Token | 't |
Token ID | 470 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
IA | +0.219 |
Ashes | +0.217 |
Rosenberg | +0.212 |
cca | +0.196 |
cko | +0.194 |
Neg logit contributions | |
phalt | -0.371 |
BELOW | -0.361 |
orrect | -0.351 |
conduc | -0.340 |
trial | -0.338 |
Token | contain |
Token ID | 3994 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
phalt | +0.179 |
BELOW | +0.174 |
orrect | +0.167 |
trial | +0.160 |
JUST | +0.158 |
Neg logit contributions | |
Ashes | -0.193 |
IA | -0.192 |
Rosenberg | -0.188 |
cca | -0.178 |
cko | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
Ashes | +1.400 |
IA | +1.399 |
Rosenberg | +1.377 |
cca | +1.294 |
cko | +1.287 |
Neg logit contributions | |
phalt | -1.204 |
BELOW | -1.158 |
orrect | -1.105 |
trial | -1.068 |
JUST | -1.055 |
Token | needed |
Token ID | 2622 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Ashes | +0.824 |
IA | +0.823 |
Rosenberg | +0.813 |
cca | +0.773 |
cko | +0.770 |
Neg logit contributions | |
phalt | -0.401 |
BELOW | -0.379 |
orrect | -0.355 |
trial | -0.337 |
JUST | -0.329 |
Token | D |
Token ID | 360 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Ashes | +1.707 |
IA | +1.704 |
Rosenberg | +1.675 |
cca | +1.553 |
cko | +1.549 |
Neg logit contributions | |
phalt | -1.811 |
BELOW | -1.744 |
orrect | -1.675 |
trial | -1.628 |
JUST | -1.601 |
Token | TB |
Token ID | 22737 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
IA | +1.261 |
Ashes | +1.234 |
Rosenberg | +1.208 |
cca | +1.128 |
cko | +1.124 |
Neg logit contributions | |
phalt | -1.495 |
BELOW | -1.456 |
orrect | -1.404 |
trial | -1.353 |
orem | -1.332 |
Token | board |
Token ID | 3096 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
IA | +4.117 |
Ashes | +4.004 |
Rosenberg | +3.925 |
Unicorn | +3.702 |
cca | +3.669 |
Neg logit contributions | |
phalt | -4.076 |
BELOW | -3.879 |
orrect | -3.716 |
trial | -3.655 |
orem | -3.601 |
Token | definition |
Token ID | 6770 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
IA | +1.437 |
Ashes | +1.428 |
Rosenberg | +1.407 |
cko | +1.320 |
cca | +1.320 |
Neg logit contributions | |
phalt | -1.402 |
BELOW | -1.348 |
orrect | -1.299 |
trial | -1.251 |
JUST | -1.230 |
Token | for |
Token ID | 329 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
IA | +0.804 |
Ashes | +0.802 |
Rosenberg | +0.788 |
cca | +0.738 |
cko | +0.737 |
Neg logit contributions | |
phalt | -0.779 |
BELOW | -0.747 |
orrect | -0.721 |
trial | -0.696 |
JUST | -0.684 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Ashes | +0.428 |
IA | +0.427 |
Rosenberg | +0.420 |
cca | +0.395 |
cko | +0.393 |
Neg logit contributions | |
phalt | -0.397 |
BELOW | -0.385 |
orrect | -0.371 |
trial | -0.354 |
JUST | -0.351 |
Token | revision |
Token ID | 18440 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Ashes | +0.259 |
IA | +0.259 |
Rosenberg | +0.254 |
cca | +0.237 |
cko | +0.236 |
Neg logit contributions | |
phalt | -0.298 |
BELOW | -0.290 |
orrect | -0.279 |
trial | -0.269 |
JUST | -0.266 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
Ashes | +0.833 |
IA | +0.828 |
Rosenberg | +0.816 |
cca | +0.766 |
cko | +0.761 |
Neg logit contributions | |
phalt | -0.776 |
BELOW | -0.749 |
orrect | -0.723 |
trial | -0.691 |
JUST | -0.686 |
Token | stating |
Token ID | 12316 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
Ashes | +0.550 |
IA | +0.547 |
Rosenberg | +0.539 |
cca | +0.507 |
cko | +0.503 |
Neg logit contributions | |
phalt | -0.502 |
BELOW | -0.486 |
orrect | -0.468 |
trial | -0.447 |
JUST | -0.443 |
Token | : |
Token ID | 25 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
Ashes | +0.469 |
IA | +0.468 |
Rosenberg | +0.460 |
cca | +0.431 |
cko | +0.429 |
Neg logit contributions | |
phalt | -0.462 |
BELOW | -0.448 |
orrect | -0.432 |
trial | -0.412 |
JUST | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
IA | +0.427 |
Ashes | +0.427 |
Rosenberg | +0.420 |
cca | +0.397 |
cko | +0.397 |
Neg logit contributions | |
phalt | -0.346 |
BELOW | -0.337 |
orrect | -0.323 |
trial | -0.307 |
JUST | -0.304 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
IA | +0.311 |
Ashes | +0.310 |
Rosenberg | +0.304 |
cca | +0.288 |
cko | +0.286 |
Neg logit contributions | |
phalt | -0.267 |
BELOW | -0.257 |
orrect | -0.248 |
conduc | -0.235 |
trial | -0.235 |
Token | Then |
Token ID | 6423 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
IA | +0.233 |
Ashes | +0.233 |
Rosenberg | +0.228 |
cca | +0.214 |
cko | +0.213 |
Neg logit contributions | |
phalt | -0.252 |
BELOW | -0.245 |
orrect | -0.236 |
trial | -0.226 |
JUST | -0.224 |
Token | the |
Token ID | 262 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Ashes | +4.018 |
Rosenberg | +3.937 |
IA | +3.902 |
cca | +3.655 |
Harold | +3.653 |
Neg logit contributions | |
phalt | -4.067 |
BELOW | -3.865 |
orrect | -3.750 |
trial | -3.598 |
JUST | -3.578 |
Token | Prophet |
Token ID | 13583 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Ashes | +0.455 |
IA | +0.453 |
Rosenberg | +0.443 |
cca | +0.412 |
cko | +0.410 |
Neg logit contributions | |
phalt | -0.592 |
BELOW | -0.577 |
orrect | -0.558 |
trial | -0.536 |
JUST | -0.533 |
Token | said |
Token ID | 531 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Ashes | +0.441 |
IA | +0.440 |
Rosenberg | +0.433 |
cca | +0.408 |
cko | +0.405 |
Neg logit contributions | |
phalt | -0.392 |
BELOW | -0.380 |
orrect | -0.364 |
trial | -0.348 |
JUST | -0.345 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Ashes | +2.274 |
IA | +2.260 |
Rosenberg | +2.227 |
cca | +2.094 |
cko | +2.067 |
Neg logit contributions | |
phalt | -2.007 |
BELOW | -1.926 |
orrect | -1.855 |
trial | -1.757 |
JUST | -1.746 |
Token | " |
Token ID | 366 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Ashes | +0.428 |
IA | +0.427 |
Rosenberg | +0.419 |
cca | +0.395 |
cko | +0.394 |
Neg logit contributions | |
phalt | -0.398 |
BELOW | -0.387 |
orrect | -0.372 |
trial | -0.355 |
JUST | -0.352 |
Token | here |
Token ID | 994 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Ashes | +1.973 |
IA | +1.957 |
Rosenberg | +1.929 |
cca | +1.804 |
cko | +1.802 |
Neg logit contributions | |
phalt | -1.709 |
BELOW | -1.626 |
orrect | -1.593 |
trial | -1.519 |
JUST | -1.511 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Ashes | +1.861 |
IA | +1.857 |
Rosenberg | +1.823 |
cca | +1.718 |
cko | +1.713 |
Neg logit contributions | |
phalt | -1.646 |
BELOW | -1.573 |
orrect | -1.536 |
trial | -1.464 |
JUST | -1.454 |
Token | Launch |
Token ID | 21225 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Ashes | +0.971 |
IA | +0.964 |
Rosenberg | +0.950 |
cca | +0.897 |
cko | +0.891 |
Neg logit contributions | |
phalt | -0.849 |
BELOW | -0.815 |
orrect | -0.792 |
trial | -0.756 |
JUST | -0.746 |
Token | Kodi |
Token ID | 44129 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Ashes | +0.657 |
IA | +0.653 |
Rosenberg | +0.642 |
cca | +0.597 |
cko | +0.594 |
Neg logit contributions | |
phalt | -0.786 |
BELOW | -0.764 |
orrect | -0.741 |
trial | -0.710 |
JUST | -0.708 |
Token | and |
Token ID | 290 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
phalt | +0.146 |
BELOW | +0.142 |
orrect | +0.137 |
trial | +0.130 |
JUST | +0.129 |
Neg logit contributions | |
Ashes | -0.155 |
IA | -0.155 |
Rosenberg | -0.152 |
cca | -0.143 |
cko | -0.142 |
Token | click |
Token ID | 3904 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Ashes | +0.759 |
IA | +0.753 |
Rosenberg | +0.740 |
cca | +0.701 |
cko | +0.697 |
Neg logit contributions | |
phalt | -0.630 |
BELOW | -0.604 |
orrect | -0.585 |
trial | -0.559 |
JUST | -0.553 |
Token | on |
Token ID | 319 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Ashes | +4.011 |
IA | +3.966 |
Rosenberg | +3.895 |
cca | +3.690 |
cko | +3.641 |
Neg logit contributions | |
phalt | -3.818 |
BELOW | -3.556 |
orrect | -3.548 |
trial | -3.406 |
JUST | -3.390 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Ashes | +1.538 |
IA | +1.531 |
Rosenberg | +1.507 |
cca | +1.415 |
cko | +1.409 |
Neg logit contributions | |
phalt | -1.405 |
BELOW | -1.348 |
orrect | -1.309 |
trial | -1.249 |
JUST | -1.244 |
Token | Settings |
Token ID | 16163 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Ashes | +1.331 |
IA | +1.326 |
Rosenberg | +1.305 |
cca | +1.225 |
cko | +1.222 |
Neg logit contributions | |
phalt | -1.212 |
BELOW | -1.158 |
orrect | -1.123 |
trial | -1.073 |
JUST | -1.068 |
Token | Icon |
Token ID | 26544 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
phalt | +0.603 |
BELOW | +0.582 |
orrect | +0.556 |
trial | +0.525 |
JUST | +0.519 |
Neg logit contributions | |
Ashes | -0.895 |
IA | -0.894 |
Rosenberg | -0.879 |
cca | -0.836 |
cko | -0.833 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Ashes | +0.224 |
IA | +0.224 |
Rosenberg | +0.219 |
cca | +0.206 |
cko | +0.206 |
Neg logit contributions | |
phalt | -0.209 |
BELOW | -0.202 |
orrect | -0.195 |
trial | -0.186 |
JUST | -0.185 |
Token | don |
Token ID | 836 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
IA | +0.548 |
Ashes | +0.547 |
Rosenberg | +0.535 |
cca | +0.507 |
cko | +0.504 |
Neg logit contributions | |
phalt | -0.496 |
BELOW | -0.482 |
orrect | -0.462 |
trial | -0.440 |
JUST | -0.436 |
Token | � |
Token ID | 447 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
phalt | +0.520 |
BELOW | +0.509 |
orrect | +0.489 |
trial | +0.469 |
JUST | +0.467 |
Neg logit contributions | |
Ashes | -0.469 |
IA | -0.466 |
Rosenberg | -0.458 |
cca | -0.428 |
cko | -0.427 |
Token | � |
Token ID | 247 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
phalt | +0.267 |
BELOW | +0.259 |
orrect | +0.248 |
trial | +0.236 |
JUST | +0.234 |
Neg logit contributions | |
Ashes | -0.352 |
IA | -0.350 |
Rosenberg | -0.345 |
cca | -0.326 |
cko | -0.326 |
Token | t |
Token ID | 83 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Ashes | +0.018 |
IA | +0.018 |
Rosenberg | +0.018 |
cca | +0.016 |
cko | +0.016 |
Neg logit contributions | |
phalt | -0.026 |
BELOW | -0.025 |
orrect | -0.024 |
trial | -0.023 |
JUST | -0.023 |
Token | know |
Token ID | 760 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
phalt | +0.315 |
BELOW | +0.306 |
orrect | +0.293 |
trial | +0.278 |
JUST | +0.276 |
Neg logit contributions | |
Ashes | -0.393 |
IA | -0.392 |
Rosenberg | -0.385 |
cca | -0.365 |
cko | -0.363 |
Token | exactly |
Token ID | 3446 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
phalt | +0.698 |
BELOW | +0.682 |
orrect | +0.652 |
trial | +0.621 |
JUST | +0.620 |
Neg logit contributions | |
Ashes | -0.740 |
IA | -0.738 |
Rosenberg | -0.722 |
cca | -0.683 |
cko | -0.681 |
Token | what |
Token ID | 644 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
IA | +3.583 |
Ashes | +3.557 |
Rosenberg | +3.495 |
cca | +3.257 |
Unicorn | +3.209 |
Neg logit contributions | |
phalt | -4.003 |
BELOW | -3.845 |
orrect | -3.795 |
trial | -3.599 |
conduc | -3.591 |
Token | I |
Token ID | 314 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Ashes | +0.741 |
IA | +0.741 |
Rosenberg | +0.727 |
cca | +0.684 |
cko | +0.680 |
Neg logit contributions | |
phalt | -0.695 |
BELOW | -0.675 |
orrect | -0.650 |
trial | -0.619 |
JUST | -0.613 |
Token | � |
Token ID | 447 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
IA | +0.739 |
Ashes | +0.737 |
Rosenberg | +0.721 |
cca | +0.682 |
cko | +0.679 |
Neg logit contributions | |
phalt | -0.659 |
BELOW | -0.640 |
orrect | -0.614 |
trial | -0.583 |
JUST | -0.578 |
Token | � |
Token ID | 247 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Ashes | +0.165 |
IA | +0.165 |
Rosenberg | +0.162 |
cca | +0.153 |
cko | +0.153 |
Neg logit contributions | |
phalt | -0.127 |
BELOW | -0.123 |
orrect | -0.118 |
trial | -0.111 |
JUST | -0.110 |
Token | m |
Token ID | 76 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
IA | +0.549 |
Ashes | +0.549 |
Rosenberg | +0.536 |
cca | +0.502 |
cko | +0.500 |
Neg logit contributions | |
phalt | -0.644 |
BELOW | -0.628 |
orrect | -0.606 |
trial | -0.580 |
JUST | -0.576 |
Token | an |
Token ID | 281 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Ashes | +0.802 |
IA | +0.800 |
Rosenberg | +0.783 |
cca | +0.739 |
cko | +0.732 |
Neg logit contributions | |
phalt | -0.783 |
BELOW | -0.758 |
orrect | -0.733 |
trial | -0.699 |
JUST | -0.695 |
Token | aer |
Token ID | 25534 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
IA | +0.983 |
Ashes | +0.980 |
Rosenberg | +0.957 |
cca | +0.910 |
cko | +0.906 |
Neg logit contributions | |
phalt | -0.828 |
BELOW | -0.801 |
orrect | -0.771 |
trial | -0.735 |
JUST | -0.729 |
Token | obic |
Token ID | 20803 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
IA | +1.973 |
Ashes | +1.967 |
Rosenberg | +1.925 |
cko | +1.837 |
cca | +1.834 |
Neg logit contributions | |
phalt | -1.583 |
BELOW | -1.557 |
orrect | -1.491 |
JUST | -1.414 |
conduc | -1.409 |
Token | pathogens |
Token ID | 38366 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
Ashes | +1.955 |
IA | +1.944 |
Rosenberg | +1.877 |
cca | +1.777 |
cko | +1.746 |
Neg logit contributions | |
phalt | -2.584 |
BELOW | -2.514 |
orrect | -2.447 |
trial | -2.354 |
JUST | -2.350 |
Token | ( |
Token ID | 357 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
phalt | +0.021 |
BELOW | +0.021 |
orrect | +0.020 |
trial | +0.019 |
JUST | +0.019 |
Neg logit contributions | |
Ashes | -0.023 |
IA | -0.023 |
Rosenberg | -0.022 |
cca | -0.021 |
cko | -0.021 |
Token | Prev |
Token ID | 36854 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
phalt | +0.290 |
BELOW | +0.283 |
orrect | +0.273 |
trial | +0.262 |
JUST | +0.260 |
Neg logit contributions | |
Ashes | -0.262 |
IA | -0.260 |
Rosenberg | -0.256 |
cca | -0.239 |
cko | -0.239 |
Token | ot |
Token ID | 313 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
IA | +3.610 |
Ashes | +3.461 |
Rosenberg | +3.435 |
cca | +3.336 |
cko | +3.206 |
Neg logit contributions | |
phalt | -4.013 |
BELOW | -3.959 |
orrect | -3.772 |
trial | -3.677 |
conduc | -3.640 |
Token | ella |
Token ID | 12627 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
phalt | +0.935 |
BELOW | +0.909 |
orrect | +0.898 |
trial | +0.847 |
� | +0.846 |
Neg logit contributions | |
Ashes | -0.692 |
IA | -0.673 |
Rosenberg | -0.666 |
ゼウス | -0.625 |
cca | -0.619 |
Token | , |
Token ID | 11 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Ashes | +0.299 |
IA | +0.298 |
Rosenberg | +0.293 |
cca | +0.277 |
cko | +0.277 |
Neg logit contributions | |
phalt | -0.246 |
BELOW | -0.239 |
orrect | -0.229 |
trial | -0.217 |
JUST | -0.215 |
Token | Pe |
Token ID | 2631 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Ashes | +0.258 |
IA | +0.258 |
Rosenberg | +0.252 |
cko | +0.237 |
cca | +0.237 |
Neg logit contributions | |
phalt | -0.274 |
BELOW | -0.267 |
orrect | -0.257 |
trial | -0.246 |
JUST | -0.244 |
Token | pt |
Token ID | 457 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
phalt | +0.080 |
BELOW | +0.078 |
orrect | +0.075 |
trial | +0.072 |
JUST | +0.071 |
Neg logit contributions | |
Ashes | -0.085 |
IA | -0.085 |
Rosenberg | -0.083 |
cca | -0.078 |
cko | -0.078 |
Token | Ryan |
Token ID | 6047 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
phalt | +0.617 |
BELOW | +0.601 |
orrect | +0.580 |
trial | +0.555 |
JUST | +0.551 |
Neg logit contributions | |
Ashes | -0.549 |
IA | -0.548 |
Rosenberg | -0.535 |
cca | -0.502 |
cko | -0.500 |
Token | , |
Token ID | 11 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
phalt | +0.875 |
BELOW | +0.850 |
orrect | +0.815 |
trial | +0.775 |
JUST | +0.768 |
Neg logit contributions | |
Ashes | -1.021 |
IA | -1.019 |
Rosenberg | -0.999 |
cca | -0.945 |
cko | -0.942 |
Token | who |
Token ID | 508 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
phalt | +0.044 |
BELOW | +0.043 |
orrect | +0.041 |
trial | +0.039 |
JUST | +0.039 |
Neg logit contributions | |
Ashes | -0.047 |
IA | -0.046 |
Rosenberg | -0.046 |
cca | -0.043 |
cko | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
IA | +0.289 |
Ashes | +0.289 |
Rosenberg | +0.285 |
cca | +0.267 |
cko | +0.265 |
Neg logit contributions | |
phalt | -0.268 |
BELOW | -0.262 |
orrect | -0.251 |
trial | -0.240 |
JUST | -0.239 |
Token | em |
Token ID | 795 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Ashes | +0.559 |
IA | +0.559 |
Rosenberg | +0.554 |
cca | +0.520 |
Unicorn | +0.512 |
Neg logit contributions | |
phalt | -0.468 |
BELOW | -0.454 |
orrect | -0.440 |
trial | -0.418 |
JUST | -0.412 |
Token | ce |
Token ID | 344 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
phalt | +0.190 |
BELOW | +0.185 |
orrect | +0.179 |
trial | +0.172 |
JUST | +0.169 |
Neg logit contributions | |
Ashes | -0.167 |
IA | -0.166 |
Rosenberg | -0.163 |
cko | -0.152 |
cca | -0.152 |
Token | e |
Token ID | 68 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
IA | +2.703 |
Rosenberg | +2.541 |
Ashes | +2.525 |
cca | +2.445 |
cko | +2.345 |
Neg logit contributions | |
phalt | -4.911 |
BELOW | -4.796 |
orrect | -4.595 |
JUST | -4.517 |
conduc | -4.473 |
Token | ing |
Token ID | 278 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
IA | +0.846 |
Ashes | +0.846 |
Rosenberg | +0.832 |
cca | +0.785 |
cko | +0.775 |
Neg logit contributions | |
phalt | -0.789 |
BELOW | -0.766 |
orrect | -0.739 |
trial | -0.704 |
JUST | -0.700 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Ashes | +0.203 |
IA | +0.203 |
Rosenberg | +0.200 |
cca | +0.188 |
cko | +0.187 |
Neg logit contributions | |
phalt | -0.177 |
BELOW | -0.172 |
orrect | -0.165 |
trial | -0.157 |
JUST | -0.156 |
Token | program |
Token ID | 1430 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
phalt | +0.782 |
BELOW | +0.767 |
orrect | +0.735 |
trial | +0.702 |
� | +0.697 |
Neg logit contributions | |
Ashes | -0.791 |
IA | -0.790 |
Rosenberg | -0.771 |
cca | -0.731 |
cko | -0.729 |
Token | , |
Token ID | 11 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
phalt | +0.551 |
BELOW | +0.535 |
orrect | +0.512 |
trial | +0.486 |
JUST | +0.481 |
Neg logit contributions | |
Ashes | -0.702 |
IA | -0.701 |
Rosenberg | -0.688 |
cca | -0.652 |
cko | -0.650 |
Token | into |
Token ID | 656 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
phalt | +0.004 |
BELOW | +0.004 |
orrect | +0.004 |
trial | +0.004 |
JUST | +0.004 |
Neg logit contributions | |
Ashes | -0.004 |
IA | -0.004 |
Rosenberg | -0.004 |
cca | -0.003 |
cko | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
phalt | +1.481 |
BELOW | +1.435 |
orrect | +1.369 |
trial | +1.305 |
JUST | +1.291 |
Neg logit contributions | |
IA | -1.668 |
Ashes | -1.660 |
Rosenberg | -1.635 |
cko | -1.550 |
cca | -1.542 |
Token | ". |
Token ID | 1911 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
phalt | +0.449 |
BELOW | +0.436 |
orrect | +0.419 |
trial | +0.399 |
JUST | +0.395 |
Neg logit contributions | |
Ashes | -0.496 |
IA | -0.495 |
Rosenberg | -0.486 |
cca | -0.458 |
cko | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
phalt | +0.434 |
BELOW | +0.422 |
orrect | +0.404 |
trial | +0.384 |
JUST | +0.381 |
Neg logit contributions | |
Ashes | -0.540 |
IA | -0.538 |
Rosenberg | -0.529 |
cca | -0.500 |
cko | -0.499 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
IA | +0.157 |
Ashes | +0.156 |
Rosenberg | +0.153 |
cca | +0.145 |
cko | +0.144 |
Neg logit contributions | |
phalt | -0.135 |
BELOW | -0.130 |
orrect | -0.125 |
conduc | -0.119 |
trial | -0.118 |
Token | Topics |
Token ID | 25902 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
phalt | +0.028 |
BELOW | +0.027 |
orrect | +0.026 |
trial | +0.025 |
JUST | +0.025 |
Neg logit contributions | |
IA | -0.026 |
Ashes | -0.026 |
Rosenberg | -0.026 |
cca | -0.024 |
cko | -0.024 |
Token | : |
Token ID | 25 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
IA | +3.971 |
Ashes | +3.959 |
Rosenberg | +3.888 |
cca | +3.717 |
cko | +3.628 |
Neg logit contributions | |
phalt | -3.562 |
conduc | -3.389 |
orrect | -3.317 |
BELOW | -3.282 |
emort | -3.163 |
Token | marine |
Token ID | 16050 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
IA | +0.738 |
Ashes | +0.738 |
Rosenberg | +0.715 |
cca | +0.672 |
cko | +0.670 |
Neg logit contributions | |
phalt | -0.711 |
BELOW | -0.694 |
orrect | -0.665 |
trial | -0.638 |
JUST | -0.632 |
Token | - |
Token ID | 12 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
IA | +1.238 |
Ashes | +1.237 |
Rosenberg | +1.192 |
cca | +1.141 |
vre | +1.138 |
Neg logit contributions | |
phalt | -1.190 |
BELOW | -1.159 |
orrect | -1.117 |
trial | -1.057 |
� | -1.055 |
Token | biology |
Token ID | 43592 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
phalt | +0.026 |
BELOW | +0.026 |
orrect | +0.025 |
conduc | +0.023 |
trial | +0.023 |
Neg logit contributions | |
IA | -0.027 |
Ashes | -0.027 |
Rosenberg | -0.026 |
cca | -0.025 |
cko | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
IA | +0.934 |
Ashes | +0.932 |
Rosenberg | +0.901 |
cca | +0.868 |
cko | +0.857 |
Neg logit contributions | |
phalt | -0.835 |
BELOW | -0.799 |
conduc | -0.785 |
orrect | -0.772 |
trial | -0.728 |
Token | , |
Token ID | 11 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
phalt | +1.199 |
BELOW | +1.175 |
orrect | +1.124 |
trial | +1.078 |
JUST | +1.066 |
Neg logit contributions | |
Ashes | -1.209 |
IA | -1.206 |
Rosenberg | -1.187 |
cca | -1.115 |
cko | -1.113 |
Token | Sidney |
Token ID | 35727 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
phalt | +0.357 |
BELOW | +0.350 |
orrect | +0.335 |
trial | +0.321 |
JUST | +0.317 |
Neg logit contributions | |
Ashes | -0.368 |
IA | -0.368 |
Rosenberg | -0.359 |
cca | -0.340 |
cko | -0.339 |
Token | Crosby |
Token ID | 33098 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
phalt | +1.219 |
BELOW | +1.206 |
orrect | +1.155 |
trial | +1.116 |
JUST | +1.105 |
Neg logit contributions | |
IA | -0.835 |
Ashes | -0.831 |
Rosenberg | -0.805 |
cca | -0.754 |
cko | -0.752 |
Token | , |
Token ID | 11 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
phalt | +0.964 |
BELOW | +0.940 |
orrect | +0.892 |
trial | +0.849 |
JUST | +0.839 |
Neg logit contributions | |
Ashes | -1.275 |
IA | -1.269 |
Rosenberg | -1.248 |
cca | -1.186 |
cko | -1.181 |
Token | Ev |
Token ID | 4319 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Ashes | +0.056 |
IA | +0.056 |
Rosenberg | +0.055 |
cca | +0.051 |
cko | +0.051 |
Neg logit contributions | |
phalt | -0.058 |
BELOW | -0.057 |
orrect | -0.055 |
trial | -0.052 |
JUST | -0.052 |
Token | gen |
Token ID | 5235 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
Ashes | +1.847 |
IA | +1.837 |
Rosenberg | +1.814 |
cca | +1.685 |
cko | +1.681 |
Neg logit contributions | |
phalt | -2.248 |
BELOW | -2.185 |
orrect | -2.118 |
JUST | -2.032 |
trial | -2.024 |
Token | i |
Token ID | 72 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
IA | +2.732 |
Ashes | +2.655 |
Rosenberg | +2.655 |
cko | +2.411 |
vre | +2.328 |
Neg logit contributions | |
phalt | -4.845 |
BELOW | -4.695 |
orrect | -4.606 |
conduc | -4.442 |
JUST | -4.426 |
Token | Malk |
Token ID | 41980 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
IA | +1.455 |
Ashes | +1.451 |
Rosenberg | +1.428 |
cko | +1.326 |
cca | +1.321 |
Neg logit contributions | |
phalt | -1.271 |
BELOW | -1.214 |
orrect | -1.168 |
JUST | -1.122 |
trial | -1.116 |
Token | in |
Token ID | 259 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
phalt | +0.773 |
BELOW | +0.757 |
orrect | +0.723 |
trial | +0.690 |
� | +0.674 |
Neg logit contributions | |
Ashes | -0.888 |
IA | -0.874 |
Rosenberg | -0.857 |
ゼウス | -0.811 |
cca | -0.809 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
IA | +0.440 |
Ashes | +0.439 |
Rosenberg | +0.431 |
cca | +0.408 |
cko | +0.407 |
Neg logit contributions | |
phalt | -0.342 |
BELOW | -0.330 |
orrect | -0.318 |
trial | -0.300 |
JUST | -0.298 |
Token | Phil |
Token ID | 4543 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
phalt | +0.150 |
BELOW | +0.146 |
orrect | +0.141 |
trial | +0.134 |
JUST | +0.133 |
Neg logit contributions | |
Ashes | -0.151 |
IA | -0.150 |
Rosenberg | -0.147 |
cca | -0.138 |
cko | -0.138 |
Token | [ |
Token ID | 685 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
phalt | +0.407 |
BELOW | +0.396 |
orrect | +0.381 |
trial | +0.365 |
JUST | +0.362 |
Neg logit contributions | |
Ashes | -0.402 |
IA | -0.401 |
Rosenberg | -0.394 |
cca | -0.371 |
cko | -0.368 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
IA | +0.649 |
Ashes | +0.647 |
Rosenberg | +0.631 |
cca | +0.594 |
cko | +0.590 |
Neg logit contributions | |
phalt | -0.722 |
BELOW | -0.702 |
orrect | -0.678 |
trial | -0.647 |
JUST | -0.641 |
Token | : |
Token ID | 25 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
IA | +2.135 |
Ashes | +2.114 |
Rosenberg | +2.078 |
cca | +1.993 |
cko | +1.961 |
Neg logit contributions | |
phalt | -1.601 |
BELOW | -1.537 |
orrect | -1.476 |
trial | -1.398 |
JUST | -1.383 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
IA | +1.323 |
Ashes | +1.291 |
Rosenberg | +1.266 |
cca | +1.204 |
cko | +1.176 |
Neg logit contributions | |
phalt | -1.665 |
BELOW | -1.582 |
orrect | -1.562 |
conduc | -1.549 |
emort | -1.468 |
Token | ] |
Token ID | 60 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
IA | +2.818 |
Ashes | +2.792 |
Rosenberg | +2.736 |
cca | +2.594 |
cko | +2.573 |
Neg logit contributions | |
phalt | -2.594 |
BELOW | -2.484 |
orrect | -2.427 |
trial | -2.307 |
JUST | -2.287 |
Token | < |
Token ID | 1279 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
IA | +2.383 |
Ashes | +2.381 |
Rosenberg | +2.349 |
cca | +2.251 |
cko | +2.247 |
Neg logit contributions | |
phalt | -0.854 |
BELOW | -0.796 |
orrect | -0.761 |
trial | -0.674 |
JUST | -0.651 |
Token | met |
Token ID | 4164 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
IA | +3.564 |
Ashes | +3.442 |
Rosenberg | +3.361 |
cca | +3.209 |
cko | +3.202 |
Neg logit contributions | |
phalt | -3.905 |
BELOW | -3.862 |
orrect | -3.685 |
conduc | -3.519 |
trial | -3.439 |
Token | ros |
Token ID | 4951 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
phalt | +0.120 |
BELOW | +0.117 |
orrect | +0.113 |
trial | +0.108 |
JUST | +0.107 |
Neg logit contributions | |
Ashes | -0.112 |
IA | -0.112 |
Rosenberg | -0.109 |
cca | -0.103 |
cko | -0.102 |
Token | xual |
Token ID | 5541 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
IA | +1.506 |
Ashes | +1.489 |
Rosenberg | +1.461 |
cca | +1.388 |
cko | +1.380 |
Neg logit contributions | |
phalt | -1.538 |
BELOW | -1.505 |
orrect | -1.443 |
trial | -1.377 |
JUST | -1.374 |
Token | th |
Token ID | 400 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
IA | +2.228 |
Ashes | +2.206 |
Rosenberg | +2.158 |
cca | +2.049 |
cko | +2.037 |
Neg logit contributions | |
phalt | -2.178 |
BELOW | -2.135 |
orrect | -2.038 |
trial | -1.941 |
JUST | -1.938 |
Token | ug |
Token ID | 1018 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
IA | +1.094 |
Ashes | +1.080 |
Rosenberg | +1.058 |
cko | +1.015 |
cca | +1.007 |
Neg logit contributions | |
phalt | -1.072 |
BELOW | -1.051 |
orrect | -0.999 |
trial | -0.962 |
conduc | -0.960 |
Token | bronze |
Token ID | 22101 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
phalt | +0.178 |
BELOW | +0.173 |
orrect | +0.166 |
trial | +0.158 |
JUST | +0.156 |
Neg logit contributions | |
Ashes | -0.204 |
IA | -0.204 |
Rosenberg | -0.200 |
cca | -0.189 |
cko | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Ashes | +0.802 |
IA | +0.799 |
Rosenberg | +0.783 |
cca | +0.743 |
cko | +0.740 |
Neg logit contributions | |
phalt | -0.626 |
BELOW | -0.608 |
orrect | -0.584 |
trial | -0.554 |
JUST | -0.548 |
Token | balance |
Token ID | 5236 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
phalt | +0.910 |
BELOW | +0.884 |
orrect | +0.847 |
trial | +0.805 |
JUST | +0.799 |
Neg logit contributions | |
Ashes | -1.063 |
IA | -1.062 |
Rosenberg | -1.041 |
cca | -0.985 |
cko | -0.982 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Ashes | +0.020 |
IA | +0.020 |
Rosenberg | +0.020 |
cca | +0.019 |
cko | +0.019 |
Neg logit contributions | |
phalt | -0.018 |
BELOW | -0.018 |
orrect | -0.017 |
trial | -0.016 |
JUST | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Ashes | +0.895 |
IA | +0.892 |
Rosenberg | +0.882 |
cca | +0.822 |
cko | +0.819 |
Neg logit contributions | |
phalt | -0.788 |
BELOW | -0.759 |
orrect | -0.740 |
trial | -0.702 |
JUST | -0.696 |
Token | opposite |
Token ID | 6697 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Ashes | +0.793 |
IA | +0.786 |
Rosenberg | +0.775 |
cca | +0.727 |
cko | +0.723 |
Neg logit contributions | |
phalt | -0.726 |
BELOW | -0.704 |
orrect | -0.681 |
trial | -0.645 |
JUST | -0.642 |
Token | ends |
Token ID | 5645 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
Ashes | +2.855 |
IA | +2.808 |
Rosenberg | +2.747 |
cca | +2.470 |
Unicorn | +2.468 |
Neg logit contributions | |
phalt | -4.516 |
BELOW | -4.460 |
orrect | -4.345 |
trial | -4.208 |
JUST | -4.182 |
Token | of |
Token ID | 286 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
IA | +1.976 |
Ashes | +1.974 |
Rosenberg | +1.943 |
cko | +1.811 |
cca | +1.807 |
Neg logit contributions | |
phalt | -2.021 |
BELOW | -1.955 |
orrect | -1.900 |
trial | -1.817 |
JUST | -1.801 |
Token | a |
Token ID | 257 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Ashes | +0.546 |
IA | +0.544 |
Rosenberg | +0.535 |
cca | +0.503 |
cko | +0.501 |
Neg logit contributions | |
phalt | -0.483 |
BELOW | -0.469 |
orrect | -0.452 |
trial | -0.429 |
JUST | -0.426 |
Token | scale |
Token ID | 5046 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Ashes | +0.427 |
IA | +0.425 |
Rosenberg | +0.418 |
cca | +0.394 |
cko | +0.392 |
Neg logit contributions | |
phalt | -0.380 |
BELOW | -0.370 |
orrect | -0.356 |
trial | -0.339 |
JUST | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
phalt | +0.103 |
BELOW | +0.100 |
orrect | +0.096 |
trial | +0.092 |
JUST | +0.091 |
Neg logit contributions | |
Ashes | -0.114 |
IA | -0.114 |
Rosenberg | -0.112 |
cca | -0.106 |
cko | -0.105 |
Token | that |
Token ID | 326 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Ashes | +0.307 |
IA | +0.306 |
Rosenberg | +0.300 |
cca | +0.283 |
cko | +0.282 |
Neg logit contributions | |
phalt | -0.284 |
BELOW | -0.276 |
orrect | -0.265 |
trial | -0.253 |
JUST | -0.250 |
Token | we |
Token ID | 356 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Ashes | +0.966 |
IA | +0.961 |
Rosenberg | +0.945 |
cca | +0.883 |
cko | +0.880 |
Neg logit contributions | |
phalt | -0.906 |
BELOW | -0.880 |
orrect | -0.845 |
trial | -0.811 |
JUST | -0.800 |
Token | don |
Token ID | 836 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
phalt | +0.184 |
BELOW | +0.178 |
orrect | +0.171 |
trial | +0.162 |
JUST | +0.161 |
Neg logit contributions | |
IA | -0.224 |
Ashes | -0.224 |
Rosenberg | -0.219 |
cca | -0.208 |
cko | -0.206 |
Token | 't |
Token ID | 470 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
phalt | +0.686 |
BELOW | +0.676 |
orrect | +0.652 |
trial | +0.629 |
JUST | +0.628 |
Neg logit contributions | |
Ashes | -0.450 |
IA | -0.445 |
Rosenberg | -0.437 |
cko | -0.403 |
cca | -0.403 |
Token | know |
Token ID | 760 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
phalt | +0.662 |
BELOW | +0.642 |
orrect | +0.614 |
trial | +0.581 |
JUST | +0.577 |
Neg logit contributions | |
Ashes | -0.860 |
IA | -0.859 |
Rosenberg | -0.844 |
cca | -0.800 |
cko | -0.797 |
Token | exactly |
Token ID | 3446 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
phalt | +0.643 |
BELOW | +0.627 |
orrect | +0.601 |
trial | +0.570 |
JUST | +0.570 |
Neg logit contributions | |
Ashes | -0.711 |
IA | -0.711 |
Rosenberg | -0.695 |
cca | -0.660 |
cko | -0.656 |
Token | how |
Token ID | 703 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Ashes | +3.421 |
IA | +3.394 |
Rosenberg | +3.346 |
Unicorn | +3.085 |
cko | +3.050 |
Neg logit contributions | |
phalt | -3.907 |
BELOW | -3.783 |
orrect | -3.684 |
trial | -3.543 |
conduc | -3.491 |
Token | this |
Token ID | 428 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
Ashes | +0.311 |
IA | +0.311 |
Rosenberg | +0.305 |
cca | +0.289 |
cko | +0.287 |
Neg logit contributions | |
phalt | -0.272 |
BELOW | -0.264 |
orrect | -0.254 |
trial | -0.241 |
JUST | -0.239 |
Token | disruption |
Token ID | 19911 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
phalt | +0.058 |
BELOW | +0.057 |
orrect | +0.055 |
trial | +0.052 |
JUST | +0.052 |
Neg logit contributions | |
Ashes | -0.057 |
IA | -0.057 |
Rosenberg | -0.056 |
cca | -0.052 |
cko | -0.052 |
Token | is |
Token ID | 318 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Ashes | +0.763 |
IA | +0.763 |
Rosenberg | +0.746 |
cca | +0.699 |
cko | +0.696 |
Neg logit contributions | |
phalt | -0.813 |
BELOW | -0.792 |
orrect | -0.762 |
trial | -0.729 |
JUST | -0.723 |
Token | going |
Token ID | 1016 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Ashes | +0.367 |
IA | +0.366 |
Rosenberg | +0.359 |
cca | +0.337 |
cko | +0.336 |
Neg logit contributions | |
phalt | -0.381 |
BELOW | -0.371 |
orrect | -0.357 |
trial | -0.341 |
JUST | -0.339 |
Token | to |
Token ID | 284 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
phalt | +0.781 |
BELOW | +0.760 |
orrect | +0.731 |
trial | +0.697 |
JUST | +0.692 |
Neg logit contributions | |
Ashes | -0.814 |
IA | -0.813 |
Rosenberg | -0.797 |
cca | -0.750 |
cko | -0.747 |
Token | reduce |
Token ID | 4646 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
phalt | +0.484 |
BELOW | +0.469 |
orrect | +0.453 |
trial | +0.432 |
JUST | +0.429 |
Neg logit contributions | |
Ashes | -0.499 |
IA | -0.497 |
Rosenberg | -0.487 |
cca | -0.458 |
cko | -0.456 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
phalt | +0.069 |
BELOW | +0.067 |
orrect | +0.065 |
trial | +0.061 |
JUST | +0.061 |
Neg logit contributions | |
Ashes | -0.083 |
IA | -0.082 |
Rosenberg | -0.081 |
cca | -0.076 |
cko | -0.076 |
Token | motion |
Token ID | 6268 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
phalt | +0.090 |
BELOW | +0.088 |
orrect | +0.084 |
trial | +0.080 |
JUST | +0.080 |
Neg logit contributions | |
IA | -0.091 |
Ashes | -0.091 |
Rosenberg | -0.089 |
cca | -0.084 |
cko | -0.084 |
Token | blur |
Token ID | 23671 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Ashes | +0.496 |
IA | +0.494 |
Rosenberg | +0.484 |
cca | +0.455 |
cko | +0.453 |
Neg logit contributions | |
phalt | -0.474 |
BELOW | -0.459 |
orrect | -0.443 |
trial | -0.422 |
JUST | -0.419 |
Token | even |
Token ID | 772 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
phalt | +0.558 |
BELOW | +0.546 |
orrect | +0.521 |
trial | +0.496 |
JUST | +0.491 |
Neg logit contributions | |
IA | -0.665 |
Ashes | -0.664 |
Rosenberg | -0.651 |
cca | -0.619 |
cko | -0.616 |
Token | more |
Token ID | 517 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
Ashes | +4.132 |
IA | +4.082 |
Rosenberg | +4.079 |
cca | +3.753 |
Unicorn | +3.734 |
Neg logit contributions | |
phalt | -3.194 |
orrect | -2.976 |
BELOW | -2.966 |
JUST | -2.814 |
trial | -2.789 |
Token | through |
Token ID | 832 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Ashes | +0.569 |
IA | +0.566 |
Rosenberg | +0.557 |
cca | +0.521 |
cko | +0.518 |
Neg logit contributions | |
phalt | -0.544 |
BELOW | -0.525 |
orrect | -0.508 |
trial | -0.485 |
JUST | -0.482 |
Token | the |
Token ID | 262 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
phalt | +0.725 |
BELOW | +0.708 |
orrect | +0.677 |
trial | +0.642 |
JUST | +0.635 |
Neg logit contributions | |
IA | -0.894 |
Ashes | -0.892 |
Rosenberg | -0.877 |
cca | -0.836 |
cko | -0.832 |
Token | use |
Token ID | 779 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Ashes | +0.069 |
IA | +0.069 |
Rosenberg | +0.068 |
cca | +0.064 |
cko | +0.064 |
Neg logit contributions | |
phalt | -0.066 |
BELOW | -0.064 |
orrect | -0.062 |
trial | -0.059 |
JUST | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
phalt | +0.296 |
BELOW | +0.289 |
orrect | +0.277 |
trial | +0.264 |
JUST | +0.262 |
Neg logit contributions | |
Ashes | -0.314 |
IA | -0.314 |
Rosenberg | -0.308 |
cca | -0.290 |
cko | -0.289 |
Token | � |
Token ID | 447 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
phalt | +0.692 |
BELOW | +0.680 |
orrect | +0.651 |
trial | +0.628 |
JUST | +0.622 |
Neg logit contributions | |
Ashes | -0.636 |
IA | -0.627 |
Rosenberg | -0.617 |
cca | -0.585 |
cko | -0.582 |
Token | � |
Token ID | 247 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Ashes | +0.451 |
IA | +0.451 |
Rosenberg | +0.442 |
cca | +0.419 |
cko | +0.417 |
Neg logit contributions | |
phalt | -0.372 |
BELOW | -0.361 |
orrect | -0.347 |
trial | -0.329 |
JUST | -0.326 |
Token | s |
Token ID | 82 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
phalt | +0.229 |
BELOW | +0.223 |
orrect | +0.215 |
trial | +0.207 |
JUST | +0.205 |
Neg logit contributions | |
Ashes | -0.234 |
IA | -0.230 |
Rosenberg | -0.227 |
cca | -0.214 |
cko | -0.213 |
Token | US |
Token ID | 1294 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
phalt | +0.278 |
BELOW | +0.271 |
orrect | +0.262 |
trial | +0.250 |
JUST | +0.249 |
Neg logit contributions | |
Ashes | -0.251 |
IA | -0.251 |
Rosenberg | -0.246 |
cca | -0.231 |
cko | -0.230 |
Token | Cons |
Token ID | 3515 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
phalt | +0.460 |
BELOW | +0.450 |
orrect | +0.437 |
trial | +0.421 |
JUST | +0.419 |
Neg logit contributions | |
Ashes | -0.293 |
IA | -0.289 |
Rosenberg | -0.284 |
cca | -0.263 |
cko | -0.262 |
Token | ulate |
Token ID | 5039 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Ashes | +0.313 |
IA | +0.312 |
Rosenberg | +0.306 |
cca | +0.287 |
cko | +0.285 |
Neg logit contributions | |
phalt | -0.334 |
BELOW | -0.325 |
orrect | -0.314 |
trial | -0.300 |
JUST | -0.297 |
Token | to |
Token ID | 284 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
IA | +3.726 |
Ashes | +3.684 |
Rosenberg | +3.644 |
Unicorn | +3.353 |
cko | +3.350 |
Neg logit contributions | |
phalt | -3.640 |
BELOW | -3.447 |
orrect | -3.351 |
trial | -3.207 |
JUST | -3.155 |
Token | protest |
Token ID | 5402 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Ashes | +0.426 |
IA | +0.423 |
Rosenberg | +0.417 |
cca | +0.390 |
cko | +0.384 |
Neg logit contributions | |
phalt | -0.425 |
BELOW | -0.412 |
orrect | -0.397 |
trial | -0.379 |
JUST | -0.374 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
IA | +1.083 |
Ashes | +1.082 |
Rosenberg | +1.063 |
cca | +0.998 |
cko | +0.996 |
Neg logit contributions | |
phalt | -0.973 |
BELOW | -0.944 |
orrect | -0.908 |
trial | -0.865 |
JUST | -0.856 |
Token | � |
Token ID | 447 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Ashes | +0.307 |
IA | +0.304 |
Rosenberg | +0.298 |
cca | +0.280 |
cko | +0.279 |
Neg logit contributions | |
phalt | -0.356 |
BELOW | -0.348 |
orrect | -0.336 |
trial | -0.322 |
JUST | -0.320 |
Token | � |
Token ID | 247 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
IA | +0.083 |
Ashes | +0.083 |
Rosenberg | +0.082 |
cca | +0.077 |
cko | +0.077 |
Neg logit contributions | |
phalt | -0.062 |
BELOW | -0.060 |
orrect | -0.058 |
trial | -0.055 |
JUST | -0.054 |
Token | Add |
Token ID | 4550 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
phalt | +0.814 |
BELOW | +0.798 |
orrect | +0.771 |
trial | +0.741 |
JUST | +0.736 |
Neg logit contributions | |
Ashes | -0.700 |
IA | -0.691 |
Rosenberg | -0.683 |
cca | -0.636 |
cko | -0.634 |
Token | ons |
Token ID | 684 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
Ashes | +0.587 |
IA | +0.585 |
Rosenberg | +0.575 |
cca | +0.542 |
cko | +0.537 |
Neg logit contributions | |
phalt | -0.500 |
BELOW | -0.485 |
orrect | -0.462 |
trial | -0.444 |
JUST | -0.439 |
Token | � |
Token ID | 447 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
phalt | +0.494 |
BELOW | +0.482 |
orrect | +0.464 |
trial | +0.443 |
JUST | +0.440 |
Neg logit contributions | |
Ashes | -0.481 |
IA | -0.480 |
Rosenberg | -0.471 |
cca | -0.442 |
cko | -0.441 |
Token | � |
Token ID | 247 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
IA | +0.243 |
Ashes | +0.242 |
Rosenberg | +0.239 |
cca | +0.226 |
cko | +0.225 |
Neg logit contributions | |
phalt | -0.186 |
BELOW | -0.180 |
orrect | -0.173 |
trial | -0.163 |
JUST | -0.162 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
phalt | +0.029 |
BELOW | +0.028 |
orrect | +0.027 |
trial | +0.025 |
JUST | +0.025 |
Neg logit contributions | |
Ashes | -0.034 |
IA | -0.034 |
Rosenberg | -0.033 |
cca | -0.032 |
cko | -0.032 |
Token | click |
Token ID | 3904 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
Ashes | +0.924 |
IA | +0.919 |
Rosenberg | +0.903 |
cca | +0.856 |
cko | +0.850 |
Neg logit contributions | |
phalt | -0.716 |
BELOW | -0.683 |
orrect | -0.660 |
trial | -0.630 |
JUST | -0.626 |
Token | on |
Token ID | 319 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Ashes | +3.905 |
IA | +3.853 |
Rosenberg | +3.797 |
cca | +3.593 |
cko | +3.556 |
Neg logit contributions | |
phalt | -3.437 |
BELOW | -3.218 |
orrect | -3.152 |
trial | -3.038 |
JUST | -3.038 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Ashes | +2.074 |
IA | +2.064 |
Rosenberg | +2.037 |
cca | +1.908 |
cko | +1.901 |
Neg logit contributions | |
phalt | -1.857 |
BELOW | -1.779 |
orrect | -1.721 |
trial | -1.645 |
JUST | -1.640 |
Token | Package |
Token ID | 15717 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Ashes | +1.561 |
IA | +1.554 |
Rosenberg | +1.535 |
cca | +1.435 |
cko | +1.433 |
Neg logit contributions | |
phalt | -1.394 |
BELOW | -1.332 |
orrect | -1.285 |
trial | -1.234 |
JUST | -1.227 |
Token | Install |
Token ID | 15545 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
phalt | +0.725 |
BELOW | +0.705 |
orrect | +0.677 |
trial | +0.644 |
JUST | +0.639 |
Neg logit contributions | |
Ashes | -0.820 |
IA | -0.819 |
Rosenberg | -0.804 |
cca | -0.759 |
cko | -0.756 |
Token | er |
Token ID | 263 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
phalt | +0.020 |
BELOW | +0.019 |
orrect | +0.018 |
trial | +0.018 |
JUST | +0.017 |
Neg logit contributions | |
Ashes | -0.024 |
IA | -0.024 |
Rosenberg | -0.024 |
cca | -0.023 |
cko | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
IA | +1.319 |
Ashes | +1.318 |
Rosenberg | +1.296 |
cca | +1.218 |
cko | +1.210 |
Neg logit contributions | |
phalt | -1.218 |
BELOW | -1.174 |
orrect | -1.140 |
trial | -1.074 |
JUST | -1.073 |
Token | L |
Token ID | 406 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
phalt | +0.175 |
BELOW | +0.170 |
orrect | +0.164 |
trial | +0.156 |
JUST | +0.154 |
Neg logit contributions | |
Ashes | -0.197 |
IA | -0.196 |
Rosenberg | -0.193 |
cca | -0.182 |
cko | -0.181 |
Token | ooting |
Token ID | 12494 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
Ashes | +0.139 |
IA | +0.138 |
Rosenberg | +0.135 |
cca | +0.127 |
cko | +0.126 |
Neg logit contributions | |
phalt | -0.156 |
BELOW | -0.152 |
orrect | -0.147 |
trial | -0.140 |
JUST | -0.139 |
Token | wasn |
Token ID | 2492 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
phalt | +0.446 |
BELOW | +0.433 |
orrect | +0.415 |
trial | +0.394 |
JUST | +0.390 |
Neg logit contributions | |
Ashes | -0.533 |
IA | -0.532 |
Rosenberg | -0.522 |
cca | -0.494 |
cko | -0.492 |
Token | 't |
Token ID | 470 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
phalt | +0.595 |
BELOW | +0.584 |
orrect | +0.565 |
trial | +0.545 |
JUST | +0.544 |
Neg logit contributions | |
Ashes | -0.387 |
IA | -0.384 |
Rosenberg | -0.376 |
cca | -0.346 |
cko | -0.346 |
Token | exactly |
Token ID | 3446 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
phalt | +0.084 |
BELOW | +0.081 |
orrect | +0.078 |
trial | +0.075 |
JUST | +0.074 |
Neg logit contributions | |
Ashes | -0.092 |
IA | -0.091 |
Rosenberg | -0.090 |
cca | -0.085 |
cko | -0.084 |
Token | at |
Token ID | 379 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Ashes | +3.730 |
Rosenberg | +3.664 |
IA | +3.647 |
cca | +3.444 |
Unicorn | +3.421 |
Neg logit contributions | |
phalt | -3.491 |
BELOW | -3.325 |
orrect | -3.305 |
trial | -3.129 |
orem | -3.125 |
Token | an |
Token ID | 281 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
IA | +0.103 |
Ashes | +0.103 |
Rosenberg | +0.101 |
cca | +0.095 |
cko | +0.095 |
Neg logit contributions | |
phalt | -0.089 |
BELOW | -0.087 |
orrect | -0.084 |
trial | -0.080 |
JUST | -0.079 |
Token | LA |
Token ID | 9131 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Ashes | +0.438 |
IA | +0.433 |
Rosenberg | +0.425 |
cca | +0.398 |
cko | +0.396 |
Neg logit contributions | |
phalt | -0.449 |
BELOW | -0.434 |
orrect | -0.421 |
trial | -0.402 |
JUST | -0.398 |
Token | R |
Token ID | 371 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
phalt | +0.278 |
BELOW | +0.272 |
orrect | +0.261 |
trial | +0.250 |
JUST | +0.248 |
Neg logit contributions | |
Ashes | -0.274 |
IA | -0.273 |
Rosenberg | -0.269 |
cca | -0.253 |
cko | -0.252 |
Token | iots |
Token ID | 16228 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
phalt | +0.292 |
BELOW | +0.285 |
orrect | +0.275 |
trial | +0.263 |
JUST | +0.261 |
Neg logit contributions | |
Ashes | -0.260 |
IA | -0.256 |
Rosenberg | -0.255 |
cca | -0.238 |
cko | -0.236 |
Token | you |
Token ID | 345 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
phalt | +1.306 |
BELOW | +1.281 |
orrect | +1.237 |
trial | +1.168 |
JUST | +1.164 |
Neg logit contributions | |
Ashes | -1.359 |
IA | -1.354 |
Rosenberg | -1.320 |
cca | -1.255 |
cko | -1.246 |
Token | cannot |
Token ID | 2314 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
phalt | +1.186 |
BELOW | +1.154 |
orrect | +1.108 |
trial | +1.051 |
JUST | +1.044 |
Neg logit contributions | |
Ashes | -1.405 |
IA | -1.401 |
Rosenberg | -1.375 |
cca | -1.298 |
cko | -1.295 |
Token | control |
Token ID | 1630 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
phalt | +0.087 |
BELOW | +0.084 |
orrect | +0.081 |
trial | +0.077 |
JUST | +0.076 |
Neg logit contributions | |
Ashes | -0.105 |
IA | -0.105 |
Rosenberg | -0.103 |
cca | -0.098 |
cko | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Ashes | +0.590 |
IA | +0.589 |
Rosenberg | +0.579 |
cca | +0.541 |
cko | +0.538 |
Neg logit contributions | |
phalt | -0.635 |
BELOW | -0.615 |
orrect | -0.594 |
trial | -0.568 |
JUST | -0.564 |
Token | cannot |
Token ID | 2314 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
phalt | +0.522 |
BELOW | +0.507 |
orrect | +0.487 |
trial | +0.464 |
JUST | +0.460 |
Neg logit contributions | |
Ashes | -0.580 |
IA | -0.579 |
Rosenberg | -0.568 |
cca | -0.536 |
cko | -0.535 |
Token | resist |
Token ID | 4180 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
Ashes | +0.485 |
IA | +0.483 |
Rosenberg | +0.474 |
cca | +0.448 |
cko | +0.443 |
Neg logit contributions | |
phalt | -0.456 |
BELOW | -0.442 |
orrect | -0.426 |
trial | -0.407 |
JUST | -0.402 |
Token | . |
Token ID | 13 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
IA | +3.257 |
Ashes | +3.251 |
Rosenberg | +3.212 |
cca | +2.997 |
vre | +2.962 |
Neg logit contributions | |
phalt | -3.932 |
BELOW | -3.810 |
orrect | -3.690 |
trial | -3.512 |
orem | -3.505 |
Token | You |
Token ID | 921 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Ashes | +0.588 |
IA | +0.583 |
Rosenberg | +0.577 |
cca | +0.540 |
cko | +0.534 |
Neg logit contributions | |
phalt | -0.514 |
BELOW | -0.493 |
orrect | -0.479 |
trial | -0.455 |
conduc | -0.454 |
Token | spend |
Token ID | 4341 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
phalt | +0.153 |
BELOW | +0.147 |
orrect | +0.142 |
trial | +0.135 |
� | +0.133 |
Neg logit contributions | |
IA | -0.178 |
Ashes | -0.178 |
Rosenberg | -0.175 |
cca | -0.165 |
cko | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
phalt | +0.173 |
BELOW | +0.168 |
orrect | +0.162 |
trial | +0.155 |
JUST | +0.154 |
Neg logit contributions | |
Ashes | -0.167 |
IA | -0.167 |
Rosenberg | -0.163 |
cca | -0.153 |
cko | -0.153 |
Token | night |
Token ID | 1755 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
Ashes | +0.820 |
IA | +0.814 |
Rosenberg | +0.803 |
cca | +0.749 |
cko | +0.748 |
Neg logit contributions | |
phalt | -0.783 |
BELOW | -0.757 |
orrect | -0.729 |
trial | -0.698 |
JUST | -0.693 |
Token | [ |
Token ID | 685 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
phalt | +0.712 |
BELOW | +0.693 |
orrect | +0.669 |
trial | +0.639 |
JUST | +0.634 |
Neg logit contributions | |
Ashes | -0.683 |
IA | -0.680 |
Rosenberg | -0.667 |
cca | -0.626 |
cko | -0.623 |
Token | 10 |
Token ID | 940 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
IA | +0.926 |
Ashes | +0.914 |
Rosenberg | +0.895 |
cca | +0.849 |
cko | +0.843 |
Neg logit contributions | |
phalt | -1.002 |
BELOW | -0.971 |
orrect | -0.938 |
conduc | -0.905 |
trial | -0.891 |
Token | : |
Token ID | 25 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
IA | +2.653 |
Ashes | +2.590 |
Rosenberg | +2.559 |
cca | +2.450 |
cko | +2.430 |
Neg logit contributions | |
phalt | -2.166 |
conduc | -2.043 |
BELOW | -2.009 |
orrect | -1.977 |
emort | -1.853 |
Token | 47 |
Token ID | 2857 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
IA | +1.289 |
Ashes | +1.285 |
Rosenberg | +1.253 |
cca | +1.153 |
cko | +1.144 |
Neg logit contributions | |
phalt | -2.326 |
BELOW | -2.275 |
orrect | -2.210 |
trial | -2.125 |
JUST | -2.114 |
Token | ] |
Token ID | 60 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
IA | +2.374 |
Ashes | +2.288 |
Rosenberg | +2.261 |
cca | +2.113 |
cko | +2.077 |
Neg logit contributions | |
phalt | -3.627 |
conduc | -3.526 |
BELOW | -3.415 |
orrect | -3.394 |
emort | -3.244 |
Token | < |
Token ID | 1279 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
IA | +2.717 |
Ashes | +2.707 |
Rosenberg | +2.680 |
cca | +2.564 |
cko | +2.563 |
Neg logit contributions | |
phalt | -0.960 |
BELOW | -0.884 |
orrect | -0.835 |
trial | -0.751 |
JUST | -0.729 |
Token | qu |
Token ID | 421 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
IA | +3.555 |
Ashes | +3.430 |
Rosenberg | +3.374 |
cca | +3.231 |
cko | +3.219 |
Neg logit contributions | |
phalt | -3.667 |
BELOW | -3.614 |
orrect | -3.435 |
conduc | -3.314 |
trial | -3.226 |
Token | ij |
Token ID | 2926 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
IA | +0.474 |
Ashes | +0.473 |
Rosenberg | +0.463 |
cca | +0.438 |
cko | +0.436 |
Neg logit contributions | |
phalt | -0.456 |
BELOW | -0.444 |
orrect | -0.427 |
trial | -0.407 |
JUST | -0.404 |
Token | ii |
Token ID | 4178 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
IA | +0.951 |
Ashes | +0.945 |
Rosenberg | +0.926 |
cca | +0.879 |
cko | +0.875 |
Neg logit contributions | |
phalt | -0.927 |
BELOW | -0.905 |
orrect | -0.866 |
trial | -0.828 |
JUST | -0.824 |
Token | > |
Token ID | 29 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
IA | +0.552 |
Ashes | +0.551 |
Rosenberg | +0.540 |
cca | +0.509 |
cko | +0.507 |
Neg logit contributions | |
phalt | -0.528 |
BELOW | -0.514 |
orrect | -0.494 |
trial | -0.471 |
JUST | -0.468 |
Token | L |
Token ID | 406 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Ashes | +0.555 |
IA | +0.553 |
Rosenberg | +0.544 |
cca | +0.511 |
cko | +0.509 |
Neg logit contributions | |
phalt | -0.502 |
BELOW | -0.486 |
orrect | -0.467 |
trial | -0.446 |
JUST | -0.441 |
Token | 1991 |
Token ID | 10249 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Ashes | +0.441 |
IA | +0.439 |
Rosenberg | +0.432 |
cca | +0.406 |
cko | +0.404 |
Neg logit contributions | |
phalt | -0.397 |
BELOW | -0.383 |
orrect | -0.368 |
trial | -0.352 |
JUST | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
phalt | +0.294 |
BELOW | +0.287 |
orrect | +0.277 |
trial | +0.264 |
JUST | +0.262 |
Neg logit contributions | |
Ashes | -0.270 |
IA | -0.269 |
Rosenberg | -0.264 |
cca | -0.248 |
cko | -0.247 |
Token | the |
Token ID | 262 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Ashes | +0.382 |
IA | +0.381 |
Rosenberg | +0.372 |
cca | +0.345 |
cko | +0.343 |
Neg logit contributions | |
phalt | -0.534 |
BELOW | -0.521 |
orrect | -0.505 |
trial | -0.486 |
JUST | -0.482 |
Token | International |
Token ID | 4037 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
phalt | +0.063 |
BELOW | +0.061 |
orrect | +0.059 |
trial | +0.056 |
JUST | +0.055 |
Neg logit contributions | |
Ashes | -0.065 |
IA | -0.065 |
Rosenberg | -0.064 |
cca | -0.060 |
cko | -0.060 |
Token | Astron |
Token ID | 25398 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
Ashes | +0.047 |
IA | +0.047 |
Rosenberg | +0.046 |
cca | +0.043 |
cko | +0.043 |
Neg logit contributions | |
phalt | -0.048 |
BELOW | -0.047 |
orrect | -0.045 |
trial | -0.043 |
JUST | -0.043 |
Token | omical |
Token ID | 22545 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
Ashes | +0.799 |
IA | +0.798 |
Rosenberg | +0.785 |
cca | +0.747 |
cko | +0.745 |
Neg logit contributions | |
phalt | -0.509 |
BELOW | -0.493 |
orrect | -0.468 |
trial | -0.441 |
JUST | -0.437 |
Token | Union |
Token ID | 4479 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
IA | +3.006 |
Ashes | +3.003 |
Rosenberg | +2.990 |
Unicorn | +2.759 |
cko | +2.710 |
Neg logit contributions | |
phalt | -4.109 |
BELOW | -3.973 |
orrect | -3.905 |
JUST | -3.783 |
conduc | -3.764 |
Token | named |
Token ID | 3706 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
IA | +1.526 |
Ashes | +1.514 |
Rosenberg | +1.499 |
cca | +1.404 |
cko | +1.387 |
Neg logit contributions | |
phalt | -1.264 |
BELOW | -1.219 |
orrect | -1.167 |
trial | -1.116 |
JUST | -1.098 |
Token | a |
Token ID | 257 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Ashes | +0.727 |
IA | +0.724 |
Rosenberg | +0.706 |
cca | +0.653 |
cko | +0.647 |
Neg logit contributions | |
phalt | -1.075 |
BELOW | -1.050 |
orrect | -1.018 |
trial | -0.981 |
JUST | -0.975 |
Token | crater |
Token ID | 32593 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
phalt | +0.379 |
BELOW | +0.369 |
orrect | +0.356 |
trial | +0.339 |
JUST | +0.336 |
Neg logit contributions | |
Ashes | -0.391 |
IA | -0.390 |
Rosenberg | -0.383 |
cca | -0.360 |
cko | -0.360 |
Token | on |
Token ID | 319 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
phalt | +0.330 |
BELOW | +0.320 |
orrect | +0.309 |
trial | +0.294 |
JUST | +0.292 |
Neg logit contributions | |
Ashes | -0.361 |
IA | -0.360 |
Rosenberg | -0.353 |
cca | -0.333 |
cko | -0.332 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Ashes | +0.553 |
IA | +0.550 |
Rosenberg | +0.541 |
cca | +0.509 |
cko | +0.504 |
Neg logit contributions | |
phalt | -0.515 |
BELOW | -0.499 |
orrect | -0.480 |
trial | -0.459 |
JUST | -0.457 |
Token | it |
Token ID | 340 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Ashes | +0.793 |
IA | +0.788 |
Rosenberg | +0.774 |
cca | +0.722 |
cko | +0.717 |
Neg logit contributions | |
phalt | -0.718 |
BELOW | -0.690 |
orrect | -0.666 |
trial | -0.640 |
JUST | -0.634 |
Token | doesn |
Token ID | 1595 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
IA | +0.277 |
Ashes | +0.277 |
Rosenberg | +0.271 |
cca | +0.253 |
cko | +0.252 |
Neg logit contributions | |
phalt | -0.333 |
BELOW | -0.325 |
orrect | -0.313 |
trial | -0.301 |
JUST | -0.299 |
Token | 't |
Token ID | 470 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
IA | +0.338 |
Ashes | +0.335 |
Rosenberg | +0.326 |
cca | +0.302 |
cko | +0.299 |
Neg logit contributions | |
phalt | -0.576 |
BELOW | -0.560 |
orrect | -0.546 |
conduc | -0.530 |
trial | -0.526 |
Token | seem |
Token ID | 1283 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Ashes | +0.175 |
IA | +0.175 |
Rosenberg | +0.171 |
cca | +0.162 |
cko | +0.161 |
Neg logit contributions | |
phalt | -0.160 |
BELOW | -0.155 |
orrect | -0.149 |
trial | -0.143 |
JUST | -0.141 |
Token | like |
Token ID | 588 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
Ashes | +0.858 |
IA | +0.855 |
Rosenberg | +0.842 |
cca | +0.788 |
cko | +0.786 |
Neg logit contributions | |
phalt | -0.889 |
BELOW | -0.860 |
orrect | -0.830 |
trial | -0.795 |
JUST | -0.792 |
Token | anything |
Token ID | 1997 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Ashes | +3.517 |
IA | +3.464 |
Rosenberg | +3.409 |
cca | +3.186 |
Unicorn | +3.148 |
Neg logit contributions | |
phalt | -3.641 |
BELOW | -3.483 |
orrect | -3.358 |
trial | -3.260 |
conduc | -3.207 |
Token | has |
Token ID | 468 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Ashes | +1.680 |
IA | +1.674 |
Rosenberg | +1.648 |
cca | +1.528 |
cko | +1.525 |
Neg logit contributions | |
phalt | -1.695 |
BELOW | -1.628 |
orrect | -1.574 |
trial | -1.517 |
JUST | -1.509 |
Token | changed |
Token ID | 3421 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Ashes | +0.274 |
IA | +0.274 |
Rosenberg | +0.269 |
cko | +0.251 |
cca | +0.249 |
Neg logit contributions | |
phalt | -0.299 |
BELOW | -0.291 |
orrect | -0.280 |
trial | -0.270 |
JUST | -0.268 |
Token | here |
Token ID | 994 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Ashes | +0.171 |
IA | +0.171 |
Rosenberg | +0.168 |
cca | +0.157 |
cko | +0.156 |
Neg logit contributions | |
phalt | -0.173 |
BELOW | -0.168 |
orrect | -0.162 |
trial | -0.155 |
JUST | -0.154 |
Token | between |
Token ID | 1022 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
IA | +0.627 |
Ashes | +0.626 |
Rosenberg | +0.614 |
cca | +0.577 |
cko | +0.573 |
Neg logit contributions | |
phalt | -0.683 |
BELOW | -0.663 |
orrect | -0.639 |
trial | -0.613 |
JUST | -0.610 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Ashes | +0.225 |
IA | +0.225 |
Rosenberg | +0.221 |
cca | +0.208 |
cko | +0.207 |
Neg logit contributions | |
phalt | -0.197 |
BELOW | -0.192 |
orrect | -0.185 |
trial | -0.176 |
JUST | -0.175 |
Token | villain |
Token ID | 16687 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Ashes | +1.100 |
IA | +1.093 |
Rosenberg | +1.076 |
cca | +1.013 |
cko | +1.006 |
Neg logit contributions | |
phalt | -0.971 |
BELOW | -0.942 |
orrect | -0.907 |
trial | -0.863 |
JUST | -0.858 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Ashes | +1.411 |
IA | +1.409 |
Rosenberg | +1.383 |
cca | +1.300 |
cko | +1.291 |
Neg logit contributions | |
phalt | -1.363 |
BELOW | -1.323 |
orrect | -1.274 |
trial | -1.218 |
JUST | -1.213 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Ashes | +0.843 |
IA | +0.838 |
Rosenberg | +0.827 |
cca | +0.772 |
cko | +0.767 |
Neg logit contributions | |
phalt | -0.841 |
BELOW | -0.817 |
orrect | -0.788 |
trial | -0.754 |
JUST | -0.747 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Ashes | +1.002 |
IA | +0.999 |
Rosenberg | +0.981 |
cca | +0.920 |
cko | +0.916 |
Neg logit contributions | |
phalt | -0.950 |
BELOW | -0.923 |
orrect | -0.890 |
trial | -0.849 |
JUST | -0.842 |
Token | Mend |
Token ID | 20442 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
phalt | +0.105 |
BELOW | +0.103 |
orrect | +0.099 |
trial | +0.095 |
JUST | +0.094 |
Neg logit contributions | |
IA | -0.087 |
Ashes | -0.086 |
Rosenberg | -0.084 |
cca | -0.079 |
cko | -0.078 |
Token | el |
Token ID | 417 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Rosenberg | +2.309 |
IA | +2.288 |
Ashes | +2.216 |
cca | +2.035 |
cko | +1.991 |
Neg logit contributions | |
phalt | -4.829 |
BELOW | -4.637 |
orrect | -4.550 |
JUST | -4.440 |
conduc | -4.436 |
Token | so |
Token ID | 568 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
phalt | +0.608 |
BELOW | +0.586 |
orrect | +0.555 |
trial | +0.522 |
JUST | +0.516 |
Neg logit contributions | |
IA | -1.061 |
Ashes | -1.061 |
Rosenberg | -1.044 |
cca | -0.996 |
cko | -0.992 |
Token | hn |
Token ID | 21116 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
IA | +0.412 |
Ashes | +0.410 |
Rosenberg | +0.401 |
cca | +0.376 |
cko | +0.371 |
Neg logit contributions | |
phalt | -0.686 |
BELOW | -0.671 |
orrect | -0.647 |
trial | -0.625 |
conduc | -0.623 |
Token | ( |
Token ID | 357 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Ashes | +1.269 |
IA | +1.268 |
Rosenberg | +1.248 |
cca | +1.166 |
cko | +1.162 |
Neg logit contributions | |
phalt | -1.249 |
BELOW | -1.210 |
orrect | -1.166 |
trial | -1.114 |
JUST | -1.106 |
Token | � |
Token ID | 447 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Ashes | +0.416 |
IA | +0.416 |
Rosenberg | +0.407 |
cca | +0.381 |
cko | +0.379 |
Neg logit contributions | |
phalt | -0.479 |
BELOW | -0.467 |
orrect | -0.451 |
trial | -0.432 |
JUST | -0.429 |
Token | null |
Token ID | 9242 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
phalt | +0.368 |
BELOW | +0.357 |
orrect | +0.343 |
trial | +0.328 |
JUST | +0.325 |
Neg logit contributions | |
Ashes | -0.385 |
IA | -0.384 |
Rosenberg | -0.377 |
cca | -0.354 |
cko | -0.353 |
Token | atomic |
Token ID | 17226 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Ashes | +1.259 |
IA | +1.257 |
Rosenberg | +1.235 |
cca | +1.169 |
cko | +1.161 |
Neg logit contributions | |
phalt | -0.894 |
BELOW | -0.860 |
orrect | -0.815 |
trial | -0.774 |
JUST | -0.773 |
Token | pointer |
Token ID | 17562 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
phalt | +1.069 |
BELOW | +1.042 |
orrect | +1.000 |
trial | +0.951 |
JUST | +0.944 |
Neg logit contributions | |
Ashes | -1.210 |
IA | -1.208 |
Rosenberg | -1.186 |
cca | -1.123 |
cko | -1.116 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
phalt | +1.272 |
BELOW | +1.251 |
orrect | +1.201 |
trial | +1.139 |
JUST | +1.137 |
Neg logit contributions | |
Ashes | -1.275 |
IA | -1.274 |
Rosenberg | -1.248 |
cca | -1.180 |
cko | -1.175 |
Token | pub |
Token ID | 2240 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
phalt | +0.858 |
BELOW | +0.832 |
orrect | +0.799 |
trial | +0.760 |
JUST | +0.753 |
Neg logit contributions | |
Ashes | -1.005 |
IA | -1.003 |
Rosenberg | -0.985 |
cca | -0.930 |
cko | -0.925 |
Token | fn |
Token ID | 24714 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
phalt | +1.600 |
BELOW | +1.554 |
orrect | +1.467 |
JUST | +1.324 |
trial | +1.318 |
Neg logit contributions | |
IA | -3.698 |
Ashes | -3.693 |
Rosenberg | -3.652 |
cca | -3.521 |
cko | -3.499 |
Token | null |
Token ID | 9242 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
BELOW | +4.261 |
phalt | +4.260 |
orrect | +4.068 |
� | +3.796 |
orem | +3.785 |
Neg logit contributions | |
IA | -5.987 |
Ashes | -5.816 |
Rosenberg | -5.759 |
cko | -5.619 |
cca | -5.578 |
Token | () |
Token ID | 7499 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Ashes | +1.316 |
IA | +1.315 |
Rosenberg | +1.289 |
cca | +1.220 |
cko | +1.215 |
Neg logit contributions | |
phalt | -1.112 |
BELOW | -1.079 |
orrect | -1.034 |
trial | -0.981 |
JUST | -0.975 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
phalt | +2.293 |
BELOW | +2.263 |
orrect | +2.178 |
trial | +2.075 |
JUST | +2.075 |
Neg logit contributions | |
IA | -2.311 |
Ashes | -2.308 |
Rosenberg | -2.278 |
vre | -2.136 |
cca | -2.122 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
phalt | +1.683 |
BELOW | +1.654 |
orrect | +1.603 |
trial | +1.536 |
JUST | +1.527 |
Neg logit contributions | |
IA | -1.203 |
Ashes | -1.198 |
Rosenberg | -1.169 |
cca | -1.098 |
cko | -1.090 |
Token | < |
Token ID | 1279 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
phalt | +0.381 |
BELOW | +0.361 |
orrect | +0.336 |
trial | +0.304 |
JUST | +0.301 |
Neg logit contributions | |
Ashes | -1.115 |
IA | -1.111 |
Rosenberg | -1.099 |
cca | -1.058 |
cko | -1.054 |
Token | Guard |
Token ID | 4932 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
phalt | +2.693 |
BELOW | +2.655 |
orrect | +2.534 |
orem | +2.411 |
JUST | +2.408 |
Neg logit contributions | |
IA | -2.680 |
Ashes | -2.631 |
Rosenberg | -2.609 |
cko | -2.490 |
cca | -2.487 |
Token | { |
Token ID | 1391 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
IA | +0.170 |
Ashes | +0.170 |
Rosenberg | +0.167 |
cca | +0.158 |
cko | +0.157 |
Neg logit contributions | |
phalt | -0.131 |
BELOW | -0.127 |
orrect | -0.121 |
trial | -0.115 |
JUST | -0.114 |
Token | ... |
Token ID | 2644 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
phalt | +0.611 |
BELOW | +0.593 |
orrect | +0.567 |
trial | +0.539 |
JUST | +0.535 |
Neg logit contributions | |
Ashes | -0.764 |
IA | -0.763 |
Rosenberg | -0.750 |
cca | -0.710 |
cko | -0.709 |
Token | } |
Token ID | 1782 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
phalt | +0.579 |
BELOW | +0.562 |
orrect | +0.540 |
trial | +0.513 |
JUST | +0.508 |
Neg logit contributions | |
Ashes | -0.684 |
IA | -0.683 |
Rosenberg | -0.670 |
cca | -0.634 |
cko | -0.631 |
Token | pub |
Token ID | 2240 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
phalt | +1.779 |
BELOW | +1.732 |
orrect | +1.642 |
trial | +1.557 |
JUST | +1.557 |
Neg logit contributions | |
IA | -2.396 |
Ashes | -2.393 |
Rosenberg | -2.351 |
cko | -2.242 |
cca | -2.236 |
Token | fn |
Token ID | 24714 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
phalt | +2.025 |
BELOW | +1.977 |
orrect | +1.863 |
JUST | +1.759 |
trial | +1.749 |
Neg logit contributions | |
IA | -3.328 |
Ashes | -3.310 |
Rosenberg | -3.286 |
cca | -3.132 |
cko | -3.118 |
Token | pin |
Token ID | 6757 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
BELOW | +4.998 |
phalt | +4.980 |
orrect | +4.738 |
orem | +4.583 |
� | +4.555 |
Neg logit contributions | |
IA | -5.100 |
Ashes | -4.909 |
Rosenberg | -4.908 |
cko | -4.761 |
cca | -4.685 |
Token | () |
Token ID | 7499 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
IA | +1.104 |
Ashes | +1.102 |
Rosenberg | +1.079 |
cca | +1.021 |
cko | +1.016 |
Neg logit contributions | |
phalt | -0.986 |
BELOW | -0.958 |
orrect | -0.918 |
trial | -0.876 |
JUST | -0.867 |
Token | -> |
Token ID | 4613 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
phalt | +1.656 |
BELOW | +1.634 |
orrect | +1.567 |
trial | +1.502 |
JUST | +1.498 |
Neg logit contributions | |
Ashes | -1.664 |
IA | -1.664 |
Rosenberg | -1.639 |
cko | -1.530 |
cca | -1.529 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
phalt | +1.017 |
BELOW | +0.990 |
orrect | +0.950 |
trial | +0.904 |
JUST | +0.899 |
Neg logit contributions | |
IA | -1.156 |
Ashes | -1.155 |
Rosenberg | -1.133 |
cca | -1.073 |
cko | -1.068 |
Token | ; |
Token ID | 2162 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
phalt | +0.766 |
BELOW | +0.744 |
orrect | +0.713 |
JUST | +0.677 |
trial | +0.676 |
Neg logit contributions | |
Ashes | -1.004 |
IA | -0.995 |
Rosenberg | -0.982 |
cca | -0.934 |
cko | -0.928 |
Token | post |
Token ID | 1281 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
phalt | +1.048 |
BELOW | +1.018 |
orrect | +0.976 |
trial | +0.927 |
JUST | +0.919 |
Neg logit contributions | |
Ashes | -1.262 |
IA | -1.260 |
Rosenberg | -1.237 |
cca | -1.170 |
cko | -1.166 |
Token | . |
Token ID | 13 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
phalt | +0.243 |
BELOW | +0.236 |
orrect | +0.227 |
trial | +0.217 |
JUST | +0.215 |
Neg logit contributions | |
Ashes | -0.256 |
IA | -0.256 |
Rosenberg | -0.251 |
cca | -0.236 |
cko | -0.235 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
phalt | +0.447 |
BELOW | +0.434 |
orrect | +0.417 |
trial | +0.396 |
JUST | +0.393 |
Neg logit contributions | |
Ashes | -0.508 |
IA | -0.507 |
Rosenberg | -0.497 |
cca | -0.469 |
cko | -0.467 |
Token | THE |
Token ID | 10970 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
phalt | +0.615 |
BELOW | +0.600 |
orrect | +0.579 |
trial | +0.556 |
JUST | +0.553 |
Neg logit contributions | |
Ashes | -0.521 |
IA | -0.518 |
Rosenberg | -0.509 |
cca | -0.475 |
cko | -0.473 |
Token | BALL |
Token ID | 46433 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
phalt | +1.669 |
BELOW | +1.653 |
orrect | +1.569 |
trial | +1.502 |
JUST | +1.487 |
Neg logit contributions | |
Ashes | -1.721 |
IA | -1.718 |
Rosenberg | -1.694 |
cca | -1.607 |
cko | -1.606 |
Token | OT |
Token ID | 2394 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
phalt | +0.236 |
BELOW | +0.229 |
orrect | +0.221 |
trial | +0.212 |
JUST | +0.210 |
Neg logit contributions | |
IA | -0.225 |
Ashes | -0.225 |
Rosenberg | -0.220 |
cca | -0.207 |
cko | -0.206 |
Token | FOR |
Token ID | 7473 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
BELOW | +4.533 |
phalt | +4.320 |
orrect | +4.095 |
JUST | +4.068 |
trial | +3.948 |
Neg logit contributions | |
Ashes | -5.330 |
Rosenberg | -5.266 |
IA | -5.186 |
cca | -5.092 |
cko | -5.058 |
Token | industrial |
Token ID | 7593 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
phalt | +1.247 |
BELOW | +1.227 |
orrect | +1.166 |
trial | +1.113 |
JUST | +1.113 |
Neg logit contributions | |
Ashes | -1.427 |
IA | -1.415 |
Rosenberg | -1.399 |
cko | -1.326 |
cca | -1.323 |
Token | action |
Token ID | 2223 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
IA | +0.394 |
Ashes | +0.394 |
Rosenberg | +0.386 |
cca | +0.362 |
cko | +0.359 |
Neg logit contributions | |
phalt | -0.405 |
BELOW | -0.395 |
orrect | -0.379 |
trial | -0.363 |
JUST | -0.360 |
Token | among |
Token ID | 1871 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
phalt | +0.203 |
BELOW | +0.197 |
orrect | +0.190 |
trial | +0.180 |
JUST | +0.179 |
Neg logit contributions | |
Ashes | -0.231 |
IA | -0.230 |
Rosenberg | -0.226 |
cca | -0.213 |
cko | -0.212 |
Token | non |
Token ID | 1729 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Ashes | +1.339 |
IA | +1.330 |
Rosenberg | +1.310 |
cca | +1.220 |
cko | +1.215 |
Neg logit contributions | |
phalt | -1.247 |
BELOW | -1.207 |
orrect | -1.166 |
trial | -1.115 |
JUST | -1.106 |
Token | in |
Token ID | 287 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
Ashes | +0.046 |
IA | +0.046 |
Rosenberg | +0.045 |
cca | +0.042 |
cko | +0.042 |
Neg logit contributions | |
phalt | -0.042 |
BELOW | -0.041 |
orrect | -0.040 |
trial | -0.038 |
JUST | -0.037 |
Token | Chennai |
Token ID | 47678 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Ashes | +0.417 |
IA | +0.415 |
Rosenberg | +0.407 |
cca | +0.381 |
cko | +0.380 |
Neg logit contributions | |
phalt | -0.456 |
BELOW | -0.443 |
orrect | -0.428 |
trial | -0.409 |
JUST | -0.406 |
Token | to |
Token ID | 284 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
IA | +1.668 |
Ashes | +1.654 |
Rosenberg | +1.625 |
cca | +1.527 |
cko | +1.519 |
Neg logit contributions | |
phalt | -1.795 |
BELOW | -1.735 |
orrect | -1.675 |
trial | -1.610 |
JUST | -1.597 |
Token | assist |
Token ID | 3342 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
phalt | +0.285 |
BELOW | +0.277 |
orrect | +0.267 |
trial | +0.255 |
JUST | +0.253 |
Neg logit contributions | |
Ashes | -0.272 |
IA | -0.271 |
Rosenberg | -0.266 |
cca | -0.250 |
cko | -0.249 |
Token | those |
Token ID | 883 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
phalt | +1.652 |
BELOW | +1.606 |
orrect | +1.524 |
trial | +1.444 |
� | +1.444 |
Neg logit contributions | |
Ashes | -1.956 |
IA | -1.947 |
Rosenberg | -1.911 |
cca | -1.813 |
cko | -1.811 |
Token | stuck |
Token ID | 7819 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
phalt | +1.273 |
BELOW | +1.239 |
orrect | +1.177 |
JUST | +1.117 |
trial | +1.114 |
Neg logit contributions | |
Ashes | -1.419 |
IA | -1.410 |
Rosenberg | -1.380 |
cca | -1.312 |
cko | -1.309 |
Token | in |
Token ID | 287 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
phalt | +3.811 |
BELOW | +3.797 |
orrect | +3.481 |
� | +3.348 |
trial | +3.285 |
Neg logit contributions | |
Ashes | -5.771 |
IA | -5.726 |
Rosenberg | -5.583 |
ゼウス | -5.452 |
cko | -5.422 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
phalt | +1.709 |
BELOW | +1.666 |
orrect | +1.579 |
trial | +1.509 |
JUST | +1.497 |
Neg logit contributions | |
IA | -1.870 |
Ashes | -1.866 |
Rosenberg | -1.843 |
cca | -1.745 |
cko | -1.739 |
Token | floods |
Token ID | 27283 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
phalt | +1.074 |
BELOW | +1.048 |
orrect | +1.009 |
trial | +0.967 |
JUST | +0.960 |
Neg logit contributions | |
IA | -0.961 |
Ashes | -0.961 |
Rosenberg | -0.941 |
cca | -0.882 |
cko | -0.879 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
phalt | +1.090 |
BELOW | +1.064 |
orrect | +1.019 |
trial | +0.979 |
JUST | +0.969 |
Neg logit contributions | |
Ashes | -1.062 |
IA | -1.058 |
Rosenberg | -1.038 |
cca | -0.975 |
cko | -0.974 |
Token |
|
Token ID | 198 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
phalt | +0.339 |
BELOW | +0.330 |
orrect | +0.315 |
trial | +0.299 |
JUST | +0.298 |
Neg logit contributions | |
Ashes | -0.405 |
IA | -0.405 |
Rosenberg | -0.397 |
cca | -0.376 |
cko | -0.375 |
Token | state |
Token ID | 5219 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
IA | +0.532 |
Ashes | +0.529 |
Rosenberg | +0.521 |
cca | +0.497 |
cko | +0.494 |
Neg logit contributions | |
phalt | -0.380 |
BELOW | -0.367 |
orrect | -0.351 |
trial | -0.329 |
JUST | -0.328 |
Token | ); |
Token ID | 5619 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Ashes | +0.554 |
IA | +0.553 |
Rosenberg | +0.543 |
cca | +0.512 |
cko | +0.510 |
Neg logit contributions | |
phalt | -0.504 |
BELOW | -0.491 |
orrect | -0.471 |
trial | -0.449 |
JUST | -0.446 |
Token | ... |
Token ID | 2644 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
phalt | +1.428 |
BELOW | +1.391 |
orrect | +1.330 |
trial | +1.264 |
JUST | +1.254 |
Neg logit contributions | |
IA | -1.724 |
Ashes | -1.721 |
Rosenberg | -1.688 |
cca | -1.601 |
cko | -1.595 |
Token | } |
Token ID | 1782 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
phalt | +1.917 |
BELOW | +1.874 |
orrect | +1.787 |
trial | +1.707 |
JUST | +1.693 |
Neg logit contributions | |
IA | -2.220 |
Ashes | -2.217 |
Rosenberg | -2.170 |
cca | -2.062 |
cko | -2.056 |
Token | pub |
Token ID | 2240 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
phalt | +2.450 |
BELOW | +2.375 |
orrect | +2.250 |
JUST | +2.144 |
trial | +2.129 |
Neg logit contributions | |
IA | -3.268 |
Ashes | -3.254 |
Rosenberg | -3.192 |
cca | -3.056 |
cko | -3.052 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
phalt | +1.210 |
BELOW | +1.144 |
orrect | +1.046 |
JUST | +0.919 |
trial | +0.914 |
Neg logit contributions | |
IA | -4.216 |
Ashes | -4.213 |
Rosenberg | -4.161 |
cca | -4.024 |
cko | -3.995 |
Token | undo |
Token ID | 23981 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
BELOW | +4.406 |
phalt | +4.326 |
orrect | +4.202 |
� | +3.964 |
orem | +3.928 |
Neg logit contributions | |
IA | -4.745 |
Ashes | -4.649 |
Rosenberg | -4.539 |
cca | -4.418 |
cko | -4.410 |
Token | _ |
Token ID | 62 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
phalt | +0.237 |
BELOW | +0.231 |
orrect | +0.222 |
trial | +0.212 |
JUST | +0.211 |
Neg logit contributions | |
Ashes | -0.226 |
IA | -0.226 |
Rosenberg | -0.221 |
cca | -0.208 |
cko | -0.207 |
Token | move |
Token ID | 21084 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
phalt | +0.422 |
BELOW | +0.410 |
orrect | +0.394 |
trial | +0.375 |
JUST | +0.373 |
Neg logit contributions | |
IA | -0.438 |
Ashes | -0.437 |
Rosenberg | -0.429 |
cca | -0.405 |
cko | -0.404 |
Token | ( |
Token ID | 357 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
phalt | +0.457 |
BELOW | +0.445 |
orrect | +0.430 |
trial | +0.411 |
JUST | +0.407 |
Neg logit contributions | |
Ashes | -0.489 |
IA | -0.488 |
Rosenberg | -0.479 |
cca | -0.451 |
cko | -0.449 |
Token | & |
Token ID | 1222 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Ashes | +0.446 |
IA | +0.445 |
Rosenberg | +0.437 |
cca | +0.415 |
cko | +0.413 |
Neg logit contributions | |
phalt | -0.329 |
BELOW | -0.319 |
orrect | -0.305 |
trial | -0.288 |
JUST | -0.286 |
Token |
|
Token ID | 198 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
phalt | +0.009 |
BELOW | +0.009 |
orrect | +0.009 |
trial | +0.008 |
conduc | +0.008 |
Neg logit contributions | |
IA | -0.011 |
Ashes | -0.011 |
Rosenberg | -0.011 |
cca | -0.010 |
cko | -0.010 |
Token | impl |
Token ID | 23928 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
IA | +0.131 |
Ashes | +0.130 |
Rosenberg | +0.127 |
cca | +0.121 |
cko | +0.120 |
Neg logit contributions | |
phalt | -0.103 |
BELOW | -0.100 |
orrect | -0.096 |
trial | -0.090 |
conduc | -0.090 |
Token | Board |
Token ID | 5926 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
phalt | +1.170 |
BELOW | +1.131 |
orrect | +1.075 |
trial | +0.982 |
JUST | +0.970 |
Neg logit contributions | |
IA | -2.360 |
Ashes | -2.356 |
Rosenberg | -2.326 |
cca | -2.230 |
cko | -2.224 |
Token | { |
Token ID | 1391 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
Ashes | +0.236 |
IA | +0.236 |
Rosenberg | +0.231 |
cca | +0.218 |
cko | +0.217 |
Neg logit contributions | |
phalt | -0.221 |
BELOW | -0.215 |
orrect | -0.207 |
trial | -0.197 |
JUST | -0.196 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
phalt | +0.448 |
BELOW | +0.432 |
orrect | +0.412 |
trial | +0.387 |
JUST | +0.383 |
Neg logit contributions | |
Ashes | -0.695 |
IA | -0.694 |
Rosenberg | -0.683 |
cca | -0.649 |
cko | -0.646 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
phalt | +0.512 |
BELOW | +0.487 |
orrect | +0.453 |
trial | +0.413 |
JUST | +0.406 |
Neg logit contributions | |
Ashes | -1.372 |
IA | -1.371 |
Rosenberg | -1.352 |
cca | -1.298 |
cko | -1.294 |
Token | copy |
Token ID | 4866 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
BELOW | +3.688 |
phalt | +3.631 |
orrect | +3.496 |
� | +3.238 |
orem | +3.230 |
Neg logit contributions | |
IA | -5.437 |
Ashes | -5.331 |
Rosenberg | -5.306 |
cca | -5.107 |
cko | -5.083 |
Token | _ |
Token ID | 62 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
phalt | +0.126 |
BELOW | +0.122 |
orrect | +0.117 |
trial | +0.111 |
JUST | +0.110 |
Neg logit contributions | |
Ashes | -0.155 |
IA | -0.155 |
Rosenberg | -0.152 |
cca | -0.144 |
cko | -0.143 |
Token | board |
Token ID | 3526 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
IA | +0.546 |
Ashes | +0.544 |
Rosenberg | +0.533 |
cca | +0.505 |
cko | +0.503 |
Neg logit contributions | |
phalt | -0.515 |
BELOW | -0.501 |
orrect | -0.479 |
trial | -0.455 |
JUST | -0.455 |
Token | ( |
Token ID | 357 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Ashes | +0.472 |
IA | +0.472 |
Rosenberg | +0.462 |
cca | +0.436 |
cko | +0.434 |
Neg logit contributions | |
phalt | -0.435 |
BELOW | -0.423 |
orrect | -0.406 |
trial | -0.387 |
JUST | -0.384 |
Token | & |
Token ID | 1222 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
IA | +0.719 |
Ashes | +0.718 |
Rosenberg | +0.704 |
cca | +0.668 |
cko | +0.666 |
Neg logit contributions | |
phalt | -0.573 |
BELOW | -0.556 |
orrect | -0.529 |
trial | -0.499 |
JUST | -0.498 |
Token | last |
Token ID | 938 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Ashes | +0.624 |
IA | +0.621 |
Rosenberg | +0.606 |
cca | +0.559 |
cko | +0.554 |
Neg logit contributions | |
phalt | -0.964 |
BELOW | -0.939 |
orrect | -0.909 |
trial | -0.878 |
JUST | -0.875 |
Token | sights |
Token ID | 21343 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
IA | +1.374 |
Ashes | +1.374 |
Rosenberg | +1.347 |
cca | +1.262 |
vre | +1.252 |
Neg logit contributions | |
phalt | -1.230 |
BELOW | -1.192 |
orrect | -1.141 |
JUST | -1.090 |
trial | -1.088 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Ashes | +0.520 |
IA | +0.519 |
Rosenberg | +0.509 |
cca | +0.479 |
cko | +0.475 |
Neg logit contributions | |
phalt | -0.489 |
BELOW | -0.473 |
orrect | -0.457 |
trial | -0.434 |
JUST | -0.433 |
Token | this |
Token ID | 428 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Ashes | +0.921 |
IA | +0.916 |
Rosenberg | +0.900 |
cca | +0.850 |
cko | +0.839 |
Neg logit contributions | |
phalt | -0.800 |
BELOW | -0.776 |
orrect | -0.746 |
trial | -0.708 |
JUST | -0.704 |
Token | indef |
Token ID | 16536 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Ashes | +0.234 |
IA | +0.233 |
Rosenberg | +0.228 |
cca | +0.215 |
cko | +0.213 |
Neg logit contributions | |
phalt | -0.224 |
BELOW | -0.218 |
orrect | -0.209 |
trial | -0.200 |
JUST | -0.198 |
Token | at |
Token ID | 265 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
phalt | +0.458 |
BELOW | +0.446 |
orrect | +0.430 |
trial | +0.411 |
JUST | +0.408 |
Neg logit contributions | |
Ashes | -0.438 |
IA | -0.438 |
Rosenberg | -0.429 |
cca | -0.403 |
cko | -0.401 |
Token | ig |
Token ID | 328 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
phalt | +3.611 |
BELOW | +3.508 |
orrect | +3.303 |
trial | +3.228 |
orem | +3.224 |
Neg logit contributions | |
Ashes | -5.310 |
Rosenberg | -5.233 |
IA | -5.223 |
toe | -4.967 |
ゼウス | -4.955 |
Token | able |
Token ID | 540 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
IA | +0.402 |
Ashes | +0.401 |
Rosenberg | +0.391 |
cca | +0.374 |
cko | +0.372 |
Neg logit contributions | |
phalt | -0.274 |
BELOW | -0.266 |
orrect | -0.252 |
JUST | -0.236 |
trial | -0.236 |
Token | optim |
Token ID | 6436 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
phalt | +1.181 |
BELOW | +1.150 |
orrect | +1.103 |
trial | +1.049 |
JUST | +1.039 |
Neg logit contributions | |
IA | -1.329 |
Ashes | -1.326 |
Rosenberg | -1.302 |
cca | -1.230 |
cko | -1.230 |
Token | ist |
Token ID | 396 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
phalt | +0.955 |
BELOW | +0.932 |
orrect | +0.905 |
trial | +0.861 |
� | +0.851 |
Neg logit contributions | |
Ashes | -0.891 |
IA | -0.876 |
Rosenberg | -0.862 |
cko | -0.800 |
cca | -0.799 |
Token | is |
Token ID | 318 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
phalt | +1.538 |
BELOW | +1.501 |
orrect | +1.437 |
� | +1.371 |
trial | +1.370 |
Neg logit contributions | |
Ashes | -1.739 |
IA | -1.734 |
Rosenberg | -1.703 |
cko | -1.616 |
cca | -1.607 |
Token | wrap |
Token ID | 37150 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
phalt | +0.699 |
BELOW | +0.678 |
orrect | +0.651 |
trial | +0.618 |
JUST | +0.612 |
Neg logit contributions | |
Ashes | -0.855 |
IA | -0.853 |
Rosenberg | -0.838 |
cca | -0.793 |
cko | -0.789 |
Token | ()) |
Token ID | 32865 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
phalt | +0.099 |
BELOW | +0.096 |
orrect | +0.093 |
trial | +0.088 |
JUST | +0.088 |
Neg logit contributions | |
Ashes | -0.109 |
IA | -0.108 |
Rosenberg | -0.106 |
cca | -0.100 |
cko | -0.100 |
Token | } |
Token ID | 1782 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
phalt | +1.481 |
BELOW | +1.456 |
orrect | +1.391 |
JUST | +1.329 |
trial | +1.324 |
Neg logit contributions | |
Ashes | -1.810 |
IA | -1.807 |
Rosenberg | -1.776 |
cko | -1.681 |
cca | -1.678 |
Token | } |
Token ID | 1782 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
phalt | +2.139 |
BELOW | +2.092 |
orrect | +1.976 |
trial | +1.894 |
JUST | +1.886 |
Neg logit contributions | |
IA | -2.627 |
Ashes | -2.603 |
Rosenberg | -2.554 |
cca | -2.455 |
cko | -2.452 |
Token | pub |
Token ID | 2240 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
phalt | +2.028 |
BELOW | +1.969 |
orrect | +1.868 |
JUST | +1.777 |
trial | +1.775 |
Neg logit contributions | |
IA | -2.637 |
Ashes | -2.631 |
Rosenberg | -2.580 |
cca | -2.468 |
cko | -2.462 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
phalt | +1.161 |
BELOW | +1.103 |
orrect | +1.017 |
trial | +0.906 |
JUST | +0.899 |
Neg logit contributions | |
IA | -3.495 |
Ashes | -3.493 |
Rosenberg | -3.449 |
cca | -3.327 |
cko | -3.308 |
Token | apply |
Token ID | 4174 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
BELOW | +4.220 |
phalt | +4.170 |
orrect | +4.031 |
� | +3.785 |
orem | +3.770 |
Neg logit contributions | |
IA | -4.749 |
Ashes | -4.641 |
Rosenberg | -4.547 |
cca | -4.402 |
cko | -4.371 |
Token | _ |
Token ID | 62 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
phalt | +0.693 |
BELOW | +0.675 |
orrect | +0.651 |
trial | +0.623 |
JUST | +0.617 |
Neg logit contributions | |
Ashes | -0.684 |
IA | -0.682 |
Rosenberg | -0.670 |
cca | -0.629 |
cko | -0.626 |
Token | move |
Token ID | 21084 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
phalt | +0.788 |
BELOW | +0.764 |
orrect | +0.738 |
trial | +0.708 |
JUST | +0.696 |
Neg logit contributions | |
Ashes | -0.872 |
IA | -0.869 |
Rosenberg | -0.855 |
cca | -0.803 |
cko | -0.798 |
Token | ( |
Token ID | 357 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
phalt | +0.300 |
BELOW | +0.291 |
orrect | +0.281 |
trial | +0.268 |
JUST | +0.266 |
Neg logit contributions | |
Ashes | -0.306 |
IA | -0.306 |
Rosenberg | -0.300 |
cca | -0.282 |
cko | -0.281 |
Token | & |
Token ID | 1222 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Ashes | +0.243 |
IA | +0.242 |
Rosenberg | +0.238 |
cca | +0.226 |
cko | +0.225 |
Neg logit contributions | |
phalt | -0.182 |
BELOW | -0.177 |
orrect | -0.168 |
trial | -0.159 |
JUST | -0.158 |
Token | < |
Token ID | 1279 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
phalt | +0.663 |
BELOW | +0.637 |
orrect | +0.604 |
trial | +0.558 |
JUST | +0.557 |
Neg logit contributions | |
Ashes | -1.342 |
IA | -1.336 |
Rosenberg | -1.319 |
cca | -1.263 |
cko | -1.260 |
Token | T |
Token ID | 309 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
phalt | +0.032 |
BELOW | +0.031 |
orrect | +0.030 |
trial | +0.029 |
JUST | +0.029 |
Neg logit contributions | |
Ashes | -0.030 |
IA | -0.029 |
Rosenberg | -0.029 |
cko | -0.027 |
cca | -0.027 |
Token | > |
Token ID | 1875 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
IA | +0.642 |
Ashes | +0.640 |
Rosenberg | +0.630 |
cca | +0.597 |
cko | +0.596 |
Neg logit contributions | |
phalt | -0.445 |
BELOW | -0.427 |
orrect | -0.410 |
trial | -0.388 |
JUST | -0.378 |
Token | { |
Token ID | 1391 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
phalt | +1.240 |
BELOW | +1.213 |
orrect | +1.168 |
JUST | +1.106 |
trial | +1.103 |
Neg logit contributions | |
Ashes | -1.321 |
IA | -1.321 |
Rosenberg | -1.290 |
cca | -1.225 |
cko | -1.218 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Ashes | +0.958 |
IA | +0.956 |
Rosenberg | +0.943 |
cca | +0.898 |
cko | +0.891 |
Neg logit contributions | |
phalt | -0.568 |
BELOW | -0.545 |
orrect | -0.519 |
trial | -0.487 |
JUST | -0.477 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
phalt | +0.751 |
BELOW | +0.721 |
orrect | +0.676 |
trial | +0.619 |
JUST | +0.614 |
Neg logit contributions | |
IA | -1.759 |
Ashes | -1.757 |
Rosenberg | -1.731 |
cca | -1.662 |
cko | -1.655 |
Token | new |
Token ID | 649 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
BELOW | +4.166 |
phalt | +4.155 |
orrect | +3.976 |
� | +3.742 |
trial | +3.714 |
Neg logit contributions | |
IA | -4.736 |
Ashes | -4.610 |
Rosenberg | -4.536 |
cca | -4.370 |
cko | -4.359 |
Token | ( |
Token ID | 357 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
Ashes | +0.057 |
IA | +0.057 |
Rosenberg | +0.056 |
cca | +0.053 |
cko | +0.053 |
Neg logit contributions | |
phalt | -0.046 |
BELOW | -0.045 |
orrect | -0.043 |
trial | -0.041 |
JUST | -0.040 |
Token | t |
Token ID | 256 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
phalt | +0.045 |
BELOW | +0.043 |
orrect | +0.041 |
trial | +0.039 |
JUST | +0.039 |
Neg logit contributions | |
Ashes | -0.058 |
IA | -0.058 |
Rosenberg | -0.057 |
cca | -0.054 |
cko | -0.054 |
Token | : |
Token ID | 1058 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Ashes | +1.874 |
IA | +1.873 |
Rosenberg | +1.841 |
cca | +1.758 |
cko | +1.750 |
Neg logit contributions | |
phalt | -1.163 |
BELOW | -1.107 |
orrect | -1.053 |
trial | -0.987 |
JUST | -0.979 |
Token | T |
Token ID | 309 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
phalt | +0.435 |
BELOW | +0.423 |
orrect | +0.407 |
trial | +0.388 |
JUST | +0.385 |
Neg logit contributions | |
Ashes | -0.463 |
IA | -0.463 |
Rosenberg | -0.454 |
cca | -0.428 |
cko | -0.426 |
Token | K |
Token ID | 42 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Ashes | +0.002 |
IA | +0.002 |
Rosenberg | +0.002 |
cca | +0.002 |
cko | +0.002 |
Neg logit contributions | |
phalt | -0.003 |
BELOW | -0.003 |
orrect | -0.003 |
trial | -0.002 |
JUST | -0.002 |
Token | ier |
Token ID | 959 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
IA | +0.590 |
Ashes | +0.585 |
Rosenberg | +0.574 |
cca | +0.543 |
cko | +0.541 |
Neg logit contributions | |
phalt | -0.573 |
BELOW | -0.561 |
orrect | -0.535 |
trial | -0.513 |
JUST | -0.507 |
Token | an |
Token ID | 272 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Ashes | +0.629 |
IA | +0.628 |
Rosenberg | +0.615 |
cca | +0.575 |
cko | +0.573 |
Neg logit contributions | |
phalt | -0.725 |
BELOW | -0.707 |
orrect | -0.682 |
trial | -0.654 |
JUST | -0.649 |
Token | Profile |
Token ID | 13118 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Ashes | +0.340 |
IA | +0.339 |
Rosenberg | +0.333 |
cca | +0.314 |
cko | +0.313 |
Neg logit contributions | |
phalt | -0.316 |
BELOW | -0.307 |
orrect | -0.295 |
trial | -0.281 |
JUST | -0.279 |
Token | Blog |
Token ID | 14001 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
phalt | +0.397 |
BELOW | +0.382 |
orrect | +0.362 |
trial | +0.337 |
JUST | +0.335 |
Neg logit contributions | |
IA | -0.699 |
Ashes | -0.698 |
Rosenberg | -0.690 |
cca | -0.658 |
cko | -0.656 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
phalt | +1.046 |
BELOW | +1.018 |
orrect | +0.976 |
trial | +0.927 |
JUST | +0.920 |
Neg logit contributions | |
IA | -1.225 |
Ashes | -1.225 |
Rosenberg | -1.203 |
cca | -1.136 |
cko | -1.133 |
Token | August |
Token ID | 2932 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
phalt | +3.014 |
BELOW | +2.986 |
orrect | +2.739 |
JUST | +2.595 |
� | +2.553 |
Neg logit contributions | |
IA | -5.729 |
Ashes | -5.615 |
Rosenberg | -5.569 |
vre | -5.484 |
ゼウス | -5.445 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
phalt | +0.741 |
BELOW | +0.712 |
orrect | +0.683 |
trial | +0.646 |
JUST | +0.638 |
Neg logit contributions | |
Ashes | -1.048 |
IA | -1.045 |
Rosenberg | -1.028 |
cca | -0.971 |
cko | -0.966 |
Token | United |
Token ID | 1578 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
phalt | +1.747 |
BELOW | +1.720 |
orrect | +1.646 |
trial | +1.569 |
JUST | +1.563 |
Neg logit contributions | |
IA | -1.753 |
Ashes | -1.748 |
Rosenberg | -1.714 |
cko | -1.624 |
cca | -1.624 |
Token | States |
Token ID | 1829 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
phalt | +0.105 |
BELOW | +0.102 |
orrect | +0.098 |
trial | +0.092 |
JUST | +0.091 |
Neg logit contributions | |
Ashes | -0.150 |
IA | -0.150 |
Rosenberg | -0.148 |
cca | -0.141 |
cko | -0.140 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
phalt | +0.328 |
BELOW | +0.320 |
orrect | +0.307 |
trial | +0.293 |
JUST | +0.291 |
Neg logit contributions | |
Ashes | -0.334 |
IA | -0.334 |
Rosenberg | -0.327 |
cca | -0.308 |
cko | -0.307 |
Token | ada |
Token ID | 4763 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
phalt | +0.133 |
BELOW | +0.129 |
orrect | +0.124 |
trial | +0.119 |
JUST | +0.118 |
Neg logit contributions | |
IA | -0.132 |
Ashes | -0.131 |
Rosenberg | -0.128 |
cca | -0.121 |
cko | -0.120 |
Token | ver |
Token ID | 332 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
IA | +1.358 |
Ashes | +1.345 |
Rosenberg | +1.318 |
cca | +1.239 |
cko | +1.231 |
Neg logit contributions | |
phalt | -1.439 |
BELOW | -1.402 |
orrect | -1.345 |
trial | -1.294 |
JUST | -1.280 |
Token | BB |
Token ID | 15199 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
IA | +1.685 |
Ashes | +1.670 |
Rosenberg | +1.631 |
cca | +1.540 |
cko | +1.533 |
Neg logit contributions | |
phalt | -1.694 |
BELOW | -1.646 |
orrect | -1.586 |
trial | -1.516 |
JUST | -1.503 |
Token | Profile |
Token ID | 13118 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
IA | +0.857 |
Ashes | +0.855 |
Rosenberg | +0.836 |
cca | +0.787 |
cko | +0.783 |
Neg logit contributions | |
phalt | -0.910 |
BELOW | -0.884 |
orrect | -0.852 |
trial | -0.816 |
JUST | -0.807 |
Token | Blog |
Token ID | 14001 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
phalt | +0.519 |
BELOW | +0.501 |
orrect | +0.475 |
trial | +0.443 |
JUST | +0.441 |
Neg logit contributions | |
Ashes | -0.871 |
IA | -0.871 |
Rosenberg | -0.858 |
cca | -0.818 |
cko | -0.815 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
phalt | +1.167 |
BELOW | +1.138 |
orrect | +1.089 |
trial | +1.034 |
JUST | +1.027 |
Neg logit contributions | |
IA | -1.387 |
Ashes | -1.385 |
Rosenberg | -1.363 |
cca | -1.288 |
cko | -1.284 |
Token | June |
Token ID | 2795 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
phalt | +2.964 |
BELOW | +2.954 |
orrect | +2.705 |
JUST | +2.560 |
� | +2.516 |
Neg logit contributions | |
IA | -5.660 |
Ashes | -5.550 |
Rosenberg | -5.505 |
vre | -5.412 |
ゼウス | -5.372 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
phalt | +0.888 |
BELOW | +0.856 |
orrect | +0.820 |
trial | +0.775 |
JUST | +0.765 |
Neg logit contributions | |
Ashes | -1.260 |
IA | -1.257 |
Rosenberg | -1.237 |
cca | -1.172 |
cko | -1.167 |
Token | Germany |
Token ID | 4486 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
phalt | +1.675 |
BELOW | +1.646 |
orrect | +1.575 |
trial | +1.499 |
JUST | +1.495 |
Neg logit contributions | |
IA | -1.735 |
Ashes | -1.733 |
Rosenberg | -1.699 |
cca | -1.610 |
cko | -1.609 |
Token | 247 |
Token ID | 30179 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
Ashes | +0.380 |
IA | +0.379 |
Rosenberg | +0.372 |
cca | +0.348 |
cko | +0.346 |
Neg logit contributions | |
phalt | -0.380 |
BELOW | -0.366 |
orrect | -0.355 |
trial | -0.339 |
conduc | -0.334 |
Token | 34 |
Token ID | 2682 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
phalt | +0.008 |
BELOW | +0.008 |
orrect | +0.008 |
trial | +0.007 |
conduc | +0.007 |
Neg logit contributions | |
Ashes | -0.013 |
IA | -0.013 |
Rosenberg | -0.012 |
cca | -0.012 |
cko | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
phalt | +0.215 |
BELOW | +0.208 |
orrect | +0.200 |
trial | +0.189 |
JUST | +0.188 |
Neg logit contributions | |
Ashes | -0.259 |
IA | -0.259 |
Rosenberg | -0.254 |
cca | -0.241 |
cko | -0.240 |
Token | Big |
Token ID | 12804 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
phalt | +0.167 |
BELOW | +0.163 |
orrect | +0.158 |
trial | +0.151 |
JUST | +0.150 |
Neg logit contributions | |
Ashes | -0.135 |
IA | -0.135 |
Rosenberg | -0.132 |
cca | -0.123 |
cko | -0.123 |
Token | Fan |
Token ID | 22480 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Ashes | +1.250 |
IA | +1.244 |
Rosenberg | +1.216 |
cca | +1.139 |
cko | +1.128 |
Neg logit contributions | |
phalt | -1.486 |
BELOW | -1.450 |
orrect | -1.401 |
trial | -1.339 |
JUST | -1.331 |
Token | Profile |
Token ID | 13118 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Ashes | +0.512 |
IA | +0.511 |
Rosenberg | +0.501 |
cca | +0.470 |
cko | +0.468 |
Neg logit contributions | |
phalt | -0.542 |
BELOW | -0.528 |
orrect | -0.509 |
trial | -0.486 |
JUST | -0.483 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
phalt | +0.607 |
BELOW | +0.585 |
orrect | +0.557 |
trial | +0.520 |
JUST | +0.519 |
Neg logit contributions | |
IA | -0.975 |
Ashes | -0.974 |
Rosenberg | -0.961 |
cca | -0.915 |
cko | -0.912 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
phalt | +0.474 |
BELOW | +0.459 |
orrect | +0.441 |
trial | +0.421 |
JUST | +0.417 |
Neg logit contributions | |
Ashes | -0.527 |
IA | -0.524 |
Rosenberg | -0.514 |
cca | -0.485 |
cko | -0.483 |
Token | December |
Token ID | 3426 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
phalt | +2.971 |
BELOW | +2.948 |
orrect | +2.705 |
JUST | +2.568 |
� | +2.532 |
Neg logit contributions | |
IA | -5.544 |
Ashes | -5.450 |
Rosenberg | -5.406 |
vre | -5.304 |
cko | -5.261 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
phalt | +0.669 |
BELOW | +0.645 |
orrect | +0.617 |
trial | +0.583 |
JUST | +0.576 |
Neg logit contributions | |
Ashes | -0.967 |
IA | -0.965 |
Rosenberg | -0.949 |
cca | -0.900 |
cko | -0.897 |
Token | TL |
Token ID | 24811 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
phalt | +1.727 |
BELOW | +1.700 |
orrect | +1.628 |
trial | +1.549 |
JUST | +1.545 |
Neg logit contributions | |
IA | -1.768 |
Ashes | -1.764 |
Rosenberg | -1.729 |
cca | -1.645 |
cko | -1.642 |
Token | AD |
Token ID | 2885 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
phalt | +0.619 |
BELOW | +0.599 |
orrect | +0.579 |
trial | +0.554 |
JUST | +0.549 |
Neg logit contributions | |
Ashes | -0.568 |
IA | -0.568 |
Rosenberg | -0.555 |
cca | -0.519 |
cko | -0.516 |
Token | T |
Token ID | 51 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
phalt | +0.765 |
BELOW | +0.751 |
orrect | +0.723 |
trial | +0.699 |
JUST | +0.698 |
Neg logit contributions | |
Ashes | -0.563 |
IA | -0.558 |
Rosenberg | -0.552 |
cca | -0.513 |
cko | -0.513 |
Token | J |
Token ID | 41 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
IA | +0.796 |
Ashes | +0.793 |
Rosenberg | +0.773 |
cca | +0.725 |
cko | +0.721 |
Neg logit contributions | |
phalt | -0.988 |
BELOW | -0.966 |
orrect | -0.932 |
trial | -0.892 |
JUST | -0.885 |
Token | aaaa |
Token ID | 24794 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
phalt | +0.069 |
BELOW | +0.067 |
orrect | +0.065 |
trial | +0.062 |
JUST | +0.062 |
Neg logit contributions | |
Ashes | -0.060 |
IA | -0.060 |
Rosenberg | -0.059 |
cca | -0.055 |
cko | -0.055 |
Token | asper |
Token ID | 32981 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
IA | +0.489 |
Ashes | +0.488 |
Rosenberg | +0.476 |
cca | +0.448 |
cko | +0.446 |
Neg logit contributions | |
phalt | -0.538 |
BELOW | -0.524 |
orrect | -0.505 |
trial | -0.483 |
JUST | -0.481 |
Token | Profile |
Token ID | 13118 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Ashes | +0.638 |
IA | +0.637 |
Rosenberg | +0.624 |
cca | +0.588 |
cko | +0.586 |
Neg logit contributions | |
phalt | -0.609 |
BELOW | -0.593 |
orrect | -0.570 |
trial | -0.544 |
JUST | -0.539 |
Token | Blog |
Token ID | 14001 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
phalt | +0.547 |
BELOW | +0.529 |
orrect | +0.505 |
trial | +0.474 |
JUST | +0.472 |
Neg logit contributions | |
IA | -0.805 |
Ashes | -0.804 |
Rosenberg | -0.793 |
cca | -0.753 |
cko | -0.751 |
Token | Joined |
Token ID | 16709 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
phalt | +1.253 |
BELOW | +1.218 |
orrect | +1.169 |
trial | +1.111 |
JUST | +1.103 |
Neg logit contributions | |
Ashes | -1.453 |
IA | -1.453 |
Rosenberg | -1.426 |
cca | -1.347 |
cko | -1.342 |
Token | April |
Token ID | 3035 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
phalt | +2.953 |
BELOW | +2.931 |
orrect | +2.697 |
JUST | +2.566 |
� | +2.520 |
Neg logit contributions | |
IA | -5.465 |
Ashes | -5.371 |
Rosenberg | -5.338 |
vre | -5.223 |
ゼウス | -5.179 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
phalt | +0.324 |
BELOW | +0.311 |
orrect | +0.299 |
trial | +0.284 |
conduc | +0.282 |
Neg logit contributions | |
Ashes | -0.439 |
IA | -0.437 |
Rosenberg | -0.430 |
cca | -0.406 |
cko | -0.403 |
Token | United |
Token ID | 1578 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
phalt | +1.523 |
BELOW | +1.496 |
orrect | +1.430 |
trial | +1.361 |
JUST | +1.358 |
Neg logit contributions | |
IA | -1.564 |
Ashes | -1.561 |
Rosenberg | -1.528 |
cca | -1.447 |
cko | -1.446 |
Token | States |
Token ID | 1829 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
phalt | +0.184 |
BELOW | +0.178 |
orrect | +0.171 |
trial | +0.160 |
JUST | +0.159 |
Neg logit contributions | |
Ashes | -0.270 |
IA | -0.270 |
Rosenberg | -0.266 |
cca | -0.255 |
cko | -0.253 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
phalt | +0.473 |
BELOW | +0.461 |
orrect | +0.443 |
trial | +0.423 |
JUST | +0.420 |
Neg logit contributions | |
Ashes | -0.484 |
IA | -0.483 |
Rosenberg | -0.473 |
cca | -0.446 |
cko | -0.444 |
Token | name |
Token ID | 1438 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
Ashes | +0.029 |
IA | +0.029 |
Rosenberg | +0.029 |
cca | +0.027 |
cko | +0.027 |
Neg logit contributions | |
phalt | -0.029 |
BELOW | -0.028 |
orrect | -0.027 |
trial | -0.026 |
JUST | -0.026 |
Token | is |
Token ID | 318 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Ashes | +0.477 |
IA | +0.477 |
Rosenberg | +0.467 |
cca | +0.439 |
cko | +0.435 |
Neg logit contributions | |
phalt | -0.502 |
BELOW | -0.487 |
orrect | -0.471 |
trial | -0.451 |
JUST | -0.447 |
Token | still |
Token ID | 991 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
phalt | +0.198 |
BELOW | +0.194 |
orrect | +0.186 |
trial | +0.178 |
JUST | +0.176 |
Neg logit contributions | |
Ashes | -0.195 |
IA | -0.195 |
Rosenberg | -0.191 |
cca | -0.179 |
cko | -0.179 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Ashes | +0.065 |
IA | +0.065 |
Rosenberg | +0.064 |
cca | +0.060 |
cko | +0.060 |
Neg logit contributions | |
phalt | -0.059 |
BELOW | -0.057 |
orrect | -0.055 |
trial | -0.052 |
JUST | -0.052 |
Token | polit |
Token ID | 1408 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Ashes | +0.093 |
IA | +0.093 |
Rosenberg | +0.091 |
cca | +0.086 |
cko | +0.086 |
Neg logit contributions | |
phalt | -0.086 |
BELOW | -0.084 |
orrect | -0.080 |
trial | -0.077 |
JUST | -0.076 |
Token | |
Token ID | 3907 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
IA | +0.342 |
Ashes | +0.342 |
Rosenberg | +0.335 |
cca | +0.318 |
cko | +0.317 |
Neg logit contributions | |
phalt | -0.284 |
BELOW | -0.276 |
orrect | -0.264 |
trial | -0.251 |
JUST | -0.249 |
Token | ic |
Token ID | 291 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
phalt | +4.367 |
BELOW | +4.190 |
orrect | +4.141 |
trial | +3.948 |
orem | +3.891 |
Neg logit contributions | |
Ashes | -4.032 |
Rosenberg | -3.967 |
IA | -3.872 |
ゼウス | -3.635 |
Unicorn | -3.627 |
Token | |
Token ID | 3907 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
phalt | +0.742 |
BELOW | +0.720 |
orrect | +0.691 |
trial | +0.653 |
JUST | +0.645 |
Neg logit contributions | |
Ashes | -0.959 |
IA | -0.955 |
Rosenberg | -0.942 |
cca | -0.888 |
cko | -0.887 |
Token | al |
Token ID | 282 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
phalt | +2.777 |
BELOW | +2.712 |
orrect | +2.686 |
trial | +2.516 |
orem | +2.477 |
Neg logit contributions | |
Ashes | -3.008 |
Rosenberg | -2.943 |
IA | -2.910 |
Unicorn | -2.728 |
ゼウス | -2.717 |
Token | in |
Token ID | 287 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
phalt | +0.144 |
BELOW | +0.140 |
orrect | +0.135 |
trial | +0.128 |
JUST | +0.127 |
Neg logit contributions | |
Ashes | -0.162 |
IA | -0.161 |
Rosenberg | -0.159 |
cca | -0.150 |
cko | -0.149 |
Token | |
Token ID | 3907 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Ashes | +0.141 |
IA | +0.141 |
Rosenberg | +0.138 |
cca | +0.131 |
cko | +0.130 |
Neg logit contributions | |
phalt | -0.116 |
BELOW | -0.112 |
orrect | -0.108 |
trial | -0.102 |
JUST | -0.101 |
Token | TB |
Token ID | 22737 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Ashes | +0.124 |
IA | +0.124 |
Rosenberg | +0.121 |
cca | +0.113 |
cko | +0.112 |
Neg logit contributions | |
phalt | -0.157 |
BELOW | -0.153 |
orrect | -0.148 |
trial | -0.142 |
JUST | -0.141 |
Token | one |
Token ID | 505 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
IA | +1.921 |
Ashes | +1.901 |
Rosenberg | +1.863 |
cca | +1.745 |
cko | +1.741 |
Neg logit contributions | |
phalt | -2.175 |
BELOW | -2.127 |
orrect | -2.037 |
trial | -1.960 |
JUST | -1.931 |
Token | - |
Token ID | 12 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
IA | +1.712 |
Ashes | +1.697 |
Rosenberg | +1.658 |
cko | +1.570 |
cca | +1.564 |
Neg logit contributions | |
phalt | -1.918 |
BELOW | -1.875 |
orrect | -1.801 |
trial | -1.719 |
conduc | -1.705 |
Token | Profile |
Token ID | 13118 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
IA | +1.325 |
Ashes | +1.312 |
Rosenberg | +1.282 |
cca | +1.203 |
cko | +1.197 |
Neg logit contributions | |
phalt | -1.621 |
BELOW | -1.588 |
orrect | -1.528 |
trial | -1.462 |
JUST | -1.449 |
Token | Blog |
Token ID | 14001 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Ashes | +1.014 |
IA | +1.011 |
Rosenberg | +0.993 |
cca | +0.945 |
cko | +0.941 |
Neg logit contributions | |
phalt | -0.661 |
BELOW | -0.640 |
orrect | -0.609 |
trial | -0.575 |
JUST | -0.567 |
Token | Joined |
Token ID | 16709 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
phalt | +0.472 |
BELOW | +0.458 |
orrect | +0.440 |
trial | +0.420 |
JUST | +0.416 |
Neg logit contributions | |
Ashes | -0.528 |
IA | -0.526 |
Rosenberg | -0.516 |
cca | -0.487 |
cko | -0.485 |
Token | November |
Token ID | 3389 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
phalt | +2.851 |
BELOW | +2.820 |
orrect | +2.601 |
JUST | +2.466 |
� | +2.424 |
Neg logit contributions | |
IA | -5.287 |
Ashes | -5.199 |
Rosenberg | -5.161 |
vre | -5.046 |
ゼウス | -5.006 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
phalt | +0.584 |
BELOW | +0.561 |
orrect | +0.538 |
trial | +0.509 |
JUST | +0.502 |
Neg logit contributions | |
Ashes | -0.828 |
IA | -0.825 |
Rosenberg | -0.812 |
cca | -0.768 |
cko | -0.764 |
Token | United |
Token ID | 1578 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
phalt | +0.855 |
BELOW | +0.837 |
orrect | +0.804 |
trial | +0.767 |
JUST | +0.763 |
Neg logit contributions | |
IA | -0.854 |
Ashes | -0.853 |
Rosenberg | -0.835 |
cca | -0.790 |
cko | -0.788 |
Token | States |
Token ID | 1829 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Ashes | +0.126 |
IA | +0.126 |
Rosenberg | +0.124 |
cca | +0.118 |
cko | +0.117 |
Neg logit contributions | |
phalt | -0.088 |
BELOW | -0.085 |
orrect | -0.082 |
trial | -0.077 |
JUST | -0.076 |
Token | 21 |
Token ID | 2310 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
phalt | +0.071 |
BELOW | +0.069 |
orrect | +0.066 |
trial | +0.063 |
JUST | +0.063 |
Neg logit contributions | |
Ashes | -0.072 |
IA | -0.072 |
Rosenberg | -0.070 |
cca | -0.066 |
cko | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
phalt | +1.555 |
BELOW | +1.534 |
orrect | +1.445 |
� | +1.365 |
trial | +1.363 |
Neg logit contributions | |
Ashes | -2.414 |
IA | -2.396 |
Rosenberg | -2.363 |
cca | -2.257 |
cko | -2.255 |
Token | this |
Token ID | 428 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
phalt | +0.897 |
BELOW | +0.872 |
orrect | +0.836 |
trial | +0.794 |
JUST | +0.788 |
Neg logit contributions | |
Ashes | -1.055 |
IA | -1.054 |
Rosenberg | -1.034 |
cca | -0.978 |
cko | -0.976 |
Token | will |
Token ID | 481 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
phalt | +0.135 |
BELOW | +0.131 |
orrect | +0.126 |
trial | +0.120 |
JUST | +0.119 |
Neg logit contributions | |
Ashes | -0.152 |
IA | -0.152 |
Rosenberg | -0.149 |
cca | -0.141 |
cko | -0.140 |
Token | give |
Token ID | 1577 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
phalt | +0.510 |
BELOW | +0.496 |
orrect | +0.478 |
trial | +0.457 |
JUST | +0.452 |
Neg logit contributions | |
Ashes | -0.511 |
IA | -0.511 |
Rosenberg | -0.500 |
cca | -0.471 |
cko | -0.468 |
Token | anyone |
Token ID | 2687 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
phalt | +1.483 |
BELOW | +1.450 |
orrect | +1.392 |
trial | +1.316 |
JUST | +1.314 |
Neg logit contributions | |
IA | -1.739 |
Ashes | -1.738 |
Rosenberg | -1.699 |
cko | -1.615 |
cca | -1.610 |
Token | looking |
Token ID | 2045 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
phalt | +0.745 |
BELOW | +0.724 |
orrect | +0.697 |
trial | +0.665 |
JUST | +0.660 |
Neg logit contributions | |
IA | -0.773 |
Ashes | -0.773 |
Rosenberg | -0.758 |
cca | -0.714 |
cko | -0.709 |
Token | to |
Token ID | 284 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
BELOW | +3.586 |
phalt | +3.516 |
orrect | +3.237 |
� | +3.125 |
trial | +3.122 |
Neg logit contributions | |
IA | -4.548 |
Ashes | -4.512 |
Rosenberg | -4.397 |
ゼウス | -4.225 |
cca | -4.203 |
Token | receive |
Token ID | 3328 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
phalt | +0.891 |
BELOW | +0.865 |
orrect | +0.832 |
trial | +0.793 |
JUST | +0.786 |
Neg logit contributions | |
Ashes | -0.969 |
IA | -0.967 |
Rosenberg | -0.948 |
cca | -0.895 |
cko | -0.890 |
Token | their |
Token ID | 511 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
phalt | +1.482 |
BELOW | +1.451 |
orrect | +1.387 |
trial | +1.311 |
JUST | +1.303 |
Neg logit contributions | |
IA | -1.918 |
Ashes | -1.916 |
Rosenberg | -1.883 |
cko | -1.790 |
cca | -1.789 |
Token | CPR |
Token ID | 42920 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
phalt | +1.031 |
BELOW | +1.009 |
orrect | +0.966 |
trial | +0.912 |
JUST | +0.908 |
Neg logit contributions | |
IA | -1.259 |
Ashes | -1.256 |
Rosenberg | -1.236 |
cca | -1.170 |
cko | -1.170 |
Token | certification |
Token ID | 18094 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
IA | +0.833 |
Ashes | +0.831 |
Rosenberg | +0.807 |
cca | +0.764 |
cko | +0.755 |
Neg logit contributions | |
phalt | -0.843 |
BELOW | -0.811 |
orrect | -0.783 |
trial | -0.748 |
JUST | -0.743 |
Token | downright |
Token ID | 31464 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
phalt | +0.024 |
BELOW | +0.023 |
orrect | +0.022 |
trial | +0.021 |
JUST | +0.021 |
Neg logit contributions | |
Ashes | -0.027 |
IA | -0.027 |
Rosenberg | -0.026 |
cca | -0.025 |
cko | -0.025 |
Token | weird |
Token ID | 7650 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
phalt | +1.359 |
BELOW | +1.320 |
orrect | +1.257 |
trial | +1.188 |
JUST | +1.180 |
Neg logit contributions | |
Ashes | -1.875 |
IA | -1.873 |
Rosenberg | -1.839 |
cca | -1.745 |
cko | -1.741 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
phalt | +0.567 |
BELOW | +0.551 |
orrect | +0.531 |
trial | +0.507 |
JUST | +0.504 |
Neg logit contributions | |
Ashes | -0.554 |
IA | -0.553 |
Rosenberg | -0.542 |
cca | -0.510 |
cko | -0.507 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
phalt | +0.306 |
BELOW | +0.297 |
orrect | +0.285 |
trial | +0.271 |
JUST | +0.269 |
Neg logit contributions | |
Ashes | -0.362 |
IA | -0.362 |
Rosenberg | -0.355 |
cca | -0.335 |
cko | -0.334 |
Token |
|
Token ID | 198 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
phalt | +0.162 |
BELOW | +0.157 |
orrect | +0.150 |
trial | +0.143 |
JUST | +0.141 |
Neg logit contributions | |
Ashes | -0.196 |
IA | -0.196 |
Rosenberg | -0.193 |
cca | -0.182 |
cko | -0.182 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
phalt | +0.298 |
BELOW | +0.291 |
orrect | +0.280 |
trial | +0.269 |
JUST | +0.267 |
Neg logit contributions | |
Ashes | -0.260 |
IA | -0.259 |
Rosenberg | -0.254 |
cca | -0.238 |
cko | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
BELOW | +3.279 |
phalt | +3.260 |
orrect | +3.056 |
JUST | +2.959 |
� | +2.925 |
Neg logit contributions | |
IA | -4.790 |
Ashes | -4.782 |
Rosenberg | -4.677 |
ゼウス | -4.494 |
cca | -4.493 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
IA | +0.482 |
Ashes | +0.480 |
Rosenberg | +0.471 |
cca | +0.445 |
cko | +0.442 |
Neg logit contributions | |
phalt | -0.424 |
BELOW | -0.406 |
orrect | -0.393 |
conduc | -0.380 |
trial | -0.373 |
Token | Read |
Token ID | 5569 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
IA | +0.144 |
Ashes | +0.144 |
Rosenberg | +0.140 |
cca | +0.131 |
cko | +0.131 |
Neg logit contributions | |
phalt | -0.165 |
BELOW | -0.160 |
orrect | -0.155 |
trial | -0.148 |
JUST | -0.147 |
Token | more |
Token ID | 517 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
phalt | +1.988 |
BELOW | +1.964 |
orrect | +1.841 |
� | +1.738 |
trial | +1.725 |
Neg logit contributions | |
IA | -3.055 |
Ashes | -3.027 |
Rosenberg | -2.957 |
ゼウス | -2.900 |
cca | -2.833 |
Token | � |
Token ID | 1587 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
Ashes | +0.501 |
IA | +0.500 |
Rosenberg | +0.492 |
cca | +0.465 |
cko | +0.464 |
Neg logit contributions | |
phalt | -0.396 |
BELOW | -0.382 |
orrect | -0.368 |
trial | -0.349 |
JUST | -0.345 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
phalt | +1.998 |
BELOW | +1.977 |
orrect | +1.875 |
JUST | +1.789 |
orem | +1.789 |
Neg logit contributions | |
IA | -2.809 |
Ashes | -2.805 |
Rosenberg | -2.794 |
cko | -2.678 |
cca | -2.643 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
phalt | +1.590 |
BELOW | +1.552 |
orrect | +1.475 |
JUST | +1.405 |
� | +1.397 |
Neg logit contributions | |
IA | -1.949 |
Ashes | -1.936 |
Rosenberg | -1.903 |
cko | -1.813 |
cca | -1.790 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
phalt | +2.196 |
BELOW | +2.154 |
orrect | +2.012 |
� | +1.929 |
JUST | +1.925 |
Neg logit contributions | |
Ashes | -2.385 |
IA | -2.375 |
Rosenberg | -2.355 |
cko | -2.244 |
cca | -2.209 |
Token | 7 |
Token ID | 767 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
phalt | +2.060 |
BELOW | +2.043 |
orrect | +1.908 |
JUST | +1.824 |
� | +1.808 |
Neg logit contributions | |
Ashes | -2.661 |
IA | -2.647 |
Rosenberg | -2.626 |
cko | -2.479 |
cca | -2.463 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
BELOW | +2.570 |
phalt | +2.535 |
orrect | +2.384 |
JUST | +2.311 |
� | +2.295 |
Neg logit contributions | |
Rosenberg | -2.444 |
Ashes | -2.444 |
IA | -2.412 |
cko | -2.301 |
cca | -2.288 |
Token | void |
Token ID | 7951 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
phalt | +1.005 |
BELOW | +0.984 |
orrect | +0.923 |
JUST | +0.878 |
trial | +0.872 |
Neg logit contributions | |
Ashes | -1.482 |
IA | -1.473 |
Rosenberg | -1.462 |
cca | -1.387 |
cko | -1.385 |
Token | vert |
Token ID | 9421 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
phalt | +4.087 |
BELOW | +4.043 |
orrect | +3.818 |
� | +3.627 |
orem | +3.622 |
Neg logit contributions | |
IA | -4.020 |
Ashes | -3.926 |
Rosenberg | -3.866 |
cca | -3.638 |
cko | -3.618 |
Token | ( |
Token ID | 357 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
phalt | +0.902 |
BELOW | +0.890 |
orrect | +0.846 |
trial | +0.808 |
JUST | +0.808 |
Neg logit contributions | |
Ashes | -0.991 |
IA | -0.988 |
Rosenberg | -0.968 |
cca | -0.914 |
cko | -0.909 |
Token | in |
Token ID | 287 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Ashes | +0.179 |
IA | +0.179 |
Rosenberg | +0.176 |
cca | +0.166 |
cko | +0.166 |
Neg logit contributions | |
phalt | -0.144 |
BELOW | -0.140 |
orrect | -0.134 |
trial | -0.127 |
JUST | -0.126 |
Token | out |
Token ID | 448 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
IA | +1.398 |
Ashes | +1.387 |
Rosenberg | +1.361 |
cko | +1.293 |
toe | +1.292 |
Neg logit contributions | |
phalt | -1.502 |
BELOW | -1.452 |
conduc | -1.398 |
orrect | -1.393 |
� | -1.342 |
Token | app |
Token ID | 598 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Ashes | +0.676 |
IA | +0.675 |
Rosenberg | +0.666 |
cko | +0.638 |
cca | +0.637 |
Neg logit contributions | |
phalt | -0.305 |
BELOW | -0.287 |
orrect | -0.274 |
trial | -0.256 |
conduc | -0.250 |
Token | < |
Token ID | 1279 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
phalt | +0.259 |
BELOW | +0.247 |
orrect | +0.229 |
trial | +0.209 |
JUST | +0.206 |
Neg logit contributions | |
Ashes | -0.707 |
IA | -0.706 |
Rosenberg | -0.697 |
cca | -0.669 |
cko | -0.667 |
Token | T |
Token ID | 309 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Ashes | +0.099 |
IA | +0.099 |
Rosenberg | +0.097 |
cca | +0.091 |
cko | +0.090 |
Neg logit contributions | |
phalt | -0.107 |
BELOW | -0.104 |
orrect | -0.100 |
trial | -0.096 |
JUST | -0.095 |
Token | > |
Token ID | 1875 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Ashes | +0.510 |
IA | +0.510 |
Rosenberg | +0.502 |
cca | +0.477 |
cko | +0.475 |
Neg logit contributions | |
phalt | -0.335 |
BELOW | -0.323 |
orrect | -0.309 |
trial | -0.290 |
JUST | -0.286 |
Token | { |
Token ID | 1391 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
phalt | +1.177 |
BELOW | +1.151 |
orrect | +1.104 |
trial | +1.048 |
JUST | +1.046 |
Neg logit contributions | |
IA | -1.240 |
Ashes | -1.237 |
Rosenberg | -1.218 |
cca | -1.149 |
cko | -1.143 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Ashes | +0.938 |
IA | +0.933 |
Rosenberg | +0.919 |
cca | +0.875 |
cko | +0.868 |
Neg logit contributions | |
phalt | -0.568 |
BELOW | -0.544 |
orrect | -0.520 |
trial | -0.490 |
JUST | -0.479 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
phalt | +0.607 |
BELOW | +0.577 |
orrect | +0.530 |
trial | +0.471 |
JUST | +0.468 |
Neg logit contributions | |
IA | -1.960 |
Ashes | -1.960 |
Rosenberg | -1.935 |
cca | -1.864 |
cko | -1.856 |
Token | load |
Token ID | 3440 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
phalt | +3.307 |
BELOW | +3.297 |
orrect | +3.104 |
� | +2.963 |
trial | +2.918 |
Neg logit contributions | |
IA | -4.648 |
Ashes | -4.557 |
Rosenberg | -4.551 |
cko | -4.334 |
cca | -4.325 |
Token | < |
Token ID | 1279 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
phalt | +0.681 |
BELOW | +0.661 |
orrect | +0.636 |
trial | +0.607 |
JUST | +0.602 |
Neg logit contributions | |
Ashes | -0.807 |
IA | -0.805 |
Rosenberg | -0.794 |
cca | -0.749 |
cko | -0.748 |
Token | ' |
Token ID | 705 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
phalt | +0.046 |
BELOW | +0.044 |
orrect | +0.043 |
trial | +0.041 |
JUST | +0.040 |
Neg logit contributions | |
Ashes | -0.041 |
IA | -0.041 |
Rosenberg | -0.040 |
cca | -0.038 |
cko | -0.037 |
Token | a |
Token ID | 64 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
IA | +1.296 |
Ashes | +1.284 |
Rosenberg | +1.250 |
cca | +1.172 |
cko | +1.165 |
Neg logit contributions | |
phalt | -1.774 |
BELOW | -1.722 |
orrect | -1.673 |
trial | -1.605 |
JUST | -1.593 |
Token | > |
Token ID | 1875 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
phalt | +0.051 |
BELOW | +0.049 |
orrect | +0.047 |
trial | +0.044 |
JUST | +0.044 |
Neg logit contributions | |
Ashes | -0.067 |
IA | -0.067 |
Rosenberg | -0.065 |
cca | -0.062 |
cko | -0.062 |
Token | ; |
Token ID | 26 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
IA | +0.549 |
Ashes | +0.549 |
Rosenberg | +0.537 |
cca | +0.507 |
cko | +0.503 |
Neg logit contributions | |
phalt | -0.524 |
BELOW | -0.508 |
orrect | -0.490 |
trial | -0.466 |
JUST | -0.463 |
Token | } |
Token ID | 1782 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
phalt | +0.214 |
BELOW | +0.209 |
orrect | +0.202 |
trial | +0.193 |
JUST | +0.192 |
Neg logit contributions | |
Ashes | -0.188 |
IA | -0.188 |
Rosenberg | -0.184 |
cca | -0.172 |
cko | -0.171 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
phalt | +1.743 |
BELOW | +1.694 |
orrect | +1.589 |
� | +1.500 |
JUST | +1.499 |
Neg logit contributions | |
IA | -2.458 |
Ashes | -2.446 |
Rosenberg | -2.426 |
cko | -2.315 |
cca | -2.304 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
phalt | +0.134 |
BELOW | +0.129 |
orrect | +0.123 |
trial | +0.117 |
JUST | +0.115 |
Neg logit contributions | |
Ashes | -0.194 |
IA | -0.193 |
Rosenberg | -0.190 |
cca | -0.181 |
cko | -0.180 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
phalt | +1.377 |
BELOW | +1.322 |
orrect | +1.241 |
� | +1.153 |
JUST | +1.148 |
Neg logit contributions | |
IA | -2.888 |
Ashes | -2.883 |
Rosenberg | -2.854 |
cko | -2.721 |
cca | -2.710 |
Token | void |
Token ID | 7951 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
phalt | +2.012 |
BELOW | +1.967 |
orrect | +1.866 |
� | +1.782 |
JUST | +1.782 |
Neg logit contributions | |
IA | -2.582 |
Ashes | -2.568 |
Rosenberg | -2.560 |
cko | -2.430 |
cca | -2.395 |
Token | vert |
Token ID | 9421 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
phalt | +4.108 |
BELOW | +4.019 |
orrect | +3.823 |
� | +3.655 |
orem | +3.621 |
Neg logit contributions | |
IA | -3.923 |
Ashes | -3.816 |
Rosenberg | -3.789 |
cca | -3.576 |
cko | -3.546 |
Token | ( |
Token ID | 357 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
phalt | +0.315 |
BELOW | +0.307 |
orrect | +0.295 |
trial | +0.281 |
JUST | +0.280 |
Neg logit contributions | |
Ashes | -0.324 |
IA | -0.324 |
Rosenberg | -0.317 |
cca | -0.299 |
cko | -0.297 |
Token | in |
Token ID | 287 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Ashes | +0.284 |
IA | +0.284 |
Rosenberg | +0.278 |
cca | +0.264 |
cko | +0.262 |
Neg logit contributions | |
phalt | -0.233 |
BELOW | -0.226 |
orrect | -0.218 |
trial | -0.207 |
JUST | -0.205 |
Token | out |
Token ID | 448 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
IA | +1.724 |
Ashes | +1.717 |
Rosenberg | +1.670 |
cca | +1.603 |
cko | +1.585 |
Neg logit contributions | |
phalt | -1.790 |
BELOW | -1.743 |
orrect | -1.678 |
conduc | -1.663 |
trial | -1.619 |
Token | app |
Token ID | 598 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Ashes | +1.263 |
IA | +1.259 |
Rosenberg | +1.242 |
cca | +1.192 |
cko | +1.191 |
Neg logit contributions | |
phalt | -0.597 |
BELOW | -0.562 |
orrect | -0.536 |
trial | -0.507 |
conduc | -0.498 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
phalt | +0.284 |
BELOW | +0.272 |
orrect | +0.264 |
conduc | +0.251 |
trial | +0.249 |
Neg logit contributions | |
IA | -0.327 |
Ashes | -0.326 |
Rosenberg | -0.320 |
cca | -0.302 |
cko | -0.301 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
IA | +0.111 |
Ashes | +0.111 |
Rosenberg | +0.109 |
cca | +0.103 |
cko | +0.103 |
Neg logit contributions | |
phalt | -0.096 |
BELOW | -0.093 |
orrect | -0.089 |
conduc | -0.085 |
trial | -0.085 |
Token | Ep |
Token ID | 13807 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
IA | +0.143 |
Ashes | +0.142 |
Rosenberg | +0.139 |
cca | +0.129 |
cko | +0.129 |
Neg logit contributions | |
phalt | -0.186 |
BELOW | -0.181 |
orrect | -0.175 |
trial | -0.168 |
JUST | -0.167 |
Token | ider |
Token ID | 1304 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
IA | +1.464 |
Ashes | +1.444 |
Rosenberg | +1.417 |
cko | +1.335 |
cca | +1.331 |
Neg logit contributions | |
phalt | -1.704 |
BELOW | -1.681 |
orrect | -1.609 |
conduc | -1.556 |
trial | -1.542 |
Token | m |
Token ID | 76 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
IA | +0.067 |
Ashes | +0.067 |
Rosenberg | +0.066 |
cko | +0.062 |
vre | +0.062 |
Neg logit contributions | |
phalt | -0.056 |
BELOW | -0.055 |
orrect | -0.052 |
conduc | -0.050 |
JUST | -0.049 |
Token | oly |
Token ID | 3366 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
phalt | +0.569 |
BELOW | +0.555 |
orrect | +0.537 |
trial | +0.515 |
JUST | +0.511 |
Neg logit contributions | |
Ashes | -0.454 |
IA | -0.453 |
Rosenberg | -0.443 |
cca | -0.413 |
cko | -0.411 |
Token | tic |
Token ID | 13370 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
IA | +2.495 |
Ashes | +2.480 |
Rosenberg | +2.438 |
cca | +2.318 |
cko | +2.288 |
Neg logit contributions | |
phalt | -2.330 |
BELOW | -2.271 |
orrect | -2.174 |
JUST | -2.081 |
trial | -2.066 |
Token | palm |
Token ID | 18057 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Ashes | +1.169 |
IA | +1.167 |
Rosenberg | +1.142 |
cca | +1.076 |
cko | +1.068 |
Neg logit contributions | |
phalt | -1.153 |
BELOW | -1.126 |
orrect | -1.080 |
trial | -1.034 |
JUST | -1.028 |
Token | opl |
Token ID | 20106 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Ashes | +0.703 |
IA | +0.702 |
Rosenberg | +0.688 |
cca | +0.646 |
cko | +0.645 |
Neg logit contributions | |
phalt | -0.737 |
BELOW | -0.720 |
orrect | -0.692 |
trial | -0.663 |
JUST | -0.658 |
Token | ant |
Token ID | 415 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
phalt | +0.370 |
BELOW | +0.357 |
orrect | +0.346 |
trial | +0.328 |
JUST | +0.323 |
Neg logit contributions | |
Ashes | -0.445 |
IA | -0.443 |
Rosenberg | -0.436 |
cca | -0.412 |
cko | -0.410 |
Token | ar |
Token ID | 283 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
phalt | +0.579 |
BELOW | +0.560 |
orrect | +0.536 |
trial | +0.506 |
JUST | +0.499 |
Neg logit contributions | |
Ashes | -0.815 |
IA | -0.812 |
Rosenberg | -0.799 |
cca | -0.759 |
cko | -0.754 |
Token | 's |
Token ID | 338 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
BELOW | +2.130 |
phalt | +2.118 |
orrect | +1.997 |
trial | +1.906 |
JUST | +1.887 |
Neg logit contributions | |
Ashes | -2.464 |
IA | -2.456 |
Rosenberg | -2.404 |
cca | -2.299 |
cko | -2.291 |
Token | financial |
Token ID | 3176 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Ashes | +0.937 |
IA | +0.933 |
Rosenberg | +0.915 |
cca | +0.857 |
cko | +0.853 |
Neg logit contributions | |
phalt | -0.987 |
BELOW | -0.958 |
orrect | -0.926 |
trial | -0.886 |
JUST | -0.880 |
Token | counselling |
Token ID | 47586 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Ashes | +0.909 |
IA | +0.908 |
Rosenberg | +0.887 |
cca | +0.828 |
cko | +0.822 |
Neg logit contributions | |
phalt | -1.153 |
BELOW | -1.123 |
orrect | -1.086 |
trial | -1.042 |
JUST | -1.036 |
Token | service |
Token ID | 2139 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Ashes | +0.683 |
IA | +0.681 |
Rosenberg | +0.669 |
cca | +0.628 |
cko | +0.625 |
Neg logit contributions | |
phalt | -0.654 |
BELOW | -0.631 |
orrect | -0.611 |
trial | -0.582 |
JUST | -0.578 |
Token | or |
Token ID | 393 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
phalt | +0.827 |
BELOW | +0.809 |
orrect | +0.773 |
trial | +0.735 |
JUST | +0.728 |
Neg logit contributions | |
Ashes | -0.943 |
IA | -0.942 |
Rosenberg | -0.923 |
cca | -0.874 |
cko | -0.871 |
Token | call |
Token ID | 869 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Ashes | +1.132 |
IA | +1.121 |
Rosenberg | +1.104 |
cca | +1.029 |
cko | +1.024 |
Neg logit contributions | |
phalt | -1.186 |
BELOW | -1.141 |
orrect | -1.110 |
trial | -1.059 |
JUST | -1.053 |
Token | K |
Token ID | 509 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Ashes | +1.972 |
IA | +1.948 |
Rosenberg | +1.908 |
cca | +1.758 |
Unicorn | +1.747 |
Neg logit contributions | |
phalt | -2.522 |
BELOW | -2.397 |
orrect | -2.360 |
trial | -2.265 |
JUST | -2.257 |
Token | ild |
Token ID | 688 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Ashes | +0.586 |
IA | +0.574 |
Rosenberg | +0.572 |
cko | +0.533 |
cca | +0.533 |
Neg logit contributions | |
phalt | -0.653 |
BELOW | -0.637 |
orrect | -0.616 |
trial | -0.589 |
JUST | -0.588 |
Token | on |
Token ID | 261 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
phalt | +0.710 |
BELOW | +0.691 |
orrect | +0.665 |
trial | +0.636 |
JUST | +0.631 |
Neg logit contributions | |
IA | -0.686 |
Ashes | -0.685 |
Rosenberg | -0.671 |
cca | -0.632 |
cko | -0.629 |
Token | an |
Token ID | 272 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
phalt | +0.327 |
BELOW | +0.319 |
orrect | +0.310 |
trial | +0.298 |
JUST | +0.296 |
Neg logit contributions | |
Ashes | -0.227 |
IA | -0.227 |
Rosenberg | -0.221 |
cca | -0.205 |
cko | -0.204 |
Token | for |
Token ID | 329 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Ashes | +0.341 |
IA | +0.340 |
Rosenberg | +0.333 |
cca | +0.313 |
cko | +0.312 |
Neg logit contributions | |
phalt | -0.367 |
BELOW | -0.360 |
orrect | -0.346 |
trial | -0.331 |
JUST | -0.329 |
Token | liberal |
Token ID | 7270 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
phalt | +0.841 |
BELOW | +0.818 |
orrect | +0.786 |
trial | +0.748 |
JUST | +0.742 |
Neg logit contributions | |
Ashes | -0.941 |
IA | -0.940 |
Rosenberg | -0.922 |
cca | -0.871 |
cko | -0.867 |
Token | like |
Token ID | 588 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
phalt | +0.251 |
BELOW | +0.244 |
orrect | +0.235 |
trial | +0.223 |
JUST | +0.222 |
Neg logit contributions | |
Ashes | -0.273 |
IA | -0.272 |
Rosenberg | -0.267 |
cca | -0.252 |
cko | -0.251 |
Token | him |
Token ID | 683 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
phalt | +2.249 |
BELOW | +2.207 |
orrect | +2.112 |
JUST | +2.033 |
trial | +2.013 |
Neg logit contributions | |
IA | -2.236 |
Ashes | -2.230 |
Rosenberg | -2.152 |
ゼウス | -2.080 |
cca | -2.074 |
Token | would |
Token ID | 561 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
Ashes | +0.472 |
IA | +0.471 |
Rosenberg | +0.463 |
cca | +0.436 |
cko | +0.433 |
Neg logit contributions | |
phalt | -0.442 |
BELOW | -0.430 |
orrect | -0.414 |
trial | -0.395 |
JUST | -0.391 |
Token | have |
Token ID | 423 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
phalt | +0.261 |
BELOW | +0.253 |
orrect | +0.243 |
trial | +0.231 |
JUST | +0.228 |
Neg logit contributions | |
Ashes | -0.319 |
IA | -0.318 |
Rosenberg | -0.312 |
cca | -0.296 |
cko | -0.294 |
Token | had |
Token ID | 550 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Ashes | +1.218 |
IA | +1.212 |
Rosenberg | +1.202 |
cca | +1.116 |
cko | +1.113 |
Neg logit contributions | |
phalt | -1.220 |
BELOW | -1.189 |
orrect | -1.147 |
trial | -1.102 |
JUST | -1.085 |
Token | considerable |
Token ID | 11091 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Ashes | +2.420 |
Rosenberg | +2.394 |
IA | +2.380 |
cko | +2.198 |
cca | +2.197 |
Neg logit contributions | |
phalt | -2.356 |
BELOW | -2.276 |
orrect | -2.193 |
trial | -2.091 |
� | -2.080 |
Token | difficulty |
Token ID | 8722 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Ashes | +0.110 |
IA | +0.109 |
Rosenberg | +0.108 |
cca | +0.101 |
cko | +0.101 |
Neg logit contributions | |
phalt | -0.098 |
BELOW | -0.095 |
orrect | -0.091 |
trial | -0.087 |
JUST | -0.086 |
Token | creating |
Token ID | 4441 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Ashes | +2.173 |
Rosenberg | +2.156 |
IA | +2.151 |
vre | +1.989 |
cca | +1.985 |
Neg logit contributions | |
phalt | -2.165 |
BELOW | -2.090 |
orrect | -2.057 |
trial | -1.963 |
� | -1.922 |
Token | a |
Token ID | 257 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Ashes | +0.948 |
IA | +0.946 |
Rosenberg | +0.930 |
cca | +0.874 |
cko | +0.870 |
Neg logit contributions | |
phalt | -0.915 |
BELOW | -0.888 |
orrect | -0.856 |
trial | -0.817 |
JUST | -0.809 |
Token | durable |
Token ID | 20923 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Ashes | +1.064 |
IA | +1.063 |
Rosenberg | +1.047 |
cca | +0.984 |
cko | +0.977 |
Neg logit contributions | |
phalt | -0.997 |
BELOW | -0.966 |
orrect | -0.933 |
trial | -0.888 |
JUST | -0.880 |
Token | � |
Token ID | 447 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
IA | +0.590 |
Ashes | +0.578 |
Rosenberg | +0.567 |
cca | +0.536 |
cko | +0.530 |
Neg logit contributions | |
phalt | -0.620 |
BELOW | -0.598 |
orrect | -0.580 |
conduc | -0.556 |
trial | -0.552 |
Token | � |
Token ID | 250 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
phalt | +0.218 |
BELOW | +0.212 |
orrect | +0.203 |
trial | +0.193 |
JUST | +0.191 |
Neg logit contributions | |
Ashes | -0.269 |
IA | -0.269 |
Rosenberg | -0.264 |
cca | -0.250 |
cko | -0.248 |
Token | DS |
Token ID | 5258 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
IA | +0.529 |
Ashes | +0.528 |
Rosenberg | +0.517 |
cca | +0.488 |
cko | +0.485 |
Neg logit contributions | |
phalt | -0.479 |
BELOW | -0.463 |
orrect | -0.447 |
trial | -0.426 |
JUST | -0.420 |
Token | CC |
Token ID | 4093 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
IA | +0.711 |
Ashes | +0.705 |
Rosenberg | +0.693 |
cca | +0.647 |
cko | +0.638 |
Neg logit contributions | |
phalt | -0.822 |
BELOW | -0.799 |
orrect | -0.776 |
trial | -0.747 |
JUST | -0.734 |
Token | As |
Token ID | 1081 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
IA | +0.564 |
Ashes | +0.560 |
Rosenberg | +0.552 |
cca | +0.517 |
cko | +0.514 |
Neg logit contributions | |
phalt | -0.492 |
BELOW | -0.471 |
orrect | -0.455 |
trial | -0.434 |
JUST | -0.429 |
Token | king |
Token ID | 3364 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
phalt | +0.067 |
BELOW | +0.066 |
orrect | +0.064 |
trial | +0.062 |
JUST | +0.061 |
Neg logit contributions | |
IA | -0.039 |
Ashes | -0.039 |
Rosenberg | -0.038 |
cca | -0.035 |
cko | -0.034 |
Token | Koch |
Token ID | 17009 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
IA | +2.621 |
Ashes | +2.618 |
Rosenberg | +2.567 |
cko | +2.383 |
Unicorn | +2.383 |
Neg logit contributions | |
phalt | -2.522 |
BELOW | -2.385 |
orrect | -2.364 |
trial | -2.272 |
conduc | -2.206 |
Token | s |
Token ID | 82 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
IA | +1.199 |
Ashes | +1.193 |
Rosenberg | +1.174 |
cca | +1.100 |
cko | +1.095 |
Neg logit contributions | |
phalt | -1.029 |
BELOW | -0.997 |
orrect | -0.959 |
trial | -0.912 |
JUST | -0.897 |
Token | for |
Token ID | 329 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Ashes | +0.281 |
IA | +0.281 |
Rosenberg | +0.275 |
cca | +0.259 |
cko | +0.258 |
Neg logit contributions | |
phalt | -0.262 |
BELOW | -0.254 |
orrect | -0.245 |
trial | -0.234 |
JUST | -0.231 |
Token | Cash |
Token ID | 16210 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
phalt | +0.440 |
BELOW | +0.429 |
orrect | +0.412 |
trial | +0.392 |
JUST | +0.390 |
Neg logit contributions | |
IA | -0.465 |
Ashes | -0.465 |
Rosenberg | -0.456 |
cca | -0.430 |
cko | -0.428 |
Token | � |
Token ID | 447 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Ashes | +0.571 |
IA | +0.570 |
Rosenberg | +0.558 |
cca | +0.526 |
cko | +0.521 |
Neg logit contributions | |
phalt | -0.493 |
BELOW | -0.475 |
orrect | -0.461 |
trial | -0.438 |
JUST | -0.431 |
Token | video |
Token ID | 2008 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
phalt | +0.244 |
BELOW | +0.234 |
orrect | +0.226 |
trial | +0.217 |
JUST | +0.215 |
Neg logit contributions | |
IA | -0.261 |
Ashes | -0.261 |
Rosenberg | -0.256 |
cca | -0.241 |
cko | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
IA | +0.325 |
Ashes | +0.325 |
Rosenberg | +0.318 |
cca | +0.300 |
cko | +0.299 |
Neg logit contributions | |
phalt | -0.299 |
BELOW | -0.290 |
orrect | -0.279 |
trial | -0.266 |
JUST | -0.264 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Ashes | +1.108 |
IA | +1.106 |
Rosenberg | +1.086 |
cca | +1.022 |
cko | +1.017 |
Neg logit contributions | |
phalt | -0.980 |
BELOW | -0.945 |
orrect | -0.916 |
trial | -0.869 |
JUST | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
IA | +0.309 |
Ashes | +0.307 |
Rosenberg | +0.302 |
cca | +0.285 |
cko | +0.284 |
Neg logit contributions | |
phalt | -0.263 |
BELOW | -0.253 |
orrect | -0.245 |
conduc | -0.232 |
trial | -0.231 |
Token | Hard |
Token ID | 17309 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
IA | +0.194 |
Ashes | +0.193 |
Rosenberg | +0.189 |
cca | +0.177 |
cko | +0.177 |
Neg logit contributions | |
phalt | -0.217 |
BELOW | -0.211 |
orrect | -0.204 |
trial | -0.195 |
conduc | -0.193 |
Token | ly |
Token ID | 306 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Ashes | +0.777 |
IA | +0.776 |
Rosenberg | +0.761 |
cca | +0.717 |
cko | +0.714 |
Neg logit contributions | |
phalt | -0.746 |
BELOW | -0.726 |
orrect | -0.698 |
trial | -0.666 |
JUST | -0.661 |
Token | an |
Token ID | 281 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Ashes | +2.582 |
IA | +2.552 |
Rosenberg | +2.529 |
cca | +2.372 |
cko | +2.341 |
Neg logit contributions | |
phalt | -2.773 |
BELOW | -2.680 |
orrect | -2.590 |
trial | -2.496 |
orem | -2.450 |
Token | entertaining |
Token ID | 17774 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Ashes | +1.388 |
IA | +1.378 |
Rosenberg | +1.350 |
cca | +1.274 |
cko | +1.267 |
Neg logit contributions | |
phalt | -1.157 |
BELOW | -1.118 |
orrect | -1.071 |
trial | -1.027 |
� | -1.011 |
Token | one |
Token ID | 530 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Ashes | +0.315 |
IA | +0.314 |
Rosenberg | +0.309 |
cca | +0.291 |
cko | +0.289 |
Neg logit contributions | |
phalt | -0.257 |
BELOW | -0.248 |
orrect | -0.238 |
trial | -0.225 |
JUST | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Ashes | +1.028 |
IA | +1.024 |
Rosenberg | +1.007 |
cca | +0.947 |
cko | +0.937 |
Neg logit contributions | |
phalt | -1.041 |
BELOW | -1.001 |
orrect | -0.971 |
trial | -0.924 |
JUST | -0.919 |
Token | either |
Token ID | 2035 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Ashes | +0.510 |
IA | +0.504 |
Rosenberg | +0.499 |
cca | +0.467 |
cko | +0.461 |
Neg logit contributions | |
phalt | -0.503 |
BELOW | -0.487 |
orrect | -0.471 |
trial | -0.449 |
JUST | -0.446 |
Token | but |
Token ID | 475 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Ashes | +0.597 |
IA | +0.593 |
Rosenberg | +0.585 |
cca | +0.547 |
cko | +0.543 |
Neg logit contributions | |
phalt | -0.611 |
BELOW | -0.594 |
orrect | -0.574 |
trial | -0.546 |
JUST | -0.541 |
Token | it |
Token ID | 340 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
phalt | +0.130 |
BELOW | +0.127 |
orrect | +0.122 |
trial | +0.116 |
JUST | +0.115 |
Neg logit contributions | |
Ashes | -0.152 |
IA | -0.152 |
Rosenberg | -0.149 |
cca | -0.141 |
cko | -0.140 |
Token | is |
Token ID | 318 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
phalt | +0.435 |
BELOW | +0.423 |
orrect | +0.407 |
trial | +0.387 |
JUST | +0.384 |
Neg logit contributions | |
Ashes | -0.482 |
IA | -0.481 |
Rosenberg | -0.472 |
cca | -0.445 |
cko | -0.444 |
Token | an |
Token ID | 281 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Ashes | +0.457 |
IA | +0.455 |
Rosenberg | +0.450 |
cca | +0.425 |
cko | +0.423 |
Neg logit contributions | |
phalt | -0.324 |
BELOW | -0.310 |
orrect | -0.301 |
trial | -0.283 |
� | -0.280 |
Token | odd |
Token ID | 5629 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Ashes | +0.593 |
IA | +0.589 |
Rosenberg | +0.578 |
cca | +0.546 |
cko | +0.543 |
Neg logit contributions | |
phalt | -0.486 |
BELOW | -0.466 |
orrect | -0.451 |
trial | -0.428 |
� | -0.425 |
Token | circumstance |
Token ID | 25179 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
IA | +0.941 |
Ashes | +0.940 |
Rosenberg | +0.922 |
cca | +0.872 |
cko | +0.864 |
Neg logit contributions | |
phalt | -0.819 |
BELOW | -0.793 |
orrect | -0.762 |
trial | -0.719 |
JUST | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Ashes | +1.146 |
IA | +1.144 |
Rosenberg | +1.125 |
cca | +1.056 |
cko | +1.047 |
Neg logit contributions | |
phalt | -1.208 |
BELOW | -1.169 |
orrect | -1.128 |
trial | -1.075 |
JUST | -1.067 |
Token | With |
Token ID | 2080 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Ashes | +1.447 |
IA | +1.431 |
Rosenberg | +1.418 |
cca | +1.323 |
Unicorn | +1.309 |
Neg logit contributions | |
phalt | -1.313 |
BELOW | -1.254 |
orrect | -1.225 |
conduc | -1.167 |
trial | -1.159 |
Token | many |
Token ID | 867 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
Ashes | +0.159 |
IA | +0.159 |
Rosenberg | +0.156 |
cca | +0.147 |
cko | +0.147 |
Neg logit contributions | |
phalt | -0.141 |
BELOW | -0.137 |
orrect | -0.132 |
trial | -0.126 |
JUST | -0.125 |
Token | of |
Token ID | 286 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Ashes | +0.044 |
IA | +0.044 |
Rosenberg | +0.043 |
cca | +0.041 |
cko | +0.040 |
Neg logit contributions | |
phalt | -0.040 |
BELOW | -0.039 |
orrect | -0.038 |
trial | -0.036 |
JUST | -0.036 |
Token | his |
Token ID | 465 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
Ashes | +0.249 |
IA | +0.248 |
Rosenberg | +0.244 |
cca | +0.230 |
cko | +0.229 |
Neg logit contributions | |
phalt | -0.201 |
BELOW | -0.195 |
orrect | -0.187 |
trial | -0.177 |
JUST | -0.176 |
Token | earliest |
Token ID | 14555 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
Ashes | +0.085 |
IA | +0.085 |
Rosenberg | +0.083 |
cca | +0.078 |
cko | +0.078 |
Neg logit contributions | |
phalt | -0.085 |
BELOW | -0.083 |
orrect | -0.080 |
trial | -0.076 |
JUST | -0.076 |
Token | production |
Token ID | 3227 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
phalt | +0.613 |
BELOW | +0.597 |
orrect | +0.574 |
trial | +0.549 |
JUST | +0.543 |
Neg logit contributions | |
IA | -0.631 |
Ashes | -0.630 |
Rosenberg | -0.617 |
cca | -0.583 |
cko | -0.581 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Ashes | +1.744 |
IA | +1.742 |
Rosenberg | +1.711 |
cca | +1.598 |
cko | +1.591 |
Neg logit contributions | |
phalt | -1.707 |
BELOW | -1.648 |
orrect | -1.591 |
JUST | -1.518 |
trial | -1.514 |
Token | a |
Token ID | 257 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Ashes | +1.005 |
IA | +1.000 |
Rosenberg | +0.992 |
cca | +0.928 |
cko | +0.923 |
Neg logit contributions | |
phalt | -0.851 |
BELOW | -0.827 |
orrect | -0.796 |
trial | -0.753 |
JUST | -0.752 |
Token | 1949 |
Token ID | 24977 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Ashes | +0.371 |
IA | +0.370 |
Rosenberg | +0.364 |
cca | +0.343 |
cko | +0.341 |
Neg logit contributions | |
phalt | -0.341 |
BELOW | -0.332 |
orrect | -0.318 |
trial | -0.303 |
JUST | -0.301 |
Token | theatrical |
Token ID | 32010 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
phalt | +0.350 |
BELOW | +0.340 |
orrect | +0.328 |
trial | +0.313 |
JUST | +0.310 |
Neg logit contributions | |
Ashes | -0.353 |
IA | -0.353 |
Rosenberg | -0.345 |
cca | -0.325 |
cko | -0.324 |
Token | version |
Token ID | 2196 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Ashes | +1.459 |
IA | +1.454 |
Rosenberg | +1.428 |
cca | +1.328 |
cko | +1.322 |
Neg logit contributions | |
phalt | -1.547 |
BELOW | -1.499 |
orrect | -1.441 |
JUST | -1.376 |
trial | -1.372 |
Token | of |
Token ID | 286 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Ashes | +1.462 |
IA | +1.461 |
Rosenberg | +1.436 |
cca | +1.349 |
cko | +1.345 |
Neg logit contributions | |
phalt | -1.383 |
BELOW | -1.341 |
orrect | -1.289 |
trial | -1.229 |
JUST | -1.223 |
Token | Comet |
Token ID | 36238 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
phalt | +0.302 |
BELOW | +0.294 |
orrect | +0.282 |
trial | +0.269 |
JUST | +0.267 |
Neg logit contributions | |
IA | -0.320 |
Ashes | -0.320 |
Rosenberg | -0.314 |
cca | -0.297 |
cko | -0.296 |
Token | in |
Token ID | 287 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Ashes | +1.074 |
IA | +1.070 |
Rosenberg | +1.052 |
cca | +0.989 |
cko | +0.985 |
Neg logit contributions | |
phalt | -0.949 |
BELOW | -0.914 |
orrect | -0.883 |
trial | -0.839 |
JUST | -0.835 |
Token | M |
Token ID | 337 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Ashes | +0.328 |
IA | +0.328 |
Rosenberg | +0.321 |
cca | +0.301 |
cko | +0.300 |
Neg logit contributions | |
phalt | -0.359 |
BELOW | -0.350 |
orrect | -0.338 |
trial | -0.323 |
JUST | -0.321 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Ashes | +1.058 |
IA | +1.056 |
Rosenberg | +1.028 |
cca | +0.975 |
cko | +0.962 |
Neg logit contributions | |
phalt | -0.928 |
BELOW | -0.888 |
orrect | -0.863 |
trial | -0.823 |
JUST | -0.816 |
Token | fast |
Token ID | 3049 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
phalt | +0.157 |
BELOW | +0.152 |
orrect | +0.146 |
trial | +0.139 |
JUST | +0.138 |
Neg logit contributions | |
Ashes | -0.192 |
IA | -0.192 |
Rosenberg | -0.188 |
cca | -0.178 |
cko | -0.177 |
Token | ed |
Token ID | 276 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
phalt | +1.352 |
BELOW | +1.328 |
orrect | +1.285 |
trial | +1.245 |
JUST | +1.233 |
Neg logit contributions | |
Ashes | -0.815 |
IA | -0.813 |
Rosenberg | -0.796 |
cko | -0.729 |
cca | -0.727 |
Token | state |
Token ID | 1181 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
phalt | +0.499 |
BELOW | +0.484 |
orrect | +0.464 |
trial | +0.441 |
JUST | +0.438 |
Neg logit contributions | |
Ashes | -0.594 |
IA | -0.593 |
Rosenberg | -0.581 |
cca | -0.551 |
cko | -0.547 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Ashes | +0.703 |
IA | +0.703 |
Rosenberg | +0.686 |
cca | +0.651 |
cko | +0.643 |
Neg logit contributions | |
phalt | -0.632 |
BELOW | -0.611 |
orrect | -0.587 |
trial | -0.560 |
JUST | -0.555 |
Token | which |
Token ID | 543 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
phalt | +0.395 |
BELOW | +0.384 |
orrect | +0.369 |
trial | +0.351 |
JUST | +0.348 |
Neg logit contributions | |
Ashes | -0.444 |
IA | -0.443 |
Rosenberg | -0.435 |
cca | -0.411 |
cko | -0.408 |
Token | gives |
Token ID | 3607 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Ashes | +0.150 |
IA | +0.150 |
Rosenberg | +0.148 |
cca | +0.139 |
cko | +0.138 |
Neg logit contributions | |
phalt | -0.136 |
BELOW | -0.132 |
orrect | -0.126 |
trial | -0.121 |
JUST | -0.120 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
phalt | +1.256 |
BELOW | +1.218 |
orrect | +1.167 |
trial | +1.106 |
JUST | +1.096 |
Neg logit contributions | |
Ashes | -1.609 |
IA | -1.607 |
Rosenberg | -1.579 |
cca | -1.495 |
cko | -1.490 |
Token | body |
Token ID | 1767 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
phalt | +1.078 |
BELOW | +1.045 |
orrect | +0.993 |
trial | +0.932 |
JUST | +0.922 |
Neg logit contributions | |
Ashes | -1.771 |
IA | -1.768 |
Rosenberg | -1.741 |
cca | -1.657 |
cko | -1.652 |
Token | more |
Token ID | 517 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
phalt | +1.983 |
BELOW | +1.941 |
orrect | +1.863 |
trial | +1.770 |
JUST | +1.757 |
Neg logit contributions | |
Ashes | -2.239 |
IA | -2.238 |
Rosenberg | -2.195 |
cko | -2.074 |
cca | -2.069 |
Token | � |
Token ID | 564 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
phalt | +0.718 |
BELOW | +0.703 |
orrect | +0.682 |
trial | +0.658 |
JUST | +0.654 |
Neg logit contributions | |
Ashes | -0.418 |
IA | -0.417 |
Rosenberg | -0.406 |
cca | -0.373 |
cko | -0.371 |
Token | their |
Token ID | 511 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
phalt | +0.364 |
BELOW | +0.354 |
orrect | +0.341 |
trial | +0.325 |
JUST | +0.323 |
Neg logit contributions | |
Ashes | -0.380 |
IA | -0.380 |
Rosenberg | -0.372 |
cca | -0.351 |
cko | -0.349 |
Token | lives |
Token ID | 3160 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
phalt | +0.255 |
BELOW | +0.248 |
orrect | +0.238 |
trial | +0.227 |
JUST | +0.225 |
Neg logit contributions | |
Ashes | -0.273 |
IA | -0.273 |
Rosenberg | -0.268 |
cca | -0.252 |
cko | -0.251 |
Token | coloring |
Token ID | 33988 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
phalt | +0.349 |
BELOW | +0.339 |
orrect | +0.326 |
trial | +0.310 |
JUST | +0.308 |
Neg logit contributions | |
Ashes | -0.379 |
IA | -0.378 |
Rosenberg | -0.371 |
cca | -0.350 |
cko | -0.348 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
phalt | +1.104 |
BELOW | +1.077 |
orrect | +1.034 |
trial | +0.987 |
JUST | +0.980 |
Neg logit contributions | |
IA | -1.127 |
Ashes | -1.125 |
Rosenberg | -1.101 |
cca | -1.039 |
cko | -1.035 |
Token | diminishing |
Token ID | 35197 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
phalt | +0.173 |
BELOW | +0.168 |
orrect | +0.161 |
trial | +0.154 |
JUST | +0.152 |
Neg logit contributions | |
Ashes | -0.194 |
IA | -0.193 |
Rosenberg | -0.190 |
cca | -0.179 |
cko | -0.178 |
Token | their |
Token ID | 511 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
phalt | +1.330 |
BELOW | +1.296 |
orrect | +1.244 |
trial | +1.186 |
JUST | +1.176 |
Neg logit contributions | |
IA | -1.399 |
Ashes | -1.398 |
Rosenberg | -1.369 |
cca | -1.293 |
cko | -1.290 |
Token | existence |
Token ID | 6224 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Ashes | +0.228 |
IA | +0.227 |
Rosenberg | +0.223 |
cca | +0.210 |
cko | +0.209 |
Neg logit contributions | |
phalt | -0.229 |
BELOW | -0.223 |
orrect | -0.215 |
trial | -0.205 |
JUST | -0.203 |
Token | has |
Token ID | 468 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Ashes | +1.599 |
IA | +1.587 |
Rosenberg | +1.568 |
cca | +1.464 |
cko | +1.450 |
Neg logit contributions | |
phalt | -1.562 |
BELOW | -1.515 |
orrect | -1.460 |
trial | -1.399 |
JUST | -1.391 |
Token | been |
Token ID | 587 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Ashes | +0.879 |
IA | +0.872 |
Rosenberg | +0.860 |
cca | +0.803 |
cko | +0.802 |
Neg logit contributions | |
phalt | -0.828 |
BELOW | -0.805 |
orrect | -0.777 |
trial | -0.745 |
JUST | -0.735 |
Token | lifted |
Token ID | 13663 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
phalt | +0.320 |
BELOW | +0.311 |
orrect | +0.298 |
trial | +0.283 |
JUST | +0.281 |
Neg logit contributions | |
IA | -0.357 |
Ashes | -0.357 |
Rosenberg | -0.350 |
cca | -0.330 |
cko | -0.329 |
Token | and |
Token ID | 290 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
phalt | +0.019 |
BELOW | +0.018 |
orrect | +0.018 |
trial | +0.017 |
JUST | +0.017 |
Neg logit contributions | |
Ashes | -0.019 |
IA | -0.019 |
Rosenberg | -0.019 |
cca | -0.018 |
cko | -0.018 |
Token | M |
Token ID | 44 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
phalt | +0.053 |
BELOW | +0.052 |
orrect | +0.051 |
trial | +0.049 |
conduc | +0.049 |
Neg logit contributions | |
IA | -0.028 |
Ashes | -0.028 |
Rosenberg | -0.027 |
cca | -0.025 |
cko | -0.025 |
Token | recommended |
Token ID | 7151 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
phalt | +0.674 |
BELOW | +0.655 |
orrect | +0.629 |
trial | +0.599 |
JUST | +0.594 |
Neg logit contributions | |
Ashes | -0.764 |
IA | -0.762 |
Rosenberg | -0.748 |
cca | -0.707 |
cko | -0.704 |
Token | that |
Token ID | 326 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Ashes | +0.397 |
IA | +0.395 |
Rosenberg | +0.388 |
cca | +0.365 |
cko | +0.362 |
Neg logit contributions | |
phalt | -0.383 |
BELOW | -0.372 |
orrect | -0.358 |
trial | -0.342 |
JUST | -0.340 |
Token | to |
Token ID | 284 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
Ashes | +0.419 |
IA | +0.418 |
Rosenberg | +0.408 |
cca | +0.386 |
cko | +0.380 |
Neg logit contributions | |
phalt | -0.365 |
BELOW | -0.356 |
orrect | -0.342 |
trial | -0.328 |
JUST | -0.326 |
Token | address |
Token ID | 2209 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
IA | +0.660 |
Ashes | +0.660 |
Rosenberg | +0.646 |
cca | +0.614 |
vre | +0.606 |
Neg logit contributions | |
phalt | -0.577 |
BELOW | -0.561 |
orrect | -0.538 |
trial | -0.515 |
JUST | -0.510 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
IA | +1.103 |
Ashes | +1.098 |
Rosenberg | +1.069 |
cca | +1.010 |
cko | +0.998 |
Neg logit contributions | |
phalt | -0.947 |
BELOW | -0.929 |
orrect | -0.888 |
trial | -0.852 |
JUST | -0.840 |
Token | pressing |
Token ID | 12273 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
IA | +0.011 |
Ashes | +0.011 |
Rosenberg | +0.011 |
cca | +0.010 |
cko | +0.010 |
Neg logit contributions | |
phalt | -0.010 |
BELOW | -0.009 |
orrect | -0.009 |
trial | -0.009 |
JUST | -0.008 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
IA | +0.247 |
Ashes | +0.246 |
Rosenberg | +0.240 |
cca | +0.226 |
cko | +0.222 |
Neg logit contributions | |
phalt | -0.233 |
BELOW | -0.227 |
orrect | -0.219 |
trial | -0.210 |
JUST | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
phalt | +1.320 |
BELOW | +1.282 |
orrect | +1.231 |
trial | +1.165 |
JUST | +1.157 |
Neg logit contributions | |
Ashes | -1.489 |
IA | -1.479 |
Rosenberg | -1.458 |
cko | -1.373 |
cca | -1.373 |
Token | road |
Token ID | 2975 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
phalt | +0.767 |
BELOW | +0.745 |
orrect | +0.713 |
trial | +0.677 |
JUST | +0.672 |
Neg logit contributions | |
Ashes | -0.966 |
IA | -0.965 |
Rosenberg | -0.946 |
cca | -0.896 |
cko | -0.891 |
Token | safety |
Token ID | 3747 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
phalt | +0.339 |
BELOW | +0.330 |
orrect | +0.317 |
trial | +0.303 |
JUST | +0.301 |
Neg logit contributions | |
Ashes | -0.331 |
IA | -0.330 |
Rosenberg | -0.323 |
cca | -0.304 |
cko | -0.303 |
Token | their |
Token ID | 511 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
phalt | +0.685 |
BELOW | +0.663 |
orrect | +0.641 |
trial | +0.612 |
JUST | +0.608 |
Neg logit contributions | |
Ashes | -0.648 |
IA | -0.648 |
Rosenberg | -0.634 |
cca | -0.594 |
cko | -0.592 |
Token | lives |
Token ID | 3160 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
phalt | +0.515 |
BELOW | +0.498 |
orrect | +0.481 |
trial | +0.461 |
JUST | +0.459 |
Neg logit contributions | |
Ashes | -0.449 |
IA | -0.449 |
Rosenberg | -0.440 |
cca | -0.411 |
cko | -0.408 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
phalt | +0.535 |
BELOW | +0.521 |
orrect | +0.502 |
trial | +0.479 |
JUST | +0.476 |
Neg logit contributions | |
Ashes | -0.539 |
IA | -0.538 |
Rosenberg | -0.527 |
cca | -0.496 |
cko | -0.494 |
Token | get |
Token ID | 651 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
phalt | +0.015 |
BELOW | +0.014 |
orrect | +0.014 |
trial | +0.013 |
� | +0.013 |
Neg logit contributions | |
Ashes | -0.015 |
IA | -0.015 |
Rosenberg | -0.015 |
cca | -0.014 |
cko | -0.014 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
phalt | +1.103 |
BELOW | +1.077 |
orrect | +1.032 |
trial | +0.985 |
JUST | +0.978 |
Neg logit contributions | |
Ashes | -1.162 |
IA | -1.160 |
Rosenberg | -1.135 |
cca | -1.071 |
cko | -1.067 |
Token | ened |
Token ID | 2945 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
phalt | +1.404 |
BELOW | +1.387 |
orrect | +1.316 |
� | +1.268 |
trial | +1.261 |
Neg logit contributions | |
Ashes | -1.193 |
IA | -1.189 |
Rosenberg | -1.161 |
cko | -1.091 |
cca | -1.078 |
Token | out |
Token ID | 503 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
phalt | +0.650 |
BELOW | +0.632 |
orrect | +0.604 |
trial | +0.573 |
JUST | +0.568 |
Neg logit contributions | |
Ashes | -0.808 |
IA | -0.807 |
Rosenberg | -0.792 |
cca | -0.750 |
cko | -0.748 |
Token | . |
Token ID | 13 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
IA | +0.990 |
Ashes | +0.989 |
Rosenberg | +0.974 |
cca | +0.914 |
cko | +0.905 |
Neg logit contributions | |
phalt | -1.010 |
BELOW | -0.971 |
orrect | -0.941 |
trial | -0.899 |
JUST | -0.894 |
Token | � |
Token ID | 447 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
phalt | +0.039 |
BELOW | +0.038 |
orrect | +0.037 |
trial | +0.035 |
JUST | +0.034 |
Neg logit contributions | |
Ashes | -0.046 |
IA | -0.046 |
Rosenberg | -0.045 |
cca | -0.042 |
cko | -0.042 |
Token | � |
Token ID | 251 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
phalt | +0.112 |
BELOW | +0.109 |
orrect | +0.105 |
trial | +0.099 |
JUST | +0.099 |
Neg logit contributions | |
Ashes | -0.138 |
IA | -0.137 |
Rosenberg | -0.135 |
cca | -0.127 |
cko | -0.127 |
Token | They |
Token ID | 1119 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
Ashes | +0.203 |
IA | +0.203 |
Rosenberg | +0.200 |
cca | +0.188 |
cko | +0.187 |
Neg logit contributions | |
phalt | -0.175 |
BELOW | -0.168 |
orrect | -0.163 |
trial | -0.154 |
JUST | -0.152 |
Token | assumption |
Token ID | 13196 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Ashes | +0.254 |
IA | +0.254 |
Rosenberg | +0.249 |
cca | +0.235 |
cko | +0.233 |
Neg logit contributions | |
phalt | -0.234 |
BELOW | -0.227 |
orrect | -0.218 |
trial | -0.208 |
JUST | -0.206 |
Token | that |
Token ID | 326 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
phalt | +0.551 |
BELOW | +0.537 |
orrect | +0.518 |
trial | +0.493 |
JUST | +0.490 |
Neg logit contributions | |
Ashes | -0.565 |
IA | -0.562 |
Rosenberg | -0.550 |
cca | -0.519 |
cko | -0.518 |
Token | every |
Token ID | 790 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Ashes | +0.432 |
IA | +0.431 |
Rosenberg | +0.423 |
cca | +0.398 |
cko | +0.396 |
Neg logit contributions | |
phalt | -0.409 |
BELOW | -0.398 |
orrect | -0.383 |
trial | -0.365 |
JUST | -0.362 |
Token | free |
Token ID | 1479 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
IA | +0.516 |
Ashes | +0.516 |
Rosenberg | +0.506 |
cca | +0.477 |
cko | +0.474 |
Neg logit contributions | |
phalt | -0.477 |
BELOW | -0.463 |
orrect | -0.446 |
trial | -0.426 |
JUST | -0.421 |
Token | - |
Token ID | 12 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
phalt | +0.872 |
BELOW | +0.846 |
orrect | +0.814 |
trial | +0.772 |
JUST | +0.767 |
Neg logit contributions | |
IA | -0.992 |
Ashes | -0.991 |
Rosenberg | -0.972 |
cca | -0.919 |
cko | -0.914 |
Token | trade |
Token ID | 25351 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
phalt | +0.841 |
BELOW | +0.814 |
orrect | +0.776 |
trial | +0.728 |
JUST | +0.724 |
Neg logit contributions | |
IA | -1.198 |
Ashes | -1.195 |
Rosenberg | -1.176 |
cca | -1.120 |
cko | -1.112 |
Token | agreement |
Token ID | 4381 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
phalt | +1.642 |
BELOW | +1.614 |
orrect | +1.566 |
trial | +1.512 |
JUST | +1.506 |
Neg logit contributions | |
Ashes | -0.896 |
IA | -0.889 |
Rosenberg | -0.866 |
cca | -0.790 |
cko | -0.788 |
Token | is |
Token ID | 318 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
phalt | +0.801 |
BELOW | +0.784 |
orrect | +0.751 |
trial | +0.716 |
JUST | +0.713 |
Neg logit contributions | |
Ashes | -0.838 |
IA | -0.833 |
Rosenberg | -0.816 |
cca | -0.769 |
cko | -0.767 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
IA | +0.154 |
Ashes | +0.154 |
Rosenberg | +0.152 |
cca | +0.144 |
cko | +0.143 |
Neg logit contributions | |
phalt | -0.128 |
BELOW | -0.124 |
orrect | -0.120 |
trial | -0.114 |
JUST | -0.112 |
Token | loser |
Token ID | 30256 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
phalt | +0.090 |
BELOW | +0.087 |
orrect | +0.084 |
trial | +0.080 |
JUST | +0.079 |
Neg logit contributions | |
Ashes | -0.095 |
IA | -0.095 |
Rosenberg | -0.093 |
cca | -0.087 |
cko | -0.087 |
Token | for |
Token ID | 329 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
phalt | +0.525 |
BELOW | +0.510 |
orrect | +0.490 |
trial | +0.468 |
JUST | +0.465 |
Neg logit contributions | |
Ashes | -0.555 |
IA | -0.553 |
Rosenberg | -0.544 |
cca | -0.511 |
cko | -0.510 |
Token | Trophy |
Token ID | 25640 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
phalt | +0.908 |
BELOW | +0.889 |
orrect | +0.860 |
trial | +0.827 |
JUST | +0.821 |
Neg logit contributions | |
Ashes | -0.699 |
IA | -0.693 |
Rosenberg | -0.691 |
cko | -0.643 |
cca | -0.641 |
Token | on |
Token ID | 319 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Ashes | +0.410 |
IA | +0.410 |
Rosenberg | +0.402 |
cca | +0.380 |
cko | +0.378 |
Neg logit contributions | |
phalt | -0.348 |
BELOW | -0.334 |
orrect | -0.323 |
trial | -0.307 |
JUST | -0.303 |
Token | home |
Token ID | 1363 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
phalt | +0.155 |
BELOW | +0.150 |
orrect | +0.144 |
trial | +0.136 |
JUST | +0.135 |
Neg logit contributions | |
Ashes | -0.190 |
IA | -0.189 |
Rosenberg | -0.186 |
cca | -0.176 |
cko | -0.175 |
Token | ice |
Token ID | 4771 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
phalt | +0.423 |
BELOW | +0.410 |
orrect | +0.392 |
trial | +0.374 |
JUST | +0.370 |
Neg logit contributions | |
Ashes | -0.547 |
IA | -0.547 |
Rosenberg | -0.538 |
cca | -0.510 |
cko | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Ashes | +0.250 |
IA | +0.249 |
Rosenberg | +0.245 |
cca | +0.231 |
cko | +0.230 |
Neg logit contributions | |
phalt | -0.208 |
BELOW | -0.201 |
orrect | -0.193 |
trial | -0.183 |
JUST | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
phalt | +0.975 |
BELOW | +0.947 |
orrect | +0.910 |
trial | +0.866 |
JUST | +0.860 |
Neg logit contributions | |
Ashes | -1.086 |
IA | -1.084 |
Rosenberg | -1.064 |
cca | -1.003 |
cko | -0.999 |
Token | Caps |
Token ID | 23534 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
phalt | +0.947 |
BELOW | +0.923 |
orrect | +0.888 |
trial | +0.849 |
JUST | +0.842 |
Neg logit contributions | |
Ashes | -0.937 |
IA | -0.936 |
Rosenberg | -0.917 |
cca | -0.863 |
cko | -0.859 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
IA | +0.083 |
Ashes | +0.083 |
Rosenberg | +0.082 |
cca | +0.077 |
cko | +0.076 |
Neg logit contributions | |
phalt | -0.073 |
BELOW | -0.069 |
orrect | -0.067 |
trial | -0.064 |
JUST | -0.064 |
Token | � |
Token ID | 447 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
phalt | +0.132 |
BELOW | +0.129 |
orrect | +0.124 |
trial | +0.119 |
JUST | +0.118 |
Neg logit contributions | |
Ashes | -0.114 |
IA | -0.114 |
Rosenberg | -0.112 |
cca | -0.105 |
cko | -0.104 |
Token | � |
Token ID | 247 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Ashes | +0.190 |
IA | +0.190 |
Rosenberg | +0.186 |
cca | +0.176 |
cko | +0.176 |
Neg logit contributions | |
phalt | -0.147 |
BELOW | -0.142 |
orrect | -0.136 |
trial | -0.129 |
JUST | -0.128 |
Token | t |
Token ID | 83 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
phalt | +0.265 |
BELOW | +0.259 |
orrect | +0.251 |
trial | +0.242 |
JUST | +0.240 |
Neg logit contributions | |
Ashes | -0.180 |
IA | -0.180 |
Rosenberg | -0.176 |
cca | -0.163 |
cko | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
phalt | +0.244 |
BELOW | +0.236 |
orrect | +0.226 |
trial | +0.215 |
JUST | +0.213 |
Neg logit contributions | |
Ashes | -0.303 |
IA | -0.302 |
Rosenberg | -0.297 |
cca | -0.281 |
cko | -0.279 |
Token | Meg |
Token ID | 8336 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
phalt | +0.720 |
BELOW | +0.699 |
orrect | +0.671 |
trial | +0.639 |
JUST | +0.633 |
Neg logit contributions | |
Ashes | -0.822 |
IA | -0.821 |
Rosenberg | -0.806 |
cca | -0.761 |
cko | -0.758 |
Token | arian |
Token ID | 3699 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
phalt | +0.978 |
BELOW | +0.949 |
orrect | +0.918 |
trial | +0.878 |
JUST | +0.867 |
Neg logit contributions | |
Ashes | -0.904 |
IA | -0.902 |
Rosenberg | -0.880 |
cca | -0.828 |
cko | -0.824 |
Token | school |
Token ID | 1524 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
IA | +0.510 |
Ashes | +0.510 |
Rosenberg | +0.499 |
cca | +0.473 |
cko | +0.468 |
Neg logit contributions | |
phalt | -0.450 |
BELOW | -0.438 |
orrect | -0.420 |
trial | -0.399 |
JUST | -0.397 |
Token | : |
Token ID | 25 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
phalt | +0.905 |
BELOW | +0.879 |
orrect | +0.846 |
trial | +0.806 |
JUST | +0.796 |
Neg logit contributions | |
Ashes | -1.033 |
IA | -1.030 |
Rosenberg | -1.011 |
cko | -0.953 |
cca | -0.952 |
Token | only |
Token ID | 8807 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
phalt | +0.103 |
BELOW | +0.100 |
orrect | +0.097 |
trial | +0.092 |
JUST | +0.091 |
Neg logit contributions | |
Ashes | -0.111 |
IA | -0.111 |
Rosenberg | -0.109 |
cca | -0.103 |
cko | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
phalt | +0.581 |
BELOW | +0.565 |
orrect | +0.542 |
trial | +0.516 |
JUST | +0.511 |
Neg logit contributions | |
Ashes | -0.665 |
IA | -0.664 |
Rosenberg | -0.651 |
cca | -0.616 |
cko | -0.613 |
Token | multiple |
Token ID | 3294 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
phalt | +1.426 |
BELOW | +1.392 |
orrect | +1.335 |
trial | +1.267 |
JUST | +1.253 |
Neg logit contributions | |
IA | -1.601 |
Ashes | -1.599 |
Rosenberg | -1.565 |
cca | -1.482 |
cko | -1.481 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
phalt | +0.286 |
BELOW | +0.278 |
orrect | +0.267 |
trial | +0.254 |
JUST | +0.251 |
Neg logit contributions | |
Ashes | -0.339 |
IA | -0.338 |
Rosenberg | -0.332 |
cca | -0.314 |
cko | -0.313 |
Token | affirmative |
Token ID | 27990 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
IA | +0.757 |
Ashes | +0.757 |
Rosenberg | +0.743 |
cca | +0.702 |
cko | +0.698 |
Neg logit contributions | |
phalt | -0.670 |
BELOW | -0.651 |
orrect | -0.626 |
trial | -0.596 |
JUST | -0.593 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Ashes | +0.039 |
IA | +0.039 |
Rosenberg | +0.039 |
cca | +0.036 |
cko | +0.036 |
Neg logit contributions | |
phalt | -0.035 |
BELOW | -0.034 |
orrect | -0.032 |
trial | -0.031 |
JUST | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
phalt | +0.075 |
BELOW | +0.073 |
orrect | +0.070 |
trial | +0.067 |
JUST | +0.066 |
Neg logit contributions | |
Ashes | -0.078 |
IA | -0.078 |
Rosenberg | -0.076 |
cca | -0.072 |
cko | -0.072 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
IA | +1.883 |
Ashes | +1.878 |
Rosenberg | +1.850 |
cca | +1.741 |
cko | +1.733 |
Neg logit contributions | |
phalt | -1.569 |
BELOW | -1.515 |
orrect | -1.478 |
trial | -1.399 |
JUST | -1.390 |
Token | There |
Token ID | 1858 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
phalt | +0.587 |
BELOW | +0.573 |
orrect | +0.553 |
trial | +0.532 |
JUST | +0.529 |
Neg logit contributions | |
Ashes | -0.498 |
IA | -0.495 |
Rosenberg | -0.486 |
cca | -0.454 |
cko | -0.452 |
Token | is |
Token ID | 318 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
IA | +1.068 |
Ashes | +1.065 |
Rosenberg | +1.045 |
cca | +0.984 |
cko | +0.980 |
Neg logit contributions | |
phalt | -1.052 |
BELOW | -1.026 |
orrect | -0.987 |
trial | -0.944 |
JUST | -0.936 |
Token | currently |
Token ID | 3058 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Ashes | +0.144 |
IA | +0.143 |
Rosenberg | +0.141 |
cca | +0.132 |
cko | +0.132 |
Neg logit contributions | |
phalt | -0.125 |
BELOW | -0.121 |
orrect | -0.116 |
trial | -0.111 |
JUST | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
phalt | +0.985 |
BELOW | +0.961 |
orrect | +0.920 |
trial | +0.872 |
JUST | +0.867 |
Neg logit contributions | |
Ashes | -1.206 |
IA | -1.201 |
Rosenberg | -1.183 |
cca | -1.123 |
cko | -1.113 |
Token | stal |
Token ID | 29049 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
phalt | +0.544 |
BELOW | +0.530 |
orrect | +0.510 |
trial | +0.487 |
JUST | +0.483 |
Neg logit contributions | |
Ashes | -0.586 |
IA | -0.584 |
Rosenberg | -0.574 |
cca | -0.541 |
cko | -0.539 |
Token | emate |
Token ID | 47686 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
phalt | +0.358 |
BELOW | +0.348 |
orrect | +0.335 |
trial | +0.319 |
JUST | +0.316 |
Neg logit contributions | |
Ashes | -0.390 |
IA | -0.389 |
Rosenberg | -0.382 |
cca | -0.360 |
cko | -0.358 |
Token | between |
Token ID | 1022 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
Ashes | +0.553 |
IA | +0.552 |
Rosenberg | +0.543 |
cca | +0.514 |
cko | +0.510 |
Neg logit contributions | |
phalt | -0.440 |
BELOW | -0.422 |
orrect | -0.407 |
trial | -0.384 |
JUST | -0.383 |
Token | Yahoo |
Token ID | 16551 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Ashes | +0.527 |
IA | +0.525 |
Rosenberg | +0.516 |
cca | +0.484 |
cko | +0.482 |
Neg logit contributions | |
phalt | -0.488 |
BELOW | -0.473 |
orrect | -0.455 |
trial | -0.434 |
JUST | -0.431 |
Token | and |
Token ID | 290 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
phalt | +0.470 |
BELOW | +0.456 |
orrect | +0.437 |
trial | +0.414 |
JUST | +0.410 |
Neg logit contributions | |
Ashes | -0.590 |
IA | -0.588 |
Rosenberg | -0.579 |
cca | -0.548 |
cko | -0.544 |
Token | Message |
Token ID | 12837 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
phalt | +0.695 |
BELOW | +0.683 |
orrect | +0.662 |
trial | +0.640 |
JUST | +0.635 |
Neg logit contributions | |
Ashes | -0.552 |
IA | -0.541 |
Rosenberg | -0.539 |
cca | -0.500 |
vre | -0.499 |
Token | )" |
Token ID | 16725 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
Ashes | +0.159 |
IA | +0.158 |
Rosenberg | +0.156 |
cca | +0.146 |
cko | +0.144 |
Neg logit contributions | |
phalt | -0.183 |
BELOW | -0.180 |
orrect | -0.173 |
trial | -0.166 |
JUST | -0.164 |
Token | break |
Token ID | 2270 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
phalt | +0.529 |
BELOW | +0.523 |
orrect | +0.497 |
trial | +0.470 |
JUST | +0.469 |
Neg logit contributions | |
IA | -0.610 |
Ashes | -0.610 |
Rosenberg | -0.599 |
cca | -0.568 |
vre | -0.565 |
Token | } |
Token ID | 1782 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
phalt | +1.763 |
BELOW | +1.755 |
orrect | +1.632 |
trial | +1.564 |
JUST | +1.554 |
Neg logit contributions | |
IA | -2.252 |
Ashes | -2.238 |
Rosenberg | -2.200 |
ゼウス | -2.112 |
vre | -2.108 |
Token | } |
Token ID | 1782 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
phalt | +1.799 |
BELOW | +1.779 |
orrect | +1.666 |
JUST | +1.591 |
trial | +1.588 |
Neg logit contributions | |
IA | -2.140 |
Ashes | -2.132 |
Rosenberg | -2.092 |
cca | -2.000 |
ゼウス | -1.991 |
Token | Process |
Token ID | 10854 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
phalt | +1.860 |
BELOW | +1.837 |
orrect | +1.730 |
trial | +1.653 |
JUST | +1.650 |
Neg logit contributions | |
IA | -2.083 |
Ashes | -2.078 |
Rosenberg | -2.038 |
cca | -1.938 |
ゼウス | -1.931 |
Token | { |
Token ID | 1391 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
phalt | +3.427 |
BELOW | +3.362 |
orrect | +3.215 |
JUST | +3.050 |
trial | +3.032 |
Neg logit contributions | |
Ashes | -3.877 |
Rosenberg | -3.846 |
IA | -3.824 |
ゼウス | -3.644 |
cca | -3.640 |
Token | # |
Token ID | 1303 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Ashes | +0.260 |
IA | +0.260 |
Rosenberg | +0.255 |
cca | +0.240 |
cko | +0.239 |
Neg logit contributions | |
phalt | -0.232 |
BELOW | -0.226 |
orrect | -0.217 |
trial | -0.207 |
JUST | -0.205 |
Token | Split |
Token ID | 27758 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Ashes | +1.126 |
IA | +1.123 |
Rosenberg | +1.100 |
cca | +1.037 |
cko | +1.031 |
Neg logit contributions | |
phalt | -1.027 |
BELOW | -0.991 |
orrect | -0.958 |
trial | -0.915 |
JUST | -0.901 |
Token | our |
Token ID | 674 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
phalt | +1.638 |
BELOW | +1.589 |
orrect | +1.519 |
trial | +1.441 |
JUST | +1.428 |
Neg logit contributions | |
IA | -1.881 |
Ashes | -1.874 |
Rosenberg | -1.849 |
cca | -1.750 |
cko | -1.741 |
Token | string |
Token ID | 4731 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
phalt | +0.541 |
BELOW | +0.525 |
orrect | +0.504 |
trial | +0.480 |
JUST | +0.476 |
Neg logit contributions | |
Ashes | -0.610 |
IA | -0.610 |
Rosenberg | -0.598 |
cca | -0.565 |
cko | -0.563 |
Token | ages |
Token ID | 1095 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
IA | +0.263 |
Ashes | +0.262 |
Rosenberg | +0.246 |
cca | +0.219 |
cko | +0.215 |
Neg logit contributions | |
phalt | -0.785 |
BELOW | -0.768 |
orrect | -0.748 |
conduc | -0.729 |
trial | -0.728 |
Token | h |
Token ID | 71 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
phalt | +0.648 |
BELOW | +0.631 |
orrect | +0.609 |
trial | +0.585 |
JUST | +0.580 |
Neg logit contributions | |
Ashes | -0.621 |
IA | -0.619 |
Rosenberg | -0.610 |
ゼウス | -0.566 |
cko | -0.564 |
Token | war |
Token ID | 5767 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Ashes | +0.008 |
IA | +0.008 |
Rosenberg | +0.008 |
cko | +0.007 |
cca | +0.007 |
Neg logit contributions | |
phalt | -0.018 |
BELOW | -0.017 |
orrect | -0.017 |
trial | -0.016 |
JUST | -0.016 |
Token | J |
Token ID | 449 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Ashes | +0.087 |
IA | +0.087 |
Rosenberg | +0.085 |
cca | +0.080 |
cko | +0.080 |
Neg logit contributions | |
phalt | -0.093 |
BELOW | -0.090 |
orrect | -0.087 |
trial | -0.084 |
JUST | -0.083 |
Token | y |
Token ID | 88 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
phalt | +1.046 |
BELOW | +1.019 |
orrect | +0.984 |
trial | +0.942 |
JUST | +0.932 |
Neg logit contributions | |
Ashes | -1.036 |
IA | -1.029 |
Rosenberg | -1.013 |
cca | -0.948 |
cko | -0.944 |
Token | ot |
Token ID | 313 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
phalt | +0.012 |
BELOW | +0.012 |
orrect | +0.011 |
trial | +0.011 |
JUST | +0.011 |
Neg logit contributions | |
Ashes | -0.011 |
IA | -0.011 |
Rosenberg | -0.011 |
cca | -0.010 |
cko | -0.010 |
Token | irling |
Token ID | 24297 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
phalt | +2.992 |
BELOW | +2.872 |
orrect | +2.806 |
trial | +2.633 |
JUST | +2.610 |
Neg logit contributions | |
Ashes | -3.571 |
IA | -3.510 |
Rosenberg | -3.460 |
ゼウス | -3.329 |
Unicorn | -3.256 |
Token | a |
Token ID | 64 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
phalt | +1.439 |
BELOW | +1.414 |
orrect | +1.360 |
trial | +1.309 |
JUST | +1.292 |
Neg logit contributions | |
Ashes | -1.213 |
IA | -1.200 |
Rosenberg | -1.191 |
cko | -1.099 |
ゼウス | -1.097 |
Token | Temple |
Token ID | 10857 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
phalt | +1.799 |
BELOW | +1.781 |
orrect | +1.691 |
trial | +1.631 |
JUST | +1.617 |
Neg logit contributions | |
IA | -1.701 |
Ashes | -1.700 |
Rosenberg | -1.662 |
ゼウス | -1.563 |
cko | -1.561 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
BELOW | +1.895 |
phalt | +1.891 |
orrect | +1.704 |
� | +1.589 |
trial | +1.582 |
Neg logit contributions | |
IA | -4.119 |
Ashes | -4.083 |
Rosenberg | -4.032 |
ゼウス | -3.890 |
cko | -3.884 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
phalt | +0.902 |
BELOW | +0.889 |
orrect | +0.840 |
JUST | +0.802 |
trial | +0.802 |
Neg logit contributions | |
Ashes | -1.200 |
IA | -1.192 |
Rosenberg | -1.176 |
cca | -1.113 |
cko | -1.110 |
Token | new |
Token ID | 649 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
phalt | +0.664 |
BELOW | +0.644 |
orrect | +0.616 |
trial | +0.584 |
JUST | +0.579 |
Neg logit contributions | |
Ashes | -0.847 |
IA | -0.846 |
Rosenberg | -0.831 |
cca | -0.787 |
cko | -0.784 |
Token | one |
Token ID | 530 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
phalt | +0.765 |
BELOW | +0.743 |
orrect | +0.713 |
trial | +0.678 |
JUST | +0.673 |
Neg logit contributions | |
Ashes | -0.883 |
IA | -0.882 |
Rosenberg | -0.866 |
cca | -0.818 |
cko | -0.814 |
Token | could |
Token ID | 714 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
phalt | +0.775 |
BELOW | +0.755 |
orrect | +0.727 |
trial | +0.690 |
JUST | +0.684 |
Neg logit contributions | |
Ashes | -0.850 |
IA | -0.850 |
Rosenberg | -0.831 |
cca | -0.788 |
cko | -0.783 |
Token | shed |
Token ID | 14999 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
phalt | +1.341 |
BELOW | +1.308 |
orrect | +1.260 |
trial | +1.197 |
JUST | +1.192 |
Neg logit contributions | |
IA | -1.348 |
Ashes | -1.347 |
Rosenberg | -1.320 |
cca | -1.241 |
cko | -1.239 |
Token | some |
Token ID | 617 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
phalt | +0.702 |
BELOW | +0.679 |
orrect | +0.650 |
trial | +0.611 |
JUST | +0.606 |
Neg logit contributions | |
IA | -1.041 |
Ashes | -1.039 |
Rosenberg | -1.022 |
cca | -0.972 |
cko | -0.970 |
Token | light |
Token ID | 1657 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
phalt | +0.547 |
BELOW | +0.528 |
orrect | +0.503 |
trial | +0.471 |
JUST | +0.467 |
Neg logit contributions | |
IA | -0.886 |
Ashes | -0.885 |
Rosenberg | -0.871 |
cca | -0.831 |
cko | -0.828 |
Token | on |
Token ID | 319 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
phalt | +2.354 |
BELOW | +2.314 |
orrect | +2.203 |
JUST | +2.065 |
trial | +2.064 |
Neg logit contributions | |
Ashes | -3.445 |
IA | -3.433 |
Rosenberg | -3.346 |
cko | -3.222 |
cca | -3.201 |
Token | what |
Token ID | 644 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
phalt | +0.189 |
BELOW | +0.184 |
orrect | +0.176 |
trial | +0.167 |
JUST | +0.166 |
Neg logit contributions | |
Ashes | -0.222 |
IA | -0.222 |
Rosenberg | -0.217 |
cca | -0.206 |
cko | -0.205 |
Token | happened |
Token ID | 3022 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
phalt | +0.572 |
BELOW | +0.555 |
orrect | +0.534 |
trial | +0.507 |
JUST | +0.504 |
Neg logit contributions | |
Ashes | -0.657 |
IA | -0.656 |
Rosenberg | -0.643 |
cca | -0.609 |
cko | -0.606 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
phalt | +2.135 |
BELOW | +2.089 |
orrect | +2.015 |
trial | +1.917 |
JUST | +1.905 |
Neg logit contributions | |
Ashes | -2.433 |
IA | -2.423 |
Rosenberg | -2.336 |
cko | -2.277 |
cca | -2.253 |
Token |
|
Token ID | 198 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
phalt | +0.140 |
BELOW | +0.137 |
orrect | +0.130 |
trial | +0.124 |
JUST | +0.124 |
Neg logit contributions | |
IA | -0.178 |
Ashes | -0.178 |
Rosenberg | -0.173 |
cca | -0.166 |
cko | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Ashes | +0.599 |
IA | +0.597 |
Rosenberg | +0.586 |
cca | +0.549 |
cko | +0.547 |
Neg logit contributions | |
phalt | -0.603 |
BELOW | -0.584 |
orrect | -0.563 |
trial | -0.539 |
JUST | -0.534 |
Token |
|
Token ID | 198 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
Ashes | +1.093 |
IA | +1.081 |
Rosenberg | +1.066 |
cca | +0.993 |
cko | +0.987 |
Neg logit contributions | |
phalt | -0.996 |
BELOW | -0.946 |
orrect | -0.922 |
trial | -0.878 |
conduc | -0.873 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
phalt | +0.058 |
BELOW | +0.056 |
orrect | +0.054 |
trial | +0.051 |
JUST | +0.050 |
Neg logit contributions | |
IA | -0.069 |
Ashes | -0.069 |
Rosenberg | -0.068 |
cca | -0.064 |
cko | -0.064 |
Token | Mus |
Token ID | 10694 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
phalt | +0.169 |
BELOW | +0.164 |
orrect | +0.159 |
trial | +0.152 |
JUST | +0.150 |
Neg logit contributions | |
IA | -0.140 |
Ashes | -0.139 |
Rosenberg | -0.136 |
cca | -0.127 |
cko | -0.126 |
Token | ically |
Token ID | 1146 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Ashes | +0.355 |
IA | +0.355 |
Rosenberg | +0.348 |
cca | +0.329 |
cko | +0.328 |
Neg logit contributions | |
phalt | -0.319 |
BELOW | -0.311 |
orrect | -0.298 |
trial | -0.284 |
JUST | -0.282 |
Token | speaking |
Token ID | 5486 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Ashes | +0.394 |
IA | +0.391 |
Rosenberg | +0.385 |
cca | +0.362 |
cko | +0.356 |
Neg logit contributions | |
phalt | -0.341 |
BELOW | -0.328 |
orrect | -0.316 |
trial | -0.302 |
JUST | -0.298 |
Token | everyone |
Token ID | 2506 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
phalt | +2.924 |
BELOW | +2.917 |
orrect | +2.754 |
JUST | +2.598 |
� | +2.593 |
Neg logit contributions | |
IA | -4.072 |
Ashes | -4.006 |
Rosenberg | -3.980 |
cca | -3.864 |
cko | -3.862 |
Token | in |
Token ID | 287 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Ashes | +0.472 |
IA | +0.470 |
Rosenberg | +0.463 |
cca | +0.436 |
cko | +0.432 |
Neg logit contributions | |
phalt | -0.439 |
BELOW | -0.423 |
orrect | -0.410 |
trial | -0.389 |
JUST | -0.387 |
Token | G |
Token ID | 402 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
phalt | +1.157 |
BELOW | +1.130 |
orrect | +1.082 |
trial | +1.026 |
JUST | +1.018 |
Neg logit contributions | |
IA | -1.472 |
Ashes | -1.470 |
Rosenberg | -1.445 |
cca | -1.374 |
cko | -1.370 |
Token | WAR |
Token ID | 16279 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
IA | +0.356 |
Ashes | +0.353 |
Rosenberg | +0.341 |
cca | +0.305 |
cko | +0.303 |
Neg logit contributions | |
phalt | -0.876 |
BELOW | -0.859 |
orrect | -0.837 |
trial | -0.810 |
JUST | -0.804 |
Token | has |
Token ID | 468 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
phalt | +0.505 |
BELOW | +0.494 |
orrect | +0.473 |
trial | +0.452 |
JUST | +0.449 |
Neg logit contributions | |
Ashes | -0.545 |
IA | -0.543 |
Rosenberg | -0.534 |
cca | -0.505 |
cko | -0.504 |
Token | dawn |
Token ID | 17577 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Ashes | +0.218 |
IA | +0.217 |
Rosenberg | +0.213 |
cca | +0.201 |
cko | +0.200 |
Neg logit contributions | |
phalt | -0.188 |
BELOW | -0.183 |
orrect | -0.176 |
trial | -0.168 |
JUST | -0.166 |
Token | - |
Token ID | 12 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
phalt | +0.174 |
BELOW | +0.168 |
orrect | +0.162 |
trial | +0.153 |
JUST | +0.152 |
Neg logit contributions | |
Ashes | -0.205 |
IA | -0.204 |
Rosenberg | -0.200 |
cca | -0.190 |
cko | -0.189 |
Token | to |
Token ID | 1462 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
IA | +0.143 |
Ashes | +0.143 |
Rosenberg | +0.139 |
cca | +0.130 |
cko | +0.130 |
Neg logit contributions | |
phalt | -0.175 |
BELOW | -0.170 |
orrect | -0.164 |
trial | -0.156 |
JUST | -0.156 |
Token | - |
Token ID | 12 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
phalt | +0.853 |
BELOW | +0.828 |
orrect | +0.794 |
trial | +0.754 |
JUST | +0.748 |
Neg logit contributions | |
Ashes | -1.031 |
IA | -1.029 |
Rosenberg | -1.011 |
cca | -0.955 |
cko | -0.952 |
Token | d |
Token ID | 67 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
IA | +0.300 |
Ashes | +0.298 |
Rosenberg | +0.292 |
cca | +0.275 |
cko | +0.274 |
Neg logit contributions | |
phalt | -0.314 |
BELOW | -0.306 |
orrect | -0.294 |
trial | -0.279 |
JUST | -0.278 |
Token | usk |
Token ID | 17990 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
phalt | +1.161 |
BELOW | +1.129 |
orrect | +1.089 |
trial | +1.042 |
JUST | +1.034 |
Neg logit contributions | |
Ashes | -1.092 |
IA | -1.089 |
Rosenberg | -1.069 |
cca | -1.001 |
cko | -0.997 |
Token | park |
Token ID | 3952 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
phalt | +2.670 |
BELOW | +2.581 |
orrect | +2.463 |
JUST | +2.330 |
trial | +2.320 |
Neg logit contributions | |
IA | -3.311 |
Ashes | -3.295 |
Rosenberg | -3.256 |
cca | -3.117 |
vre | -3.098 |
Token | hours |
Token ID | 2250 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Ashes | +0.221 |
IA | +0.221 |
Rosenberg | +0.217 |
cca | +0.205 |
cko | +0.205 |
Neg logit contributions | |
phalt | -0.180 |
BELOW | -0.174 |
orrect | -0.167 |
trial | -0.159 |
JUST | -0.157 |
Token | at |
Token ID | 379 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
phalt | +0.779 |
BELOW | +0.754 |
orrect | +0.728 |
trial | +0.693 |
JUST | +0.687 |
Neg logit contributions | |
IA | -0.841 |
Ashes | -0.841 |
Rosenberg | -0.825 |
cca | -0.777 |
cko | -0.773 |
Token | Battery |
Token ID | 23490 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Ashes | +0.373 |
IA | +0.372 |
Rosenberg | +0.365 |
cca | +0.342 |
cko | +0.340 |
Neg logit contributions | |
phalt | -0.392 |
BELOW | -0.381 |
orrect | -0.369 |
trial | -0.352 |
JUST | -0.350 |
Token | Park |
Token ID | 3250 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
IA | +1.405 |
Ashes | +1.402 |
Rosenberg | +1.382 |
cca | +1.309 |
cko | +1.301 |
Neg logit contributions | |
phalt | -1.047 |
BELOW | -1.007 |
orrect | -0.973 |
trial | -0.924 |
conduc | -0.910 |