Token | December |
Token ID | 3426 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Philipp | +2.898 |
TE | +2.890 |
Soda | +2.867 |
Sel | +2.796 |
CONFIG | +2.732 |
Neg logit contributions | |
interstitial | -7.492 |
ebus | -7.002 |
�� | -6.776 |
agara | -6.607 |
Cu | -6.490 |
Token | 13 |
Token ID | 1511 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Philipp | +2.627 |
HEL | +2.546 |
Soda | +2.512 |
Sel | +2.504 |
Whe | +2.502 |
Neg logit contributions | |
interstitial | -3.939 |
ebus | -3.754 |
�� | -3.565 |
agara | -3.459 |
Cu | -3.440 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Philipp | +3.226 |
TE | +3.153 |
HEL | +3.145 |
Whe | +3.125 |
Sel | +3.110 |
Neg logit contributions | |
interstitial | -6.613 |
ebus | -6.178 |
�� | -6.096 |
avorite | -5.921 |
agara | -5.835 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Philipp | +3.946 |
HEL | +3.860 |
Whe | +3.821 |
TE | +3.820 |
Sel | +3.757 |
Neg logit contributions | |
interstitial | -4.948 |
ebus | -4.509 |
�� | -4.443 |
agara | -4.278 |
avorite | -4.270 |
Token | boys |
Token ID | 13202 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
wic | +1.147 |
Philipp | +1.135 |
TE | +1.133 |
HEL | +1.125 |
CONFIG | +1.050 |
Neg logit contributions | |
interstitial | -4.658 |
ebus | -4.559 |
�� | -4.475 |
agara | -4.296 |
�� | -4.262 |
Token | beware |
Token ID | 40600 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
interstitial | +3.597 |
ebus | +3.478 |
�� | +3.240 |
agara | +3.232 |
Cu | +3.188 |
Neg logit contributions | |
Philipp | -2.672 |
Soda | -2.583 |
HEL | -2.576 |
Whe | -2.514 |
Sel | -2.504 |
Token |
|
Token ID | 198 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Philipp | +7.624 |
TE | +7.495 |
Sel | +7.456 |
Soda | +7.384 |
Dear | +7.360 |
Neg logit contributions | |
interstitial | -12.387 |
ebus | -12.386 |
�� | -11.839 |
agara | -11.389 |
EVA | -11.196 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
interstitial | +0.155 |
ebus | +0.149 |
�� | +0.136 |
Cu | +0.136 |
agara | +0.134 |
Neg logit contributions | |
Philipp | -0.161 |
HEL | -0.156 |
Soda | -0.156 |
Whe | -0.153 |
TE | -0.152 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Philipp | +0.484 |
HEL | +0.475 |
Soda | +0.471 |
TE | +0.465 |
Whe | +0.465 |
Neg logit contributions | |
interstitial | -1.000 |
ebus | -0.982 |
�� | -0.938 |
agara | -0.911 |
EVA | -0.894 |
Token | : |
Token ID | 25 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
interstitial | +2.300 |
ebus | +2.276 |
Cu | +2.113 |
mare | +2.038 |
EVA | +2.025 |
Neg logit contributions | |
Philipp | -2.444 |
HEL | -2.373 |
Soda | -2.371 |
CONFIG | -2.316 |
Whe | -2.310 |
Token | j |
Token ID | 474 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Philipp | +1.147 |
HEL | +1.117 |
Soda | +1.108 |
Whe | +1.096 |
TE | +1.094 |
Neg logit contributions | |
interstitial | -1.508 |
ebus | -1.443 |
�� | -1.349 |
agara | -1.324 |
Cu | -1.320 |
Token | active |
Token ID | 4075 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Philipp | +1.724 |
HEL | +1.693 |
TE | +1.671 |
Sel | +1.668 |
Soda | +1.662 |
Neg logit contributions | |
interstitial | -2.045 |
ebus | -1.947 |
�� | -1.831 |
Cu | -1.778 |
agara | -1.773 |
Token | : |
Token ID | 25 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Philipp | +0.980 |
HEL | +0.949 |
Soda | +0.938 |
Whe | +0.934 |
TE | +0.933 |
Neg logit contributions | |
interstitial | -1.410 |
ebus | -1.353 |
�� | -1.271 |
agara | -1.244 |
Cu | -1.241 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Philipp | +1.776 |
HEL | +1.744 |
TE | +1.728 |
Whe | +1.717 |
Sel | +1.715 |
Neg logit contributions | |
interstitial | -2.126 |
ebus | -2.039 |
�� | -1.875 |
Cu | -1.860 |
agara | -1.848 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Philipp | +0.312 |
HEL | +0.304 |
Soda | +0.302 |
Whe | +0.298 |
TE | +0.297 |
Neg logit contributions | |
interstitial | -0.315 |
ebus | -0.302 |
�� | -0.278 |
Cu | -0.274 |
agara | -0.273 |
Token | pub |
Token ID | 12984 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Philipp | +0.694 |
HEL | +0.682 |
TE | +0.669 |
Sel | +0.669 |
wic | +0.669 |
Neg logit contributions | |
interstitial | -0.819 |
ebus | -0.794 |
�� | -0.743 |
agara | -0.721 |
Cu | -0.713 |
Token | struct |
Token ID | 2878 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Philipp | +1.940 |
HEL | +1.870 |
Sel | +1.850 |
TE | +1.847 |
Whe | +1.815 |
Neg logit contributions | |
interstitial | -3.747 |
ebus | -3.627 |
�� | -3.410 |
Cu | -3.357 |
agara | -3.333 |
Token | Guard |
Token ID | 4932 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
Sel | +8.424 |
Philipp | +8.343 |
TE | +8.321 |
Whe | +8.179 |
HEL | +8.169 |
Neg logit contributions | |
interstitial | -11.380 |
ebus | -10.833 |
Cu | -10.071 |
�� | -10.049 |
agara | -9.878 |
Token | { |
Token ID | 1391 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
Philipp | +0.034 |
HEL | +0.033 |
Whe | +0.033 |
Soda | +0.033 |
Sel | +0.032 |
Neg logit contributions | |
interstitial | -0.033 |
ebus | -0.032 |
�� | -0.030 |
agara | -0.029 |
Cu | -0.029 |
Token | ... |
Token ID | 2644 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
Philipp | +3.801 |
TE | +3.756 |
HEL | +3.750 |
Sel | +3.735 |
Whe | +3.674 |
Neg logit contributions | |
interstitial | -4.812 |
ebus | -4.645 |
�� | -4.295 |
Cu | -4.218 |
agara | -4.213 |
Token | } |
Token ID | 1782 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Philipp | +0.514 |
HEL | +0.500 |
Sel | +0.493 |
TE | +0.493 |
Soda | +0.493 |
Neg logit contributions | |
interstitial | -0.611 |
ebus | -0.586 |
�� | -0.542 |
agara | -0.534 |
Cu | -0.531 |
Token | pub |
Token ID | 2240 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Philipp | +1.312 |
HEL | +1.279 |
TE | +1.261 |
Sel | +1.261 |
Whe | +1.259 |
Neg logit contributions | |
interstitial | -1.620 |
ebus | -1.551 |
�� | -1.447 |
agara | -1.405 |
Cu | -1.403 |
Token | < |
Token ID | 1279 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Philipp | +4.115 |
Whe | +3.968 |
TE | +3.957 |
HEL | +3.947 |
Sel | +3.876 |
Neg logit contributions | |
interstitial | -5.605 |
ebus | -5.393 |
�� | -5.144 |
agara | -4.995 |
mare | -4.870 |
Token | T |
Token ID | 309 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Philipp | +3.355 |
TE | +3.325 |
HEL | +3.246 |
Sel | +3.215 |
Lin | +3.174 |
Neg logit contributions | |
interstitial | -6.294 |
ebus | -6.063 |
�� | -5.710 |
Cu | -5.641 |
agara | -5.590 |
Token | > |
Token ID | 1875 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Philipp | +0.738 |
HEL | +0.716 |
Soda | +0.712 |
TE | +0.705 |
Whe | +0.704 |
Neg logit contributions | |
interstitial | -0.810 |
ebus | -0.773 |
�� | -0.718 |
Cu | -0.703 |
agara | -0.703 |
Token | { |
Token ID | 1391 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Philipp | +2.087 |
HEL | +2.028 |
TE | +2.025 |
Whe | +2.019 |
Soda | +2.003 |
Neg logit contributions | |
interstitial | -2.490 |
ebus | -2.360 |
�� | -2.235 |
agara | -2.165 |
Cu | -2.154 |
Token | pub |
Token ID | 2240 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Philipp | +3.325 |
HEL | +3.277 |
TE | +3.248 |
Sel | +3.229 |
Whe | +3.211 |
Neg logit contributions | |
interstitial | -4.740 |
ebus | -4.558 |
�� | -4.256 |
Cu | -4.162 |
agara | -4.125 |
Token | fn |
Token ID | 24714 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Philipp | +0.570 |
HEL | +0.550 |
Soda | +0.540 |
TE | +0.539 |
Whe | +0.539 |
Neg logit contributions | |
interstitial | -0.945 |
ebus | -0.912 |
�� | -0.853 |
Cu | -0.843 |
agara | -0.840 |
Token | new |
Token ID | 649 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Philipp | +7.880 |
TE | +7.837 |
HEL | +7.782 |
CONFIG | +7.731 |
Sel | +7.716 |
Neg logit contributions | |
interstitial | -9.560 |
ebus | -9.322 |
Cu | -8.589 |
�� | -8.543 |
agara | -8.376 |
Token | ( |
Token ID | 357 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Philipp | +1.960 |
HEL | +1.868 |
Soda | +1.866 |
Whe | +1.859 |
Sel | +1.849 |
Neg logit contributions | |
interstitial | -3.011 |
ebus | -2.980 |
�� | -2.768 |
agara | -2.716 |
Cu | -2.704 |
Token | t |
Token ID | 256 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Philipp | +2.576 |
HEL | +2.513 |
Sel | +2.497 |
TE | +2.495 |
CONFIG | +2.466 |
Neg logit contributions | |
interstitial | -4.930 |
ebus | -4.836 |
�� | -4.518 |
Cu | -4.396 |
agara | -4.376 |
Token | : |
Token ID | 1058 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
interstitial | +1.931 |
ebus | +1.853 |
�� | +1.713 |
Cu | +1.680 |
agara | +1.677 |
Neg logit contributions | |
Philipp | -2.007 |
HEL | -1.959 |
Soda | -1.949 |
Whe | -1.917 |
TE | -1.912 |
Token | T |
Token ID | 309 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Philipp | +3.619 |
TE | +3.593 |
HEL | +3.491 |
Sel | +3.466 |
Whe | +3.427 |
Neg logit contributions | |
interstitial | -6.686 |
ebus | -6.425 |
�� | -5.983 |
Cu | -5.921 |
agara | -5.897 |
Token | ( |
Token ID | 357 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
HEL | +2.834 |
Philipp | +2.813 |
TE | +2.771 |
CONFIG | +2.756 |
Whe | +2.699 |
Neg logit contributions | |
interstitial | -5.022 |
ebus | -4.865 |
agara | -4.563 |
�� | -4.513 |
Cu | -4.458 |
Token | line |
Token ID | 1627 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
HEL | +4.811 |
CONFIG | +4.778 |
Philipp | +4.754 |
TE | +4.695 |
Whe | +4.648 |
Neg logit contributions | |
interstitial | -6.550 |
ebus | -6.273 |
�� | -5.816 |
Cu | -5.746 |
agara | -5.656 |
Token | , |
Token ID | 837 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
interstitial | +0.330 |
ebus | +0.318 |
�� | +0.296 |
Cu | +0.291 |
agara | +0.290 |
Neg logit contributions | |
Philipp | -0.263 |
HEL | -0.255 |
Soda | -0.253 |
Whe | -0.250 |
TE | -0.249 |
Token | r |
Token ID | 374 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
Philipp | +3.948 |
HEL | +3.945 |
CONFIG | +3.896 |
TE | +3.873 |
Sel | +3.799 |
Neg logit contributions | |
interstitial | -5.955 |
ebus | -5.729 |
�� | -5.284 |
Cu | -5.210 |
agara | -5.202 |
Token | ' |
Token ID | 705 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
interstitial | +0.566 |
ebus | +0.543 |
�� | +0.502 |
agara | +0.492 |
Cu | +0.492 |
Neg logit contributions | |
Philipp | -0.536 |
HEL | -0.521 |
Soda | -0.518 |
Whe | -0.512 |
TE | -0.511 |
Token | \ |
Token ID | 59 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Philipp | +3.576 |
Soda | +3.482 |
HEL | +3.481 |
wic | +3.464 |
CONFIG | +3.430 |
Neg logit contributions | |
interstitial | -5.242 |
ebus | -5.057 |
�� | -4.740 |
agara | -4.637 |
mare | -4.456 |
Token | [ |
Token ID | 58 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
CONFIG | +6.269 |
Whe | +6.231 |
Soda | +6.206 |
wic | +6.203 |
Philipp | +6.144 |
Neg logit contributions | |
interstitial | -10.604 |
ebus | -10.485 |
agara | -9.557 |
�� | -9.455 |
EVA | -9.330 |
Token | + |
Token ID | 10 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Philipp | +1.056 |
HEL | +1.034 |
Soda | +1.030 |
Whe | +1.018 |
TE | +1.013 |
Neg logit contributions | |
interstitial | -1.038 |
ebus | -0.998 |
�� | -0.925 |
agara | -0.903 |
Cu | -0.885 |
Token | \ |
Token ID | 59 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Philipp | +1.414 |
HEL | +1.376 |
Soda | +1.369 |
Whe | +1.356 |
TE | +1.351 |
Neg logit contributions | |
interstitial | -1.865 |
ebus | -1.802 |
�� | -1.696 |
agara | -1.656 |
Cu | -1.624 |
Token | S |
Token ID | 50 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
Soda | +4.464 |
wic | +4.398 |
Philipp | +4.350 |
HEL | +4.334 |
Whe | +4.329 |
Neg logit contributions | |
interstitial | -8.190 |
ebus | -7.965 |
�� | -7.433 |
agara | -7.404 |
EVA | -7.080 |
Token | + |
Token ID | 10 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
interstitial | +0.434 |
ebus | +0.413 |
�� | +0.378 |
agara | +0.368 |
Cu | +0.368 |
Neg logit contributions | |
Philipp | -0.532 |
HEL | -0.520 |
Soda | -0.517 |
Whe | -0.512 |
TE | -0.510 |
Token | Madrid |
Token ID | 14708 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
interstitial | +2.284 |
ebus | +2.198 |
�� | +2.042 |
Cu | +2.008 |
agara | +2.000 |
Neg logit contributions | |
Philipp | -1.861 |
HEL | -1.816 |
Soda | -1.799 |
Whe | -1.772 |
wic | -1.769 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
interstitial | +1.403 |
ebus | +1.348 |
�� | +1.251 |
Cu | +1.226 |
agara | +1.226 |
Neg logit contributions | |
Philipp | -1.211 |
HEL | -1.175 |
Soda | -1.169 |
Whe | -1.154 |
TE | -1.152 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Philipp | +0.523 |
HEL | +0.509 |
Soda | +0.506 |
Whe | +0.499 |
TE | +0.498 |
Neg logit contributions | |
interstitial | -0.527 |
ebus | -0.507 |
�� | -0.466 |
Cu | -0.459 |
agara | -0.457 |
Token | Dri |
Token ID | 20564 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Philipp | +0.770 |
HEL | +0.752 |
Soda | +0.751 |
Sel | +0.744 |
TE | +0.742 |
Neg logit contributions | |
interstitial | -0.774 |
ebus | -0.742 |
�� | -0.690 |
agara | -0.679 |
Cu | -0.648 |
Token | ving |
Token ID | 1075 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Philipp | +2.876 |
Whe | +2.771 |
Sel | +2.750 |
wic | +2.750 |
TE | +2.749 |
Neg logit contributions | |
interstitial | -3.493 |
ebus | -3.260 |
�� | -3.133 |
Cu | -3.033 |
agara | -2.981 |
Token | slowly |
Token ID | 6364 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Philipp | +3.083 |
HEL | +2.943 |
Soda | +2.942 |
Sel | +2.917 |
TE | +2.913 |
Neg logit contributions | |
interstitial | -3.552 |
ebus | -3.330 |
�� | -3.196 |
agara | -3.075 |
Cu | -3.058 |
Token | along |
Token ID | 1863 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Philipp | +5.645 |
Whe | +5.216 |
Sel | +5.110 |
Lin | +5.069 |
TE | +4.990 |
Neg logit contributions | |
interstitial | -12.297 |
ebus | -11.604 |
�� | -11.306 |
�� | -10.926 |
Cu | -10.921 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Philipp | +2.293 |
Sel | +2.202 |
Soda | +2.186 |
HEL | +2.158 |
TE | +2.144 |
Neg logit contributions | |
interstitial | -2.957 |
ebus | -2.883 |
�� | -2.666 |
agara | -2.634 |
Cu | -2.601 |
Token | city |
Token ID | 1748 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Philipp | +1.030 |
Sel | +0.982 |
HEL | +0.977 |
Soda | +0.973 |
TE | +0.962 |
Neg logit contributions | |
interstitial | -1.558 |
ebus | -1.507 |
�� | -1.404 |
agara | -1.380 |
Cu | -1.378 |
Token | 's |
Token ID | 338 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
interstitial | +1.404 |
ebus | +1.341 |
�� | +1.230 |
Cu | +1.201 |
agara | +1.201 |
Neg logit contributions | |
Philipp | -1.602 |
HEL | -1.562 |
Soda | -1.553 |
Whe | -1.536 |
TE | -1.533 |
Token | broad |
Token ID | 3154 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
interstitial | +4.016 |
ebus | +3.893 |
�� | +3.592 |
agara | +3.549 |
Cu | +3.545 |
Neg logit contributions | |
Philipp | -3.303 |
Soda | -3.232 |
HEL | -3.218 |
wic | -3.141 |
TE | -3.130 |
Token | Guard |
Token ID | 4932 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
Sel | +8.424 |
Philipp | +8.343 |
TE | +8.321 |
Whe | +8.179 |
HEL | +8.169 |
Neg logit contributions | |
interstitial | -11.380 |
ebus | -10.833 |
Cu | -10.071 |
�� | -10.049 |
agara | -9.878 |
Token | { |
Token ID | 1391 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
Philipp | +0.034 |
HEL | +0.033 |
Whe | +0.033 |
Soda | +0.033 |
Sel | +0.032 |
Neg logit contributions | |
interstitial | -0.033 |
ebus | -0.032 |
�� | -0.030 |
agara | -0.029 |
Cu | -0.029 |
Token | ... |
Token ID | 2644 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
Philipp | +3.801 |
TE | +3.756 |
HEL | +3.750 |
Sel | +3.735 |
Whe | +3.674 |
Neg logit contributions | |
interstitial | -4.812 |
ebus | -4.645 |
�� | -4.295 |
Cu | -4.218 |
agara | -4.213 |
Token | } |
Token ID | 1782 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Philipp | +0.514 |
HEL | +0.500 |
Sel | +0.493 |
TE | +0.493 |
Soda | +0.493 |
Neg logit contributions | |
interstitial | -0.611 |
ebus | -0.586 |
�� | -0.542 |
agara | -0.534 |
Cu | -0.531 |
Token | pub |
Token ID | 2240 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Philipp | +1.312 |
HEL | +1.279 |
TE | +1.261 |
Sel | +1.261 |
Whe | +1.259 |
Neg logit contributions | |
interstitial | -1.620 |
ebus | -1.551 |
�� | -1.447 |
agara | -1.405 |
Cu | -1.403 |
Token | fn |
Token ID | 24714 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Philipp | +2.050 |
HEL | +1.979 |
TE | +1.948 |
Sel | +1.943 |
Whe | +1.928 |
Neg logit contributions | |
interstitial | -3.753 |
ebus | -3.623 |
�� | -3.391 |
agara | -3.347 |
Cu | -3.347 |
Token | pin |
Token ID | 6757 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Philipp | +7.950 |
Sel | +7.832 |
HEL | +7.788 |
TE | +7.727 |
CONFIG | +7.589 |
Neg logit contributions | |
interstitial | -9.200 |
ebus | -8.959 |
Cu | -8.225 |
�� | -8.084 |
agara | -7.938 |
Token | () |
Token ID | 7499 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Philipp | +0.738 |
HEL | +0.709 |
Whe | +0.705 |
Soda | +0.700 |
Sel | +0.698 |
Neg logit contributions | |
interstitial | -0.961 |
ebus | -0.939 |
�� | -0.872 |
agara | -0.849 |
Cu | -0.842 |
Token | -> |
Token ID | 4613 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Philipp | +1.293 |
HEL | +1.262 |
Soda | +1.252 |
Sel | +1.249 |
Whe | +1.247 |
Neg logit contributions | |
interstitial | -1.167 |
ebus | -1.109 |
�� | -1.028 |
agara | -0.991 |
Cu | -0.977 |
Token | Guard |
Token ID | 4932 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Philipp | +4.672 |
TE | +4.543 |
Sel | +4.519 |
Whe | +4.491 |
HEL | +4.474 |
Neg logit contributions | |
interstitial | -6.720 |
ebus | -6.413 |
agara | -5.969 |
�� | -5.960 |
Cu | -5.862 |
Token | ; |
Token ID | 2162 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Philipp | +2.139 |
HEL | +2.066 |
Whe | +2.062 |
TE | +2.043 |
Sel | +2.040 |
Neg logit contributions | |
interstitial | -2.244 |
ebus | -2.145 |
�� | -1.979 |
agara | -1.962 |
mare | -1.895 |
Token | : |
Token ID | 25 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
interstitial | +1.919 |
ebus | +1.842 |
�� | +1.714 |
Cu | +1.683 |
agara | +1.677 |
Neg logit contributions | |
Philipp | -1.590 |
HEL | -1.544 |
Soda | -1.533 |
Whe | -1.510 |
TE | -1.505 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Philipp | +2.405 |
HEL | +2.317 |
Whe | +2.292 |
Soda | +2.292 |
TE | +2.279 |
Neg logit contributions | |
interstitial | -3.284 |
ebus | -3.212 |
�� | -2.999 |
agara | -2.955 |
Cu | -2.926 |
Token | | |
Token ID | 930 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
interstitial | +1.420 |
ebus | +1.365 |
�� | +1.270 |
Cu | +1.247 |
agara | +1.246 |
Neg logit contributions | |
Philipp | -1.144 |
HEL | -1.111 |
Soda | -1.104 |
Whe | -1.088 |
TE | -1.083 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
interstitial | +1.279 |
ebus | +1.232 |
�� | +1.151 |
agara | +1.131 |
Cu | +1.130 |
Neg logit contributions | |
Philipp | -0.925 |
HEL | -0.895 |
Soda | -0.889 |
Whe | -0.877 |
TE | -0.875 |
Token | | |
Token ID | 930 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
interstitial | +1.685 |
ebus | +1.621 |
�� | +1.506 |
Cu | +1.477 |
agara | +1.476 |
Neg logit contributions | |
Philipp | -1.408 |
HEL | -1.367 |
Soda | -1.359 |
Whe | -1.340 |
TE | -1.336 |
Token | struct |
Token ID | 2878 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Philipp | +0.614 |
HEL | +0.593 |
Soda | +0.587 |
TE | +0.584 |
Whe | +0.582 |
Neg logit contributions | |
interstitial | -0.832 |
ebus | -0.798 |
�� | -0.748 |
Cu | -0.735 |
agara | -0.735 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Philipp | +6.481 |
Soda | +6.265 |
Sel | +6.253 |
TE | +6.215 |
Whe | +6.197 |
Neg logit contributions | |
interstitial | -10.490 |
ebus | -10.153 |
agara | -9.445 |
�� | -9.418 |
Cu | -9.338 |
Token | { |
Token ID | 1391 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
interstitial | +1.844 |
ebus | +1.760 |
�� | +1.614 |
Cu | +1.579 |
agara | +1.576 |
Neg logit contributions | |
Philipp | -2.116 |
HEL | -2.063 |
Soda | -2.052 |
Whe | -2.028 |
TE | -2.024 |
Token | | |
Token ID | 930 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Philipp | +2.923 |
Sel | +2.850 |
Soda | +2.840 |
TE | +2.838 |
HEL | +2.827 |
Neg logit contributions | |
interstitial | -3.599 |
ebus | -3.474 |
�� | -3.227 |
agara | -3.166 |
Cu | -3.163 |
Token | ^ |
Token ID | 10563 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
interstitial | +1.472 |
ebus | +1.418 |
�� | +1.321 |
agara | +1.298 |
Cu | +1.296 |
Neg logit contributions | |
Philipp | -1.120 |
HEL | -1.085 |
Soda | -1.079 |
Whe | -1.065 |
TE | -1.061 |
Token | ^^^^ |
Token ID | 39397 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Philipp | +1.348 |
Soda | +1.299 |
HEL | +1.297 |
Whe | +1.289 |
TE | +1.288 |
Neg logit contributions | |
interstitial | -1.727 |
ebus | -1.680 |
�� | -1.546 |
agara | -1.522 |
Cu | -1.508 |
Token | null |
Token ID | 9242 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
interstitial | +1.653 |
ebus | +1.591 |
�� | +1.482 |
Cu | +1.455 |
agara | +1.455 |
Neg logit contributions | |
Philipp | -1.298 |
HEL | -1.257 |
Soda | -1.250 |
Whe | -1.232 |
TE | -1.228 |
Token | atomic |
Token ID | 17226 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Philipp | +1.046 |
HEL | +1.020 |
TE | +1.010 |
Soda | +1.005 |
Whe | +1.001 |
Neg logit contributions | |
interstitial | -1.517 |
ebus | -1.466 |
�� | -1.359 |
Cu | -1.336 |
agara | -1.335 |
Token | pointer |
Token ID | 17562 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Philipp | +1.163 |
HEL | +1.139 |
TE | +1.132 |
Whe | +1.124 |
Sel | +1.118 |
Neg logit contributions | |
interstitial | -1.478 |
ebus | -1.417 |
�� | -1.308 |
Cu | -1.290 |
agara | -1.284 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Philipp | +1.764 |
HEL | +1.717 |
TE | +1.712 |
Whe | +1.699 |
Soda | +1.693 |
Neg logit contributions | |
interstitial | -2.505 |
ebus | -2.418 |
�� | -2.242 |
agara | -2.197 |
Cu | -2.194 |
Token | pub |
Token ID | 2240 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Philipp | +0.281 |
HEL | +0.273 |
Soda | +0.270 |
Whe | +0.268 |
TE | +0.268 |
Neg logit contributions | |
interstitial | -0.375 |
ebus | -0.361 |
�� | -0.336 |
Cu | -0.330 |
agara | -0.329 |
Token | fn |
Token ID | 24714 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Philipp | +0.651 |
HEL | +0.630 |
TE | +0.618 |
Whe | +0.618 |
Soda | +0.617 |
Neg logit contributions | |
interstitial | -1.105 |
ebus | -1.069 |
�� | -0.998 |
Cu | -0.988 |
agara | -0.980 |
Token | null |
Token ID | 9242 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Philipp | +6.674 |
TE | +6.660 |
CONFIG | +6.556 |
HEL | +6.521 |
Lin | +6.482 |
Neg logit contributions | |
interstitial | -10.275 |
ebus | -9.962 |
Cu | -9.120 |
�� | -9.040 |
agara | -8.875 |
Token | () |
Token ID | 7499 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
Philipp | +2.292 |
HEL | +2.209 |
Whe | +2.200 |
Soda | +2.192 |
TE | +2.190 |
Neg logit contributions | |
interstitial | -3.254 |
ebus | -3.232 |
�� | -2.965 |
agara | -2.898 |
Cu | -2.873 |
Token | -> |
Token ID | 4613 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
interstitial | +0.147 |
ebus | +0.140 |
�� | +0.129 |
agara | +0.125 |
Cu | +0.124 |
Neg logit contributions | |
Philipp | -0.175 |
HEL | -0.171 |
Soda | -0.170 |
Whe | -0.169 |
TE | -0.168 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Philipp | +3.095 |
TE | +3.051 |
Whe | +3.001 |
HEL | +2.993 |
Soda | +2.965 |
Neg logit contributions | |
interstitial | -5.333 |
ebus | -5.161 |
�� | -4.802 |
agara | -4.745 |
Cu | -4.729 |
Token | < |
Token ID | 1279 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Philipp | +3.003 |
Whe | +2.912 |
HEL | +2.897 |
TE | +2.881 |
Sel | +2.857 |
Neg logit contributions | |
interstitial | -4.196 |
ebus | -4.035 |
�� | -3.729 |
agara | -3.693 |
mare | -3.633 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
HEL | +2.975 |
Philipp | +2.939 |
CONFIG | +2.907 |
Whe | +2.848 |
Sel | +2.832 |
Neg logit contributions | |
interstitial | -8.130 |
ebus | -7.884 |
�� | -7.431 |
agara | -7.274 |
Cu | -7.269 |
Token | System |
Token ID | 11964 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Philipp | +1.920 |
wic | +1.866 |
HEL | +1.820 |
CONFIG | +1.801 |
Whe | +1.798 |
Neg logit contributions | |
interstitial | -9.417 |
ebus | -9.328 |
�� | -9.002 |
agara | -8.765 |
avorite | -8.641 |
Token | . |
Token ID | 13 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Philipp | +2.452 |
HEL | +2.390 |
Sel | +2.366 |
Whe | +2.363 |
TE | +2.363 |
Neg logit contributions | |
interstitial | -3.828 |
ebus | -3.653 |
�� | -3.487 |
agara | -3.381 |
�� | -3.301 |
Token | Draw |
Token ID | 25302 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Philipp | +2.853 |
Whe | +2.786 |
HEL | +2.753 |
wic | +2.750 |
TE | +2.736 |
Neg logit contributions | |
interstitial | -6.275 |
ebus | -6.095 |
�� | -5.854 |
agara | -5.749 |
avorite | -5.651 |
Token | ing |
Token ID | 278 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
Sel | +5.134 |
Philipp | +5.124 |
wic | +5.087 |
Whe | +5.067 |
TE | +5.043 |
Neg logit contributions | |
interstitial | -7.004 |
�� | -6.602 |
ebus | -6.585 |
avorite | -6.345 |
�� | -6.319 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Philipp | +3.368 |
HEL | +3.305 |
Sel | +3.304 |
Whe | +3.291 |
TE | +3.286 |
Neg logit contributions | |
interstitial | -5.898 |
ebus | -5.567 |
�� | -5.391 |
agara | -5.242 |
avorite | -5.192 |
Token | Font |
Token ID | 23252 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
wic | +3.387 |
screen | +3.297 |
Lin | +3.286 |
Philipp | +3.286 |
CONFIG | +3.212 |
Neg logit contributions | |
interstitial | -12.437 |
ebus | -12.169 |
agara | -12.040 |
�� | -11.736 |
axter | -11.471 |
Token | Style |
Token ID | 21466 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Philipp | +4.092 |
Soda | +4.063 |
TE | +4.046 |
Sel | +4.013 |
HEL | +4.008 |
Neg logit contributions | |
interstitial | -5.850 |
ebus | -5.604 |
�� | -5.260 |
agara | -5.240 |
axter | -5.029 |
Token | ] |
Token ID | 60 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Philipp | +2.451 |
HEL | +2.392 |
Soda | +2.360 |
Whe | +2.353 |
Sel | +2.352 |
Neg logit contributions | |
interstitial | -3.609 |
ebus | -3.458 |
�� | -3.268 |
agara | -3.194 |
Cu | -3.126 |
Token | :: |
Token ID | 3712 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
interstitial | +0.335 |
ebus | +0.324 |
Cu | +0.295 |
�� | +0.294 |
agara | +0.290 |
Neg logit contributions | |
Philipp | -0.369 |
Soda | -0.358 |
HEL | -0.358 |
Whe | -0.351 |
Sel | -0.349 |
Token | B |
Token ID | 33 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Philipp | +1.154 |
HEL | +1.134 |
Soda | +1.129 |
Whe | +1.125 |
TE | +1.118 |
Neg logit contributions | |
interstitial | -0.794 |
ebus | -0.760 |
�� | -0.687 |
agara | -0.678 |
Cu | -0.637 |
Token | made |
Token ID | 925 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
Philipp | +0.965 |
HEL | +0.931 |
Soda | +0.919 |
Sel | +0.915 |
TE | +0.913 |
Neg logit contributions | |
interstitial | -1.139 |
ebus | -1.084 |
�� | -1.015 |
agara | -0.989 |
Cu | -0.984 |
Token | them |
Token ID | 606 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
interstitial | +0.798 |
ebus | +0.768 |
�� | +0.714 |
Cu | +0.701 |
agara | +0.701 |
Neg logit contributions | |
Philipp | -0.644 |
HEL | -0.625 |
Soda | -0.621 |
Whe | -0.613 |
TE | -0.611 |
Token | � |
Token ID | 564 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Philipp | +1.347 |
HEL | +1.305 |
Soda | +1.298 |
TE | +1.287 |
Whe | +1.279 |
Neg logit contributions | |
interstitial | -1.774 |
ebus | -1.701 |
�� | -1.598 |
Cu | -1.545 |
agara | -1.541 |
Token | � |
Token ID | 250 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
Philipp | +0.930 |
HEL | +0.910 |
Soda | +0.905 |
TE | +0.898 |
Whe | +0.895 |
Neg logit contributions | |
interstitial | -0.743 |
ebus | -0.700 |
�� | -0.630 |
Cu | -0.625 |
agara | -0.624 |
Token | pro |
Token ID | 1676 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
interstitial | +0.329 |
ebus | +0.318 |
�� | +0.296 |
agara | +0.289 |
Cu | +0.287 |
Neg logit contributions | |
Philipp | -0.272 |
HEL | -0.264 |
Soda | -0.262 |
Whe | -0.259 |
TE | -0.259 |
Token | fl |
Token ID | 2704 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Philipp | +1.207 |
HEL | +1.176 |
Soda | +1.174 |
TE | +1.166 |
Whe | +1.156 |
Neg logit contributions | |
interstitial | -1.604 |
ebus | -1.552 |
�� | -1.446 |
agara | -1.422 |
Cu | -1.414 |
Token | igate |
Token ID | 10055 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
oqu | +6.135 |
Philipp | +6.015 |
wic | +5.973 |
Soda | +5.823 |
Lin | +5.798 |
Neg logit contributions | |
interstitial | -10.078 |
ebus | -9.590 |
�� | -9.128 |
EVA | -8.789 |
Cu | -8.665 |
Token | was |
Token ID | 373 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Philipp | +0.644 |
HEL | +0.625 |
Soda | +0.619 |
TE | +0.613 |
Whe | +0.610 |
Neg logit contributions | |
interstitial | -0.845 |
ebus | -0.805 |
�� | -0.753 |
agara | -0.738 |
Cu | -0.737 |
Token | ters |
Token ID | 1010 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Philipp | +2.660 |
HEL | +2.589 |
Soda | +2.577 |
TE | +2.552 |
Sel | +2.539 |
Neg logit contributions | |
interstitial | -3.467 |
ebus | -3.301 |
�� | -3.084 |
agara | -2.991 |
Cu | -2.979 |
Token | of |
Token ID | 286 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
Philipp | +1.305 |
HEL | +1.254 |
Soda | +1.246 |
TE | +1.236 |
Sel | +1.232 |
Neg logit contributions | |
interstitial | -1.847 |
ebus | -1.764 |
�� | -1.655 |
Cu | -1.618 |
agara | -1.614 |
Token | energy |
Token ID | 2568 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Philipp | +0.534 |
HEL | +0.518 |
Soda | +0.517 |
TE | +0.508 |
Whe | +0.508 |
Neg logit contributions | |
interstitial | -0.722 |
ebus | -0.691 |
�� | -0.646 |
agara | -0.633 |
Cu | -0.631 |
Token | < |
Token ID | 1279 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Philipp | +3.163 |
HEL | +3.045 |
Whe | +3.033 |
TE | +3.028 |
Soda | +3.007 |
Neg logit contributions | |
interstitial | -4.253 |
ebus | -4.103 |
�� | -3.889 |
agara | -3.794 |
Cu | -3.707 |
Token | T |
Token ID | 309 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
TE | +3.207 |
Philipp | +3.199 |
HEL | +3.105 |
Soda | +3.097 |
CONFIG | +3.066 |
Neg logit contributions | |
interstitial | -5.850 |
ebus | -5.659 |
�� | -5.298 |
Cu | -5.210 |
agara | -5.176 |
Token | > |
Token ID | 1875 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Philipp | +0.986 |
HEL | +0.957 |
Soda | +0.954 |
TE | +0.942 |
Whe | +0.941 |
Neg logit contributions | |
interstitial | -1.050 |
ebus | -1.001 |
�� | -0.925 |
agara | -0.909 |
Cu | -0.908 |
Token | { |
Token ID | 1391 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Philipp | +2.225 |
HEL | +2.158 |
Soda | +2.155 |
Whe | +2.148 |
TE | +2.142 |
Neg logit contributions | |
interstitial | -2.234 |
ebus | -2.125 |
�� | -1.994 |
agara | -1.941 |
Cu | -1.926 |
Token | pub |
Token ID | 2240 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
Philipp | +2.052 |
HEL | +2.000 |
TE | +1.979 |
Whe | +1.979 |
Sel | +1.973 |
Neg logit contributions | |
interstitial | -2.650 |
ebus | -2.555 |
�� | -2.370 |
Cu | -2.331 |
agara | -2.308 |
Token | fn |
Token ID | 24714 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Philipp | +0.305 |
HEL | +0.295 |
Soda | +0.292 |
Whe | +0.290 |
TE | +0.289 |
Neg logit contributions | |
interstitial | -0.458 |
ebus | -0.442 |
�� | -0.413 |
Cu | -0.406 |
agara | -0.406 |
Token | load |
Token ID | 3440 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Philipp | +6.351 |
TE | +6.222 |
HEL | +6.165 |
CONFIG | +6.118 |
Sel | +6.107 |
Neg logit contributions | |
interstitial | -9.449 |
ebus | -9.227 |
�� | -8.825 |
Cu | -8.571 |
agara | -8.443 |
Token | < |
Token ID | 1279 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
Philipp | +1.897 |
HEL | +1.817 |
Soda | +1.816 |
Whe | +1.799 |
Sel | +1.791 |
Neg logit contributions | |
interstitial | -2.893 |
ebus | -2.834 |
�� | -2.652 |
agara | -2.606 |
Cu | -2.549 |
Token | ' |
Token ID | 705 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Philipp | +3.586 |
TE | +3.553 |
Soda | +3.503 |
HEL | +3.496 |
Sel | +3.473 |
Neg logit contributions | |
interstitial | -5.477 |
ebus | -5.348 |
�� | -5.022 |
agara | -4.885 |
Cu | -4.846 |
Token | a |
Token ID | 64 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
interstitial | +2.798 |
ebus | +2.653 |
�� | +2.404 |
agara | +2.372 |
Cu | +2.371 |
Neg logit contributions | |
Philipp | -3.649 |
HEL | -3.558 |
Soda | -3.535 |
Whe | -3.509 |
Sel | -3.483 |
Token | > |
Token ID | 1875 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
interstitial | +1.860 |
ebus | +1.791 |
�� | +1.664 |
Cu | +1.635 |
agara | +1.634 |
Neg logit contributions | |
Philipp | -1.535 |
HEL | -1.490 |
Soda | -1.479 |
Whe | -1.458 |
TE | -1.450 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
interstitial | +0.419 |
ebus | +0.403 |
�� | +0.375 |
agara | +0.367 |
Cu | +0.367 |
Neg logit contributions | |
Philipp | -0.340 |
HEL | -0.330 |
Soda | -0.328 |
Whe | -0.323 |
TE | -0.323 |
Token | guy |
Token ID | 3516 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
interstitial | +0.144 |
ebus | +0.139 |
�� | +0.130 |
agara | +0.127 |
Cu | +0.127 |
Neg logit contributions | |
Philipp | -0.106 |
HEL | -0.103 |
Soda | -0.102 |
Whe | -0.101 |
TE | -0.100 |
Token | no |
Token ID | 645 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Philipp | +0.452 |
HEL | +0.436 |
Soda | +0.432 |
Whe | +0.427 |
TE | +0.426 |
Neg logit contributions | |
interstitial | -0.651 |
ebus | -0.625 |
�� | -0.587 |
agara | -0.576 |
Cu | -0.575 |
Token | matter |
Token ID | 2300 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Philipp | +0.332 |
HEL | +0.322 |
Soda | +0.318 |
TE | +0.317 |
Whe | +0.315 |
Neg logit contributions | |
interstitial | -0.407 |
ebus | -0.390 |
�� | -0.364 |
Cu | -0.355 |
agara | -0.355 |
Token | how |
Token ID | 703 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Philipp | +0.633 |
HEL | +0.614 |
Soda | +0.610 |
Whe | +0.605 |
TE | +0.603 |
Neg logit contributions | |
interstitial | -0.775 |
ebus | -0.743 |
�� | -0.691 |
agara | -0.679 |
Cu | -0.677 |
Token | am |
Token ID | 716 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Philipp | +1.676 |
HEL | +1.625 |
Soda | +1.603 |
TE | +1.599 |
Whe | +1.598 |
Neg logit contributions | |
interstitial | -2.133 |
ebus | -2.040 |
�� | -1.913 |
agara | -1.870 |
Cu | -1.850 |
Token | iable |
Token ID | 3379 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Philipp | +6.911 |
Whe | +6.798 |
Sel | +6.787 |
HEL | +6.779 |
TE | +6.750 |
Neg logit contributions | |
interstitial | -8.351 |
ebus | -8.095 |
�� | -7.870 |
EVA | -7.551 |
bilt | -7.487 |
Token | he |
Token ID | 339 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Philipp | +1.155 |
HEL | +1.112 |
Soda | +1.105 |
Whe | +1.104 |
Sel | +1.099 |
Neg logit contributions | |
interstitial | -1.383 |
ebus | -1.321 |
�� | -1.236 |
agara | -1.219 |
Cu | -1.200 |
Token | seemed |
Token ID | 3947 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Philipp | +1.387 |
HEL | +1.346 |
Soda | +1.334 |
TE | +1.328 |
Whe | +1.327 |
Neg logit contributions | |
interstitial | -1.456 |
ebus | -1.387 |
�� | -1.290 |
agara | -1.264 |
Cu | -1.255 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
Philipp | +0.150 |
HEL | +0.145 |
Soda | +0.144 |
Whe | +0.142 |
Sel | +0.142 |
Neg logit contributions | |
interstitial | -0.201 |
ebus | -0.193 |
�� | -0.181 |
agara | -0.178 |
Cu | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
interstitial | +0.255 |
ebus | +0.246 |
�� | +0.228 |
Cu | +0.223 |
agara | +0.223 |
Neg logit contributions | |
Philipp | -0.223 |
HEL | -0.216 |
Soda | -0.215 |
Whe | -0.212 |
TE | -0.211 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Philipp | +2.395 |
HEL | +2.315 |
Whe | +2.298 |
TE | +2.297 |
Sel | +2.281 |
Neg logit contributions | |
interstitial | -4.311 |
ebus | -4.083 |
�� | -3.955 |
agara | -3.809 |
avorite | -3.762 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Philipp | +4.781 |
Whe | +4.649 |
HEL | +4.627 |
Sel | +4.577 |
TE | +4.565 |
Neg logit contributions | |
interstitial | -6.293 |
ebus | -5.680 |
�� | -5.673 |
avorite | -5.522 |
agara | -5.438 |
Token | Que |
Token ID | 15681 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Philipp | +2.251 |
HEL | +2.236 |
Whe | +2.229 |
wic | +2.221 |
TE | +2.207 |
Neg logit contributions | |
interstitial | -2.402 |
ebus | -2.311 |
�� | -2.190 |
agara | -2.094 |
avorite | -2.041 |
Token | er |
Token ID | 263 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
interstitial | +0.100 |
ebus | +0.095 |
�� | +0.084 |
agara | +0.084 |
Cu | +0.084 |
Neg logit contributions | |
Philipp | -0.153 |
HEL | -0.149 |
Soda | -0.149 |
TE | -0.146 |
Whe | -0.146 |
Token | magnet |
Token ID | 19972 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Philipp | +0.909 |
HEL | +0.882 |
Soda | +0.873 |
Whe | +0.866 |
Sel | +0.864 |
Neg logit contributions | |
interstitial | -1.037 |
ebus | -0.998 |
�� | -0.929 |
Cu | -0.906 |
agara | -0.903 |
Token | ? |
Token ID | 30 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Philipp | +2.975 |
HEL | +2.863 |
Whe | +2.827 |
Sel | +2.827 |
TE | +2.819 |
Neg logit contributions | |
interstitial | -4.107 |
ebus | -3.924 |
�� | -3.667 |
agara | -3.597 |
Cu | -3.570 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Philipp | +6.219 |
TE | +6.004 |
HEL | +5.999 |
Whe | +5.864 |
Sel | +5.838 |
Neg logit contributions | |
interstitial | -9.440 |
ebus | -9.055 |
agara | -8.512 |
�� | -8.484 |
Cu | -8.455 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
interstitial | +1.652 |
ebus | +1.625 |
Cu | +1.494 |
mare | +1.439 |
agara | +1.434 |
Neg logit contributions | |
Philipp | -2.030 |
HEL | -1.977 |
Soda | -1.972 |
wic | -1.920 |
Whe | -1.914 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
interstitial | +1.190 |
ebus | +1.155 |
�� | +1.089 |
agara | +1.069 |
Cu | +1.061 |
Neg logit contributions | |
Philipp | -0.672 |
HEL | -0.650 |
Soda | -0.645 |
Whe | -0.635 |
TE | -0.633 |
Token | : |
Token ID | 25 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
interstitial | +3.012 |
ebus | +3.007 |
Cu | +2.815 |
mare | +2.711 |
EVA | +2.680 |
Neg logit contributions | |
Philipp | -3.473 |
Soda | -3.379 |
HEL | -3.376 |
CONFIG | -3.303 |
Whe | -3.276 |
Token | hey |
Token ID | 17207 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Philipp | +0.347 |
HEL | +0.337 |
Soda | +0.335 |
Whe | +0.331 |
TE | +0.330 |
Neg logit contributions | |
interstitial | -0.464 |
ebus | -0.446 |
�� | -0.416 |
agara | -0.409 |
Cu | -0.408 |
Token | out |
Token ID | 503 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Philipp | +0.502 |
HEL | +0.488 |
Soda | +0.485 |
TE | +0.479 |
Whe | +0.479 |
Neg logit contributions | |
interstitial | -0.605 |
ebus | -0.584 |
�� | -0.544 |
Cu | -0.529 |
agara | -0.529 |
Token | there |
Token ID | 612 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Philipp | +3.697 |
Whe | +3.650 |
Sel | +3.634 |
HEL | +3.631 |
Soda | +3.628 |
Neg logit contributions | |
interstitial | -4.838 |
ebus | -4.767 |
�� | -4.411 |
Cu | -4.254 |
agara | -4.207 |
Token | than |
Token ID | 621 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
Philipp | +1.930 |
Soda | +1.859 |
HEL | +1.858 |
TE | +1.852 |
Whe | +1.848 |
Neg logit contributions | |
interstitial | -2.854 |
ebus | -2.716 |
�� | -2.577 |
Cu | -2.511 |
agara | -2.484 |
Token | most |
Token ID | 749 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
interstitial | +0.631 |
ebus | +0.608 |
�� | +0.565 |
agara | +0.554 |
Cu | +0.554 |
Neg logit contributions | |
Philipp | -0.519 |
HEL | -0.504 |
Soda | -0.501 |
Whe | -0.494 |
TE | -0.493 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
interstitial | +1.739 |
ebus | +1.672 |
�� | +1.557 |
Cu | +1.532 |
agara | +1.529 |
Neg logit contributions | |
Philipp | -1.347 |
HEL | -1.303 |
Soda | -1.295 |
Whe | -1.275 |
TE | -1.269 |
Token | - |
Token ID | 532 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Philipp | +2.612 |
Soda | +2.526 |
HEL | +2.524 |
Whe | +2.520 |
Sel | +2.488 |
Neg logit contributions | |
interstitial | -3.857 |
ebus | -3.693 |
�� | -3.475 |
agara | -3.426 |
Cu | -3.321 |
Token | July |
Token ID | 2901 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
HEL | +4.851 |
Philipp | +4.791 |
Whe | +4.582 |
TE | +4.369 |
Gins | +4.245 |
Neg logit contributions | |
interstitial | -10.756 |
ebus | -10.143 |
�� | -10.058 |
agara | -9.855 |
�� | -9.677 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Philipp | +3.858 |
TE | +3.641 |
HEL | +3.639 |
Sel | +3.597 |
Whe | +3.576 |
Neg logit contributions | |
interstitial | -9.009 |
ebus | -8.428 |
�� | -8.286 |
avorite | -8.066 |
�� | -8.049 |
Token | , |
Token ID | 11 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Philipp | +3.177 |
TE | +3.105 |
HEL | +3.095 |
Whe | +3.077 |
Sel | +3.056 |
Neg logit contributions | |
interstitial | -6.464 |
ebus | -6.041 |
�� | -5.922 |
avorite | -5.765 |
agara | -5.712 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Philipp | +4.964 |
HEL | +4.859 |
Whe | +4.822 |
TE | +4.793 |
Sel | +4.722 |
Neg logit contributions | |
interstitial | -6.730 |
ebus | -6.077 |
�� | -6.050 |
avorite | -5.942 |
agara | -5.835 |
Token | R |
Token ID | 49 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
TE | +4.839 |
Philipp | +4.811 |
HEL | +4.771 |
Whe | +4.761 |
CONFIG | +4.725 |
Neg logit contributions | |
interstitial | -3.861 |
ebus | -3.784 |
�� | -3.551 |
agara | -3.488 |
avorite | -3.304 |
Token | a |
Token ID | 257 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Philipp | +2.819 |
Soda | +2.794 |
Whe | +2.775 |
HEL | +2.762 |
TE | +2.753 |
Neg logit contributions | |
interstitial | -4.107 |
ebus | -3.851 |
�� | -3.691 |
agara | -3.587 |
Cu | -3.539 |
Token | L |
Token ID | 406 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
Philipp | +3.451 |
Soda | +3.437 |
Whe | +3.433 |
TE | +3.398 |
HEL | +3.378 |
Neg logit contributions | |
interstitial | -5.543 |
ebus | -5.136 |
�� | -4.935 |
agara | -4.815 |
axter | -4.711 |
Token | CH |
Token ID | 3398 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Philipp | +3.571 |
HEL | +3.544 |
Soda | +3.524 |
Whe | +3.493 |
TE | +3.459 |
Neg logit contributions | |
interstitial | -5.241 |
ebus | -4.820 |
�� | -4.671 |
agara | -4.458 |
Cu | -4.405 |
Token | F |
Token ID | 37 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
interstitial | +0.690 |
ebus | +0.657 |
�� | +0.592 |
agara | +0.572 |
Cu | +0.565 |
Neg logit contributions | |
Philipp | -1.023 |
HEL | -1.004 |
Soda | -0.999 |
Whe | -0.992 |
TE | -0.992 |
Token | ( |
Token ID | 357 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Philipp | +1.587 |
Soda | +1.554 |
Whe | +1.547 |
HEL | +1.547 |
TE | +1.537 |
Neg logit contributions | |
interstitial | -2.873 |
ebus | -2.731 |
�� | -2.592 |
agara | -2.546 |
Cu | -2.497 |
Token | Low |
Token ID | 20535 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Philipp | +3.928 |
Soda | +3.863 |
Whe | +3.857 |
Sel | +3.841 |
wic | +3.839 |
Neg logit contributions | |
ebus | -5.594 |
interstitial | -5.539 |
�� | -5.213 |
agara | -5.122 |
Cu | -4.892 |
Token | Carb |
Token ID | 20453 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Whe | +5.008 |
Sel | +5.007 |
Soda | +4.991 |
Philipp | +4.931 |
TE | +4.865 |
Neg logit contributions | |
interstitial | -10.357 |
ebus | -9.613 |
�� | -9.217 |
avorite | -9.094 |
agara | -9.043 |
Token | High |
Token ID | 3334 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Philipp | +4.635 |
Soda | +4.544 |
Sel | +4.544 |
Whe | +4.527 |
TE | +4.427 |
Neg logit contributions | |
interstitial | -8.937 |
ebus | -8.372 |
�� | -8.045 |
agara | -7.982 |
avorite | -7.863 |
Token | Fat |
Token ID | 12301 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Philipp | +1.632 |
Soda | +1.615 |
Whe | +1.592 |
HEL | +1.578 |
TE | +1.566 |
Neg logit contributions | |
interstitial | -2.641 |
ebus | -2.516 |
�� | -2.378 |
agara | -2.330 |
Cu | -2.308 |
Token | ) |
Token ID | 8 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Philipp | +3.285 |
Soda | +3.251 |
Whe | +3.247 |
TE | +3.178 |
Sel | +3.156 |
Neg logit contributions | |
interstitial | -5.912 |
ebus | -5.506 |
�� | -5.305 |
agara | -5.221 |
Cu | -5.110 |
Token | diet |
Token ID | 5496 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Philipp | +1.376 |
Soda | +1.352 |
Whe | +1.341 |
HEL | +1.328 |
TE | +1.319 |
Neg logit contributions | |
interstitial | -3.088 |
ebus | -2.950 |
�� | -2.808 |
agara | -2.760 |
Cu | -2.728 |
Token | 33 |
Token ID | 2091 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
interstitial | +3.322 |
ebus | +3.204 |
Cu | +2.973 |
�� | +2.969 |
agara | +2.911 |
Neg logit contributions | |
Philipp | -2.481 |
HEL | -2.398 |
Soda | -2.385 |
Whe | -2.336 |
TE | -2.328 |
Token | s |
Token ID | 82 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
interstitial | +0.512 |
ebus | +0.494 |
�� | +0.461 |
Cu | +0.453 |
agara | +0.452 |
Neg logit contributions | |
Philipp | -0.375 |
HEL | -0.363 |
Soda | -0.360 |
Whe | -0.356 |
TE | -0.354 |
Token | )} |
Token ID | 38165 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Philipp | +0.835 |
HEL | +0.813 |
Soda | +0.809 |
TE | +0.799 |
Whe | +0.799 |
Neg logit contributions | |
interstitial | -0.862 |
ebus | -0.823 |
�� | -0.763 |
agara | -0.744 |
Cu | -0.741 |
Token | O |
Token ID | 440 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
Philipp | +2.619 |
Sel | +2.498 |
Soda | +2.491 |
Whe | +2.483 |
TE | +2.472 |
Neg logit contributions | |
interstitial | -3.829 |
ebus | -3.696 |
�� | -3.496 |
agara | -3.404 |
EVA | -3.338 |
Token | - |
Token ID | 12 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Philipp | +2.947 |
Whe | +2.846 |
Sel | +2.801 |
Soda | +2.788 |
TE | +2.779 |
Neg logit contributions | |
interstitial | -5.651 |
ebus | -5.482 |
�� | -5.288 |
agara | -5.077 |
�� | -5.051 |
Token | O |
Token ID | 46 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Philipp | +3.197 |
Whe | +3.090 |
TE | +3.072 |
Soda | +3.059 |
wic | +3.029 |
Neg logit contributions | |
interstitial | -4.667 |
ebus | -4.523 |
�� | -4.243 |
agara | -4.226 |
bilt | -4.082 |
Token | { |
Token ID | 1391 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Philipp | +6.932 |
TE | +6.677 |
Sel | +6.625 |
Soda | +6.605 |
Whe | +6.570 |
Neg logit contributions | |
interstitial | -8.164 |
ebus | -7.736 |
�� | -7.212 |
agara | -7.130 |
bilt | -6.888 |
Token | ( |
Token ID | 7 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Philipp | +2.753 |
HEL | +2.684 |
TE | +2.664 |
Soda | +2.662 |
Sel | +2.659 |
Neg logit contributions | |
interstitial | -4.072 |
ebus | -3.875 |
�� | -3.706 |
agara | -3.582 |
avorite | -3.507 |
Token | 99 |
Token ID | 2079 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
interstitial | +2.728 |
ebus | +2.629 |
�� | +2.443 |
Cu | +2.434 |
agara | +2.395 |
Neg logit contributions | |
Philipp | -2.026 |
HEL | -1.960 |
Soda | -1.947 |
Whe | -1.914 |
TE | -1.906 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
interstitial | +0.599 |
ebus | +0.578 |
�� | +0.539 |
Cu | +0.530 |
agara | +0.530 |
Neg logit contributions | |
Philipp | -0.435 |
HEL | -0.421 |
Soda | -0.418 |
Whe | -0.412 |
TE | -0.411 |
Token | s |
Token ID | 82 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Philipp | +1.770 |
Soda | +1.719 |
HEL | +1.705 |
Sel | +1.691 |
TE | +1.686 |
Neg logit contributions | |
interstitial | -2.764 |
ebus | -2.659 |
�� | -2.506 |
agara | -2.441 |
Cu | -2.419 |
Token | )} |
Token ID | 38165 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Philipp | +1.767 |
HEL | +1.721 |
Soda | +1.714 |
TE | +1.699 |
Whe | +1.692 |
Neg logit contributions | |
interstitial | -1.916 |
ebus | -1.821 |
�� | -1.698 |
agara | -1.652 |
Cu | -1.639 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Philipp | +2.718 |
Sel | +2.626 |
TE | +2.607 |
HEL | +2.604 |
Soda | +2.591 |
Neg logit contributions | |
interstitial | -3.757 |
ebus | -3.654 |
�� | -3.384 |
Cu | -3.328 |
agara | -3.317 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
interstitial | +1.163 |
ebus | +1.132 |
Cu | +1.051 |
�� | +1.028 |
mare | +1.024 |
Neg logit contributions | |
Philipp | -1.038 |
HEL | -1.014 |
Soda | -1.010 |
CONFIG | -0.985 |
Whe | -0.983 |
Token | O |
Token ID | 440 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Philipp | +3.363 |
Sel | +3.202 |
Whe | +3.188 |
TE | +3.183 |
Soda | +3.171 |
Neg logit contributions | |
interstitial | -4.809 |
ebus | -4.689 |
�� | -4.395 |
agara | -4.310 |
EVA | -4.214 |
Token | - |
Token ID | 12 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Philipp | +2.389 |
Whe | +2.285 |
TE | +2.248 |
Sel | +2.237 |
HEL | +2.221 |
Neg logit contributions | |
interstitial | -4.661 |
ebus | -4.555 |
�� | -4.363 |
agara | -4.200 |
�� | -4.168 |
Token | O |
Token ID | 46 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Philipp | +3.162 |
Whe | +3.053 |
Soda | +3.019 |
TE | +3.014 |
Sel | +2.993 |
Neg logit contributions | |
interstitial | -4.448 |
ebus | -4.354 |
agara | -4.007 |
�� | -4.001 |
bilt | -3.860 |
Token | { |
Token ID | 1391 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Philipp | +6.849 |
TE | +6.660 |
Whe | +6.642 |
Sel | +6.526 |
Soda | +6.492 |
Neg logit contributions | |
interstitial | -8.006 |
ebus | -7.797 |
�� | -7.246 |
agara | -7.192 |
avorite | -7.061 |
Token | ( |
Token ID | 7 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Philipp | +3.128 |
HEL | +3.043 |
TE | +3.034 |
Soda | +3.029 |
Sel | +3.027 |
Neg logit contributions | |
interstitial | -4.689 |
ebus | -4.463 |
�� | -4.277 |
agara | -4.132 |
�� | -4.057 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
interstitial | +1.567 |
ebus | +1.512 |
�� | +1.410 |
Cu | +1.397 |
agara | +1.384 |
Neg logit contributions | |
Philipp | -1.106 |
HEL | -1.072 |
Soda | -1.063 |
Whe | -1.045 |
TE | -1.043 |
Token | s |
Token ID | 82 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
interstitial | +0.023 |
ebus | +0.022 |
�� | +0.020 |
Cu | +0.020 |
agara | +0.020 |
Neg logit contributions | |
Philipp | -0.017 |
HEL | -0.016 |
Soda | -0.016 |
Whe | -0.016 |
TE | -0.016 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
Philipp | +1.406 |
HEL | +1.369 |
Soda | +1.365 |
TE | +1.353 |
Whe | +1.347 |
Neg logit contributions | |
interstitial | -1.525 |
ebus | -1.449 |
�� | -1.350 |
agara | -1.314 |
Cu | -1.303 |
Token | ing |
Token ID | 278 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
Philipp | +4.624 |
Sel | +4.562 |
wic | +4.556 |
Soda | +4.552 |
Whe | +4.516 |
Neg logit contributions | |
interstitial | -5.731 |
ebus | -5.390 |
�� | -5.291 |
�� | -5.023 |
agara | -5.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Philipp | +3.705 |
HEL | +3.661 |
Whe | +3.649 |
Sel | +3.638 |
Soda | +3.630 |
Neg logit contributions | |
interstitial | -6.494 |
ebus | -6.134 |
�� | -5.910 |
agara | -5.783 |
avorite | -5.682 |
Token | Font |
Token ID | 23252 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Lin | +6.048 |
Philipp | +6.044 |
HEL | +6.001 |
wic | +5.989 |
Whe | +5.963 |
Neg logit contributions | |
interstitial | -7.945 |
ebus | -7.791 |
agara | -7.424 |
�� | -7.323 |
axter | -6.983 |
Token | Style |
Token ID | 21466 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Philipp | +2.992 |
HEL | +2.956 |
Soda | +2.926 |
TE | +2.905 |
Sel | +2.891 |
Neg logit contributions | |
interstitial | -3.897 |
ebus | -3.798 |
�� | -3.510 |
agara | -3.505 |
Cu | -3.358 |
Token | ] |
Token ID | 60 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Philipp | +1.191 |
HEL | +1.160 |
Soda | +1.150 |
Whe | +1.137 |
TE | +1.135 |
Neg logit contributions | |
interstitial | -1.555 |
ebus | -1.490 |
�� | -1.390 |
agara | -1.369 |
Cu | -1.353 |
Token | :: |
Token ID | 3712 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Philipp | +0.866 |
HEL | +0.845 |
Soda | +0.837 |
TE | +0.831 |
Whe | +0.829 |
Neg logit contributions | |
interstitial | -0.918 |
ebus | -0.880 |
�� | -0.813 |
agara | -0.798 |
Cu | -0.792 |
Token | B |
Token ID | 33 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
HEL | +6.881 |
Philipp | +6.817 |
Lin | +6.770 |
Whe | +6.768 |
wic | +6.711 |
Neg logit contributions | |
ebus | -7.405 |
interstitial | -7.391 |
agara | -6.763 |
�� | -6.760 |
avorite | -6.324 |
Token | old |
Token ID | 727 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
Philipp | +1.446 |
HEL | +1.413 |
Whe | +1.402 |
Soda | +1.400 |
Sel | +1.394 |
Neg logit contributions | |
interstitial | -1.693 |
ebus | -1.623 |
�� | -1.539 |
agara | -1.495 |
EVA | -1.473 |
Token | ) |
Token ID | 8 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Philipp | +0.560 |
HEL | +0.545 |
Soda | +0.539 |
Whe | +0.535 |
TE | +0.533 |
Neg logit contributions | |
interstitial | -0.683 |
ebus | -0.657 |
�� | -0.609 |
agara | -0.600 |
Cu | -0.593 |
Token | $ |
Token ID | 720 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
Philipp | +0.813 |
HEL | +0.788 |
Soda | +0.783 |
Whe | +0.772 |
TE | +0.771 |
Neg logit contributions | |
interstitial | -1.039 |
ebus | -1.001 |
�� | -0.932 |
agara | -0.916 |
Cu | -0.913 |
Token | Br |
Token ID | 9414 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Philipp | +0.374 |
HEL | +0.361 |
Soda | +0.357 |
Whe | +0.352 |
TE | +0.352 |
Neg logit contributions | |
interstitial | -0.642 |
ebus | -0.622 |
�� | -0.586 |
agara | -0.576 |
Cu | -0.573 |
Token | When |
Token ID | 1649 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Philipp | +0.929 |
HEL | +0.909 |
Soda | +0.898 |
TE | +0.894 |
Whe | +0.890 |
Neg logit contributions | |
interstitial | -1.093 |
ebus | -1.058 |
�� | -0.979 |
agara | -0.956 |
Cu | -0.944 |
Token | we |
Token ID | 356 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Philipp | +2.382 |
HEL | +2.317 |
Soda | +2.291 |
Whe | +2.290 |
TE | +2.284 |
Neg logit contributions | |
interstitial | -3.033 |
ebus | -2.916 |
�� | -2.720 |
agara | -2.652 |
Cu | -2.648 |
Token | watched |
Token ID | 7342 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Philipp | +2.028 |
HEL | +1.962 |
TE | +1.961 |
Soda | +1.961 |
Whe | +1.957 |
Neg logit contributions | |
interstitial | -2.572 |
ebus | -2.438 |
�� | -2.291 |
Cu | -2.197 |
agara | -2.196 |
Token | this |
Token ID | 428 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Philipp | +3.076 |
Soda | +2.972 |
Sel | +2.951 |
HEL | +2.949 |
Whe | +2.941 |
Neg logit contributions | |
interstitial | -4.097 |
ebus | -3.910 |
�� | -3.717 |
agara | -3.567 |
Cu | -3.527 |
Token | little |
Token ID | 1310 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Philipp | +2.874 |
Soda | +2.773 |
Sel | +2.754 |
HEL | +2.740 |
TE | +2.735 |
Neg logit contributions | |
interstitial | -6.012 |
ebus | -5.861 |
�� | -5.660 |
agara | -5.448 |
Cu | -5.433 |
Token | gag |
Token ID | 32261 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Philipp | +1.110 |
HEL | +1.062 |
Soda | +1.052 |
Whe | +1.035 |
TE | +1.032 |
Neg logit contributions | |
interstitial | -2.452 |
ebus | -2.377 |
�� | -2.253 |
Cu | -2.209 |
agara | -2.206 |
Token | with |
Token ID | 351 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Philipp | +4.742 |
Sel | +4.637 |
HEL | +4.595 |
TE | +4.590 |
Whe | +4.580 |
Neg logit contributions | |
interstitial | -10.266 |
ebus | -9.691 |
�� | -9.436 |
�� | -9.234 |
agara | -9.112 |
Token | Erin |
Token ID | 28894 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Philipp | +1.605 |
HEL | +1.550 |
Soda | +1.547 |
Sel | +1.539 |
Whe | +1.536 |
Neg logit contributions | |
interstitial | -1.829 |
ebus | -1.763 |
�� | -1.634 |
Cu | -1.598 |
agara | -1.598 |
Token | and |
Token ID | 290 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Philipp | +2.062 |
HEL | +1.978 |
Sel | +1.960 |
Whe | +1.957 |
Soda | +1.939 |
Neg logit contributions | |
interstitial | -3.533 |
ebus | -3.422 |
�� | -3.232 |
agara | -3.147 |
Cu | -3.126 |
Token | Jill |
Token ID | 22772 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
interstitial | +2.762 |
ebus | +2.650 |
�� | +2.450 |
Cu | +2.410 |
agara | +2.404 |
Neg logit contributions | |
Philipp | -2.451 |
HEL | -2.391 |
Soda | -2.388 |
TE | -2.354 |
Whe | -2.353 |
Token | ian |
Token ID | 666 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Philipp | +1.264 |
HEL | +1.210 |
Soda | +1.196 |
Sel | +1.181 |
Whe | +1.180 |
Neg logit contributions | |
interstitial | -1.969 |
ebus | -1.909 |
�� | -1.818 |
agara | -1.757 |
Cu | -1.754 |
Token | agreed |
Token ID | 4987 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
Philipp | +0.304 |
HEL | +0.295 |
Soda | +0.291 |
TE | +0.291 |
Whe | +0.290 |
Neg logit contributions | |
interstitial | -0.357 |
ebus | -0.340 |
�� | -0.317 |
Cu | -0.310 |
agara | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Philipp | +0.420 |
HEL | +0.408 |
Soda | +0.403 |
TE | +0.402 |
Whe | +0.401 |
Neg logit contributions | |
interstitial | -0.494 |
ebus | -0.469 |
�� | -0.439 |
agara | -0.430 |
Cu | -0.428 |
Token | — |
Token ID | 851 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Philipp | +0.893 |
HEL | +0.858 |
Whe | +0.848 |
Soda | +0.847 |
Sel | +0.838 |
Neg logit contributions | |
interstitial | -1.506 |
ebus | -1.446 |
�� | -1.358 |
agara | -1.341 |
Cu | -1.325 |
Token | Ren |
Token ID | 7152 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
Philipp | +2.501 |
HEL | +2.399 |
Sel | +2.385 |
Soda | +2.379 |
Whe | +2.366 |
Neg logit contributions | |
interstitial | -3.448 |
ebus | -3.253 |
�� | -3.048 |
agara | -3.023 |
Cu | -3.008 |
Token | aud |
Token ID | 3885 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Philipp | +0.334 |
HEL | +0.318 |
Whe | +0.312 |
Soda | +0.311 |
Sel | +0.307 |
Neg logit contributions | |
interstitial | -0.863 |
ebus | -0.835 |
�� | -0.795 |
Cu | -0.781 |
agara | -0.778 |
Token | Lav |
Token ID | 21438 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Philipp | +1.123 |
HEL | +1.086 |
Soda | +1.075 |
Whe | +1.067 |
Sel | +1.064 |
Neg logit contributions | |
interstitial | -1.894 |
ebus | -1.819 |
�� | -1.704 |
agara | -1.678 |
Cu | -1.664 |
Token | o |
Token ID | 78 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
TE | +2.199 |
oqu | +2.084 |
Whe | +2.082 |
wic | +2.074 |
Philipp | +2.064 |
Neg logit contributions | |
interstitial | -12.687 |
ebus | -11.998 |
�� | -11.840 |
�� | -11.640 |
avorite | -11.412 |
Token | ie |
Token ID | 494 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
interstitial | +0.861 |
ebus | +0.834 |
�� | +0.764 |
Cu | +0.759 |
agara | +0.756 |
Neg logit contributions | |
Philipp | -0.776 |
HEL | -0.755 |
Soda | -0.751 |
Whe | -0.735 |
TE | -0.734 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Philipp | +0.568 |
HEL | +0.544 |
Soda | +0.539 |
Whe | +0.529 |
TE | +0.527 |
Neg logit contributions | |
interstitial | -1.251 |
ebus | -1.211 |
�� | -1.145 |
agara | -1.127 |
Cu | -1.125 |
Token | ren |
Token ID | 918 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Philipp | +0.764 |
HEL | +0.734 |
Soda | +0.723 |
TE | +0.717 |
wic | +0.716 |
Neg logit contributions | |
interstitial | -1.671 |
ebus | -1.621 |
�� | -1.542 |
Cu | -1.509 |
agara | -1.508 |
Token | lav |
Token ID | 18809 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Philipp | +0.117 |
HEL | +0.114 |
Soda | +0.113 |
Whe | +0.112 |
TE | +0.112 |
Neg logit contributions | |
interstitial | -0.095 |
ebus | -0.090 |
�� | -0.082 |
agara | -0.081 |
Cu | -0.081 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
Philipp | +2.010 |
HEL | +1.948 |
Soda | +1.927 |
TE | +1.908 |
Whe | +1.902 |
Neg logit contributions | |
interstitial | -2.728 |
ebus | -2.637 |
�� | -2.455 |
agara | -2.411 |
Cu | -2.407 |
Token | Try |
Token ID | 9993 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
interstitial | +0.492 |
ebus | +0.474 |
�� | +0.443 |
Cu | +0.435 |
agara | +0.434 |
Neg logit contributions | |
Philipp | -0.373 |
HEL | -0.362 |
Soda | -0.359 |
Whe | -0.354 |
TE | -0.353 |
Token | { |
Token ID | 1391 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
interstitial | +2.754 |
ebus | +2.618 |
�� | +2.352 |
Cu | +2.349 |
agara | +2.280 |
Neg logit contributions | |
Philipp | -3.705 |
HEL | -3.631 |
Soda | -3.630 |
TE | -3.581 |
Whe | -3.568 |
Token | for |
Token ID | 329 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
interstitial | +0.700 |
ebus | +0.676 |
�� | +0.633 |
Cu | +0.623 |
agara | +0.622 |
Neg logit contributions | |
Philipp | -0.457 |
HEL | -0.441 |
Soda | -0.438 |
Whe | -0.432 |
TE | -0.430 |
Token | ($ |
Token ID | 7198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
interstitial | +1.982 |
ebus | +1.904 |
�� | +1.783 |
Cu | +1.755 |
agara | +1.744 |
Neg logit contributions | |
Philipp | -1.413 |
HEL | -1.364 |
Soda | -1.357 |
Whe | -1.334 |
wic | -1.326 |
Token | i |
Token ID | 72 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
interstitial | +2.646 |
ebus | +2.486 |
�� | +2.288 |
Cu | +2.263 |
agara | +2.238 |
Neg logit contributions | |
Philipp | -3.072 |
HEL | -3.011 |
Soda | -2.985 |
Whe | -2.954 |
TE | -2.940 |
Token | ; |
Token ID | 2162 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
interstitial | +8.497 |
ebus | +8.041 |
�� | +7.432 |
Cu | +7.389 |
agara | +7.360 |
Neg logit contributions | |
Philipp | -10.520 |
Soda | -10.338 |
HEL | -10.330 |
Whe | -10.279 |
wic | -10.221 |
Token | $ |
Token ID | 720 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
interstitial | +1.756 |
ebus | +1.677 |
�� | +1.552 |
Cu | +1.524 |
agara | +1.513 |
Neg logit contributions | |
Philipp | -1.740 |
HEL | -1.693 |
Soda | -1.686 |
Whe | -1.663 |
Sel | -1.657 |
Token | i |
Token ID | 72 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
interstitial | +1.812 |
ebus | +1.711 |
�� | +1.561 |
Cu | +1.530 |
agara | +1.527 |
Neg logit contributions | |
Philipp | -2.179 |
HEL | -2.129 |
Soda | -2.118 |
Whe | -2.093 |
TE | -2.088 |
Token | - |
Token ID | 532 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
interstitial | +7.559 |
ebus | +7.171 |
Cu | +6.660 |
agara | +6.551 |
�� | +6.528 |
Neg logit contributions | |
Philipp | -7.314 |
wic | -7.067 |
HEL | -7.012 |
Soda | -6.998 |
Whe | -6.960 |
Token | le |
Token ID | 293 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Philipp | +0.646 |
HEL | +0.624 |
Soda | +0.617 |
Sel | +0.611 |
Whe | +0.610 |
Neg logit contributions | |
interstitial | -0.927 |
ebus | -0.900 |
�� | -0.841 |
agara | -0.826 |
Cu | -0.820 |
Token | for |
Token ID | 329 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
interstitial | +1.756 |
ebus | +1.686 |
�� | +1.559 |
Cu | +1.528 |
agara | +1.528 |
Neg logit contributions | |
Philipp | -1.656 |
HEL | -1.610 |
Soda | -1.599 |
Whe | -1.582 |
TE | -1.573 |
Token | ( |
Token ID | 7 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
interstitial | +5.135 |
ebus | +4.916 |
�� | +4.585 |
Cu | +4.571 |
agara | +4.496 |
Neg logit contributions | |
Philipp | -3.641 |
Soda | -3.515 |
HEL | -3.477 |
Whe | -3.456 |
Sel | -3.434 |
Token | size |
Token ID | 2546 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
interstitial | +5.323 |
ebus | +5.072 |
�� | +4.753 |
Cu | +4.664 |
EVA | +4.644 |
Neg logit contributions | |
Philipp | -4.164 |
HEL | -4.059 |
Soda | -4.012 |
Whe | -4.008 |
wic | -3.928 |
Token | _ |
Token ID | 62 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
interstitial | +4.830 |
ebus | +4.752 |
Cu | +4.389 |
�� | +4.284 |
agara | +4.269 |
Neg logit contributions | |
Philipp | -4.434 |
Soda | -4.328 |
HEL | -4.314 |
Whe | -4.245 |
wic | -4.224 |
Token | t |
Token ID | 83 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
interstitial | +4.484 |
ebus | +4.302 |
�� | +3.953 |
Cu | +3.953 |
agara | +3.946 |
Neg logit contributions | |
Philipp | -3.685 |
HEL | -3.638 |
Soda | -3.600 |
Whe | -3.527 |
Sel | -3.471 |
Token | u |
Token ID | 334 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
interstitial | +4.692 |
ebus | +4.503 |
�� | +4.180 |
agara | +4.092 |
Cu | +4.085 |
Neg logit contributions | |
Philipp | -4.539 |
HEL | -4.403 |
Soda | -4.398 |
Whe | -4.347 |
Sel | -4.323 |
Token | Part |
Token ID | 7841 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
interstitial | +7.979 |
ebus | +7.627 |
�� | +6.964 |
Cu | +6.954 |
mare | +6.913 |
Neg logit contributions | |
Philipp | -9.882 |
HEL | -9.840 |
Soda | -9.699 |
Whe | -9.548 |
Sel | -9.535 |
Token | icle |
Token ID | 1548 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
interstitial | +0.864 |
ebus | +0.826 |
�� | +0.777 |
agara | +0.762 |
Cu | +0.756 |
Neg logit contributions | |
Philipp | -0.587 |
HEL | -0.568 |
Soda | -0.565 |
Whe | -0.556 |
Sel | -0.555 |
Token | = |
Token ID | 796 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
interstitial | +3.984 |
ebus | +3.832 |
�� | +3.527 |
Cu | +3.480 |
agara | +3.453 |
Neg logit contributions | |
Philipp | -4.069 |
HEL | -3.966 |
Soda | -3.942 |
Whe | -3.891 |
Sel | -3.881 |
Token | 0 |
Token ID | 657 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
Philipp | +2.041 |
HEL | +2.002 |
Soda | +1.977 |
TE | +1.976 |
CONFIG | +1.951 |
Neg logit contributions | |
interstitial | -2.651 |
ebus | -2.554 |
�� | -2.397 |
Cu | -2.335 |
agara | -2.301 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Philipp | +0.038 |
HEL | +0.037 |
Soda | +0.037 |
TE | +0.036 |
Whe | +0.036 |
Neg logit contributions | |
interstitial | -0.064 |
ebus | -0.061 |
�� | -0.057 |
agara | -0.057 |
Cu | -0.056 |
Token | # |
Token ID | 1303 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Philipp | +1.897 |
HEL | +1.788 |
CONFIG | +1.778 |
TE | +1.768 |
Sel | +1.748 |
Neg logit contributions | |
interstitial | -4.692 |
ebus | -4.543 |
�� | -4.301 |
agara | -4.246 |
Cu | -4.227 |
Token | import |
Token ID | 1330 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
interstitial | +1.233 |
ebus | +1.180 |
�� | +1.083 |
Cu | +1.057 |
agara | +1.056 |
Neg logit contributions | |
Philipp | -1.385 |
HEL | -1.350 |
Soda | -1.345 |
Whe | -1.329 |
TE | -1.322 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
interstitial | +1.449 |
ebus | +1.397 |
�� | +1.277 |
Cu | +1.270 |
agara | +1.252 |
Neg logit contributions | |
Philipp | -1.473 |
HEL | -1.440 |
Soda | -1.433 |
wic | -1.410 |
Whe | -1.401 |
Token | necessary |
Token ID | 3306 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Philipp | +0.735 |
HEL | +0.716 |
Soda | +0.712 |
TE | +0.700 |
Whe | +0.700 |
Neg logit contributions | |
interstitial | -0.814 |
ebus | -0.784 |
�� | -0.722 |
agara | -0.712 |
Cu | -0.711 |
Token | packages |
Token ID | 10392 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
interstitial | +3.352 |
ebus | +3.344 |
Cu | +3.063 |
�� | +2.975 |
mare | +2.972 |
Neg logit contributions | |
Philipp | -3.397 |
Soda | -3.329 |
HEL | -3.304 |
wic | -3.234 |
Whe | -3.141 |
Token | from |
Token ID | 422 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
interstitial | +2.307 |
ebus | +2.229 |
Cu | +2.054 |
�� | +2.027 |
agara | +2.021 |
Neg logit contributions | |
Philipp | -2.265 |
HEL | -2.196 |
Soda | -2.189 |
wic | -2.164 |
Whe | -2.138 |
Token | im |
Token ID | 545 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ebus | +8.644 |
interstitial | +8.510 |
agara | +7.575 |
�� | +7.468 |
mare | +7.341 |
Neg logit contributions | |
HEL | -7.935 |
Soda | -7.900 |
Philipp | -7.895 |
wic | -7.814 |
Whe | -7.745 |
Token | utils |
Token ID | 26791 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
interstitial | +4.866 |
ebus | +4.745 |
agara | +4.230 |
Cu | +4.127 |
mare | +4.048 |
Neg logit contributions | |
Philipp | -6.969 |
HEL | -6.843 |
Soda | -6.814 |
Whe | -6.626 |
Sel | -6.615 |
Token | import |
Token ID | 1330 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
interstitial | +2.560 |
ebus | +2.464 |
Cu | +2.180 |
agara | +2.150 |
mare | +2.124 |
Neg logit contributions | |
Philipp | -3.785 |
HEL | -3.701 |
Soda | -3.684 |
wic | -3.648 |
Whe | -3.639 |
Token | paths |
Token ID | 13532 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Philipp | +2.895 |
HEL | +2.770 |
CONFIG | +2.757 |
Sel | +2.753 |
Whe | +2.702 |
Neg logit contributions | |
interstitial | -5.290 |
ebus | -5.126 |
�� | -4.769 |
Cu | -4.766 |
agara | -4.719 |
Token | import |
Token ID | 1330 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
interstitial | +2.531 |
ebus | +2.425 |
Cu | +2.168 |
�� | +2.146 |
mare | +2.131 |
Neg logit contributions | |
Philipp | -3.547 |
HEL | -3.459 |
Soda | -3.445 |
Whe | -3.423 |
wic | -3.418 |
Token | Flag |
Token ID | 34227 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
interstitial | +1.619 |
ebus | +1.511 |
Cu | +1.342 |
�� | +1.307 |
EVA | +1.260 |
Neg logit contributions | |
Philipp | -3.491 |
HEL | -3.417 |
Soda | -3.405 |
Whe | -3.366 |
TE | -3.354 |
Token | Reply |
Token ID | 14883 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
interstitial | +3.291 |
ebus | +3.142 |
�� | +2.884 |
Cu | +2.828 |
mare | +2.793 |
Neg logit contributions | |
Philipp | -3.574 |
HEL | -3.508 |
wic | -3.488 |
Soda | -3.454 |
Whe | -3.421 |
Token |
|
Token ID | 198 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
interstitial | +3.402 |
ebus | +3.379 |
Cu | +3.080 |
mare | +2.977 |
�� | +2.950 |
Neg logit contributions | |
Philipp | -4.689 |
Soda | -4.576 |
HEL | -4.557 |
wic | -4.520 |
CONFIG | -4.438 |
Token |
|
Token ID | 198 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
ebus | +4.495 |
Cu | +4.394 |
interstitial | +4.331 |
mare | +4.109 |
EVA | +4.074 |
Neg logit contributions | |
Philipp | -8.359 |
Soda | -8.238 |
HEL | -8.155 |
wic | -7.968 |
CONFIG | -7.908 |
Token | 55 |
Token ID | 2816 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
interstitial | +6.157 |
ebus | +5.860 |
Cu | +5.692 |
EVA | +5.496 |
mare | +5.315 |
Neg logit contributions | |
Philipp | -6.036 |
HEL | -5.845 |
Soda | -5.806 |
Whe | -5.701 |
wic | -5.670 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
interstitial | +3.240 |
ebus | +3.119 |
�� | +2.917 |
Cu | +2.911 |
agara | +2.835 |
Neg logit contributions | |
Philipp | -2.934 |
wic | -2.847 |
HEL | -2.840 |
Soda | -2.827 |
Whe | -2.788 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ebus | +5.351 |
Cu | +5.050 |
interstitial | +4.971 |
mare | +4.710 |
EVA | +4.606 |
Neg logit contributions | |
Philipp | -10.176 |
Soda | -10.042 |
HEL | -10.000 |
wic | -9.988 |
CONFIG | -9.718 |
Token |
|
Token ID | 198 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
interstitial | +1.447 |
ebus | +1.414 |
Cu | +1.307 |
�� | +1.267 |
agara | +1.262 |
Neg logit contributions | |
Philipp | -1.718 |
Soda | -1.674 |
HEL | -1.672 |
wic | -1.630 |
Whe | -1.625 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
interstitial | +2.628 |
ebus | +2.353 |
Cu | +2.198 |
�� | +2.086 |
EVA | +2.019 |
Neg logit contributions | |
Philipp | -5.503 |
Soda | -5.339 |
HEL | -5.311 |
Whe | -5.267 |
TE | -5.252 |
Token | Share |
Token ID | 8734 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
interstitial | +3.606 |
ebus | +3.457 |
�� | +3.028 |
Cu | +2.914 |
agara | +2.661 |
Neg logit contributions | |
wic | -9.194 |
Philipp | -9.093 |
Soda | -8.959 |
HEL | -8.876 |
UCHIJ | -8.864 |
Token | this |
Token ID | 428 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
interstitial | +1.796 |
ebus | +1.740 |
�� | +1.581 |
Cu | +1.579 |
agara | +1.558 |
Neg logit contributions | |
Philipp | -1.800 |
HEL | -1.748 |
Soda | -1.743 |
Whe | -1.721 |
wic | -1.713 |
Token | will |
Token ID | 481 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
interstitial | +1.326 |
ebus | +1.301 |
Cu | +1.175 |
agara | +1.175 |
�� | +1.170 |
Neg logit contributions | |
Philipp | -1.501 |
Soda | -1.474 |
HEL | -1.460 |
wic | -1.430 |
Whe | -1.419 |
Token | contain |
Token ID | 3994 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Philipp | +1.887 |
HEL | +1.833 |
TE | +1.785 |
Sel | +1.782 |
Whe | +1.781 |
Neg logit contributions | |
interstitial | -3.763 |
ebus | -3.605 |
�� | -3.405 |
Cu | -3.323 |
agara | -3.296 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
interstitial | +0.136 |
ebus | +0.131 |
�� | +0.121 |
Cu | +0.119 |
agara | +0.119 |
Neg logit contributions | |
Philipp | -0.124 |
HEL | -0.120 |
Soda | -0.120 |
Whe | -0.118 |
TE | -0.118 |
Token | instructions |
Token ID | 7729 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
interstitial | +1.463 |
ebus | +1.405 |
�� | +1.304 |
agara | +1.299 |
Cu | +1.291 |
Neg logit contributions | |
Philipp | -1.048 |
Soda | -1.021 |
HEL | -1.010 |
wic | -0.996 |
Whe | -0.995 |
Token | to |
Token ID | 284 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
interstitial | +0.415 |
ebus | +0.400 |
�� | +0.366 |
Cu | +0.363 |
agara | +0.361 |
Neg logit contributions | |
Philipp | -0.431 |
HEL | -0.419 |
Soda | -0.417 |
Whe | -0.410 |
wic | -0.408 |
Token | create |
Token ID | 2251 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
interstitial | +3.534 |
ebus | +3.487 |
agara | +3.226 |
Cu | +3.142 |
�� | +3.086 |
Neg logit contributions | |
Philipp | -4.127 |
HEL | -3.994 |
Soda | -3.992 |
Whe | -3.929 |
wic | -3.905 |
Token | lambda |
Token ID | 37456 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
interstitial | +6.476 |
ebus | +6.215 |
agara | +5.642 |
�� | +5.575 |
Cu | +5.373 |
Neg logit contributions | |
Philipp | -9.762 |
Soda | -9.752 |
wic | -9.467 |
Whe | -9.382 |
Gins | -9.315 |
Token | functions |
Token ID | 5499 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
interstitial | +2.538 |
ebus | +2.477 |
agara | +2.122 |
Cu | +2.073 |
�� | +2.051 |
Neg logit contributions | |
Soda | -5.863 |
Philipp | -5.845 |
HEL | -5.686 |
wic | -5.684 |
Whe | -5.609 |
Token | using |
Token ID | 1262 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Philipp | +0.520 |
HEL | +0.501 |
Soda | +0.497 |
Whe | +0.490 |
TE | +0.489 |
Neg logit contributions | |
interstitial | -0.905 |
ebus | -0.872 |
�� | -0.823 |
agara | -0.807 |
Cu | -0.806 |
Token | the |
Token ID | 262 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
interstitial | +2.899 |
ebus | +2.858 |
Cu | +2.587 |
agara | +2.564 |
�� | +2.561 |
Neg logit contributions | |
Philipp | -3.224 |
HEL | -3.135 |
Soda | -3.128 |
wic | -3.085 |
Whe | -3.056 |
Token | archived |
Token ID | 33962 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
interstitial | +3.494 |
ebus | +3.338 |
�� | +3.103 |
agara | +3.048 |
Cu | +3.011 |
Neg logit contributions | |
Philipp | -3.804 |
Soda | -3.683 |
HEL | -3.675 |
TE | -3.621 |
Whe | -3.619 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
interstitial | +3.642 |
ebus | +3.547 |
�� | +3.259 |
Cu | +3.181 |
agara | +3.178 |
Neg logit contributions | |
Philipp | -3.552 |
HEL | -3.456 |
Soda | -3.407 |
wic | -3.353 |
TE | -3.339 |
Token | all |
Token ID | 477 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
interstitial | +1.833 |
ebus | +1.769 |
�� | +1.653 |
Cu | +1.624 |
agara | +1.624 |
Neg logit contributions | |
Philipp | -1.319 |
HEL | -1.276 |
Soda | -1.267 |
Whe | -1.247 |
TE | -1.244 |
Token | parts |
Token ID | 3354 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
interstitial | +1.289 |
ebus | +1.241 |
�� | +1.156 |
agara | +1.135 |
Cu | +1.135 |
Neg logit contributions | |
Philipp | -0.973 |
HEL | -0.943 |
Soda | -0.938 |
Whe | -0.925 |
TE | -0.922 |
Token | for |
Token ID | 329 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
interstitial | +3.490 |
ebus | +3.383 |
�� | +3.143 |
Cu | +3.106 |
agara | +3.088 |
Neg logit contributions | |
Philipp | -3.036 |
HEL | -2.939 |
Soda | -2.903 |
wic | -2.852 |
TE | -2.848 |
Token | ( |
Token ID | 357 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
interstitial | +2.110 |
ebus | +2.036 |
�� | +1.909 |
Cu | +1.878 |
agara | +1.876 |
Neg logit contributions | |
Philipp | -1.381 |
HEL | -1.333 |
Soda | -1.324 |
Whe | -1.300 |
TE | -1.298 |
Token | part |
Token ID | 3911 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
interstitial | +2.652 |
ebus | +2.552 |
�� | +2.380 |
agara | +2.339 |
Cu | +2.338 |
Neg logit contributions | |
Philipp | -2.066 |
HEL | -2.004 |
Soda | -1.989 |
Whe | -1.961 |
TE | -1.956 |
Token | in |
Token ID | 287 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
interstitial | +8.416 |
ebus | +8.303 |
Cu | +7.699 |
�� | +7.654 |
mare | +7.605 |
Neg logit contributions | |
Philipp | -7.753 |
HEL | -7.586 |
Soda | -7.495 |
Whe | -7.372 |
wic | -7.372 |
Token | parts |
Token ID | 3354 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Philipp | +2.130 |
Whe | +2.063 |
Soda | +2.061 |
HEL | +2.059 |
TE | +2.055 |
Neg logit contributions | |
interstitial | -2.978 |
ebus | -2.841 |
�� | -2.668 |
Cu | -2.605 |
agara | -2.582 |
Token | ) |
Token ID | 8 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
interstitial | +2.462 |
ebus | +2.364 |
�� | +2.192 |
Cu | +2.161 |
agara | +2.149 |
Neg logit contributions | |
Philipp | -2.316 |
HEL | -2.251 |
Soda | -2.239 |
Whe | -2.206 |
TE | -2.201 |
Token | return |
Token ID | 1441 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
interstitial | +4.040 |
ebus | +3.876 |
�� | +3.550 |
agara | +3.497 |
Cu | +3.495 |
Neg logit contributions | |
Philipp | -4.655 |
HEL | -4.530 |
Soda | -4.501 |
Whe | -4.435 |
wic | -4.415 |
Token | ob |
Token ID | 909 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Philipp | +0.910 |
HEL | +0.880 |
Soda | +0.877 |
Whe | +0.873 |
TE | +0.869 |
Neg logit contributions | |
interstitial | -1.234 |
ebus | -1.188 |
�� | -1.115 |
Cu | -1.085 |
agara | -1.079 |
Token | anticipating |
Token ID | 40807 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
interstitial | +1.923 |
ebus | +1.849 |
�� | +1.717 |
Cu | +1.698 |
agara | +1.690 |
Neg logit contributions | |
Philipp | -1.551 |
HEL | -1.508 |
Soda | -1.495 |
Whe | -1.472 |
wic | -1.468 |
Token | an |
Token ID | 281 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Philipp | +0.635 |
HEL | +0.614 |
Soda | +0.614 |
TE | +0.610 |
Whe | +0.610 |
Neg logit contributions | |
interstitial | -0.764 |
ebus | -0.729 |
�� | -0.681 |
agara | -0.662 |
Cu | -0.660 |
Token | evening |
Token ID | 6180 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Philipp | +1.525 |
HEL | +1.495 |
TE | +1.479 |
Soda | +1.476 |
Whe | +1.476 |
Neg logit contributions | |
interstitial | -1.996 |
ebus | -1.938 |
�� | -1.775 |
Cu | -1.755 |
agara | -1.753 |
Token | of |
Token ID | 286 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
interstitial | +1.188 |
ebus | +1.143 |
�� | +1.063 |
agara | +1.043 |
Cu | +1.042 |
Neg logit contributions | |
Philipp | -0.945 |
HEL | -0.918 |
Soda | -0.912 |
Whe | -0.900 |
TE | -0.899 |
Token | trick |
Token ID | 6908 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
Philipp | +0.315 |
HEL | +0.306 |
Soda | +0.305 |
TE | +0.303 |
Whe | +0.302 |
Neg logit contributions | |
interstitial | -0.344 |
ebus | -0.330 |
�� | -0.307 |
agara | -0.300 |
Cu | -0.298 |
Token | or |
Token ID | 393 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
interstitial | +0.617 |
ebus | +0.596 |
�� | +0.559 |
Cu | +0.550 |
agara | +0.550 |
Neg logit contributions | |
Philipp | -0.382 |
HEL | -0.369 |
Soda | -0.366 |
Whe | -0.361 |
TE | -0.359 |
Token | treating |
Token ID | 13622 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ebus | +7.119 |
interstitial | +7.009 |
Cu | +6.504 |
agara | +6.401 |
�� | +6.369 |
Neg logit contributions | |
wic | -8.407 |
Philipp | -8.053 |
Soda | -7.935 |
HEL | -7.771 |
Whe | -7.747 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
interstitial | +1.854 |
ebus | +1.785 |
�� | +1.664 |
Cu | +1.638 |
agara | +1.634 |
Neg logit contributions | |
Philipp | -1.438 |
HEL | -1.394 |
Soda | -1.383 |
Whe | -1.361 |
TE | -1.356 |
Token | With |
Token ID | 2080 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
interstitial | +0.163 |
ebus | +0.157 |
�� | +0.145 |
agara | +0.142 |
Cu | +0.142 |
Neg logit contributions | |
Philipp | -0.139 |
HEL | -0.135 |
Soda | -0.135 |
Whe | -0.133 |
TE | -0.133 |
Token | those |
Token ID | 883 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
interstitial | +0.285 |
ebus | +0.274 |
�� | +0.254 |
agara | +0.250 |
Cu | +0.249 |
Neg logit contributions | |
Philipp | -0.224 |
HEL | -0.217 |
Soda | -0.216 |
Whe | -0.214 |
TE | -0.213 |
Token | schools |
Token ID | 4266 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
interstitial | +3.464 |
ebus | +3.349 |
�� | +3.117 |
Cu | +3.073 |
agara | +3.062 |
Neg logit contributions | |
Philipp | -2.671 |
HEL | -2.593 |
Soda | -2.580 |
wic | -2.516 |
CONFIG | -2.516 |
Token | what |
Token ID | 644 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Philipp | +0.140 |
HEL | +0.136 |
Soda | +0.135 |
Whe | +0.133 |
TE | +0.133 |
Neg logit contributions | |
interstitial | -0.174 |
ebus | -0.167 |
�� | -0.156 |
agara | -0.153 |
Cu | -0.153 |
Token | you |
Token ID | 345 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Philipp | +0.307 |
HEL | +0.298 |
Soda | +0.296 |
Whe | +0.293 |
TE | +0.292 |
Neg logit contributions | |
interstitial | -0.376 |
ebus | -0.363 |
�� | -0.338 |
agara | -0.330 |
Cu | -0.329 |
Token | � |
Token ID | 447 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
interstitial | +1.634 |
ebus | +1.565 |
�� | +1.443 |
Cu | +1.412 |
agara | +1.412 |
Neg logit contributions | |
Philipp | -1.656 |
HEL | -1.612 |
Soda | -1.603 |
Whe | -1.584 |
TE | -1.581 |
Token | � |
Token ID | 247 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
Philipp | +1.304 |
HEL | +1.278 |
Soda | +1.269 |
Sel | +1.260 |
Whe | +1.259 |
Neg logit contributions | |
interstitial | -1.137 |
ebus | -1.097 |
Cu | -0.984 |
agara | -0.982 |
�� | -0.981 |
Token | re |
Token ID | 260 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
interstitial | +0.074 |
ebus | +0.071 |
�� | +0.066 |
agara | +0.065 |
Cu | +0.064 |
Neg logit contributions | |
Philipp | -0.073 |
HEL | -0.070 |
Soda | -0.070 |
TE | -0.070 |
Whe | -0.070 |
Token | talking |
Token ID | 3375 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
interstitial | +2.304 |
ebus | +2.190 |
�� | +2.011 |
Cu | +1.981 |
agara | +1.978 |
Neg logit contributions | |
Philipp | -2.441 |
HEL | -2.367 |
Soda | -2.366 |
Whe | -2.332 |
wic | -2.319 |
Token | about |
Token ID | 546 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
interstitial | +6.481 |
ebus | +6.353 |
Cu | +5.684 |
�� | +5.683 |
mare | +5.633 |
Neg logit contributions | |
Philipp | -8.988 |
HEL | -8.980 |
wic | -8.979 |
Soda | -8.846 |
CONFIG | -8.681 |
Token | . |
Token ID | 13 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
interstitial | +3.071 |
ebus | +2.983 |
�� | +2.748 |
Cu | +2.720 |
agara | +2.704 |
Neg logit contributions | |
Philipp | -2.517 |
HEL | -2.451 |
Soda | -2.433 |
wic | -2.389 |
Whe | -2.383 |
Token | Like |
Token ID | 4525 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
Philipp | +0.569 |
HEL | +0.551 |
Soda | +0.548 |
Whe | +0.542 |
TE | +0.540 |
Neg logit contributions | |
interstitial | -0.756 |
ebus | -0.728 |
�� | -0.679 |
agara | -0.666 |
Cu | -0.663 |
Token | when |
Token ID | 618 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
interstitial | +0.566 |
ebus | +0.545 |
�� | +0.508 |
Cu | +0.500 |
agara | +0.499 |
Neg logit contributions | |
Philipp | -0.422 |
HEL | -0.409 |
Soda | -0.406 |
Whe | -0.400 |
TE | -0.399 |
Token | I |
Token ID | 314 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
Philipp | +0.833 |
HEL | +0.805 |
Soda | +0.803 |
Sel | +0.795 |
Whe | +0.794 |
Neg logit contributions | |
interstitial | -1.084 |
ebus | -1.049 |
�� | -0.981 |
agara | -0.954 |
Cu | -0.952 |
Token | (- |
Token ID | 32590 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
Philipp | +0.258 |
HEL | +0.250 |
Soda | +0.248 |
TE | +0.245 |
Whe | +0.245 |
Neg logit contributions | |
interstitial | -0.359 |
ebus | -0.346 |
�� | -0.321 |
agara | -0.318 |
Cu | -0.315 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
Philipp | +0.355 |
HEL | +0.342 |
Soda | +0.340 |
TE | +0.337 |
Whe | +0.334 |
Neg logit contributions | |
interstitial | -0.537 |
ebus | -0.521 |
�� | -0.487 |
agara | -0.479 |
Cu | -0.475 |
Token | / |
Token ID | 14 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
Philipp | +0.175 |
HEL | +0.170 |
Soda | +0.170 |
TE | +0.168 |
Whe | +0.167 |
Neg logit contributions | |
interstitial | -0.230 |
ebus | -0.223 |
�� | -0.206 |
agara | -0.203 |
Cu | -0.201 |
Token | u |
Token ID | 84 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
interstitial | +0.308 |
ebus | +0.296 |
�� | +0.276 |
agara | +0.271 |
Cu | +0.268 |
Neg logit contributions | |
Philipp | -0.244 |
HEL | -0.236 |
Soda | -0.236 |
TE | -0.233 |
Whe | -0.231 |
Token | )) |
Token ID | 4008 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
interstitial | +3.754 |
ebus | +3.602 |
�� | +3.362 |
Cu | +3.342 |
agara | +3.303 |
Neg logit contributions | |
Philipp | -3.391 |
HEL | -3.269 |
Soda | -3.239 |
Whe | -3.213 |
wic | -3.197 |
Token | � |
Token ID | 6184 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Philipp | +0.436 |
Soda | +0.421 |
HEL | +0.421 |
TE | +0.416 |
Whe | +0.414 |
Neg logit contributions | |
interstitial | -0.566 |
ebus | -0.545 |
�� | -0.506 |
agara | -0.499 |
Cu | -0.495 |
Token | � |
Token ID | 110 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
interstitial | +4.413 |
ebus | +4.233 |
�� | +4.066 |
�� | +3.551 |
Cu | +3.509 |
Neg logit contributions | |
Philipp | -11.085 |
HEL | -10.853 |
Soda | -10.843 |
CONFIG | -10.704 |
Whe | -10.671 |
Token | t |
Token ID | 256 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
interstitial | +2.105 |
ebus | +2.029 |
�� | +1.897 |
Cu | +1.862 |
agara | +1.853 |
Neg logit contributions | |
Philipp | -1.656 |
HEL | -1.609 |
Soda | -1.598 |
Whe | -1.578 |
Sel | -1.564 |
Token | 0 |
Token ID | 15 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
interstitial | +2.576 |
ebus | +2.486 |
�� | +2.340 |
Cu | +2.294 |
agara | +2.281 |
Neg logit contributions | |
Philipp | -1.882 |
HEL | -1.833 |
Soda | -1.819 |
Whe | -1.796 |
TE | -1.772 |
Token | t |
Token ID | 256 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
interstitial | +2.661 |
ebus | +2.569 |
�� | +2.404 |
Cu | +2.358 |
agara | +2.348 |
Neg logit contributions | |
Philipp | -2.177 |
HEL | -2.120 |
Soda | -2.106 |
Whe | -2.081 |
wic | -2.059 |
Token | - |
Token ID | 12 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
interstitial | +2.035 |
ebus | +1.960 |
�� | +1.836 |
Cu | +1.806 |
agara | +1.802 |
Neg logit contributions | |
Philipp | -1.414 |
HEL | -1.370 |
Soda | -1.362 |
Whe | -1.345 |
Sel | -1.328 |
Token | Flag |
Token ID | 34227 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
interstitial | +1.967 |
ebus | +1.842 |
Cu | +1.696 |
EVA | +1.567 |
�� | +1.553 |
Neg logit contributions | |
Philipp | -4.804 |
HEL | -4.682 |
Soda | -4.674 |
Whe | -4.602 |
TE | -4.595 |
Token | Reply |
Token ID | 14883 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
interstitial | +4.054 |
ebus | +3.902 |
�� | +3.508 |
mare | +3.505 |
Cu | +3.481 |
Neg logit contributions | |
Philipp | -5.037 |
wic | -4.997 |
HEL | -4.950 |
Soda | -4.857 |
TE | -4.802 |
Token |
|
Token ID | 198 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
interstitial | +3.326 |
ebus | +3.315 |
Cu | +3.053 |
mare | +2.913 |
EVA | +2.878 |
Neg logit contributions | |
Philipp | -4.753 |
Soda | -4.660 |
HEL | -4.624 |
wic | -4.513 |
Whe | -4.480 |
Token |
|
Token ID | 198 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
ebus | +4.386 |
Cu | +4.278 |
interstitial | +4.202 |
mare | +3.994 |
EVA | +3.964 |
Neg logit contributions | |
Philipp | -8.109 |
Soda | -8.004 |
HEL | -7.909 |
wic | -7.730 |
CONFIG | -7.695 |
Token | 19 |
Token ID | 1129 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
interstitial | +5.808 |
ebus | +5.563 |
Cu | +5.409 |
EVA | +5.207 |
�� | +5.086 |
Neg logit contributions | |
Philipp | -5.121 |
HEL | -4.920 |
Soda | -4.892 |
Whe | -4.819 |
TE | -4.766 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
interstitial | +4.253 |
ebus | +4.157 |
Cu | +3.910 |
�� | +3.838 |
agara | +3.748 |
Neg logit contributions | |
Philipp | -4.159 |
wic | -4.027 |
HEL | -4.025 |
Soda | -4.009 |
Whe | -3.990 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ebus | +5.117 |
interstitial | +4.835 |
Cu | +4.803 |
mare | +4.516 |
EVA | +4.473 |
Neg logit contributions | |
Philipp | -9.393 |
Soda | -9.231 |
HEL | -9.206 |
wic | -9.173 |
CONFIG | -8.955 |
Token |
|
Token ID | 198 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
interstitial | +2.266 |
ebus | +2.238 |
Cu | +2.087 |
mare | +1.996 |
EVA | +1.987 |
Neg logit contributions | |
Philipp | -2.947 |
Soda | -2.878 |
HEL | -2.869 |
wic | -2.798 |
CONFIG | -2.780 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
interstitial | +3.258 |
ebus | +2.940 |
Cu | +2.849 |
EVA | +2.545 |
�� | +2.472 |
Neg logit contributions | |
Philipp | -8.096 |
Soda | -7.851 |
HEL | -7.785 |
Whe | -7.720 |
TE | -7.698 |
Token | Share |
Token ID | 8734 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
interstitial | +3.354 |
ebus | +3.305 |
�� | +2.818 |
Cu | +2.701 |
mare | +2.515 |
Neg logit contributions | |
wic | -8.641 |
Philipp | -8.607 |
Soda | -8.426 |
HEL | -8.389 |
UCHIJ | -8.331 |
Token | this |
Token ID | 428 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
interstitial | +1.139 |
ebus | +1.103 |
Cu | +1.003 |
�� | +1.003 |
agara | +0.989 |
Neg logit contributions | |
Philipp | -1.136 |
HEL | -1.103 |
Soda | -1.100 |
Whe | -1.083 |
wic | -1.078 |
Token | as |
Token ID | 292 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
interstitial | +3.728 |
ebus | +3.613 |
�� | +3.389 |
Cu | +3.351 |
agara | +3.319 |
Neg logit contributions | |
Philipp | -2.600 |
Soda | -2.516 |
HEL | -2.508 |
Whe | -2.475 |
wic | -2.448 |
Token | Le |
Token ID | 1004 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
interstitial | +1.877 |
ebus | +1.811 |
�� | +1.694 |
Cu | +1.665 |
agara | +1.663 |
Neg logit contributions | |
Philipp | -1.313 |
HEL | -1.271 |
Soda | -1.263 |
Whe | -1.245 |
TE | -1.239 |
Token | Fort |
Token ID | 6401 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
interstitial | +0.094 |
ebus | +0.090 |
�� | +0.084 |
agara | +0.082 |
Cu | +0.082 |
Neg logit contributions | |
Philipp | -0.070 |
HEL | -0.068 |
Soda | -0.067 |
Whe | -0.067 |
TE | -0.066 |
Token | de |
Token ID | 390 |
Feature activation | +3.51e-03 |
Pos logit contributions | |
interstitial | +4.072 |
ebus | +3.936 |
�� | +3.635 |
Cu | +3.608 |
agara | +3.533 |
Neg logit contributions | |
Philipp | -4.595 |
HEL | -4.495 |
Soda | -4.494 |
Whe | -4.425 |
wic | -4.415 |
Token | Br |
Token ID | 1709 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Philipp | +0.019 |
HEL | +0.018 |
Soda | +0.018 |
Whe | +0.018 |
TE | +0.018 |
Neg logit contributions | |
interstitial | -0.034 |
ebus | -0.033 |
�� | -0.031 |
agara | -0.030 |
Cu | -0.030 |
Token | é |
Token ID | 2634 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Philipp | +1.370 |
HEL | +1.329 |
Soda | +1.321 |
wic | +1.320 |
Whe | +1.317 |
Neg logit contributions | |
interstitial | -1.398 |
ebus | -1.329 |
�� | -1.253 |
Cu | -1.197 |
agara | -1.193 |
Token | gan |
Token ID | 1030 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ebus | +8.503 |
interstitial | +8.501 |
mare | +7.902 |
Cu | +7.826 |
agara | +7.666 |
Neg logit contributions | |
Philipp | -6.691 |
HEL | -6.508 |
Soda | -6.467 |
Whe | -6.351 |
Gins | -6.350 |
Token | ç |
Token ID | 16175 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Philipp | +0.831 |
HEL | +0.769 |
Soda | +0.766 |
TE | +0.761 |
Sel | +0.747 |
Neg logit contributions | |
interstitial | -2.118 |
ebus | -2.045 |
�� | -1.944 |
agara | -1.898 |
Cu | -1.890 |
Token | on |
Token ID | 261 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
interstitial | +3.045 |
ebus | +2.941 |
�� | +2.769 |
agara | +2.727 |
Cu | +2.721 |
Neg logit contributions | |
Philipp | -1.844 |
HEL | -1.791 |
Soda | -1.789 |
Whe | -1.753 |
CONFIG | -1.736 |
Token | ser |
Token ID | 1055 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
Philipp | +1.734 |
HEL | +1.666 |
Soda | +1.646 |
TE | +1.644 |
Sel | +1.634 |
Neg logit contributions | |
interstitial | -2.459 |
ebus | -2.352 |
�� | -2.181 |
agara | -2.154 |
Cu | -2.130 |
Token | a |
Token ID | 64 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
interstitial | +0.062 |
ebus | +0.059 |
�� | +0.055 |
agara | +0.054 |
Cu | +0.053 |
Neg logit contributions | |
Philipp | -0.053 |
HEL | -0.051 |
Soda | -0.051 |
TE | -0.050 |
Sel | -0.050 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
interstitial | +1.935 |
ebus | +1.868 |
�� | +1.733 |
Cu | +1.703 |
agara | +1.703 |
Neg logit contributions | |
Philipp | -1.601 |
HEL | -1.553 |
Soda | -1.550 |
Whe | -1.523 |
TE | -1.518 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
interstitial | +7.419 |
ebus | +7.354 |
Cu | +6.787 |
mare | +6.728 |
�� | +6.703 |
Neg logit contributions | |
Philipp | -7.213 |
Soda | -7.141 |
HEL | -6.998 |
wic | -6.959 |
CONFIG | -6.838 |
Token | With |
Token ID | 2080 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
interstitial | +1.283 |
ebus | +1.236 |
�� | +1.154 |
Cu | +1.134 |
agara | +1.132 |
Neg logit contributions | |
Philipp | -0.950 |
HEL | -0.921 |
Soda | -0.915 |
Whe | -0.901 |
TE | -0.898 |
Token | your |
Token ID | 534 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Philipp | +0.308 |
HEL | +0.298 |
Soda | +0.294 |
TE | +0.293 |
Whe | +0.293 |
Neg logit contributions | |
interstitial | -0.398 |
ebus | -0.380 |
�� | -0.353 |
Cu | -0.348 |
agara | -0.347 |
Token | left |
Token ID | 1364 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Philipp | +2.147 |
HEL | +2.089 |
TE | +2.071 |
Whe | +2.061 |
Sel | +2.058 |
Neg logit contributions | |
interstitial | -2.046 |
ebus | -1.919 |
�� | -1.786 |
agara | -1.737 |
Cu | -1.725 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
interstitial | +2.870 |
ebus | +2.792 |
�� | +2.584 |
Cu | +2.541 |
agara | +2.541 |
Neg logit contributions | |
Philipp | -2.393 |
Soda | -2.336 |
HEL | -2.330 |
wic | -2.280 |
Whe | -2.270 |
Token | hold |
Token ID | 1745 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
ebus | +7.292 |
interstitial | +7.263 |
Cu | +6.811 |
agara | +6.670 |
mare | +6.642 |
Neg logit contributions | |
Philipp | -7.629 |
HEL | -7.448 |
Soda | -7.443 |
wic | -7.308 |
CONFIG | -7.219 |
Token | onto |
Token ID | 4291 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
Philipp | +0.040 |
HEL | +0.039 |
Soda | +0.039 |
TE | +0.038 |
Sel | +0.038 |
Neg logit contributions | |
interstitial | -0.051 |
ebus | -0.048 |
�� | -0.045 |
agara | -0.044 |
Cu | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
Philipp | +0.501 |
HEL | +0.486 |
Soda | +0.483 |
TE | +0.479 |
Sel | +0.478 |
Neg logit contributions | |
interstitial | -0.632 |
ebus | -0.606 |
�� | -0.561 |
Cu | -0.549 |
agara | -0.549 |
Token | top |
Token ID | 1353 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Philipp | +0.651 |
HEL | +0.633 |
Soda | +0.630 |
TE | +0.628 |
Whe | +0.625 |
Neg logit contributions | |
interstitial | -0.688 |
ebus | -0.653 |
�� | -0.606 |
agara | -0.590 |
Cu | -0.589 |
Token | thread |
Token ID | 4704 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Philipp | +0.471 |
HEL | +0.457 |
TE | +0.454 |
Whe | +0.451 |
Soda | +0.450 |
Neg logit contributions | |
interstitial | -0.627 |
ebus | -0.596 |
�� | -0.558 |
Cu | -0.542 |
agara | -0.541 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
interstitial | +0.585 |
ebus | +0.562 |
�� | +0.522 |
agara | +0.512 |
Cu | +0.511 |
Neg logit contributions | |
Philipp | -0.484 |
HEL | -0.472 |
Soda | -0.468 |
TE | -0.462 |
Whe | -0.462 |
Token | air |
Token ID | 1633 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Philipp | +0.184 |
HEL | +0.179 |
Soda | +0.178 |
TE | +0.176 |
Whe | +0.176 |
Neg logit contributions | |
interstitial | -0.231 |
ebus | -0.221 |
�� | -0.206 |
agara | -0.202 |
Cu | -0.201 |
Token | is |
Token ID | 318 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
interstitial | +1.911 |
ebus | +1.837 |
�� | +1.710 |
Cu | +1.686 |
agara | +1.681 |
Neg logit contributions | |
Philipp | -1.604 |
HEL | -1.551 |
Soda | -1.549 |
Whe | -1.520 |
TE | -1.511 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
interstitial | +1.380 |
ebus | +1.330 |
�� | +1.236 |
Cu | +1.216 |
agara | +1.213 |
Neg logit contributions | |
Philipp | -1.127 |
HEL | -1.093 |
Soda | -1.086 |
Whe | -1.071 |
TE | -1.067 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
interstitial | +0.151 |
ebus | +0.145 |
�� | +0.133 |
Cu | +0.132 |
agara | +0.131 |
Neg logit contributions | |
Philipp | -0.156 |
HEL | -0.152 |
Soda | -0.151 |
Whe | -0.149 |
TE | -0.148 |
Token | � |
Token ID | 127 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
interstitial | +1.219 |
ebus | +1.173 |
�� | +1.091 |
agara | +1.070 |
Cu | +1.068 |
Neg logit contributions | |
Philipp | -0.993 |
HEL | -0.964 |
Soda | -0.958 |
Whe | -0.945 |
TE | -0.943 |
Token | � |
Token ID | 110 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
interstitial | +6.070 |
ebus | +5.967 |
�� | +5.879 |
�� | +5.315 |
Cu | +5.310 |
Neg logit contributions | |
Philipp | -9.159 |
Soda | -8.987 |
HEL | -8.917 |
CONFIG | -8.807 |
Whe | -8.806 |
Token | t |
Token ID | 256 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
interstitial | +3.700 |
ebus | +3.553 |
�� | +3.347 |
Cu | +3.310 |
agara | +3.262 |
Neg logit contributions | |
Philipp | -2.866 |
HEL | -2.774 |
Soda | -2.750 |
Whe | -2.722 |
wic | -2.701 |
Token | 0 |
Token ID | 15 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
interstitial | +4.067 |
ebus | +3.899 |
�� | +3.681 |
Cu | +3.613 |
agara | +3.578 |
Neg logit contributions | |
Philipp | -3.230 |
HEL | -3.144 |
Soda | -3.121 |
Whe | -3.068 |
TE | -3.047 |
Token | t |
Token ID | 256 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
interstitial | +3.019 |
ebus | +2.902 |
�� | +2.724 |
Cu | +2.680 |
agara | +2.665 |
Neg logit contributions | |
Philipp | -2.364 |
HEL | -2.294 |
Soda | -2.281 |
Whe | -2.250 |
wic | -2.234 |
Token | f |
Token ID | 277 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
interstitial | +4.923 |
ebus | +4.725 |
�� | +4.476 |
Cu | +4.414 |
agara | +4.356 |
Neg logit contributions | |
Philipp | -3.563 |
HEL | -3.462 |
Soda | -3.430 |
Whe | -3.377 |
Sel | -3.346 |
Token | Don |
Token ID | 2094 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Philipp | +1.612 |
Soda | +1.553 |
HEL | +1.548 |
TE | +1.533 |
Sel | +1.532 |
Neg logit contributions | |
interstitial | -1.904 |
ebus | -1.830 |
�� | -1.698 |
agara | -1.663 |
Cu | -1.648 |
Token | Giovanni |
Token ID | 50191 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Philipp | +0.389 |
HEL | +0.373 |
Soda | +0.369 |
Sel | +0.369 |
Whe | +0.369 |
Neg logit contributions | |
interstitial | -0.482 |
ebus | -0.453 |
�� | -0.423 |
EVA | -0.412 |
Cu | -0.410 |
Token | and |
Token ID | 290 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
Philipp | +2.510 |
Soda | +2.429 |
Whe | +2.383 |
HEL | +2.383 |
TE | +2.371 |
Neg logit contributions | |
interstitial | -3.486 |
ebus | -3.362 |
�� | -3.145 |
agara | -3.067 |
Cu | -3.025 |
Token | La |
Token ID | 4689 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Philipp | +0.279 |
Soda | +0.269 |
HEL | +0.269 |
Sel | +0.264 |
Whe | +0.264 |
Neg logit contributions | |
interstitial | -0.351 |
ebus | -0.338 |
�� | -0.314 |
agara | -0.308 |
Cu | -0.307 |
Token | Boh |
Token ID | 44366 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Philipp | +1.867 |
Soda | +1.811 |
HEL | +1.796 |
Sel | +1.786 |
Whe | +1.785 |
Neg logit contributions | |
interstitial | -2.538 |
ebus | -2.402 |
�� | -2.259 |
agara | -2.207 |
EVA | -2.186 |
Token | è |
Token ID | 14064 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
interstitial | +1.068 |
ebus | +1.024 |
�� | +0.929 |
Cu | +0.906 |
agara | +0.903 |
Neg logit contributions | |
Philipp | -1.343 |
HEL | -1.306 |
Soda | -1.306 |
TE | -1.289 |
Whe | -1.287 |
Token | me |
Token ID | 1326 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
interstitial | +6.471 |
Cu | +5.984 |
ebus | +5.888 |
�� | +5.735 |
mare | +5.734 |
Neg logit contributions | |
HEL | -8.279 |
Philipp | -8.229 |
CONFIG | -8.179 |
ographically | -7.951 |
wic | -7.950 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
interstitial | +1.680 |
ebus | +1.618 |
�� | +1.511 |
Cu | +1.486 |
agara | +1.484 |
Neg logit contributions | |
Philipp | -1.242 |
HEL | -1.204 |
Soda | -1.194 |
Whe | -1.178 |
TE | -1.174 |
Token | visits |
Token ID | 11864 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Philipp | +1.144 |
Soda | +1.108 |
HEL | +1.099 |
Sel | +1.087 |
TE | +1.086 |
Neg logit contributions | |
interstitial | -1.446 |
ebus | -1.386 |
�� | -1.297 |
agara | -1.265 |
Cu | -1.254 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
interstitial | +1.037 |
ebus | +0.996 |
�� | +0.924 |
Cu | +0.904 |
agara | +0.903 |
Neg logit contributions | |
Philipp | -0.926 |
HEL | -0.898 |
Soda | -0.894 |
Whe | -0.882 |
TE | -0.879 |
Token | the |
Token ID | 262 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
interstitial | +0.944 |
ebus | +0.910 |
�� | +0.847 |
agara | +0.830 |
Cu | +0.830 |
Neg logit contributions | |
Philipp | -0.746 |
HEL | -0.721 |
Soda | -0.718 |
Whe | -0.708 |
Sel | -0.706 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Philipp | +0.467 |
HEL | +0.454 |
Whe | +0.448 |
Soda | +0.448 |
TE | +0.446 |
Neg logit contributions | |
interstitial | -0.576 |
ebus | -0.554 |
�� | -0.514 |
Cu | -0.506 |
agara | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
interstitial | +2.107 |
ebus | +2.079 |
Cu | +1.913 |
agara | +1.831 |
EVA | +1.829 |
Neg logit contributions | |
Philipp | -2.598 |
HEL | -2.544 |
Soda | -2.539 |
CONFIG | -2.462 |
wic | -2.456 |
Token | Sh |
Token ID | 2484 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
interstitial | +1.077 |
ebus | +1.038 |
�� | +0.969 |
Cu | +0.953 |
agara | +0.951 |
Neg logit contributions | |
Philipp | -0.782 |
HEL | -0.757 |
Soda | -0.754 |
Whe | -0.741 |
TE | -0.739 |
Token | ared |
Token ID | 1144 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
interstitial | +1.727 |
ebus | +1.652 |
�� | +1.524 |
Cu | +1.491 |
agara | +1.487 |
Neg logit contributions | |
Philipp | -1.790 |
HEL | -1.744 |
Soda | -1.733 |
Whe | -1.713 |
TE | -1.711 |
Token | < |
Token ID | 27 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
interstitial | +1.814 |
ebus | +1.729 |
�� | +1.575 |
Cu | +1.537 |
agara | +1.536 |
Neg logit contributions | |
Philipp | -2.333 |
HEL | -2.277 |
Soda | -2.268 |
Whe | -2.241 |
TE | -2.235 |
Token | ' |
Token ID | 6 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
interstitial | +0.336 |
ebus | +0.323 |
�� | +0.298 |
agara | +0.292 |
Cu | +0.291 |
Neg logit contributions | |
Philipp | -0.326 |
HEL | -0.318 |
Soda | -0.315 |
TE | -0.312 |
Whe | -0.312 |
Token | a |
Token ID | 64 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
interstitial | +6.297 |
ebus | +5.960 |
Cu | +5.470 |
agara | +5.453 |
�� | +5.335 |
Neg logit contributions | |
Philipp | -9.191 |
Soda | -8.844 |
HEL | -8.834 |
Whe | -8.750 |
Sel | -8.649 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
interstitial | +2.479 |
ebus | +2.388 |
�� | +2.207 |
Cu | +2.170 |
agara | +2.164 |
Neg logit contributions | |
Philipp | -2.326 |
HEL | -2.259 |
Soda | -2.250 |
Whe | -2.211 |
wic | -2.202 |
Token | T |
Token ID | 309 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
interstitial | +0.189 |
ebus | +0.182 |
�� | +0.170 |
agara | +0.167 |
Cu | +0.167 |
Neg logit contributions | |
Philipp | -0.135 |
HEL | -0.131 |
Soda | -0.129 |
TE | -0.128 |
Whe | -0.128 |
Token | > |
Token ID | 29 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
interstitial | +2.008 |
ebus | +1.927 |
�� | +1.774 |
agara | +1.736 |
Cu | +1.734 |
Neg logit contributions | |
Philipp | -2.178 |
HEL | -2.119 |
Soda | -2.113 |
Whe | -2.083 |
TE | -2.074 |
Token | , |
Token ID | 837 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Philipp | +0.883 |
HEL | +0.855 |
Whe | +0.846 |
Soda | +0.840 |
TE | +0.837 |
Neg logit contributions | |
interstitial | -1.246 |
ebus | -1.201 |
�� | -1.116 |
Cu | -1.102 |
agara | -1.099 |
Token | Are |
Token ID | 4231 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
interstitial | +2.262 |
ebus | +2.175 |
�� | +2.014 |
agara | +1.993 |
Cu | +1.985 |
Neg logit contributions | |
Philipp | -2.088 |
HEL | -2.039 |
Soda | -2.026 |
Whe | -1.994 |
wic | -1.987 |
Token | More |
Token ID | 3125 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
interstitial | +1.847 |
ebus | +1.781 |
�� | +1.663 |
Cu | +1.644 |
agara | +1.638 |
Neg logit contributions | |
Philipp | -1.299 |
HEL | -1.258 |
Soda | -1.244 |
Whe | -1.225 |
TE | -1.224 |
Token | Similar |
Token ID | 11014 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
interstitial | +0.189 |
ebus | +0.183 |
�� | +0.171 |
agara | +0.168 |
Cu | +0.168 |
Neg logit contributions | |
Philipp | -0.130 |
HEL | -0.125 |
Soda | -0.125 |
Whe | -0.123 |
TE | -0.122 |
Token | Than |
Token ID | 17924 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Philipp | +0.990 |
HEL | +0.945 |
Soda | +0.945 |
Sel | +0.937 |
Whe | +0.935 |
Neg logit contributions | |
interstitial | -1.366 |
ebus | -1.294 |
�� | -1.206 |
Cu | -1.197 |
agara | -1.185 |
Token | You |
Token ID | 921 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
interstitial | +1.703 |
ebus | +1.644 |
�� | +1.533 |
Cu | +1.510 |
agara | +1.510 |
Neg logit contributions | |
Philipp | -1.202 |
HEL | -1.166 |
Soda | -1.152 |
Whe | -1.137 |
TE | -1.134 |
Token | Think |
Token ID | 11382 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
interstitial | +3.147 |
ebus | +3.058 |
�� | +2.831 |
Cu | +2.816 |
agara | +2.797 |
Neg logit contributions | |
Philipp | -2.087 |
HEL | -2.045 |
Soda | -1.991 |
wic | -1.991 |
Whe | -1.967 |
Token |
|
Token ID | 198 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
interstitial | +7.547 |
ebus | +7.349 |
Cu | +6.829 |
�� | +6.795 |
agara | +6.631 |
Neg logit contributions | |
Philipp | -7.031 |
HEL | -6.975 |
wic | -6.886 |
CONFIG | -6.766 |
Soda | -6.754 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
interstitial | +0.523 |
ebus | +0.501 |
�� | +0.463 |
Cu | +0.454 |
agara | +0.453 |
Neg logit contributions | |
Philipp | -0.509 |
HEL | -0.495 |
Soda | -0.492 |
Whe | -0.486 |
TE | -0.485 |
Token | The |
Token ID | 464 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Philipp | +0.270 |
HEL | +0.264 |
Soda | +0.262 |
Whe | +0.260 |
TE | +0.259 |
Neg logit contributions | |
interstitial | -0.289 |
ebus | -0.279 |
�� | -0.259 |
agara | -0.254 |
Cu | -0.245 |
Token | biggest |
Token ID | 4094 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Philipp | +1.394 |
Soda | +1.347 |
HEL | +1.343 |
Sel | +1.328 |
Whe | +1.328 |
Neg logit contributions | |
interstitial | -1.854 |
ebus | -1.765 |
�� | -1.656 |
agara | -1.634 |
Cu | -1.623 |
Token | difference |
Token ID | 3580 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
Philipp | +1.060 |
Soda | +1.026 |
HEL | +1.025 |
Whe | +1.015 |
TE | +1.014 |
Neg logit contributions | |
interstitial | -1.369 |
ebus | -1.317 |
�� | -1.235 |
agara | -1.206 |
Cu | -1.199 |
Token | for |
Token ID | 329 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
interstitial | +0.700 |
ebus | +0.676 |
�� | +0.633 |
Cu | +0.623 |
agara | +0.622 |
Neg logit contributions | |
Philipp | -0.457 |
HEL | -0.441 |
Soda | -0.438 |
Whe | -0.432 |
TE | -0.430 |
Token | ($ |
Token ID | 7198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
interstitial | +1.982 |
ebus | +1.904 |
�� | +1.783 |
Cu | +1.755 |
agara | +1.744 |
Neg logit contributions | |
Philipp | -1.413 |
HEL | -1.364 |
Soda | -1.357 |
Whe | -1.334 |
wic | -1.326 |
Token | i |
Token ID | 72 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
interstitial | +2.646 |
ebus | +2.486 |
�� | +2.288 |
Cu | +2.263 |
agara | +2.238 |
Neg logit contributions | |
Philipp | -3.072 |
HEL | -3.011 |
Soda | -2.985 |
Whe | -2.954 |
TE | -2.940 |
Token | ; |
Token ID | 2162 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
interstitial | +8.497 |
ebus | +8.041 |
�� | +7.432 |
Cu | +7.389 |
agara | +7.360 |
Neg logit contributions | |
Philipp | -10.520 |
Soda | -10.338 |
HEL | -10.330 |
Whe | -10.279 |
wic | -10.221 |
Token | $ |
Token ID | 720 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
interstitial | +1.756 |
ebus | +1.677 |
�� | +1.552 |
Cu | +1.524 |
agara | +1.513 |
Neg logit contributions | |
Philipp | -1.740 |
HEL | -1.693 |
Soda | -1.686 |
Whe | -1.663 |
Sel | -1.657 |
Token | i |
Token ID | 72 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
interstitial | +1.812 |
ebus | +1.711 |
�� | +1.561 |
Cu | +1.530 |
agara | +1.527 |
Neg logit contributions | |
Philipp | -2.179 |
HEL | -2.129 |
Soda | -2.118 |
Whe | -2.093 |
TE | -2.088 |
Token | - |
Token ID | 532 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
interstitial | +7.559 |
ebus | +7.171 |
Cu | +6.660 |
agara | +6.551 |
�� | +6.528 |
Neg logit contributions | |
Philipp | -7.314 |
wic | -7.067 |
HEL | -7.012 |
Soda | -6.998 |
Whe | -6.960 |
Token | le |
Token ID | 293 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Philipp | +0.646 |
HEL | +0.624 |
Soda | +0.617 |
Sel | +0.611 |
Whe | +0.610 |
Neg logit contributions | |
interstitial | -0.927 |
ebus | -0.900 |
�� | -0.841 |
agara | -0.826 |
Cu | -0.820 |
Token | $ |
Token ID | 720 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Philipp | +0.757 |
HEL | +0.731 |
Soda | +0.726 |
TE | +0.719 |
Whe | +0.718 |
Neg logit contributions | |
interstitial | -0.931 |
ebus | -0.894 |
�� | -0.829 |
agara | -0.811 |
Cu | -0.810 |
Token | art |
Token ID | 433 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Philipp | +1.390 |
HEL | +1.356 |
wic | +1.348 |
Soda | +1.347 |
TE | +1.334 |
Neg logit contributions | |
interstitial | -1.443 |
ebus | -1.408 |
�� | -1.303 |
agara | -1.273 |
Cu | -1.262 |
Token | ext |
Token ID | 2302 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
interstitial | +1.863 |
ebus | +1.803 |
�� | +1.661 |
Cu | +1.655 |
agara | +1.648 |
Neg logit contributions | |
Philipp | -1.442 |
HEL | -1.396 |
Soda | -1.383 |
Whe | -1.362 |
Sel | -1.344 |
Token | from |
Token ID | 422 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Philipp | +0.467 |
HEL | +0.452 |
Soda | +0.448 |
Whe | +0.445 |
TE | +0.444 |
Neg logit contributions | |
interstitial | -0.667 |
ebus | -0.642 |
�� | -0.602 |
agara | -0.587 |
Cu | -0.586 |
Token | you |
Token ID | 345 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Philipp | +1.899 |
HEL | +1.845 |
Sel | +1.829 |
TE | +1.828 |
Soda | +1.822 |
Neg logit contributions | |
interstitial | -2.556 |
ebus | -2.442 |
�� | -2.279 |
Cu | -2.219 |
agara | -2.209 |
Token | with |
Token ID | 351 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Philipp | +0.929 |
HEL | +0.903 |
TE | +0.893 |
Whe | +0.887 |
Soda | +0.886 |
Neg logit contributions | |
interstitial | -1.308 |
ebus | -1.261 |
�� | -1.181 |
Cu | -1.154 |
agara | -1.154 |
Token | your |
Token ID | 534 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
interstitial | +0.186 |
ebus | +0.178 |
�� | +0.165 |
Cu | +0.162 |
agara | +0.162 |
Neg logit contributions | |
Philipp | -0.151 |
HEL | -0.147 |
Soda | -0.145 |
TE | -0.144 |
Whe | -0.144 |
Token | right |
Token ID | 826 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
interstitial | +1.663 |
ebus | +1.609 |
�� | +1.476 |
Cu | +1.451 |
agara | +1.450 |
Neg logit contributions | |
Philipp | -1.667 |
HEL | -1.619 |
Soda | -1.616 |
wic | -1.596 |
Whe | -1.592 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
interstitial | +1.935 |
ebus | +1.868 |
�� | +1.733 |
Cu | +1.703 |
agara | +1.703 |
Neg logit contributions | |
Philipp | -1.601 |
HEL | -1.553 |
Soda | -1.550 |
Whe | -1.523 |
TE | -1.518 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
interstitial | +7.419 |
ebus | +7.354 |
Cu | +6.787 |
mare | +6.728 |
�� | +6.703 |
Neg logit contributions | |
Philipp | -7.213 |
Soda | -7.141 |
HEL | -6.998 |
wic | -6.959 |
CONFIG | -6.838 |
Token | With |
Token ID | 2080 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
interstitial | +1.283 |
ebus | +1.236 |
�� | +1.154 |
Cu | +1.134 |
agara | +1.132 |
Neg logit contributions | |
Philipp | -0.950 |
HEL | -0.921 |
Soda | -0.915 |
Whe | -0.901 |
TE | -0.898 |
Token | your |
Token ID | 534 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Philipp | +0.308 |
HEL | +0.298 |
Soda | +0.294 |
TE | +0.293 |
Whe | +0.293 |
Neg logit contributions | |
interstitial | -0.398 |
ebus | -0.380 |
�� | -0.353 |
Cu | -0.348 |
agara | -0.347 |
Token | left |
Token ID | 1364 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Philipp | +2.147 |
HEL | +2.089 |
TE | +2.071 |
Whe | +2.061 |
Sel | +2.058 |
Neg logit contributions | |
interstitial | -2.046 |
ebus | -1.919 |
�� | -1.786 |
agara | -1.737 |
Cu | -1.725 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
interstitial | +2.870 |
ebus | +2.792 |
�� | +2.584 |
Cu | +2.541 |
agara | +2.541 |
Neg logit contributions | |
Philipp | -2.393 |
Soda | -2.336 |
HEL | -2.330 |
wic | -2.280 |
Whe | -2.270 |
Token | capacity |
Token ID | 5339 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
Philipp | +0.273 |
HEL | +0.264 |
Soda | +0.264 |
Whe | +0.260 |
TE | +0.259 |
Neg logit contributions | |
interstitial | -0.391 |
ebus | -0.377 |
�� | -0.353 |
Cu | -0.346 |
agara | -0.346 |
Token | from |
Token ID | 422 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
interstitial | +0.207 |
ebus | +0.199 |
�� | +0.186 |
agara | +0.182 |
Cu | +0.181 |
Neg logit contributions | |
Philipp | -0.158 |
HEL | -0.152 |
Soda | -0.151 |
Whe | -0.150 |
TE | -0.150 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
interstitial | +0.090 |
ebus | +0.087 |
�� | +0.081 |
agara | +0.080 |
Cu | +0.080 |
Neg logit contributions | |
Philipp | -0.065 |
HEL | -0.063 |
Soda | -0.063 |
Whe | -0.062 |
TE | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
interstitial | +2.192 |
ebus | +2.114 |
�� | +1.977 |
Cu | +1.942 |
agara | +1.942 |
Neg logit contributions | |
Philipp | -1.516 |
HEL | -1.466 |
Soda | -1.456 |
Whe | -1.435 |
TE | -1.430 |
Token | 700 |
Token ID | 9879 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
interstitial | +1.601 |
ebus | +1.547 |
�� | +1.442 |
Cu | +1.426 |
agara | +1.417 |
Neg logit contributions | |
Philipp | -1.125 |
HEL | -1.089 |
Soda | -1.079 |
Whe | -1.063 |
TE | -1.057 |
Token | seats |
Token ID | 8632 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
interstitial | +2.711 |
ebus | +2.599 |
�� | +2.401 |
Cu | +2.361 |
agara | +2.351 |
Neg logit contributions | |
Philipp | -2.597 |
HEL | -2.529 |
Soda | -2.511 |
Whe | -2.482 |
Sel | -2.471 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
interstitial | +6.965 |
ebus | +6.804 |
�� | +6.221 |
Cu | +6.138 |
agara | +6.119 |
Neg logit contributions | |
Philipp | -7.673 |
HEL | -7.514 |
Soda | -7.487 |
Whe | -7.374 |
CONFIG | -7.349 |
Token | 2 |
Token ID | 362 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
interstitial | +0.886 |
ebus | +0.854 |
�� | +0.797 |
Cu | +0.782 |
agara | +0.782 |
Neg logit contributions | |
Philipp | -0.648 |
HEL | -0.628 |
Soda | -0.624 |
Whe | -0.615 |
TE | -0.613 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Philipp | +0.355 |
HEL | +0.343 |
Soda | +0.340 |
Whe | +0.336 |
TE | +0.335 |
Neg logit contributions | |
interstitial | -0.535 |
ebus | -0.515 |
�� | -0.483 |
agara | -0.474 |
Cu | -0.472 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Philipp | +1.784 |
HEL | +1.712 |
Soda | +1.708 |
TE | +1.687 |
Whe | +1.685 |
Neg logit contributions | |
interstitial | -2.838 |
ebus | -2.719 |
�� | -2.568 |
agara | -2.521 |
Cu | -2.488 |
Token | seats |
Token ID | 8632 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Philipp | +1.029 |
HEL | +0.984 |
Soda | +0.981 |
TE | +0.976 |
Whe | +0.971 |
Neg logit contributions | |
interstitial | -1.538 |
ebus | -1.480 |
�� | -1.388 |
agara | -1.363 |
Cu | -1.353 |
Token | 90 |
Token ID | 4101 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Philipp | +0.206 |
HEL | +0.199 |
Soda | +0.197 |
Whe | +0.193 |
TE | +0.193 |
Neg logit contributions | |
interstitial | -0.356 |
ebus | -0.345 |
�� | -0.324 |
Cu | -0.319 |
agara | -0.318 |
Token | F |
Token ID | 376 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
interstitial | +4.392 |
ebus | +4.310 |
EVA | +3.868 |
�� | +3.867 |
mare | +3.849 |
Neg logit contributions | |
Philipp | -4.836 |
Soda | -4.754 |
HEL | -4.707 |
wic | -4.693 |
Whe | -4.601 |
Token | OV |
Token ID | 8874 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ebus | +2.035 |
interstitial | +2.035 |
EVA | +1.859 |
Cu | +1.841 |
�� | +1.790 |
Neg logit contributions | |
Philipp | -3.322 |
Soda | -3.240 |
HEL | -3.229 |
Sel | -3.159 |
Whe | -3.154 |
Token | even |
Token ID | 772 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
interstitial | +2.834 |
ebus | +2.707 |
�� | +2.402 |
EVA | +2.331 |
agara | +2.300 |
Neg logit contributions | |
Philipp | -6.160 |
wic | -6.101 |
HEL | -6.029 |
Soda | -5.999 |
Whe | -5.940 |
Token | double |
Token ID | 4274 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
interstitial | +4.099 |
ebus | +4.056 |
�� | +3.666 |
Cu | +3.638 |
mare | +3.603 |
Neg logit contributions | |
Philipp | -3.989 |
HEL | -3.911 |
wic | -3.870 |
Soda | -3.802 |
Whe | -3.774 |
Token | or |
Token ID | 393 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
interstitial | +2.113 |
ebus | +2.051 |
�� | +1.907 |
Cu | +1.888 |
agara | +1.886 |
Neg logit contributions | |
Philipp | -1.536 |
HEL | -1.484 |
Soda | -1.477 |
wic | -1.449 |
Whe | -1.441 |
Token | 4 |
Token ID | 604 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
interstitial | +5.838 |
ebus | +5.831 |
�� | +5.314 |
EVA | +5.205 |
mare | +5.199 |
Neg logit contributions | |
Philipp | -8.541 |
HEL | -8.500 |
wic | -8.225 |
Soda | -8.019 |
Sel | -7.919 |
Token | x |
Token ID | 87 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
interstitial | +0.623 |
ebus | +0.603 |
Cu | +0.562 |
�� | +0.559 |
agara | +0.554 |
Neg logit contributions | |
Philipp | -0.438 |
HEL | -0.422 |
Soda | -0.418 |
Whe | -0.410 |
TE | -0.407 |
Token | 1080 |
Token ID | 17729 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
interstitial | +4.059 |
ebus | +4.036 |
�� | +3.749 |
Cu | +3.685 |
EVA | +3.679 |
Neg logit contributions | |
Philipp | -3.673 |
Soda | -3.501 |
HEL | -3.490 |
wic | -3.395 |
Sel | -3.365 |
Token | P |
Token ID | 47 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
interstitial | +2.023 |
ebus | +1.958 |
Cu | +1.789 |
EVA | +1.723 |
�� | +1.701 |
Neg logit contributions | |
Philipp | -3.667 |
Soda | -3.575 |
HEL | -3.556 |
Whe | -3.500 |
wic | -3.497 |
Token | resolution |
Token ID | 6323 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
interstitial | +2.394 |
ebus | +2.334 |
�� | +2.155 |
agara | +2.120 |
Cu | +2.119 |
Neg logit contributions | |
Philipp | -2.191 |
HEL | -2.127 |
Soda | -2.105 |
wic | -2.099 |
Whe | -2.058 |
Token | now |
Token ID | 783 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Philipp | +0.015 |
HEL | +0.015 |
Soda | +0.015 |
Whe | +0.015 |
wic | +0.015 |
Neg logit contributions | |
interstitial | -0.017 |
ebus | -0.017 |
�� | -0.016 |
Cu | -0.015 |
agara | -0.015 |
Token | receives |
Token ID | 11583 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Philipp | +1.878 |
HEL | +1.801 |
Soda | +1.773 |
TE | +1.767 |
Whe | +1.750 |
Neg logit contributions | |
interstitial | -3.569 |
ebus | -3.425 |
�� | -3.252 |
Cu | -3.183 |
agara | -3.143 |
Token | secret |
Token ID | 3200 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Philipp | +2.237 |
HEL | +2.168 |
Sel | +2.167 |
TE | +2.160 |
Soda | +2.121 |
Neg logit contributions | |
interstitial | -3.034 |
ebus | -2.901 |
�� | -2.777 |
agara | -2.640 |
Cu | -2.638 |
Token | voices |
Token ID | 10839 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Philipp | +0.763 |
HEL | +0.740 |
Soda | +0.733 |
Whe | +0.724 |
TE | +0.723 |
Neg logit contributions | |
interstitial | -1.070 |
ebus | -1.031 |
�� | -0.965 |
Cu | -0.945 |
agara | -0.944 |
Token | in |
Token ID | 287 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Philipp | +2.738 |
HEL | +2.663 |
TE | +2.649 |
Sel | +2.632 |
Soda | +2.625 |
Neg logit contributions | |
interstitial | -3.520 |
ebus | -3.361 |
�� | -3.224 |
agara | -3.071 |
�� | -3.045 |
Token | his |
Token ID | 465 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Philipp | +2.199 |
HEL | +2.137 |
Soda | +2.118 |
Sel | +2.106 |
Whe | +2.104 |
Neg logit contributions | |
interstitial | -2.435 |
ebus | -2.339 |
�� | -2.179 |
agara | -2.129 |
Cu | -2.111 |
Token | or |
Token ID | 393 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Philipp | +3.716 |
HEL | +3.530 |
Sel | +3.510 |
TE | +3.504 |
Whe | +3.450 |
Neg logit contributions | |
interstitial | -8.666 |
ebus | -8.249 |
�� | -8.090 |
�� | -7.825 |
avorite | -7.787 |
Token | her |
Token ID | 607 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
interstitial | +2.411 |
ebus | +2.351 |
Cu | +2.173 |
agara | +2.173 |
�� | +2.162 |
Neg logit contributions | |
Philipp | -1.756 |
HEL | -1.722 |
Soda | -1.711 |
wic | -1.690 |
CONFIG | -1.687 |
Token | head |
Token ID | 1182 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Philipp | +2.063 |
HEL | +2.010 |
Soda | +1.995 |
Whe | +1.976 |
TE | +1.973 |
Neg logit contributions | |
interstitial | -1.937 |
ebus | -1.850 |
�� | -1.710 |
Cu | -1.664 |
agara | -1.664 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Philipp | +0.228 |
HEL | +0.221 |
Soda | +0.220 |
Whe | +0.215 |
TE | +0.214 |
Neg logit contributions | |
interstitial | -0.309 |
ebus | -0.301 |
�� | -0.278 |
Cu | -0.277 |
agara | -0.274 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Philipp | +1.802 |
HEL | +1.735 |
Soda | +1.712 |
TE | +1.712 |
Sel | +1.711 |
Neg logit contributions | |
interstitial | -2.995 |
ebus | -2.871 |
�� | -2.720 |
agara | -2.652 |
Cu | -2.623 |
Token | there |
Token ID | 612 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Philipp | +3.697 |
Whe | +3.650 |
Sel | +3.634 |
HEL | +3.631 |
Soda | +3.628 |
Neg logit contributions | |
interstitial | -4.838 |
ebus | -4.767 |
�� | -4.411 |
Cu | -4.254 |
agara | -4.207 |
Token | than |
Token ID | 621 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
Philipp | +1.930 |
Soda | +1.859 |
HEL | +1.858 |
TE | +1.852 |
Whe | +1.848 |
Neg logit contributions | |
interstitial | -2.854 |
ebus | -2.716 |
�� | -2.577 |
Cu | -2.511 |
agara | -2.484 |
Token | most |
Token ID | 749 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
interstitial | +0.631 |
ebus | +0.608 |
�� | +0.565 |
agara | +0.554 |
Cu | +0.554 |
Neg logit contributions | |
Philipp | -0.519 |
HEL | -0.504 |
Soda | -0.501 |
Whe | -0.494 |
TE | -0.493 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
interstitial | +1.739 |
ebus | +1.672 |
�� | +1.557 |
Cu | +1.532 |
agara | +1.529 |
Neg logit contributions | |
Philipp | -1.347 |
HEL | -1.303 |
Soda | -1.295 |
Whe | -1.275 |
TE | -1.269 |
Token | - |
Token ID | 532 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Philipp | +2.612 |
Soda | +2.526 |
HEL | +2.524 |
Whe | +2.520 |
Sel | +2.488 |
Neg logit contributions | |
interstitial | -3.857 |
ebus | -3.693 |
�� | -3.475 |
agara | -3.426 |
Cu | -3.321 |
Token | July |
Token ID | 2901 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
HEL | +4.851 |
Philipp | +4.791 |
Whe | +4.582 |
TE | +4.369 |
Gins | +4.245 |
Neg logit contributions | |
interstitial | -10.756 |
ebus | -10.143 |
�� | -10.058 |
agara | -9.855 |
�� | -9.677 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Philipp | +3.858 |
TE | +3.641 |
HEL | +3.639 |
Sel | +3.597 |
Whe | +3.576 |
Neg logit contributions | |
interstitial | -9.009 |
ebus | -8.428 |
�� | -8.286 |
avorite | -8.066 |
�� | -8.049 |
Token | , |
Token ID | 11 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Philipp | +3.177 |
TE | +3.105 |
HEL | +3.095 |
Whe | +3.077 |
Sel | +3.056 |
Neg logit contributions | |
interstitial | -6.464 |
ebus | -6.041 |
�� | -5.922 |
avorite | -5.765 |
agara | -5.712 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Philipp | +4.964 |
HEL | +4.859 |
Whe | +4.822 |
TE | +4.793 |
Sel | +4.722 |
Neg logit contributions | |
interstitial | -6.730 |
ebus | -6.077 |
�� | -6.050 |
avorite | -5.942 |
agara | -5.835 |
Token | R |
Token ID | 49 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
TE | +4.839 |
Philipp | +4.811 |
HEL | +4.771 |
Whe | +4.761 |
CONFIG | +4.725 |
Neg logit contributions | |
interstitial | -3.861 |
ebus | -3.784 |
�� | -3.551 |
agara | -3.488 |
avorite | -3.304 |
Token | iff |
Token ID | 733 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
interstitial | +1.968 |
ebus | +1.919 |
agara | +1.709 |
Cu | +1.706 |
�� | +1.700 |
Neg logit contributions | |
Philipp | -1.967 |
HEL | -1.928 |
Soda | -1.912 |
Sel | -1.874 |
Whe | -1.868 |
Token | Miss |
Token ID | 4544 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
interstitial | +3.427 |
ebus | +3.383 |
Cu | +3.035 |
agara | +3.019 |
�� | +3.011 |
Neg logit contributions | |
Philipp | -3.949 |
HEL | -3.889 |
CONFIG | -3.819 |
Soda | -3.801 |
wic | -3.786 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
interstitial | +2.723 |
ebus | +2.639 |
�� | +2.454 |
Cu | +2.414 |
agara | +2.410 |
Neg logit contributions | |
Philipp | -2.099 |
HEL | -2.033 |
Soda | -2.016 |
Whe | -1.979 |
wic | -1.978 |
Token |
|
Token ID | 198 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
interstitial | +1.989 |
ebus | +1.917 |
�� | +1.782 |
Cu | +1.773 |
agara | +1.737 |
Neg logit contributions | |
Philipp | -1.732 |
HEL | -1.688 |
Soda | -1.674 |
wic | -1.652 |
CONFIG | -1.644 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
interstitial | +0.656 |
ebus | +0.635 |
Cu | +0.580 |
�� | +0.577 |
agara | +0.569 |
Neg logit contributions | |
Philipp | -0.706 |
HEL | -0.687 |
Soda | -0.686 |
Whe | -0.671 |
TE | -0.668 |
Token | This |
Token ID | 1212 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
interstitial | +1.466 |
ebus | +1.404 |
�� | +1.296 |
Cu | +1.273 |
agara | +1.268 |
Neg logit contributions | |
Philipp | -1.449 |
HEL | -1.409 |
Soda | -1.402 |
Whe | -1.384 |
TE | -1.380 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Philipp | +1.269 |
HEL | +1.233 |
Soda | +1.218 |
TE | +1.211 |
Whe | +1.206 |
Neg logit contributions | |
interstitial | -1.635 |
ebus | -1.576 |
�� | -1.477 |
agara | -1.444 |
Cu | -1.438 |
Token | requires |
Token ID | 4433 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Philipp | +4.513 |
HEL | +4.466 |
TE | +4.446 |
CONFIG | +4.395 |
Sel | +4.325 |
Neg logit contributions | |
interstitial | -7.392 |
ebus | -6.921 |
�� | -6.591 |
Cu | -6.362 |
agara | -6.339 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
interstitial | +1.869 |
ebus | +1.811 |
�� | +1.629 |
Cu | +1.620 |
agara | +1.608 |
Neg logit contributions | |
Philipp | -2.287 |
HEL | -2.224 |
Soda | -2.205 |
wic | -2.197 |
Whe | -2.184 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
interstitial | +0.486 |
ebus | +0.471 |
Cu | +0.434 |
�� | +0.433 |
agara | +0.428 |
Neg logit contributions | |
Philipp | -0.408 |
HEL | -0.395 |
Soda | -0.395 |
wic | -0.385 |
Whe | -0.385 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
interstitial | +2.468 |
ebus | +2.382 |
�� | +2.203 |
Cu | +2.162 |
agara | +2.137 |
Neg logit contributions | |
Philipp | -2.609 |
Soda | -2.530 |
HEL | -2.525 |
wic | -2.501 |
Whe | -2.477 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
interstitial | +2.196 |
ebus | +2.165 |
Cu | +2.014 |
mare | +1.921 |
EVA | +1.914 |
Neg logit contributions | |
Philipp | -2.804 |
Soda | -2.731 |
HEL | -2.729 |
CONFIG | -2.648 |
wic | -2.646 |
Token | brutal |
Token ID | 12399 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Philipp | +2.056 |
Soda | +1.980 |
Sel | +1.971 |
HEL | +1.963 |
TE | +1.956 |
Neg logit contributions | |
interstitial | -2.580 |
ebus | -2.459 |
�� | -2.301 |
Cu | -2.249 |
agara | -2.242 |
Token | frontier |
Token ID | 27580 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Philipp | +0.918 |
Soda | +0.881 |
Sel | +0.873 |
HEL | +0.871 |
TE | +0.867 |
Neg logit contributions | |
interstitial | -1.219 |
ebus | -1.166 |
�� | -1.084 |
agara | -1.073 |
Cu | -1.072 |
Token | setting |
Token ID | 4634 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
Philipp | +1.525 |
Soda | +1.459 |
HEL | +1.457 |
Sel | +1.452 |
TE | +1.448 |
Neg logit contributions | |
interstitial | -1.950 |
ebus | -1.867 |
�� | -1.732 |
agara | -1.715 |
Cu | -1.707 |
Token | and |
Token ID | 290 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Philipp | +3.479 |
HEL | +3.370 |
Whe | +3.331 |
TE | +3.328 |
Soda | +3.326 |
Neg logit contributions | |
interstitial | -4.907 |
ebus | -4.660 |
�� | -4.356 |
agara | -4.301 |
Cu | -4.267 |
Token | Bill |
Token ID | 3941 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Philipp | +0.296 |
Soda | +0.286 |
HEL | +0.285 |
Sel | +0.281 |
TE | +0.281 |
Neg logit contributions | |
interstitial | -0.358 |
ebus | -0.344 |
�� | -0.320 |
Cu | -0.314 |
agara | -0.314 |
Token | Elm |
Token ID | 35189 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Philipp | +0.744 |
HEL | +0.719 |
Sel | +0.717 |
Soda | +0.714 |
Whe | +0.712 |
Neg logit contributions | |
interstitial | -1.080 |
ebus | -1.041 |
�� | -0.980 |
agara | -0.958 |
Cu | -0.955 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Philipp | +4.809 |
Sel | +4.689 |
Whe | +4.669 |
HEL | +4.625 |
Soda | +4.611 |
Neg logit contributions | |
interstitial | -6.361 |
ebus | -6.181 |
�� | -5.736 |
agara | -5.695 |
Cu | -5.548 |
Token | Woody |
Token ID | 37684 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
interstitial | +1.744 |
ebus | +1.690 |
�� | +1.589 |
agara | +1.563 |
Cu | +1.563 |
Neg logit contributions | |
Philipp | -0.938 |
HEL | -0.904 |
Soda | -0.894 |
Whe | -0.878 |
TE | -0.875 |
Token | Jackson |
Token ID | 6612 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Philipp | +3.456 |
Sel | +3.310 |
HEL | +3.296 |
Soda | +3.295 |
Lin | +3.234 |
Neg logit contributions | |
interstitial | -5.745 |
ebus | -5.522 |
�� | -5.259 |
agara | -5.177 |
Cu | -5.102 |
Token | � |
Token ID | 447 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Philipp | +2.334 |
HEL | +2.274 |
Soda | +2.265 |
Whe | +2.251 |
Sel | +2.244 |
Neg logit contributions | |
interstitial | -2.779 |
ebus | -2.704 |
�� | -2.511 |
agara | -2.461 |
Cu | -2.419 |
Token | � |
Token ID | 247 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Philipp | +1.110 |
HEL | +1.091 |
Soda | +1.077 |
Sel | +1.066 |
TE | +1.066 |
Neg logit contributions | |
interstitial | -1.141 |
ebus | -1.098 |
agara | -0.992 |
Cu | -0.991 |
�� | -0.991 |
Token | " |
Token ID | 1 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Philipp | +1.507 |
HEL | +1.440 |
Soda | +1.430 |
Sel | +1.414 |
Whe | +1.411 |
Neg logit contributions | |
interstitial | -2.421 |
ebus | -2.327 |
�� | -2.168 |
Cu | -2.157 |
agara | -2.140 |
Token | and |
Token ID | 290 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
interstitial | +1.036 |
ebus | +1.001 |
�� | +0.937 |
Cu | +0.921 |
agara | +0.920 |
Neg logit contributions | |
Philipp | -0.684 |
HEL | -0.662 |
Soda | -0.658 |
Whe | -0.647 |
TE | -0.645 |
Token | " |
Token ID | 366 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
interstitial | +1.424 |
ebus | +1.369 |
�� | +1.272 |
Cu | +1.248 |
agara | +1.247 |
Neg logit contributions | |
Philipp | -1.196 |
HEL | -1.162 |
Soda | -1.155 |
Whe | -1.139 |
TE | -1.136 |
Token | to |
Token ID | 1462 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
Philipp | +0.434 |
HEL | +0.419 |
Soda | +0.413 |
Sel | +0.411 |
TE | +0.411 |
Neg logit contributions | |
interstitial | -0.662 |
ebus | -0.647 |
�� | -0.600 |
agara | -0.587 |
Cu | -0.583 |
Token | enc |
Token ID | 2207 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Philipp | +0.541 |
HEL | +0.525 |
Soda | +0.521 |
TE | +0.516 |
Sel | +0.516 |
Neg logit contributions | |
interstitial | -0.603 |
ebus | -0.578 |
�� | -0.533 |
agara | -0.520 |
Cu | -0.520 |
Token | irc |
Token ID | 1980 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Philipp | +0.548 |
Sel | +0.513 |
wic | +0.512 |
HEL | +0.508 |
Soda | +0.508 |
Neg logit contributions | |
interstitial | -1.914 |
ebus | -1.844 |
�� | -1.784 |
Cu | -1.738 |
EVA | -1.729 |
Token | le |
Token ID | 293 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Philipp | +2.120 |
HEL | +1.964 |
Sel | +1.954 |
TE | +1.951 |
Whe | +1.855 |
Neg logit contributions | |
interstitial | -10.775 |
ebus | -10.335 |
�� | -9.880 |
Cu | -9.691 |
�� | -9.683 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Philipp | +1.306 |
HEL | +1.250 |
Soda | +1.238 |
Sel | +1.234 |
Whe | +1.226 |
Neg logit contributions | |
interstitial | -1.850 |
ebus | -1.781 |
�� | -1.662 |
agara | -1.628 |
Cu | -1.625 |
Token | destroy |
Token ID | 4117 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
interstitial | +1.300 |
ebus | +1.242 |
�� | +1.138 |
Cu | +1.111 |
agara | +1.110 |
Neg logit contributions | |
Philipp | -1.591 |
HEL | -1.554 |
Soda | -1.547 |
Whe | -1.530 |
TE | -1.523 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Philipp | +1.553 |
HEL | +1.488 |
Soda | +1.476 |
Sel | +1.470 |
Whe | +1.462 |
Neg logit contributions | |
interstitial | -2.128 |
ebus | -2.065 |
�� | -1.916 |
Cu | -1.875 |
agara | -1.874 |
Token | enemy |
Token ID | 4472 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Philipp | +1.168 |
HEL | +1.123 |
Soda | +1.115 |
Sel | +1.111 |
Whe | +1.104 |
Neg logit contributions | |
interstitial | -1.474 |
ebus | -1.426 |
�� | -1.321 |
Cu | -1.297 |
agara | -1.295 |
Token | important |
Token ID | 1593 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
interstitial | +0.006 |
ebus | +0.006 |
�� | +0.006 |
Cu | +0.005 |
agara | +0.005 |
Neg logit contributions | |
Philipp | -0.005 |
HEL | -0.005 |
Soda | -0.005 |
Whe | -0.005 |
TE | -0.005 |
Token | than |
Token ID | 621 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Philipp | +0.277 |
HEL | +0.268 |
Soda | +0.267 |
Whe | +0.264 |
Sel | +0.264 |
Neg logit contributions | |
interstitial | -0.339 |
ebus | -0.326 |
�� | -0.302 |
agara | -0.296 |
Cu | -0.296 |
Token | ever |
Token ID | 1683 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
interstitial | +1.215 |
ebus | +1.160 |
�� | +1.069 |
Cu | +1.044 |
agara | +1.043 |
Neg logit contributions | |
Philipp | -1.368 |
HEL | -1.331 |
Soda | -1.323 |
Whe | -1.307 |
TE | -1.304 |
Token | to |
Token ID | 284 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
interstitial | +0.366 |
ebus | +0.351 |
�� | +0.325 |
Cu | +0.319 |
agara | +0.319 |
Neg logit contributions | |
Philipp | -0.330 |
HEL | -0.321 |
Soda | -0.319 |
Whe | -0.315 |
TE | -0.314 |
Token | spread |
Token ID | 4104 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
Philipp | +1.946 |
HEL | +1.894 |
TE | +1.880 |
Soda | +1.878 |
Sel | +1.866 |
Neg logit contributions | |
interstitial | -2.262 |
ebus | -2.164 |
�� | -2.009 |
Cu | -1.949 |
agara | -1.948 |
Token | complete |
Token ID | 1844 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
interstitial | +0.515 |
ebus | +0.495 |
�� | +0.460 |
Cu | +0.452 |
agara | +0.451 |
Neg logit contributions | |
Philipp | -0.426 |
HEL | -0.414 |
Soda | -0.411 |
Whe | -0.406 |
TE | -0.405 |
Token | and |
Token ID | 290 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Philipp | +2.171 |
HEL | +2.128 |
TE | +2.114 |
Sel | +2.099 |
Whe | +2.088 |
Neg logit contributions | |
interstitial | -2.920 |
ebus | -2.769 |
�� | -2.579 |
Cu | -2.515 |
agara | -2.502 |
Token | accurate |
Token ID | 7187 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
interstitial | +2.775 |
ebus | +2.679 |
�� | +2.501 |
agara | +2.455 |
Cu | +2.453 |
Neg logit contributions | |
Philipp | -2.240 |
Soda | -2.171 |
HEL | -2.157 |
Whe | -2.122 |
wic | -2.118 |
Token | information |
Token ID | 1321 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Philipp | +0.610 |
HEL | +0.595 |
Soda | +0.589 |
TE | +0.585 |
Whe | +0.584 |
Neg logit contributions | |
interstitial | -0.717 |
ebus | -0.689 |
�� | -0.637 |
agara | -0.625 |
Cu | -0.625 |
Token | about |
Token ID | 546 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Philipp | +0.992 |
HEL | +0.969 |
Soda | +0.951 |
TE | +0.950 |
Whe | +0.949 |
Neg logit contributions | |
interstitial | -1.234 |
ebus | -1.178 |
�� | -1.093 |
Cu | -1.071 |
agara | -1.069 |
Token | the |
Token ID | 262 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Philipp | +1.149 |
HEL | +1.116 |
Soda | +1.106 |
Whe | +1.098 |
TE | +1.096 |
Neg logit contributions | |
interstitial | -1.479 |
ebus | -1.422 |
�� | -1.323 |
Cu | -1.298 |
agara | -1.297 |
Token | or |
Token ID | 393 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
interstitial | +0.464 |
ebus | +0.446 |
�� | +0.417 |
Cu | +0.408 |
agara | +0.408 |
Neg logit contributions | |
Philipp | -0.356 |
HEL | -0.345 |
Soda | -0.342 |
Whe | -0.338 |
TE | -0.338 |
Token | two |
Token ID | 734 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
interstitial | +1.175 |
ebus | +1.130 |
�� | +1.051 |
Cu | +1.031 |
agara | +1.031 |
Neg logit contributions | |
Philipp | -0.963 |
HEL | -0.935 |
Soda | -0.929 |
Whe | -0.917 |
TE | -0.913 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Philipp | +0.123 |
HEL | +0.119 |
Soda | +0.118 |
Whe | +0.117 |
TE | +0.117 |
Neg logit contributions | |
interstitial | -0.163 |
ebus | -0.157 |
�� | -0.147 |
agara | -0.144 |
Cu | -0.144 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Philipp | +1.097 |
HEL | +1.067 |
Soda | +1.054 |
Whe | +1.052 |
TE | +1.044 |
Neg logit contributions | |
interstitial | -1.478 |
ebus | -1.412 |
�� | -1.317 |
agara | -1.299 |
Cu | -1.273 |
Token | Pro |
Token ID | 2964 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Philipp | +0.123 |
HEL | +0.121 |
Soda | +0.120 |
Whe | +0.119 |
TE | +0.118 |
Neg logit contributions | |
interstitial | -0.128 |
ebus | -0.124 |
�� | -0.115 |
agara | -0.112 |
Cu | -0.109 |
Token | ced |
Token ID | 771 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Philipp | +0.162 |
HEL | +0.157 |
Soda | +0.156 |
Whe | +0.154 |
TE | +0.154 |
Neg logit contributions | |
interstitial | -0.222 |
ebus | -0.214 |
�� | -0.200 |
agara | -0.196 |
Cu | -0.195 |
Token | ural |
Token ID | 1523 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
Philipp | +4.177 |
HEL | +4.084 |
TE | +4.050 |
Soda | +4.046 |
Sel | +4.036 |
Neg logit contributions | |
interstitial | -4.853 |
ebus | -4.682 |
�� | -4.495 |
agara | -4.216 |
bilt | -4.203 |
Token | City |
Token ID | 2254 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Philipp | +0.559 |
Soda | +0.538 |
HEL | +0.538 |
TE | +0.530 |
Whe | +0.530 |
Neg logit contributions | |
interstitial | -0.766 |
ebus | -0.741 |
�� | -0.689 |
agara | -0.676 |
Cu | -0.676 |
Token | Generation |
Token ID | 16588 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
interstitial | +2.930 |
ebus | +2.829 |
�� | +2.652 |
Cu | +2.612 |
agara | +2.603 |
Neg logit contributions | |
Philipp | -2.039 |
HEL | -1.978 |
Soda | -1.956 |
Whe | -1.928 |
TE | -1.919 |
Token | For |
Token ID | 1114 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
interstitial | +1.120 |
ebus | +1.077 |
�� | +1.006 |
Cu | +0.986 |
agara | +0.986 |
Neg logit contributions | |
Philipp | -0.836 |
HEL | -0.810 |
Soda | -0.805 |
Whe | -0.794 |
TE | -0.792 |
Token | D |
Token ID | 360 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
interstitial | +0.967 |
ebus | +0.932 |
�� | +0.872 |
Cu | +0.856 |
agara | +0.856 |
Neg logit contributions | |
Philipp | -0.668 |
HEL | -0.646 |
Soda | -0.642 |
Whe | -0.633 |
TE | -0.631 |
Token | become |
Token ID | 1716 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Philipp | +0.146 |
HEL | +0.142 |
Soda | +0.141 |
TE | +0.139 |
Whe | +0.139 |
Neg logit contributions | |
interstitial | -0.181 |
ebus | -0.174 |
�� | -0.162 |
Cu | -0.159 |
agara | -0.159 |
Token | even |
Token ID | 772 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Philipp | +0.111 |
HEL | +0.108 |
Soda | +0.107 |
TE | +0.106 |
Whe | +0.106 |
Neg logit contributions | |
interstitial | -0.142 |
ebus | -0.137 |
�� | -0.127 |
Cu | -0.124 |
agara | -0.124 |
Token | more |
Token ID | 517 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
Philipp | +2.035 |
HEL | +2.003 |
TE | +1.991 |
Sel | +1.970 |
Whe | +1.951 |
Neg logit contributions | |
interstitial | -3.070 |
ebus | -2.959 |
�� | -2.806 |
agara | -2.716 |
Cu | -2.688 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
interstitial | +0.512 |
ebus | +0.492 |
�� | +0.455 |
Cu | +0.445 |
agara | +0.445 |
Neg logit contributions | |
Philipp | -0.478 |
HEL | -0.465 |
Soda | -0.462 |
Whe | -0.457 |
TE | -0.456 |
Token | than |
Token ID | 621 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
Philipp | +0.925 |
HEL | +0.891 |
Soda | +0.886 |
TE | +0.881 |
Whe | +0.879 |
Neg logit contributions | |
interstitial | -1.323 |
ebus | -1.272 |
�� | -1.192 |
Cu | -1.160 |
agara | -1.160 |
Token | it |
Token ID | 340 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Philipp | +0.579 |
HEL | +0.561 |
Soda | +0.559 |
TE | +0.552 |
Whe | +0.551 |
Neg logit contributions | |
interstitial | -0.746 |
ebus | -0.721 |
�� | -0.672 |
agara | -0.658 |
Cu | -0.656 |
Token | is |
Token ID | 318 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Philipp | +0.984 |
HEL | +0.960 |
Soda | +0.951 |
TE | +0.940 |
Whe | +0.939 |
Neg logit contributions | |
interstitial | -1.122 |
ebus | -1.071 |
�� | -0.995 |
agara | -0.973 |
Cu | -0.972 |
Token | now |
Token ID | 783 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
interstitial | +1.231 |
ebus | +1.186 |
�� | +1.101 |
Cu | +1.082 |
agara | +1.081 |
Neg logit contributions | |
Philipp | -1.030 |
HEL | -1.001 |
Soda | -0.995 |
Whe | -0.981 |
TE | -0.977 |
Token | because |
Token ID | 780 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
interstitial | +2.274 |
ebus | +2.193 |
�� | +2.036 |
Cu | +2.005 |
agara | +2.003 |
Neg logit contributions | |
Philipp | -1.813 |
HEL | -1.761 |
Soda | -1.752 |
Whe | -1.722 |
TE | -1.714 |
Token | I |
Token ID | 314 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
interstitial | +0.178 |
ebus | +0.171 |
�� | +0.159 |
Cu | +0.156 |
agara | +0.156 |
Neg logit contributions | |
Philipp | -0.145 |
HEL | -0.140 |
Soda | -0.139 |
Whe | -0.137 |
TE | -0.137 |
Token | won |
Token ID | 1839 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
interstitial | +1.026 |
ebus | +0.984 |
�� | +0.910 |
agara | +0.897 |
Cu | +0.897 |
Neg logit contributions | |
Philipp | -0.962 |
HEL | -0.935 |
Soda | -0.931 |
Whe | -0.919 |
Sel | -0.911 |
Token | P |
Token ID | 47 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Sel | +4.166 |
Philipp | +4.166 |
HEL | +4.126 |
Soda | +4.091 |
TE | +4.079 |
Neg logit contributions | |
interstitial | -5.039 |
ebus | -5.011 |
�� | -4.687 |
agara | -4.580 |
bilt | -4.340 |
Token | ly |
Token ID | 306 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Philipp | +1.450 |
TE | +1.415 |
Sel | +1.409 |
HEL | +1.401 |
Soda | +1.388 |
Neg logit contributions | |
interstitial | -2.179 |
ebus | -2.081 |
�� | -1.948 |
EVA | -1.917 |
agara | -1.883 |
Token | Count |
Token ID | 12332 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Philipp | +4.727 |
HEL | +4.706 |
TE | +4.647 |
Soda | +4.644 |
Sel | +4.614 |
Neg logit contributions | |
interstitial | -3.280 |
ebus | -3.040 |
agara | -2.701 |
�� | -2.675 |
EVA | -2.501 |
Token | " |
Token ID | 366 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Philipp | +2.228 |
HEL | +2.070 |
Sel | +2.045 |
Soda | +2.021 |
Whe | +2.008 |
Neg logit contributions | |
interstitial | -4.703 |
ebus | -4.502 |
agara | -4.264 |
�� | -4.200 |
Cu | -4.086 |
Token | 94 |
Token ID | 5824 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Philipp | +2.854 |
HEL | +2.763 |
Soda | +2.735 |
Whe | +2.734 |
TE | +2.724 |
Neg logit contributions | |
interstitial | -4.282 |
ebus | -4.091 |
�� | -3.881 |
agara | -3.828 |
�� | -3.712 |
Token | "] |
Token ID | 8973 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Philipp | +1.287 |
HEL | +1.241 |
Soda | +1.231 |
TE | +1.213 |
Whe | +1.212 |
Neg logit contributions | |
interstitial | -1.882 |
ebus | -1.807 |
�� | -1.683 |
agara | -1.664 |
Cu | -1.655 |
Token | [ |
Token ID | 685 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Philipp | +2.471 |
HEL | +2.351 |
Soda | +2.322 |
TE | +2.313 |
Sel | +2.305 |
Neg logit contributions | |
interstitial | -5.139 |
ebus | -4.923 |
�� | -4.648 |
agara | -4.589 |
axter | -4.514 |
Token | Event |
Token ID | 9237 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Philipp | +3.853 |
Sel | +3.827 |
Soda | +3.816 |
TE | +3.809 |
HEL | +3.780 |
Neg logit contributions | |
interstitial | -4.527 |
ebus | -4.325 |
�� | -4.107 |
agara | -3.970 |
�� | -3.797 |
Token | Date |
Token ID | 10430 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Philipp | +0.939 |
HEL | +0.903 |
Soda | +0.900 |
Sel | +0.883 |
TE | +0.882 |
Neg logit contributions | |
interstitial | -1.605 |
ebus | -1.556 |
�� | -1.458 |
agara | -1.435 |
Cu | -1.423 |
Token | " |
Token ID | 366 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Philipp | +0.867 |
HEL | +0.835 |
Soda | +0.827 |
Whe | +0.818 |
Sel | +0.817 |
Neg logit contributions | |
interstitial | -1.580 |
ebus | -1.519 |
�� | -1.434 |
agara | -1.414 |
Cu | -1.391 |
Token | 2016 |
Token ID | 5304 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
interstitial | +0.404 |
ebus | +0.386 |
�� | +0.354 |
agara | +0.351 |
Cu | +0.340 |
Neg logit contributions | |
Philipp | -0.387 |
Soda | -0.375 |
HEL | -0.375 |
Whe | -0.370 |
TE | -0.370 |
Token | post |
Token ID | 1281 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Philipp | +1.080 |
HEL | +1.050 |
Soda | +1.045 |
Whe | +1.038 |
TE | +1.032 |
Neg logit contributions | |
interstitial | -1.405 |
ebus | -1.351 |
�� | -1.258 |
agara | -1.237 |
Cu | -1.236 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
interstitial | +1.489 |
ebus | +1.433 |
�� | +1.336 |
Cu | +1.310 |
agara | +1.308 |
Neg logit contributions | |
Philipp | -1.165 |
HEL | -1.129 |
Soda | -1.122 |
Whe | -1.104 |
TE | -1.102 |
Token | To |
Token ID | 1675 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
interstitial | +0.028 |
ebus | +0.026 |
�� | +0.024 |
agara | +0.024 |
Cu | +0.024 |
Neg logit contributions | |
Philipp | -0.023 |
HEL | -0.023 |
Soda | -0.023 |
Whe | -0.022 |
TE | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
interstitial | +1.583 |
ebus | +1.527 |
�� | +1.418 |
Cu | +1.393 |
agara | +1.393 |
Neg logit contributions | |
Philipp | -1.334 |
HEL | -1.293 |
Soda | -1.286 |
Whe | -1.265 |
TE | -1.262 |
Token | notified |
Token ID | 17600 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
interstitial | +1.245 |
ebus | +1.196 |
�� | +1.115 |
Cu | +1.095 |
agara | +1.094 |
Neg logit contributions | |
Philipp | -0.969 |
HEL | -0.941 |
Soda | -0.933 |
Whe | -0.922 |
TE | -0.919 |
Token | when |
Token ID | 618 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
interstitial | +1.931 |
ebus | +1.872 |
�� | +1.737 |
Cu | +1.706 |
agara | +1.704 |
Neg logit contributions | |
Philipp | -1.559 |
HEL | -1.514 |
Soda | -1.503 |
Whe | -1.471 |
TE | -1.470 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Philipp | +0.354 |
HEL | +0.344 |
Whe | +0.341 |
Soda | +0.341 |
Sel | +0.338 |
Neg logit contributions | |
interstitial | -0.415 |
ebus | -0.398 |
�� | -0.371 |
Cu | -0.363 |
agara | -0.363 |
Token | post |
Token ID | 1281 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
interstitial | +0.890 |
ebus | +0.857 |
�� | +0.798 |
Cu | +0.783 |
agara | +0.783 |
Neg logit contributions | |
Philipp | -0.701 |
HEL | -0.679 |
Soda | -0.675 |
Whe | -0.666 |
TE | -0.664 |
Token | is |
Token ID | 318 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
interstitial | +3.915 |
ebus | +3.756 |
�� | +3.464 |
agara | +3.410 |
Cu | +3.389 |
Neg logit contributions | |
Philipp | -3.539 |
Soda | -3.423 |
HEL | -3.405 |
Whe | -3.345 |
CONFIG | -3.338 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
interstitial | +1.929 |
ebus | +1.852 |
�� | +1.717 |
Cu | +1.683 |
agara | +1.682 |
Neg logit contributions | |
Philipp | -1.731 |
HEL | -1.682 |
Soda | -1.671 |
Whe | -1.652 |
TE | -1.647 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
interstitial | +1.696 |
ebus | +1.637 |
�� | +1.528 |
Cu | +1.502 |
agara | +1.500 |
Neg logit contributions | |
Philipp | -1.215 |
HEL | -1.176 |
Soda | -1.169 |
Whe | -1.150 |
TE | -1.147 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
interstitial | +2.784 |
ebus | +2.682 |
�� | +2.515 |
Cu | +2.476 |
agara | +2.463 |
Neg logit contributions | |
Philipp | -2.096 |
HEL | -2.025 |
Soda | -2.015 |
Whe | -1.993 |
wic | -1.974 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
interstitial | +0.521 |
ebus | +0.503 |
�� | +0.472 |
Cu | +0.464 |
agara | +0.464 |
Neg logit contributions | |
Philipp | -0.327 |
HEL | -0.316 |
Soda | -0.313 |
Whe | -0.308 |
TE | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
interstitial | +1.009 |
ebus | +0.974 |
�� | +0.911 |
Cu | +0.895 |
agara | +0.894 |
Neg logit contributions | |
Philipp | -0.724 |
HEL | -0.700 |
Soda | -0.695 |
Whe | -0.686 |
TE | -0.682 |
Token | 4 |
Token ID | 19 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
interstitial | +4.444 |
ebus | +4.188 |
Cu | +3.996 |
EVA | +3.876 |
agara | +3.867 |
Neg logit contributions | |
Philipp | -4.786 |
HEL | -4.710 |
Soda | -4.587 |
Whe | -4.522 |
wic | -4.478 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
interstitial | +2.430 |
ebus | +2.349 |
�� | +2.197 |
Cu | +2.166 |
agara | +2.154 |
Neg logit contributions | |
Philipp | -1.854 |
HEL | -1.790 |
Soda | -1.777 |
Whe | -1.757 |
wic | -1.745 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
interstitial | +1.644 |
ebus | +1.586 |
Cu | +1.478 |
�� | +1.475 |
agara | +1.450 |
Neg logit contributions | |
Philipp | -1.326 |
Soda | -1.280 |
HEL | -1.278 |
Whe | -1.245 |
TE | -1.242 |
Token | ]. |
Token ID | 4083 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
interstitial | +1.265 |
ebus | +1.217 |
�� | +1.132 |
Cu | +1.112 |
agara | +1.111 |
Neg logit contributions | |
Philipp | -1.020 |
HEL | -0.989 |
Soda | -0.983 |
Whe | -0.970 |
TE | -0.967 |
Token | each |
Token ID | 27379 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Philipp | +0.648 |
HEL | +0.628 |
Soda | +0.617 |
TE | +0.614 |
wic | +0.614 |
Neg logit contributions | |
interstitial | -1.118 |
ebus | -1.095 |
�� | -1.024 |
Cu | -1.007 |
agara | -1.003 |
Token | { |
Token ID | 1391 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
interstitial | +2.141 |
ebus | +2.043 |
�� | +1.888 |
agara | +1.845 |
Cu | +1.839 |
Neg logit contributions | |
Philipp | -2.257 |
HEL | -2.194 |
Soda | -2.189 |
Whe | -2.159 |
TE | -2.146 |
Token | | |
Token ID | 91 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
Philipp | +1.073 |
HEL | +1.048 |
Soda | +1.042 |
TE | +1.036 |
Sel | +1.027 |
Neg logit contributions | |
interstitial | -1.146 |
ebus | -1.116 |
�� | -1.021 |
agara | -1.002 |
Cu | -1.000 |
Token | i |
Token ID | 72 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
interstitial | +5.137 |
ebus | +4.724 |
�� | +4.310 |
Cu | +4.258 |
agara | +4.190 |
Neg logit contributions | |
Philipp | -6.832 |
HEL | -6.668 |
Soda | -6.613 |
Whe | -6.604 |
Sel | -6.553 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Philipp | +0.309 |
HEL | +0.301 |
Soda | +0.296 |
Sel | +0.295 |
TE | +0.294 |
Neg logit contributions | |
interstitial | -0.394 |
ebus | -0.380 |
�� | -0.351 |
Cu | -0.344 |
agara | -0.344 |
Token | of |
Token ID | 286 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
Philipp | +1.993 |
Soda | +1.954 |
Sel | +1.954 |
HEL | +1.940 |
Whe | +1.934 |
Neg logit contributions | |
interstitial | -2.712 |
ebus | -2.610 |
�� | -2.418 |
Cu | -2.362 |
agara | -2.359 |
Token | Allen |
Token ID | 9659 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Philipp | +0.029 |
HEL | +0.028 |
Soda | +0.028 |
Whe | +0.028 |
Sel | +0.028 |
Neg logit contributions | |
interstitial | -0.035 |
ebus | -0.034 |
�� | -0.031 |
Cu | -0.031 |
agara | -0.031 |
Token | � |
Token ID | 447 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Philipp | +2.301 |
HEL | +2.247 |
Whe | +2.240 |
Sel | +2.235 |
Soda | +2.231 |
Neg logit contributions | |
interstitial | -2.889 |
ebus | -2.798 |
�� | -2.592 |
agara | -2.541 |
EVA | -2.497 |
Token | � |
Token ID | 247 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Philipp | +1.071 |
HEL | +1.055 |
Soda | +1.044 |
Sel | +1.035 |
TE | +1.033 |
Neg logit contributions | |
interstitial | -1.096 |
ebus | -1.054 |
�� | -0.960 |
agara | -0.952 |
Cu | -0.948 |
Token | s |
Token ID | 82 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Philipp | +3.292 |
HEL | +3.205 |
Sel | +3.195 |
Soda | +3.175 |
Whe | +3.160 |
Neg logit contributions | |
interstitial | -5.374 |
ebus | -5.181 |
�� | -4.804 |
agara | -4.766 |
EVA | -4.686 |
Token | wheel |
Token ID | 7825 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
interstitial | +3.483 |
ebus | +3.398 |
�� | +3.144 |
Cu | +3.136 |
agara | +3.117 |
Neg logit contributions | |
Philipp | -2.940 |
HEL | -2.860 |
Soda | -2.832 |
wic | -2.817 |
CONFIG | -2.815 |
Token | house |
Token ID | 4803 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Philipp | +0.148 |
HEL | +0.144 |
Soda | +0.143 |
Whe | +0.142 |
TE | +0.142 |
Neg logit contributions | |
interstitial | -0.227 |
ebus | -0.217 |
�� | -0.205 |
agara | -0.200 |
Cu | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
interstitial | +2.818 |
ebus | +2.719 |
�� | +2.515 |
Cu | +2.495 |
agara | +2.478 |
Neg logit contributions | |
Philipp | -2.284 |
HEL | -2.219 |
Soda | -2.204 |
Whe | -2.167 |
CONFIG | -2.161 |
Token | But |
Token ID | 887 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
interstitial | +0.657 |
ebus | +0.632 |
�� | +0.589 |
Cu | +0.580 |
agara | +0.578 |
Neg logit contributions | |
Philipp | -0.506 |
HEL | -0.491 |
Soda | -0.487 |
Whe | -0.479 |
TE | -0.479 |
Token | this |
Token ID | 428 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
interstitial | +2.386 |
ebus | +2.288 |
�� | +2.126 |
agara | +2.088 |
Cu | +2.087 |
Neg logit contributions | |
Philipp | -2.042 |
HEL | -1.987 |
Soda | -1.969 |
TE | -1.941 |
CONFIG | -1.934 |
Token | Pad |
Token ID | 26114 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
interstitial | +0.784 |
ebus | +0.720 |
�� | +0.607 |
agara | +0.576 |
Cu | +0.574 |
Neg logit contributions | |
Philipp | -2.296 |
HEL | -2.255 |
Soda | -2.248 |
Whe | -2.229 |
TE | -2.226 |
Token | features |
Token ID | 3033 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
interstitial | +1.164 |
ebus | +1.116 |
�� | +1.033 |
agara | +1.008 |
Cu | +1.007 |
Neg logit contributions | |
Philipp | -1.109 |
HEL | -1.079 |
Soda | -1.074 |
Whe | -1.062 |
TE | -1.059 |
Token | elicit |
Token ID | 44055 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
interstitial | +0.841 |
ebus | +0.807 |
�� | +0.747 |
Cu | +0.731 |
agara | +0.731 |
Neg logit contributions | |
Philipp | -0.786 |
HEL | -0.765 |
Soda | -0.761 |
Whe | -0.751 |
TE | -0.749 |
Token | the |
Token ID | 262 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
interstitial | +4.288 |
ebus | +4.085 |
�� | +3.765 |
Cu | +3.723 |
agara | +3.712 |
Neg logit contributions | |
Philipp | -3.753 |
HEL | -3.656 |
Soda | -3.625 |
wic | -3.584 |
Whe | -3.556 |
Token | same |
Token ID | 976 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
interstitial | +2.742 |
ebus | +2.642 |
�� | +2.444 |
Cu | +2.414 |
agara | +2.398 |
Neg logit contributions | |
Philipp | -2.258 |
HEL | -2.189 |
Soda | -2.178 |
wic | -2.145 |
Whe | -2.138 |
Token | � |
Token ID | 564 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
interstitial | +2.526 |
ebus | +2.427 |
�� | +2.237 |
Cu | +2.207 |
agara | +2.203 |
Neg logit contributions | |
Philipp | -2.187 |
HEL | -2.125 |
Soda | -2.114 |
wic | -2.080 |
Whe | -2.080 |
Token | � |
Token ID | 250 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
interstitial | +0.310 |
ebus | +0.295 |
�� | +0.265 |
agara | +0.264 |
Cu | +0.264 |
Neg logit contributions | |
Philipp | -0.370 |
HEL | -0.361 |
Soda | -0.359 |
Whe | -0.355 |
TE | -0.355 |
Token | You |
Token ID | 1639 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
interstitial | +2.064 |
ebus | +1.985 |
�� | +1.847 |
Cu | +1.816 |
agara | +1.813 |
Neg logit contributions | |
Philipp | -1.624 |
HEL | -1.574 |
Soda | -1.564 |
Whe | -1.542 |
TE | -1.538 |
Token | have |
Token ID | 423 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
interstitial | +1.162 |
ebus | +1.117 |
�� | +1.038 |
agara | +1.021 |
Cu | +1.017 |
Neg logit contributions | |
Philipp | -0.896 |
HEL | -0.871 |
Soda | -0.868 |
TE | -0.856 |
Whe | -0.855 |
Token | to |
Token ID | 284 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
interstitial | +0.246 |
ebus | +0.236 |
�� | +0.219 |
agara | +0.215 |
Cu | +0.214 |
Neg logit contributions | |
Philipp | -0.207 |
HEL | -0.202 |
Soda | -0.201 |
Whe | -0.199 |
TE | -0.198 |
Token | try |
Token ID | 1949 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
interstitial | +4.214 |
ebus | +4.098 |
�� | +3.786 |
Cu | +3.752 |
agara | +3.737 |
Neg logit contributions | |
Philipp | -4.063 |
HEL | -3.944 |
Soda | -3.909 |
wic | -3.865 |
Whe | -3.856 |
Token | were |
Token ID | 547 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
interstitial | +2.257 |
ebus | +2.203 |
�� | +1.988 |
agara | +1.986 |
Cu | +1.972 |
Neg logit contributions | |
Philipp | -2.551 |
Soda | -2.507 |
HEL | -2.504 |
Whe | -2.460 |
Sel | -2.436 |
Token | am |
Token ID | 716 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Philipp | +0.288 |
HEL | +0.279 |
Soda | +0.276 |
TE | +0.274 |
Whe | +0.273 |
Neg logit contributions | |
interstitial | -0.357 |
ebus | -0.342 |
�� | -0.320 |
Cu | -0.312 |
agara | -0.312 |
Token | assing |
Token ID | 19696 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
Philipp | +2.615 |
HEL | +2.501 |
TE | +2.430 |
Sel | +2.394 |
Soda | +2.389 |
Neg logit contributions | |
interstitial | -6.223 |
ebus | -6.046 |
�� | -5.870 |
Cu | -5.691 |
agara | -5.654 |
Token | as |
Token ID | 355 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
interstitial | +4.808 |
ebus | +4.697 |
�� | +4.296 |
agara | +4.231 |
Cu | +4.210 |
Neg logit contributions | |
Philipp | -4.455 |
HEL | -4.390 |
Soda | -4.380 |
CONFIG | -4.288 |
Whe | -4.276 |
Token | they |
Token ID | 484 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
interstitial | +1.811 |
ebus | +1.746 |
�� | +1.626 |
Cu | +1.594 |
agara | +1.589 |
Neg logit contributions | |
Philipp | -1.646 |
HEL | -1.600 |
Soda | -1.597 |
wic | -1.574 |
Whe | -1.566 |
Token | held |
Token ID | 2714 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ebus | +4.247 |
interstitial | +4.191 |
�� | +3.826 |
agara | +3.812 |
Cu | +3.800 |
Neg logit contributions | |
Philipp | -4.345 |
Soda | -4.300 |
HEL | -4.215 |
wic | -4.131 |
Whe | -4.124 |
Token | up |
Token ID | 510 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
interstitial | +0.966 |
ebus | +0.930 |
�� | +0.866 |
Cu | +0.850 |
agara | +0.850 |
Neg logit contributions | |
Philipp | -0.759 |
HEL | -0.736 |
Soda | -0.732 |
Whe | -0.721 |
TE | -0.718 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
interstitial | +2.051 |
ebus | +1.973 |
�� | +1.831 |
Cu | +1.799 |
agara | +1.797 |
Neg logit contributions | |
Philipp | -1.778 |
HEL | -1.727 |
Soda | -1.720 |
wic | -1.688 |
Whe | -1.688 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
interstitial | +2.646 |
ebus | +2.546 |
�� | +2.371 |
Cu | +2.327 |
agara | +2.313 |
Neg logit contributions | |
Philipp | -2.360 |
Soda | -2.290 |
HEL | -2.289 |
wic | -2.240 |
CONFIG | -2.239 |
Token | tea |
Token ID | 8887 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
interstitial | +1.554 |
ebus | +1.494 |
�� | +1.386 |
Cu | +1.360 |
agara | +1.358 |
Neg logit contributions | |
Philipp | -1.338 |
HEL | -1.299 |
Soda | -1.292 |
Whe | -1.274 |
TE | -1.270 |
Token | party |
Token ID | 2151 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
interstitial | +2.500 |
ebus | +2.416 |
�� | +2.268 |
Cu | +2.241 |
agara | +2.235 |
Neg logit contributions | |
Philipp | -1.594 |
HEL | -1.546 |
Soda | -1.536 |
Whe | -1.502 |
TE | -1.499 |
Token | 's |
Token ID | 338 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
interstitial | +2.533 |
ebus | +2.450 |
�� | +2.260 |
Cu | +2.229 |
agara | +2.218 |
Neg logit contributions | |
Philipp | -2.287 |
HEL | -2.222 |
Soda | -2.204 |
Whe | -2.173 |
TE | -2.168 |
Token | iPad |
Token ID | 13133 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
interstitial | +2.031 |
ebus | +1.960 |
�� | +1.807 |
Cu | +1.785 |
agara | +1.773 |
Neg logit contributions | |
Philipp | -1.770 |
HEL | -1.717 |
Soda | -1.703 |
Whe | -1.677 |
wic | -1.675 |
Token | hit |
Token ID | 2277 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Philipp | +0.546 |
HEL | +0.531 |
Soda | +0.529 |
Whe | +0.525 |
TE | +0.522 |
Neg logit contributions | |
interstitial | -0.773 |
ebus | -0.742 |
�� | -0.690 |
agara | -0.678 |
Cu | -0.675 |
Token | the |
Token ID | 262 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
interstitial | +2.069 |
ebus | +1.989 |
�� | +1.848 |
Cu | +1.819 |
agara | +1.813 |
Neg logit contributions | |
Philipp | -1.655 |
HEL | -1.603 |
Soda | -1.593 |
Whe | -1.567 |
TE | -1.563 |
Token | 100 |
Token ID | 1802 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
interstitial | +0.056 |
ebus | +0.054 |
�� | +0.050 |
agara | +0.049 |
Cu | +0.049 |
Neg logit contributions | |
Philipp | -0.045 |
HEL | -0.044 |
Soda | -0.043 |
Whe | -0.043 |
TE | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
interstitial | +2.414 |
ebus | +2.318 |
�� | +2.152 |
Cu | +2.114 |
agara | +2.109 |
Neg logit contributions | |
Philipp | -2.124 |
HEL | -2.065 |
Soda | -2.052 |
Whe | -2.024 |
TE | -2.018 |
Token | 000 |
Token ID | 830 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
interstitial | +0.560 |
ebus | +0.540 |
�� | +0.503 |
agara | +0.494 |
Cu | +0.492 |
Neg logit contributions | |
Philipp | -0.432 |
HEL | -0.419 |
Soda | -0.417 |
Whe | -0.411 |
TE | -0.410 |
Token | mark |
Token ID | 1317 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
interstitial | +1.908 |
ebus | +1.834 |
�� | +1.693 |
agara | +1.654 |
Cu | +1.653 |
Neg logit contributions | |
Philipp | -1.857 |
HEL | -1.806 |
Soda | -1.797 |
Whe | -1.776 |
TE | -1.774 |
Token | recently |
Token ID | 2904 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
interstitial | +0.359 |
ebus | +0.345 |
�� | +0.322 |
agara | +0.316 |
Cu | +0.315 |
Neg logit contributions | |
Philipp | -0.287 |
HEL | -0.278 |
Soda | -0.276 |
Whe | -0.273 |
TE | -0.272 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Philipp | +0.570 |
HEL | +0.548 |
Soda | +0.544 |
Whe | +0.540 |
TE | +0.538 |
Neg logit contributions | |
interstitial | -0.863 |
ebus | -0.826 |
�� | -0.778 |
agara | -0.762 |
Cu | -0.762 |
Token | according |
Token ID | 1864 |
Feature activation | -8.15e-03 |
Pos logit contributions | |
interstitial | +1.411 |
ebus | +1.360 |
�� | +1.268 |
Cu | +1.250 |
agara | +1.244 |
Neg logit contributions | |
Philipp | -1.045 |
HEL | -1.013 |
Soda | -1.003 |
Whe | -0.987 |
TE | -0.985 |
Token | show |
Token ID | 905 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
interstitial | +1.049 |
ebus | +1.007 |
�� | +0.932 |
agara | +0.917 |
Cu | +0.917 |
Neg logit contributions | |
Philipp | -0.986 |
HEL | -0.958 |
Soda | -0.953 |
Whe | -0.939 |
Sel | -0.935 |
Token | that |
Token ID | 326 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
interstitial | +0.031 |
ebus | +0.030 |
�� | +0.028 |
agara | +0.027 |
Cu | +0.027 |
Neg logit contributions | |
Philipp | -0.027 |
HEL | -0.026 |
Soda | -0.026 |
Whe | -0.026 |
TE | -0.026 |
Token | bigger |
Token ID | 5749 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
interstitial | +0.269 |
ebus | +0.259 |
�� | +0.242 |
agara | +0.237 |
Cu | +0.237 |
Neg logit contributions | |
Philipp | -0.209 |
HEL | -0.203 |
Soda | -0.201 |
Whe | -0.199 |
TE | -0.198 |
Token | is |
Token ID | 318 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
interstitial | +0.406 |
ebus | +0.390 |
�� | +0.362 |
Cu | +0.354 |
agara | +0.354 |
Neg logit contributions | |
Philipp | -0.352 |
HEL | -0.342 |
Soda | -0.340 |
Whe | -0.335 |
TE | -0.335 |
Token | not |
Token ID | 407 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
interstitial | +4.078 |
ebus | +3.926 |
�� | +3.582 |
Cu | +3.574 |
agara | +3.557 |
Neg logit contributions | |
Philipp | -4.761 |
Soda | -4.565 |
HEL | -4.565 |
CONFIG | -4.552 |
wic | -4.535 |
Token | necessarily |
Token ID | 6646 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
interstitial | +5.146 |
ebus | +5.098 |
Cu | +4.625 |
agara | +4.606 |
�� | +4.603 |
Neg logit contributions | |
Philipp | -6.312 |
wic | -6.082 |
CONFIG | -6.025 |
Soda | -6.006 |
HEL | -5.991 |
Token | better |
Token ID | 1365 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
interstitial | +5.097 |
ebus | +5.032 |
Cu | +4.506 |
�� | +4.493 |
agara | +4.454 |
Neg logit contributions | |
Philipp | -7.921 |
wic | -7.670 |
CONFIG | -7.614 |
HEL | -7.557 |
Soda | -7.556 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
interstitial | +4.338 |
ebus | +4.174 |
�� | +3.882 |
Cu | +3.837 |
agara | +3.807 |
Neg logit contributions | |
Philipp | -3.688 |
HEL | -3.549 |
Soda | -3.524 |
wic | -3.475 |
Whe | -3.473 |
Token | The |
Token ID | 383 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
interstitial | +1.432 |
ebus | +1.390 |
�� | +1.293 |
Cu | +1.286 |
agara | +1.270 |
Neg logit contributions | |
Philipp | -1.080 |
HEL | -1.046 |
Soda | -1.036 |
wic | -1.025 |
Whe | -1.023 |
Token | number |
Token ID | 1271 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
interstitial | +1.383 |
ebus | +1.335 |
�� | +1.237 |
Cu | +1.218 |
agara | +1.215 |
Neg logit contributions | |
Philipp | -1.156 |
HEL | -1.120 |
Soda | -1.112 |
Whe | -1.099 |
TE | -1.094 |
Token | of |
Token ID | 286 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
interstitial | +2.801 |
ebus | +2.705 |
�� | +2.507 |
agara | +2.484 |
Cu | +2.476 |
Neg logit contributions | |
Philipp | -2.471 |
HEL | -2.401 |
Soda | -2.376 |
Whe | -2.353 |
CONFIG | -2.349 |
Token | Q |
Token ID | 48 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
Philipp | +1.337 |
HEL | +1.322 |
TE | +1.301 |
Soda | +1.284 |
Whe | +1.271 |
Neg logit contributions | |
interstitial | -2.109 |
ebus | -2.034 |
�� | -1.917 |
agara | -1.884 |
Cu | -1.851 |
Token | UE |
Token ID | 8924 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
interstitial | +0.660 |
ebus | +0.637 |
�� | +0.601 |
agara | +0.593 |
Cu | +0.589 |
Neg logit contributions | |
Philipp | -0.389 |
HEL | -0.377 |
Soda | -0.373 |
TE | -0.369 |
Whe | -0.367 |
Token | / |
Token ID | 14 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
HEL | +2.154 |
Philipp | +2.145 |
TE | +2.106 |
Soda | +2.069 |
Sel | +2.066 |
Neg logit contributions | |
interstitial | -3.543 |
ebus | -3.414 |
�� | -3.212 |
agara | -3.191 |
Cu | -3.068 |
Token | RE |
Token ID | 2200 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
Philipp | +0.443 |
HEL | +0.440 |
Soda | +0.430 |
TE | +0.428 |
Sel | +0.428 |
Neg logit contributions | |
interstitial | -0.517 |
ebus | -0.497 |
�� | -0.462 |
agara | -0.458 |
Cu | -0.445 |
Token | UTERS |
Token ID | 14974 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
interstitial | +0.250 |
ebus | +0.238 |
�� | +0.217 |
agara | +0.212 |
Cu | +0.212 |
Neg logit contributions | |
Philipp | -0.310 |
HEL | -0.302 |
Soda | -0.301 |
Whe | -0.298 |
TE | -0.297 |
Token | Presidential |
Token ID | 17471 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
interstitial | +2.171 |
ebus | +2.115 |
�� | +1.953 |
Cu | +1.949 |
agara | +1.928 |
Neg logit contributions | |
Philipp | -1.494 |
HEL | -1.445 |
wic | -1.428 |
Soda | -1.426 |
Whe | -1.401 |
Token | candidate |
Token ID | 4540 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
interstitial | +6.630 |
ebus | +6.535 |
Cu | +6.006 |
�� | +5.978 |
agara | +5.935 |
Neg logit contributions | |
Philipp | -3.844 |
HEL | -3.783 |
Soda | -3.755 |
wic | -3.754 |
CONFIG | -3.671 |
Token | Senator |
Token ID | 8962 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
interstitial | +2.524 |
ebus | +2.431 |
�� | +2.248 |
Cu | +2.245 |
agara | +2.228 |
Neg logit contributions | |
Philipp | -1.751 |
Soda | -1.693 |
HEL | -1.691 |
wic | -1.674 |
CONFIG | -1.657 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
interstitial | +2.333 |
ebus | +2.237 |
�� | +2.069 |
Cu | +2.051 |
agara | +2.048 |
Neg logit contributions | |
Philipp | -2.060 |
Soda | -2.002 |
HEL | -2.000 |
wic | -1.967 |
CONFIG | -1.961 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
interstitial | +0.476 |
ebus | +0.459 |
Cu | +0.420 |
�� | +0.418 |
agara | +0.414 |
Neg logit contributions | |
Philipp | -0.492 |
HEL | -0.479 |
Soda | -0.476 |
wic | -0.472 |
TE | -0.470 |
Token | com |
Token ID | 401 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
interstitial | +0.576 |
ebus | +0.555 |
�� | +0.514 |
Cu | +0.506 |
agara | +0.506 |
Neg logit contributions | |
Philipp | -0.476 |
HEL | -0.461 |
Soda | -0.459 |
Whe | -0.452 |
TE | -0.451 |
Token | an |
Token ID | 281 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
interstitial | +1.153 |
ebus | +1.109 |
�� | +1.030 |
Cu | +1.011 |
agara | +1.010 |
Neg logit contributions | |
Philipp | -0.968 |
HEL | -0.939 |
Soda | -0.933 |
Whe | -0.921 |
TE | -0.919 |
Token | additional |
Token ID | 3224 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
interstitial | +0.141 |
ebus | +0.135 |
�� | +0.125 |
Cu | +0.123 |
agara | +0.122 |
Neg logit contributions | |
Philipp | -0.129 |
HEL | -0.126 |
Soda | -0.125 |
Whe | -0.124 |
TE | -0.123 |
Token | attempt |
Token ID | 2230 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
Philipp | +0.114 |
HEL | +0.111 |
Soda | +0.110 |
Whe | +0.109 |
TE | +0.109 |
Neg logit contributions | |
interstitial | -0.135 |
ebus | -0.130 |
�� | -0.121 |
Cu | -0.118 |
agara | -0.118 |
Token | by |
Token ID | 416 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
Philipp | +0.161 |
HEL | +0.157 |
Soda | +0.155 |
Whe | +0.154 |
Sel | +0.154 |
Neg logit contributions | |
interstitial | -0.186 |
ebus | -0.178 |
�� | -0.164 |
agara | -0.162 |
Cu | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
Philipp | +0.670 |
HEL | +0.647 |
Soda | +0.645 |
Whe | +0.638 |
Sel | +0.637 |
Neg logit contributions | |
interstitial | -0.773 |
ebus | -0.741 |
�� | -0.689 |
agara | -0.677 |
Cu | -0.674 |
Token | club |
Token ID | 3430 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
Philipp | +0.624 |
HEL | +0.611 |
Soda | +0.610 |
Sel | +0.604 |
Whe | +0.603 |
Neg logit contributions | |
interstitial | -0.492 |
ebus | -0.466 |
�� | -0.430 |
agara | -0.418 |
Cu | -0.415 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
interstitial | +5.376 |
ebus | +5.254 |
�� | +4.724 |
Cu | +4.689 |
agara | +4.634 |
Neg logit contributions | |
Philipp | -6.644 |
Soda | -6.394 |
HEL | -6.388 |
CONFIG | -6.356 |
wic | -6.350 |
Token | bolster |
Token ID | 26091 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
interstitial | +1.589 |
ebus | +1.533 |
�� | +1.421 |
agara | +1.406 |
Cu | +1.394 |
Neg logit contributions | |
Philipp | -1.473 |
HEL | -1.429 |
Soda | -1.421 |
Whe | -1.406 |
wic | -1.393 |
Token | their |
Token ID | 511 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
interstitial | +1.273 |
ebus | +1.228 |
�� | +1.147 |
agara | +1.127 |
Cu | +1.126 |
Neg logit contributions | |
Philipp | -0.903 |
HEL | -0.874 |
Soda | -0.868 |
Whe | -0.856 |
TE | -0.853 |
Token | case |
Token ID | 1339 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
interstitial | +1.544 |
ebus | +1.484 |
�� | +1.376 |
Cu | +1.350 |
agara | +1.350 |
Neg logit contributions | |
Philipp | -1.352 |
HEL | -1.312 |
Soda | -1.305 |
Whe | -1.288 |
TE | -1.284 |
Token | against |
Token ID | 1028 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Philipp | +0.190 |
HEL | +0.184 |
Soda | +0.183 |
Whe | +0.181 |
Sel | +0.180 |
Neg logit contributions | |
interstitial | -0.251 |
ebus | -0.241 |
�� | -0.225 |
agara | -0.221 |
Cu | -0.221 |
Token | not |
Token ID | 407 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
Philipp | +0.357 |
HEL | +0.346 |
Soda | +0.343 |
Whe | +0.339 |
TE | +0.338 |
Neg logit contributions | |
interstitial | -0.486 |
ebus | -0.467 |
�� | -0.436 |
Cu | -0.427 |
agara | -0.427 |
Token | an |
Token ID | 281 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Philipp | +0.059 |
HEL | +0.057 |
Soda | +0.056 |
Whe | +0.056 |
TE | +0.056 |
Neg logit contributions | |
interstitial | -0.075 |
ebus | -0.072 |
�� | -0.067 |
Cu | -0.066 |
agara | -0.066 |
Token | apples |
Token ID | 22514 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Philipp | +0.743 |
HEL | +0.721 |
Soda | +0.711 |
Whe | +0.704 |
Sel | +0.704 |
Neg logit contributions | |
interstitial | -1.113 |
ebus | -1.076 |
�� | -1.000 |
Cu | -0.985 |
agara | -0.979 |
Token | - |
Token ID | 12 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
interstitial | +3.422 |
ebus | +3.300 |
�� | +3.085 |
agara | +3.050 |
Cu | +3.045 |
Neg logit contributions | |
Philipp | -2.333 |
HEL | -2.275 |
Soda | -2.250 |
Whe | -2.220 |
TE | -2.205 |
Token | to |
Token ID | 1462 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
interstitial | +4.054 |
ebus | +3.753 |
Cu | +3.577 |
agara | +3.570 |
�� | +3.548 |
Neg logit contributions | |
Philipp | -3.277 |
HEL | -3.238 |
Soda | -3.192 |
Whe | -3.117 |
Sel | -3.097 |
Token | - |
Token ID | 12 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
interstitial | +4.135 |
ebus | +4.027 |
Cu | +3.744 |
mare | +3.678 |
agara | +3.662 |
Neg logit contributions | |
Philipp | -3.422 |
HEL | -3.358 |
Soda | -3.334 |
CONFIG | -3.217 |
TE | -3.216 |
Token | app |
Token ID | 1324 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
interstitial | +6.609 |
ebus | +6.089 |
mare | +5.875 |
Cu | +5.857 |
agara | +5.744 |
Neg logit contributions | |
Philipp | -5.216 |
HEL | -5.126 |
Soda | -5.064 |
UCH | -4.968 |
TE | -4.962 |
Token | les |
Token ID | 829 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
interstitial | +0.230 |
ebus | +0.224 |
�� | +0.212 |
Cu | +0.209 |
agara | +0.209 |
Neg logit contributions | |
Philipp | -0.082 |
HEL | -0.078 |
Soda | -0.077 |
Whe | -0.075 |
TE | -0.075 |
Token | comparison |
Token ID | 7208 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
interstitial | +0.940 |
ebus | +0.904 |
�� | +0.841 |
Cu | +0.825 |
agara | +0.824 |
Neg logit contributions | |
Philipp | -0.759 |
HEL | -0.736 |
Soda | -0.732 |
Whe | -0.722 |
TE | -0.721 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
interstitial | +1.694 |
ebus | +1.638 |
�� | +1.527 |
agara | +1.501 |
Cu | +1.501 |
Neg logit contributions | |
Philipp | -1.263 |
HEL | -1.225 |
Soda | -1.219 |
Whe | -1.197 |
TE | -1.194 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
Philipp | +0.767 |
HEL | +0.743 |
Soda | +0.740 |
Whe | +0.731 |
TE | +0.727 |
Neg logit contributions | |
interstitial | -0.995 |
ebus | -0.952 |
�� | -0.885 |
agara | -0.872 |
Cu | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
interstitial | +1.465 |
ebus | +1.437 |
Cu | +1.332 |
�� | +1.297 |
agara | +1.291 |
Neg logit contributions | |
Philipp | -1.338 |
Soda | -1.294 |
HEL | -1.293 |
wic | -1.259 |
CONFIG | -1.256 |
Token | 85 |
Token ID | 5332 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Philipp | +0.918 |
HEL | +0.890 |
Soda | +0.875 |
Whe | +0.869 |
TE | +0.869 |
Neg logit contributions | |
interstitial | -1.675 |
ebus | -1.615 |
�� | -1.530 |
agara | -1.496 |
Cu | -1.481 |
Token | 17 |
Token ID | 1558 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
interstitial | +3.898 |
ebus | +3.782 |
Cu | +3.600 |
EVA | +3.481 |
mare | +3.469 |
Neg logit contributions | |
Philipp | -3.467 |
Soda | -3.371 |
wic | -3.342 |
HEL | -3.340 |
Whe | -3.263 |
Token | 4 |
Token ID | 604 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Philipp | +0.402 |
HEL | +0.389 |
Soda | +0.386 |
TE | +0.382 |
Whe | +0.382 |
Neg logit contributions | |
interstitial | -0.606 |
ebus | -0.582 |
�� | -0.546 |
agara | -0.536 |
Cu | -0.534 |
Token | * |
Token ID | 9 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
interstitial | +6.248 |
ebus | +6.191 |
Cu | +5.975 |
EVA | +5.762 |
mare | +5.684 |
Neg logit contributions | |
Philipp | -5.052 |
HEL | -4.847 |
Soda | -4.827 |
wic | -4.750 |
Gins | -4.663 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
interstitial | +2.622 |
ebus | +2.540 |
�� | +2.357 |
Cu | +2.339 |
agara | +2.308 |
Neg logit contributions | |
Philipp | -2.082 |
HEL | -2.016 |
Soda | -2.006 |
wic | -1.968 |
Whe | -1.966 |
Token | * |
Token ID | 9 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
interstitial | +5.203 |
ebus | +5.152 |
Cu | +5.043 |
EVA | +4.803 |
mare | +4.773 |
Neg logit contributions | |
Philipp | -4.360 |
Soda | -4.179 |
HEL | -4.145 |
wic | -4.085 |
Gins | -3.999 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
interstitial | +1.211 |
ebus | +1.174 |
�� | +1.094 |
Cu | +1.079 |
agara | +1.070 |
Neg logit contributions | |
Philipp | -0.906 |
HEL | -0.879 |
Soda | -0.872 |
Whe | -0.855 |
wic | -0.854 |
Token | * |
Token ID | 9 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
interstitial | +4.853 |
ebus | +4.755 |
Cu | +4.638 |
EVA | +4.427 |
mare | +4.374 |
Neg logit contributions | |
Philipp | -3.691 |
Soda | -3.553 |
HEL | -3.538 |
wic | -3.450 |
CONFIG | -3.405 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
interstitial | +0.544 |
ebus | +0.525 |
�� | +0.490 |
Cu | +0.483 |
agara | +0.481 |
Neg logit contributions | |
Philipp | -0.383 |
HEL | -0.371 |
Soda | -0.368 |
Whe | -0.362 |
Sel | -0.360 |
Token | * |
Token ID | 9 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
interstitial | +3.823 |
ebus | +3.736 |
Cu | +3.583 |
EVA | +3.452 |
�� | +3.430 |
Neg logit contributions | |
Philipp | -2.693 |
Soda | -2.575 |
HEL | -2.574 |
wic | -2.526 |
CONFIG | -2.489 |