Token | that |
Token ID | 326 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
weather | +0.960 |
ipers | +0.917 |
opp | +0.893 |
rador | +0.886 |
ricted | +0.871 |
Neg logit contributions | |
hens | -1.153 |
@@@@ | -1.142 |
═ | -1.026 |
� | -1.023 |
hust | -1.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
weather | +1.411 |
ipers | +1.345 |
opp | +1.309 |
rador | +1.298 |
ricted | +1.276 |
Neg logit contributions | |
hens | -1.790 |
@@@@ | -1.772 |
═ | -1.595 |
� | -1.591 |
hust | -1.587 |
Token | Top |
Token ID | 5849 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
weather | +0.813 |
ipers | +0.776 |
opp | +0.756 |
rador | +0.750 |
ricted | +0.738 |
Neg logit contributions | |
hens | -0.974 |
@@@@ | -0.964 |
═ | -0.865 |
hust | -0.863 |
tin | -0.862 |
Token | End |
Token ID | 5268 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
hens | +0.778 |
@@@@ | +0.765 |
tin | +0.689 |
═ | +0.687 |
� | +0.684 |
Neg logit contributions | |
weather | -0.613 |
ipers | -0.585 |
opp | -0.569 |
rador | -0.564 |
ricted | -0.551 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
weather | +0.918 |
ipers | +0.875 |
opp | +0.853 |
rador | +0.847 |
ricted | +0.832 |
Neg logit contributions | |
hens | -1.054 |
@@@@ | -1.037 |
═ | -0.930 |
tin | -0.926 |
hust | -0.926 |
Token | Kimber |
Token ID | 36015 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
weather | +0.234 |
ipers | +0.224 |
opp | +0.219 |
rador | +0.217 |
ricted | +0.214 |
Neg logit contributions | |
hens | -0.224 |
@@@@ | -0.221 |
═ | -0.196 |
� | -0.195 |
hust | -0.195 |
Token | ley |
Token ID | 1636 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
hens | +5.707 |
@@@@ | +5.622 |
═ | +4.839 |
tin | +4.837 |
hust | +4.821 |
Neg logit contributions | |
weather | -9.428 |
ipers | -9.167 |
Downloadha | -9.044 |
opp | -8.946 |
rador | -8.922 |
Token | rock |
Token ID | 3881 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
hens | +3.049 |
@@@@ | +2.961 |
tin | +2.733 |
hust | +2.730 |
@#& | +2.700 |
Neg logit contributions | |
weather | -2.234 |
ipers | -2.117 |
opp | -2.071 |
rador | -2.039 |
ricted | -2.015 |
Token | - |
Token ID | 12 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hens | +3.560 |
@@@@ | +3.452 |
═ | +3.156 |
hust | +3.138 |
tin | +3.133 |
Neg logit contributions | |
weather | -2.744 |
ipers | -2.625 |
opp | -2.598 |
ricted | -2.577 |
rador | -2.554 |
Token | wall |
Token ID | 11930 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
hens | +1.139 |
@@@@ | +1.117 |
tin | +1.022 |
═ | +1.021 |
� | +1.013 |
Neg logit contributions | |
weather | -0.703 |
ipers | -0.669 |
opp | -0.648 |
rador | -0.648 |
ricted | -0.638 |
Token | aby |
Token ID | 3930 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
hens | +0.758 |
@@@@ | +0.735 |
hust | +0.669 |
tin | +0.662 |
═ | +0.662 |
Neg logit contributions | |
weather | -0.580 |
ipers | -0.543 |
opp | -0.533 |
rador | -0.530 |
ricted | -0.527 |
Token | ological |
Token ID | 2770 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
hens | +4.503 |
@@@@ | +4.391 |
═ | +3.965 |
tin | +3.922 |
Scroll | +3.902 |
Neg logit contributions | |
weather | -3.771 |
ipers | -3.669 |
rador | -3.581 |
Downloadha | -3.579 |
ricted | -3.519 |
Token | profile |
Token ID | 7034 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
hens | +2.960 |
@@@@ | +2.958 |
hust | +2.700 |
tin | +2.662 |
═ | +2.608 |
Neg logit contributions | |
weather | -3.009 |
ipers | -2.893 |
rador | -2.859 |
Downloadha | -2.802 |
esta | -2.771 |
Token | of |
Token ID | 286 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
hens | +0.303 |
@@@@ | +0.299 |
═ | +0.269 |
� | +0.268 |
tin | +0.267 |
Neg logit contributions | |
weather | -0.254 |
ipers | -0.243 |
opp | -0.236 |
rador | -0.235 |
ricted | -0.230 |
Token | N |
Token ID | 399 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
weather | +0.226 |
ipers | +0.216 |
opp | +0.210 |
rador | +0.209 |
ricted | +0.206 |
Neg logit contributions | |
hens | -0.254 |
@@@@ | -0.251 |
═ | -0.225 |
tin | -0.223 |
hust | -0.223 |
Token | - |
Token ID | 12 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
weather | +0.573 |
ipers | +0.546 |
opp | +0.532 |
rador | +0.525 |
ricted | +0.517 |
Neg logit contributions | |
hens | -0.758 |
@@@@ | -0.751 |
� | -0.677 |
═ | -0.676 |
hust | -0.674 |
Token | cyclop |
Token ID | 22873 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
weather | +0.205 |
ipers | +0.194 |
opp | +0.188 |
rador | +0.186 |
ricted | +0.182 |
Neg logit contributions | |
hens | -0.326 |
@@@@ | -0.323 |
� | -0.294 |
═ | -0.293 |
hust | -0.292 |
Token | rop |
Token ID | 1773 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
hens | +8.587 |
@@@@ | +7.967 |
dial | +7.441 |
═ | +7.429 |
tin | +7.423 |
Neg logit contributions | |
Downloadha | -6.657 |
weather | -6.608 |
ipers | -6.317 |
rador | -6.295 |
ricted | -6.063 |
Token | yl |
Token ID | 2645 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hens | +4.204 |
@@@@ | +3.816 |
tin | +3.633 |
dial | +3.549 |
hust | +3.505 |
Neg logit contributions | |
weather | -2.958 |
ipers | -2.853 |
Downloadha | -2.777 |
rador | -2.765 |
opp | -2.708 |
Token | methyl |
Token ID | 43654 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
weather | +0.966 |
ipers | +0.922 |
opp | +0.902 |
rador | +0.887 |
ricted | +0.873 |
Neg logit contributions | |
@@@@ | -1.203 |
hens | -1.201 |
� | -1.077 |
═ | -1.076 |
hust | -1.067 |
Token | - |
Token ID | 12 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
hens | +0.264 |
@@@@ | +0.261 |
═ | +0.235 |
� | +0.234 |
tin | +0.233 |
Neg logit contributions | |
weather | -0.224 |
ipers | -0.214 |
opp | -0.208 |
rador | -0.207 |
ricted | -0.204 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
hens | +0.129 |
@@@@ | +0.127 |
═ | +0.115 |
tin | +0.115 |
� | +0.114 |
Neg logit contributions | |
weather | -0.107 |
ipers | -0.102 |
rador | -0.099 |
opp | -0.099 |
ricted | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
weather | +1.425 |
ipers | +1.362 |
opp | +1.329 |
rador | +1.314 |
ricted | +1.295 |
Neg logit contributions | |
hens | -1.747 |
@@@@ | -1.730 |
═ | -1.561 |
� | -1.558 |
tin | -1.544 |
Token | B |
Token ID | 347 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
weather | +0.302 |
ipers | +0.289 |
opp | +0.282 |
rador | +0.280 |
ricted | +0.276 |
Neg logit contributions | |
hens | -0.317 |
@@@@ | -0.313 |
═ | -0.278 |
hust | -0.278 |
� | -0.278 |
Token | orne |
Token ID | 8553 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
hens | +0.671 |
@@@@ | +0.665 |
� | +0.597 |
tin | +0.597 |
hust | +0.595 |
Neg logit contributions | |
weather | -0.569 |
ipers | -0.542 |
rador | -0.526 |
opp | -0.522 |
ricted | -0.516 |
Token | o |
Token ID | 78 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
weather | +0.274 |
ipers | +0.262 |
rador | +0.254 |
opp | +0.253 |
ricted | +0.247 |
Neg logit contributions | |
hens | -0.377 |
@@@@ | -0.373 |
hust | -0.337 |
═ | -0.337 |
� | -0.337 |
Token | or |
Token ID | 393 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
weather | +1.048 |
ipers | +1.003 |
opp | +0.982 |
rador | +0.970 |
ricted | +0.957 |
Neg logit contributions | |
hens | -1.016 |
@@@@ | -1.009 |
═ | -0.895 |
� | -0.891 |
ONSORED | -0.886 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
weather | +0.228 |
ipers | +0.219 |
opp | +0.214 |
rador | +0.213 |
ricted | +0.209 |
Neg logit contributions | |
hens | -0.220 |
@@@@ | -0.218 |
═ | -0.193 |
� | -0.193 |
hust | -0.192 |
Token | Out |
Token ID | 3806 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
hens | +7.350 |
@@@@ | +7.072 |
hust | +6.880 |
� | +6.331 |
dial | +6.282 |
Neg logit contributions | |
weather | -7.392 |
ipers | -7.348 |
rador | -7.172 |
Downloadha | -7.151 |
opp | -7.026 |
Token | back |
Token ID | 1891 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
hens | +2.007 |
@@@@ | +1.913 |
hust | +1.592 |
tin | +1.592 |
═ | +1.561 |
Neg logit contributions | |
weather | -4.473 |
ipers | -4.371 |
rador | -4.280 |
opp | -4.277 |
Downloadha | -4.219 |
Token | cast |
Token ID | 3350 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
hens | +1.693 |
@@@@ | +1.663 |
hust | +1.496 |
═ | +1.483 |
tin | +1.482 |
Neg logit contributions | |
weather | -1.615 |
ipers | -1.552 |
opp | -1.513 |
rador | -1.509 |
ricted | -1.481 |
Token | members |
Token ID | 1866 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
hens | +0.628 |
@@@@ | +0.620 |
═ | +0.554 |
hust | +0.553 |
� | +0.553 |
Neg logit contributions | |
weather | -0.587 |
ipers | -0.560 |
opp | -0.546 |
rador | -0.544 |
ricted | -0.536 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
hens | +0.394 |
@@@@ | +0.390 |
hust | +0.350 |
═ | +0.349 |
� | +0.349 |
Neg logit contributions | |
weather | -0.326 |
ipers | -0.312 |
opp | -0.303 |
rador | -0.303 |
ricted | -0.296 |
Token | - |
Token ID | 12 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
hens | +2.506 |
@@@@ | +2.449 |
hust | +2.225 |
═ | +2.223 |
tin | +2.217 |
Neg logit contributions | |
weather | -1.887 |
ipers | -1.804 |
opp | -1.764 |
ricted | -1.744 |
rador | -1.740 |
Token | wall |
Token ID | 11930 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
weather | +0.056 |
ipers | +0.054 |
opp | +0.052 |
rador | +0.052 |
ricted | +0.051 |
Neg logit contributions | |
hens | -0.092 |
@@@@ | -0.090 |
tin | -0.082 |
═ | -0.082 |
hust | -0.082 |
Token | aby |
Token ID | 3930 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
weather | +0.021 |
ipers | +0.020 |
opp | +0.019 |
rador | +0.019 |
ricted | +0.019 |
Neg logit contributions | |
hens | -0.021 |
@@@@ | -0.021 |
hust | -0.018 |
tin | -0.018 |
@#& | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
hens | +1.623 |
@@@@ | +1.587 |
hust | +1.428 |
tin | +1.422 |
� | +1.394 |
Neg logit contributions | |
weather | -1.579 |
ipers | -1.502 |
rador | -1.458 |
opp | -1.457 |
ricted | -1.438 |
Token | the |
Token ID | 262 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
hens | +1.804 |
@@@@ | +1.778 |
hust | +1.589 |
═ | +1.586 |
tin | +1.583 |
Neg logit contributions | |
weather | -1.602 |
ipers | -1.536 |
opp | -1.493 |
rador | -1.477 |
ricted | -1.461 |
Token | Kimber |
Token ID | 36015 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
hens | +0.448 |
@@@@ | +0.441 |
hust | +0.386 |
═ | +0.385 |
tin | +0.384 |
Neg logit contributions | |
weather | -0.568 |
ipers | -0.548 |
opp | -0.536 |
rador | -0.532 |
ricted | -0.525 |
Token | ley |
Token ID | 1636 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
hens | +5.525 |
@@@@ | +5.324 |
tin | +4.681 |
hust | +4.548 |
dial | +4.539 |
Neg logit contributions | |
weather | -9.129 |
ipers | -9.014 |
Downloadha | -8.902 |
rador | -8.746 |
odor | -8.701 |
Token | is |
Token ID | 318 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
hens | +2.523 |
@@@@ | +2.439 |
hust | +2.221 |
tin | +2.203 |
═ | +2.180 |
Neg logit contributions | |
weather | -2.513 |
ipers | -2.427 |
rador | -2.358 |
opp | -2.348 |
ricted | -2.307 |
Token | larger |
Token ID | 4025 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
hens | +0.415 |
@@@@ | +0.408 |
hust | +0.370 |
tin | +0.366 |
═ | +0.363 |
Neg logit contributions | |
weather | -0.366 |
ipers | -0.347 |
rador | -0.337 |
opp | -0.333 |
ricted | -0.328 |
Token | ( |
Token ID | 357 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
weather | +1.252 |
ipers | +1.197 |
opp | +1.167 |
rador | +1.157 |
ricted | +1.138 |
Neg logit contributions | |
hens | -1.488 |
@@@@ | -1.474 |
═ | -1.323 |
� | -1.323 |
tin | -1.314 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
hens | +1.384 |
@@@@ | +1.354 |
tin | +1.225 |
═ | +1.219 |
Scroll | +1.203 |
Neg logit contributions | |
weather | -1.079 |
ipers | -1.049 |
rador | -1.014 |
ricted | -0.993 |
opp | -0.989 |
Token | ), |
Token ID | 828 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
hens | +0.512 |
@@@@ | +0.505 |
hust | +0.460 |
═ | +0.459 |
� | +0.458 |
Neg logit contributions | |
weather | -0.329 |
ipers | -0.309 |
opp | -0.300 |
rador | -0.299 |
ricted | -0.292 |
Token | – |
Token ID | 784 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
weather | +0.420 |
ipers | +0.402 |
opp | +0.391 |
rador | +0.390 |
ricted | +0.383 |
Neg logit contributions | |
hens | -0.440 |
@@@@ | -0.434 |
═ | -0.387 |
hust | -0.385 |
� | -0.384 |
Token | one |
Token ID | 530 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
hens | +0.020 |
@@@@ | +0.020 |
═ | +0.018 |
� | +0.018 |
tin | +0.018 |
Neg logit contributions | |
weather | -0.017 |
ipers | -0.016 |
opp | -0.016 |
rador | -0.016 |
ricted | -0.016 |
Token | from |
Token ID | 422 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
hens | +1.727 |
@@@@ | +1.700 |
hust | +1.536 |
tin | +1.532 |
═ | +1.507 |
Neg logit contributions | |
weather | -1.599 |
ipers | -1.505 |
opp | -1.468 |
rador | -1.466 |
ricted | -1.433 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
hens | +1.571 |
@@@@ | +1.536 |
hust | +1.356 |
tin | +1.347 |
@#& | +1.337 |
Neg logit contributions | |
weather | -1.868 |
ipers | -1.790 |
opp | -1.745 |
rador | -1.739 |
ricted | -1.718 |
Token | Kimber |
Token ID | 36015 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
hens | +0.836 |
@@@@ | +0.823 |
hust | +0.733 |
tin | +0.726 |
═ | +0.724 |
Neg logit contributions | |
weather | -0.916 |
ipers | -0.879 |
opp | -0.858 |
rador | -0.852 |
ricted | -0.841 |
Token | ley |
Token ID | 1636 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
hens | +5.535 |
@@@@ | +5.360 |
tin | +4.791 |
@#& | +4.732 |
hust | +4.660 |
Neg logit contributions | |
weather | -8.962 |
ipers | -8.755 |
rador | -8.553 |
Downloadha | -8.459 |
orage | -8.350 |
Token | and |
Token ID | 290 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
hens | +2.340 |
@@@@ | +2.293 |
hust | +2.078 |
═ | +2.072 |
tin | +2.065 |
Neg logit contributions | |
weather | -2.033 |
ipers | -1.961 |
opp | -1.888 |
rador | -1.885 |
ricted | -1.845 |
Token | western |
Token ID | 8830 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
hens | +0.585 |
@@@@ | +0.579 |
═ | +0.518 |
� | +0.516 |
hust | +0.516 |
Neg logit contributions | |
weather | -0.519 |
ipers | -0.496 |
opp | -0.482 |
rador | -0.479 |
ricted | -0.473 |
Token | Northern |
Token ID | 8342 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
hens | +2.735 |
@@@@ | +2.691 |
hust | +2.421 |
tin | +2.375 |
═ | +2.347 |
Neg logit contributions | |
weather | -3.349 |
ipers | -3.235 |
opp | -3.155 |
rador | -3.137 |
Downloadha | -3.086 |
Token | Territory |
Token ID | 25219 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
hens | +4.022 |
@@@@ | +3.817 |
hust | +3.466 |
tin | +3.367 |
═ | +3.357 |
Neg logit contributions | |
weather | -5.367 |
ipers | -5.258 |
opp | -5.180 |
rador | -5.078 |
ocal | -4.981 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
hens | +0.019 |
@@@@ | +0.019 |
═ | +0.017 |
� | +0.017 |
hust | +0.017 |
Neg logit contributions | |
weather | -0.017 |
ipers | -0.016 |
opp | -0.015 |
rador | -0.015 |
ricted | -0.015 |
Token | as |
Token ID | 355 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
weather | +0.392 |
ipers | +0.376 |
opp | +0.366 |
rador | +0.364 |
ricted | +0.359 |
Neg logit contributions | |
hens | -0.428 |
@@@@ | -0.422 |
═ | -0.377 |
hust | -0.377 |
� | -0.375 |
Token | the |
Token ID | 262 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
hens | +0.547 |
@@@@ | +0.539 |
═ | +0.483 |
hust | +0.483 |
� | +0.481 |
Neg logit contributions | |
weather | -0.454 |
ipers | -0.434 |
opp | -0.421 |
rador | -0.420 |
ricted | -0.413 |
Token | villain |
Token ID | 16687 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
hens | +0.271 |
@@@@ | +0.267 |
hust | +0.241 |
═ | +0.238 |
tin | +0.238 |
Neg logit contributions | |
weather | -0.240 |
ipers | -0.232 |
rador | -0.224 |
opp | -0.224 |
ricted | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
hens | +3.355 |
@@@@ | +3.300 |
hust | +3.023 |
tin | +2.981 |
@#& | +2.918 |
Neg logit contributions | |
weather | -3.270 |
ipers | -3.182 |
rador | -3.106 |
opp | -3.040 |
ricted | -3.025 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
hens | +0.339 |
@@@@ | +0.335 |
hust | +0.300 |
═ | +0.297 |
tin | +0.297 |
Neg logit contributions | |
weather | -0.315 |
ipers | -0.302 |
rador | -0.294 |
opp | -0.294 |
ricted | -0.288 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
hens | +7.146 |
@@@@ | +7.029 |
hust | +6.698 |
tin | +6.366 |
@#& | +6.222 |
Neg logit contributions | |
weather | -7.043 |
ipers | -6.965 |
rador | -6.703 |
opp | -6.632 |
ricted | -6.614 |
Token | Mend |
Token ID | 20442 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
hens | +0.281 |
@@@@ | +0.276 |
hust | +0.246 |
tin | +0.246 |
═ | +0.243 |
Neg logit contributions | |
weather | -0.266 |
ipers | -0.256 |
rador | -0.249 |
opp | -0.249 |
ricted | -0.246 |
Token | el |
Token ID | 417 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
hens | +2.706 |
@@@@ | +2.621 |
tin | +2.433 |
hust | +2.388 |
═ | +2.366 |
Neg logit contributions | |
weather | -2.278 |
ipers | -2.240 |
Downloadha | -2.209 |
rador | -2.154 |
ricted | -2.118 |
Token | so |
Token ID | 568 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
weather | +1.469 |
ipers | +1.397 |
opp | +1.372 |
rador | +1.352 |
ricted | +1.333 |
Neg logit contributions | |
hens | -1.594 |
@@@@ | -1.578 |
� | -1.414 |
═ | -1.412 |
ONSORED | -1.398 |
Token | hn |
Token ID | 21116 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
weather | +0.028 |
ipers | +0.027 |
opp | +0.026 |
rador | +0.026 |
ricted | +0.026 |
Neg logit contributions | |
hens | -0.032 |
@@@@ | -0.031 |
═ | -0.028 |
� | -0.028 |
tin | -0.028 |
Token | wil |
Token ID | 39716 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
hens | +0.011 |
@@@@ | +0.011 |
hust | +0.010 |
═ | +0.010 |
� | +0.010 |
Neg logit contributions | |
weather | -0.011 |
ipers | -0.010 |
opp | -0.010 |
rador | -0.010 |
ricted | -0.010 |
Token | kins |
Token ID | 5331 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hens | +1.852 |
@@@@ | +1.730 |
tin | +1.615 |
hust | +1.562 |
@#& | +1.547 |
Neg logit contributions | |
weather | -1.797 |
ipers | -1.700 |
rador | -1.698 |
opp | -1.671 |
ricted | -1.665 |
Token | i |
Token ID | 72 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
hens | +0.964 |
@@@@ | +0.943 |
tin | +0.851 |
═ | +0.851 |
hust | +0.849 |
Neg logit contributions | |
weather | -0.751 |
ipers | -0.707 |
rador | -0.692 |
opp | -0.688 |
ricted | -0.678 |
Token | ), |
Token ID | 828 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
weather | +0.521 |
ipers | +0.492 |
opp | +0.476 |
rador | +0.475 |
ricted | +0.464 |
Neg logit contributions | |
hens | -0.819 |
@@@@ | -0.809 |
═ | -0.734 |
� | -0.732 |
hust | -0.730 |
Token | after |
Token ID | 706 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
weather | +0.364 |
ipers | +0.349 |
opp | +0.340 |
rador | +0.339 |
ricted | +0.334 |
Neg logit contributions | |
hens | -0.365 |
@@@@ | -0.361 |
═ | -0.320 |
� | -0.319 |
hust | -0.318 |
Token | Australian |
Token ID | 6638 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
hens | +1.653 |
@@@@ | +1.626 |
hust | +1.464 |
tin | +1.455 |
� | +1.450 |
Neg logit contributions | |
weather | -1.401 |
ipers | -1.350 |
opp | -1.310 |
rador | -1.294 |
ricted | -1.286 |
Token | explorer |
Token ID | 39349 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
hens | +6.657 |
@@@@ | +6.520 |
hust | +6.084 |
tin | +5.929 |
@#& | +5.848 |
Neg logit contributions | |
ipers | -7.043 |
weather | -6.976 |
Downloadha | -6.861 |
opp | -6.780 |
rador | -6.712 |
Token | , |
Token ID | 11 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
hens | +3.773 |
@@@@ | +3.707 |
tin | +3.406 |
hust | +3.392 |
@#& | +3.335 |
Neg logit contributions | |
weather | -3.656 |
ipers | -3.607 |
opp | -3.507 |
rador | -3.505 |
ricted | -3.431 |
Token | natural |
Token ID | 3288 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
hens | +0.685 |
@@@@ | +0.678 |
� | +0.603 |
hust | +0.602 |
═ | +0.602 |
Neg logit contributions | |
weather | -0.678 |
ipers | -0.653 |
opp | -0.637 |
rador | -0.633 |
ricted | -0.625 |
Token | ist |
Token ID | 396 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
hens | +1.661 |
@@@@ | +1.636 |
hust | +1.461 |
tin | +1.460 |
� | +1.455 |
Neg logit contributions | |
weather | -1.707 |
ipers | -1.642 |
opp | -1.611 |
rador | -1.596 |
ricted | -1.581 |
Token | and |
Token ID | 290 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
hens | +3.449 |
@@@@ | +3.429 |
tin | +3.095 |
hust | +3.084 |
@#& | +3.041 |
Neg logit contributions | |
weather | -3.525 |
ipers | -3.454 |
opp | -3.349 |
rador | -3.325 |
ricted | -3.293 |
Token | request |
Token ID | 2581 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
hens | +0.377 |
@@@@ | +0.373 |
═ | +0.327 |
� | +0.326 |
hust | +0.324 |
Neg logit contributions | |
weather | -0.459 |
ipers | -0.441 |
opp | -0.432 |
rador | -0.429 |
ricted | -0.423 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
hens | +0.307 |
@@@@ | +0.303 |
═ | +0.272 |
� | +0.271 |
hust | +0.270 |
Neg logit contributions | |
weather | -0.270 |
ipers | -0.258 |
opp | -0.251 |
rador | -0.249 |
ricted | -0.245 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
weather | +0.232 |
ipers | +0.223 |
opp | +0.217 |
rador | +0.216 |
ricted | +0.212 |
Neg logit contributions | |
hens | -0.235 |
@@@@ | -0.233 |
═ | -0.207 |
� | -0.207 |
tin | -0.205 |
Token | trustees |
Token ID | 36636 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
weather | +1.036 |
ipers | +0.988 |
opp | +0.964 |
rador | +0.956 |
ricted | +0.940 |
Neg logit contributions | |
hens | -1.268 |
@@@@ | -1.255 |
═ | -1.129 |
� | -1.129 |
tin | -1.122 |
Token | were |
Token ID | 547 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
weather | +0.611 |
ipers | +0.585 |
opp | +0.570 |
rador | +0.566 |
ricted | +0.557 |
Neg logit contributions | |
hens | -0.689 |
@@@@ | -0.682 |
═ | -0.610 |
� | -0.609 |
tin | -0.606 |
Token | reimb |
Token ID | 46496 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
weather | +0.918 |
ipers | +0.875 |
opp | +0.852 |
rador | +0.845 |
ricted | +0.831 |
Neg logit contributions | |
hens | -1.163 |
@@@@ | -1.153 |
═ | -1.039 |
� | -1.037 |
tin | -1.030 |
Token | ursed |
Token ID | 17539 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
hens | +5.582 |
@@@@ | +4.769 |
tin | +4.490 |
hust | +4.353 |
ategory | +4.250 |
Neg logit contributions | |
Downloadha | -8.292 |
weather | -8.129 |
ipers | -8.031 |
odor | -7.782 |
rador | -7.707 |
Token | for |
Token ID | 329 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
hens | +2.151 |
@@@@ | +2.109 |
hust | +1.913 |
tin | +1.872 |
═ | +1.859 |
Neg logit contributions | |
weather | -2.128 |
ipers | -2.046 |
rador | -2.001 |
opp | -1.972 |
ocal | -1.938 |
Token | hand |
Token ID | 1021 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
weather | +1.903 |
ipers | +1.817 |
opp | +1.773 |
rador | +1.756 |
ricted | +1.731 |
Neg logit contributions | |
hens | -2.215 |
@@@@ | -2.193 |
� | -1.971 |
═ | -1.970 |
tin | -1.949 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
weather | +0.295 |
ipers | +0.282 |
opp | +0.273 |
rador | +0.273 |
ricted | +0.270 |
Neg logit contributions | |
hens | -0.358 |
@@@@ | -0.352 |
hust | -0.320 |
tin | -0.318 |
═ | -0.317 |
Token | ion |
Token ID | 295 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
weather | +1.137 |
ipers | +1.093 |
opp | +1.069 |
rador | +1.064 |
ricted | +1.047 |
Neg logit contributions | |
hens | -1.017 |
@@@@ | -1.005 |
═ | -0.886 |
� | -0.882 |
tin | -0.881 |
Token | Herod |
Token ID | 48084 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
hens | +2.719 |
@@@@ | +2.624 |
tin | +2.375 |
hust | +2.368 |
� | +2.356 |
Neg logit contributions | |
weather | -2.511 |
ipers | -2.440 |
rador | -2.400 |
opp | -2.358 |
ricted | -2.334 |
Token | ot |
Token ID | 313 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
weather | +2.380 |
ipers | +2.234 |
opp | +2.200 |
rador | +2.133 |
ocal | +2.100 |
Neg logit contributions | |
hens | -3.766 |
@@@@ | -3.754 |
═ | -3.435 |
� | -3.421 |
ONSORED | -3.421 |
Token | us |
Token ID | 385 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
weather | +0.767 |
ipers | +0.725 |
rador | +0.698 |
opp | +0.698 |
ricted | +0.681 |
Neg logit contributions | |
hens | -1.318 |
@@@@ | -1.302 |
═ | -1.190 |
� | -1.186 |
tin | -1.185 |
Token | begins |
Token ID | 6140 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
weather | +0.589 |
ipers | +0.564 |
opp | +0.552 |
rador | +0.547 |
ricted | +0.538 |
Neg logit contributions | |
hens | -0.563 |
@@@@ | -0.558 |
═ | -0.496 |
� | -0.494 |
tin | -0.489 |
Token | the |
Token ID | 262 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
hens | +0.509 |
@@@@ | +0.503 |
═ | +0.453 |
� | +0.452 |
hust | +0.451 |
Neg logit contributions | |
weather | -0.396 |
ipers | -0.378 |
opp | -0.368 |
rador | -0.365 |
ricted | -0.359 |
Token | Australian |
Token ID | 6638 |
Feature activation | +9.59e+00 |
Pos logit contributions | |
hens | +0.341 |
@@@@ | +0.337 |
hust | +0.299 |
� | +0.297 |
═ | +0.297 |
Neg logit contributions | |
weather | -0.342 |
ipers | -0.329 |
opp | -0.320 |
rador | -0.320 |
ricted | -0.315 |
Token | Alan |
Token ID | 12246 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
hens | +6.541 |
@@@@ | +6.452 |
hust | +6.030 |
Scroll | +5.742 |
� | +5.671 |
Neg logit contributions | |
ipers | -6.907 |
weather | -6.806 |
rador | -6.723 |
ricted | -6.661 |
Downloadha | -6.559 |
Token | Moore |
Token ID | 8877 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
hens | +1.020 |
@@@@ | +1.008 |
tin | +0.898 |
hust | +0.897 |
═ | +0.892 |
Neg logit contributions | |
weather | -0.957 |
ipers | -0.923 |
rador | -0.895 |
opp | -0.892 |
ricted | -0.878 |
Token | head |
Token ID | 2256 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
hens | +4.136 |
@@@@ | +4.067 |
hust | +3.691 |
tin | +3.654 |
ONSORED | +3.581 |
Neg logit contributions | |
weather | -3.741 |
ipers | -3.664 |
rador | -3.577 |
opp | -3.510 |
ricted | -3.496 |
Token | � |
Token ID | 447 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
hens | +0.572 |
@@@@ | +0.564 |
tin | +0.503 |
hust | +0.503 |
═ | +0.501 |
Neg logit contributions | |
weather | -0.530 |
ipers | -0.510 |
opp | -0.495 |
rador | -0.495 |
ricted | -0.486 |
Token | � |
Token ID | 247 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
hens | +0.047 |
@@@@ | +0.046 |
═ | +0.041 |
� | +0.041 |
ONSORED | +0.041 |
Neg logit contributions | |
weather | -0.045 |
ipers | -0.043 |
rador | -0.042 |
opp | -0.042 |
ricted | -0.041 |
Token | The |
Token ID | 464 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
hens | +0.400 |
@@@@ | +0.400 |
tin | +0.356 |
� | +0.355 |
═ | +0.353 |
Neg logit contributions | |
weather | -0.347 |
ipers | -0.338 |
rador | -0.325 |
opp | -0.320 |
ricted | -0.320 |
Token | most |
Token ID | 749 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
weather | +0.624 |
ipers | +0.599 |
opp | +0.587 |
rador | +0.583 |
ricted | +0.574 |
Neg logit contributions | |
hens | -0.542 |
@@@@ | -0.536 |
═ | -0.472 |
� | -0.470 |
tin | -0.467 |
Token | common |
Token ID | 2219 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
weather | +1.923 |
ipers | +1.834 |
opp | +1.790 |
rador | +1.778 |
ricted | +1.740 |
Neg logit contributions | |
hens | -2.417 |
@@@@ | -2.402 |
═ | -2.172 |
� | -2.160 |
ONSORED | -2.149 |
Token | category |
Token ID | 6536 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
weather | +3.439 |
ipers | +3.267 |
opp | +3.205 |
rador | +3.167 |
ricted | +3.089 |
Neg logit contributions | |
hens | -3.849 |
@@@@ | -3.805 |
═ | -3.467 |
ONSORED | -3.460 |
� | -3.434 |
Token | of |
Token ID | 286 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
hens | +0.377 |
@@@@ | +0.373 |
═ | +0.335 |
� | +0.333 |
tin | +0.333 |
Neg logit contributions | |
weather | -0.327 |
ipers | -0.312 |
opp | -0.303 |
rador | -0.302 |
ricted | -0.296 |
Token | Mongol |
Token ID | 42188 |
Feature activation | +9.50e+00 |
Pos logit contributions | |
hens | +0.021 |
@@@@ | +0.021 |
hust | +0.018 |
� | +0.018 |
tin | +0.018 |
Neg logit contributions | |
weather | -0.025 |
ipers | -0.024 |
opp | -0.024 |
rador | -0.024 |
ricted | -0.023 |
Token | names |
Token ID | 3891 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
hens | +4.572 |
@@@@ | +4.360 |
tin | +3.668 |
hust | +3.636 |
� | +3.604 |
Neg logit contributions | |
weather | -8.955 |
ipers | -8.684 |
ricted | -8.533 |
opp | -8.507 |
Downloadha | -8.497 |
Token | were |
Token ID | 547 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
hens | +1.321 |
@@@@ | +1.297 |
tin | +1.165 |
hust | +1.155 |
═ | +1.151 |
Neg logit contributions | |
weather | -1.327 |
ipers | -1.269 |
rador | -1.246 |
opp | -1.228 |
ricted | -1.218 |
Token | those |
Token ID | 883 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
weather | +1.123 |
ipers | +1.073 |
opp | +1.047 |
rador | +1.039 |
ricted | +1.021 |
Neg logit contributions | |
hens | -1.305 |
@@@@ | -1.292 |
═ | -1.159 |
� | -1.155 |
hust | -1.149 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
hens | +1.536 |
@@@@ | +1.517 |
tin | +1.367 |
hust | +1.366 |
� | +1.347 |
Neg logit contributions | |
weather | -1.386 |
ipers | -1.330 |
rador | -1.287 |
opp | -1.285 |
ricted | -1.264 |
Token | ausp |
Token ID | 45062 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
hens | +0.861 |
@@@@ | +0.850 |
hust | +0.761 |
� | +0.759 |
tin | +0.758 |
Neg logit contributions | |
weather | -0.740 |
ipers | -0.711 |
opp | -0.689 |
rador | -0.684 |
ricted | -0.676 |
Token | ás |
Token ID | 40138 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
hens | +2.191 |
@@@@ | +2.124 |
tin | +1.963 |
hust | +1.919 |
� | +1.909 |
Neg logit contributions | |
weather | -1.624 |
ipers | -1.528 |
rador | -1.477 |
opp | -1.474 |
ricted | -1.450 |
Token | is |
Token ID | 318 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
weather | +1.789 |
ipers | +1.715 |
opp | +1.678 |
rador | +1.660 |
ricted | +1.632 |
Neg logit contributions | |
hens | -1.818 |
@@@@ | -1.810 |
� | -1.618 |
═ | -1.613 |
ONSORED | -1.601 |
Token | a |
Token ID | 257 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
hens | +0.788 |
@@@@ | +0.782 |
hust | +0.706 |
═ | +0.697 |
tin | +0.696 |
Neg logit contributions | |
weather | -0.696 |
ipers | -0.669 |
rador | -0.644 |
opp | -0.643 |
ricted | -0.634 |
Token | showcase |
Token ID | 21742 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
hens | +0.534 |
@@@@ | +0.528 |
hust | +0.475 |
═ | +0.469 |
tin | +0.468 |
Neg logit contributions | |
weather | -0.514 |
ipers | -0.493 |
opp | -0.479 |
rador | -0.476 |
ricted | -0.470 |
Token | of |
Token ID | 286 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
weather | +0.395 |
ipers | +0.379 |
opp | +0.366 |
rador | +0.365 |
ricted | +0.359 |
Neg logit contributions | |
hens | -0.485 |
@@@@ | -0.479 |
hust | -0.433 |
═ | -0.431 |
tin | -0.430 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | +9.50e+00 |
Pos logit contributions | |
hens | +0.459 |
@@@@ | +0.453 |
hust | +0.409 |
═ | +0.407 |
tin | +0.405 |
Neg logit contributions | |
weather | -0.397 |
ipers | -0.378 |
opp | -0.368 |
rador | -0.367 |
ricted | -0.362 |
Token | faith |
Token ID | 4562 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hens | +6.482 |
@@@@ | +6.245 |
hust | +6.143 |
tin | +5.768 |
═ | +5.561 |
Neg logit contributions | |
weather | -7.059 |
Downloadha | -6.785 |
ricted | -6.717 |
rador | -6.672 |
ipers | -6.650 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
hens | +0.887 |
@@@@ | +0.877 |
═ | +0.789 |
hust | +0.788 |
tin | +0.786 |
Neg logit contributions | |
weather | -0.733 |
ipers | -0.700 |
opp | -0.680 |
rador | -0.679 |
ricted | -0.668 |
Token | including |
Token ID | 1390 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
hens | +0.155 |
@@@@ | +0.154 |
hust | +0.138 |
═ | +0.138 |
tin | +0.137 |
Neg logit contributions | |
weather | -0.134 |
ipers | -0.128 |
opp | -0.124 |
rador | -0.124 |
ricted | -0.122 |
Token | several |
Token ID | 1811 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
weather | +2.253 |
ipers | +2.157 |
opp | +2.117 |
rador | +2.078 |
ricted | +2.044 |
Neg logit contributions | |
hens | -2.752 |
@@@@ | -2.733 |
═ | -2.456 |
� | -2.444 |
ONSORED | -2.436 |
Token | old |
Token ID | 1468 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
hens | +0.267 |
@@@@ | +0.264 |
═ | +0.234 |
� | +0.234 |
hust | +0.234 |
Neg logit contributions | |
weather | -0.265 |
ipers | -0.254 |
opp | -0.248 |
rador | -0.247 |
ricted | -0.243 |
Token | Now |
Token ID | 3844 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
weather | +0.216 |
ipers | +0.210 |
rador | +0.202 |
opp | +0.200 |
ricted | +0.199 |
Neg logit contributions | |
hens | -0.244 |
@@@@ | -0.244 |
tin | -0.216 |
� | -0.216 |
═ | -0.216 |
Token | adays |
Token ID | 20544 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
hens | +3.787 |
@@@@ | +3.610 |
tin | +3.146 |
hust | +3.126 |
═ | +3.115 |
Neg logit contributions | |
weather | -5.373 |
ipers | -5.245 |
rador | -5.093 |
opp | -5.073 |
ricted | -5.049 |
Token | most |
Token ID | 749 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
hens | +1.305 |
@@@@ | +1.293 |
hust | +1.164 |
tin | +1.158 |
═ | +1.147 |
Neg logit contributions | |
weather | -1.131 |
ipers | -1.094 |
rador | -1.052 |
opp | -1.048 |
ricted | -1.037 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
weather | +1.703 |
ipers | +1.618 |
opp | +1.583 |
rador | +1.570 |
ricted | +1.539 |
Neg logit contributions | |
hens | -2.022 |
@@@@ | -2.009 |
═ | -1.819 |
� | -1.805 |
ONSORED | -1.799 |
Token | give |
Token ID | 1577 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
hens | +1.038 |
@@@@ | +1.016 |
hust | +0.922 |
tin | +0.906 |
═ | +0.896 |
Neg logit contributions | |
weather | -1.071 |
ipers | -1.041 |
rador | -1.008 |
opp | -1.007 |
ricted | -0.995 |
Token | Mongol |
Token ID | 42188 |
Feature activation | +9.40e+00 |
Pos logit contributions | |
hens | +1.292 |
@@@@ | +1.286 |
hust | +1.146 |
tin | +1.142 |
═ | +1.132 |
Neg logit contributions | |
weather | -1.153 |
ipers | -1.101 |
rador | -1.065 |
opp | -1.064 |
ricted | -1.049 |
Token | ian |
Token ID | 666 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
hens | +3.503 |
@@@@ | +3.346 |
tin | +2.667 |
hust | +2.569 |
Scroll | +2.555 |
Neg logit contributions | |
weather | -9.907 |
ipers | -9.565 |
ricted | -9.505 |
rador | -9.497 |
Downloadha | -9.421 |
Token | names |
Token ID | 3891 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
hens | +4.392 |
@@@@ | +4.286 |
hust | +3.899 |
tin | +3.848 |
� | +3.794 |
Neg logit contributions | |
weather | -3.618 |
ipers | -3.440 |
rador | -3.355 |
ricted | -3.347 |
Downloadha | -3.306 |
Token | to |
Token ID | 284 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
hens | +1.039 |
@@@@ | +1.026 |
hust | +0.917 |
tin | +0.916 |
═ | +0.914 |
Neg logit contributions | |
weather | -0.923 |
ipers | -0.885 |
rador | -0.863 |
opp | -0.855 |
ricted | -0.844 |
Token | their |
Token ID | 511 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
weather | +0.289 |
ipers | +0.276 |
opp | +0.268 |
rador | +0.265 |
ricted | +0.262 |
Neg logit contributions | |
hens | -0.354 |
@@@@ | -0.351 |
═ | -0.314 |
hust | -0.314 |
� | -0.313 |
Token | children |
Token ID | 1751 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
weather | +1.120 |
ipers | +1.051 |
opp | +1.016 |
rador | +1.007 |
ricted | +0.976 |
Neg logit contributions | |
hens | -2.216 |
@@@@ | -2.203 |
═ | -2.028 |
� | -2.025 |
tin | -2.008 |
Token | among |
Token ID | 1871 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
weather | +0.227 |
ipers | +0.217 |
opp | +0.211 |
rador | +0.210 |
ricted | +0.206 |
Neg logit contributions | |
hens | -0.273 |
@@@@ | -0.270 |
═ | -0.242 |
� | -0.242 |
hust | -0.241 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
weather | +0.333 |
ipers | +0.320 |
opp | +0.313 |
rador | +0.311 |
ricted | +0.307 |
Neg logit contributions | |
hens | -0.292 |
@@@@ | -0.289 |
═ | -0.254 |
� | -0.253 |
hust | -0.252 |
Token | Turk |
Token ID | 8484 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
hens | +0.273 |
@@@@ | +0.268 |
═ | +0.233 |
� | +0.232 |
hust | +0.232 |
Neg logit contributions | |
weather | -0.367 |
ipers | -0.354 |
opp | -0.347 |
rador | -0.345 |
ricted | -0.341 |
Token | ic |
Token ID | 291 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
hens | +0.146 |
@@@@ | +0.143 |
═ | +0.126 |
� | +0.126 |
tin | +0.126 |
Neg logit contributions | |
weather | -0.166 |
ipers | -0.159 |
opp | -0.156 |
rador | -0.155 |
ricted | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
hens | +1.813 |
@@@@ | +1.776 |
hust | +1.592 |
═ | +1.587 |
� | +1.586 |
Neg logit contributions | |
weather | -1.643 |
ipers | -1.575 |
opp | -1.530 |
rador | -1.523 |
ricted | -1.506 |
Token | Mongol |
Token ID | 42188 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
weather | +0.073 |
ipers | +0.071 |
opp | +0.069 |
rador | +0.068 |
ricted | +0.068 |
Neg logit contributions | |
hens | -0.066 |
@@@@ | -0.065 |
═ | -0.057 |
� | -0.057 |
hust | -0.057 |
Token | peoples |
Token ID | 14366 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
hens | +5.441 |
@@@@ | +5.204 |
hust | +4.590 |
dial | +4.561 |
Scroll | +4.526 |
Neg logit contributions | |
weather | -7.980 |
ipers | -7.647 |
Downloadha | -7.523 |
rador | -7.459 |
ricted | -7.394 |
Token | ( |
Token ID | 357 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
hens | +1.182 |
@@@@ | +1.166 |
hust | +1.047 |
═ | +1.044 |
tin | +1.039 |
Neg logit contributions | |
weather | -1.032 |
ipers | -0.994 |
rador | -0.967 |
opp | -0.957 |
ricted | -0.944 |
Token | especially |
Token ID | 16480 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
hens | +1.492 |
@@@@ | +1.461 |
tin | +1.335 |
� | +1.319 |
═ | +1.314 |
Neg logit contributions | |
weather | -1.148 |
ipers | -1.112 |
rador | -1.077 |
ricted | -1.063 |
opp | -1.057 |
Token | Ong |
Token ID | 48041 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
weather | +3.895 |
ipers | +3.722 |
opp | +3.677 |
rador | +3.619 |
ocal | +3.546 |
Neg logit contributions | |
hens | -4.296 |
@@@@ | -4.268 |
═ | -3.848 |
ONSORED | -3.824 |
� | -3.779 |
Token | uts |
Token ID | 5500 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
weather | +0.307 |
ipers | +0.293 |
opp | +0.286 |
rador | +0.284 |
ricted | +0.280 |
Neg logit contributions | |
hens | -0.356 |
@@@@ | -0.351 |
tin | -0.314 |
═ | -0.314 |
� | -0.314 |
Token | � |
Token ID | 564 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
weather | +0.705 |
ipers | +0.675 |
opp | +0.661 |
rador | +0.656 |
ricted | +0.646 |
Neg logit contributions | |
hens | -0.723 |
@@@@ | -0.715 |
═ | -0.637 |
� | -0.635 |
tin | -0.631 |
Token | � |
Token ID | 250 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
@@@@ | +0.846 |
hens | +0.843 |
═ | +0.746 |
tin | +0.737 |
� | +0.734 |
Neg logit contributions | |
weather | -0.880 |
ipers | -0.836 |
rador | -0.809 |
opp | -0.808 |
ricted | -0.792 |
Token | quick |
Token ID | 24209 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
hens | +1.213 |
@@@@ | +1.193 |
tin | +1.081 |
hust | +1.070 |
═ | +1.066 |
Neg logit contributions | |
weather | -1.000 |
ipers | -0.974 |
rador | -0.936 |
ricted | -0.925 |
opp | -0.925 |
Token | and |
Token ID | 290 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
hens | +2.393 |
@@@@ | +2.340 |
hust | +2.102 |
tin | +2.072 |
� | +2.038 |
Neg logit contributions | |
weather | -2.860 |
ipers | -2.790 |
opp | -2.712 |
ricted | -2.704 |
rador | -2.692 |
Token | raging |
Token ID | 30082 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
hens | +0.077 |
@@@@ | +0.076 |
hust | +0.068 |
tin | +0.067 |
═ | +0.067 |
Neg logit contributions | |
weather | -0.071 |
ipers | -0.068 |
opp | -0.066 |
rador | -0.066 |
ricted | -0.065 |
Token | temper |
Token ID | 4124 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
hens | +3.585 |
@@@@ | +3.553 |
hust | +3.279 |
tin | +3.134 |
� | +3.120 |
Neg logit contributions | |
weather | -3.807 |
ipers | -3.699 |
opp | -3.556 |
rador | -3.541 |
ricted | -3.519 |
Token | � |
Token ID | 447 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
hens | +6.696 |
@@@@ | +6.604 |
═ | +5.899 |
hust | +5.868 |
tin | +5.787 |
Neg logit contributions | |
weather | -6.645 |
ipers | -6.439 |
rador | -6.269 |
Downloadha | -6.156 |
opp | -6.075 |
Token | � |
Token ID | 251 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
weather | +0.245 |
ipers | +0.233 |
opp | +0.227 |
rador | +0.226 |
ricted | +0.222 |
Neg logit contributions | |
hens | -0.253 |
@@@@ | -0.252 |
═ | -0.224 |
� | -0.222 |
hust | -0.222 |
Token | but |
Token ID | 475 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
weather | +0.308 |
ipers | +0.295 |
opp | +0.287 |
rador | +0.286 |
ricted | +0.281 |
Neg logit contributions | |
hens | -0.342 |
@@@@ | -0.339 |
═ | -0.303 |
� | -0.301 |
hust | -0.301 |
Token | also |
Token ID | 635 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
hens | +3.250 |
@@@@ | +3.190 |
hust | +2.905 |
═ | +2.842 |
� | +2.816 |
Neg logit contributions | |
weather | -3.273 |
ipers | -3.192 |
rador | -3.077 |
opp | -2.999 |
ricted | -2.994 |
Token | for |
Token ID | 329 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
hens | +0.412 |
@@@@ | +0.409 |
hust | +0.369 |
═ | +0.368 |
� | +0.367 |
Neg logit contributions | |
weather | -0.341 |
ipers | -0.326 |
opp | -0.315 |
rador | -0.314 |
ricted | -0.308 |
Token | of |
Token ID | 286 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
hens | +1.888 |
@@@@ | +1.866 |
═ | +1.681 |
� | +1.672 |
tin | +1.671 |
Neg logit contributions | |
weather | -1.646 |
ipers | -1.585 |
rador | -1.536 |
opp | -1.531 |
ricted | -1.489 |
Token | great |
Token ID | 1049 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
hens | +0.384 |
@@@@ | +0.380 |
hust | +0.340 |
═ | +0.339 |
tin | +0.338 |
Neg logit contributions | |
weather | -0.360 |
ipers | -0.345 |
opp | -0.335 |
rador | -0.335 |
ricted | -0.328 |
Token | � |
Token ID | 564 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
hens | +0.203 |
@@@@ | +0.201 |
═ | +0.179 |
hust | +0.179 |
tin | +0.178 |
Neg logit contributions | |
weather | -0.196 |
ipers | -0.188 |
opp | -0.183 |
rador | -0.182 |
ricted | -0.179 |
Token | � |
Token ID | 247 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
@@@@ | +0.438 |
hens | +0.438 |
═ | +0.391 |
� | +0.386 |
@#& | +0.386 |
Neg logit contributions | |
weather | -0.364 |
ipers | -0.346 |
opp | -0.334 |
rador | -0.333 |
ricted | -0.325 |
Token | jack |
Token ID | 19650 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
hens | +0.393 |
@@@@ | +0.388 |
tin | +0.349 |
═ | +0.347 |
hust | +0.345 |
Neg logit contributions | |
weather | -0.340 |
ipers | -0.329 |
rador | -0.320 |
opp | -0.316 |
ricted | -0.315 |
Token | marsh |
Token ID | 22397 |
Feature activation | +9.29e+00 |
Pos logit contributions | |
hens | +4.422 |
@@@@ | +4.331 |
hust | +3.947 |
═ | +3.893 |
tin | +3.878 |
Neg logit contributions | |
weather | -4.950 |
ipers | -4.833 |
opp | -4.746 |
ricted | -4.734 |
rador | -4.643 |
Token | als |
Token ID | 874 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
hens | +4.640 |
@@@@ | +4.245 |
tin | +3.832 |
@#& | +3.776 |
hust | +3.752 |
Neg logit contributions | |
weather | -8.279 |
ipers | -8.046 |
Downloadha | -7.965 |
rador | -7.912 |
ricted | -7.885 |
Token | available |
Token ID | 1695 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
hens | +1.348 |
@@@@ | +1.327 |
═ | +1.190 |
hust | +1.188 |
tin | +1.184 |
Neg logit contributions | |
weather | -1.314 |
ipers | -1.263 |
rador | -1.232 |
opp | -1.225 |
ricted | -1.203 |
Token | to |
Token ID | 284 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
hens | +3.933 |
@@@@ | +3.863 |
═ | +3.506 |
hust | +3.462 |
tin | +3.462 |
Neg logit contributions | |
weather | -3.754 |
ipers | -3.652 |
rador | -3.562 |
opp | -3.494 |
Downloadha | -3.469 |
Token | them |
Token ID | 606 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
hens | +0.067 |
@@@@ | +0.067 |
hust | +0.059 |
═ | +0.059 |
tin | +0.059 |
Neg logit contributions | |
weather | -0.063 |
ipers | -0.061 |
rador | -0.059 |
opp | -0.059 |
ricted | -0.058 |
Token | : |
Token ID | 25 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hens | +0.586 |
@@@@ | +0.579 |
═ | +0.522 |
� | +0.518 |
hust | +0.518 |
Neg logit contributions | |
weather | -0.494 |
ipers | -0.473 |
opp | -0.460 |
rador | -0.458 |
ricted | -0.449 |
Token | s |
Token ID | 82 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
hens | +0.467 |
@@@@ | +0.458 |
tin | +0.406 |
═ | +0.404 |
hust | +0.401 |
Neg logit contributions | |
weather | -0.522 |
ipers | -0.503 |
opp | -0.488 |
rador | -0.488 |
ricted | -0.481 |
Token | eye |
Token ID | 4151 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
hens | +1.302 |
@@@@ | +1.296 |
hust | +1.178 |
tin | +1.153 |
� | +1.147 |
Neg logit contributions | |
weather | -1.156 |
ipers | -1.102 |
rador | -1.078 |
opp | -1.062 |
ricted | -1.055 |
Token | up |
Token ID | 510 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
weather | +1.535 |
ipers | +1.473 |
opp | +1.441 |
rador | +1.427 |
ricted | +1.406 |
Neg logit contributions | |
hens | -1.542 |
@@@@ | -1.523 |
═ | -1.355 |
� | -1.354 |
tin | -1.342 |
Token | like |
Token ID | 588 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
hens | +0.999 |
@@@@ | +0.989 |
═ | +0.886 |
tin | +0.886 |
hust | +0.883 |
Neg logit contributions | |
weather | -0.855 |
ipers | -0.820 |
rador | -0.793 |
opp | -0.792 |
ricted | -0.780 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
weather | +0.508 |
ipers | +0.484 |
opp | +0.471 |
rador | +0.467 |
ricted | +0.459 |
Neg logit contributions | |
hens | -0.666 |
@@@@ | -0.660 |
═ | -0.595 |
� | -0.594 |
hust | -0.591 |
Token | marsh |
Token ID | 22397 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
hens | +0.178 |
@@@@ | +0.176 |
hust | +0.157 |
tin | +0.156 |
═ | +0.156 |
Neg logit contributions | |
weather | -0.175 |
ipers | -0.168 |
opp | -0.164 |
rador | -0.163 |
ricted | -0.160 |
Token | mallow |
Token ID | 42725 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
hens | +3.922 |
@@@@ | +3.807 |
tin | +3.567 |
� | +3.363 |
hust | +3.358 |
Neg logit contributions | |
weather | -8.857 |
ipers | -8.792 |
esta | -8.593 |
rador | -8.540 |
Downloadha | -8.514 |
Token | . |
Token ID | 13 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
hens | +3.640 |
@@@@ | +3.582 |
hust | +3.240 |
tin | +3.240 |
═ | +3.199 |
Neg logit contributions | |
weather | -3.263 |
ipers | -3.176 |
rador | -3.074 |
opp | -3.047 |
ricted | -3.018 |
Token | It |
Token ID | 632 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
hens | +0.367 |
@@@@ | +0.362 |
═ | +0.322 |
hust | +0.319 |
tin | +0.319 |
Neg logit contributions | |
weather | -0.371 |
ipers | -0.356 |
rador | -0.347 |
opp | -0.347 |
ricted | -0.341 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
hens | +0.361 |
@@@@ | +0.357 |
═ | +0.317 |
� | +0.315 |
hust | +0.315 |
Neg logit contributions | |
weather | -0.372 |
ipers | -0.358 |
opp | -0.349 |
rador | -0.347 |
ricted | -0.341 |
Token | also |
Token ID | 635 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
weather | +0.228 |
ipers | +0.218 |
opp | +0.213 |
rador | +0.211 |
ricted | +0.208 |
Neg logit contributions | |
hens | -0.256 |
@@@@ | -0.253 |
═ | -0.227 |
� | -0.226 |
hust | -0.225 |
Token | also |
Token ID | 635 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hens | +1.241 |
@@@@ | +1.217 |
hust | +1.106 |
tin | +1.089 |
ONSORED | +1.081 |
Neg logit contributions | |
weather | -1.172 |
ipers | -1.125 |
opp | -1.095 |
rador | -1.086 |
ricted | -1.064 |
Token | been |
Token ID | 587 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
hens | +0.888 |
@@@@ | +0.869 |
hust | +0.790 |
tin | +0.782 |
═ | +0.771 |
Neg logit contributions | |
weather | -0.823 |
ipers | -0.791 |
opp | -0.770 |
rador | -0.763 |
ricted | -0.748 |
Token | told |
Token ID | 1297 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
hens | +2.322 |
@@@@ | +2.290 |
hust | +2.112 |
tin | +2.051 |
═ | +2.018 |
Neg logit contributions | |
weather | -2.149 |
ipers | -2.084 |
rador | -2.007 |
opp | -2.004 |
ricted | -1.954 |
Token | by |
Token ID | 416 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
hens | +2.481 |
@@@@ | +2.424 |
hust | +2.211 |
tin | +2.175 |
═ | +2.168 |
Neg logit contributions | |
weather | -2.352 |
ipers | -2.269 |
rador | -2.208 |
opp | -2.184 |
ricted | -2.157 |
Token | a |
Token ID | 257 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
hens | +0.882 |
@@@@ | +0.867 |
hust | +0.789 |
═ | +0.773 |
tin | +0.772 |
Neg logit contributions | |
weather | -0.803 |
ipers | -0.774 |
opp | -0.749 |
rador | -0.749 |
ricted | -0.736 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
hens | +0.287 |
@@@@ | +0.284 |
hust | +0.257 |
═ | +0.253 |
tin | +0.253 |
Neg logit contributions | |
weather | -0.259 |
ipers | -0.249 |
opp | -0.241 |
rador | -0.240 |
ricted | -0.236 |
Token | prosecutor |
Token ID | 13683 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
hens | +6.260 |
hust | +6.080 |
@@@@ | +6.040 |
tin | +5.600 |
�� | +5.445 |
Neg logit contributions | |
weather | -6.604 |
ipers | -6.518 |
rador | -6.323 |
ricted | -6.292 |
opp | -6.164 |
Token | that |
Token ID | 326 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
hens | +2.283 |
@@@@ | +2.241 |
hust | +2.052 |
tin | +2.019 |
═ | +1.997 |
Neg logit contributions | |
weather | -2.208 |
ipers | -2.121 |
rador | -2.071 |
opp | -2.051 |
ricted | -2.042 |
Token | Rolls |
Token ID | 40074 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
weather | +0.690 |
ipers | +0.660 |
opp | +0.642 |
rador | +0.639 |
ricted | +0.628 |
Neg logit contributions | |
hens | -0.783 |
@@@@ | -0.773 |
═ | -0.692 |
hust | -0.691 |
� | -0.688 |
Token | - |
Token ID | 12 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
weather | +1.634 |
ipers | +1.557 |
opp | +1.516 |
rador | +1.502 |
ricted | +1.477 |
Neg logit contributions | |
hens | -2.050 |
@@@@ | -2.034 |
═ | -1.828 |
� | -1.827 |
tin | -1.816 |
Token | Roy |
Token ID | 32027 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
hens | +0.954 |
@@@@ | +0.947 |
tin | +0.879 |
═ | +0.874 |
hust | +0.870 |
Neg logit contributions | |
weather | -0.356 |
ipers | -0.331 |
rador | -0.310 |
opp | -0.304 |
ricted | -0.304 |
Token | ( |
Token ID | 357 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
weather | +0.401 |
ipers | +0.384 |
opp | +0.375 |
rador | +0.373 |
ricted | +0.367 |
Neg logit contributions | |
hens | -0.398 |
@@@@ | -0.394 |
═ | -0.350 |
� | -0.348 |
tin | -0.347 |
Token | Fre |
Token ID | 20366 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
hens | +0.827 |
@@@@ | +0.819 |
═ | +0.728 |
tin | +0.726 |
ONSORED | +0.724 |
Neg logit contributions | |
weather | -0.773 |
ipers | -0.746 |
rador | -0.724 |
opp | -0.717 |
ricted | -0.711 |
Token | ire |
Token ID | 557 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
hens | +0.645 |
@@@@ | +0.627 |
tin | +0.542 |
hust | +0.539 |
═ | +0.531 |
Neg logit contributions | |
weather | -0.949 |
ipers | -0.905 |
opp | -0.897 |
rador | -0.888 |
ricted | -0.882 |
Token | was |
Token ID | 373 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
hens | +1.119 |
@@@@ | +1.097 |
hust | +0.987 |
═ | +0.985 |
tin | +0.984 |
Neg logit contributions | |
weather | -1.014 |
ipers | -0.977 |
rador | -0.948 |
opp | -0.944 |
ricted | -0.929 |
Token | a |
Token ID | 257 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
weather | +0.215 |
ipers | +0.205 |
opp | +0.199 |
rador | +0.198 |
ricted | +0.195 |
Neg logit contributions | |
hens | -0.253 |
@@@@ | -0.251 |
═ | -0.224 |
hust | -0.224 |
� | -0.224 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
hens | +0.228 |
@@@@ | +0.225 |
hust | +0.202 |
═ | +0.201 |
tin | +0.200 |
Neg logit contributions | |
weather | -0.209 |
ipers | -0.201 |
opp | -0.194 |
rador | -0.194 |
ricted | -0.191 |
Token | leftist |
Token ID | 28318 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
hens | +6.565 |
@@@@ | +6.352 |
hust | +6.294 |
tin | +5.707 |
� | +5.671 |
Neg logit contributions | |
weather | -6.446 |
ipers | -6.225 |
Downloadha | -6.148 |
ricted | -6.104 |
rador | -6.033 |
Token | who |
Token ID | 508 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
hens | +3.133 |
@@@@ | +3.113 |
hust | +2.920 |
tin | +2.781 |
═ | +2.759 |
Neg logit contributions | |
weather | -3.061 |
ipers | -2.951 |
rador | -2.852 |
ricted | -2.829 |
Downloadha | -2.823 |
Token | wrote |
Token ID | 2630 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
hens | +1.603 |
@@@@ | +1.571 |
hust | +1.453 |
tin | +1.424 |
═ | +1.392 |
Neg logit contributions | |
weather | -1.647 |
ipers | -1.587 |
rador | -1.542 |
opp | -1.515 |
ricted | -1.504 |
Token | a |
Token ID | 257 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
weather | +0.434 |
ipers | +0.414 |
opp | +0.403 |
rador | +0.400 |
ricted | +0.394 |
Neg logit contributions | |
hens | -0.520 |
@@@@ | -0.515 |
═ | -0.462 |
� | -0.461 |
hust | -0.460 |
Token | social |
Token ID | 1919 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
weather | +0.384 |
ipers | +0.369 |
opp | +0.360 |
rador | +0.359 |
ricted | +0.353 |
Neg logit contributions | |
hens | -0.347 |
@@@@ | -0.343 |
═ | -0.303 |
� | -0.302 |
hust | -0.302 |
Token | et |
Token ID | 316 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
hens | +0.506 |
@@@@ | +0.499 |
tin | +0.446 |
═ | +0.443 |
hust | +0.443 |
Neg logit contributions | |
weather | -0.452 |
ipers | -0.440 |
rador | -0.422 |
opp | -0.422 |
ricted | -0.420 |
Token | ernal |
Token ID | 35220 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
weather | +1.967 |
ipers | +1.833 |
opp | +1.790 |
rador | +1.768 |
ricted | +1.725 |
Neg logit contributions | |
@@@@ | -4.376 |
hens | -4.358 |
═ | -4.073 |
� | -4.066 |
ONSORED | -4.043 |
Token | " |
Token ID | 1 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
weather | +0.433 |
ipers | +0.415 |
opp | +0.403 |
rador | +0.400 |
ricted | +0.395 |
Neg logit contributions | |
hens | -0.501 |
@@@@ | -0.496 |
═ | -0.444 |
hust | -0.443 |
� | -0.443 |
Token | in |
Token ID | 287 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
weather | +0.227 |
ipers | +0.218 |
opp | +0.212 |
rador | +0.211 |
ricted | +0.207 |
Neg logit contributions | |
hens | -0.259 |
@@@@ | -0.256 |
═ | -0.229 |
� | -0.228 |
hust | -0.228 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
hens | +0.218 |
@@@@ | +0.215 |
═ | +0.192 |
� | +0.192 |
hust | +0.192 |
Neg logit contributions | |
weather | -0.198 |
ipers | -0.190 |
opp | -0.185 |
rador | -0.184 |
ricted | -0.181 |
Token | Mongol |
Token ID | 42188 |
Feature activation | +9.16e+00 |
Pos logit contributions | |
hens | +0.385 |
@@@@ | +0.381 |
═ | +0.339 |
� | +0.339 |
hust | +0.338 |
Neg logit contributions | |
weather | -0.369 |
ipers | -0.354 |
opp | -0.345 |
rador | -0.342 |
ricted | -0.337 |
Token | ian |
Token ID | 666 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
hens | +5.587 |
@@@@ | +5.404 |
hust | +4.785 |
� | +4.741 |
Scroll | +4.730 |
Neg logit contributions | |
weather | -7.514 |
ipers | -7.395 |
Downloadha | -7.298 |
rador | -7.172 |
ricted | -7.161 |
Token | language |
Token ID | 3303 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
hens | +4.094 |
@@@@ | +3.991 |
hust | +3.687 |
� | +3.627 |
@#& | +3.615 |
Neg logit contributions | |
weather | -3.230 |
ipers | -3.152 |
Downloadha | -3.004 |
opp | -3.002 |
rador | -2.999 |
Token | ).[ |
Token ID | 42669 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
hens | +2.528 |
@@@@ | +2.497 |
hust | +2.277 |
� | +2.269 |
@#& | +2.264 |
Neg logit contributions | |
weather | -1.704 |
ipers | -1.638 |
rador | -1.569 |
opp | -1.553 |
ricted | -1.543 |
Token | 1 |
Token ID | 16 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
weather | +4.063 |
ipers | +3.784 |
opp | +3.762 |
ocal | +3.569 |
ored | +3.564 |
Neg logit contributions | |
hens | -5.730 |
@@@@ | -5.712 |
� | -5.303 |
�� | -5.264 |
hust | -5.206 |
Token | ] |
Token ID | 60 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
weather | +0.465 |
ipers | +0.435 |
opp | +0.421 |
rador | +0.413 |
ricted | +0.405 |
Neg logit contributions | |
hens | -0.946 |
@@@@ | -0.939 |
� | -0.861 |
═ | -0.860 |
hust | -0.857 |
Token | in |
Token ID | 259 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
weather | +0.091 |
ipers | +0.087 |
opp | +0.084 |
rador | +0.083 |
ricted | +0.082 |
Neg logit contributions | |
hens | -0.132 |
@@@@ | -0.130 |
tin | -0.118 |
═ | -0.118 |
� | -0.117 |
Token | ) |
Token ID | 8 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
weather | +1.355 |
ipers | +1.293 |
opp | +1.265 |
rador | +1.254 |
ricted | +1.231 |
Neg logit contributions | |
hens | -1.555 |
@@@@ | -1.542 |
═ | -1.382 |
� | -1.379 |
hust | -1.372 |
Token | tribe |
Token ID | 14893 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
weather | +0.311 |
ipers | +0.298 |
opp | +0.292 |
rador | +0.289 |
ricted | +0.284 |
Neg logit contributions | |
hens | -0.314 |
@@@@ | -0.311 |
═ | -0.277 |
� | -0.276 |
hust | -0.275 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hens | +0.232 |
@@@@ | +0.230 |
═ | +0.205 |
hust | +0.204 |
tin | +0.204 |
Neg logit contributions | |
weather | -0.206 |
ipers | -0.197 |
opp | -0.192 |
rador | -0.191 |
ricted | -0.188 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
weather | +0.217 |
ipers | +0.208 |
opp | +0.202 |
rador | +0.202 |
ricted | +0.199 |
Neg logit contributions | |
hens | -0.228 |
@@@@ | -0.225 |
hust | -0.200 |
tin | -0.200 |
═ | -0.200 |
Token | Mongol |
Token ID | 42188 |
Feature activation | +9.07e+00 |
Pos logit contributions | |
hens | +0.518 |
@@@@ | +0.513 |
hust | +0.459 |
� | +0.458 |
tin | +0.458 |
Neg logit contributions | |
weather | -0.434 |
ipers | -0.417 |
opp | -0.404 |
rador | -0.401 |
ricted | -0.397 |
Token | general |
Token ID | 2276 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
hens | +5.893 |
@@@@ | +5.850 |
tin | +5.100 |
hust | +5.092 |
� | +5.067 |
Neg logit contributions | |
weather | -7.021 |
ipers | -6.871 |
ricted | -6.690 |
rador | -6.646 |
Downloadha | -6.631 |
Token | Mang |
Token ID | 27609 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
weather | +0.710 |
ipers | +0.680 |
opp | +0.664 |
rador | +0.659 |
ricted | +0.649 |
Neg logit contributions | |
hens | -0.753 |
@@@@ | -0.745 |
═ | -0.665 |
� | -0.663 |
hust | -0.660 |
Token | gh |
Token ID | 456 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
hens | +1.916 |
@@@@ | +1.865 |
tin | +1.723 |
hust | +1.679 |
═ | +1.667 |
Neg logit contributions | |
weather | -1.455 |
ipers | -1.395 |
opp | -1.345 |
rador | -1.334 |
ricted | -1.325 |
Token | ud |
Token ID | 463 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
hens | +0.018 |
@@@@ | +0.018 |
tin | +0.016 |
═ | +0.016 |
� | +0.016 |
Neg logit contributions | |
weather | -0.015 |
ipers | -0.014 |
opp | -0.014 |
rador | -0.013 |
ricted | -0.013 |
Token | ai |
Token ID | 1872 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
weather | +3.222 |
ipers | +3.043 |
opp | +3.013 |
rador | +2.973 |
ricted | +2.923 |
Neg logit contributions | |
@@@@ | -3.682 |
hens | -3.668 |
� | -3.326 |
═ | -3.312 |
hust | -3.269 |
Token | ch |
Token ID | 354 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
weather | +0.947 |
ipers | +0.904 |
opp | +0.885 |
rador | +0.874 |
ricted | +0.862 |
Neg logit contributions | |
hens | -1.031 |
@@@@ | -1.024 |
═ | -0.916 |
� | -0.914 |
hust | -0.908 |
Token | uck |
Token ID | 1347 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
weather | +2.005 |
ipers | +1.920 |
opp | +1.878 |
rador | +1.840 |
ricted | +1.805 |
Neg logit contributions | |
@@@@ | -3.045 |
hens | -3.037 |
� | -2.797 |
═ | -2.786 |
�� | -2.758 |
Token | . |
Token ID | 13 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
weather | +0.701 |
ipers | +0.671 |
opp | +0.654 |
rador | +0.650 |
ricted | +0.639 |
Neg logit contributions | |
hens | -0.784 |
@@@@ | -0.776 |
═ | -0.694 |
� | -0.692 |
tin | -0.689 |
Token | html |
Token ID | 6494 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
hens | +0.445 |
@@@@ | +0.436 |
tin | +0.380 |
═ | +0.379 |
� | +0.377 |
Neg logit contributions | |
weather | -0.563 |
ipers | -0.545 |
opp | -0.532 |
rador | -0.531 |
ricted | -0.524 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
weather | +1.873 |
ipers | +1.765 |
opp | +1.733 |
rador | +1.707 |
ricted | +1.678 |
Neg logit contributions | |
hens | -2.653 |
@@@@ | -2.638 |
hust | -2.391 |
═ | -2.382 |
� | -2.378 |
Token | Sen |
Token ID | 10445 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
weather | +1.648 |
ipers | +1.577 |
opp | +1.536 |
rador | +1.527 |
ricted | +1.502 |
Neg logit contributions | |
hens | -1.863 |
@@@@ | -1.845 |
═ | -1.650 |
� | -1.646 |
tin | -1.640 |
Token | . |
Token ID | 13 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
weather | +6.779 |
opp | +6.646 |
ipers | +6.617 |
ored | +6.353 |
rador | +6.196 |
Neg logit contributions | |
@@@@ | -11.454 |
hens | -10.976 |
═ | -10.747 |
� | -10.733 |
@#& | -10.550 |
Token | Harry |
Token ID | 5850 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
hens | +0.384 |
@@@@ | +0.378 |
tin | +0.341 |
hust | +0.339 |
� | +0.337 |
Neg logit contributions | |
weather | -0.324 |
ipers | -0.310 |
rador | -0.303 |
opp | -0.300 |
ricted | -0.296 |
Token | Reid |
Token ID | 16095 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
weather | +2.315 |
ipers | +2.160 |
opp | +2.103 |
rador | +2.003 |
ricted | +1.995 |
Neg logit contributions | |
@@@@ | -4.939 |
hens | -4.891 |
═ | -4.615 |
� | -4.580 |
hust | -4.466 |
Token | spoke |
Token ID | 5158 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
weather | +3.777 |
ipers | +3.546 |
opp | +3.477 |
ricted | +3.399 |
rador | +3.361 |
Neg logit contributions | |
@@@@ | -4.739 |
hens | -4.681 |
� | -4.355 |
═ | -4.297 |
@#& | -4.237 |
Token | on |
Token ID | 319 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
weather | +0.497 |
ipers | +0.476 |
opp | +0.464 |
rador | +0.462 |
ricted | +0.455 |
Neg logit contributions | |
hens | -0.535 |
@@@@ | -0.529 |
hust | -0.472 |
═ | -0.472 |
tin | -0.470 |
Token | : |
Token ID | 25 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
hens | +1.268 |
@@@@ | +1.252 |
hust | +1.129 |
tin | +1.123 |
═ | +1.120 |
Neg logit contributions | |
weather | -1.055 |
ipers | -1.010 |
opp | -0.978 |
rador | -0.972 |
ricted | -0.956 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hens | +0.594 |
@@@@ | +0.589 |
═ | +0.528 |
hust | +0.528 |
� | +0.527 |
Neg logit contributions | |
weather | -0.470 |
ipers | -0.450 |
opp | -0.436 |
rador | -0.435 |
ricted | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
weather | +0.672 |
ipers | +0.639 |
opp | +0.622 |
rador | +0.616 |
ricted | +0.605 |
Neg logit contributions | |
hens | -0.922 |
@@@@ | -0.913 |
═ | -0.826 |
� | -0.825 |
hust | -0.821 |
Token | < |
Token ID | 27 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
weather | +0.835 |
ipers | +0.800 |
opp | +0.780 |
rador | +0.774 |
ricted | +0.762 |
Neg logit contributions | |
hens | -0.919 |
@@@@ | -0.909 |
═ | -0.812 |
� | -0.810 |
tin | -0.807 |
Token | body |
Token ID | 2618 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
weather | +4.618 |
opp | +4.312 |
ipers | +4.234 |
liction | +4.095 |
ricted | +4.095 |
Neg logit contributions | |
hens | -5.378 |
@@@@ | -5.349 |
� | -4.876 |
ONSORED | -4.868 |
�� | -4.831 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
weather | +2.921 |
ipers | +2.615 |
opp | +2.583 |
rador | +2.551 |
ored | +2.528 |
Neg logit contributions | |
hens | -6.092 |
@@@@ | -6.044 |
ONSORED | -5.619 |
� | -5.596 |
═ | -5.564 |
Token | - |
Token ID | 12 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
weather | +5.997 |
ipers | +5.360 |
ored | +5.180 |
opp | +5.152 |
ocal | +5.021 |
Neg logit contributions | |
hens | -11.236 |
@@@@ | -10.888 |
�� | -10.537 |
ONSORED | -10.364 |
awaru | -10.217 |
Token | controller |
Token ID | 36500 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
weather | +1.100 |
ipers | +1.042 |
opp | +1.020 |
rador | +1.003 |
ricted | +0.984 |
Neg logit contributions | |
hens | -1.469 |
@@@@ | -1.457 |
� | -1.322 |
═ | -1.318 |
ONSORED | -1.315 |
Token | =" |
Token ID | 2625 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
weather | +2.153 |
ipers | +2.054 |
opp | +2.000 |
rador | +1.992 |
ricted | +1.954 |
Neg logit contributions | |
hens | -2.997 |
@@@@ | -2.947 |
� | -2.691 |
═ | -2.687 |
tin | -2.675 |
Token | Phone |
Token ID | 6132 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
weather | +2.048 |
ipers | +1.942 |
opp | +1.914 |
rador | +1.878 |
ricted | +1.850 |
Neg logit contributions | |
hens | -2.145 |
@@@@ | -2.118 |
� | -1.898 |
═ | -1.894 |
ONSORED | -1.882 |
Token | List |
Token ID | 8053 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
weather | +0.923 |
ipers | +0.882 |
opp | +0.857 |
rador | +0.852 |
ricted | +0.837 |
Neg logit contributions | |
hens | -1.168 |
@@@@ | -1.158 |
═ | -1.042 |
� | -1.039 |
hust | -1.035 |
Token | mang |
Token ID | 45663 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
weather | +0.354 |
ipers | +0.339 |
opp | +0.331 |
rador | +0.330 |
ricted | +0.325 |
Neg logit contributions | |
hens | -0.333 |
@@@@ | -0.329 |
hust | -0.291 |
═ | -0.290 |
tin | -0.289 |
Token | le |
Token ID | 293 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
weather | +0.735 |
ipers | +0.716 |
rador | +0.698 |
opp | +0.697 |
ricted | +0.691 |
Neg logit contributions | |
hens | -0.439 |
@@@@ | -0.432 |
tin | -0.368 |
hust | -0.367 |
═ | -0.366 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
hens | +0.325 |
@@@@ | +0.322 |
hust | +0.288 |
═ | +0.288 |
tin | +0.287 |
Neg logit contributions | |
weather | -0.269 |
ipers | -0.255 |
rador | -0.249 |
opp | -0.248 |
ricted | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
weather | +0.011 |
ipers | +0.011 |
opp | +0.010 |
rador | +0.010 |
ricted | +0.010 |
Neg logit contributions | |
hens | -0.014 |
@@@@ | -0.014 |
═ | -0.012 |
� | -0.012 |
tin | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
weather | +0.099 |
ipers | +0.095 |
rador | +0.092 |
opp | +0.092 |
ricted | +0.090 |
Neg logit contributions | |
hens | -0.128 |
@@@@ | -0.126 |
tin | -0.113 |
═ | -0.113 |
hust | -0.113 |
Token | Sen |
Token ID | 10445 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
hens | +0.018 |
@@@@ | +0.018 |
tin | +0.016 |
═ | +0.016 |
Scroll | +0.016 |
Neg logit contributions | |
weather | -0.016 |
ipers | -0.015 |
rador | -0.015 |
opp | -0.015 |
ricted | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
weather | +6.424 |
opp | +6.259 |
ipers | +6.169 |
ored | +5.961 |
rador | +5.898 |
Neg logit contributions | |
@@@@ | -9.817 |
hens | -9.561 |
� | -9.201 |
hust | -8.926 |
@#& | -8.911 |
Token | Cruz |
Token ID | 8742 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
hens | +0.815 |
@@@@ | +0.807 |
tin | +0.743 |
═ | +0.743 |
hust | +0.739 |
Neg logit contributions | |
weather | -0.343 |
ipers | -0.322 |
rador | -0.306 |
opp | -0.304 |
ricted | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
weather | +2.779 |
ipers | +2.635 |
opp | +2.604 |
rador | +2.553 |
ricted | +2.509 |
Neg logit contributions | |
hens | -2.925 |
@@@@ | -2.908 |
� | -2.606 |
═ | -2.590 |
�� | -2.567 |
Token | in |
Token ID | 287 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
hens | +0.454 |
@@@@ | +0.449 |
═ | +0.400 |
hust | +0.399 |
� | +0.398 |
Neg logit contributions | |
weather | -0.436 |
ipers | -0.418 |
opp | -0.407 |
rador | -0.405 |
ricted | -0.399 |
Token | his |
Token ID | 465 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
hens | +0.709 |
@@@@ | +0.698 |
hust | +0.627 |
═ | +0.625 |
tin | +0.622 |
Neg logit contributions | |
weather | -0.640 |
ipers | -0.612 |
rador | -0.587 |
opp | -0.586 |
ricted | -0.579 |
Token | in |
Token ID | 287 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
weather | +1.821 |
ipers | +1.742 |
opp | +1.705 |
rador | +1.682 |
ricted | +1.654 |
Neg logit contributions | |
hens | -2.097 |
@@@@ | -2.080 |
� | -1.877 |
═ | -1.868 |
ONSORED | -1.860 |
Token | instead |
Token ID | 2427 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
hens | +0.258 |
@@@@ | +0.255 |
hust | +0.228 |
═ | +0.228 |
tin | +0.228 |
Neg logit contributions | |
weather | -0.216 |
ipers | -0.208 |
rador | -0.200 |
opp | -0.200 |
ricted | -0.197 |
Token | of |
Token ID | 286 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
weather | +1.383 |
ipers | +1.314 |
opp | +1.288 |
rador | +1.272 |
ricted | +1.249 |
Neg logit contributions | |
hens | -1.814 |
@@@@ | -1.796 |
� | -1.624 |
═ | -1.615 |
ONSORED | -1.615 |
Token | going |
Token ID | 1016 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
hens | +0.143 |
@@@@ | +0.141 |
hust | +0.126 |
═ | +0.126 |
tin | +0.126 |
Neg logit contributions | |
weather | -0.125 |
ipers | -0.120 |
opp | -0.116 |
rador | -0.116 |
ricted | -0.114 |
Token | through |
Token ID | 832 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
hens | +0.332 |
@@@@ | +0.328 |
═ | +0.291 |
hust | +0.290 |
� | +0.290 |
Neg logit contributions | |
weather | -0.334 |
ipers | -0.320 |
opp | -0.312 |
rador | -0.310 |
ricted | -0.306 |
Token | std |
Token ID | 14367 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
hens | +0.315 |
@@@@ | +0.311 |
hust | +0.280 |
═ | +0.279 |
tin | +0.278 |
Neg logit contributions | |
weather | -0.254 |
ipers | -0.241 |
rador | -0.234 |
opp | -0.234 |
ricted | -0.231 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
weather | +6.712 |
opp | +6.056 |
ipers | +5.935 |
ocal | +5.901 |
ored | +5.865 |
Neg logit contributions | |
hens | -9.593 |
@@@@ | -9.425 |
ONSORED | -8.985 |
� | -8.933 |
@#& | -8.582 |
Token | ist |
Token ID | 396 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
weather | +0.962 |
ipers | +0.918 |
opp | +0.894 |
rador | +0.887 |
ricted | +0.871 |
Neg logit contributions | |
hens | -1.185 |
@@@@ | -1.173 |
═ | -1.055 |
� | -1.053 |
hust | -1.048 |
Token | ream |
Token ID | 1476 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
hens | +1.646 |
@@@@ | +1.637 |
═ | +1.494 |
tin | +1.489 |
hust | +1.489 |
Neg logit contributions | |
weather | -1.031 |
ipers | -0.990 |
rador | -0.938 |
opp | -0.937 |
Downloadha | -0.936 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
weather | +0.148 |
ipers | +0.141 |
opp | +0.137 |
rador | +0.136 |
ricted | +0.134 |
Neg logit contributions | |
hens | -0.184 |
@@@@ | -0.183 |
═ | -0.164 |
� | -0.164 |
hust | -0.163 |
Token | I |
Token ID | 314 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
weather | +0.088 |
ipers | +0.085 |
opp | +0.082 |
rador | +0.082 |
ricted | +0.081 |
Neg logit contributions | |
hens | -0.094 |
@@@@ | -0.093 |
═ | -0.083 |
� | -0.082 |
tin | -0.082 |
Token | opposite |
Token ID | 6697 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
weather | +0.329 |
ipers | +0.314 |
rador | +0.304 |
opp | +0.300 |
ricted | +0.296 |
Neg logit contributions | |
hens | -0.430 |
@@@@ | -0.424 |
hust | -0.386 |
tin | -0.381 |
═ | -0.380 |
Token | sex |
Token ID | 1714 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
weather | +1.822 |
ipers | +1.710 |
opp | +1.671 |
rador | +1.634 |
ricted | +1.606 |
Neg logit contributions | |
hens | -3.001 |
@@@@ | -2.981 |
═ | -2.726 |
� | -2.712 |
tin | -2.694 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
weather | +0.041 |
ipers | +0.039 |
rador | +0.038 |
opp | +0.037 |
ricted | +0.037 |
Neg logit contributions | |
hens | -0.050 |
@@@@ | -0.050 |
hust | -0.045 |
═ | -0.045 |
tin | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
weather | +0.850 |
ipers | +0.812 |
opp | +0.791 |
rador | +0.784 |
ricted | +0.772 |
Neg logit contributions | |
hens | -1.017 |
@@@@ | -1.007 |
═ | -0.904 |
� | -0.903 |
hust | -0.898 |
Token |
|
Token ID | 198 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
weather | +0.706 |
ipers | +0.671 |
opp | +0.653 |
rador | +0.646 |
ricted | +0.635 |
Neg logit contributions | |
hens | -0.968 |
@@@@ | -0.959 |
═ | -0.867 |
� | -0.866 |
hust | -0.861 |
Token | Sen |
Token ID | 10445 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
weather | +0.575 |
ipers | +0.554 |
rador | +0.537 |
opp | +0.525 |
ricted | +0.523 |
Neg logit contributions | |
hens | -0.746 |
@@@@ | -0.741 |
tin | -0.663 |
═ | -0.659 |
Scroll | -0.659 |
Token | . |
Token ID | 13 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
opp | +5.347 |
weather | +5.324 |
ipers | +5.186 |
ored | +5.161 |
itch | +4.952 |
Neg logit contributions | |
@@@@ | -10.304 |
� | -10.026 |
hens | -9.863 |
═ | -9.850 |
�� | -9.603 |
Token | Sylvia |
Token ID | 45425 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
weather | +0.064 |
ipers | +0.062 |
rador | +0.060 |
opp | +0.060 |
ricted | +0.059 |
Neg logit contributions | |
hens | -0.074 |
@@@@ | -0.073 |
tin | -0.066 |
hust | -0.066 |
═ | -0.065 |
Token | Garcia |
Token ID | 18555 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
weather | +2.932 |
ipers | +2.796 |
opp | +2.744 |
rador | +2.682 |
ricted | +2.678 |
Neg logit contributions | |
@@@@ | -3.199 |
hens | -3.198 |
═ | -2.908 |
� | -2.887 |
�� | -2.840 |
Token | , |
Token ID | 11 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
weather | +0.361 |
ipers | +0.344 |
opp | +0.335 |
rador | +0.333 |
ricted | +0.327 |
Neg logit contributions | |
hens | -0.450 |
@@@@ | -0.445 |
═ | -0.401 |
� | -0.399 |
hust | -0.399 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
hens | +0.585 |
@@@@ | +0.577 |
hust | +0.517 |
tin | +0.514 |
═ | +0.513 |
Neg logit contributions | |
weather | -0.495 |
ipers | -0.474 |
rador | -0.457 |
opp | -0.455 |
ricted | -0.450 |
Token | Senate |
Token ID | 3845 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
weather | +0.181 |
ipers | +0.172 |
rador | +0.166 |
opp | +0.166 |
ricted | +0.163 |
Neg logit contributions | |
hens | -0.240 |
@@@@ | -0.235 |
hust | -0.214 |
tin | -0.211 |
═ | -0.210 |
Token | floor |
Token ID | 4314 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
weather | +4.214 |
opp | +4.001 |
ipers | +3.976 |
ored | +3.765 |
rador | +3.762 |
Neg logit contributions | |
hens | -8.487 |
@@@@ | -8.481 |
� | -8.007 |
═ | -7.975 |
ONSORED | -7.859 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
weather | +1.819 |
ipers | +1.726 |
opp | +1.697 |
rador | +1.657 |
ricted | +1.634 |
Neg logit contributions | |
hens | -2.518 |
@@@@ | -2.504 |
� | -2.275 |
═ | -2.266 |
@#& | -2.246 |
Token |
|
Token ID | 198 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
weather | +0.423 |
ipers | +0.404 |
rador | +0.392 |
opp | +0.392 |
ricted | +0.384 |
Neg logit contributions | |
hens | -0.492 |
@@@@ | -0.485 |
═ | -0.435 |
hust | -0.432 |
tin | -0.432 |
Token |
|
Token ID | 198 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
weather | +0.510 |
ipers | +0.486 |
opp | +0.471 |
rador | +0.469 |
ricted | +0.460 |
Neg logit contributions | |
hens | -0.686 |
@@@@ | -0.679 |
═ | -0.612 |
tin | -0.609 |
� | -0.609 |
Token | Sen |
Token ID | 10445 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
weather | +0.291 |
ipers | +0.282 |
rador | +0.272 |
opp | +0.266 |
ricted | +0.266 |
Neg logit contributions | |
hens | -0.352 |
@@@@ | -0.349 |
Scroll | -0.311 |
tin | -0.311 |
═ | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
weather | +5.457 |
ipers | +5.390 |
opp | +5.378 |
ored | +5.231 |
rador | +5.021 |
Neg logit contributions | |
@@@@ | -9.580 |
hens | -9.264 |
� | -8.962 |
═ | -8.920 |
@#& | -8.909 |
Token | Lois |
Token ID | 42879 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
hens | +0.297 |
@@@@ | +0.294 |
tin | +0.263 |
hust | +0.263 |
═ | +0.261 |
Neg logit contributions | |
weather | -0.256 |
ipers | -0.246 |
rador | -0.239 |
opp | -0.238 |
ricted | -0.234 |
Token | K |
Token ID | 509 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
weather | +2.919 |
ipers | +2.770 |
opp | +2.739 |
ricted | +2.664 |
rador | +2.656 |
Neg logit contributions | |
@@@@ | -3.049 |
hens | -3.048 |
═ | -2.763 |
� | -2.759 |
hust | -2.701 |
Token | olk |
Token ID | 13597 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
weather | +0.592 |
ipers | +0.563 |
rador | +0.545 |
opp | +0.542 |
ricted | +0.536 |
Neg logit contributions | |
hens | -0.767 |
@@@@ | -0.753 |
tin | -0.677 |
hust | -0.674 |
� | -0.672 |
Token | hor |
Token ID | 17899 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
weather | +0.449 |
ipers | +0.430 |
opp | +0.416 |
rador | +0.415 |
ricted | +0.409 |
Neg logit contributions | |
hens | -0.537 |
@@@@ | -0.527 |
tin | -0.473 |
hust | -0.472 |
═ | -0.471 |
Token | T |
Token ID | 51 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
weather | +2.756 |
ipers | +2.598 |
opp | +2.571 |
ricted | +2.506 |
rador | +2.492 |
Neg logit contributions | |
hens | -3.107 |
@@@@ | -3.072 |
� | -2.794 |
hust | -2.761 |
═ | -2.760 |
Token | > |
Token ID | 29 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
weather | +0.192 |
ipers | +0.180 |
opp | +0.174 |
rador | +0.172 |
ricted | +0.168 |
Neg logit contributions | |
hens | -0.371 |
@@@@ | -0.368 |
═ | -0.337 |
� | -0.336 |
tin | -0.335 |
Token | , |
Token ID | 837 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
weather | +2.423 |
ipers | +2.322 |
opp | +2.278 |
rador | +2.250 |
ricted | +2.237 |
Neg logit contributions | |
hens | -2.390 |
@@@@ | -2.373 |
� | -2.114 |
hust | -2.105 |
tin | -2.097 |
Token | akin |
Token ID | 22107 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
weather | +0.423 |
ipers | +0.405 |
opp | +0.393 |
rador | +0.392 |
ricted | +0.385 |
Neg logit contributions | |
hens | -0.472 |
@@@@ | -0.467 |
═ | -0.418 |
� | -0.416 |
tin | -0.415 |
Token | to |
Token ID | 284 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
hens | +0.681 |
@@@@ | +0.673 |
═ | +0.601 |
tin | +0.599 |
hust | +0.597 |
Neg logit contributions | |
weather | -0.620 |
ipers | -0.594 |
opp | -0.577 |
rador | -0.575 |
ricted | -0.565 |
Token | std |
Token ID | 14367 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
hens | +0.002 |
@@@@ | +0.002 |
═ | +0.002 |
hust | +0.002 |
tin | +0.002 |
Neg logit contributions | |
weather | -0.002 |
ipers | -0.002 |
opp | -0.002 |
rador | -0.002 |
ricted | -0.002 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
weather | +4.253 |
ricted | +3.642 |
opp | +3.596 |
ipers | +3.466 |
ored | +3.453 |
Neg logit contributions | |
hens | -11.316 |
@@@@ | -11.129 |
� | -10.527 |
ONSORED | -10.430 |
@#& | -10.349 |
Token | sync |
Token ID | 27261 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
weather | +1.034 |
ipers | +0.977 |
opp | +0.955 |
rador | +0.941 |
ricted | +0.926 |
Neg logit contributions | |
hens | -1.455 |
@@@@ | -1.445 |
� | -1.308 |
═ | -1.306 |
hust | -1.299 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
weather | +0.217 |
ipers | +0.206 |
opp | +0.200 |
rador | +0.199 |
ricted | +0.195 |
Neg logit contributions | |
hens | -0.305 |
@@@@ | -0.302 |
═ | -0.274 |
� | -0.273 |
hust | -0.272 |
Token | atomic |
Token ID | 47116 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
weather | +0.954 |
ipers | +0.908 |
opp | +0.887 |
rador | +0.877 |
ricted | +0.863 |
Neg logit contributions | |
hens | -1.143 |
@@@@ | -1.132 |
═ | -1.018 |
� | -1.017 |
hust | -1.011 |
Token | :: |
Token ID | 3712 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
hens | +2.019 |
@@@@ | +2.009 |
═ | +1.801 |
� | +1.787 |
@#& | +1.787 |
Neg logit contributions | |
weather | -1.580 |
ipers | -1.509 |
rador | -1.465 |
opp | -1.462 |
ricted | -1.427 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
weather | +0.550 |
ipers | +0.526 |
opp | +0.511 |
rador | +0.509 |
ricted | +0.500 |
Neg logit contributions | |
hens | -0.653 |
@@@@ | -0.647 |
═ | -0.581 |
hust | -0.577 |
� | -0.577 |
Token | Instead |
Token ID | 5455 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
weather | +0.778 |
ipers | +0.743 |
opp | +0.726 |
rador | +0.718 |
ricted | +0.706 |
Neg logit contributions | |
hens | -0.897 |
@@@@ | -0.889 |
� | -0.797 |
═ | -0.797 |
hust | -0.791 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
weather | +1.944 |
ipers | +1.849 |
opp | +1.807 |
rador | +1.787 |
ricted | +1.754 |
Neg logit contributions | |
hens | -2.494 |
@@@@ | -2.467 |
� | -2.231 |
═ | -2.224 |
ONSORED | -2.223 |
Token | use |
Token ID | 779 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
weather | +0.749 |
ipers | +0.717 |
opp | +0.699 |
rador | +0.694 |
ricted | +0.683 |
Neg logit contributions | |
hens | -0.824 |
@@@@ | -0.815 |
═ | -0.728 |
� | -0.726 |
hust | -0.725 |
Token | the |
Token ID | 262 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
weather | +1.252 |
ipers | +1.192 |
opp | +1.160 |
rador | +1.150 |
ricted | +1.130 |
Neg logit contributions | |
hens | -1.628 |
@@@@ | -1.613 |
═ | -1.454 |
� | -1.452 |
tin | -1.445 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
weather | +0.297 |
ipers | +0.283 |
opp | +0.276 |
rador | +0.275 |
ricted | +0.270 |
Neg logit contributions | |
hens | -0.351 |
@@@@ | -0.347 |
═ | -0.311 |
� | -0.310 |
hust | -0.310 |
Token | - |
Token ID | 12 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
weather | +6.134 |
ipers | +5.538 |
opp | +5.417 |
ored | +5.358 |
ocal | +5.293 |
Neg logit contributions | |
hens | -9.001 |
@@@@ | -8.907 |
�� | -8.244 |
� | -8.189 |
@#& | -8.179 |
Token | bind |
Token ID | 21653 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
weather | +0.726 |
ipers | +0.686 |
opp | +0.666 |
rador | +0.659 |
ricted | +0.646 |
Neg logit contributions | |
hens | -1.167 |
@@@@ | -1.157 |
═ | -1.053 |
� | -1.051 |
hust | -1.046 |
Token | directive |
Token ID | 22644 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
weather | +0.504 |
ipers | +0.484 |
opp | +0.472 |
rador | +0.469 |
ricted | +0.462 |
Neg logit contributions | |
hens | -0.508 |
@@@@ | -0.502 |
═ | -0.447 |
� | -0.446 |
hust | -0.443 |
Token | : |
Token ID | 25 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
weather | +0.246 |
ipers | +0.235 |
opp | +0.229 |
rador | +0.228 |
ricted | +0.224 |
Neg logit contributions | |
hens | -0.300 |
@@@@ | -0.297 |
═ | -0.267 |
hust | -0.266 |
tin | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hens | +0.593 |
@@@@ | +0.588 |
═ | +0.530 |
� | +0.528 |
hust | +0.527 |
Neg logit contributions | |
weather | -0.449 |
ipers | -0.427 |
opp | -0.416 |
rador | -0.413 |
ricted | -0.407 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
weather | +1.869 |
ipers | +1.747 |
opp | +1.697 |
rador | +1.664 |
ricted | +1.626 |
Neg logit contributions | |
hens | -3.544 |
@@@@ | -3.526 |
═ | -3.247 |
� | -3.238 |
ONSORED | -3.211 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
weather | +1.448 |
ipers | +1.327 |
opp | +1.273 |
rador | +1.230 |
ricted | +1.207 |
Neg logit contributions | |
hens | -3.820 |
@@@@ | -3.790 |
═ | -3.530 |
� | -3.525 |
hust | -3.483 |
Token | lashed |
Token ID | 44416 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
weather | +1.288 |
ipers | +1.224 |
opp | +1.196 |
rador | +1.181 |
ricted | +1.166 |
Neg logit contributions | |
hens | -1.447 |
@@@@ | -1.435 |
═ | -1.290 |
� | -1.288 |
@#& | -1.273 |
Token | out |
Token ID | 503 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
hens | +0.374 |
@@@@ | +0.370 |
═ | +0.321 |
hust | +0.320 |
� | +0.319 |
Neg logit contributions | |
weather | -0.494 |
ipers | -0.476 |
opp | -0.464 |
rador | -0.464 |
ricted | -0.457 |
Token | at |
Token ID | 379 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
hens | +2.214 |
@@@@ | +2.180 |
hust | +1.960 |
═ | +1.944 |
tin | +1.941 |
Neg logit contributions | |
weather | -2.047 |
ipers | -1.957 |
rador | -1.920 |
opp | -1.899 |
ricted | -1.879 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
hens | +1.685 |
@@@@ | +1.656 |
hust | +1.507 |
tin | +1.470 |
═ | +1.468 |
Neg logit contributions | |
weather | -1.476 |
ipers | -1.418 |
rador | -1.370 |
opp | -1.368 |
ricted | -1.344 |
Token | . |
Token ID | 13 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
weather | +5.208 |
opp | +4.967 |
ipers | +4.842 |
ored | +4.735 |
itch | +4.636 |
Neg logit contributions | |
@@@@ | -9.775 |
hens | -9.618 |
� | -9.521 |
�� | -9.497 |
═ | -9.306 |
Token | Jeff |
Token ID | 19139 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
hens | +0.816 |
@@@@ | +0.806 |
tin | +0.730 |
hust | +0.729 |
� | +0.720 |
Neg logit contributions | |
weather | -0.646 |
ipers | -0.617 |
rador | -0.603 |
opp | -0.596 |
ricted | -0.587 |
Token | Flake |
Token ID | 39727 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
weather | +2.242 |
ipers | +2.128 |
opp | +2.069 |
rador | +2.049 |
ricted | +2.011 |
Neg logit contributions | |
hens | -3.241 |
@@@@ | -3.215 |
═ | -2.916 |
� | -2.909 |
hust | -2.893 |
Token | ( |
Token ID | 7 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
weather | +0.877 |
ipers | +0.838 |
opp | +0.817 |
rador | +0.812 |
ricted | +0.798 |
Neg logit contributions | |
hens | -1.028 |
@@@@ | -1.017 |
═ | -0.912 |
� | -0.909 |
hust | -0.907 |
Token | R |
Token ID | 49 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
weather | +1.068 |
ipers | +1.013 |
opp | +0.982 |
rador | +0.974 |
ricted | +0.955 |
Neg logit contributions | |
hens | -1.627 |
@@@@ | -1.612 |
═ | -1.464 |
� | -1.460 |
tin | -1.455 |
Token | vote |
Token ID | 27257 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
weather | +0.499 |
ipers | +0.484 |
rador | +0.464 |
opp | +0.461 |
ricted | +0.456 |
Neg logit contributions | |
hens | -0.574 |
@@@@ | -0.563 |
tin | -0.509 |
hust | -0.506 |
═ | -0.503 |
Token | efforts |
Token ID | 4040 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
weather | +4.475 |
ipers | +4.319 |
opp | +4.300 |
rador | +4.106 |
ricted | +4.080 |
Neg logit contributions | |
hens | -5.623 |
@@@@ | -5.567 |
═ | -5.033 |
@#& | -4.971 |
ategory | -4.960 |
Token | , |
Token ID | 11 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
weather | +0.679 |
ipers | +0.648 |
opp | +0.631 |
rador | +0.627 |
ricted | +0.616 |
Neg logit contributions | |
hens | -0.814 |
@@@@ | -0.806 |
═ | -0.724 |
� | -0.722 |
hust | -0.720 |
Token | and |
Token ID | 290 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
weather | +0.471 |
ipers | +0.451 |
opp | +0.438 |
rador | +0.437 |
ricted | +0.430 |
Neg logit contributions | |
hens | -0.514 |
@@@@ | -0.508 |
hust | -0.454 |
═ | -0.454 |
� | -0.453 |
Token | populist |
Token ID | 26815 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
weather | +0.559 |
ipers | +0.534 |
opp | +0.520 |
rador | +0.516 |
ricted | +0.508 |
Neg logit contributions | |
hens | -0.644 |
@@@@ | -0.637 |
═ | -0.571 |
� | -0.569 |
hust | -0.568 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
hens | +0.241 |
@@@@ | +0.238 |
hust | +0.216 |
═ | +0.213 |
tin | +0.213 |
Neg logit contributions | |
weather | -0.219 |
ipers | -0.211 |
rador | -0.204 |
opp | -0.203 |
ricted | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
weather | +5.138 |
opp | +5.005 |
ipers | +4.798 |
ored | +4.774 |
rador | +4.760 |
Neg logit contributions | |
@@@@ | -9.542 |
hens | -9.266 |
�� | -8.923 |
� | -8.901 |
═ | -8.855 |
Token | Bernard |
Token ID | 16197 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
hens | +0.252 |
@@@@ | +0.250 |
tin | +0.224 |
hust | +0.222 |
� | +0.222 |
Neg logit contributions | |
weather | -0.222 |
ipers | -0.214 |
rador | -0.207 |
opp | -0.207 |
ricted | -0.203 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
weather | +1.395 |
ipers | +1.316 |
opp | +1.257 |
rador | +1.252 |
ricted | +1.220 |
Neg logit contributions | |
hens | -2.918 |
@@@@ | -2.890 |
═ | -2.649 |
tin | -2.648 |
hust | -2.647 |
Token | of |
Token ID | 286 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
weather | +1.084 |
ipers | +1.026 |
opp | +1.010 |
rador | +0.993 |
ricted | +0.978 |
Neg logit contributions | |
hens | -1.281 |
@@@@ | -1.270 |
═ | -1.139 |
� | -1.135 |
tin | -1.131 |
Token | Vermont |
Token ID | 16033 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
hens | +0.839 |
@@@@ | +0.822 |
hust | +0.719 |
═ | +0.712 |
� | +0.710 |
Neg logit contributions | |
weather | -1.135 |
ipers | -1.095 |
opp | -1.065 |
rador | -1.064 |
ricted | -1.056 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
weather | +0.030 |
ipers | +0.029 |
rador | +0.028 |
opp | +0.028 |
ricted | +0.028 |
Neg logit contributions | |
hens | -0.037 |
@@@@ | -0.036 |
hust | -0.033 |
tin | -0.032 |
═ | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
weather | +2.339 |
ipers | +2.221 |
opp | +2.170 |
rador | +2.154 |
ricted | +2.103 |
Neg logit contributions | |
hens | -3.022 |
@@@@ | -2.994 |
� | -2.724 |
═ | -2.717 |
@#& | -2.700 |
Token | chair |
Token ID | 5118 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
weather | +0.134 |
ipers | +0.129 |
rador | +0.125 |
opp | +0.125 |
ricted | +0.122 |
Neg logit contributions | |
hens | -0.153 |
@@@@ | -0.151 |
hust | -0.136 |
tin | -0.135 |
═ | -0.134 |
Token | woman |
Token ID | 8580 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
weather | +0.899 |
ipers | +0.856 |
opp | +0.833 |
rador | +0.823 |
ricted | +0.808 |
Neg logit contributions | |
hens | -1.243 |
@@@@ | -1.234 |
═ | -1.118 |
� | -1.118 |
hust | -1.108 |
Token | , |
Token ID | 11 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
weather | +0.679 |
ipers | +0.648 |
opp | +0.631 |
rador | +0.625 |
ricted | +0.615 |
Neg logit contributions | |
hens | -0.856 |
@@@@ | -0.847 |
═ | -0.764 |
� | -0.762 |
tin | -0.757 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
weather | +0.278 |
ipers | +0.265 |
opp | +0.257 |
rador | +0.257 |
ricted | +0.252 |
Neg logit contributions | |
hens | -0.335 |
@@@@ | -0.331 |
hust | -0.297 |
═ | -0.297 |
tin | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
weather | +4.940 |
opp | +4.812 |
ipers | +4.664 |
ored | +4.608 |
itch | +4.440 |
Neg logit contributions | |
@@@@ | -9.475 |
�� | -9.448 |
� | -9.417 |
hens | -9.406 |
warr | -9.287 |
Token | Joan |
Token ID | 26640 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
hens | +0.047 |
@@@@ | +0.046 |
tin | +0.041 |
hust | +0.041 |
═ | +0.041 |
Neg logit contributions | |
weather | -0.041 |
ipers | -0.039 |
rador | -0.038 |
opp | -0.038 |
ricted | -0.038 |
Token | Huff |
Token ID | 14721 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
weather | +1.264 |
ipers | +1.209 |
opp | +1.183 |
rador | +1.169 |
ricted | +1.155 |
Neg logit contributions | |
hens | -1.319 |
@@@@ | -1.309 |
═ | -1.172 |
� | -1.169 |
hust | -1.158 |
Token | man |
Token ID | 805 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
weather | +1.720 |
ipers | +1.626 |
opp | +1.594 |
rador | +1.574 |
ricted | +1.545 |
Neg logit contributions | |
hens | -2.294 |
@@@@ | -2.290 |
� | -2.074 |
═ | -2.064 |
@#& | -2.047 |
Token | of |
Token ID | 286 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
hens | +1.690 |
@@@@ | +1.663 |
═ | +1.492 |
hust | +1.491 |
tin | +1.487 |
Neg logit contributions | |
weather | -1.402 |
ipers | -1.344 |
rador | -1.303 |
opp | -1.302 |
ricted | -1.278 |
Token | pitcher |
Token ID | 18086 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
weather | +2.532 |
ipers | +2.367 |
opp | +2.297 |
ricted | +2.243 |
rador | +2.237 |
Neg logit contributions | |
hens | -5.047 |
@@@@ | -5.026 |
═ | -4.665 |
� | -4.652 |
ONSORED | -4.570 |
Token | from |
Token ID | 422 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
weather | +3.937 |
ipers | +3.684 |
opp | +3.669 |
ricted | +3.546 |
rador | +3.517 |
Neg logit contributions | |
hens | -5.176 |
@@@@ | -5.147 |
� | -4.688 |
═ | -4.662 |
ONSORED | -4.630 |
Token | a |
Token ID | 257 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
hens | +1.106 |
@@@@ | +1.084 |
hust | +0.978 |
═ | +0.976 |
tin | +0.969 |
Neg logit contributions | |
weather | -0.948 |
ipers | -0.919 |
rador | -0.889 |
opp | -0.884 |
ricted | -0.860 |
Token | group |
Token ID | 1448 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
weather | +0.172 |
ipers | +0.165 |
opp | +0.160 |
rador | +0.159 |
ricted | +0.156 |
Neg logit contributions | |
hens | -0.186 |
@@@@ | -0.184 |
hust | -0.165 |
═ | -0.164 |
tin | -0.164 |
Token | include |
Token ID | 2291 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
weather | +0.448 |
ipers | +0.427 |
opp | +0.417 |
rador | +0.413 |
ricted | +0.407 |
Neg logit contributions | |
hens | -0.532 |
@@@@ | -0.527 |
═ | -0.473 |
� | -0.472 |
tin | -0.469 |
Token | Tampa |
Token ID | 15528 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
weather | +1.116 |
ipers | +1.067 |
opp | +1.038 |
rador | +1.032 |
ricted | +1.012 |
Neg logit contributions | |
hens | -1.364 |
@@@@ | -1.348 |
═ | -1.212 |
� | -1.208 |
hust | -1.208 |
Token | � |
Token ID | 447 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
weather | +4.672 |
ipers | +4.361 |
opp | +4.277 |
ricted | +4.041 |
itch | +4.019 |
Neg logit contributions | |
@@@@ | -10.197 |
hens | -10.079 |
ONSORED | -9.488 |
� | -9.396 |
tin | -9.334 |
Token | � |
Token ID | 247 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
hens | +0.257 |
@@@@ | +0.256 |
═ | +0.228 |
@#& | +0.226 |
hust | +0.226 |
Neg logit contributions | |
weather | -0.212 |
ipers | -0.202 |
opp | -0.195 |
rador | -0.194 |
ricted | -0.190 |
Token | s |
Token ID | 82 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
hens | +0.247 |
@@@@ | +0.243 |
tin | +0.215 |
═ | +0.215 |
hust | +0.213 |
Neg logit contributions | |
weather | -0.276 |
ipers | -0.269 |
rador | -0.261 |
opp | -0.260 |
ricted | -0.256 |
Token | Jake |
Token ID | 14757 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
hens | +0.674 |
@@@@ | +0.663 |
hust | +0.606 |
tin | +0.597 |
═ | +0.594 |
Neg logit contributions | |
weather | -0.546 |
ipers | -0.525 |
rador | -0.512 |
opp | -0.507 |
ricted | -0.494 |
Token | Od |
Token ID | 10529 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
weather | +3.028 |
ipers | +2.955 |
opp | +2.874 |
rador | +2.782 |
ocal | +2.770 |
Neg logit contributions | |
@@@@ | -3.229 |
hens | -3.177 |
� | -2.964 |
═ | -2.948 |
ONSORED | -2.842 |
Token | alone |
Token ID | 3436 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
hens | +1.348 |
@@@@ | +1.318 |
hust | +1.194 |
tin | +1.172 |
═ | +1.166 |
Neg logit contributions | |
weather | -1.443 |
ipers | -1.394 |
rador | -1.354 |
opp | -1.353 |
ricted | -1.340 |
Token | make |
Token ID | 787 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
hens | +0.823 |
@@@@ | +0.807 |
hust | +0.726 |
tin | +0.716 |
═ | +0.713 |
Neg logit contributions | |
weather | -0.912 |
ipers | -0.883 |
opp | -0.858 |
rador | -0.857 |
ricted | -0.850 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
hens | +0.396 |
@@@@ | +0.393 |
hust | +0.353 |
tin | +0.351 |
═ | +0.351 |
Neg logit contributions | |
weather | -0.350 |
ipers | -0.335 |
opp | -0.326 |
rador | -0.325 |
ricted | -0.321 |
Token | ocean |
Token ID | 9151 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
weather | +0.136 |
ipers | +0.131 |
opp | +0.128 |
rador | +0.127 |
ricted | +0.125 |
Neg logit contributions | |
hens | -0.117 |
@@@@ | -0.116 |
═ | -0.102 |
hust | -0.102 |
� | -0.102 |
Token | our |
Token ID | 674 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hens | +0.278 |
@@@@ | +0.275 |
═ | +0.248 |
� | +0.247 |
hust | +0.247 |
Neg logit contributions | |
weather | -0.217 |
ipers | -0.207 |
opp | -0.201 |
rador | -0.199 |
ricted | -0.196 |
Token | umb |
Token ID | 20810 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
weather | +0.724 |
ipers | +0.691 |
opp | +0.675 |
rador | +0.669 |
ricted | +0.657 |
Neg logit contributions | |
hens | -0.827 |
@@@@ | -0.818 |
═ | -0.733 |
� | -0.733 |
tin | -0.727 |
Token | il |
Token ID | 346 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
weather | +4.383 |
ipers | +4.105 |
rador | +3.990 |
opp | +3.919 |
esta | +3.888 |
Neg logit contributions | |
@@@@ | -10.571 |
hens | -10.460 |
� | -10.061 |
═ | -9.899 |
ONSORED | -9.872 |
Token | ical |
Token ID | 605 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
weather | +3.971 |
opp | +3.857 |
ipers | +3.840 |
ocal | +3.761 |
esta | +3.727 |
Neg logit contributions | |
hens | -3.130 |
@@@@ | -3.127 |
═ | -2.772 |
�� | -2.747 |
ONSORED | -2.729 |
Token | cord |
Token ID | 15050 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
weather | +0.470 |
ipers | +0.446 |
opp | +0.431 |
rador | +0.428 |
ricted | +0.419 |
Neg logit contributions | |
hens | -0.760 |
@@@@ | -0.753 |
═ | -0.685 |
� | -0.683 |
hust | -0.682 |
Token | to |
Token ID | 284 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
weather | +2.348 |
ipers | +2.215 |
opp | +2.156 |
rador | +2.142 |
ricted | +2.100 |
Neg logit contributions | |
hens | -3.013 |
@@@@ | -3.002 |
� | -2.727 |
ONSORED | -2.695 |
═ | -2.690 |
Token | life |
Token ID | 1204 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
hens | +0.059 |
@@@@ | +0.059 |
═ | +0.053 |
hust | +0.052 |
tin | +0.052 |
Neg logit contributions | |
weather | -0.050 |
ipers | -0.048 |
opp | -0.047 |
rador | -0.046 |
ricted | -0.046 |
Token | as |
Token ID | 355 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
weather | +0.504 |
ipers | +0.483 |
opp | +0.470 |
rador | +0.468 |
ricted | +0.462 |
Neg logit contributions | |
hens | -0.575 |
@@@@ | -0.573 |
hust | -0.510 |
tin | -0.508 |
═ | -0.507 |
Token | his |
Token ID | 465 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
weather | +0.135 |
ipers | +0.131 |
rador | +0.125 |
opp | +0.125 |
ricted | +0.123 |
Neg logit contributions | |
@@@@ | -0.157 |
hens | -0.157 |
hust | -0.141 |
tin | -0.139 |
═ | -0.139 |
Token | running |
Token ID | 2491 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
weather | +0.536 |
ipers | +0.518 |
rador | +0.496 |
ricted | +0.490 |
opp | +0.489 |
Neg logit contributions | |
@@@@ | -0.772 |
hens | -0.770 |
hust | -0.706 |
tin | -0.693 |
� | -0.685 |
Token | mate |
Token ID | 16133 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
weather | +1.370 |
ipers | +1.310 |
opp | +1.275 |
rador | +1.267 |
ricted | +1.246 |
Neg logit contributions | |
hens | -1.587 |
@@@@ | -1.573 |
═ | -1.408 |
� | -1.405 |
hust | -1.401 |
Token | after |
Token ID | 706 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
@@@@ | +3.385 |
hens | +3.375 |
hust | +3.040 |
tin | +2.984 |
═ | +2.951 |
Neg logit contributions | |
weather | -3.237 |
ipers | -3.172 |
rador | -3.092 |
ricted | -3.042 |
opp | -3.019 |
Token | Sen |
Token ID | 2311 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
hens | +1.485 |
@@@@ | +1.482 |
hust | +1.341 |
tin | +1.324 |
═ | +1.310 |
Neg logit contributions | |
weather | -1.189 |
ipers | -1.145 |
rador | -1.105 |
opp | -1.100 |
ricted | -1.085 |
Token | . |
Token ID | 13 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
weather | +5.024 |
opp | +4.757 |
ipers | +4.652 |
ored | +4.523 |
rador | +4.460 |
Neg logit contributions | |
hens | -9.051 |
@@@@ | -9.041 |
� | -8.878 |
�� | -8.855 |
═ | -8.704 |
Token | Bob |
Token ID | 5811 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
@@@@ | +0.619 |
hens | +0.613 |
tin | +0.560 |
hust | +0.558 |
� | +0.548 |
Neg logit contributions | |
weather | -0.490 |
ipers | -0.472 |
rador | -0.462 |
opp | -0.454 |
ricted | -0.448 |
Token | Corker |
Token ID | 44421 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
weather | +0.231 |
ipers | +0.220 |
opp | +0.213 |
rador | +0.213 |
ricted | +0.211 |
Neg logit contributions | |
hens | -0.302 |
@@@@ | -0.298 |
hust | -0.270 |
tin | -0.269 |
ONSORED | -0.268 |
Token | suggested |
Token ID | 5220 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
weather | +4.042 |
ipers | +3.769 |
opp | +3.714 |
rador | +3.610 |
ored | +3.600 |
Neg logit contributions | |
hens | -5.351 |
@@@@ | -5.290 |
� | -4.891 |
═ | -4.775 |
@#& | -4.747 |
Token | the |
Token ID | 262 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
hens | +0.285 |
@@@@ | +0.284 |
hust | +0.254 |
tin | +0.253 |
═ | +0.252 |
Neg logit contributions | |
weather | -0.258 |
ipers | -0.248 |
rador | -0.241 |
opp | -0.239 |
ricted | -0.237 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
weather | +0.412 |
ipers | +0.396 |
opp | +0.388 |
rador | +0.380 |
ricted | +0.374 |
Neg logit contributions | |
hens | -0.497 |
@@@@ | -0.494 |
═ | -0.441 |
tin | -0.439 |
� | -0.438 |
Token | Next |
Token ID | 7406 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
weather | +0.345 |
ipers | +0.333 |
opp | +0.324 |
rador | +0.318 |
ricted | +0.315 |
Neg logit contributions | |
hens | -0.400 |
@@@@ | -0.394 |
tin | -0.352 |
� | -0.352 |
═ | -0.350 |
Token | All |
Token ID | 1439 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
weather | +0.982 |
ipers | +0.944 |
opp | +0.924 |
rador | +0.915 |
ricted | +0.902 |
Neg logit contributions | |
hens | -0.947 |
@@@@ | -0.936 |
═ | -0.831 |
� | -0.828 |
hust | -0.823 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
hens | +1.877 |
@@@@ | +1.868 |
hust | +1.678 |
═ | +1.666 |
ONSORED | +1.655 |
Neg logit contributions | |
weather | -2.074 |
rador | -1.986 |
ipers | -1.984 |
opp | -1.940 |
ricted | -1.915 |
Token | Republican |
Token ID | 25777 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
weather | +1.635 |
ipers | +1.564 |
opp | +1.524 |
rador | +1.515 |
ricted | +1.490 |
Neg logit contributions | |
hens | -1.844 |
@@@@ | -1.826 |
═ | -1.633 |
� | -1.629 |
tin | -1.623 |
Token | Sen |
Token ID | 2311 |
Feature activation | -9.87e+00 |
Pos logit contributions | |
weather | +0.385 |
ipers | +0.368 |
opp | +0.356 |
rador | +0.355 |
ricted | +0.349 |
Neg logit contributions | |
hens | -0.483 |
@@@@ | -0.477 |
hust | -0.430 |
═ | -0.428 |
tin | -0.428 |
Token | . |
Token ID | 13 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
weather | +5.146 |
opp | +4.961 |
ipers | +4.888 |
ored | +4.684 |
rador | +4.667 |
Neg logit contributions | |
@@@@ | -9.065 |
hens | -8.881 |
� | -8.536 |
═ | -8.461 |
�� | -8.332 |
Token | Rand |
Token ID | 8790 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
hens | +0.640 |
@@@@ | +0.632 |
tin | +0.574 |
hust | +0.569 |
� | +0.563 |
Neg logit contributions | |
weather | -0.536 |
ipers | -0.515 |
rador | -0.503 |
opp | -0.497 |
ricted | -0.492 |
Token | Paul |
Token ID | 3362 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
weather | +1.493 |
ipers | +1.416 |
opp | +1.362 |
rador | +1.362 |
ricted | +1.331 |
Neg logit contributions | |
hens | -2.317 |
@@@@ | -2.294 |
═ | -2.080 |
hust | -2.077 |
tin | -2.077 |
Token | is |
Token ID | 318 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
weather | +0.097 |
ipers | +0.092 |
opp | +0.090 |
rador | +0.089 |
ricted | +0.088 |
Neg logit contributions | |
hens | -0.107 |
@@@@ | -0.106 |
═ | -0.095 |
� | -0.094 |
hust | -0.094 |
Token | " |
Token ID | 366 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
hens | +0.504 |
@@@@ | +0.497 |
hust | +0.454 |
tin | +0.448 |
═ | +0.440 |
Neg logit contributions | |
weather | -0.430 |
ipers | -0.416 |
rador | -0.402 |
opp | -0.397 |
ricted | -0.394 |
Token | coalition |
Token ID | 9906 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hens | +0.726 |
@@@@ | +0.715 |
hust | +0.640 |
═ | +0.639 |
tin | +0.637 |
Neg logit contributions | |
weather | -0.679 |
ipers | -0.650 |
opp | -0.633 |
rador | -0.628 |
ricted | -0.619 |
Token | is |
Token ID | 318 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
weather | +0.217 |
ipers | +0.208 |
opp | +0.203 |
rador | +0.202 |
ricted | +0.198 |
Neg logit contributions | |
hens | -0.226 |
@@@@ | -0.224 |
═ | -0.199 |
� | -0.199 |
hust | -0.198 |
Token | determined |
Token ID | 5295 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
hens | +0.498 |
@@@@ | +0.492 |
hust | +0.445 |
tin | +0.441 |
═ | +0.437 |
Neg logit contributions | |
weather | -0.452 |
ipers | -0.433 |
rador | -0.420 |
opp | -0.419 |
ricted | -0.414 |
Token | to |
Token ID | 284 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
hens | +2.568 |
@@@@ | +2.532 |
═ | +2.274 |
hust | +2.259 |
tin | +2.255 |
Neg logit contributions | |
weather | -2.405 |
ipers | -2.307 |
opp | -2.229 |
rador | -2.221 |
ricted | -2.202 |
Token | spike |
Token ID | 20240 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
hens | +0.157 |
@@@@ | +0.155 |
hust | +0.138 |
═ | +0.137 |
tin | +0.137 |
Neg logit contributions | |
weather | -0.173 |
ipers | -0.166 |
opp | -0.161 |
rador | -0.161 |
ricted | -0.159 |
Token | Sen |
Token ID | 2311 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
hens | +2.370 |
@@@@ | +2.327 |
hust | +2.120 |
═ | +2.096 |
ONSORED | +2.095 |
Neg logit contributions | |
weather | -2.000 |
ipers | -1.893 |
rador | -1.839 |
ricted | -1.813 |
opp | -1.808 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
weather | +5.211 |
opp | +5.054 |
ipers | +5.044 |
rador | +4.795 |
ored | +4.753 |
Neg logit contributions | |
@@@@ | -8.765 |
hens | -8.652 |
� | -8.190 |
═ | -8.108 |
@#& | -8.093 |
Token | Paul |
Token ID | 3362 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
hens | +0.736 |
@@@@ | +0.721 |
tin | +0.654 |
hust | +0.649 |
ONSORED | +0.641 |
Neg logit contributions | |
weather | -0.672 |
ipers | -0.645 |
rador | -0.628 |
opp | -0.622 |
ricted | -0.616 |
Token | � |
Token ID | 447 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
weather | +0.020 |
ipers | +0.019 |
opp | +0.018 |
rador | +0.018 |
ricted | +0.018 |
Neg logit contributions | |
hens | -0.027 |
@@@@ | -0.027 |
═ | -0.024 |
� | -0.024 |
tin | -0.024 |
Token | � |
Token ID | 247 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
hens | +0.141 |
@@@@ | +0.140 |
═ | +0.125 |
tin | +0.124 |
� | +0.124 |
Neg logit contributions | |
weather | -0.118 |
ipers | -0.113 |
opp | -0.108 |
rador | -0.107 |
ricted | -0.106 |
Token | s |
Token ID | 82 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hens | +0.376 |
@@@@ | +0.368 |
tin | +0.328 |
═ | +0.327 |
� | +0.324 |
Neg logit contributions | |
weather | -0.408 |
ipers | -0.394 |
opp | -0.381 |
rador | -0.381 |
ricted | -0.378 |
Token | prices |
Token ID | 4536 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
hens | +0.519 |
@@@@ | +0.512 |
═ | +0.458 |
hust | +0.458 |
tin | +0.456 |
Neg logit contributions | |
weather | -0.478 |
ipers | -0.461 |
opp | -0.446 |
rador | -0.445 |
ricted | -0.440 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
hens | +0.418 |
@@@@ | +0.412 |
═ | +0.369 |
hust | +0.367 |
� | +0.366 |
Neg logit contributions | |
weather | -0.389 |
ipers | -0.374 |
opp | -0.363 |
rador | -0.362 |
ricted | -0.357 |
Token |
|
Token ID | 198 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
weather | +0.188 |
ipers | +0.181 |
rador | +0.175 |
opp | +0.175 |
ricted | +0.172 |
Neg logit contributions | |
hens | -0.243 |
@@@@ | -0.241 |
═ | -0.217 |
� | -0.216 |
tin | -0.216 |
Token | By |
Token ID | 3886 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
weather | +0.040 |
ipers | +0.039 |
rador | +0.037 |
opp | +0.037 |
ricted | +0.037 |
Neg logit contributions | |
hens | -0.045 |
@@@@ | -0.044 |
tin | -0.039 |
� | -0.039 |
═ | -0.039 |
Token | : |
Token ID | 25 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
weather | +0.135 |
ipers | +0.131 |
opp | +0.127 |
rador | +0.126 |
ricted | +0.124 |
Neg logit contributions | |
hens | -0.152 |
@@@@ | -0.151 |
hust | -0.135 |
tin | -0.134 |
═ | -0.134 |
Token | Sen |
Token ID | 2311 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
hens | +1.602 |
@@@@ | +1.582 |
hust | +1.421 |
tin | +1.412 |
═ | +1.400 |
Neg logit contributions | |
weather | -1.418 |
ipers | -1.371 |
rador | -1.326 |
opp | -1.324 |
ricted | -1.296 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
weather | +5.717 |
opp | +5.461 |
ipers | +5.438 |
rador | +5.301 |
ored | +5.280 |
Neg logit contributions | |
@@@@ | -8.235 |
hens | -8.202 |
═ | -7.689 |
� | -7.648 |
@#& | -7.589 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
hens | +0.734 |
@@@@ | +0.728 |
tin | +0.656 |
hust | +0.650 |
ONSORED | +0.646 |
Neg logit contributions | |
weather | -0.641 |
ipers | -0.615 |
rador | -0.602 |
opp | -0.594 |
ricted | -0.589 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
weather | +2.417 |
ipers | +2.233 |
opp | +2.169 |
rador | +2.092 |
ricted | +2.036 |
Neg logit contributions | |
hens | -5.716 |
@@@@ | -5.672 |
═ | -5.275 |
� | -5.265 |
�� | -5.233 |
Token |
|
Token ID | 198 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
weather | +1.440 |
ipers | +1.367 |
opp | +1.338 |
rador | +1.322 |
ricted | +1.300 |
Neg logit contributions | |
hens | -1.793 |
@@@@ | -1.776 |
═ | -1.601 |
� | -1.597 |
tin | -1.587 |
Token |
|
Token ID | 198 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
hens | +0.400 |
@@@@ | +0.396 |
tin | +0.355 |
═ | +0.352 |
hust | +0.352 |
Neg logit contributions | |
weather | -0.320 |
ipers | -0.309 |
rador | -0.300 |
opp | -0.296 |
ricted | -0.292 |
Token | < |
Token ID | 1279 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
weather | +2.914 |
ipers | +2.719 |
opp | +2.668 |
rador | +2.586 |
ocal | +2.565 |
Neg logit contributions | |
hens | -3.984 |
@@@@ | -3.904 |
� | -3.564 |
hust | -3.558 |
@#& | -3.527 |
Token | ul |
Token ID | 377 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
weather | +3.399 |
opp | +3.192 |
ipers | +3.175 |
rador | +3.048 |
ricted | +3.041 |
Neg logit contributions | |
hens | -4.010 |
@@@@ | -3.988 |
� | -3.634 |
�� | -3.609 |
ONSORED | -3.602 |
Token | > |
Token ID | 29 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
weather | +2.579 |
ipers | +2.420 |
opp | +2.356 |
rador | +2.329 |
ocal | +2.269 |
Neg logit contributions | |
hens | -5.151 |
@@@@ | -5.104 |
� | -4.706 |
═ | -4.693 |
ONSORED | -4.682 |
Token | < |
Token ID | 1279 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
weather | +2.520 |
ipers | +2.366 |
opp | +2.313 |
rador | +2.259 |
ocal | +2.231 |
Neg logit contributions | |
hens | -3.390 |
@@@@ | -3.337 |
� | -3.033 |
hust | -3.017 |
═ | -3.009 |
Token | li |
Token ID | 4528 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
weather | +3.121 |
opp | +2.945 |
ipers | +2.944 |
rador | +2.805 |
ricted | +2.795 |
Neg logit contributions | |
hens | -4.056 |
@@@@ | -4.045 |
� | -3.701 |
═ | -3.674 |
hust | -3.657 |
Token | ng |
Token ID | 23370 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
weather | +3.619 |
opp | +3.251 |
ipers | +3.247 |
rador | +3.196 |
ocal | +3.155 |
Neg logit contributions | |
hens | -7.792 |
@@@@ | -7.645 |
� | -7.192 |
tin | -7.120 |
ONSORED | -7.107 |
Token | - |
Token ID | 12 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
weather | +4.871 |
ipers | +4.341 |
opp | +4.324 |
ored | +4.177 |
rador | +4.149 |
Neg logit contributions | |
hens | -9.251 |
@@@@ | -9.044 |
�� | -8.673 |
� | -8.599 |
═ | -8.502 |
Token | repeat |
Token ID | 44754 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
weather | +0.762 |
ipers | +0.720 |
opp | +0.696 |
rador | +0.690 |
ricted | +0.676 |
Neg logit contributions | |
hens | -1.303 |
@@@@ | -1.292 |
═ | -1.178 |
� | -1.176 |
hust | -1.172 |
Token | =" |
Token ID | 2625 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
weather | +0.517 |
ipers | +0.490 |
opp | +0.475 |
rador | +0.471 |
ricted | +0.462 |
Neg logit contributions | |
hens | -0.776 |
@@@@ | -0.769 |
═ | -0.698 |
� | -0.697 |
hust | -0.694 |
Token | phone |
Token ID | 4862 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
weather | +2.033 |
ipers | +1.926 |
opp | +1.898 |
rador | +1.867 |
ricted | +1.833 |
Neg logit contributions | |
hens | -2.042 |
@@@@ | -2.008 |
� | -1.794 |
═ | -1.792 |
hust | -1.783 |
Token | in |
Token ID | 287 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
weather | +0.543 |
ipers | +0.517 |
opp | +0.502 |
rador | +0.498 |
ricted | +0.490 |
Neg logit contributions | |
hens | -0.749 |
@@@@ | -0.744 |
═ | -0.672 |
� | -0.670 |
hust | -0.668 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
hens | +0.370 |
@@@@ | +0.367 |
hust | +0.330 |
═ | +0.329 |
tin | +0.328 |
Neg logit contributions | |
weather | -0.310 |
ipers | -0.298 |
opp | -0.288 |
rador | -0.287 |
ricted | -0.283 |
Token | point |
Token ID | 966 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
hens | +0.166 |
@@@@ | +0.165 |
hust | +0.148 |
═ | +0.147 |
tin | +0.146 |
Neg logit contributions | |
weather | -0.151 |
ipers | -0.146 |
rador | -0.141 |
opp | -0.141 |
ricted | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
weather | +0.792 |
ipers | +0.755 |
opp | +0.737 |
rador | +0.729 |
ricted | +0.718 |
Neg logit contributions | |
hens | -0.952 |
@@@@ | -0.944 |
═ | -0.847 |
� | -0.847 |
ONSORED | -0.840 |
Token | I |
Token ID | 314 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
weather | +0.081 |
ipers | +0.078 |
opp | +0.076 |
rador | +0.076 |
ricted | +0.074 |
Neg logit contributions | |
hens | -0.074 |
@@@@ | -0.073 |
═ | -0.065 |
� | -0.064 |
tin | -0.064 |
Token | admire |
Token ID | 21099 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
hens | +0.240 |
@@@@ | +0.237 |
═ | +0.211 |
hust | +0.210 |
� | +0.209 |
Neg logit contributions | |
weather | -0.256 |
ipers | -0.247 |
opp | -0.239 |
rador | -0.239 |
ricted | -0.235 |
Token | Sen |
Token ID | 2311 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
weather | +1.567 |
ipers | +1.488 |
opp | +1.448 |
rador | +1.434 |
ricted | +1.408 |
Neg logit contributions | |
hens | -2.217 |
@@@@ | -2.196 |
═ | -1.989 |
� | -1.985 |
hust | -1.975 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
weather | +5.431 |
ipers | +5.204 |
opp | +5.197 |
ored | +4.936 |
rador | +4.930 |
Neg logit contributions | |
hens | -8.351 |
@@@@ | -8.332 |
@#& | -7.678 |
ONSORED | -7.676 |
� | -7.652 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
hens | +0.519 |
@@@@ | +0.515 |
tin | +0.473 |
hust | +0.469 |
═ | +0.468 |
Neg logit contributions | |
weather | -0.258 |
ipers | -0.245 |
rador | -0.236 |
ricted | -0.230 |
opp | -0.230 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
weather | +2.525 |
ipers | +2.382 |
opp | +2.350 |
rador | +2.315 |
ricted | +2.265 |
Neg logit contributions | |
hens | -3.041 |
@@@@ | -3.015 |
� | -2.713 |
═ | -2.702 |
ONSORED | -2.701 |
Token | his |
Token ID | 465 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
weather | +0.080 |
ipers | +0.077 |
opp | +0.074 |
rador | +0.074 |
ricted | +0.073 |
Neg logit contributions | |
hens | -0.074 |
@@@@ | -0.074 |
═ | -0.065 |
hust | -0.065 |
� | -0.065 |
Token | accomplishments |
Token ID | 26516 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
weather | +0.508 |
ipers | +0.486 |
opp | +0.471 |
rador | +0.469 |
ricted | +0.463 |
Neg logit contributions | |
hens | -0.593 |
@@@@ | -0.587 |
hust | -0.526 |
═ | -0.526 |
� | -0.526 |
Token | : |
Token ID | 25 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
weather | +0.246 |
ipers | +0.235 |
opp | +0.229 |
rador | +0.228 |
ricted | +0.224 |
Neg logit contributions | |
hens | -0.300 |
@@@@ | -0.297 |
═ | -0.267 |
hust | -0.266 |
tin | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hens | +0.593 |
@@@@ | +0.588 |
═ | +0.530 |
� | +0.528 |
hust | +0.527 |
Neg logit contributions | |
weather | -0.449 |
ipers | -0.427 |
opp | -0.416 |
rador | -0.413 |
ricted | -0.407 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weather | +0.786 |
ipers | +0.747 |
opp | +0.727 |
rador | +0.719 |
ricted | +0.707 |
Neg logit contributions | |
hens | -1.086 |
@@@@ | -1.076 |
� | -0.974 |
═ | -0.974 |
hust | -0.967 |
Token | < |
Token ID | 27 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
weather | +0.866 |
ipers | +0.827 |
opp | +0.807 |
rador | +0.800 |
ricted | +0.787 |
Neg logit contributions | |
hens | -0.994 |
@@@@ | -0.984 |
═ | -0.882 |
� | -0.880 |
hust | -0.876 |
Token | body |
Token ID | 2618 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
weather | +4.367 |
opp | +4.128 |
ipers | +4.067 |
liction | +3.907 |
ricted | +3.905 |
Neg logit contributions | |
hens | -4.968 |
@@@@ | -4.941 |
� | -4.531 |
ONSORED | -4.467 |
�� | -4.467 |
Token | ng |
Token ID | 23370 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
weather | +2.661 |
ipers | +2.449 |
opp | +2.402 |
rador | +2.374 |
ricted | +2.324 |
Neg logit contributions | |
hens | -5.365 |
@@@@ | -5.310 |
� | -4.910 |
ONSORED | -4.889 |
═ | -4.884 |
Token | - |
Token ID | 12 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
weather | +4.790 |
ipers | +4.325 |
opp | +4.284 |
ored | +4.140 |
ocal | +4.108 |
Neg logit contributions | |
hens | -9.137 |
@@@@ | -9.047 |
�� | -8.847 |
� | -8.771 |
warr | -8.545 |
Token | controller |
Token ID | 36500 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
weather | +0.604 |
ipers | +0.567 |
opp | +0.546 |
rador | +0.541 |
ricted | +0.528 |
Neg logit contributions | |
hens | -1.220 |
@@@@ | -1.210 |
═ | -1.110 |
� | -1.106 |
tin | -1.104 |
Token | =" |
Token ID | 2625 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
weather | +1.258 |
ipers | +1.195 |
opp | +1.161 |
rador | +1.154 |
ricted | +1.125 |
Neg logit contributions | |
hens | -2.089 |
@@@@ | -2.063 |
� | -1.886 |
tin | -1.886 |
═ | -1.879 |
Token | Phone |
Token ID | 6132 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
weather | +1.444 |
ipers | +1.366 |
opp | +1.335 |
rador | +1.314 |
ricted | +1.291 |
Neg logit contributions | |
hens | -1.919 |
@@@@ | -1.899 |
═ | -1.717 |
� | -1.715 |
hust | -1.711 |
Token | List |
Token ID | 8053 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
hens | +0.215 |
@@@@ | +0.214 |
═ | +0.193 |
� | +0.191 |
hust | +0.191 |
Neg logit contributions | |
weather | -0.171 |
ipers | -0.163 |
opp | -0.159 |
rador | -0.158 |
ricted | -0.155 |
Token | kson |
Token ID | 46505 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
weather | +0.251 |
ipers | +0.237 |
rador | +0.229 |
opp | +0.229 |
ricted | +0.224 |
Neg logit contributions | |
hens | -0.448 |
@@@@ | -0.442 |
tin | -0.404 |
═ | -0.403 |
hust | -0.400 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
hens | +0.247 |
@@@@ | +0.243 |
hust | +0.218 |
═ | +0.218 |
tin | +0.217 |
Neg logit contributions | |
weather | -0.217 |
ipers | -0.209 |
opp | -0.203 |
rador | -0.202 |
ricted | -0.199 |
Token | a |
Token ID | 257 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
hens | +0.946 |
@@@@ | +0.935 |
hust | +0.838 |
═ | +0.835 |
tin | +0.833 |
Neg logit contributions | |
weather | -0.812 |
ipers | -0.780 |
opp | -0.755 |
rador | -0.750 |
ricted | -0.743 |
Token | professor |
Token ID | 6240 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
hens | +0.408 |
@@@@ | +0.401 |
hust | +0.359 |
tin | +0.357 |
═ | +0.356 |
Neg logit contributions | |
weather | -0.416 |
ipers | -0.400 |
opp | -0.390 |
rador | -0.387 |
ricted | -0.383 |
Token | of |
Token ID | 286 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
hens | +1.155 |
@@@@ | +1.143 |
hust | +1.018 |
tin | +1.016 |
═ | +1.013 |
Neg logit contributions | |
weather | -1.106 |
ipers | -1.067 |
opp | -1.038 |
rador | -1.032 |
ricted | -1.009 |
Token | biological |
Token ID | 10685 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
hens | +0.584 |
@@@@ | +0.568 |
hust | +0.515 |
tin | +0.509 |
@#& | +0.506 |
Neg logit contributions | |
weather | -0.576 |
ipers | -0.552 |
opp | -0.540 |
rador | -0.535 |
ricted | -0.530 |
Token | science |
Token ID | 3783 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
hens | +3.835 |
@@@@ | +3.649 |
hust | +3.384 |
tin | +3.363 |
═ | +3.282 |
Neg logit contributions | |
weather | -4.744 |
ipers | -4.503 |
Downloadha | -4.439 |
rador | -4.434 |
opp | -4.427 |
Token | at |
Token ID | 379 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
hens | +1.967 |
@@@@ | +1.928 |
hust | +1.725 |
tin | +1.716 |
═ | +1.698 |
Neg logit contributions | |
weather | -2.100 |
ipers | -2.024 |
opp | -1.962 |
rador | -1.958 |
ricted | -1.929 |
Token | Florida |
Token ID | 4744 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
hens | +2.392 |
@@@@ | +2.312 |
tin | +2.066 |
hust | +2.054 |
@#& | +2.046 |
Neg logit contributions | |
weather | -2.294 |
ipers | -2.213 |
opp | -2.172 |
rador | -2.170 |
ricted | -2.130 |
Token | State |
Token ID | 1812 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
weather | +1.858 |
ipers | +1.783 |
opp | +1.736 |
rador | +1.712 |
ricted | +1.698 |
Neg logit contributions | |
hens | -1.781 |
@@@@ | -1.771 |
═ | -1.576 |
� | -1.576 |
ONSORED | -1.562 |
Token | University |
Token ID | 2059 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
weather | +1.115 |
ipers | +1.071 |
opp | +1.046 |
rador | +1.036 |
ricted | +1.024 |
Neg logit contributions | |
hens | -1.020 |
@@@@ | -1.012 |
� | -0.894 |
═ | -0.893 |
hust | -0.884 |
Token | official |
Token ID | 1743 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
weather | +1.405 |
ipers | +1.343 |
opp | +1.315 |
rador | +1.306 |
ricted | +1.286 |
Neg logit contributions | |
hens | -1.459 |
@@@@ | -1.445 |
═ | -1.291 |
� | -1.283 |
tin | -1.278 |
Token | languages |
Token ID | 8950 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
hens | +2.329 |
@@@@ | +2.293 |
� | +2.082 |
hust | +2.078 |
═ | +2.054 |
Neg logit contributions | |
weather | -1.746 |
ipers | -1.670 |
opp | -1.623 |
rador | -1.610 |
ricted | -1.584 |
Token | and |
Token ID | 290 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
hens | +1.969 |
@@@@ | +1.932 |
hust | +1.746 |
═ | +1.725 |
tin | +1.719 |
Neg logit contributions | |
weather | -1.737 |
ipers | -1.681 |
rador | -1.635 |
opp | -1.611 |
ricted | -1.589 |
Token | understand |
Token ID | 1833 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
weather | +0.607 |
ipers | +0.582 |
opp | +0.567 |
rador | +0.564 |
ricted | +0.555 |
Neg logit contributions | |
hens | -0.632 |
@@@@ | -0.624 |
═ | -0.556 |
� | -0.555 |
hust | -0.553 |
Token | both |
Token ID | 1111 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
weather | +0.210 |
ipers | +0.201 |
opp | +0.194 |
rador | +0.193 |
ricted | +0.190 |
Neg logit contributions | |
hens | -0.261 |
@@@@ | -0.258 |
hust | -0.232 |
� | -0.232 |
═ | -0.232 |
Token | French |
Token ID | 4141 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
weather | +1.219 |
ipers | +1.166 |
opp | +1.141 |
rador | +1.131 |
ricted | +1.114 |
Neg logit contributions | |
hens | -1.320 |
@@@@ | -1.307 |
═ | -1.168 |
� | -1.164 |
tin | -1.158 |
Token | and |
Token ID | 290 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
hens | +3.911 |
@@@@ | +3.837 |
� | +3.455 |
═ | +3.419 |
hust | +3.368 |
Neg logit contributions | |
weather | -4.212 |
ipers | -4.100 |
rador | -4.001 |
ricted | -3.965 |
Downloadha | -3.932 |
Token | English |
Token ID | 3594 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
weather | +0.612 |
ipers | +0.585 |
opp | +0.568 |
rador | +0.563 |
ricted | +0.554 |
Neg logit contributions | |
hens | -0.717 |
@@@@ | -0.706 |
� | -0.635 |
hust | -0.633 |
═ | -0.633 |
Token | without |
Token ID | 1231 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hens | +0.923 |
@@@@ | +0.911 |
═ | +0.820 |
� | +0.820 |
hust | +0.817 |
Neg logit contributions | |
weather | -0.761 |
ipers | -0.730 |
opp | -0.705 |
rador | -0.704 |
ricted | -0.691 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
weather | +0.738 |
ipers | +0.700 |
opp | +0.679 |
rador | +0.676 |
ricted | +0.665 |
Neg logit contributions | |
hens | -0.933 |
@@@@ | -0.924 |
hust | -0.834 |
═ | -0.832 |
� | -0.832 |
Token | help |
Token ID | 1037 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
weather | +0.170 |
ipers | +0.163 |
rador | +0.158 |
opp | +0.158 |
ricted | +0.156 |
Neg logit contributions | |
hens | -0.149 |
@@@@ | -0.147 |
hust | -0.130 |
� | -0.130 |
═ | -0.129 |
Token | ton |
Token ID | 5680 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
weather | +0.214 |
ipers | +0.205 |
opp | +0.198 |
rador | +0.197 |
ricted | +0.193 |
Neg logit contributions | |
hens | -0.258 |
@@@@ | -0.255 |
═ | -0.229 |
hust | -0.229 |
� | -0.229 |
Token | of |
Token ID | 286 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
hens | +1.888 |
@@@@ | +1.866 |
═ | +1.681 |
� | +1.672 |
tin | +1.671 |
Neg logit contributions | |
weather | -1.646 |
ipers | -1.585 |
rador | -1.536 |
opp | -1.531 |
ricted | -1.489 |
Token | great |
Token ID | 1049 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
hens | +0.384 |
@@@@ | +0.380 |
hust | +0.340 |
═ | +0.339 |
tin | +0.338 |
Neg logit contributions | |
weather | -0.360 |
ipers | -0.345 |
opp | -0.335 |
rador | -0.335 |
ricted | -0.328 |
Token | � |
Token ID | 564 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
hens | +0.203 |
@@@@ | +0.201 |
═ | +0.179 |
hust | +0.179 |
tin | +0.178 |
Neg logit contributions | |
weather | -0.196 |
ipers | -0.188 |
opp | -0.183 |
rador | -0.182 |
ricted | -0.179 |
Token | � |
Token ID | 247 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
@@@@ | +0.438 |
hens | +0.438 |
═ | +0.391 |
� | +0.386 |
@#& | +0.386 |
Neg logit contributions | |
weather | -0.364 |
ipers | -0.346 |
opp | -0.334 |
rador | -0.333 |
ricted | -0.325 |
Token | jack |
Token ID | 19650 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
hens | +0.393 |
@@@@ | +0.388 |
tin | +0.349 |
═ | +0.347 |
hust | +0.345 |
Neg logit contributions | |
weather | -0.340 |
ipers | -0.329 |
rador | -0.320 |
opp | -0.316 |
ricted | -0.315 |
Token | marsh |
Token ID | 22397 |
Feature activation | +9.29e+00 |
Pos logit contributions | |
hens | +4.422 |
@@@@ | +4.331 |
hust | +3.947 |
═ | +3.893 |
tin | +3.878 |
Neg logit contributions | |
weather | -4.950 |
ipers | -4.833 |
opp | -4.746 |
ricted | -4.734 |
rador | -4.643 |
Token | als |
Token ID | 874 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
hens | +4.640 |
@@@@ | +4.245 |
tin | +3.832 |
@#& | +3.776 |
hust | +3.752 |
Neg logit contributions | |
weather | -8.279 |
ipers | -8.046 |
Downloadha | -7.965 |
rador | -7.912 |
ricted | -7.885 |
Token | available |
Token ID | 1695 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
hens | +1.348 |
@@@@ | +1.327 |
═ | +1.190 |
hust | +1.188 |
tin | +1.184 |
Neg logit contributions | |
weather | -1.314 |
ipers | -1.263 |
rador | -1.232 |
opp | -1.225 |
ricted | -1.203 |
Token | to |
Token ID | 284 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
hens | +3.933 |
@@@@ | +3.863 |
═ | +3.506 |
hust | +3.462 |
tin | +3.462 |
Neg logit contributions | |
weather | -3.754 |
ipers | -3.652 |
rador | -3.562 |
opp | -3.494 |
Downloadha | -3.469 |
Token | them |
Token ID | 606 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
hens | +0.067 |
@@@@ | +0.067 |
hust | +0.059 |
═ | +0.059 |
tin | +0.059 |
Neg logit contributions | |
weather | -0.063 |
ipers | -0.061 |
rador | -0.059 |
opp | -0.059 |
ricted | -0.058 |
Token | will |
Token ID | 481 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
hens | +3.298 |
@@@@ | +3.194 |
tin | +2.914 |
hust | +2.893 |
═ | +2.867 |
Neg logit contributions | |
weather | -3.507 |
ipers | -3.402 |
opp | -3.258 |
Downloadha | -3.251 |
rador | -3.250 |
Token | act |
Token ID | 719 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
hens | +0.459 |
@@@@ | +0.452 |
hust | +0.397 |
═ | +0.397 |
tin | +0.396 |
Neg logit contributions | |
weather | -0.538 |
ipers | -0.517 |
opp | -0.505 |
rador | -0.503 |
ricted | -0.496 |
Token | more |
Token ID | 517 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
hens | +0.156 |
@@@@ | +0.154 |
═ | +0.140 |
hust | +0.139 |
� | +0.139 |
Neg logit contributions | |
weather | -0.120 |
ipers | -0.115 |
rador | -0.111 |
opp | -0.111 |
ricted | -0.109 |
Token | like |
Token ID | 588 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
hens | +0.533 |
@@@@ | +0.519 |
hust | +0.478 |
═ | +0.470 |
tin | +0.469 |
Neg logit contributions | |
weather | -0.417 |
ipers | -0.398 |
opp | -0.384 |
rador | -0.383 |
ricted | -0.375 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
weather | +1.400 |
ipers | +1.338 |
opp | +1.303 |
rador | +1.292 |
ricted | +1.269 |
Neg logit contributions | |
hens | -1.738 |
@@@@ | -1.723 |
═ | -1.550 |
� | -1.548 |
ONSORED | -1.536 |
Token | nut |
Token ID | 6701 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
weather | +0.099 |
ipers | +0.094 |
opp | +0.092 |
rador | +0.092 |
ricted | +0.090 |
Neg logit contributions | |
hens | -0.101 |
@@@@ | -0.100 |
hust | -0.089 |
═ | -0.089 |
tin | -0.089 |
Token | flour |
Token ID | 10601 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
hens | +3.759 |
@@@@ | +3.676 |
tin | +3.376 |
hust | +3.345 |
═ | +3.287 |
Neg logit contributions | |
weather | -3.546 |
ipers | -3.429 |
opp | -3.298 |
rador | -3.258 |
Downloadha | -3.228 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
weather | +0.677 |
ipers | +0.645 |
opp | +0.630 |
rador | +0.625 |
ricted | +0.614 |
Neg logit contributions | |
hens | -0.804 |
@@@@ | -0.796 |
═ | -0.715 |
� | -0.714 |
ONSORED | -0.709 |
Token | but |
Token ID | 475 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
weather | +0.155 |
ipers | +0.149 |
opp | +0.145 |
rador | +0.144 |
ricted | +0.142 |
Neg logit contributions | |
hens | -0.155 |
@@@@ | -0.153 |
═ | -0.136 |
hust | -0.136 |
tin | -0.136 |
Token | you |
Token ID | 345 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
hens | +3.210 |
@@@@ | +3.110 |
hust | +2.916 |
tin | +2.862 |
═ | +2.825 |
Neg logit contributions | |
weather | -3.060 |
ipers | -2.949 |
opp | -2.851 |
rador | -2.839 |
ricted | -2.814 |
Token | can |
Token ID | 460 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
hens | +0.510 |
@@@@ | +0.502 |
═ | +0.448 |
� | +0.445 |
hust | +0.444 |
Neg logit contributions | |
weather | -0.534 |
ipers | -0.517 |
opp | -0.501 |
rador | -0.500 |
ricted | -0.492 |
Token | and |
Token ID | 290 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
hens | +0.224 |
@@@@ | +0.221 |
═ | +0.197 |
hust | +0.197 |
tin | +0.196 |
Neg logit contributions | |
weather | -0.219 |
ipers | -0.211 |
opp | -0.206 |
rador | -0.205 |
ricted | -0.202 |
Token | his |
Token ID | 465 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
hens | +0.568 |
@@@@ | +0.557 |
hust | +0.501 |
tin | +0.499 |
═ | +0.496 |
Neg logit contributions | |
weather | -0.533 |
ipers | -0.513 |
opp | -0.498 |
rador | -0.493 |
ricted | -0.488 |
Token | Assistant |
Token ID | 15286 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
weather | +0.254 |
ipers | +0.243 |
opp | +0.237 |
rador | +0.234 |
ricted | +0.232 |
Neg logit contributions | |
hens | -0.302 |
@@@@ | -0.298 |
hust | -0.268 |
═ | -0.267 |
tin | -0.266 |
Token | Commissioner |
Token ID | 13270 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
hens | +2.052 |
@@@@ | +2.002 |
tin | +1.797 |
hust | +1.795 |
═ | +1.771 |
Neg logit contributions | |
weather | -1.992 |
ipers | -1.939 |
opp | -1.888 |
rador | -1.846 |
Downloadha | -1.825 |
Token | Kim |
Token ID | 6502 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
hens | +0.292 |
@@@@ | +0.289 |
hust | +0.258 |
tin | +0.258 |
═ | +0.257 |
Neg logit contributions | |
weather | -0.258 |
ipers | -0.248 |
opp | -0.241 |
rador | -0.240 |
ricted | -0.235 |
Token | Bond |
Token ID | 12812 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
hens | +1.333 |
@@@@ | +1.303 |
tin | +1.170 |
hust | +1.163 |
@#& | +1.154 |
Neg logit contributions | |
weather | -1.217 |
ipers | -1.170 |
rador | -1.138 |
opp | -1.134 |
ricted | -1.116 |
Token | e |
Token ID | 68 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
hens | +3.881 |
@@@@ | +3.733 |
tin | +3.411 |
hust | +3.383 |
═ | +3.372 |
Neg logit contributions | |
weather | -3.473 |
ipers | -3.429 |
Downloadha | -3.291 |
opp | -3.275 |
rador | -3.263 |
Token | attended |
Token ID | 9141 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
weather | +1.429 |
ipers | +1.363 |
opp | +1.333 |
rador | +1.322 |
ricted | +1.301 |
Neg logit contributions | |
hens | -1.497 |
@@@@ | -1.487 |
═ | -1.324 |
� | -1.324 |
ONSORED | -1.313 |
Token | one |
Token ID | 530 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
hens | +0.234 |
@@@@ | +0.229 |
hust | +0.207 |
tin | +0.206 |
═ | +0.206 |
Neg logit contributions | |
weather | -0.194 |
ipers | -0.186 |
opp | -0.181 |
rador | -0.179 |
ricted | -0.176 |
Token | of |
Token ID | 286 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
hens | +1.866 |
@@@@ | +1.847 |
hust | +1.664 |
tin | +1.647 |
@#& | +1.637 |
Neg logit contributions | |
weather | -1.700 |
ipers | -1.645 |
opp | -1.594 |
rador | -1.564 |
Downloadha | -1.556 |
Token | my |
Token ID | 616 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
hens | +1.437 |
@@@@ | +1.412 |
hust | +1.284 |
tin | +1.273 |
═ | +1.271 |
Neg logit contributions | |
weather | -1.179 |
ipers | -1.151 |
opp | -1.110 |
rador | -1.093 |
ricted | -1.075 |
Token | Patriots |
Token ID | 13104 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
weather | +2.865 |
ipers | +2.725 |
opp | +2.658 |
rador | +2.626 |
ricted | +2.586 |
Neg logit contributions | |
hens | -3.743 |
@@@@ | -3.717 |
� | -3.356 |
═ | -3.349 |
tin | -3.330 |
Token | : |
Token ID | 25 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
weather | +1.980 |
ipers | +1.875 |
opp | +1.815 |
rador | +1.786 |
ricted | +1.768 |
Neg logit contributions | |
hens | -3.337 |
@@@@ | -3.292 |
� | -3.006 |
tin | -3.005 |
@#& | -2.992 |
Token | QB |
Token ID | 16135 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
hens | +1.220 |
@@@@ | +1.206 |
tin | +1.060 |
hust | +1.060 |
═ | +1.053 |
Neg logit contributions | |
weather | -1.315 |
ipers | -1.267 |
rador | -1.238 |
opp | -1.227 |
ricted | -1.206 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
weather | +1.255 |
ipers | +1.189 |
opp | +1.160 |
rador | +1.142 |
ricted | +1.122 |
Neg logit contributions | |
hens | -1.871 |
@@@@ | -1.852 |
═ | -1.684 |
� | -1.680 |
tin | -1.669 |
Token | Brady |
Token ID | 15260 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
weather | +3.269 |
ipers | +3.088 |
opp | +3.057 |
rador | +2.990 |
ricted | +2.930 |
Neg logit contributions | |
hens | -4.085 |
@@@@ | -4.061 |
═ | -3.695 |
� | -3.689 |
tin | -3.626 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
weather | +0.298 |
ipers | +0.284 |
opp | +0.276 |
rador | +0.274 |
ricted | +0.269 |
Neg logit contributions | |
hens | -0.394 |
@@@@ | -0.390 |
═ | -0.352 |
� | -0.352 |
tin | -0.350 |
Token |
|
Token ID | 198 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
hens | +0.234 |
@@@@ | +0.231 |
tin | +0.207 |
═ | +0.207 |
hust | +0.206 |
Neg logit contributions | |
weather | -0.181 |
ipers | -0.174 |
rador | -0.168 |
opp | -0.168 |
ricted | -0.164 |
Token | Contract |
Token ID | 45845 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hens | +0.072 |
@@@@ | +0.072 |
═ | +0.064 |
� | +0.064 |
tin | +0.064 |
Neg logit contributions | |
weather | -0.052 |
ipers | -0.050 |
rador | -0.048 |
opp | -0.048 |
ricted | -0.047 |
Token | : |
Token ID | 25 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
weather | +0.743 |
ipers | +0.702 |
opp | +0.682 |
rador | +0.676 |
ricted | +0.663 |
Neg logit contributions | |
hens | -1.163 |
@@@@ | -1.153 |
� | -1.049 |
═ | -1.048 |
hust | -1.042 |
Token | A |
Token ID | 317 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
hens | +0.602 |
@@@@ | +0.593 |
═ | +0.523 |
tin | +0.520 |
hust | +0.517 |
Neg logit contributions | |
weather | -0.683 |
ipers | -0.659 |
opp | -0.642 |
rador | -0.641 |
ricted | -0.624 |
Token | two |
Token ID | 734 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
hens | +0.848 |
@@@@ | +0.839 |
hust | +0.753 |
═ | +0.750 |
tin | +0.748 |
Neg logit contributions | |
weather | -0.751 |
ipers | -0.721 |
opp | -0.700 |
rador | -0.697 |
Downloadha | -0.676 |
Token | Berlin |
Token ID | 11307 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
hens | +0.195 |
@@@@ | +0.191 |
hust | +0.169 |
tin | +0.168 |
═ | +0.168 |
Neg logit contributions | |
weather | -0.204 |
ipers | -0.195 |
opp | -0.190 |
rador | -0.190 |
ricted | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
weather | +0.057 |
ipers | +0.054 |
opp | +0.053 |
rador | +0.052 |
ricted | +0.052 |
Neg logit contributions | |
hens | -0.073 |
@@@@ | -0.072 |
═ | -0.065 |
hust | -0.065 |
tin | -0.064 |
Token | where |
Token ID | 810 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
weather | +0.039 |
ipers | +0.038 |
opp | +0.037 |
rador | +0.036 |
ricted | +0.036 |
Neg logit contributions | |
hens | -0.045 |
@@@@ | -0.045 |
═ | -0.040 |
� | -0.040 |
tin | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
hens | +1.118 |
@@@@ | +1.097 |
hust | +0.985 |
tin | +0.972 |
═ | +0.972 |
Neg logit contributions | |
weather | -1.113 |
ipers | -1.067 |
rador | -1.034 |
opp | -1.027 |
ricted | -1.020 |
Token | report |
Token ID | 989 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
weather | +0.392 |
ipers | +0.376 |
opp | +0.367 |
rador | +0.365 |
ricted | +0.360 |
Neg logit contributions | |
hens | -0.379 |
@@@@ | -0.373 |
hust | -0.331 |
═ | -0.331 |
tin | -0.329 |
Token | was |
Token ID | 373 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
weather | +0.940 |
ipers | +0.901 |
opp | +0.880 |
rador | +0.876 |
ricted | +0.860 |
Neg logit contributions | |
hens | -0.967 |
@@@@ | -0.958 |
═ | -0.854 |
� | -0.853 |
tin | -0.844 |
Token | presented |
Token ID | 5545 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
weather | +0.233 |
ipers | +0.223 |
opp | +0.217 |
rador | +0.216 |
ricted | +0.212 |
Neg logit contributions | |
hens | -0.248 |
@@@@ | -0.245 |
hust | -0.219 |
═ | -0.218 |
tin | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
weather | +0.498 |
ipers | +0.475 |
opp | +0.462 |
rador | +0.458 |
ricted | +0.450 |
Neg logit contributions | |
hens | -0.639 |
@@@@ | -0.633 |
═ | -0.570 |
� | -0.569 |
hust | -0.566 |
Token | Peter |
Token ID | 19727 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
weather | +0.326 |
ipers | +0.312 |
opp | +0.303 |
rador | +0.302 |
ricted | +0.297 |
Neg logit contributions | |
hens | -0.369 |
@@@@ | -0.365 |
═ | -0.327 |
� | -0.325 |
tin | -0.324 |
Token | Bet |
Token ID | 5147 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
weather | +3.434 |
ipers | +3.275 |
opp | +3.234 |
rador | +3.158 |
ricted | +3.114 |
Neg logit contributions | |
@@@@ | -3.566 |
hens | -3.565 |
� | -3.219 |
═ | -3.196 |
ONSORED | -3.140 |
Token | zel |
Token ID | 17396 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
hens | +2.052 |
@@@@ | +1.963 |
tin | +1.803 |
hust | +1.742 |
═ | +1.738 |
Neg logit contributions | |
weather | -2.057 |
ipers | -1.989 |
rador | -1.930 |
opp | -1.918 |
ricted | -1.898 |
Token | the |
Token ID | 262 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
weather | +1.333 |
ipers | +1.269 |
opp | +1.236 |
rador | +1.223 |
ricted | +1.201 |
Neg logit contributions | |
hens | -1.769 |
@@@@ | -1.752 |
═ | -1.582 |
� | -1.579 |
tin | -1.570 |
Token | first |
Token ID | 717 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
hens | +0.224 |
@@@@ | +0.221 |
hust | +0.199 |
═ | +0.198 |
tin | +0.197 |
Neg logit contributions | |
weather | -0.192 |
ipers | -0.184 |
opp | -0.179 |
rador | -0.178 |
ricted | -0.176 |
Token | attempt |
Token ID | 2230 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
hens | +1.561 |
@@@@ | +1.548 |
hust | +1.382 |
tin | +1.360 |
═ | +1.344 |
Neg logit contributions | |
weather | -1.809 |
ipers | -1.730 |
rador | -1.694 |
opp | -1.693 |
ricted | -1.684 |
Token | is |
Token ID | 318 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hens | +0.373 |
@@@@ | +0.368 |
═ | +0.327 |
hust | +0.326 |
� | +0.325 |
Neg logit contributions | |
weather | -0.377 |
ipers | -0.361 |
opp | -0.352 |
rador | -0.351 |
ricted | -0.345 |
Token | typically |
Token ID | 6032 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
weather | +0.176 |
ipers | +0.168 |
opp | +0.163 |
rador | +0.163 |
ricted | +0.160 |
Neg logit contributions | |
hens | -0.213 |
@@@@ | -0.211 |
═ | -0.189 |
hust | -0.189 |
� | -0.188 |
Token | N |
Token ID | 399 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
weather | +2.304 |
ipers | +2.204 |
opp | +2.153 |
rador | +2.103 |
ricted | +2.079 |
Neg logit contributions | |
hens | -2.909 |
@@@@ | -2.891 |
═ | -2.613 |
� | -2.612 |
ONSORED | -2.590 |
Token | . |
Token ID | 13 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
weather | +0.381 |
ipers | +0.363 |
opp | +0.354 |
rador | +0.352 |
ricted | +0.345 |
Neg logit contributions | |
hens | -0.467 |
@@@@ | -0.463 |
═ | -0.416 |
� | -0.415 |
tin | -0.413 |
Token | The |
Token ID | 383 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
hens | +0.741 |
@@@@ | +0.734 |
═ | +0.652 |
� | +0.648 |
tin | +0.647 |
Neg logit contributions | |
weather | -0.735 |
ipers | -0.705 |
opp | -0.686 |
rador | -0.685 |
ricted | -0.675 |
Token | rate |
Token ID | 2494 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
weather | +0.130 |
ipers | +0.124 |
opp | +0.120 |
rador | +0.120 |
ricted | +0.118 |
Neg logit contributions | |
hens | -0.169 |
@@@@ | -0.167 |
hust | -0.151 |
═ | -0.150 |
� | -0.150 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
hens | +2.586 |
@@@@ | +2.549 |
═ | +2.288 |
hust | +2.286 |
� | +2.269 |
Neg logit contributions | |
weather | -2.429 |
ipers | -2.322 |
rador | -2.266 |
opp | -2.248 |
ricted | -2.219 |
Token | failure |
Token ID | 5287 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
hens | +0.093 |
@@@@ | +0.092 |
═ | +0.082 |
hust | +0.082 |
� | +0.082 |
Neg logit contributions | |
weather | -0.082 |
ipers | -0.078 |
opp | -0.076 |
rador | -0.076 |
ricted | -0.075 |
Token | on |
Token ID | 319 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hens | +0.238 |
@@@@ | +0.235 |
═ | +0.211 |
hust | +0.209 |
tin | +0.209 |
Neg logit contributions | |
weather | -0.219 |
ipers | -0.210 |
opp | -0.204 |
rador | -0.203 |
ricted | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
weather | +0.963 |
ipers | +0.919 |
opp | +0.892 |
rador | +0.886 |
ricted | +0.870 |
Neg logit contributions | |
hens | -1.275 |
@@@@ | -1.263 |
═ | -1.140 |
� | -1.136 |
hust | -1.133 |
Token | upper |
Token ID | 6727 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
hens | +0.290 |
@@@@ | +0.287 |
═ | +0.255 |
hust | +0.255 |
tin | +0.253 |
Neg logit contributions | |
weather | -0.281 |
ipers | -0.272 |
opp | -0.264 |
rador | -0.263 |
ricted | -0.258 |
Token | right |
Token ID | 826 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
weather | +1.823 |
ipers | +1.741 |
opp | +1.704 |
rador | +1.689 |
ricted | +1.667 |
Neg logit contributions | |
hens | -1.853 |
@@@@ | -1.832 |
� | -1.633 |
═ | -1.633 |
tin | -1.625 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
weather | +1.485 |
ipers | +1.418 |
opp | +1.385 |
rador | +1.374 |
ricted | +1.352 |
Neg logit contributions | |
hens | -1.703 |
@@@@ | -1.684 |
═ | -1.508 |
� | -1.507 |
tin | -1.499 |
Token |
|
Token ID | 198 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
hens | +0.198 |
@@@@ | +0.196 |
═ | +0.175 |
tin | +0.174 |
� | +0.174 |
Neg logit contributions | |
weather | -0.179 |
ipers | -0.172 |
opp | -0.167 |
rador | -0.166 |
ricted | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
hens | +0.309 |
@@@@ | +0.306 |
tin | +0.274 |
═ | +0.273 |
hust | +0.272 |
Neg logit contributions | |
weather | -0.244 |
ipers | -0.235 |
rador | -0.228 |
opp | -0.227 |
ricted | -0.223 |
Token | Like |
Token ID | 7594 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
hens | +0.214 |
@@@@ | +0.214 |
tin | +0.190 |
═ | +0.189 |
� | +0.189 |
Neg logit contributions | |
weather | -0.202 |
ipers | -0.195 |
rador | -0.190 |
opp | -0.187 |
ricted | -0.186 |
Token | this |
Token ID | 428 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
weather | +1.799 |
ipers | +1.710 |
opp | +1.667 |
rador | +1.642 |
ricted | +1.618 |
Neg logit contributions | |
hens | -2.286 |
@@@@ | -2.277 |
� | -2.051 |
═ | -2.045 |
ONSORED | -2.037 |
Token | : |
Token ID | 25 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
hens | +1.291 |
@@@@ | +1.284 |
hust | +1.166 |
tin | +1.158 |
═ | +1.158 |
Neg logit contributions | |
weather | -0.989 |
ipers | -0.939 |
rador | -0.908 |
opp | -0.903 |
ricted | -0.884 |
Token | Like |
Token ID | 4525 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
hens | +0.535 |
@@@@ | +0.528 |
═ | +0.479 |
tin | +0.477 |
� | +0.477 |
Neg logit contributions | |
weather | -0.380 |
ipers | -0.362 |
rador | -0.356 |
opp | -0.354 |
ricted | -0.341 |
Token | she |
Token ID | 673 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
weather | +0.180 |
ipers | +0.173 |
rador | +0.167 |
opp | +0.167 |
ricted | +0.165 |
Neg logit contributions | |
hens | -0.208 |
@@@@ | -0.205 |
hust | -0.184 |
tin | -0.183 |
═ | -0.183 |
Token | said |
Token ID | 531 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hens | +0.695 |
@@@@ | +0.685 |
hust | +0.625 |
tin | +0.624 |
═ | +0.623 |
Neg logit contributions | |
weather | -0.445 |
ipers | -0.425 |
opp | -0.410 |
rador | -0.409 |
ricted | -0.400 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
weather | +0.188 |
ipers | +0.179 |
opp | +0.175 |
rador | +0.173 |
ricted | +0.169 |
Neg logit contributions | |
hens | -0.256 |
@@@@ | -0.254 |
═ | -0.230 |
� | -0.230 |
tin | -0.228 |
Token | Brick |
Token ID | 28347 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
weather | +0.306 |
ipers | +0.294 |
opp | +0.285 |
rador | +0.285 |
ricted | +0.280 |
Neg logit contributions | |
hens | -0.360 |
@@@@ | -0.356 |
═ | -0.319 |
tin | -0.318 |
hust | -0.317 |
Token | and |
Token ID | 290 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
hens | +1.434 |
@@@@ | +1.397 |
tin | +1.272 |
hust | +1.266 |
═ | +1.263 |
Neg logit contributions | |
weather | -1.254 |
ipers | -1.206 |
rador | -1.179 |
ricted | -1.159 |
opp | -1.158 |
Token | mortar |
Token ID | 29871 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
hens | +0.312 |
@@@@ | +0.308 |
hust | +0.278 |
tin | +0.278 |
═ | +0.277 |
Neg logit contributions | |
weather | -0.301 |
ipers | -0.287 |
opp | -0.280 |
rador | -0.277 |
ricted | -0.276 |
Token | stores |
Token ID | 7000 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
hens | +1.725 |
@@@@ | +1.686 |
hust | +1.547 |
tin | +1.513 |
═ | +1.484 |
Neg logit contributions | |
weather | -1.885 |
ipers | -1.821 |
rador | -1.775 |
ricted | -1.760 |
opp | -1.747 |
Token | rely |
Token ID | 8814 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
weather | +0.729 |
ipers | +0.700 |
opp | +0.680 |
rador | +0.678 |
ricted | +0.667 |
Neg logit contributions | |
hens | -0.753 |
@@@@ | -0.743 |
hust | -0.663 |
═ | -0.662 |
� | -0.660 |
Token | on |
Token ID | 319 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
weather | +0.541 |
ipers | +0.518 |
opp | +0.506 |
rador | +0.503 |
ricted | +0.495 |
Neg logit contributions | |
hens | -0.547 |
@@@@ | -0.542 |
═ | -0.482 |
� | -0.480 |
hust | -0.478 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
weather | +1.586 |
ipers | +1.515 |
opp | +1.475 |
rador | +1.466 |
ricted | +1.441 |
Neg logit contributions | |
hens | -1.877 |
@@@@ | -1.857 |
═ | -1.667 |
� | -1.662 |
hust | -1.660 |
Token | same |
Token ID | 976 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
weather | +0.071 |
ipers | +0.069 |
rador | +0.067 |
opp | +0.066 |
ricted | +0.066 |
Neg logit contributions | |
hens | -0.080 |
@@@@ | -0.079 |
hust | -0.072 |
tin | -0.070 |
═ | -0.070 |
Token | Us |
Token ID | 4021 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
weather | +1.724 |
ipers | +1.644 |
opp | +1.607 |
rador | +1.587 |
ricted | +1.568 |
Neg logit contributions | |
hens | -1.970 |
@@@@ | -1.953 |
� | -1.754 |
═ | -1.751 |
hust | -1.736 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
hens | +2.516 |
@@@@ | +2.460 |
═ | +2.211 |
hust | +2.188 |
tin | +2.187 |
Neg logit contributions | |
weather | -2.147 |
ipers | -2.049 |
rador | -2.014 |
opp | -2.013 |
ricted | -1.955 |
Token | To |
Token ID | 1675 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
hens | +1.173 |
@@@@ | +1.161 |
═ | +1.032 |
tin | +1.016 |
� | +1.016 |
Neg logit contributions | |
weather | -1.252 |
ipers | -1.204 |
rador | -1.178 |
opp | -1.175 |
ricted | -1.154 |
Token | Take |
Token ID | 7214 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
hens | +1.189 |
@@@@ | +1.176 |
═ | +1.039 |
hust | +1.033 |
tin | +1.027 |
Neg logit contributions | |
weather | -1.228 |
ipers | -1.179 |
rador | -1.153 |
opp | -1.147 |
ricted | -1.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
hens | +1.117 |
@@@@ | +1.096 |
═ | +0.974 |
tin | +0.973 |
hust | +0.967 |
Neg logit contributions | |
weather | -1.095 |
ipers | -1.045 |
rador | -1.022 |
opp | -1.015 |
ricted | -1.000 |
Token | Both |
Token ID | 5747 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
hens | +1.311 |
@@@@ | +1.292 |
tin | +1.140 |
═ | +1.140 |
hust | +1.129 |
Neg logit contributions | |
weather | -1.392 |
ipers | -1.339 |
rador | -1.306 |
opp | -1.300 |
ricted | -1.283 |
Token | of |
Token ID | 286 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
weather | +1.038 |
ipers | +0.990 |
opp | +0.964 |
rador | +0.950 |
ricted | +0.941 |
Neg logit contributions | |
hens | -1.314 |
@@@@ | -1.306 |
� | -1.181 |
═ | -1.176 |
tin | -1.171 |
Token | us |
Token ID | 514 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
hens | +1.426 |
@@@@ | +1.412 |
═ | +1.277 |
tin | +1.260 |
@#& | +1.259 |
Neg logit contributions | |
weather | -1.149 |
ipers | -1.093 |
rador | -1.075 |
opp | -1.073 |
ricted | -1.040 |
Token | are |
Token ID | 389 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
hens | +2.247 |
@@@@ | +2.215 |
═ | +1.993 |
hust | +1.991 |
tin | +1.967 |
Neg logit contributions | |
weather | -1.916 |
ipers | -1.835 |
rador | -1.792 |
opp | -1.788 |
ricted | -1.748 |
Token | on |
Token ID | 319 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
weather | +0.388 |
ipers | +0.372 |
opp | +0.363 |
rador | +0.361 |
ricted | +0.355 |
Neg logit contributions | |
hens | -0.397 |
@@@@ | -0.393 |
═ | -0.350 |
� | -0.349 |
hust | -0.347 |
Token | medication |
Token ID | 14103 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
weather | +0.465 |
ipers | +0.444 |
opp | +0.433 |
rador | +0.430 |
ricted | +0.423 |
Neg logit contributions | |
hens | -0.545 |
@@@@ | -0.540 |
═ | -0.484 |
� | -0.482 |
hust | -0.482 |
Token | offers |
Token ID | 4394 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
weather | +1.496 |
ipers | +1.425 |
opp | +1.402 |
rador | +1.394 |
ricted | +1.362 |
Neg logit contributions | |
hens | -1.640 |
@@@@ | -1.627 |
� | -1.459 |
═ | -1.456 |
@#& | -1.443 |
Token | short |
Token ID | 1790 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
weather | +0.281 |
ipers | +0.268 |
rador | +0.258 |
opp | +0.258 |
ricted | +0.254 |
Neg logit contributions | |
hens | -0.344 |
@@@@ | -0.340 |
hust | -0.309 |
tin | -0.306 |
═ | -0.306 |
Token | - |
Token ID | 12 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
weather | +1.757 |
ipers | +1.668 |
opp | +1.623 |
rador | +1.608 |
ricted | +1.575 |
Neg logit contributions | |
hens | -2.475 |
@@@@ | -2.457 |
═ | -2.221 |
� | -2.219 |
ONSORED | -2.207 |
Token | term |
Token ID | 4354 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
weather | +0.758 |
ipers | +0.729 |
rador | +0.695 |
opp | +0.691 |
ricted | +0.685 |
Neg logit contributions | |
hens | -1.360 |
@@@@ | -1.332 |
tin | -1.228 |
hust | -1.226 |
═ | -1.219 |
Token | help |
Token ID | 1037 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
hens | +0.552 |
@@@@ | +0.545 |
hust | +0.498 |
tin | +0.489 |
═ | +0.488 |
Neg logit contributions | |
weather | -0.449 |
ipers | -0.432 |
opp | -0.414 |
rador | -0.414 |
ricted | -0.408 |
Token | for |
Token ID | 329 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
weather | +2.170 |
ipers | +2.061 |
opp | +2.028 |
rador | +2.004 |
ricted | +1.954 |
Neg logit contributions | |
hens | -2.740 |
@@@@ | -2.731 |
� | -2.461 |
═ | -2.446 |
@#& | -2.431 |
Token | the |
Token ID | 262 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
weather | +2.514 |
ipers | +2.371 |
opp | +2.329 |
rador | +2.298 |
ricted | +2.247 |
Neg logit contributions | |
hens | -3.749 |
@@@@ | -3.726 |
� | -3.413 |
═ | -3.380 |
ONSORED | -3.353 |
Token | recently |
Token ID | 2904 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
weather | +0.495 |
ipers | +0.475 |
opp | +0.459 |
rador | +0.457 |
ricted | +0.450 |
Neg logit contributions | |
hens | -0.614 |
@@@@ | -0.606 |
hust | -0.547 |
═ | -0.546 |
tin | -0.543 |
Token | ev |
Token ID | 819 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
weather | +1.342 |
ipers | +1.274 |
opp | +1.248 |
rador | +1.237 |
ricted | +1.216 |
Neg logit contributions | |
hens | -1.483 |
@@@@ | -1.480 |
� | -1.326 |
═ | -1.323 |
ONSORED | -1.312 |
Token | icted |
Token ID | 5722 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
weather | +3.104 |
opp | +2.936 |
ipers | +2.858 |
ricted | +2.857 |
rador | +2.812 |
Neg logit contributions | |
@@@@ | -4.202 |
hens | -4.097 |
�� | -3.885 |
═ | -3.828 |
� | -3.801 |
Token | . |
Token ID | 13 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
hens | +0.739 |
@@@@ | +0.732 |
═ | +0.657 |
hust | +0.656 |
tin | +0.653 |
Neg logit contributions | |
weather | -0.619 |
ipers | -0.594 |
opp | -0.574 |
rador | -0.572 |
ricted | -0.563 |
Token | have |
Token ID | 423 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
hens | +0.969 |
@@@@ | +0.955 |
hust | +0.855 |
═ | +0.847 |
tin | +0.846 |
Neg logit contributions | |
weather | -1.028 |
ipers | -0.995 |
rador | -0.967 |
opp | -0.957 |
ricted | -0.943 |
Token | imposed |
Token ID | 10893 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
hens | +0.069 |
@@@@ | +0.068 |
hust | +0.061 |
tin | +0.061 |
═ | +0.061 |
Neg logit contributions | |
weather | -0.062 |
ipers | -0.059 |
opp | -0.057 |
rador | -0.057 |
ricted | -0.056 |
Token | travel |
Token ID | 3067 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
hens | +2.033 |
@@@@ | +1.966 |
hust | +1.771 |
tin | +1.735 |
═ | +1.710 |
Neg logit contributions | |
weather | -2.479 |
ipers | -2.384 |
rador | -2.335 |
opp | -2.316 |
Downloadha | -2.287 |
Token | bans |
Token ID | 20075 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
weather | +0.063 |
ipers | +0.060 |
opp | +0.059 |
rador | +0.058 |
ricted | +0.058 |
Neg logit contributions | |
hens | -0.068 |
@@@@ | -0.068 |
� | -0.061 |
═ | -0.061 |
@#& | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
hens | +0.775 |
@@@@ | +0.764 |
═ | +0.681 |
hust | +0.677 |
� | +0.676 |
Neg logit contributions | |
weather | -0.744 |
ipers | -0.717 |
rador | -0.698 |
opp | -0.696 |
ricted | -0.684 |
Token | asset |
Token ID | 11171 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
weather | +0.969 |
ipers | +0.928 |
opp | +0.908 |
rador | +0.898 |
ricted | +0.889 |
Neg logit contributions | |
hens | -1.040 |
@@@@ | -1.032 |
═ | -0.923 |
� | -0.921 |
@#& | -0.913 |
Token | freezes |
Token ID | 44389 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
weather | +0.970 |
ipers | +0.921 |
opp | +0.894 |
rador | +0.884 |
ricted | +0.868 |
Neg logit contributions | |
hens | -1.419 |
@@@@ | -1.410 |
═ | -1.281 |
� | -1.280 |
ONSORED | -1.274 |
Token | on |
Token ID | 319 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
hens | +0.920 |
@@@@ | +0.905 |
═ | +0.807 |
hust | +0.801 |
tin | +0.799 |
Neg logit contributions | |
weather | -0.930 |
ipers | -0.898 |
rador | -0.872 |
opp | -0.869 |
ricted | -0.857 |
Token | senior |
Token ID | 4664 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
weather | +1.248 |
ipers | +1.188 |
opp | +1.158 |
rador | +1.142 |
ricted | +1.126 |
Neg logit contributions | |
hens | -1.685 |
@@@@ | -1.675 |
═ | -1.515 |
� | -1.514 |
ONSORED | -1.500 |
Token | Russian |
Token ID | 3394 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
weather | +1.758 |
ipers | +1.672 |
opp | +1.634 |
rador | +1.601 |
ricted | +1.583 |
Neg logit contributions | |
hens | -2.230 |
@@@@ | -2.230 |
� | -2.021 |
═ | -2.021 |
ONSORED | -1.998 |
Token | and |
Token ID | 290 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
hens | +2.113 |
@@@@ | +2.047 |
hust | +1.872 |
tin | +1.830 |
@#& | +1.797 |
Neg logit contributions | |
weather | -2.200 |
ipers | -2.108 |
rador | -2.078 |
opp | -2.048 |
ricted | -2.045 |
Token | matches |
Token ID | 7466 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
weather | +1.910 |
ipers | +1.819 |
opp | +1.779 |
rador | +1.756 |
ricted | +1.735 |
Neg logit contributions | |
hens | -2.123 |
@@@@ | -2.111 |
═ | -1.891 |
� | -1.887 |
ONSORED | -1.868 |
Token | are |
Token ID | 389 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
hens | +0.500 |
@@@@ | +0.491 |
hust | +0.438 |
═ | +0.436 |
tin | +0.435 |
Neg logit contributions | |
weather | -0.526 |
ipers | -0.507 |
rador | -0.493 |
opp | -0.493 |
ricted | -0.484 |
Token | going |
Token ID | 1016 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
weather | +1.281 |
ipers | +1.228 |
opp | +1.194 |
rador | +1.189 |
ricted | +1.166 |
Neg logit contributions | |
hens | -1.430 |
@@@@ | -1.415 |
═ | -1.264 |
hust | -1.263 |
� | -1.262 |
Token | to |
Token ID | 284 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
hens | +0.401 |
@@@@ | +0.396 |
═ | +0.353 |
� | +0.353 |
hust | +0.352 |
Neg logit contributions | |
weather | -0.362 |
ipers | -0.346 |
opp | -0.337 |
rador | -0.336 |
ricted | -0.330 |
Token | be |
Token ID | 307 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
hens | +0.518 |
@@@@ | +0.510 |
hust | +0.452 |
tin | +0.448 |
═ | +0.447 |
Neg logit contributions | |
weather | -0.607 |
ipers | -0.591 |
opp | -0.572 |
rador | -0.571 |
ricted | -0.563 |
Token | played |
Token ID | 2826 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
hens | +0.772 |
@@@@ | +0.760 |
hust | +0.694 |
tin | +0.679 |
� | +0.674 |
Neg logit contributions | |
weather | -0.717 |
ipers | -0.692 |
rador | -0.675 |
opp | -0.667 |
ricted | -0.652 |
Token | in |
Token ID | 287 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
weather | +0.969 |
ipers | +0.927 |
opp | +0.907 |
rador | +0.898 |
ricted | +0.885 |
Neg logit contributions | |
hens | -1.013 |
@@@@ | -1.003 |
═ | -0.894 |
� | -0.892 |
hust | -0.886 |
Token | Tehran |
Token ID | 20882 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
hens | +0.107 |
@@@@ | +0.105 |
hust | +0.094 |
tin | +0.094 |
═ | +0.094 |
Neg logit contributions | |
weather | -0.102 |
ipers | -0.098 |
rador | -0.095 |
opp | -0.095 |
ricted | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
weather | +0.770 |
ipers | +0.735 |
opp | +0.715 |
rador | +0.710 |
ricted | +0.697 |
Neg logit contributions | |
hens | -0.955 |
@@@@ | -0.946 |
═ | -0.851 |
� | -0.849 |
hust | -0.845 |
Token | so |
Token ID | 523 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
weather | +0.033 |
ipers | +0.032 |
opp | +0.031 |
rador | +0.031 |
ricted | +0.031 |
Neg logit contributions | |
hens | -0.037 |
@@@@ | -0.036 |
hust | -0.032 |
═ | -0.032 |
tin | -0.032 |
Token | their |
Token ID | 511 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
hens | +0.039 |
@@@@ | +0.038 |
hust | +0.034 |
tin | +0.034 |
═ | +0.034 |
Neg logit contributions | |
weather | -0.034 |
ipers | -0.033 |
rador | -0.032 |
opp | -0.032 |
ricted | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
weather | +0.176 |
ipers | +0.168 |
opp | +0.163 |
rador | +0.162 |
ricted | +0.160 |
Neg logit contributions | |
hens | -0.204 |
@@@@ | -0.201 |
═ | -0.181 |
hust | -0.180 |
� | -0.180 |
Token | over |
Token ID | 625 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
hens | +0.404 |
@@@@ | +0.399 |
hust | +0.356 |
═ | +0.355 |
tin | +0.353 |
Neg logit contributions | |
weather | -0.393 |
ipers | -0.377 |
opp | -0.366 |
rador | -0.365 |
ricted | -0.360 |
Token | 25 |
Token ID | 1679 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
hens | +1.071 |
@@@@ | +1.050 |
═ | +0.943 |
hust | +0.942 |
tin | +0.937 |
Neg logit contributions | |
weather | -0.940 |
ipers | -0.902 |
opp | -0.877 |
rador | -0.874 |
ricted | -0.865 |
Token | years |
Token ID | 812 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
hens | +2.188 |
@@@@ | +2.144 |
hust | +1.883 |
═ | +1.863 |
tin | +1.859 |
Neg logit contributions | |
weather | -2.819 |
ipers | -2.717 |
rador | -2.638 |
opp | -2.637 |
ricted | -2.605 |
Token | since |
Token ID | 1201 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
weather | +0.249 |
ipers | +0.238 |
opp | +0.233 |
rador | +0.231 |
ricted | +0.227 |
Neg logit contributions | |
hens | -0.258 |
@@@@ | -0.255 |
═ | -0.228 |
� | -0.227 |
tin | -0.226 |
Token | its |
Token ID | 663 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
hens | +0.906 |
@@@@ | +0.892 |
hust | +0.795 |
═ | +0.790 |
tin | +0.788 |
Neg logit contributions | |
weather | -0.930 |
ipers | -0.895 |
opp | -0.868 |
rador | -0.865 |
ricted | -0.856 |
Token | inception |
Token ID | 30839 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
weather | +0.934 |
ipers | +0.897 |
opp | +0.878 |
rador | +0.872 |
ricted | +0.859 |
Neg logit contributions | |
hens | -0.845 |
@@@@ | -0.835 |
═ | -0.737 |
� | -0.735 |
hust | -0.731 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
weather | +0.180 |
ipers | +0.172 |
opp | +0.167 |
rador | +0.166 |
ricted | +0.163 |
Neg logit contributions | |
hens | -0.222 |
@@@@ | -0.220 |
═ | -0.198 |
� | -0.197 |
hust | -0.196 |
Token | while |
Token ID | 981 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
weather | +0.106 |
ipers | +0.102 |
opp | +0.100 |
rador | +0.099 |
ricted | +0.098 |
Neg logit contributions | |
hens | -0.084 |
@@@@ | -0.083 |
═ | -0.073 |
� | -0.073 |
hust | -0.072 |
Token | punk |
Token ID | 22782 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
hens | +1.110 |
@@@@ | +1.101 |
hust | +0.989 |
tin | +0.982 |
═ | +0.981 |
Neg logit contributions | |
weather | -1.038 |
ipers | -0.997 |
opp | -0.962 |
rador | -0.959 |
ricted | -0.947 |
Token | has |
Token ID | 468 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
hens | +2.330 |
@@@@ | +2.302 |
hust | +2.075 |
tin | +2.062 |
═ | +2.046 |
Neg logit contributions | |
weather | -2.422 |
ipers | -2.326 |
rador | -2.263 |
opp | -2.258 |
ricted | -2.214 |
Token | loader |
Token ID | 29356 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
hens | +2.531 |
@@@@ | +2.461 |
hust | +2.280 |
═ | +2.266 |
tin | +2.261 |
Neg logit contributions | |
weather | -1.668 |
ipers | -1.602 |
rador | -1.535 |
opp | -1.520 |
ricted | -1.511 |
Token | in |
Token ID | 287 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
hens | +1.711 |
@@@@ | +1.670 |
hust | +1.535 |
tin | +1.501 |
═ | +1.477 |
Neg logit contributions | |
weather | -1.781 |
ipers | -1.727 |
rador | -1.678 |
opp | -1.662 |
ricted | -1.645 |
Token | this |
Token ID | 428 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
hens | +0.530 |
@@@@ | +0.524 |
hust | +0.471 |
═ | +0.471 |
tin | +0.470 |
Neg logit contributions | |
weather | -0.442 |
ipers | -0.425 |
rador | -0.410 |
opp | -0.408 |
ricted | -0.402 |
Token | watch |
Token ID | 2342 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
hens | +2.183 |
@@@@ | +2.170 |
hust | +1.983 |
═ | +1.949 |
tin | +1.945 |
Neg logit contributions | |
weather | -1.767 |
ipers | -1.696 |
rador | -1.636 |
opp | -1.633 |
ricted | -1.601 |
Token | is |
Token ID | 318 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
hens | +0.350 |
@@@@ | +0.346 |
═ | +0.307 |
tin | +0.306 |
hust | +0.306 |
Neg logit contributions | |
weather | -0.349 |
ipers | -0.336 |
opp | -0.327 |
rador | -0.326 |
ricted | -0.323 |
Token | poorly |
Token ID | 13455 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
weather | +0.021 |
ipers | +0.020 |
rador | +0.020 |
opp | +0.019 |
ricted | +0.019 |
Neg logit contributions | |
hens | -0.025 |
@@@@ | -0.024 |
hust | -0.022 |
tin | -0.022 |
═ | -0.022 |
Token | coded |
Token ID | 30817 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
weather | +4.655 |
ipers | +4.282 |
opp | +4.238 |
rador | +4.143 |
ocal | +4.134 |
Neg logit contributions | |
@@@@ | -6.960 |
hens | -6.956 |
�� | -6.250 |
� | -6.196 |
ONSORED | -6.183 |
Token | The |
Token ID | 383 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
weather | +0.826 |
ipers | +0.788 |
opp | +0.767 |
rador | +0.762 |
ricted | +0.749 |
Neg logit contributions | |
hens | -1.007 |
@@@@ | -0.997 |
═ | -0.896 |
� | -0.893 |
hust | -0.891 |
Token | boot |
Token ID | 6297 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
hens | +0.487 |
@@@@ | +0.482 |
hust | +0.428 |
═ | +0.426 |
tin | +0.424 |
Neg logit contributions | |
weather | -0.512 |
ipers | -0.492 |
opp | -0.480 |
rador | -0.479 |
ricted | -0.472 |
Token | loader |
Token ID | 29356 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
hens | +2.107 |
@@@@ | +2.053 |
hust | +1.855 |
═ | +1.840 |
tin | +1.837 |
Neg logit contributions | |
weather | -2.112 |
ipers | -2.034 |
rador | -1.980 |
opp | -1.962 |
ricted | -1.956 |
Token | res |
Token ID | 581 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
hens | +2.025 |
@@@@ | +1.982 |
hust | +1.815 |
tin | +1.782 |
═ | +1.744 |
Neg logit contributions | |
weather | -2.078 |
ipers | -2.009 |
rador | -1.950 |
opp | -1.917 |
ricted | -1.902 |
Token | to |
Token ID | 284 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
hens | +2.755 |
@@@@ | +2.690 |
hust | +2.417 |
═ | +2.408 |
tin | +2.381 |
Neg logit contributions | |
weather | -2.719 |
ipers | -2.628 |
rador | -2.534 |
opp | -2.533 |
ricted | -2.528 |
Token | Jun |
Token ID | 7653 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
hens | +0.071 |
@@@@ | +0.069 |
hust | +0.064 |
tin | +0.063 |
═ | +0.063 |
Neg logit contributions | |
weather | -0.049 |
ipers | -0.047 |
rador | -0.045 |
ricted | -0.044 |
opp | -0.044 |
Token | cker |
Token ID | 15280 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
weather | +3.744 |
ipers | +3.550 |
opp | +3.489 |
rador | +3.284 |
ricted | +3.282 |
Neg logit contributions | |
@@@@ | -5.727 |
hens | -5.594 |
� | -5.398 |
ONSORED | -5.321 |
�� | -5.316 |
Token | . |
Token ID | 13 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
weather | +0.327 |
ipers | +0.312 |
opp | +0.303 |
rador | +0.301 |
ricted | +0.296 |
Neg logit contributions | |
hens | -0.418 |
@@@@ | -0.413 |
═ | -0.373 |
� | -0.371 |
hust | -0.371 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
hens | +0.271 |
@@@@ | +0.266 |
═ | +0.240 |
tin | +0.239 |
hust | +0.238 |
Neg logit contributions | |
weather | -0.221 |
ipers | -0.211 |
rador | -0.204 |
opp | -0.204 |
ricted | -0.201 |
Token | Ill |
Token ID | 21478 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
weather | +1.622 |
ipers | +1.553 |
opp | +1.512 |
rador | +1.504 |
ricted | +1.479 |
Neg logit contributions | |
hens | -1.832 |
@@@@ | -1.814 |
═ | -1.622 |
� | -1.618 |
tin | -1.613 |
Token | ustration |
Token ID | 44027 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
weather | +5.727 |
ipers | +5.410 |
opp | +5.297 |
rador | +5.184 |
ocal | +5.162 |
Neg logit contributions | |
@@@@ | -7.052 |
hens | -6.958 |
� | -6.430 |
@#& | -6.313 |
═ | -6.299 |
Token | by |
Token ID | 416 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
weather | +2.932 |
ipers | +2.789 |
opp | +2.767 |
rador | +2.721 |
ricted | +2.696 |
Neg logit contributions | |
hens | -3.107 |
@@@@ | -3.075 |
═ | -2.762 |
� | -2.757 |
@#& | -2.744 |
Token | Allison |
Token ID | 33461 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
weather | +0.269 |
ipers | +0.257 |
opp | +0.250 |
rador | +0.249 |
ricted | +0.245 |
Neg logit contributions | |
hens | -0.306 |
@@@@ | -0.302 |
═ | -0.270 |
hust | -0.270 |
tin | -0.269 |
Token | Br |
Token ID | 1709 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
weather | +1.581 |
ipers | +1.512 |
opp | +1.479 |
rador | +1.464 |
ricted | +1.443 |
Neg logit contributions | |
hens | -1.642 |
@@@@ | -1.625 |
═ | -1.450 |
� | -1.447 |
hust | -1.435 |
Token | uns |
Token ID | 13271 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
hens | +3.034 |
@@@@ | +2.887 |
tin | +2.727 |
hust | +2.660 |
@#& | +2.625 |
Neg logit contributions | |
weather | -2.111 |
ipers | -1.980 |
rador | -1.941 |
Downloadha | -1.924 |
opp | -1.898 |
Token | process |
Token ID | 1429 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
hens | +0.120 |
@@@@ | +0.119 |
hust | +0.108 |
� | +0.107 |
═ | +0.107 |
Neg logit contributions | |
weather | -0.087 |
ipers | -0.082 |
opp | -0.079 |
rador | -0.079 |
ricted | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
hens | +0.585 |
@@@@ | +0.577 |
═ | +0.519 |
hust | +0.518 |
� | +0.517 |
Neg logit contributions | |
weather | -0.474 |
ipers | -0.452 |
opp | -0.439 |
rador | -0.439 |
ricted | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
weather | +0.256 |
ipers | +0.245 |
opp | +0.239 |
rador | +0.237 |
ricted | +0.233 |
Neg logit contributions | |
hens | -0.297 |
@@@@ | -0.294 |
═ | -0.263 |
� | -0.263 |
hust | -0.261 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
weather | +0.283 |
ipers | +0.270 |
opp | +0.262 |
rador | +0.261 |
ricted | +0.256 |
Neg logit contributions | |
hens | -0.375 |
@@@@ | -0.372 |
═ | -0.335 |
tin | -0.334 |
hust | -0.333 |
Token | [ |
Token ID | 58 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
weather | +0.184 |
ipers | +0.178 |
rador | +0.172 |
opp | +0.171 |
ricted | +0.169 |
Neg logit contributions | |
hens | -0.203 |
@@@@ | -0.202 |
═ | -0.180 |
tin | -0.179 |
� | -0.179 |
Token | ng |
Token ID | 782 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
weather | +3.005 |
ipers | +2.838 |
opp | +2.808 |
rador | +2.743 |
ricted | +2.714 |
Neg logit contributions | |
hens | -3.174 |
@@@@ | -3.144 |
� | -2.823 |
hust | -2.798 |
═ | -2.791 |
Token | gallery |
Token ID | 24460 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
weather | +4.220 |
ipers | +3.830 |
opp | +3.812 |
rador | +3.717 |
ored | +3.636 |
Neg logit contributions | |
hens | -7.167 |
@@@@ | -7.024 |
�� | -6.503 |
@#& | -6.500 |
═ | -6.475 |
Token | id |
Token ID | 4686 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
weather | +3.260 |
ipers | +3.065 |
opp | +3.027 |
rador | +2.961 |
ricted | +2.922 |
Neg logit contributions | |
hens | -4.410 |
@@@@ | -4.338 |
�� | -3.960 |
� | -3.935 |
ONSORED | -3.919 |
Token | = |
Token ID | 28 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
weather | +1.257 |
ipers | +1.183 |
opp | +1.146 |
rador | +1.135 |
ricted | +1.111 |
Neg logit contributions | |
hens | -2.071 |
@@@@ | -2.047 |
� | -1.869 |
═ | -1.867 |
tin | -1.862 |
Token | 159 |
Token ID | 19707 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
hens | +0.788 |
@@@@ | +0.782 |
═ | +0.707 |
tin | +0.703 |
� | +0.698 |
Neg logit contributions | |
weather | -0.580 |
ipers | -0.556 |
rador | -0.538 |
opp | -0.535 |
ricted | -0.529 |
Token | ] |
Token ID | 60 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
weather | +1.227 |
ipers | +1.166 |
opp | +1.129 |
rador | +1.121 |
ricted | +1.099 |
Neg logit contributions | |
hens | -1.850 |
@@@@ | -1.835 |
═ | -1.665 |
� | -1.662 |
hust | -1.656 |
Token | Republican |
Token ID | 3415 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
weather | +1.668 |
ipers | +1.594 |
opp | +1.561 |
rador | +1.547 |
ricted | +1.524 |
Neg logit contributions | |
hens | -1.802 |
@@@@ | -1.789 |
� | -1.599 |
═ | -1.594 |
tin | -1.584 |
Token | bill |
Token ID | 2855 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
hens | +0.971 |
@@@@ | +0.961 |
hust | +0.871 |
═ | +0.865 |
tin | +0.858 |
Neg logit contributions | |
weather | -0.837 |
ipers | -0.804 |
opp | -0.769 |
rador | -0.765 |
ricted | -0.759 |
Token | that |
Token ID | 326 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
weather | +0.307 |
ipers | +0.293 |
opp | +0.284 |
rador | +0.283 |
ricted | +0.279 |
Neg logit contributions | |
hens | -0.357 |
@@@@ | -0.353 |
═ | -0.317 |
� | -0.315 |
hust | -0.315 |
Token | reduced |
Token ID | 5322 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
weather | +0.700 |
ipers | +0.670 |
opp | +0.653 |
rador | +0.648 |
ricted | +0.638 |
Neg logit contributions | |
hens | -0.759 |
@@@@ | -0.751 |
═ | -0.671 |
� | -0.669 |
hust | -0.666 |
Token | early |
Token ID | 1903 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
weather | +0.577 |
ipers | +0.552 |
opp | +0.535 |
rador | +0.533 |
ricted | +0.523 |
Neg logit contributions | |
hens | -0.683 |
@@@@ | -0.676 |
═ | -0.606 |
� | -0.604 |
hust | -0.604 |
Token | voting |
Token ID | 6709 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
weather | +1.500 |
ipers | +1.426 |
opp | +1.394 |
rador | +1.374 |
ricted | +1.353 |
Neg logit contributions | |
hens | -1.910 |
@@@@ | -1.891 |
═ | -1.711 |
� | -1.702 |
ONSORED | -1.689 |
Token | in |
Token ID | 287 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
weather | +4.299 |
opp | +4.215 |
ipers | +4.058 |
rador | +3.946 |
ricted | +3.875 |
Neg logit contributions | |
hens | -5.959 |
@@@@ | -5.927 |
�� | -5.467 |
� | -5.417 |
@#& | -5.409 |
Token | the |
Token ID | 262 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
weather | +0.325 |
ipers | +0.312 |
rador | +0.301 |
opp | +0.301 |
ricted | +0.294 |
Neg logit contributions | |
hens | -0.368 |
@@@@ | -0.362 |
hust | -0.325 |
tin | -0.324 |
═ | -0.324 |
Token | state |
Token ID | 1181 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
weather | +0.172 |
ipers | +0.165 |
rador | +0.160 |
opp | +0.159 |
ricted | +0.156 |
Neg logit contributions | |
hens | -0.188 |
@@@@ | -0.185 |
hust | -0.166 |
tin | -0.165 |
═ | -0.164 |
Token | from |
Token ID | 422 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
weather | +0.765 |
ipers | +0.729 |
opp | +0.712 |
rador | +0.705 |
ricted | +0.695 |
Neg logit contributions | |
hens | -0.945 |
@@@@ | -0.938 |
═ | -0.843 |
� | -0.842 |
tin | -0.836 |
Token | 45 |
Token ID | 4153 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
hens | +1.400 |
@@@@ | +1.368 |
hust | +1.239 |
tin | +1.236 |
@#& | +1.223 |
Neg logit contributions | |
weather | -1.234 |
ipers | -1.173 |
rador | -1.148 |
opp | -1.128 |
ricted | -1.110 |
Token | from |
Token ID | 422 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
weather | +1.623 |
ipers | +1.551 |
opp | +1.513 |
rador | +1.503 |
ricted | +1.478 |
Neg logit contributions | |
hens | -1.731 |
@@@@ | -1.714 |
═ | -1.532 |
� | -1.527 |
@#& | -1.517 |
Token | complaining |
Token ID | 18705 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
hens | +1.746 |
@@@@ | +1.715 |
hust | +1.617 |
tin | +1.572 |
ONSORED | +1.539 |
Neg logit contributions | |
weather | -1.379 |
ipers | -1.338 |
rador | -1.287 |
ricted | -1.269 |
opp | -1.263 |
Token | to |
Token ID | 284 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
weather | +1.181 |
ipers | +1.127 |
opp | +1.098 |
rador | +1.089 |
ricted | +1.071 |
Neg logit contributions | |
hens | -1.424 |
@@@@ | -1.410 |
═ | -1.266 |
� | -1.264 |
tin | -1.257 |
Token | Congress |
Token ID | 3162 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
weather | +0.268 |
ipers | +0.259 |
rador | +0.249 |
opp | +0.248 |
ricted | +0.245 |
Neg logit contributions | |
hens | -0.330 |
@@@@ | -0.325 |
hust | -0.294 |
═ | -0.291 |
tin | -0.290 |
Token | about |
Token ID | 546 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
weather | +1.374 |
ipers | +1.307 |
opp | +1.277 |
rador | +1.263 |
ricted | +1.241 |
Neg logit contributions | |
hens | -1.740 |
@@@@ | -1.726 |
� | -1.556 |
═ | -1.555 |
tin | -1.541 |
Token | poor |
Token ID | 3595 |
Feature activation | -8.43e+00 |
Pos logit contributions | |
weather | +1.282 |
ipers | +1.220 |
opp | +1.184 |
rador | +1.178 |
ricted | +1.154 |
Neg logit contributions | |
hens | -1.658 |
@@@@ | -1.642 |
═ | -1.478 |
hust | -1.476 |
� | -1.473 |
Token | treatment |
Token ID | 3513 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
weather | +5.199 |
ipers | +4.912 |
opp | +4.807 |
odor | +4.710 |
ricted | +4.653 |
Neg logit contributions | |
hens | -7.196 |
@@@@ | -7.142 |
═ | -6.605 |
� | -6.517 |
@#& | -6.454 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weather | +1.351 |
ipers | +1.291 |
opp | +1.256 |
rador | +1.249 |
ricted | +1.228 |
Neg logit contributions | |
hens | -1.587 |
@@@@ | -1.572 |
═ | -1.407 |
� | -1.404 |
hust | -1.402 |
Token | according |
Token ID | 1864 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
weather | +0.955 |
ipers | +0.917 |
opp | +0.894 |
rador | +0.891 |
ricted | +0.878 |
Neg logit contributions | |
hens | -0.901 |
@@@@ | -0.889 |
═ | -0.787 |
� | -0.784 |
hust | -0.784 |
Token | to |
Token ID | 284 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
weather | +1.471 |
ipers | +1.388 |
opp | +1.370 |
rador | +1.335 |
ricted | +1.319 |
Neg logit contributions | |
hens | -1.827 |
@@@@ | -1.816 |
� | -1.670 |
═ | -1.642 |
�� | -1.638 |
Token | one |
Token ID | 530 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
weather | +0.657 |
ipers | +0.628 |
opp | +0.609 |
rador | +0.609 |
ricted | +0.598 |
Neg logit contributions | |
hens | -0.763 |
@@@@ | -0.752 |
hust | -0.674 |
═ | -0.674 |
tin | -0.671 |