -2.486 |
nesota | -2.388 |
ieft | -2.374 |
olkien | -2.357 |
harassing | -2.345 |
Token | I |
Token ID | 40 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
iatus | +2.468 |
maj | +2.106 |
AST | +2.088 |
Ast | +2.057 |
代 | +1.997 |
Neg logit contributions | |
psychiat | -2.643 |
nesota | -2.554 |
olkien | -2.502 |
ieft | -2.479 |
harassing | -2.475 |
Token | fully |
Token ID | 3938 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
iatus | +1.584 |
AST | +1.411 |
maj | +1.371 |
代 | +1.361 |
Ast | +1.341 |
Neg logit contributions | |
psychiat | -0.950 |
ieft | -0.918 |
nesota | -0.884 |
harassing | -0.882 |
olkien | -0.877 |
Token | expect |
Token ID | 1607 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
psychiat | +0.479 |
ieft | +0.478 |
nesota | +0.460 |
harassing | +0.455 |
olkien | +0.453 |
Neg logit contributions | |
iatus | -0.673 |
AST | -0.600 |
maj | -0.581 |
代 | -0.572 |
Ast | -0.568 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
iatus | +1.007 |
maj | +0.887 |
AST | +0.883 |
Ast | +0.872 |
Toast | +0.843 |
Neg logit contributions | |
psychiat | -0.749 |
olkien | -0.706 |
nesota | -0.704 |
ieft | -0.700 |
harassing | -0.685 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
iatus | +0.925 |
maj | +0.828 |
AST | +0.822 |
Ast | +0.807 |
Toast | +0.784 |
Neg logit contributions | |
psychiat | -0.593 |
olkien | -0.567 |
nesota | -0.563 |
ieft | -0.557 |
harassing | -0.539 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
iatus | +2.161 |
AST | +1.675 |
Ast | +1.633 |
maj | +1.611 |
Toast | +1.544 |
Neg logit contributions | |
psychiat | -4.477 |
olkien | -4.306 |
nesota | -4.297 |
ieft | -4.287 |
harassing | -4.204 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
iatus | +4.323 |
Ast | +3.774 |
maj | +3.741 |
AST | +3.630 |
Romance | +3.608 |
Neg logit contributions | |
psychiat | -3.658 |
nesota | -3.438 |
olkien | -3.359 |
ieft | -3.337 |
harassing | -3.091 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
iatus | +4.800 |
maj | +4.220 |
AST | +4.193 |
Ast | +4.142 |
Romance | +4.037 |
Neg logit contributions | |
psychiat | -3.823 |
olkien | -3.567 |
ieft | -3.534 |
nesota | -3.514 |
harassing | -3.464 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
iatus | +4.309 |
maj | +3.634 |
AST | +3.618 |
Ast | +3.507 |
代 | +3.467 |
Neg logit contributions | |
psychiat | -4.581 |
nesota | -4.408 |
ieft | -4.365 |
olkien | -4.356 |
harassing | -4.323 |
Token | : |
Token ID | 25 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
iatus | +3.842 |
AST | +3.091 |
maj | +3.010 |
Ast | +2.981 |
Toast | +2.833 |
Neg logit contributions | |
psychiat | -6.231 |
nesota | -5.990 |
ieft | -5.982 |
olkien | -5.951 |
harassing | -5.792 |
Token | ' |
Token ID | 705 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
iatus | +1.966 |
maj | +1.675 |
AST | +1.666 |
代 | +1.609 |
Ast | +1.585 |
Neg logit contributions | |
psychiat | -1.961 |
nesota | -1.904 |
ieft | -1.901 |
olkien | -1.880 |
harassing | -1.874 |
Token | I |
Token ID | 40 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
iatus | +2.206 |
maj | +1.886 |
AST | +1.878 |
Ast | +1.823 |
代 | +1.800 |
Neg logit contributions | |
psychiat | -2.161 |
nesota | -2.084 |
ieft | -2.053 |
olkien | -2.048 |
harassing | -2.032 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
iatus | +1.184 |
AST | +1.058 |
maj | +1.021 |
代 | +1.021 |
Ast | +1.000 |
Neg logit contributions | |
psychiat | -0.681 |
ieft | -0.661 |
harassing | -0.627 |
olkien | -0.624 |
nesota | -0.624 |
Token | expect |
Token ID | 1607 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
ieft | +0.692 |
psychiat | +0.683 |
nesota | +0.660 |
harassing | +0.656 |
olkien | +0.650 |
Neg logit contributions | |
iatus | -0.908 |
AST | -0.807 |
maj | -0.777 |
代 | -0.770 |
Romance | -0.765 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
iatus | +0.805 |
AST | +0.706 |
maj | +0.705 |
Ast | +0.684 |
代 | +0.678 |
Neg logit contributions | |
psychiat | -0.530 |
nesota | -0.504 |
ieft | -0.501 |
olkien | -0.496 |
harassing | -0.492 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
iatus | +0.918 |
maj | +0.815 |
AST | +0.813 |
Ast | +0.792 |
代 | +0.780 |
Neg logit contributions | |
psychiat | -0.545 |
nesota | -0.517 |
olkien | -0.512 |
ieft | -0.511 |
harassing | -0.500 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
iatus | +2.106 |
AST | +1.642 |
Ast | +1.599 |
maj | +1.579 |
Toast | +1.532 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.289 |
olkien | -4.286 |
ieft | -4.263 |
harassing | -4.182 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
iatus | +4.433 |
Ast | +3.869 |
maj | +3.858 |
AST | +3.728 |
Romance | +3.711 |
Neg logit contributions | |
psychiat | -3.832 |
nesota | -3.632 |
olkien | -3.498 |
ieft | -3.468 |
harassing | -3.231 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
iatus | +4.593 |
maj | +4.034 |
AST | +4.028 |
Ast | +3.958 |
Romance | +3.862 |
Neg logit contributions | |
psychiat | -3.525 |
olkien | -3.291 |
nesota | -3.270 |
ieft | -3.256 |
harassing | -3.208 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
iatus | +4.140 |
maj | +3.486 |
AST | +3.482 |
Ast | +3.366 |
代 | +3.328 |
Neg logit contributions | |
psychiat | -4.553 |
nesota | -4.379 |
ieft | -4.335 |
olkien | -4.323 |
harassing | -4.299 |
Token | : |
Token ID | 25 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
iatus | +3.603 |
AST | +2.881 |
maj | +2.796 |
Ast | +2.754 |
Toast | +2.611 |
Neg logit contributions | |
psychiat | -6.269 |
nesota | -6.033 |
ieft | -6.003 |
olkien | -5.988 |
harassing | -5.830 |
Token | ' |
Token ID | 705 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
iatus | +1.693 |
maj | +1.440 |
AST | +1.435 |
代 | +1.382 |
Ast | +1.367 |
Neg logit contributions | |
psychiat | -1.704 |
ieft | -1.653 |
nesota | -1.653 |
olkien | -1.634 |
harassing | -1.627 |
Token | I |
Token ID | 40 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
iatus | +2.201 |
maj | +1.881 |
AST | +1.869 |
Ast | +1.828 |
代 | +1.801 |
Neg logit contributions | |
psychiat | -2.276 |
nesota | -2.204 |
olkien | -2.159 |
ieft | -2.153 |
harassing | -2.140 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iatus | +1.145 |
AST | +1.017 |
maj | +0.991 |
代 | +0.982 |
Ast | +0.968 |
Neg logit contributions | |
psychiat | -0.683 |
ieft | -0.658 |
nesota | -0.636 |
olkien | -0.632 |
harassing | -0.632 |
Token | expect |
Token ID | 1607 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ieft | +0.714 |
psychiat | +0.712 |
nesota | +0.682 |
harassing | +0.677 |
olkien | +0.674 |
Neg logit contributions | |
iatus | -1.005 |
AST | -0.894 |
maj | -0.865 |
代 | -0.854 |
Romance | -0.851 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
iatus | +0.021 |
maj | +0.018 |
AST | +0.018 |
Ast | +0.017 |
代 | +0.017 |
Neg logit contributions | |
psychiat | -0.020 |
nesota | -0.019 |
ieft | -0.019 |
olkien | -0.019 |
harassing | -0.019 |
Token | Atmospheric |
Token ID | 41516 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
psychiat | +1.071 |
nesota | +1.036 |
ieft | +1.029 |
olkien | +1.020 |
harassing | +1.017 |
Neg logit contributions | |
iatus | -0.929 |
maj | -0.779 |
AST | -0.775 |
代 | -0.741 |
Ast | -0.737 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
psychiat | +0.750 |
nesota | +0.718 |
ieft | +0.712 |
harassing | +0.706 |
olkien | +0.702 |
Neg logit contributions | |
iatus | -0.924 |
AST | -0.799 |
maj | -0.794 |
代 | -0.772 |
Ast | -0.760 |
Token | ( |
Token ID | 357 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
psychiat | +0.304 |
nesota | +0.291 |
ieft | +0.290 |
olkien | +0.287 |
harassing | +0.286 |
Neg logit contributions | |
iatus | -0.332 |
AST | -0.285 |
maj | -0.285 |
Ast | -0.274 |
代 | -0.272 |
Token | So |
Token ID | 2396 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
psychiat | +0.439 |
nesota | +0.421 |
ieft | +0.419 |
harassing | +0.412 |
olkien | +0.411 |
Neg logit contributions | |
iatus | -0.500 |
maj | -0.430 |
AST | -0.427 |
代 | -0.411 |
Ast | -0.410 |
Token | MAS |
Token ID | 31180 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
iatus | +2.142 |
AST | +1.848 |
maj | +1.846 |
Ast | +1.782 |
代 | +1.763 |
Neg logit contributions | |
psychiat | -1.846 |
nesota | -1.768 |
ieft | -1.760 |
olkien | -1.744 |
harassing | -1.734 |
Token | ). |
Token ID | 737 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
iatus | +4.545 |
AST | +3.859 |
maj | +3.826 |
Ast | +3.786 |
� | +3.638 |
Neg logit contributions | |
psychiat | -4.954 |
ieft | -4.790 |
nesota | -4.789 |
olkien | -4.749 |
harassing | -4.746 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
iatus | +0.461 |
AST | +0.400 |
maj | +0.400 |
Ast | +0.387 |
代 | +0.383 |
Neg logit contributions | |
psychiat | -0.368 |
nesota | -0.352 |
ieft | -0.350 |
olkien | -0.346 |
harassing | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
iatus | +0.232 |
AST | +0.202 |
maj | +0.202 |
Ast | +0.196 |
代 | +0.194 |
Neg logit contributions | |
psychiat | -0.177 |
nesota | -0.168 |
ieft | -0.167 |
olkien | -0.166 |
harassing | -0.165 |
Token | � |
Token ID | 447 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
iatus | +0.574 |
AST | +0.492 |
maj | +0.492 |
Ast | +0.474 |
代 | +0.470 |
Neg logit contributions | |
psychiat | -0.529 |
nesota | -0.507 |
ieft | -0.503 |
olkien | -0.499 |
harassing | -0.498 |
Token | � |
Token ID | 250 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
iatus | +0.020 |
maj | +0.017 |
AST | +0.017 |
Ast | +0.017 |
代 | +0.017 |
Neg logit contributions | |
psychiat | -0.013 |
nesota | -0.013 |
ieft | -0.012 |
olkien | -0.012 |
harassing | -0.012 |
Token | ada |
Token ID | 4763 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
psychiat | +0.313 |
ieft | +0.301 |
nesota | +0.301 |
olkien | +0.298 |
harassing | +0.296 |
Neg logit contributions | |
iatus | -0.283 |
AST | -0.240 |
maj | -0.239 |
Ast | -0.230 |
代 | -0.229 |
Token | ver |
Token ID | 332 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
iatus | +0.321 |
AST | +0.274 |
maj | +0.274 |
Ast | +0.263 |
代 | +0.262 |
Neg logit contributions | |
psychiat | -0.313 |
nesota | -0.301 |
ieft | -0.300 |
olkien | -0.297 |
harassing | -0.296 |
Token | BB |
Token ID | 15199 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
psychiat | +0.423 |
ieft | +0.408 |
nesota | +0.407 |
olkien | +0.403 |
harassing | +0.403 |
Neg logit contributions | |
iatus | -0.346 |
AST | -0.290 |
maj | -0.289 |
Ast | -0.276 |
代 | -0.275 |
Token | Profile |
Token ID | 13118 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
iatus | +0.423 |
AST | +0.354 |
maj | +0.354 |
Ast | +0.337 |
代 | +0.335 |
Neg logit contributions | |
psychiat | -0.524 |
nesota | -0.506 |
ieft | -0.505 |
olkien | -0.500 |
harassing | -0.498 |
Token | Blog |
Token ID | 14001 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
iatus | +2.394 |
AST | +1.990 |
maj | +1.974 |
Ast | +1.903 |
� | +1.853 |
Neg logit contributions | |
psychiat | -3.430 |
nesota | -3.344 |
ieft | -3.296 |
olkien | -3.291 |
harassing | -3.248 |
Token | Joined |
Token ID | 16709 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
iatus | +2.066 |
AST | +1.733 |
maj | +1.709 |
Ast | +1.678 |
� | +1.621 |
Neg logit contributions | |
psychiat | -2.990 |
nesota | -2.868 |
olkien | -2.845 |
ieft | -2.824 |
harassing | -2.783 |
Token | June |
Token ID | 2795 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
iatus | +4.564 |
AST | +4.083 |
Ast | +4.037 |
maj | +4.000 |
� | +3.863 |
Neg logit contributions | |
psychiat | -4.859 |
olkien | -4.726 |
nesota | -4.721 |
ieft | -4.654 |
harassing | -4.460 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
iatus | +3.082 |
AST | +2.723 |
maj | +2.694 |
Ast | +2.631 |
� | +2.572 |
Neg logit contributions | |
psychiat | -3.235 |
nesota | -3.101 |
olkien | -3.093 |
ieft | -3.061 |
harassing | -3.007 |
Token | Germany |
Token ID | 4486 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
iatus | +3.842 |
AST | +3.400 |
maj | +3.338 |
Ast | +3.305 |
� | +3.235 |
Neg logit contributions | |
psychiat | -3.312 |
olkien | -3.155 |
nesota | -3.145 |
ieft | -3.117 |
harassing | -3.054 |
Token | 247 |
Token ID | 30179 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
iatus | +3.017 |
AST | +2.640 |
maj | +2.606 |
Ast | +2.549 |
� | +2.493 |
Neg logit contributions | |
psychiat | -2.990 |
nesota | -2.858 |
olkien | -2.841 |
ieft | -2.822 |
harassing | -2.773 |
Token | 34 |
Token ID | 2682 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
iatus | +2.220 |
AST | +1.901 |
maj | +1.878 |
Ast | +1.837 |
代 | +1.801 |
Neg logit contributions | |
psychiat | -2.472 |
nesota | -2.349 |
ieft | -2.325 |
olkien | -2.321 |
harassing | -2.301 |
Token | Ramsey |
Token ID | 30552 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
iatus | +0.576 |
AST | +0.487 |
maj | +0.485 |
Ast | +0.474 |
代 | +0.461 |
Neg logit contributions | |
psychiat | -0.624 |
nesota | -0.598 |
ieft | -0.596 |
olkien | -0.589 |
harassing | -0.583 |
Token | , |
Token ID | 11 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
psychiat | +0.191 |
nesota | +0.183 |
ieft | +0.182 |
olkien | +0.181 |
harassing | +0.179 |
Neg logit contributions | |
iatus | -0.208 |
AST | -0.179 |
maj | -0.179 |
Ast | -0.172 |
代 | -0.171 |
Token | Jaguars |
Token ID | 28392 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
psychiat | +0.042 |
nesota | +0.040 |
ieft | +0.039 |
olkien | +0.039 |
harassing | +0.039 |
Neg logit contributions | |
iatus | -0.060 |
maj | -0.052 |
AST | -0.052 |
Ast | -0.051 |
代 | -0.050 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
iatus | +1.817 |
AST | +1.579 |
maj | +1.558 |
Ast | +1.518 |
Toast | +1.483 |
Neg logit contributions | |
psychiat | -1.817 |
ieft | -1.727 |
nesota | -1.721 |
olkien | -1.721 |
harassing | -1.692 |
Token | Next |
Token ID | 7406 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
iatus | +2.309 |
AST | +2.008 |
maj | +1.980 |
Ast | +1.924 |
代 | +1.879 |
Neg logit contributions | |
psychiat | -2.258 |
ieft | -2.156 |
nesota | -2.149 |
olkien | -2.137 |
harassing | -2.116 |
Token | up |
Token ID | 510 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
iatus | +1.836 |
maj | +1.554 |
AST | +1.551 |
Ast | +1.489 |
Toast | +1.421 |
Neg logit contributions | |
psychiat | -2.750 |
olkien | -2.625 |
ieft | -2.625 |
nesota | -2.603 |
harassing | -2.569 |
Token | : |
Token ID | 25 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
iatus | +4.095 |
AST | +3.624 |
maj | +3.590 |
Ast | +3.528 |
� | +3.466 |
Neg logit contributions | |
psychiat | -5.387 |
olkien | -4.956 |
ieft | -4.861 |
nesota | -4.823 |
harassing | -4.794 |
Token | vs |
Token ID | 3691 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
iatus | +1.554 |
AST | +1.349 |
maj | +1.348 |
Ast | +1.303 |
Toast | +1.275 |
Neg logit contributions | |
psychiat | -1.429 |
ieft | -1.371 |
nesota | -1.365 |
olkien | -1.356 |
harassing | -1.337 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
iatus | +0.129 |
AST | +0.111 |
maj | +0.110 |
Ast | +0.107 |
代 | +0.105 |
Neg logit contributions | |
psychiat | -0.130 |
nesota | -0.123 |
ieft | -0.123 |
olkien | -0.123 |
harassing | -0.122 |
Token | Los |
Token ID | 5401 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
psychiat | +0.160 |
nesota | +0.152 |
ieft | +0.152 |
olkien | +0.150 |
harassing | +0.148 |
Neg logit contributions | |
iatus | -0.245 |
AST | -0.216 |
maj | -0.215 |
Ast | -0.209 |
代 | -0.207 |
Token | Angeles |
Token ID | 5652 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
iatus | +0.069 |
maj | +0.059 |
AST | +0.059 |
Ast | +0.056 |
代 | +0.056 |
Neg logit contributions | |
psychiat | -0.069 |
nesota | -0.066 |
ieft | -0.066 |
olkien | -0.065 |
harassing | -0.065 |
Token | September |
Token ID | 2693 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
iatus | +2.962 |
AST | +2.578 |
maj | +2.574 |
Ast | +2.498 |
� | +2.448 |
Neg logit contributions | |
psychiat | -2.510 |
nesota | -2.406 |
olkien | -2.396 |
ieft | -2.394 |
harassing | -2.328 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
iatus | +1.478 |
AST | +1.262 |
maj | +1.255 |
Ast | +1.215 |
Toast | +1.182 |
Neg logit contributions | |
psychiat | -1.632 |
nesota | -1.568 |
ieft | -1.557 |
olkien | -1.551 |
harassing | -1.533 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
iatus | +1.221 |
AST | +1.055 |
maj | +1.054 |
Ast | +1.022 |
Toast | +1.000 |
Neg logit contributions | |
psychiat | -1.060 |
nesota | -1.019 |
ieft | -1.007 |
olkien | -1.002 |
harassing | -0.991 |
Token | 07 |
Token ID | 8753 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
iatus | +0.576 |
AST | +0.479 |
maj | +0.478 |
Ast | +0.459 |
代 | +0.447 |
Neg logit contributions | |
psychiat | -0.772 |
nesota | -0.746 |
ieft | -0.742 |
olkien | -0.737 |
harassing | -0.731 |
Token | : |
Token ID | 25 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
iatus | +3.014 |
AST | +2.641 |
maj | +2.639 |
Ast | +2.563 |
� | +2.491 |
Neg logit contributions | |
psychiat | -3.307 |
nesota | -3.144 |
olkien | -3.095 |
ieft | -3.092 |
harassing | -3.050 |
Token | 50 |
Token ID | 1120 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
iatus | +2.807 |
AST | +2.457 |
maj | +2.453 |
Ast | +2.404 |
� | +2.347 |
Neg logit contributions | |
psychiat | -2.605 |
nesota | -2.435 |
harassing | -2.380 |
olkien | -2.376 |
ieft | -2.372 |
Token | pur |
Token ID | 1308 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
iatus | +5.093 |
maj | +4.525 |
AST | +4.468 |
Ast | +4.362 |
� | +4.313 |
Neg logit contributions | |
psychiat | -4.019 |
nesota | -3.900 |
ieft | -3.844 |
olkien | -3.831 |
harassing | -3.726 |
Token | ak |
Token ID | 461 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
iatus | +1.913 |
maj | +1.610 |
AST | +1.610 |
Ast | +1.540 |
� | +1.523 |
Neg logit contributions | |
psychiat | -2.246 |
nesota | -2.113 |
harassing | -2.087 |
olkien | -2.082 |
ieft | -2.078 |
Token | ushi |
Token ID | 17731 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
iatus | +1.241 |
maj | +1.072 |
AST | +1.066 |
Ast | +1.034 |
代 | +1.026 |
Neg logit contributions | |
psychiat | -0.988 |
nesota | -0.939 |
ieft | -0.930 |
olkien | -0.927 |
harassing | -0.919 |
Token | wrote |
Token ID | 2630 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
iatus | +1.381 |
maj | +1.174 |
AST | +1.166 |
Ast | +1.122 |
代 | +1.109 |
Neg logit contributions | |
psychiat | -1.493 |
nesota | -1.439 |
ieft | -1.428 |
olkien | -1.418 |
harassing | -1.409 |
Token | : |
Token ID | 25 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
iatus | +0.687 |
AST | +0.595 |
maj | +0.593 |
Ast | +0.574 |
代 | +0.562 |
Neg logit contributions | |
psychiat | -0.649 |
nesota | -0.618 |
ieft | -0.615 |
olkien | -0.611 |
harassing | -0.606 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
psychiat | +0.163 |
nesota | +0.156 |
ieft | +0.155 |
olkien | +0.153 |
harassing | +0.152 |
Neg logit contributions | |
iatus | -0.213 |
AST | -0.186 |
maj | -0.186 |
Ast | -0.180 |
代 | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
iatus | +1.081 |
AST | +0.947 |
maj | +0.945 |
Ast | +0.918 |
� | +0.899 |
Neg logit contributions | |
psychiat | -0.903 |
nesota | -0.846 |
ieft | -0.840 |
olkien | -0.836 |
harassing | -0.828 |
Token | Ko |
Token ID | 48735 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
iatus | +1.183 |
maj | +1.007 |
AST | +1.005 |
Ast | +0.969 |
代 | +0.959 |
Neg logit contributions | |
psychiat | -1.180 |
nesota | -1.134 |
ieft | -1.126 |
olkien | -1.117 |
harassing | -1.115 |
Token | Do |
Token ID | 5211 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
psychiat | +1.027 |
ieft | +0.995 |
nesota | +0.986 |
olkien | +0.978 |
harassing | +0.970 |
Neg logit contributions | |
iatus | -1.013 |
AST | -0.865 |
maj | -0.864 |
代 | -0.830 |
Ast | -0.828 |
Token | Profile |
Token ID | 13118 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
iatus | +0.905 |
AST | +0.767 |
maj | +0.767 |
Ast | +0.737 |
代 | +0.730 |
Neg logit contributions | |
psychiat | -0.950 |
nesota | -0.914 |
ieft | -0.910 |
olkien | -0.902 |
harassing | -0.897 |
Token | Joined |
Token ID | 16709 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
iatus | +2.136 |
AST | +1.775 |
maj | +1.764 |
Ast | +1.700 |
� | +1.655 |
Neg logit contributions | |
psychiat | -3.014 |
nesota | -2.928 |
ieft | -2.887 |
olkien | -2.885 |
harassing | -2.856 |
Token | December |
Token ID | 3426 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
iatus | +4.383 |
AST | +3.928 |
Ast | +3.862 |
maj | +3.854 |
� | +3.711 |
Neg logit contributions | |
psychiat | -4.669 |
olkien | -4.500 |
nesota | -4.482 |
ieft | -4.442 |
harassing | -4.273 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
iatus | +1.551 |
AST | +1.354 |
maj | +1.333 |
Ast | +1.308 |
� | +1.271 |
Neg logit contributions | |
psychiat | -1.474 |
nesota | -1.409 |
olkien | -1.401 |
ieft | -1.395 |
harassing | -1.378 |
Token | United |
Token ID | 1578 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
iatus | +3.239 |
AST | +2.858 |
maj | +2.809 |
Ast | +2.772 |
� | +2.708 |
Neg logit contributions | |
psychiat | -2.596 |
nesota | -2.458 |
olkien | -2.453 |
ieft | -2.433 |
harassing | -2.401 |
Token | States |
Token ID | 1829 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
iatus | +3.011 |
AST | +2.651 |
maj | +2.614 |
Ast | +2.587 |
Toast | +2.538 |
Neg logit contributions | |
psychiat | -2.586 |
olkien | -2.424 |
nesota | -2.406 |
ieft | -2.400 |
harassing | -2.380 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
iatus | +3.341 |
AST | +2.923 |
maj | +2.897 |
Ast | +2.828 |
� | +2.762 |
Neg logit contributions | |
psychiat | -3.249 |
olkien | -3.106 |
nesota | -3.104 |
ieft | -3.080 |
harassing | -3.025 |
Token | presidential |
Token ID | 4787 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
psychiat | +0.743 |
nesota | +0.712 |
ieft | +0.708 |
harassing | +0.699 |
olkien | +0.694 |
Neg logit contributions | |
iatus | -0.918 |
AST | -0.792 |
maj | -0.789 |
代 | -0.763 |
Ast | -0.760 |
Token | nominee |
Token ID | 10429 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
psychiat | +0.731 |
nesota | +0.697 |
ieft | +0.696 |
harassing | +0.685 |
olkien | +0.676 |
Neg logit contributions | |
iatus | -1.073 |
AST | -0.943 |
maj | -0.937 |
代 | -0.914 |
Ast | -0.907 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iatus | +0.874 |
maj | +0.773 |
AST | +0.772 |
Ast | +0.751 |
代 | +0.740 |
Neg logit contributions | |
psychiat | -0.514 |
nesota | -0.489 |
ieft | -0.484 |
olkien | -0.482 |
harassing | -0.474 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +0.675 |
maj | +0.593 |
AST | +0.592 |
Ast | +0.575 |
代 | +0.569 |
Neg logit contributions | |
psychiat | -0.443 |
nesota | -0.421 |
ieft | -0.419 |
olkien | -0.415 |
harassing | -0.411 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
iatus | +0.947 |
maj | +0.819 |
AST | +0.815 |
Ast | +0.789 |
代 | +0.776 |
Neg logit contributions | |
psychiat | -0.857 |
nesota | -0.824 |
ieft | -0.819 |
olkien | -0.816 |
harassing | -0.802 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
iatus | +2.611 |
Ast | +1.951 |
AST | +1.931 |
maj | +1.866 |
Toast | +1.824 |
Neg logit contributions | |
psychiat | -5.663 |
olkien | -5.446 |
nesota | -5.394 |
ieft | -5.388 |
harassing | -5.310 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +4.803 |
Ast | +4.188 |
maj | +4.065 |
Romance | +3.936 |
AST | +3.920 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.162 |
olkien | -4.083 |
ieft | -4.048 |
uman | -3.752 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
iatus | +4.976 |
maj | +4.368 |
AST | +4.348 |
Ast | +4.283 |
Romance | +4.189 |
Neg logit contributions | |
psychiat | -3.901 |
olkien | -3.630 |
nesota | -3.609 |
ieft | -3.593 |
harassing | -3.543 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
iatus | +4.269 |
maj | +3.611 |
AST | +3.595 |
Ast | +3.508 |
代 | +3.456 |
Neg logit contributions | |
psychiat | -4.465 |
nesota | -4.284 |
olkien | -4.227 |
ieft | -4.218 |
harassing | -4.195 |
Token | : |
Token ID | 25 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
iatus | +4.295 |
AST | +3.494 |
Ast | +3.440 |
maj | +3.404 |
Toast | +3.244 |
Neg logit contributions | |
psychiat | -6.142 |
nesota | -5.870 |
ieft | -5.824 |
olkien | -5.816 |
harassing | -5.598 |
Token | ' |
Token ID | 705 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
iatus | +2.299 |
AST | +1.946 |
maj | +1.943 |
Ast | +1.871 |
代 | +1.842 |
Neg logit contributions | |
psychiat | -2.486 |
nesota | -2.388 |
ieft | -2.374 |
olkien | -2.357 |
harassing | -2.345 |
Token | berg |
Token ID | 3900 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
psychiat | +0.595 |
nesota | +0.574 |
ieft | +0.571 |
olkien | +0.566 |
harassing | +0.563 |
Neg logit contributions | |
iatus | -0.556 |
AST | -0.471 |
maj | -0.470 |
Ast | -0.451 |
代 | -0.447 |
Token | witz |
Token ID | 28155 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
iatus | +0.374 |
AST | +0.327 |
maj | +0.327 |
Ast | +0.317 |
代 | +0.313 |
Neg logit contributions | |
psychiat | -0.273 |
nesota | -0.259 |
ieft | -0.258 |
olkien | -0.256 |
harassing | -0.254 |
Token | West |
Token ID | 2688 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
iatus | +1.132 |
AST | +0.994 |
maj | +0.992 |
Ast | +0.967 |
代 | +0.951 |
Neg logit contributions | |
psychiat | -0.798 |
ieft | -0.753 |
nesota | -0.752 |
olkien | -0.749 |
harassing | -0.741 |
Token | chester |
Token ID | 35983 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
iatus | +3.349 |
maj | +2.955 |
AST | +2.955 |
Ast | +2.903 |
Toast | +2.820 |
Neg logit contributions | |
psychiat | -2.366 |
olkien | -2.247 |
ieft | -2.220 |
nesota | -2.216 |
harassing | -2.205 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
iatus | +3.102 |
AST | +2.694 |
maj | +2.683 |
Ast | +2.625 |
� | +2.548 |
Neg logit contributions | |
psychiat | -2.821 |
olkien | -2.693 |
ieft | -2.683 |
nesota | -2.674 |
harassing | -2.642 |
Token | hour |
Token ID | 1711 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
iatus | +1.710 |
AST | +1.352 |
maj | +1.335 |
Ast | +1.262 |
代 | +1.229 |
Neg logit contributions | |
psychiat | -3.510 |
nesota | -3.401 |
ieft | -3.401 |
olkien | -3.381 |
harassing | -3.350 |
Token | ago |
Token ID | 2084 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
iatus | +5.224 |
AST | +4.668 |
maj | +4.588 |
Ast | +4.478 |
� | +4.402 |
Neg logit contributions | |
psychiat | -3.797 |
olkien | -3.519 |
ieft | -3.430 |
harassing | -3.351 |
nesota | -3.263 |
Token | Pretty |
Token ID | 20090 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
iatus | +2.524 |
AST | +2.196 |
maj | +2.180 |
Ast | +2.125 |
Toast | +2.079 |
Neg logit contributions | |
psychiat | -2.488 |
ieft | -2.371 |
nesota | -2.370 |
olkien | -2.359 |
harassing | -2.315 |
Token | simple |
Token ID | 2829 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
iatus | +2.053 |
maj | +1.821 |
AST | +1.806 |
Ast | +1.752 |
Toast | +1.716 |
Neg logit contributions | |
psychiat | -1.578 |
nesota | -1.518 |
ieft | -1.512 |
olkien | -1.509 |
harassing | -1.458 |
Token | Paul |
Token ID | 3362 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
psychiat | +0.431 |
nesota | +0.411 |
ieft | +0.409 |
harassing | +0.407 |
olkien | +0.403 |
Neg logit contributions | |
iatus | -0.462 |
AST | -0.393 |
maj | -0.393 |
代 | -0.379 |
Ast | -0.378 |
Token | : |
Token ID | 25 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
psychiat | +0.105 |
nesota | +0.101 |
ieft | +0.101 |
olkien | +0.100 |
harassing | +0.099 |
Neg logit contributions | |
iatus | -0.115 |
AST | -0.099 |
maj | -0.099 |
Ast | -0.095 |
代 | -0.094 |
Token | Smith |
Token ID | 4176 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
psychiat | +1.056 |
ieft | +1.026 |
nesota | +1.012 |
olkien | +1.008 |
harassing | +1.006 |
Neg logit contributions | |
iatus | -1.526 |
maj | -1.343 |
AST | -1.324 |
代 | -1.303 |
Ast | -1.255 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
iatus | +0.741 |
AST | +0.637 |
maj | +0.636 |
Ast | +0.615 |
代 | +0.607 |
Neg logit contributions | |
psychiat | -0.702 |
nesota | -0.667 |
ieft | -0.667 |
olkien | -0.662 |
harassing | -0.655 |
Token | Ravens |
Token ID | 20091 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
psychiat | +1.019 |
nesota | +0.988 |
ieft | +0.973 |
harassing | +0.970 |
olkien | +0.957 |
Neg logit contributions | |
iatus | -1.296 |
maj | -1.111 |
AST | -1.105 |
代 | -1.071 |
Ast | -1.059 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
iatus | +1.690 |
AST | +1.462 |
maj | +1.444 |
Ast | +1.406 |
Toast | +1.372 |
Neg logit contributions | |
psychiat | -1.722 |
ieft | -1.638 |
olkien | -1.633 |
nesota | -1.633 |
harassing | -1.606 |
Token | Next |
Token ID | 7406 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
iatus | +2.306 |
AST | +1.999 |
maj | +1.970 |
Ast | +1.913 |
代 | +1.865 |
Neg logit contributions | |
psychiat | -2.372 |
ieft | -2.272 |
nesota | -2.263 |
olkien | -2.252 |
harassing | -2.225 |
Token | up |
Token ID | 510 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
iatus | +1.760 |
AST | +1.487 |
maj | +1.487 |
Ast | +1.428 |
Toast | +1.360 |
Neg logit contributions | |
psychiat | -2.619 |
olkien | -2.499 |
ieft | -2.499 |
nesota | -2.480 |
harassing | -2.447 |
Token | : |
Token ID | 25 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
iatus | +3.946 |
AST | +3.498 |
maj | +3.462 |
Ast | +3.399 |
� | +3.331 |
Neg logit contributions | |
psychiat | -5.120 |
olkien | -4.717 |
ieft | -4.629 |
nesota | -4.589 |
harassing | -4.558 |
Token | Bye |
Token ID | 47843 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
iatus | +1.890 |
AST | +1.645 |
maj | +1.643 |
Ast | +1.587 |
Toast | +1.551 |
Neg logit contributions | |
psychiat | -1.773 |
ieft | -1.701 |
nesota | -1.692 |
olkien | -1.682 |
harassing | -1.655 |
Token | week |
Token ID | 1285 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
psychiat | +0.247 |
nesota | +0.236 |
ieft | +0.235 |
olkien | +0.233 |
harassing | +0.232 |
Neg logit contributions | |
iatus | -0.284 |
AST | -0.245 |
maj | -0.244 |
Ast | -0.236 |
代 | -0.233 |
Token | ( |
Token ID | 357 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
iatus | +0.937 |
AST | +0.809 |
maj | +0.807 |
Ast | +0.780 |
代 | +0.768 |
Neg logit contributions | |
psychiat | -0.846 |
nesota | -0.809 |
ieft | -0.807 |
olkien | -0.800 |
harassing | -0.792 |
Token | at |
Token ID | 265 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
psychiat | +0.170 |
nesota | +0.164 |
ieft | +0.163 |
olkien | +0.161 |
harassing | +0.160 |
Neg logit contributions | |
iatus | -0.170 |
AST | -0.145 |
maj | -0.145 |
Ast | -0.139 |
代 | -0.138 |
Token | J |
Token ID | 41 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
iatus | +1.280 |
maj | +1.092 |
AST | +1.088 |
Ast | +1.049 |
代 | +1.040 |
Neg logit contributions | |
psychiat | -1.263 |
nesota | -1.214 |
ieft | -1.204 |
olkien | -1.195 |
harassing | -1.193 |
Token | aaaa |
Token ID | 24794 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
psychiat | +0.306 |
nesota | +0.294 |
ieft | +0.294 |
olkien | +0.291 |
harassing | +0.288 |
Neg logit contributions | |
iatus | -0.296 |
AST | -0.253 |
maj | -0.252 |
Ast | -0.242 |
代 | -0.240 |
Token | asper |
Token ID | 32981 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
psychiat | +1.223 |
ieft | +1.191 |
nesota | +1.184 |
olkien | +1.176 |
harassing | +1.160 |
Neg logit contributions | |
iatus | -1.177 |
AST | -1.005 |
maj | -1.002 |
代 | -0.963 |
Ast | -0.961 |
Token | Profile |
Token ID | 13118 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
iatus | +0.493 |
AST | +0.402 |
maj | +0.402 |
Ast | +0.382 |
代 | +0.378 |
Neg logit contributions | |
psychiat | -0.725 |
nesota | -0.701 |
ieft | -0.699 |
olkien | -0.693 |
harassing | -0.690 |
Token | Blog |
Token ID | 14001 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
iatus | +2.653 |
AST | +2.212 |
maj | +2.180 |
Ast | +2.121 |
� | +2.058 |
Neg logit contributions | |
psychiat | -3.796 |
nesota | -3.690 |
olkien | -3.640 |
ieft | -3.630 |
harassing | -3.594 |
Token | Joined |
Token ID | 16709 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
iatus | +1.429 |
AST | +1.195 |
maj | +1.185 |
Ast | +1.156 |
� | +1.121 |
Neg logit contributions | |
psychiat | -1.957 |
nesota | -1.882 |
olkien | -1.867 |
ieft | -1.858 |
harassing | -1.837 |
Token | April |
Token ID | 3035 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
iatus | +4.306 |
AST | +3.839 |
Ast | +3.792 |
maj | +3.769 |
� | +3.622 |
Neg logit contributions | |
psychiat | -4.518 |
nesota | -4.365 |
olkien | -4.358 |
ieft | -4.299 |
harassing | -4.150 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
iatus | +2.708 |
AST | +2.366 |
maj | +2.337 |
Ast | +2.288 |
� | +2.222 |
Neg logit contributions | |
psychiat | -2.739 |
nesota | -2.624 |
olkien | -2.608 |
ieft | -2.590 |
harassing | -2.556 |
Token | United |
Token ID | 1578 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
iatus | +2.656 |
AST | +2.339 |
maj | +2.304 |
Ast | +2.269 |
Toast | +2.215 |
Neg logit contributions | |
psychiat | -2.260 |
nesota | -2.150 |
olkien | -2.144 |
ieft | -2.125 |
harassing | -2.096 |
Token | States |
Token ID | 1829 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
iatus | +4.208 |
AST | +3.661 |
maj | +3.634 |
Ast | +3.589 |
Toast | +3.517 |
Neg logit contributions | |
psychiat | -3.627 |
olkien | -3.433 |
nesota | -3.415 |
ieft | -3.399 |
harassing | -3.395 |
Token | 5 |
Token ID | 642 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
iatus | +3.481 |
AST | +3.042 |
maj | +3.010 |
Ast | +2.948 |
� | +2.870 |
Neg logit contributions | |
psychiat | -3.489 |
nesota | -3.333 |
olkien | -3.330 |
ieft | -3.300 |
harassing | -3.248 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
psychiat | +0.482 |
nesota | +0.459 |
ieft | +0.456 |
olkien | +0.450 |
harassing | +0.449 |
Neg logit contributions | |
iatus | -0.720 |
AST | -0.630 |
maj | -0.630 |
Ast | -0.610 |
代 | -0.606 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
iatus | +1.007 |
maj | +0.887 |
AST | +0.883 |
Ast | +0.872 |
Toast | +0.843 |
Neg logit contributions | |
psychiat | -0.749 |
olkien | -0.706 |
nesota | -0.704 |
ieft | -0.700 |
harassing | -0.685 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
iatus | +0.925 |
maj | +0.828 |
AST | +0.822 |
Ast | +0.807 |
Toast | +0.784 |
Neg logit contributions | |
psychiat | -0.593 |
olkien | -0.567 |
nesota | -0.563 |
ieft | -0.557 |
harassing | -0.539 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
iatus | +2.161 |
AST | +1.675 |
Ast | +1.633 |
maj | +1.611 |
Toast | +1.544 |
Neg logit contributions | |
psychiat | -4.477 |
olkien | -4.306 |
nesota | -4.297 |
ieft | -4.287 |
harassing | -4.204 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
iatus | +4.323 |
Ast | +3.774 |
maj | +3.741 |
AST | +3.630 |
Romance | +3.608 |
Neg logit contributions | |
psychiat | -3.658 |
nesota | -3.438 |
olkien | -3.359 |
ieft | -3.337 |
harassing | -3.091 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
iatus | +4.800 |
maj | +4.220 |
AST | +4.193 |
Ast | +4.142 |
Romance | +4.037 |
Neg logit contributions | |
psychiat | -3.823 |
olkien | -3.567 |
ieft | -3.534 |
nesota | -3.514 |
harassing | -3.464 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
iatus | +4.309 |
maj | +3.634 |
AST | +3.618 |
Ast | +3.507 |
代 | +3.467 |
Neg logit contributions | |
psychiat | -4.581 |
nesota | -4.408 |
ieft | -4.365 |
olkien | -4.356 |
harassing | -4.323 |
Token | : |
Token ID | 25 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
iatus | +3.842 |
AST | +3.091 |
maj | +3.010 |
Ast | +2.981 |
Toast | +2.833 |
Neg logit contributions | |
psychiat | -6.231 |
nesota | -5.990 |
ieft | -5.982 |
olkien | -5.951 |
harassing | -5.792 |
Token | ' |
Token ID | 705 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
iatus | +1.966 |
maj | +1.675 |
AST | +1.666 |
代 | +1.609 |
Ast | +1.585 |
Neg logit contributions | |
psychiat | -1.961 |
nesota | -1.904 |
ieft | -1.901 |
olkien | -1.880 |
harassing | -1.874 |
Token | I |
Token ID | 40 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
iatus | +2.206 |
maj | +1.886 |
AST | +1.878 |
Ast | +1.823 |
代 | +1.800 |
Neg logit contributions | |
psychiat | -2.161 |
nesota | -2.084 |
ieft | -2.053 |
olkien | -2.048 |
harassing | -2.032 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
iatus | +1.184 |
AST | +1.058 |
maj | +1.021 |
代 | +1.021 |
Ast | +1.000 |
Neg logit contributions | |
psychiat | -0.681 |
ieft | -0.661 |
harassing | -0.627 |
olkien | -0.624 |
nesota | -0.624 |
Token | the |
Token ID | 262 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
iatus | +0.370 |
AST | +0.314 |
maj | +0.313 |
Ast | +0.301 |
代 | +0.300 |
Neg logit contributions | |
psychiat | -0.375 |
nesota | -0.360 |
ieft | -0.358 |
olkien | -0.355 |
harassing | -0.354 |
Token | blame |
Token ID | 8138 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
psychiat | +0.717 |
nesota | +0.687 |
ieft | +0.684 |
olkien | +0.678 |
harassing | +0.676 |
Neg logit contributions | |
iatus | -0.757 |
AST | -0.647 |
maj | -0.646 |
Ast | -0.622 |
代 | -0.618 |
Token | towards |
Token ID | 3371 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
psychiat | +1.584 |
nesota | +1.506 |
ieft | +1.500 |
harassing | +1.494 |
olkien | +1.482 |
Neg logit contributions | |
iatus | -1.739 |
AST | -1.480 |
maj | -1.460 |
代 | -1.424 |
Ast | -1.418 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
psychiat | +0.187 |
nesota | +0.179 |
ieft | +0.178 |
harassing | +0.177 |
olkien | +0.176 |
Neg logit contributions | |
iatus | -0.203 |
AST | -0.173 |
maj | -0.172 |
Ast | -0.166 |
代 | -0.166 |
Token | dis |
Token ID | 595 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
psychiat | +0.136 |
nesota | +0.130 |
ieft | +0.129 |
harassing | +0.128 |
olkien | +0.127 |
Neg logit contributions | |
iatus | -0.174 |
AST | -0.150 |
maj | -0.150 |
Ast | -0.145 |
代 | -0.145 |
Token | ench |
Token ID | 24421 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +0.178 |
AST | +0.149 |
maj | +0.149 |
Ast | +0.143 |
代 | +0.141 |
Neg logit contributions | |
psychiat | -0.210 |
ieft | -0.202 |
nesota | -0.202 |
olkien | -0.200 |
harassing | -0.199 |
Token | anted |
Token ID | 4126 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
iatus | +3.870 |
AST | +3.217 |
maj | +3.181 |
Ast | +3.088 |
� | +3.000 |
Neg logit contributions | |
psychiat | -4.982 |
olkien | -4.715 |
harassing | -4.710 |
nesota | -4.706 |
ieft | -4.586 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
iatus | +2.032 |
maj | +1.770 |
AST | +1.765 |
Ast | +1.710 |
Toast | +1.667 |
Neg logit contributions | |
psychiat | -1.847 |
nesota | -1.808 |
ieft | -1.785 |
olkien | -1.782 |
harassing | -1.737 |
Token | j |
Token ID | 474 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
iatus | +0.988 |
maj | +0.851 |
AST | +0.850 |
Ast | +0.820 |
代 | +0.807 |
Neg logit contributions | |
psychiat | -0.924 |
nesota | -0.895 |
ieft | -0.887 |
olkien | -0.879 |
harassing | -0.868 |
Token | aded |
Token ID | 5286 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
iatus | +0.451 |
AST | +0.380 |
maj | +0.380 |
Ast | +0.364 |
代 | +0.360 |
Neg logit contributions | |
psychiat | -0.511 |
nesota | -0.492 |
ieft | -0.490 |
olkien | -0.486 |
harassing | -0.484 |
Token | young |
Token ID | 1862 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
psychiat | +0.142 |
nesota | +0.135 |
ieft | +0.135 |
harassing | +0.133 |
olkien | +0.133 |
Neg logit contributions | |
iatus | -0.164 |
AST | -0.141 |
maj | -0.141 |
Ast | -0.136 |
代 | -0.135 |
Token | with |
Token ID | 351 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
iatus | +1.294 |
maj | +1.116 |
AST | +1.112 |
Ast | +1.080 |
代 | +1.057 |
Neg logit contributions | |
psychiat | -1.218 |
nesota | -1.170 |
ieft | -1.164 |
olkien | -1.159 |
harassing | -1.136 |
Token | Republican |
Token ID | 3415 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
iatus | +1.204 |
maj | +1.061 |
AST | +1.056 |
Ast | +1.031 |
代 | +1.010 |
Neg logit contributions | |
psychiat | -0.803 |
nesota | -0.764 |
ieft | -0.759 |
olkien | -0.754 |
harassing | -0.739 |
Token | nominee |
Token ID | 10429 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
psychiat | +0.602 |
nesota | +0.572 |
ieft | +0.569 |
harassing | +0.561 |
olkien | +0.560 |
Neg logit contributions | |
iatus | -0.909 |
AST | -0.796 |
maj | -0.794 |
Ast | -0.769 |
代 | -0.767 |
Token | Donald |
Token ID | 3759 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
iatus | +0.369 |
maj | +0.329 |
AST | +0.329 |
Ast | +0.321 |
代 | +0.315 |
Neg logit contributions | |
psychiat | -0.178 |
nesota | -0.168 |
ieft | -0.167 |
olkien | -0.166 |
harassing | -0.161 |
Token | Trump |
Token ID | 1301 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
iatus | +0.687 |
AST | +0.602 |
maj | +0.599 |
Ast | +0.587 |
Toast | +0.569 |
Neg logit contributions | |
psychiat | -0.556 |
nesota | -0.521 |
ieft | -0.518 |
olkien | -0.516 |
harassing | -0.510 |
Token | Donald |
Token ID | 3759 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +0.905 |
maj | +0.813 |
AST | +0.813 |
Ast | +0.805 |
� | +0.773 |
Neg logit contributions | |
psychiat | -0.501 |
nesota | -0.483 |
ieft | -0.479 |
olkien | -0.477 |
harassing | -0.443 |
Token | John |
Token ID | 1757 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
iatus | +4.429 |
AST | +3.892 |
maj | +3.828 |
Ast | +3.785 |
Toast | +3.740 |
Neg logit contributions | |
psychiat | -4.407 |
olkien | -4.059 |
ieft | -3.969 |
nesota | -3.932 |
harassing | -3.920 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
iatus | +3.302 |
maj | +2.817 |
AST | +2.802 |
Ast | +2.794 |
Toast | +2.647 |
Neg logit contributions | |
psychiat | -3.022 |
olkien | -2.813 |
nesota | -2.778 |
ieft | -2.750 |
harassing | -2.688 |
Token | House |
Token ID | 18102 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
iatus | +3.835 |
maj | +3.258 |
AST | +3.245 |
Ast | +3.197 |
代 | +3.141 |
Neg logit contributions | |
psychiat | -3.542 |
nesota | -3.363 |
olkien | -3.319 |
harassing | -3.306 |
ieft | -3.293 |
Token | committee |
Token ID | 5583 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
iatus | +4.381 |
Ast | +3.888 |
maj | +3.862 |
AST | +3.815 |
Romance | +3.786 |
Neg logit contributions | |
psychiat | -3.539 |
olkien | -3.326 |
nesota | -3.181 |
ieft | -3.178 |
harassing | -3.138 |
Token | believes |
Token ID | 5804 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
iatus | +1.625 |
maj | +1.366 |
AST | +1.355 |
Ast | +1.313 |
代 | +1.279 |
Neg logit contributions | |
psychiat | -2.134 |
olkien | -2.066 |
nesota | -2.053 |
ieft | -2.050 |
harassing | -2.009 |
Token | nominee |
Token ID | 10429 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
psychiat | +0.731 |
nesota | +0.697 |
ieft | +0.696 |
harassing | +0.685 |
olkien | +0.676 |
Neg logit contributions | |
iatus | -1.073 |
AST | -0.943 |
maj | -0.937 |
代 | -0.914 |
Ast | -0.907 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iatus | +0.874 |
maj | +0.773 |
AST | +0.772 |
Ast | +0.751 |
代 | +0.740 |
Neg logit contributions | |
psychiat | -0.514 |
nesota | -0.489 |
ieft | -0.484 |
olkien | -0.482 |
harassing | -0.474 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +0.675 |
maj | +0.593 |
AST | +0.592 |
Ast | +0.575 |
代 | +0.569 |
Neg logit contributions | |
psychiat | -0.443 |
nesota | -0.421 |
ieft | -0.419 |
olkien | -0.415 |
harassing | -0.411 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
iatus | +0.947 |
maj | +0.819 |
AST | +0.815 |
Ast | +0.789 |
代 | +0.776 |
Neg logit contributions | |
psychiat | -0.857 |
nesota | -0.824 |
ieft | -0.819 |
olkien | -0.816 |
harassing | -0.802 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
iatus | +2.611 |
Ast | +1.951 |
AST | +1.931 |
maj | +1.866 |
Toast | +1.824 |
Neg logit contributions | |
psychiat | -5.663 |
olkien | -5.446 |
nesota | -5.394 |
ieft | -5.388 |
harassing | -5.310 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +4.803 |
Ast | +4.188 |
maj | +4.065 |
Romance | +3.936 |
AST | +3.920 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.162 |
olkien | -4.083 |
ieft | -4.048 |
uman | -3.752 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
iatus | +4.976 |
maj | +4.368 |
AST | +4.348 |
Ast | +4.283 |
Romance | +4.189 |
Neg logit contributions | |
psychiat | -3.901 |
olkien | -3.630 |
nesota | -3.609 |
ieft | -3.593 |
harassing | -3.543 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
iatus | +4.269 |
maj | +3.611 |
AST | +3.595 |
Ast | +3.508 |
代 | +3.456 |
Neg logit contributions | |
psychiat | -4.465 |
nesota | -4.284 |
olkien | -4.227 |
ieft | -4.218 |
harassing | -4.195 |
Token | : |
Token ID | 25 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
iatus | +4.295 |
AST | +3.494 |
Ast | +3.440 |
maj | +3.404 |
Toast | +3.244 |
Neg logit contributions | |
psychiat | -6.142 |
nesota | -5.870 |
ieft | -5.824 |
olkien | -5.816 |
harassing | -5.598 |
Token | ' |
Token ID | 705 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
iatus | +2.299 |
AST | +1.946 |
maj | +1.943 |
Ast | +1.871 |
代 | +1.842 |
Neg logit contributions | |
psychiat | -2.486 |
nesota | -2.388 |
ieft | -2.374 |
olkien | -2.357 |
harassing | -2.345 |
Token | I |
Token ID | 40 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
iatus | +2.468 |
maj | +2.106 |
AST | +2.088 |
Ast | +2.057 |
代 | +1.997 |
Neg logit contributions | |
psychiat | -2.643 |
nesota | -2.554 |
olkien | -2.502 |
ieft | -2.479 |
harassing | -2.475 |
Token | saving |
Token ID | 8914 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
iatus | +0.064 |
AST | +0.054 |
maj | +0.054 |
Ast | +0.052 |
代 | +0.052 |
Neg logit contributions | |
psychiat | -0.067 |
nesota | -0.065 |
ieft | -0.064 |
olkien | -0.064 |
harassing | -0.064 |
Token | / |
Token ID | 14 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
iatus | +1.221 |
maj | +1.051 |
AST | +1.050 |
Ast | +1.012 |
代 | +0.998 |
Neg logit contributions | |
psychiat | -1.132 |
nesota | -1.088 |
ieft | -1.082 |
olkien | -1.073 |
harassing | -1.065 |
Token | management |
Token ID | 27604 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
iatus | +1.273 |
maj | +1.085 |
AST | +1.083 |
Ast | +1.043 |
代 | +1.030 |
Neg logit contributions | |
psychiat | -1.310 |
nesota | -1.260 |
ieft | -1.250 |
olkien | -1.244 |
harassing | -1.231 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
iatus | +1.301 |
maj | +1.119 |
AST | +1.118 |
Ast | +1.077 |
代 | +1.060 |
Neg logit contributions | |
psychiat | -1.232 |
nesota | -1.185 |
ieft | -1.179 |
olkien | -1.169 |
harassing | -1.158 |
Token | try |
Token ID | 1949 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
iatus | +0.827 |
maj | +0.713 |
AST | +0.711 |
Ast | +0.686 |
代 | +0.672 |
Neg logit contributions | |
psychiat | -0.834 |
nesota | -0.804 |
ieft | -0.798 |
olkien | -0.792 |
harassing | -0.782 |
Token | i |
Token ID | 1312 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
iatus | +0.598 |
maj | +0.517 |
AST | +0.516 |
Ast | +0.498 |
代 | +0.491 |
Neg logit contributions | |
psychiat | -0.543 |
nesota | -0.524 |
ieft | -0.519 |
olkien | -0.515 |
harassing | -0.509 |
Token | w |
Token ID | 86 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
iatus | +3.590 |
maj | +3.000 |
AST | +2.886 |
Ast | +2.822 |
Toast | +2.783 |
Neg logit contributions | |
psychiat | -4.986 |
nesota | -4.828 |
ieft | -4.762 |
harassing | -4.739 |
olkien | -4.735 |
Token | config |
Token ID | 11250 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
iatus | +2.878 |
maj | +2.509 |
AST | +2.484 |
Ast | +2.402 |
代 | +2.371 |
Neg logit contributions | |
psychiat | -2.528 |
nesota | -2.423 |
olkien | -2.408 |
ieft | -2.403 |
harassing | -2.380 |
Token | to |
Token ID | 284 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
iatus | +1.595 |
maj | +1.386 |
AST | +1.385 |
Ast | +1.333 |
� | +1.317 |
Neg logit contributions | |
psychiat | -1.519 |
nesota | -1.467 |
ieft | -1.456 |
olkien | -1.442 |
harassing | -1.432 |
Token | see |
Token ID | 766 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
iatus | +0.477 |
maj | +0.409 |
AST | +0.408 |
Ast | +0.391 |
� | +0.381 |
Neg logit contributions | |
psychiat | -0.554 |
nesota | -0.539 |
ieft | -0.533 |
olkien | -0.530 |
harassing | -0.523 |
Token | if |
Token ID | 611 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
iatus | +0.827 |
maj | +0.712 |
AST | +0.709 |
Ast | +0.683 |
代 | +0.670 |
Neg logit contributions | |
psychiat | -0.830 |
nesota | -0.799 |
ieft | -0.794 |
olkien | -0.789 |
harassing | -0.781 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
iatus | +0.874 |
maj | +0.773 |
AST | +0.772 |
Ast | +0.751 |
代 | +0.740 |
Neg logit contributions | |
psychiat | -0.514 |
nesota | -0.489 |
ieft | -0.484 |
olkien | -0.482 |
harassing | -0.474 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +0.675 |
maj | +0.593 |
AST | +0.592 |
Ast | +0.575 |
代 | +0.569 |
Neg logit contributions | |
psychiat | -0.443 |
nesota | -0.421 |
ieft | -0.419 |
olkien | -0.415 |
harassing | -0.411 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
iatus | +0.947 |
maj | +0.819 |
AST | +0.815 |
Ast | +0.789 |
代 | +0.776 |
Neg logit contributions | |
psychiat | -0.857 |
nesota | -0.824 |
ieft | -0.819 |
olkien | -0.816 |
harassing | -0.802 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
iatus | +2.611 |
Ast | +1.951 |
AST | +1.931 |
maj | +1.866 |
Toast | +1.824 |
Neg logit contributions | |
psychiat | -5.663 |
olkien | -5.446 |
nesota | -5.394 |
ieft | -5.388 |
harassing | -5.310 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +4.803 |
Ast | +4.188 |
maj | +4.065 |
Romance | +3.936 |
AST | +3.920 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.162 |
olkien | -4.083 |
ieft | -4.048 |
uman | -3.752 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
iatus | +4.976 |
maj | +4.368 |
AST | +4.348 |
Ast | +4.283 |
Romance | +4.189 |
Neg logit contributions | |
psychiat | -3.901 |
olkien | -3.630 |
nesota | -3.609 |
ieft | -3.593 |
harassing | -3.543 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
iatus | +4.269 |
maj | +3.611 |
AST | +3.595 |
Ast | +3.508 |
代 | +3.456 |
Neg logit contributions | |
psychiat | -4.465 |
nesota | -4.284 |
olkien | -4.227 |
ieft | -4.218 |
harassing | -4.195 |
Token | : |
Token ID | 25 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
iatus | +4.295 |
AST | +3.494 |
Ast | +3.440 |
maj | +3.404 |
Toast | +3.244 |
Neg logit contributions | |
psychiat | -6.142 |
nesota | -5.870 |
ieft | -5.824 |
olkien | -5.816 |
harassing | -5.598 |
Token | ' |
Token ID | 705 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
iatus | +2.299 |
AST | +1.946 |
maj | +1.943 |
Ast | +1.871 |
代 | +1.842 |
Neg logit contributions | |
psychiat | -2.486 |
nesota | -2.388 |
ieft | -2.374 |
olkien | -2.357 |
harassing | -2.345 |
Token | I |
Token ID | 40 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
iatus | +2.468 |
maj | +2.106 |
AST | +2.088 |
Ast | +2.057 |
代 | +1.997 |
Neg logit contributions | |
psychiat | -2.643 |
nesota | -2.554 |
olkien | -2.502 |
ieft | -2.479 |
harassing | -2.475 |
Token | fully |
Token ID | 3938 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
iatus | +1.584 |
AST | +1.411 |
maj | +1.371 |
代 | +1.361 |
Ast | +1.341 |
Neg logit contributions | |
psychiat | -0.950 |
ieft | -0.918 |
nesota | -0.884 |
harassing | -0.882 |
olkien | -0.877 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
iatus | +0.019 |
maj | +0.016 |
AST | +0.016 |
Ast | +0.016 |
代 | +0.016 |
Neg logit contributions | |
psychiat | -0.016 |
nesota | -0.015 |
ieft | -0.015 |
olkien | -0.015 |
harassing | -0.014 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
iatus | +0.805 |
AST | +0.706 |
maj | +0.705 |
Ast | +0.684 |
代 | +0.678 |
Neg logit contributions | |
psychiat | -0.530 |
nesota | -0.504 |
ieft | -0.501 |
olkien | -0.496 |
harassing | -0.492 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
iatus | +0.918 |
maj | +0.815 |
AST | +0.813 |
Ast | +0.792 |
代 | +0.780 |
Neg logit contributions | |
psychiat | -0.545 |
nesota | -0.517 |
olkien | -0.512 |
ieft | -0.511 |
harassing | -0.500 |
Token | Diane |
Token ID | 26542 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
iatus | +2.106 |
AST | +1.642 |
Ast | +1.599 |
maj | +1.579 |
Toast | +1.532 |
Neg logit contributions | |
psychiat | -4.461 |
nesota | -4.289 |
olkien | -4.286 |
ieft | -4.263 |
harassing | -4.182 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
iatus | +4.433 |
Ast | +3.869 |
maj | +3.858 |
AST | +3.728 |
Romance | +3.711 |
Neg logit contributions | |
psychiat | -3.832 |
nesota | -3.632 |
olkien | -3.498 |
ieft | -3.468 |
harassing | -3.231 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
iatus | +4.593 |
maj | +4.034 |
AST | +4.028 |
Ast | +3.958 |
Romance | +3.862 |
Neg logit contributions | |
psychiat | -3.525 |
olkien | -3.291 |
nesota | -3.270 |
ieft | -3.256 |
harassing | -3.208 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
iatus | +4.140 |
maj | +3.486 |
AST | +3.482 |
Ast | +3.366 |
代 | +3.328 |
Neg logit contributions | |
psychiat | -4.553 |
nesota | -4.379 |
ieft | -4.335 |
olkien | -4.323 |
harassing | -4.299 |
Token | : |
Token ID | 25 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
iatus | +3.603 |
AST | +2.881 |
maj | +2.796 |
Ast | +2.754 |
Toast | +2.611 |
Neg logit contributions | |
psychiat | -6.269 |
nesota | -6.033 |
ieft | -6.003 |
olkien | -5.988 |
harassing | -5.830 |
Token | ' |
Token ID | 705 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
iatus | +1.693 |
maj | +1.440 |
AST | +1.435 |
代 | +1.382 |
Ast | +1.367 |
Neg logit contributions | |
psychiat | -1.704 |
ieft | -1.653 |
nesota | -1.653 |
olkien | -1.634 |
harassing | -1.627 |
Token | I |
Token ID | 40 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
iatus | +2.201 |
maj | +1.881 |
AST | +1.869 |
Ast | +1.828 |
代 | +1.801 |
Neg logit contributions | |
psychiat | -2.276 |
nesota | -2.204 |
olkien | -2.159 |
ieft | -2.153 |
harassing | -2.140 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iatus | +1.145 |
AST | +1.017 |
maj | +0.991 |
代 | +0.982 |
Ast | +0.968 |
Neg logit contributions | |
psychiat | -0.683 |
ieft | -0.658 |
nesota | -0.636 |
olkien | -0.632 |
harassing | -0.632 |
Token | : |
Token ID | 25 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
iatus | +0.079 |
AST | +0.068 |
maj | +0.068 |
Ast | +0.066 |
代 | +0.065 |
Neg logit contributions | |
psychiat | -0.070 |
nesota | -0.066 |
ieft | -0.066 |
olkien | -0.066 |
harassing | -0.065 |
Token | 10 |
Token ID | 838 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
psychiat | +0.966 |
nesota | +0.923 |
ieft | +0.920 |
harassing | +0.913 |
olkien | +0.913 |
Neg logit contributions | |
iatus | -0.911 |
AST | -0.766 |
maj | -0.764 |
代 | -0.732 |
Ast | -0.731 |
Token | . |
Token ID | 13 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
iatus | +0.359 |
AST | +0.307 |
maj | +0.307 |
Ast | +0.295 |
代 | +0.293 |
Neg logit contributions | |
psychiat | -0.338 |
nesota | -0.325 |
ieft | -0.324 |
olkien | -0.321 |
harassing | -0.319 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
psychiat | +0.571 |
nesota | +0.549 |
ieft | +0.548 |
olkien | +0.543 |
harassing | +0.538 |
Neg logit contributions | |
iatus | -0.569 |
AST | -0.483 |
maj | -0.482 |
Ast | -0.464 |
代 | -0.458 |
Token | 86 |
Token ID | 4521 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
psychiat | +1.192 |
nesota | +1.152 |
ieft | +1.148 |
olkien | +1.138 |
harassing | +1.129 |
Neg logit contributions | |
iatus | -1.177 |
AST | -1.003 |
maj | -0.995 |
Ast | -0.959 |
Toast | -0.950 |
Token | / |
Token ID | 14 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
psychiat | +2.995 |
ieft | +2.978 |
nesota | +2.972 |
olkien | +2.937 |
harassing | +2.893 |
Neg logit contributions | |
iatus | -4.453 |
maj | -3.809 |
AST | -3.776 |
Toast | -3.647 |
代 | -3.645 |
Token | 34 |
Token ID | 2682 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
psychiat | +4.749 |
ieft | +4.638 |
nesota | +4.624 |
olkien | +4.563 |
harassing | +4.437 |
Neg logit contributions | |
iatus | -5.457 |
AST | -4.739 |
maj | -4.651 |
Toast | -4.561 |
Ast | -4.491 |
Token | 110 |
Token ID | 11442 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
psychiat | +2.267 |
nesota | +2.193 |
ieft | +2.189 |
olkien | +2.164 |
harassing | +2.126 |
Neg logit contributions | |
iatus | -2.938 |
AST | -2.566 |
maj | -2.554 |
Ast | -2.448 |
Toast | -2.446 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
psychiat | +1.140 |
nesota | +1.094 |
ieft | +1.090 |
olkien | +1.082 |
harassing | +1.073 |
Neg logit contributions | |
iatus | -1.279 |
AST | -1.098 |
maj | -1.097 |
Ast | -1.055 |
代 | -1.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
psychiat | +1.765 |
ieft | +1.674 |
nesota | +1.674 |
olkien | +1.662 |
harassing | +1.654 |
Neg logit contributions | |
iatus | -2.069 |
maj | -1.772 |
AST | -1.753 |
Ast | -1.693 |
代 | -1.690 |
Token |
|
Token ID | 198 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
psychiat | +1.028 |
nesota | +0.998 |
ieft | +0.994 |
olkien | +0.978 |
harassing | +0.975 |
Neg logit contributions | |
iatus | -1.500 |
maj | -1.301 |
AST | -1.300 |
代 | -1.256 |
Ast | -1.254 |
Token | bullies |
Token ID | 42677 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
psychiat | +0.223 |
nesota | +0.212 |
ieft | +0.211 |
olkien | +0.208 |
harassing | +0.208 |
Neg logit contributions | |
iatus | -0.308 |
AST | -0.268 |
maj | -0.268 |
Ast | -0.259 |
代 | -0.257 |
Token | in |
Token ID | 287 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
psychiat | +1.210 |
nesota | +1.145 |
ieft | +1.145 |
harassing | +1.139 |
olkien | +1.128 |
Neg logit contributions | |
iatus | -1.420 |
AST | -1.218 |
maj | -1.217 |
Ast | -1.172 |
代 | -1.169 |
Token | adolescence |
Token ID | 37258 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
iatus | +0.559 |
AST | +0.483 |
maj | +0.483 |
Ast | +0.466 |
代 | +0.459 |
Neg logit contributions | |
psychiat | -0.486 |
nesota | -0.469 |
ieft | -0.466 |
olkien | -0.462 |
harassing | -0.456 |
Token | . |
Token ID | 764 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
psychiat | +0.952 |
nesota | +0.910 |
ieft | +0.906 |
olkien | +0.896 |
harassing | +0.894 |
Neg logit contributions | |
iatus | -1.086 |
maj | -0.933 |
AST | -0.933 |
Ast | -0.899 |
代 | -0.892 |
Token | Journal |
Token ID | 4913 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
psychiat | +1.804 |
nesota | +1.737 |
ieft | +1.725 |
harassing | +1.703 |
olkien | +1.693 |
Neg logit contributions | |
iatus | -2.094 |
maj | -1.789 |
AST | -1.771 |
代 | -1.701 |
Ast | -1.693 |
Token | of |
Token ID | 286 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
psychiat | +1.762 |
nesota | +1.723 |
ieft | +1.697 |
harassing | +1.676 |
olkien | +1.662 |
Neg logit contributions | |
iatus | -2.190 |
AST | -1.862 |
maj | -1.860 |
代 | -1.791 |
Ast | -1.775 |
Token | Youth |
Token ID | 17582 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
psychiat | +4.225 |
harassing | +3.982 |
nesota | +3.935 |
ieft | +3.925 |
olkien | +3.841 |
Neg logit contributions | |
iatus | -5.168 |
AST | -4.422 |
maj | -4.408 |
代 | -4.289 |
� | -4.164 |
Token | and |
Token ID | 290 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
psychiat | +2.306 |
nesota | +2.193 |
ieft | +2.191 |
olkien | +2.164 |
harassing | +2.162 |
Neg logit contributions | |
iatus | -2.615 |
AST | -2.232 |
maj | -2.226 |
代 | -2.151 |
Ast | -2.138 |
Token | Ad |
Token ID | 1215 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
psychiat | +2.885 |
ieft | +2.763 |
olkien | +2.747 |
nesota | +2.732 |
harassing | +2.714 |
Neg logit contributions | |
iatus | -3.497 |
maj | -3.072 |
AST | -3.002 |
代 | -2.937 |
HQ | -2.821 |
Token | olesc |
Token ID | 16850 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
psychiat | +1.307 |
nesota | +1.266 |
ieft | +1.264 |
olkien | +1.237 |
harassing | +1.221 |
Neg logit contributions | |
iatus | -1.731 |
AST | -1.515 |
maj | -1.506 |
代 | -1.448 |
Toast | -1.425 |
Token | ence |
Token ID | 594 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
psychiat | +2.450 |
nesota | +2.374 |
ieft | +2.347 |
olkien | +2.307 |
harassing | +2.296 |
Neg logit contributions | |
iatus | -3.422 |
AST | -3.014 |
maj | -3.001 |
代 | -2.896 |
Ast | -2.890 |
Token | : |
Token ID | 25 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
iatus | +0.482 |
AST | +0.415 |
maj | +0.414 |
Ast | +0.399 |
代 | +0.396 |
Neg logit contributions | |
psychiat | -0.426 |
nesota | -0.409 |
ieft | -0.406 |
olkien | -0.403 |
harassing | -0.401 |
Token | 10 |
Token ID | 838 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
psychiat | +1.222 |
nesota | +1.173 |
ieft | +1.164 |
harassing | +1.155 |
olkien | +1.154 |
Neg logit contributions | |
iatus | -1.195 |
maj | -1.007 |
AST | -1.006 |
代 | -0.967 |
Ast | -0.961 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
iatus | +0.310 |
AST | +0.265 |
maj | +0.265 |
Ast | +0.255 |
代 | +0.253 |
Neg logit contributions | |
psychiat | -0.297 |
nesota | -0.285 |
ieft | -0.283 |
olkien | -0.281 |
harassing | -0.280 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
psychiat | +0.495 |
ieft | +0.483 |
nesota | +0.480 |
olkien | +0.473 |
harassing | +0.465 |
Neg logit contributions | |
iatus | -0.543 |
maj | -0.459 |
AST | -0.458 |
Ast | -0.440 |
Toast | -0.438 |
Token | 71 |
Token ID | 4869 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
nesota | +1.020 |
psychiat | +1.012 |
ieft | +0.995 |
olkien | +0.989 |
harassing | +0.963 |
Neg logit contributions | |
iatus | -1.414 |
AST | -1.251 |
maj | -1.234 |
Toast | -1.207 |
代 | -1.199 |
Token | / |
Token ID | 14 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
ieft | +1.941 |
nesota | +1.940 |
psychiat | +1.929 |
olkien | +1.912 |
harassing | +1.887 |
Neg logit contributions | |
iatus | -2.958 |
maj | -2.542 |
AST | -2.517 |
Toast | -2.454 |
代 | -2.416 |
Token | Z |
Token ID | 57 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
psychiat | +4.791 |
ieft | +4.654 |
nesota | +4.645 |
olkien | +4.580 |
harassing | +4.520 |
Neg logit contributions | |
iatus | -4.395 |
AST | -3.705 |
maj | -3.638 |
Toast | -3.529 |
Bulg | -3.521 |
Token | O |
Token ID | 46 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
psychiat | +2.419 |
ieft | +2.346 |
nesota | +2.323 |
olkien | +2.315 |
harassing | +2.281 |
Neg logit contributions | |
iatus | -2.216 |
maj | -1.861 |
AST | -1.844 |
代 | -1.785 |
Ast | -1.758 |
Token | 130 |
Token ID | 12952 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
psychiat | +1.047 |
nesota | +1.020 |
ieft | +1.019 |
olkien | +1.005 |
harassing | +0.990 |
Neg logit contributions | |
iatus | -0.922 |
maj | -0.777 |
AST | -0.764 |
Toast | -0.733 |
代 | -0.732 |
Token | 95 |
Token ID | 3865 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
psychiat | +0.319 |
nesota | +0.307 |
ieft | +0.306 |
olkien | +0.303 |
harassing | +0.300 |
Neg logit contributions | |
iatus | -0.373 |
maj | -0.321 |
AST | -0.321 |
Ast | -0.309 |
代 | -0.306 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
psychiat | +0.742 |
nesota | +0.707 |
ieft | +0.704 |
olkien | +0.697 |
harassing | +0.693 |
Neg logit contributions | |
iatus | -1.044 |
maj | -0.911 |
AST | -0.909 |
Ast | -0.879 |
代 | -0.873 |
Token | called |
Token ID | 1444 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
psychiat | +1.781 |
harassing | +1.705 |
nesota | +1.696 |
ieft | +1.684 |
olkien | +1.661 |
Neg logit contributions | |
iatus | -1.899 |
AST | -1.619 |
maj | -1.609 |
代 | -1.554 |
Ast | -1.550 |
Token | absurd |
Token ID | 12986 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
psychiat | +0.428 |
nesota | +0.410 |
ieft | +0.408 |
olkien | +0.404 |
harassing | +0.404 |
Neg logit contributions | |
iatus | -0.455 |
AST | -0.389 |
maj | -0.388 |
Ast | -0.374 |
代 | -0.371 |
Token | and |
Token ID | 290 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
psychiat | +1.883 |
nesota | +1.797 |
harassing | +1.787 |
ieft | +1.783 |
olkien | +1.771 |
Neg logit contributions | |
iatus | -2.084 |
AST | -1.788 |
maj | -1.784 |
Ast | -1.715 |
代 | -1.710 |
Token | fear |
Token ID | 3252 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
psychiat | +0.493 |
nesota | +0.469 |
ieft | +0.465 |
harassing | +0.461 |
olkien | +0.460 |
Neg logit contributions | |
iatus | -0.687 |
AST | -0.599 |
maj | -0.598 |
Ast | -0.579 |
代 | -0.576 |
Token | m |
Token ID | 285 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
psychiat | +1.747 |
harassing | +1.674 |
ieft | +1.663 |
nesota | +1.658 |
olkien | +1.644 |
Neg logit contributions | |
iatus | -1.495 |
AST | -1.236 |
maj | -1.225 |
代 | -1.186 |
Ast | -1.164 |
Token | ong |
Token ID | 506 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
psychiat | +0.751 |
ieft | +0.732 |
nesota | +0.730 |
olkien | +0.719 |
harassing | +0.713 |
Neg logit contributions | |
iatus | -0.850 |
maj | -0.730 |
AST | -0.728 |
代 | -0.702 |
Ast | -0.695 |
Token | ering |
Token ID | 1586 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
psychiat | +5.035 |
harassing | +4.877 |
nesota | +4.874 |
ieft | +4.814 |
olkien | +4.797 |
Neg logit contributions | |
iatus | -4.138 |
maj | -3.473 |
AST | -3.455 |
代 | -3.416 |
Toast | -3.294 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
psychiat | +0.132 |
nesota | +0.127 |
ieft | +0.126 |
olkien | +0.125 |
harassing | +0.123 |
Neg logit contributions | |
iatus | -0.145 |
maj | -0.125 |
AST | -0.125 |
Ast | -0.120 |
代 | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
psychiat | +0.083 |
nesota | +0.079 |
ieft | +0.079 |
olkien | +0.078 |
harassing | +0.078 |
Neg logit contributions | |
iatus | -0.104 |
maj | -0.090 |
AST | -0.090 |
Ast | -0.086 |
代 | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
psychiat | +0.085 |
nesota | +0.081 |
ieft | +0.081 |
olkien | +0.080 |
harassing | +0.080 |
Neg logit contributions | |
iatus | -0.113 |
AST | -0.098 |
maj | -0.098 |
Ast | -0.095 |
代 | -0.094 |
Token | The |
Token ID | 464 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
iatus | +0.456 |
AST | +0.390 |
maj | +0.390 |
Ast | +0.376 |
代 | +0.372 |
Neg logit contributions | |
psychiat | -0.423 |
nesota | -0.406 |
ieft | -0.404 |
olkien | -0.400 |
harassing | -0.398 |
Token | only |
Token ID | 691 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
iatus | +0.055 |
AST | +0.047 |
maj | +0.047 |
Ast | +0.046 |
代 | +0.046 |
Neg logit contributions | |
psychiat | -0.049 |
nesota | -0.047 |
ieft | -0.047 |
olkien | -0.046 |
harassing | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
iatus | +0.287 |
AST | +0.244 |
maj | +0.244 |
Ast | +0.234 |
代 | +0.232 |
Neg logit contributions | |
psychiat | -0.293 |
nesota | -0.281 |
ieft | -0.280 |
olkien | -0.277 |
harassing | -0.276 |
Token | Vim |
Token ID | 36645 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
psychiat | +0.718 |
nesota | +0.683 |
ieft | +0.680 |
harassing | +0.679 |
olkien | +0.673 |
Neg logit contributions | |
iatus | -0.758 |
AST | -0.641 |
maj | -0.638 |
代 | -0.622 |
Ast | -0.615 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
psychiat | +0.849 |
nesota | +0.811 |
ieft | +0.807 |
harassing | +0.806 |
olkien | +0.806 |
Neg logit contributions | |
iatus | -0.762 |
maj | -0.635 |
AST | -0.635 |
代 | -0.615 |
Ast | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
psychiat | +1.283 |
ieft | +1.222 |
nesota | +1.221 |
olkien | +1.220 |
harassing | +1.213 |
Neg logit contributions | |
iatus | -1.498 |
AST | -1.278 |
maj | -1.277 |
代 | -1.243 |
Ast | -1.242 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
psychiat | +0.208 |
nesota | +0.199 |
ieft | +0.198 |
olkien | +0.196 |
harassing | +0.195 |
Neg logit contributions | |
iatus | -0.251 |
AST | -0.217 |
maj | -0.216 |
Ast | -0.209 |
代 | -0.208 |
Token | and |
Token ID | 290 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
psychiat | +3.749 |
harassing | +3.538 |
olkien | +3.515 |
nesota | +3.487 |
ieft | +3.486 |
Neg logit contributions | |
iatus | -4.856 |
代 | -4.125 |
AST | -4.109 |
maj | -4.094 |
Ast | -3.992 |
Token | later |
Token ID | 1568 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
psychiat | +1.715 |
harassing | +1.627 |
nesota | +1.614 |
olkien | +1.604 |
ieft | +1.603 |
Neg logit contributions | |
iatus | -2.009 |
AST | -1.709 |
maj | -1.689 |
代 | -1.684 |
Ast | -1.635 |
Token | : |
Token ID | 25 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
psychiat | +2.207 |
harassing | +2.090 |
nesota | +2.077 |
ieft | +2.069 |
olkien | +2.055 |
Neg logit contributions | |
iatus | -2.701 |
AST | -2.302 |
maj | -2.286 |
代 | -2.280 |
Ast | -2.213 |
Token | /* |
Token ID | 11900 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
psychiat | +0.898 |
nesota | +0.857 |
ieft | +0.851 |
harassing | +0.845 |
olkien | +0.844 |
Neg logit contributions | |
iatus | -1.012 |
AST | -0.865 |
maj | -0.859 |
代 | -0.838 |
Ast | -0.831 |
Token | vim |
Token ID | 43907 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
psychiat | +1.474 |
nesota | +1.411 |
ieft | +1.395 |
harassing | +1.384 |
olkien | +1.384 |
Neg logit contributions | |
iatus | -1.721 |
AST | -1.484 |
maj | -1.460 |
代 | -1.436 |
Ast | -1.417 |
Token | to |
Token ID | 284 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
psychiat | +0.911 |
ieft | +0.866 |
nesota | +0.864 |
harassing | +0.855 |
olkien | +0.852 |
Neg logit contributions | |
iatus | -1.116 |
AST | -0.963 |
maj | -0.961 |
Ast | -0.932 |
代 | -0.925 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
iatus | +0.555 |
AST | +0.468 |
maj | +0.468 |
Ast | +0.449 |
代 | +0.445 |
Neg logit contributions | |
psychiat | -0.607 |
nesota | -0.584 |
ieft | -0.581 |
olkien | -0.576 |
harassing | -0.574 |
Token | lined |
Token ID | 16566 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
psychiat | +0.262 |
nesota | +0.252 |
ieft | +0.251 |
olkien | +0.249 |
harassing | +0.247 |
Neg logit contributions | |
iatus | -0.256 |
AST | -0.217 |
maj | -0.217 |
Ast | -0.209 |
代 | -0.207 |
Token | structural |
Token ID | 13204 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
psychiat | +1.070 |
nesota | +1.022 |
ieft | +1.020 |
harassing | +1.017 |
olkien | +1.004 |
Neg logit contributions | |
iatus | -1.142 |
maj | -0.969 |
AST | -0.964 |
Ast | -0.936 |
代 | -0.936 |
Token | fill |
Token ID | 6070 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
psychiat | +0.839 |
nesota | +0.796 |
ieft | +0.790 |
harassing | +0.781 |
olkien | +0.778 |
Neg logit contributions | |
iatus | -1.366 |
AST | -1.194 |
maj | -1.192 |
Ast | -1.158 |
代 | -1.156 |
Token | solution |
Token ID | 4610 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
psychiat | +2.156 |
nesota | +2.067 |
ieft | +2.065 |
olkien | +2.046 |
harassing | +2.044 |
Neg logit contributions | |
iatus | -1.773 |
maj | -1.468 |
AST | -1.460 |
Ast | -1.405 |
代 | -1.401 |
Token | while |
Token ID | 981 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
psychiat | +3.657 |
ieft | +3.451 |
harassing | +3.447 |
nesota | +3.439 |
olkien | +3.413 |
Neg logit contributions | |
iatus | -5.014 |
maj | -4.294 |
AST | -4.265 |
Toast | -4.161 |
代 | -4.142 |
Token | continuing |
Token ID | 8282 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
iatus | +0.683 |
AST | +0.590 |
maj | +0.590 |
Ast | +0.568 |
代 | +0.558 |
Neg logit contributions | |
psychiat | -0.633 |
nesota | -0.610 |
ieft | -0.606 |
olkien | -0.603 |
harassing | -0.593 |
Token | to |
Token ID | 284 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
iatus | +0.095 |
maj | +0.081 |
AST | +0.081 |
Ast | +0.078 |
代 | +0.078 |
Neg logit contributions | |
psychiat | -0.089 |
nesota | -0.085 |
ieft | -0.085 |
harassing | -0.084 |
olkien | -0.084 |
Token | search |
Token ID | 2989 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
psychiat | +0.062 |
nesota | +0.059 |
ieft | +0.059 |
olkien | +0.059 |
harassing | +0.059 |
Neg logit contributions | |
iatus | -0.066 |
AST | -0.056 |
maj | -0.056 |
Ast | -0.054 |
代 | -0.054 |
Token | for |
Token ID | 329 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
iatus | +0.213 |
maj | +0.178 |
AST | +0.178 |
Ast | +0.171 |
代 | +0.170 |
Neg logit contributions | |
psychiat | -0.240 |
nesota | -0.231 |
ieft | -0.230 |
harassing | -0.228 |
olkien | -0.228 |
Token | States |
Token ID | 1829 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
psychiat | +0.362 |
nesota | +0.345 |
ieft | +0.343 |
olkien | +0.341 |
harassing | +0.337 |
Neg logit contributions | |
iatus | -0.472 |
AST | -0.413 |
maj | -0.412 |
Ast | -0.400 |
代 | -0.393 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
psychiat | +0.111 |
nesota | +0.107 |
ieft | +0.106 |
olkien | +0.105 |
harassing | +0.105 |
Neg logit contributions | |
iatus | -0.125 |
AST | -0.108 |
maj | -0.108 |
Ast | -0.104 |
代 | -0.103 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
psychiat | +0.818 |
nesota | +0.783 |
ieft | +0.779 |
harassing | +0.770 |
olkien | +0.770 |
Neg logit contributions | |
iatus | -0.851 |
AST | -0.724 |
maj | -0.723 |
Ast | -0.695 |
代 | -0.692 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
psychiat | +0.427 |
nesota | +0.406 |
ieft | +0.404 |
olkien | +0.399 |
harassing | +0.397 |
Neg logit contributions | |
iatus | -0.623 |
AST | -0.545 |
maj | -0.545 |
Ast | -0.528 |
代 | -0.524 |
Token | Pres |
Token ID | 1763 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
psychiat | +1.383 |
nesota | +1.326 |
ieft | +1.315 |
olkien | +1.294 |
harassing | +1.293 |
Neg logit contributions | |
iatus | -1.861 |
maj | -1.614 |
AST | -1.605 |
Ast | -1.548 |
代 | -1.547 |
Token | ented |
Token ID | 4714 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
psychiat | +0.006 |
nesota | +0.006 |
ieft | +0.006 |
olkien | +0.006 |
harassing | +0.006 |
Neg logit contributions | |
iatus | -0.004 |
maj | -0.003 |
AST | -0.003 |
Ast | -0.003 |
代 | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
psychiat | +3.823 |
nesota | +3.539 |
ieft | +3.510 |
harassing | +3.502 |
olkien | +3.436 |
Neg logit contributions | |
iatus | -4.848 |
AST | -4.100 |
maj | -4.077 |
代 | -3.958 |
Ast | -3.950 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
psychiat | +1.344 |
nesota | +1.288 |
ieft | +1.277 |
harassing | +1.264 |
olkien | +1.261 |
Neg logit contributions | |
iatus | -1.439 |
maj | -1.225 |
AST | -1.215 |
代 | -1.173 |
Ast | -1.170 |
Token | 57 |
Token ID | 7632 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
psychiat | +1.530 |
nesota | +1.461 |
ieft | +1.452 |
olkien | +1.434 |
harassing | +1.434 |
Neg logit contributions | |
iatus | -1.782 |
maj | -1.529 |
AST | -1.521 |
代 | -1.467 |
Ast | -1.464 |
Token | th |
Token ID | 400 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
psychiat | +1.687 |
nesota | +1.628 |
ieft | +1.623 |
olkien | +1.602 |
harassing | +1.600 |
Neg logit contributions | |
iatus | -1.344 |
maj | -1.112 |
AST | -1.112 |
Ast | -1.054 |
代 | -1.046 |
Token | Annual |
Token ID | 16328 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
psychiat | +0.776 |
nesota | +0.734 |
ieft | +0.727 |
harassing | +0.717 |
olkien | +0.716 |
Neg logit contributions | |
iatus | -1.311 |
maj | -1.149 |
AST | -1.145 |
代 | -1.108 |
Ast | -1.108 |
Token | t |
Token ID | 83 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
iatus | +0.312 |
AST | +0.261 |
maj | +0.261 |
Ast | +0.250 |
代 | +0.247 |
Neg logit contributions | |
psychiat | -0.373 |
nesota | -0.359 |
ieft | -0.357 |
olkien | -0.355 |
harassing | -0.353 |
Token | work |
Token ID | 670 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
iatus | +1.182 |
AST | +1.002 |
maj | +1.001 |
Ast | +0.961 |
代 | +0.951 |
Neg logit contributions | |
psychiat | -1.263 |
nesota | -1.215 |
ieft | -1.209 |
olkien | -1.199 |
harassing | -1.193 |
Token | is |
Token ID | 318 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
iatus | +0.238 |
AST | +0.201 |
maj | +0.201 |
代 | +0.194 |
Ast | +0.194 |
Neg logit contributions | |
psychiat | -0.237 |
nesota | -0.227 |
ieft | -0.226 |
harassing | -0.224 |
olkien | -0.223 |
Token | because |
Token ID | 780 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
psychiat | +0.710 |
nesota | +0.679 |
ieft | +0.676 |
harassing | +0.670 |
olkien | +0.667 |
Neg logit contributions | |
iatus | -0.788 |
maj | -0.670 |
AST | -0.667 |
代 | -0.646 |
Ast | -0.645 |
Token | a |
Token ID | 257 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
psychiat | +0.531 |
nesota | +0.507 |
ieft | +0.506 |
harassing | +0.502 |
olkien | +0.500 |
Neg logit contributions | |
iatus | -0.584 |
maj | -0.498 |
AST | -0.496 |
代 | -0.477 |
Ast | -0.477 |
Token | ) |
Token ID | 8 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
psychiat | +0.296 |
nesota | +0.283 |
ieft | +0.281 |
olkien | +0.279 |
harassing | +0.277 |
Neg logit contributions | |
iatus | -0.363 |
AST | -0.315 |
maj | -0.315 |
Ast | -0.304 |
代 | -0.301 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
psychiat | +3.902 |
harassing | +3.792 |
ieft | +3.735 |
nesota | +3.669 |
olkien | +3.630 |
Neg logit contributions | |
iatus | -4.658 |
maj | -3.911 |
AST | -3.866 |
代 | -3.804 |
Ast | -3.650 |
Token | mouse |
Token ID | 10211 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
iatus | +0.361 |
AST | +0.317 |
maj | +0.316 |
Ast | +0.306 |
代 | +0.300 |
Neg logit contributions | |
psychiat | -0.280 |
nesota | -0.269 |
ieft | -0.266 |
olkien | -0.265 |
harassing | -0.261 |
Token | would |
Token ID | 561 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
psychiat | +0.286 |
nesota | +0.274 |
ieft | +0.273 |
olkien | +0.270 |
harassing | +0.270 |
Neg logit contributions | |
iatus | -0.324 |
AST | -0.278 |
maj | -0.277 |
Ast | -0.267 |
代 | -0.266 |
Token | be |
Token ID | 307 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
psychiat | +0.226 |
nesota | +0.216 |
ieft | +0.216 |
olkien | +0.213 |
harassing | +0.213 |
Neg logit contributions | |
iatus | -0.247 |
AST | -0.211 |
maj | -0.211 |
Ast | -0.204 |
代 | -0.202 |
Token | locked |
Token ID | 8970 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
psychiat | +0.342 |
nesota | +0.327 |
ieft | +0.326 |
harassing | +0.325 |
olkien | +0.323 |
Neg logit contributions | |
iatus | -0.333 |
AST | -0.281 |
maj | -0.280 |
Ast | -0.269 |
代 | -0.269 |
Token | Beck |
Token ID | 11739 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
iatus | +0.002 |
AST | +0.002 |
maj | +0.002 |
Ast | +0.001 |
代 | +0.001 |
Neg logit contributions | |
psychiat | -0.001 |
nesota | -0.001 |
ieft | -0.001 |
olkien | -0.001 |
harassing | -0.001 |
Token | Depression |
Token ID | 22483 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
psychiat | +0.822 |
nesota | +0.783 |
ieft | +0.783 |
harassing | +0.774 |
olkien | +0.773 |
Neg logit contributions | |
iatus | -0.848 |
maj | -0.724 |
AST | -0.720 |
Ast | -0.692 |
代 | -0.687 |
Token | Inventory |
Token ID | 35772 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
iatus | +0.126 |
AST | +0.105 |
maj | +0.104 |
Ast | +0.101 |
代 | +0.098 |
Neg logit contributions | |
psychiat | -0.169 |
nesota | -0.164 |
ieft | -0.163 |
olkien | -0.162 |
harassing | -0.161 |
Token | . |
Token ID | 764 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
iatus | +0.257 |
AST | +0.223 |
maj | +0.223 |
Ast | +0.216 |
代 | +0.213 |
Neg logit contributions | |
psychiat | -0.219 |
nesota | -0.211 |
ieft | -0.210 |
olkien | -0.208 |
harassing | -0.206 |
Token | Journal |
Token ID | 4913 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
psychiat | +2.311 |
nesota | +2.216 |
ieft | +2.199 |
harassing | +2.167 |
olkien | +2.163 |
Neg logit contributions | |
iatus | -2.708 |
maj | -2.317 |
AST | -2.290 |
代 | -2.196 |
Ast | -2.187 |
Token | of |
Token ID | 286 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
psychiat | +0.848 |
nesota | +0.818 |
ieft | +0.812 |
olkien | +0.803 |
harassing | +0.800 |
Neg logit contributions | |
iatus | -0.967 |
AST | -0.829 |
maj | -0.828 |
Ast | -0.796 |
代 | -0.793 |
Token | Consulting |
Token ID | 41005 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
psychiat | +3.776 |
harassing | +3.513 |
nesota | +3.512 |
ieft | +3.491 |
olkien | +3.452 |
Neg logit contributions | |
iatus | -4.833 |
AST | -4.166 |
maj | -4.156 |
代 | -4.024 |
� | -3.945 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
psychiat | +1.891 |
ieft | +1.792 |
nesota | +1.790 |
olkien | +1.774 |
harassing | +1.768 |
Neg logit contributions | |
iatus | -2.435 |
AST | -2.118 |
maj | -2.099 |
代 | -2.022 |
Toast | -1.999 |
Token | Clinical |
Token ID | 21234 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
psychiat | +3.034 |
ieft | +2.855 |
nesota | +2.852 |
olkien | +2.851 |
harassing | +2.848 |
Neg logit contributions | |
iatus | -4.090 |
maj | -3.504 |
AST | -3.484 |
代 | -3.370 |
Toast | -3.349 |
Token | Psychology |
Token ID | 18430 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
psychiat | +2.606 |
nesota | +2.471 |
ieft | +2.463 |
harassing | +2.448 |
olkien | +2.406 |
Neg logit contributions | |
iatus | -3.594 |
AST | -3.109 |
代 | -3.077 |
maj | -3.042 |
Toast | -2.871 |
Token | , |
Token ID | 11 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
psychiat | +1.030 |
nesota | +0.989 |
ieft | +0.983 |
olkien | +0.972 |
harassing | +0.964 |
Neg logit contributions | |
iatus | -1.205 |
maj | -1.040 |
AST | -1.035 |
代 | -0.992 |
Ast | -0.990 |
Token | . |
Token ID | 764 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
iatus | +1.134 |
maj | +0.976 |
AST | +0.976 |
Ast | +0.939 |
代 | +0.928 |
Neg logit contributions | |
psychiat | -1.051 |
nesota | -1.015 |
ieft | -1.006 |
olkien | -1.000 |
harassing | -0.990 |
Token | British |
Token ID | 3517 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
psychiat | +1.569 |
nesota | +1.508 |
ieft | +1.500 |
olkien | +1.480 |
harassing | +1.476 |
Neg logit contributions | |
iatus | -1.821 |
maj | -1.561 |
AST | -1.560 |
Ast | -1.498 |
代 | -1.491 |
Token | Journal |
Token ID | 4913 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
psychiat | +0.597 |
nesota | +0.570 |
ieft | +0.569 |
olkien | +0.562 |
harassing | +0.561 |
Neg logit contributions | |
iatus | -0.645 |
AST | -0.551 |
maj | -0.551 |
Ast | -0.529 |
代 | -0.526 |
Token | of |
Token ID | 286 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
psychiat | +1.341 |
nesota | +1.305 |
ieft | +1.290 |
harassing | +1.274 |
olkien | +1.262 |
Neg logit contributions | |
iatus | -1.703 |
AST | -1.453 |
maj | -1.448 |
代 | -1.402 |
Ast | -1.380 |
Token | Development |
Token ID | 7712 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
psychiat | +3.552 |
harassing | +3.306 |
ieft | +3.304 |
nesota | +3.266 |
olkien | +3.261 |
Neg logit contributions | |
iatus | -4.240 |
AST | -3.645 |
maj | -3.627 |
代 | -3.578 |
� | -3.430 |
Token | al |
Token ID | 282 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
psychiat | +2.521 |
nesota | +2.409 |
ieft | +2.398 |
olkien | +2.358 |
harassing | +2.354 |
Neg logit contributions | |
iatus | -3.091 |
maj | -2.672 |
AST | -2.670 |
代 | -2.571 |
Ast | -2.535 |
Token | Psychology |
Token ID | 18430 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
psychiat | +4.098 |
nesota | +3.863 |
ieft | +3.849 |
harassing | +3.816 |
olkien | +3.775 |
Neg logit contributions | |
iatus | -4.503 |
AST | -3.837 |
maj | -3.820 |
代 | -3.688 |
� | -3.568 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
psychiat | +0.826 |
nesota | +0.792 |
ieft | +0.787 |
olkien | +0.779 |
harassing | +0.775 |
Neg logit contributions | |
iatus | -0.948 |
maj | -0.817 |
AST | -0.813 |
Ast | -0.780 |
代 | -0.780 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
psychiat | +2.167 |
nesota | +2.077 |
ieft | +2.069 |
harassing | +2.045 |
olkien | +2.028 |
Neg logit contributions | |
iatus | -2.799 |
maj | -2.395 |
AST | -2.376 |
代 | -2.324 |
Ast | -2.281 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
psychiat | +1.786 |
nesota | +1.710 |
ieft | +1.702 |
olkien | +1.677 |
harassing | +1.661 |
Neg logit contributions | |
iatus | -2.185 |
maj | -1.894 |
AST | -1.888 |
Ast | -1.808 |
Toast | -1.796 |
Token | 259 |
Token ID | 37831 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
psychiat | +1.488 |
nesota | +1.423 |
ieft | +1.420 |
olkien | +1.404 |
harassing | +1.402 |
Neg logit contributions | |
iatus | -1.620 |
maj | -1.375 |
AST | -1.372 |
代 | -1.323 |
Ast | -1.321 |
Token | not |
Token ID | 1662 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
psychiat | +0.947 |
nesota | +0.912 |
ieft | +0.907 |
olkien | +0.900 |
harassing | +0.896 |
Neg logit contributions | |
iatus | -0.861 |
AST | -0.727 |
maj | -0.726 |
Ast | -0.697 |
代 | -0.690 |
Token | ch |
Token ID | 354 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
psychiat | +2.421 |
nesota | +2.349 |
ieft | +2.346 |
harassing | +2.306 |
olkien | +2.303 |
Neg logit contributions | |
iatus | -3.070 |
maj | -2.634 |
AST | -2.630 |
Ast | -2.535 |
代 | -2.525 |
Token | rating |
Token ID | 7955 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
iatus | +0.591 |
AST | +0.514 |
maj | +0.513 |
Ast | +0.495 |
Toast | +0.483 |
Neg logit contributions | |
psychiat | -0.548 |
nesota | -0.529 |
olkien | -0.523 |
ieft | -0.523 |
harassing | -0.512 |
Token | in |
Token ID | 287 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
iatus | +0.352 |
AST | +0.304 |
maj | +0.304 |
Ast | +0.292 |
代 | +0.287 |
Neg logit contributions | |
psychiat | -0.342 |
nesota | -0.329 |
ieft | -0.328 |
olkien | -0.326 |
harassing | -0.322 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
psychiat | +1.269 |
nesota | +1.214 |
ieft | +1.208 |
harassing | +1.199 |
olkien | +1.197 |
Neg logit contributions | |
iatus | -1.401 |
maj | -1.196 |
AST | -1.192 |
代 | -1.151 |
Ast | -1.142 |
Token | event |
Token ID | 1785 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
psychiat | +1.149 |
nesota | +1.095 |
ieft | +1.089 |
harassing | +1.080 |
olkien | +1.077 |
Neg logit contributions | |
iatus | -1.380 |
maj | -1.188 |
AST | -1.187 |
代 | -1.141 |
Ast | -1.141 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
psychiat | +3.613 |
nesota | +3.480 |
ieft | +3.467 |
harassing | +3.431 |
olkien | +3.308 |
Neg logit contributions | |
iatus | -4.857 |
AST | -4.120 |
maj | -4.069 |
代 | -4.029 |
Toast | -3.997 |
Token | a |
Token ID | 257 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
psychiat | +0.798 |
nesota | +0.766 |
ieft | +0.765 |
harassing | +0.761 |
olkien | +0.752 |
Neg logit contributions | |
iatus | -0.814 |
AST | -0.693 |
maj | -0.688 |
代 | -0.670 |
Ast | -0.661 |
Token | default |
Token ID | 4277 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
iatus | +0.282 |
maj | +0.247 |
AST | +0.247 |
Ast | +0.239 |
代 | +0.236 |
Neg logit contributions | |
psychiat | -0.197 |
nesota | -0.188 |
ieft | -0.187 |
olkien | -0.185 |
harassing | -0.183 |
Token | but |
Token ID | 475 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
iatus | +0.891 |
maj | +0.766 |
AST | +0.765 |
Ast | +0.737 |
代 | +0.729 |
Neg logit contributions | |
psychiat | -0.830 |
nesota | -0.797 |
ieft | -0.792 |
olkien | -0.785 |
harassing | -0.780 |
Token | not |
Token ID | 407 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
iatus | +0.328 |
AST | +0.283 |
maj | +0.283 |
Ast | +0.273 |
代 | +0.270 |
Neg logit contributions | |
psychiat | -0.277 |
nesota | -0.265 |
ieft | -0.264 |
olkien | -0.262 |
harassing | -0.260 |
Token | / |
Token ID | 14 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
psychiat | +0.179 |
nesota | +0.175 |
ieft | +0.174 |
olkien | +0.172 |
harassing | +0.171 |
Neg logit contributions | |
iatus | -0.239 |
AST | -0.206 |
maj | -0.206 |
代 | -0.199 |
Ast | -0.199 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
psychiat | +1.991 |
nesota | +1.930 |
ieft | +1.901 |
olkien | +1.892 |
harassing | +1.864 |
Neg logit contributions | |
iatus | -2.363 |
AST | -2.033 |
maj | -2.021 |
Toast | -1.947 |
Ast | -1.943 |
Token | . |
Token ID | 13 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
psychiat | +0.935 |
nesota | +0.914 |
ieft | +0.912 |
olkien | +0.900 |
harassing | +0.889 |
Neg logit contributions | |
iatus | -1.117 |
maj | -0.951 |
AST | -0.951 |
Ast | -0.911 |
代 | -0.908 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
psychiat | +0.005 |
ieft | +0.005 |
nesota | +0.005 |
olkien | +0.005 |
harassing | +0.005 |
Neg logit contributions | |
iatus | -0.006 |
AST | -0.005 |
maj | -0.005 |
代 | -0.005 |
Toast | -0.005 |
Token | 71 |
Token ID | 4869 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
psychiat | +0.976 |
nesota | +0.929 |
ieft | +0.924 |
olkien | +0.911 |
harassing | +0.910 |
Neg logit contributions | |
iatus | -1.437 |
AST | -1.264 |
maj | -1.263 |
Ast | -1.224 |
代 | -1.210 |
Token | / |
Token ID | 14 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
psychiat | +1.810 |
nesota | +1.789 |
ieft | +1.780 |
olkien | +1.756 |
harassing | +1.754 |
Neg logit contributions | |
iatus | -2.599 |
maj | -2.237 |
AST | -2.233 |
Toast | -2.167 |
Ast | -2.146 |
Token | journal |
Token ID | 24891 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
psychiat | +4.225 |
nesota | +3.996 |
harassing | +3.950 |
ieft | +3.940 |
olkien | +3.929 |
Neg logit contributions | |
iatus | -4.322 |
AST | -3.642 |
maj | -3.589 |
Bulg | -3.434 |
Toast | -3.419 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ieft | +2.403 |
nesota | +2.378 |
olkien | +2.310 |
psychiat | +2.307 |
harassing | +2.253 |
Neg logit contributions | |
iatus | -3.284 |
AST | -2.815 |
maj | -2.797 |
代 | -2.713 |
Toast | -2.713 |
Token | p |
Token ID | 79 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
psychiat | +0.927 |
nesota | +0.896 |
ieft | +0.890 |
olkien | +0.889 |
harassing | +0.841 |
Neg logit contributions | |
iatus | -1.305 |
AST | -1.159 |
maj | -1.131 |
Toast | -1.118 |
Ast | -1.108 |
Token | one |
Token ID | 505 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
nesota | +2.960 |
psychiat | +2.907 |
olkien | +2.894 |
ieft | +2.854 |
uman | +2.755 |
Neg logit contributions | |
iatus | -2.138 |
AST | -1.892 |
Toast | -1.843 |
代 | -1.815 |
Bulg | -1.763 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
psychiat | +1.444 |
ieft | +1.438 |
nesota | +1.432 |
olkien | +1.416 |
harassing | +1.386 |
Neg logit contributions | |
iatus | -1.868 |
AST | -1.604 |
maj | -1.596 |
代 | -1.533 |
Ast | -1.531 |
Token | � |
Token ID | 447 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
psychiat | +1.022 |
ieft | +0.978 |
nesota | +0.974 |
harassing | +0.968 |
olkien | +0.965 |
Neg logit contributions | |
iatus | -1.135 |
AST | -0.969 |
maj | -0.962 |
Ast | -0.929 |
代 | -0.924 |
Token | � |
Token ID | 247 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
psychiat | +0.819 |
nesota | +0.780 |
ieft | +0.775 |
harassing | +0.758 |
olkien | +0.756 |
Neg logit contributions | |
iatus | -1.704 |
AST | -1.520 |
maj | -1.513 |
Ast | -1.476 |
代 | -1.462 |
Token | s |
Token ID | 82 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
psychiat | +1.638 |
ieft | +1.587 |
nesota | +1.579 |
harassing | +1.564 |
olkien | +1.561 |
Neg logit contributions | |
iatus | -1.587 |
AST | -1.333 |
maj | -1.331 |
Ast | -1.277 |
代 | -1.261 |
Token | built |
Token ID | 3170 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
psychiat | +1.229 |
ieft | +1.179 |
nesota | +1.178 |
harassing | +1.167 |
olkien | +1.166 |
Neg logit contributions | |
iatus | -1.413 |
AST | -1.210 |
maj | -1.201 |
Ast | -1.161 |
代 | -1.160 |
Token | - |
Token ID | 12 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
psychiat | +2.171 |
ieft | +2.080 |
nesota | +2.056 |
olkien | +2.031 |
harassing | +2.028 |
Neg logit contributions | |
iatus | -2.715 |
maj | -2.297 |
AST | -2.283 |
代 | -2.231 |
Ast | -2.213 |
Token | in |
Token ID | 259 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
psychiat | +1.825 |
ieft | +1.824 |
nesota | +1.806 |
olkien | +1.766 |
harassing | +1.765 |
Neg logit contributions | |
iatus | -1.910 |
AST | -1.599 |
maj | -1.594 |
Ast | -1.537 |
Toast | -1.528 |
Token | browser |
Token ID | 6444 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
psychiat | +3.456 |
harassing | +3.254 |
ieft | +3.232 |
nesota | +3.213 |
olkien | +3.198 |
Neg logit contributions | |
iatus | -4.905 |
AST | -4.152 |
maj | -4.144 |
代 | -4.067 |
Ast | -3.983 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
psychiat | +0.903 |
ieft | +0.865 |
nesota | +0.862 |
olkien | +0.858 |
harassing | +0.854 |
Neg logit contributions | |
iatus | -1.041 |
AST | -0.887 |
maj | -0.886 |
Ast | -0.855 |
代 | -0.850 |
Token | and |
Token ID | 290 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
psychiat | +0.975 |
ieft | +0.934 |
nesota | +0.932 |
harassing | +0.929 |
olkien | +0.927 |
Neg logit contributions | |
iatus | -0.926 |
AST | -0.770 |
maj | -0.768 |
代 | -0.739 |
Ast | -0.737 |
Token | if |
Token ID | 611 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
psychiat | +1.303 |
ieft | +1.245 |
nesota | +1.244 |
harassing | +1.232 |
olkien | +1.231 |
Neg logit contributions | |
iatus | -1.414 |
AST | -1.193 |
maj | -1.189 |
代 | -1.148 |
Ast | -1.144 |
Token | you |
Token ID | 345 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
psychiat | +1.114 |
nesota | +1.066 |
ieft | +1.063 |
harassing | +1.059 |
olkien | +1.059 |
Neg logit contributions | |
iatus | -1.249 |
maj | -1.050 |
AST | -1.049 |
代 | -1.005 |
Ast | -1.003 |
Token | upper |
Token ID | 6727 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
iatus | +0.591 |
AST | +0.503 |
maj | +0.502 |
Ast | +0.482 |
代 | +0.481 |
Neg logit contributions | |
psychiat | -0.564 |
nesota | -0.541 |
ieft | -0.539 |
harassing | -0.534 |
olkien | -0.533 |
Token | right |
Token ID | 826 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
iatus | +0.960 |
AST | +0.825 |
maj | +0.825 |
Ast | +0.795 |
代 | +0.787 |
Neg logit contributions | |
psychiat | -0.872 |
nesota | -0.836 |
ieft | -0.831 |
olkien | -0.824 |
harassing | -0.819 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
iatus | +2.265 |
maj | +1.946 |
AST | +1.941 |
Ast | +1.873 |
代 | +1.839 |
Neg logit contributions | |
psychiat | -2.279 |
nesota | -2.200 |
ieft | -2.186 |
olkien | -2.181 |
harassing | -2.150 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
psychiat | +0.277 |
nesota | +0.264 |
ieft | +0.263 |
olkien | +0.260 |
harassing | +0.259 |
Neg logit contributions | |
iatus | -0.366 |
AST | -0.318 |
maj | -0.318 |
Ast | -0.308 |
代 | -0.305 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
psychiat | +1.183 |
nesota | +1.154 |
ieft | +1.148 |
olkien | +1.127 |
harassing | +1.126 |
Neg logit contributions | |
iatus | -1.760 |
AST | -1.526 |
maj | -1.526 |
代 | -1.474 |
Ast | -1.471 |
Token | Like |
Token ID | 7594 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
psychiat | +1.618 |
nesota | +1.563 |
ieft | +1.561 |
olkien | +1.540 |
harassing | +1.525 |
Neg logit contributions | |
iatus | -1.773 |
AST | -1.540 |
maj | -1.525 |
Ast | -1.469 |
代 | -1.451 |
Token | this |
Token ID | 428 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
psychiat | +3.265 |
harassing | +3.025 |
nesota | +3.009 |
ieft | +2.993 |
olkien | +2.952 |
Neg logit contributions | |
iatus | -5.036 |
AST | -4.374 |
maj | -4.340 |
代 | -4.258 |
Toast | -4.126 |
Token | : |
Token ID | 25 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
iatus | +0.925 |
AST | +0.793 |
maj | +0.792 |
Ast | +0.762 |
代 | +0.756 |
Neg logit contributions | |
psychiat | -0.864 |
nesota | -0.829 |
ieft | -0.825 |
olkien | -0.818 |
harassing | -0.814 |
Token | Like |
Token ID | 4525 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
iatus | +1.851 |
maj | +1.503 |
AST | +1.498 |
Ast | +1.480 |
Toast | +1.419 |
Neg logit contributions | |
psychiat | -2.949 |
ieft | -2.825 |
nesota | -2.817 |
olkien | -2.757 |
harassing | -2.749 |
Token | Loading |
Token ID | 12320 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
psychiat | +0.903 |
nesota | +0.871 |
ieft | +0.862 |
olkien | +0.855 |
harassing | +0.843 |
Neg logit contributions | |
iatus | -1.064 |
AST | -0.923 |
maj | -0.922 |
Ast | -0.899 |
Toast | -0.880 |
Token | ... |
Token ID | 986 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
iatus | +0.876 |
AST | +0.671 |
maj | +0.671 |
Ast | +0.635 |
Toast | +0.606 |
Neg logit contributions | |
psychiat | -1.998 |
nesota | -1.935 |
ieft | -1.935 |
olkien | -1.926 |
harassing | -1.909 |
Token | Society |
Token ID | 7023 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
iatus | +1.007 |
AST | +0.887 |
maj | +0.884 |
Ast | +0.864 |
代 | +0.849 |
Neg logit contributions | |
psychiat | -0.652 |
nesota | -0.620 |
ieft | -0.617 |
olkien | -0.612 |
harassing | -0.603 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
iatus | +0.547 |
AST | +0.473 |
maj | +0.472 |
Ast | +0.457 |
代 | +0.452 |
Neg logit contributions | |
psychiat | -0.457 |
nesota | -0.438 |
ieft | -0.436 |
olkien | -0.432 |
harassing | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
psychiat | +0.221 |
nesota | +0.212 |
ieft | +0.211 |
olkien | +0.208 |
harassing | +0.207 |
Neg logit contributions | |
iatus | -0.299 |
maj | -0.260 |
AST | -0.259 |
Ast | -0.250 |
代 | -0.250 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
iatus | +0.119 |
AST | +0.104 |
maj | +0.104 |
Ast | +0.101 |
代 | +0.099 |
Neg logit contributions | |
psychiat | -0.094 |
nesota | -0.089 |
ieft | -0.088 |
olkien | -0.087 |
harassing | -0.087 |
Token | B |
Token ID | 33 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iatus | +0.537 |
AST | +0.465 |
maj | +0.464 |
Ast | +0.450 |
代 | +0.445 |
Neg logit contributions | |
psychiat | -0.434 |
nesota | -0.415 |
ieft | -0.412 |
olkien | -0.409 |
harassing | -0.407 |
Token | art |
Token ID | 433 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
psychiat | +1.103 |
ieft | +1.068 |
nesota | +1.060 |
olkien | +1.056 |
harassing | +1.035 |
Neg logit contributions | |
iatus | -1.057 |
maj | -0.905 |
AST | -0.897 |
Ast | -0.860 |
代 | -0.855 |
Token | had |
Token ID | 550 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
psychiat | +3.730 |
ieft | +3.483 |
nesota | +3.481 |
harassing | +3.469 |
olkien | +3.430 |
Neg logit contributions | |
iatus | -4.474 |
AST | -3.880 |
maj | -3.864 |
代 | -3.758 |
� | -3.692 |
Token | surgery |
Token ID | 8185 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
psychiat | +0.378 |
nesota | +0.361 |
ieft | +0.358 |
harassing | +0.355 |
olkien | +0.354 |
Neg logit contributions | |
iatus | -0.452 |
AST | -0.389 |
maj | -0.388 |
Ast | -0.374 |
代 | -0.374 |
Token | on |
Token ID | 319 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
psychiat | +0.017 |
nesota | +0.016 |
ieft | +0.016 |
olkien | +0.016 |
harassing | +0.016 |
Neg logit contributions | |
iatus | -0.018 |
AST | -0.015 |
maj | -0.015 |
Ast | -0.015 |
代 | -0.015 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
iatus | +0.135 |
AST | +0.116 |
maj | +0.116 |
Ast | +0.111 |
代 | +0.111 |
Neg logit contributions | |
psychiat | -0.125 |
nesota | -0.120 |
ieft | -0.119 |
olkien | -0.118 |
harassing | -0.118 |
Token | night |
Token ID | 1755 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
psychiat | +0.086 |
nesota | +0.082 |
ieft | +0.081 |
harassing | +0.081 |
olkien | +0.081 |
Neg logit contributions | |
iatus | -0.096 |
AST | -0.082 |
maj | -0.082 |
Ast | -0.079 |
代 | -0.079 |
Token | last |
Token ID | 938 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
iatus | +0.052 |
AST | +0.045 |
maj | +0.045 |
Ast | +0.043 |
代 | +0.043 |
Neg logit contributions | |
psychiat | -0.044 |
nesota | -0.043 |
ieft | -0.042 |
olkien | -0.042 |
harassing | -0.042 |
Token | month |
Token ID | 1227 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
iatus | +1.151 |
AST | +0.974 |
maj | +0.973 |
Ast | +0.937 |
代 | +0.917 |
Neg logit contributions | |
psychiat | -1.291 |
nesota | -1.250 |
ieft | -1.245 |
olkien | -1.238 |
harassing | -1.225 |
Token | in |
Token ID | 287 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
iatus | +1.765 |
AST | +1.530 |
maj | +1.523 |
Ast | +1.484 |
代 | +1.454 |
Neg logit contributions | |
psychiat | -1.727 |
nesota | -1.680 |
ieft | -1.667 |
olkien | -1.653 |
harassing | -1.642 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
iatus | +0.008 |
maj | +0.007 |
AST | +0.007 |
代 | +0.007 |
Ast | +0.007 |
Neg logit contributions | |
psychiat | -0.008 |
nesota | -0.007 |
ieft | -0.007 |
harassing | -0.007 |
olkien | -0.007 |
Token | Proceedings |
Token ID | 30641 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
psychiat | +0.572 |
nesota | +0.542 |
ieft | +0.537 |
harassing | +0.533 |
olkien | +0.528 |
Neg logit contributions | |
iatus | -0.772 |
maj | -0.667 |
AST | -0.666 |
代 | -0.642 |
Ast | -0.637 |
Token | of |
Token ID | 286 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
psychiat | +1.982 |
nesota | +1.929 |
ieft | +1.907 |
harassing | +1.882 |
olkien | +1.868 |
Neg logit contributions | |
iatus | -2.610 |
maj | -2.198 |
AST | -2.186 |
代 | -2.118 |
Toast | -2.079 |
Token | the |
Token ID | 262 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
psychiat | +3.592 |
nesota | +3.332 |
harassing | +3.307 |
ieft | +3.264 |
olkien | +3.216 |
Neg logit contributions | |
iatus | -4.690 |
maj | -3.937 |
AST | -3.877 |
代 | -3.864 |
� | -3.704 |
Token | National |
Token ID | 2351 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
psychiat | +3.024 |
nesota | +2.849 |
ieft | +2.831 |
harassing | +2.826 |
olkien | +2.772 |
Neg logit contributions | |
iatus | -3.510 |
maj | -2.966 |
AST | -2.929 |
代 | -2.864 |
Toast | -2.768 |
Token | Academy |
Token ID | 8581 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
psychiat | +2.686 |
nesota | +2.575 |
ieft | +2.570 |
harassing | +2.549 |
olkien | +2.512 |
Neg logit contributions | |
iatus | -2.024 |
AST | -1.623 |
maj | -1.623 |
代 | -1.535 |
Toast | -1.493 |
Token | of |
Token ID | 286 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
psychiat | +0.584 |
nesota | +0.561 |
ieft | +0.558 |
olkien | +0.552 |
harassing | +0.550 |
Neg logit contributions | |
iatus | -0.659 |
AST | -0.564 |
maj | -0.564 |
Ast | -0.543 |
代 | -0.540 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
psychiat | +1.373 |
nesota | +1.317 |
ieft | +1.288 |
harassing | +1.276 |
olkien | +1.263 |
Neg logit contributions | |
iatus | -1.971 |
maj | -1.720 |
AST | -1.707 |
代 | -1.671 |
Toast | -1.633 |
Token | all |
Token ID | 477 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
psychiat | +0.832 |
nesota | +0.792 |
ieft | +0.791 |
olkien | +0.784 |
harassing | +0.782 |
Neg logit contributions | |
iatus | -1.030 |
AST | -0.889 |
maj | -0.887 |
Ast | -0.855 |
代 | -0.852 |
Token | of |
Token ID | 286 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
psychiat | +1.396 |
nesota | +1.331 |
ieft | +1.330 |
harassing | +1.320 |
olkien | +1.316 |
Neg logit contributions | |
iatus | -1.627 |
AST | -1.391 |
maj | -1.386 |
代 | -1.331 |
Ast | -1.328 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
psychiat | +0.347 |
nesota | +0.332 |
ieft | +0.331 |
olkien | +0.328 |
harassing | +0.326 |
Neg logit contributions | |
iatus | -0.398 |
AST | -0.343 |
maj | -0.342 |
Ast | -0.330 |
代 | -0.327 |
Token | reasons |
Token ID | 3840 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
psychiat | +0.014 |
nesota | +0.013 |
ieft | +0.013 |
olkien | +0.013 |
harassing | +0.013 |
Neg logit contributions | |
iatus | -0.019 |
AST | -0.016 |
maj | -0.016 |
Ast | -0.016 |
代 | -0.015 |
Token | mentioned |
Token ID | 4750 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
iatus | +0.434 |
maj | +0.358 |
AST | +0.356 |
Ast | +0.340 |
代 | +0.333 |
Neg logit contributions | |
psychiat | -0.627 |
nesota | -0.609 |
ieft | -0.605 |
olkien | -0.600 |
harassing | -0.596 |
Token | above |
Token ID | 2029 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
psychiat | +3.326 |
olkien | +3.139 |
ieft | +3.121 |
harassing | +3.118 |
nesota | +3.098 |
Neg logit contributions | |
iatus | -4.189 |
AST | -3.610 |
maj | -3.557 |
代 | -3.479 |
Toast | -3.447 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
psychiat | +3.626 |
harassing | +3.480 |
ieft | +3.465 |
olkien | +3.438 |
nesota | +3.413 |
Neg logit contributions | |
iatus | -4.539 |
AST | -3.893 |
maj | -3.856 |
代 | -3.779 |
Toast | -3.756 |
Token | Israel |
Token ID | 2692 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
psychiat | +1.214 |
ieft | +1.153 |
harassing | +1.152 |
nesota | +1.151 |
olkien | +1.140 |
Neg logit contributions | |
iatus | -1.403 |
AST | -1.199 |
maj | -1.193 |
代 | -1.152 |
Ast | -1.143 |
Token | has |
Token ID | 468 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
psychiat | +1.717 |
ieft | +1.640 |
nesota | +1.629 |
harassing | +1.628 |
olkien | +1.624 |
Neg logit contributions | |
iatus | -1.659 |
AST | -1.406 |
maj | -1.391 |
Toast | -1.343 |
Ast | -1.339 |
Token | exhibited |
Token ID | 25212 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
psychiat | +0.159 |
nesota | +0.151 |
ieft | +0.151 |
harassing | +0.149 |
olkien | +0.149 |
Neg logit contributions | |
iatus | -0.183 |
AST | -0.157 |
maj | -0.156 |
Ast | -0.151 |
代 | -0.151 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
psychiat | +0.180 |
nesota | +0.173 |
ieft | +0.172 |
olkien | +0.171 |
harassing | +0.170 |
Neg logit contributions | |
iatus | -0.185 |
AST | -0.158 |
maj | -0.158 |
Ast | -0.152 |
代 | -0.150 |
Token | now |
Token ID | 783 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
iatus | +0.530 |
AST | +0.454 |
maj | +0.453 |
Ast | +0.437 |
代 | +0.432 |
Neg logit contributions | |
psychiat | -0.504 |
nesota | -0.484 |
ieft | -0.482 |
olkien | -0.477 |
harassing | -0.475 |
Token | published |
Token ID | 3199 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
iatus | +0.939 |
AST | +0.810 |
maj | +0.810 |
Ast | +0.781 |
代 | +0.774 |
Neg logit contributions | |
psychiat | -0.820 |
nesota | -0.787 |
ieft | -0.783 |
olkien | -0.776 |
harassing | -0.770 |
Token | in |
Token ID | 287 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
psychiat | +0.379 |
nesota | +0.361 |
ieft | +0.359 |
olkien | +0.355 |
harassing | +0.354 |
Neg logit contributions | |
iatus | -0.448 |
AST | -0.385 |
maj | -0.385 |
Ast | -0.370 |
代 | -0.368 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
psychiat | +1.044 |
ieft | +0.991 |
nesota | +0.990 |
harassing | +0.981 |
olkien | +0.971 |
Neg logit contributions | |
iatus | -1.131 |
maj | -0.962 |
AST | -0.953 |
代 | -0.922 |
Toast | -0.906 |
Token | Proceedings |
Token ID | 30641 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
psychiat | +0.815 |
nesota | +0.768 |
ieft | +0.767 |
harassing | +0.760 |
olkien | +0.752 |
Neg logit contributions | |
iatus | -1.059 |
maj | -0.913 |
AST | -0.912 |
代 | -0.877 |
Ast | -0.868 |
Token | of |
Token ID | 286 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
psychiat | +2.052 |
nesota | +1.993 |
ieft | +1.981 |
harassing | +1.947 |
olkien | +1.934 |
Neg logit contributions | |
iatus | -2.692 |
maj | -2.267 |
AST | -2.262 |
代 | -2.182 |
Toast | -2.152 |
Token | the |
Token ID | 262 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
psychiat | +3.590 |
ieft | +3.346 |
nesota | +3.324 |
harassing | +3.320 |
olkien | +3.245 |
Neg logit contributions | |
iatus | -4.587 |
maj | -3.889 |
AST | -3.830 |
代 | -3.790 |
� | -3.655 |
Token | National |
Token ID | 2351 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
psychiat | +3.251 |
ieft | +3.076 |
nesota | +3.051 |
harassing | +3.045 |
olkien | +2.982 |
Neg logit contributions | |
iatus | -3.829 |
maj | -3.249 |
AST | -3.212 |
代 | -3.140 |
Toast | -3.045 |
Token | Academy |
Token ID | 8581 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
psychiat | +2.532 |
ieft | +2.442 |
nesota | +2.438 |
harassing | +2.413 |
olkien | +2.394 |
Neg logit contributions | |
iatus | -1.833 |
maj | -1.482 |
AST | -1.481 |
代 | -1.407 |
Toast | -1.375 |
Token | of |
Token ID | 286 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
psychiat | +0.338 |
nesota | +0.324 |
ieft | +0.323 |
olkien | +0.319 |
harassing | +0.318 |
Neg logit contributions | |
iatus | -0.376 |
AST | -0.323 |
maj | -0.323 |
Ast | -0.311 |
代 | -0.308 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
psychiat | +1.422 |
nesota | +1.360 |
ieft | +1.351 |
olkien | +1.330 |
harassing | +1.330 |
Neg logit contributions | |
iatus | -1.918 |
maj | -1.669 |
AST | -1.664 |
代 | -1.607 |
Ast | -1.601 |
Token | forms |
Token ID | 23914 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
psychiat | +1.260 |
nesota | +1.216 |
ieft | +1.212 |
olkien | +1.196 |
harassing | +1.186 |
Neg logit contributions | |
iatus | -1.163 |
AST | -0.983 |
maj | -0.980 |
Ast | -0.938 |
代 | -0.929 |
Token | ') |
Token ID | 11537 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
psychiat | +1.019 |
nesota | +0.977 |
ieft | +0.974 |
olkien | +0.967 |
harassing | +0.955 |
Neg logit contributions | |
iatus | -1.181 |
maj | -1.021 |
AST | -1.013 |
Ast | -0.982 |
代 | -0.974 |
Token | | |
Token ID | 930 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
psychiat | +1.067 |
nesota | +1.027 |
ieft | +1.020 |
olkien | +1.013 |
harassing | +1.010 |
Neg logit contributions | |
iatus | -1.020 |
maj | -0.861 |
AST | -0.859 |
Ast | -0.824 |
代 | -0.824 |
Token | out |
Token ID | 503 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
iatus | +0.091 |
maj | +0.077 |
AST | +0.076 |
Ast | +0.073 |
代 | +0.073 |
Neg logit contributions | |
psychiat | -0.099 |
nesota | -0.095 |
ieft | -0.095 |
olkien | -0.094 |
harassing | -0.093 |
Token | - |
Token ID | 12 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
psychiat | +0.515 |
nesota | +0.503 |
ieft | +0.500 |
olkien | +0.493 |
harassing | +0.491 |
Neg logit contributions | |
iatus | -0.596 |
maj | -0.509 |
AST | -0.507 |
代 | -0.490 |
Ast | -0.488 |
Token | null |
Token ID | 8423 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
psychiat | +0.683 |
nesota | +0.658 |
ieft | +0.652 |
olkien | +0.643 |
harassing | +0.636 |
Neg logit contributions | |
iatus | -1.233 |
AST | -1.092 |
maj | -1.091 |
Ast | -1.059 |
代 | -1.052 |
Token | # |
Token ID | 1303 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
psychiat | +4.154 |
nesota | +3.967 |
harassing | +3.944 |
ieft | +3.927 |
olkien | +3.900 |
Neg logit contributions | |
iatus | -3.954 |
maj | -3.286 |
AST | -3.248 |
代 | -3.217 |
Ast | -3.115 |
Token | Draw |
Token ID | 15315 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
psychiat | +3.626 |
nesota | +3.449 |
ieft | +3.437 |
olkien | +3.427 |
harassing | +3.420 |
Neg logit contributions | |
iatus | -3.649 |
maj | -3.060 |
AST | -3.028 |
代 | -2.932 |
Ast | -2.898 |
Token | string |
Token ID | 4731 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
iatus | +1.330 |
AST | +1.152 |
maj | +1.146 |
Ast | +1.105 |
代 | +1.086 |
Neg logit contributions | |
psychiat | -1.288 |
nesota | -1.238 |
ieft | -1.233 |
olkien | -1.225 |
harassing | -1.205 |
Token | > |
Token ID | 1875 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
iatus | +0.944 |
AST | +0.816 |
maj | +0.812 |
Ast | +0.784 |
代 | +0.771 |
Neg logit contributions | |
psychiat | -0.884 |
nesota | -0.852 |
ieft | -0.848 |
olkien | -0.840 |
harassing | -0.830 |
Token | align |
Token ID | 10548 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
psychiat | +0.557 |
nesota | +0.535 |
ieft | +0.532 |
olkien | +0.527 |
harassing | +0.526 |
Neg logit contributions | |
iatus | -0.572 |
maj | -0.486 |
AST | -0.485 |
Ast | -0.467 |
代 | -0.464 |
Token | North |
Token ID | 2258 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
psychiat | +0.613 |
nesota | +0.585 |
ieft | +0.581 |
harassing | +0.576 |
olkien | +0.573 |
Neg logit contributions | |
iatus | -0.703 |
maj | -0.604 |
AST | -0.604 |
Ast | -0.581 |
代 | -0.579 |
Token | America |
Token ID | 2253 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
psychiat | +0.128 |
nesota | +0.123 |
ieft | +0.122 |
olkien | +0.121 |
harassing | +0.120 |
Neg logit contributions | |
iatus | -0.156 |
maj | -0.135 |
AST | -0.135 |
Ast | -0.130 |
代 | -0.129 |
Token | . |
Token ID | 764 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
psychiat | +1.655 |
nesota | +1.575 |
ieft | +1.564 |
harassing | +1.553 |
olkien | +1.546 |
Neg logit contributions | |
iatus | -1.943 |
maj | -1.674 |
AST | -1.668 |
Ast | -1.606 |
代 | -1.597 |
Token | International |
Token ID | 4037 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
psychiat | +2.142 |
nesota | +2.058 |
ieft | +2.045 |
harassing | +2.022 |
olkien | +1.997 |
Neg logit contributions | |
iatus | -2.544 |
maj | -2.175 |
AST | -2.150 |
代 | -2.064 |
Ast | -2.050 |
Token | Journal |
Token ID | 4913 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
iatus | +0.190 |
AST | +0.162 |
maj | +0.162 |
Ast | +0.156 |
代 | +0.155 |
Neg logit contributions | |
psychiat | -0.180 |
nesota | -0.173 |
ieft | -0.172 |
olkien | -0.171 |
harassing | -0.170 |
Token | of |
Token ID | 286 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
psychiat | +1.624 |
nesota | +1.566 |
ieft | +1.535 |
harassing | +1.526 |
olkien | +1.502 |
Neg logit contributions | |
iatus | -2.000 |
maj | -1.712 |
AST | -1.712 |
代 | -1.639 |
Ast | -1.632 |
Token | Public |
Token ID | 5094 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
psychiat | +3.585 |
harassing | +3.391 |
nesota | +3.354 |
ieft | +3.335 |
olkien | +3.244 |
Neg logit contributions | |
iatus | -4.617 |
maj | -3.952 |
AST | -3.938 |
代 | -3.855 |
� | -3.738 |
Token | Health |
Token ID | 3893 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
psychiat | +1.314 |
ieft | +1.229 |
nesota | +1.218 |
harassing | +1.204 |
olkien | +1.201 |
Neg logit contributions | |
iatus | -2.356 |
AST | -2.088 |
maj | -2.075 |
代 | -2.021 |
Ast | -2.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
psychiat | +1.918 |
nesota | +1.824 |
ieft | +1.806 |
harassing | +1.785 |
olkien | +1.774 |
Neg logit contributions | |
iatus | -2.316 |
maj | -2.018 |
AST | -2.011 |
代 | -1.933 |
Toast | -1.915 |
Token | 54 |
Token ID | 7175 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
psychiat | +2.246 |
nesota | +2.147 |
ieft | +2.132 |
harassing | +2.123 |
olkien | +2.091 |
Neg logit contributions | |
iatus | -2.730 |
maj | -2.323 |
AST | -2.299 |
代 | -2.253 |
Ast | -2.201 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
psychiat | +1.101 |
nesota | +1.055 |
ieft | +1.049 |
olkien | +1.034 |
harassing | +1.029 |
Neg logit contributions | |
iatus | -1.369 |
AST | -1.185 |
maj | -1.184 |
Ast | -1.139 |
代 | -1.125 |
Token | Donald |
Token ID | 3759 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
iatus | +0.369 |
maj | +0.329 |
AST | +0.329 |
Ast | +0.321 |
代 | +0.315 |
Neg logit contributions | |
psychiat | -0.178 |
nesota | -0.168 |
ieft | -0.167 |
olkien | -0.166 |
harassing | -0.161 |
Token | Trump |
Token ID | 1301 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
iatus | +0.687 |
AST | +0.602 |
maj | +0.599 |
Ast | +0.587 |
Toast | +0.569 |
Neg logit contributions | |
psychiat | -0.556 |
nesota | -0.521 |
ieft | -0.518 |
olkien | -0.516 |
harassing | -0.510 |
Token | Donald |
Token ID | 3759 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iatus | +0.905 |
maj | +0.813 |
AST | +0.813 |
Ast | +0.805 |
� | +0.773 |
Neg logit contributions | |
psychiat | -0.501 |
nesota | -0.483 |
ieft | -0.479 |
olkien | -0.477 |
harassing | -0.443 |
Token | John |
Token ID | 1757 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
iatus | +4.429 |
AST | +3.892 |
maj | +3.828 |
Ast | +3.785 |
Toast | +3.740 |
Neg logit contributions | |
psychiat | -4.407 |
olkien | -4.059 |
ieft | -3.969 |
nesota | -3.932 |
harassing | -3.920 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
iatus | +3.302 |
maj | +2.817 |
AST | +2.802 |
Ast | +2.794 |
Toast | +2.647 |
Neg logit contributions | |
psychiat | -3.022 |
olkien | -2.813 |
nesota | -2.778 |
ieft | -2.750 |
harassing | -2.688 |
Token | House |
Token ID | 18102 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
iatus | +3.835 |
maj | +3.258 |
AST | +3.245 |
Ast | +3.197 |
代 | +3.141 |
Neg logit contributions | |
psychiat | -3.542 |
nesota | -3.363 |
olkien | -3.319 |
harassing | -3.306 |
ieft | -3.293 |
Token | committee |
Token ID | 5583 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
iatus | +4.381 |
Ast | +3.888 |
maj | +3.862 |
AST | +3.815 |
Romance | +3.786 |
Neg logit contributions | |
psychiat | -3.539 |
olkien | -3.326 |
nesota | -3.181 |
ieft | -3.178 |
harassing | -3.138 |
Token | believes |
Token ID | 5804 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
iatus | +1.625 |
maj | +1.366 |
AST | +1.355 |
Ast | +1.313 |
代 | +1.279 |
Neg logit contributions | |
psychiat | -2.134 |
olkien | -2.066 |
nesota | -2.053 |
ieft | -2.050 |
harassing | -2.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
iatus | +0.517 |
maj | +0.460 |
AST | +0.459 |
Ast | +0.448 |
代 | +0.443 |
Neg logit contributions | |
psychiat | -0.296 |
ieft | -0.277 |
nesota | -0.276 |
olkien | -0.272 |
harassing | -0.267 |
Token | has |
Token ID | 468 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
iatus | +1.082 |
maj | +0.950 |
AST | +0.940 |
Ast | +0.916 |
代 | +0.902 |
Neg logit contributions | |
psychiat | -0.974 |
nesota | -0.917 |
olkien | -0.914 |
ieft | -0.913 |
harassing | -0.876 |
Token | evidence |
Token ID | 2370 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
iatus | +1.080 |
AST | +0.926 |
maj | +0.919 |
Ast | +0.887 |
代 | +0.886 |
Neg logit contributions | |
psychiat | -0.971 |
nesota | -0.941 |
ieft | -0.931 |
harassing | -0.924 |
olkien | -0.917 |
Token | It |
Token ID | 1026 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
psychiat | +0.513 |
nesota | +0.495 |
ieft | +0.495 |
olkien | +0.490 |
harassing | +0.484 |
Neg logit contributions | |
iatus | -0.521 |
AST | -0.446 |
maj | -0.444 |
Ast | -0.427 |
代 | -0.421 |
Token | doesn |
Token ID | 1595 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
iatus | +0.023 |
AST | +0.020 |
maj | +0.020 |
Ast | +0.019 |
代 | +0.019 |
Neg logit contributions | |
psychiat | -0.020 |
nesota | -0.019 |
ieft | -0.019 |
olkien | -0.019 |
harassing | -0.019 |
Token | � |
Token ID | 447 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
iatus | +0.878 |
AST | +0.752 |
maj | +0.751 |
Ast | +0.725 |
代 | +0.716 |
Neg logit contributions | |
psychiat | -0.910 |
nesota | -0.861 |
ieft | -0.856 |
olkien | -0.852 |
harassing | -0.850 |
Token | � |
Token ID | 247 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
psychiat | +0.496 |
nesota | +0.464 |
olkien | +0.463 |
ieft | +0.460 |
harassing | +0.456 |
Neg logit contributions | |
iatus | -0.605 |
maj | -0.529 |
AST | -0.525 |
Ast | -0.511 |
代 | -0.505 |
Token | t |
Token ID | 83 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
psychiat | +0.557 |
nesota | +0.538 |
ieft | +0.537 |
olkien | +0.531 |
harassing | +0.529 |
Neg logit contributions | |
iatus | -0.484 |
AST | -0.406 |
maj | -0.405 |
Ast | -0.389 |
代 | -0.384 |
Token | sound |
Token ID | 2128 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
psychiat | +0.055 |
nesota | +0.053 |
ieft | +0.053 |
olkien | +0.053 |
harassing | +0.053 |
Neg logit contributions | |
iatus | -0.049 |
AST | -0.041 |
maj | -0.041 |
Ast | -0.039 |
代 | -0.039 |
Token | like |
Token ID | 588 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
iatus | +3.363 |
maj | +2.945 |
AST | +2.914 |
Ast | +2.829 |
� | +2.748 |
Neg logit contributions | |
psychiat | -3.333 |
nesota | -3.301 |
ieft | -3.287 |
olkien | -3.252 |
harassing | -3.123 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
psychiat | +0.397 |
nesota | +0.380 |
ieft | +0.379 |
olkien | +0.376 |
harassing | +0.375 |
Neg logit contributions | |
iatus | -0.426 |
maj | -0.363 |
AST | -0.363 |
Ast | -0.349 |
代 | -0.349 |
Token | great |
Token ID | 1049 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
iatus | +1.460 |
maj | +1.265 |
AST | +1.256 |
Ast | +1.215 |
代 | +1.193 |
Neg logit contributions | |
psychiat | -1.287 |
nesota | -1.245 |
ieft | -1.231 |
olkien | -1.217 |
harassing | -1.204 |
Token | trade |
Token ID | 3292 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
psychiat | +0.038 |
nesota | +0.037 |
ieft | +0.037 |
olkien | +0.036 |
harassing | +0.036 |
Neg logit contributions | |
iatus | -0.046 |
AST | -0.040 |
maj | -0.039 |
Ast | -0.038 |
代 | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
psychiat | +2.434 |
ieft | +2.325 |
nesota | +2.311 |
olkien | +2.310 |
harassing | +2.294 |
Neg logit contributions | |
iatus | -2.597 |
maj | -2.213 |
AST | -2.206 |
代 | -2.148 |
Ast | -2.142 |
Token | [ |
Token ID | 685 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
psychiat | +2.475 |
nesota | +2.435 |
ieft | +2.425 |
harassing | +2.407 |
olkien | +2.383 |
Neg logit contributions | |
iatus | -1.964 |
maj | -1.620 |
AST | -1.576 |
代 | -1.527 |
Toast | -1.487 |
Token | Round |
Token ID | 22685 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
iatus | +3.056 |
Ast | +2.678 |
AST | +2.659 |
maj | +2.634 |
代 | +2.556 |
Neg logit contributions | |
psychiat | -2.956 |
olkien | -2.765 |
nesota | -2.764 |
harassing | -2.735 |
ieft | -2.731 |
Token | " |
Token ID | 366 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
iatus | +2.976 |
maj | +2.640 |
AST | +2.609 |
Ast | +2.525 |
代 | +2.469 |
Neg logit contributions | |
psychiat | -2.748 |
olkien | -2.569 |
ieft | -2.563 |
nesota | -2.553 |
harassing | -2.527 |
Token | 11 |
Token ID | 1157 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
iatus | +1.984 |
maj | +1.703 |
AST | +1.701 |
Ast | +1.645 |
代 | +1.630 |
Neg logit contributions | |
psychiat | -1.950 |
nesota | -1.866 |
ieft | -1.839 |
olkien | -1.838 |
harassing | -1.827 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
psychiat | +0.528 |
nesota | +0.507 |
ieft | +0.504 |
harassing | +0.501 |
olkien | +0.497 |
Neg logit contributions | |
iatus | -0.585 |
AST | -0.500 |
maj | -0.497 |
代 | -0.476 |
Ast | -0.475 |
Token | [ |
Token ID | 685 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
psychiat | +1.214 |
nesota | +1.195 |
ieft | +1.189 |
harassing | +1.179 |
olkien | +1.173 |
Neg logit contributions | |
iatus | -0.936 |
maj | -0.765 |
AST | -0.755 |
代 | -0.725 |
Ast | -0.714 |
Token | White |
Token ID | 12256 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
iatus | +2.914 |
AST | +2.485 |
maj | +2.484 |
Ast | +2.455 |
代 | +2.421 |
Neg logit contributions | |
psychiat | -3.390 |
nesota | -3.197 |
ieft | -3.190 |
olkien | -3.187 |
harassing | -3.148 |
Token | " |
Token ID | 366 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +2.041 |
maj | +1.808 |
AST | +1.774 |
Ast | +1.752 |
Toast | +1.711 |
Neg logit contributions | |
psychiat | -1.757 |
nesota | -1.662 |
ieft | -1.644 |
olkien | -1.641 |
harassing | -1.605 |
Token | Ab |
Token ID | 4826 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
iatus | +0.916 |
maj | +0.783 |
AST | +0.780 |
Ast | +0.755 |
代 | +0.746 |
Neg logit contributions | |
psychiat | -0.888 |
nesota | -0.853 |
ieft | -0.846 |
olkien | -0.840 |
harassing | -0.838 |
Token | as |
Token ID | 292 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
iatus | +0.097 |
AST | +0.084 |
maj | +0.084 |
Ast | +0.081 |
代 | +0.080 |
Neg logit contributions | |
psychiat | -0.082 |
nesota | -0.078 |
ieft | -0.078 |
olkien | -0.077 |
harassing | -0.077 |
Token | ov |
Token ID | 709 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
psychiat | +2.186 |
nesota | +2.109 |
ieft | +2.109 |
harassing | +2.073 |
olkien | +2.072 |
Neg logit contributions | |
iatus | -2.139 |
AST | -1.825 |
maj | -1.824 |
代 | -1.749 |
Ast | -1.733 |
Token | very |
Token ID | 845 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
iatus | +0.462 |
AST | +0.399 |
maj | +0.398 |
Ast | +0.385 |
代 | +0.377 |
Neg logit contributions | |
psychiat | -0.432 |
nesota | -0.415 |
ieft | -0.414 |
olkien | -0.411 |
harassing | -0.405 |
Token | good |
Token ID | 922 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
psychiat | +0.078 |
nesota | +0.074 |
ieft | +0.074 |
olkien | +0.073 |
harassing | +0.073 |
Neg logit contributions | |
iatus | -0.092 |
AST | -0.080 |
maj | -0.079 |
Ast | -0.077 |
代 | -0.076 |
Token | chances |
Token ID | 8395 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
psychiat | +0.307 |
nesota | +0.295 |
ieft | +0.294 |
olkien | +0.291 |
harassing | +0.290 |
Neg logit contributions | |
iatus | -0.314 |
AST | -0.268 |
maj | -0.268 |
Ast | -0.258 |
代 | -0.255 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
psychiat | +0.405 |
nesota | +0.388 |
ieft | +0.385 |
harassing | +0.383 |
olkien | +0.382 |
Neg logit contributions | |
iatus | -0.473 |
AST | -0.405 |
maj | -0.404 |
代 | -0.390 |
Ast | -0.390 |
Token | in |
Token ID | 287 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
psychiat | +0.178 |
nesota | +0.170 |
ieft | +0.170 |
olkien | +0.168 |
harassing | +0.167 |
Neg logit contributions | |
iatus | -0.193 |
AST | -0.165 |
maj | -0.165 |
Ast | -0.159 |
代 | -0.158 |
Token | international |
Token ID | 3230 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
psychiat | +1.186 |
nesota | +1.139 |
ieft | +1.132 |
olkien | +1.121 |
harassing | +1.118 |
Neg logit contributions | |
iatus | -1.279 |
AST | -1.094 |
maj | -1.094 |
Ast | -1.052 |
代 | -1.045 |
Token | football |
Token ID | 4346 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
iatus | +2.905 |
maj | +2.564 |
AST | +2.535 |
Ast | +2.476 |
Toast | +2.393 |
Neg logit contributions | |
psychiat | -2.828 |
ieft | -2.756 |
olkien | -2.744 |
nesota | -2.720 |
harassing | -2.646 |
Token | you |
Token ID | 345 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
iatus | +2.305 |
AST | +2.000 |
maj | +1.994 |
Ast | +1.933 |
Toast | +1.874 |
Neg logit contributions | |
psychiat | -2.298 |
nesota | -2.208 |
ieft | -2.206 |
olkien | -2.197 |
harassing | -2.154 |
Token | have |
Token ID | 423 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
iatus | +1.567 |
maj | +1.363 |
AST | +1.356 |
Ast | +1.307 |
代 | +1.280 |
Neg logit contributions | |
psychiat | -1.504 |
nesota | -1.441 |
ieft | -1.431 |
olkien | -1.422 |
harassing | -1.403 |
Token | to |
Token ID | 284 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
iatus | +1.493 |
AST | +1.290 |
maj | +1.287 |
Ast | +1.244 |
代 | +1.210 |
Neg logit contributions | |
psychiat | -1.523 |
nesota | -1.464 |
ieft | -1.461 |
olkien | -1.453 |
harassing | -1.429 |
Token | take |
Token ID | 1011 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
iatus | +0.207 |
AST | +0.177 |
maj | +0.177 |
Ast | +0.170 |
代 | +0.169 |
Neg logit contributions | |
psychiat | -0.193 |
nesota | -0.185 |
ieft | -0.185 |
olkien | -0.183 |
harassing | -0.182 |
Token | appeared |
Token ID | 4120 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
iatus | +0.167 |
AST | +0.142 |
maj | +0.141 |
Ast | +0.136 |
代 | +0.136 |
Neg logit contributions | |
psychiat | -0.167 |
nesota | -0.160 |
ieft | -0.159 |
olkien | -0.158 |
harassing | -0.158 |
Token | New |
Token ID | 968 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
iatus | +0.107 |
AST | +0.092 |
maj | +0.091 |
代 | +0.088 |
Ast | +0.088 |
Neg logit contributions | |
psychiat | -0.100 |
nesota | -0.095 |
ieft | -0.095 |
harassing | -0.094 |
olkien | -0.094 |
Token | Zealand |
Token ID | 8936 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
iatus | +1.068 |
AST | +0.965 |
maj | +0.964 |
Ast | +0.946 |
Toast | +0.935 |
Neg logit contributions | |
psychiat | -0.321 |
nesota | -0.289 |
ieft | -0.287 |
olkien | -0.284 |
harassing | -0.280 |
Token | 's |
Token ID | 338 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
iatus | +0.600 |
AST | +0.514 |
maj | +0.513 |
Ast | +0.495 |
代 | +0.491 |
Neg logit contributions | |
psychiat | -0.548 |
nesota | -0.526 |
ieft | -0.523 |
olkien | -0.518 |
harassing | -0.516 |
Token | love |
Token ID | 1842 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
iatus | +0.492 |
AST | +0.422 |
maj | +0.421 |
Ast | +0.406 |
代 | +0.405 |
Neg logit contributions | |
psychiat | -0.435 |
nesota | -0.416 |
ieft | -0.414 |
harassing | -0.409 |
olkien | -0.409 |
Token | affair |
Token ID | 14669 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
psychiat | +0.477 |
nesota | +0.460 |
ieft | +0.460 |
harassing | +0.456 |
olkien | +0.454 |
Neg logit contributions | |
iatus | -0.374 |
AST | -0.307 |
maj | -0.307 |
Ast | -0.293 |
代 | -0.293 |
Token | with |
Token ID | 351 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
iatus | +2.940 |
maj | +2.529 |
AST | +2.523 |
Ast | +2.440 |
代 | +2.406 |
Neg logit contributions | |
psychiat | -2.703 |
nesota | -2.597 |
ieft | -2.580 |
olkien | -2.563 |
harassing | -2.540 |
Token | cooking |
Token ID | 10801 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
iatus | +1.900 |
maj | +1.635 |
AST | +1.629 |
Ast | +1.575 |
Toast | +1.546 |
Neg logit contributions | |
psychiat | -1.876 |
nesota | -1.807 |
ieft | -1.803 |
olkien | -1.785 |
harassing | -1.763 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
iatus | +1.009 |
maj | +0.865 |
AST | +0.864 |
Ast | +0.832 |
代 | +0.820 |
Neg logit contributions | |
psychiat | -0.977 |
nesota | -0.942 |
ieft | -0.937 |
olkien | -0.928 |
harassing | -0.921 |
Token | was |
Token ID | 373 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
iatus | +1.266 |
maj | +1.087 |
AST | +1.084 |
Ast | +1.046 |
代 | +1.025 |
Neg logit contributions | |
psychiat | -1.230 |
nesota | -1.187 |
ieft | -1.182 |
olkien | -1.168 |
harassing | -1.157 |
Token | waning |
Token ID | 50073 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
iatus | +0.607 |
AST | +0.522 |
maj | +0.520 |
Ast | +0.503 |
代 | +0.500 |
Neg logit contributions | |
psychiat | -0.545 |
nesota | -0.521 |
ieft | -0.518 |
harassing | -0.513 |
olkien | -0.513 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
psychiat | +0.265 |
nesota | +0.254 |
ieft | +0.254 |
olkien | +0.252 |
harassing | +0.251 |
Neg logit contributions | |
iatus | -0.290 |
AST | -0.248 |
maj | -0.247 |
Ast | -0.238 |
代 | -0.238 |
Token | while |
Token ID | 981 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
iatus | +1.188 |
maj | +1.022 |
AST | +1.012 |
Ast | +0.982 |
代 | +0.947 |
Neg logit contributions | |
psychiat | -1.376 |
nesota | -1.333 |
ieft | -1.315 |
olkien | -1.311 |
harassing | -1.284 |
Token | Gand |
Token ID | 17727 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
iatus | +2.161 |
maj | +1.940 |
AST | +1.935 |
Ast | +1.906 |
Toast | +1.847 |
Neg logit contributions | |
psychiat | -1.316 |
nesota | -1.261 |
ieft | -1.233 |
olkien | -1.227 |
harassing | -1.174 |
Token | alf |
Token ID | 1604 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
iatus | +1.350 |
maj | +1.153 |
AST | +1.132 |
Ast | +1.103 |
� | +1.061 |
Neg logit contributions | |
psychiat | -1.726 |
nesota | -1.613 |
ieft | -1.595 |
harassing | -1.589 |
olkien | -1.586 |
Token | dep |
Token ID | 1207 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
iatus | +2.826 |
maj | +2.521 |
AST | +2.486 |
Ast | +2.433 |
� | +2.358 |
Neg logit contributions | |
psychiat | -2.276 |
olkien | -2.174 |
nesota | -2.173 |
ieft | -2.170 |
harassing | -2.075 |
Token | arts |
Token ID | 5889 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
iatus | +1.308 |
AST | +1.075 |
maj | +1.072 |
Ast | +1.031 |
代 | +1.007 |
Neg logit contributions | |
psychiat | -1.816 |
nesota | -1.742 |
harassing | -1.736 |
ieft | -1.733 |
olkien | -1.727 |
Token | to |
Token ID | 284 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
iatus | +0.982 |
maj | +0.857 |
AST | +0.852 |
Ast | +0.826 |
代 | +0.802 |
Neg logit contributions | |
psychiat | -0.965 |
nesota | -0.939 |
ieft | -0.925 |
olkien | -0.919 |
harassing | -0.902 |
Token | seek |
Token ID | 5380 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
iatus | +0.340 |
AST | +0.296 |
maj | +0.296 |
Ast | +0.287 |
代 | +0.280 |
Neg logit contributions | |
psychiat | -0.300 |
nesota | -0.288 |
ieft | -0.285 |
olkien | -0.283 |
harassing | -0.279 |
Token | help |
Token ID | 1037 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
psychiat | +0.493 |
nesota | +0.470 |
ieft | +0.465 |
olkien | +0.462 |
harassing | +0.457 |
Neg logit contributions | |
iatus | -0.624 |
maj | -0.545 |
AST | -0.545 |
Ast | -0.528 |
代 | -0.519 |
Token | from |
Token ID | 422 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
psychiat | +1.375 |
nesota | +1.318 |
ieft | +1.314 |
olkien | +1.303 |
harassing | +1.301 |
Neg logit contributions | |
iatus | -1.611 |
AST | -1.378 |
maj | -1.374 |
Ast | -1.322 |
代 | -1.318 |
Token | Tree |
Token ID | 12200 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
psychiat | +0.912 |
nesota | +0.872 |
ieft | +0.867 |
olkien | +0.859 |
harassing | +0.854 |
Neg logit contributions | |
iatus | -1.113 |
AST | -0.963 |
maj | -0.962 |
Ast | -0.929 |
代 | -0.921 |
Token | thank |
Token ID | 5875 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
psychiat | +0.350 |
nesota | +0.335 |
ieft | +0.334 |
harassing | +0.332 |
olkien | +0.329 |
Neg logit contributions | |
iatus | -0.377 |
AST | -0.319 |
maj | -0.316 |
代 | -0.309 |
Ast | -0.307 |
Token | you |
Token ID | 345 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
psychiat | +1.989 |
ieft | +1.912 |
harassing | +1.895 |
nesota | +1.891 |
olkien | +1.875 |
Neg logit contributions | |
iatus | -2.441 |
AST | -2.083 |
maj | -2.047 |
代 | -2.007 |
Ast | -1.979 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
psychiat | +0.065 |
nesota | +0.062 |
ieft | +0.062 |
harassing | +0.062 |
olkien | +0.062 |
Neg logit contributions | |
iatus | -0.073 |
AST | -0.062 |
maj | -0.061 |
代 | -0.059 |
Ast | -0.059 |
Token | � |
Token ID | 447 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
psychiat | +0.890 |
ieft | +0.863 |
nesota | +0.861 |
olkien | +0.853 |
harassing | +0.848 |
Neg logit contributions | |
iatus | -0.762 |
maj | -0.632 |
AST | -0.632 |
代 | -0.600 |
Ast | -0.597 |
Token | � |
Token ID | 251 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
iatus | +0.769 |
maj | +0.694 |
AST | +0.694 |
Ast | +0.679 |
代 | +0.674 |
Neg logit contributions | |
psychiat | -0.239 |
nesota | -0.219 |
ieft | -0.217 |
olkien | -0.212 |
harassing | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
psychiat | +1.480 |
ieft | +1.433 |
nesota | +1.426 |
olkien | +1.408 |
harassing | +1.403 |
Neg logit contributions | |
iatus | -2.052 |
maj | -1.770 |
AST | -1.766 |
代 | -1.706 |
Ast | -1.684 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
iatus | +0.032 |
AST | +0.028 |
maj | +0.028 |
Ast | +0.027 |
代 | +0.027 |
Neg logit contributions | |
psychiat | -0.025 |
nesota | -0.023 |
ieft | -0.023 |
olkien | -0.023 |
harassing | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
iatus | +0.349 |
AST | +0.305 |
maj | +0.304 |
Ast | +0.294 |
代 | +0.292 |
Neg logit contributions | |
psychiat | -0.246 |
nesota | -0.236 |
ieft | -0.235 |
olkien | -0.232 |
harassing | -0.230 |
Token | Gentle |
Token ID | 25066 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
psychiat | +1.223 |
ieft | +1.175 |
nesota | +1.172 |
harassing | +1.169 |
olkien | +1.155 |
Neg logit contributions | |
iatus | -1.375 |
AST | -1.163 |
maj | -1.156 |
代 | -1.124 |
Ast | -1.113 |
Token | men |
Token ID | 3653 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
psychiat | +0.523 |
ieft | +0.506 |
nesota | +0.505 |
olkien | +0.500 |
harassing | +0.499 |
Neg logit contributions | |
iatus | -0.506 |
AST | -0.426 |
maj | -0.424 |
代 | -0.407 |
Ast | -0.404 |
Token | � |
Token ID | 447 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
psychiat | +0.405 |
ieft | +0.387 |
nesota | +0.387 |
harassing | +0.383 |
olkien | +0.382 |
Neg logit contributions | |
iatus | -0.482 |
AST | -0.412 |
maj | -0.411 |
Ast | -0.396 |
代 | -0.395 |
Token | out |
Token ID | 503 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
psychiat | +1.120 |
ieft | +1.067 |
nesota | +1.066 |
harassing | +1.061 |
olkien | +1.056 |
Neg logit contributions | |
iatus | -1.289 |
AST | -1.098 |
maj | -1.091 |
代 | -1.061 |
Ast | -1.054 |
Token | there |
Token ID | 612 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
psychiat | +0.092 |
ieft | +0.088 |
nesota | +0.088 |
olkien | +0.087 |
harassing | +0.087 |
Neg logit contributions | |
iatus | -0.097 |
AST | -0.082 |
maj | -0.082 |
Ast | -0.079 |
代 | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
iatus | +0.891 |
maj | +0.760 |
AST | +0.760 |
Ast | +0.731 |
代 | +0.723 |
Neg logit contributions | |
psychiat | -0.878 |
nesota | -0.844 |
ieft | -0.840 |
olkien | -0.832 |
harassing | -0.827 |
Token | it |
Token ID | 340 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
iatus | +0.022 |
AST | +0.019 |
maj | +0.019 |
Ast | +0.018 |
代 | +0.018 |
Neg logit contributions | |
psychiat | -0.021 |
nesota | -0.020 |
ieft | -0.020 |
harassing | -0.019 |
olkien | -0.019 |
Token | could |
Token ID | 714 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
psychiat | +0.352 |
nesota | +0.338 |
ieft | +0.336 |
olkien | +0.333 |
harassing | +0.331 |
Neg logit contributions | |
iatus | -0.413 |
AST | -0.356 |
maj | -0.355 |
Ast | -0.343 |
代 | -0.340 |
Token | grow |
Token ID | 1663 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
iatus | +1.144 |
maj | +0.990 |
AST | +0.988 |
Ast | +0.950 |
代 | +0.937 |
Neg logit contributions | |
psychiat | -1.050 |
nesota | -1.005 |
ieft | -0.999 |
olkien | -0.990 |
harassing | -0.983 |
Token | pretty |
Token ID | 2495 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
iatus | +0.948 |
maj | +0.818 |
AST | +0.813 |
Ast | +0.784 |
代 | +0.771 |
Neg logit contributions | |
psychiat | -0.918 |
nesota | -0.886 |
ieft | -0.881 |
olkien | -0.874 |
harassing | -0.865 |
Token | rapidly |
Token ID | 8902 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
iatus | +0.577 |
maj | +0.505 |
AST | +0.502 |
Ast | +0.485 |
代 | +0.479 |
Neg logit contributions | |
psychiat | -0.461 |
nesota | -0.442 |
ieft | -0.439 |
olkien | -0.436 |
harassing | -0.431 |
Token | , |
Token ID | 11 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
iatus | +0.725 |
maj | +0.618 |
AST | +0.618 |
Ast | +0.594 |
代 | +0.587 |
Neg logit contributions | |
psychiat | -0.728 |
nesota | -0.701 |
ieft | -0.697 |
olkien | -0.691 |
harassing | -0.687 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
iatus | +0.382 |
maj | +0.329 |
AST | +0.329 |
Ast | +0.317 |
代 | +0.313 |
Neg logit contributions | |
psychiat | -0.357 |
nesota | -0.344 |
ieft | -0.342 |
olkien | -0.338 |
harassing | -0.336 |
Token | then |
Token ID | 788 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
iatus | +0.113 |
AST | +0.097 |
maj | +0.097 |
Ast | +0.093 |
代 | +0.093 |
Neg logit contributions | |
psychiat | -0.104 |
nesota | -0.100 |
ieft | -0.100 |
olkien | -0.099 |
harassing | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
iatus | +0.422 |
maj | +0.361 |
AST | +0.361 |
Ast | +0.348 |
代 | +0.344 |
Neg logit contributions | |
psychiat | -0.400 |
nesota | -0.384 |
ieft | -0.382 |
olkien | -0.379 |
harassing | -0.376 |
Token | in |
Token ID | 287 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
iatus | +0.574 |
maj | +0.496 |
AST | +0.494 |
Ast | +0.477 |
代 | +0.471 |
Neg logit contributions | |
psychiat | -0.515 |
nesota | -0.495 |
ieft | -0.493 |
olkien | -0.489 |
harassing | -0.481 |
Token | grid |
Token ID | 10706 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
iatus | +0.817 |
maj | +0.703 |
AST | +0.702 |
Ast | +0.677 |
代 | +0.670 |
Neg logit contributions | |
psychiat | -0.743 |
nesota | -0.712 |
ieft | -0.709 |
olkien | -0.703 |
harassing | -0.698 |
Token | lock |
Token ID | 5354 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iatus | +0.464 |
maj | +0.393 |
AST | +0.391 |
Ast | +0.376 |
代 | +0.368 |
Neg logit contributions | |
psychiat | -0.538 |
nesota | -0.519 |
ieft | -0.515 |
olkien | -0.513 |
harassing | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
iatus | +0.942 |
AST | +0.808 |
maj | +0.807 |
Ast | +0.778 |
代 | +0.771 |
Neg logit contributions | |
psychiat | -0.857 |
nesota | -0.821 |
ieft | -0.818 |
olkien | -0.810 |
harassing | -0.807 |
Token | they |
Token ID | 484 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
iatus | +0.050 |
AST | +0.043 |
maj | +0.043 |
Ast | +0.041 |
代 | +0.041 |
Neg logit contributions | |
psychiat | -0.047 |
nesota | -0.045 |
ieft | -0.045 |
harassing | -0.045 |
olkien | -0.045 |
Token | couldn |
Token ID | 3521 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
iatus | +0.727 |
AST | +0.620 |
maj | +0.619 |
Ast | +0.596 |
代 | +0.591 |
Neg logit contributions | |
psychiat | -0.705 |
nesota | -0.677 |
ieft | -0.674 |
olkien | -0.668 |
harassing | -0.665 |
Token | � |
Token ID | 447 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
iatus | +0.590 |
AST | +0.492 |
maj | +0.492 |
Ast | +0.470 |
代 | +0.465 |
Neg logit contributions | |
psychiat | -0.736 |
nesota | -0.709 |
ieft | -0.705 |
olkien | -0.700 |
harassing | -0.698 |
Token | � |
Token ID | 247 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
psychiat | +0.047 |
nesota | +0.044 |
olkien | +0.044 |
ieft | +0.043 |
harassing | +0.043 |
Neg logit contributions | |
iatus | -0.077 |
maj | -0.068 |
AST | -0.068 |
Ast | -0.066 |
代 | -0.065 |
Token | t |
Token ID | 83 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
iatus | +0.396 |
maj | +0.331 |
AST | +0.331 |
Ast | +0.317 |
代 | +0.314 |
Neg logit contributions | |
psychiat | -0.482 |
nesota | -0.463 |
ieft | -0.459 |
olkien | -0.457 |
harassing | -0.455 |
Token | reload |
Token ID | 18126 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
iatus | +0.806 |
AST | +0.690 |
maj | +0.690 |
Ast | +0.664 |
代 | +0.657 |
Neg logit contributions | |
psychiat | -0.768 |
nesota | -0.738 |
ieft | -0.734 |
olkien | -0.728 |
harassing | -0.723 |
Token | � |
Token ID | 447 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
psychiat | +1.160 |
nesota | +1.120 |
ieft | +1.117 |
olkien | +1.101 |
harassing | +1.100 |
Neg logit contributions | |
iatus | -1.195 |
AST | -1.015 |
maj | -1.013 |
Ast | -0.977 |
代 | -0.970 |
Token | � |
Token ID | 247 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
iatus | +0.021 |
maj | +0.018 |
AST | +0.018 |
Ast | +0.018 |
代 | +0.017 |
Neg logit contributions | |
psychiat | -0.012 |
nesota | -0.011 |
olkien | -0.011 |
ieft | -0.011 |
harassing | -0.011 |
Token | t |
Token ID | 83 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
iatus | +0.642 |
maj | +0.537 |
AST | +0.533 |
Ast | +0.512 |
代 | +0.506 |
Neg logit contributions | |
psychiat | -0.801 |
nesota | -0.770 |
ieft | -0.764 |
olkien | -0.761 |
harassing | -0.758 |
Token | wait |
Token ID | 4043 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
iatus | +0.615 |
AST | +0.525 |
maj | +0.525 |
Ast | +0.504 |
代 | +0.498 |
Neg logit contributions | |
psychiat | -0.615 |
nesota | -0.591 |
ieft | -0.588 |
olkien | -0.583 |
harassing | -0.579 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
iatus | +1.213 |
AST | +1.034 |
maj | +1.033 |
Ast | +0.994 |
代 | +0.984 |
Neg logit contributions | |
psychiat | -1.197 |
nesota | -1.150 |
ieft | -1.145 |
olkien | -1.135 |
harassing | -1.129 |
Token | get |
Token ID | 651 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
iatus | +1.109 |
AST | +0.949 |
maj | +0.947 |
Ast | +0.910 |
代 | +0.892 |
Neg logit contributions | |
psychiat | -1.209 |
nesota | -1.164 |
ieft | -1.160 |
olkien | -1.153 |
harassing | -1.138 |
Token | them |
Token ID | 606 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
iatus | +0.668 |
maj | +0.570 |
AST | +0.570 |
Ast | +0.549 |
Toast | +0.534 |
Neg logit contributions | |
psychiat | -0.763 |
ieft | -0.737 |
nesota | -0.737 |
olkien | -0.735 |
harassing | -0.721 |
Token | back |
Token ID | 736 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
psychiat | +0.778 |
nesota | +0.748 |
ieft | +0.743 |
harassing | +0.738 |
olkien | +0.734 |
Neg logit contributions | |
iatus | -0.684 |
AST | -0.571 |
maj | -0.569 |
代 | -0.546 |
Ast | -0.546 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
psychiat | +0.563 |
nesota | +0.540 |
ieft | +0.535 |
harassing | +0.533 |
olkien | +0.529 |
Neg logit contributions | |
iatus | -0.620 |
AST | -0.529 |
maj | -0.526 |
代 | -0.509 |
Ast | -0.507 |
Token |
|
Token ID | 198 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
psychiat | +0.495 |
nesota | +0.481 |
ieft | +0.476 |
olkien | +0.470 |
harassing | +0.468 |
Neg logit contributions | |
iatus | -0.591 |
maj | -0.510 |
AST | -0.505 |
代 | -0.488 |
Ast | -0.486 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
psychiat | +0.349 |
nesota | +0.335 |
ieft | +0.333 |
olkien | +0.329 |
harassing | +0.328 |
Neg logit contributions | |
iatus | -0.479 |
AST | -0.416 |
maj | -0.416 |
Ast | -0.402 |
代 | -0.400 |
Token | G |
Token ID | 38 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
psychiat | +1.207 |
nesota | +1.158 |
ieft | +1.153 |
olkien | +1.140 |
harassing | +1.136 |
Neg logit contributions | |
iatus | -1.565 |
maj | -1.356 |
AST | -1.354 |
Ast | -1.308 |
代 | -1.299 |
Token | ), |
Token ID | 828 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
psychiat | +1.084 |
olkien | +1.037 |
harassing | +1.036 |
ieft | +1.036 |
nesota | +1.029 |
Neg logit contributions | |
iatus | -1.254 |
maj | -1.065 |
AST | -1.052 |
代 | -1.021 |
Ast | -1.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
psychiat | +0.490 |
ieft | +0.469 |
nesota | +0.468 |
harassing | +0.466 |
olkien | +0.462 |
Neg logit contributions | |
iatus | -0.542 |
maj | -0.460 |
AST | -0.460 |
代 | -0.442 |
Ast | -0.441 |
Token | smooth |
Token ID | 7209 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
psychiat | +1.179 |
nesota | +1.129 |
ieft | +1.128 |
harassing | +1.123 |
olkien | +1.107 |
Neg logit contributions | |
iatus | -1.255 |
AST | -1.055 |
maj | -1.053 |
代 | -1.021 |
Ast | -1.011 |
Token | movement |
Token ID | 3356 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
iatus | +0.325 |
AST | +0.274 |
maj | +0.274 |
Ast | +0.263 |
代 | +0.262 |
Neg logit contributions | |
psychiat | -0.339 |
nesota | -0.326 |
ieft | -0.325 |
olkien | -0.322 |
harassing | -0.321 |
Token | thanks |
Token ID | 5176 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
psychiat | +0.596 |
nesota | +0.570 |
harassing | +0.569 |
ieft | +0.565 |
olkien | +0.559 |
Neg logit contributions | |
iatus | -0.668 |
AST | -0.562 |
maj | -0.560 |
代 | -0.544 |
Ast | -0.539 |
Token | to |
Token ID | 284 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
psychiat | +1.144 |
nesota | +1.106 |
ieft | +1.106 |
harassing | +1.094 |
olkien | +1.086 |
Neg logit contributions | |
iatus | -1.313 |
AST | -1.110 |
maj | -1.108 |
代 | -1.073 |
Ast | -1.065 |
Token | its |
Token ID | 663 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
psychiat | +0.393 |
nesota | +0.377 |
ieft | +0.377 |
harassing | +0.375 |
olkien | +0.372 |
Neg logit contributions | |
iatus | -0.414 |
maj | -0.349 |
AST | -0.347 |
代 | -0.336 |
Ast | -0.333 |
Token | increased |
Token ID | 3220 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
iatus | +0.827 |
AST | +0.717 |
maj | +0.715 |
Ast | +0.691 |
代 | +0.681 |
Neg logit contributions | |
psychiat | -0.724 |
nesota | -0.695 |
ieft | -0.690 |
olkien | -0.685 |
harassing | -0.678 |
Token | refresh |
Token ID | 14976 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
iatus | +0.645 |
maj | +0.553 |
AST | +0.553 |
Ast | +0.533 |
代 | +0.529 |
Neg logit contributions | |
psychiat | -0.575 |
nesota | -0.551 |
ieft | -0.549 |
olkien | -0.543 |
harassing | -0.541 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
iatus | +0.184 |
maj | +0.154 |
AST | +0.154 |
Ast | +0.148 |
代 | +0.146 |
Neg logit contributions | |
psychiat | -0.198 |
nesota | -0.191 |
ieft | -0.190 |
harassing | -0.188 |
olkien | -0.188 |
Token | devices |
Token ID | 4410 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
iatus | +0.374 |
AST | +0.327 |
maj | +0.326 |
Ast | +0.316 |
代 | +0.312 |
Neg logit contributions | |
psychiat | -0.291 |
nesota | -0.279 |
ieft | -0.278 |
olkien | -0.275 |
harassing | -0.272 |
Token | , |
Token ID | 11 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
iatus | +0.767 |
AST | +0.656 |
maj | +0.656 |
Ast | +0.631 |
代 | +0.625 |
Neg logit contributions | |
psychiat | -0.731 |
nesota | -0.702 |
ieft | -0.699 |
olkien | -0.692 |
harassing | -0.689 |
Token | I |
Token ID | 314 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
iatus | +0.249 |
AST | +0.211 |
maj | +0.211 |
Ast | +0.203 |
代 | +0.202 |
Neg logit contributions | |
psychiat | -0.250 |
nesota | -0.240 |
ieft | -0.239 |
olkien | -0.237 |
harassing | -0.236 |
Token | started |
Token ID | 2067 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
psychiat | +0.006 |
nesota | +0.006 |
ieft | +0.006 |
olkien | +0.006 |
harassing | +0.006 |
Neg logit contributions | |
iatus | -0.006 |
AST | -0.005 |
maj | -0.005 |
Ast | -0.005 |
代 | -0.005 |
Token | smoking |
Token ID | 9216 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
iatus | +0.364 |
AST | +0.314 |
maj | +0.314 |
Ast | +0.303 |
代 | +0.300 |
Neg logit contributions | |
psychiat | -0.316 |
nesota | -0.304 |
ieft | -0.302 |
olkien | -0.299 |
harassing | -0.297 |
Token | and |
Token ID | 290 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
psychiat | +1.442 |
nesota | +1.345 |
harassing | +1.338 |
ieft | +1.333 |
olkien | +1.322 |
Neg logit contributions | |
iatus | -1.999 |
AST | -1.717 |
maj | -1.706 |
代 | -1.665 |
Ast | -1.648 |
Token | I |
Token ID | 314 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
psychiat | +0.687 |
nesota | +0.652 |
ieft | +0.651 |
harassing | +0.650 |
olkien | +0.644 |
Neg logit contributions | |
iatus | -0.729 |
AST | -0.621 |
maj | -0.616 |
代 | -0.596 |
Ast | -0.591 |
Token | realized |
Token ID | 6939 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
psychiat | +0.245 |
nesota | +0.235 |
ieft | +0.235 |
olkien | +0.232 |
harassing | +0.232 |
Neg logit contributions | |
iatus | -0.259 |
AST | -0.221 |
maj | -0.219 |
Ast | -0.212 |
代 | -0.211 |
Token | cannabis |
Token ID | 9499 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
iatus | +1.129 |
maj | +0.976 |
AST | +0.974 |
Ast | +0.942 |
代 | +0.925 |
Neg logit contributions | |
psychiat | -1.037 |
nesota | -1.001 |
ieft | -0.995 |
olkien | -0.986 |
harassing | -0.975 |
Token | has |
Token ID | 468 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
psychiat | +0.442 |
nesota | +0.421 |
ieft | +0.420 |
harassing | +0.417 |
olkien | +0.416 |
Neg logit contributions | |
iatus | -0.458 |
AST | -0.387 |
maj | -0.386 |
代 | -0.371 |
Ast | -0.371 |
Token | an |
Token ID | 281 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
iatus | +0.089 |
AST | +0.077 |
maj | +0.077 |
Ast | +0.074 |
代 | +0.073 |
Neg logit contributions | |
psychiat | -0.079 |
nesota | -0.076 |
ieft | -0.076 |
olkien | -0.075 |
harassing | -0.074 |
Token | brand |
Token ID | 4508 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
iatus | +0.394 |
maj | +0.340 |
AST | +0.340 |
Ast | +0.328 |
代 | +0.324 |
Neg logit contributions | |
psychiat | -0.341 |
nesota | -0.327 |
ieft | -0.325 |
olkien | -0.322 |
harassing | -0.320 |
Token | names |
Token ID | 3891 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
iatus | +1.370 |
maj | +1.166 |
AST | +1.165 |
Ast | +1.122 |
代 | +1.107 |
Neg logit contributions | |
psychiat | -1.512 |
nesota | -1.457 |
ieft | -1.443 |
olkien | -1.440 |
harassing | -1.416 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
psychiat | +0.137 |
nesota | +0.131 |
ieft | +0.131 |
olkien | +0.130 |
harassing | +0.129 |
Neg logit contributions | |
iatus | -0.161 |
AST | -0.138 |
maj | -0.138 |
Ast | -0.133 |
代 | -0.132 |
Token | products |
Token ID | 3186 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
iatus | +0.098 |
AST | +0.084 |
maj | +0.084 |
Ast | +0.081 |
代 | +0.081 |
Neg logit contributions | |
psychiat | -0.084 |
nesota | -0.081 |
ieft | -0.080 |
olkien | -0.080 |
harassing | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
iatus | +0.937 |
maj | +0.810 |
AST | +0.807 |
Ast | +0.779 |
代 | +0.771 |
Neg logit contributions | |
psychiat | -0.840 |
nesota | -0.808 |
ieft | -0.802 |
olkien | -0.794 |
harassing | -0.787 |
Token | television |
Token ID | 5581 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
psychiat | +0.506 |
nesota | +0.485 |
ieft | +0.483 |
harassing | +0.477 |
olkien | +0.477 |
Neg logit contributions | |
iatus | -0.570 |
AST | -0.489 |
maj | -0.488 |
Ast | -0.471 |
代 | -0.468 |
Token | shows |
Token ID | 2523 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
psychiat | +0.151 |
nesota | +0.145 |
ieft | +0.144 |
olkien | +0.143 |
harassing | +0.143 |
Neg logit contributions | |
iatus | -0.147 |
AST | -0.125 |
maj | -0.125 |
Ast | -0.120 |
代 | -0.119 |
Token | that |
Token ID | 326 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
psychiat | +0.025 |
nesota | +0.024 |
ieft | +0.024 |
olkien | +0.024 |
harassing | +0.024 |
Neg logit contributions | |
iatus | -0.029 |
maj | -0.025 |
AST | -0.025 |
Ast | -0.024 |
代 | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
iatus | +0.679 |
maj | +0.588 |
AST | +0.585 |
Ast | +0.566 |
代 | +0.557 |
Neg logit contributions | |
psychiat | -0.623 |
nesota | -0.602 |
ieft | -0.597 |
olkien | -0.592 |
harassing | -0.584 |
Token | planned |
Token ID | 6027 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
iatus | +1.016 |
maj | +0.878 |
AST | +0.868 |
Ast | +0.837 |
代 | +0.823 |
Neg logit contributions | |
psychiat | -0.997 |
nesota | -0.965 |
ieft | -0.955 |
olkien | -0.947 |
harassing | -0.936 |
Token | to |
Token ID | 284 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
iatus | +0.975 |
maj | +0.835 |
AST | +0.834 |
Ast | +0.803 |
代 | +0.794 |
Neg logit contributions | |
psychiat | -0.955 |
nesota | -0.921 |
ieft | -0.915 |
olkien | -0.906 |
harassing | -0.900 |
Token | checked |
Token ID | 10667 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
psychiat | +0.845 |
nesota | +0.806 |
ieft | +0.803 |
olkien | +0.795 |
harassing | +0.793 |
Neg logit contributions | |
iatus | -1.043 |
AST | -0.899 |
maj | -0.899 |
Ast | -0.869 |
代 | -0.863 |
Token | for |
Token ID | 329 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
psychiat | +0.015 |
nesota | +0.015 |
ieft | +0.015 |
olkien | +0.014 |
harassing | +0.014 |
Neg logit contributions | |
iatus | -0.017 |
AST | -0.014 |
maj | -0.014 |
Ast | -0.014 |
代 | -0.014 |
Token | model |
Token ID | 2746 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
psychiat | +1.386 |
nesota | +1.333 |
harassing | +1.326 |
ieft | +1.315 |
olkien | +1.309 |
Neg logit contributions | |
iatus | -1.553 |
maj | -1.300 |
AST | -1.298 |
代 | -1.283 |
Ast | -1.258 |
Token | ines |
Token ID | 1127 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
iatus | +1.412 |
AST | +1.209 |
maj | +1.208 |
Ast | +1.162 |
代 | +1.149 |
Neg logit contributions | |
psychiat | -1.360 |
nesota | -1.306 |
ieft | -1.300 |
olkien | -1.288 |
harassing | -1.281 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
psychiat | +0.093 |
nesota | +0.090 |
ieft | +0.089 |
olkien | +0.089 |
harassing | +0.088 |
Neg logit contributions | |
iatus | -0.106 |
AST | -0.091 |
maj | -0.091 |
Ast | -0.088 |
代 | -0.087 |
Token | This |
Token ID | 770 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
iatus | +0.109 |
AST | +0.093 |
maj | +0.093 |
代 | +0.089 |
Ast | +0.089 |
Neg logit contributions | |
psychiat | -0.101 |
nesota | -0.097 |
ieft | -0.097 |
olkien | -0.096 |
harassing | -0.096 |
Token | is |
Token ID | 318 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
psychiat | +1.185 |
nesota | +1.128 |
harassing | +1.120 |
ieft | +1.117 |
olkien | +1.105 |
Neg logit contributions | |
iatus | -1.463 |
AST | -1.249 |
maj | -1.247 |
代 | -1.227 |
Ast | -1.206 |
Token | explained |
Token ID | 4893 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
psychiat | +0.022 |
nesota | +0.021 |
ieft | +0.021 |
olkien | +0.021 |
harassing | +0.021 |
Neg logit contributions | |
iatus | -0.025 |
AST | -0.022 |
maj | -0.022 |
Ast | -0.021 |
代 | -0.021 |
Token | here |
Token ID | 994 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
psychiat | +0.614 |
nesota | +0.582 |
ieft | +0.579 |
harassing | +0.575 |
olkien | +0.574 |
Neg logit contributions | |
iatus | -0.776 |
AST | -0.667 |
maj | -0.665 |
代 | -0.647 |
Ast | -0.644 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
psychiat | +0.637 |
nesota | +0.608 |
ieft | +0.607 |
olkien | +0.602 |
harassing | +0.601 |
Neg logit contributions | |
iatus | -0.708 |
maj | -0.605 |
AST | -0.604 |
Ast | -0.583 |
代 | -0.582 |
Token | * |
Token ID | 1635 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
iatus | +0.048 |
maj | +0.040 |
AST | +0.040 |
代 | +0.038 |
Ast | +0.038 |
Neg logit contributions | |
psychiat | -0.051 |
nesota | -0.049 |
ieft | -0.048 |
olkien | -0.048 |
harassing | -0.048 |
Token | comment |
Token ID | 2912 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
iatus | +0.255 |
AST | +0.217 |
maj | +0.216 |
Ast | +0.208 |
代 | +0.207 |
Neg logit contributions | |
psychiat | -0.238 |
nesota | -0.227 |
harassing | -0.226 |
ieft | -0.226 |
olkien | -0.224 |
Token | thread |
Token ID | 4704 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
psychiat | +0.182 |
nesota | +0.175 |
ieft | +0.174 |
harassing | +0.172 |
olkien | +0.172 |
Neg logit contributions | |
iatus | -0.205 |
maj | -0.176 |
AST | -0.176 |
Ast | -0.169 |
代 | -0.168 |
Token | within |
Token ID | 1626 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
iatus | +1.645 |
maj | +1.414 |
AST | +1.414 |
Ast | +1.363 |
代 | +1.349 |
Neg logit contributions | |
psychiat | -1.489 |
nesota | -1.429 |
ieft | -1.421 |
olkien | -1.407 |
harassing | -1.396 |
Token | a |
Token ID | 257 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
iatus | +1.115 |
maj | +0.948 |
AST | +0.948 |
Ast | +0.910 |
代 | +0.907 |
Neg logit contributions | |
psychiat | -1.099 |
nesota | -1.055 |
ieft | -1.049 |
harassing | -1.039 |
olkien | -1.038 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
iatus | +0.651 |
AST | +0.552 |
maj | +0.552 |
Ast | +0.531 |
代 | +0.527 |
Neg logit contributions | |
psychiat | -0.651 |
nesota | -0.623 |
ieft | -0.621 |
harassing | -0.617 |
olkien | -0.614 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
psychiat | +1.216 |
nesota | +1.177 |
ieft | +1.175 |
harassing | +1.170 |
olkien | +1.160 |
Neg logit contributions | |
iatus | -1.030 |
maj | -0.862 |
AST | -0.858 |
Ast | -0.821 |
代 | -0.821 |
Token | it |
Token ID | 340 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
psychiat | +0.222 |
nesota | +0.213 |
ieft | +0.213 |
harassing | +0.211 |
olkien | +0.211 |
Neg logit contributions | |
iatus | -0.231 |
AST | -0.196 |
maj | -0.196 |
Ast | -0.188 |
代 | -0.188 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
iatus | +0.177 |
maj | +0.153 |
AST | +0.152 |
Ast | +0.147 |
代 | +0.145 |
Neg logit contributions | |
psychiat | -0.161 |
nesota | -0.155 |
ieft | -0.154 |
olkien | -0.152 |
harassing | -0.151 |
Token | 't |
Token ID | 470 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
iatus | +0.120 |
AST | +0.102 |
maj | +0.102 |
Ast | +0.098 |
代 | +0.097 |
Neg logit contributions | |
psychiat | -0.116 |
nesota | -0.111 |
ieft | -0.111 |
olkien | -0.110 |
harassing | -0.109 |
Token | counted |
Token ID | 14789 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
iatus | +0.519 |
maj | +0.456 |
AST | +0.455 |
Ast | +0.441 |
代 | +0.435 |
Neg logit contributions | |
psychiat | -0.367 |
nesota | -0.351 |
ieft | -0.348 |
olkien | -0.345 |
harassing | -0.340 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
iatus | +1.496 |
maj | +1.285 |
AST | +1.281 |
Ast | +1.235 |
代 | +1.214 |
Neg logit contributions | |
psychiat | -1.479 |
nesota | -1.423 |
ieft | -1.417 |
olkien | -1.397 |
harassing | -1.387 |
Token | States |
Token ID | 1829 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
psychiat | +0.362 |
nesota | +0.345 |
ieft | +0.343 |
olkien | +0.341 |
harassing | +0.337 |
Neg logit contributions | |
iatus | -0.472 |
AST | -0.413 |
maj | -0.412 |
Ast | -0.400 |
代 | -0.393 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
psychiat | +0.111 |
nesota | +0.107 |
ieft | +0.106 |
olkien | +0.105 |
harassing | +0.105 |
Neg logit contributions | |
iatus | -0.125 |
AST | -0.108 |
maj | -0.108 |
Ast | -0.104 |
代 | -0.103 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
psychiat | +0.818 |
nesota | +0.783 |
ieft | +0.779 |
harassing | +0.770 |
olkien | +0.770 |
Neg logit contributions | |
iatus | -0.851 |
AST | -0.724 |
maj | -0.723 |
Ast | -0.695 |
代 | -0.692 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
psychiat | +0.427 |
nesota | +0.406 |
ieft | +0.404 |
olkien | +0.399 |
harassing | +0.397 |
Neg logit contributions | |
iatus | -0.623 |
AST | -0.545 |
maj | -0.545 |
Ast | -0.528 |
代 | -0.524 |
Token | Pres |
Token ID | 1763 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
psychiat | +1.383 |
nesota | +1.326 |
ieft | +1.315 |
olkien | +1.294 |
harassing | +1.293 |
Neg logit contributions | |
iatus | -1.861 |
maj | -1.614 |
AST | -1.605 |
Ast | -1.548 |
代 | -1.547 |
Token | ented |
Token ID | 4714 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
psychiat | +0.006 |
nesota | +0.006 |
ieft | +0.006 |
olkien | +0.006 |
harassing | +0.006 |
Neg logit contributions | |
iatus | -0.004 |
maj | -0.003 |
AST | -0.003 |
Ast | -0.003 |
代 | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
psychiat | +3.823 |
nesota | +3.539 |
ieft | +3.510 |
harassing | +3.502 |
olkien | +3.436 |
Neg logit contributions | |
iatus | -4.848 |
AST | -4.100 |
maj | -4.077 |
代 | -3.958 |
Ast | -3.950 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
psychiat | +1.344 |
nesota | +1.288 |
ieft | +1.277 |
harassing | +1.264 |
olkien | +1.261 |
Neg logit contributions | |
iatus | -1.439 |
maj | -1.225 |
AST | -1.215 |
代 | -1.173 |
Ast | -1.170 |
Token | 57 |
Token ID | 7632 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
psychiat | +1.530 |
nesota | +1.461 |
ieft | +1.452 |
olkien | +1.434 |
harassing | +1.434 |
Neg logit contributions | |
iatus | -1.782 |
maj | -1.529 |
AST | -1.521 |
代 | -1.467 |
Ast | -1.464 |
Token | th |
Token ID | 400 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
psychiat | +1.687 |
nesota | +1.628 |
ieft | +1.623 |
olkien | +1.602 |
harassing | +1.600 |
Neg logit contributions | |
iatus | -1.344 |
maj | -1.112 |
AST | -1.112 |
Ast | -1.054 |
代 | -1.046 |
Token | Annual |
Token ID | 16328 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
psychiat | +0.776 |
nesota | +0.734 |
ieft | +0.727 |
harassing | +0.717 |
olkien | +0.716 |
Neg logit contributions | |
iatus | -1.311 |
maj | -1.149 |
AST | -1.145 |
代 | -1.108 |
Ast | -1.108 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
psychiat | +0.423 |
nesota | +0.409 |
ieft | +0.407 |
olkien | +0.404 |
harassing | +0.402 |
Neg logit contributions | |
iatus | -0.324 |
AST | -0.268 |
maj | -0.268 |
Ast | -0.256 |
代 | -0.253 |
Token | Read |
Token ID | 4149 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
psychiat | +0.207 |
nesota | +0.198 |
ieft | +0.197 |
olkien | +0.195 |
harassing | +0.194 |
Neg logit contributions | |
iatus | -0.232 |
AST | -0.200 |
maj | -0.200 |
Ast | -0.192 |
代 | -0.191 |
Token | on |
Token ID | 319 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
psychiat | +0.485 |
nesota | +0.464 |
ieft | +0.461 |
olkien | +0.459 |
harassing | +0.458 |
Neg logit contributions | |
iatus | -0.556 |
maj | -0.475 |
AST | -0.475 |
Ast | -0.457 |
代 | -0.456 |
Token | to |
Token ID | 284 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
iatus | +0.522 |
AST | +0.442 |
maj | +0.441 |
Ast | +0.425 |
代 | +0.421 |
Neg logit contributions | |
psychiat | -0.534 |
nesota | -0.510 |
ieft | -0.510 |
olkien | -0.506 |
harassing | -0.504 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
iatus | +0.696 |
AST | +0.589 |
maj | +0.589 |
Ast | +0.565 |
代 | +0.556 |
Neg logit contributions | |
psychiat | -0.776 |
nesota | -0.749 |
ieft | -0.744 |
olkien | -0.738 |
harassing | -0.734 |
Token | more |
Token ID | 517 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
psychiat | +1.148 |
nesota | +1.095 |
ieft | +1.092 |
harassing | +1.088 |
olkien | +1.082 |
Neg logit contributions | |
iatus | -1.231 |
AST | -1.033 |
maj | -1.033 |
代 | -1.002 |
Ast | -0.991 |
Token | about |
Token ID | 546 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
psychiat | +3.290 |
ieft | +3.133 |
nesota | +3.129 |
olkien | +3.124 |
harassing | +3.123 |
Neg logit contributions | |
iatus | -3.867 |
AST | -3.248 |
maj | -3.223 |
代 | -3.178 |
Ast | -3.113 |
Token | this |
Token ID | 428 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
psychiat | +2.041 |
harassing | +1.946 |
nesota | +1.937 |
ieft | +1.934 |
olkien | +1.915 |
Neg logit contributions | |
iatus | -2.332 |
AST | -1.969 |
maj | -1.966 |
代 | -1.901 |
Ast | -1.886 |
Token | fish |
Token ID | 5916 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
psychiat | +1.299 |
nesota | +1.239 |
ieft | +1.238 |
harassing | +1.230 |
olkien | +1.221 |
Neg logit contributions | |
iatus | -1.346 |
AST | -1.137 |
maj | -1.135 |
代 | -1.093 |
Ast | -1.090 |
Token | - |
Token ID | 12 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
psychiat | +2.344 |
ieft | +2.250 |
harassing | +2.234 |
nesota | +2.223 |
olkien | +2.205 |
Neg logit contributions | |
iatus | -2.713 |
AST | -2.342 |
maj | -2.322 |
Ast | -2.245 |
代 | -2.227 |
Token | tra |
Token ID | 9535 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
iatus | +0.088 |
AST | +0.075 |
maj | +0.075 |
Ast | +0.072 |
代 | +0.071 |
Neg logit contributions | |
psychiat | -0.089 |
nesota | -0.085 |
ieft | -0.085 |
olkien | -0.084 |
harassing | -0.084 |
Token | man |
Token ID | 582 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
psychiat | +0.068 |
nesota | +0.065 |
ieft | +0.064 |
olkien | +0.064 |
harassing | +0.063 |
Neg logit contributions | |
iatus | -0.094 |
AST | -0.082 |
maj | -0.082 |
Ast | -0.079 |
代 | -0.079 |
Token | is |
Token ID | 318 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
iatus | +0.383 |
maj | +0.330 |
AST | +0.330 |
Ast | +0.318 |
代 | +0.314 |
Neg logit contributions | |
psychiat | -0.343 |
nesota | -0.330 |
ieft | -0.328 |
olkien | -0.326 |
harassing | -0.321 |
Token | just |
Token ID | 655 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
psychiat | +0.349 |
nesota | +0.334 |
ieft | +0.332 |
olkien | +0.329 |
harassing | +0.328 |
Neg logit contributions | |
iatus | -0.379 |
AST | -0.325 |
maj | -0.324 |
Ast | -0.313 |
代 | -0.310 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
psychiat | +1.503 |
nesota | +1.429 |
harassing | +1.426 |
ieft | +1.422 |
olkien | +1.414 |
Neg logit contributions | |
iatus | -1.520 |
AST | -1.283 |
maj | -1.279 |
Ast | -1.233 |
代 | -1.233 |
Token | convenient |
Token ID | 11282 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
psychiat | +1.347 |
nesota | +1.273 |
ieft | +1.269 |
harassing | +1.263 |
olkien | +1.257 |
Neg logit contributions | |
iatus | -1.736 |
AST | -1.504 |
maj | -1.498 |
Ast | -1.451 |
代 | -1.446 |
Token | scapego |
Token ID | 42374 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
psychiat | +0.104 |
nesota | +0.101 |
ieft | +0.100 |
olkien | +0.099 |
harassing | +0.097 |
Neg logit contributions | |
iatus | -0.129 |
maj | -0.113 |
AST | -0.112 |
Ast | -0.109 |
代 | -0.107 |
Token | at |
Token ID | 265 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
psychiat | +2.673 |
ieft | +2.660 |
nesota | +2.597 |
olkien | +2.587 |
harassing | +2.550 |
Neg logit contributions | |
iatus | -2.964 |
AST | -2.596 |
maj | -2.557 |
代 | -2.512 |
Toast | -2.471 |
Token | perpet |
Token ID | 8939 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
psychiat | +0.713 |
nesota | +0.680 |
ieft | +0.680 |
harassing | +0.675 |
olkien | +0.673 |
Neg logit contributions | |
iatus | -0.728 |
AST | -0.621 |
maj | -0.618 |
Ast | -0.594 |
代 | -0.592 |
Token | uated |
Token ID | 6605 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
psychiat | +2.596 |
ieft | +2.508 |
nesota | +2.500 |
harassing | +2.481 |
olkien | +2.471 |
Neg logit contributions | |
iatus | -2.966 |
AST | -2.589 |
maj | -2.562 |
Ast | -2.486 |
代 | -2.464 |
Token | by |
Token ID | 416 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
psychiat | +1.463 |
nesota | +1.383 |
ieft | +1.378 |
harassing | +1.376 |
olkien | +1.366 |
Neg logit contributions | |
iatus | -1.844 |
AST | -1.598 |
maj | -1.584 |
代 | -1.536 |
Ast | -1.535 |
Token | homophobic |
Token ID | 36034 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
psychiat | +0.523 |
nesota | +0.499 |
ieft | +0.496 |
harassing | +0.492 |
olkien | +0.492 |
Neg logit contributions | |
iatus | -0.601 |
AST | -0.516 |
maj | -0.516 |
Ast | -0.497 |
代 | -0.495 |
Token | was |
Token ID | 373 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
psychiat | +0.423 |
nesota | +0.404 |
ieft | +0.402 |
harassing | +0.400 |
olkien | +0.398 |
Neg logit contributions | |
iatus | -0.475 |
AST | -0.407 |
maj | -0.404 |
Ast | -0.390 |
代 | -0.390 |
Token | becoming |
Token ID | 5033 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
psychiat | +1.432 |
harassing | +1.362 |
ieft | +1.356 |
nesota | +1.345 |
olkien | +1.335 |
Neg logit contributions | |
iatus | -1.565 |
AST | -1.326 |
maj | -1.306 |
代 | -1.288 |
Ast | -1.266 |
Token | even |
Token ID | 772 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
iatus | +0.585 |
AST | +0.501 |
maj | +0.499 |
Ast | +0.481 |
代 | +0.480 |
Neg logit contributions | |
psychiat | -0.533 |
nesota | -0.509 |
ieft | -0.507 |
harassing | -0.502 |
olkien | -0.500 |
Token | stronger |
Token ID | 7387 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
psychiat | +0.398 |
nesota | +0.376 |
ieft | +0.375 |
harassing | +0.371 |
olkien | +0.369 |
Neg logit contributions | |
iatus | -0.579 |
AST | -0.504 |
maj | -0.502 |
代 | -0.488 |
Ast | -0.486 |
Token | than |
Token ID | 621 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
psychiat | +1.661 |
harassing | +1.582 |
nesota | +1.568 |
ieft | +1.561 |
olkien | +1.539 |
Neg logit contributions | |
iatus | -1.993 |
AST | -1.705 |
maj | -1.678 |
代 | -1.663 |
Toast | -1.639 |
Token | ever |
Token ID | 1683 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
psychiat | +0.567 |
ieft | +0.535 |
nesota | +0.533 |
harassing | +0.533 |
olkien | +0.527 |
Neg logit contributions | |
iatus | -0.687 |
AST | -0.588 |
maj | -0.582 |
代 | -0.572 |
Ast | -0.563 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
psychiat | +2.465 |
harassing | +2.298 |
ieft | +2.296 |
olkien | +2.284 |
nesota | +2.252 |
Neg logit contributions | |
iatus | -3.359 |
AST | -2.920 |
maj | -2.851 |
代 | -2.805 |
Toast | -2.789 |
Token | The |
Token ID | 383 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
psychiat | +0.800 |
ieft | +0.782 |
nesota | +0.779 |
olkien | +0.771 |
harassing | +0.760 |
Neg logit contributions | |
iatus | -0.938 |
maj | -0.797 |
AST | -0.785 |
代 | -0.759 |
Toast | -0.750 |
Token | below |
Token ID | 2174 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
iatus | +0.245 |
AST | +0.209 |
maj | +0.209 |
代 | +0.201 |
Ast | +0.201 |
Neg logit contributions | |
psychiat | -0.209 |
nesota | -0.199 |
ieft | -0.199 |
harassing | -0.197 |
olkien | -0.196 |
Token | chart |
Token ID | 8262 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
iatus | +0.197 |
maj | +0.165 |
AST | +0.165 |
Ast | +0.159 |
代 | +0.158 |
Neg logit contributions | |
psychiat | -0.204 |
ieft | -0.196 |
nesota | -0.196 |
harassing | -0.193 |
olkien | -0.193 |
Token | shows |
Token ID | 2523 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
psychiat | +0.262 |
nesota | +0.252 |
ieft | +0.251 |
olkien | +0.248 |
harassing | +0.247 |
Neg logit contributions | |
iatus | -0.267 |
AST | -0.228 |
maj | -0.227 |
Ast | -0.219 |
代 | -0.217 |
Token | of |
Token ID | 286 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
iatus | +1.546 |
maj | +1.333 |
AST | +1.328 |
Ast | +1.284 |
代 | +1.266 |
Neg logit contributions | |
psychiat | -1.475 |
nesota | -1.416 |
ieft | -1.409 |
olkien | -1.398 |
harassing | -1.383 |
Token | CBS |
Token ID | 11133 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
iatus | +1.689 |
maj | +1.412 |
AST | +1.410 |
Ast | +1.355 |
Toast | +1.328 |
Neg logit contributions | |
psychiat | -2.165 |
nesota | -2.084 |
ieft | -2.078 |
olkien | -2.071 |
harassing | -2.044 |
Token | let |
Token ID | 1309 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
iatus | +0.912 |
maj | +0.753 |
AST | +0.752 |
Ast | +0.719 |
代 | +0.707 |
Neg logit contributions | |
psychiat | -1.265 |
nesota | -1.221 |
ieft | -1.218 |
olkien | -1.210 |
harassing | -1.201 |
Token | Pence |
Token ID | 17339 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
iatus | +0.011 |
AST | +0.009 |
maj | +0.009 |
Ast | +0.009 |
代 | +0.009 |
Neg logit contributions | |
psychiat | -0.010 |
nesota | -0.009 |
ieft | -0.009 |
olkien | -0.009 |
harassing | -0.009 |
Token | get |
Token ID | 651 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
iatus | +0.774 |
AST | +0.662 |
maj | +0.662 |
Ast | +0.637 |
代 | +0.631 |
Neg logit contributions | |
psychiat | -0.743 |
nesota | -0.714 |
ieft | -0.710 |
olkien | -0.704 |
harassing | -0.700 |
Token | away |
Token ID | 1497 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
psychiat | +0.082 |
nesota | +0.078 |
ieft | +0.078 |
harassing | +0.078 |
olkien | +0.077 |
Neg logit contributions | |
iatus | -0.084 |
AST | -0.071 |
maj | -0.071 |
Ast | -0.068 |
代 | -0.068 |
Token | with |
Token ID | 351 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
psychiat | +2.924 |
harassing | +2.819 |
nesota | +2.781 |
ieft | +2.774 |
olkien | +2.722 |
Neg logit contributions | |
iatus | -3.827 |
maj | -3.321 |
AST | -3.302 |
代 | -3.198 |
Toast | -3.197 |
Token | a |
Token ID | 257 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
psychiat | +0.654 |
nesota | +0.626 |
ieft | +0.622 |
harassing | +0.620 |
olkien | +0.616 |
Neg logit contributions | |
iatus | -0.708 |
AST | -0.604 |
maj | -0.604 |
Ast | -0.580 |
代 | -0.579 |
Token | lot |
Token ID | 1256 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
iatus | +0.606 |
maj | +0.521 |
AST | +0.520 |
Ast | +0.501 |
代 | +0.495 |
Neg logit contributions | |
psychiat | -0.564 |
nesota | -0.542 |
ieft | -0.539 |
olkien | -0.535 |
harassing | -0.529 |
Token | of |
Token ID | 286 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
iatus | +0.529 |
maj | +0.455 |
AST | +0.454 |
Ast | +0.438 |
代 | +0.433 |
Neg logit contributions | |
psychiat | -0.480 |
nesota | -0.461 |
ieft | -0.459 |
olkien | -0.455 |
harassing | -0.451 |
Token | his |
Token ID | 465 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
iatus | +0.692 |
maj | +0.593 |
AST | +0.592 |
Ast | +0.571 |
代 | +0.557 |
Neg logit contributions | |
psychiat | -0.720 |
nesota | -0.694 |
ieft | -0.692 |
olkien | -0.688 |
harassing | -0.672 |