Token | Convention |
Token ID | 11680 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Mehran | +4.860 |
lapt | +4.501 |
unta | +4.182 |
etsk | +4.169 |
caut | +4.122 |
Neg logit contributions | |
toe | -6.572 |
acted | -6.276 |
enough | -6.050 |
ring | -5.967 |
uther | -5.806 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
toe | +2.756 |
acted | +2.552 |
ring | +2.501 |
enough | +2.462 |
atively | +2.376 |
Neg logit contributions | |
Mehran | -3.746 |
lapt | -3.682 |
etsk | -3.562 |
caut | -3.501 |
unta | -3.450 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Mehran | +1.558 |
lapt | +1.527 |
etsk | +1.475 |
caut | +1.444 |
unta | +1.429 |
Neg logit contributions | |
toe | -1.567 |
acted | -1.459 |
ring | -1.421 |
enough | -1.414 |
atively | -1.367 |
Token | American |
Token ID | 1605 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Mehran | +0.347 |
lapt | +0.340 |
etsk | +0.329 |
caut | +0.321 |
unta | +0.318 |
Neg logit contributions | |
toe | -0.360 |
acted | -0.336 |
ring | -0.327 |
enough | -0.326 |
atively | -0.315 |
Token | Ge |
Token ID | 2269 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
Mehran | +1.152 |
lapt | +1.120 |
etsk | +1.078 |
caut | +1.064 |
unta | +1.057 |
Neg logit contributions | |
toe | -1.102 |
acted | -1.023 |
ring | -0.992 |
enough | -0.991 |
atively | -0.956 |
Token | ophysical |
Token ID | 41789 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
Mehran | +6.159 |
etsk | +5.721 |
lapt | +5.700 |
irty | +5.666 |
ebin | +5.636 |
Neg logit contributions | |
toe | -11.836 |
acted | -10.820 |
enough | -10.681 |
ring | -10.563 |
mates | -10.332 |
Token | Union |
Token ID | 4479 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
Mehran | +7.308 |
lapt | +6.285 |
unta | +5.949 |
ebin | +5.680 |
Lumpur | +5.631 |
Neg logit contributions | |
toe | -14.400 |
acted | -13.292 |
enough | -13.255 |
ring | -13.205 |
atively | -13.042 |
Token | in |
Token ID | 287 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
toe | +0.500 |
acted | +0.460 |
ring | +0.446 |
enough | +0.443 |
atively | +0.425 |
Neg logit contributions | |
Mehran | -0.668 |
lapt | -0.657 |
etsk | -0.636 |
caut | -0.626 |
unta | -0.620 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
Mehran | +0.020 |
lapt | +0.020 |
etsk | +0.019 |
caut | +0.019 |
unta | +0.019 |
Neg logit contributions | |
toe | -0.023 |
acted | -0.021 |
ring | -0.021 |
enough | -0.021 |
atively | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
toe | +2.017 |
acted | +1.852 |
ring | +1.775 |
enough | +1.755 |
atively | +1.682 |
Neg logit contributions | |
Mehran | -3.528 |
lapt | -3.483 |
etsk | -3.386 |
caut | -3.322 |
unta | -3.294 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
toe | +0.591 |
acted | +0.551 |
ring | +0.537 |
enough | +0.534 |
atively | +0.517 |
Neg logit contributions | |
Mehran | -0.580 |
lapt | -0.569 |
etsk | -0.549 |
caut | -0.537 |
unta | -0.532 |
Token | conference |
Token ID | 4495 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
Mehran | +1.251 |
lapt | +1.218 |
etsk | +1.166 |
caut | +1.139 |
unta | +1.129 |
Neg logit contributions | |
toe | -1.569 |
acted | -1.473 |
enough | -1.434 |
ring | -1.431 |
atively | -1.388 |
Token | of |
Token ID | 286 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
toe | +0.729 |
acted | +0.681 |
ring | +0.667 |
enough | +0.656 |
atively | +0.640 |
Neg logit contributions | |
Mehran | -0.751 |
lapt | -0.739 |
etsk | -0.716 |
caut | -0.700 |
unta | -0.692 |
Token | the |
Token ID | 262 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
toe | +0.637 |
acted | +0.593 |
ring | +0.579 |
enough | +0.574 |
atively | +0.555 |
Neg logit contributions | |
Mehran | -0.681 |
lapt | -0.669 |
etsk | -0.648 |
caut | -0.634 |
unta | -0.626 |
Token | American |
Token ID | 1605 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
toe | +0.519 |
acted | +0.483 |
ring | +0.472 |
enough | +0.468 |
atively | +0.453 |
Neg logit contributions | |
Mehran | -0.537 |
lapt | -0.528 |
etsk | -0.512 |
caut | -0.500 |
unta | -0.494 |
Token | Ge |
Token ID | 2269 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
Mehran | +0.648 |
lapt | +0.634 |
etsk | +0.612 |
caut | +0.601 |
unta | +0.597 |
Neg logit contributions | |
toe | -0.616 |
acted | -0.572 |
ring | -0.554 |
enough | -0.553 |
atively | -0.534 |
Token | ophysical |
Token ID | 41789 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
lapt | +4.457 |
Mehran | +4.301 |
etsk | +4.224 |
unta | +3.982 |
irty | +3.980 |
Neg logit contributions | |
toe | -12.480 |
acted | -11.423 |
enough | -11.310 |
yards | -11.028 |
ring | -11.021 |
Token | Union |
Token ID | 4479 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Mehran | +6.397 |
lapt | +5.796 |
etsk | +5.082 |
caut | +5.059 |
unta | +4.821 |
Neg logit contributions | |
toe | -15.200 |
atively | -14.123 |
ring | -14.010 |
enegger | -13.801 |
enough | -13.757 |
Token | ( |
Token ID | 357 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
toe | +1.471 |
acted | +1.346 |
ring | +1.304 |
enough | +1.292 |
atively | +1.236 |
Neg logit contributions | |
Mehran | -2.296 |
lapt | -2.263 |
etsk | -2.200 |
caut | -2.162 |
unta | -2.142 |
Token | AG |
Token ID | 4760 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
toe | +2.107 |
acted | +1.943 |
enough | +1.915 |
ring | +1.858 |
atively | +1.838 |
Neg logit contributions | |
Mehran | -2.536 |
lapt | -2.521 |
etsk | -2.492 |
caut | -2.389 |
pload | -2.357 |
Token | U |
Token ID | 52 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
Mehran | +3.827 |
lapt | +3.751 |
unta | +3.579 |
etsk | +3.534 |
caut | +3.470 |
Neg logit contributions | |
toe | -4.637 |
acted | -4.431 |
ring | -4.309 |
enough | -4.270 |
atively | -4.118 |
Token | ) |
Token ID | 8 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Mehran | +4.155 |
lapt | +3.982 |
etsk | +3.841 |
caut | +3.783 |
unta | +3.776 |
Neg logit contributions | |
toe | -3.947 |
acted | -3.759 |
enough | -3.589 |
ring | -3.570 |
atively | -3.466 |
Token | casualty |
Token ID | 39068 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
toe | +0.884 |
acted | +0.823 |
ring | +0.804 |
enough | +0.795 |
atively | +0.775 |
Neg logit contributions | |
Mehran | -0.902 |
lapt | -0.887 |
etsk | -0.856 |
caut | -0.834 |
unta | -0.830 |
Token | could |
Token ID | 714 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Mehran | +0.564 |
lapt | +0.553 |
etsk | +0.533 |
caut | +0.523 |
unta | +0.517 |
Neg logit contributions | |
toe | -0.582 |
acted | -0.542 |
enough | -0.527 |
ring | -0.527 |
atively | -0.507 |
Token | be |
Token ID | 307 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
Mehran | +0.911 |
lapt | +0.890 |
etsk | +0.854 |
caut | +0.828 |
unta | +0.819 |
Neg logit contributions | |
toe | -1.400 |
acted | -1.322 |
ring | -1.288 |
enough | -1.286 |
atively | -1.251 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
toe | +0.021 |
acted | +0.019 |
ring | +0.019 |
enough | +0.019 |
atively | +0.018 |
Neg logit contributions | |
Mehran | -0.020 |
lapt | -0.020 |
etsk | -0.019 |
caut | -0.019 |
unta | -0.019 |
Token | Mars |
Token ID | 8706 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
toe | +1.949 |
acted | +1.835 |
ring | +1.807 |
enough | +1.779 |
atively | +1.734 |
Neg logit contributions | |
Mehran | -1.729 |
lapt | -1.702 |
etsk | -1.643 |
caut | -1.594 |
unta | -1.590 |
Token | Atmosp |
Token ID | 33276 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Mehran | +0.820 |
lapt | +0.803 |
etsk | +0.776 |
caut | +0.759 |
unta | +0.753 |
Neg logit contributions | |
toe | -0.845 |
acted | -0.789 |
ring | -0.765 |
enough | -0.763 |
atively | -0.738 |
Token | here |
Token ID | 1456 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
etsk | +6.859 |
Mehran | +6.336 |
� | +6.269 |
irty | +6.163 |
unta | +6.120 |
Neg logit contributions | |
toe | -14.380 |
enegger | -13.250 |
theless | -13.113 |
shire | -13.072 |
enough | -13.066 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Mehran | +0.375 |
lapt | +0.368 |
etsk | +0.355 |
caut | +0.348 |
unta | +0.345 |
Neg logit contributions | |
toe | -0.354 |
acted | -0.329 |
ring | -0.321 |
enough | -0.319 |
atively | -0.308 |
Token | Vol |
Token ID | 4709 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
Mehran | +2.709 |
lapt | +2.655 |
etsk | +2.568 |
caut | +2.515 |
unta | +2.491 |
Neg logit contributions | |
toe | -2.553 |
acted | -2.372 |
ring | -2.307 |
enough | -2.296 |
atively | -2.216 |
Token | atile |
Token ID | 12610 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
etsk | +1.848 |
Mehran | +1.823 |
unta | +1.784 |
lapt | +1.685 |
� | +1.548 |
Neg logit contributions | |
toe | -7.830 |
acted | -7.450 |
ring | -7.240 |
enough | -7.178 |
atively | -7.082 |
Token | Evolution |
Token ID | 15815 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Mehran | +5.994 |
etsk | +5.813 |
lapt | +5.612 |
unta | +5.552 |
� | +5.360 |
Neg logit contributions | |
toe | -5.168 |
acted | -4.833 |
enough | -4.605 |
ring | -4.599 |
uther | -4.575 |
Token | given |
Token ID | 1813 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Mehran | +0.347 |
lapt | +0.340 |
etsk | +0.329 |
caut | +0.322 |
unta | +0.319 |
Neg logit contributions | |
toe | -0.345 |
acted | -0.321 |
ring | -0.313 |
enough | -0.311 |
atively | -0.301 |
Token | by |
Token ID | 416 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Mehran | +0.462 |
lapt | +0.453 |
etsk | +0.439 |
caut | +0.431 |
unta | +0.427 |
Neg logit contributions | |
toe | -0.381 |
acted | -0.351 |
ring | -0.341 |
enough | -0.340 |
atively | -0.326 |
Token | people |
Token ID | 661 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Mehran | +0.261 |
lapt | +0.256 |
etsk | +0.247 |
caut | +0.243 |
unta | +0.240 |
Neg logit contributions | |
toe | -0.248 |
acted | -0.231 |
ring | -0.224 |
enough | -0.223 |
atively | -0.215 |
Token | like |
Token ID | 588 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Mehran | +0.864 |
lapt | +0.848 |
etsk | +0.821 |
caut | +0.805 |
unta | +0.797 |
Neg logit contributions | |
toe | -0.758 |
acted | -0.703 |
ring | -0.684 |
enough | -0.680 |
atively | -0.655 |
Token | Bill |
Token ID | 3941 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
Mehran | +0.919 |
lapt | +0.892 |
etsk | +0.862 |
caut | +0.848 |
unta | +0.837 |
Neg logit contributions | |
toe | -0.888 |
acted | -0.826 |
ring | -0.802 |
enough | -0.800 |
atively | -0.770 |
Token | Moy |
Token ID | 28523 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Mehran | +2.411 |
lapt | +2.308 |
etsk | +2.216 |
caut | +2.186 |
unta | +2.154 |
Neg logit contributions | |
toe | -3.050 |
acted | -2.856 |
enough | -2.784 |
ring | -2.757 |
atively | -2.682 |
Token | ers |
Token ID | 364 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
lapt | +8.637 |
Mehran | +8.565 |
unta | +8.512 |
etsk | +8.405 |
irty | +8.214 |
Neg logit contributions | |
toe | -11.279 |
acted | -11.011 |
atively | -10.031 |
enough | -9.874 |
enegger | -9.746 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Mehran | +0.803 |
lapt | +0.788 |
etsk | +0.767 |
caut | +0.754 |
unta | +0.748 |
Neg logit contributions | |
toe | -0.562 |
acted | -0.514 |
ring | -0.496 |
enough | -0.495 |
atively | -0.474 |
Token | suggests |
Token ID | 5644 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Mehran | +0.546 |
lapt | +0.537 |
etsk | +0.519 |
caut | +0.508 |
unta | +0.503 |
Neg logit contributions | |
toe | -0.528 |
acted | -0.491 |
ring | -0.479 |
enough | -0.476 |
atively | -0.460 |
Token | that |
Token ID | 326 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
toe | +1.290 |
acted | +1.185 |
ring | +1.148 |
enough | +1.140 |
atively | +1.094 |
Neg logit contributions | |
Mehran | -1.817 |
lapt | -1.787 |
etsk | -1.736 |
caut | -1.704 |
unta | -1.690 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Mehran | +0.037 |
lapt | +0.036 |
etsk | +0.035 |
caut | +0.034 |
unta | +0.034 |
Neg logit contributions | |
toe | -0.035 |
acted | -0.033 |
ring | -0.032 |
enough | -0.032 |
atively | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
toe | +3.223 |
acted | +3.050 |
ring | +2.984 |
enough | +2.921 |
atively | +2.872 |
Neg logit contributions | |
Mehran | -2.919 |
lapt | -2.871 |
etsk | -2.769 |
caut | -2.700 |
unta | -2.671 |
Token | � |
Token ID | 447 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
toe | +1.306 |
acted | +1.203 |
ring | +1.165 |
enough | +1.154 |
atively | +1.105 |
Neg logit contributions | |
Mehran | -1.722 |
lapt | -1.710 |
etsk | -1.656 |
caut | -1.620 |
unta | -1.597 |
Token | � |
Token ID | 251 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
toe | +0.392 |
acted | +0.369 |
ring | +0.361 |
enough | +0.359 |
atively | +0.349 |
Neg logit contributions | |
Mehran | -0.290 |
lapt | -0.284 |
etsk | -0.272 |
caut | -0.265 |
unta | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
toe | +0.586 |
acted | +0.540 |
ring | +0.524 |
enough | +0.521 |
atively | +0.501 |
Neg logit contributions | |
Mehran | -0.737 |
lapt | -0.726 |
etsk | -0.703 |
caut | -0.690 |
unta | -0.683 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Mehran | +1.964 |
lapt | +1.881 |
etsk | +1.851 |
unta | +1.809 |
caut | +1.791 |
Neg logit contributions | |
toe | -1.598 |
acted | -1.477 |
enough | -1.428 |
ring | -1.427 |
atively | -1.378 |
Token | Wal |
Token ID | 21902 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Mehran | +1.805 |
lapt | +1.775 |
etsk | +1.732 |
unta | +1.689 |
caut | +1.683 |
Neg logit contributions | |
toe | -1.473 |
acted | -1.355 |
enough | -1.316 |
ring | -1.314 |
atively | -1.272 |
Token | ton |
Token ID | 1122 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
etsk | +5.538 |
lapt | +5.304 |
unta | +5.301 |
Mehran | +5.286 |
undai | +4.788 |
Neg logit contributions | |
toe | -14.286 |
acted | -13.937 |
atively | -13.643 |
hole | -13.278 |
ring | -13.174 |
Token | � |
Token ID | 447 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Mehran | +0.290 |
lapt | +0.285 |
etsk | +0.275 |
caut | +0.270 |
unta | +0.268 |
Neg logit contributions | |
toe | -0.262 |
acted | -0.243 |
ring | -0.236 |
enough | -0.236 |
atively | -0.227 |
Token | � |
Token ID | 247 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Mehran | +0.558 |
lapt | +0.551 |
etsk | +0.525 |
caut | +0.515 |
unta | +0.505 |
Neg logit contributions | |
toe | -0.714 |
acted | -0.678 |
ring | -0.661 |
enough | -0.654 |
atively | -0.640 |
Token | s |
Token ID | 82 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Mehran | +0.443 |
lapt | +0.435 |
etsk | +0.423 |
caut | +0.415 |
unta | +0.413 |
Neg logit contributions | |
toe | -0.321 |
acted | -0.293 |
enough | -0.284 |
ring | -0.284 |
atively | -0.271 |
Token | attorney |
Token ID | 6136 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Mehran | +0.942 |
lapt | +0.924 |
etsk | +0.891 |
caut | +0.874 |
unta | +0.865 |
Neg logit contributions | |
toe | -0.937 |
acted | -0.872 |
ring | -0.849 |
enough | -0.846 |
atively | -0.816 |
Token | pots |
Token ID | 32195 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
toe | +4.632 |
ring | +4.265 |
acted | +4.261 |
works | +4.124 |
enough | +4.108 |
Neg logit contributions | |
Mehran | -4.903 |
lapt | -4.779 |
etsk | -4.655 |
ebin | -4.539 |
unta | -4.501 |
Token | while |
Token ID | 981 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
Mehran | +0.038 |
lapt | +0.037 |
etsk | +0.036 |
caut | +0.035 |
unta | +0.035 |
Neg logit contributions | |
toe | -0.034 |
acted | -0.031 |
ring | -0.030 |
enough | -0.030 |
atively | -0.029 |
Token | digging |
Token ID | 18894 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Mehran | +3.535 |
lapt | +3.486 |
etsk | +3.337 |
caut | +3.284 |
unta | +3.229 |
Neg logit contributions | |
toe | -3.561 |
acted | -3.332 |
enough | -3.241 |
ring | -3.194 |
atively | -3.091 |
Token | at |
Token ID | 379 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Mehran | +1.268 |
lapt | +1.239 |
etsk | +1.196 |
caut | +1.165 |
unta | +1.156 |
Neg logit contributions | |
toe | -1.499 |
acted | -1.403 |
ring | -1.366 |
enough | -1.363 |
atively | -1.316 |
Token | Kh |
Token ID | 5311 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
Mehran | +1.820 |
lapt | +1.765 |
etsk | +1.713 |
caut | +1.671 |
unta | +1.664 |
Neg logit contributions | |
toe | -1.832 |
acted | -1.707 |
enough | -1.656 |
ring | -1.651 |
atively | -1.596 |
Token | uj |
Token ID | 23577 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
Mehran | +6.113 |
etsk | +6.042 |
lapt | +5.966 |
unta | +5.940 |
caut | +5.681 |
Neg logit contributions | |
toe | -5.943 |
acted | -5.541 |
enough | -5.294 |
atively | -5.193 |
ring | -5.092 |
Token | ut |
Token ID | 315 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Mehran | +11.128 |
unta | +11.059 |
etsk | +11.048 |
lapt | +10.316 |
ebin | +10.167 |
Neg logit contributions | |
toe | -8.816 |
acted | -8.273 |
enough | -8.201 |
atively | -7.602 |
works | -7.509 |
Token | Rab |
Token ID | 28559 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Mehran | +2.329 |
lapt | +2.278 |
etsk | +2.222 |
caut | +2.164 |
unta | +2.161 |
Neg logit contributions | |
toe | -1.998 |
acted | -1.858 |
enough | -1.792 |
ring | -1.783 |
atively | -1.725 |
Token | u |
Token ID | 84 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
Mehran | +4.906 |
etsk | +4.725 |
lapt | +4.715 |
unta | +4.629 |
caut | +4.500 |
Neg logit contributions | |
toe | -4.528 |
acted | -4.263 |
enough | -4.094 |
ring | -4.061 |
atively | -3.956 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
Mehran | +3.972 |
lapt | +3.858 |
etsk | +3.780 |
unta | +3.710 |
caut | +3.677 |
Neg logit contributions | |
toe | -3.218 |
acted | -2.994 |
enough | -2.874 |
ring | -2.830 |
atively | -2.755 |
Token | just |
Token ID | 655 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Mehran | +2.675 |
lapt | +2.608 |
etsk | +2.531 |
caut | +2.457 |
unta | +2.441 |
Neg logit contributions | |
toe | -2.769 |
acted | -2.586 |
ring | -2.499 |
enough | -2.492 |
atively | -2.415 |
Token | three |
Token ID | 1115 |
Feature activation | -9.63e+00 |
Pos logit contributions | |
Mehran | +0.250 |
lapt | +0.243 |
etsk | +0.235 |
caut | +0.228 |
unta | +0.226 |
Neg logit contributions | |
toe | -0.282 |
acted | -0.265 |
enough | -0.257 |
ring | -0.257 |
atively | -0.249 |
Token | actions |
Token ID | 4028 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
toe | +5.305 |
acted | +5.207 |
ring | +4.940 |
works | +4.876 |
atively | +4.833 |
Neg logit contributions | |
lapt | -9.520 |
ccording | -9.398 |
Mehran | -8.792 |
mosqu | -8.783 |
caut | -8.744 |
Token | in |
Token ID | 287 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Mehran | +1.392 |
lapt | +1.374 |
etsk | +1.315 |
caut | +1.292 |
unta | +1.271 |
Neg logit contributions | |
toe | -1.639 |
acted | -1.536 |
ring | -1.503 |
enough | -1.490 |
atively | -1.447 |
Token | your |
Token ID | 534 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
toe | +1.011 |
acted | +0.944 |
ring | +0.932 |
enough | +0.903 |
atively | +0.879 |
Neg logit contributions | |
lapt | -1.103 |
Mehran | -1.084 |
etsk | -1.042 |
caut | -1.039 |
ccording | -1.034 |
Token | inbox |
Token ID | 13734 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
Mehran | +1.987 |
lapt | +1.923 |
etsk | +1.841 |
caut | +1.783 |
unta | +1.762 |
Neg logit contributions | |
toe | -3.393 |
acted | -3.208 |
ring | -3.132 |
enough | -3.132 |
atively | -3.051 |
Token | every |
Token ID | 790 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
Mehran | +4.521 |
lapt | +4.257 |
ebin | +4.166 |
etsk | +4.110 |
unta | +4.071 |
Neg logit contributions | |
toe | -4.304 |
acted | -3.992 |
enough | -3.845 |
ring | -3.786 |
atively | -3.664 |
Token | week |
Token ID | 1285 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
Mehran | +3.676 |
ebin | +2.762 |
pload | +2.481 |
lapt | +2.264 |
etsk | +2.167 |
Neg logit contributions | |
toe | -17.169 |
acted | -16.720 |
enough | -16.615 |
enegger | -16.239 |
ring | -15.763 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Mehran | +7.278 |
etsk | +6.637 |
ebin | +6.611 |
unta | +6.566 |
irty | +6.368 |
Neg logit contributions | |
toe | -5.187 |
acted | -4.704 |
enough | -4.530 |
atively | -4.456 |
ring | -4.399 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Mehran | +2.215 |
lapt | +2.117 |
etsk | +2.066 |
caut | +2.021 |
unta | +2.019 |
Neg logit contributions | |
toe | -2.002 |
acted | -1.843 |
enough | -1.793 |
ring | -1.786 |
atively | -1.733 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Mehran | +3.395 |
lapt | +3.171 |
etsk | +3.164 |
unta | +3.107 |
ebin | +3.055 |
Neg logit contributions | |
toe | -2.939 |
acted | -2.723 |
enough | -2.641 |
ring | -2.619 |
atively | -2.563 |
Token | Thank |
Token ID | 10449 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Mehran | +2.710 |
lapt | +2.631 |
etsk | +2.561 |
unta | +2.475 |
caut | +2.470 |
Neg logit contributions | |
toe | -3.004 |
acted | -2.804 |
ring | -2.718 |
enough | -2.705 |
atively | -2.658 |
Token | before |
Token ID | 878 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Mehran | +1.222 |
lapt | +1.198 |
etsk | +1.155 |
caut | +1.128 |
unta | +1.117 |
Neg logit contributions | |
toe | -1.394 |
acted | -1.302 |
ring | -1.267 |
enough | -1.263 |
atively | -1.223 |
Token | , |
Token ID | 11 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Mehran | +0.293 |
lapt | +0.291 |
etsk | +0.282 |
caut | +0.277 |
unta | +0.274 |
Neg logit contributions | |
toe | -0.202 |
acted | -0.182 |
ring | -0.178 |
enough | -0.177 |
atively | -0.169 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
toe | +0.359 |
acted | +0.334 |
ring | +0.326 |
enough | +0.324 |
atively | +0.312 |
Neg logit contributions | |
Mehran | -0.391 |
lapt | -0.383 |
etsk | -0.372 |
caut | -0.364 |
unta | -0.360 |
Token | grid |
Token ID | 10706 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
toe | +0.937 |
acted | +0.879 |
ring | +0.861 |
enough | +0.854 |
atively | +0.829 |
Neg logit contributions | |
Mehran | -0.810 |
lapt | -0.789 |
etsk | -0.767 |
caut | -0.749 |
unta | -0.743 |
Token | automatically |
Token ID | 6338 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
Mehran | +2.914 |
lapt | +2.889 |
etsk | +2.805 |
caut | +2.738 |
unta | +2.714 |
Neg logit contributions | |
toe | -2.720 |
acted | -2.519 |
enough | -2.456 |
ring | -2.409 |
atively | -2.342 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
Mehran | +3.831 |
lapt | +3.723 |
etsk | +3.626 |
caut | +3.549 |
unta | +3.480 |
Neg logit contributions | |
toe | -4.264 |
acted | -3.974 |
ring | -3.871 |
enough | -3.851 |
uther | -3.681 |
Token | itself |
Token ID | 2346 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Mehran | +9.814 |
lapt | +9.693 |
unta | +9.056 |
etsk | +9.022 |
caut | +8.998 |
Neg logit contributions | |
toe | -10.636 |
acted | -9.771 |
enough | -9.591 |
ring | -9.286 |
shire | -9.114 |
Token | each |
Token ID | 1123 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
Mehran | +0.987 |
lapt | +0.969 |
etsk | +0.938 |
caut | +0.921 |
unta | +0.912 |
Neg logit contributions | |
toe | -0.844 |
acted | -0.781 |
ring | -0.758 |
enough | -0.755 |
atively | -0.726 |
Token | update |
Token ID | 4296 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Mehran | +5.804 |
lapt | +5.789 |
etsk | +5.355 |
unta | +5.342 |
caut | +5.326 |
Neg logit contributions | |
toe | -7.958 |
acted | -7.542 |
enough | -7.231 |
ring | -7.213 |
atively | -6.953 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Mehran | +4.632 |
lapt | +4.539 |
etsk | +4.394 |
unta | +4.363 |
caut | +4.358 |
Neg logit contributions | |
toe | -3.586 |
acted | -3.305 |
enough | -3.218 |
ring | -3.158 |
atively | -2.991 |
Token | fit |
Token ID | 4197 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Mehran | +1.023 |
lapt | +1.005 |
etsk | +0.962 |
caut | +0.943 |
unta | +0.933 |
Neg logit contributions | |
toe | -1.193 |
acted | -1.119 |
ring | -1.089 |
enough | -1.085 |
atively | -1.051 |
Token | this |
Token ID | 428 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
toe | +3.674 |
acted | +3.433 |
ring | +3.404 |
enough | +3.356 |
atively | +3.215 |
Neg logit contributions | |
Mehran | -4.169 |
lapt | -4.066 |
etsk | -3.959 |
unta | -3.855 |
caut | -3.844 |
Token | at |
Token ID | 379 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
toe | +0.682 |
acted | +0.638 |
ring | +0.626 |
enough | +0.622 |
atively | +0.601 |
Neg logit contributions | |
Mehran | -0.642 |
lapt | -0.625 |
etsk | -0.605 |
caut | -0.591 |
unta | -0.588 |
Token | the |
Token ID | 262 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Mehran | +1.417 |
lapt | +1.388 |
etsk | +1.335 |
caut | +1.314 |
unta | +1.292 |
Neg logit contributions | |
toe | -1.542 |
acted | -1.435 |
ring | -1.393 |
enough | -1.390 |
atively | -1.343 |
Token | current |
Token ID | 1459 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
toe | +0.421 |
acted | +0.394 |
ring | +0.388 |
enough | +0.385 |
atively | +0.374 |
Neg logit contributions | |
Mehran | -0.334 |
lapt | -0.325 |
etsk | -0.314 |
caut | -0.305 |
unta | -0.303 |
Token | block |
Token ID | 2512 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
Mehran | +1.800 |
lapt | +1.770 |
etsk | +1.682 |
caut | +1.651 |
unta | +1.624 |
Neg logit contributions | |
toe | -2.380 |
acted | -2.240 |
ring | -2.173 |
enough | -2.168 |
atively | -2.100 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
Mehran | +0.063 |
lapt | +0.062 |
etsk | +0.060 |
caut | +0.059 |
unta | +0.058 |
Neg logit contributions | |
toe | -0.053 |
acted | -0.049 |
ring | -0.047 |
enough | -0.047 |
atively | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Mehran | +10.986 |
lapt | +10.620 |
ebin | +10.495 |
etsk | +10.203 |
caut | +10.178 |
Neg logit contributions | |
toe | -9.202 |
acted | -8.818 |
enough | -8.050 |
ring | -7.748 |
enegger | -7.697 |
Token | These |
Token ID | 2312 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
toe | +0.116 |
acted | +0.107 |
ring | +0.104 |
enough | +0.103 |
atively | +0.099 |
Neg logit contributions | |
Mehran | -0.149 |
lapt | -0.147 |
etsk | -0.143 |
caut | -0.140 |
unta | -0.139 |
Token | have |
Token ID | 423 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
Mehran | +2.474 |
lapt | +2.443 |
etsk | +2.344 |
caut | +2.297 |
unta | +2.250 |
Neg logit contributions | |
toe | -2.859 |
acted | -2.664 |
ring | -2.576 |
enough | -2.576 |
atively | -2.488 |
Token | not |
Token ID | 407 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
toe | +3.456 |
acted | +3.226 |
ring | +3.127 |
enough | +3.115 |
atively | +3.034 |
Neg logit contributions | |
Mehran | -4.749 |
lapt | -4.584 |
etsk | -4.538 |
caut | -4.391 |
unta | -4.387 |
Token | yet |
Token ID | 1865 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
toe | +4.296 |
acted | +4.067 |
enough | +3.891 |
ring | +3.861 |
atively | +3.775 |
Neg logit contributions | |
Mehran | -7.386 |
lapt | -7.218 |
etsk | -7.036 |
caut | -6.944 |
unta | -6.862 |
Token | films |
Token ID | 7328 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
toe | +1.660 |
acted | +1.546 |
ring | +1.516 |
enough | +1.496 |
works | +1.442 |
Neg logit contributions | |
Mehran | -1.750 |
lapt | -1.732 |
etsk | -1.676 |
caut | -1.639 |
unta | -1.610 |
Token | Seven |
Token ID | 13723 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Mehran | +0.016 |
lapt | +0.016 |
etsk | +0.015 |
caut | +0.015 |
unta | +0.015 |
Neg logit contributions | |
toe | -0.012 |
acted | -0.011 |
ring | -0.011 |
enough | -0.011 |
atively | -0.010 |
Token | Samurai |
Token ID | 23882 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
toe | +1.702 |
acted | +1.451 |
ring | +1.411 |
enough | +1.347 |
works | +1.256 |
Neg logit contributions | |
Mehran | -4.813 |
lapt | -4.786 |
etsk | -4.639 |
caut | -4.573 |
ebin | -4.533 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Mehran | +0.604 |
lapt | +0.589 |
etsk | +0.573 |
caut | +0.564 |
unta | +0.562 |
Neg logit contributions | |
toe | -0.497 |
acted | -0.459 |
enough | -0.442 |
ring | -0.439 |
atively | -0.428 |
Token | Y |
Token ID | 575 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
Mehran | +1.067 |
lapt | +1.041 |
etsk | +1.005 |
caut | +0.988 |
unta | +0.981 |
Neg logit contributions | |
toe | -0.984 |
acted | -0.913 |
ring | -0.886 |
enough | -0.882 |
atively | -0.855 |
Token | oj |
Token ID | 13210 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
Mehran | +3.433 |
lapt | +3.323 |
unta | +3.279 |
etsk | +3.262 |
caut | +3.141 |
Neg logit contributions | |
toe | -5.138 |
acted | -4.867 |
enough | -4.794 |
ring | -4.690 |
atively | -4.539 |
Token | im |
Token ID | 320 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
unta | +5.098 |
Mehran | +4.815 |
lapt | +4.323 |
undai | +4.245 |
etsk | +4.231 |
Neg logit contributions | |
toe | -15.004 |
acted | -14.676 |
enough | -14.261 |
enegger | -14.032 |
hole | -13.836 |
Token | bo |
Token ID | 2127 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Mehran | +2.333 |
lapt | +2.267 |
etsk | +2.250 |
unta | +2.209 |
caut | +2.193 |
Neg logit contributions | |
toe | -1.143 |
acted | -1.060 |
enough | -1.020 |
ring | -0.986 |
atively | -0.944 |
Token | , |
Token ID | 11 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Mehran | +2.284 |
lapt | +2.240 |
etsk | +2.188 |
unta | +2.151 |
caut | +2.143 |
Neg logit contributions | |
toe | -1.494 |
acted | -1.381 |
enough | -1.315 |
ring | -1.300 |
atively | -1.268 |
Token | among |
Token ID | 1871 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Mehran | +0.463 |
lapt | +0.454 |
etsk | +0.439 |
caut | +0.430 |
unta | +0.426 |
Neg logit contributions | |
toe | -0.441 |
acted | -0.410 |
ring | -0.399 |
enough | -0.397 |
atively | -0.384 |
Token | others |
Token ID | 1854 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Mehran | +0.583 |
lapt | +0.569 |
etsk | +0.552 |
caut | +0.541 |
unta | +0.537 |
Neg logit contributions | |
toe | -0.491 |
acted | -0.452 |
enough | -0.437 |
ring | -0.437 |
atively | -0.421 |
Token | ig |
Token ID | 328 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
toe | +0.795 |
acted | +0.753 |
enough | +0.735 |
ring | +0.729 |
atively | +0.710 |
Neg logit contributions | |
Mehran | -0.478 |
lapt | -0.467 |
etsk | -0.450 |
unta | -0.436 |
caut | -0.435 |
Token | lia |
Token ID | 24660 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Mehran | +0.471 |
lapt | +0.465 |
etsk | +0.450 |
unta | +0.439 |
caut | +0.437 |
Neg logit contributions | |
toe | -0.540 |
acted | -0.507 |
enough | -0.491 |
ring | -0.489 |
atively | -0.473 |
Token | MAS |
Token ID | 32337 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
Mehran | +0.092 |
lapt | +0.091 |
etsk | +0.088 |
caut | +0.086 |
unta | +0.086 |
Neg logit contributions | |
toe | -0.078 |
acted | -0.072 |
ring | -0.070 |
enough | -0.070 |
atively | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Mehran | +5.788 |
lapt | +5.651 |
etsk | +5.555 |
unta | +5.474 |
caut | +5.436 |
Neg logit contributions | |
toe | -4.672 |
acted | -4.257 |
enough | -4.164 |
ring | -3.950 |
atively | -3.891 |
Token | Prince |
Token ID | 9005 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Mehran | +1.306 |
lapt | +1.280 |
etsk | +1.232 |
caut | +1.210 |
unta | +1.198 |
Neg logit contributions | |
toe | -1.397 |
acted | -1.300 |
enough | -1.267 |
ring | -1.266 |
atively | -1.223 |
Token | Jun |
Token ID | 7653 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Mehran | +0.284 |
lapt | +0.278 |
etsk | +0.269 |
caut | +0.263 |
unta | +0.261 |
Neg logit contributions | |
toe | -0.272 |
acted | -0.253 |
ring | -0.246 |
enough | -0.246 |
atively | -0.237 |
Token | io |
Token ID | 952 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
etsk | +8.973 |
Mehran | +8.905 |
unta | +8.818 |
ebin | +8.536 |
lapt | +8.381 |
Neg logit contributions | |
toe | -10.662 |
acted | -9.793 |
atively | -9.257 |
enough | -9.105 |
ring | -8.958 |
Token | Val |
Token ID | 3254 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
Mehran | +4.368 |
lapt | +4.085 |
etsk | +3.960 |
unta | +3.932 |
caut | +3.879 |
Neg logit contributions | |
toe | -5.832 |
enough | -5.335 |
acted | -5.312 |
atively | -5.148 |
ring | -5.141 |
Token | er |
Token ID | 263 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
Mehran | +3.607 |
etsk | +3.475 |
lapt | +3.439 |
unta | +3.401 |
ebin | +3.351 |
Neg logit contributions | |
toe | -2.740 |
acted | -2.518 |
enough | -2.426 |
ring | -2.413 |
atively | -2.356 |
Token | io |
Token ID | 952 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
toe | +0.046 |
acted | +0.043 |
ring | +0.042 |
enough | +0.042 |
atively | +0.041 |
Neg logit contributions | |
Mehran | -0.041 |
lapt | -0.041 |
etsk | -0.039 |
caut | -0.038 |
ccording | -0.037 |
Token | Borg |
Token ID | 29004 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Mehran | +1.406 |
lapt | +1.374 |
etsk | +1.349 |
caut | +1.326 |
unta | +1.311 |
Neg logit contributions | |
toe | -0.829 |
acted | -0.730 |
enough | -0.718 |
ring | -0.698 |
atively | -0.676 |
Token | months |
Token ID | 1933 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
toe | +0.267 |
acted | +0.249 |
ring | +0.244 |
enough | +0.241 |
atively | +0.234 |
Neg logit contributions | |
Mehran | -0.259 |
lapt | -0.254 |
etsk | -0.246 |
caut | -0.240 |
unta | -0.238 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
Mehran | +2.006 |
lapt | +1.936 |
etsk | +1.847 |
caut | +1.773 |
unta | +1.733 |
Neg logit contributions | |
toe | -3.883 |
acted | -3.710 |
ring | -3.607 |
enough | -3.602 |
atively | -3.530 |
Token | , |
Token ID | 11 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
toe | +2.226 |
acted | +2.068 |
ring | +2.028 |
enough | +2.002 |
atively | +1.921 |
Neg logit contributions | |
Mehran | -2.993 |
lapt | -2.965 |
etsk | -2.877 |
caut | -2.827 |
unta | -2.792 |
Token | Jo |
Token ID | 5302 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
toe | +0.557 |
acted | +0.521 |
ring | +0.510 |
enough | +0.506 |
atively | +0.490 |
Neg logit contributions | |
Mehran | -0.543 |
lapt | -0.537 |
etsk | -0.518 |
caut | -0.508 |
unta | -0.501 |
Token | Song |
Token ID | 10940 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Mehran | +1.794 |
lapt | +1.725 |
etsk | +1.648 |
unta | +1.570 |
ebin | +1.559 |
Neg logit contributions | |
toe | -4.277 |
acted | -4.044 |
enough | -3.973 |
ring | -3.966 |
atively | -3.902 |
Token | Gy |
Token ID | 18488 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Mehran | +0.457 |
lapt | +0.448 |
etsk | +0.434 |
caut | +0.426 |
unta | +0.422 |
Neg logit contributions | |
toe | -0.385 |
acted | -0.356 |
ring | -0.346 |
enough | -0.344 |
atively | -0.331 |
Token | u |
Token ID | 84 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
unta | +8.458 |
Mehran | +8.252 |
etsk | +8.111 |
ebin | +8.108 |
ongyang | +7.832 |
Neg logit contributions | |
toe | -10.887 |
acted | -10.120 |
enough | -9.783 |
ring | -9.723 |
works | -9.602 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Mehran | +6.771 |
lapt | +6.702 |
unta | +6.592 |
etsk | +6.548 |
pload | +6.409 |
Neg logit contributions | |
toe | -5.034 |
acted | -4.556 |
enough | -4.375 |
ring | -4.294 |
atively | -4.231 |
Token | director |
Token ID | 3437 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Mehran | +1.855 |
lapt | +1.805 |
etsk | +1.747 |
caut | +1.698 |
unta | +1.690 |
Neg logit contributions | |
toe | -2.014 |
acted | -1.871 |
enough | -1.823 |
ring | -1.818 |
atively | -1.753 |
Token | of |
Token ID | 286 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Mehran | +0.656 |
lapt | +0.637 |
etsk | +0.626 |
caut | +0.607 |
unta | +0.604 |
Neg logit contributions | |
toe | -0.682 |
acted | -0.638 |
enough | -0.621 |
ring | -0.613 |
atively | -0.588 |
Token | the |
Token ID | 262 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Mehran | +0.168 |
lapt | +0.164 |
etsk | +0.159 |
caut | +0.155 |
unta | +0.153 |
Neg logit contributions | |
toe | -0.183 |
acted | -0.171 |
ring | -0.167 |
enough | -0.166 |
atively | -0.161 |
Token | the |
Token ID | 262 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Mehran | +0.464 |
lapt | +0.454 |
etsk | +0.438 |
caut | +0.429 |
unta | +0.425 |
Neg logit contributions | |
toe | -0.476 |
acted | -0.444 |
ring | -0.432 |
enough | -0.430 |
atively | -0.416 |
Token | National |
Token ID | 2351 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
toe | +0.508 |
acted | +0.475 |
ring | +0.464 |
enough | +0.460 |
atively | +0.446 |
Neg logit contributions | |
Mehran | -0.489 |
lapt | -0.483 |
etsk | -0.466 |
caut | -0.456 |
unta | -0.449 |
Token | Ocean |
Token ID | 10692 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
Mehran | +3.398 |
lapt | +3.213 |
etsk | +3.122 |
unta | +3.075 |
caut | +3.067 |
Neg logit contributions | |
toe | -3.058 |
acted | -2.796 |
enough | -2.728 |
ring | -2.718 |
atively | -2.624 |
Token | ic |
Token ID | 291 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Mehran | +4.707 |
etsk | +4.551 |
lapt | +4.544 |
caut | +4.370 |
unta | +4.340 |
Neg logit contributions | |
toe | -3.488 |
acted | -3.177 |
enough | -3.118 |
ring | -3.020 |
atively | -2.929 |
Token | and |
Token ID | 290 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Mehran | +1.958 |
lapt | +1.885 |
etsk | +1.815 |
caut | +1.766 |
unta | +1.754 |
Neg logit contributions | |
toe | -2.106 |
acted | -1.963 |
enough | -1.914 |
ring | -1.900 |
atively | -1.835 |
Token | Atmospheric |
Token ID | 41516 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
Mehran | +2.726 |
lapt | +2.630 |
etsk | +2.538 |
caut | +2.490 |
unta | +2.487 |
Neg logit contributions | |
toe | -2.586 |
acted | -2.393 |
enough | -2.322 |
ring | -2.315 |
atively | -2.238 |
Token | Administration |
Token ID | 8694 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Mehran | +6.795 |
etsk | +5.969 |
� | +5.901 |
lapt | +5.602 |
unta | +5.578 |
Neg logit contributions | |
toe | -13.225 |
acted | -12.272 |
ring | -12.148 |
enough | -11.972 |
uther | -11.896 |
Token | � |
Token ID | 447 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Mehran | +2.395 |
lapt | +2.327 |
etsk | +2.273 |
unta | +2.233 |
caut | +2.223 |
Neg logit contributions | |
toe | -1.742 |
acted | -1.600 |
enough | -1.537 |
ring | -1.517 |
atively | -1.466 |
Token | � |
Token ID | 247 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Mehran | +1.661 |
lapt | +1.605 |
etsk | +1.555 |
caut | +1.501 |
unta | +1.481 |
Neg logit contributions | |
toe | -2.604 |
acted | -2.440 |
ring | -2.390 |
enough | -2.387 |
atively | -2.310 |
Token | s |
Token ID | 82 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mehran | +1.460 |
lapt | +1.425 |
etsk | +1.393 |
caut | +1.364 |
unta | +1.357 |
Neg logit contributions | |
toe | -1.063 |
acted | -0.975 |
enough | -0.939 |
ring | -0.936 |
atively | -0.898 |
Token | National |
Token ID | 2351 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Mehran | +0.913 |
lapt | +0.892 |
etsk | +0.860 |
caut | +0.843 |
unta | +0.836 |
Neg logit contributions | |
toe | -0.979 |
acted | -0.913 |
ring | -0.890 |
enough | -0.887 |
atively | -0.857 |
Token | decision |
Token ID | 2551 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
toe | +0.833 |
acted | +0.784 |
ring | +0.764 |
enough | +0.756 |
atively | +0.738 |
Neg logit contributions | |
Mehran | -0.749 |
lapt | -0.733 |
etsk | -0.713 |
caut | -0.695 |
unta | -0.685 |
Token | of |
Token ID | 286 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Mehran | +3.691 |
lapt | +3.602 |
etsk | +3.526 |
caut | +3.459 |
unta | +3.452 |
Neg logit contributions | |
toe | -2.937 |
acted | -2.671 |
enough | -2.638 |
ring | -2.556 |
atively | -2.457 |
Token | several |
Token ID | 1811 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
Mehran | +1.219 |
lapt | +1.188 |
etsk | +1.150 |
caut | +1.124 |
unta | +1.115 |
Neg logit contributions | |
toe | -1.220 |
acted | -1.132 |
ring | -1.100 |
enough | -1.100 |
atively | -1.058 |
Token | Silicon |
Token ID | 18210 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
toe | +0.381 |
acted | +0.355 |
ring | +0.348 |
enough | +0.344 |
atively | +0.334 |
Neg logit contributions | |
Mehran | -0.382 |
lapt | -0.375 |
etsk | -0.363 |
caut | -0.355 |
unta | -0.351 |
Token | Valley |
Token ID | 6916 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Mehran | +3.171 |
lapt | +3.087 |
etsk | +2.986 |
caut | +2.876 |
unta | +2.875 |
Neg logit contributions | |
toe | -4.173 |
acted | -3.920 |
enough | -3.829 |
ring | -3.814 |
atively | -3.700 |
Token | mog |
Token ID | 32985 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Mehran | +0.599 |
lapt | +0.586 |
etsk | +0.566 |
caut | +0.553 |
unta | +0.547 |
Neg logit contributions | |
toe | -0.666 |
acted | -0.623 |
ring | -0.609 |
enough | -0.606 |
atively | -0.586 |
Token | uls |
Token ID | 5753 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Mehran | +3.452 |
unta | +3.285 |
etsk | +3.041 |
pload | +2.942 |
irty | +2.919 |
Neg logit contributions | |
toe | -15.507 |
acted | -14.605 |
enough | -14.569 |
backer | -14.441 |
shire | -14.286 |
Token | to |
Token ID | 284 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Mehran | +2.741 |
lapt | +2.649 |
etsk | +2.581 |
caut | +2.538 |
unta | +2.530 |
Neg logit contributions | |
toe | -1.933 |
acted | -1.755 |
enough | -1.711 |
ring | -1.698 |
atively | -1.622 |
Token | pour |
Token ID | 12797 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Mehran | +2.008 |
lapt | +1.961 |
etsk | +1.892 |
caut | +1.840 |
unta | +1.825 |
Neg logit contributions | |
toe | -2.533 |
acted | -2.389 |
ring | -2.319 |
enough | -2.317 |
atively | -2.245 |
Token | millions |
Token ID | 5242 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
toe | +0.092 |
acted | +0.086 |
ring | +0.084 |
enough | +0.083 |
atively | +0.081 |
Neg logit contributions | |
Mehran | -0.085 |
lapt | -0.083 |
etsk | -0.081 |
caut | -0.079 |
unta | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Mehran | +3.281 |
lapt | +3.126 |
etsk | +3.048 |
unta | +2.937 |
caut | +2.921 |
Neg logit contributions | |
toe | -4.610 |
acted | -4.383 |
enough | -4.260 |
ring | -4.225 |
atively | -4.087 |
Token | San |
Token ID | 2986 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
toe | +1.751 |
acted | +1.634 |
ring | +1.600 |
enough | +1.572 |
atively | +1.531 |
Neg logit contributions | |
Mehran | -1.711 |
lapt | -1.693 |
etsk | -1.642 |
caut | -1.598 |
unta | -1.569 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Mehran | +4.842 |
lapt | +4.511 |
etsk | +4.327 |
unta | +4.313 |
caut | +4.293 |
Neg logit contributions | |
toe | -7.583 |
acted | -7.020 |
ring | -7.000 |
enough | -6.983 |
atively | -6.826 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Mehran | +1.220 |
lapt | +1.181 |
etsk | +1.114 |
caut | +1.098 |
unta | +1.086 |
Neg logit contributions | |
toe | -1.936 |
acted | -1.820 |
enough | -1.788 |
ring | -1.782 |
atively | -1.740 |
Token | , |
Token ID | 11 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
toe | +2.405 |
acted | +2.171 |
ring | +2.105 |
enough | +2.076 |
atively | +1.992 |
Neg logit contributions | |
Mehran | -4.183 |
lapt | -4.122 |
etsk | -4.013 |
caut | -3.945 |
unta | -3.906 |
Token | K |
Token ID | 509 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
toe | +0.065 |
acted | +0.060 |
ring | +0.059 |
enough | +0.058 |
atively | +0.056 |
Neg logit contributions | |
Mehran | -0.066 |
lapt | -0.065 |
etsk | -0.063 |
caut | -0.061 |
unta | -0.061 |
Token | uy |
Token ID | 4669 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
Mehran | +2.041 |
lapt | +1.937 |
etsk | +1.867 |
unta | +1.809 |
ebin | +1.736 |
Neg logit contributions | |
toe | -5.405 |
acted | -5.150 |
enough | -5.051 |
ring | -5.023 |
atively | -4.918 |
Token | k |
Token ID | 74 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
etsk | +10.144 |
Mehran | +10.032 |
unta | +9.814 |
ebin | +9.375 |
pload | +9.136 |
Neg logit contributions | |
toe | -8.537 |
acted | -8.115 |
atively | -7.737 |
enough | -7.705 |
ring | -7.534 |
Token | end |
Token ID | 437 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Mehran | +3.668 |
lapt | +3.580 |
etsk | +3.525 |
unta | +3.454 |
caut | +3.423 |
Neg logit contributions | |
toe | -1.906 |
acted | -1.721 |
ring | -1.636 |
enough | -1.636 |
atively | -1.554 |
Token | all |
Token ID | 439 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
toe | +0.311 |
acted | +0.288 |
ring | +0.281 |
enough | +0.279 |
atively | +0.264 |
Neg logit contributions | |
Mehran | -0.428 |
lapt | -0.428 |
caut | -0.408 |
etsk | -0.405 |
ccording | -0.402 |
Token | became |
Token ID | 2627 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
toe | +1.418 |
acted | +1.319 |
ring | +1.284 |
enough | +1.274 |
atively | +1.229 |
Neg logit contributions | |
Mehran | -1.538 |
lapt | -1.511 |
etsk | -1.459 |
caut | -1.434 |
unta | -1.414 |
Token | a |
Token ID | 257 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Mehran | +3.035 |
lapt | +2.895 |
etsk | +2.804 |
caut | +2.777 |
unta | +2.764 |
Neg logit contributions | |
toe | -3.340 |
acted | -3.078 |
enough | -3.030 |
ring | -3.029 |
works | -2.896 |
Token | forward |
Token ID | 2651 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
toe | +4.614 |
ring | +4.217 |
acted | +4.165 |
atively | +4.132 |
enough | +4.072 |
Neg logit contributions | |
lapt | -3.758 |
Mehran | -3.745 |
caut | -3.558 |
ccording | -3.506 |
etsk | -3.503 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
toe | +2.562 |
acted | +2.318 |
ring | +2.268 |
enough | +2.231 |
atively | +2.181 |
Neg logit contributions | |
Mehran | -4.025 |
lapt | -3.977 |
etsk | -3.844 |
caut | -3.808 |
unta | -3.751 |
Token | , |
Token ID | 11 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
toe | +1.200 |
acted | +1.116 |
ring | +1.098 |
enough | +1.087 |
atively | +1.057 |
Neg logit contributions | |
Mehran | -1.016 |
lapt | -0.991 |
etsk | -0.958 |
caut | -0.938 |
unta | -0.927 |
Token | while |
Token ID | 981 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
toe | +0.392 |
acted | +0.364 |
ring | +0.357 |
enough | +0.352 |
atively | +0.342 |
Neg logit contributions | |
Mehran | -0.438 |
lapt | -0.431 |
etsk | -0.418 |
caut | -0.408 |
unta | -0.407 |
Token | K |
Token ID | 509 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
Mehran | +1.065 |
lapt | +1.045 |
etsk | +1.009 |
caut | +0.988 |
unta | +0.975 |
Neg logit contributions | |
toe | -1.089 |
acted | -1.016 |
ring | -0.987 |
enough | -0.985 |
atively | -0.948 |
Token | uy |
Token ID | 4669 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Mehran | +1.956 |
lapt | +1.875 |
etsk | +1.856 |
unta | +1.820 |
ebin | +1.741 |
Neg logit contributions | |
toe | -5.611 |
acted | -5.371 |
enough | -5.292 |
ring | -5.201 |
atively | -5.127 |
Token | t |
Token ID | 83 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
unta | +7.974 |
ebin | +7.897 |
etsk | +7.893 |
Mehran | +7.872 |
pload | +7.263 |
Neg logit contributions | |
toe | -10.174 |
acted | -10.055 |
atively | -9.614 |
enough | -9.551 |
ring | -9.536 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
toe | +0.025 |
acted | +0.023 |
ring | +0.022 |
enough | +0.022 |
atively | +0.022 |
Neg logit contributions | |
Mehran | -0.025 |
lapt | -0.024 |
etsk | -0.023 |
caut | -0.023 |
unta | -0.023 |
Token | Bruno |
Token ID | 31045 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
Mehran | +0.200 |
lapt | +0.195 |
etsk | +0.188 |
caut | +0.184 |
unta | +0.182 |
Neg logit contributions | |
toe | -0.204 |
acted | -0.190 |
ring | -0.185 |
enough | -0.185 |
atively | -0.178 |
Token | Mart |
Token ID | 3981 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Mehran | +0.600 |
lapt | +0.588 |
etsk | +0.567 |
caut | +0.558 |
unta | +0.551 |
Neg logit contributions | |
toe | -0.604 |
acted | -0.563 |
enough | -0.548 |
ring | -0.547 |
atively | -0.528 |
Token | ins |
Token ID | 1040 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Mehran | +1.690 |
lapt | +1.663 |
etsk | +1.613 |
unta | +1.582 |
ebin | +1.572 |
Neg logit contributions | |
toe | -1.573 |
acted | -1.477 |
ring | -1.427 |
enough | -1.427 |
atively | -1.375 |
Token | obligations |
Token ID | 13675 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
toe | +5.931 |
acted | +5.533 |
ring | +5.512 |
enough | +5.190 |
works | +5.186 |
Neg logit contributions | |
Mehran | -8.167 |
lapt | -8.044 |
etsk | -7.693 |
caut | -7.637 |
ebin | -7.616 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
toe | +0.293 |
acted | +0.269 |
ring | +0.260 |
enough | +0.260 |
atively | +0.249 |
Neg logit contributions | |
Mehran | -0.393 |
lapt | -0.385 |
etsk | -0.374 |
caut | -0.367 |
unta | -0.364 |
Token | which |
Token ID | 543 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Mehran | +1.340 |
lapt | +1.308 |
etsk | +1.257 |
caut | +1.233 |
unta | +1.220 |
Neg logit contributions | |
toe | -1.447 |
acted | -1.346 |
enough | -1.309 |
ring | -1.308 |
atively | -1.261 |
Token | often |
Token ID | 1690 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
Mehran | +1.077 |
lapt | +1.053 |
etsk | +1.011 |
caut | +0.986 |
unta | +0.975 |
Neg logit contributions | |
toe | -1.406 |
acted | -1.317 |
enough | -1.285 |
ring | -1.285 |
atively | -1.243 |
Token | were |
Token ID | 547 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Mehran | +2.683 |
lapt | +2.630 |
etsk | +2.559 |
caut | +2.467 |
unta | +2.445 |
Neg logit contributions | |
toe | -3.762 |
acted | -3.525 |
enough | -3.438 |
ring | -3.409 |
atively | -3.337 |
Token | priced |
Token ID | 19744 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Mehran | +1.360 |
lapt | +1.334 |
etsk | +1.283 |
caut | +1.258 |
unta | +1.241 |
Neg logit contributions | |
toe | -1.462 |
acted | -1.356 |
ring | -1.319 |
enough | -1.315 |
atively | -1.270 |
Token | based |
Token ID | 1912 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Mehran | +8.707 |
lapt | +8.223 |
etsk | +7.984 |
caut | +7.848 |
unta | +7.543 |
Neg logit contributions | |
toe | -10.790 |
acted | -9.929 |
enegger | -9.704 |
enough | -9.685 |
ring | -9.595 |
Token | on |
Token ID | 319 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Mehran | +2.834 |
lapt | +2.765 |
etsk | +2.666 |
caut | +2.617 |
unta | +2.567 |
Neg logit contributions | |
toe | -3.830 |
acted | -3.566 |
enough | -3.488 |
ring | -3.459 |
hole | -3.329 |
Token | giant |
Token ID | 6175 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
toe | +0.286 |
acted | +0.268 |
ring | +0.261 |
enough | +0.259 |
atively | +0.252 |
Neg logit contributions | |
Mehran | -0.267 |
lapt | -0.262 |
etsk | -0.253 |
caut | -0.247 |
unta | -0.245 |
Token | pools |
Token ID | 20354 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Mehran | +2.318 |
lapt | +2.266 |
etsk | +2.160 |
caut | +2.115 |
unta | +2.094 |
Neg logit contributions | |
toe | -2.568 |
acted | -2.395 |
enough | -2.339 |
ring | -2.324 |
atively | -2.241 |
Token | of |
Token ID | 286 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
toe | +0.220 |
acted | +0.204 |
ring | +0.198 |
enough | +0.198 |
atively | +0.190 |
Neg logit contributions | |
Mehran | -0.236 |
lapt | -0.231 |
etsk | -0.224 |
caut | -0.220 |
unta | -0.217 |
Token | in |
Token ID | 287 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
Mehran | +1.809 |
lapt | +1.781 |
etsk | +1.711 |
caut | +1.675 |
unta | +1.660 |
Neg logit contributions | |
toe | -1.868 |
acted | -1.741 |
enough | -1.698 |
ring | -1.688 |
atively | -1.628 |
Token | ppm |
Token ID | 39719 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Mehran | +0.051 |
lapt | +0.050 |
etsk | +0.048 |
caut | +0.047 |
unta | +0.046 |
Neg logit contributions | |
toe | -0.054 |
acted | -0.050 |
ring | -0.049 |
enough | -0.049 |
atively | -0.047 |
Token | measured |
Token ID | 8630 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
Mehran | +1.156 |
lapt | +1.138 |
etsk | +1.103 |
caut | +1.079 |
unta | +1.073 |
Neg logit contributions | |
toe | -0.988 |
acted | -0.917 |
ring | -0.890 |
enough | -0.888 |
atively | -0.854 |
Token | at |
Token ID | 379 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
Mehran | +5.658 |
lapt | +5.629 |
etsk | +5.377 |
unta | +5.260 |
caut | +5.219 |
Neg logit contributions | |
toe | -6.961 |
acted | -6.527 |
enough | -6.479 |
ring | -6.257 |
atively | -6.121 |
Token | M |
Token ID | 337 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
Mehran | +3.327 |
lapt | +3.260 |
etsk | +3.106 |
unta | +3.053 |
caut | +3.050 |
Neg logit contributions | |
toe | -3.713 |
acted | -3.488 |
enough | -3.387 |
ring | -3.376 |
atively | -3.262 |
Token | auna |
Token ID | 32837 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Mehran | +1.686 |
lapt | +1.580 |
etsk | +1.490 |
unta | +1.460 |
ebin | +1.329 |
Neg logit contributions | |
toe | -7.450 |
acted | -7.229 |
enough | -7.105 |
ring | -7.032 |
atively | -6.880 |
Token | Lo |
Token ID | 6706 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
Mehran | +8.220 |
etsk | +7.462 |
lapt | +7.288 |
unta | +7.256 |
pload | +6.856 |
Neg logit contributions | |
toe | -11.633 |
acted | -11.225 |
enough | -11.000 |
ring | -10.905 |
enegger | -10.832 |
Token | a |
Token ID | 64 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
Mehran | +6.089 |
lapt | +5.833 |
etsk | +5.823 |
unta | +5.763 |
ebin | +5.676 |
Neg logit contributions | |
toe | -3.758 |
acted | -3.425 |
ring | -3.278 |
enough | -3.274 |
atively | -3.093 |
Token | observ |
Token ID | 3799 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Mehran | +4.302 |
lapt | +4.256 |
etsk | +4.131 |
unta | +4.062 |
caut | +4.047 |
Neg logit contributions | |
toe | -3.582 |
acted | -3.326 |
enough | -3.234 |
ring | -3.156 |
atively | -3.107 |
Token | atory |
Token ID | 2870 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Mehran | +2.232 |
lapt | +2.193 |
etsk | +2.152 |
caut | +2.093 |
unta | +2.089 |
Neg logit contributions | |
toe | -1.957 |
acted | -1.788 |
enough | -1.736 |
ring | -1.732 |
atively | -1.646 |
Token | ( |
Token ID | 357 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
toe | +1.554 |
acted | +1.429 |
ring | +1.408 |
enough | +1.368 |
works | +1.330 |
Neg logit contributions | |
Mehran | -2.021 |
lapt | -1.979 |
etsk | -1.917 |
caut | -1.892 |
ebin | -1.860 |
Token | 2004 |
Token ID | 5472 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
toe | +0.171 |
acted | +0.161 |
ring | +0.157 |
enough | +0.156 |
atively | +0.152 |
Neg logit contributions | |
Mehran | -0.132 |
lapt | -0.130 |
etsk | -0.125 |
caut | -0.122 |
unta | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
toe | +2.435 |
acted | +2.247 |
ring | +2.184 |
enough | +2.157 |
atively | +2.077 |
Neg logit contributions | |
Mehran | -3.595 |
lapt | -3.550 |
etsk | -3.451 |
caut | -3.398 |
unta | -3.346 |
Token |
|
Token ID | 198 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
lapt | +0.023 |
Mehran | +0.023 |
etsk | +0.022 |
caut | +0.022 |
ccording | +0.022 |
Neg logit contributions | |
toe | -0.017 |
acted | -0.015 |
ring | -0.015 |
enough | -0.015 |
atively | -0.014 |
Token | 5 |
Token ID | 20 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
toe | +0.345 |
acted | +0.320 |
ring | +0.312 |
enough | +0.310 |
atively | +0.299 |
Neg logit contributions | |
Mehran | -0.390 |
lapt | -0.383 |
etsk | -0.370 |
caut | -0.363 |
unta | -0.359 |
Token | million |
Token ID | 1510 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
toe | +2.021 |
acted | +1.846 |
ring | +1.787 |
enough | +1.772 |
atively | +1.697 |
Neg logit contributions | |
Mehran | -3.070 |
lapt | -3.019 |
etsk | -2.936 |
caut | -2.884 |
unta | -2.859 |
Token | Estimated |
Token ID | 47737 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
Mehran | +3.116 |
lapt | +3.048 |
caut | +2.871 |
etsk | +2.862 |
unta | +2.824 |
Neg logit contributions | |
toe | -3.035 |
acted | -2.802 |
ring | -2.722 |
enough | -2.721 |
atively | -2.605 |
Token | number |
Token ID | 1271 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Mehran | +8.541 |
lapt | +8.397 |
caut | +7.804 |
unta | +7.419 |
ccording | +7.360 |
Neg logit contributions | |
toe | -10.957 |
acted | -10.079 |
enough | -9.739 |
ring | -9.670 |
backer | -9.402 |
Token | of |
Token ID | 286 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Mehran | +3.555 |
lapt | +3.384 |
etsk | +3.297 |
unta | +3.226 |
caut | +3.181 |
Neg logit contributions | |
toe | -3.857 |
acted | -3.575 |
enough | -3.504 |
ring | -3.470 |
atively | -3.351 |
Token | Buddh |
Token ID | 20921 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Mehran | +2.010 |
lapt | +1.962 |
etsk | +1.880 |
caut | +1.855 |
unta | +1.831 |
Neg logit contributions | |
toe | -2.032 |
acted | -1.882 |
ring | -1.831 |
enough | -1.827 |
atively | -1.757 |
Token | ists |
Token ID | 1023 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Mehran | +0.257 |
lapt | +0.257 |
etsk | +0.248 |
caut | +0.247 |
unta | +0.242 |
Neg logit contributions | |
toe | -0.101 |
acted | -0.091 |
ring | -0.086 |
enough | -0.085 |
atively | -0.081 |
Token | in |
Token ID | 287 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
Mehran | +1.062 |
lapt | +1.039 |
etsk | +1.000 |
caut | +0.978 |
unta | +0.967 |
Neg logit contributions | |
toe | -1.244 |
acted | -1.163 |
ring | -1.135 |
enough | -1.131 |
atively | -1.095 |
Token | Alberta |
Token ID | 15555 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Mehran | +0.912 |
lapt | +0.893 |
etsk | +0.860 |
caut | +0.846 |
unta | +0.837 |
Neg logit contributions | |
toe | -0.851 |
acted | -0.790 |
enough | -0.765 |
ring | -0.764 |
atively | -0.733 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
toe | +0.937 |
acted | +0.860 |
ring | +0.836 |
enough | +0.826 |
atively | +0.798 |
Neg logit contributions | |
Mehran | -1.334 |
lapt | -1.313 |
etsk | -1.275 |
caut | -1.252 |
unta | -1.242 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Mehran | +2.532 |
lapt | +2.483 |
etsk | +2.383 |
caut | +2.343 |
unta | +2.318 |
Neg logit contributions | |
toe | -2.485 |
acted | -2.314 |
enough | -2.238 |
ring | -2.237 |
atively | -2.149 |
Token | think |
Token ID | 892 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
toe | +0.968 |
acted | +0.908 |
ring | +0.893 |
enough | +0.882 |
atively | +0.859 |
Neg logit contributions | |
Mehran | -0.777 |
lapt | -0.757 |
etsk | -0.729 |
caut | -0.709 |
unta | -0.700 |
Token | these |
Token ID | 777 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
toe | +0.817 |
acted | +0.758 |
ring | +0.743 |
enough | +0.735 |
atively | +0.719 |
Neg logit contributions | |
Mehran | -0.905 |
lapt | -0.886 |
etsk | -0.867 |
caut | -0.843 |
unta | -0.837 |
Token | salaries |
Token ID | 17058 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
Mehran | +1.698 |
lapt | +1.668 |
etsk | +1.590 |
caut | +1.556 |
unta | +1.527 |
Neg logit contributions | |
toe | -2.281 |
acted | -2.139 |
enough | -2.085 |
ring | -2.079 |
atively | -2.015 |
Token | are |
Token ID | 389 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Mehran | +8.598 |
lapt | +8.437 |
etsk | +7.915 |
caut | +7.810 |
unta | +7.689 |
Neg logit contributions | |
toe | -10.666 |
acted | -9.922 |
enough | -9.663 |
uther | -9.487 |
ring | -9.324 |
Token | right |
Token ID | 826 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Mehran | +2.536 |
lapt | +2.501 |
etsk | +2.410 |
caut | +2.371 |
unta | +2.349 |
Neg logit contributions | |
toe | -2.081 |
acted | -1.921 |
ring | -1.858 |
enough | -1.846 |
atively | -1.776 |
Token | in |
Token ID | 287 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
toe | +2.615 |
acted | +2.449 |
ring | +2.392 |
enough | +2.373 |
atively | +2.316 |
Neg logit contributions | |
Mehran | -2.693 |
lapt | -2.631 |
etsk | -2.557 |
caut | -2.505 |
unta | -2.486 |
Token | line |
Token ID | 1627 |
Feature activation | -8.43e+00 |
Pos logit contributions | |
toe | +1.846 |
acted | +1.712 |
ring | +1.668 |
enough | +1.650 |
atively | +1.599 |
Neg logit contributions | |
Mehran | -2.148 |
lapt | -2.105 |
etsk | -2.047 |
caut | -2.005 |
unta | -1.986 |
Token | or |
Token ID | 393 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
toe | +5.953 |
acted | +5.573 |
ring | +5.488 |
enough | +5.333 |
atively | +5.252 |
Neg logit contributions | |
Mehran | -7.054 |
lapt | -6.889 |
etsk | -6.730 |
caut | -6.589 |
unta | -6.469 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
toe | +0.362 |
acted | +0.338 |
ring | +0.329 |
enough | +0.327 |
atively | +0.316 |
Neg logit contributions | |
Mehran | -0.355 |
lapt | -0.348 |
etsk | -0.336 |
caut | -0.329 |
unta | -0.326 |
Token | , |
Token ID | 11 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Mehran | +1.155 |
lapt | +1.139 |
etsk | +1.107 |
caut | +1.092 |
unta | +1.080 |
Neg logit contributions | |
toe | -0.752 |
acted | -0.678 |
ring | -0.656 |
enough | -0.653 |
atively | -0.623 |
Token | and |
Token ID | 290 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
toe | +0.183 |
acted | +0.170 |
ring | +0.166 |
enough | +0.165 |
atively | +0.159 |
Neg logit contributions | |
Mehran | -0.209 |
lapt | -0.205 |
etsk | -0.199 |
caut | -0.195 |
unta | -0.193 |
Token | added |
Token ID | 2087 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
toe | +1.645 |
acted | +1.545 |
ring | +1.507 |
enough | +1.486 |
atively | +1.439 |
Neg logit contributions | |
Mehran | -1.779 |
lapt | -1.739 |
etsk | -1.699 |
caut | -1.647 |
unta | -1.640 |
Token | : |
Token ID | 25 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
toe | +3.167 |
acted | +2.924 |
ring | +2.868 |
enough | +2.797 |
atively | +2.728 |
Neg logit contributions | |
Mehran | -4.468 |
lapt | -4.376 |
etsk | -4.271 |
caut | -4.178 |
unta | -4.137 |
Token | � |
Token ID | 564 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
toe | +3.169 |
acted | +2.942 |
ring | +2.872 |
enough | +2.853 |
atively | +2.752 |
Neg logit contributions | |
Mehran | -3.328 |
lapt | -3.267 |
etsk | -3.152 |
caut | -3.097 |
unta | -3.057 |
Token | � |
Token ID | 250 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
toe | +13.080 |
acted | +12.643 |
ring | +12.416 |
enough | +12.191 |
atively | +12.106 |
Neg logit contributions | |
Mehran | -8.771 |
lapt | -8.569 |
etsk | -8.183 |
caut | -8.006 |
mosqu | -7.672 |
Token | It |
Token ID | 1026 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
toe | +0.953 |
acted | +0.883 |
ring | +0.858 |
enough | +0.854 |
atively | +0.822 |
Neg logit contributions | |
Mehran | -1.102 |
lapt | -1.082 |
etsk | -1.047 |
caut | -1.027 |
unta | -1.017 |
Token | � |
Token ID | 447 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
toe | +0.316 |
acted | +0.293 |
ring | +0.285 |
enough | +0.283 |
atively | +0.273 |
Neg logit contributions | |
Mehran | -0.359 |
lapt | -0.353 |
etsk | -0.341 |
caut | -0.335 |
unta | -0.331 |
Token | � |
Token ID | 247 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Mehran | +2.697 |
lapt | +2.624 |
etsk | +2.536 |
caut | +2.445 |
unta | +2.438 |
Neg logit contributions | |
toe | -3.968 |
acted | -3.716 |
ring | -3.641 |
enough | -3.631 |
atively | -3.522 |
Token | s |
Token ID | 82 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Mehran | +2.110 |
lapt | +2.070 |
etsk | +2.004 |
caut | +1.962 |
unta | +1.957 |
Neg logit contributions | |
toe | -1.914 |
acted | -1.762 |
enough | -1.714 |
ring | -1.703 |
atively | -1.648 |
Token | a |
Token ID | 257 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Mehran | +1.672 |
lapt | +1.636 |
etsk | +1.588 |
caut | +1.556 |
unta | +1.543 |
Neg logit contributions | |
toe | -1.434 |
acted | -1.323 |
ring | -1.282 |
enough | -1.280 |
atively | -1.223 |
Token | question |
Token ID | 1808 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Mehran | +0.535 |
lapt | +0.524 |
etsk | +0.504 |
caut | +0.493 |
unta | +0.487 |
Neg logit contributions | |
toe | -0.629 |
acted | -0.589 |
ring | -0.575 |
enough | -0.573 |
atively | -0.555 |
Token | , |
Token ID | 11 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
toe | +0.435 |
acted | +0.401 |
ring | +0.389 |
enough | +0.386 |
atively | +0.372 |
Neg logit contributions | |
Mehran | -0.586 |
lapt | -0.576 |
etsk | -0.558 |
caut | -0.548 |
unta | -0.543 |
Token | stating |
Token ID | 12316 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Mehran | +0.652 |
lapt | +0.640 |
etsk | +0.618 |
caut | +0.606 |
unta | +0.600 |
Neg logit contributions | |
toe | -0.609 |
acted | -0.566 |
ring | -0.551 |
enough | -0.548 |
atively | -0.529 |
Token | : |
Token ID | 25 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
toe | +1.403 |
acted | +1.285 |
ring | +1.243 |
enough | +1.233 |
atively | +1.184 |
Neg logit contributions | |
Mehran | -2.127 |
lapt | -2.093 |
etsk | -2.031 |
caut | -1.998 |
unta | -1.979 |
Token | � |
Token ID | 564 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
toe | +2.608 |
acted | +2.420 |
ring | +2.355 |
enough | +2.343 |
atively | +2.257 |
Neg logit contributions | |
Mehran | -2.847 |
lapt | -2.795 |
etsk | -2.698 |
caut | -2.648 |
unta | -2.620 |
Token | � |
Token ID | 250 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
toe | +12.425 |
acted | +12.329 |
ring | +11.670 |
atively | +11.552 |
enough | +11.518 |
Neg logit contributions | |
lapt | -9.128 |
Mehran | -8.749 |
caut | -8.358 |
etsk | -8.277 |
mosqu | -7.984 |
Token | The |
Token ID | 464 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
toe | +1.255 |
acted | +1.164 |
ring | +1.127 |
enough | +1.127 |
atively | +1.081 |
Neg logit contributions | |
Mehran | -1.497 |
lapt | -1.471 |
etsk | -1.422 |
caut | -1.396 |
unta | -1.381 |
Token | separatists |
Token ID | 34214 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
toe | +0.657 |
acted | +0.613 |
ring | +0.598 |
enough | +0.594 |
atively | +0.574 |
Neg logit contributions | |
Mehran | -0.655 |
lapt | -0.643 |
etsk | -0.619 |
caut | -0.608 |
unta | -0.600 |
Token | are |
Token ID | 389 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Mehran | +1.662 |
lapt | +1.627 |
etsk | +1.569 |
caut | +1.531 |
unta | +1.516 |
Neg logit contributions | |
toe | -2.058 |
acted | -1.923 |
ring | -1.879 |
enough | -1.874 |
atively | -1.816 |
Token | saying |
Token ID | 2282 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
toe | +0.132 |
acted | +0.123 |
ring | +0.120 |
enough | +0.119 |
atively | +0.115 |
Neg logit contributions | |
Mehran | -0.139 |
lapt | -0.136 |
etsk | -0.132 |
caut | -0.129 |
unta | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Mehran | +2.342 |
lapt | +2.220 |
etsk | +2.198 |
unta | +2.151 |
caut | +2.114 |
Neg logit contributions | |
toe | -1.960 |
acted | -1.816 |
enough | -1.756 |
ring | -1.746 |
atively | -1.698 |
Token | Its |
Token ID | 20459 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Mehran | +1.556 |
lapt | +1.511 |
etsk | +1.474 |
unta | +1.431 |
caut | +1.418 |
Neg logit contributions | |
toe | -1.827 |
acted | -1.709 |
ring | -1.660 |
enough | -1.655 |
atively | -1.618 |
Token | source |
Token ID | 2723 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Mehran | +0.021 |
lapt | +0.020 |
etsk | +0.020 |
caut | +0.019 |
unta | +0.019 |
Neg logit contributions | |
toe | -0.021 |
acted | -0.020 |
ring | -0.020 |
enough | -0.019 |
atively | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
toe | +3.392 |
acted | +3.216 |
ring | +3.148 |
enough | +3.093 |
atively | +3.031 |
Neg logit contributions | |
Mehran | -3.614 |
lapt | -3.560 |
etsk | -3.426 |
caut | -3.378 |
unta | -3.307 |
Token | : |
Token ID | 25 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
toe | +0.512 |
acted | +0.475 |
ring | +0.462 |
enough | +0.459 |
atively | +0.444 |
Neg logit contributions | |
Mehran | -0.590 |
lapt | -0.579 |
etsk | -0.561 |
caut | -0.550 |
unta | -0.545 |
Token | � |
Token ID | 564 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
toe | +1.675 |
acted | +1.562 |
ring | +1.515 |
enough | +1.512 |
atively | +1.461 |
Neg logit contributions | |
Mehran | -1.733 |
lapt | -1.697 |
etsk | -1.645 |
caut | -1.608 |
unta | -1.596 |
Token | � |
Token ID | 246 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
toe | +13.207 |
acted | +12.781 |
ring | +12.576 |
enough | +12.247 |
atively | +12.210 |
Neg logit contributions | |
Mehran | -7.261 |
lapt | -6.802 |
etsk | -6.395 |
caut | -6.149 |
unta | -6.140 |
Token | I |
Token ID | 40 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
toe | +3.106 |
acted | +2.916 |
ring | +2.849 |
enough | +2.842 |
works | +2.725 |
Neg logit contributions | |
Mehran | -3.100 |
lapt | -3.047 |
etsk | -2.945 |
caut | -2.889 |
unta | -2.818 |
Token | heard |
Token ID | 2982 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
toe | +2.101 |
acted | +1.972 |
ring | +1.929 |
enough | +1.902 |
atively | +1.835 |
Neg logit contributions | |
Mehran | -2.006 |
lapt | -1.957 |
etsk | -1.883 |
caut | -1.845 |
unta | -1.817 |
Token | from |
Token ID | 422 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
toe | +0.678 |
acted | +0.630 |
ring | +0.616 |
enough | +0.610 |
atively | +0.590 |
Neg logit contributions | |
Mehran | -0.815 |
lapt | -0.801 |
etsk | -0.777 |
caut | -0.762 |
unta | -0.757 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
toe | +0.213 |
acted | +0.199 |
ring | +0.194 |
enough | +0.193 |
atively | +0.186 |
Neg logit contributions | |
Mehran | -0.222 |
lapt | -0.218 |
etsk | -0.211 |
caut | -0.207 |
unta | -0.205 |
Token | remembered |
Token ID | 12086 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
toe | +3.375 |
acted | +3.191 |
ring | +3.075 |
enough | +3.018 |
atively | +2.934 |
Neg logit contributions | |
lapt | -4.059 |
Mehran | -4.037 |
etsk | -3.932 |
caut | -3.851 |
ebin | -3.789 |
Token | him |
Token ID | 683 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
toe | +1.673 |
acted | +1.574 |
ring | +1.546 |
enough | +1.517 |
atively | +1.480 |
Neg logit contributions | |
Mehran | -1.683 |
lapt | -1.660 |
etsk | -1.614 |
caut | -1.570 |
unta | -1.552 |
Token | by |
Token ID | 416 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
toe | +2.948 |
acted | +2.754 |
ring | +2.696 |
enough | +2.647 |
atively | +2.567 |
Neg logit contributions | |
Mehran | -3.425 |
lapt | -3.390 |
etsk | -3.269 |
caut | -3.208 |
unta | -3.175 |
Token | saying |
Token ID | 2282 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
toe | +0.162 |
acted | +0.150 |
enough | +0.146 |
ring | +0.146 |
atively | +0.140 |
Neg logit contributions | |
Mehran | -0.171 |
lapt | -0.167 |
etsk | -0.161 |
caut | -0.159 |
unta | -0.157 |
Token | : |
Token ID | 25 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
toe | +0.941 |
acted | +0.871 |
ring | +0.846 |
enough | +0.841 |
atively | +0.811 |
Neg logit contributions | |
Mehran | -1.110 |
lapt | -1.091 |
etsk | -1.056 |
caut | -1.036 |
unta | -1.026 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
toe | +2.388 |
acted | +2.218 |
ring | +2.160 |
enough | +2.148 |
atively | +2.073 |
Neg logit contributions | |
Mehran | -2.535 |
lapt | -2.488 |
etsk | -2.405 |
caut | -2.357 |
unta | -2.333 |
Token | � |
Token ID | 250 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
toe | +13.680 |
acted | +13.121 |
ring | +12.999 |
enough | +12.678 |
atively | +12.468 |
Neg logit contributions | |
Mehran | -6.353 |
lapt | -6.218 |
etsk | -5.712 |
caut | -5.532 |
unta | -5.290 |
Token | He |
Token ID | 1544 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
toe | +1.637 |
acted | +1.525 |
ring | +1.482 |
enough | +1.476 |
atively | +1.416 |
Neg logit contributions | |
Mehran | -1.795 |
lapt | -1.765 |
etsk | -1.704 |
caut | -1.675 |
unta | -1.651 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
toe | +1.442 |
acted | +1.351 |
ring | +1.310 |
enough | +1.297 |
atively | +1.255 |
Neg logit contributions | |
Mehran | -1.486 |
lapt | -1.462 |
etsk | -1.406 |
caut | -1.377 |
unta | -1.364 |
Token | like |
Token ID | 588 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Mehran | +1.023 |
lapt | +1.002 |
etsk | +0.971 |
caut | +0.952 |
unta | +0.941 |
Neg logit contributions | |
toe | -0.937 |
acted | -0.867 |
ring | -0.844 |
enough | -0.841 |
atively | -0.809 |
Token | a |
Token ID | 257 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
toe | +0.413 |
acted | +0.383 |
ring | +0.372 |
enough | +0.371 |
atively | +0.357 |
Neg logit contributions | |
Mehran | -0.455 |
lapt | -0.447 |
etsk | -0.432 |
caut | -0.424 |
unta | -0.419 |
Token | Ast |
Token ID | 8304 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
Mehran | +1.342 |
lapt | +1.286 |
etsk | +1.265 |
caut | +1.229 |
unta | +1.228 |
Neg logit contributions | |
toe | -1.172 |
acted | -1.078 |
ring | -1.048 |
enough | -1.047 |
atively | -1.006 |
Token | roph |
Token ID | 10051 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
Mehran | +4.631 |
etsk | +4.423 |
lapt | +4.281 |
unta | +4.184 |
ebin | +4.170 |
Neg logit contributions | |
toe | -7.449 |
acted | -6.816 |
enough | -6.676 |
atively | -6.522 |
ring | -6.522 |
Token | ysics |
Token ID | 23154 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
Mehran | +4.503 |
etsk | +4.354 |
lapt | +4.242 |
unta | +4.219 |
ebin | +4.133 |
Neg logit contributions | |
toe | -6.286 |
acted | -5.764 |
enough | -5.623 |
ring | -5.602 |
atively | -5.475 |
Token | added |
Token ID | 2087 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Mehran | +4.458 |
lapt | +4.317 |
etsk | +4.242 |
caut | +4.084 |
unta | +4.067 |
Neg logit contributions | |
toe | -4.695 |
acted | -4.295 |
enough | -4.206 |
ring | -4.106 |
atively | -4.002 |
Token | : |
Token ID | 25 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
toe | +1.264 |
acted | +1.157 |
enough | +1.114 |
ring | +1.111 |
atively | +1.057 |
Neg logit contributions | |
Mehran | -1.824 |
lapt | -1.798 |
etsk | -1.739 |
caut | -1.714 |
unta | -1.701 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
toe | +2.666 |
acted | +2.477 |
ring | +2.414 |
enough | +2.401 |
atively | +2.319 |
Neg logit contributions | |
Mehran | -2.767 |
lapt | -2.715 |
etsk | -2.621 |
caut | -2.570 |
unta | -2.542 |
Token | � |
Token ID | 250 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
toe | +13.030 |
acted | +12.388 |
ring | +12.337 |
enough | +11.967 |
atively | +11.924 |
Neg logit contributions | |
Mehran | -7.212 |
lapt | -6.840 |
etsk | -6.444 |
caut | -6.182 |
unta | -6.029 |
Token | this |
Token ID | 5661 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
toe | +0.187 |
acted | +0.174 |
ring | +0.170 |
enough | +0.169 |
atively | +0.164 |
Neg logit contributions | |
Mehran | -0.182 |
lapt | -0.179 |
etsk | -0.173 |
caut | -0.169 |
unta | -0.168 |
Token | is |
Token ID | 318 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Mehran | +0.938 |
lapt | +0.922 |
etsk | +0.888 |
caut | +0.870 |
unta | +0.860 |
Neg logit contributions | |
toe | -0.993 |
acted | -0.925 |
ring | -0.899 |
enough | -0.896 |
atively | -0.867 |
Token | the |
Token ID | 262 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Mehran | +0.865 |
lapt | +0.851 |
etsk | +0.822 |
caut | +0.807 |
unta | +0.798 |
Neg logit contributions | |
toe | -0.771 |
acted | -0.715 |
ring | -0.693 |
enough | -0.690 |
atively | -0.665 |
Token | Godzilla |
Token ID | 38104 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
toe | +0.570 |
acted | +0.531 |
ring | +0.522 |
enough | +0.515 |
atively | +0.499 |
Neg logit contributions | |
Mehran | -0.593 |
lapt | -0.578 |
etsk | -0.563 |
caut | -0.549 |
unta | -0.545 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
toe | +0.874 |
acted | +0.805 |
ring | +0.780 |
enough | +0.776 |
atively | +0.745 |
Neg logit contributions | |
Mehran | -1.135 |
lapt | -1.115 |
etsk | -1.082 |
caut | -1.062 |
unta | -1.052 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Mehran | +2.213 |
lapt | +2.128 |
etsk | +2.088 |
unta | +2.039 |
caut | +2.027 |
Neg logit contributions | |
toe | -1.792 |
acted | -1.657 |
enough | -1.600 |
ring | -1.597 |
atively | -1.543 |
Token | He |
Token ID | 1544 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Mehran | +1.687 |
lapt | +1.648 |
etsk | +1.604 |
caut | +1.565 |
unta | +1.563 |
Neg logit contributions | |
toe | -1.572 |
acted | -1.462 |
enough | -1.409 |
ring | -1.407 |
atively | -1.367 |
Token | added |
Token ID | 2087 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
toe | +0.819 |
acted | +0.768 |
ring | +0.750 |
enough | +0.744 |
atively | +0.720 |
Neg logit contributions | |
Mehran | -0.783 |
lapt | -0.769 |
etsk | -0.738 |
caut | -0.725 |
unta | -0.715 |
Token | : |
Token ID | 25 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
toe | +1.982 |
acted | +1.811 |
ring | +1.747 |
enough | +1.741 |
atively | +1.659 |
Neg logit contributions | |
Mehran | -2.955 |
lapt | -2.909 |
etsk | -2.825 |
caut | -2.779 |
unta | -2.756 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
toe | +2.227 |
acted | +2.031 |
ring | +1.967 |
enough | +1.954 |
atively | +1.868 |
Neg logit contributions | |
Mehran | -3.405 |
lapt | -3.351 |
etsk | -3.257 |
caut | -3.196 |
unta | -3.176 |
Token | � |
Token ID | 250 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
toe | +10.402 |
acted | +9.788 |
ring | +9.666 |
enough | +9.377 |
atively | +9.247 |
Neg logit contributions | |
lapt | -9.752 |
mosqu | -9.370 |
ccording | -9.249 |
caut | -9.213 |
Mehran | -9.206 |
Token | Next |
Token ID | 10019 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
toe | +1.067 |
acted | +0.995 |
ring | +0.971 |
enough | +0.969 |
atively | +0.932 |
Neg logit contributions | |
Mehran | -1.061 |
lapt | -1.039 |
etsk | -1.001 |
caut | -0.982 |
unta | -0.967 |
Token | year |
Token ID | 614 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Mehran | +4.883 |
lapt | +4.789 |
etsk | +4.605 |
unta | +4.510 |
caut | +4.477 |
Neg logit contributions | |
toe | -8.459 |
acted | -8.011 |
enough | -7.724 |
ring | -7.680 |
atively | -7.552 |
Token | will |
Token ID | 481 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Mehran | +1.233 |
lapt | +1.215 |
etsk | +1.177 |
caut | +1.160 |
unta | +1.146 |
Neg logit contributions | |
toe | -0.934 |
acted | -0.861 |
ring | -0.825 |
enough | -0.823 |
atively | -0.787 |
Token | defin |
Token ID | 2730 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
Mehran | +1.693 |
lapt | +1.649 |
etsk | +1.591 |
caut | +1.541 |
unta | +1.530 |
Neg logit contributions | |
toe | -2.352 |
acted | -2.234 |
enough | -2.159 |
ring | -2.147 |
atively | -2.090 |
Token | , |
Token ID | 11 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
toe | +0.677 |
acted | +0.631 |
ring | +0.616 |
enough | +0.612 |
atively | +0.591 |
Neg logit contributions | |
Mehran | -0.694 |
lapt | -0.680 |
etsk | -0.659 |
caut | -0.645 |
unta | -0.637 |
Token | city |
Token ID | 1748 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
toe | +0.444 |
acted | +0.414 |
ring | +0.404 |
enough | +0.401 |
atively | +0.387 |
Neg logit contributions | |
Mehran | -0.459 |
lapt | -0.450 |
etsk | -0.436 |
caut | -0.426 |
unta | -0.422 |
Token | wide |
Token ID | 4421 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
Mehran | +0.637 |
lapt | +0.630 |
etsk | +0.607 |
caut | +0.600 |
unta | +0.597 |
Neg logit contributions | |
toe | -0.420 |
acted | -0.383 |
enough | -0.367 |
ring | -0.365 |
atively | -0.348 |
Token | style |
Token ID | 3918 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Mehran | +3.015 |
lapt | +2.984 |
etsk | +2.825 |
caut | +2.812 |
unta | +2.787 |
Neg logit contributions | |
toe | -2.790 |
acted | -2.582 |
enough | -2.483 |
ring | -2.457 |
atively | -2.389 |
Token | : |
Token ID | 25 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
toe | +1.485 |
acted | +1.352 |
ring | +1.306 |
enough | +1.296 |
atively | +1.237 |
Neg logit contributions | |
Mehran | -2.432 |
lapt | -2.396 |
etsk | -2.329 |
caut | -2.291 |
unta | -2.270 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
toe | +2.763 |
acted | +2.558 |
ring | +2.530 |
enough | +2.489 |
atively | +2.407 |
Neg logit contributions | |
Mehran | -2.984 |
lapt | -2.916 |
etsk | -2.833 |
caut | -2.774 |
ebin | -2.747 |
Token | � |
Token ID | 250 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
toe | +12.869 |
acted | +12.407 |
ring | +12.194 |
enough | +11.840 |
atively | +11.787 |
Neg logit contributions | |
Mehran | -6.974 |
lapt | -6.720 |
etsk | -6.255 |
caut | -5.969 |
unta | -5.896 |
Token | When |
Token ID | 2215 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
toe | +1.273 |
acted | +1.181 |
ring | +1.149 |
enough | +1.142 |
atively | +1.100 |
Neg logit contributions | |
Mehran | -1.477 |
lapt | -1.451 |
etsk | -1.403 |
caut | -1.377 |
unta | -1.361 |
Token | I |
Token ID | 314 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Mehran | +2.517 |
lapt | +2.456 |
etsk | +2.376 |
caut | +2.327 |
unta | +2.310 |
Neg logit contributions | |
toe | -2.630 |
acted | -2.442 |
enough | -2.372 |
ring | -2.363 |
atively | -2.292 |
Token | meet |
Token ID | 1826 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
Mehran | +0.035 |
lapt | +0.034 |
etsk | +0.033 |
caut | +0.032 |
unta | +0.032 |
Neg logit contributions | |
toe | -0.037 |
acted | -0.035 |
ring | -0.034 |
enough | -0.034 |
atively | -0.033 |
Token | people |
Token ID | 661 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Mehran | +3.862 |
lapt | +3.688 |
etsk | +3.609 |
caut | +3.481 |
unta | +3.475 |
Neg logit contributions | |
toe | -4.282 |
acted | -3.983 |
enough | -3.850 |
ring | -3.806 |
atively | -3.686 |
Token | ig |
Token ID | 328 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Mehran | +4.418 |
lapt | +4.379 |
etsk | +4.240 |
unta | +4.192 |
caut | +4.125 |
Neg logit contributions | |
toe | -3.858 |
acted | -3.507 |
enough | -3.414 |
ring | -3.369 |
atively | -3.269 |
Token | dem |
Token ID | 9536 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Mehran | +2.590 |
lapt | +2.582 |
etsk | +2.496 |
unta | +2.459 |
caut | +2.426 |
Neg logit contributions | |
toe | -2.073 |
acted | -1.934 |
enough | -1.854 |
ring | -1.841 |
atively | -1.771 |
Token | ont |
Token ID | 756 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
toe | +0.249 |
acted | +0.230 |
ring | +0.222 |
enough | +0.222 |
atively | +0.213 |
Neg logit contributions | |
Mehran | -0.314 |
lapt | -0.308 |
etsk | -0.299 |
caut | -0.293 |
unta | -0.291 |
Token | said |
Token ID | 531 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
toe | +4.438 |
acted | +4.156 |
ring | +4.048 |
enough | +3.965 |
atively | +3.889 |
Neg logit contributions | |
Mehran | -5.324 |
lapt | -5.128 |
etsk | -4.978 |
caut | -4.901 |
unta | -4.785 |
Token | : |
Token ID | 25 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
Mehran | +0.211 |
lapt | +0.208 |
etsk | +0.201 |
caut | +0.197 |
unta | +0.196 |
Neg logit contributions | |
toe | -0.177 |
acted | -0.164 |
ring | -0.159 |
enough | -0.158 |
atively | -0.152 |
Token | � |
Token ID | 564 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
toe | +1.971 |
acted | +1.815 |
ring | +1.768 |
enough | +1.759 |
atively | +1.692 |
Neg logit contributions | |
Mehran | -2.570 |
lapt | -2.521 |
etsk | -2.453 |
caut | -2.401 |
unta | -2.383 |
Token | � |
Token ID | 250 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
toe | +12.858 |
acted | +12.360 |
ring | +12.141 |
enough | +11.897 |
atively | +11.834 |
Neg logit contributions | |
Mehran | -7.325 |
lapt | -6.887 |
etsk | -6.526 |
caut | -6.150 |
unta | -6.149 |
Token | The |
Token ID | 464 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
toe | +0.484 |
acted | +0.451 |
ring | +0.440 |
enough | +0.439 |
atively | +0.423 |
Neg logit contributions | |
Mehran | -0.477 |
lapt | -0.466 |
etsk | -0.450 |
caut | -0.441 |
unta | -0.436 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
toe | +1.190 |
acted | +1.113 |
ring | +1.088 |
enough | +1.079 |
atively | +1.047 |
Neg logit contributions | |
Mehran | -1.138 |
lapt | -1.109 |
etsk | -1.072 |
caut | -1.048 |
unta | -1.037 |
Token | referendum |
Token ID | 11467 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Mehran | +2.293 |
lapt | +2.260 |
etsk | +2.162 |
caut | +2.114 |
unta | +2.106 |
Neg logit contributions | |
toe | -2.722 |
acted | -2.549 |
enough | -2.478 |
ring | -2.471 |
atively | -2.391 |
Token | will |
Token ID | 481 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Mehran | +0.536 |
lapt | +0.525 |
etsk | +0.507 |
caut | +0.496 |
unta | +0.490 |
Neg logit contributions | |
toe | -0.563 |
acted | -0.525 |
ring | -0.512 |
enough | -0.509 |
atively | -0.493 |
Token | his |
Token ID | 465 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Mehran | +2.660 |
lapt | +2.580 |
etsk | +2.497 |
caut | +2.441 |
unta | +2.391 |
Neg logit contributions | |
toe | -2.961 |
acted | -2.751 |
enough | -2.692 |
ring | -2.653 |
atively | -2.558 |
Token | eyes |
Token ID | 2951 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
toe | +0.719 |
acted | +0.649 |
ring | +0.626 |
enough | +0.611 |
atively | +0.581 |
Neg logit contributions | |
Mehran | -1.452 |
lapt | -1.421 |
etsk | -1.397 |
caut | -1.366 |
unta | -1.359 |
Token | and |
Token ID | 290 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Mehran | +0.023 |
lapt | +0.022 |
etsk | +0.022 |
caut | +0.022 |
unta | +0.021 |
Neg logit contributions | |
toe | -0.017 |
acted | -0.016 |
ring | -0.015 |
enough | -0.015 |
atively | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
toe | +0.656 |
acted | +0.619 |
ring | +0.603 |
enough | +0.599 |
atively | +0.581 |
Neg logit contributions | |
Mehran | -0.581 |
lapt | -0.570 |
etsk | -0.552 |
caut | -0.534 |
unta | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
toe | +0.907 |
acted | +0.830 |
ring | +0.801 |
enough | +0.797 |
atively | +0.762 |
Neg logit contributions | |
Mehran | -1.352 |
lapt | -1.330 |
etsk | -1.292 |
caut | -1.270 |
unta | -1.259 |
Token | � |
Token ID | 564 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
toe | +1.658 |
acted | +1.543 |
ring | +1.504 |
enough | +1.496 |
atively | +1.444 |
Neg logit contributions | |
Mehran | -1.713 |
lapt | -1.680 |
etsk | -1.622 |
caut | -1.590 |
unta | -1.573 |
Token | � |
Token ID | 250 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
toe | +11.060 |
acted | +10.728 |
enough | +10.172 |
ring | +10.082 |
atively | +9.940 |
Neg logit contributions | |
lapt | -8.899 |
Mehran | -8.804 |
etsk | -8.310 |
caut | -8.255 |
mosqu | -7.905 |
Token | No |
Token ID | 2949 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
toe | +0.941 |
acted | +0.872 |
enough | +0.846 |
ring | +0.846 |
atively | +0.810 |
Neg logit contributions | |
Mehran | -1.098 |
lapt | -1.078 |
etsk | -1.043 |
caut | -1.023 |
unta | -1.012 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
toe | +0.695 |
acted | +0.638 |
ring | +0.618 |
enough | +0.614 |
atively | +0.589 |
Neg logit contributions | |
Mehran | -0.967 |
lapt | -0.950 |
etsk | -0.922 |
caut | -0.906 |
unta | -0.898 |
Token | I |
Token ID | 314 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Mehran | +0.483 |
lapt | +0.471 |
etsk | +0.458 |
caut | +0.450 |
unta | +0.445 |
Neg logit contributions | |
toe | -0.401 |
acted | -0.370 |
ring | -0.359 |
enough | -0.357 |
atively | -0.345 |
Token | want |
Token ID | 765 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
toe | +2.166 |
acted | +2.031 |
ring | +1.981 |
enough | +1.967 |
atively | +1.897 |
Neg logit contributions | |
Mehran | -2.095 |
lapt | -2.056 |
etsk | -1.975 |
caut | -1.920 |
unta | -1.904 |
Token | he |
Token ID | 339 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
toe | +1.659 |
acted | +1.553 |
ring | +1.515 |
enough | +1.504 |
atively | +1.457 |
Neg logit contributions | |
Mehran | -1.744 |
lapt | -1.731 |
etsk | -1.679 |
caut | -1.631 |
unta | -1.622 |
Token | added |
Token ID | 2087 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
toe | +2.368 |
acted | +2.221 |
ring | +2.171 |
enough | +2.141 |
atively | +2.088 |
Neg logit contributions | |
Mehran | -2.424 |
lapt | -2.417 |
etsk | -2.310 |
caut | -2.257 |
unta | -2.235 |
Token | the |
Token ID | 262 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
toe | +2.108 |
acted | +1.939 |
ring | +1.888 |
enough | +1.862 |
atively | +1.808 |
Neg logit contributions | |
Mehran | -3.070 |
lapt | -3.020 |
etsk | -2.945 |
caut | -2.882 |
unta | -2.859 |
Token | concern |
Token ID | 2328 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
toe | +3.198 |
acted | +3.034 |
ring | +2.986 |
enough | +2.943 |
atively | +2.890 |
Neg logit contributions | |
Mehran | -2.374 |
lapt | -2.315 |
etsk | -2.244 |
caut | -2.176 |
unta | -2.166 |
Token | : |
Token ID | 25 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
toe | +0.431 |
acted | +0.398 |
ring | +0.386 |
enough | +0.384 |
atively | +0.369 |
Neg logit contributions | |
Mehran | -0.538 |
lapt | -0.529 |
etsk | -0.513 |
caut | -0.503 |
unta | -0.499 |
Token | � |
Token ID | 564 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
toe | +1.876 |
acted | +1.738 |
ring | +1.701 |
enough | +1.685 |
atively | +1.631 |
Neg logit contributions | |
Mehran | -2.123 |
lapt | -2.082 |
etsk | -2.019 |
caut | -1.980 |
unta | -1.957 |
Token | � |
Token ID | 250 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
toe | +13.085 |
ring | +12.510 |
acted | +12.480 |
enough | +12.054 |
atively | +11.956 |
Neg logit contributions | |
Mehran | -6.843 |
lapt | -6.631 |
etsk | -6.267 |
caut | -5.896 |
unta | -5.845 |
Token | Whether |
Token ID | 15354 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
toe | +1.462 |
acted | +1.352 |
ring | +1.314 |
enough | +1.307 |
atively | +1.258 |
Neg logit contributions | |
Mehran | -1.778 |
lapt | -1.745 |
etsk | -1.693 |
caut | -1.660 |
unta | -1.643 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
toe | +0.448 |
acted | +0.418 |
ring | +0.407 |
enough | +0.405 |
atively | +0.392 |
Neg logit contributions | |
Mehran | -0.471 |
lapt | -0.462 |
etsk | -0.448 |
caut | -0.437 |
unta | -0.433 |
Token | overall |
Token ID | 4045 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Mehran | +0.762 |
lapt | +0.745 |
etsk | +0.714 |
caut | +0.697 |
unta | +0.688 |
Neg logit contributions | |
toe | -1.011 |
acted | -0.948 |
ring | -0.925 |
enough | -0.923 |
atively | -0.895 |
Token | tax |
Token ID | 1687 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Mehran | +3.923 |
lapt | +3.885 |
etsk | +3.602 |
caut | +3.549 |
unta | +3.526 |
Neg logit contributions | |
toe | -4.975 |
acted | -4.624 |
enough | -4.535 |
ring | -4.491 |
uther | -4.325 |
Token | career |
Token ID | 3451 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
toe | +1.400 |
acted | +1.304 |
ring | +1.278 |
enough | +1.257 |
atively | +1.223 |
Neg logit contributions | |
Mehran | -1.630 |
lapt | -1.579 |
etsk | -1.553 |
caut | -1.508 |
unta | -1.497 |
Token | plans |
Token ID | 3352 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
toe | +1.715 |
acted | +1.583 |
ring | +1.548 |
enough | +1.521 |
atively | +1.470 |
Neg logit contributions | |
Mehran | -2.438 |
lapt | -2.381 |
etsk | -2.325 |
caut | -2.273 |
unta | -2.256 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Mehran | +1.567 |
lapt | +1.535 |
etsk | +1.503 |
caut | +1.474 |
unta | +1.462 |
Neg logit contributions | |
toe | -0.993 |
acted | -0.896 |
enough | -0.866 |
ring | -0.863 |
atively | -0.818 |
Token | saying |
Token ID | 2282 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
Mehran | +0.988 |
lapt | +0.971 |
etsk | +0.938 |
caut | +0.921 |
unta | +0.912 |
Neg logit contributions | |
toe | -0.851 |
acted | -0.787 |
ring | -0.763 |
enough | -0.760 |
atively | -0.732 |
Token | : |
Token ID | 25 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
toe | +0.062 |
acted | +0.057 |
ring | +0.055 |
enough | +0.055 |
atively | +0.053 |
Neg logit contributions | |
Mehran | -0.065 |
lapt | -0.064 |
etsk | -0.062 |
caut | -0.061 |
unta | -0.060 |
Token | � |
Token ID | 564 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
toe | +1.548 |
acted | +1.427 |
ring | +1.403 |
enough | +1.388 |
atively | +1.330 |
Neg logit contributions | |
Mehran | -1.735 |
lapt | -1.728 |
etsk | -1.646 |
caut | -1.644 |
unta | -1.594 |
Token | � |
Token ID | 250 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
toe | +12.067 |
acted | +11.713 |
ring | +11.426 |
enough | +11.274 |
atively | +11.109 |
Neg logit contributions | |
Mehran | -7.855 |
lapt | -7.613 |
etsk | -7.239 |
caut | -7.180 |
unta | -6.771 |
Token | I |
Token ID | 40 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
toe | +1.239 |
acted | +1.145 |
ring | +1.111 |
enough | +1.107 |
atively | +1.064 |
Neg logit contributions | |
Mehran | -1.505 |
lapt | -1.479 |
etsk | -1.433 |
caut | -1.406 |
unta | -1.392 |
Token | think |
Token ID | 892 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
toe | +2.582 |
acted | +2.418 |
ring | +2.368 |
enough | +2.331 |
atively | +2.267 |
Neg logit contributions | |
Mehran | -2.451 |
lapt | -2.398 |
etsk | -2.306 |
caut | -2.250 |
unta | -2.215 |
Token | we |
Token ID | 356 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
toe | +1.661 |
acted | +1.549 |
ring | +1.520 |
enough | +1.501 |
atively | +1.468 |
Neg logit contributions | |
Mehran | -1.915 |
lapt | -1.874 |
etsk | -1.833 |
caut | -1.778 |
unta | -1.764 |
Token | � |
Token ID | 447 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
toe | +1.423 |
acted | +1.334 |
ring | +1.303 |
enough | +1.293 |
atively | +1.257 |
Neg logit contributions | |
Mehran | -1.213 |
lapt | -1.188 |
etsk | -1.135 |
caut | -1.110 |
unta | -1.096 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Mehran | +1.738 |
lapt | +1.668 |
etsk | +1.635 |
unta | +1.603 |
caut | +1.583 |
Neg logit contributions | |
toe | -1.495 |
acted | -1.379 |
ring | -1.338 |
enough | -1.332 |
atively | -1.298 |
Token | They |
Token ID | 2990 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Mehran | +1.510 |
lapt | +1.472 |
etsk | +1.433 |
unta | +1.391 |
caut | +1.385 |
Neg logit contributions | |
toe | -1.717 |
acted | -1.605 |
ring | -1.561 |
enough | -1.555 |
atively | -1.520 |
Token | have |
Token ID | 423 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Mehran | +1.676 |
lapt | +1.640 |
etsk | +1.581 |
caut | +1.543 |
unta | +1.524 |
Neg logit contributions | |
toe | -2.263 |
acted | -2.128 |
ring | -2.073 |
enough | -2.073 |
atively | -2.013 |
Token | been |
Token ID | 587 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
toe | +4.442 |
acted | +4.186 |
ring | +4.077 |
enough | +4.041 |
atively | +3.898 |
Neg logit contributions | |
Mehran | -5.081 |
lapt | -4.889 |
etsk | -4.871 |
unta | -4.697 |
ebin | -4.663 |
Token | right |
Token ID | 826 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Mehran | +0.947 |
lapt | +0.929 |
etsk | +0.895 |
caut | +0.881 |
unta | +0.866 |
Neg logit contributions | |
toe | -0.935 |
acted | -0.869 |
ring | -0.845 |
enough | -0.843 |
atively | -0.814 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +3.028 |
acted | +2.795 |
ring | +2.729 |
enough | +2.704 |
atively | +2.620 |
Neg logit contributions | |
Mehran | -4.021 |
lapt | -3.980 |
etsk | -3.831 |
caut | -3.760 |
unta | -3.733 |
Token | � |
Token ID | 250 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
toe | +10.885 |
acted | +10.623 |
ring | +10.370 |
enough | +10.079 |
atively | +9.954 |
Neg logit contributions | |
Mehran | -8.672 |
lapt | -8.445 |
etsk | -8.179 |
caut | -7.781 |
ebin | -7.770 |
Token | there |
Token ID | 8117 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
toe | +0.230 |
acted | +0.212 |
ring | +0.206 |
enough | +0.205 |
atively | +0.197 |
Neg logit contributions | |
Mehran | -0.282 |
lapt | -0.277 |
etsk | -0.268 |
caut | -0.263 |
unta | -0.261 |
Token | � |
Token ID | 447 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
toe | +1.917 |
acted | +1.781 |
ring | +1.730 |
enough | +1.722 |
atively | +1.655 |
Neg logit contributions | |
Mehran | -2.355 |
lapt | -2.313 |
etsk | -2.242 |
caut | -2.201 |
unta | -2.170 |
Token | � |
Token ID | 251 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Mehran | +1.822 |
lapt | +1.777 |
etsk | +1.708 |
caut | +1.658 |
unta | +1.642 |
Neg logit contributions | |
toe | -2.623 |
acted | -2.468 |
ring | -2.414 |
enough | -2.405 |
atively | -2.336 |
Token | all |
Token ID | 477 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mehran | +0.228 |
lapt | +0.224 |
etsk | +0.217 |
caut | +0.213 |
unta | +0.211 |
Neg logit contributions | |
toe | -0.167 |
acted | -0.154 |
ring | -0.148 |
enough | -0.148 |
atively | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
toe | +0.176 |
acted | +0.162 |
ring | +0.157 |
enough | +0.157 |
atively | +0.150 |
Neg logit contributions | |
Mehran | -0.233 |
lapt | -0.229 |
etsk | -0.222 |
caut | -0.218 |
unta | -0.216 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Mehran | +2.891 |
lapt | +2.709 |
etsk | +2.693 |
unta | +2.642 |
ebin | +2.595 |
Neg logit contributions | |
toe | -2.480 |
acted | -2.302 |
enough | -2.225 |
ring | -2.209 |
atively | -2.157 |
Token | He |
Token ID | 1544 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Mehran | +2.494 |
lapt | +2.430 |
etsk | +2.362 |
caut | +2.313 |
unta | +2.300 |
Neg logit contributions | |
toe | -2.120 |
acted | -1.972 |
enough | -1.899 |
ring | -1.885 |
atively | -1.838 |
Token | added |
Token ID | 2087 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
toe | +0.909 |
acted | +0.852 |
ring | +0.832 |
enough | +0.825 |
atively | +0.800 |
Neg logit contributions | |
Mehran | -0.865 |
lapt | -0.851 |
etsk | -0.817 |
caut | -0.802 |
unta | -0.792 |
Token | : |
Token ID | 25 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
toe | +1.888 |
acted | +1.724 |
ring | +1.671 |
enough | +1.655 |
atively | +1.589 |
Neg logit contributions | |
Mehran | -2.892 |
lapt | -2.846 |
etsk | -2.768 |
caut | -2.717 |
unta | -2.695 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +1.991 |
acted | +1.819 |
ring | +1.761 |
enough | +1.749 |
atively | +1.674 |
Neg logit contributions | |
Mehran | -2.975 |
lapt | -2.927 |
etsk | -2.846 |
caut | -2.794 |
unta | -2.773 |
Token | � |
Token ID | 250 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
toe | +11.007 |
acted | +10.411 |
ring | +10.347 |
enough | +10.003 |
atively | +9.970 |
Neg logit contributions | |
Mehran | -8.630 |
lapt | -8.385 |
etsk | -7.918 |
caut | -7.792 |
unta | -7.502 |
Token | Before |
Token ID | 8421 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
toe | +0.873 |
acted | +0.813 |
ring | +0.796 |
enough | +0.793 |
atively | +0.763 |
Neg logit contributions | |
Mehran | -0.836 |
lapt | -0.821 |
etsk | -0.792 |
caut | -0.776 |
unta | -0.764 |
Token | we |
Token ID | 356 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
toe | +0.833 |
acted | +0.773 |
ring | +0.757 |
enough | +0.751 |
atively | +0.727 |
Neg logit contributions | |
Mehran | -0.897 |
lapt | -0.883 |
etsk | -0.861 |
caut | -0.834 |
unta | -0.830 |
Token | take |
Token ID | 1011 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
toe | +1.228 |
acted | +1.158 |
ring | +1.137 |
enough | +1.126 |
atively | +1.094 |
Neg logit contributions | |
Mehran | -0.980 |
lapt | -0.964 |
etsk | -0.926 |
caut | -0.896 |
unta | -0.885 |
Token | these |
Token ID | 777 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Mehran | +0.331 |
lapt | +0.325 |
etsk | +0.314 |
caut | +0.309 |
unta | +0.305 |
Neg logit contributions | |
toe | -0.293 |
acted | -0.272 |
ring | -0.264 |
enough | -0.263 |
atively | -0.253 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
toe | +0.324 |
acted | +0.299 |
ring | +0.290 |
enough | +0.288 |
atively | +0.277 |
Neg logit contributions | |
Mehran | -0.408 |
lapt | -0.400 |
etsk | -0.388 |
caut | -0.381 |
unta | -0.377 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Mehran | +1.921 |
lapt | +1.857 |
etsk | +1.819 |
unta | +1.776 |
caut | +1.768 |
Neg logit contributions | |
toe | -1.535 |
acted | -1.417 |
ring | -1.369 |
enough | -1.369 |
atively | -1.319 |
Token | He |
Token ID | 1544 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Mehran | +1.573 |
lapt | +1.536 |
etsk | +1.494 |
caut | +1.449 |
unta | +1.446 |
Neg logit contributions | |
toe | -1.735 |
acted | -1.615 |
enough | -1.572 |
ring | -1.561 |
atively | -1.522 |
Token | added |
Token ID | 2087 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
toe | +0.891 |
acted | +0.830 |
ring | +0.811 |
enough | +0.801 |
atively | +0.778 |
Neg logit contributions | |
Mehran | -0.956 |
lapt | -0.944 |
etsk | -0.904 |
caut | -0.889 |
unta | -0.877 |
Token | : |
Token ID | 25 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
toe | +1.351 |
acted | +1.238 |
ring | +1.200 |
enough | +1.190 |
atively | +1.144 |
Neg logit contributions | |
Mehran | -1.977 |
lapt | -1.944 |
etsk | -1.889 |
caut | -1.855 |
unta | -1.839 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +3.075 |
acted | +2.843 |
ring | +2.777 |
enough | +2.758 |
atively | +2.663 |
Neg logit contributions | |
Mehran | -3.392 |
lapt | -3.330 |
etsk | -3.216 |
caut | -3.152 |
unta | -3.124 |
Token | � |
Token ID | 250 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
toe | +12.889 |
acted | +12.425 |
ring | +12.320 |
atively | +11.937 |
enough | +11.876 |
Neg logit contributions | |
Mehran | -6.879 |
lapt | -6.584 |
etsk | -6.027 |
unta | -5.794 |
caut | -5.640 |
Token | The |
Token ID | 464 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
toe | +0.647 |
acted | +0.604 |
ring | +0.589 |
enough | +0.588 |
atively | +0.567 |
Neg logit contributions | |
Mehran | -0.613 |
lapt | -0.602 |
etsk | -0.580 |
caut | -0.568 |
unta | -0.560 |
Token | bottom |
Token ID | 4220 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
toe | +1.307 |
acted | +1.226 |
ring | +1.201 |
enough | +1.185 |
atively | +1.152 |
Neg logit contributions | |
Mehran | -1.285 |
lapt | -1.250 |
etsk | -1.214 |
caut | -1.180 |
unta | -1.169 |
Token | line |
Token ID | 1627 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Mehran | +2.522 |
lapt | +2.485 |
etsk | +2.434 |
caut | +2.343 |
unta | +2.341 |
Neg logit contributions | |
toe | -2.722 |
acted | -2.553 |
enough | -2.531 |
ring | -2.438 |
atively | -2.384 |
Token | is |
Token ID | 318 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
toe | +1.610 |
acted | +1.497 |
ring | +1.460 |
enough | +1.448 |
atively | +1.403 |
Neg logit contributions | |
Mehran | -1.708 |
lapt | -1.675 |
etsk | -1.620 |
caut | -1.587 |
unta | -1.570 |
Token | 70 |
Token ID | 2154 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Mehran | +4.710 |
lapt | +4.560 |
etsk | +4.492 |
unta | +4.388 |
ebin | +4.313 |
Neg logit contributions | |
toe | -2.871 |
acted | -2.618 |
enough | -2.535 |
ring | -2.501 |
atively | -2.409 |
Token | Hawk |
Token ID | 26698 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Mehran | +1.026 |
lapt | +1.002 |
etsk | +0.958 |
caut | +0.934 |
unta | +0.922 |
Neg logit contributions | |
toe | -1.352 |
acted | -1.277 |
enough | -1.246 |
ring | -1.239 |
atively | -1.200 |
Token | uses |
Token ID | 3544 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Mehran | +0.455 |
lapt | +0.447 |
etsk | +0.431 |
caut | +0.423 |
unta | +0.418 |
Neg logit contributions | |
toe | -0.445 |
acted | -0.414 |
ring | -0.403 |
enough | -0.401 |
atively | -0.388 |
Token | Military |
Token ID | 12842 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Mehran | +1.091 |
lapt | +1.066 |
etsk | +1.022 |
caut | +1.003 |
unta | +0.995 |
Neg logit contributions | |
toe | -1.134 |
acted | -1.055 |
enough | -1.026 |
ring | -1.023 |
atively | -0.987 |
Token | Class |
Token ID | 5016 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Mehran | +0.617 |
lapt | +0.606 |
etsk | +0.586 |
caut | +0.576 |
unta | +0.572 |
Neg logit contributions | |
toe | -0.480 |
acted | -0.444 |
ring | -0.430 |
enough | -0.428 |
atively | -0.411 |
Token | III |
Token ID | 6711 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +3.479 |
acted | +3.233 |
ring | +3.165 |
enough | +3.120 |
works | +3.047 |
Neg logit contributions | |
Mehran | -3.597 |
lapt | -3.545 |
etsk | -3.458 |
caut | -3.364 |
ebin | -3.297 |
Token | components |
Token ID | 6805 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
toe | +9.408 |
acted | +8.804 |
ring | +8.758 |
works | +8.339 |
enough | +8.312 |
Neg logit contributions | |
Mehran | -9.744 |
lapt | -9.512 |
etsk | -9.391 |
caut | -9.104 |
ebin | -9.057 |
Token | which |
Token ID | 543 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
toe | +1.832 |
acted | +1.684 |
ring | +1.646 |
enough | +1.627 |
atively | +1.568 |
Neg logit contributions | |
Mehran | -2.284 |
lapt | -2.256 |
etsk | -2.184 |
caut | -2.146 |
unta | -2.114 |
Token | have |
Token ID | 423 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
Mehran | +1.252 |
lapt | +1.227 |
etsk | +1.177 |
caut | +1.149 |
unta | +1.136 |
Neg logit contributions | |
toe | -1.572 |
acted | -1.478 |
enough | -1.437 |
ring | -1.437 |
atively | -1.391 |
Token | passed |
Token ID | 3804 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
toe | +3.438 |
acted | +3.196 |
ring | +3.123 |
enough | +3.097 |
atively | +3.001 |
Neg logit contributions | |
Mehran | -3.867 |
lapt | -3.776 |
etsk | -3.702 |
caut | -3.608 |
unta | -3.588 |
Token | rigorous |
Token ID | 22888 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
toe | +0.974 |
acted | +0.904 |
ring | +0.883 |
enough | +0.880 |
atively | +0.852 |
Neg logit contributions | |
Mehran | -1.019 |
lapt | -1.005 |
etsk | -0.974 |
caut | -0.951 |
unta | -0.938 |
Token | Yes |
Token ID | 5297 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
toe | +3.201 |
acted | +2.936 |
enough | +2.896 |
ring | +2.865 |
atively | +2.752 |
Neg logit contributions | |
Mehran | -3.910 |
lapt | -3.810 |
etsk | -3.706 |
caut | -3.625 |
unta | -3.582 |
Token | to |
Token ID | 284 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
toe | +1.585 |
acted | +1.452 |
ring | +1.407 |
enough | +1.398 |
atively | +1.341 |
Neg logit contributions | |
Mehran | -2.289 |
lapt | -2.251 |
etsk | -2.185 |
caut | -2.149 |
unta | -2.130 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Mehran | +0.436 |
lapt | +0.426 |
etsk | +0.413 |
caut | +0.404 |
unta | +0.400 |
Neg logit contributions | |
toe | -0.442 |
acted | -0.412 |
ring | -0.401 |
enough | -0.398 |
atively | -0.384 |
Token | questions |
Token ID | 2683 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
toe | +1.218 |
acted | +1.140 |
ring | +1.112 |
enough | +1.106 |
atively | +1.071 |
Neg logit contributions | |
Mehran | -1.106 |
lapt | -1.081 |
etsk | -1.039 |
caut | -1.019 |
unta | -1.010 |
Token | : |
Token ID | 25 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Mehran | +3.376 |
lapt | +3.306 |
etsk | +3.254 |
caut | +3.168 |
unta | +3.134 |
Neg logit contributions | |
toe | -2.654 |
acted | -2.448 |
enough | -2.374 |
ring | -2.374 |
atively | -2.257 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +1.235 |
acted | +1.146 |
ring | +1.120 |
enough | +1.115 |
atively | +1.074 |
Neg logit contributions | |
Mehran | -1.345 |
lapt | -1.319 |
etsk | -1.277 |
caut | -1.252 |
unta | -1.240 |
Token | � |
Token ID | 250 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
toe | +12.072 |
acted | +11.605 |
ring | +11.451 |
enough | +11.124 |
atively | +11.095 |
Neg logit contributions | |
Mehran | -7.480 |
lapt | -7.233 |
etsk | -6.942 |
caut | -6.559 |
unta | -6.458 |
Token | Do |
Token ID | 5211 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
toe | +0.867 |
acted | +0.804 |
ring | +0.781 |
enough | +0.778 |
atively | +0.749 |
Neg logit contributions | |
Mehran | -1.003 |
lapt | -0.985 |
etsk | -0.955 |
caut | -0.936 |
unta | -0.926 |
Token | you |
Token ID | 345 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
toe | +3.993 |
acted | +3.749 |
ring | +3.695 |
enough | +3.663 |
atively | +3.558 |
Neg logit contributions | |
Mehran | -3.449 |
lapt | -3.379 |
etsk | -3.249 |
caut | -3.182 |
unta | -3.144 |
Token | want |
Token ID | 765 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Mehran | +1.202 |
lapt | +1.180 |
etsk | +1.136 |
caut | +1.110 |
unta | +1.097 |
Neg logit contributions | |
toe | -1.323 |
acted | -1.239 |
enough | -1.200 |
ring | -1.200 |
atively | -1.160 |
Token | Catalonia |
Token ID | 33859 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
toe | +0.759 |
acted | +0.698 |
ring | +0.675 |
enough | +0.672 |
atively | +0.645 |
Neg logit contributions | |
Mehran | -1.010 |
lapt | -0.992 |
etsk | -0.961 |
caut | -0.945 |
unta | -0.937 |
Token | year |
Token ID | 1941 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
toe | +2.828 |
acted | +2.625 |
ring | +2.559 |
enough | +2.537 |
atively | +2.439 |
Neg logit contributions | |
Mehran | -3.151 |
lapt | -3.093 |
etsk | -2.996 |
caut | -2.933 |
unta | -2.900 |
Token | - |
Token ID | 12 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
Mehran | +0.237 |
lapt | +0.235 |
etsk | +0.230 |
caut | +0.228 |
unta | +0.223 |
Neg logit contributions | |
toe | -0.111 |
acted | -0.101 |
ring | -0.097 |
enough | -0.094 |
atively | -0.090 |
Token | old |
Token ID | 727 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
toe | +3.018 |
acted | +2.817 |
ring | +2.795 |
enough | +2.736 |
works | +2.647 |
Neg logit contributions | |
lapt | -3.226 |
Mehran | -3.108 |
caut | -3.080 |
ccording | -3.048 |
mosqu | -2.986 |
Token | said |
Token ID | 531 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
toe | +0.931 |
acted | +0.870 |
ring | +0.850 |
enough | +0.840 |
atively | +0.814 |
Neg logit contributions | |
Mehran | -0.940 |
lapt | -0.923 |
etsk | -0.894 |
caut | -0.872 |
unta | -0.865 |
Token | : |
Token ID | 25 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
toe | +0.306 |
acted | +0.281 |
ring | +0.272 |
enough | +0.271 |
atively | +0.260 |
Neg logit contributions | |
Mehran | -0.404 |
lapt | -0.397 |
etsk | -0.386 |
caut | -0.379 |
unta | -0.375 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
toe | +1.965 |
acted | +1.833 |
ring | +1.781 |
enough | +1.775 |
atively | +1.716 |
Neg logit contributions | |
Mehran | -1.978 |
lapt | -1.937 |
etsk | -1.874 |
caut | -1.832 |
unta | -1.815 |
Token | � |
Token ID | 250 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
toe | +12.365 |
acted | +11.791 |
ring | +11.697 |
enough | +11.396 |
atively | +11.293 |
Neg logit contributions | |
Mehran | -7.349 |
lapt | -7.337 |
caut | -6.976 |
etsk | -6.720 |
mosqu | -6.601 |
Token | Thousands |
Token ID | 37482 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
toe | +0.965 |
acted | +0.897 |
ring | +0.873 |
enough | +0.870 |
atively | +0.839 |
Neg logit contributions | |
Mehran | -1.014 |
lapt | -0.996 |
etsk | -0.962 |
caut | -0.943 |
unta | -0.933 |
Token | of |
Token ID | 286 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Mehran | +0.618 |
lapt | +0.607 |
etsk | +0.585 |
caut | +0.573 |
unta | +0.568 |
Neg logit contributions | |
toe | -0.629 |
acted | -0.585 |
ring | -0.570 |
enough | -0.569 |
atively | -0.551 |
Token | young |
Token ID | 1862 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
Mehran | +0.681 |
lapt | +0.668 |
etsk | +0.643 |
caut | +0.631 |
unta | +0.624 |
Neg logit contributions | |
toe | -0.696 |
acted | -0.649 |
ring | -0.631 |
enough | -0.629 |
atively | -0.608 |
Token | men |
Token ID | 1450 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Mehran | +3.794 |
lapt | +3.734 |
etsk | +3.530 |
caut | +3.507 |
unta | +3.462 |
Neg logit contributions | |
toe | -4.236 |
acted | -3.932 |
ring | -3.790 |
enough | -3.781 |
atively | -3.713 |
Token | s |
Token ID | 82 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
Mehran | +1.594 |
lapt | +1.566 |
etsk | +1.522 |
caut | +1.495 |
unta | +1.484 |
Neg logit contributions | |
toe | -1.113 |
acted | -1.020 |
ring | -0.986 |
enough | -0.981 |
atively | -0.939 |
Token | nomination |
Token ID | 11872 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
Mehran | +0.752 |
lapt | +0.738 |
etsk | +0.712 |
caut | +0.699 |
unta | +0.691 |
Neg logit contributions | |
toe | -0.724 |
acted | -0.673 |
ring | -0.654 |
enough | -0.652 |
atively | -0.629 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Mehran | +0.649 |
lapt | +0.634 |
etsk | +0.622 |
caut | +0.611 |
unta | +0.605 |
Neg logit contributions | |
toe | -0.425 |
acted | -0.385 |
enough | -0.374 |
ring | -0.369 |
atively | -0.351 |
Token | stating |
Token ID | 12316 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Mehran | +1.693 |
lapt | +1.653 |
etsk | +1.601 |
caut | +1.568 |
unta | +1.546 |
Neg logit contributions | |
toe | -1.688 |
acted | -1.566 |
ring | -1.523 |
enough | -1.519 |
atively | -1.468 |
Token | : |
Token ID | 25 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
toe | +1.434 |
acted | +1.320 |
ring | +1.280 |
enough | +1.271 |
atively | +1.223 |
Neg logit contributions | |
Mehran | -1.939 |
lapt | -1.907 |
etsk | -1.849 |
caut | -1.817 |
unta | -1.800 |
Token | � |
Token ID | 564 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
toe | +2.597 |
acted | +2.398 |
ring | +2.328 |
enough | +2.316 |
atively | +2.228 |
Neg logit contributions | |
Mehran | -3.173 |
lapt | -3.119 |
etsk | -3.018 |
caut | -2.963 |
unta | -2.937 |
Token | � |
Token ID | 250 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
toe | +12.167 |
acted | +11.734 |
ring | +11.348 |
enough | +11.266 |
atively | +11.051 |
Neg logit contributions | |
Mehran | -7.400 |
lapt | -7.372 |
etsk | -6.666 |
caut | -6.584 |
mosqu | -6.359 |
Token | Mr |
Token ID | 5246 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
toe | +1.328 |
acted | +1.235 |
ring | +1.201 |
enough | +1.198 |
atively | +1.154 |
Neg logit contributions | |
Mehran | -1.374 |
lapt | -1.348 |
etsk | -1.301 |
caut | -1.277 |
unta | -1.262 |
Token | . |
Token ID | 13 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
Mehran | +6.106 |
etsk | +5.608 |
lapt | +5.594 |
ebin | +5.556 |
unta | +5.538 |
Neg logit contributions | |
toe | -3.793 |
acted | -3.407 |
enough | -3.320 |
ring | -3.279 |
atively | -3.143 |
Token | Pruitt |
Token ID | 39637 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Mehran | +4.198 |
etsk | +3.698 |
lapt | +3.631 |
caut | +3.527 |
ebin | +3.436 |
Neg logit contributions | |
toe | -6.980 |
acted | -6.425 |
enough | -6.397 |
ring | -6.327 |
works | -6.147 |
Token | � |
Token ID | 447 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
toe | +0.631 |
acted | +0.581 |
ring | +0.564 |
enough | +0.563 |
atively | +0.539 |
Neg logit contributions | |
Mehran | -0.774 |
lapt | -0.759 |
etsk | -0.736 |
caut | -0.723 |
unta | -0.716 |
Token | Greg |
Token ID | 8547 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
toe | +0.380 |
acted | +0.354 |
ring | +0.344 |
enough | +0.343 |
atively | +0.331 |
Neg logit contributions | |
Mehran | -0.391 |
lapt | -0.383 |
etsk | -0.371 |
caut | -0.363 |
unta | -0.359 |
Token | or |
Token ID | 273 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Mehran | +2.062 |
lapt | +2.001 |
etsk | +1.960 |
caut | +1.902 |
unta | +1.898 |
Neg logit contributions | |
toe | -1.784 |
acted | -1.637 |
enough | -1.593 |
ring | -1.586 |
atively | -1.533 |
Token | Townsend |
Token ID | 46811 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Mehran | +3.240 |
lapt | +3.128 |
etsk | +3.076 |
caut | +2.997 |
unta | +2.991 |
Neg logit contributions | |
toe | -1.879 |
acted | -1.680 |
enough | -1.658 |
ring | -1.616 |
atively | -1.544 |
Token | said |
Token ID | 531 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Mehran | +0.114 |
lapt | +0.111 |
etsk | +0.108 |
caut | +0.105 |
unta | +0.104 |
Neg logit contributions | |
toe | -0.114 |
acted | -0.106 |
ring | -0.103 |
enough | -0.103 |
atively | -0.099 |
Token | : |
Token ID | 25 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
toe | +0.574 |
acted | +0.526 |
ring | +0.508 |
enough | +0.506 |
atively | +0.484 |
Neg logit contributions | |
Mehran | -0.809 |
lapt | -0.796 |
etsk | -0.773 |
caut | -0.759 |
unta | -0.751 |
Token | � |
Token ID | 564 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
toe | +1.998 |
acted | +1.868 |
ring | +1.813 |
enough | +1.810 |
atively | +1.749 |
Neg logit contributions | |
Mehran | -2.009 |
lapt | -1.964 |
etsk | -1.905 |
caut | -1.856 |
unta | -1.840 |
Token | � |
Token ID | 250 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
toe | +13.426 |
acted | +12.806 |
ring | +12.730 |
enough | +12.446 |
atively | +12.365 |
Neg logit contributions | |
Mehran | -6.193 |
lapt | -5.902 |
etsk | -5.558 |
caut | -5.437 |
unta | -5.390 |
Token | Le |
Token ID | 3123 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
toe | +0.787 |
acted | +0.730 |
ring | +0.709 |
enough | +0.706 |
atively | +0.681 |
Neg logit contributions | |
Mehran | -0.885 |
lapt | -0.867 |
etsk | -0.840 |
caut | -0.822 |
unta | -0.814 |
Token | icester |
Token ID | 26382 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
toe | +3.509 |
acted | +3.274 |
ring | +3.225 |
enough | +3.136 |
uther | +3.073 |
Neg logit contributions | |
Mehran | -3.549 |
lapt | -3.488 |
etsk | -3.300 |
unta | -3.283 |
caut | -3.262 |
Token | have |
Token ID | 423 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
toe | +2.825 |
acted | +2.649 |
ring | +2.594 |
enough | +2.547 |
atively | +2.490 |
Neg logit contributions | |
Mehran | -2.440 |
lapt | -2.377 |
etsk | -2.295 |
caut | -2.234 |
unta | -2.227 |
Token | an |
Token ID | 281 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
toe | +3.640 |
acted | +3.395 |
ring | +3.303 |
enough | +3.260 |
atively | +3.171 |
Neg logit contributions | |
Mehran | -4.333 |
lapt | -4.169 |
etsk | -4.131 |
caut | -4.013 |
unta | -3.998 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
toe | +2.780 |
acted | +2.530 |
ring | +2.486 |
enough | +2.432 |
atively | +2.374 |
Neg logit contributions | |
Mehran | -3.550 |
lapt | -3.468 |
etsk | -3.342 |
caut | -3.295 |
unta | -3.255 |
Token | she |
Token ID | 673 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Mehran | +1.009 |
lapt | +0.986 |
etsk | +0.952 |
caut | +0.933 |
unta | +0.921 |
Neg logit contributions | |
toe | -1.132 |
acted | -1.057 |
ring | -1.028 |
enough | -1.027 |
atively | -0.993 |
Token | simply |
Token ID | 2391 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
toe | +0.879 |
acted | +0.823 |
ring | +0.802 |
enough | +0.792 |
atively | +0.769 |
Neg logit contributions | |
Mehran | -0.949 |
lapt | -0.934 |
etsk | -0.897 |
caut | -0.876 |
unta | -0.872 |
Token | answered |
Token ID | 9373 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
toe | +0.905 |
acted | +0.848 |
ring | +0.823 |
enough | +0.817 |
atively | +0.789 |
Neg logit contributions | |
Mehran | -0.979 |
lapt | -0.960 |
etsk | -0.922 |
caut | -0.906 |
unta | -0.898 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
toe | +0.690 |
acted | +0.632 |
ring | +0.612 |
enough | +0.606 |
atively | +0.583 |
Neg logit contributions | |
Mehran | -1.019 |
lapt | -1.002 |
etsk | -0.974 |
caut | -0.956 |
unta | -0.948 |
Token | � |
Token ID | 564 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
toe | +1.768 |
acted | +1.645 |
ring | +1.602 |
enough | +1.594 |
atively | +1.540 |
Neg logit contributions | |
Mehran | -1.804 |
lapt | -1.769 |
etsk | -1.709 |
caut | -1.674 |
unta | -1.657 |
Token | � |
Token ID | 250 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
toe | +11.984 |
acted | +11.522 |
ring | +11.287 |
enough | +11.032 |
atively | +10.778 |
Neg logit contributions | |
Mehran | -7.562 |
lapt | -7.379 |
etsk | -6.971 |
caut | -6.797 |
unta | -6.570 |
Token | Why |
Token ID | 5195 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
toe | +0.925 |
acted | +0.855 |
ring | +0.830 |
enough | +0.826 |
atively | +0.794 |
Neg logit contributions | |
Mehran | -1.142 |
lapt | -1.122 |
etsk | -1.087 |
caut | -1.066 |
unta | -1.056 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
Mehran | +2.340 |
lapt | +2.314 |
etsk | +2.227 |
caut | +2.189 |
unta | +2.160 |
Neg logit contributions | |
toe | -2.519 |
acted | -2.353 |
enough | -2.273 |
ring | -2.270 |
atively | -2.203 |
Token | � |
Token ID | 447 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Mehran | +4.297 |
etsk | +4.043 |
lapt | +3.972 |
unta | +3.931 |
ebin | +3.831 |
Neg logit contributions | |
toe | -4.372 |
acted | -4.067 |
enough | -3.956 |
ring | -3.940 |
atively | -3.836 |
Token | � |
Token ID | 247 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Mehran | +1.928 |
lapt | +1.883 |
etsk | +1.814 |
caut | +1.765 |
unta | +1.750 |
Neg logit contributions | |
toe | -2.474 |
acted | -2.320 |
ring | -2.268 |
enough | -2.258 |
atively | -2.191 |
Token | ] |
Token ID | 60 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Mehran | +0.861 |
lapt | +0.854 |
etsk | +0.827 |
caut | +0.814 |
unta | +0.800 |
Neg logit contributions | |
toe | -0.785 |
acted | -0.703 |
enough | -0.694 |
ring | -0.684 |
atively | -0.673 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Mehran | +0.727 |
lapt | +0.718 |
etsk | +0.689 |
caut | +0.676 |
unta | +0.663 |
Neg logit contributions | |
toe | -0.838 |
acted | -0.784 |
ring | -0.767 |
enough | -0.761 |
atively | -0.737 |
Token | From |
Token ID | 4863 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
toe | +1.307 |
acted | +1.225 |
ring | +1.197 |
enough | +1.191 |
atively | +1.153 |
Neg logit contributions | |
Mehran | -1.081 |
lapt | -1.058 |
etsk | -1.018 |
caut | -0.995 |
unta | -0.982 |
Token | Ar |
Token ID | 3163 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Mehran | +2.913 |
lapt | +2.838 |
etsk | +2.750 |
unta | +2.714 |
caut | +2.676 |
Neg logit contributions | |
toe | -2.224 |
acted | -2.055 |
enough | -1.994 |
ring | -1.952 |
atively | -1.909 |
Token | gb |
Token ID | 22296 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Mehran | +1.843 |
lapt | +1.815 |
etsk | +1.751 |
caut | +1.729 |
unta | +1.699 |
Neg logit contributions | |
toe | -1.500 |
acted | -1.388 |
ring | -1.348 |
enough | -1.340 |
atively | -1.288 |
Token | ($ |
Token ID | 16763 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
Mehran | +0.330 |
lapt | +0.326 |
etsk | +0.307 |
caut | +0.302 |
unta | +0.298 |
Neg logit contributions | |
toe | -0.448 |
acted | -0.423 |
enough | -0.411 |
ring | -0.408 |
atively | -0.403 |
Token | FC |
Token ID | 4851 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
lapt | +6.063 |
Mehran | +5.951 |
etsk | +5.792 |
unta | +5.682 |
caut | +5.608 |
Neg logit contributions | |
toe | -6.059 |
acted | -5.660 |
enough | -5.475 |
atively | -5.375 |
ring | -5.297 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
toe | +0.729 |
acted | +0.677 |
ring | +0.660 |
enough | +0.655 |
atively | +0.633 |
Neg logit contributions | |
Mehran | -0.779 |
lapt | -0.762 |
etsk | -0.740 |
caut | -0.725 |
unta | -0.715 |
Token | [ |
Token ID | 58 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
toe | +1.006 |
acted | +0.929 |
ring | +0.903 |
enough | +0.897 |
atively | +0.862 |
Neg logit contributions | |
Mehran | -1.240 |
lapt | -1.218 |
etsk | -1.181 |
caut | -1.159 |
unta | -1.147 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Mehran | +1.401 |
lapt | +1.375 |
etsk | +1.316 |
unta | +1.288 |
caut | +1.281 |
Neg logit contributions | |
toe | -1.604 |
acted | -1.513 |
enough | -1.456 |
ring | -1.448 |
atively | -1.424 |
Token | ], |
Token ID | 4357 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
toe | +0.418 |
acted | +0.383 |
enough | +0.373 |
ring | +0.371 |
atively | +0.358 |
Neg logit contributions | |
Mehran | -0.500 |
lapt | -0.491 |
etsk | -0.475 |
caut | -0.467 |
unta | -0.466 |
Token | plan |
Token ID | 1410 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
toe | +2.623 |
acted | +2.464 |
ring | +2.423 |
enough | +2.394 |
atively | +2.315 |
Neg logit contributions | |
Mehran | -2.415 |
lapt | -2.380 |
etsk | -2.303 |
caut | -2.223 |
unta | -2.190 |
Token | . |
Token ID | 13 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
Mehran | +0.035 |
lapt | +0.035 |
etsk | +0.034 |
caut | +0.033 |
unta | +0.033 |
Neg logit contributions | |
toe | -0.023 |
acted | -0.021 |
enough | -0.020 |
ring | -0.020 |
atively | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
toe | +0.691 |
acted | +0.638 |
ring | +0.619 |
enough | +0.615 |
atively | +0.591 |
Neg logit contributions | |
Mehran | -0.869 |
lapt | -0.856 |
etsk | -0.829 |
caut | -0.814 |
unta | -0.805 |
Token | says |
Token ID | 1139 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
toe | +0.648 |
acted | +0.607 |
ring | +0.592 |
enough | +0.587 |
atively | +0.570 |
Neg logit contributions | |
Mehran | -0.618 |
lapt | -0.609 |
etsk | -0.584 |
caut | -0.572 |
unta | -0.566 |
Token | club |
Token ID | 3430 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
toe | +0.477 |
acted | +0.445 |
ring | +0.434 |
enough | +0.431 |
atively | +0.417 |
Neg logit contributions | |
Mehran | -0.468 |
lapt | -0.459 |
etsk | -0.443 |
caut | -0.433 |
unta | -0.429 |
Token | managers |
Token ID | 11663 |
Feature activation | +9.00e+00 |
Pos logit contributions | |
toe | +2.122 |
acted | +1.999 |
ring | +1.964 |
enough | +1.931 |
atively | +1.885 |
Neg logit contributions | |
Mehran | -1.756 |
lapt | -1.723 |
etsk | -1.668 |
caut | -1.609 |
unta | -1.591 |
Token | assured |
Token ID | 13933 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Mehran | +6.299 |
lapt | +6.132 |
caut | +6.005 |
unta | +5.956 |
etsk | +5.883 |
Neg logit contributions | |
toe | -7.269 |
enough | -6.659 |
acted | -6.600 |
ring | -6.529 |
atively | -6.344 |
Token | her |
Token ID | 607 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
Mehran | +2.150 |
lapt | +2.106 |
etsk | +2.016 |
caut | +1.993 |
unta | +1.992 |
Neg logit contributions | |
toe | -2.232 |
acted | -2.053 |
enough | -1.999 |
ring | -1.993 |
works | -1.913 |
Token | that |
Token ID | 326 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
toe | +2.439 |
acted | +2.270 |
ring | +2.224 |
enough | +2.206 |
atively | +2.131 |
Neg logit contributions | |
Mehran | -2.682 |
lapt | -2.634 |
etsk | -2.565 |
caut | -2.499 |
unta | -2.467 |
Token | if |
Token ID | 611 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
Mehran | +0.504 |
lapt | +0.494 |
etsk | +0.474 |
caut | +0.467 |
unta | +0.462 |
Neg logit contributions | |
toe | -0.525 |
acted | -0.489 |
ring | -0.475 |
enough | -0.473 |
atively | -0.458 |
Token | she |
Token ID | 673 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Mehran | +2.627 |
lapt | +2.555 |
etsk | +2.437 |
caut | +2.419 |
unta | +2.411 |
Neg logit contributions | |
toe | -3.283 |
acted | -3.033 |
ring | -2.966 |
enough | -2.946 |
atively | -2.872 |
Token | ic |
Token ID | 291 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
Mehran | +2.121 |
lapt | +2.082 |
etsk | +2.021 |
caut | +1.986 |
unta | +1.977 |
Neg logit contributions | |
toe | -1.418 |
acted | -1.296 |
enough | -1.249 |
ring | -1.245 |
atively | -1.185 |
Token | names |
Token ID | 3891 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
toe | +2.679 |
acted | +2.488 |
ring | +2.454 |
enough | +2.386 |
atively | +2.350 |
Neg logit contributions | |
Mehran | -3.250 |
lapt | -3.207 |
etsk | -3.119 |
caut | -3.054 |
unta | -3.007 |
Token | were |
Token ID | 547 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Mehran | +3.817 |
lapt | +3.744 |
etsk | +3.643 |
caut | +3.581 |
unta | +3.567 |
Neg logit contributions | |
toe | -3.640 |
acted | -3.372 |
enough | -3.281 |
ring | -3.256 |
atively | -3.127 |
Token | common |
Token ID | 2219 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
Mehran | +1.496 |
lapt | +1.468 |
etsk | +1.419 |
caut | +1.393 |
unta | +1.378 |
Neg logit contributions | |
toe | -1.378 |
acted | -1.278 |
ring | -1.242 |
enough | -1.237 |
atively | -1.192 |
Token | among |
Token ID | 1871 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
toe | +2.787 |
acted | +2.640 |
ring | +2.609 |
enough | +2.592 |
atively | +2.509 |
Neg logit contributions | |
Mehran | -2.784 |
lapt | -2.734 |
etsk | -2.631 |
caut | -2.573 |
unta | -2.554 |
Token | Mong |
Token ID | 18428 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
Mehran | +0.461 |
lapt | +0.452 |
etsk | +0.437 |
caut | +0.427 |
unta | +0.423 |
Neg logit contributions | |
toe | -0.479 |
acted | -0.447 |
ring | -0.436 |
enough | -0.434 |
atively | -0.420 |
Token | ols |
Token ID | 10220 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Mehran | +3.088 |
lapt | +2.940 |
etsk | +2.907 |
unta | +2.856 |
caut | +2.597 |
Neg logit contributions | |
toe | -9.376 |
enough | -8.897 |
acted | -8.882 |
works | -8.525 |
backer | -8.451 |
Token | ( |
Token ID | 357 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Mehran | +2.458 |
lapt | +2.415 |
etsk | +2.345 |
caut | +2.295 |
unta | +2.285 |
Neg logit contributions | |
toe | -2.123 |
acted | -1.956 |
ring | -1.881 |
enough | -1.879 |
atively | -1.806 |
Token | such |
Token ID | 10508 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
toe | +1.129 |
acted | +1.043 |
ring | +1.019 |
enough | +1.016 |
atively | +0.970 |
Neg logit contributions | |
Mehran | -1.411 |
lapt | -1.383 |
etsk | -1.336 |
caut | -1.322 |
unta | -1.295 |
Token | as |
Token ID | 355 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Mehran | +3.234 |
lapt | +3.175 |
etsk | +3.090 |
caut | +3.003 |
unta | +2.940 |
Neg logit contributions | |
toe | -3.919 |
acted | -3.693 |
enough | -3.586 |
ring | -3.435 |
hole | -3.371 |
Token | O |
Token ID | 440 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
toe | +0.190 |
acted | +0.177 |
ring | +0.173 |
enough | +0.172 |
atively | +0.166 |
Neg logit contributions | |
Mehran | -0.184 |
lapt | -0.181 |
etsk | -0.175 |
caut | -0.171 |
unta | -0.169 |
Token | Jake |
Token ID | 43930 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Mehran | +1.812 |
lapt | +1.760 |
etsk | +1.730 |
unta | +1.670 |
caut | +1.646 |
Neg logit contributions | |
toe | -2.074 |
acted | -1.943 |
enough | -1.888 |
ring | -1.878 |
atively | -1.843 |
Token | was |
Token ID | 373 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Mehran | +1.786 |
lapt | +1.774 |
etsk | +1.700 |
caut | +1.651 |
unta | +1.631 |
Neg logit contributions | |
toe | -2.474 |
acted | -2.318 |
enough | -2.263 |
ring | -2.257 |
atively | -2.181 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Mehran | +1.394 |
lapt | +1.368 |
etsk | +1.324 |
caut | +1.294 |
unta | +1.282 |
Neg logit contributions | |
toe | -1.374 |
acted | -1.275 |
ring | -1.238 |
enough | -1.236 |
atively | -1.190 |
Token | first |
Token ID | 717 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
toe | +0.223 |
acted | +0.207 |
ring | +0.203 |
enough | +0.200 |
atively | +0.195 |
Neg logit contributions | |
Mehran | -0.231 |
lapt | -0.227 |
etsk | -0.219 |
caut | -0.214 |
unta | -0.212 |
Token | rock |
Token ID | 3881 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Mehran | +1.238 |
lapt | +1.212 |
etsk | +1.166 |
caut | +1.142 |
unta | +1.135 |
Neg logit contributions | |
toe | -1.366 |
acted | -1.278 |
enough | -1.242 |
ring | -1.237 |
atively | -1.196 |
Token | analyzed |
Token ID | 15475 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
Mehran | +0.258 |
lapt | +0.253 |
etsk | +0.245 |
caut | +0.240 |
unta | +0.239 |
Neg logit contributions | |
toe | -0.224 |
acted | -0.207 |
enough | -0.201 |
ring | -0.201 |
atively | -0.193 |
Token | by |
Token ID | 416 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Mehran | +5.835 |
lapt | +5.546 |
etsk | +5.523 |
unta | +5.361 |
caut | +5.316 |
Neg logit contributions | |
toe | -6.564 |
acted | -6.050 |
enough | -5.967 |
ring | -5.787 |
uther | -5.637 |
Token | the |
Token ID | 262 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Mehran | +2.123 |
lapt | +2.039 |
etsk | +1.985 |
caut | +1.949 |
unta | +1.922 |
Neg logit contributions | |
toe | -2.292 |
acted | -2.114 |
enough | -2.061 |
ring | -2.043 |
atively | -1.982 |
Token | rover |
Token ID | 35761 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
toe | +0.219 |
acted | +0.204 |
ring | +0.199 |
enough | +0.198 |
atively | +0.191 |
Neg logit contributions | |
Mehran | -0.219 |
lapt | -0.215 |
etsk | -0.208 |
caut | -0.204 |
unta | -0.201 |
Token | 's |
Token ID | 338 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Mehran | +2.487 |
lapt | +2.447 |
etsk | +2.386 |
caut | +2.327 |
unta | +2.319 |
Neg logit contributions | |
toe | -2.109 |
acted | -1.950 |
enough | -1.865 |
ring | -1.839 |
atively | -1.789 |
Token | arm |
Token ID | 3211 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
Mehran | +1.048 |
lapt | +1.026 |
etsk | +0.994 |
caut | +0.974 |
unta | +0.963 |
Neg logit contributions | |
toe | -1.012 |
acted | -0.940 |
ring | -0.912 |
enough | -0.909 |
atively | -0.878 |
Token | get |
Token ID | 651 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
toe | +0.383 |
acted | +0.357 |
ring | +0.353 |
enough | +0.350 |
atively | +0.340 |
Neg logit contributions | |
Mehran | -0.306 |
lapt | -0.298 |
etsk | -0.287 |
caut | -0.280 |
unta | -0.277 |
Token | some |
Token ID | 617 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Mehran | +0.330 |
lapt | +0.324 |
etsk | +0.313 |
caut | +0.307 |
unta | +0.304 |
Neg logit contributions | |
toe | -0.304 |
acted | -0.282 |
ring | -0.274 |
enough | -0.273 |
atively | -0.263 |
Token | recorded |
Token ID | 6264 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Mehran | +0.123 |
lapt | +0.121 |
etsk | +0.116 |
caut | +0.114 |
unta | +0.113 |
Neg logit contributions | |
toe | -0.119 |
acted | -0.111 |
ring | -0.108 |
enough | -0.107 |
atively | -0.103 |
Token | within |
Token ID | 1626 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Mehran | +1.542 |
lapt | +1.521 |
etsk | +1.452 |
caut | +1.430 |
ebin | +1.408 |
Neg logit contributions | |
toe | -1.479 |
acted | -1.373 |
ring | -1.329 |
enough | -1.327 |
atively | -1.278 |
Token | the |
Token ID | 262 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Mehran | +1.834 |
lapt | +1.801 |
etsk | +1.711 |
ebin | +1.692 |
caut | +1.692 |
Neg logit contributions | |
toe | -1.913 |
acted | -1.770 |
ring | -1.711 |
enough | -1.702 |
atively | -1.647 |
Token | coming |
Token ID | 2406 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
toe | +0.448 |
acted | +0.421 |
ring | +0.412 |
enough | +0.410 |
atively | +0.397 |
Neg logit contributions | |
Mehran | -0.373 |
lapt | -0.365 |
etsk | -0.353 |
caut | -0.343 |
unta | -0.340 |
Token | weeks |
Token ID | 2745 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Mehran | +6.576 |
lapt | +6.441 |
ebin | +6.226 |
etsk | +5.969 |
caut | +5.958 |
Neg logit contributions | |
toe | -7.461 |
acted | -6.837 |
ring | -6.596 |
enough | -6.506 |
atively | -6.414 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Mehran | +4.023 |
lapt | +3.937 |
etsk | +3.842 |
ebin | +3.802 |
caut | +3.783 |
Neg logit contributions | |
toe | -2.743 |
acted | -2.524 |
ring | -2.384 |
enough | -2.359 |
atively | -2.265 |
Token | Or |
Token ID | 1471 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
toe | +0.574 |
acted | +0.529 |
ring | +0.514 |
enough | +0.512 |
atively | +0.490 |
Neg logit contributions | |
Mehran | -0.718 |
lapt | -0.707 |
etsk | -0.686 |
caut | -0.672 |
unta | -0.665 |
Token | are |
Token ID | 389 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
toe | +0.183 |
acted | +0.169 |
ring | +0.165 |
enough | +0.164 |
atively | +0.158 |
Neg logit contributions | |
Mehran | -0.215 |
lapt | -0.210 |
etsk | -0.204 |
caut | -0.200 |
unta | -0.199 |
Token | you |
Token ID | 345 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Mehran | +0.832 |
lapt | +0.818 |
etsk | +0.786 |
caut | +0.774 |
unta | +0.761 |
Neg logit contributions | |
toe | -0.884 |
acted | -0.823 |
ring | -0.800 |
enough | -0.796 |
atively | -0.770 |
Token | use |
Token ID | 779 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Mehran | +4.222 |
lapt | +4.140 |
etsk | +3.938 |
caut | +3.866 |
unta | +3.828 |
Neg logit contributions | |
toe | -4.803 |
acted | -4.455 |
enough | -4.376 |
ring | -4.308 |
uther | -4.147 |
Token | different |
Token ID | 1180 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Mehran | +1.799 |
lapt | +1.754 |
etsk | +1.666 |
caut | +1.651 |
unta | +1.615 |
Neg logit contributions | |
toe | -2.142 |
acted | -2.005 |
enough | -1.953 |
ring | -1.949 |
atively | -1.881 |
Token | devices |
Token ID | 4410 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
toe | +0.847 |
acted | +0.794 |
ring | +0.777 |
enough | +0.770 |
atively | +0.754 |
Neg logit contributions | |
Mehran | -0.786 |
lapt | -0.768 |
etsk | -0.752 |
caut | -0.727 |
unta | -0.725 |
Token |
|
Token ID | 198 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Mehran | +0.935 |
lapt | +0.916 |
etsk | +0.884 |
caut | +0.869 |
unta | +0.860 |
Neg logit contributions | |
toe | -0.779 |
acted | -0.722 |
ring | -0.698 |
enough | -0.697 |
atively | -0.667 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
toe | +0.275 |
acted | +0.252 |
ring | +0.246 |
enough | +0.242 |
atively | +0.231 |
Neg logit contributions | |
lapt | -0.390 |
Mehran | -0.388 |
etsk | -0.373 |
caut | -0.371 |
ccording | -0.365 |
Token | Mark |
Token ID | 9704 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
toe | +0.780 |
acted | +0.724 |
ring | +0.706 |
enough | +0.702 |
atively | +0.675 |
Neg logit contributions | |
Mehran | -0.833 |
lapt | -0.819 |
etsk | -0.792 |
caut | -0.777 |
unta | -0.768 |
Token | eting |
Token ID | 13629 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
Mehran | +2.601 |
lapt | +2.484 |
etsk | +2.433 |
caut | +2.314 |
unta | +2.268 |
Neg logit contributions | |
toe | -4.504 |
acted | -4.279 |
enough | -4.199 |
ring | -4.106 |
atively | -4.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Mehran | +6.074 |
lapt | +5.957 |
caut | +5.689 |
etsk | +5.649 |
unta | +5.585 |
Neg logit contributions | |
toe | -5.608 |
acted | -5.352 |
enough | -5.144 |
ring | -4.981 |
atively | -4.874 |
Token | business |
Token ID | 1597 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
Mehran | +1.223 |
lapt | +1.197 |
etsk | +1.149 |
caut | +1.127 |
unta | +1.112 |
Neg logit contributions | |
toe | -1.383 |
acted | -1.296 |
ring | -1.261 |
enough | -1.256 |
atively | -1.216 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Mehran | +3.784 |
lapt | +3.729 |
etsk | +3.544 |
caut | +3.524 |
unta | +3.480 |
Neg logit contributions | |
toe | -3.555 |
acted | -3.357 |
enough | -3.210 |
ring | -3.185 |
atively | -3.083 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
toe | +0.976 |
acted | +0.917 |
ring | +0.896 |
enough | +0.891 |
atively | +0.866 |
Neg logit contributions | |
Mehran | -0.770 |
lapt | -0.756 |
etsk | -0.728 |
caut | -0.710 |
unta | -0.701 |
Token | thirds |
Token ID | 17936 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
toe | +2.305 |
acted | +2.120 |
ring | +2.076 |
enough | +2.072 |
atively | +1.969 |
Neg logit contributions | |
Mehran | -2.781 |
lapt | -2.731 |
etsk | -2.642 |
caut | -2.606 |
unta | -2.568 |
Token | stating |
Token ID | 12316 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
toe | +2.354 |
acted | +2.159 |
ring | +2.138 |
enough | +2.093 |
atively | +2.038 |
Neg logit contributions | |
Mehran | -2.859 |
lapt | -2.790 |
etsk | -2.733 |
caut | -2.662 |
unta | -2.660 |
Token | that |
Token ID | 326 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
toe | +0.520 |
acted | +0.481 |
ring | +0.468 |
enough | +0.465 |
atively | +0.449 |
Neg logit contributions | |
Mehran | -0.609 |
lapt | -0.597 |
etsk | -0.579 |
caut | -0.567 |
unta | -0.562 |
Token | they |
Token ID | 484 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Mehran | +0.169 |
lapt | +0.166 |
etsk | +0.159 |
caut | +0.156 |
unta | +0.154 |
Neg logit contributions | |
toe | -0.198 |
acted | -0.185 |
ring | -0.181 |
enough | -0.180 |
atively | -0.174 |
Token | would |
Token ID | 561 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
Mehran | +1.067 |
lapt | +1.043 |
etsk | +1.000 |
caut | +0.976 |
unta | +0.964 |
Neg logit contributions | |
toe | -1.430 |
acted | -1.344 |
ring | -1.314 |
enough | -1.309 |
atively | -1.270 |
Token | be |
Token ID | 307 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Mehran | +3.112 |
lapt | +3.042 |
etsk | +2.926 |
caut | +2.834 |
unta | +2.794 |
Neg logit contributions | |
toe | -4.388 |
acted | -4.179 |
enough | -4.044 |
ring | -4.025 |
atively | -3.914 |
Token | more |
Token ID | 517 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Mehran | +3.260 |
lapt | +3.209 |
etsk | +3.096 |
caut | +3.063 |
unta | +3.007 |
Neg logit contributions | |
toe | -2.367 |
acted | -2.171 |
ring | -2.101 |
enough | -2.083 |
atively | -1.996 |
Token | inclined |
Token ID | 19514 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Mehran | +0.998 |
lapt | +0.975 |
etsk | +0.934 |
caut | +0.911 |
unta | +0.899 |
Neg logit contributions | |
toe | -1.401 |
acted | -1.319 |
ring | -1.290 |
enough | -1.285 |
atively | -1.248 |
Token | to |
Token ID | 284 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
toe | +2.137 |
acted | +1.953 |
ring | +1.886 |
enough | +1.856 |
atively | +1.795 |
Neg logit contributions | |
Mehran | -3.525 |
lapt | -3.482 |
etsk | -3.407 |
caut | -3.336 |
unta | -3.304 |
Token | take |
Token ID | 1011 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
toe | +0.640 |
acted | +0.593 |
ring | +0.585 |
enough | +0.580 |
atively | +0.562 |
Neg logit contributions | |
Mehran | -0.569 |
lapt | -0.559 |
etsk | -0.537 |
caut | -0.528 |
unta | -0.520 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
toe | +0.627 |
acted | +0.581 |
ring | +0.568 |
enough | +0.564 |
atively | +0.547 |
Neg logit contributions | |
Mehran | -0.680 |
lapt | -0.668 |
etsk | -0.648 |
caut | -0.635 |
unta | -0.629 |
Token | products |
Token ID | 3186 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Mehran | +1.255 |
lapt | +1.229 |
etsk | +1.177 |
caut | +1.157 |
unta | +1.146 |
Neg logit contributions | |
toe | -1.271 |
acted | -1.190 |
enough | -1.156 |
ring | -1.149 |
atively | -1.114 |
Token | increasing |
Token ID | 3649 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
Mehran | +0.910 |
lapt | +0.893 |
etsk | +0.862 |
caut | +0.844 |
unta | +0.835 |
Neg logit contributions | |
toe | -0.933 |
acted | -0.869 |
ring | -0.848 |
enough | -0.843 |
atively | -0.816 |
Token | like |
Token ID | 588 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Mehran | +4.088 |
lapt | +4.022 |
etsk | +3.745 |
caut | +3.723 |
unta | +3.637 |
Neg logit contributions | |
toe | -4.706 |
acted | -4.374 |
enough | -4.227 |
ring | -4.205 |
atively | -4.023 |
Token | crazy |
Token ID | 7165 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
toe | +0.324 |
acted | +0.301 |
ring | +0.295 |
enough | +0.294 |
atively | +0.284 |
Neg logit contributions | |
Mehran | -0.302 |
lapt | -0.296 |
etsk | -0.286 |
caut | -0.280 |
unta | -0.276 |
Token | over |
Token ID | 625 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
toe | +0.137 |
acted | +0.128 |
ring | +0.124 |
enough | +0.124 |
atively | +0.119 |
Neg logit contributions | |
Mehran | -0.145 |
lapt | -0.142 |
etsk | -0.138 |
caut | -0.135 |
unta | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Mehran | +0.573 |
lapt | +0.561 |
etsk | +0.540 |
caut | +0.527 |
unta | +0.523 |
Neg logit contributions | |
toe | -0.619 |
acted | -0.577 |
ring | -0.562 |
enough | -0.560 |
atively | -0.542 |
Token | next |
Token ID | 1306 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Mehran | +0.225 |
lapt | +0.220 |
etsk | +0.211 |
caut | +0.207 |
unta | +0.204 |
Neg logit contributions | |
toe | -0.263 |
acted | -0.246 |
ring | -0.240 |
enough | -0.239 |
atively | -0.232 |
Token | couple |
Token ID | 3155 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Mehran | +6.294 |
lapt | +6.188 |
ebin | +5.648 |
caut | +5.463 |
etsk | +5.455 |
Neg logit contributions | |
toe | -10.444 |
acted | -9.767 |
ring | -9.322 |
enough | -9.292 |
atively | -9.160 |
Token | of |
Token ID | 286 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Mehran | +1.164 |
lapt | +1.137 |
etsk | +1.104 |
caut | +1.077 |
unta | +1.058 |
Neg logit contributions | |
toe | -1.094 |
acted | -1.022 |
enough | -0.987 |
ring | -0.974 |
atively | -0.944 |
Token | months |
Token ID | 1933 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
Mehran | +2.405 |
lapt | +2.366 |
etsk | +2.281 |
caut | +2.244 |
unta | +2.225 |
Neg logit contributions | |
toe | -1.673 |
acted | -1.525 |
enough | -1.463 |
ring | -1.456 |
atively | -1.409 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Mehran | +4.017 |
lapt | +3.912 |
etsk | +3.822 |
caut | +3.738 |
unta | +3.714 |
Neg logit contributions | |
toe | -2.691 |
acted | -2.490 |
enough | -2.333 |
ring | -2.324 |
atively | -2.227 |
Token | � |
Token ID | 116 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
toe | +1.731 |
acted | +1.650 |
ring | +1.622 |
enough | +1.604 |
atively | +1.565 |
Neg logit contributions | |
Mehran | -0.926 |
lapt | -0.894 |
etsk | -0.848 |
caut | -0.821 |
unta | -0.803 |
Token | � |
Token ID | 141 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
Mehran | +2.757 |
lapt | +2.697 |
etsk | +2.595 |
caut | +2.569 |
unta | +2.539 |
Neg logit contributions | |
toe | -2.598 |
acted | -2.388 |
enough | -2.336 |
ring | -2.315 |
atively | -2.237 |
Token | � |
Token ID | 227 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
Mehran | +4.403 |
� | +4.266 |
lapt | +4.220 |
etsk | +4.045 |
unta | +3.812 |
Neg logit contributions | |
toe | -12.330 |
acted | -11.582 |
enough | -11.557 |
ring | -11.344 |
enegger | -11.129 |
Token | � |
Token ID | 12466 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
Mehran | +7.226 |
lapt | +7.048 |
etsk | +6.851 |
caut | +6.726 |
unta | +6.701 |
Neg logit contributions | |
toe | -5.097 |
acted | -4.657 |
enough | -4.438 |
ring | -4.393 |
atively | -4.203 |
Token | � |
Token ID | 111 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Mehran | +2.050 |
lapt | +2.004 |
etsk | +1.901 |
caut | +1.848 |
unta | +1.826 |
Neg logit contributions | |
toe | -4.135 |
acted | -3.896 |
enough | -3.833 |
ring | -3.812 |
atively | -3.727 |
Token | и |
Token ID | 18849 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Mehran | +4.384 |
lapt | +4.269 |
etsk | +4.094 |
caut | +4.044 |
ebin | +4.029 |
Neg logit contributions | |
toe | -4.791 |
acted | -4.447 |
enough | -4.373 |
ring | -4.302 |
atively | -4.166 |
Token | � |
Token ID | 140 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
Mehran | +3.959 |
lapt | +3.857 |
etsk | +3.709 |
caut | +3.614 |
unta | +3.601 |
Neg logit contributions | |
toe | -4.045 |
acted | -3.792 |
enough | -3.692 |
ring | -3.643 |
atively | -3.542 |
Token | � |
Token ID | 109 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Mehran | +1.579 |
lapt | +1.534 |
etsk | +1.464 |
caut | +1.411 |
unta | +1.392 |
Neg logit contributions | |
toe | -3.372 |
acted | -3.180 |
enough | -3.128 |
ring | -3.113 |
atively | -3.047 |
Token | е |
Token ID | 16843 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
toe | +0.497 |
acted | +0.463 |
ring | +0.451 |
enough | +0.448 |
atively | +0.433 |
Neg logit contributions | |
Mehran | -0.521 |
lapt | -0.512 |
etsk | -0.495 |
caut | -0.485 |
unta | -0.479 |
Token | л |
Token ID | 30143 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Mehran | +0.749 |
lapt | +0.733 |
etsk | +0.706 |
caut | +0.691 |
unta | +0.685 |
Neg logit contributions | |
toe | -0.844 |
acted | -0.791 |
enough | -0.769 |
ring | -0.768 |
atively | -0.743 |
Token | ь |
Token ID | 45367 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
toe | +1.542 |
acted | +1.441 |
ring | +1.413 |
enough | +1.399 |
atively | +1.359 |
Neg logit contributions | |
Mehran | -1.383 |
lapt | -1.357 |
etsk | -1.306 |
caut | -1.279 |
unta | -1.262 |
Token | make |
Token ID | 787 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Mehran | +1.764 |
lapt | +1.724 |
etsk | +1.657 |
caut | +1.616 |
unta | +1.596 |
Neg logit contributions | |
toe | -2.331 |
acted | -2.195 |
ring | -2.136 |
enough | -2.133 |
atively | -2.070 |
Token | a |
Token ID | 257 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Mehran | +3.151 |
lapt | +3.071 |
etsk | +2.917 |
caut | +2.885 |
unta | +2.854 |
Neg logit contributions | |
toe | -3.624 |
acted | -3.345 |
enough | -3.250 |
ring | -3.235 |
atively | -3.114 |
Token | political |
Token ID | 1964 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Mehran | +2.337 |
lapt | +2.291 |
etsk | +2.187 |
caut | +2.145 |
unta | +2.105 |
Neg logit contributions | |
toe | -2.848 |
acted | -2.665 |
ring | -2.592 |
enough | -2.591 |
atively | -2.512 |
Token | statement |
Token ID | 2643 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
Mehran | +3.126 |
lapt | +3.076 |
etsk | +2.914 |
caut | +2.884 |
unta | +2.802 |
Neg logit contributions | |
toe | -3.742 |
acted | -3.496 |
enough | -3.384 |
ring | -3.367 |
atively | -3.274 |
Token | of |
Token ID | 286 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
toe | +0.323 |
acted | +0.296 |
ring | +0.287 |
enough | +0.285 |
atively | +0.273 |
Neg logit contributions | |
Mehran | -0.468 |
lapt | -0.461 |
etsk | -0.448 |
caut | -0.439 |
unta | -0.436 |
Token | some |
Token ID | 617 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
toe | +1.673 |
acted | +1.559 |
ring | +1.532 |
enough | +1.516 |
atively | +1.475 |
Neg logit contributions | |
Mehran | -1.761 |
lapt | -1.712 |
etsk | -1.672 |
caut | -1.623 |
unta | -1.607 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Mehran | +0.693 |
lapt | +0.677 |
etsk | +0.654 |
caut | +0.637 |
unta | +0.630 |
Neg logit contributions | |
toe | -0.834 |
acted | -0.781 |
ring | -0.764 |
enough | -0.760 |
atively | -0.738 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
toe | +0.938 |
acted | +0.851 |
ring | +0.821 |
enough | +0.814 |
atively | +0.775 |
Neg logit contributions | |
Mehran | -1.650 |
lapt | -1.627 |
etsk | -1.581 |
caut | -1.556 |
unta | -1.543 |
Token | I |
Token ID | 314 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
toe | +0.884 |
acted | +0.815 |
ring | +0.795 |
enough | +0.787 |
atively | +0.754 |
Neg logit contributions | |
lapt | -1.106 |
Mehran | -1.100 |
etsk | -1.066 |
caut | -1.044 |
unta | -1.027 |
Token | have |
Token ID | 423 |
Feature activation | -8.95e+00 |
Pos logit contributions | |
toe | +3.053 |
acted | +2.860 |
ring | +2.836 |
enough | +2.768 |
atively | +2.689 |
Neg logit contributions | |
Mehran | -2.971 |
lapt | -2.911 |
etsk | -2.800 |
caut | -2.725 |
unta | -2.677 |
Token | seen |
Token ID | 1775 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
toe | +5.822 |
acted | +5.711 |
ring | +5.662 |
enough | +5.516 |
atively | +5.278 |
Neg logit contributions | |
Mehran | -7.473 |
etsk | -7.257 |
lapt | -7.230 |
unta | -7.018 |
aeper | -6.903 |
Token | plan |
Token ID | 1410 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
toe | +4.202 |
acted | +3.945 |
ring | +3.864 |
works | +3.743 |
enough | +3.688 |
Neg logit contributions | |
Mehran | -4.895 |
lapt | -4.683 |
etsk | -4.611 |
caut | -4.565 |
unta | -4.423 |
Token | for |
Token ID | 329 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
toe | +0.683 |
acted | +0.630 |
ring | +0.611 |
enough | +0.606 |
atively | +0.584 |
Neg logit contributions | |
Mehran | -0.876 |
lapt | -0.861 |
etsk | -0.835 |
caut | -0.819 |
unta | -0.811 |
Token | trails |
Token ID | 19196 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Mehran | +0.760 |
lapt | +0.746 |
etsk | +0.719 |
caut | +0.704 |
unta | +0.697 |
Neg logit contributions | |
toe | -0.803 |
acted | -0.749 |
ring | -0.729 |
enough | -0.727 |
atively | -0.702 |
Token | along |
Token ID | 1863 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Mehran | +1.449 |
lapt | +1.426 |
etsk | +1.383 |
caut | +1.351 |
unta | +1.341 |
Neg logit contributions | |
toe | -1.304 |
acted | -1.207 |
enough | -1.176 |
ring | -1.167 |
atively | -1.119 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Mehran | +1.296 |
lapt | +1.270 |
etsk | +1.225 |
caut | +1.195 |
unta | +1.190 |
Neg logit contributions | |
toe | -1.402 |
acted | -1.299 |
enough | -1.267 |
ring | -1.266 |
atively | -1.221 |
Token | creek |
Token ID | 39459 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Mehran | +0.838 |
lapt | +0.819 |
etsk | +0.788 |
caut | +0.769 |
unta | +0.760 |
Neg logit contributions | |
toe | -1.057 |
acted | -0.991 |
ring | -0.968 |
enough | -0.965 |
atively | -0.936 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
toe | +2.358 |
acted | +2.169 |
ring | +2.107 |
enough | +2.058 |
atively | +1.993 |
Neg logit contributions | |
Mehran | -3.614 |
lapt | -3.541 |
etsk | -3.456 |
caut | -3.398 |
unta | -3.343 |
Token | That |
Token ID | 1320 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Mehran | +0.209 |
lapt | +0.204 |
etsk | +0.198 |
caut | +0.194 |
unta | +0.193 |
Neg logit contributions | |
toe | -0.167 |
acted | -0.154 |
enough | -0.149 |
ring | -0.149 |
atively | -0.143 |
Token | urged |
Token ID | 11643 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Mehran | +3.391 |
lapt | +3.369 |
etsk | +3.175 |
caut | +3.149 |
unta | +3.095 |
Neg logit contributions | |
toe | -4.003 |
acted | -3.718 |
enough | -3.657 |
ring | -3.603 |
uther | -3.468 |
Token | road |
Token ID | 2975 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Mehran | +0.340 |
lapt | +0.333 |
etsk | +0.322 |
caut | +0.315 |
unta | +0.312 |
Neg logit contributions | |
toe | -0.348 |
acted | -0.325 |
ring | -0.317 |
enough | -0.315 |
atively | -0.305 |
Token | crossings |
Token ID | 41930 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
toe | +2.767 |
acted | +2.585 |
ring | +2.567 |
enough | +2.501 |
works | +2.473 |
Neg logit contributions | |
Mehran | -2.663 |
lapt | -2.547 |
etsk | -2.494 |
caut | -2.420 |
unta | -2.408 |
Token | on |
Token ID | 319 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Mehran | +0.648 |
lapt | +0.634 |
etsk | +0.611 |
caut | +0.602 |
unta | +0.597 |
Neg logit contributions | |
toe | -0.585 |
acted | -0.544 |
enough | -0.527 |
ring | -0.527 |
atively | -0.505 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
toe | +0.151 |
acted | +0.140 |
ring | +0.136 |
enough | +0.135 |
atively | +0.130 |
Neg logit contributions | |
Mehran | -0.170 |
lapt | -0.167 |
etsk | -0.161 |
caut | -0.158 |
unta | -0.157 |
Token | The |
Token ID | 383 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
Mehran | +1.241 |
lapt | +1.216 |
etsk | +1.178 |
caut | +1.155 |
unta | +1.145 |
Neg logit contributions | |
toe | -1.070 |
acted | -0.992 |
ring | -0.963 |
enough | -0.958 |
atively | -0.923 |
Token | retailers |
Token ID | 16167 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
toe | +0.717 |
acted | +0.670 |
ring | +0.654 |
enough | +0.648 |
atively | +0.628 |
Neg logit contributions | |
Mehran | -0.695 |
lapt | -0.683 |
etsk | -0.662 |
caut | -0.645 |
unta | -0.637 |
Token | today |
Token ID | 1909 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
Mehran | +5.275 |
lapt | +5.166 |
caut | +4.946 |
etsk | +4.894 |
unta | +4.867 |
Neg logit contributions | |
toe | -5.884 |
acted | -5.478 |
enough | -5.347 |
ring | -5.307 |
uther | -5.162 |
Token | have |
Token ID | 423 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
Mehran | +2.245 |
lapt | +2.195 |
etsk | +2.095 |
caut | +2.064 |
unta | +2.042 |
Neg logit contributions | |
toe | -2.738 |
acted | -2.562 |
enough | -2.500 |
ring | -2.494 |
atively | -2.411 |
Token | probably |
Token ID | 2192 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
toe | +4.199 |
acted | +3.915 |
ring | +3.792 |
enough | +3.788 |
atively | +3.664 |
Neg logit contributions | |
Mehran | -5.021 |
lapt | -4.931 |
etsk | -4.925 |
unta | -4.658 |
caut | -4.657 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
toe | +1.212 |
acted | +1.127 |
enough | +1.093 |
ring | +1.092 |
atively | +1.049 |
Neg logit contributions | |
Mehran | -1.471 |
lapt | -1.433 |
etsk | -1.412 |
unta | -1.366 |
caut | -1.365 |
Token | hardest |
Token ID | 17612 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
toe | +1.779 |
acted | +1.659 |
ring | +1.635 |
enough | +1.621 |
atively | +1.567 |
Neg logit contributions | |
Mehran | -1.567 |
lapt | -1.525 |
etsk | -1.495 |
unta | -1.442 |
caut | -1.440 |
Token | job |
Token ID | 1693 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Mehran | +3.320 |
lapt | +3.284 |
etsk | +3.085 |
caut | +3.047 |
ebin | +2.980 |
Neg logit contributions | |
toe | -4.155 |
acted | -3.896 |
enough | -3.764 |
ring | -3.759 |
atively | -3.681 |
Token | they |
Token ID | 484 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Mehran | +1.053 |
lapt | +1.031 |
etsk | +0.990 |
caut | +0.975 |
unta | +0.963 |
Neg logit contributions | |
toe | -1.097 |
acted | -1.027 |
enough | -0.997 |
ring | -0.989 |
atively | -0.958 |
Token | Font |
Token ID | 23252 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
lapt | +6.452 |
Mehran | +6.347 |
etsk | +6.145 |
unta | +6.070 |
ebin | +5.983 |
Neg logit contributions | |
toe | -5.679 |
acted | -5.302 |
atively | -5.037 |
enough | -5.035 |
ring | -4.933 |
Token | Name |
Token ID | 5376 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
Mehran | +0.699 |
lapt | +0.687 |
etsk | +0.655 |
unta | +0.645 |
caut | +0.644 |
Neg logit contributions | |
toe | -0.668 |
acted | -0.618 |
enough | -0.600 |
ring | -0.598 |
atively | -0.580 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Mehran | +4.475 |
lapt | +4.380 |
etsk | +4.183 |
unta | +4.138 |
caut | +4.104 |
Neg logit contributions | |
toe | -3.537 |
acted | -3.263 |
enough | -3.148 |
ring | -3.107 |
atively | -3.048 |
Token | $ |
Token ID | 3 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
Mehran | +1.732 |
lapt | +1.697 |
etsk | +1.626 |
caut | +1.581 |
unta | +1.576 |
Neg logit contributions | |
toe | -1.940 |
acted | -1.829 |
enough | -1.765 |
ring | -1.756 |
atively | -1.722 |
Token | FS |
Token ID | 10652 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
lapt | +5.282 |
Mehran | +5.229 |
etsk | +5.054 |
unta | +4.977 |
ebin | +4.883 |
Neg logit contributions | |
toe | -5.536 |
acted | -5.203 |
enough | -4.919 |
atively | -4.888 |
ring | -4.862 |
Token | 1 |
Token ID | 16 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Mehran | +1.507 |
lapt | +1.485 |
etsk | +1.403 |
unta | +1.382 |
caut | +1.376 |
Neg logit contributions | |
toe | -1.848 |
acted | -1.735 |
enough | -1.683 |
ring | -1.667 |
atively | -1.630 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
toe | +0.507 |
acted | +0.464 |
ring | +0.449 |
enough | +0.447 |
atively | +0.428 |
Neg logit contributions | |
Mehran | -0.719 |
lapt | -0.707 |
etsk | -0.686 |
caut | -0.674 |
unta | -0.669 |
Token | System |
Token ID | 11964 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Mehran | +3.224 |
lapt | +3.186 |
etsk | +3.034 |
unta | +2.965 |
caut | +2.930 |
Neg logit contributions | |
toe | -3.583 |
acted | -3.399 |
enough | -3.244 |
atively | -3.211 |
ring | -3.207 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
Mehran | +3.145 |
lapt | +3.045 |
etsk | +2.996 |
unta | +2.946 |
ebin | +2.919 |
Neg logit contributions | |
toe | -1.690 |
acted | -1.520 |
enough | -1.458 |
ring | -1.456 |
atively | -1.383 |
Token | Draw |
Token ID | 25302 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Mehran | +2.302 |
lapt | +2.219 |
etsk | +2.123 |
caut | +2.070 |
unta | +2.056 |
Neg logit contributions | |
toe | -3.309 |
acted | -3.118 |
enough | -3.033 |
ring | -3.012 |
atively | -2.954 |
Token | ing |
Token ID | 278 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
Mehran | +2.738 |
lapt | +2.684 |
etsk | +2.643 |
unta | +2.587 |
caut | +2.583 |
Neg logit contributions | |
toe | -1.089 |
acted | -0.960 |
enough | -0.906 |
ring | -0.897 |
atively | -0.850 |
Token | a |
Token ID | 257 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
toe | +2.519 |
acted | +2.338 |
ring | +2.287 |
enough | +2.258 |
atively | +2.190 |
Neg logit contributions | |
Mehran | -2.950 |
lapt | -2.892 |
etsk | -2.814 |
caut | -2.773 |
unta | -2.736 |
Token | big |
Token ID | 1263 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
Mehran | +0.298 |
lapt | +0.292 |
etsk | +0.282 |
caut | +0.275 |
unta | +0.272 |
Neg logit contributions | |
toe | -0.332 |
acted | -0.310 |
ring | -0.303 |
enough | -0.302 |
atively | -0.292 |
Token | room |
Token ID | 2119 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
lapt | +7.101 |
Mehran | +7.029 |
etsk | +6.589 |
unta | +6.412 |
ebin | +6.401 |
Neg logit contributions | |
toe | -7.121 |
acted | -6.521 |
atively | -6.201 |
ring | -6.169 |
uther | -6.064 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
toe | +0.575 |
acted | +0.529 |
ring | +0.514 |
enough | +0.511 |
atively | +0.491 |
Neg logit contributions | |
Mehran | -0.772 |
lapt | -0.757 |
etsk | -0.736 |
caut | -0.723 |
unta | -0.716 |
Token | a |
Token ID | 257 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Mehran | +1.592 |
lapt | +1.567 |
etsk | +1.507 |
caut | +1.477 |
unta | +1.461 |
Neg logit contributions | |
toe | -1.531 |
acted | -1.424 |
ring | -1.381 |
enough | -1.375 |
atively | -1.327 |
Token | pair |
Token ID | 5166 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Mehran | +0.560 |
lapt | +0.547 |
etsk | +0.529 |
caut | +0.517 |
unta | +0.512 |
Neg logit contributions | |
toe | -0.635 |
acted | -0.594 |
ring | -0.580 |
enough | -0.577 |
atively | -0.558 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
toe | +3.662 |
acted | +3.402 |
ring | +3.352 |
enough | +3.265 |
atively | +3.200 |
Neg logit contributions | |
Mehran | -4.169 |
lapt | -4.084 |
etsk | -3.953 |
caut | -3.895 |
unta | -3.884 |
Token | Silver |
Token ID | 7698 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
toe | +1.365 |
acted | +1.273 |
ring | +1.243 |
enough | +1.233 |
atively | +1.194 |
Neg logit contributions | |
Mehran | -1.391 |
lapt | -1.361 |
etsk | -1.322 |
caut | -1.294 |
unta | -1.287 |
Token | Phant |
Token ID | 38699 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
Mehran | +1.983 |
lapt | +1.952 |
etsk | +1.876 |
caut | +1.846 |
unta | +1.809 |
Neg logit contributions | |
toe | -1.538 |
acted | -1.422 |
enough | -1.391 |
ring | -1.357 |
atively | -1.318 |
Token | oms |
Token ID | 3150 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Mehran | +4.297 |
etsk | +3.957 |
lapt | +3.925 |
unta | +3.716 |
ebin | +3.698 |
Neg logit contributions | |
toe | -7.063 |
acted | -6.693 |
enough | -6.563 |
ring | -6.539 |
shire | -6.294 |
Token | should |
Token ID | 815 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Mehran | +2.872 |
lapt | +2.839 |
etsk | +2.694 |
caut | +2.644 |
unta | +2.587 |
Neg logit contributions | |
toe | -3.284 |
acted | -3.063 |
enough | -2.980 |
ring | -2.962 |
atively | -2.880 |
Token | in |
Token ID | 287 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
toe | +3.924 |
acted | +3.708 |
ring | +3.679 |
enough | +3.578 |
atively | +3.531 |
Neg logit contributions | |
lapt | -3.780 |
Mehran | -3.779 |
caut | -3.575 |
etsk | -3.549 |
unta | -3.509 |
Token | the |
Token ID | 262 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
toe | +2.918 |
acted | +2.713 |
ring | +2.671 |
enough | +2.627 |
atively | +2.539 |
Neg logit contributions | |
Mehran | -3.087 |
lapt | -3.073 |
etsk | -2.975 |
caut | -2.921 |
unta | -2.873 |
Token | Elven |
Token ID | 40748 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
toe | +2.179 |
acted | +2.020 |
ring | +1.994 |
enough | +1.946 |
atively | +1.888 |
Neg logit contributions | |
Mehran | -2.199 |
lapt | -2.166 |
etsk | -2.105 |
caut | -2.055 |
unta | -2.023 |
Token | forest |
Token ID | 8222 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
toe | +5.731 |
ring | +5.324 |
acted | +5.210 |
works | +5.068 |
enough | +5.024 |
Neg logit contributions | |
Mehran | -5.609 |
lapt | -5.600 |
etsk | -5.412 |
caut | -5.296 |
unta | -5.187 |
Token | of |
Token ID | 286 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
toe | +4.308 |
acted | +3.938 |
ring | +3.921 |
enough | +3.740 |
atively | +3.673 |
Neg logit contributions | |
Mehran | -6.428 |
lapt | -6.357 |
etsk | -6.131 |
caut | -6.067 |
unta | -5.967 |
Token | L |
Token ID | 406 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
toe | +0.081 |
acted | +0.076 |
ring | +0.074 |
enough | +0.073 |
atively | +0.071 |
Neg logit contributions | |
Mehran | -0.081 |
lapt | -0.080 |
etsk | -0.077 |
caut | -0.075 |
unta | -0.074 |
Token | oth |
Token ID | 849 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
toe | +3.442 |
acted | +3.224 |
ring | +3.194 |
enough | +3.154 |
atively | +3.091 |
Neg logit contributions | |
Mehran | -2.621 |
lapt | -2.619 |
caut | -2.479 |
etsk | -2.415 |
ccording | -2.401 |
Token | l |
Token ID | 75 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
toe | +2.852 |
acted | +2.603 |
ring | +2.599 |
enough | +2.516 |
atively | +2.423 |
Neg logit contributions | |
Mehran | -3.725 |
lapt | -3.677 |
etsk | -3.528 |
caut | -3.509 |
unta | -3.405 |
Token | ó |
Token ID | 10205 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
toe | +2.849 |
acted | +2.550 |
enough | +2.518 |
ring | +2.516 |
atively | +2.439 |
Neg logit contributions | |
lapt | -3.922 |
Mehran | -3.906 |
caut | -3.731 |
etsk | -3.687 |
ccording | -3.682 |
Token | rien |
Token ID | 15355 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
Mehran | +1.699 |
lapt | +1.627 |
etsk | +1.582 |
unta | +1.552 |
caut | +1.539 |
Neg logit contributions | |
toe | -3.969 |
acted | -3.751 |
enough | -3.680 |
ring | -3.595 |
hole | -3.576 |
Token | , |
Token ID | 11 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
toe | +2.968 |
acted | +2.669 |
ring | +2.632 |
enough | +2.550 |
shire | +2.427 |
Neg logit contributions | |
Mehran | -5.647 |
lapt | -5.558 |
etsk | -5.334 |
caut | -5.331 |
unta | -5.243 |
Token | queue |
Token ID | 16834 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Mehran | +2.777 |
lapt | +2.740 |
caut | +2.536 |
etsk | +2.536 |
unta | +2.529 |
Neg logit contributions | |
toe | -4.225 |
acted | -3.928 |
enough | -3.845 |
ring | -3.810 |
atively | -3.724 |
Token | but |
Token ID | 475 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
toe | +1.616 |
acted | +1.497 |
ring | +1.470 |
enough | +1.450 |
atively | +1.405 |
Neg logit contributions | |
Mehran | -2.025 |
lapt | -1.981 |
etsk | -1.934 |
caut | -1.884 |
unta | -1.865 |
Token | I |
Token ID | 314 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
toe | +0.789 |
acted | +0.735 |
ring | +0.719 |
enough | +0.714 |
atively | +0.689 |
Neg logit contributions | |
Mehran | -0.914 |
lapt | -0.896 |
etsk | -0.874 |
caut | -0.852 |
unta | -0.845 |
Token | did |
Token ID | 750 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
toe | +2.429 |
acted | +2.293 |
ring | +2.252 |
enough | +2.221 |
atively | +2.138 |
Neg logit contributions | |
Mehran | -2.465 |
lapt | -2.413 |
etsk | -2.371 |
unta | -2.263 |
caut | -2.251 |
Token | not |
Token ID | 407 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
toe | +1.704 |
acted | +1.577 |
ring | +1.540 |
enough | +1.527 |
atively | +1.467 |
Neg logit contributions | |
Mehran | -2.264 |
lapt | -2.221 |
etsk | -2.161 |
caut | -2.110 |
unta | -2.102 |
Token | have |
Token ID | 423 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
toe | +5.031 |
ring | +4.792 |
acted | +4.713 |
enough | +4.705 |
atively | +4.475 |
Neg logit contributions | |
Mehran | -5.244 |
lapt | -5.064 |
aeper | -4.933 |
etsk | -4.914 |
ccording | -4.893 |
Token | to |
Token ID | 284 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
toe | +6.170 |
acted | +5.921 |
enough | +5.901 |
ring | +5.768 |
atively | +5.489 |
Neg logit contributions | |
Mehran | -7.482 |
lapt | -7.275 |
etsk | -7.267 |
unta | -7.037 |
ccording | -6.926 |
Token | go |
Token ID | 467 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
toe | +2.597 |
ring | +2.403 |
acted | +2.399 |
enough | +2.355 |
atively | +2.283 |
Neg logit contributions | |
Mehran | -2.474 |
lapt | -2.414 |
etsk | -2.347 |
ccording | -2.265 |
caut | -2.259 |
Token | through |
Token ID | 832 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Mehran | +0.805 |
lapt | +0.789 |
etsk | +0.762 |
caut | +0.750 |
unta | +0.741 |
Neg logit contributions | |
toe | -0.725 |
acted | -0.675 |
ring | -0.653 |
enough | -0.651 |
atively | -0.628 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
toe | +1.706 |
acted | +1.584 |
ring | +1.546 |
enough | +1.534 |
atively | +1.480 |
Neg logit contributions | |
Mehran | -1.955 |
lapt | -1.924 |
etsk | -1.869 |
caut | -1.822 |
unta | -1.807 |
Token | queue |
Token ID | 16834 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
toe | +1.618 |
acted | +1.519 |
ring | +1.495 |
enough | +1.478 |
atively | +1.434 |
Neg logit contributions | |
Mehran | -1.507 |
lapt | -1.472 |
etsk | -1.440 |
caut | -1.386 |
unta | -1.385 |
Token | Mary |
Token ID | 5335 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
toe | +1.285 |
acted | +1.187 |
ring | +1.156 |
enough | +1.149 |
atively | +1.107 |
Neg logit contributions | |
Mehran | -1.528 |
lapt | -1.501 |
etsk | -1.454 |
caut | -1.424 |
unta | -1.412 |
Token | is |
Token ID | 318 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Mehran | +0.890 |
lapt | +0.875 |
etsk | +0.841 |
caut | +0.828 |
unta | +0.818 |
Neg logit contributions | |
toe | -0.886 |
acted | -0.822 |
enough | -0.798 |
ring | -0.796 |
atively | -0.772 |
Token | well |
Token ID | 880 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
toe | +0.906 |
acted | +0.846 |
ring | +0.829 |
enough | +0.821 |
atively | +0.794 |
Neg logit contributions | |
Mehran | -0.963 |
lapt | -0.942 |
etsk | -0.917 |
caut | -0.891 |
unta | -0.884 |
Token | known |
Token ID | 1900 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
toe | +4.199 |
acted | +3.955 |
ring | +3.823 |
enough | +3.816 |
works | +3.629 |
Neg logit contributions | |
Mehran | -5.754 |
lapt | -5.593 |
etsk | -5.560 |
unta | -5.338 |
caut | -5.323 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
toe | +1.683 |
acted | +1.534 |
ring | +1.484 |
enough | +1.474 |
atively | +1.405 |
Neg logit contributions | |
Mehran | -2.719 |
lapt | -2.674 |
etsk | -2.602 |
caut | -2.557 |
unta | -2.536 |
Token | Certainly |
Token ID | 23631 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
toe | +1.985 |
acted | +1.811 |
ring | +1.771 |
enough | +1.757 |
works | +1.690 |
Neg logit contributions | |
lapt | -2.595 |
Mehran | -2.548 |
etsk | -2.508 |
caut | -2.435 |
unta | -2.399 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
toe | +4.683 |
acted | +4.343 |
ring | +4.316 |
enough | +4.274 |
works | +4.070 |
Neg logit contributions | |
Mehran | -6.970 |
lapt | -6.793 |
etsk | -6.704 |
unta | -6.495 |
ebin | -6.447 |
Token | there |
Token ID | 612 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
toe | +1.226 |
acted | +1.137 |
ring | +1.110 |
enough | +1.104 |
atively | +1.063 |
Neg logit contributions | |
Mehran | -1.397 |
lapt | -1.370 |
etsk | -1.333 |
caut | -1.299 |
unta | -1.291 |
Token | are |
Token ID | 389 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
toe | +4.015 |
acted | +3.793 |
ring | +3.731 |
enough | +3.705 |
works | +3.599 |
Neg logit contributions | |
Mehran | -2.941 |
lapt | -2.912 |
etsk | -2.797 |
caut | -2.699 |
unta | -2.651 |
Token | Marian |
Token ID | 37919 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
toe | +2.882 |
acted | +2.659 |
ring | +2.620 |
enough | +2.603 |
atively | +2.504 |
Neg logit contributions | |
Mehran | -3.624 |
lapt | -3.537 |
etsk | -3.459 |
unta | -3.377 |
caut | -3.369 |
Token | abuses |
Token ID | 19544 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
toe | +0.625 |
acted | +0.576 |
ring | +0.558 |
enough | +0.555 |
atively | +0.534 |
Neg logit contributions | |
Mehran | -0.798 |
lapt | -0.784 |
etsk | -0.760 |
caut | -0.747 |
unta | -0.739 |
Token | which |
Token ID | 543 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Mehran | +0.672 |
lapt | +0.659 |
etsk | +0.638 |
caut | +0.625 |
unta | +0.620 |
Neg logit contributions | |
toe | -0.653 |
acted | -0.607 |
ring | -0.592 |
enough | -0.590 |
atively | -0.569 |
Token | is |
Token ID | 318 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Mehran | +0.972 |
lapt | +0.953 |
etsk | +0.919 |
caut | +0.899 |
unta | +0.889 |
Neg logit contributions | |
toe | -1.040 |
acted | -0.971 |
ring | -0.945 |
enough | -0.941 |
atively | -0.910 |
Token | just |
Token ID | 655 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Mehran | +0.406 |
lapt | +0.397 |
etsk | +0.387 |
caut | +0.378 |
unta | +0.375 |
Neg logit contributions | |
toe | -0.352 |
acted | -0.327 |
enough | -0.318 |
ring | -0.318 |
atively | -0.305 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
Mehran | +0.580 |
lapt | +0.568 |
etsk | +0.553 |
caut | +0.541 |
unta | +0.537 |
Neg logit contributions | |
toe | -0.485 |
acted | -0.449 |
ring | -0.437 |
enough | -0.437 |
atively | -0.419 |
Token | w |
Token ID | 266 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Mehran | +0.710 |
lapt | +0.705 |
etsk | +0.674 |
caut | +0.670 |
unta | +0.660 |
Neg logit contributions | |
toe | -0.541 |
acted | -0.497 |
ring | -0.481 |
enough | -0.476 |
atively | -0.458 |
Token | ort |
Token ID | 419 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
toe | +2.811 |
acted | +2.674 |
ring | +2.619 |
enough | +2.607 |
atively | +2.543 |
Neg logit contributions | |
Mehran | -1.541 |
lapt | -1.495 |
etsk | -1.415 |
caut | -1.378 |
unta | -1.336 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
toe | +4.862 |
acted | +4.495 |
ring | +4.408 |
enough | +4.360 |
atively | +4.192 |
Neg logit contributions | |
Mehran | -7.286 |
lapt | -7.092 |
etsk | -6.930 |
caut | -6.800 |
unta | -6.710 |
Token | cover |
Token ID | 3002 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Mehran | +1.354 |
lapt | +1.325 |
etsk | +1.270 |
caut | +1.239 |
unta | +1.224 |
Neg logit contributions | |
toe | -1.839 |
acted | -1.731 |
ring | -1.689 |
enough | -1.682 |
atively | -1.634 |
Token | the |
Token ID | 262 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Mehran | +2.523 |
lapt | +2.489 |
etsk | +2.373 |
caut | +2.331 |
unta | +2.310 |
Neg logit contributions | |
toe | -2.567 |
acted | -2.396 |
ring | -2.315 |
enough | -2.289 |
atively | -2.200 |
Token | hops |
Token ID | 29438 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
toe | +0.235 |
acted | +0.219 |
ring | +0.213 |
enough | +0.212 |
atively | +0.206 |
Neg logit contributions | |
Mehran | -0.234 |
lapt | -0.227 |
etsk | -0.222 |
caut | -0.216 |
unta | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Mehran | +1.394 |
lapt | +1.373 |
etsk | +1.330 |
caut | +1.306 |
unta | +1.295 |
Neg logit contributions | |
toe | -1.130 |
acted | -1.043 |
ring | -1.012 |
enough | -1.004 |
atively | -0.967 |
Token | Mc |
Token ID | 1982 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
toe | +0.429 |
acted | +0.394 |
ring | +0.382 |
enough | +0.380 |
atively | +0.364 |
Neg logit contributions | |
Mehran | -0.588 |
lapt | -0.579 |
etsk | -0.561 |
caut | -0.551 |
unta | -0.547 |
Token | All |
Token ID | 3237 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
Mehran | +3.933 |
lapt | +3.923 |
etsk | +3.768 |
caut | +3.678 |
unta | +3.657 |
Neg logit contributions | |
toe | -4.090 |
acted | -3.859 |
enough | -3.737 |
ring | -3.713 |
atively | -3.631 |
Token | ister |
Token ID | 1694 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
Mehran | +3.624 |
lapt | +3.583 |
etsk | +3.474 |
unta | +3.389 |
caut | +3.377 |
Neg logit contributions | |
toe | -3.463 |
acted | -3.204 |
enough | -3.106 |
ring | -3.079 |
atively | -3.003 |
Token | said |
Token ID | 531 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
toe | +4.559 |
acted | +4.255 |
ring | +4.155 |
enough | +4.107 |
atively | +3.961 |
Neg logit contributions | |
Mehran | -5.067 |
lapt | -4.903 |
etsk | -4.753 |
caut | -4.637 |
unta | -4.626 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
toe | +0.933 |
acted | +0.858 |
ring | +0.835 |
enough | +0.828 |
atively | +0.797 |
Neg logit contributions | |
Mehran | -1.242 |
lapt | -1.220 |
etsk | -1.184 |
caut | -1.161 |
unta | -1.153 |
Token | � |
Token ID | 564 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
toe | +2.349 |
acted | +2.158 |
ring | +2.109 |
enough | +2.078 |
atively | +1.998 |
Neg logit contributions | |
Mehran | -3.054 |
lapt | -3.047 |
etsk | -2.929 |
caut | -2.884 |
unta | -2.853 |
Token | � |
Token ID | 250 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
toe | +10.184 |
acted | +9.820 |
ring | +9.787 |
atively | +9.363 |
enough | +9.360 |
Neg logit contributions | |
Mehran | -6.565 |
lapt | -6.252 |
etsk | -5.876 |
unta | -5.746 |
caut | -5.621 |
Token | He |
Token ID | 1544 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
toe | +0.864 |
acted | +0.806 |
ring | +0.786 |
enough | +0.783 |
atively | +0.752 |
Neg logit contributions | |
Mehran | -0.860 |
lapt | -0.845 |
etsk | -0.812 |
caut | -0.798 |
unta | -0.788 |
Token | told |
Token ID | 1297 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
toe | +1.639 |
acted | +1.541 |
ring | +1.493 |
enough | +1.480 |
atively | +1.436 |
Neg logit contributions | |
Mehran | -1.620 |
lapt | -1.591 |
etsk | -1.515 |
caut | -1.485 |
unta | -1.471 |
Token | me |
Token ID | 502 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
Mehran | +0.587 |
lapt | +0.574 |
etsk | +0.555 |
caut | +0.543 |
unta | +0.536 |
Neg logit contributions | |
toe | -0.636 |
acted | -0.593 |
ring | -0.579 |
enough | -0.578 |
atively | -0.556 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
toe | +4.924 |
ring | +4.540 |
acted | +4.497 |
enough | +4.437 |
atively | +4.321 |
Neg logit contributions | |
Mehran | -6.288 |
lapt | -6.153 |
etsk | -5.998 |
unta | -5.838 |
ebin | -5.813 |
Token | - |
Token ID | 12 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Mehran | +1.621 |
lapt | +1.588 |
etsk | +1.545 |
caut | +1.514 |
unta | +1.512 |
Neg logit contributions | |
toe | -1.125 |
acted | -1.029 |
enough | -1.001 |
ring | -0.982 |
atively | -0.955 |
Token | Ang |
Token ID | 13450 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
toe | +1.823 |
acted | +1.695 |
ring | +1.659 |
enough | +1.639 |
works | +1.572 |
Neg logit contributions | |
Mehran | -1.880 |
lapt | -1.860 |
etsk | -1.791 |
caut | -1.761 |
unta | -1.724 |
Token | ry |
Token ID | 563 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Mehran | +4.307 |
lapt | +4.236 |
etsk | +4.113 |
unta | +4.063 |
caut | +4.056 |
Neg logit contributions | |
toe | -3.795 |
acted | -3.485 |
enough | -3.346 |
ring | -3.304 |
atively | -3.268 |
Token | Video |
Token ID | 7623 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Mehran | +2.304 |
lapt | +2.244 |
etsk | +2.175 |
caut | +2.125 |
unta | +2.119 |
Neg logit contributions | |
toe | -2.214 |
acted | -2.054 |
ring | -1.995 |
enough | -1.994 |
atively | -1.934 |
Token | Game |
Token ID | 3776 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
toe | +0.592 |
acted | +0.547 |
ring | +0.533 |
enough | +0.527 |
atively | +0.506 |
Neg logit contributions | |
Mehran | -0.729 |
lapt | -0.719 |
etsk | -0.697 |
caut | -0.683 |
unta | -0.675 |
Token | Nerd |
Token ID | 44031 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
toe | +1.165 |
acted | +1.081 |
ring | +1.051 |
enough | +1.040 |
atively | +1.001 |
Neg logit contributions | |
Mehran | -1.399 |
lapt | -1.379 |
etsk | -1.336 |
caut | -1.311 |
unta | -1.293 |
Token | Guy |
Token ID | 13145 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
toe | +6.562 |
acted | +6.221 |
ring | +6.113 |
works | +5.803 |
enough | +5.777 |
Neg logit contributions | |
Mehran | -7.453 |
lapt | -7.423 |
etsk | -7.194 |
caut | -7.040 |
ebin | -6.827 |
Token | - |
Token ID | 12 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
toe | +2.101 |
acted | +1.934 |
ring | +1.880 |
enough | +1.850 |
atively | +1.778 |
Neg logit contributions | |
Mehran | -2.869 |
lapt | -2.829 |
etsk | -2.744 |
caut | -2.694 |
unta | -2.659 |
Token | E |
Token ID | 36 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
toe | +3.224 |
acted | +2.998 |
ring | +2.942 |
enough | +2.890 |
works | +2.784 |
Neg logit contributions | |
Mehran | -3.352 |
lapt | -3.341 |
etsk | -3.214 |
caut | -3.159 |
unta | -3.073 |
Token | ps |
Token ID | 862 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
toe | +2.353 |
acted | +2.208 |
ring | +2.165 |
enough | +2.143 |
atively | +2.081 |
Neg logit contributions | |
Mehran | -1.942 |
lapt | -1.899 |
etsk | -1.821 |
caut | -1.781 |
unta | -1.751 |
Token | ch |
Token ID | 354 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Mehran | +1.528 |
lapt | +1.499 |
etsk | +1.460 |
caut | +1.425 |
unta | +1.419 |
Neg logit contributions | |
toe | -1.189 |
acted | -1.095 |
enough | -1.058 |
ring | -1.055 |
atively | -1.018 |