Token | ALL |
Token ID | 11096 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
Reviewer | +0.645 |
iary | +0.606 |
romeda | +0.567 |
raid | +0.537 |
stroke | +0.535 |
Neg logit contributions | |
arta | -0.790 |
urrent | -0.655 |
ighthouse | -0.647 |
eger | -0.615 |
istar | -0.606 |
Token | PERSON |
Token ID | 46740 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Reviewer | +0.782 |
iary | +0.740 |
romeda | +0.693 |
raid | +0.658 |
stroke | +0.656 |
Neg logit contributions | |
arta | -0.783 |
urrent | -0.638 |
ighthouse | -0.629 |
eger | -0.596 |
istar | -0.584 |
Token | EL |
Token ID | 3698 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
Reviewer | +1.709 |
iary | +1.603 |
romeda | +1.482 |
raid | +1.374 |
stroke | +1.373 |
Neg logit contributions | |
arta | -2.653 |
urrent | -2.241 |
ighthouse | -2.210 |
eger | -2.118 |
istar | -2.096 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
arta | +1.328 |
urrent | +1.120 |
ighthouse | +1.107 |
eger | +1.061 |
istar | +1.046 |
Neg logit contributions | |
Reviewer | -0.877 |
iary | -0.820 |
romeda | -0.762 |
raid | -0.710 |
stroke | -0.705 |
Token | : |
Token ID | 25 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
arta | +0.028 |
urrent | +0.023 |
ighthouse | +0.023 |
eger | +0.022 |
istar | +0.021 |
Neg logit contributions | |
Reviewer | -0.027 |
iary | -0.025 |
romeda | -0.024 |
raid | -0.022 |
stroke | -0.022 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
arta | +4.213 |
urrent | +3.388 |
ighthouse | +3.376 |
eger | +3.174 |
istar | +3.168 |
Neg logit contributions | |
Reviewer | -4.118 |
iary | -3.821 |
romeda | -3.618 |
raid | -3.418 |
stroke | -3.387 |
Token | 605 |
Token ID | 32417 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arta | +10.557 |
urrent | +8.236 |
ighthouse | +8.004 |
esson | +8.000 |
utor | +7.753 |
Neg logit contributions | |
romeda | -14.442 |
iary | -14.033 |
Reviewer | -13.721 |
achev | -13.699 |
raid | -12.946 |
Token | z |
Token ID | 89 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
arta | +1.426 |
urrent | +1.107 |
ighthouse | +1.090 |
eger | +1.021 |
istar | +1.010 |
Neg logit contributions | |
Reviewer | -1.818 |
iary | -1.725 |
romeda | -1.644 |
raid | -1.553 |
stroke | -1.534 |
Token | BLACK |
Token ID | 31963 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
Reviewer | +2.499 |
iary | +2.366 |
romeda | +2.218 |
stroke | +2.084 |
raid | +2.073 |
Neg logit contributions | |
arta | -3.225 |
urrent | -2.711 |
ighthouse | -2.678 |
eger | -2.545 |
istar | -2.494 |
Token | FO |
Token ID | 6080 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
arta | +0.124 |
urrent | +0.103 |
ighthouse | +0.101 |
eger | +0.097 |
istar | +0.095 |
Neg logit contributions | |
Reviewer | -0.101 |
iary | -0.095 |
romeda | -0.088 |
raid | -0.084 |
stroke | -0.083 |
Token | OT |
Token ID | 2394 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
arta | +0.370 |
urrent | +0.277 |
ighthouse | +0.272 |
eger | +0.251 |
istar | +0.246 |
Neg logit contributions | |
Reviewer | -0.609 |
iary | -0.586 |
romeda | -0.562 |
raid | -0.538 |
stroke | -0.536 |
Token | white |
Token ID | 2330 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
arta | +3.645 |
urrent | +2.968 |
ighthouse | +2.882 |
eger | +2.797 |
istar | +2.756 |
Neg logit contributions | |
Reviewer | -3.409 |
iary | -3.206 |
romeda | -3.000 |
stroke | -2.834 |
raid | -2.816 |
Token | onion |
Token ID | 21670 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
arta | +2.266 |
urrent | +1.861 |
ighthouse | +1.822 |
eger | +1.749 |
istar | +1.715 |
Neg logit contributions | |
Reviewer | -1.924 |
iary | -1.818 |
romeda | -1.702 |
raid | -1.592 |
stroke | -1.589 |
Token | into |
Token ID | 656 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
arta | +6.783 |
urrent | +5.404 |
ighthouse | +5.174 |
eger | +5.067 |
esson | +5.063 |
Neg logit contributions | |
Reviewer | -6.705 |
iary | -6.330 |
romeda | -6.024 |
stroke | -5.556 |
raid | -5.535 |
Token | strips |
Token ID | 22670 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
arta | +0.159 |
urrent | +0.132 |
ighthouse | +0.130 |
eger | +0.124 |
istar | +0.122 |
Neg logit contributions | |
Reviewer | -0.133 |
iary | -0.125 |
romeda | -0.117 |
raid | -0.110 |
stroke | -0.110 |
Token | or |
Token ID | 393 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
arta | +2.254 |
urrent | +1.861 |
ighthouse | +1.829 |
eger | +1.748 |
istar | +1.725 |
Neg logit contributions | |
Reviewer | -1.861 |
iary | -1.742 |
romeda | -1.628 |
stroke | -1.527 |
raid | -1.521 |
Token | just |
Token ID | 655 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
arta | +5.793 |
urrent | +4.705 |
ighthouse | +4.577 |
isu | +4.377 |
esson | +4.294 |
Neg logit contributions | |
Reviewer | -5.652 |
iary | -5.327 |
romeda | -4.930 |
stroke | -4.725 |
achev | -4.695 |
Token | as |
Token ID | 355 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
arta | +11.104 |
esson | +8.857 |
ighthouse | +8.851 |
urrent | +8.799 |
atan | +8.335 |
Neg logit contributions | |
Reviewer | -13.796 |
iary | -12.314 |
romeda | -11.413 |
stroke | -10.953 |
achev | -10.952 |
Token | you |
Token ID | 345 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
arta | +5.892 |
urrent | +4.791 |
ighthouse | +4.722 |
eger | +4.513 |
istar | +4.430 |
Neg logit contributions | |
Reviewer | -5.837 |
iary | -5.459 |
romeda | -5.220 |
stroke | -4.889 |
raid | -4.762 |
Token | want |
Token ID | 765 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
arta | +1.826 |
urrent | +1.487 |
ighthouse | +1.471 |
eger | +1.403 |
istar | +1.385 |
Neg logit contributions | |
Reviewer | -1.522 |
iary | -1.394 |
romeda | -1.321 |
raid | -1.220 |
stroke | -1.216 |
Token | to |
Token ID | 284 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
arta | +3.315 |
urrent | +2.717 |
ighthouse | +2.674 |
eger | +2.584 |
istar | +2.538 |
Neg logit contributions | |
Reviewer | -2.905 |
iary | -2.704 |
romeda | -2.575 |
raid | -2.404 |
stroke | -2.391 |
Token | have |
Token ID | 423 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
arta | +6.682 |
urrent | +5.233 |
ighthouse | +5.103 |
eger | +4.954 |
esson | +4.936 |
Neg logit contributions | |
Reviewer | -7.298 |
iary | -6.569 |
romeda | -6.434 |
stroke | -5.863 |
achev | -5.812 |
Token | contributor |
Token ID | 18920 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Reviewer | +5.767 |
iary | +5.766 |
romeda | +4.873 |
stroke | +4.776 |
pl | +4.585 |
Neg logit contributions | |
arta | -11.588 |
ighthouse | -9.857 |
byss | -9.677 |
urrent | -9.530 |
istar | -9.343 |
Token | : |
Token ID | 25 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +3.896 |
iary | +3.751 |
romeda | +3.401 |
stroke | +3.222 |
raid | +3.162 |
Neg logit contributions | |
arta | -5.693 |
urrent | -4.684 |
ighthouse | -4.680 |
istar | -4.430 |
eger | -4.422 |
Token | David |
Token ID | 3271 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Reviewer | +1.404 |
iary | +1.332 |
romeda | +1.235 |
raid | +1.160 |
stroke | +1.158 |
Neg logit contributions | |
arta | -1.941 |
urrent | -1.623 |
ighthouse | -1.605 |
eger | -1.540 |
istar | -1.513 |
Token | A |
Token ID | 317 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arta | +2.049 |
urrent | +1.692 |
ighthouse | +1.673 |
eger | +1.593 |
istar | +1.569 |
Neg logit contributions | |
Reviewer | -1.668 |
iary | -1.561 |
romeda | -1.468 |
raid | -1.379 |
stroke | -1.368 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
arta | +1.799 |
urrent | +1.494 |
ighthouse | +1.474 |
eger | +1.405 |
istar | +1.387 |
Neg logit contributions | |
Reviewer | -1.431 |
iary | -1.350 |
romeda | -1.264 |
raid | -1.187 |
stroke | -1.181 |
Token | Sle |
Token ID | 19498 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
arta | +1.918 |
urrent | +1.624 |
ighthouse | +1.609 |
eger | +1.544 |
istar | +1.525 |
Neg logit contributions | |
Reviewer | -1.181 |
iary | -1.101 |
romeda | -1.021 |
raid | -0.945 |
stroke | -0.936 |
Token | et |
Token ID | 316 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
arta | +9.715 |
eger | +7.880 |
ighthouse | +7.546 |
urrent | +7.185 |
istar | +6.423 |
Neg logit contributions | |
Reviewer | -16.826 |
romeda | -14.656 |
版 | -13.872 |
disadvant | -13.865 |
iary | -13.407 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Reviewer | +0.325 |
iary | +0.309 |
romeda | +0.288 |
raid | +0.269 |
stroke | +0.269 |
Neg logit contributions | |
arta | -0.431 |
urrent | -0.359 |
ighthouse | -0.357 |
eger | -0.338 |
istar | -0.334 |
Token | d |
Token ID | 288 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
arta | +3.501 |
urrent | +2.858 |
ighthouse | +2.801 |
eger | +2.643 |
istar | +2.637 |
Neg logit contributions | |
Reviewer | -3.471 |
iary | -3.246 |
romeda | -3.098 |
raid | -2.913 |
stroke | -2.883 |
Token | sle |
Token ID | 26738 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Reviewer | +0.950 |
iary | +0.913 |
romeda | +0.853 |
raid | +0.815 |
stroke | +0.811 |
Neg logit contributions | |
arta | -1.064 |
urrent | -0.870 |
ighthouse | -0.858 |
eger | -0.811 |
istar | -0.803 |
Token | et |
Token ID | 316 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
arta | +5.193 |
urrent | +4.358 |
ighthouse | +4.310 |
eger | +4.164 |
istar | +3.969 |
Neg logit contributions | |
Reviewer | -5.029 |
iary | -4.605 |
romeda | -4.389 |
stroke | -4.071 |
raid | -4.065 |
Token | for |
Token ID | 329 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
arta | +1.789 |
urrent | +1.505 |
ighthouse | +1.487 |
eger | +1.423 |
istar | +1.405 |
Neg logit contributions | |
Reviewer | -1.223 |
iary | -1.147 |
romeda | -1.067 |
raid | -0.994 |
stroke | -0.989 |
Token | natural |
Token ID | 3288 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
arta | +2.990 |
urrent | +2.369 |
ighthouse | +2.339 |
eger | +2.192 |
stration | +2.133 |
Neg logit contributions | |
Reviewer | -3.847 |
iary | -3.607 |
romeda | -3.452 |
raid | -3.290 |
stroke | -3.246 |
Token | gas |
Token ID | 3623 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
arta | +0.793 |
urrent | +0.634 |
ighthouse | +0.623 |
eger | +0.587 |
istar | +0.579 |
Neg logit contributions | |
Reviewer | -0.878 |
iary | -0.837 |
romeda | -0.790 |
raid | -0.751 |
stroke | -0.749 |
Token | ." |
Token ID | 526 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
arta | +3.815 |
urrent | +3.123 |
ighthouse | +3.059 |
eger | +2.944 |
istar | +2.874 |
Neg logit contributions | |
Reviewer | -3.453 |
iary | -3.227 |
romeda | -3.067 |
raid | -2.852 |
stroke | -2.808 |
Token | Jan |
Token ID | 2365 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Reviewer | +0.735 |
iary | +0.697 |
romeda | +0.654 |
raid | +0.616 |
stroke | +0.615 |
Neg logit contributions | |
arta | -0.827 |
urrent | -0.681 |
ighthouse | -0.672 |
eger | -0.640 |
istar | -0.629 |
Token | Re |
Token ID | 797 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
arta | +2.853 |
urrent | +2.362 |
ighthouse | +2.328 |
eger | +2.236 |
istar | +2.176 |
Neg logit contributions | |
Reviewer | -2.362 |
iary | -2.172 |
romeda | -2.062 |
raid | -1.925 |
stroke | -1.907 |
Token | es |
Token ID | 274 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
arta | +7.702 |
eger | +6.102 |
ighthouse | +5.737 |
esson | +5.272 |
mington | +5.225 |
Neg logit contributions | |
Reviewer | -17.611 |
romeda | -16.417 |
iary | -15.176 |
raid | -14.835 |
disadvant | -14.738 |
Token | - |
Token ID | 12 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
arta | +3.440 |
urrent | +2.693 |
ighthouse | +2.693 |
eger | +2.584 |
istar | +2.472 |
Neg logit contributions | |
Reviewer | -3.993 |
iary | -3.678 |
romeda | -3.596 |
raid | -3.351 |
stroke | -3.338 |
Token | Jones |
Token ID | 25784 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
arta | +2.986 |
urrent | +2.454 |
ighthouse | +2.452 |
eger | +2.309 |
isu | +2.261 |
Neg logit contributions | |
Reviewer | -2.526 |
iary | -2.419 |
romeda | -2.410 |
raid | -2.148 |
achev | -2.138 |
Token | remembers |
Token ID | 18140 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
arta | +0.340 |
urrent | +0.281 |
ighthouse | +0.278 |
eger | +0.265 |
istar | +0.261 |
Neg logit contributions | |
Reviewer | -0.283 |
iary | -0.266 |
romeda | -0.250 |
raid | -0.235 |
stroke | -0.234 |
Token | when |
Token ID | 618 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Reviewer | +0.362 |
iary | +0.342 |
romeda | +0.321 |
raid | +0.301 |
stroke | +0.300 |
Neg logit contributions | |
arta | -0.442 |
urrent | -0.366 |
ighthouse | -0.361 |
eger | -0.344 |
istar | -0.340 |
Token | Director |
Token ID | 5890 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
Reviewer | +0.432 |
iary | +0.408 |
romeda | +0.383 |
raid | +0.360 |
stroke | +0.359 |
Neg logit contributions | |
arta | -0.510 |
urrent | -0.421 |
ighthouse | -0.415 |
eger | -0.396 |
istar | -0.390 |
Token | ; |
Token ID | 26 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
arta | +1.296 |
urrent | +1.080 |
ighthouse | +1.066 |
eger | +1.019 |
istar | +1.005 |
Neg logit contributions | |
Reviewer | -0.988 |
iary | -0.931 |
romeda | -0.869 |
raid | -0.813 |
stroke | -0.810 |
Token | David |
Token ID | 3271 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Reviewer | +1.258 |
iary | +1.192 |
romeda | +1.112 |
stroke | +1.043 |
raid | +1.039 |
Neg logit contributions | |
arta | -1.598 |
urrent | -1.326 |
ighthouse | -1.309 |
eger | -1.256 |
istar | -1.234 |
Token | A |
Token ID | 317 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Reviewer | +1.119 |
iary | +1.076 |
romeda | +0.994 |
stroke | +0.931 |
raid | +0.930 |
Neg logit contributions | |
arta | -1.494 |
urrent | -1.253 |
ighthouse | -1.236 |
eger | -1.183 |
istar | -1.169 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
arta | +4.436 |
urrent | +3.641 |
ighthouse | +3.606 |
eger | +3.474 |
istar | +3.381 |
Neg logit contributions | |
Reviewer | -3.924 |
iary | -3.607 |
romeda | -3.481 |
stroke | -3.210 |
raid | -3.201 |
Token | Sle |
Token ID | 19498 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
arta | +0.444 |
urrent | +0.368 |
ighthouse | +0.363 |
eger | +0.346 |
istar | +0.342 |
Neg logit contributions | |
Reviewer | -0.362 |
iary | -0.343 |
romeda | -0.321 |
raid | -0.301 |
stroke | -0.300 |
Token | et |
Token ID | 316 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
arta | +15.200 |
eger | +13.399 |
urrent | +13.050 |
ighthouse | +12.886 |
mington | +12.728 |
Neg logit contributions | |
Reviewer | -10.236 |
romeda | -8.743 |
iary | -7.854 |
raid | -7.494 |
stroke | -7.306 |
Token | , |
Token ID | 11 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
arta | +3.532 |
urrent | +2.904 |
ighthouse | +2.877 |
eger | +2.779 |
istar | +2.696 |
Neg logit contributions | |
Reviewer | -2.918 |
iary | -2.687 |
romeda | -2.551 |
raid | -2.374 |
stroke | -2.360 |
Token | PhD |
Token ID | 16394 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
arta | +4.619 |
urrent | +3.765 |
ighthouse | +3.732 |
istar | +3.485 |
eger | +3.449 |
Neg logit contributions | |
Reviewer | -4.319 |
iary | -3.980 |
romeda | -3.802 |
raid | -3.569 |
achev | -3.518 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Reviewer | +0.076 |
iary | +0.072 |
romeda | +0.067 |
raid | +0.063 |
stroke | +0.063 |
Neg logit contributions | |
arta | -0.104 |
urrent | -0.086 |
ighthouse | -0.086 |
eger | -0.082 |
istar | -0.081 |
Token | Div |
Token ID | 4777 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
arta | +2.406 |
urrent | +1.966 |
ighthouse | +1.948 |
istar | +1.824 |
eger | +1.821 |
Neg logit contributions | |
Reviewer | -2.254 |
iary | -2.091 |
romeda | -1.987 |
raid | -1.872 |
stroke | -1.848 |
Token | St |
Token ID | 1273 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
arta | +3.859 |
urrent | +3.184 |
ighthouse | +3.139 |
eger | +2.956 |
istar | +2.928 |
Neg logit contributions | |
Reviewer | -3.451 |
iary | -3.334 |
romeda | -3.186 |
raid | -2.935 |
stroke | -2.918 |
Token | all |
Token ID | 439 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Reviewer | +0.441 |
iary | +0.420 |
romeda | +0.394 |
raid | +0.373 |
stroke | +0.369 |
Neg logit contributions | |
arta | -0.501 |
urrent | -0.412 |
ighthouse | -0.407 |
eger | -0.387 |
istar | -0.382 |
Token | one |
Token ID | 505 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
arta | +7.024 |
urrent | +5.712 |
ighthouse | +5.700 |
istar | +5.387 |
eger | +5.374 |
Neg logit contributions | |
Reviewer | -5.868 |
iary | -5.361 |
romeda | -5.227 |
raid | -4.714 |
stroke | -4.698 |
Token | - |
Token ID | 12 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
arta | +8.590 |
urrent | +7.033 |
ighthouse | +6.923 |
stration | +6.617 |
eger | +6.592 |
Neg logit contributions | |
Reviewer | -7.604 |
iary | -6.958 |
romeda | -6.725 |
raid | -6.206 |
stroke | -6.085 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
arta | +3.997 |
urrent | +3.298 |
ighthouse | +3.253 |
eger | +3.067 |
istar | +3.039 |
Neg logit contributions | |
Reviewer | -3.526 |
iary | -3.404 |
romeda | -3.263 |
raid | -2.997 |
stroke | -2.979 |
Token | Cruise |
Token ID | 29147 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
arta | +0.175 |
urrent | +0.144 |
ighthouse | +0.141 |
eger | +0.134 |
istar | +0.132 |
Neg logit contributions | |
Reviewer | -0.156 |
iary | -0.148 |
romeda | -0.139 |
raid | -0.131 |
stroke | -0.131 |
Token | Book |
Token ID | 4897 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
arta | +11.943 |
urrent | +9.497 |
ighthouse | +9.190 |
istar | +9.058 |
stration | +8.946 |
Neg logit contributions | |
Reviewer | -12.054 |
romeda | -11.018 |
iary | -10.897 |
raid | -10.194 |
achev | -9.931 |
Token | - |
Token ID | 12 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
arta | +3.760 |
urrent | +3.100 |
ighthouse | +3.044 |
istar | +2.885 |
eger | +2.866 |
Neg logit contributions | |
Reviewer | -3.379 |
iary | -3.149 |
romeda | -3.042 |
stroke | -2.785 |
raid | -2.782 |
Token | M |
Token ID | 44 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
arta | +4.690 |
urrent | +3.869 |
ighthouse | +3.817 |
eger | +3.589 |
istar | +3.562 |
Neg logit contributions | |
Reviewer | -4.159 |
iary | -4.048 |
romeda | -3.885 |
raid | -3.559 |
stroke | -3.540 |
Token | unch |
Token ID | 3316 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Reviewer | +0.477 |
iary | +0.453 |
romeda | +0.423 |
raid | +0.401 |
stroke | +0.395 |
Neg logit contributions | |
arta | -0.569 |
urrent | -0.471 |
ighthouse | -0.462 |
eger | -0.443 |
istar | -0.434 |
Token | kins |
Token ID | 5331 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Reviewer | +4.052 |
iary | +3.922 |
romeda | +3.676 |
raid | +3.507 |
stroke | +3.465 |
Neg logit contributions | |
arta | -5.278 |
urrent | -4.425 |
ighthouse | -4.414 |
eger | -4.273 |
byss | -4.119 |
Token | ALL |
Token ID | 11096 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Reviewer | +2.053 |
iary | +1.923 |
romeda | +1.799 |
raid | +1.709 |
stroke | +1.702 |
Neg logit contributions | |
arta | -2.641 |
urrent | -2.198 |
ighthouse | -2.173 |
eger | -2.066 |
istar | -2.040 |
Token | PERSON |
Token ID | 46740 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Reviewer | +1.761 |
iary | +1.661 |
romeda | +1.541 |
raid | +1.472 |
stroke | +1.465 |
Neg logit contributions | |
arta | -1.881 |
urrent | -1.543 |
ighthouse | -1.523 |
eger | -1.444 |
istar | -1.418 |
Token | EL |
Token ID | 3698 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
Reviewer | +1.381 |
iary | +1.294 |
romeda | +1.201 |
raid | +1.117 |
stroke | +1.113 |
Neg logit contributions | |
arta | -2.070 |
urrent | -1.744 |
ighthouse | -1.722 |
eger | -1.649 |
istar | -1.631 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
arta | +1.339 |
urrent | +1.128 |
ighthouse | +1.115 |
eger | +1.068 |
istar | +1.053 |
Neg logit contributions | |
Reviewer | -0.897 |
iary | -0.840 |
romeda | -0.780 |
raid | -0.727 |
stroke | -0.723 |
Token | : |
Token ID | 25 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
arta | +0.712 |
urrent | +0.589 |
ighthouse | +0.581 |
eger | +0.552 |
istar | +0.544 |
Neg logit contributions | |
Reviewer | -0.599 |
iary | -0.567 |
romeda | -0.530 |
raid | -0.500 |
stroke | -0.498 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
arta | +4.350 |
urrent | +3.477 |
ighthouse | +3.472 |
eger | +3.266 |
istar | +3.249 |
Neg logit contributions | |
Reviewer | -4.458 |
iary | -4.145 |
romeda | -3.929 |
raid | -3.694 |
achev | -3.685 |
Token | 555 |
Token ID | 31046 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
arta | +8.977 |
urrent | +7.048 |
ighthouse | +6.650 |
esson | +6.646 |
stration | +6.473 |
Neg logit contributions | |
romeda | -13.706 |
achev | -13.650 |
Reviewer | -13.639 |
iary | -13.505 |
raid | -12.629 |
Token | z |
Token ID | 89 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
arta | +1.310 |
urrent | +1.021 |
ighthouse | +1.000 |
eger | +0.937 |
istar | +0.927 |
Neg logit contributions | |
Reviewer | -1.705 |
iary | -1.617 |
romeda | -1.538 |
raid | -1.454 |
stroke | -1.432 |
Token | MO |
Token ID | 13070 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
Reviewer | +3.548 |
iary | +3.337 |
romeda | +3.126 |
stroke | +2.936 |
raid | +2.923 |
Neg logit contributions | |
arta | -4.792 |
urrent | -4.036 |
ighthouse | -3.981 |
eger | -3.791 |
istar | -3.721 |
Token | HA |
Token ID | 7801 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
arta | +0.031 |
urrent | +0.025 |
ighthouse | +0.025 |
eger | +0.024 |
istar | +0.023 |
Neg logit contributions | |
Reviewer | -0.028 |
iary | -0.026 |
romeda | -0.025 |
raid | -0.023 |
stroke | -0.023 |
Token | W |
Token ID | 54 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
arta | +1.832 |
urrent | +1.498 |
ighthouse | +1.484 |
eger | +1.413 |
istar | +1.389 |
Neg logit contributions | |
Reviewer | -1.598 |
iary | -1.510 |
romeda | -1.427 |
raid | -1.336 |
stroke | -1.330 |
Token | for |
Token ID | 329 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Reviewer | +1.868 |
iary | +1.795 |
romeda | +1.655 |
stroke | +1.542 |
raid | +1.516 |
Neg logit contributions | |
arta | -2.710 |
urrent | -2.280 |
ighthouse | -2.244 |
eger | -2.132 |
istar | -2.111 |
Token | Harmon |
Token ID | 39712 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Reviewer | +1.033 |
iary | +0.981 |
romeda | +0.917 |
stroke | +0.855 |
raid | +0.852 |
Neg logit contributions | |
arta | -1.315 |
urrent | -1.086 |
ighthouse | -1.068 |
eger | -1.024 |
istar | -1.012 |
Token | � |
Token ID | 447 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
arta | +4.294 |
urrent | +3.553 |
ighthouse | +3.526 |
eger | +3.335 |
istar | +3.282 |
Neg logit contributions | |
Reviewer | -3.592 |
iary | -3.360 |
romeda | -3.237 |
raid | -3.000 |
stroke | -2.980 |
Token | � |
Token ID | 247 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
arta | +1.735 |
urrent | +1.362 |
ighthouse | +1.341 |
eger | +1.271 |
istar | +1.209 |
Neg logit contributions | |
Reviewer | -2.448 |
iary | -2.320 |
romeda | -2.210 |
raid | -2.115 |
stroke | -2.097 |
Token | s |
Token ID | 82 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
arta | +1.551 |
urrent | +1.249 |
ighthouse | +1.229 |
eger | +1.157 |
istar | +1.142 |
Neg logit contributions | |
Reviewer | -1.690 |
iary | -1.608 |
romeda | -1.531 |
raid | -1.446 |
stroke | -1.438 |
Token | Re |
Token ID | 797 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
arta | +4.325 |
urrent | +3.565 |
ighthouse | +3.532 |
eger | +3.320 |
istar | +3.273 |
Neg logit contributions | |
Reviewer | -3.888 |
iary | -3.579 |
romeda | -3.391 |
raid | -3.238 |
stroke | -3.194 |
Token | ception |
Token ID | 4516 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
arta | +13.193 |
ighthouse | +10.875 |
eger | +10.735 |
urrent | +10.196 |
isu | +9.925 |
Neg logit contributions | |
Reviewer | -11.397 |
romeda | -10.492 |
iary | -10.027 |
raid | -9.284 |
stroke | -9.041 |
Token | Perception |
Token ID | 35802 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
arta | +1.948 |
urrent | +1.606 |
ighthouse | +1.589 |
eger | +1.509 |
istar | +1.490 |
Neg logit contributions | |
Reviewer | -1.601 |
iary | -1.503 |
romeda | -1.418 |
raid | -1.336 |
stroke | -1.322 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-03 |
Pos logit contributions | |
Reviewer | +0.869 |
iary | +0.825 |
romeda | +0.770 |
stroke | +0.725 |
raid | +0.718 |
Neg logit contributions | |
arta | -1.019 |
urrent | -0.846 |
ighthouse | -0.829 |
eger | -0.796 |
istar | -0.784 |
Token |
|
Token ID | 198 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
arta | +0.022 |
urrent | +0.018 |
ighthouse | +0.018 |
eger | +0.017 |
istar | +0.017 |
Neg logit contributions | |
Reviewer | -0.021 |
iary | -0.020 |
romeda | -0.019 |
raid | -0.018 |
stroke | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
arta | +0.834 |
urrent | +0.663 |
ighthouse | +0.659 |
eger | +0.618 |
istar | +0.609 |
Neg logit contributions | |
Reviewer | -0.935 |
iary | -0.881 |
romeda | -0.853 |
raid | -0.802 |
stroke | -0.785 |
Token | piece |
Token ID | 3704 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
arta | +0.345 |
urrent | +0.284 |
ighthouse | +0.280 |
eger | +0.266 |
istar | +0.262 |
Neg logit contributions | |
Reviewer | -0.306 |
iary | -0.289 |
romeda | -0.272 |
raid | -0.256 |
stroke | -0.255 |
Token | that |
Token ID | 326 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Reviewer | +4.644 |
iary | +4.301 |
romeda | +3.980 |
raid | +3.703 |
stroke | +3.676 |
Neg logit contributions | |
arta | -6.823 |
urrent | -5.673 |
eger | -5.584 |
ighthouse | -5.583 |
byss | -5.433 |
Token | — |
Token ID | 851 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
Reviewer | +2.486 |
iary | +2.351 |
romeda | +2.212 |
stroke | +2.065 |
raid | +2.053 |
Neg logit contributions | |
arta | -3.043 |
urrent | -2.524 |
ighthouse | -2.499 |
eger | -2.396 |
byss | -2.345 |
Token | by |
Token ID | 416 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
arta | +0.969 |
urrent | +0.802 |
ighthouse | +0.793 |
eger | +0.755 |
istar | +0.744 |
Neg logit contributions | |
Reviewer | -0.806 |
iary | -0.758 |
romeda | -0.712 |
raid | -0.669 |
stroke | -0.664 |
Token | his |
Token ID | 465 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
arta | +6.406 |
urrent | +5.233 |
ighthouse | +5.152 |
eger | +4.870 |
stration | +4.839 |
Neg logit contributions | |
Reviewer | -5.844 |
iary | -5.534 |
romeda | -5.119 |
raid | -4.849 |
stroke | -4.775 |
Token | own |
Token ID | 898 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
arta | +8.988 |
urrent | +6.990 |
stration | +6.785 |
eger | +6.594 |
ighthouse | +6.536 |
Neg logit contributions | |
Reviewer | -10.630 |
iary | -10.118 |
romeda | -9.626 |
raid | -9.394 |
achev | -9.153 |
Token | admission |
Token ID | 13938 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
arta | +9.723 |
stration | +7.292 |
urrent | +7.191 |
eger | +6.890 |
istar | +6.843 |
Neg logit contributions | |
Reviewer | -12.954 |
iary | -12.592 |
romeda | -11.962 |
raid | -11.634 |
achev | -11.124 |
Token | — |
Token ID | 851 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
arta | +3.160 |
urrent | +2.603 |
ighthouse | +2.566 |
eger | +2.454 |
istar | +2.413 |
Neg logit contributions | |
Reviewer | -2.761 |
iary | -2.607 |
romeda | -2.479 |
raid | -2.321 |
stroke | -2.307 |
Token | has |
Token ID | 468 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
arta | +0.721 |
urrent | +0.595 |
ighthouse | +0.587 |
eger | +0.559 |
istar | +0.553 |
Neg logit contributions | |
Reviewer | -0.612 |
iary | -0.576 |
romeda | -0.542 |
raid | -0.510 |
stroke | -0.506 |
Token | inspired |
Token ID | 7867 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
arta | +2.405 |
urrent | +1.986 |
ighthouse | +1.951 |
istar | +1.866 |
eger | +1.860 |
Neg logit contributions | |
Reviewer | -2.116 |
iary | -1.993 |
romeda | -1.880 |
raid | -1.793 |
stroke | -1.757 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
arta | +3.608 |
urrent | +2.995 |
ighthouse | +2.941 |
istar | +2.789 |
eger | +2.786 |
Neg logit contributions | |
Reviewer | -3.083 |
iary | -2.901 |
romeda | -2.734 |
stroke | -2.557 |
raid | -2.556 |
Token | L |
Token ID | 406 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Reviewer | +1.141 |
iary | +1.069 |
romeda | +1.017 |
raid | +0.950 |
stroke | +0.937 |
Neg logit contributions | |
arta | -1.373 |
urrent | -1.128 |
ighthouse | -1.112 |
eger | -1.073 |
istar | -1.050 |
Token | ensing |
Token ID | 26426 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Reviewer | +3.765 |
iary | +3.547 |
romeda | +3.369 |
raid | +3.168 |
pl | +3.102 |
Neg logit contributions | |
arta | -4.308 |
urrent | -3.549 |
eger | -3.446 |
istar | -3.312 |
byss | -3.307 |
Token | Accuracy |
Token ID | 33222 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Reviewer | +5.304 |
iary | +4.926 |
romeda | +4.754 |
stroke | +4.430 |
raid | +4.366 |
Neg logit contributions | |
arta | -6.433 |
urrent | -5.272 |
ighthouse | -5.141 |
eger | -5.104 |
byss | -4.955 |
Token | Testing |
Token ID | 23983 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Reviewer | +5.193 |
iary | +4.764 |
romeda | +4.633 |
raid | +4.173 |
stroke | +4.161 |
Neg logit contributions | |
arta | -7.226 |
urrent | -6.070 |
eger | -5.862 |
ighthouse | -5.844 |
mington | -5.601 |
Token | Challenge |
Token ID | 13879 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Reviewer | +1.681 |
iary | +1.588 |
romeda | +1.499 |
raid | +1.400 |
stroke | +1.388 |
Neg logit contributions | |
arta | -2.138 |
urrent | -1.781 |
ighthouse | -1.737 |
eger | -1.685 |
istar | -1.641 |
Token | ( |
Token ID | 357 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
arta | +0.147 |
urrent | +0.122 |
ighthouse | +0.120 |
eger | +0.115 |
istar | +0.113 |
Neg logit contributions | |
Reviewer | -0.116 |
iary | -0.110 |
romeda | -0.103 |
raid | -0.096 |
stroke | -0.096 |
Token | GRE |
Token ID | 28934 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
arta | +9.503 |
urrent | +7.693 |
ighthouse | +7.378 |
eger | +7.366 |
Lens | +7.261 |
Neg logit contributions | |
Reviewer | -12.672 |
iary | -12.390 |
romeda | -11.718 |
raid | -11.084 |
achev | -11.032 |
Token | AT |
Token ID | 1404 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
arta | +7.524 |
urrent | +6.035 |
ighthouse | +5.995 |
esson | +5.584 |
mington | +5.569 |
Neg logit contributions | |
Reviewer | -7.169 |
iary | -6.881 |
romeda | -6.330 |
stroke | -6.041 |
raid | -5.880 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
arta | +2.623 |
urrent | +2.168 |
ighthouse | +2.146 |
eger | +2.039 |
istar | +2.019 |
Neg logit contributions | |
Reviewer | -2.103 |
iary | -1.979 |
romeda | -1.837 |
raid | -1.719 |
stroke | -1.717 |
Token | ). |
Token ID | 737 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
arta | +2.169 |
urrent | +1.809 |
ighthouse | +1.791 |
eger | +1.707 |
istar | +1.683 |
Neg logit contributions | |
Reviewer | -1.672 |
iary | -1.575 |
romeda | -1.463 |
stroke | -1.372 |
raid | -1.366 |
Token | In |
Token ID | 554 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
arta | +0.402 |
urrent | +0.327 |
ighthouse | +0.323 |
eger | +0.306 |
istar | +0.301 |
Neg logit contributions | |
Reviewer | -0.390 |
iary | -0.369 |
romeda | -0.349 |
raid | -0.329 |
stroke | -0.328 |
Token | time |
Token ID | 640 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Reviewer | +2.645 |
iary | +2.435 |
romeda | +2.215 |
stroke | +2.108 |
raid | +2.032 |
Neg logit contributions | |
arta | -5.049 |
urrent | -4.315 |
ighthouse | -4.270 |
byss | -4.136 |
eger | -4.073 |
Token | and |
Token ID | 290 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
arta | +2.110 |
urrent | +1.730 |
ighthouse | +1.718 |
eger | +1.651 |
istar | +1.619 |
Neg logit contributions | |
Reviewer | -1.756 |
iary | -1.661 |
romeda | -1.562 |
raid | -1.462 |
stroke | -1.447 |
Token | make |
Token ID | 787 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Reviewer | +0.509 |
iary | +0.481 |
romeda | +0.454 |
raid | +0.429 |
stroke | +0.427 |
Neg logit contributions | |
arta | -0.528 |
urrent | -0.430 |
ighthouse | -0.424 |
eger | -0.403 |
istar | -0.397 |
Token | sure |
Token ID | 1654 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Reviewer | +0.707 |
iary | +0.663 |
romeda | +0.601 |
raid | +0.550 |
stroke | +0.547 |
Neg logit contributions | |
arta | -1.462 |
urrent | -1.258 |
ighthouse | -1.246 |
eger | -1.200 |
istar | -1.182 |
Token | you |
Token ID | 345 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
arta | +3.890 |
urrent | +3.165 |
ighthouse | +3.138 |
eger | +3.000 |
istar | +2.978 |
Neg logit contributions | |
Reviewer | -3.477 |
iary | -3.276 |
romeda | -3.067 |
raid | -2.905 |
stroke | -2.846 |
Token | dont |
Token ID | 17666 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
arta | +2.060 |
urrent | +1.654 |
ighthouse | +1.634 |
eger | +1.563 |
istar | +1.549 |
Neg logit contributions | |
Reviewer | -2.103 |
iary | -1.941 |
romeda | -1.830 |
raid | -1.726 |
stroke | -1.702 |
Token | let |
Token ID | 1309 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
arta | +10.071 |
urrent | +7.638 |
istar | +7.585 |
ighthouse | +7.563 |
eger | +7.562 |
Neg logit contributions | |
Reviewer | -13.734 |
romeda | -11.672 |
iary | -11.558 |
achev | -10.283 |
raid | -10.261 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
arta | +7.013 |
ighthouse | +5.517 |
urrent | +5.509 |
eger | +5.369 |
istar | +5.192 |
Neg logit contributions | |
Reviewer | -7.247 |
iary | -6.831 |
romeda | -6.484 |
raid | -6.065 |
stroke | -5.881 |
Token | car |
Token ID | 1097 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
arta | +2.067 |
urrent | +1.687 |
ighthouse | +1.666 |
eger | +1.596 |
istar | +1.562 |
Neg logit contributions | |
Reviewer | -1.905 |
iary | -1.809 |
romeda | -1.701 |
raid | -1.603 |
stroke | -1.586 |
Token | l |
Token ID | 300 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
arta | +7.980 |
ighthouse | +6.073 |
urrent | +6.020 |
istar | +5.952 |
eger | +5.846 |
Neg logit contributions | |
Reviewer | -8.989 |
iary | -8.102 |
romeda | -8.024 |
raid | -7.394 |
achev | -7.120 |
Token | urch |
Token ID | 2575 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Reviewer | +2.859 |
iary | +2.680 |
raid | +2.464 |
romeda | +2.459 |
stroke | +2.322 |
Neg logit contributions | |
arta | -4.134 |
urrent | -3.459 |
ighthouse | -3.363 |
byss | -3.338 |
eger | -3.245 |
Token | za |
Token ID | 4496 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
arta | +0.713 |
urrent | +0.523 |
ighthouse | +0.519 |
eger | +0.479 |
istar | +0.471 |
Neg logit contributions | |
Reviewer | -1.169 |
iary | -1.108 |
romeda | -1.066 |
raid | -1.010 |
stroke | -1.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Reviewer | +0.155 |
iary | +0.147 |
romeda | +0.137 |
raid | +0.128 |
stroke | +0.127 |
Neg logit contributions | |
arta | -0.208 |
urrent | -0.174 |
ighthouse | -0.171 |
eger | -0.164 |
istar | -0.162 |
Token | working |
Token ID | 1762 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Reviewer | +2.200 |
iary | +2.099 |
romeda | +1.954 |
stroke | +1.843 |
raid | +1.833 |
Neg logit contributions | |
arta | -2.873 |
urrent | -2.368 |
ighthouse | -2.323 |
eger | -2.226 |
istar | -2.218 |
Token | at |
Token ID | 379 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
Reviewer | +0.237 |
iary | +0.223 |
romeda | +0.208 |
raid | +0.195 |
stroke | +0.194 |
Neg logit contributions | |
arta | -0.316 |
urrent | -0.264 |
ighthouse | -0.260 |
eger | -0.249 |
istar | -0.246 |
Token | an |
Token ID | 281 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Reviewer | +0.792 |
iary | +0.754 |
romeda | +0.699 |
raid | +0.659 |
stroke | +0.654 |
Neg logit contributions | |
arta | -1.075 |
urrent | -0.898 |
ighthouse | -0.879 |
eger | -0.846 |
istar | -0.836 |
Token | All |
Token ID | 1439 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
arta | +2.055 |
urrent | +1.685 |
ighthouse | +1.662 |
eger | +1.561 |
istar | +1.550 |
Neg logit contributions | |
Reviewer | -1.952 |
iary | -1.819 |
romeda | -1.716 |
raid | -1.625 |
stroke | -1.616 |
Token | ent |
Token ID | 298 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
arta | +7.275 |
ighthouse | +5.593 |
istar | +5.214 |
urrent | +5.024 |
eger | +4.675 |
Neg logit contributions | |
Reviewer | -15.937 |
romeda | -14.179 |
iary | -13.461 |
achev | -13.402 |
stroke | -13.270 |
Token | own |
Token ID | 593 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
arta | +5.059 |
urrent | +4.062 |
ighthouse | +3.880 |
eger | +3.583 |
istar | +3.481 |
Neg logit contributions | |
Reviewer | -7.803 |
romeda | -7.040 |
iary | -6.896 |
raid | -6.406 |
achev | -6.403 |
Token | construction |
Token ID | 5103 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Reviewer | +2.438 |
iary | +2.378 |
romeda | +2.200 |
raid | +2.108 |
stroke | +2.081 |
Neg logit contributions | |
arta | -2.506 |
urrent | -2.052 |
ighthouse | -1.993 |
eger | -1.881 |
istar | -1.879 |
Token | site |
Token ID | 2524 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Reviewer | +1.247 |
iary | +1.186 |
romeda | +1.098 |
raid | +1.038 |
stroke | +1.028 |
Neg logit contributions | |
arta | -1.638 |
urrent | -1.369 |
ighthouse | -1.346 |
eger | -1.285 |
istar | -1.269 |
Token | at |
Token ID | 379 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Reviewer | +1.462 |
iary | +1.400 |
romeda | +1.285 |
raid | +1.208 |
stroke | +1.201 |
Neg logit contributions | |
arta | -2.204 |
urrent | -1.864 |
ighthouse | -1.832 |
eger | -1.746 |
istar | -1.736 |
Token | problem |
Token ID | 1917 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Reviewer | +2.614 |
iary | +2.546 |
romeda | +2.302 |
stroke | +2.209 |
raid | +2.174 |
Neg logit contributions | |
arta | -3.336 |
urrent | -2.814 |
ighthouse | -2.763 |
eger | -2.621 |
byss | -2.590 |
Token | many |
Token ID | 867 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Reviewer | +1.706 |
iary | +1.635 |
romeda | +1.486 |
stroke | +1.412 |
raid | +1.385 |
Neg logit contributions | |
arta | -2.517 |
urrent | -2.100 |
ighthouse | -2.084 |
eger | -1.995 |
istar | -1.962 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
arta | +0.564 |
urrent | +0.464 |
ighthouse | +0.458 |
eger | +0.433 |
istar | +0.429 |
Neg logit contributions | |
Reviewer | -0.510 |
iary | -0.479 |
romeda | -0.451 |
raid | -0.425 |
stroke | -0.423 |
Token | Carolina |
Token ID | 5913 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
arta | +1.321 |
urrent | +1.098 |
ighthouse | +1.087 |
eger | +1.035 |
istar | +1.022 |
Neg logit contributions | |
Reviewer | -1.085 |
iary | -1.021 |
romeda | -0.958 |
raid | -0.899 |
stroke | -0.896 |
Token | 's |
Token ID | 338 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Reviewer | +1.492 |
iary | +1.387 |
romeda | +1.263 |
stroke | +1.181 |
raid | +1.178 |
Neg logit contributions | |
arta | -2.467 |
urrent | -2.080 |
ighthouse | -2.029 |
eger | -1.983 |
istar | -1.944 |
Token | offensive |
Token ID | 5859 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
arta | +4.380 |
ighthouse | +3.550 |
urrent | +3.549 |
istar | +3.319 |
eger | +3.286 |
Neg logit contributions | |
Reviewer | -5.178 |
iary | -4.757 |
romeda | -4.580 |
raid | -4.352 |
stroke | -4.265 |
Token | linemen |
Token ID | 41683 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
arta | +8.198 |
ighthouse | +6.308 |
urrent | +5.918 |
stration | +5.647 |
eger | +5.591 |
Neg logit contributions | |
Reviewer | -14.127 |
iary | -12.993 |
romeda | -12.958 |
raid | -12.071 |
achev | -11.939 |
Token | have |
Token ID | 423 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Reviewer | +2.042 |
iary | +2.024 |
romeda | +1.896 |
stroke | +1.787 |
raid | +1.778 |
Neg logit contributions | |
arta | -2.467 |
urrent | -2.032 |
ighthouse | -2.018 |
byss | -1.912 |
eger | -1.906 |
Token | -- |
Token ID | 1377 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
iary | +3.686 |
Reviewer | +3.658 |
romeda | +3.365 |
stroke | +3.256 |
pl | +3.100 |
Neg logit contributions | |
arta | -6.327 |
urrent | -5.287 |
ighthouse | -5.241 |
byss | -5.108 |
esson | -4.899 |
Token | he |
Token ID | 339 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
arta | +0.762 |
urrent | +0.629 |
ighthouse | +0.621 |
eger | +0.591 |
istar | +0.583 |
Neg logit contributions | |
Reviewer | -0.647 |
iary | -0.609 |
romeda | -0.573 |
raid | -0.539 |
stroke | -0.535 |
Token | can |
Token ID | 460 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
arta | +0.197 |
urrent | +0.163 |
ighthouse | +0.161 |
eger | +0.153 |
istar | +0.151 |
Neg logit contributions | |
Reviewer | -0.164 |
iary | -0.155 |
romeda | -0.146 |
raid | -0.137 |
stroke | -0.136 |
Token | maintained |
Token ID | 9456 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
arta | +0.901 |
urrent | +0.748 |
ighthouse | +0.739 |
eger | +0.705 |
istar | +0.696 |
Neg logit contributions | |
Reviewer | -0.733 |
iary | -0.689 |
romeda | -0.644 |
raid | -0.607 |
stroke | -0.601 |
Token | an |
Token ID | 281 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
Reviewer | +2.100 |
iary | +1.990 |
romeda | +1.849 |
stroke | +1.737 |
raid | +1.716 |
Neg logit contributions | |
arta | -3.034 |
urrent | -2.564 |
ighthouse | -2.506 |
eger | -2.401 |
istar | -2.382 |
Token | identity |
Token ID | 5369 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Reviewer | +0.534 |
iary | +0.508 |
romeda | +0.480 |
raid | +0.450 |
stroke | +0.449 |
Neg logit contributions | |
arta | -0.575 |
urrent | -0.469 |
ighthouse | -0.463 |
eger | -0.442 |
istar | -0.433 |
Token | as |
Token ID | 355 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
arta | +1.501 |
urrent | +1.246 |
ighthouse | +1.231 |
eger | +1.174 |
istar | +1.159 |
Neg logit contributions | |
Reviewer | -1.198 |
iary | -1.125 |
romeda | -1.058 |
raid | -0.994 |
stroke | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
arta | +2.710 |
urrent | +2.253 |
ighthouse | +2.232 |
eger | +2.116 |
istar | +2.093 |
Neg logit contributions | |
Reviewer | -2.270 |
iary | -2.132 |
romeda | -2.006 |
raid | -1.875 |
stroke | -1.859 |
Token | rushing |
Token ID | 15795 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
arta | +6.032 |
urrent | +4.841 |
ighthouse | +4.807 |
eger | +4.601 |
stration | +4.555 |
Neg logit contributions | |
Reviewer | -6.223 |
iary | -5.744 |
romeda | -5.463 |
achev | -5.106 |
stroke | -5.104 |
Token | offense |
Token ID | 6907 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
arta | +8.798 |
ighthouse | +6.545 |
urrent | +6.258 |
stration | +6.212 |
suburb | +6.166 |
Neg logit contributions | |
Reviewer | -13.534 |
iary | -12.122 |
romeda | -11.961 |
achev | -11.726 |
raid | -11.388 |
Token | that |
Token ID | 326 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
arta | +5.851 |
urrent | +4.669 |
ighthouse | +4.627 |
eger | +4.496 |
istar | +4.341 |
Neg logit contributions | |
Reviewer | -5.779 |
iary | -5.254 |
romeda | -5.003 |
raid | -4.807 |
stroke | -4.673 |
Token | uses |
Token ID | 3544 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
arta | +1.184 |
urrent | +0.965 |
ighthouse | +0.953 |
eger | +0.907 |
istar | +0.890 |
Neg logit contributions | |
Reviewer | -1.090 |
iary | -1.023 |
romeda | -0.964 |
raid | -0.912 |
stroke | -0.906 |
Token | bigger |
Token ID | 5749 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
arta | +2.260 |
urrent | +1.865 |
ighthouse | +1.837 |
eger | +1.758 |
istar | +1.719 |
Neg logit contributions | |
Reviewer | -1.917 |
iary | -1.787 |
romeda | -1.676 |
raid | -1.579 |
stroke | -1.563 |
Token | personnel |
Token ID | 8213 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
arta | +3.694 |
urrent | +3.005 |
ighthouse | +2.944 |
eger | +2.849 |
istar | +2.774 |
Neg logit contributions | |
Reviewer | -3.263 |
iary | -3.018 |
romeda | -2.861 |
raid | -2.724 |
stroke | -2.668 |
Token | An |
Token ID | 2025 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
arta | +3.768 |
urrent | +3.114 |
ighthouse | +3.068 |
eger | +2.896 |
istar | +2.870 |
Neg logit contributions | |
Reviewer | -3.328 |
iary | -3.212 |
romeda | -3.075 |
raid | -2.824 |
stroke | -2.809 |
Token | ore |
Token ID | 382 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
arta | +0.594 |
urrent | +0.492 |
ighthouse | +0.486 |
eger | +0.464 |
istar | +0.455 |
Neg logit contributions | |
Reviewer | -0.484 |
iary | -0.459 |
romeda | -0.429 |
raid | -0.402 |
stroke | -0.401 |
Token | x |
Token ID | 87 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
arta | +4.594 |
urrent | +3.522 |
ighthouse | +3.387 |
eger | +3.243 |
istar | +3.136 |
Neg logit contributions | |
Reviewer | -8.648 |
iary | -8.129 |
romeda | -7.861 |
raid | -7.528 |
stroke | -7.338 |
Token | ic |
Token ID | 291 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Reviewer | +2.150 |
iary | +2.102 |
romeda | +1.911 |
raid | +1.797 |
stroke | +1.787 |
Neg logit contributions | |
arta | -3.032 |
urrent | -2.548 |
ighthouse | -2.519 |
eger | -2.404 |
byss | -2.356 |
Token | Karen |
Token ID | 18678 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
arta | +5.794 |
urrent | +4.753 |
ighthouse | +4.643 |
istar | +4.407 |
eger | +4.404 |
Neg logit contributions | |
Reviewer | -4.995 |
iary | -4.532 |
romeda | -4.465 |
raid | -4.129 |
stroke | -4.107 |
Token | Carpenter |
Token ID | 32659 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
arta | +3.538 |
urrent | +2.883 |
ighthouse | +2.824 |
eger | +2.687 |
istar | +2.666 |
Neg logit contributions | |
Reviewer | -3.502 |
iary | -3.309 |
romeda | -3.150 |
raid | -2.953 |
stroke | -2.944 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
arta | +10.120 |
urrent | +7.985 |
ighthouse | +7.494 |
istar | +7.479 |
stration | +7.329 |
Neg logit contributions | |
Reviewer | -11.752 |
romeda | -11.010 |
iary | -11.003 |
raid | -10.327 |
achev | -10.067 |
Token | 01 |
Token ID | 486 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
arta | +0.905 |
urrent | +0.756 |
ighthouse | +0.747 |
eger | +0.714 |
istar | +0.706 |
Neg logit contributions | |
Reviewer | -0.639 |
iary | -0.596 |
romeda | -0.568 |
raid | -0.522 |
stroke | -0.517 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
arta | +4.954 |
urrent | +3.839 |
ighthouse | +3.819 |
eger | +3.569 |
istar | +3.564 |
Neg logit contributions | |
Reviewer | -5.532 |
iary | -5.279 |
romeda | -5.144 |
raid | -4.815 |
stroke | -4.759 |
Token | O |
Token ID | 440 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
arta | +2.763 |
urrent | +2.096 |
ighthouse | +2.043 |
stration | +1.871 |
istar | +1.869 |
Neg logit contributions | |
Reviewer | -3.916 |
iary | -3.707 |
romeda | -3.616 |
raid | -3.489 |
achev | -3.397 |
Token | & |
Token ID | 5 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Reviewer | +0.224 |
iary | +0.217 |
romeda | +0.209 |
raid | +0.201 |
stroke | +0.200 |
Neg logit contributions | |
arta | -0.089 |
urrent | -0.059 |
ighthouse | -0.058 |
eger | -0.051 |
istar | -0.049 |
Token | andro |
Token ID | 28092 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
arta | +4.377 |
urrent | +3.438 |
ighthouse | +3.375 |
eger | +3.192 |
istar | +3.155 |
Neg logit contributions | |
Reviewer | -5.153 |
iary | -4.682 |
romeda | -4.539 |
stroke | -4.329 |
raid | -4.326 |
Token | Pav |
Token ID | 24081 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
arta | +8.496 |
urrent | +6.906 |
ighthouse | +6.783 |
eger | +6.569 |
stration | +6.405 |
Neg logit contributions | |
Reviewer | -7.544 |
iary | -6.667 |
romeda | -6.434 |
raid | -6.065 |
stroke | -5.869 |
Token | olini |
Token ID | 43232 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
arta | +2.425 |
urrent | +2.016 |
ighthouse | +1.986 |
eger | +1.904 |
istar | +1.884 |
Neg logit contributions | |
Reviewer | -1.879 |
iary | -1.740 |
romeda | -1.637 |
raid | -1.530 |
stroke | -1.521 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
arta | +0.095 |
urrent | +0.079 |
ighthouse | +0.078 |
eger | +0.075 |
istar | +0.074 |
Neg logit contributions | |
Reviewer | -0.077 |
iary | -0.073 |
romeda | -0.068 |
raid | -0.064 |
stroke | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
arta | +0.167 |
urrent | +0.138 |
ighthouse | +0.136 |
eger | +0.130 |
istar | +0.128 |
Neg logit contributions | |
Reviewer | -0.137 |
iary | -0.130 |
romeda | -0.122 |
raid | -0.114 |
stroke | -0.114 |
Token | Dec |
Token ID | 4280 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
arta | +4.498 |
urrent | +3.728 |
ighthouse | +3.632 |
istar | +3.424 |
eger | +3.419 |
Neg logit contributions | |
Reviewer | -4.086 |
iary | -3.751 |
romeda | -3.516 |
stroke | -3.326 |
raid | -3.323 |
Token | ima |
Token ID | 8083 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
arta | +13.216 |
urrent | +11.246 |
ighthouse | +10.454 |
esson | +9.861 |
istar | +9.830 |
Neg logit contributions | |
Reviewer | -10.400 |
iary | -8.430 |
romeda | -8.186 |
stroke | -7.536 |
raid | -7.312 |
Token | Fl |
Token ID | 1610 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Reviewer | +0.130 |
iary | +0.124 |
romeda | +0.116 |
raid | +0.110 |
stroke | +0.109 |
Neg logit contributions | |
arta | -0.144 |
urrent | -0.119 |
ighthouse | -0.117 |
eger | -0.111 |
istar | -0.110 |
Token | ott |
Token ID | 1252 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
arta | +3.419 |
urrent | +2.830 |
ighthouse | +2.815 |
istar | +2.643 |
eger | +2.636 |
Neg logit contributions | |
Reviewer | -2.849 |
iary | -2.604 |
romeda | -2.461 |
stroke | -2.310 |
raid | -2.287 |
Token | ig |
Token ID | 328 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
Reviewer | +1.899 |
iary | +1.862 |
romeda | +1.749 |
raid | +1.641 |
stroke | +1.625 |
Neg logit contributions | |
arta | -2.069 |
urrent | -1.702 |
ighthouse | -1.676 |
eger | -1.603 |
byss | -1.568 |
Token | lia |
Token ID | 24660 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
arta | +1.218 |
urrent | +1.004 |
ighthouse | +0.990 |
eger | +0.943 |
istar | +0.930 |
Neg logit contributions | |
Reviewer | -1.017 |
iary | -0.954 |
romeda | -0.897 |
raid | -0.843 |
stroke | -0.840 |
Token | - |
Token ID | 12 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
arta | +5.254 |
urrent | +4.201 |
ighthouse | +4.120 |
istar | +3.939 |
eger | +3.881 |
Neg logit contributions | |
Reviewer | -5.439 |
iary | -5.121 |
romeda | -4.932 |
raid | -4.596 |
stroke | -4.487 |
Token | Ang |
Token ID | 13450 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
arta | +5.610 |
urrent | +4.610 |
ighthouse | +4.565 |
eger | +4.273 |
istar | +4.261 |
Neg logit contributions | |
Reviewer | -4.948 |
iary | -4.869 |
romeda | -4.702 |
raid | -4.295 |
achev | -4.253 |
Token | ry |
Token ID | 563 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
arta | +1.832 |
urrent | +1.458 |
ighthouse | +1.438 |
eger | +1.353 |
istar | +1.339 |
Neg logit contributions | |
Reviewer | -2.092 |
iary | -1.983 |
romeda | -1.881 |
raid | -1.784 |
stroke | -1.780 |
Token | Video |
Token ID | 7623 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
arta | +6.727 |
urrent | +5.466 |
ighthouse | +5.446 |
eger | +5.141 |
esson | +5.119 |
Neg logit contributions | |
Reviewer | -5.996 |
iary | -5.569 |
romeda | -5.277 |
raid | -4.963 |
stroke | -4.940 |
Token | Game |
Token ID | 3776 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
arta | +6.376 |
urrent | +5.237 |
ighthouse | +5.104 |
eger | +4.808 |
stration | +4.792 |
Neg logit contributions | |
Reviewer | -6.413 |
iary | -5.720 |
romeda | -5.647 |
stroke | -5.299 |
achev | -5.254 |
Token | Nerd |
Token ID | 44031 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arta | +7.019 |
urrent | +5.788 |
ighthouse | +5.544 |
stration | +5.321 |
istar | +5.298 |
Neg logit contributions | |
Reviewer | -6.684 |
iary | -6.109 |
romeda | -5.983 |
raid | -5.680 |
stroke | -5.639 |
Token | Guy |
Token ID | 13145 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
arta | +11.299 |
urrent | +9.159 |
stration | +9.000 |
ighthouse | +8.850 |
istar | +8.835 |
Neg logit contributions | |
Reviewer | -10.378 |
romeda | -9.297 |
iary | -8.994 |
raid | -8.612 |
stroke | -8.566 |
Token | - |
Token ID | 12 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
arta | +6.473 |
urrent | +5.198 |
ighthouse | +5.017 |
stration | +4.866 |
istar | +4.842 |
Neg logit contributions | |
Reviewer | -6.763 |
iary | -6.252 |
romeda | -6.139 |
raid | -5.741 |
stroke | -5.685 |
Token | E |
Token ID | 36 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
arta | +5.331 |
urrent | +4.389 |
ighthouse | +4.335 |
eger | +4.066 |
istar | +4.055 |
Neg logit contributions | |
Reviewer | -4.693 |
iary | -4.584 |
romeda | -4.431 |
raid | -4.045 |
stroke | -4.018 |
Token | ps |
Token ID | 862 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Reviewer | +0.565 |
iary | +0.534 |
romeda | +0.502 |
raid | +0.482 |
stroke | +0.474 |
Neg logit contributions | |
arta | -0.580 |
urrent | -0.472 |
ighthouse | -0.466 |
eger | -0.440 |
istar | -0.434 |
Token | ch |
Token ID | 354 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Reviewer | +1.046 |
iary | +1.004 |
romeda | +0.912 |
stroke | +0.854 |
raid | +0.850 |
Neg logit contributions | |
arta | -1.669 |
urrent | -1.415 |
ighthouse | -1.398 |
eger | -1.327 |
istar | -1.322 |
Token | insufficient |
Token ID | 19022 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arta | +0.015 |
urrent | +0.013 |
ighthouse | +0.012 |
eger | +0.012 |
istar | +0.012 |
Neg logit contributions | |
Reviewer | -0.012 |
iary | -0.011 |
romeda | -0.010 |
raid | -0.010 |
stroke | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
arta | +1.603 |
urrent | +1.328 |
ighthouse | +1.311 |
eger | +1.253 |
istar | +1.237 |
Neg logit contributions | |
Reviewer | -1.289 |
iary | -1.212 |
romeda | -1.142 |
raid | -1.070 |
stroke | -1.060 |
Token | A |
Token ID | 317 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
arta | +2.521 |
urrent | +2.012 |
ighthouse | +1.982 |
eger | +1.861 |
istar | +1.841 |
Neg logit contributions | |
Reviewer | -2.689 |
iary | -2.543 |
romeda | -2.428 |
raid | -2.327 |
stroke | -2.294 |
Token | majority |
Token ID | 3741 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
arta | +3.260 |
urrent | +2.685 |
ighthouse | +2.618 |
eger | +2.548 |
stration | +2.482 |
Neg logit contributions | |
Reviewer | -2.960 |
iary | -2.774 |
romeda | -2.639 |
raid | -2.464 |
stroke | -2.440 |
Token | of |
Token ID | 286 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
arta | +3.282 |
urrent | +2.710 |
ighthouse | +2.674 |
eger | +2.527 |
istar | +2.502 |
Neg logit contributions | |
Reviewer | -2.668 |
iary | -2.512 |
romeda | -2.372 |
raid | -2.221 |
stroke | -2.185 |
Token | average |
Token ID | 2811 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arta | +6.005 |
urrent | +4.959 |
ighthouse | +4.830 |
eger | +4.621 |
istar | +4.533 |
Neg logit contributions | |
Reviewer | -6.014 |
iary | -5.592 |
romeda | -5.269 |
raid | -5.097 |
stroke | -4.932 |
Token | Germans |
Token ID | 16064 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
arta | +9.539 |
urrent | +7.411 |
suburb | +6.985 |
ighthouse | +6.974 |
isu | +6.751 |
Neg logit contributions | |
Reviewer | -12.288 |
iary | -11.397 |
romeda | -11.225 |
raid | -11.089 |
achev | -10.496 |
Token | sat |
Token ID | 3332 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
arta | +3.747 |
urrent | +3.053 |
ighthouse | +3.036 |
eger | +2.857 |
istar | +2.830 |
Neg logit contributions | |
Reviewer | -3.495 |
iary | -3.245 |
romeda | -3.068 |
raid | -2.919 |
stroke | -2.862 |
Token | on |
Token ID | 319 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Reviewer | +1.173 |
iary | +1.107 |
romeda | +1.020 |
stroke | +0.961 |
raid | +0.953 |
Neg logit contributions | |
arta | -1.608 |
urrent | -1.348 |
ighthouse | -1.323 |
eger | -1.270 |
istar | -1.250 |
Token | their |
Token ID | 511 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
arta | +2.983 |
urrent | +2.450 |
ighthouse | +2.427 |
eger | +2.321 |
stration | +2.274 |
Neg logit contributions | |
Reviewer | -2.615 |
iary | -2.466 |
romeda | -2.339 |
raid | -2.202 |
stroke | -2.172 |
Token | hands |
Token ID | 2832 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
arta | +3.912 |
urrent | +3.292 |
ighthouse | +3.268 |
eger | +3.145 |
stration | +3.104 |
Neg logit contributions | |
Reviewer | -2.107 |
iary | -1.947 |
romeda | -1.828 |
raid | -1.659 |
stroke | -1.615 |
Token | SC |
Token ID | 6173 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
arta | +0.322 |
urrent | +0.264 |
ighthouse | +0.260 |
eger | +0.247 |
istar | +0.243 |
Neg logit contributions | |
Reviewer | -0.295 |
iary | -0.279 |
romeda | -0.262 |
raid | -0.248 |
stroke | -0.247 |
Token | OTT |
Token ID | 29089 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
arta | +6.558 |
urrent | +5.475 |
ighthouse | +5.018 |
eger | +4.703 |
ISM | +4.699 |
Neg logit contributions | |
Reviewer | -7.992 |
iary | -7.342 |
romeda | -6.940 |
stroke | -6.922 |
raid | -6.596 |
Token | MOR |
Token ID | 35208 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
arta | +2.807 |
urrent | +2.325 |
ighthouse | +2.286 |
eger | +2.185 |
istar | +2.153 |
Neg logit contributions | |
Reviewer | -2.251 |
iary | -2.088 |
romeda | -1.988 |
raid | -1.862 |
stroke | -1.838 |
Token | GAN |
Token ID | 45028 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
arta | +2.730 |
urrent | +2.212 |
ighthouse | +2.173 |
eger | +2.078 |
istar | +2.036 |
Neg logit contributions | |
Reviewer | -2.736 |
iary | -2.597 |
romeda | -2.501 |
raid | -2.333 |
stroke | -2.316 |
Token | / |
Token ID | 14 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
arta | +3.682 |
urrent | +2.964 |
ighthouse | +2.917 |
eger | +2.798 |
istar | +2.753 |
Neg logit contributions | |
Reviewer | -3.490 |
iary | -3.243 |
romeda | -3.091 |
raid | -2.932 |
stroke | -2.911 |
Token | RE |
Token ID | 2200 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arta | +1.959 |
urrent | +1.561 |
ighthouse | +1.524 |
eger | +1.436 |
istar | +1.432 |
Neg logit contributions | |
Reviewer | -2.184 |
iary | -2.080 |
romeda | -1.987 |
raid | -1.877 |
stroke | -1.849 |
Token | UTERS |
Token ID | 14974 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
arta | +3.341 |
ISM | +1.908 |
mington | +1.805 |
ighthouse | +1.756 |
urrent | +1.701 |
Neg logit contributions | |
Reviewer | -18.643 |
iary | -17.416 |
romeda | -17.286 |
raid | -17.141 |
unin | -15.940 |
Token | Supporters |
Token ID | 39995 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
arta | +6.091 |
urrent | +4.863 |
ighthouse | +4.768 |
istar | +4.640 |
esson | +4.572 |
Neg logit contributions | |
Reviewer | -6.128 |
iary | -5.599 |
romeda | -5.253 |
raid | -5.158 |
stroke | -5.027 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Reviewer | +3.551 |
iary | +3.492 |
romeda | +3.275 |
stroke | +3.064 |
raid | +3.049 |
Neg logit contributions | |
arta | -4.695 |
urrent | -3.941 |
ighthouse | -3.861 |
eger | -3.715 |
byss | -3.650 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Reviewer | +1.015 |
iary | +0.961 |
romeda | +0.902 |
raid | +0.835 |
stroke | +0.832 |
Neg logit contributions | |
arta | -1.358 |
urrent | -1.135 |
ighthouse | -1.122 |
eger | -1.078 |
istar | -1.052 |
Token | presidential |
Token ID | 4787 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
arta | +4.027 |
urrent | +3.211 |
ighthouse | +3.155 |
istar | +2.998 |
eger | +2.953 |
Neg logit contributions | |
Reviewer | -4.273 |
iary | -3.983 |
romeda | -3.793 |
raid | -3.678 |
stroke | -3.620 |
Token | attorney |
Token ID | 6136 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
Reviewer | +1.762 |
iary | +1.699 |
romeda | +1.593 |
raid | +1.493 |
stroke | +1.488 |
Neg logit contributions | |
arta | -2.208 |
urrent | -1.828 |
ighthouse | -1.800 |
eger | -1.721 |
istar | -1.701 |
Token | representing |
Token ID | 10200 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
arta | +0.779 |
urrent | +0.648 |
ighthouse | +0.641 |
eger | +0.612 |
istar | +0.603 |
Neg logit contributions | |
Reviewer | -0.610 |
iary | -0.574 |
romeda | -0.538 |
raid | -0.504 |
stroke | -0.501 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
arta | +2.695 |
urrent | +2.143 |
ighthouse | +2.126 |
eger | +2.011 |
istar | +1.974 |
Neg logit contributions | |
Reviewer | -2.995 |
iary | -2.823 |
romeda | -2.670 |
raid | -2.542 |
stroke | -2.525 |
Token | city |
Token ID | 1748 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
Reviewer | +1.320 |
iary | +1.265 |
romeda | +1.190 |
raid | +1.113 |
stroke | +1.109 |
Neg logit contributions | |
arta | -1.651 |
urrent | -1.370 |
ighthouse | -1.352 |
eger | -1.283 |
istar | -1.278 |
Token | and |
Token ID | 290 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
arta | +1.279 |
urrent | +1.068 |
ighthouse | +1.055 |
eger | +1.007 |
istar | +0.993 |
Neg logit contributions | |
Reviewer | -0.962 |
iary | -0.903 |
romeda | -0.846 |
raid | -0.791 |
stroke | -0.787 |
Token | All |
Token ID | 1439 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
arta | +4.161 |
ighthouse | +3.225 |
urrent | +3.212 |
eger | +2.953 |
stration | +2.843 |
Neg logit contributions | |
Reviewer | -5.923 |
iary | -5.453 |
romeda | -5.065 |
raid | -4.939 |
achev | -4.912 |
Token | ent |
Token ID | 298 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
arta | +6.747 |
ighthouse | +4.926 |
istar | +4.560 |
urrent | +4.483 |
eger | +4.000 |
Neg logit contributions | |
Reviewer | -15.610 |
romeda | -13.828 |
iary | -13.325 |
achev | -13.186 |
stroke | -13.114 |
Token | own |
Token ID | 593 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
arta | +4.998 |
urrent | +3.945 |
ighthouse | +3.797 |
eger | +3.511 |
istar | +3.440 |
Neg logit contributions | |
Reviewer | -7.559 |
romeda | -6.788 |
iary | -6.637 |
stroke | -6.142 |
achev | -6.139 |
Token | Detective |
Token ID | 20220 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
Reviewer | +4.259 |
iary | +4.194 |
romeda | +3.864 |
raid | +3.692 |
stroke | +3.620 |
Neg logit contributions | |
arta | -5.477 |
urrent | -4.608 |
ighthouse | -4.476 |
istar | -4.316 |
eger | -4.267 |
Token | Christie |
Token ID | 16929 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Reviewer | +0.386 |
iary | +0.364 |
romeda | +0.340 |
raid | +0.319 |
stroke | +0.318 |
Neg logit contributions | |
arta | -0.499 |
urrent | -0.416 |
ighthouse | -0.411 |
eger | -0.393 |
istar | -0.388 |
Token | Cor |
Token ID | 2744 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
arta | +3.063 |
urrent | +2.515 |
ighthouse | +2.489 |
eger | +2.381 |
istar | +2.333 |
Neg logit contributions | |
Reviewer | -2.524 |
iary | -2.345 |
romeda | -2.225 |
raid | -2.078 |
stroke | -2.058 |
Token | larger |
Token ID | 4025 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Reviewer | +3.474 |
iary | +3.242 |
romeda | +2.845 |
tera | +2.765 |
eter | +2.748 |
Neg logit contributions | |
arta | -4.741 |
ighthouse | -3.972 |
urrent | -3.948 |
eger | -3.859 |
istar | -3.733 |
Token | image |
Token ID | 2939 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Reviewer | +5.918 |
iary | +5.495 |
romeda | +5.011 |
stroke | +4.902 |
eter | +4.867 |
Neg logit contributions | |
arta | -7.936 |
urrent | -6.840 |
byss | -6.789 |
ighthouse | -6.735 |
eger | -6.488 |
Token |
|
Token ID | 198 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Reviewer | +6.740 |
iary | +6.545 |
romeda | +5.754 |
pl | +5.629 |
stroke | +5.458 |
Neg logit contributions | |
arta | -10.466 |
mosqu | -9.101 |
byss | -9.080 |
ighthouse | -9.032 |
urrent | -8.995 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Reviewer | +4.784 |
iary | +4.612 |
stroke | +4.113 |
pl | +4.083 |
romeda | +3.968 |
Neg logit contributions | |
arta | -7.208 |
mosqu | -6.517 |
urrent | -6.204 |
byss | -6.167 |
ighthouse | -6.095 |
Token | larg |
Token ID | 15521 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +4.631 |
iary | +4.274 |
romeda | +4.055 |
stroke | +4.039 |
pl | +3.966 |
Neg logit contributions | |
arta | -4.701 |
ighthouse | -4.032 |
istar | -3.836 |
urrent | -3.826 |
eger | -3.701 |
Token | er |
Token ID | 263 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
iary | +6.209 |
Reviewer | +5.875 |
eter | +5.775 |
romeda | +5.216 |
pl | +5.204 |
Neg logit contributions | |
arta | -16.164 |
mosqu | -14.394 |
byss | -14.022 |
urrent | -13.859 |
kefeller | -13.751 |
Token | image |
Token ID | 2939 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iary | +8.147 |
Reviewer | +7.846 |
eter | +7.656 |
romeda | +7.294 |
pl | +7.243 |
Neg logit contributions | |
arta | -16.837 |
byss | -16.165 |
mosqu | -16.062 |
urrent | -15.229 |
kefeller | -15.218 |
Token | T |
Token ID | 309 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Reviewer | +7.983 |
iary | +7.594 |
pl | +6.630 |
romeda | +6.565 |
eter | +6.424 |
Neg logit contributions | |
arta | -15.456 |
byss | -14.843 |
kefeller | -14.358 |
ighthouse | -14.247 |
eger | -14.188 |
Token | IFF |
Token ID | 29267 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
iary | +3.970 |
Reviewer | +3.796 |
romeda | +3.432 |
raid | +3.349 |
stroke | +3.330 |
Neg logit contributions | |
arta | -7.646 |
ighthouse | -6.656 |
urrent | -6.559 |
byss | -6.312 |
mington | -6.287 |
Token | original |
Token ID | 2656 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Reviewer | +4.747 |
iary | +4.651 |
romeda | +4.063 |
stroke | +3.997 |
raid | +3.931 |
Neg logit contributions | |
arta | -7.644 |
byss | -6.913 |
ighthouse | -6.896 |
urrent | -6.599 |
eger | -6.576 |
Token | image |
Token ID | 2939 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Reviewer | +6.549 |
iary | +6.387 |
romeda | +5.699 |
eter | +5.619 |
pl | +5.616 |
Neg logit contributions | |
arta | -9.305 |
urrent | -7.936 |
byss | -7.757 |
ighthouse | -7.733 |
eger | -7.506 |
Token | necessarily |
Token ID | 6646 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
Reviewer | +2.168 |
iary | +2.061 |
romeda | +1.924 |
stroke | +1.785 |
raid | +1.764 |
Neg logit contributions | |
arta | -3.298 |
urrent | -2.783 |
ighthouse | -2.743 |
eger | -2.638 |
stration | -2.587 |
Token | during |
Token ID | 1141 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Reviewer | +0.838 |
iary | +0.796 |
romeda | +0.747 |
stroke | +0.698 |
raid | +0.697 |
Neg logit contributions | |
arta | -1.046 |
urrent | -0.867 |
ighthouse | -0.856 |
eger | -0.816 |
istar | -0.802 |
Token | capture |
Token ID | 8006 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Reviewer | +4.070 |
iary | +3.916 |
romeda | +3.689 |
stroke | +3.488 |
raid | +3.373 |
Neg logit contributions | |
arta | -5.133 |
urrent | -4.216 |
ighthouse | -4.207 |
eger | -3.948 |
byss | -3.929 |
Token | or |
Token ID | 393 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Reviewer | +1.058 |
iary | +0.982 |
romeda | +0.919 |
stroke | +0.872 |
raid | +0.864 |
Neg logit contributions | |
arta | -1.425 |
urrent | -1.195 |
ighthouse | -1.184 |
eger | -1.129 |
istar | -1.102 |
Token | on |
Token ID | 319 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Reviewer | +4.181 |
iary | +3.967 |
romeda | +3.770 |
stroke | +3.492 |
raid | +3.376 |
Neg logit contributions | |
arta | -5.152 |
urrent | -4.245 |
ighthouse | -4.196 |
eger | -3.969 |
byss | -3.935 |
Token | - |
Token ID | 12 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Reviewer | +6.203 |
iary | +5.892 |
romeda | +5.613 |
stroke | +5.323 |
raid | +5.095 |
Neg logit contributions | |
arta | -7.641 |
urrent | -6.259 |
ighthouse | -6.234 |
byss | -5.843 |
eger | -5.835 |
Token | camera |
Token ID | 25695 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Reviewer | +11.158 |
stroke | +10.812 |
iary | +10.243 |
raid | +9.976 |
pl | +9.872 |
Neg logit contributions | |
arta | -13.823 |
urrent | -11.698 |
ighthouse | -11.620 |
mosqu | -10.952 |
eger | -10.917 |
Token | playback |
Token ID | 16388 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Reviewer | +4.612 |
iary | +4.341 |
romeda | +4.155 |
stroke | +3.883 |
raid | +3.730 |
Neg logit contributions | |
arta | -5.415 |
urrent | -4.457 |
ighthouse | -4.423 |
byss | -4.138 |
eger | -4.112 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Reviewer | +2.390 |
iary | +2.203 |
romeda | +2.061 |
stroke | +1.959 |
raid | +1.911 |
Neg logit contributions | |
arta | -3.481 |
urrent | -2.933 |
ighthouse | -2.915 |
eger | -2.782 |
istar | -2.700 |
Token | I |
Token ID | 314 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Reviewer | +0.676 |
iary | +0.642 |
romeda | +0.605 |
stroke | +0.569 |
raid | +0.569 |
Neg logit contributions | |
arta | -0.713 |
urrent | -0.583 |
ighthouse | -0.573 |
eger | -0.545 |
istar | -0.535 |
Token | was |
Token ID | 373 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Reviewer | +1.819 |
iary | +1.744 |
romeda | +1.643 |
raid | +1.546 |
stroke | +1.542 |
Neg logit contributions | |
arta | -2.219 |
urrent | -1.827 |
ighthouse | -1.807 |
eger | -1.731 |
istar | -1.697 |
Token | if |
Token ID | 611 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Reviewer | +2.439 |
iary | +2.307 |
romeda | +2.174 |
stroke | +2.014 |
raid | +2.012 |
Neg logit contributions | |
arta | -3.327 |
urrent | -2.793 |
ighthouse | -2.742 |
eger | -2.642 |
byss | -2.596 |
Token | it |
Token ID | 340 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Reviewer | +3.378 |
iary | +3.190 |
romeda | +3.014 |
raid | +2.801 |
stroke | +2.794 |
Neg logit contributions | |
arta | -4.933 |
urrent | -4.175 |
ighthouse | -4.112 |
eger | -3.971 |
byss | -3.921 |
Token | 's |
Token ID | 338 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +1.921 |
iary | +1.890 |
romeda | +1.747 |
stroke | +1.628 |
raid | +1.605 |
Neg logit contributions | |
arta | -2.802 |
urrent | -2.371 |
ighthouse | -2.341 |
eger | -2.238 |
byss | -2.232 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Reviewer | +1.446 |
iary | +1.375 |
romeda | +1.288 |
stroke | +1.205 |
raid | +1.202 |
Neg logit contributions | |
arta | -1.895 |
urrent | -1.579 |
ighthouse | -1.559 |
eger | -1.492 |
istar | -1.466 |
Token | mum |
Token ID | 25682 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
Reviewer | +3.049 |
iary | +2.942 |
romeda | +2.711 |
raid | +2.587 |
stroke | +2.581 |
Neg logit contributions | |
arta | -3.867 |
urrent | -3.256 |
ighthouse | -3.194 |
istar | -3.021 |
eger | -3.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Reviewer | +0.570 |
iary | +0.537 |
romeda | +0.500 |
raid | +0.469 |
stroke | +0.466 |
Neg logit contributions | |
arta | -0.767 |
urrent | -0.644 |
ighthouse | -0.633 |
eger | -0.607 |
istar | -0.600 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
romeda | +8.322 |
iary | +8.236 |
Reviewer | +7.816 |
pl | +7.097 |
raid | +7.074 |
Neg logit contributions | |
arta | -14.678 |
urrent | -13.287 |
ighthouse | -13.255 |
byss | -12.573 |
REDACTED | -12.472 |
Token | business |
Token ID | 1597 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Reviewer | +1.329 |
iary | +1.272 |
romeda | +1.180 |
stroke | +1.107 |
raid | +1.105 |
Neg logit contributions | |
arta | -1.776 |
urrent | -1.495 |
ighthouse | -1.471 |
eger | -1.400 |
istar | -1.387 |
Token | that |
Token ID | 326 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
Reviewer | +1.810 |
iary | +1.720 |
romeda | +1.606 |
stroke | +1.502 |
raid | +1.499 |
Neg logit contributions | |
arta | -2.449 |
urrent | -2.062 |
ighthouse | -2.024 |
eger | -1.934 |
istar | -1.913 |
Token | 's |
Token ID | 338 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Reviewer | +0.614 |
iary | +0.581 |
romeda | +0.546 |
raid | +0.512 |
stroke | +0.510 |
Neg logit contributions | |
arta | -0.731 |
urrent | -0.605 |
ighthouse | -0.596 |
eger | -0.569 |
istar | -0.560 |
Token | not |
Token ID | 407 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
arta | +2.187 |
urrent | +1.781 |
ighthouse | +1.769 |
eger | +1.686 |
istar | +1.675 |
Neg logit contributions | |
Reviewer | -1.991 |
iary | -1.852 |
romeda | -1.738 |
raid | -1.649 |
stroke | -1.631 |
Token | to |
Token ID | 284 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Reviewer | +3.314 |
iary | +3.139 |
romeda | +2.844 |
stroke | +2.727 |
raid | +2.598 |
Neg logit contributions | |
arta | -5.145 |
urrent | -4.318 |
ighthouse | -4.260 |
eger | -4.084 |
byss | -4.074 |
Token | be |
Token ID | 307 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
iary | +5.639 |
Reviewer | +5.570 |
romeda | +5.110 |
stroke | +4.801 |
pl | +4.719 |
Neg logit contributions | |
arta | -8.772 |
urrent | -7.368 |
byss | -7.132 |
ighthouse | -7.114 |
mosqu | -7.044 |
Token | equally |
Token ID | 8603 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
Reviewer | +2.056 |
iary | +1.841 |
romeda | +1.686 |
stroke | +1.415 |
raid | +1.397 |
Neg logit contributions | |
arta | -5.934 |
urrent | -5.131 |
ighthouse | -5.059 |
eger | -5.024 |
stration | -4.844 |
Token | as |
Token ID | 355 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Reviewer | +4.211 |
iary | +4.061 |
romeda | +3.703 |
stroke | +3.420 |
raid | +3.389 |
Neg logit contributions | |
arta | -7.243 |
urrent | -6.238 |
ighthouse | -6.012 |
eger | -5.894 |
byss | -5.890 |
Token | tight |
Token ID | 5381 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Reviewer | +3.884 |
iary | +3.740 |
romeda | +3.502 |
raid | +3.347 |
stroke | +3.301 |
Neg logit contributions | |
arta | -3.595 |
urrent | -2.933 |
ighthouse | -2.804 |
eger | -2.687 |
byss | -2.669 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Reviewer | +6.027 |
iary | +5.790 |
romeda | +5.374 |
stroke | +5.026 |
raid | +4.909 |
Neg logit contributions | |
arta | -9.549 |
urrent | -8.423 |
ighthouse | -8.151 |
byss | -7.830 |
mosqu | -7.709 |
Token | f |
Token ID | 69 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Reviewer | +6.334 |
iary | +5.961 |
pl | +5.729 |
raid | +5.715 |
stroke | +5.615 |
Neg logit contributions | |
arta | -17.163 |
mosqu | -16.586 |
byss | -15.116 |
�� | -15.061 |
urrent | -14.998 |
Token | isted |
Token ID | 6347 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Reviewer | +1.709 |
iary | +1.518 |
raid | +1.078 |
romeda | +1.008 |
eter | +0.746 |
Neg logit contributions | |
arta | -9.375 |
byss | -8.237 |
urrent | -8.217 |
mosqu | -8.176 |
ighthouse | -8.171 |
Token | as |
Token ID | 355 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Reviewer | +4.717 |
iary | +4.243 |
romeda | +3.975 |
raid | +3.795 |
stroke | +3.600 |
Neg logit contributions | |
arta | -8.764 |
urrent | -7.580 |
ighthouse | -7.395 |
eger | -7.225 |
isu | -7.084 |
Token | the |
Token ID | 262 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Reviewer | +4.341 |
iary | +4.096 |
romeda | +3.775 |
stroke | +3.477 |
raid | +3.434 |
Neg logit contributions | |
arta | -7.563 |
urrent | -6.312 |
ighthouse | -6.172 |
eger | -6.060 |
byss | -6.007 |
Token | Conservatives |
Token ID | 17897 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Reviewer | +4.594 |
iary | +4.291 |
romeda | +3.820 |
raid | +3.598 |
stroke | +3.491 |
Neg logit contributions | |
arta | -9.645 |
urrent | -8.090 |
byss | -7.965 |
ighthouse | -7.963 |
eger | -7.819 |
Token | image |
Token ID | 2939 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Reviewer | +5.918 |
iary | +5.495 |
romeda | +5.011 |
stroke | +4.902 |
eter | +4.867 |
Neg logit contributions | |
arta | -7.936 |
urrent | -6.840 |
byss | -6.789 |
ighthouse | -6.735 |
eger | -6.488 |
Token |
|
Token ID | 198 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Reviewer | +6.740 |
iary | +6.545 |
romeda | +5.754 |
pl | +5.629 |
stroke | +5.458 |
Neg logit contributions | |
arta | -10.466 |
mosqu | -9.101 |
byss | -9.080 |
ighthouse | -9.032 |
urrent | -8.995 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Reviewer | +4.784 |
iary | +4.612 |
stroke | +4.113 |
pl | +4.083 |
romeda | +3.968 |
Neg logit contributions | |
arta | -7.208 |
mosqu | -6.517 |
urrent | -6.204 |
byss | -6.167 |
ighthouse | -6.095 |
Token | larg |
Token ID | 15521 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +4.631 |
iary | +4.274 |
romeda | +4.055 |
stroke | +4.039 |
pl | +3.966 |
Neg logit contributions | |
arta | -4.701 |
ighthouse | -4.032 |
istar | -3.836 |
urrent | -3.826 |
eger | -3.701 |
Token | er |
Token ID | 263 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
iary | +6.209 |
Reviewer | +5.875 |
eter | +5.775 |
romeda | +5.216 |
pl | +5.204 |
Neg logit contributions | |
arta | -16.164 |
mosqu | -14.394 |
byss | -14.022 |
urrent | -13.859 |
kefeller | -13.751 |
Token | image |
Token ID | 2939 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iary | +8.147 |
Reviewer | +7.846 |
eter | +7.656 |
romeda | +7.294 |
pl | +7.243 |
Neg logit contributions | |
arta | -16.837 |
byss | -16.165 |
mosqu | -16.062 |
urrent | -15.229 |
kefeller | -15.218 |
Token | T |
Token ID | 309 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Reviewer | +7.983 |
iary | +7.594 |
pl | +6.630 |
romeda | +6.565 |
eter | +6.424 |
Neg logit contributions | |
arta | -15.456 |
byss | -14.843 |
kefeller | -14.358 |
ighthouse | -14.247 |
eger | -14.188 |
Token | IFF |
Token ID | 29267 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
iary | +3.970 |
Reviewer | +3.796 |
romeda | +3.432 |
raid | +3.349 |
stroke | +3.330 |
Neg logit contributions | |
arta | -7.646 |
ighthouse | -6.656 |
urrent | -6.559 |
byss | -6.312 |
mington | -6.287 |
Token | original |
Token ID | 2656 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Reviewer | +4.747 |
iary | +4.651 |
romeda | +4.063 |
stroke | +3.997 |
raid | +3.931 |
Neg logit contributions | |
arta | -7.644 |
byss | -6.913 |
ighthouse | -6.896 |
urrent | -6.599 |
eger | -6.576 |
Token | image |
Token ID | 2939 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Reviewer | +6.549 |
iary | +6.387 |
romeda | +5.699 |
eter | +5.619 |
pl | +5.616 |
Neg logit contributions | |
arta | -9.305 |
urrent | -7.936 |
byss | -7.757 |
ighthouse | -7.733 |
eger | -7.506 |
Token | Download |
Token ID | 10472 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Reviewer | +7.820 |
iary | +7.569 |
pl | +6.589 |
romeda | +6.489 |
raid | +6.256 |
Neg logit contributions | |
arta | -10.968 |
ighthouse | -9.641 |
kefeller | -9.620 |
byss | -9.564 |
eger | -9.489 |
Token | 22 |
Token ID | 2534 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
Reviewer | +3.656 |
iary | +3.625 |
romeda | +3.328 |
stroke | +3.109 |
raid | +3.094 |
Neg logit contributions | |
arta | -4.638 |
urrent | -3.871 |
ighthouse | -3.821 |
eger | -3.715 |
istar | -3.588 |
Token | Film |
Token ID | 13741 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Reviewer | +0.934 |
iary | +0.883 |
romeda | +0.821 |
raid | +0.775 |
stroke | +0.772 |
Neg logit contributions | |
arta | -1.106 |
urrent | -0.921 |
ighthouse | -0.902 |
eger | -0.863 |
istar | -0.848 |
Token | Collection |
Token ID | 12251 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Reviewer | +2.593 |
iary | +2.461 |
romeda | +2.294 |
raid | +2.166 |
stroke | +2.135 |
Neg logit contributions | |
arta | -3.076 |
urrent | -2.572 |
ighthouse | -2.545 |
eger | -2.422 |
istar | -2.353 |
Token | [ |
Token ID | 685 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
arta | +2.189 |
urrent | +1.813 |
ighthouse | +1.785 |
eger | +1.706 |
istar | +1.682 |
Neg logit contributions | |
Reviewer | -1.707 |
iary | -1.614 |
romeda | -1.520 |
raid | -1.419 |
stroke | -1.417 |
Token | Blu |
Token ID | 38676 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
arta | +3.733 |
urrent | +3.057 |
ighthouse | +2.989 |
eger | +2.852 |
istar | +2.786 |
Neg logit contributions | |
Reviewer | -3.381 |
iary | -3.265 |
romeda | -3.109 |
raid | -2.870 |
stroke | -2.869 |
Token | - |
Token ID | 12 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
arta | +0.177 |
urrent | +0.145 |
ighthouse | +0.142 |
eger | +0.135 |
istar | +0.133 |
Neg logit contributions | |
Reviewer | -0.165 |
iary | -0.156 |
romeda | -0.147 |
raid | -0.139 |
stroke | -0.138 |
Token | ray |
Token ID | 2433 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Reviewer | +4.230 |
iary | +3.881 |
raid | +3.662 |
romeda | +3.333 |
pl | +3.243 |
Neg logit contributions | |
arta | -17.609 |
urrent | -15.543 |
ighthouse | -15.474 |
mosqu | -15.379 |
eger | -15.338 |
Token | --- |
Token ID | 11420 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Reviewer | +3.368 |
iary | +3.226 |
romeda | +2.951 |
raid | +2.797 |
stroke | +2.756 |
Neg logit contributions | |
arta | -4.208 |
urrent | -3.583 |
ighthouse | -3.536 |
eger | -3.365 |
istar | -3.301 |
Token | Then |
Token ID | 3244 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
arta | +2.433 |
urrent | +2.006 |
ighthouse | +1.977 |
eger | +1.884 |
istar | +1.849 |
Neg logit contributions | |
Reviewer | -1.995 |
iary | -1.896 |
romeda | -1.789 |
raid | -1.671 |
stroke | -1.669 |
Token | buy |
Token ID | 2822 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
Reviewer | +0.454 |
iary | +0.427 |
romeda | +0.400 |
raid | +0.377 |
stroke | +0.375 |
Neg logit contributions | |
arta | -0.550 |
urrent | -0.456 |
ighthouse | -0.450 |
eger | -0.429 |
istar | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
arta | +1.198 |
urrent | +0.992 |
ighthouse | +0.980 |
eger | +0.935 |
istar | +0.923 |
Neg logit contributions | |
Reviewer | -0.959 |
iary | -0.906 |
romeda | -0.849 |
raid | -0.796 |
stroke | -0.796 |
Token | automated |
Token ID | 16359 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Reviewer | +4.048 |
iary | +3.943 |
romeda | +3.626 |
stroke | +3.436 |
raid | +3.389 |
Neg logit contributions | |
arta | -5.198 |
ighthouse | -4.303 |
urrent | -4.244 |
byss | -4.102 |
eger | -4.057 |
Token | messages |
Token ID | 6218 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Reviewer | +1.911 |
iary | +1.819 |
romeda | +1.683 |
raid | +1.574 |
stroke | +1.573 |
Neg logit contributions | |
arta | -2.387 |
urrent | -1.976 |
ighthouse | -1.964 |
eger | -1.861 |
istar | -1.838 |
Token | from |
Token ID | 422 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Reviewer | +3.894 |
iary | +3.734 |
romeda | +3.432 |
stroke | +3.204 |
raid | +3.140 |
Neg logit contributions | |
arta | -6.201 |
ighthouse | -5.244 |
urrent | -5.220 |
eger | -5.008 |
byss | -4.913 |
Token | personal |
Token ID | 2614 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Reviewer | +4.749 |
iary | +4.740 |
romeda | +4.302 |
stroke | +4.041 |
raid | +3.958 |
Neg logit contributions | |
arta | -6.787 |
ighthouse | -5.553 |
urrent | -5.513 |
byss | -5.364 |
eger | -5.212 |
Token | one |
Token ID | 530 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Reviewer | +1.690 |
iary | +1.621 |
romeda | +1.490 |
stroke | +1.408 |
raid | +1.406 |
Neg logit contributions | |
arta | -2.152 |
urrent | -1.782 |
ighthouse | -1.774 |
eger | -1.685 |
istar | -1.664 |
Token | - |
Token ID | 12 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Reviewer | +2.183 |
iary | +2.071 |
romeda | +1.887 |
stroke | +1.827 |
raid | +1.774 |
Neg logit contributions | |
arta | -2.629 |
urrent | -2.183 |
ighthouse | -2.169 |
eger | -2.034 |
istar | -2.032 |
Token | on |
Token ID | 261 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Reviewer | +8.535 |
stroke | +8.509 |
iary | +7.906 |
pl | +7.600 |
raid | +7.358 |
Neg logit contributions | |
arta | -13.900 |
ighthouse | -12.171 |
urrent | -11.622 |
byss | -11.617 |
mosqu | -11.541 |
Token | - |
Token ID | 12 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Reviewer | +1.718 |
iary | +1.633 |
romeda | +1.532 |
stroke | +1.449 |
raid | +1.444 |
Neg logit contributions | |
arta | -1.856 |
urrent | -1.520 |
ighthouse | -1.500 |
eger | -1.421 |
istar | -1.401 |
Token | one |
Token ID | 505 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Reviewer | +3.796 |
iary | +3.534 |
stroke | +3.283 |
raid | +3.234 |
romeda | +3.169 |
Neg logit contributions | |
arta | -4.254 |
urrent | -3.403 |
ighthouse | -3.378 |
eger | -3.228 |
byss | -3.202 |
Token | messages |
Token ID | 6218 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Reviewer | +3.158 |
iary | +3.031 |
romeda | +2.792 |
stroke | +2.626 |
raid | +2.600 |
Neg logit contributions | |
arta | -3.619 |
ighthouse | -2.995 |
urrent | -2.977 |
eger | -2.799 |
byss | -2.784 |
Token | . |
Token ID | 13 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Reviewer | +3.296 |
iary | +3.130 |
romeda | +2.899 |
stroke | +2.715 |
raid | +2.673 |
Neg logit contributions | |
arta | -5.013 |
ighthouse | -4.197 |
urrent | -4.187 |
eger | -3.997 |
istar | -3.915 |
Token | � |
Token ID | 447 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Reviewer | +1.653 |
iary | +1.585 |
romeda | +1.484 |
stroke | +1.407 |
raid | +1.404 |
Neg logit contributions | |
arta | -1.926 |
urrent | -1.574 |
ighthouse | -1.567 |
eger | -1.488 |
istar | -1.465 |
Token | � |
Token ID | 247 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Reviewer | +3.890 |
iary | +3.720 |
romeda | +3.495 |
stroke | +3.345 |
raid | +3.343 |
Neg logit contributions | |
arta | -4.039 |
urrent | -3.227 |
ighthouse | -3.204 |
istar | -3.047 |
byss | -3.019 |
Token | ve |
Token ID | 303 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Reviewer | +1.695 |
iary | +1.610 |
romeda | +1.490 |
raid | +1.435 |
stroke | +1.416 |
Neg logit contributions | |
arta | -2.251 |
urrent | -1.867 |
ighthouse | -1.851 |
eger | -1.766 |
istar | -1.744 |
Token | asserted |
Token ID | 21635 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Reviewer | +2.048 |
iary | +1.966 |
romeda | +1.831 |
stroke | +1.729 |
raid | +1.709 |
Neg logit contributions | |
arta | -2.533 |
urrent | -2.089 |
ighthouse | -2.088 |
eger | -1.963 |
byss | -1.945 |
Token | that |
Token ID | 326 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Reviewer | +1.997 |
iary | +1.895 |
romeda | +1.751 |
stroke | +1.637 |
raid | +1.613 |
Neg logit contributions | |
arta | -2.859 |
urrent | -2.406 |
ighthouse | -2.346 |
eger | -2.259 |
istar | -2.218 |
Token | Team |
Token ID | 4816 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Reviewer | +2.566 |
iary | +2.425 |
romeda | +2.265 |
stroke | +2.083 |
raid | +2.072 |
Neg logit contributions | |
arta | -3.907 |
urrent | -3.317 |
ighthouse | -3.245 |
byss | -3.100 |
eger | -3.100 |
Token | USA |
Token ID | 4916 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
Reviewer | +6.784 |
iary | +6.618 |
romeda | +5.576 |
achev | +5.419 |
tera | +5.255 |
Neg logit contributions | |
arta | -15.109 |
urrent | -13.461 |
byss | -12.659 |
ighthouse | -12.580 |
eger | -12.518 |
Token | is |
Token ID | 318 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Reviewer | +0.577 |
iary | +0.546 |
romeda | +0.511 |
raid | +0.481 |
stroke | +0.480 |
Neg logit contributions | |
arta | -0.716 |
urrent | -0.593 |
ighthouse | -0.587 |
eger | -0.560 |
istar | -0.550 |
Token | so |
Token ID | 523 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Reviewer | +1.813 |
iary | +1.716 |
romeda | +1.603 |
raid | +1.516 |
stroke | +1.504 |
Neg logit contributions | |
arta | -2.210 |
urrent | -1.830 |
ighthouse | -1.800 |
eger | -1.718 |
istar | -1.687 |
Token | turned |
Token ID | 2900 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
Reviewer | +6.451 |
iary | +6.427 |
romeda | +5.763 |
raid | +5.603 |
pl | +5.437 |
Neg logit contributions | |
arta | -8.108 |
urrent | -6.691 |
ighthouse | -6.524 |
eger | -6.296 |
istar | -6.183 |
Token | off |
Token ID | 572 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
arta | +0.593 |
urrent | +0.488 |
ighthouse | +0.479 |
eger | +0.457 |
istar | +0.449 |
Neg logit contributions | |
Reviewer | -0.535 |
iary | -0.506 |
romeda | -0.477 |
raid | -0.449 |
stroke | -0.447 |
Token | by |
Token ID | 416 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
arta | +3.210 |
urrent | +2.667 |
ighthouse | +2.622 |
eger | +2.509 |
istar | +2.467 |
Neg logit contributions | |
Reviewer | -2.952 |
iary | -2.780 |
romeda | -2.636 |
raid | -2.479 |
stroke | -2.444 |
Token | work |
Token ID | 670 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Reviewer | +0.694 |
iary | +0.660 |
romeda | +0.618 |
stroke | +0.584 |
raid | +0.583 |
Neg logit contributions | |
arta | -0.835 |
urrent | -0.686 |
ighthouse | -0.679 |
eger | -0.646 |
istar | -0.634 |
Token | permit |
Token ID | 8749 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Reviewer | +3.428 |
iary | +3.274 |
romeda | +3.042 |
stroke | +2.964 |
raid | +2.895 |
Neg logit contributions | |
arta | -4.574 |
urrent | -3.791 |
ighthouse | -3.783 |
eger | -3.658 |
byss | -3.545 |
Token | problems |
Token ID | 2761 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Reviewer | +1.278 |
iary | +1.217 |
romeda | +1.129 |
stroke | +1.074 |
raid | +1.073 |
Neg logit contributions | |
arta | -1.492 |
urrent | -1.234 |
ighthouse | -1.218 |
eger | -1.159 |
istar | -1.135 |
Token | , |
Token ID | 11 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
Reviewer | +3.573 |
iary | +3.504 |
romeda | +3.170 |
stroke | +3.015 |
raid | +2.960 |
Neg logit contributions | |
arta | -6.241 |
ighthouse | -5.211 |
urrent | -5.196 |
eger | -4.981 |
byss | -4.956 |
Token | knee |
Token ID | 10329 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
arta | +1.001 |
urrent | +0.842 |
ighthouse | +0.832 |
eger | +0.796 |
istar | +0.786 |
Neg logit contributions | |
Reviewer | -0.695 |
iary | -0.649 |
romeda | -0.605 |
raid | -0.563 |
stroke | -0.559 |
Token | surgery |
Token ID | 8185 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
iary | +7.802 |
stroke | +7.428 |
Reviewer | +7.197 |
pl | +7.163 |
romeda | +6.470 |
Neg logit contributions | |
arta | -13.758 |
ighthouse | -11.976 |
urrent | -11.837 |
byss | -11.787 |
eger | -11.411 |
Token | , |
Token ID | 11 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
Reviewer | +0.189 |
iary | +0.179 |
romeda | +0.167 |
stroke | +0.157 |
raid | +0.156 |
Neg logit contributions | |
arta | -0.267 |
urrent | -0.223 |
ighthouse | -0.221 |
eger | -0.211 |
istar | -0.208 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Reviewer | +0.982 |
iary | +0.934 |
romeda | +0.874 |
stroke | +0.822 |
raid | +0.819 |
Neg logit contributions | |
arta | -1.252 |
urrent | -1.035 |
ighthouse | -1.023 |
eger | -0.976 |
istar | -0.959 |
Token | broken |
Token ID | 5445 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
Reviewer | +1.228 |
iary | +1.172 |
romeda | +1.099 |
stroke | +1.040 |
raid | +1.038 |
Neg logit contributions | |
arta | -1.447 |
urrent | -1.188 |
ighthouse | -1.179 |
eger | -1.115 |
istar | -1.103 |
Token | finger |
Token ID | 7660 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
arta | +0.293 |
urrent | +0.240 |
ighthouse | +0.237 |
eger | +0.225 |
istar | +0.222 |
Neg logit contributions | |
Reviewer | -0.262 |
iary | -0.248 |
romeda | -0.233 |
raid | -0.220 |
stroke | -0.219 |
Token | PNG |
Token ID | 36182 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Reviewer | +1.258 |
iary | +1.147 |
romeda | +1.019 |
stroke | +0.924 |
raid | +0.922 |
Neg logit contributions | |
arta | -2.782 |
urrent | -2.394 |
ighthouse | -2.394 |
eger | -2.345 |
istar | -2.273 |
Token | larger |
Token ID | 4025 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Reviewer | +3.474 |
iary | +3.242 |
romeda | +2.845 |
tera | +2.765 |
eter | +2.748 |
Neg logit contributions | |
arta | -4.741 |
ighthouse | -3.972 |
urrent | -3.948 |
eger | -3.859 |
istar | -3.733 |
Token | image |
Token ID | 2939 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Reviewer | +5.918 |
iary | +5.495 |
romeda | +5.011 |
stroke | +4.902 |
eter | +4.867 |
Neg logit contributions | |
arta | -7.936 |
urrent | -6.840 |
byss | -6.789 |
ighthouse | -6.735 |
eger | -6.488 |
Token |
|
Token ID | 198 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Reviewer | +6.740 |
iary | +6.545 |
romeda | +5.754 |
pl | +5.629 |
stroke | +5.458 |
Neg logit contributions | |
arta | -10.466 |
mosqu | -9.101 |
byss | -9.080 |
ighthouse | -9.032 |
urrent | -8.995 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Reviewer | +4.784 |
iary | +4.612 |
stroke | +4.113 |
pl | +4.083 |
romeda | +3.968 |
Neg logit contributions | |
arta | -7.208 |
mosqu | -6.517 |
urrent | -6.204 |
byss | -6.167 |
ighthouse | -6.095 |
Token | larg |
Token ID | 15521 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +4.631 |
iary | +4.274 |
romeda | +4.055 |
stroke | +4.039 |
pl | +3.966 |
Neg logit contributions | |
arta | -4.701 |
ighthouse | -4.032 |
istar | -3.836 |
urrent | -3.826 |
eger | -3.701 |
Token | er |
Token ID | 263 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
iary | +6.209 |
Reviewer | +5.875 |
eter | +5.775 |
romeda | +5.216 |
pl | +5.204 |
Neg logit contributions | |
arta | -16.164 |
mosqu | -14.394 |
byss | -14.022 |
urrent | -13.859 |
kefeller | -13.751 |
Token | image |
Token ID | 2939 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iary | +8.147 |
Reviewer | +7.846 |
eter | +7.656 |
romeda | +7.294 |
pl | +7.243 |
Neg logit contributions | |
arta | -16.837 |
byss | -16.165 |
mosqu | -16.062 |
urrent | -15.229 |
kefeller | -15.218 |
Token | T |
Token ID | 309 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Reviewer | +7.983 |
iary | +7.594 |
pl | +6.630 |
romeda | +6.565 |
eter | +6.424 |
Neg logit contributions | |
arta | -15.456 |
byss | -14.843 |
kefeller | -14.358 |
ighthouse | -14.247 |
eger | -14.188 |
Token | IFF |
Token ID | 29267 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
iary | +3.970 |
Reviewer | +3.796 |
romeda | +3.432 |
raid | +3.349 |
stroke | +3.330 |
Neg logit contributions | |
arta | -7.646 |
ighthouse | -6.656 |
urrent | -6.559 |
byss | -6.312 |
mington | -6.287 |
Token | original |
Token ID | 2656 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Reviewer | +4.747 |
iary | +4.651 |
romeda | +4.063 |
stroke | +3.997 |
raid | +3.931 |
Neg logit contributions | |
arta | -7.644 |
byss | -6.913 |
ighthouse | -6.896 |
urrent | -6.599 |
eger | -6.576 |
Token | Never |
Token ID | 12295 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Reviewer | +2.442 |
iary | +2.248 |
romeda | +2.057 |
stroke | +1.991 |
raid | +1.982 |
Neg logit contributions | |
arta | -2.930 |
urrent | -2.423 |
ighthouse | -2.376 |
eger | -2.279 |
istar | -2.246 |
Token | mind |
Token ID | 2000 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
arta | +1.457 |
urrent | +1.233 |
ighthouse | +1.220 |
eger | +1.170 |
istar | +1.155 |
Neg logit contributions | |
Reviewer | -0.915 |
iary | -0.855 |
romeda | -0.793 |
raid | -0.736 |
stroke | -0.731 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Reviewer | +3.177 |
iary | +2.963 |
romeda | +2.822 |
stroke | +2.574 |
raid | +2.554 |
Neg logit contributions | |
arta | -4.934 |
urrent | -4.123 |
ighthouse | -4.016 |
eger | -3.850 |
istar | -3.839 |
Token | fact |
Token ID | 1109 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
Reviewer | +1.618 |
iary | +1.524 |
romeda | +1.393 |
stroke | +1.295 |
raid | +1.286 |
Neg logit contributions | |
arta | -2.692 |
urrent | -2.265 |
ighthouse | -2.255 |
eger | -2.154 |
istar | -2.134 |
Token | that |
Token ID | 326 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Reviewer | +4.098 |
iary | +3.774 |
romeda | +3.423 |
stroke | +3.209 |
pl | +3.161 |
Neg logit contributions | |
arta | -7.715 |
urrent | -6.497 |
ighthouse | -6.228 |
byss | -6.067 |
eger | -6.059 |
Token | Team |
Token ID | 4816 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +3.632 |
iary | +3.397 |
romeda | +3.217 |
stroke | +2.964 |
raid | +2.938 |
Neg logit contributions | |
arta | -5.183 |
urrent | -4.338 |
ighthouse | -4.262 |
byss | -4.113 |
eger | -4.069 |
Token | Canada |
Token ID | 3340 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Reviewer | +6.681 |
iary | +6.412 |
romeda | +5.328 |
achev | +5.232 |
pl | +5.174 |
Neg logit contributions | |
arta | -15.069 |
urrent | -13.389 |
ighthouse | -12.754 |
byss | -12.622 |
eger | -12.497 |
Token | also |
Token ID | 635 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
arta | +0.250 |
urrent | +0.207 |
ighthouse | +0.204 |
eger | +0.195 |
istar | +0.192 |
Neg logit contributions | |
Reviewer | -0.207 |
iary | -0.195 |
romeda | -0.183 |
raid | -0.172 |
stroke | -0.171 |
Token | left |
Token ID | 1364 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
arta | +2.326 |
urrent | +1.923 |
ighthouse | +1.885 |
eger | +1.800 |
istar | +1.780 |
Neg logit contributions | |
Reviewer | -2.068 |
iary | -1.917 |
romeda | -1.818 |
raid | -1.705 |
stroke | -1.703 |
Token | off |
Token ID | 572 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Reviewer | +1.692 |
iary | +1.595 |
romeda | +1.488 |
raid | +1.387 |
stroke | +1.386 |
Neg logit contributions | |
arta | -2.377 |
urrent | -1.980 |
ighthouse | -1.931 |
eger | -1.873 |
istar | -1.837 |
Token | top |
Token ID | 1353 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Reviewer | +1.280 |
iary | +1.211 |
romeda | +1.124 |
raid | +1.051 |
stroke | +1.049 |
Neg logit contributions | |
arta | -1.818 |
urrent | -1.511 |
ighthouse | -1.486 |
eger | -1.424 |
istar | -1.412 |
Token | What |
Token ID | 1867 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Reviewer | +1.364 |
iary | +1.281 |
romeda | +1.177 |
raid | +1.104 |
stroke | +1.102 |
Neg logit contributions | |
arta | -2.346 |
urrent | -2.009 |
ighthouse | -1.997 |
eger | -1.893 |
istar | -1.881 |
Token | are |
Token ID | 389 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Reviewer | +2.118 |
iary | +2.077 |
romeda | +1.926 |
raid | +1.783 |
stroke | +1.781 |
Neg logit contributions | |
arta | -2.800 |
urrent | -2.367 |
ighthouse | -2.318 |
eger | -2.229 |
istar | -2.205 |
Token | these |
Token ID | 777 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Reviewer | +2.922 |
iary | +2.718 |
romeda | +2.228 |
pl | +2.160 |
stroke | +2.134 |
Neg logit contributions | |
arta | -6.077 |
urrent | -5.099 |
ighthouse | -5.093 |
byss | -4.908 |
eger | -4.893 |
Token | ? |
Token ID | 30 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Reviewer | +2.329 |
iary | +2.196 |
romeda | +2.065 |
raid | +1.954 |
stroke | +1.950 |
Neg logit contributions | |
arta | -2.534 |
urrent | -2.073 |
ighthouse | -2.035 |
eger | -1.940 |
istar | -1.910 |
Token | E |
Token ID | 412 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Reviewer | +2.847 |
iary | +2.534 |
romeda | +2.208 |
pl | +2.167 |
raid | +2.132 |
Neg logit contributions | |
arta | -7.471 |
urrent | -6.464 |
eger | -6.390 |
ighthouse | -6.303 |
byss | -6.161 |
Token | - |
Token ID | 12 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +5.293 |
iary | +4.597 |
pl | +4.286 |
romeda | +4.078 |
unin | +4.025 |
Neg logit contributions | |
arta | -8.667 |
ighthouse | -7.269 |
urrent | -7.265 |
istar | -6.975 |
REDACTED | -6.888 |
Token | mail |
Token ID | 4529 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Reviewer | +7.426 |
iary | +5.756 |
pl | +5.163 |
unin | +4.938 |
masters | +4.913 |
Neg logit contributions | |
arta | -15.997 |
esson | -14.623 |
ighthouse | -13.835 |
byss | -13.220 |
istar | -13.182 |
Token | this |
Token ID | 428 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
Reviewer | +3.552 |
iary | +3.255 |
romeda | +3.078 |
raid | +3.021 |
stroke | +2.938 |
Neg logit contributions | |
arta | -7.167 |
urrent | -6.219 |
ighthouse | -6.070 |
esson | -5.892 |
eger | -5.874 |
Token | to |
Token ID | 284 |
Feature activation | -6.76e-04 |
Pos logit contributions | |
Reviewer | +0.361 |
iary | +0.340 |
romeda | +0.318 |
raid | +0.298 |
stroke | +0.296 |
Neg logit contributions | |
arta | -0.461 |
urrent | -0.383 |
ighthouse | -0.379 |
eger | -0.361 |
istar | -0.357 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +0.007 |
iary | +0.007 |
romeda | +0.006 |
stroke | +0.006 |
raid | +0.006 |
Neg logit contributions | |
arta | -0.009 |
urrent | -0.007 |
ighthouse | -0.007 |
eger | -0.007 |
istar | -0.007 |
Token | friend |
Token ID | 1545 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Reviewer | +1.175 |
iary | +1.081 |
romeda | +0.994 |
raid | +0.921 |
stroke | +0.909 |
Neg logit contributions | |
arta | -2.176 |
urrent | -1.850 |
ighthouse | -1.846 |
byss | -1.763 |
eger | -1.760 |
Token | alleg |
Token ID | 2868 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
arta | +2.646 |
urrent | +2.177 |
ighthouse | +2.144 |
eger | +2.041 |
istar | +2.018 |
Neg logit contributions | |
Reviewer | -2.238 |
iary | -2.089 |
romeda | -1.962 |
raid | -1.855 |
stroke | -1.841 |
Token | ory |
Token ID | 652 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
arta | +4.986 |
urrent | +4.130 |
ighthouse | +4.022 |
eger | +3.852 |
istar | +3.838 |
Neg logit contributions | |
Reviewer | -4.044 |
iary | -3.742 |
romeda | -3.561 |
stroke | -3.297 |
raid | -3.289 |
Token | ( |
Token ID | 357 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
arta | +0.463 |
urrent | +0.384 |
ighthouse | +0.379 |
eger | +0.362 |
istar | +0.358 |
Neg logit contributions | |
Reviewer | -0.362 |
iary | -0.340 |
romeda | -0.319 |
raid | -0.299 |
stroke | -0.296 |
Token | in |
Token ID | 259 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
arta | +4.225 |
urrent | +3.405 |
ighthouse | +3.334 |
eger | +3.150 |
istar | +3.102 |
Neg logit contributions | |
Reviewer | -4.553 |
iary | -4.309 |
romeda | -4.159 |
raid | -3.802 |
stroke | -3.786 |
Token | Greek |
Token ID | 8312 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
arta | +1.101 |
urrent | +0.915 |
ighthouse | +0.904 |
eger | +0.863 |
istar | +0.851 |
Neg logit contributions | |
Reviewer | -0.860 |
iary | -0.808 |
romeda | -0.758 |
raid | -0.710 |
stroke | -0.706 |
Token | h |
Token ID | 289 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Reviewer | +3.947 |
iary | +3.783 |
romeda | +3.447 |
stroke | +3.333 |
raid | +3.280 |
Neg logit contributions | |
arta | -5.944 |
urrent | -5.133 |
ighthouse | -5.026 |
eger | -4.788 |
stration | -4.701 |
Token | upon |
Token ID | 27287 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
iary | +10.918 |
Reviewer | +10.532 |
romeda | +10.035 |
raid | +9.925 |
eter | +9.518 |
Neg logit contributions | |
arta | -10.060 |
mosqu | -8.546 |
urrent | -8.532 |
ighthouse | -8.391 |
REDACTED | -8.377 |
Token | o |
Token ID | 78 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Reviewer | +3.496 |
iary | +3.381 |
romeda | +3.136 |
raid | +3.015 |
stroke | +2.982 |
Neg logit contributions | |
arta | -3.986 |
urrent | -3.334 |
ighthouse | -3.275 |
eger | -3.103 |
istar | -3.030 |
Token | ia |
Token ID | 544 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Reviewer | +5.472 |
iary | +5.384 |
romeda | +4.809 |
raid | +4.763 |
pl | +4.753 |
Neg logit contributions | |
arta | -6.847 |
urrent | -5.907 |
ighthouse | -5.769 |
eger | -5.519 |
mington | -5.390 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Reviewer | +5.258 |
iary | +5.066 |
romeda | +4.585 |
pl | +4.538 |
raid | +4.472 |
Neg logit contributions | |
arta | -7.124 |
urrent | -6.108 |
ighthouse | -6.063 |
eger | -5.737 |
mington | -5.618 |
Token | � |
Token ID | 564 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
Reviewer | +2.368 |
iary | +2.269 |
romeda | +2.091 |
raid | +1.971 |
stroke | +1.968 |
Neg logit contributions | |
arta | -3.196 |
urrent | -2.698 |
ighthouse | -2.658 |
eger | -2.557 |
istar | -2.493 |
Token | cameras |
Token ID | 9073 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Reviewer | +5.947 |
iary | +5.493 |
romeda | +5.221 |
raid | +4.887 |
stroke | +4.818 |
Neg logit contributions | |
arta | -7.408 |
urrent | -6.014 |
ighthouse | -6.000 |
eger | -5.780 |
byss | -5.731 |
Token | to |
Token ID | 284 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
Reviewer | +2.286 |
iary | +2.111 |
romeda | +1.929 |
stroke | +1.863 |
raid | +1.800 |
Neg logit contributions | |
arta | -3.403 |
urrent | -2.861 |
ighthouse | -2.817 |
eger | -2.710 |
esson | -2.679 |
Token | switch |
Token ID | 5078 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Reviewer | +6.536 |
iary | +6.312 |
romeda | +5.858 |
stroke | +5.696 |
raid | +5.440 |
Neg logit contributions | |
arta | -7.596 |
urrent | -6.139 |
ighthouse | -6.005 |
byss | -5.920 |
esson | -5.735 |
Token | to |
Token ID | 284 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Reviewer | +5.918 |
iary | +5.335 |
stroke | +4.957 |
romeda | +4.842 |
achev | +4.589 |
Neg logit contributions | |
arta | -10.247 |
urrent | -8.699 |
ighthouse | -8.506 |
esson | -8.274 |
eger | -8.258 |
Token | full |
Token ID | 1336 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Reviewer | +5.830 |
iary | +5.464 |
romeda | +5.216 |
stroke | +4.904 |
pl | +4.748 |
Neg logit contributions | |
arta | -7.835 |
urrent | -6.393 |
ighthouse | -6.353 |
eger | -6.100 |
byss | -6.006 |
Token | power |
Token ID | 1176 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Reviewer | +5.761 |
iary | +5.472 |
romeda | +5.164 |
stroke | +4.956 |
raid | +4.698 |
Neg logit contributions | |
arta | -7.110 |
urrent | -5.912 |
ighthouse | -5.845 |
esson | -5.505 |
byss | -5.499 |
Token | and |
Token ID | 290 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Reviewer | +7.876 |
iary | +6.888 |
stroke | +6.699 |
raid | +6.063 |
romeda | +6.032 |
Neg logit contributions | |
arta | -14.095 |
ighthouse | -12.231 |
urrent | -12.047 |
eger | -11.626 |
esson | -11.322 |
Token | start |
Token ID | 923 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Reviewer | +6.756 |
iary | +6.322 |
romeda | +6.084 |
stroke | +5.787 |
raid | +5.646 |
Neg logit contributions | |
arta | -6.980 |
urrent | -5.693 |
ighthouse | -5.603 |
eger | -5.424 |
byss | -5.240 |
Token | returning |
Token ID | 8024 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Reviewer | +4.705 |
iary | +4.468 |
romeda | +4.247 |
stroke | +4.004 |
raid | +3.880 |
Neg logit contributions | |
arta | -6.361 |
urrent | -5.259 |
ighthouse | -5.161 |
eger | -5.059 |
esson | -4.925 |
Token | images |
Token ID | 4263 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Reviewer | +6.242 |
iary | +5.823 |
romeda | +5.695 |
stroke | +5.259 |
pl | +4.966 |
Neg logit contributions | |
arta | -9.367 |
urrent | -7.699 |
ighthouse | -7.686 |
eger | -7.439 |
byss | -7.421 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Reviewer | +4.905 |
iary | +4.669 |
romeda | +4.101 |
stroke | +3.937 |
pl | +3.870 |
Neg logit contributions | |
arta | -9.233 |
ighthouse | -7.886 |
urrent | -7.877 |
eger | -7.618 |
stration | -7.437 |
Token | What |
Token ID | 1867 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Reviewer | +1.018 |
iary | +0.954 |
romeda | +0.878 |
raid | +0.823 |
stroke | +0.819 |
Neg logit contributions | |
arta | -1.654 |
urrent | -1.411 |
ighthouse | -1.398 |
eger | -1.330 |
istar | -1.318 |
Token | are |
Token ID | 389 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Reviewer | +2.553 |
iary | +2.517 |
romeda | +2.325 |
stroke | +2.143 |
raid | +2.131 |
Neg logit contributions | |
arta | -3.517 |
urrent | -2.994 |
ighthouse | -2.921 |
eger | -2.810 |
istar | -2.782 |
Token | these |
Token ID | 777 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Reviewer | +3.508 |
iary | +3.248 |
pl | +2.581 |
romeda | +2.563 |
achev | +2.474 |
Neg logit contributions | |
arta | -7.941 |
urrent | -6.777 |
ighthouse | -6.776 |
byss | -6.580 |
eger | -6.518 |
Token | ? |
Token ID | 30 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Reviewer | +3.174 |
iary | +2.972 |
romeda | +2.768 |
raid | +2.633 |
stroke | +2.630 |
Neg logit contributions | |
arta | -3.648 |
urrent | -3.010 |
ighthouse | -2.937 |
eger | -2.814 |
istar | -2.777 |
Token | E |
Token ID | 412 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Reviewer | +3.007 |
iary | +2.651 |
romeda | +2.398 |
pl | +2.306 |
raid | +2.251 |
Neg logit contributions | |
arta | -7.699 |
urrent | -6.700 |
eger | -6.607 |
ighthouse | -6.506 |
byss | -6.337 |
Token | - |
Token ID | 12 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Reviewer | +5.250 |
iary | +4.571 |
pl | +4.316 |
unin | +4.071 |
romeda | +4.056 |
Neg logit contributions | |
arta | -8.754 |
ighthouse | -7.384 |
urrent | -7.361 |
istar | -7.055 |
esson | -7.025 |
Token | mail |
Token ID | 4529 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Reviewer | +7.681 |
iary | +5.977 |
pl | +5.591 |
unin | +5.265 |
raid | +5.249 |
Neg logit contributions | |
arta | -15.610 |
esson | -14.137 |
ighthouse | -13.474 |
istar | -12.913 |
byss | -12.700 |
Token | this |
Token ID | 428 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Reviewer | +3.729 |
iary | +3.384 |
romeda | +3.187 |
raid | +3.139 |
stroke | +3.073 |
Neg logit contributions | |
arta | -7.911 |
urrent | -6.874 |
ighthouse | -6.789 |
esson | -6.512 |
eger | -6.495 |
Token | to |
Token ID | 284 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Reviewer | +0.521 |
iary | +0.491 |
romeda | +0.459 |
raid | +0.430 |
stroke | +0.428 |
Neg logit contributions | |
arta | -0.669 |
urrent | -0.556 |
ighthouse | -0.549 |
eger | -0.524 |
istar | -0.517 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Reviewer | +0.283 |
iary | +0.267 |
romeda | +0.249 |
stroke | +0.231 |
raid | +0.231 |
Neg logit contributions | |
arta | -0.345 |
urrent | -0.284 |
ighthouse | -0.280 |
eger | -0.267 |
istar | -0.264 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
Reviewer | +1.396 |
iary | +1.277 |
romeda | +1.174 |
raid | +1.092 |
stroke | +1.077 |
Neg logit contributions | |
arta | -2.583 |
urrent | -2.194 |
ighthouse | -2.193 |
byss | -2.097 |
eger | -2.096 |
Token | and |
Token ID | 290 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Reviewer | +0.229 |
iary | +0.216 |
romeda | +0.201 |
raid | +0.189 |
stroke | +0.189 |
Neg logit contributions | |
arta | -0.304 |
urrent | -0.254 |
ighthouse | -0.250 |
eger | -0.239 |
istar | -0.236 |
Token | have |
Token ID | 423 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
arta | +0.397 |
urrent | +0.323 |
ighthouse | +0.319 |
eger | +0.303 |
istar | +0.300 |
Neg logit contributions | |
Reviewer | -0.371 |
iary | -0.348 |
romeda | -0.327 |
raid | -0.310 |
stroke | -0.307 |
Token | them |
Token ID | 606 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Reviewer | +2.346 |
iary | +2.237 |
romeda | +2.089 |
stroke | +1.971 |
raid | +1.942 |
Neg logit contributions | |
arta | -3.274 |
urrent | -2.756 |
ighthouse | -2.691 |
eger | -2.586 |
istar | -2.530 |
Token | once |
Token ID | 1752 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
arta | +0.646 |
urrent | +0.525 |
ighthouse | +0.517 |
eger | +0.491 |
istar | +0.485 |
Neg logit contributions | |
Reviewer | -0.632 |
iary | -0.595 |
romeda | -0.561 |
raid | -0.531 |
stroke | -0.526 |
Token | more |
Token ID | 517 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
Reviewer | +1.139 |
iary | +1.075 |
romeda | +0.982 |
stroke | +0.917 |
raid | +0.907 |
Neg logit contributions | |
arta | -1.900 |
urrent | -1.618 |
ighthouse | -1.588 |
eger | -1.523 |
istar | -1.499 |
Token | laid |
Token ID | 8104 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Reviewer | +0.434 |
iary | +0.411 |
romeda | +0.387 |
raid | +0.364 |
stroke | +0.363 |
Neg logit contributions | |
arta | -0.491 |
urrent | -0.403 |
ighthouse | -0.398 |
eger | -0.378 |
istar | -0.372 |
Token | bare |
Token ID | 6247 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
iary | +8.323 |
Reviewer | +7.828 |
romeda | +7.599 |
stroke | +7.483 |
pl | +7.253 |
Neg logit contributions | |
arta | -12.865 |
urrent | -11.287 |
ighthouse | -10.720 |
byss | -10.390 |
esson | -10.228 |
Token | to |
Token ID | 284 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
arta | +0.084 |
urrent | +0.070 |
ighthouse | +0.069 |
eger | +0.066 |
istar | +0.065 |
Neg logit contributions | |
Reviewer | -0.064 |
iary | -0.060 |
romeda | -0.057 |
raid | -0.053 |
stroke | -0.053 |
Token | each |
Token ID | 1123 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Reviewer | +0.585 |
iary | +0.552 |
romeda | +0.516 |
stroke | +0.482 |
raid | +0.482 |
Neg logit contributions | |
arta | -0.789 |
urrent | -0.659 |
ighthouse | -0.650 |
eger | -0.623 |
istar | -0.612 |
Token | other |
Token ID | 584 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
arta | +1.819 |
urrent | +1.488 |
ighthouse | +1.467 |
eger | +1.394 |
istar | +1.372 |
Neg logit contributions | |
Reviewer | -1.683 |
iary | -1.594 |
romeda | -1.501 |
raid | -1.416 |
stroke | -1.411 |
Token | and |
Token ID | 290 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
Reviewer | +2.904 |
iary | +2.740 |
romeda | +2.568 |
stroke | +2.445 |
raid | +2.383 |
Neg logit contributions | |
arta | -4.295 |
urrent | -3.623 |
ighthouse | -3.568 |
eger | -3.424 |
istar | -3.315 |
Token | � |
Token ID | 247 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
arta | +0.633 |
urrent | +0.502 |
ighthouse | +0.493 |
eger | +0.467 |
istar | +0.448 |
Neg logit contributions | |
Reviewer | -0.853 |
iary | -0.812 |
romeda | -0.771 |
raid | -0.736 |
stroke | -0.732 |
Token | s |
Token ID | 82 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Reviewer | +4.113 |
iary | +3.792 |
romeda | +3.590 |
raid | +3.492 |
stroke | +3.481 |
Neg logit contributions | |
arta | -4.487 |
urrent | -3.672 |
ighthouse | -3.645 |
eger | -3.520 |
mington | -3.368 |
Token | sixty |
Token ID | 24742 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
Reviewer | +7.114 |
iary | +6.763 |
romeda | +6.357 |
raid | +6.036 |
pl | +5.849 |
Neg logit contributions | |
arta | -9.973 |
urrent | -8.383 |
ighthouse | -8.205 |
eger | -8.023 |
byss | -7.970 |
Token | - |
Token ID | 12 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
arta | +0.071 |
urrent | +0.058 |
ighthouse | +0.057 |
eger | +0.055 |
istar | +0.054 |
Neg logit contributions | |
Reviewer | -0.059 |
iary | -0.056 |
romeda | -0.053 |
raid | -0.049 |
stroke | -0.049 |
Token | w |
Token ID | 86 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Reviewer | +0.298 |
iary | +0.283 |
romeda | +0.265 |
stroke | +0.252 |
raid | +0.251 |
Neg logit contributions | |
arta | -0.347 |
urrent | -0.285 |
ighthouse | -0.281 |
eger | -0.268 |
istar | -0.263 |
Token | att |
Token ID | 1078 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
arta | +0.170 |
urrent | +0.138 |
ighthouse | +0.136 |
eger | +0.129 |
istar | +0.126 |
Neg logit contributions | |
Reviewer | -0.173 |
iary | -0.164 |
romeda | -0.155 |
raid | -0.147 |
stroke | -0.146 |
Token | transmitter |
Token ID | 35099 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Reviewer | +9.241 |
iary | +9.040 |
romeda | +8.284 |
raid | +7.987 |
stroke | +7.833 |
Neg logit contributions | |
arta | -11.897 |
urrent | -9.763 |
byss | -9.547 |
ighthouse | -9.498 |
stration | -9.253 |
Token | would |
Token ID | 561 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Reviewer | +3.806 |
iary | +3.626 |
romeda | +3.300 |
stroke | +3.176 |
raid | +3.126 |
Neg logit contributions | |
arta | -6.627 |
urrent | -5.676 |
ighthouse | -5.632 |
eger | -5.478 |
esson | -5.352 |
Token | start |
Token ID | 923 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Reviewer | +4.470 |
iary | +4.282 |
romeda | +3.986 |
stroke | +3.841 |
raid | +3.773 |
Neg logit contributions | |
arta | -5.207 |
urrent | -4.290 |
ighthouse | -4.163 |
byss | -3.992 |
eger | -3.965 |
Token | be |
Token ID | 307 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Reviewer | +3.666 |
iary | +3.395 |
romeda | +3.163 |
stroke | +2.997 |
raid | +2.875 |
Neg logit contributions | |
arta | -5.862 |
urrent | -4.922 |
ighthouse | -4.807 |
eger | -4.657 |
esson | -4.561 |
Token | aming |
Token ID | 3723 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Reviewer | +6.132 |
iary | +5.704 |
romeda | +5.447 |
stroke | +5.273 |
raid | +5.269 |
Neg logit contributions | |
arta | -7.064 |
urrent | -5.587 |
ighthouse | -5.439 |
esson | -5.280 |
istar | -5.261 |
Token | " |
Token ID | 366 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
arta | +2.990 |
urrent | +2.483 |
ighthouse | +2.426 |
eger | +2.319 |
istar | +2.295 |
Neg logit contributions | |
Reviewer | -2.551 |
iary | -2.427 |
romeda | -2.247 |
stroke | -2.166 |
raid | -2.137 |
Token | Sky |
Token ID | 22308 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
arta | +4.800 |
urrent | +3.981 |
ighthouse | +3.859 |
eger | +3.698 |
istar | +3.656 |
Neg logit contributions | |
Reviewer | -4.190 |
iary | -4.101 |
romeda | -3.853 |
stroke | -3.613 |
raid | -3.572 |
Token | fall |
Token ID | 7207 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Reviewer | +0.162 |
iary | +0.153 |
romeda | +0.143 |
raid | +0.134 |
stroke | +0.134 |
Neg logit contributions | |
arta | -0.204 |
urrent | -0.170 |
ighthouse | -0.167 |
eger | -0.160 |
istar | -0.158 |
Token | " |
Token ID | 1 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
arta | +0.572 |
urrent | +0.468 |
ighthouse | +0.462 |
eger | +0.439 |
istar | +0.432 |
Neg logit contributions | |
Reviewer | -0.526 |
iary | -0.498 |
romeda | -0.469 |
raid | -0.442 |
stroke | -0.440 |
Token | Blu |
Token ID | 12391 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
arta | +1.740 |
urrent | +1.411 |
ighthouse | +1.390 |
eger | +1.315 |
istar | +1.307 |
Neg logit contributions | |
Reviewer | -1.644 |
iary | -1.558 |
romeda | -1.472 |
stroke | -1.392 |
raid | -1.387 |
Token | - |
Token ID | 12 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
arta | +0.177 |
urrent | +0.146 |
ighthouse | +0.143 |
eger | +0.137 |
istar | +0.134 |
Neg logit contributions | |
Reviewer | -0.162 |
iary | -0.154 |
romeda | -0.144 |
raid | -0.136 |
stroke | -0.135 |
Token | Ray |
Token ID | 19591 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Reviewer | +5.031 |
iary | +4.122 |
raid | +3.739 |
romeda | +3.457 |
stroke | +3.434 |
Neg logit contributions | |
arta | -16.107 |
urrent | -14.213 |
ighthouse | -14.054 |
eger | -13.989 |
esson | -13.866 |
Token | : |
Token ID | 25 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Reviewer | +1.922 |
iary | +1.814 |
romeda | +1.700 |
raid | +1.596 |
stroke | +1.585 |
Neg logit contributions | |
arta | -2.345 |
urrent | -1.967 |
ighthouse | -1.942 |
eger | -1.853 |
istar | -1.818 |
Token | Sky |
Token ID | 5274 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
arta | +2.236 |
urrent | +1.847 |
ighthouse | +1.828 |
eger | +1.737 |
istar | +1.721 |
Neg logit contributions | |
Reviewer | -1.767 |
iary | -1.679 |
romeda | -1.568 |
raid | -1.470 |
stroke | -1.469 |
Token | fall |
Token ID | 7207 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
arta | +0.700 |
urrent | +0.582 |
ighthouse | +0.574 |
eger | +0.550 |
istar | +0.541 |
Neg logit contributions | |
Reviewer | -0.537 |
iary | -0.506 |
romeda | -0.472 |
raid | -0.445 |
stroke | -0.444 |
Token | ( |
Token ID | 357 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Reviewer | +3.010 |
iary | +2.826 |
romeda | +2.640 |
raid | +2.499 |
stroke | +2.453 |
Neg logit contributions | |
arta | -3.593 |
urrent | -3.037 |
ighthouse | -3.007 |
eger | -2.861 |
istar | -2.819 |
Token | ine |
Token ID | 500 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Reviewer | +2.900 |
iary | +2.855 |
romeda | +2.548 |
stroke | +2.416 |
raid | +2.404 |
Neg logit contributions | |
arta | -4.726 |
urrent | -3.979 |
ighthouse | -3.900 |
byss | -3.781 |
eger | -3.742 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
arta | +1.438 |
urrent | +1.178 |
ighthouse | +1.163 |
eger | +1.111 |
istar | +1.088 |
Neg logit contributions | |
Reviewer | -1.274 |
iary | -1.178 |
romeda | -1.118 |
raid | -1.047 |
stroke | -1.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
Reviewer | +2.859 |
iary | +2.757 |
romeda | +2.521 |
raid | +2.376 |
stroke | +2.362 |
Neg logit contributions | |
arta | -4.511 |
urrent | -3.768 |
ighthouse | -3.744 |
eger | -3.627 |
istar | -3.550 |
Token | former |
Token ID | 1966 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
Reviewer | +0.178 |
iary | +0.167 |
romeda | +0.156 |
raid | +0.146 |
stroke | +0.145 |
Neg logit contributions | |
arta | -0.235 |
urrent | -0.196 |
ighthouse | -0.193 |
eger | -0.185 |
istar | -0.182 |
Token | deputy |
Token ID | 10636 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
arta | +0.465 |
urrent | +0.384 |
ighthouse | +0.378 |
eger | +0.359 |
istar | +0.356 |
Neg logit contributions | |
Reviewer | -0.403 |
iary | -0.378 |
romeda | -0.357 |
raid | -0.335 |
stroke | -0.333 |
Token | prime |
Token ID | 6994 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Reviewer | +4.109 |
iary | +4.028 |
romeda | +3.600 |
stroke | +3.501 |
raid | +3.456 |
Neg logit contributions | |
arta | -5.297 |
urrent | -4.389 |
ighthouse | -4.314 |
eger | -4.201 |
byss | -4.134 |
Token | minister |
Token ID | 5342 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
iary | +6.100 |
Reviewer | +5.353 |
stroke | +4.859 |
raid | +4.712 |
romeda | +4.694 |
Neg logit contributions | |
arta | -15.455 |
urrent | -13.805 |
ighthouse | -13.501 |
byss | -13.378 |
esson | -13.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Reviewer | +3.244 |
iary | +3.160 |
romeda | +2.822 |
stroke | +2.676 |
raid | +2.598 |
Neg logit contributions | |
arta | -5.249 |
urrent | -4.428 |
ighthouse | -4.364 |
istar | -4.196 |
eger | -4.157 |
Token | is |
Token ID | 318 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Reviewer | +2.323 |
iary | +2.260 |
romeda | +2.101 |
stroke | +1.979 |
raid | +1.971 |
Neg logit contributions | |
arta | -3.089 |
urrent | -2.579 |
ighthouse | -2.543 |
eger | -2.428 |
istar | -2.403 |
Token | known |
Token ID | 1900 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
arta | +1.788 |
urrent | +1.473 |
ighthouse | +1.450 |
eger | +1.377 |
istar | +1.357 |
Neg logit contributions | |
Reviewer | -1.630 |
iary | -1.520 |
romeda | -1.430 |
raid | -1.345 |
stroke | -1.338 |
Token | for |
Token ID | 329 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Reviewer | +1.048 |
iary | +0.985 |
romeda | +0.894 |
stroke | +0.852 |
raid | +0.830 |
Neg logit contributions | |
arta | -1.619 |
urrent | -1.369 |
ighthouse | -1.346 |
eger | -1.293 |
istar | -1.273 |
Token | Talk |
Token ID | 12167 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +1.635 |
iary | +1.569 |
romeda | +1.470 |
raid | +1.384 |
stroke | +1.371 |
Neg logit contributions | |
arta | -2.128 |
urrent | -1.764 |
ighthouse | -1.733 |
eger | -1.672 |
istar | -1.637 |
Token | To |
Token ID | 2514 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Reviewer | +1.515 |
iary | +1.436 |
romeda | +1.336 |
raid | +1.272 |
stroke | +1.268 |
Neg logit contributions | |
arta | -1.834 |
urrent | -1.512 |
ighthouse | -1.496 |
eger | -1.439 |
istar | -1.403 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
arta | +2.045 |
urrent | +1.678 |
ighthouse | +1.652 |
eger | +1.565 |
istar | +1.546 |
Neg logit contributions | |
Reviewer | -1.854 |
iary | -1.750 |
romeda | -1.648 |
raid | -1.547 |
stroke | -1.543 |
Token | a |
Token ID | 257 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Reviewer | +1.310 |
iary | +1.232 |
romeda | +1.150 |
raid | +1.075 |
stroke | +1.064 |
Neg logit contributions | |
arta | -1.931 |
urrent | -1.628 |
ighthouse | -1.591 |
eger | -1.542 |
istar | -1.512 |
Token | three |
Token ID | 1115 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Reviewer | +2.081 |
iary | +2.003 |
romeda | +1.872 |
raid | +1.772 |
stroke | +1.757 |
Neg logit contributions | |
arta | -2.511 |
urrent | -2.085 |
ighthouse | -2.053 |
eger | -1.952 |
istar | -1.939 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Reviewer | +4.401 |
iary | +4.320 |
stroke | +3.846 |
romeda | +3.798 |
pl | +3.612 |
Neg logit contributions | |
arta | -5.921 |
urrent | -5.033 |
ighthouse | -4.798 |
byss | -4.646 |
esson | -4.627 |
Token | year |
Token ID | 1941 |
Feature activation | -8.85e-03 |
Pos logit contributions | |
Reviewer | +8.623 |
stroke | +8.415 |
iary | +8.217 |
raid | +7.948 |
pl | +7.906 |
Neg logit contributions | |
arta | -12.125 |
urrent | -10.455 |
ighthouse | -9.969 |
esson | -9.865 |
byss | -9.785 |
Token | - |
Token ID | 12 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
Reviewer | +0.098 |
iary | +0.094 |
romeda | +0.088 |
raid | +0.083 |
stroke | +0.083 |
Neg logit contributions | |
arta | -0.108 |
urrent | -0.089 |
ighthouse | -0.087 |
eger | -0.083 |
istar | -0.082 |
Token | old |
Token ID | 727 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Reviewer | +0.699 |
iary | +0.659 |
romeda | +0.615 |
raid | +0.579 |
stroke | +0.576 |
Neg logit contributions | |
arta | -0.934 |
urrent | -0.778 |
ighthouse | -0.768 |
eger | -0.735 |
istar | -0.724 |
Token | company |
Token ID | 1664 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
Reviewer | +3.722 |
iary | +3.660 |
romeda | +3.383 |
raid | +3.197 |
stroke | +3.191 |
Neg logit contributions | |
arta | -4.864 |
urrent | -4.077 |
ighthouse | -3.981 |
eger | -3.817 |
byss | -3.808 |
Token | Path |
Token ID | 10644 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
Reviewer | +0.410 |
iary | +0.387 |
romeda | +0.363 |
raid | +0.338 |
stroke | +0.336 |
Neg logit contributions | |
arta | -0.549 |
urrent | -0.458 |
ighthouse | -0.450 |
eger | -0.432 |
istar | -0.426 |
Token | Time |
Token ID | 7575 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
arta | +0.566 |
urrent | +0.438 |
ighthouse | +0.431 |
istar | +0.396 |
eger | +0.396 |
Neg logit contributions | |
Reviewer | -0.797 |
iary | -0.766 |
romeda | -0.731 |
raid | -0.696 |
stroke | -0.694 |
Token | Control |
Token ID | 15988 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
arta | +0.780 |
urrent | +0.626 |
ighthouse | +0.620 |
eger | +0.581 |
istar | +0.575 |
Neg logit contributions | |
Reviewer | -0.838 |
iary | -0.795 |
romeda | -0.753 |
raid | -0.713 |
stroke | -0.709 |
Token | " |
Token ID | 366 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
arta | +5.599 |
urrent | +4.388 |
ighthouse | +4.367 |
istar | +4.152 |
eger | +4.151 |
Neg logit contributions | |
Reviewer | -6.044 |
iary | -5.851 |
romeda | -5.569 |
raid | -5.284 |
achev | -5.156 |
Token | 40 |
Token ID | 1821 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
arta | +4.991 |
urrent | +4.124 |
ighthouse | +4.033 |
eger | +3.790 |
istar | +3.771 |
Neg logit contributions | |
Reviewer | -5.013 |
iary | -4.744 |
romeda | -4.477 |
raid | -4.256 |
achev | -4.165 |
Token | / |
Token ID | 14 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
arta | +4.976 |
urrent | +4.106 |
ighthouse | +4.047 |
eger | +3.823 |
istar | +3.813 |
Neg logit contributions | |
Reviewer | -4.764 |
iary | -4.366 |
romeda | -4.157 |
raid | -3.904 |
stroke | -3.811 |
Token | 6000 |
Token ID | 43434 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
arta | +5.187 |
urrent | +4.289 |
ighthouse | +4.233 |
eger | +4.006 |
istar | +3.990 |
Neg logit contributions | |
Reviewer | -4.694 |
iary | -4.298 |
romeda | -4.138 |
raid | -3.807 |
achev | -3.779 |
Token | + |
Token ID | 10 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
arta | +8.753 |
urrent | +7.143 |
ighthouse | +6.872 |
istar | +6.625 |
eger | +6.538 |
Neg logit contributions | |
Reviewer | -9.208 |
iary | -8.618 |
romeda | -8.115 |
raid | -7.686 |
stroke | -7.564 |
Token | 30 |
Token ID | 1270 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
arta | +1.472 |
urrent | +1.215 |
ighthouse | +1.199 |
eger | +1.141 |
istar | +1.125 |
Neg logit contributions | |
Reviewer | -1.253 |
iary | -1.183 |
romeda | -1.111 |
raid | -1.044 |
stroke | -1.039 |
Token | : |
Token ID | 25 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
arta | +4.540 |
urrent | +3.722 |
ighthouse | +3.659 |
eger | +3.400 |
istar | +3.382 |
Neg logit contributions | |
Reviewer | -4.900 |
iary | -4.587 |
romeda | -4.343 |
raid | -4.081 |
stroke | -4.028 |
Token | 20 |
Token ID | 1238 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
arta | +2.028 |
urrent | +1.707 |
ighthouse | +1.687 |
eger | +1.612 |
istar | +1.597 |
Neg logit contributions | |
Reviewer | -1.347 |
iary | -1.256 |
romeda | -1.168 |
raid | -1.092 |
stroke | -1.075 |
Token | / |
Token ID | 14 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
arta | +3.759 |
urrent | +3.047 |
ighthouse | +2.993 |
eger | +2.832 |
istar | +2.790 |
Neg logit contributions | |
Reviewer | -4.003 |
iary | -3.766 |
romeda | -3.580 |
raid | -3.386 |
stroke | -3.344 |
Token | single |
Token ID | 2060 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Reviewer | +0.380 |
iary | +0.357 |
romeda | +0.333 |
raid | +0.311 |
stroke | +0.310 |
Neg logit contributions | |
arta | -0.531 |
urrent | -0.444 |
ighthouse | -0.439 |
eger | -0.420 |
istar | -0.415 |
Token | turn |
Token ID | 1210 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
arta | +2.401 |
urrent | +1.985 |
ighthouse | +1.938 |
eger | +1.871 |
istar | +1.831 |
Neg logit contributions | |
Reviewer | -2.205 |
iary | -2.059 |
romeda | -1.946 |
raid | -1.804 |
stroke | -1.781 |
Token | ! |
Token ID | 0 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
arta | +2.905 |
urrent | +2.394 |
ighthouse | +2.351 |
eger | +2.242 |
istar | +2.225 |
Neg logit contributions | |
Reviewer | -2.612 |
iary | -2.468 |
romeda | -2.328 |
raid | -2.176 |
stroke | -2.147 |
Token | One |
Token ID | 1881 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
arta | +0.209 |
urrent | +0.171 |
ighthouse | +0.168 |
eger | +0.160 |
istar | +0.157 |
Neg logit contributions | |
Reviewer | -0.201 |
iary | -0.190 |
romeda | -0.179 |
raid | -0.170 |
stroke | -0.169 |
Token | way |
Token ID | 835 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
arta | +1.606 |
urrent | +1.326 |
ighthouse | +1.311 |
eger | +1.254 |
istar | +1.231 |
Neg logit contributions | |
Reviewer | -1.372 |
iary | -1.284 |
romeda | -1.213 |
raid | -1.140 |
stroke | -1.128 |
Token | to |
Token ID | 284 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Reviewer | +0.723 |
iary | +0.676 |
romeda | +0.633 |
raid | +0.591 |
stroke | +0.590 |
Neg logit contributions | |
arta | -1.003 |
urrent | -0.840 |
ighthouse | -0.826 |
eger | -0.796 |
istar | -0.775 |
Token | avoid |
Token ID | 3368 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
arta | +6.030 |
urrent | +4.854 |
ighthouse | +4.831 |
istar | +4.658 |
eger | +4.572 |
Neg logit contributions | |
Reviewer | -8.283 |
iary | -7.601 |
romeda | -7.246 |
raid | -6.888 |
stroke | -6.686 |
Token | this |
Token ID | 428 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
arta | +3.922 |
urrent | +3.226 |
ighthouse | +3.192 |
eger | +3.056 |
istar | +3.039 |
Neg logit contributions | |
Reviewer | -3.681 |
iary | -3.383 |
romeda | -3.205 |
raid | -3.031 |
stroke | -2.993 |
Token | is |
Token ID | 318 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
arta | +1.486 |
urrent | +1.228 |
ighthouse | +1.213 |
eger | +1.156 |
istar | +1.141 |
Neg logit contributions | |
Reviewer | -1.247 |
iary | -1.166 |
romeda | -1.098 |
raid | -1.031 |
stroke | -1.018 |
Token | to |
Token ID | 284 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
arta | +3.513 |
urrent | +2.920 |
ighthouse | +2.895 |
eger | +2.738 |
istar | +2.720 |
Neg logit contributions | |
Reviewer | -2.980 |
iary | -2.802 |
romeda | -2.629 |
raid | -2.480 |
stroke | -2.469 |
Token | activate |
Token ID | 15155 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
arta | +2.759 |
urrent | +2.265 |
ighthouse | +2.223 |
eger | +2.112 |
istar | +2.093 |
Neg logit contributions | |
Reviewer | -2.810 |
iary | -2.607 |
romeda | -2.458 |
stroke | -2.318 |
raid | -2.311 |
Token | to |
Token ID | 284 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
arta | +3.930 |
urrent | +3.266 |
ighthouse | +3.202 |
eger | +3.060 |
istar | +3.024 |
Neg logit contributions | |
Reviewer | -3.435 |
iary | -3.209 |
romeda | -3.009 |
raid | -2.882 |
stroke | -2.773 |
Token | a |
Token ID | 257 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
arta | +7.905 |
urrent | +6.469 |
ighthouse | +6.367 |
eger | +5.963 |
istar | +5.960 |
Neg logit contributions | |
Reviewer | -8.014 |
iary | -7.285 |
romeda | -6.841 |
raid | -6.599 |
stroke | -6.297 |
Token | value |
Token ID | 1988 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
arta | +5.378 |
urrent | +4.497 |
ighthouse | +4.409 |
eger | +4.340 |
stration | +4.069 |
Neg logit contributions | |
Reviewer | -5.115 |
iary | -4.704 |
romeda | -4.418 |
raid | -4.245 |
achev | -4.091 |
Token | value |
Token ID | 1988 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
arta | +7.943 |
urrent | +6.693 |
ighthouse | +6.550 |
eger | +6.266 |
esson | +6.070 |
Neg logit contributions | |
Reviewer | -8.080 |
iary | -7.336 |
romeda | -7.028 |
raid | -6.904 |
achev | -6.474 |
Token | called |
Token ID | 1444 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
arta | +6.644 |
urrent | +5.572 |
ighthouse | +5.396 |
eger | +5.238 |
esson | +5.056 |
Neg logit contributions | |
Reviewer | -6.449 |
iary | -5.948 |
romeda | -5.649 |
raid | -5.465 |
achev | -5.161 |
Token | _ |
Token ID | 4808 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
arta | +8.270 |
urrent | +6.812 |
ighthouse | +6.760 |
eger | +6.458 |
istar | +6.245 |
Neg logit contributions | |
Reviewer | -8.236 |
iary | -7.594 |
romeda | -7.079 |
raid | -6.948 |
unin | -6.561 |
Token | P |
Token ID | 47 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
arta | +8.193 |
urrent | +6.819 |
ighthouse | +6.688 |
eger | +6.499 |
istar | +6.285 |
Neg logit contributions | |
Reviewer | -7.418 |
iary | -6.992 |
romeda | -6.469 |
raid | -6.035 |
achev | -5.875 |
Token | ulse |
Token ID | 9615 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
arta | +1.496 |
urrent | +1.235 |
ighthouse | +1.216 |
eger | +1.158 |
istar | +1.141 |
Neg logit contributions | |
Reviewer | -1.289 |
iary | -1.217 |
romeda | -1.138 |
raid | -1.072 |
stroke | -1.069 |
Token | Amount |
Token ID | 31264 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
arta | +0.706 |
urrent | +0.583 |
ighthouse | +0.576 |
eger | +0.549 |
istar | +0.541 |
Neg logit contributions | |
Reviewer | -0.593 |
iary | -0.560 |
romeda | -0.526 |
raid | -0.494 |
stroke | -0.492 |
Token | , |
Token ID | 11 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
arta | +0.753 |
urrent | +0.620 |
ighthouse | +0.613 |
eger | +0.583 |
istar | +0.575 |
Neg logit contributions | |
Reviewer | -0.648 |
iary | -0.612 |
romeda | -0.575 |
raid | -0.541 |
stroke | -0.539 |
Token | completing |
Token ID | 14339 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
arta | +4.765 |
urrent | +3.976 |
ighthouse | +3.933 |
eger | +3.760 |
istar | +3.693 |
Neg logit contributions | |
Reviewer | -3.976 |
iary | -3.674 |
romeda | -3.440 |
raid | -3.287 |
stroke | -3.152 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Reviewer | +2.352 |
iary | +2.280 |
romeda | +2.053 |
stroke | +1.955 |
raid | +1.929 |
Neg logit contributions | |
arta | -3.742 |
urrent | -3.174 |
ighthouse | -3.130 |
eger | -2.960 |
istar | -2.956 |
Token | items |
Token ID | 3709 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Reviewer | +0.320 |
iary | +0.303 |
romeda | +0.285 |
raid | +0.268 |
stroke | +0.267 |
Neg logit contributions | |
arta | -0.368 |
urrent | -0.303 |
ighthouse | -0.299 |
eger | -0.285 |
istar | -0.281 |
Token | for |
Token ID | 329 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Reviewer | +1.715 |
iary | +1.648 |
romeda | +1.503 |
stroke | +1.414 |
raid | +1.402 |
Neg logit contributions | |
arta | -2.621 |
urrent | -2.224 |
ighthouse | -2.190 |
eger | -2.084 |
istar | -2.069 |
Token | recycling |
Token ID | 25914 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Reviewer | +0.214 |
iary | +0.203 |
romeda | +0.190 |
raid | +0.179 |
stroke | +0.178 |
Neg logit contributions | |
arta | -0.250 |
urrent | -0.206 |
ighthouse | -0.203 |
eger | -0.194 |
istar | -0.191 |
Token | at |
Token ID | 379 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
arta | +1.495 |
urrent | +1.239 |
ighthouse | +1.222 |
eger | +1.169 |
istar | +1.153 |
Neg logit contributions | |
Reviewer | -1.221 |
iary | -1.136 |
romeda | -1.072 |
raid | -1.002 |
stroke | -0.991 |
Token | Pur |
Token ID | 9330 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
Reviewer | +1.018 |
iary | +0.971 |
romeda | +0.902 |
raid | +0.854 |
stroke | +0.848 |
Neg logit contributions | |
arta | -1.381 |
urrent | -1.158 |
ighthouse | -1.137 |
eger | -1.091 |
istar | -1.079 |
Token | fleet |
Token ID | 33559 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
arta | +8.334 |
ighthouse | +6.839 |
urrent | +6.819 |
istar | +6.426 |
eger | +6.416 |
Neg logit contributions | |
Reviewer | -7.225 |
iary | -6.389 |
romeda | -6.269 |
raid | -5.607 |
stroke | -5.572 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
arta | +1.226 |
urrent | +1.008 |
ighthouse | +0.997 |
eger | +0.946 |
istar | +0.933 |
Neg logit contributions | |
Reviewer | -1.064 |
iary | -1.003 |
romeda | -0.945 |
raid | -0.887 |
stroke | -0.885 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
arta | +0.048 |
urrent | +0.040 |
ighthouse | +0.039 |
eger | +0.037 |
istar | +0.037 |
Neg logit contributions | |
Reviewer | -0.046 |
iary | -0.043 |
romeda | -0.041 |
raid | -0.038 |
stroke | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Reviewer | +1.861 |
iary | +1.769 |
romeda | +1.648 |
stroke | +1.569 |
raid | +1.562 |
Neg logit contributions | |
arta | -2.033 |
urrent | -1.672 |
ighthouse | -1.643 |
eger | -1.565 |
istar | -1.543 |
Token | A |
Token ID | 32 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
arta | +1.115 |
urrent | +0.917 |
ighthouse | +0.908 |
eger | +0.861 |
istar | +0.852 |
Neg logit contributions | |
Reviewer | -0.943 |
iary | -0.897 |
romeda | -0.847 |
raid | -0.789 |
stroke | -0.786 |
Token | $ |
Token ID | 720 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
arta | +3.175 |
urrent | +2.637 |
ighthouse | +2.615 |
eger | +2.489 |
istar | +2.473 |
Neg logit contributions | |
Reviewer | -2.662 |
iary | -2.476 |
romeda | -2.295 |
raid | -2.159 |
stroke | -2.157 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Reviewer | +0.775 |
iary | +0.732 |
romeda | +0.687 |
raid | +0.649 |
stroke | +0.648 |
Neg logit contributions | |
arta | -0.939 |
urrent | -0.778 |
ighthouse | -0.768 |
eger | -0.733 |
istar | -0.722 |
Token | ( |
Token ID | 357 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
arta | +2.569 |
urrent | +2.116 |
ighthouse | +2.097 |
eger | +1.999 |
istar | +1.976 |
Neg logit contributions | |
Reviewer | -2.144 |
iary | -2.020 |
romeda | -1.893 |
raid | -1.777 |
stroke | -1.753 |
Token | or |
Token ID | 273 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
arta | +5.311 |
urrent | +4.253 |
ighthouse | +4.221 |
istar | +3.991 |
eger | +3.975 |
Neg logit contributions | |
Reviewer | -5.437 |
iary | -5.161 |
romeda | -4.947 |
raid | -4.482 |
stroke | -4.479 |
Token | possibly |
Token ID | 5457 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
arta | +3.632 |
urrent | +2.975 |
ighthouse | +2.966 |
eger | +2.803 |
istar | +2.780 |
Neg logit contributions | |
Reviewer | -3.077 |
iary | -2.833 |
romeda | -2.625 |
stroke | -2.500 |
raid | -2.469 |
Token | nothing |
Token ID | 2147 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
arta | +6.307 |
ighthouse | +5.111 |
urrent | +5.044 |
eger | +4.776 |
istar | +4.741 |
Neg logit contributions | |
Reviewer | -6.274 |
iary | -5.615 |
romeda | -5.294 |
raid | -5.060 |
stroke | -5.013 |
Token | if |
Token ID | 611 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
arta | +9.230 |
ighthouse | +7.379 |
urrent | +7.343 |
eger | +7.077 |
esson | +7.006 |
Neg logit contributions | |
Reviewer | -9.643 |
iary | -8.698 |
romeda | -8.446 |
raid | -8.016 |
stroke | -7.666 |
Token | you |
Token ID | 345 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arta | +2.612 |
urrent | +2.152 |
ighthouse | +2.124 |
eger | +2.027 |
istar | +2.001 |
Neg logit contributions | |
Reviewer | -2.299 |
iary | -2.159 |
romeda | -2.023 |
raid | -1.911 |
stroke | -1.894 |
Token | have |
Token ID | 423 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Reviewer | +1.546 |
iary | +1.486 |
romeda | +1.398 |
raid | +1.316 |
stroke | +1.312 |
Neg logit contributions | |
arta | -1.751 |
urrent | -1.437 |
ighthouse | -1.422 |
eger | -1.357 |
istar | -1.325 |
Token | some |
Token ID | 617 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
arta | +3.030 |
urrent | +2.537 |
ighthouse | +2.486 |
istar | +2.382 |
eger | +2.373 |
Neg logit contributions | |
Reviewer | -2.503 |
iary | -2.320 |
romeda | -2.176 |
raid | -2.050 |
stroke | -2.033 |
Token | metal |
Token ID | 6147 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
arta | +2.364 |
urrent | +1.996 |
ighthouse | +1.968 |
eger | +1.888 |
istar | +1.876 |
Neg logit contributions | |
Reviewer | -1.589 |
iary | -1.458 |
romeda | -1.366 |
raid | -1.280 |
stroke | -1.248 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
arta | +2.272 |
urrent | +1.882 |
ighthouse | +1.861 |
eger | +1.780 |
istar | +1.745 |
Neg logit contributions | |
Reviewer | -1.881 |
iary | -1.769 |
romeda | -1.665 |
raid | -1.565 |
stroke | -1.550 |
Token | reasons |
Token ID | 3840 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
arta | +2.503 |
urrent | +2.041 |
ighthouse | +2.004 |
eger | +1.936 |
stration | +1.865 |
Neg logit contributions | |
Reviewer | -2.413 |
iary | -2.260 |
romeda | -2.145 |
raid | -2.039 |
stroke | -1.995 |
Token | why |
Token ID | 1521 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
arta | +1.803 |
urrent | +1.494 |
ighthouse | +1.479 |
eger | +1.416 |
istar | +1.391 |
Neg logit contributions | |
Reviewer | -1.448 |
iary | -1.356 |
romeda | -1.273 |
raid | -1.196 |
stroke | -1.185 |
Token | I |
Token ID | 314 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
arta | +0.323 |
urrent | +0.269 |
ighthouse | +0.265 |
eger | +0.254 |
istar | +0.250 |
Neg logit contributions | |
Reviewer | -0.254 |
iary | -0.239 |
romeda | -0.223 |
raid | -0.209 |
stroke | -0.208 |
Token | haven |
Token ID | 4398 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
arta | +0.752 |
urrent | +0.615 |
ighthouse | +0.606 |
eger | +0.575 |
istar | +0.569 |
Neg logit contributions | |
Reviewer | -0.682 |
iary | -0.634 |
romeda | -0.596 |
raid | -0.561 |
stroke | -0.558 |
Token | 't |
Token ID | 470 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Reviewer | +0.568 |
iary | +0.536 |
romeda | +0.506 |
raid | +0.475 |
stroke | +0.470 |
Neg logit contributions | |
arta | -0.671 |
urrent | -0.553 |
ighthouse | -0.547 |
eger | -0.521 |
istar | -0.514 |
Token | been |
Token ID | 587 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
arta | +2.000 |
urrent | +1.629 |
ighthouse | +1.596 |
eger | +1.541 |
istar | +1.525 |
Neg logit contributions | |
Reviewer | -1.924 |
iary | -1.765 |
romeda | -1.676 |
raid | -1.587 |
stroke | -1.561 |
Token | real |
Token ID | 1103 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Reviewer | +4.250 |
iary | +4.132 |
romeda | +3.779 |
stroke | +3.560 |
raid | +3.536 |
Neg logit contributions | |
arta | -6.247 |
urrent | -5.287 |
ighthouse | -5.173 |
byss | -4.975 |
eger | -4.956 |
Token | clear |
Token ID | 1598 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
arta | +0.391 |
urrent | +0.323 |
ighthouse | +0.319 |
eger | +0.305 |
istar | +0.300 |
Neg logit contributions | |
Reviewer | -0.326 |
iary | -0.306 |
romeda | -0.288 |
raid | -0.270 |
stroke | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
Reviewer | +2.297 |
iary | +2.221 |
romeda | +2.035 |
raid | +1.892 |
stroke | +1.889 |
Neg logit contributions | |
arta | -3.556 |
urrent | -3.056 |
ighthouse | -2.969 |
eger | -2.830 |
byss | -2.827 |
Token | I |
Token ID | 314 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
Reviewer | +0.809 |
iary | +0.764 |
romeda | +0.717 |
raid | +0.673 |
stroke | +0.671 |
Neg logit contributions | |
arta | -0.972 |
urrent | -0.805 |
ighthouse | -0.794 |
eger | -0.757 |
istar | -0.746 |
Token | ? |
Token ID | 30 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
arta | +0.186 |
urrent | +0.153 |
ighthouse | +0.151 |
eger | +0.144 |
istar | +0.142 |
Neg logit contributions | |
Reviewer | -0.160 |
iary | -0.151 |
romeda | -0.142 |
raid | -0.134 |
stroke | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
arta | +0.263 |
urrent | +0.215 |
ighthouse | +0.212 |
eger | +0.202 |
istar | +0.198 |
Neg logit contributions | |
Reviewer | -0.239 |
iary | -0.226 |
romeda | -0.212 |
raid | -0.202 |
stroke | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
Reviewer | +0.330 |
iary | +0.312 |
romeda | +0.297 |
raid | +0.280 |
stroke | +0.277 |
Neg logit contributions | |
arta | -0.320 |
urrent | -0.258 |
ighthouse | -0.255 |
eger | -0.241 |
istar | -0.237 |
Token | D |
Token ID | 35 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
arta | +0.814 |
urrent | +0.668 |
ighthouse | +0.658 |
eger | +0.626 |
istar | +0.616 |
Neg logit contributions | |
Reviewer | -0.733 |
iary | -0.697 |
romeda | -0.660 |
raid | -0.616 |
stroke | -0.614 |
Token | read |
Token ID | 961 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
iary | +7.286 |
Reviewer | +7.028 |
romeda | +6.569 |
raid | +6.383 |
eter | +6.147 |
Neg logit contributions | |
arta | -6.428 |
ighthouse | -5.245 |
urrent | -5.090 |
eger | -4.877 |
byss | -4.830 |
Token | will |
Token ID | 481 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Reviewer | +2.388 |
iary | +2.336 |
romeda | +2.145 |
stroke | +2.071 |
raid | +2.062 |
Neg logit contributions | |
arta | -3.223 |
urrent | -2.676 |
ighthouse | -2.630 |
eger | -2.523 |
istar | -2.473 |
Token | only |
Token ID | 691 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
arta | +1.603 |
urrent | +1.311 |
ighthouse | +1.287 |
eger | +1.233 |
istar | +1.216 |
Neg logit contributions | |
Reviewer | -1.575 |
iary | -1.462 |
romeda | -1.389 |
raid | -1.305 |
stroke | -1.290 |
Token | really |
Token ID | 1107 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
arta | +2.457 |
urrent | +2.015 |
ighthouse | +1.956 |
eger | +1.893 |
istar | +1.862 |
Neg logit contributions | |
Reviewer | -2.582 |
iary | -2.356 |
romeda | -2.239 |
raid | -2.118 |
stroke | -2.097 |
Token | increase |
Token ID | 2620 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
arta | +2.990 |
urrent | +2.436 |
ighthouse | +2.380 |
eger | +2.288 |
istar | +2.255 |
Neg logit contributions | |
Reviewer | -3.230 |
iary | -2.908 |
romeda | -2.768 |
raid | -2.628 |
stroke | -2.598 |
Token | if |
Token ID | 611 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Reviewer | +1.096 |
iary | +1.043 |
romeda | +0.969 |
raid | +0.907 |
stroke | +0.906 |
Neg logit contributions | |
arta | -1.497 |
urrent | -1.248 |
ighthouse | -1.233 |
eger | -1.177 |
istar | -1.166 |
Token | players |
Token ID | 1938 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
arta | +1.718 |
urrent | +1.428 |
ighthouse | +1.402 |
eger | +1.345 |
istar | +1.323 |
Neg logit contributions | |
Reviewer | -1.401 |
iary | -1.313 |
romeda | -1.232 |
raid | -1.154 |
stroke | -1.149 |
Token | to |
Token ID | 284 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
arta | +2.195 |
urrent | +1.808 |
ighthouse | +1.801 |
eger | +1.710 |
istar | +1.692 |
Neg logit contributions | |
Reviewer | -1.718 |
iary | -1.595 |
romeda | -1.494 |
raid | -1.409 |
stroke | -1.393 |
Token | see |
Token ID | 766 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
arta | +0.645 |
urrent | +0.526 |
ighthouse | +0.519 |
eger | +0.492 |
istar | +0.484 |
Neg logit contributions | |
Reviewer | -0.611 |
iary | -0.575 |
romeda | -0.542 |
raid | -0.513 |
stroke | -0.507 |
Token | where |
Token ID | 810 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Reviewer | +2.528 |
iary | +2.435 |
romeda | +2.301 |
stroke | +2.117 |
raid | +2.077 |
Neg logit contributions | |
arta | -3.790 |
urrent | -3.195 |
ighthouse | -3.142 |
eger | -3.027 |
byss | -2.996 |
Token | in |
Token ID | 287 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Reviewer | +1.988 |
iary | +1.914 |
romeda | +1.797 |
stroke | +1.685 |
raid | +1.668 |
Neg logit contributions | |
arta | -2.525 |
urrent | -2.098 |
ighthouse | -2.085 |
eger | -1.992 |
istar | -1.954 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
iary | +3.105 |
Reviewer | +3.076 |
romeda | +2.874 |
stroke | +2.659 |
pl | +2.617 |
Neg logit contributions | |
arta | -4.782 |
urrent | -4.055 |
ighthouse | -4.040 |
eger | -3.830 |
istar | -3.798 |
Token | world |
Token ID | 995 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
arta | +1.292 |
urrent | +1.057 |
ighthouse | +1.038 |
eger | +0.991 |
istar | +0.974 |
Neg logit contributions | |
Reviewer | -1.193 |
iary | -1.113 |
romeda | -1.048 |
raid | -0.994 |
stroke | -0.986 |
Token | turtles |
Token ID | 36288 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
arta | +3.620 |
urrent | +2.944 |
ighthouse | +2.888 |
eger | +2.732 |
istar | +2.722 |
Neg logit contributions | |
Reviewer | -3.505 |
iary | -3.230 |
romeda | -3.043 |
raid | -2.906 |
stroke | -2.870 |
Token | are |
Token ID | 389 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
arta | +0.508 |
urrent | +0.417 |
ighthouse | +0.411 |
eger | +0.391 |
istar | +0.386 |
Neg logit contributions | |
Reviewer | -0.456 |
iary | -0.429 |
romeda | -0.405 |
raid | -0.382 |
stroke | -0.379 |
Token | at |
Token ID | 379 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
arta | +1.638 |
urrent | +1.362 |
ighthouse | +1.339 |
eger | +1.288 |
istar | +1.272 |
Neg logit contributions | |
Reviewer | -1.380 |
iary | -1.269 |
romeda | -1.194 |
raid | -1.134 |
stroke | -1.115 |
Token | highest |
Token ID | 4511 |
Feature activation | +6.71e-04 |
Pos logit contributions | |
Reviewer | +0.729 |
iary | +0.695 |
romeda | +0.651 |
stroke | +0.609 |
raid | +0.607 |
Neg logit contributions | |
arta | -0.919 |
urrent | -0.763 |
ighthouse | -0.753 |
eger | -0.717 |
istar | -0.710 |
Token | risk |
Token ID | 2526 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
arta | +0.007 |
urrent | +0.006 |
ighthouse | +0.005 |
eger | +0.005 |
istar | +0.005 |
Neg logit contributions | |
Reviewer | -0.009 |
iary | -0.008 |
romeda | -0.008 |
raid | -0.007 |
stroke | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
arta | +2.198 |
urrent | +1.816 |
ighthouse | +1.796 |
eger | +1.714 |
istar | +1.680 |
Neg logit contributions | |
Reviewer | -1.881 |
iary | -1.765 |
romeda | -1.671 |
raid | -1.565 |
stroke | -1.553 |
Token | When |
Token ID | 1649 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
arta | +0.298 |
urrent | +0.243 |
ighthouse | +0.239 |
eger | +0.226 |
istar | +0.223 |
Neg logit contributions | |
Reviewer | -0.292 |
iary | -0.277 |
romeda | -0.262 |
raid | -0.247 |
stroke | -0.247 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
arta | +4.388 |
urrent | +3.630 |
ighthouse | +3.563 |
eger | +3.345 |
istar | +3.338 |
Neg logit contributions | |
Reviewer | -4.060 |
iary | -3.881 |
romeda | -3.633 |
stroke | -3.401 |
raid | -3.371 |
Token | Bob |
Token ID | 5811 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
arta | +1.170 |
urrent | +0.945 |
ighthouse | +0.932 |
eger | +0.881 |
istar | +0.867 |
Neg logit contributions | |
Reviewer | -1.207 |
iary | -1.146 |
romeda | -1.084 |
raid | -1.025 |
stroke | -1.022 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
arta | +4.452 |
urrent | +3.724 |
ighthouse | +3.611 |
eger | +3.434 |
istar | +3.389 |
Neg logit contributions | |
Reviewer | -3.893 |
iary | -3.690 |
romeda | -3.461 |
stroke | -3.246 |
raid | -3.228 |
Token | for |
Token ID | 329 |
Feature activation | -7.55e-03 |
Pos logit contributions | |
Reviewer | +0.326 |
iary | +0.306 |
romeda | +0.284 |
raid | +0.267 |
stroke | +0.264 |
Neg logit contributions | |
arta | -0.451 |
urrent | -0.378 |
ighthouse | -0.374 |
eger | -0.358 |
istar | -0.352 |
Token | Senate |
Token ID | 3845 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +0.077 |
iary | +0.073 |
romeda | +0.068 |
raid | +0.064 |
stroke | +0.064 |
Neg logit contributions | |
arta | -0.099 |
urrent | -0.083 |
ighthouse | -0.082 |
eger | -0.078 |
istar | -0.077 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Reviewer | +1.406 |
iary | +1.339 |
romeda | +1.234 |
stroke | +1.163 |
raid | +1.158 |
Neg logit contributions | |
arta | -1.936 |
urrent | -1.613 |
ighthouse | -1.600 |
eger | -1.529 |
istar | -1.503 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Reviewer | +1.337 |
iary | +1.284 |
romeda | +1.205 |
stroke | +1.138 |
raid | +1.137 |
Neg logit contributions | |
arta | -1.396 |
urrent | -1.138 |
ighthouse | -1.127 |
eger | -1.066 |
istar | -1.051 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Reviewer | +1.469 |
iary | +1.380 |
romeda | +1.266 |
raid | +1.191 |
stroke | +1.181 |
Neg logit contributions | |
arta | -2.174 |
urrent | -1.815 |
ighthouse | -1.800 |
eger | -1.727 |
istar | -1.699 |
Token | he |
Token ID | 339 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
arta | +2.015 |
urrent | +1.679 |
ighthouse | +1.653 |
eger | +1.569 |
istar | +1.554 |
Neg logit contributions | |
Reviewer | -1.663 |
iary | -1.570 |
romeda | -1.476 |
raid | -1.380 |
stroke | -1.376 |
Token | no |
Token ID | 645 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
arta | +2.000 |
urrent | +1.637 |
ighthouse | +1.619 |
eger | +1.540 |
istar | +1.511 |
Neg logit contributions | |
Reviewer | -1.824 |
iary | -1.723 |
romeda | -1.616 |
raid | -1.536 |
stroke | -1.513 |
Token | doubt |
Token ID | 4719 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Reviewer | +3.001 |
iary | +2.835 |
romeda | +2.623 |
stroke | +2.559 |
raid | +2.512 |
Neg logit contributions | |
arta | -3.785 |
urrent | -3.173 |
ighthouse | -3.132 |
eger | -2.942 |
byss | -2.917 |
Token | partially |
Token ID | 12387 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
arta | +2.284 |
urrent | +1.883 |
ighthouse | +1.854 |
eger | +1.774 |
istar | +1.743 |
Neg logit contributions | |
Reviewer | -1.958 |
iary | -1.832 |
romeda | -1.719 |
raid | -1.624 |
stroke | -1.598 |
Token | owed |
Token ID | 21057 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
Reviewer | +1.526 |
iary | +1.462 |
romeda | +1.359 |
stroke | +1.279 |
raid | +1.267 |
Neg logit contributions | |
arta | -1.987 |
urrent | -1.665 |
ighthouse | -1.642 |
eger | -1.560 |
istar | -1.553 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Reviewer | +0.817 |
iary | +0.768 |
romeda | +0.700 |
stroke | +0.664 |
raid | +0.656 |
Neg logit contributions | |
arta | -1.183 |
urrent | -0.990 |
ighthouse | -0.975 |
eger | -0.934 |
istar | -0.927 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Reviewer | +1.114 |
iary | +1.052 |
romeda | +0.981 |
stroke | +0.920 |
raid | +0.916 |
Neg logit contributions | |
arta | -1.503 |
urrent | -1.247 |
ighthouse | -1.236 |
eger | -1.184 |
istar | -1.174 |
Token | local |
Token ID | 1957 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arta | +2.018 |
urrent | +1.665 |
ighthouse | +1.635 |
eger | +1.559 |
istar | +1.529 |
Neg logit contributions | |
Reviewer | -1.753 |
iary | -1.649 |
romeda | -1.555 |
raid | -1.469 |
stroke | -1.454 |
Token | top |
Token ID | 1353 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Reviewer | +1.551 |
iary | +1.487 |
romeda | +1.372 |
raid | +1.301 |
stroke | +1.295 |
Neg logit contributions | |
arta | -1.740 |
urrent | -1.439 |
ighthouse | -1.416 |
eger | -1.351 |
istar | -1.340 |
Token | ography |
Token ID | 4867 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
iary | +2.959 |
Reviewer | +2.926 |
romeda | +2.433 |
stroke | +2.386 |
raid | +2.320 |
Neg logit contributions | |
arta | -4.856 |
urrent | -4.210 |
ighthouse | -4.161 |
eger | -3.916 |
istar | -3.913 |
Token | – |
Token ID | 784 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Reviewer | +1.920 |
iary | +1.818 |
romeda | +1.649 |
stroke | +1.569 |
raid | +1.555 |
Neg logit contributions | |
arta | -2.807 |
urrent | -2.377 |
ighthouse | -2.339 |
eger | -2.243 |
istar | -2.232 |
Token | I |
Token ID | 314 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
arta | +3.041 |
urrent | +2.491 |
ighthouse | +2.486 |
eger | +2.346 |
istar | +2.305 |
Neg logit contributions | |
Reviewer | -2.521 |
iary | -2.379 |
romeda | -2.233 |
raid | -2.106 |
stroke | -2.074 |
Token | with |
Token ID | 351 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
arta | +2.590 |
urrent | +2.136 |
ighthouse | +2.120 |
eger | +2.017 |
istar | +1.991 |
Neg logit contributions | |
Reviewer | -2.177 |
iary | -2.061 |
romeda | -1.917 |
raid | -1.818 |
stroke | -1.792 |
Token | an |
Token ID | 281 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
arta | +1.082 |
urrent | +0.896 |
ighthouse | +0.885 |
eger | +0.845 |
istar | +0.832 |
Neg logit contributions | |
Reviewer | -0.882 |
iary | -0.832 |
romeda | -0.778 |
raid | -0.732 |
stroke | -0.727 |
Token | advanced |
Token ID | 6190 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
arta | +1.558 |
urrent | +1.292 |
ighthouse | +1.273 |
eger | +1.209 |
istar | +1.197 |
Neg logit contributions | |
Reviewer | -1.298 |
iary | -1.227 |
romeda | -1.142 |
raid | -1.085 |
stroke | -1.072 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Reviewer | +1.333 |
iary | +1.262 |
romeda | +1.184 |
stroke | +1.112 |
raid | +1.111 |
Neg logit contributions | |
arta | -1.621 |
urrent | -1.345 |
ighthouse | -1.322 |
eger | -1.260 |
istar | -1.243 |
Token | easier |
Token ID | 4577 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
arta | +2.250 |
urrent | +1.850 |
ighthouse | +1.843 |
eger | +1.752 |
istar | +1.720 |
Neg logit contributions | |
Reviewer | -1.919 |
iary | -1.811 |
romeda | -1.685 |
raid | -1.603 |
stroke | -1.573 |
Token | - |
Token ID | 12 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
arta | +0.456 |
urrent | +0.374 |
ighthouse | +0.368 |
eger | +0.350 |
istar | +0.345 |
Neg logit contributions | |
Reviewer | -0.421 |
iary | -0.398 |
romeda | -0.375 |
raid | -0.354 |
stroke | -0.353 |
Token | to |
Token ID | 1462 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Reviewer | +3.131 |
iary | +2.846 |
stroke | +2.748 |
romeda | +2.674 |
raid | +2.607 |
Neg logit contributions | |
arta | -3.702 |
urrent | -3.054 |
ighthouse | -2.995 |
eger | -2.866 |
esson | -2.810 |
Token | - |
Token ID | 12 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Reviewer | +0.577 |
iary | +0.546 |
romeda | +0.516 |
raid | +0.488 |
stroke | +0.484 |
Neg logit contributions | |
arta | -0.587 |
urrent | -0.476 |
ighthouse | -0.470 |
eger | -0.446 |
istar | -0.439 |
Token | use |
Token ID | 1904 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
arta | +0.444 |
urrent | +0.369 |
ighthouse | +0.364 |
eger | +0.347 |
istar | +0.343 |
Neg logit contributions | |
Reviewer | -0.352 |
iary | -0.331 |
romeda | -0.310 |
raid | -0.291 |
stroke | -0.290 |
Token | version |
Token ID | 2196 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
arta | +1.321 |
urrent | +1.089 |
ighthouse | +1.074 |
eger | +1.027 |
istar | +1.012 |
Neg logit contributions | |
Reviewer | -1.111 |
iary | -1.048 |
romeda | -0.983 |
raid | -0.927 |
stroke | -0.918 |
Token | of |
Token ID | 286 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Reviewer | +2.235 |
iary | +2.141 |
romeda | +1.953 |
stroke | +1.846 |
raid | +1.835 |
Neg logit contributions | |
arta | -3.542 |
urrent | -3.015 |
ighthouse | -2.936 |
eger | -2.822 |
istar | -2.788 |
Token | biggest |
Token ID | 4094 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Reviewer | +1.705 |
iary | +1.624 |
romeda | +1.511 |
stroke | +1.425 |
raid | +1.416 |
Neg logit contributions | |
arta | -2.061 |
urrent | -1.693 |
ighthouse | -1.683 |
eger | -1.602 |
istar | -1.576 |
Token | winner |
Token ID | 8464 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
arta | +2.319 |
urrent | +1.920 |
ighthouse | +1.875 |
eger | +1.801 |
istar | +1.741 |
Neg logit contributions | |
Reviewer | -2.116 |
iary | -1.964 |
romeda | -1.894 |
raid | -1.786 |
stroke | -1.734 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Reviewer | +0.515 |
iary | +0.488 |
romeda | +0.453 |
stroke | +0.424 |
raid | +0.422 |
Neg logit contributions | |
arta | -0.711 |
urrent | -0.597 |
ighthouse | -0.589 |
eger | -0.562 |
istar | -0.557 |
Token | the |
Token ID | 262 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
arta | +1.543 |
urrent | +1.279 |
ighthouse | +1.260 |
eger | +1.199 |
istar | +1.179 |
Neg logit contributions | |
Reviewer | -1.288 |
iary | -1.212 |
romeda | -1.137 |
raid | -1.066 |
stroke | -1.060 |
Token | shale |
Token ID | 30498 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
arta | +0.468 |
urrent | +0.385 |
ighthouse | +0.378 |
eger | +0.360 |
istar | +0.354 |
Neg logit contributions | |
Reviewer | -0.424 |
iary | -0.400 |
romeda | -0.377 |
raid | -0.354 |
stroke | -0.353 |
Token | fracking |
Token ID | 25441 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Reviewer | +1.192 |
iary | +1.142 |
romeda | +1.069 |
raid | +1.023 |
stroke | +1.017 |
Neg logit contributions | |
arta | -1.268 |
urrent | -1.032 |
ighthouse | -1.020 |
eger | -0.969 |
istar | -0.959 |
Token | boom |
Token ID | 14166 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Reviewer | +1.238 |
iary | +1.183 |
romeda | +1.110 |
raid | +1.057 |
stroke | +1.051 |
Neg logit contributions | |
arta | -1.332 |
urrent | -1.090 |
ighthouse | -1.076 |
eger | -1.025 |
istar | -1.007 |
Token | . |
Token ID | 13 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
Reviewer | +1.951 |
iary | +1.864 |
romeda | +1.727 |
stroke | +1.634 |
raid | +1.626 |
Neg logit contributions | |
arta | -2.756 |
urrent | -2.315 |
ighthouse | -2.294 |
eger | -2.193 |
istar | -2.170 |
Token | And |
Token ID | 843 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
arta | +0.865 |
urrent | +0.704 |
ighthouse | +0.695 |
eger | +0.656 |
istar | +0.648 |
Neg logit contributions | |
Reviewer | -0.826 |
iary | -0.782 |
romeda | -0.741 |
raid | -0.700 |
stroke | -0.694 |
Token | that |
Token ID | 326 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Reviewer | +0.835 |
iary | +0.787 |
romeda | +0.738 |
raid | +0.687 |
stroke | +0.684 |
Neg logit contributions | |
arta | -1.121 |
urrent | -0.935 |
ighthouse | -0.926 |
eger | -0.884 |
istar | -0.874 |
Token | figure |
Token ID | 3785 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Reviewer | +0.932 |
iary | +0.882 |
romeda | +0.825 |
stroke | +0.772 |
raid | +0.767 |
Neg logit contributions | |
arta | -1.214 |
urrent | -1.012 |
ighthouse | -1.001 |
eger | -0.955 |
istar | -0.946 |
Token | Obviously |
Token ID | 20670 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Reviewer | +0.272 |
iary | +0.257 |
romeda | +0.240 |
raid | +0.225 |
stroke | +0.225 |
Neg logit contributions | |
arta | -0.323 |
urrent | -0.267 |
ighthouse | -0.263 |
eger | -0.251 |
istar | -0.248 |
Token | it |
Token ID | 340 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Reviewer | +3.112 |
iary | +2.958 |
romeda | +2.788 |
stroke | +2.555 |
raid | +2.528 |
Neg logit contributions | |
arta | -4.624 |
urrent | -3.888 |
ighthouse | -3.854 |
istar | -3.659 |
eger | -3.659 |
Token | was |
Token ID | 373 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Reviewer | +2.125 |
iary | +2.060 |
romeda | +1.906 |
stroke | +1.802 |
raid | +1.754 |
Neg logit contributions | |
arta | -3.057 |
urrent | -2.586 |
ighthouse | -2.560 |
eger | -2.439 |
byss | -2.411 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Reviewer | +3.880 |
iary | +3.649 |
romeda | +3.487 |
stroke | +3.255 |
raid | +3.138 |
Neg logit contributions | |
arta | -5.928 |
urrent | -4.983 |
ighthouse | -4.885 |
eger | -4.694 |
byss | -4.665 |
Token | mismatch |
Token ID | 46318 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Reviewer | +2.109 |
iary | +2.001 |
romeda | +1.876 |
stroke | +1.767 |
raid | +1.749 |
Neg logit contributions | |
arta | -2.855 |
urrent | -2.389 |
ighthouse | -2.356 |
eger | -2.235 |
istar | -2.227 |
Token | tonight |
Token ID | 9975 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Reviewer | +1.781 |
iary | +1.700 |
romeda | +1.585 |
stroke | +1.493 |
raid | +1.471 |
Neg logit contributions | |
arta | -2.579 |
urrent | -2.166 |
ighthouse | -2.144 |
eger | -2.054 |
istar | -2.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Reviewer | +2.215 |
iary | +2.093 |
romeda | +1.944 |
stroke | +1.825 |
raid | +1.811 |
Neg logit contributions | |
arta | -3.243 |
urrent | -2.712 |
ighthouse | -2.669 |
eger | -2.570 |
istar | -2.510 |
Token | Look |
Token ID | 6803 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
Reviewer | +1.160 |
iary | +1.098 |
romeda | +1.028 |
stroke | +0.964 |
raid | +0.960 |
Neg logit contributions | |
arta | -1.417 |
urrent | -1.179 |
ighthouse | -1.160 |
eger | -1.112 |
istar | -1.091 |
Token | ed |
Token ID | 276 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Reviewer | +0.340 |
iary | +0.320 |
romeda | +0.297 |
raid | +0.276 |
stroke | +0.276 |
Neg logit contributions | |
arta | -0.500 |
urrent | -0.422 |
ighthouse | -0.416 |
eger | -0.397 |
istar | -0.394 |
Token | like |
Token ID | 588 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Reviewer | +1.421 |
iary | +1.354 |
romeda | +1.259 |
raid | +1.179 |
stroke | +1.179 |
Neg logit contributions | |
arta | -1.920 |
urrent | -1.606 |
ighthouse | -1.577 |
eger | -1.502 |
istar | -1.481 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Reviewer | +0.112 |
iary | +0.106 |
romeda | +0.099 |
raid | +0.093 |
stroke | +0.092 |
Neg logit contributions | |
arta | -0.150 |
urrent | -0.125 |
ighthouse | -0.124 |
eger | -0.118 |
istar | -0.117 |
Token | g |
Token ID | 70 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Reviewer | +0.090 |
iary | +0.086 |
romeda | +0.081 |
raid | +0.077 |
stroke | +0.076 |
Neg logit contributions | |
arta | -0.093 |
urrent | -0.076 |
ighthouse | -0.075 |
eger | -0.071 |
istar | -0.070 |
Token | wit |
Token ID | 39289 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Reviewer | +3.361 |
iary | +3.232 |
romeda | +3.007 |
stroke | +2.902 |
raid | +2.889 |
Neg logit contributions | |
arta | -3.294 |
urrent | -2.650 |
ighthouse | -2.594 |
eger | -2.484 |
istar | -2.431 |
Token | 4 |
Token ID | 604 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
Reviewer | +1.365 |
iary | +1.302 |
romeda | +1.212 |
raid | +1.149 |
stroke | +1.147 |
Neg logit contributions | |
arta | -1.654 |
urrent | -1.360 |
ighthouse | -1.339 |
eger | -1.286 |
istar | -1.256 |
Token | MB |
Token ID | 10744 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
Reviewer | +0.902 |
iary | +0.853 |
romeda | +0.797 |
raid | +0.754 |
stroke | +0.751 |
Neg logit contributions | |
arta | -1.133 |
urrent | -0.935 |
ighthouse | -0.920 |
eger | -0.881 |
istar | -0.867 |
Token | block |
Token ID | 2512 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Reviewer | +0.890 |
iary | +0.846 |
romeda | +0.792 |
raid | +0.750 |
stroke | +0.749 |
Neg logit contributions | |
arta | -1.044 |
urrent | -0.859 |
ighthouse | -0.847 |
eger | -0.809 |
istar | -0.795 |
Token | soft |
Token ID | 2705 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Reviewer | +4.283 |
iary | +4.153 |
romeda | +3.822 |
stroke | +3.706 |
raid | +3.699 |
Neg logit contributions | |
arta | -5.518 |
urrent | -4.595 |
ighthouse | -4.510 |
eger | -4.372 |
byss | -4.227 |
Token | - |
Token ID | 12 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
Reviewer | +2.509 |
iary | +2.319 |
romeda | +2.154 |
raid | +2.094 |
stroke | +2.073 |
Neg logit contributions | |
arta | -4.009 |
urrent | -3.431 |
ighthouse | -3.324 |
eger | -3.230 |
istar | -3.187 |
Token | fork |
Token ID | 32523 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Reviewer | +4.964 |
raid | +4.634 |
stroke | +4.515 |
iary | +4.474 |
pl | +4.257 |
Neg logit contributions | |
arta | -10.989 |
urrent | -9.438 |
ighthouse | -9.074 |
mosqu | -9.009 |
byss | -8.929 |
Token | which |
Token ID | 543 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
Reviewer | +1.449 |
iary | +1.379 |
romeda | +1.289 |
raid | +1.214 |
stroke | +1.211 |
Neg logit contributions | |
arta | -1.968 |
urrent | -1.641 |
ighthouse | -1.625 |
eger | -1.560 |
istar | -1.529 |
Token | increases |
Token ID | 5732 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
arta | +0.489 |
urrent | +0.404 |
ighthouse | +0.399 |
eger | +0.380 |
istar | +0.375 |
Neg logit contributions | |
Reviewer | -0.405 |
iary | -0.381 |
romeda | -0.358 |
raid | -0.337 |
stroke | -0.335 |
Token | capacity |
Token ID | 5339 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
arta | +2.444 |
urrent | +2.034 |
ighthouse | +2.012 |
eger | +1.902 |
istar | +1.887 |
Neg logit contributions | |
Reviewer | -2.027 |
iary | -1.912 |
romeda | -1.804 |
raid | -1.695 |
stroke | -1.673 |
Token | passed |
Token ID | 3804 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Reviewer | +0.868 |
iary | +0.820 |
romeda | +0.769 |
raid | +0.723 |
stroke | +0.722 |
Neg logit contributions | |
arta | -1.038 |
urrent | -0.860 |
ighthouse | -0.850 |
eger | -0.808 |
istar | -0.794 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Reviewer | +3.008 |
iary | +2.820 |
romeda | +2.644 |
raid | +2.450 |
stroke | +2.450 |
Neg logit contributions | |
arta | -4.066 |
urrent | -3.423 |
ighthouse | -3.363 |
eger | -3.197 |
byss | -3.163 |
Token | 2 |
Token ID | 362 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
Reviewer | +2.813 |
iary | +2.681 |
romeda | +2.548 |
raid | +2.379 |
stroke | +2.357 |
Neg logit contributions | |
arta | -3.295 |
urrent | -2.721 |
ighthouse | -2.701 |
eger | -2.557 |
byss | -2.530 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
arta | +0.902 |
urrent | +0.751 |
ighthouse | +0.740 |
eger | +0.707 |
istar | +0.697 |
Neg logit contributions | |
Reviewer | -0.690 |
iary | -0.651 |
romeda | -0.608 |
raid | -0.570 |
stroke | -0.569 |
Token | 07 |
Token ID | 2998 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Reviewer | +1.689 |
iary | +1.612 |
romeda | +1.515 |
raid | +1.429 |
stroke | +1.428 |
Neg logit contributions | |
arta | -1.903 |
urrent | -1.570 |
ighthouse | -1.540 |
eger | -1.470 |
istar | -1.447 |
Token | 6 |
Token ID | 21 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
Reviewer | +1.319 |
iary | +1.260 |
romeda | +1.178 |
stroke | +1.107 |
raid | +1.102 |
Neg logit contributions | |
arta | -1.588 |
urrent | -1.315 |
ighthouse | -1.302 |
eger | -1.239 |
istar | -1.216 |
Token | - |
Token ID | 12 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Reviewer | +0.845 |
iary | +0.809 |
romeda | +0.769 |
stroke | +0.735 |
raid | +0.731 |
Neg logit contributions | |
arta | -0.616 |
urrent | -0.479 |
ighthouse | -0.467 |
eger | -0.435 |
istar | -0.426 |
Token | kil |
Token ID | 34553 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Reviewer | +4.537 |
iary | +4.291 |
stroke | +4.018 |
romeda | +4.006 |
raid | +3.879 |
Neg logit contributions | |
arta | -5.228 |
urrent | -4.279 |
ighthouse | -4.150 |
eger | -4.075 |
byss | -3.945 |
Token | ometer |
Token ID | 15635 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
arta | +1.340 |
urrent | +1.021 |
ighthouse | +0.999 |
eger | +0.930 |
istar | +0.910 |
Neg logit contributions | |
Reviewer | -2.076 |
iary | -1.976 |
romeda | -1.897 |
raid | -1.816 |
stroke | -1.804 |
Token | ( |
Token ID | 357 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Reviewer | +6.121 |
iary | +5.919 |
romeda | +5.770 |
stroke | +5.384 |
pl | +5.163 |
Neg logit contributions | |
arta | -9.049 |
urrent | -7.746 |
ighthouse | -7.639 |
byss | -7.345 |
stration | -7.264 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
arta | +0.350 |
urrent | +0.288 |
ighthouse | +0.284 |
eger | +0.270 |
istar | +0.266 |
Neg logit contributions | |
Reviewer | -0.307 |
iary | -0.290 |
romeda | -0.272 |
raid | -0.257 |
stroke | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Reviewer | +3.816 |
iary | +3.734 |
romeda | +3.427 |
stroke | +3.209 |
raid | +3.184 |
Neg logit contributions | |
arta | -5.081 |
urrent | -4.348 |
ighthouse | -4.248 |
eger | -4.113 |
istar | -3.987 |
Token |
|
Token ID | 198 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Reviewer | +2.834 |
iary | +2.705 |
romeda | +2.469 |
stroke | +2.395 |
raid | +2.356 |
Neg logit contributions | |
arta | -3.408 |
urrent | -2.844 |
ighthouse | -2.789 |
byss | -2.667 |
eger | -2.664 |
Token | James |
Token ID | 14731 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Reviewer | +4.968 |
iary | +4.465 |
romeda | +4.025 |
stroke | +4.006 |
raid | +4.003 |
Neg logit contributions | |
arta | -5.789 |
urrent | -4.879 |
ighthouse | -4.820 |
mosqu | -4.703 |
eger | -4.654 |
Token | Barnes |
Token ID | 21335 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Reviewer | +3.334 |
iary | +3.301 |
romeda | +3.020 |
stroke | +2.893 |
raid | +2.883 |
Neg logit contributions | |
arta | -4.278 |
urrent | -3.618 |
ighthouse | -3.538 |
eger | -3.396 |
istar | -3.380 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
arta | +2.519 |
urrent | +2.077 |
ighthouse | +2.056 |
eger | +1.966 |
istar | +1.926 |
Neg logit contributions | |
Reviewer | -2.086 |
iary | -1.924 |
romeda | -1.822 |
raid | -1.705 |
stroke | -1.690 |
Token | chief |
Token ID | 4039 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Reviewer | +3.007 |
iary | +2.894 |
romeda | +2.677 |
stroke | +2.499 |
raid | +2.479 |
Neg logit contributions | |
arta | -4.595 |
urrent | -3.852 |
ighthouse | -3.788 |
eger | -3.680 |
byss | -3.581 |
Token | executive |
Token ID | 4640 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
iary | +5.754 |
Reviewer | +5.586 |
stroke | +4.615 |
pl | +4.500 |
romeda | +4.414 |
Neg logit contributions | |
arta | -10.824 |
urrent | -9.425 |
ighthouse | -9.156 |
esson | -8.923 |
istar | -8.814 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
arta | +1.307 |
urrent | +1.093 |
ighthouse | +1.079 |
eger | +1.032 |
istar | +1.019 |
Neg logit contributions | |
Reviewer | -0.956 |
iary | -0.900 |
romeda | -0.839 |
raid | -0.784 |
stroke | -0.781 |
Token | D |
Token ID | 360 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Reviewer | +1.086 |
iary | +1.035 |
romeda | +0.966 |
raid | +0.904 |
stroke | +0.901 |
Neg logit contributions | |
arta | -1.426 |
urrent | -1.190 |
ighthouse | -1.175 |
eger | -1.125 |
istar | -1.110 |
Token | obbies |
Token ID | 41372 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Reviewer | +3.539 |
iary | +3.337 |
romeda | +2.961 |
raid | +2.795 |
stroke | +2.697 |
Neg logit contributions | |
arta | -6.648 |
urrent | -5.761 |
ighthouse | -5.634 |
byss | -5.484 |
mosqu | -5.475 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Reviewer | +1.345 |
iary | +1.296 |
romeda | +1.184 |
stroke | +1.114 |
raid | +1.111 |
Neg logit contributions | |
arta | -1.918 |
urrent | -1.615 |
ighthouse | -1.592 |
eger | -1.519 |
istar | -1.518 |
Token | due |
Token ID | 2233 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
arta | +0.851 |
urrent | +0.707 |
ighthouse | +0.697 |
eger | +0.665 |
istar | +0.656 |
Neg logit contributions | |
Reviewer | -0.683 |
iary | -0.642 |
romeda | -0.603 |
raid | -0.564 |
stroke | -0.562 |
Token | to |
Token ID | 284 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
arta | +2.501 |
urrent | +2.078 |
ighthouse | +2.052 |
eger | +1.956 |
istar | +1.930 |
Neg logit contributions | |
Reviewer | -1.981 |
iary | -1.866 |
romeda | -1.754 |
raid | -1.641 |
stroke | -1.630 |
Token | an |
Token ID | 281 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
arta | +0.760 |
urrent | +0.629 |
ighthouse | +0.620 |
eger | +0.591 |
istar | +0.583 |
Neg logit contributions | |
Reviewer | -0.634 |
iary | -0.598 |
romeda | -0.561 |
raid | -0.528 |
stroke | -0.525 |
Token | omission |
Token ID | 35725 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
arta | +0.958 |
urrent | +0.786 |
ighthouse | +0.775 |
eger | +0.737 |
istar | +0.726 |
Neg logit contributions | |
Reviewer | -0.862 |
iary | -0.816 |
romeda | -0.768 |
raid | -0.724 |
stroke | -0.721 |
Token | from |
Token ID | 422 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
arta | +0.523 |
urrent | +0.437 |
ighthouse | +0.432 |
eger | +0.413 |
istar | +0.407 |
Neg logit contributions | |
Reviewer | -0.388 |
iary | -0.366 |
romeda | -0.341 |
raid | -0.319 |
stroke | -0.318 |
Token | Team |
Token ID | 4816 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
Reviewer | +0.364 |
iary | +0.345 |
romeda | +0.322 |
raid | +0.301 |
stroke | +0.301 |
Neg logit contributions | |
arta | -0.468 |
urrent | -0.387 |
ighthouse | -0.382 |
eger | -0.364 |
istar | -0.359 |
Token | USA |
Token ID | 4916 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
Reviewer | +6.861 |
iary | +6.819 |
romeda | +5.904 |
pl | +5.707 |
achev | +5.557 |
Neg logit contributions | |
arta | -12.992 |
urrent | -11.534 |
byss | -11.084 |
ighthouse | -10.990 |
eger | -10.858 |
Token | � |
Token ID | 447 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
arta | +0.433 |
urrent | +0.361 |
ighthouse | +0.356 |
eger | +0.340 |
istar | +0.336 |
Neg logit contributions | |
Reviewer | -0.329 |
iary | -0.310 |
romeda | -0.290 |
raid | -0.271 |
stroke | -0.270 |
Token | � |
Token ID | 247 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
Reviewer | +1.709 |
iary | +1.631 |
romeda | +1.546 |
raid | +1.468 |
stroke | +1.466 |
Neg logit contributions | |
arta | -1.509 |
urrent | -1.200 |
ighthouse | -1.179 |
eger | -1.108 |
istar | -1.099 |
Token | s |
Token ID | 82 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Reviewer | +0.943 |
iary | +0.895 |
romeda | +0.843 |
raid | +0.805 |
stroke | +0.803 |
Neg logit contributions | |
arta | -0.916 |
urrent | -0.740 |
ighthouse | -0.731 |
eger | -0.692 |
istar | -0.676 |
Token | roster |
Token ID | 9354 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
arta | +3.810 |
urrent | +3.178 |
ighthouse | +3.117 |
istar | +2.970 |
eger | +2.952 |
Neg logit contributions | |
Reviewer | -3.381 |
iary | -3.104 |
romeda | -2.927 |
raid | -2.761 |
stroke | -2.746 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Reviewer | +0.934 |
iary | +0.866 |
romeda | +0.808 |
stroke | +0.752 |
raid | +0.748 |
Neg logit contributions | |
arta | -1.287 |
urrent | -1.072 |
ighthouse | -1.054 |
eger | -1.013 |
istar | -0.996 |
Token | most |
Token ID | 749 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arta | +1.471 |
urrent | +1.192 |
ighthouse | +1.172 |
eger | +1.110 |
istar | +1.094 |
Neg logit contributions | |
Reviewer | -1.535 |
iary | -1.465 |
romeda | -1.383 |
raid | -1.312 |
stroke | -1.303 |
Token | skill |
Token ID | 5032 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
arta | +1.386 |
urrent | +1.115 |
ighthouse | +1.100 |
eger | +1.036 |
istar | +1.018 |
Neg logit contributions | |
Reviewer | -1.506 |
iary | -1.432 |
romeda | -1.353 |
raid | -1.287 |
stroke | -1.281 |
Token | fully |
Token ID | 2759 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Reviewer | +2.629 |
iary | +2.392 |
romeda | +2.166 |
stroke | +2.134 |
raid | +2.084 |
Neg logit contributions | |
arta | -4.587 |
urrent | -3.881 |
ighthouse | -3.845 |
eger | -3.675 |
istar | -3.623 |
Token | - |
Token ID | 12 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
arta | +0.659 |
urrent | +0.550 |
ighthouse | +0.543 |
eger | +0.518 |
istar | +0.511 |
Neg logit contributions | |
Reviewer | -0.506 |
iary | -0.475 |
romeda | -0.445 |
raid | -0.417 |
stroke | -0.415 |
Token | l |
Token ID | 75 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
Reviewer | +2.985 |
iary | +2.825 |
romeda | +2.607 |
stroke | +2.576 |
raid | +2.547 |
Neg logit contributions | |
arta | -3.668 |
urrent | -3.012 |
ighthouse | -2.989 |
eger | -2.863 |
istar | -2.819 |
Token | iked |
Token ID | 17951 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
Reviewer | +6.817 |
iary | +6.465 |
pl | +5.796 |
raid | +5.681 |
romeda | +5.493 |
Neg logit contributions | |
arta | -11.596 |
mosqu | -10.021 |
byss | -9.889 |
urrent | -9.762 |
eger | -9.624 |
Token | media |
Token ID | 2056 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
arta | +1.238 |
urrent | +1.024 |
ighthouse | +1.009 |
eger | +0.962 |
istar | +0.948 |
Neg logit contributions | |
Reviewer | -1.051 |
iary | -0.990 |
romeda | -0.934 |
raid | -0.874 |
stroke | -0.873 |
Token | centers |
Token ID | 10399 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
arta | +7.268 |
urrent | +5.985 |
ighthouse | +5.953 |
eger | +5.575 |
istar | +5.506 |
Neg logit contributions | |
Reviewer | -6.111 |
iary | -5.703 |
romeda | -5.362 |
stroke | -4.997 |
raid | -4.917 |
Token | . |
Token ID | 13 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
arta | +3.902 |
urrent | +3.224 |
ighthouse | +3.203 |
eger | +3.013 |
istar | +2.994 |
Neg logit contributions | |
Reviewer | -3.381 |
iary | -3.166 |
romeda | -2.986 |
raid | -2.831 |
stroke | -2.798 |
Token | Therefore |
Token ID | 8447 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
arta | +1.100 |
urrent | +0.896 |
ighthouse | +0.884 |
eger | +0.832 |
istar | +0.824 |
Neg logit contributions | |
Reviewer | -1.066 |
iary | -1.012 |
romeda | -0.957 |
raid | -0.905 |
stroke | -0.898 |
Token | Nom |
Token ID | 21198 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Reviewer | +5.457 |
iary | +5.201 |
romeda | +4.614 |
raid | +4.386 |
stroke | +4.383 |
Neg logit contributions | |
arta | -6.361 |
urrent | -5.204 |
ighthouse | -5.090 |
eger | -4.934 |
byss | -4.882 |
Token | ination |
Token ID | 1883 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Reviewer | +0.807 |
iary | +0.783 |
romeda | +0.739 |
raid | +0.708 |
stroke | +0.705 |
Neg logit contributions | |
arta | -0.547 |
urrent | -0.420 |
ighthouse | -0.410 |
eger | -0.383 |
istar | -0.373 |
Token | Pack |
Token ID | 6400 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Reviewer | +3.192 |
iary | +3.021 |
romeda | +2.693 |
stroke | +2.496 |
raid | +2.491 |
Neg logit contributions | |
arta | -4.684 |
urrent | -3.999 |
ighthouse | -3.888 |
eger | -3.762 |
istar | -3.709 |
Token | et |
Token ID | 316 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
Reviewer | +1.644 |
iary | +1.575 |
romeda | +1.448 |
raid | +1.358 |
stroke | +1.330 |
Neg logit contributions | |
arta | -2.386 |
urrent | -2.020 |
ighthouse | -1.996 |
eger | -1.907 |
istar | -1.894 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Reviewer | +1.317 |
iary | +1.248 |
romeda | +1.145 |
raid | +1.073 |
stroke | +1.061 |
Neg logit contributions | |
arta | -1.877 |
urrent | -1.571 |
ighthouse | -1.556 |
eger | -1.489 |
istar | -1.473 |
Token | submit |
Token ID | 9199 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Reviewer | +2.494 |
iary | +2.384 |
romeda | +2.227 |
stroke | +2.055 |
raid | +2.054 |
Neg logit contributions | |
arta | -2.960 |
urrent | -2.424 |
ighthouse | -2.413 |
eger | -2.289 |
istar | -2.285 |
Token | all |
Token ID | 477 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Reviewer | +5.652 |
iary | +5.558 |
romeda | +4.571 |
pl | +4.237 |
stroke | +4.139 |
Neg logit contributions | |
arta | -11.954 |
urrent | -10.029 |
ighthouse | -9.954 |
byss | -9.540 |
istar | -9.512 |
Token | materials |
Token ID | 5696 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Reviewer | +5.689 |
iary | +5.663 |
romeda | +4.969 |
pl | +4.555 |
stroke | +4.532 |
Neg logit contributions | |
arta | -8.083 |
urrent | -6.593 |
ighthouse | -6.377 |
eger | -6.163 |
byss | -6.157 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Reviewer | +1.144 |
iary | +1.078 |
romeda | +0.991 |
stroke | +0.932 |
raid | +0.927 |
Neg logit contributions | |
arta | -1.593 |
urrent | -1.332 |
ighthouse | -1.314 |
eger | -1.251 |
istar | -1.242 |
Token | groups |
Token ID | 2628 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Reviewer | +0.117 |
iary | +0.111 |
romeda | +0.104 |
raid | +0.098 |
stroke | +0.098 |
Neg logit contributions | |
arta | -0.135 |
urrent | -0.111 |
ighthouse | -0.110 |
eger | -0.104 |
istar | -0.103 |
Token | @ |
Token ID | 31 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Reviewer | +2.669 |
iary | +2.545 |
romeda | +2.385 |
raid | +2.211 |
stroke | +2.195 |
Neg logit contributions | |
arta | -3.925 |
urrent | -3.270 |
ighthouse | -3.230 |
eger | -3.116 |
istar | -3.062 |
Token | its |
Token ID | 663 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Reviewer | +3.281 |
iary | +3.094 |
romeda | +2.836 |
raid | +2.648 |
stroke | +2.630 |
Neg logit contributions | |
arta | -4.560 |
urrent | -3.795 |
ighthouse | -3.785 |
eger | -3.631 |
byss | -3.614 |
Token | 10 |
Token ID | 838 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Reviewer | +3.303 |
iary | +3.187 |
romeda | +2.932 |
raid | +2.761 |
stroke | +2.703 |
Neg logit contributions | |
arta | -4.180 |
urrent | -3.406 |
ighthouse | -3.385 |
eger | -3.270 |
byss | -3.211 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Reviewer | +4.116 |
iary | +4.026 |
romeda | +3.494 |
raid | +3.392 |
stroke | +3.386 |
Neg logit contributions | |
arta | -5.671 |
urrent | -4.673 |
ighthouse | -4.536 |
eger | -4.442 |
istar | -4.337 |
Token | 000 |
Token ID | 830 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Reviewer | +3.447 |
iary | +3.317 |
romeda | +3.057 |
raid | +2.904 |
stroke | +2.904 |
Neg logit contributions | |
arta | -3.519 |
urrent | -2.848 |
ighthouse | -2.750 |
eger | -2.677 |
byss | -2.618 |
Token | - |
Token ID | 12 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
Reviewer | +2.800 |
iary | +2.694 |
romeda | +2.456 |
stroke | +2.322 |
raid | +2.313 |
Neg logit contributions | |
arta | -3.287 |
urrent | -2.705 |
ighthouse | -2.662 |
eger | -2.561 |
byss | -2.501 |
Token | piece |
Token ID | 12239 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Reviewer | +4.103 |
iary | +3.854 |
stroke | +3.357 |
romeda | +3.353 |
raid | +3.349 |
Neg logit contributions | |
arta | -7.262 |
urrent | -6.195 |
ighthouse | -6.192 |
eger | -6.077 |
byss | -5.890 |
Token | collection |
Token ID | 4947 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
iary | +7.784 |
Reviewer | +7.750 |
romeda | +7.017 |
pl | +6.513 |
raid | +6.490 |
Neg logit contributions | |
arta | -8.969 |
ighthouse | -7.435 |
urrent | -7.426 |
byss | -7.295 |
eger | -7.181 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
arta | +3.379 |
urrent | +2.751 |
ighthouse | +2.710 |
eger | +2.578 |
istar | +2.557 |
Neg logit contributions | |
Reviewer | -3.086 |
iary | -2.872 |
romeda | -2.731 |
raid | -2.607 |
stroke | -2.596 |
Token | featured |
Token ID | 8096 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
Reviewer | +0.037 |
iary | +0.035 |
romeda | +0.033 |
raid | +0.031 |
stroke | +0.031 |
Neg logit contributions | |
arta | -0.039 |
urrent | -0.032 |
ighthouse | -0.031 |
eger | -0.030 |
istar | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
Reviewer | +0.532 |
iary | +0.501 |
romeda | +0.465 |
stroke | +0.438 |
raid | +0.436 |
Neg logit contributions | |
arta | -0.676 |
urrent | -0.562 |
ighthouse | -0.555 |
eger | -0.528 |
istar | -0.523 |
Token | 38 |
Token ID | 4353 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Reviewer | +0.344 |
iary | +0.325 |
romeda | +0.301 |
raid | +0.284 |
stroke | +0.282 |
Neg logit contributions | |
arta | -0.434 |
urrent | -0.362 |
ighthouse | -0.356 |
eger | -0.341 |
istar | -0.336 |