Token | wetlands |
Token ID | 49297 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
bilt | +1.974 |
NESS | +1.654 |
hess | +1.641 |
ewater | +1.557 |
�� | +1.509 |
Neg logit contributions | |
ependence | -2.145 |
idates | -2.133 |
los | -2.121 |
ogh | -2.104 |
yg | -2.001 |
Token | was |
Token ID | 373 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
bilt | +2.124 |
NESS | +1.813 |
hess | +1.807 |
ewater | +1.698 |
�� | +1.664 |
Neg logit contributions | |
ependence | -1.946 |
idates | -1.942 |
los | -1.928 |
ogh | -1.914 |
yg | -1.817 |
Token | happening |
Token ID | 5836 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
idates | +0.775 |
los | +0.773 |
ogh | +0.773 |
ependence | +0.767 |
yg | +0.728 |
Neg logit contributions | |
bilt | -0.914 |
NESS | -0.779 |
hess | -0.773 |
�� | -0.730 |
ewater | -0.729 |
Token | at |
Token ID | 379 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
idates | +0.377 |
los | +0.376 |
ependence | +0.376 |
ogh | +0.375 |
yg | +0.353 |
Neg logit contributions | |
bilt | -0.444 |
NESS | -0.381 |
hess | -0.378 |
ewater | -0.356 |
�� | -0.355 |
Token | Kan |
Token ID | 14248 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
idates | +2.474 |
ogh | +2.431 |
ependence | +2.425 |
los | +2.422 |
yg | +2.309 |
Neg logit contributions | |
bilt | -2.674 |
NESS | -2.286 |
hess | -2.267 |
�� | -2.118 |
ewater | -2.086 |
Token | akia |
Token ID | 21897 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ependence | +1.318 |
idates | +1.314 |
los | +1.287 |
ogh | +1.286 |
yg | +1.181 |
Neg logit contributions | |
bilt | -2.871 |
NESS | -2.610 |
hess | -2.523 |
�� | -2.477 |
ewater | -2.425 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ogh | +6.819 |
idates | +6.502 |
ependence | +6.398 |
yg | +6.028 |
bu | +5.801 |
Neg logit contributions | |
bilt | -16.297 |
NESS | -14.584 |
hess | -14.579 |
�� | -14.243 |
ewater | -13.644 |
Token | Several |
Token ID | 12168 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
idates | +1.049 |
ependence | +1.037 |
los | +1.036 |
ogh | +1.030 |
yg | +0.967 |
Neg logit contributions | |
bilt | -1.460 |
hess | -1.261 |
NESS | -1.257 |
�� | -1.204 |
ewater | -1.189 |
Token | trees |
Token ID | 7150 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
bilt | +2.142 |
NESS | +1.809 |
hess | +1.790 |
ewater | +1.702 |
�� | +1.651 |
Neg logit contributions | |
ependence | -2.131 |
idates | -2.123 |
los | -2.106 |
ogh | -2.096 |
yg | -1.986 |
Token | have |
Token ID | 423 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
bilt | +1.795 |
NESS | +1.528 |
hess | +1.525 |
ewater | +1.435 |
�� | +1.411 |
Neg logit contributions | |
idates | -1.620 |
ependence | -1.614 |
los | -1.599 |
ogh | -1.588 |
yg | -1.508 |
Token | been |
Token ID | 587 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
idates | +0.569 |
ependence | +0.565 |
los | +0.565 |
ogh | +0.563 |
yg | +0.532 |
Neg logit contributions | |
bilt | -0.728 |
NESS | -0.630 |
hess | -0.623 |
ewater | -0.588 |
�� | -0.587 |
Token | ves |
Token ID | 1158 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ependence | +2.742 |
idates | +2.741 |
ogh | +2.741 |
los | +2.703 |
bu | +2.523 |
Neg logit contributions | |
bilt | -5.348 |
NESS | -4.752 |
hess | -4.626 |
�� | -4.470 |
ewater | -4.403 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
idates | +1.719 |
los | +1.703 |
ependence | +1.699 |
ogh | +1.685 |
yg | +1.599 |
Neg logit contributions | |
bilt | -2.215 |
NESS | -1.911 |
hess | -1.879 |
�� | -1.803 |
ewater | -1.770 |
Token | wetlands |
Token ID | 49297 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
idates | +1.916 |
los | +1.909 |
ogh | +1.906 |
ependence | +1.901 |
yg | +1.812 |
Neg logit contributions | |
bilt | -2.078 |
NESS | -1.764 |
hess | -1.755 |
�� | -1.657 |
ewater | -1.609 |
Token | at |
Token ID | 379 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
idates | +0.926 |
los | +0.918 |
ependence | +0.914 |
ogh | +0.907 |
yg | +0.857 |
Neg logit contributions | |
bilt | -1.196 |
NESS | -1.029 |
hess | -1.014 |
�� | -0.975 |
ewater | -0.958 |
Token | Kan |
Token ID | 14248 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
idates | +2.469 |
ependence | +2.443 |
ogh | +2.440 |
los | +2.431 |
yg | +2.304 |
Neg logit contributions | |
bilt | -2.371 |
NESS | -2.019 |
hess | -2.004 |
�� | -1.874 |
ewater | -1.827 |
Token | akia |
Token ID | 21897 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ependence | +2.504 |
idates | +2.482 |
ogh | +2.448 |
los | +2.439 |
bu | +2.251 |
Neg logit contributions | |
bilt | -5.248 |
NESS | -4.821 |
hess | -4.597 |
�� | -4.574 |
�� | -4.428 |
Token | Nag |
Token ID | 15196 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
ogh | +9.089 |
idates | +8.712 |
ependence | +8.699 |
bu | +8.485 |
los | +8.390 |
Neg logit contributions | |
bilt | -13.325 |
�� | -11.885 |
NESS | -11.756 |
hess | -11.333 |
�� | -10.658 |
Token | ar |
Token ID | 283 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
los | +2.626 |
ogh | +2.612 |
idates | +2.610 |
ependence | +2.448 |
bu | +2.431 |
Neg logit contributions | |
bilt | -6.835 |
NESS | -6.465 |
�� | -6.126 |
hess | -6.055 |
�� | -5.832 |
Token | in |
Token ID | 287 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
idates | +2.650 |
ogh | +2.608 |
ependence | +2.595 |
los | +2.593 |
bu | +2.433 |
Neg logit contributions | |
bilt | -3.558 |
NESS | -3.120 |
hess | -3.016 |
�� | -2.938 |
ewater | -2.826 |
Token | Mir |
Token ID | 7381 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
idates | +3.036 |
ependence | +3.021 |
ogh | +2.966 |
los | +2.934 |
yg | +2.811 |
Neg logit contributions | |
bilt | -3.710 |
NESS | -3.242 |
hess | -3.170 |
�� | -3.074 |
ewater | -3.008 |
Token | a |
Token ID | 64 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
idates | +1.168 |
los | +1.150 |
ogh | +1.150 |
ependence | +1.148 |
yg | +1.067 |
Neg logit contributions | |
bilt | -1.818 |
NESS | -1.601 |
hess | -1.591 |
�� | -1.513 |
ewater | -1.510 |
Token | play |
Token ID | 711 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
bilt | +0.664 |
NESS | +0.565 |
hess | +0.563 |
ewater | +0.531 |
�� | +0.526 |
Neg logit contributions | |
idates | -0.600 |
ependence | -0.599 |
los | -0.595 |
ogh | -0.592 |
yg | -0.561 |
Token | with |
Token ID | 351 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
bilt | +2.393 |
NESS | +2.034 |
hess | +2.025 |
ewater | +1.898 |
�� | +1.866 |
Neg logit contributions | |
idates | -2.192 |
ependence | -2.183 |
los | -2.176 |
ogh | -2.155 |
yg | -2.056 |
Token | Blake |
Token ID | 13307 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
idates | +0.919 |
ependence | +0.917 |
los | +0.913 |
ogh | +0.905 |
yg | +0.856 |
Neg logit contributions | |
bilt | -1.051 |
NESS | -0.890 |
hess | -0.887 |
ewater | -0.844 |
�� | -0.831 |
Token | Wheeler |
Token ID | 27512 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
idates | +0.204 |
ependence | +0.203 |
los | +0.203 |
ogh | +0.200 |
yg | +0.188 |
Neg logit contributions | |
bilt | -0.304 |
NESS | -0.266 |
hess | -0.265 |
ewater | -0.251 |
�� | -0.249 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
bilt | +1.580 |
NESS | +1.354 |
hess | +1.343 |
ewater | +1.267 |
�� | +1.253 |
Neg logit contributions | |
idates | -1.368 |
ependence | -1.361 |
los | -1.354 |
ogh | -1.346 |
yg | -1.276 |
Token | Mark |
Token ID | 2940 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
idates | +2.197 |
los | +2.177 |
ependence | +2.175 |
ogh | +2.160 |
yg | +2.048 |
Neg logit contributions | |
bilt | -2.304 |
hess | -1.964 |
NESS | -1.943 |
ewater | -1.848 |
�� | -1.835 |
Token | Sche |
Token ID | 10011 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
los | +6.114 |
ogh | +5.634 |
ependence | +5.535 |
idates | +5.209 |
yg | +5.147 |
Neg logit contributions | |
bilt | -15.227 |
NESS | -14.449 |
�� | -13.804 |
hess | -13.800 |
ewater | -13.389 |
Token | ife |
Token ID | 901 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
bilt | +2.207 |
hess | +1.919 |
NESS | +1.918 |
ewater | +1.820 |
�� | +1.802 |
Neg logit contributions | |
idates | -1.411 |
ependence | -1.407 |
los | -1.398 |
ogh | -1.389 |
yg | -1.301 |
Token | le |
Token ID | 293 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
bilt | +1.716 |
NESS | +1.553 |
hess | +1.543 |
ewater | +1.489 |
�� | +1.484 |
Neg logit contributions | |
idates | -0.424 |
ependence | -0.421 |
los | -0.419 |
ogh | -0.409 |
yg | -0.359 |
Token | has |
Token ID | 468 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bilt | +2.624 |
NESS | +2.240 |
hess | +2.227 |
ewater | +2.098 |
�� | +2.066 |
Neg logit contributions | |
idates | -2.325 |
ependence | -2.315 |
los | -2.307 |
ogh | -2.289 |
yg | -2.176 |
Token | been |
Token ID | 587 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
bilt | +1.454 |
NESS | +1.246 |
hess | +1.239 |
ewater | +1.168 |
�� | +1.155 |
Neg logit contributions | |
idates | -1.246 |
ependence | -1.243 |
los | -1.236 |
ogh | -1.228 |
yg | -1.162 |
Token | run |
Token ID | 5143 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
los | +1.716 |
ependence | +1.713 |
ogh | +1.696 |
idates | +1.675 |
yg | +1.559 |
Neg logit contributions | |
bilt | -3.178 |
NESS | -2.817 |
hess | -2.771 |
�� | -2.686 |
ewater | -2.623 |
Token | on |
Token ID | 319 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
ependence | +2.832 |
idates | +2.802 |
los | +2.801 |
ogh | +2.800 |
)+ | +2.621 |
Neg logit contributions | |
bilt | -3.675 |
NESS | -3.174 |
hess | -3.153 |
�� | -3.039 |
ewater | -2.974 |
Token | their |
Token ID | 511 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
bilt | +0.907 |
NESS | +0.776 |
hess | +0.771 |
ewater | +0.727 |
�� | +0.719 |
Neg logit contributions | |
idates | -0.792 |
ependence | -0.790 |
los | -0.786 |
ogh | -0.781 |
yg | -0.740 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
bilt | +2.946 |
NESS | +2.498 |
hess | +2.474 |
ewater | +2.330 |
�� | +2.293 |
Neg logit contributions | |
idates | -2.960 |
ependence | -2.945 |
los | -2.919 |
ogh | -2.909 |
yg | -2.762 |
Token | page |
Token ID | 2443 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ependence | +1.755 |
los | +1.743 |
idates | +1.741 |
ogh | +1.720 |
yg | +1.656 |
Neg logit contributions | |
bilt | -1.374 |
hess | -1.117 |
NESS | -1.116 |
ewater | -1.038 |
�� | -1.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
los | +5.382 |
ependence | +5.309 |
idates | +5.276 |
ogh | +5.200 |
)+ | +4.977 |
Neg logit contributions | |
bilt | -7.668 |
NESS | -6.563 |
hess | -6.555 |
�� | -6.212 |
ewater | -6.164 |
Token | 12 |
Token ID | 1065 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
los | +8.751 |
idates | +8.747 |
yg | +8.330 |
ependence | +8.323 |
ogh | +8.276 |
Neg logit contributions | |
bilt | -11.873 |
hess | -10.568 |
NESS | -10.092 |
�� | -9.832 |
ewater | -9.620 |
Token | .- |
Token ID | 7874 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ependence | +3.132 |
idates | +3.132 |
los | +3.090 |
ogh | +3.071 |
yg | +2.849 |
Neg logit contributions | |
bilt | -6.036 |
NESS | -5.373 |
hess | -5.306 |
ewater | -5.094 |
�� | -5.059 |
Token | All |
Token ID | 1439 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
los | +3.160 |
ogh | +3.159 |
idates | +3.141 |
ependence | +3.130 |
yg | +2.973 |
Neg logit contributions | |
bilt | -3.635 |
hess | -3.150 |
NESS | -3.149 |
ewater | -2.913 |
�� | -2.860 |
Token | stages |
Token ID | 9539 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
los | +4.007 |
ependence | +3.974 |
idates | +3.970 |
ogh | +3.957 |
yg | +3.757 |
Neg logit contributions | |
bilt | -4.644 |
hess | -3.958 |
NESS | -3.954 |
�� | -3.744 |
ewater | -3.713 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
idates | +2.039 |
ependence | +2.033 |
los | +2.028 |
ogh | +2.017 |
yg | +1.893 |
Neg logit contributions | |
bilt | -2.507 |
hess | -2.174 |
NESS | -2.171 |
ewater | -2.033 |
�� | -2.016 |
Token | = |
Token ID | 28 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
bilt | +2.249 |
NESS | +1.897 |
hess | +1.885 |
ewater | +1.762 |
�� | +1.712 |
Neg logit contributions | |
idates | -2.411 |
ependence | -2.404 |
los | -2.382 |
ogh | -2.376 |
yg | -2.257 |
Token | c |
Token ID | 66 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
idates | +3.849 |
los | +3.843 |
ependence | +3.817 |
ogh | +3.807 |
yg | +3.679 |
Neg logit contributions | |
bilt | -4.705 |
NESS | -4.035 |
hess | -4.011 |
�� | -3.988 |
ewater | -3.846 |
Token | \ |
Token ID | 59 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
idates | +0.199 |
ependence | +0.198 |
los | +0.196 |
ogh | +0.195 |
yg | +0.183 |
Neg logit contributions | |
bilt | -0.329 |
NESS | -0.288 |
hess | -0.286 |
ewater | -0.273 |
�� | -0.272 |
Token | :\ |
Token ID | 7479 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
los | +2.885 |
idates | +2.870 |
ependence | +2.847 |
ogh | +2.837 |
yg | +2.754 |
Neg logit contributions | |
bilt | -3.722 |
NESS | -3.222 |
hess | -3.183 |
�� | -3.078 |
ewater | -3.030 |
Token | tmp |
Token ID | 22065 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
los | +5.939 |
idates | +5.862 |
ependence | +5.842 |
ogh | +5.765 |
sung | +5.653 |
Neg logit contributions | |
bilt | -7.700 |
NESS | -6.618 |
hess | -6.608 |
�� | -6.409 |
ewater | -6.265 |
Token | : |
Token ID | 25 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ependence | +3.003 |
los | +3.003 |
idates | +2.992 |
ogh | +2.927 |
yg | +2.819 |
Neg logit contributions | |
bilt | -4.828 |
NESS | -4.216 |
hess | -4.192 |
�� | -4.033 |
ewater | -3.989 |
Token | */ |
Token ID | 9466 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
los | +8.521 |
idates | +8.517 |
ependence | +8.467 |
yg | +8.422 |
bu | +8.252 |
Neg logit contributions | |
bilt | -11.801 |
hess | -10.211 |
NESS | -10.127 |
�� | -10.100 |
ewater | -9.780 |
Token | This |
Token ID | 770 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
idates | +4.253 |
ependence | +4.206 |
ogh | +4.170 |
los | +4.142 |
yg | +4.004 |
Neg logit contributions | |
bilt | -6.403 |
hess | -5.485 |
NESS | -5.485 |
�� | -5.453 |
ewater | -5.189 |
Token | sets |
Token ID | 5621 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
idates | +5.240 |
ogh | +5.195 |
ependence | +5.140 |
los | +5.093 |
yg | +4.976 |
Neg logit contributions | |
bilt | -7.816 |
�� | -6.731 |
hess | -6.585 |
NESS | -6.577 |
�� | -6.302 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
idates | +2.946 |
ependence | +2.905 |
ogh | +2.878 |
los | +2.857 |
yg | +2.730 |
Neg logit contributions | |
bilt | -3.878 |
hess | -3.346 |
NESS | -3.323 |
�� | -3.177 |
ewater | -3.157 |
Token | ' |
Token ID | 705 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
idates | +2.805 |
ependence | +2.769 |
los | +2.746 |
ogh | +2.730 |
yg | +2.632 |
Neg logit contributions | |
bilt | -3.672 |
hess | -3.158 |
NESS | -3.117 |
�� | -3.005 |
ewater | -2.987 |
Token | with |
Token ID | 351 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Goldman | +4.737 |
ependence | +4.651 |
idates | +4.580 |
ogh | +4.496 |
los | +4.414 |
Neg logit contributions | |
bilt | -10.459 |
hess | -9.092 |
NESS | -8.921 |
ewater | -8.587 |
�� | -8.576 |
Token | ' |
Token ID | 705 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ependence | +1.546 |
los | +1.539 |
ogh | +1.528 |
idates | +1.526 |
yg | +1.442 |
Neg logit contributions | |
bilt | -1.935 |
hess | -1.618 |
NESS | -1.607 |
ewater | -1.512 |
�� | -1.508 |
Token | 44 |
Token ID | 2598 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
ependence | +1.623 |
los | +1.618 |
ogh | +1.591 |
idates | +1.530 |
yg | +1.523 |
Neg logit contributions | |
bilt | -2.172 |
hess | -1.818 |
NESS | -1.810 |
�� | -1.728 |
ewater | -1.704 |
Token | ' |
Token ID | 6 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
bilt | +0.489 |
hess | +0.413 |
NESS | +0.412 |
ewater | +0.387 |
�� | +0.382 |
Neg logit contributions | |
ependence | -0.492 |
idates | -0.490 |
los | -0.487 |
ogh | -0.484 |
yg | -0.462 |
Token | on |
Token ID | 319 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ependence | +2.397 |
idates | +2.395 |
los | +2.381 |
ogh | +2.367 |
yg | +2.231 |
Neg logit contributions | |
bilt | -3.402 |
NESS | -2.932 |
hess | -2.927 |
ewater | -2.775 |
�� | -2.739 |
Token | sleeve |
Token ID | 23179 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ependence | +2.261 |
ogh | +2.243 |
los | +2.227 |
idates | +2.219 |
yg | +2.121 |
Neg logit contributions | |
bilt | -3.097 |
hess | -2.645 |
NESS | -2.598 |
ewater | -2.515 |
�� | -2.435 |
Token | at |
Token ID | 379 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Goldman | +7.482 |
idates | +7.023 |
ogh | +6.972 |
)+ | +6.927 |
bu | +6.800 |
Neg logit contributions | |
bilt | -14.466 |
NESS | -12.130 |
hess | -11.966 |
ewater | -11.700 |
�� | -11.547 |
Token | basketball |
Token ID | 9669 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ependence | +1.685 |
ogh | +1.624 |
idates | +1.569 |
Goldman | +1.490 |
los | +1.486 |
Neg logit contributions | |
bilt | -3.520 |
NESS | -3.105 |
hess | -3.104 |
�� | -2.959 |
�� | -2.852 |
Token | game |
Token ID | 983 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
idates | +1.735 |
ependence | +1.733 |
ogh | +1.702 |
los | +1.695 |
yg | +1.656 |
Neg logit contributions | |
bilt | -2.117 |
NESS | -1.779 |
hess | -1.748 |
ewater | -1.695 |
�� | -1.685 |
Token | MORE |
Token ID | 12011 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
idates | +3.945 |
ependence | +3.916 |
los | +3.915 |
ogh | +3.854 |
yg | +3.695 |
Neg logit contributions | |
bilt | -4.997 |
hess | -4.273 |
NESS | -4.263 |
ewater | -4.082 |
�� | -4.064 |
Token | and |
Token ID | 290 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ependence | +1.579 |
idates | +1.569 |
los | +1.563 |
ogh | +1.554 |
yg | +1.461 |
Neg logit contributions | |
bilt | -2.142 |
NESS | -1.858 |
hess | -1.853 |
�� | -1.747 |
ewater | -1.735 |
Token | \ |
Token ID | 59 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
ogh | +5.132 |
idates | +5.081 |
los | +5.079 |
ependence | +5.022 |
)+ | +5.017 |
Neg logit contributions | |
bilt | -7.057 |
NESS | -6.165 |
hess | -6.103 |
ewater | -5.780 |
�� | -5.768 |
Token | s |
Token ID | 82 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
bilt | +0.365 |
NESS | +0.306 |
hess | +0.304 |
ewater | +0.284 |
�� | +0.280 |
Neg logit contributions | |
ependence | -0.390 |
idates | -0.389 |
los | -0.386 |
ogh | -0.385 |
yg | -0.365 |
Token | + |
Token ID | 10 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
idates | +3.073 |
los | +3.036 |
ependence | +3.010 |
ogh | +2.986 |
)+ | +2.917 |
Neg logit contributions | |
bilt | -6.148 |
hess | -5.449 |
NESS | -5.443 |
ewater | -5.211 |
�� | -5.154 |
Token | "( |
Token ID | 18109 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
idates | +3.610 |
ogh | +3.589 |
los | +3.587 |
ependence | +3.572 |
yg | +3.421 |
Neg logit contributions | |
bilt | -4.055 |
NESS | -3.451 |
hess | -3.435 |
�� | -3.244 |
ewater | -3.228 |
Token | \ |
Token ID | 59 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ogh | +4.470 |
idates | +4.448 |
los | +4.448 |
ependence | +4.433 |
)+ | +4.348 |
Neg logit contributions | |
bilt | -7.011 |
hess | -6.063 |
NESS | -6.027 |
�� | -5.839 |
ewater | -5.804 |
Token | S |
Token ID | 50 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
idates | +2.754 |
los | +2.736 |
ogh | +2.719 |
ependence | +2.712 |
)+ | +2.596 |
Neg logit contributions | |
bilt | -3.011 |
hess | -2.551 |
NESS | -2.550 |
ewater | -2.409 |
�� | -2.401 |
Token | +) |
Token ID | 28988 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
)+ | +6.593 |
idates | +6.148 |
los | +5.968 |
ogh | +5.955 |
ependence | +5.884 |
Neg logit contributions | |
bilt | -13.711 |
hess | -12.314 |
NESS | -12.249 |
ewater | -11.734 |
�� | -11.696 |
Token | "] |
Token ID | 8973 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
idates | +4.397 |
ogh | +4.396 |
los | +4.348 |
ependence | +4.341 |
yg | +4.200 |
Neg logit contributions | |
bilt | -4.467 |
NESS | -3.748 |
hess | -3.711 |
�� | -3.563 |
ewater | -3.491 |
Token | ' |
Token ID | 6 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
idates | +2.905 |
ependence | +2.899 |
los | +2.892 |
ogh | +2.886 |
yg | +2.740 |
Neg logit contributions | |
bilt | -2.687 |
NESS | -2.241 |
hess | -2.229 |
ewater | -2.093 |
�� | -2.085 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
bilt | +3.463 |
NESS | +2.979 |
hess | +2.927 |
ewater | +2.703 |
�� | +2.650 |
Neg logit contributions | |
idates | -4.060 |
ependence | -4.040 |
ogh | -4.034 |
los | -4.011 |
yg | -3.861 |
Token | AS |
Token ID | 7054 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
idates | +0.983 |
ependence | +0.971 |
los | +0.967 |
ogh | +0.964 |
)+ | +0.895 |
Neg logit contributions | |
bilt | -1.471 |
hess | -1.271 |
NESS | -1.271 |
ewater | -1.220 |
�� | -1.203 |
Token | ( |
Token ID | 7 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
los | +1.366 |
idates | +1.357 |
ependence | +1.349 |
ogh | +1.334 |
bu | +1.280 |
Neg logit contributions | |
bilt | -1.641 |
NESS | -1.384 |
hess | -1.374 |
�� | -1.366 |
ewater | -1.321 |
Token | 0 |
Token ID | 15 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
bilt | +1.877 |
NESS | +1.600 |
hess | +1.597 |
ewater | +1.490 |
�� | +1.456 |
Neg logit contributions | |
ependence | -1.725 |
idates | -1.720 |
ogh | -1.699 |
los | -1.696 |
ochond | -1.604 |
Token | s |
Token ID | 82 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
bilt | +2.539 |
NESS | +2.105 |
hess | +2.100 |
ewater | +1.943 |
�� | +1.875 |
Neg logit contributions | |
ependence | -3.209 |
idates | -3.198 |
ogh | -3.164 |
los | -3.158 |
ochond | -3.015 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
)+ | +1.486 |
los | +1.405 |
idates | +1.326 |
ependence | +1.246 |
ogh | +1.222 |
Neg logit contributions | |
bilt | -10.367 |
NESS | -9.486 |
hess | -9.338 |
�� | -9.313 |
�� | -9.127 |
Token | c |
Token ID | 269 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ogh | +4.597 |
idates | +4.535 |
los | +4.528 |
ependence | +4.427 |
yg | +4.411 |
Neg logit contributions | |
bilt | -7.363 |
NESS | -6.166 |
�� | -6.048 |
hess | -5.983 |
ewater | -5.922 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
bilt | +2.866 |
hess | +2.509 |
NESS | +2.483 |
ewater | +2.349 |
�� | +2.290 |
Neg logit contributions | |
idates | -2.170 |
ependence | -2.169 |
los | -2.144 |
ogh | -2.131 |
yg | -2.007 |
Token | { |
Token ID | 1391 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
los | +7.631 |
ependence | +7.432 |
ogh | +7.380 |
idates | +7.377 |
yg | +7.222 |
Neg logit contributions | |
bilt | -12.629 |
NESS | -11.084 |
hess | -10.629 |
ewater | -10.608 |
�� | -10.168 |
Token | ( |
Token ID | 7 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
los | +1.714 |
idates | +1.697 |
ependence | +1.686 |
ogh | +1.665 |
bu | +1.608 |
Neg logit contributions | |
bilt | -2.105 |
NESS | -1.770 |
�� | -1.767 |
hess | -1.766 |
ewater | -1.696 |
Token | 60 |
Token ID | 1899 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
bilt | +1.649 |
NESS | +1.407 |
hess | +1.403 |
ewater | +1.307 |
�� | +1.278 |
Neg logit contributions | |
ependence | -1.531 |
idates | -1.524 |
ogh | -1.507 |
los | -1.502 |
ochond | -1.423 |
Token | s |
Token ID | 82 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
los | +1.182 |
idates | +1.181 |
ogh | +1.172 |
ependence | +1.158 |
)+ | +1.115 |
Neg logit contributions | |
bilt | -1.163 |
NESS | -0.978 |
hess | -0.961 |
�� | -0.931 |
ewater | -0.913 |
Token | )} |
Token ID | 38165 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
)+ | +1.762 |
los | +1.709 |
idates | +1.571 |
ogh | +1.479 |
ependence | +1.475 |
Neg logit contributions | |
bilt | -11.115 |
NESS | -10.142 |
�� | -9.997 |
hess | -9.986 |
�� | -9.746 |
Token | vim |
Token ID | 31124 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
bilt | +1.005 |
NESS | +0.864 |
hess | +0.859 |
ewater | +0.812 |
�� | +0.798 |
Neg logit contributions | |
idates | -0.828 |
ependence | -0.828 |
los | -0.821 |
ogh | -0.819 |
yg | -0.770 |
Token | : |
Token ID | 25 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
bilt | +0.215 |
NESS | +0.187 |
hess | +0.185 |
ewater | +0.176 |
�� | +0.175 |
Neg logit contributions | |
idates | -0.155 |
ependence | -0.154 |
los | -0.153 |
ogh | -0.151 |
yg | -0.143 |
Token | * |
Token ID | 9 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
idates | +2.639 |
ependence | +2.601 |
los | +2.595 |
ogh | +2.563 |
yg | +2.475 |
Neg logit contributions | |
bilt | -3.370 |
NESS | -2.902 |
hess | -2.882 |
�� | -2.778 |
ewater | -2.728 |
Token | * |
Token ID | 1635 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
idates | +0.468 |
ependence | +0.465 |
los | +0.462 |
ogh | +0.459 |
yg | +0.437 |
Neg logit contributions | |
bilt | -0.571 |
NESS | -0.491 |
hess | -0.488 |
ewater | -0.461 |
�� | -0.460 |
Token | vi |
Token ID | 8903 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
idates | +0.275 |
ependence | +0.273 |
los | +0.272 |
ogh | +0.270 |
yg | +0.256 |
Neg logit contributions | |
bilt | -0.349 |
NESS | -0.300 |
hess | -0.298 |
ewater | -0.283 |
�� | -0.281 |
Token | : |
Token ID | 25 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
idates | +0.250 |
ependence | +0.249 |
los | +0.248 |
ogh | +0.246 |
yg | +0.232 |
Neg logit contributions | |
bilt | -0.347 |
NESS | -0.301 |
hess | -0.299 |
ewater | -0.284 |
�� | -0.281 |
Token | * |
Token ID | 9 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
idates | +6.791 |
ependence | +6.557 |
ogh | +6.533 |
los | +6.428 |
yg | +6.314 |
Neg logit contributions | |
bilt | -12.812 |
hess | -11.257 |
NESS | -11.164 |
�� | -11.136 |
ewater | -11.024 |
Token | * |
Token ID | 1635 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
idates | +3.518 |
ependence | +3.468 |
los | +3.434 |
ogh | +3.417 |
yg | +3.298 |
Neg logit contributions | |
bilt | -4.835 |
hess | -4.162 |
NESS | -4.159 |
�� | -3.980 |
ewater | -3.942 |
Token | ex |
Token ID | 1069 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
bilt | +0.786 |
NESS | +0.680 |
hess | +0.676 |
ewater | +0.641 |
�� | +0.634 |
Neg logit contributions | |
idates | -0.582 |
ependence | -0.580 |
los | -0.576 |
ogh | -0.573 |
yg | -0.539 |
Token | : |
Token ID | 25 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
bilt | +3.064 |
hess | +2.662 |
NESS | +2.657 |
ewater | +2.511 |
�� | +2.463 |
Neg logit contributions | |
ependence | -2.253 |
idates | -2.241 |
los | -2.229 |
ogh | -2.222 |
ochond | -2.085 |
Token | * |
Token ID | 9 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
idates | +6.817 |
ogh | +6.658 |
los | +6.590 |
ependence | +6.542 |
yg | +6.365 |
Neg logit contributions | |
bilt | -11.346 |
hess | -9.915 |
NESS | -9.863 |
�� | -9.838 |
ewater | -9.689 |
Token | the |
Token ID | 262 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
bilt | +0.417 |
NESS | +0.358 |
hess | +0.358 |
ewater | +0.338 |
�� | +0.335 |
Neg logit contributions | |
idates | -0.350 |
ependence | -0.348 |
ogh | -0.346 |
los | -0.346 |
yg | -0.326 |
Token | National |
Token ID | 2351 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
bilt | +2.500 |
NESS | +2.150 |
hess | +2.126 |
ewater | +2.014 |
�� | +1.985 |
Neg logit contributions | |
idates | -2.081 |
ependence | -2.079 |
los | -2.063 |
ogh | -2.048 |
yg | -1.937 |
Token | Sample |
Token ID | 27565 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
bilt | +0.033 |
hess | +0.029 |
NESS | +0.028 |
�� | +0.027 |
ewater | +0.027 |
Neg logit contributions | |
idates | -0.024 |
los | -0.024 |
ogh | -0.024 |
ependence | -0.024 |
yg | -0.023 |
Token | Survey |
Token ID | 13084 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
bilt | +3.129 |
NESS | +2.468 |
hess | +2.468 |
ewater | +2.284 |
�� | +2.139 |
Neg logit contributions | |
idates | -5.150 |
ependence | -5.119 |
los | -5.089 |
ogh | -5.039 |
yg | -4.901 |
Token | Organisation |
Token ID | 30801 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
bilt | +2.632 |
NESS | +2.255 |
hess | +2.247 |
ewater | +2.121 |
�� | +2.085 |
Neg logit contributions | |
idates | -2.254 |
ependence | -2.248 |
los | -2.232 |
ogh | -2.208 |
yg | -2.109 |
Token | ( |
Token ID | 357 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
bilt | +0.433 |
NESS | +0.374 |
hess | +0.372 |
ewater | +0.352 |
�� | +0.349 |
Neg logit contributions | |
idates | -0.333 |
ependence | -0.332 |
los | -0.330 |
ogh | -0.328 |
yg | -0.309 |
Token | N |
Token ID | 45 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
NP | +7.723 |
idates | +7.551 |
los | +7.464 |
ogh | +7.202 |
ependence | +7.191 |
Neg logit contributions | |
bilt | -12.039 |
hess | -10.307 |
�� | -9.847 |
�� | -9.709 |
ewater | -9.615 |
Token | SS |
Token ID | 5432 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
los | +2.540 |
idates | +2.489 |
ependence | +2.474 |
ogh | +2.424 |
sung | +2.387 |
Neg logit contributions | |
bilt | -7.255 |
NESS | -6.316 |
hess | -6.249 |
�� | -6.137 |
�� | -6.043 |
Token | O |
Token ID | 46 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
bilt | +2.272 |
NESS | +1.935 |
hess | +1.883 |
ewater | +1.770 |
�� | +1.738 |
Neg logit contributions | |
idates | -2.857 |
ependence | -2.809 |
los | -2.801 |
ogh | -2.779 |
yg | -2.696 |
Token | ) |
Token ID | 8 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
bilt | +0.412 |
NESS | +0.353 |
hess | +0.351 |
ewater | +0.332 |
�� | +0.328 |
Neg logit contributions | |
idates | -0.353 |
ependence | -0.351 |
los | -0.349 |
ogh | -0.347 |
yg | -0.329 |
Token | for |
Token ID | 329 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
bilt | +4.649 |
NESS | +3.963 |
hess | +3.917 |
ewater | +3.700 |
�� | +3.638 |
Neg logit contributions | |
idates | -4.391 |
ependence | -4.385 |
los | -4.355 |
ogh | -4.310 |
ochond | -4.111 |
Token | hitting |
Token ID | 9008 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
los | +0.534 |
idates | +0.533 |
ogh | +0.530 |
ependence | +0.530 |
yg | +0.501 |
Neg logit contributions | |
bilt | -0.664 |
NESS | -0.570 |
hess | -0.567 |
ewater | -0.538 |
�� | -0.537 |
Token | all |
Token ID | 477 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
bilt | +0.316 |
NESS | +0.271 |
hess | +0.270 |
ewater | +0.254 |
�� | +0.253 |
Neg logit contributions | |
idates | -0.269 |
ependence | -0.268 |
los | -0.268 |
ogh | -0.266 |
yg | -0.252 |
Token | Target |
Token ID | 12744 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
bilt | +1.310 |
NESS | +1.118 |
hess | +1.111 |
ewater | +1.048 |
�� | +1.037 |
Neg logit contributions | |
idates | -1.128 |
ependence | -1.125 |
los | -1.117 |
ogh | -1.111 |
yg | -1.052 |
Token | stores |
Token ID | 7000 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
idates | +0.209 |
ependence | +0.208 |
los | +0.207 |
ogh | +0.205 |
yg | +0.196 |
Neg logit contributions | |
bilt | -0.172 |
NESS | -0.142 |
hess | -0.142 |
ewater | -0.132 |
�� | -0.131 |
Token | up |
Token ID | 510 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
bilt | +2.079 |
NESS | +1.789 |
hess | +1.778 |
ewater | +1.677 |
�� | +1.657 |
Neg logit contributions | |
idates | -1.708 |
ependence | -1.702 |
los | -1.691 |
ogh | -1.679 |
yg | -1.592 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
los | +4.737 |
ependence | +4.655 |
ogh | +4.629 |
idates | +4.548 |
bu | +4.349 |
Neg logit contributions | |
bilt | -6.560 |
NESS | -5.829 |
hess | -5.716 |
�� | -5.496 |
ewater | -5.432 |
Token | down |
Token ID | 866 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ependence | +6.380 |
ogh | +6.309 |
los | +6.222 |
idates | +6.109 |
yg | +6.008 |
Neg logit contributions | |
bilt | -12.416 |
NESS | -11.529 |
hess | -11.394 |
�� | -10.842 |
ewater | -10.715 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
los | +3.557 |
ependence | +3.516 |
ogh | +3.494 |
idates | +3.479 |
ochond | +3.226 |
Neg logit contributions | |
bilt | -4.761 |
NESS | -4.151 |
hess | -4.133 |
ewater | -3.889 |
�� | -3.870 |
Token | eastern |
Token ID | 10183 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
los | +2.753 |
idates | +2.736 |
ogh | +2.689 |
ependence | +2.678 |
yg | +2.509 |
Neg logit contributions | |
bilt | -3.783 |
hess | -3.307 |
NESS | -3.293 |
�� | -3.128 |
ewater | -3.121 |
Token | se |
Token ID | 384 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
los | +1.421 |
idates | +1.409 |
ogh | +1.409 |
ependence | +1.407 |
yg | +1.328 |
Neg logit contributions | |
bilt | -1.658 |
NESS | -1.414 |
hess | -1.407 |
ewater | -1.331 |
�� | -1.328 |
Token | ab |
Token ID | 397 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
bilt | +1.018 |
NESS | +0.834 |
hess | +0.817 |
�� | +0.763 |
ewater | +0.755 |
Neg logit contributions | |
idates | -1.326 |
los | -1.324 |
ependence | -1.323 |
ogh | -1.313 |
yg | -1.257 |
Token | on |
Token ID | 319 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
bilt | +0.774 |
NESS | +0.669 |
hess | +0.665 |
ewater | +0.628 |
�� | +0.625 |
Neg logit contributions | |
idates | -0.571 |
ependence | -0.568 |
los | -0.567 |
ogh | -0.563 |
yg | -0.530 |
Token | the |
Token ID | 262 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
bilt | +0.510 |
NESS | +0.440 |
hess | +0.438 |
ewater | +0.414 |
�� | +0.411 |
Neg logit contributions | |
idates | -0.391 |
ependence | -0.389 |
los | -0.387 |
ogh | -0.385 |
yg | -0.363 |
Token | conflicts |
Token ID | 12333 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
bilt | +2.981 |
NESS | +2.568 |
hess | +2.532 |
ewater | +2.435 |
�� | +2.372 |
Neg logit contributions | |
ependence | -2.299 |
idates | -2.297 |
los | -2.287 |
ogh | -2.269 |
yg | -2.146 |
Token | in |
Token ID | 287 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
bilt | +0.989 |
NESS | +0.850 |
hess | +0.844 |
ewater | +0.798 |
�� | +0.791 |
Neg logit contributions | |
idates | -0.819 |
ependence | -0.816 |
los | -0.812 |
ogh | -0.806 |
yg | -0.762 |
Token | Iraq |
Token ID | 3908 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
idates | +1.859 |
ogh | +1.854 |
ependence | +1.834 |
los | +1.825 |
yg | +1.692 |
Neg logit contributions | |
bilt | -3.402 |
NESS | -3.006 |
hess | -2.996 |
�� | -2.864 |
ewater | -2.811 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
idates | +2.134 |
ependence | +2.128 |
los | +2.120 |
ogh | +2.107 |
yg | +1.986 |
Neg logit contributions | |
bilt | -2.552 |
NESS | -2.183 |
hess | -2.166 |
ewater | -2.041 |
�� | -2.028 |
Token | Afghanistan |
Token ID | 8037 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
idates | +5.551 |
los | +5.361 |
ependence | +5.274 |
ogh | +5.123 |
bu | +4.916 |
Neg logit contributions | |
bilt | -14.207 |
NESS | -12.554 |
�� | -12.466 |
hess | -12.464 |
�� | -11.740 |
Token | . |
Token ID | 13 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
idates | +0.122 |
ependence | +0.121 |
los | +0.121 |
ogh | +0.120 |
yg | +0.113 |
Neg logit contributions | |
bilt | -0.153 |
NESS | -0.132 |
hess | -0.130 |
ewater | -0.123 |
�� | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ependence | +0.393 |
idates | +0.393 |
los | +0.390 |
ogh | +0.389 |
yg | +0.371 |
Neg logit contributions | |
bilt | -0.373 |
NESS | -0.313 |
hess | -0.312 |
ewater | -0.295 |
�� | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
los | +2.136 |
idates | +2.079 |
ependence | +2.074 |
ogh | +2.071 |
bu | +1.982 |
Neg logit contributions | |
bilt | -2.868 |
�� | -2.488 |
NESS | -2.453 |
hess | -2.433 |
�� | -2.379 |
Token | Ass |
Token ID | 8021 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
los | +1.199 |
idates | +1.196 |
ependence | +1.183 |
ogh | +1.179 |
yg | +1.118 |
Neg logit contributions | |
bilt | -1.499 |
NESS | -1.275 |
hess | -1.270 |
�� | -1.228 |
ewater | -1.208 |
Token | Hart |
Token ID | 11345 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
idates | +0.445 |
ependence | +0.444 |
los | +0.440 |
ogh | +0.439 |
yg | +0.414 |
Neg logit contributions | |
bilt | -0.540 |
NESS | -0.465 |
hess | -0.462 |
ewater | -0.436 |
�� | -0.433 |
Token | z |
Token ID | 89 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ependence | +2.969 |
ogh | +2.953 |
los | +2.943 |
idates | +2.903 |
yg | +2.779 |
Neg logit contributions | |
bilt | -3.543 |
NESS | -3.104 |
hess | -3.038 |
�� | -3.006 |
ewater | -2.803 |
Token | ell |
Token ID | 695 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
los | +3.482 |
ependence | +3.479 |
ogh | +3.401 |
idates | +3.388 |
yg | +3.199 |
Neg logit contributions | |
bilt | -4.215 |
NESS | -3.700 |
hess | -3.544 |
�� | -3.443 |
ewater | -3.335 |
Token | House |
Token ID | 2097 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
ependence | +1.209 |
idates | +1.203 |
los | +1.197 |
ogh | +1.193 |
yg | +1.119 |
Neg logit contributions | |
bilt | -1.586 |
NESS | -1.379 |
hess | -1.362 |
�� | -1.298 |
ewater | -1.292 |
Token | Bed |
Token ID | 15585 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
idates | +0.603 |
ependence | +0.602 |
los | +0.600 |
ogh | +0.596 |
yg | +0.560 |
Neg logit contributions | |
bilt | -0.759 |
NESS | -0.657 |
hess | -0.653 |
ewater | -0.618 |
�� | -0.615 |
Token | & |
Token ID | 1222 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
bilt | +2.204 |
NESS | +1.887 |
hess | +1.875 |
ewater | +1.789 |
�� | +1.742 |
Neg logit contributions | |
idates | -1.817 |
ependence | -1.802 |
los | -1.781 |
ogh | -1.774 |
yg | -1.675 |
Token | Breakfast |
Token ID | 32175 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
idates | +6.224 |
ependence | +6.036 |
yg | +6.019 |
ogh | +5.936 |
los | +5.915 |
Neg logit contributions | |
bilt | -13.218 |
hess | -12.074 |
NESS | -11.716 |
�� | -11.010 |
ewater | -10.948 |
Token | in |
Token ID | 287 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
idates | +0.338 |
ependence | +0.337 |
los | +0.335 |
ogh | +0.333 |
yg | +0.314 |
Neg logit contributions | |
bilt | -0.425 |
NESS | -0.364 |
hess | -0.364 |
ewater | -0.344 |
�� | -0.341 |
Token | Add |
Token ID | 3060 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
bilt | +0.934 |
NESS | +0.801 |
hess | +0.796 |
ewater | +0.753 |
�� | +0.743 |
Neg logit contributions | |
idates | -0.774 |
ependence | -0.771 |
los | -0.766 |
ogh | -0.762 |
yg | -0.720 |
Token | ision |
Token ID | 1166 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
ependence | +0.621 |
idates | +0.619 |
los | +0.618 |
ogh | +0.612 |
yg | +0.589 |
Neg logit contributions | |
bilt | -0.468 |
NESS | -0.387 |
hess | -0.380 |
�� | -0.351 |
ewater | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
idates | +0.040 |
ependence | +0.040 |
los | +0.039 |
ogh | +0.039 |
yg | +0.037 |
Neg logit contributions | |
bilt | -0.052 |
NESS | -0.045 |
hess | -0.045 |
ewater | -0.042 |
�� | -0.042 |
Token | such |
Token ID | 884 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
idates | +0.370 |
los | +0.370 |
ependence | +0.369 |
ogh | +0.367 |
yg | +0.345 |
Neg logit contributions | |
bilt | -0.472 |
NESS | -0.402 |
hess | -0.401 |
�� | -0.380 |
ewater | -0.378 |
Token | as |
Token ID | 355 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
bilt | +3.746 |
NESS | +3.193 |
hess | +3.158 |
ewater | +2.967 |
�� | +2.878 |
Neg logit contributions | |
idates | -3.504 |
ependence | -3.482 |
ogh | -3.454 |
los | -3.442 |
yg | -3.278 |
Token | Bac |
Token ID | 35583 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ependence | +2.033 |
los | +2.020 |
idates | +2.005 |
ogh | +1.991 |
sung | +1.868 |
Neg logit contributions | |
bilt | -2.676 |
NESS | -2.301 |
hess | -2.296 |
�� | -2.163 |
ewater | -2.156 |
Token | ile |
Token ID | 576 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
los | +1.924 |
idates | +1.920 |
ependence | +1.897 |
ogh | +1.858 |
yg | +1.781 |
Neg logit contributions | |
bilt | -3.772 |
NESS | -3.375 |
hess | -3.283 |
�� | -3.240 |
�� | -3.103 |
Token | 's |
Token ID | 338 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
idates | +1.147 |
los | +1.147 |
ogh | +1.141 |
ependence | +1.140 |
yg | +1.072 |
Neg logit contributions | |
bilt | -1.480 |
NESS | -1.262 |
hess | -1.259 |
ewater | -1.187 |
�� | -1.187 |
Token | Inn |
Token ID | 10849 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
los | +1.103 |
ependence | +1.101 |
idates | +1.099 |
ogh | +1.092 |
yg | +1.023 |
Neg logit contributions | |
bilt | -1.371 |
hess | -1.175 |
NESS | -1.163 |
ewater | -1.098 |
�� | -1.090 |
Token | oc |
Token ID | 420 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ependence | +3.637 |
los | +3.469 |
ogh | +3.415 |
ocrates | +3.361 |
idates | +3.133 |
Neg logit contributions | |
bilt | -16.127 |
NESS | -14.538 |
hess | -14.380 |
�� | -13.704 |
�� | -13.532 |
Token | ence |
Token ID | 594 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
idates | +0.113 |
ependence | +0.112 |
los | +0.111 |
ogh | +0.107 |
yg | +0.093 |
Neg logit contributions | |
bilt | -0.453 |
NESS | -0.409 |
hess | -0.407 |
ewater | -0.393 |
�� | -0.392 |
Token | of |
Token ID | 286 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
los | +1.979 |
idates | +1.944 |
ogh | +1.910 |
ependence | +1.893 |
ochond | +1.830 |
Neg logit contributions | |
bilt | -2.908 |
NESS | -2.518 |
hess | -2.512 |
ewater | -2.372 |
�� | -2.356 |
Token | Muslims |
Token ID | 7045 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
bilt | +2.157 |
NESS | +1.907 |
hess | +1.897 |
ewater | +1.835 |
�� | +1.799 |
Neg logit contributions | |
ependence | -1.114 |
idates | -1.114 |
los | -1.096 |
ogh | -1.091 |
yg | -1.002 |
Token | are |
Token ID | 389 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
idates | +0.418 |
ependence | +0.418 |
los | +0.417 |
ogh | +0.416 |
yg | +0.391 |
Neg logit contributions | |
bilt | -0.520 |
hess | -0.442 |
NESS | -0.441 |
ewater | -0.418 |
�� | -0.413 |
Token | 42 |
Token ID | 3682 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
los | +2.027 |
idates | +1.930 |
ogh | +1.923 |
ependence | +1.893 |
yg | +1.847 |
Neg logit contributions | |
bilt | -4.514 |
�� | -4.004 |
hess | -3.987 |
ewater | -3.901 |
NESS | -3.827 |
Token | z |
Token ID | 89 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
bilt | +0.762 |
NESS | +0.622 |
hess | +0.609 |
�� | +0.572 |
ewater | +0.567 |
Neg logit contributions | |
los | -1.084 |
idates | -1.083 |
ependence | -1.079 |
ogh | -1.076 |
yg | -1.036 |
Token | SH |
Token ID | 6006 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
bilt | +2.494 |
NESS | +2.169 |
hess | +2.126 |
ewater | +2.001 |
�� | +1.984 |
Neg logit contributions | |
ependence | -2.131 |
idates | -2.126 |
los | -2.105 |
ogh | -2.104 |
ochond | -1.977 |
Token | AM |
Token ID | 2390 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
bilt | +1.477 |
NESS | +1.291 |
hess | +1.275 |
ewater | +1.209 |
�� | +1.197 |
Neg logit contributions | |
idates | -1.041 |
ependence | -1.041 |
los | -1.030 |
ogh | -1.023 |
yg | -0.959 |
Token | SH |
Token ID | 9693 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
idates | +0.422 |
ependence | +0.420 |
los | +0.418 |
ogh | +0.415 |
yg | +0.393 |
Neg logit contributions | |
bilt | -0.490 |
hess | -0.417 |
NESS | -0.416 |
ewater | -0.394 |
�� | -0.390 |
Token | E |
Token ID | 36 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
idates | +0.887 |
los | +0.883 |
ependence | +0.877 |
ogh | +0.876 |
yg | +0.826 |
Neg logit contributions | |
bilt | -1.208 |
hess | -1.044 |
NESS | -1.011 |
ewater | -0.998 |
�� | -0.980 |
Token | ER |
Token ID | 1137 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
idates | +8.096 |
ogh | +7.808 |
IG | +7.806 |
bu | +7.791 |
BP | +7.676 |
Neg logit contributions | |
bilt | -10.699 |
hess | -9.157 |
ewater | -8.873 |
�� | -8.620 |
NESS | -8.255 |
Token | T |
Token ID | 309 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
idates | +2.746 |
los | +2.700 |
ependence | +2.672 |
ogh | +2.654 |
yg | +2.541 |
Neg logit contributions | |
bilt | -3.500 |
hess | -2.991 |
ewater | -2.882 |
NESS | -2.860 |
�� | -2.837 |
Token | OC |
Token ID | 4503 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
idates | +0.615 |
ependence | +0.612 |
los | +0.607 |
ogh | +0.602 |
yg | +0.552 |
Neg logit contributions | |
bilt | -1.431 |
NESS | -1.272 |
hess | -1.267 |
ewater | -1.215 |
�� | -1.205 |
Token | AK |
Token ID | 15837 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
idates | +3.426 |
los | +3.366 |
ependence | +3.307 |
ogh | +3.268 |
)+ | +3.184 |
Neg logit contributions | |
bilt | -4.533 |
hess | -3.855 |
ewater | -3.713 |
NESS | -3.659 |
�� | -3.649 |
Token | NOW |
Token ID | 45669 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
idates | +0.009 |
ependence | +0.009 |
los | +0.009 |
ogh | +0.009 |
yg | +0.008 |
Neg logit contributions | |
bilt | -0.022 |
hess | -0.019 |
NESS | -0.019 |
ewater | -0.019 |
�� | -0.019 |
Token | gig |
Token ID | 12526 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
idates | +1.046 |
ependence | +1.044 |
los | +1.043 |
ogh | +1.035 |
yg | +0.964 |
Neg logit contributions | |
bilt | -2.001 |
hess | -1.757 |
NESS | -1.755 |
ewater | -1.672 |
�� | -1.670 |
Token | abytes |
Token ID | 38346 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
idates | +0.811 |
ependence | +0.809 |
los | +0.805 |
ogh | +0.801 |
yg | +0.761 |
Neg logit contributions | |
bilt | -0.922 |
NESS | -0.784 |
hess | -0.775 |
�� | -0.731 |
ewater | -0.728 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
bilt | +0.888 |
NESS | +0.754 |
hess | +0.750 |
ewater | +0.702 |
�� | +0.697 |
Neg logit contributions | |
idates | -0.843 |
ependence | -0.841 |
los | -0.838 |
ogh | -0.833 |
yg | -0.789 |
Token | month |
Token ID | 1227 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
bilt | +1.138 |
NESS | +0.964 |
hess | +0.956 |
ewater | +0.900 |
�� | +0.887 |
Neg logit contributions | |
idates | -1.127 |
ependence | -1.126 |
los | -1.118 |
ogh | -1.112 |
yg | -1.056 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
los | +0.750 |
idates | +0.746 |
ogh | +0.743 |
ependence | +0.743 |
yg | +0.695 |
Neg logit contributions | |
bilt | -0.951 |
NESS | -0.821 |
hess | -0.815 |
�� | -0.769 |
ewater | -0.767 |
Token | or |
Token ID | 393 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
idates | +1.563 |
los | +1.558 |
ependence | +1.543 |
ogh | +1.536 |
yg | +1.451 |
Neg logit contributions | |
bilt | -2.165 |
hess | -1.873 |
NESS | -1.862 |
�� | -1.779 |
ewater | -1.752 |
Token | as |
Token ID | 355 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
los | +7.028 |
bu | +6.765 |
Goldman | +6.690 |
idates | +6.547 |
ogh | +6.446 |
Neg logit contributions | |
bilt | -11.868 |
hess | -10.201 |
NESS | -9.846 |
�� | -9.804 |
ewater | -9.389 |
Token | the |
Token ID | 262 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
bilt | +2.902 |
NESS | +2.435 |
hess | +2.397 |
ewater | +2.263 |
�� | +2.208 |
Neg logit contributions | |
ependence | -3.261 |
idates | -3.260 |
ogh | -3.220 |
los | -3.219 |
yg | -3.060 |
Token | report |
Token ID | 989 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
idates | +0.602 |
los | +0.600 |
ependence | +0.596 |
ogh | +0.588 |
yg | +0.561 |
Neg logit contributions | |
bilt | -0.678 |
hess | -0.585 |
NESS | -0.578 |
�� | -0.544 |
ewater | -0.543 |
Token | says |
Token ID | 1139 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
bilt | +0.165 |
NESS | +0.142 |
hess | +0.142 |
�� | +0.134 |
ewater | +0.134 |
Neg logit contributions | |
idates | -0.126 |
ependence | -0.125 |
los | -0.125 |
ogh | -0.124 |
yg | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
bilt | +0.856 |
NESS | +0.731 |
hess | +0.725 |
ewater | +0.686 |
�� | +0.678 |
Neg logit contributions | |
idates | -0.773 |
ependence | -0.770 |
los | -0.762 |
ogh | -0.761 |
yg | -0.718 |
Token | 7 |
Token ID | 22 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
bilt | +3.327 |
hess | +2.880 |
NESS | +2.875 |
ewater | +2.708 |
�� | +2.644 |
Neg logit contributions | |
ependence | -2.621 |
idates | -2.620 |
los | -2.586 |
ogh | -2.574 |
yg | -2.430 |
Token | { |
Token ID | 1391 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
los | +5.108 |
idates | +5.005 |
ependence | +4.920 |
)+ | +4.917 |
yg | +4.861 |
Neg logit contributions | |
bilt | -8.461 |
NESS | -7.300 |
hess | -7.265 |
ewater | -7.195 |
�� | -7.167 |
Token | ( |
Token ID | 7 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bilt | +0.109 |
NESS | +0.092 |
hess | +0.092 |
�� | +0.088 |
ewater | +0.087 |
Neg logit contributions | |
idates | -0.100 |
los | -0.100 |
ependence | -0.099 |
ogh | -0.099 |
yg | -0.094 |
Token | 33 |
Token ID | 2091 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
bilt | +1.534 |
NESS | +1.323 |
hess | +1.316 |
ewater | +1.247 |
�� | +1.235 |
Neg logit contributions | |
idates | -1.188 |
ependence | -1.184 |
los | -1.178 |
ogh | -1.170 |
yg | -1.104 |
Token | s |
Token ID | 82 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
idates | +1.407 |
ependence | +1.406 |
los | +1.396 |
ogh | +1.391 |
yg | +1.328 |
Neg logit contributions | |
bilt | -1.168 |
NESS | -0.970 |
hess | -0.963 |
ewater | -0.896 |
�� | -0.882 |
Token | )} |
Token ID | 38165 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
)+ | +1.368 |
los | +1.367 |
idates | +1.298 |
ependence | +1.269 |
ogh | +1.185 |
Neg logit contributions | |
bilt | -8.065 |
NESS | -7.332 |
hess | -7.244 |
�� | -7.208 |
�� | -7.074 |
Token | 34 |
Token ID | 4974 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
idates | +5.678 |
ependence | +5.616 |
yg | +5.524 |
los | +5.498 |
ogh | +5.335 |
Neg logit contributions | |
bilt | -14.097 |
NESS | -12.247 |
hess | -12.048 |
ewater | -11.734 |
�� | -11.524 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
idates | +0.693 |
los | +0.693 |
ependence | +0.685 |
ogh | +0.681 |
yg | +0.650 |
Neg logit contributions | |
bilt | -0.975 |
NESS | -0.839 |
hess | -0.831 |
�� | -0.813 |
ewater | -0.804 |
Token | Q |
Token ID | 1195 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
idates | +3.030 |
ogh | +3.014 |
ependence | +2.969 |
los | +2.962 |
yg | +2.876 |
Neg logit contributions | |
bilt | -4.642 |
NESS | -4.011 |
hess | -3.886 |
�� | -3.862 |
ewater | -3.821 |
Token | d |
Token ID | 67 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
bilt | +1.761 |
hess | +1.484 |
NESS | +1.479 |
ewater | +1.383 |
�� | +1.356 |
Neg logit contributions | |
idates | -1.853 |
ependence | -1.852 |
los | -1.834 |
ogh | -1.825 |
yg | -1.730 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
bilt | +2.627 |
NESS | +2.226 |
hess | +2.223 |
ewater | +2.079 |
�� | +2.045 |
Neg logit contributions | |
idates | -2.619 |
ependence | -2.616 |
los | -2.595 |
ogh | -2.583 |
yg | -2.454 |
Token | )\ |
Token ID | 19415 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
)+ | +4.213 |
idates | +4.151 |
ogh | +4.142 |
los | +4.106 |
ependence | +4.015 |
Neg logit contributions | |
bilt | -8.367 |
NESS | -7.480 |
hess | -7.440 |
�� | -7.153 |
ewater | -7.069 |
Token | s |
Token ID | 82 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
idates | +1.360 |
los | +1.347 |
ependence | +1.342 |
ogh | +1.339 |
yg | +1.278 |
Neg logit contributions | |
bilt | -1.425 |
NESS | -1.208 |
hess | -1.200 |
ewater | -1.131 |
�� | -1.123 |
Token | + |
Token ID | 10 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
idates | +3.011 |
los | +2.952 |
)+ | +2.902 |
ependence | +2.894 |
ogh | +2.881 |
Neg logit contributions | |
bilt | -5.771 |
NESS | -5.136 |
hess | -5.105 |
ewater | -4.835 |
�� | -4.822 |
Token | " |
Token ID | 1 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ogh | +3.816 |
idates | +3.810 |
los | +3.804 |
ependence | +3.729 |
)+ | +3.689 |
Neg logit contributions | |
bilt | -5.927 |
NESS | -5.180 |
hess | -5.118 |
�� | -4.888 |
ewater | -4.857 |
Token | \ |
Token ID | 59 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
idates | +0.210 |
ependence | +0.209 |
los | +0.208 |
ogh | +0.207 |
yg | +0.194 |
Neg logit contributions | |
bilt | -0.316 |
NESS | -0.275 |
hess | -0.274 |
ewater | -0.260 |
�� | -0.259 |
Token | S |
Token ID | 50 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
idates | +4.763 |
los | +4.757 |
ogh | +4.711 |
ependence | +4.633 |
)+ | +4.629 |
Neg logit contributions | |
bilt | -5.313 |
NESS | -4.526 |
hess | -4.453 |
�� | -4.311 |
ewater | -4.233 |
Token | + |
Token ID | 10 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
)+ | +7.409 |
idates | +7.077 |
los | +6.922 |
ogh | +6.895 |
ependence | +6.718 |
Neg logit contributions | |
bilt | -11.359 |
hess | -9.935 |
NESS | -9.919 |
�� | -9.667 |
�� | -9.533 |
Token | "] |
Token ID | 8973 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ogh | +3.310 |
idates | +3.305 |
los | +3.294 |
ependence | +3.253 |
)+ | +3.155 |
Neg logit contributions | |
bilt | -4.581 |
NESS | -3.949 |
hess | -3.903 |
�� | -3.737 |
ewater | -3.729 |
Token | ' |
Token ID | 6 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
los | +3.255 |
idates | +3.232 |
ogh | +3.231 |
ependence | +3.227 |
)+ | +3.122 |
Neg logit contributions | |
bilt | -4.545 |
NESS | -3.907 |
hess | -3.883 |
�� | -3.783 |
ewater | -3.733 |
Token | ) |
Token ID | 1267 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
bilt | +4.497 |
NESS | +3.882 |
hess | +3.820 |
ewater | +3.485 |
td | +3.462 |
Neg logit contributions | |
idates | -5.073 |
ependence | -5.060 |
ogh | -5.008 |
los | -4.991 |
ochond | -4.757 |
Token | AS |
Token ID | 7054 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
bilt | +0.969 |
NESS | +0.830 |
hess | +0.826 |
ewater | +0.781 |
�� | +0.772 |
Neg logit contributions | |
idates | -0.811 |
ependence | -0.808 |
los | -0.803 |
ogh | -0.799 |
yg | -0.755 |
Token | note |
Token ID | 3465 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
los | +2.358 |
ependence | +2.340 |
idates | +2.334 |
ogh | +2.314 |
yg | +2.236 |
Neg logit contributions | |
bilt | -2.707 |
NESS | -2.354 |
hess | -2.343 |
�� | -2.229 |
ewater | -2.184 |
Token | doesn |
Token ID | 1595 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
idates | +1.599 |
los | +1.597 |
ependence | +1.594 |
ogh | +1.565 |
yg | +1.483 |
Neg logit contributions | |
bilt | -2.170 |
NESS | -1.869 |
hess | -1.845 |
�� | -1.802 |
ewater | -1.737 |
Token | 't |
Token ID | 470 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
los | +0.279 |
idates | +0.277 |
ependence | +0.274 |
ogh | +0.274 |
yg | +0.256 |
Neg logit contributions | |
bilt | -0.471 |
NESS | -0.411 |
hess | -0.407 |
�� | -0.397 |
ewater | -0.391 |
Token | change |
Token ID | 1487 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
idates | +2.046 |
los | +2.035 |
ogh | +2.002 |
ependence | +1.961 |
yg | +1.912 |
Neg logit contributions | |
bilt | -2.583 |
hess | -2.212 |
NESS | -2.201 |
�� | -2.113 |
�� | -2.069 |
Token | anything |
Token ID | 1997 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
los | +1.982 |
idates | +1.973 |
ependence | +1.950 |
ogh | +1.935 |
yg | +1.858 |
Neg logit contributions | |
bilt | -2.406 |
hess | -2.058 |
NESS | -2.030 |
�� | -1.926 |
ewater | -1.915 |
Token | ," |
Token ID | 553 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
los | +0.194 |
idates | +0.194 |
ependence | +0.194 |
ogh | +0.191 |
yg | +0.180 |
Neg logit contributions | |
bilt | -0.268 |
NESS | -0.231 |
hess | -0.231 |
�� | -0.218 |
ewater | -0.218 |
Token | Sy |
Token ID | 1632 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
idates | +7.146 |
los | +7.016 |
ependence | +6.909 |
yg | +6.872 |
Goldman | +6.827 |
Neg logit contributions | |
bilt | -11.304 |
NESS | -9.733 |
hess | -9.721 |
�� | -9.509 |
�� | -9.415 |
Token | kes |
Token ID | 5209 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
idates | +0.705 |
los | +0.666 |
ependence | +0.596 |
ogh | +0.571 |
yg | +0.499 |
Neg logit contributions | |
bilt | -4.604 |
NESS | -4.214 |
�� | -4.183 |
�� | -4.095 |
hess | -4.084 |
Token | said |
Token ID | 531 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
idates | +1.356 |
ependence | +1.351 |
los | +1.345 |
ogh | +1.338 |
yg | +1.264 |
Neg logit contributions | |
bilt | -2.119 |
NESS | -1.848 |
hess | -1.839 |
�� | -1.748 |
ewater | -1.742 |
Token | on |
Token ID | 319 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
idates | +1.527 |
ependence | +1.523 |
los | +1.518 |
ogh | +1.509 |
yg | +1.432 |
Neg logit contributions | |
bilt | -1.991 |
NESS | -1.719 |
hess | -1.713 |
ewater | -1.606 |
�� | -1.604 |
Token | his |
Token ID | 465 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
los | +3.553 |
idates | +3.547 |
ependence | +3.538 |
ogh | +3.476 |
yg | +3.349 |
Neg logit contributions | |
bilt | -4.887 |
hess | -4.253 |
NESS | -4.249 |
ewater | -3.972 |
�� | -3.956 |
Token | 29 |
Token ID | 1959 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
bilt | +0.695 |
NESS | +0.592 |
hess | +0.591 |
�� | +0.571 |
ewater | +0.565 |
Neg logit contributions | |
los | -0.568 |
idates | -0.567 |
ependence | -0.561 |
ogh | -0.559 |
yg | -0.530 |
Token | x |
Token ID | 2124 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
bilt | +1.353 |
NESS | +0.936 |
hess | +0.918 |
ewater | +0.774 |
�� | +0.737 |
Neg logit contributions | |
idates | -4.104 |
ependence | -4.097 |
los | -4.072 |
ogh | -4.064 |
yg | -3.922 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
bilt | +1.138 |
NESS | +0.979 |
hess | +0.972 |
ewater | +0.922 |
�� | +0.920 |
Neg logit contributions | |
idates | -0.913 |
ependence | -0.910 |
los | -0.910 |
ogh | -0.901 |
yg | -0.855 |
Token | x |
Token ID | 87 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
los | +0.634 |
idates | +0.630 |
ependence | +0.626 |
ogh | +0.624 |
yg | +0.611 |
Neg logit contributions | |
bilt | -0.262 |
NESS | -0.195 |
hess | -0.187 |
�� | -0.176 |
ewater | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
los | +2.980 |
ogh | +2.822 |
idates | +2.820 |
ependence | +2.781 |
yg | +2.762 |
Neg logit contributions | |
bilt | -5.102 |
�� | -4.552 |
NESS | -4.499 |
�� | -4.394 |
hess | -4.373 |
Token | x |
Token ID | 87 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
los | +4.231 |
idates | +4.129 |
ogh | +4.083 |
ependence | +4.082 |
yg | +4.071 |
Neg logit contributions | |
bilt | -2.077 |
NESS | -1.658 |
�� | -1.601 |
hess | -1.533 |
�� | -1.459 |
Token | . |
Token ID | 13 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
los | +5.679 |
.# | +5.490 |
)+ | +5.160 |
yg | +5.082 |
idates | +5.026 |
Neg logit contributions | |
bilt | -12.914 |
NESS | -12.022 |
corrid | -11.949 |
�� | -11.871 |
�� | -11.730 |
Token | 124 |
Token ID | 17464 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
los | +3.620 |
idates | +3.487 |
ependence | +3.083 |
yg | +2.991 |
bu | +2.981 |
Neg logit contributions | |
bilt | -10.796 |
NESS | -10.104 |
hess | -9.717 |
�� | -9.260 |
ewater | -9.231 |
Token | 10 |
Token ID | 838 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
bilt | +0.972 |
NESS | +0.835 |
hess | +0.832 |
ewater | +0.789 |
�� | +0.784 |
Neg logit contributions | |
idates | -0.768 |
los | -0.765 |
ependence | -0.765 |
ogh | -0.759 |
yg | -0.714 |
Token | 409 |
Token ID | 29416 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
los | +4.173 |
idates | +4.022 |
ependence | +3.999 |
ogh | +3.986 |
bu | +3.912 |
Neg logit contributions | |
bilt | -5.117 |
�� | -4.427 |
hess | -4.293 |
ewater | -4.287 |
NESS | -4.233 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
los | +2.117 |
idates | +2.031 |
ogh | +2.019 |
ependence | +2.008 |
bu | +1.970 |
Neg logit contributions | |
bilt | -3.200 |
�� | -2.831 |
hess | -2.764 |
ewater | -2.699 |
NESS | -2.689 |
Token | # |
Token ID | 1303 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
bilt | +1.429 |
NESS | +1.243 |
hess | +1.214 |
ewater | +1.144 |
�� | +1.124 |
Neg logit contributions | |
idates | -1.333 |
ependence | -1.320 |
los | -1.315 |
ogh | -1.295 |
ocrates | -1.226 |
Token | morph |
Token ID | 17488 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
bilt | +2.267 |
NESS | +1.779 |
hess | +1.766 |
ewater | +1.587 |
�� | +1.532 |
Neg logit contributions | |
idates | -3.984 |
ependence | -3.974 |
los | -3.927 |
ogh | -3.921 |
yg | -3.764 |
Token | ological |
Token ID | 2770 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ependence | +0.559 |
los | +0.553 |
idates | +0.549 |
ogh | +0.546 |
yg | +0.507 |
Neg logit contributions | |
bilt | -1.152 |
NESS | -1.029 |
hess | -1.016 |
�� | -0.980 |
ewater | -0.974 |
Token | operator |
Token ID | 10088 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
bilt | +3.463 |
hess | +2.820 |
NESS | +2.774 |
ewater | +2.500 |
td | +2.436 |
Neg logit contributions | |
idates | -5.978 |
ependence | -5.933 |
ogh | -5.840 |
los | -5.839 |
igree | -5.724 |
Token | to |
Token ID | 284 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
bilt | +5.454 |
hess | +4.596 |
NESS | +4.477 |
ewater | +4.067 |
td | +3.948 |
Neg logit contributions | |
idates | -7.766 |
ependence | -7.759 |
ogh | -7.683 |
los | -7.556 |
igree | -7.541 |
Token | find |
Token ID | 1064 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
bilt | +2.994 |
NESS | +2.502 |
hess | +2.458 |
ewater | +2.280 |
�� | +2.225 |
Neg logit contributions | |
ependence | -3.842 |
idates | -3.838 |
ogh | -3.789 |
los | -3.785 |
yg | -3.630 |
Token | dark |
Token ID | 3223 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
bilt | +4.264 |
hess | +2.816 |
NESS | +2.777 |
darker | +2.737 |
td | +2.511 |
Neg logit contributions | |
ependence | -19.817 |
idates | -19.575 |
ocrates | -19.293 |
los | -19.127 |
igree | -18.968 |
Token | regions |
Token ID | 7652 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
bilt | +5.657 |
NESS | +5.064 |
hess | +4.694 |
ewater | +4.083 |
td | +3.858 |
Neg logit contributions | |
ependence | -12.407 |
idates | -12.012 |
los | -11.918 |
ogh | -11.813 |
igree | -11.791 |
Token | on |
Token ID | 319 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
bilt | +3.882 |
NESS | +3.377 |
hess | +3.374 |
ewater | +3.186 |
�� | +3.096 |
Neg logit contributions | |
ependence | -2.868 |
idates | -2.865 |
los | -2.815 |
ogh | -2.796 |
igree | -2.660 |
Token | a |
Token ID | 257 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
bilt | +6.362 |
NESS | +5.152 |
hess | +5.126 |
td | +4.752 |
ewater | +4.703 |
Neg logit contributions | |
idates | -9.295 |
ependence | -9.290 |
los | -9.119 |
ogh | -9.035 |
igree | -8.830 |
Token | light |
Token ID | 1657 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
bilt | +3.993 |
NESS | +3.243 |
hess | +3.142 |
ewater | +2.899 |
dime | +2.826 |
Neg logit contributions | |
idates | -7.221 |
ependence | -7.206 |
los | -7.075 |
ogh | -6.950 |
ocrates | -6.830 |
Token | variants |
Token ID | 17670 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
idates | +2.024 |
los | +2.016 |
ependence | +2.012 |
ogh | +2.001 |
yg | +1.918 |
Neg logit contributions | |
bilt | -2.491 |
NESS | -2.121 |
hess | -2.107 |
�� | -2.019 |
ewater | -2.011 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
idates | +0.521 |
ependence | +0.520 |
ogh | +0.515 |
los | +0.515 |
yg | +0.489 |
Neg logit contributions | |
bilt | -0.661 |
NESS | -0.567 |
hess | -0.558 |
ewater | -0.534 |
�� | -0.532 |
Token | you |
Token ID | 345 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
bilt | +3.822 |
NESS | +3.259 |
hess | +3.241 |
ewater | +3.037 |
�� | +2.954 |
Neg logit contributions | |
ependence | -3.845 |
los | -3.810 |
idates | -3.804 |
ogh | -3.794 |
ochond | -3.602 |
Token | can |
Token ID | 460 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
bilt | +5.156 |
NESS | +4.297 |
hess | +4.267 |
ewater | +4.050 |
�� | +3.834 |
Neg logit contributions | |
ependence | -5.896 |
ogh | -5.781 |
idates | -5.764 |
los | -5.741 |
ocrates | -5.510 |
Token | enable |
Token ID | 7139 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
bilt | +5.173 |
NESS | +4.363 |
hess | +4.346 |
ewater | +4.122 |
td | +3.983 |
Neg logit contributions | |
ependence | -5.638 |
los | -5.503 |
ogh | -5.486 |
idates | -5.480 |
ocrates | -5.291 |
Token | / |
Token ID | 14 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
idates | +1.569 |
ependence | +1.550 |
ogh | +1.544 |
los | +1.533 |
yg | +1.466 |
Neg logit contributions | |
bilt | -2.070 |
NESS | -1.774 |
hess | -1.759 |
ewater | -1.681 |
�� | -1.658 |
Token | disable |
Token ID | 40223 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bilt | +8.517 |
hess | +7.488 |
Per | +7.167 |
NESS | +6.960 |
ewater | +6.488 |
Neg logit contributions | |
ocrates | -14.305 |
ogh | -14.036 |
ependence | -13.445 |
ochond | -13.415 |
igree | -13.269 |
Token | each |
Token ID | 1123 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
bilt | +0.138 |
NESS | +0.118 |
hess | +0.117 |
ewater | +0.111 |
�� | +0.110 |
Neg logit contributions | |
idates | -0.112 |
ependence | -0.111 |
los | -0.110 |
ogh | -0.110 |
yg | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
idates | +1.550 |
ependence | +1.548 |
los | +1.544 |
ogh | +1.528 |
yg | +1.473 |
Neg logit contributions | |
bilt | -2.047 |
NESS | -1.759 |
hess | -1.736 |
ewater | -1.663 |
�� | -1.659 |
Token | drag |
Token ID | 6715 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
bilt | +3.878 |
NESS | +3.280 |
hess | +3.258 |
ewater | +3.056 |
�� | +2.982 |
Neg logit contributions | |
ependence | -4.006 |
idates | -3.949 |
los | -3.922 |
ogh | -3.918 |
ocrates | -3.744 |
Token | them |
Token ID | 606 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
idates | +2.195 |
ependence | +2.184 |
los | +2.173 |
ogh | +2.158 |
yg | +2.077 |
Neg logit contributions | |
bilt | -2.848 |
NESS | -2.448 |
hess | -2.425 |
�� | -2.317 |
ewater | -2.298 |
Token | x |
Token ID | 2124 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
bilt | +1.633 |
NESS | +1.149 |
hess | +1.124 |
�� | +0.892 |
td | +0.872 |
Neg logit contributions | |
idates | -5.631 |
ependence | -5.604 |
los | -5.562 |
ogh | -5.523 |
ocrates | -5.364 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
bilt | +2.670 |
NESS | +2.288 |
hess | +2.276 |
ewater | +2.137 |
�� | +2.095 |
Neg logit contributions | |
idates | -2.340 |
ependence | -2.332 |
los | -2.305 |
ogh | -2.300 |
yg | -2.167 |
Token | x |
Token ID | 87 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
bilt | +0.895 |
NESS | +0.635 |
hess | +0.626 |
ewater | +0.540 |
�� | +0.524 |
Neg logit contributions | |
idates | -2.466 |
ependence | -2.462 |
los | -2.453 |
ogh | -2.444 |
yg | -2.362 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
los | +0.686 |
idates | +0.675 |
ependence | +0.670 |
ogh | +0.670 |
yg | +0.645 |
Neg logit contributions | |
bilt | -0.970 |
NESS | -0.840 |
hess | -0.829 |
�� | -0.817 |
ewater | -0.798 |
Token | x |
Token ID | 87 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
bilt | +1.272 |
NESS | +0.888 |
hess | +0.881 |
ewater | +0.751 |
�� | +0.708 |
Neg logit contributions | |
idates | -3.645 |
ependence | -3.641 |
los | -3.615 |
ogh | -3.613 |
yg | -3.476 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
bilt | +4.156 |
NESS | +3.539 |
hess | +3.514 |
ewater | +3.272 |
td | +3.138 |
Neg logit contributions | |
idates | -4.009 |
ependence | -4.004 |
ogh | -3.952 |
los | -3.934 |
igree | -3.784 |
Token | 79 |
Token ID | 3720 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
bilt | +5.551 |
NESS | +4.221 |
hess | +3.807 |
td | +3.348 |
ewater | +3.295 |
Neg logit contributions | |
ogh | -16.008 |
los | -15.740 |
ependence | -15.587 |
ochond | -15.301 |
idates | -15.274 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ogh | +3.070 |
los | +3.032 |
idates | +3.021 |
ependence | +3.018 |
yg | +2.900 |
Neg logit contributions | |
bilt | -3.852 |
NESS | -3.299 |
hess | -3.291 |
ewater | -3.104 |
�� | -3.100 |
Token | 65 |
Token ID | 2996 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
los | +1.493 |
idates | +1.482 |
ependence | +1.478 |
ogh | +1.471 |
yg | +1.405 |
Neg logit contributions | |
bilt | -1.780 |
hess | -1.516 |
NESS | -1.515 |
ewater | -1.455 |
�� | -1.442 |
Token | 110 |
Token ID | 11442 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
idates | +1.458 |
los | +1.450 |
ependence | +1.446 |
ogh | +1.438 |
yg | +1.363 |
Neg logit contributions | |
bilt | -1.717 |
NESS | -1.465 |
hess | -1.453 |
ewater | -1.386 |
�� | -1.385 |
Token | x |
Token ID | 2124 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
bilt | +2.000 |
NESS | +1.565 |
hess | +1.516 |
ewater | +1.318 |
�� | +1.308 |
Neg logit contributions | |
idates | -4.334 |
ependence | -4.314 |
los | -4.255 |
ogh | -4.245 |
igree | -4.091 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
los | +2.834 |
idates | +2.810 |
ogh | +2.789 |
ependence | +2.775 |
bu | +2.653 |
Neg logit contributions | |
bilt | -3.736 |
NESS | -3.255 |
hess | -3.253 |
ewater | -3.099 |
�� | -3.090 |
Token | I |
Token ID | 314 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
los | +2.460 |
idates | +2.452 |
ependence | +2.396 |
ogh | +2.387 |
bu | +2.278 |
Neg logit contributions | |
bilt | -3.724 |
hess | -3.237 |
NESS | -3.198 |
�� | -3.164 |
ewater | -3.119 |
Token | remembered |
Token ID | 12086 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
bilt | +2.400 |
NESS | +2.059 |
hess | +2.047 |
ewater | +1.933 |
�� | +1.914 |
Neg logit contributions | |
idates | -2.021 |
ependence | -2.014 |
los | -2.003 |
ogh | -1.991 |
yg | -1.884 |
Token | thinking |
Token ID | 3612 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bilt | +1.684 |
NESS | +1.441 |
hess | +1.431 |
ewater | +1.351 |
�� | +1.333 |
Neg logit contributions | |
idates | -1.481 |
ependence | -1.478 |
los | -1.467 |
ogh | -1.459 |
yg | -1.380 |
Token | " |
Token ID | 366 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
bilt | +0.156 |
NESS | +0.134 |
hess | +0.133 |
ewater | +0.125 |
�� | +0.125 |
Neg logit contributions | |
idates | -0.128 |
ependence | -0.127 |
los | -0.127 |
ogh | -0.126 |
yg | -0.119 |
Token | God |
Token ID | 13482 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
bilt | +3.617 |
NESS | +3.135 |
hess | +3.111 |
ewater | +2.951 |
�� | +2.859 |
Neg logit contributions | |
idates | -2.853 |
ependence | -2.847 |
ogh | -2.792 |
los | -2.782 |
yg | -2.624 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
bilt | +10.543 |
NESS | +8.928 |
hess | +8.330 |
ewater | +8.186 |
dime | +7.884 |
Neg logit contributions | |
idates | -11.359 |
ependence | -11.202 |
los | -11.142 |
ogh | -10.909 |
)+ | -10.499 |
Token | how |
Token ID | 703 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bilt | +1.468 |
NESS | +1.262 |
hess | +1.255 |
ewater | +1.186 |
�� | +1.173 |
Neg logit contributions | |
idates | -1.208 |
ependence | -1.204 |
los | -1.197 |
ogh | -1.190 |
yg | -1.125 |
Token | could |
Token ID | 714 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
los | +1.131 |
ependence | +1.120 |
idates | +1.120 |
ogh | +1.118 |
yg | +1.051 |
Neg logit contributions | |
bilt | -1.254 |
NESS | -1.066 |
hess | -1.063 |
�� | -1.002 |
ewater | -0.992 |
Token | a |
Token ID | 257 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
idates | +1.599 |
los | +1.590 |
ependence | +1.581 |
ogh | +1.575 |
yg | +1.488 |
Neg logit contributions | |
bilt | -1.958 |
NESS | -1.669 |
hess | -1.664 |
ewater | -1.585 |
�� | -1.578 |
Token | guy |
Token ID | 3516 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
los | +4.054 |
ogh | +4.023 |
idates | +4.022 |
ependence | +3.961 |
yg | +3.899 |
Neg logit contributions | |
bilt | -4.956 |
hess | -4.331 |
NESS | -4.315 |
�� | -4.093 |
ewater | -4.074 |
Token | aud |
Token ID | 3885 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
bilt | +5.722 |
hess | +4.851 |
NESS | +4.568 |
ewater | +4.525 |
�� | +4.198 |
Neg logit contributions | |
idates | -5.934 |
ependence | -5.932 |
los | -5.795 |
ogh | -5.694 |
yg | -5.579 |
Token | Lav |
Token ID | 21438 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
bilt | +3.722 |
hess | +2.542 |
NESS | +2.515 |
ewater | +2.139 |
td | +1.844 |
Neg logit contributions | |
ependence | -10.796 |
idates | -10.793 |
los | -10.393 |
ogh | -10.389 |
igree | -10.345 |
Token | o |
Token ID | 78 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
los | +1.650 |
ogh | +1.624 |
ependence | +1.543 |
idates | +1.509 |
yg | +1.429 |
Neg logit contributions | |
bilt | -4.534 |
NESS | -4.100 |
�� | -3.996 |
hess | -3.960 |
�� | -3.877 |
Token | ie |
Token ID | 494 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
ependence | +0.981 |
los | +0.977 |
ogh | +0.976 |
idates | +0.973 |
yg | +0.909 |
Neg logit contributions | |
bilt | -2.362 |
NESS | -2.115 |
hess | -2.052 |
�� | -2.035 |
ewater | -1.986 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
los | +0.721 |
ogh | +0.719 |
idates | +0.716 |
ependence | +0.711 |
)+ | +0.673 |
Neg logit contributions | |
bilt | -0.973 |
NESS | -0.834 |
hess | -0.832 |
�� | -0.811 |
ewater | -0.805 |
Token | ren |
Token ID | 918 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
bilt | +3.082 |
hess | +2.706 |
NESS | +2.702 |
ewater | +2.570 |
�� | +2.527 |
Neg logit contributions | |
idates | -1.770 |
ependence | -1.766 |
ogh | -1.737 |
los | -1.734 |
yg | -1.618 |
Token | lav |
Token ID | 18809 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
bilt | +8.170 |
hess | +6.596 |
ewater | +6.134 |
illard | +5.460 |
NESS | +5.404 |
Neg logit contributions | |
idates | -13.925 |
ependence | -13.263 |
ocrates | -12.697 |
contrace | -12.605 |
Goldman | -12.595 |
Token | o |
Token ID | 78 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
bilt | +2.664 |
hess | +2.353 |
NESS | +2.350 |
ewater | +2.255 |
�� | +2.205 |
Neg logit contributions | |
idates | -1.299 |
ependence | -1.289 |
los | -1.263 |
ogh | -1.254 |
yg | -1.162 |
Token | iet |
Token ID | 1155 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ogh | +1.972 |
ependence | +1.966 |
los | +1.930 |
idates | +1.921 |
yg | +1.864 |
Neg logit contributions | |
bilt | -2.906 |
NESS | -2.579 |
�� | -2.468 |
hess | -2.444 |
�� | -2.378 |
Token | va |
Token ID | 6862 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
bilt | +2.985 |
hess | +2.573 |
NESS | +2.563 |
ewater | +2.436 |
�� | +2.370 |
Neg logit contributions | |
idates | -2.374 |
ependence | -2.346 |
los | -2.320 |
ogh | -2.315 |
yg | -2.184 |
Token | ) |
Token ID | 8 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
los | +1.634 |
ogh | +1.613 |
idates | +1.595 |
ependence | +1.590 |
)+ | +1.568 |
Neg logit contributions | |
bilt | -2.810 |
NESS | -2.448 |
�� | -2.436 |
hess | -2.429 |
ewater | -2.355 |
Token | an |
Token ID | 281 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
bilt | +1.010 |
NESS | +0.863 |
hess | +0.858 |
ewater | +0.808 |
�� | +0.801 |
Neg logit contributions | |
idates | -0.895 |
ependence | -0.892 |
los | -0.888 |
ogh | -0.883 |
yg | -0.836 |
Token | aging |
Token ID | 14736 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
idates | +0.542 |
ependence | +0.542 |
los | +0.534 |
ogh | +0.532 |
yg | +0.499 |
Neg logit contributions | |
bilt | -0.646 |
NESS | -0.548 |
hess | -0.548 |
�� | -0.515 |
ewater | -0.513 |
Token | population |
Token ID | 3265 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ependence | +1.259 |
los | +1.254 |
idates | +1.252 |
ogh | +1.249 |
yg | +1.174 |
Neg logit contributions | |
bilt | -1.400 |
hess | -1.206 |
NESS | -1.194 |
�� | -1.128 |
ewater | -1.105 |
Token | . |
Token ID | 13 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
bilt | +0.163 |
NESS | +0.140 |
hess | +0.139 |
ewater | +0.131 |
�� | +0.130 |
Neg logit contributions | |
ependence | -0.135 |
idates | -0.134 |
los | -0.134 |
ogh | -0.133 |
yg | -0.125 |
Token | Truth |
Token ID | 14056 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
bilt | +0.630 |
NESS | +0.542 |
hess | +0.541 |
ewater | +0.511 |
�� | +0.510 |
Neg logit contributions | |
idates | -0.492 |
ependence | -0.490 |
los | -0.489 |
ogh | -0.484 |
yg | -0.456 |
Token | be |
Token ID | 307 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
bilt | +5.810 |
NESS | +5.128 |
hess | +4.927 |
ewater | +4.870 |
�� | +4.546 |
Neg logit contributions | |
ependence | -6.405 |
ogh | -6.281 |
idates | -6.267 |
los | -6.183 |
igree | -6.089 |
Token | known |
Token ID | 1900 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
bilt | +7.897 |
NESS | +6.805 |
hess | +6.355 |
damned | +5.886 |
td | +5.881 |
Neg logit contributions | |
idates | -13.306 |
ependence | -13.152 |
los | -12.936 |
ogh | -12.612 |
igree | -12.530 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
bilt | +3.840 |
NESS | +3.324 |
hess | +3.268 |
ewater | +3.074 |
�� | +2.996 |
Neg logit contributions | |
idates | -3.705 |
los | -3.662 |
ependence | -3.654 |
ogh | -3.637 |
igree | -3.448 |
Token | the |
Token ID | 262 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
idates | +0.178 |
ependence | +0.177 |
los | +0.177 |
ogh | +0.176 |
yg | +0.167 |
Neg logit contributions | |
bilt | -0.171 |
NESS | -0.144 |
hess | -0.143 |
�� | -0.133 |
ewater | -0.133 |
Token | majority |
Token ID | 3741 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
idates | +0.882 |
ependence | +0.877 |
los | +0.876 |
ogh | +0.871 |
yg | +0.823 |
Neg logit contributions | |
bilt | -0.870 |
hess | -0.739 |
NESS | -0.735 |
�� | -0.685 |
ewater | -0.681 |
Token | are |
Token ID | 389 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
bilt | +0.890 |
NESS | +0.758 |
hess | +0.743 |
ewater | +0.715 |
�� | +0.706 |
Neg logit contributions | |
idates | -0.811 |
los | -0.806 |
ependence | -0.806 |
ogh | -0.799 |
yg | -0.763 |
Token | go |
Token ID | 467 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
bilt | +0.845 |
hess | +0.725 |
NESS | +0.721 |
ewater | +0.680 |
�� | +0.677 |
Neg logit contributions | |
idates | -0.692 |
los | -0.685 |
ependence | -0.682 |
ogh | -0.679 |
yg | -0.647 |
Token | over |
Token ID | 625 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
idates | +1.230 |
los | +1.223 |
ogh | +1.218 |
ependence | +1.216 |
yg | +1.170 |
Neg logit contributions | |
bilt | -1.316 |
hess | -1.128 |
NESS | -1.117 |
�� | -1.059 |
ewater | -1.058 |
Token | some |
Token ID | 617 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
idates | +1.056 |
los | +1.050 |
ependence | +1.045 |
ogh | +1.037 |
yg | +0.984 |
Neg logit contributions | |
bilt | -1.336 |
NESS | -1.148 |
hess | -1.137 |
ewater | -1.084 |
�� | -1.076 |
Token | basic |
Token ID | 4096 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
los | +1.778 |
idates | +1.777 |
ogh | +1.752 |
ependence | +1.737 |
yg | +1.657 |
Neg logit contributions | |
bilt | -2.364 |
NESS | -2.020 |
hess | -2.015 |
�� | -1.920 |
ewater | -1.909 |
Token | dos |
Token ID | 23430 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
los | +1.383 |
idates | +1.374 |
ogh | +1.359 |
ependence | +1.352 |
yg | +1.300 |
Neg logit contributions | |
bilt | -1.609 |
hess | -1.360 |
NESS | -1.353 |
�� | -1.293 |
ewater | -1.280 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
los | +1.582 |
idates | +1.582 |
ependence | +1.577 |
ogh | +1.564 |
yg | +1.479 |
Neg logit contributions | |
bilt | -1.999 |
NESS | -1.714 |
hess | -1.681 |
�� | -1.601 |
ewater | -1.599 |
Token | don |
Token ID | 836 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
hess | +5.761 |
bilt | +5.353 |
NESS | +4.571 |
ewater | +3.998 |
vol | +3.800 |
Neg logit contributions | |
ependence | -15.675 |
ogh | -15.055 |
idates | -15.049 |
ochond | -14.962 |
antry | -14.887 |
Token | 't |
Token ID | 470 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
bilt | +4.407 |
hess | +3.888 |
NESS | +3.796 |
ewater | +3.589 |
td | +3.420 |
Neg logit contributions | |
ependence | -3.473 |
idates | -3.441 |
ogh | -3.323 |
los | -3.319 |
igree | -3.240 |
Token | s |
Token ID | 82 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
bilt | +0.490 |
NESS | +0.408 |
hess | +0.405 |
ewater | +0.378 |
�� | +0.373 |
Neg logit contributions | |
idates | -0.566 |
ependence | -0.564 |
los | -0.562 |
ogh | -0.559 |
yg | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
los | +2.753 |
ependence | +2.695 |
idates | +2.687 |
ogh | +2.646 |
yg | +2.543 |
Neg logit contributions | |
bilt | -3.887 |
NESS | -3.301 |
hess | -3.291 |
�� | -3.174 |
ewater | -3.122 |
Token | using |
Token ID | 1262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
bilt | +0.026 |
NESS | +0.022 |
hess | +0.022 |
�� | +0.021 |
ewater | +0.021 |
Neg logit contributions | |
los | -0.021 |
idates | -0.021 |
ependence | -0.021 |
ogh | -0.021 |
yg | -0.020 |
Token | once |
Token ID | 1752 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
bilt | +5.189 |
NESS | +4.487 |
hess | +4.481 |
ewater | +4.269 |
�� | +4.126 |
Neg logit contributions | |
idates | -4.639 |
ependence | -4.534 |
los | -4.523 |
ogh | -4.499 |
ochond | -4.327 |
Token | I |
Token ID | 314 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
bilt | +2.476 |
NESS | +2.175 |
hess | +2.163 |
ewater | +2.062 |
�� | +2.036 |
Neg logit contributions | |
idates | -1.441 |
ependence | -1.437 |
los | -1.424 |
ogh | -1.415 |
yg | -1.320 |
Token | turn |
Token ID | 1210 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
bilt | +3.118 |
NESS | +2.673 |
hess | +2.664 |
ewater | +2.524 |
�� | +2.484 |
Neg logit contributions | |
idates | -2.505 |
ependence | -2.480 |
los | -2.461 |
ogh | -2.452 |
yg | -2.311 |
Token | AA |
Token ID | 15923 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
bilt | +2.878 |
NESS | +2.419 |
hess | +2.380 |
ewater | +2.237 |
�� | +2.193 |
Neg logit contributions | |
idates | -3.342 |
ependence | -3.316 |
los | -3.307 |
ogh | -3.293 |
igree | -3.136 |
Token | on |
Token ID | 319 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
bilt | +2.720 |
NESS | +2.374 |
hess | +2.366 |
ewater | +2.254 |
�� | +2.180 |
Neg logit contributions | |
idates | -1.949 |
ependence | -1.940 |
los | -1.916 |
ogh | -1.912 |
igree | -1.814 |
Token | things |
Token ID | 1243 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
bilt | +2.777 |
NESS | +2.306 |
hess | +2.253 |
ewater | +2.082 |
�� | +1.988 |
Neg logit contributions | |
idates | -4.059 |
ependence | -4.036 |
los | -3.992 |
ogh | -3.980 |
igree | -3.826 |
Token | slow |
Token ID | 3105 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
bilt | +3.359 |
ewater | +2.037 |
NESS | +1.904 |
hess | +1.893 |
td | +1.809 |
Neg logit contributions | |
idates | -17.272 |
ogh | -17.078 |
los | -16.936 |
ocrates | -16.914 |
ependence | -16.877 |
Token | down |
Token ID | 866 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
bilt | +5.746 |
NESS | +4.929 |
hess | +4.876 |
ewater | +4.746 |
td | +4.504 |
Neg logit contributions | |
ogh | -6.789 |
idates | -6.753 |
ependence | -6.678 |
los | -6.652 |
igree | -6.468 |
Token | quite |
Token ID | 2407 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
bilt | +2.487 |
NESS | +2.102 |
hess | +2.092 |
ewater | +1.964 |
�� | +1.929 |
Neg logit contributions | |
idates | -2.504 |
ependence | -2.489 |
los | -2.477 |
ogh | -2.462 |
yg | -2.344 |
Token | a |
Token ID | 257 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
bilt | +5.698 |
NESS | +4.713 |
hess | +4.576 |
ewater | +4.368 |
td | +4.251 |
Neg logit contributions | |
idates | -7.601 |
ependence | -7.548 |
los | -7.458 |
ogh | -7.411 |
igree | -7.247 |
Token | bit |
Token ID | 1643 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
bilt | +3.644 |
NESS | +3.055 |
hess | +3.043 |
ewater | +2.873 |
�� | +2.708 |
Neg logit contributions | |
idates | -4.250 |
ependence | -4.192 |
los | -4.134 |
ogh | -4.109 |
igree | -3.978 |
Token | the |
Token ID | 262 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
ependence | +0.980 |
idates | +0.980 |
los | +0.968 |
ogh | +0.965 |
yg | +0.908 |
Neg logit contributions | |
bilt | -1.284 |
NESS | -1.102 |
hess | -1.101 |
�� | -1.038 |
ewater | -1.038 |
Token | National |
Token ID | 2351 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
bilt | +0.045 |
NESS | +0.039 |
hess | +0.039 |
ewater | +0.037 |
�� | +0.037 |
Neg logit contributions | |
idates | -0.023 |
ependence | -0.022 |
los | -0.022 |
ogh | -0.022 |
yg | -0.020 |
Token | Party |
Token ID | 3615 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
idates | +0.694 |
ependence | +0.693 |
los | +0.687 |
ogh | +0.681 |
yg | +0.641 |
Neg logit contributions | |
bilt | -0.922 |
NESS | -0.800 |
hess | -0.792 |
ewater | -0.745 |
�� | -0.745 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
idates | +1.345 |
ependence | +1.343 |
los | +1.331 |
ogh | +1.320 |
yg | +1.249 |
Neg logit contributions | |
bilt | -1.593 |
NESS | -1.366 |
hess | -1.356 |
ewater | -1.281 |
�� | -1.269 |
Token | 190 |
Token ID | 19782 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
bilt | +8.911 |
NESS | +6.942 |
hess | +6.793 |
cakes | +6.165 |
Per | +6.118 |
Neg logit contributions | |
ependence | -11.528 |
ogh | -11.387 |
yg | -11.147 |
igree | -10.956 |
los | -10.921 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
bilt | +1.623 |
NESS | +1.345 |
hess | +1.339 |
ewater | +1.248 |
�� | +1.219 |
Neg logit contributions | |
idates | -1.885 |
ependence | -1.879 |
los | -1.869 |
ogh | -1.856 |
yg | -1.768 |
Token | 191 |
Token ID | 26492 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
bilt | +8.727 |
NESS | +7.135 |
hess | +6.986 |
Per | +6.364 |
cci | +5.812 |
Neg logit contributions | |
ependence | -12.425 |
yg | -12.139 |
ochond | -11.972 |
ogh | -11.921 |
igree | -11.827 |
Token | ] |
Token ID | 60 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
bilt | +1.577 |
NESS | +1.269 |
hess | +1.269 |
ewater | +1.178 |
�� | +1.150 |
Neg logit contributions | |
idates | -2.067 |
los | -2.048 |
ependence | -2.046 |
ogh | -2.024 |
ocrates | -1.952 |
Token | Within |
Token ID | 12511 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
idates | +0.917 |
ependence | +0.905 |
los | +0.905 |
ogh | +0.895 |
yg | +0.845 |
Neg logit contributions | |
bilt | -1.328 |
hess | -1.156 |
NESS | -1.153 |
�� | -1.107 |
ewater | -1.099 |
Token | Australian |
Token ID | 6638 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
bilt | +1.518 |
NESS | +1.293 |
hess | +1.283 |
ewater | +1.213 |
�� | +1.196 |
Neg logit contributions | |
idates | -1.373 |
ependence | -1.371 |
los | -1.364 |
ogh | -1.355 |
yg | -1.285 |
Token | political |
Token ID | 1964 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
idates | +1.791 |
ependence | +1.789 |
ogh | +1.777 |
los | +1.773 |
yg | +1.679 |
Neg logit contributions | |
bilt | -2.541 |
NESS | -2.203 |
hess | -2.176 |
�� | -2.110 |
ewater | -2.055 |
Token | les |
Token ID | 829 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
bilt | +1.847 |
NESS | +1.622 |
hess | +1.616 |
ewater | +1.542 |
�� | +1.523 |
Neg logit contributions | |
idates | -1.048 |
ependence | -1.046 |
los | -1.034 |
ogh | -1.029 |
yg | -0.959 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
bilt | +3.105 |
NESS | +2.660 |
hess | +2.594 |
ewater | +2.500 |
�� | +2.374 |
Neg logit contributions | |
idates | -3.130 |
ependence | -3.064 |
los | -3.033 |
ogh | -3.003 |
ochond | -2.856 |
Token |
|
Token ID | 198 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
bilt | +4.694 |
NESS | +4.101 |
hess | +4.052 |
ewater | +3.780 |
cakes | +3.603 |
Neg logit contributions | |
idates | -5.419 |
ependence | -5.322 |
ogh | -5.260 |
los | -5.250 |
ochond | -5.060 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
bilt | +0.866 |
NESS | +0.732 |
hess | +0.727 |
�� | +0.690 |
ewater | +0.686 |
Neg logit contributions | |
idates | -0.826 |
los | -0.825 |
ependence | -0.824 |
ogh | -0.817 |
yg | -0.777 |
Token | Oh |
Token ID | 5812 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
bilt | +3.901 |
NESS | +3.484 |
hess | +3.404 |
ewater | +3.170 |
Per | +3.101 |
Neg logit contributions | |
idates | -3.452 |
ependence | -3.401 |
ogh | -3.330 |
los | -3.314 |
igree | -3.187 |
Token | god |
Token ID | 5770 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
bilt | +4.582 |
NESS | +3.951 |
hess | +3.858 |
ewater | +3.663 |
�� | +3.492 |
Neg logit contributions | |
idates | -4.584 |
ependence | -4.482 |
los | -4.393 |
ogh | -4.367 |
ochond | -4.179 |
Token | . |
Token ID | 13 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
bilt | +9.368 |
NESS | +8.166 |
hess | +7.961 |
ewater | +7.339 |
td | +7.147 |
Neg logit contributions | |
idates | -11.331 |
ependence | -10.942 |
ogh | -10.529 |
los | -10.489 |
)+ | -10.368 |
Token | I |
Token ID | 314 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
bilt | +5.013 |
NESS | +4.426 |
hess | +4.336 |
ewater | +4.065 |
�� | +3.945 |
Neg logit contributions | |
idates | -4.258 |
ependence | -4.227 |
ogh | -4.164 |
los | -4.143 |
igree | -3.943 |
Token | know |
Token ID | 760 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
bilt | +0.295 |
NESS | +0.254 |
hess | +0.254 |
�� | +0.243 |
ewater | +0.241 |
Neg logit contributions | |
los | -0.210 |
ependence | -0.210 |
idates | -0.209 |
ogh | -0.206 |
yg | -0.197 |
Token | that |
Token ID | 326 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
bilt | +4.375 |
NESS | +3.834 |
hess | +3.772 |
ewater | +3.561 |
�� | +3.432 |
Neg logit contributions | |
idates | -4.002 |
ependence | -3.955 |
ogh | -3.900 |
los | -3.897 |
ochond | -3.679 |
Token | I |
Token ID | 314 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
bilt | +2.895 |
NESS | +2.508 |
hess | +2.487 |
ewater | +2.355 |
�� | +2.311 |
Neg logit contributions | |
idates | -2.272 |
ependence | -2.259 |
los | -2.239 |
ogh | -2.231 |
yg | -2.096 |
Token | Kop |
Token ID | 40500 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
idates | +1.324 |
los | +1.318 |
ependence | +1.313 |
ogh | +1.295 |
yg | +1.233 |
Neg logit contributions | |
bilt | -1.741 |
NESS | -1.509 |
hess | -1.498 |
ewater | -1.412 |
�� | -1.395 |
Token | onen |
Token ID | 34481 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
bilt | +1.601 |
NESS | +1.401 |
hess | +1.391 |
ewater | +1.326 |
�� | +1.314 |
Neg logit contributions | |
idates | -1.005 |
ependence | -1.001 |
los | -0.995 |
ogh | -0.987 |
yg | -0.924 |
Token | ( |
Token ID | 357 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
idates | +1.511 |
ependence | +1.506 |
los | +1.496 |
ogh | +1.488 |
yg | +1.407 |
Neg logit contributions | |
bilt | -1.818 |
NESS | -1.560 |
hess | -1.551 |
ewater | -1.466 |
�� | -1.450 |
Token | who |
Token ID | 8727 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
bilt | +0.913 |
NESS | +0.794 |
hess | +0.790 |
ewater | +0.750 |
�� | +0.742 |
Neg logit contributions | |
idates | -0.623 |
ependence | -0.620 |
los | -0.615 |
ogh | -0.612 |
yg | -0.575 |
Token | may |
Token ID | 743 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
idates | +2.551 |
ogh | +2.529 |
los | +2.523 |
ependence | +2.482 |
bu | +2.381 |
Neg logit contributions | |
bilt | -3.201 |
NESS | -2.799 |
hess | -2.770 |
�� | -2.700 |
ewater | -2.643 |
Token | or |
Token ID | 393 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
idates | +1.562 |
los | +1.561 |
ependence | +1.543 |
ogh | +1.543 |
yg | +1.457 |
Neg logit contributions | |
bilt | -2.136 |
hess | -1.848 |
NESS | -1.845 |
�� | -1.758 |
ewater | -1.742 |
Token | may |
Token ID | 743 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
bilt | +6.471 |
hess | +5.138 |
NESS | +5.061 |
ewater | +4.529 |
td | +4.339 |
Neg logit contributions | |
idates | -13.762 |
ependence | -13.483 |
ogh | -13.462 |
ocrates | -13.449 |
igree | -13.345 |
Token | not |
Token ID | 407 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
bilt | +0.845 |
NESS | +0.712 |
hess | +0.710 |
�� | +0.668 |
ewater | +0.665 |
Neg logit contributions | |
idates | -0.817 |
los | -0.815 |
ependence | -0.814 |
ogh | -0.809 |
yg | -0.767 |
Token | take |
Token ID | 1011 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
idates | +2.235 |
los | +2.233 |
ependence | +2.179 |
ogh | +2.174 |
yg | +2.063 |
Neg logit contributions | |
bilt | -3.575 |
NESS | -3.122 |
hess | -3.121 |
�� | -3.001 |
ewater | -2.958 |
Token | an |
Token ID | 281 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
los | +4.565 |
idates | +4.477 |
ogh | +4.476 |
ependence | +4.398 |
)+ | +4.247 |
Neg logit contributions | |
bilt | -6.066 |
NESS | -5.191 |
hess | -5.190 |
�� | -4.941 |
ewater | -4.923 |
Token | actual |
Token ID | 4036 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
idates | +4.442 |
los | +4.338 |
ogh | +4.299 |
ependence | +4.256 |
bu | +4.097 |
Neg logit contributions | |
bilt | -5.980 |
NESS | -4.894 |
hess | -4.893 |
ewater | -4.800 |
�� | -4.708 |
Token | for |
Token ID | 329 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
bilt | +4.289 |
NESS | +3.591 |
hess | +3.398 |
ewater | +3.334 |
�� | +3.124 |
Neg logit contributions | |
idates | -5.317 |
ependence | -5.292 |
los | -5.291 |
ogh | -5.244 |
ocrates | -5.044 |
Token | each |
Token ID | 1123 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
bilt | +3.955 |
NESS | +3.334 |
hess | +3.275 |
ewater | +3.108 |
�� | +3.034 |
Neg logit contributions | |
ependence | -3.930 |
idates | -3.917 |
ogh | -3.895 |
los | -3.886 |
ochond | -3.683 |
Token | apex |
Token ID | 40167 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
bilt | +1.461 |
NESS | +1.233 |
hess | +1.223 |
ewater | +1.154 |
�� | +1.132 |
Neg logit contributions | |
idates | -1.447 |
ependence | -1.443 |
los | -1.433 |
ogh | -1.430 |
yg | -1.356 |
Token | ! |
Token ID | 0 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
bilt | +1.855 |
NESS | +1.582 |
hess | +1.572 |
ewater | +1.489 |
�� | +1.463 |
Neg logit contributions | |
idates | -1.657 |
ependence | -1.655 |
los | -1.641 |
ogh | -1.634 |
yg | -1.547 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
bilt | +6.264 |
NESS | +5.277 |
hess | +5.150 |
ewater | +4.917 |
td | +4.712 |
Neg logit contributions | |
ependence | -5.855 |
ogh | -5.779 |
idates | -5.721 |
los | -5.702 |
ochond | -5.528 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bilt | +3.557 |
NESS | +2.984 |
hess | +2.954 |
ewater | +2.735 |
�� | +2.599 |
Neg logit contributions | |
ependence | -4.193 |
idates | -4.187 |
ogh | -4.145 |
los | -4.099 |
igree | -3.981 |
Token | Speed |
Token ID | 22785 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
bilt | +9.749 |
NESS | +8.255 |
Per | +8.236 |
hess | +7.870 |
Week | +7.305 |
Neg logit contributions | |
ogh | -11.065 |
ependence | -11.022 |
idates | -10.567 |
igree | -10.494 |
ochond | -10.346 |
Token | - |
Token ID | 532 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
bilt | +0.954 |
NESS | +0.802 |
hess | +0.793 |
ewater | +0.753 |
�� | +0.733 |
Neg logit contributions | |
idates | -0.972 |
ependence | -0.965 |
los | -0.960 |
ogh | -0.958 |
yg | -0.913 |
Token | Best |
Token ID | 6705 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
bilt | +6.247 |
NESS | +5.252 |
hess | +5.124 |
ewater | +4.950 |
�� | +4.747 |
Neg logit contributions | |
ependence | -5.336 |
ogh | -5.269 |
los | -5.244 |
idates | -5.219 |
ochond | -5.037 |
Token | top |
Token ID | 1353 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
bilt | +2.129 |
NESS | +1.793 |
hess | +1.764 |
ewater | +1.666 |
�� | +1.633 |
Neg logit contributions | |
ependence | -2.206 |
idates | -2.206 |
los | -2.187 |
ogh | -2.178 |
yg | -2.076 |
Token | speed |
Token ID | 2866 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
bilt | +1.637 |
NESS | +1.336 |
hess | +1.318 |
ewater | +1.235 |
�� | +1.203 |
Neg logit contributions | |
idates | -2.181 |
ependence | -2.178 |
los | -2.159 |
ogh | -2.147 |
yg | -2.063 |
Token | � |
Token ID | 564 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
bilt | +1.168 |
NESS | +1.001 |
hess | +0.988 |
ewater | +0.931 |
�� | +0.912 |
Neg logit contributions | |
idates | -1.101 |
ependence | -1.101 |
los | -1.092 |
ogh | -1.088 |
yg | -1.032 |
Token | � |
Token ID | 250 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
bilt | +1.644 |
NESS | +1.288 |
hess | +1.250 |
�� | +1.173 |
ewater | +1.131 |
Neg logit contributions | |
ependence | -3.155 |
idates | -3.152 |
los | -3.122 |
ogh | -3.114 |
ochond | -3.015 |
Token | Now |
Token ID | 3844 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
bilt | +3.811 |
NESS | +3.287 |
hess | +3.239 |
ewater | +3.032 |
�� | +2.929 |
Neg logit contributions | |
idates | -3.652 |
ependence | -3.631 |
ogh | -3.602 |
los | -3.586 |
igree | -3.439 |
Token | that |
Token ID | 326 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
bilt | +2.631 |
NESS | +2.247 |
hess | +2.230 |
ewater | +2.112 |
�� | +2.080 |
Neg logit contributions | |
idates | -2.221 |
ependence | -2.206 |
los | -2.196 |
ogh | -2.182 |
yg | -2.066 |
Token | may |
Token ID | 743 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
bilt | +2.600 |
NESS | +2.220 |
hess | +2.205 |
ewater | +2.080 |
�� | +2.051 |
Neg logit contributions | |
idates | -2.228 |
ependence | -2.225 |
los | -2.205 |
ogh | -2.196 |
yg | -2.077 |
Token | or |
Token ID | 393 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
idates | +2.447 |
ogh | +2.440 |
los | +2.436 |
ependence | +2.432 |
yg | +2.310 |
Neg logit contributions | |
bilt | -3.177 |
hess | -2.737 |
NESS | -2.712 |
�� | -2.578 |
ewater | -2.562 |
Token | may |
Token ID | 743 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
bilt | +6.764 |
NESS | +5.527 |
hess | +5.379 |
Per | +4.647 |
ewater | +4.641 |
Neg logit contributions | |
idates | -13.457 |
los | -12.982 |
ochond | -12.908 |
)+ | -12.890 |
ependence | -12.855 |
Token | not |
Token ID | 407 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
bilt | +2.324 |
NESS | +1.965 |
hess | +1.943 |
ewater | +1.815 |
�� | +1.782 |
Neg logit contributions | |
idates | -2.515 |
ependence | -2.504 |
los | -2.483 |
ogh | -2.470 |
yg | -2.360 |
Token | be |
Token ID | 307 |
Feature activation | -3.69e-04 |
Pos logit contributions | |
idates | +2.915 |
ogh | +2.897 |
los | +2.893 |
ependence | +2.870 |
yg | +2.758 |
Neg logit contributions | |
bilt | -3.927 |
hess | -3.377 |
NESS | -3.368 |
�� | -3.171 |
ewater | -3.169 |
Token | a |
Token ID | 257 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
bilt | +0.004 |
NESS | +0.003 |
hess | +0.003 |
ewater | +0.003 |
�� | +0.003 |
Neg logit contributions | |
idates | -0.003 |
ependence | -0.003 |
los | -0.003 |
ogh | -0.003 |
yg | -0.003 |
Token | good |
Token ID | 922 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
bilt | +0.450 |
NESS | +0.385 |
hess | +0.383 |
ewater | +0.362 |
�� | +0.358 |
Neg logit contributions | |
idates | -0.385 |
ependence | -0.383 |
los | -0.382 |
ogh | -0.379 |
yg | -0.359 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
bilt | +2.754 |
NESS | +2.221 |
hess | +2.211 |
ewater | +2.004 |
�� | +1.895 |
Neg logit contributions | |
ependence | -4.146 |
idates | -4.139 |
ogh | -4.115 |
los | -4.071 |
igree | -3.961 |
Token | . |
Token ID | 764 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
los | +0.660 |
idates | +0.659 |
ependence | +0.651 |
ogh | +0.649 |
yg | +0.625 |
Neg logit contributions | |
bilt | -0.831 |
NESS | -0.711 |
hess | -0.702 |
�� | -0.695 |
ewater | -0.678 |
Token | MOR |
Token ID | 35208 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
bilt | +5.713 |
NESS | +5.013 |
hess | +4.728 |
ewater | +4.486 |
�� | +4.448 |
Neg logit contributions | |
los | -4.623 |
ependence | -4.590 |
idates | -4.484 |
ogh | -4.470 |
sung | -4.347 |
Token | PH |
Token ID | 11909 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
idates | +0.337 |
ogh | +0.337 |
los | +0.335 |
ependence | +0.332 |
yg | +0.312 |
Neg logit contributions | |
bilt | -0.632 |
hess | -0.548 |
NESS | -0.540 |
ewater | -0.537 |
�� | -0.530 |
Token | _ |
Token ID | 62 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
bilt | +4.325 |
NESS | +3.854 |
hess | +3.745 |
ewater | +3.496 |
�� | +3.387 |
Neg logit contributions | |
ependence | -3.404 |
idates | -3.389 |
ogh | -3.363 |
los | -3.330 |
igree | -3.229 |
Token | BL |
Token ID | 9148 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bilt | +4.349 |
NESS | +3.842 |
hess | +3.366 |
Per | +2.900 |
�� | +2.889 |
Neg logit contributions | |
idates | -7.727 |
ependence | -7.721 |
ogh | -7.581 |
los | -7.563 |
igree | -7.515 |
Token | ACK |
Token ID | 8120 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
NESS | +8.901 |
bilt | +8.516 |
hess | +7.318 |
DX | +6.894 |
Per | +6.721 |
Neg logit contributions | |
idates | -11.972 |
los | -11.717 |
igree | -11.635 |
ependence | -11.620 |
ocrates | -11.149 |
Token | H |
Token ID | 39 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
NESS | +7.348 |
bilt | +7.345 |
hess | +6.519 |
Per | +5.616 |
td | +5.440 |
Neg logit contributions | |
idates | -10.393 |
ependence | -10.380 |
igree | -10.128 |
los | -10.111 |
entary | -10.006 |
Token | AT |
Token ID | 1404 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
bilt | +1.029 |
hess | +0.875 |
NESS | +0.872 |
ewater | +0.837 |
�� | +0.828 |
Neg logit contributions | |
idates | -0.829 |
ependence | -0.824 |
los | -0.821 |
ogh | -0.820 |
yg | -0.773 |
Token | , |
Token ID | 837 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
bilt | +5.298 |
NESS | +4.683 |
hess | +4.491 |
ewater | +4.072 |
td | +3.937 |
Neg logit contributions | |
idates | -6.727 |
ependence | -6.706 |
ogh | -6.582 |
los | -6.542 |
igree | -6.518 |
Token | rect |
Token ID | 13621 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
bilt | +5.148 |
hess | +4.253 |
NESS | +4.245 |
td | +3.813 |
ewater | +3.641 |
Neg logit contributions | |
idates | -8.938 |
los | -8.914 |
ependence | -8.849 |
sung | -8.621 |
ogh | -8.536 |
Token | : |
Token ID | 25 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
idates | +0.662 |
ependence | +0.662 |
los | +0.661 |
ogh | +0.651 |
yg | +0.613 |
Neg logit contributions | |
bilt | -1.027 |
NESS | -0.893 |
hess | -0.888 |
�� | -0.854 |
ewater | -0.853 |
Token | 17 |
Token ID | 1558 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
los | +3.413 |
idates | +3.223 |
bu | +3.115 |
)+ | +3.097 |
ogh | +3.060 |
Neg logit contributions | |
bilt | -6.518 |
�� | -5.964 |
ewater | -5.728 |
hess | -5.707 |
�� | -5.598 |
Token | UTC |
Token ID | 18119 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
bilt | +2.212 |
NESS | +1.881 |
hess | +1.872 |
ewater | +1.726 |
�� | +1.703 |
Neg logit contributions | |
idates | -2.274 |
ependence | -2.251 |
ogh | -2.234 |
los | -2.227 |
yg | -2.128 |
Token | ): |
Token ID | 2599 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
bilt | +4.532 |
NESS | +3.885 |
hess | +3.880 |
ewater | +3.596 |
�� | +3.517 |
Neg logit contributions | |
idates | -3.959 |
ependence | -3.950 |
ogh | -3.902 |
los | -3.855 |
igree | -3.745 |
Token | PA |
Token ID | 4537 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
bilt | +1.849 |
NESS | +1.596 |
hess | +1.586 |
ewater | +1.500 |
�� | +1.481 |
Neg logit contributions | |
idates | -1.443 |
ependence | -1.438 |
los | -1.427 |
ogh | -1.422 |
yg | -1.338 |
Token | UL |
Token ID | 6239 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
bilt | +1.825 |
NESS | +1.588 |
hess | +1.578 |
ewater | +1.494 |
�� | +1.477 |
Neg logit contributions | |
idates | -1.289 |
ependence | -1.287 |
los | -1.279 |
ogh | -1.273 |
yg | -1.188 |
Token | I |
Token ID | 40 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
bilt | +10.393 |
NESS | +9.621 |
hess | +8.805 |
td | +8.137 |
の� | +7.891 |
Neg logit contributions | |
ependence | -10.107 |
ogh | -9.724 |
idates | -9.647 |
igree | -9.571 |
ochond | -9.456 |
Token | RE |
Token ID | 4526 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
bilt | +3.603 |
NESS | +3.170 |
hess | +3.102 |
ewater | +2.913 |
�� | +2.872 |
Neg logit contributions | |
ependence | -2.838 |
idates | -2.824 |
los | -2.789 |
ogh | -2.778 |
igree | -2.644 |
Token | IN |
Token ID | 1268 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
bilt | +5.039 |
NESS | +4.558 |
hess | +4.367 |
ewater | +4.057 |
�� | +4.053 |
Neg logit contributions | |
ependence | -3.650 |
idates | -3.601 |
los | -3.572 |
ogh | -3.523 |
igree | -3.374 |
Token | IK |
Token ID | 18694 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
bilt | +2.855 |
NESS | +2.533 |
hess | +2.481 |
ewater | +2.282 |
�� | +2.272 |
Neg logit contributions | |
idates | -2.370 |
ependence | -2.342 |
los | -2.311 |
ogh | -2.310 |
yg | -2.177 |
Token | AIN |
Token ID | 29833 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
bilt | +2.580 |
NESS | +2.258 |
hess | +2.210 |
ewater | +2.063 |
�� | +2.054 |
Neg logit contributions | |
idates | -2.166 |
ependence | -2.165 |
los | -2.131 |
ogh | -2.124 |
yg | -2.017 |
Token | partner |
Token ID | 5212 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
bilt | +1.151 |
NESS | +0.990 |
hess | +0.982 |
ewater | +0.930 |
�� | +0.924 |
Neg logit contributions | |
idates | -0.931 |
ependence | -0.929 |
los | -0.924 |
ogh | -0.916 |
yg | -0.867 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ependence | +1.132 |
idates | +1.132 |
los | +1.124 |
ogh | +1.112 |
yg | +1.053 |
Neg logit contributions | |
bilt | -1.503 |
NESS | -1.299 |
hess | -1.292 |
�� | -1.228 |
ewater | -1.225 |
Token | the |
Token ID | 262 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
ependence | +0.980 |
idates | +0.980 |
los | +0.968 |
ogh | +0.965 |
yg | +0.908 |
Neg logit contributions | |
bilt | -1.284 |
NESS | -1.102 |
hess | -1.101 |
�� | -1.038 |
ewater | -1.038 |
Token | National |
Token ID | 2351 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
bilt | +0.045 |
NESS | +0.039 |
hess | +0.039 |
ewater | +0.037 |
�� | +0.037 |
Neg logit contributions | |
idates | -0.023 |
ependence | -0.022 |
los | -0.022 |
ogh | -0.022 |
yg | -0.020 |
Token | Party |
Token ID | 3615 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
idates | +0.694 |
ependence | +0.693 |
los | +0.687 |
ogh | +0.681 |
yg | +0.641 |
Neg logit contributions | |
bilt | -0.922 |
NESS | -0.800 |
hess | -0.792 |
ewater | -0.745 |
�� | -0.745 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
idates | +1.345 |
ependence | +1.343 |
los | +1.331 |
ogh | +1.320 |
yg | +1.249 |
Neg logit contributions | |
bilt | -1.593 |
NESS | -1.366 |
hess | -1.356 |
ewater | -1.281 |
�� | -1.269 |
Token | 190 |
Token ID | 19782 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
bilt | +8.911 |
NESS | +6.942 |
hess | +6.793 |
cakes | +6.165 |
Per | +6.118 |
Neg logit contributions | |
ependence | -11.528 |
ogh | -11.387 |
yg | -11.147 |
igree | -10.956 |
los | -10.921 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
bilt | +1.623 |
NESS | +1.345 |
hess | +1.339 |
ewater | +1.248 |
�� | +1.219 |
Neg logit contributions | |
idates | -1.885 |
ependence | -1.879 |
los | -1.869 |
ogh | -1.856 |
yg | -1.768 |
Token | 191 |
Token ID | 26492 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
bilt | +8.727 |
NESS | +7.135 |
hess | +6.986 |
Per | +6.364 |
cci | +5.812 |
Neg logit contributions | |
ependence | -12.425 |
yg | -12.139 |
ochond | -11.972 |
ogh | -11.921 |
igree | -11.827 |
Token | ] |
Token ID | 60 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
bilt | +1.577 |
NESS | +1.269 |
hess | +1.269 |
ewater | +1.178 |
�� | +1.150 |
Neg logit contributions | |
idates | -2.067 |
los | -2.048 |
ependence | -2.046 |
ogh | -2.024 |
ocrates | -1.952 |
Token | Within |
Token ID | 12511 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
idates | +0.917 |
ependence | +0.905 |
los | +0.905 |
ogh | +0.895 |
yg | +0.845 |
Neg logit contributions | |
bilt | -1.328 |
hess | -1.156 |
NESS | -1.153 |
�� | -1.107 |
ewater | -1.099 |
Token | will |
Token ID | 481 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
bilt | +1.999 |
NESS | +1.699 |
hess | +1.688 |
ewater | +1.589 |
�� | +1.563 |
Neg logit contributions | |
idates | -1.904 |
ependence | -1.898 |
los | -1.887 |
ogh | -1.877 |
yg | -1.779 |
Token | contain |
Token ID | 3994 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
bilt | +2.110 |
NESS | +1.834 |
hess | +1.824 |
ewater | +1.733 |
�� | +1.716 |
Neg logit contributions | |
idates | -1.459 |
ependence | -1.455 |
los | -1.445 |
ogh | -1.436 |
yg | -1.349 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
bilt | +1.294 |
NESS | +1.114 |
hess | +1.107 |
ewater | +1.048 |
�� | +1.038 |
Neg logit contributions | |
idates | -1.054 |
ependence | -1.051 |
los | -1.046 |
ogh | -1.038 |
yg | -0.983 |
Token | instructions |
Token ID | 7729 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
idates | +1.128 |
los | +1.121 |
ependence | +1.116 |
ogh | +1.087 |
yg | +1.050 |
Neg logit contributions | |
bilt | -1.130 |
NESS | -0.945 |
hess | -0.938 |
ewater | -0.892 |
�� | -0.869 |
Token | to |
Token ID | 284 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
bilt | +0.437 |
NESS | +0.370 |
hess | +0.367 |
�� | +0.348 |
ewater | +0.346 |
Neg logit contributions | |
idates | -0.408 |
los | -0.408 |
ependence | -0.408 |
ogh | -0.402 |
yg | -0.384 |
Token | create |
Token ID | 2251 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
bilt | +4.906 |
NESS | +4.242 |
hess | +4.178 |
ewater | +3.943 |
�� | +3.852 |
Neg logit contributions | |
ependence | -4.605 |
idates | -4.583 |
ogh | -4.571 |
los | -4.535 |
ocrates | -4.286 |
Token | lambda |
Token ID | 37456 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
bilt | +6.408 |
hess | +5.100 |
td | +4.826 |
NESS | +4.794 |
ewater | +4.525 |
Neg logit contributions | |
idates | -12.694 |
ependence | -12.436 |
los | -12.421 |
ogh | -12.407 |
sung | -12.211 |
Token | functions |
Token ID | 5499 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
bilt | +5.201 |
hess | +4.294 |
NESS | +4.180 |
ewater | +3.653 |
�� | +3.550 |
Neg logit contributions | |
ependence | -10.143 |
los | -9.868 |
idates | -9.846 |
igree | -9.794 |
ogh | -9.787 |
Token | using |
Token ID | 1262 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
bilt | +1.343 |
NESS | +1.145 |
hess | +1.139 |
ewater | +1.072 |
�� | +1.066 |
Neg logit contributions | |
idates | -1.190 |
ependence | -1.190 |
los | -1.180 |
ogh | -1.178 |
yg | -1.116 |
Token | the |
Token ID | 262 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
bilt | +2.334 |
NESS | +1.989 |
hess | +1.979 |
ewater | +1.866 |
�� | +1.834 |
Neg logit contributions | |
idates | -2.048 |
ependence | -2.042 |
los | -2.025 |
ogh | -2.016 |
yg | -1.901 |
Token | archived |
Token ID | 33962 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
bilt | +1.839 |
NESS | +1.549 |
hess | +1.546 |
ewater | +1.449 |
�� | +1.434 |
Neg logit contributions | |
idates | -1.855 |
ependence | -1.850 |
los | -1.832 |
ogh | -1.827 |
yg | -1.727 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ependence | +2.305 |
los | +2.296 |
idates | +2.271 |
ogh | +2.262 |
yg | +2.137 |
Neg logit contributions | |
bilt | -3.212 |
NESS | -2.747 |
hess | -2.717 |
ewater | -2.642 |
�� | -2.595 |
Token | and |
Token ID | 290 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
los | +1.326 |
idates | +1.323 |
ogh | +1.318 |
ependence | +1.318 |
yg | +1.235 |
Neg logit contributions | |
bilt | -1.632 |
hess | -1.393 |
NESS | -1.388 |
ewater | -1.313 |
�� | -1.311 |
Token | getting |
Token ID | 1972 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
idates | +2.536 |
ogh | +2.519 |
los | +2.506 |
ependence | +2.501 |
Goldman | +2.360 |
Neg logit contributions | |
bilt | -3.343 |
hess | -2.851 |
NESS | -2.814 |
ewater | -2.715 |
�� | -2.704 |
Token | bigger |
Token ID | 5749 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
idates | +0.814 |
ependence | +0.814 |
los | +0.811 |
ogh | +0.810 |
yg | +0.764 |
Neg logit contributions | |
bilt | -0.971 |
NESS | -0.830 |
hess | -0.822 |
�� | -0.782 |
ewater | -0.778 |
Token | week |
Token ID | 1285 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
los | +2.689 |
ependence | +2.664 |
idates | +2.655 |
ogh | +2.629 |
yg | +2.479 |
Neg logit contributions | |
bilt | -3.447 |
hess | -2.954 |
NESS | -2.911 |
�� | -2.803 |
ewater | -2.763 |
Token | by |
Token ID | 416 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
bilt | +0.035 |
NESS | +0.030 |
hess | +0.029 |
�� | +0.028 |
ewater | +0.028 |
Neg logit contributions | |
idates | -0.029 |
los | -0.029 |
ependence | -0.029 |
ogh | -0.029 |
yg | -0.027 |
Token | week |
Token ID | 1285 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
bilt | +6.780 |
dime | +5.091 |
NESS | +4.898 |
td | +4.776 |
ewater | +4.748 |
Neg logit contributions | |
ependence | -13.173 |
idates | -13.091 |
los | -12.939 |
ogh | -12.703 |
sung | -12.618 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
los | +3.135 |
ependence | +3.132 |
idates | +3.122 |
ogh | +3.107 |
bu | +2.879 |
Neg logit contributions | |
bilt | -4.436 |
NESS | -3.826 |
hess | -3.809 |
ewater | -3.653 |
�� | -3.645 |
Token | First |
Token ID | 3274 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
idates | +2.601 |
los | +2.594 |
ependence | +2.569 |
ogh | +2.534 |
Goldman | +2.433 |
Neg logit contributions | |
bilt | -3.810 |
hess | -3.265 |
NESS | -3.259 |
�� | -3.187 |
ewater | -3.171 |
Token | it |
Token ID | 340 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
idates | +1.297 |
ependence | +1.288 |
ogh | +1.280 |
los | +1.276 |
yg | +1.200 |
Neg logit contributions | |
bilt | -1.629 |
hess | -1.399 |
NESS | -1.396 |
ewater | -1.315 |
�� | -1.312 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
idates | +0.477 |
ependence | +0.472 |
ogh | +0.469 |
los | +0.469 |
yg | +0.440 |
Neg logit contributions | |
bilt | -0.648 |
NESS | -0.561 |
hess | -0.556 |
�� | -0.533 |
ewater | -0.528 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
bilt | +2.616 |
NESS | +2.219 |
hess | +2.205 |
ewater | +2.075 |
�� | +2.048 |
Neg logit contributions | |
idates | -2.511 |
ependence | -2.504 |
los | -2.491 |
ogh | -2.477 |
yg | -2.353 |
Token | few |
Token ID | 1178 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
bilt | +2.102 |
NESS | +1.793 |
hess | +1.787 |
ewater | +1.691 |
�� | +1.661 |
Neg logit contributions | |
idates | -1.857 |
ependence | -1.852 |
los | -1.838 |
ogh | -1.836 |
yg | -1.734 |
Token | minutes |
Token ID | 2431 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
idates | +1.249 |
ependence | +1.238 |
los | +1.234 |
ogh | +1.227 |
yg | +1.151 |
Neg logit contributions | |
bilt | -1.745 |
NESS | -1.492 |
hess | -1.472 |
�� | -1.426 |
ewater | -1.386 |
Token | until |
Token ID | 1566 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
bilt | +0.379 |
NESS | +0.339 |
hess | +0.335 |
�� | +0.322 |
ewater | +0.322 |
Neg logit contributions | |
ependence | -0.124 |
idates | -0.123 |
ogh | -0.120 |
los | -0.120 |
)+ | -0.108 |
Token | fork |
Token ID | 15563 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
bilt | +4.930 |
hess | +4.063 |
NESS | +4.038 |
ewater | +3.838 |
�� | +3.668 |
Neg logit contributions | |
idates | -5.628 |
los | -5.595 |
ependence | -5.569 |
ogh | -5.531 |
igree | -5.236 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
bilt | +6.806 |
hess | +5.687 |
NESS | +5.512 |
ewater | +5.241 |
td | +5.200 |
Neg logit contributions | |
idates | -7.201 |
ependence | -7.177 |
ogh | -7.094 |
los | -6.928 |
igree | -6.858 |
Token | t |
Token ID | 83 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
bilt | +8.198 |
hess | +6.702 |
td | +6.009 |
NESS | +5.924 |
ewater | +5.875 |
Neg logit contributions | |
idates | -11.850 |
ependence | -11.821 |
ogh | -11.576 |
ocrates | -11.534 |
igree | -11.341 |
Token | ender |
Token ID | 2194 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
bilt | +9.029 |
hess | +7.748 |
ewater | +7.337 |
NESS | +6.939 |
illard | +6.866 |
Neg logit contributions | |
los | -8.810 |
idates | -8.598 |
ependence | -8.274 |
ogh | -8.221 |
bu | -8.130 |
Token | . |
Token ID | 13 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
los | +2.090 |
ependence | +2.075 |
ogh | +2.071 |
idates | +2.050 |
)+ | +1.980 |
Neg logit contributions | |
bilt | -3.356 |
NESS | -2.941 |
�� | -2.918 |
hess | -2.898 |
�� | -2.813 |
Token | Chop |
Token ID | 40159 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
bilt | +5.263 |
hess | +4.317 |
NESS | +4.105 |
ewater | +3.682 |
�� | +3.595 |
Neg logit contributions | |
ependence | -8.450 |
idates | -8.308 |
los | -8.285 |
ogh | -8.167 |
igree | -7.882 |
Token | fl |
Token ID | 781 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
bilt | +4.203 |
NESS | +3.393 |
hess | +3.355 |
ewater | +3.232 |
td | +3.014 |
Neg logit contributions | |
idates | -5.921 |
ependence | -5.899 |
ogh | -5.787 |
los | -5.772 |
ocrates | -5.633 |
Token | investors |
Token ID | 7713 |
Feature activation | +8.51e-04 |
Pos logit contributions | |
bilt | +1.711 |
NESS | +1.461 |
hess | +1.448 |
ewater | +1.371 |
�� | +1.349 |
Neg logit contributions | |
idates | -1.506 |
ependence | -1.496 |
los | -1.489 |
ogh | -1.482 |
yg | -1.404 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
idates | +0.007 |
ependence | +0.007 |
los | +0.007 |
ogh | +0.007 |
yg | +0.007 |
Neg logit contributions | |
bilt | -0.009 |
NESS | -0.008 |
hess | -0.008 |
�� | -0.007 |
ewater | -0.007 |
Token | Green |
Token ID | 3469 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
bilt | +1.715 |
NESS | +1.485 |
hess | +1.478 |
ewater | +1.402 |
�� | +1.392 |
Neg logit contributions | |
idates | -1.245 |
ependence | -1.241 |
los | -1.234 |
ogh | -1.224 |
yg | -1.153 |
Token | for |
Token ID | 329 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
bilt | +2.405 |
NESS | +2.058 |
hess | +2.028 |
ewater | +1.937 |
�� | +1.874 |
Neg logit contributions | |
ependence | -2.162 |
idates | -2.161 |
los | -2.139 |
ogh | -2.128 |
yg | -2.020 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
bilt | +3.992 |
NESS | +3.420 |
hess | +3.339 |
ewater | +3.229 |
�� | +3.101 |
Neg logit contributions | |
ependence | -3.627 |
idates | -3.617 |
ogh | -3.588 |
los | -3.580 |
yg | -3.421 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
los | +1.312 |
idates | +1.311 |
ependence | +1.309 |
ogh | +1.299 |
yg | +1.214 |
Neg logit contributions | |
bilt | -1.655 |
NESS | -1.423 |
hess | -1.421 |
�� | -1.347 |
ewater | -1.328 |
Token | red |
Token ID | 2266 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
bilt | +8.644 |
NESS | +7.602 |
dime | +7.443 |
hess | +7.182 |
ewater | +7.124 |
Neg logit contributions | |
ependence | -10.762 |
ogh | -10.690 |
idates | -10.564 |
los | -10.502 |
sung | -10.182 |
Token | for |
Token ID | 329 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
bilt | +4.650 |
NESS | +3.978 |
hess | +3.812 |
ewater | +3.704 |
�� | +3.448 |
Neg logit contributions | |
idates | -6.094 |
ependence | -6.064 |
ogh | -6.010 |
los | -5.936 |
yg | -5.787 |
Token | natural |
Token ID | 3288 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bilt | +1.564 |
NESS | +1.367 |
hess | +1.354 |
ewater | +1.299 |
�� | +1.276 |
Neg logit contributions | |
idates | -0.987 |
ependence | -0.984 |
los | -0.974 |
ogh | -0.972 |
yg | -0.909 |
Token | gas |
Token ID | 3623 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
idates | +1.223 |
ependence | +1.223 |
los | +1.205 |
ogh | +1.198 |
yg | +1.106 |
Neg logit contributions | |
bilt | -2.526 |
NESS | -2.230 |
hess | -2.227 |
�� | -2.120 |
ewater | -2.101 |
Token | ." |
Token ID | 526 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
idates | +0.034 |
ependence | +0.034 |
los | +0.034 |
ogh | +0.034 |
yg | +0.032 |
Neg logit contributions | |
bilt | -0.042 |
NESS | -0.036 |
hess | -0.036 |
ewater | -0.034 |
�� | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
los | +2.744 |
ependence | +2.674 |
ogh | +2.622 |
idates | +2.616 |
yg | +2.516 |
Neg logit contributions | |
bilt | -4.518 |
�� | -4.011 |
NESS | -3.941 |
hess | -3.926 |
�� | -3.839 |
Token | Thank |
Token ID | 6952 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
los | +2.595 |
idates | +2.393 |
ependence | +2.370 |
bu | +2.302 |
ogh | +2.297 |
Neg logit contributions | |
bilt | -8.515 |
�� | -7.741 |
hess | -7.711 |
ewater | -7.672 |
NESS | -7.586 |
Token | you |
Token ID | 345 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ependence | +0.289 |
idates | +0.288 |
los | +0.288 |
ogh | +0.284 |
yg | +0.269 |
Neg logit contributions | |
bilt | -0.327 |
NESS | -0.279 |
hess | -0.277 |
�� | -0.264 |
ewater | -0.259 |
Token | for |
Token ID | 329 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
los | +1.842 |
ependence | +1.841 |
ogh | +1.837 |
idates | +1.815 |
yg | +1.732 |
Neg logit contributions | |
bilt | -2.322 |
NESS | -1.986 |
hess | -1.966 |
�� | -1.960 |
�� | -1.872 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ogh | +1.573 |
ependence | +1.560 |
los | +1.535 |
idates | +1.511 |
bu | +1.478 |
Neg logit contributions | |
bilt | -2.744 |
NESS | -2.430 |
hess | -2.389 |
�� | -2.336 |
ewater | -2.256 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
los | +2.778 |
idates | +2.728 |
ependence | +2.701 |
ogh | +2.684 |
yg | +2.559 |
Neg logit contributions | |
bilt | -4.642 |
�� | -4.092 |
NESS | -4.041 |
hess | -4.038 |
�� | -3.989 |
Token | An |
Token ID | 1052 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
los | +2.771 |
ogh | +2.716 |
ependence | +2.627 |
bu | +2.616 |
idates | +2.564 |
Neg logit contributions | |
bilt | -10.947 |
�� | -9.944 |
hess | -9.888 |
ewater | -9.712 |
�� | -9.572 |
Token | error |
Token ID | 4049 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
idates | +0.381 |
ependence | +0.380 |
los | +0.378 |
ogh | +0.373 |
yg | +0.356 |
Neg logit contributions | |
bilt | -0.598 |
NESS | -0.522 |
hess | -0.514 |
�� | -0.499 |
ewater | -0.496 |
Token | has |
Token ID | 468 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
los | +0.514 |
idates | +0.512 |
ependence | +0.510 |
ogh | +0.510 |
yg | +0.484 |
Neg logit contributions | |
bilt | -0.648 |
NESS | -0.564 |
�� | -0.544 |
hess | -0.536 |
ewater | -0.520 |
Token | occurred |
Token ID | 5091 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
bilt | +0.845 |
NESS | +0.734 |
hess | +0.723 |
�� | +0.689 |
ewater | +0.687 |
Neg logit contributions | |
idates | -0.619 |
los | -0.616 |
ependence | -0.614 |
ogh | -0.612 |
yg | -0.579 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
los | +0.706 |
idates | +0.702 |
ependence | +0.702 |
ogh | +0.696 |
yg | +0.662 |
Neg logit contributions | |
bilt | -0.973 |
NESS | -0.854 |
hess | -0.833 |
�� | -0.818 |
ewater | -0.799 |
Token | found |
Token ID | 1043 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
idates | +0.565 |
los | +0.559 |
ogh | +0.558 |
ependence | +0.552 |
yg | +0.523 |
Neg logit contributions | |
bilt | -0.741 |
NESS | -0.642 |
hess | -0.634 |
�� | -0.612 |
ewater | -0.601 |
Token | that |
Token ID | 326 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
idates | +0.277 |
los | +0.275 |
ogh | +0.274 |
ependence | +0.273 |
yg | +0.258 |
Neg logit contributions | |
bilt | -0.337 |
NESS | -0.288 |
hess | -0.286 |
�� | -0.271 |
ewater | -0.269 |
Token | having |
Token ID | 1719 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
bilt | +1.525 |
NESS | +1.301 |
hess | +1.293 |
ewater | +1.218 |
�� | +1.206 |
Neg logit contributions | |
idates | -1.371 |
ependence | -1.366 |
los | -1.359 |
ogh | -1.352 |
yg | -1.281 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
bilt | +1.382 |
NESS | +1.179 |
hess | +1.171 |
ewater | +1.104 |
�� | +1.092 |
Neg logit contributions | |
idates | -1.253 |
ependence | -1.249 |
los | -1.242 |
ogh | -1.236 |
yg | -1.172 |
Token | elbow |
Token ID | 22662 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
idates | +0.981 |
ependence | +0.979 |
los | +0.977 |
ogh | +0.974 |
yg | +0.927 |
Neg logit contributions | |
bilt | -1.043 |
NESS | -0.887 |
hess | -0.876 |
�� | -0.829 |
ewater | -0.826 |
Token | bent |
Token ID | 17157 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ogh | +3.328 |
los | +3.326 |
idates | +3.325 |
ependence | +3.318 |
yg | +3.160 |
Neg logit contributions | |
bilt | -4.070 |
NESS | -3.542 |
hess | -3.471 |
�� | -3.345 |
�� | -3.243 |
Token | at |
Token ID | 379 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ogh | +5.347 |
idates | +5.264 |
ependence | +5.172 |
los | +5.163 |
yg | +4.998 |
Neg logit contributions | |
bilt | -7.610 |
NESS | -6.460 |
hess | -6.415 |
�� | -6.378 |
�� | -6.228 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
idates | +3.279 |
ogh | +3.219 |
ependence | +3.199 |
los | +3.193 |
yg | +3.019 |
Neg logit contributions | |
bilt | -4.439 |
NESS | -3.864 |
hess | -3.824 |
�� | -3.666 |
�� | -3.580 |
Token | degrees |
Token ID | 7370 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
idates | +3.441 |
ogh | +3.431 |
ependence | +3.424 |
los | +3.409 |
yg | +3.298 |
Neg logit contributions | |
bilt | -3.986 |
NESS | -3.400 |
hess | -3.374 |
�� | -3.274 |
ewater | -3.150 |
Token | was |
Token ID | 373 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
idates | +1.527 |
ogh | +1.512 |
los | +1.503 |
ependence | +1.502 |
yg | +1.420 |
Neg logit contributions | |
bilt | -1.893 |
NESS | -1.626 |
hess | -1.613 |
�� | -1.542 |
ewater | -1.525 |
Token | actually |
Token ID | 1682 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
idates | +1.734 |
los | +1.732 |
ogh | +1.722 |
ependence | +1.695 |
ocrates | +1.617 |
Neg logit contributions | |
bilt | -2.114 |
NESS | -1.777 |
hess | -1.765 |
�� | -1.705 |
ewater | -1.688 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
bilt | +1.945 |
NESS | +1.640 |
hess | +1.629 |
ewater | +1.526 |
�� | +1.497 |
Neg logit contributions | |
idates | -2.029 |
ependence | -2.024 |
los | -2.009 |
ogh | -2.002 |
yg | -1.903 |
Token | The |
Token ID | 464 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
bilt | +0.249 |
NESS | +0.215 |
hess | +0.214 |
ewater | +0.202 |
�� | +0.200 |
Neg logit contributions | |
idates | -0.195 |
ependence | -0.194 |
los | -0.193 |
ogh | -0.192 |
yg | -0.181 |
Token | proposal |
Token ID | 6961 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
idates | +1.122 |
ependence | +1.116 |
los | +1.113 |
ogh | +1.102 |
yg | +1.056 |
Neg logit contributions | |
bilt | -0.903 |
NESS | -0.751 |
hess | -0.750 |
�� | -0.697 |
ewater | -0.686 |
Token | for |
Token ID | 329 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
idates | +1.055 |
los | +1.041 |
ependence | +1.039 |
ogh | +1.033 |
yg | +0.969 |
Neg logit contributions | |
bilt | -1.294 |
NESS | -1.112 |
hess | -1.096 |
�� | -1.061 |
ewater | -1.042 |
Token | the |
Token ID | 262 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
idates | +1.939 |
ependence | +1.934 |
los | +1.913 |
ogh | +1.897 |
yg | +1.791 |
Neg logit contributions | |
bilt | -2.367 |
NESS | -2.047 |
hess | -2.043 |
�� | -1.923 |
ewater | -1.909 |
Token | second |
Token ID | 1218 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
idates | +1.020 |
ependence | +1.015 |
los | +1.013 |
ogh | +1.001 |
yg | +0.961 |
Neg logit contributions | |
bilt | -0.854 |
hess | -0.712 |
NESS | -0.711 |
�� | -0.662 |
ewater | -0.656 |
Token | phase |
Token ID | 7108 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
idates | +5.136 |
los | +5.121 |
ogh | +5.008 |
ependence | +4.976 |
yg | +4.708 |
Neg logit contributions | |
bilt | -8.553 |
NESS | -7.482 |
�� | -7.410 |
hess | -7.373 |
ewater | -6.877 |
Token | would |
Token ID | 561 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
idates | +1.611 |
los | +1.586 |
ogh | +1.578 |
ependence | +1.578 |
yg | +1.476 |
Neg logit contributions | |
bilt | -1.991 |
NESS | -1.721 |
hess | -1.694 |
�� | -1.632 |
ewater | -1.594 |
Token | rebuild |
Token ID | 17884 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
idates | +1.658 |
ependence | +1.633 |
los | +1.633 |
ogh | +1.624 |
yg | +1.548 |
Neg logit contributions | |
bilt | -2.075 |
NESS | -1.781 |
hess | -1.776 |
�� | -1.688 |
ewater | -1.656 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
idates | +0.101 |
ependence | +0.101 |
los | +0.101 |
ogh | +0.100 |
yg | +0.095 |
Neg logit contributions | |
bilt | -0.119 |
NESS | -0.102 |
hess | -0.102 |
ewater | -0.096 |
�� | -0.095 |
Token | board |
Token ID | 3096 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ependence | +2.920 |
idates | +2.899 |
los | +2.885 |
ogh | +2.859 |
yg | +2.722 |
Neg logit contributions | |
bilt | -3.754 |
hess | -3.280 |
NESS | -3.238 |
�� | -3.105 |
ewater | -3.067 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
bilt | +2.647 |
NESS | +2.270 |
hess | +2.257 |
ewater | +2.123 |
�� | +2.077 |
Neg logit contributions | |
idates | -2.463 |
ependence | -2.435 |
los | -2.408 |
ogh | -2.400 |
yg | -2.271 |
Token | and |
Token ID | 290 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
ependence | +0.275 |
idates | +0.275 |
los | +0.274 |
ogh | +0.273 |
yg | +0.259 |
Neg logit contributions | |
bilt | -0.314 |
NESS | -0.266 |
hess | -0.266 |
�� | -0.250 |
ewater | -0.250 |
Token | important |
Token ID | 1593 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ependence | +0.430 |
idates | +0.428 |
los | +0.427 |
ogh | +0.425 |
yg | +0.402 |
Neg logit contributions | |
bilt | -0.523 |
NESS | -0.445 |
hess | -0.444 |
�� | -0.421 |
ewater | -0.420 |
Token | as |
Token ID | 355 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
bilt | +1.329 |
NESS | +1.123 |
hess | +1.117 |
ewater | +1.052 |
�� | +1.044 |
Neg logit contributions | |
idates | -1.270 |
ependence | -1.270 |
los | -1.263 |
ogh | -1.256 |
yg | -1.193 |
Token | Europe |
Token ID | 2031 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ependence | +1.225 |
idates | +1.218 |
los | +1.215 |
ogh | +1.209 |
yg | +1.146 |
Neg logit contributions | |
bilt | -1.647 |
hess | -1.393 |
NESS | -1.393 |
�� | -1.329 |
ewater | -1.322 |
Token | is |
Token ID | 318 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
ependence | +4.034 |
los | +3.971 |
idates | +3.909 |
ogh | +3.882 |
ocrates | +3.593 |
Neg logit contributions | |
bilt | -5.773 |
NESS | -5.051 |
hess | -4.968 |
�� | -4.852 |
ewater | -4.785 |
Token | as |
Token ID | 355 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
ependence | +5.418 |
los | +5.392 |
ogh | +5.192 |
Goldman | +5.066 |
idates | +4.980 |
Neg logit contributions | |
bilt | -8.427 |
�� | -7.235 |
NESS | -7.165 |
hess | -7.128 |
�� | -7.015 |
Token | a |
Token ID | 257 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ependence | +0.500 |
idates | +0.498 |
los | +0.496 |
ogh | +0.494 |
yg | +0.467 |
Neg logit contributions | |
bilt | -0.582 |
hess | -0.494 |
NESS | -0.493 |
ewater | -0.465 |
�� | -0.465 |
Token | marketplace |
Token ID | 17432 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ependence | +1.501 |
ogh | +1.488 |
idates | +1.473 |
los | +1.472 |
yg | +1.425 |
Neg logit contributions | |
bilt | -1.651 |
NESS | -1.383 |
hess | -1.379 |
�� | -1.333 |
ewater | -1.304 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ependence | +1.419 |
los | +1.398 |
ogh | +1.395 |
idates | +1.394 |
yg | +1.324 |
Neg logit contributions | |
bilt | -1.826 |
NESS | -1.549 |
hess | -1.537 |
�� | -1.484 |
ewater | -1.471 |
Token | it |
Token ID | 340 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ependence | +2.281 |
idates | +2.250 |
los | +2.244 |
ogh | +2.241 |
yg | +2.116 |
Neg logit contributions | |
bilt | -2.927 |
hess | -2.471 |
NESS | -2.465 |
�� | -2.385 |
ewater | -2.343 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ependence | +1.697 |
idates | +1.681 |
ogh | +1.675 |
los | +1.672 |
yg | +1.571 |
Neg logit contributions | |
bilt | -2.269 |
hess | -1.938 |
NESS | -1.931 |
ewater | -1.814 |
�� | -1.810 |
Token | whose |
Token ID | 3025 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
idates | +1.073 |
ependence | +1.069 |
los | +1.062 |
ogh | +1.060 |
yg | +0.999 |
Neg logit contributions | |
bilt | -1.377 |
hess | -1.189 |
NESS | -1.188 |
ewater | -1.110 |
�� | -1.108 |
Token | interests |
Token ID | 5353 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
idates | +0.633 |
ependence | +0.631 |
los | +0.631 |
ogh | +0.627 |
yg | +0.594 |
Neg logit contributions | |
bilt | -0.662 |
hess | -0.562 |
NESS | -0.555 |
�� | -0.524 |
ewater | -0.507 |
Token | Pruitt |
Token ID | 39637 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
bilt | +1.475 |
NESS | +1.259 |
hess | +1.244 |
ewater | +1.179 |
�� | +1.163 |
Neg logit contributions | |
idates | -1.354 |
ependence | -1.351 |
los | -1.345 |
ogh | -1.333 |
yg | -1.262 |
Token | really |
Token ID | 1107 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
idates | +0.894 |
ependence | +0.887 |
ogh | +0.883 |
los | +0.883 |
yg | +0.837 |
Neg logit contributions | |
bilt | -1.154 |
hess | -0.992 |
NESS | -0.992 |
ewater | -0.932 |
�� | -0.927 |
Token | serves |
Token ID | 9179 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
idates | +0.239 |
ogh | +0.236 |
los | +0.235 |
ependence | +0.235 |
yg | +0.223 |
Neg logit contributions | |
bilt | -0.295 |
NESS | -0.253 |
hess | -0.252 |
�� | -0.239 |
ewater | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ependence | +5.275 |
los | +5.242 |
ogh | +5.174 |
idates | +5.156 |
.# | +4.813 |
Neg logit contributions | |
bilt | -8.642 |
hess | -7.484 |
NESS | -7.449 |
�� | -7.080 |
�� | -7.051 |
Token | � |
Token ID | 447 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
idates | +3.761 |
ependence | +3.717 |
los | +3.701 |
ogh | +3.672 |
yg | +3.523 |
Neg logit contributions | |
bilt | -4.788 |
hess | -4.116 |
NESS | -4.088 |
�� | -3.890 |
ewater | -3.885 |
Token | � |
Token ID | 251 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
bilt | +1.075 |
NESS | +0.838 |
hess | +0.815 |
�� | +0.762 |
ewater | +0.726 |
Neg logit contributions | |
ependence | -2.223 |
idates | -2.220 |
los | -2.216 |
ogh | -2.200 |
ochond | -2.129 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
idates | +1.989 |
ependence | +1.982 |
los | +1.967 |
ogh | +1.954 |
yg | +1.864 |
Neg logit contributions | |
bilt | -2.316 |
NESS | -1.975 |
hess | -1.974 |
ewater | -1.864 |
�� | -1.855 |
Token | WH |
Token ID | 12418 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
bilt | +3.085 |
NESS | +2.665 |
hess | +2.642 |
ewater | +2.465 |
�� | +2.399 |
Neg logit contributions | |
ependence | -2.683 |
idates | -2.670 |
ogh | -2.631 |
los | -2.607 |
igree | -2.488 |
Token | cons |
Token ID | 762 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
los | +2.221 |
idates | +2.206 |
ependence | +2.203 |
ogh | +2.192 |
yg | +2.048 |
Neg logit contributions | |
bilt | -3.089 |
NESS | -2.702 |
hess | -2.697 |
�� | -2.592 |
ewater | -2.556 |
Token | ented |
Token ID | 4714 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
idates | +3.857 |
ependence | +3.815 |
los | +3.803 |
ogh | +3.713 |
yg | +3.548 |
Neg logit contributions | |
bilt | -5.849 |
NESS | -5.158 |
hess | -4.987 |
�� | -4.830 |
ewater | -4.774 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ependence | +1.697 |
los | +1.696 |
idates | +1.695 |
ogh | +1.683 |
yg | +1.591 |
Neg logit contributions | |
bilt | -2.007 |
NESS | -1.712 |
hess | -1.709 |
ewater | -1.609 |
�� | -1.605 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
los | +1.919 |
idates | +1.896 |
ogh | +1.890 |
ependence | +1.889 |
yg | +1.788 |
Neg logit contributions | |
bilt | -2.258 |
NESS | -1.956 |
hess | -1.935 |
�� | -1.863 |
ewater | -1.826 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
idates | +1.103 |
los | +1.099 |
ependence | +1.098 |
ogh | +1.092 |
yg | +1.029 |
Neg logit contributions | |
bilt | -1.270 |
NESS | -1.092 |
hess | -1.083 |
ewater | -1.024 |
�� | -1.012 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
los | +1.181 |
idates | +1.172 |
ependence | +1.167 |
ogh | +1.160 |
yg | +1.109 |
Neg logit contributions | |
bilt | -1.412 |
hess | -1.207 |
NESS | -1.207 |
�� | -1.141 |
ewater | -1.130 |
Token | of |
Token ID | 286 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
los | +1.666 |
idates | +1.640 |
ogh | +1.626 |
ependence | +1.625 |
bu | +1.529 |
Neg logit contributions | |
bilt | -2.353 |
NESS | -2.045 |
hess | -2.022 |
�� | -1.948 |
ewater | -1.901 |
Token | a |
Token ID | 257 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
bilt | +0.050 |
NESS | +0.043 |
hess | +0.043 |
ewater | +0.041 |
�� | +0.041 |
Neg logit contributions | |
idates | -0.033 |
los | -0.033 |
ependence | -0.033 |
ogh | -0.033 |
yg | -0.031 |
Token | recent |
Token ID | 2274 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
idates | +0.328 |
los | +0.326 |
ependence | +0.325 |
ogh | +0.322 |
yg | +0.307 |
Neg logit contributions | |
bilt | -0.376 |
NESS | -0.320 |
hess | -0.319 |
ewater | -0.301 |
�� | -0.299 |
Token | decision |
Token ID | 2551 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
bilt | +0.713 |
NESS | +0.613 |
hess | +0.610 |
ewater | +0.576 |
�� | +0.572 |
Neg logit contributions | |
idates | -0.588 |
ependence | -0.585 |
los | -0.584 |
ogh | -0.580 |
yg | -0.549 |
Token | by |
Token ID | 416 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
bilt | +0.933 |
NESS | +0.798 |
hess | +0.792 |
ewater | +0.748 |
�� | +0.741 |
Neg logit contributions | |
idates | -0.806 |
ependence | -0.803 |
los | -0.800 |
ogh | -0.795 |
yg | -0.753 |
Token | just |
Token ID | 655 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ependence | +1.950 |
idates | +1.935 |
los | +1.934 |
ogh | +1.930 |
yg | +1.826 |
Neg logit contributions | |
bilt | -2.410 |
NESS | -2.065 |
hess | -2.043 |
ewater | -1.942 |
�� | -1.921 |
Token | learning |
Token ID | 4673 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ependence | +2.794 |
ogh | +2.776 |
los | +2.770 |
idates | +2.735 |
yg | +2.604 |
Neg logit contributions | |
bilt | -3.336 |
NESS | -2.826 |
hess | -2.813 |
�� | -2.653 |
ewater | -2.631 |
Token | the |
Token ID | 262 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
bilt | +2.125 |
NESS | +1.835 |
hess | +1.819 |
ewater | +1.717 |
�� | +1.692 |
Neg logit contributions | |
idates | -1.837 |
ependence | -1.822 |
los | -1.801 |
ogh | -1.799 |
yg | -1.698 |
Token | layout |
Token ID | 12461 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
idates | +0.079 |
los | +0.078 |
ependence | +0.078 |
ogh | +0.078 |
yg | +0.074 |
Neg logit contributions | |
bilt | -0.088 |
NESS | -0.074 |
hess | -0.074 |
ewater | -0.070 |
�� | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ependence | +0.632 |
idates | +0.630 |
los | +0.626 |
ogh | +0.624 |
yg | +0.589 |
Neg logit contributions | |
bilt | -0.795 |
NESS | -0.680 |
hess | -0.674 |
ewater | -0.640 |
�� | -0.636 |
Token | Tal |
Token ID | 7193 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
bilt | +1.324 |
NESS | +1.133 |
hess | +1.124 |
ewater | +1.060 |
�� | +1.044 |
Neg logit contributions | |
idates | -1.167 |
ependence | -1.162 |
los | -1.153 |
ogh | -1.147 |
yg | -1.084 |
Token | os |
Token ID | 418 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
los | +3.812 |
ogh | +3.740 |
idates | +3.651 |
ependence | +3.619 |
ocrates | +3.408 |
Neg logit contributions | |
bilt | -5.042 |
�� | -4.445 |
NESS | -4.414 |
�� | -4.286 |
hess | -4.195 |
Token | - |
Token ID | 12 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
idates | +0.470 |
ependence | +0.469 |
los | +0.466 |
ogh | +0.463 |
yg | +0.437 |
Neg logit contributions | |
bilt | -0.602 |
NESS | -0.518 |
hess | -0.515 |
ewater | -0.488 |
�� | -0.484 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
idates | +1.821 |
ependence | +1.819 |
los | +1.809 |
ogh | +1.798 |
yg | +1.706 |
Neg logit contributions | |
bilt | -1.941 |
NESS | -1.649 |
hess | -1.641 |
ewater | -1.544 |
�� | -1.532 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
ependence | +2.012 |
los | +2.005 |
ogh | +1.980 |
idates | +1.978 |
yg | +1.900 |
Neg logit contributions | |
bilt | -2.833 |
NESS | -2.437 |
hess | -2.419 |
�� | -2.325 |
ewater | -2.322 |
Token | It |
Token ID | 632 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
idates | +0.027 |
los | +0.026 |
ependence | +0.026 |
ogh | +0.026 |
yg | +0.025 |
Neg logit contributions | |
bilt | -0.037 |
NESS | -0.032 |
hess | -0.031 |
�� | -0.030 |
ewater | -0.030 |
Token | from |
Token ID | 422 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
idates | +0.601 |
los | +0.601 |
ependence | +0.598 |
ogh | +0.595 |
yg | +0.563 |
Neg logit contributions | |
bilt | -0.736 |
NESS | -0.629 |
hess | -0.622 |
�� | -0.598 |
ewater | -0.582 |
Token | a |
Token ID | 257 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
idates | +0.084 |
ependence | +0.084 |
los | +0.084 |
ogh | +0.083 |
yg | +0.079 |
Neg logit contributions | |
bilt | -0.101 |
NESS | -0.087 |
hess | -0.086 |
ewater | -0.081 |
�� | -0.081 |
Token | North |
Token ID | 2258 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
bilt | +0.138 |
NESS | +0.118 |
hess | +0.117 |
ewater | +0.111 |
�� | +0.109 |
Neg logit contributions | |
idates | -0.124 |
ependence | -0.124 |
los | -0.123 |
ogh | -0.122 |
yg | -0.116 |
Token | Korean |
Token ID | 6983 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
bilt | +0.503 |
NESS | +0.431 |
hess | +0.429 |
ewater | +0.409 |
�� | +0.401 |
Neg logit contributions | |
idates | -0.380 |
ependence | -0.379 |
los | -0.376 |
ogh | -0.375 |
yg | -0.352 |
Token | prison |
Token ID | 3770 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
idates | +3.995 |
ependence | +3.949 |
ogh | +3.909 |
los | +3.901 |
bu | +3.777 |
Neg logit contributions | |
bilt | -6.329 |
hess | -5.556 |
NESS | -5.554 |
�� | -5.542 |
�� | -5.139 |
Token | last |
Token ID | 938 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
los | +2.009 |
idates | +1.995 |
ogh | +1.973 |
ependence | +1.973 |
bu | +1.890 |
Neg logit contributions | |
bilt | -2.864 |
NESS | -2.505 |
hess | -2.440 |
�� | -2.429 |
ewater | -2.316 |
Token | week |
Token ID | 1285 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
idates | +1.463 |
los | +1.447 |
ependence | +1.437 |
ogh | +1.434 |
yg | +1.369 |
Neg logit contributions | |
bilt | -1.625 |
NESS | -1.407 |
hess | -1.397 |
�� | -1.332 |
ewater | -1.303 |
Token | died |
Token ID | 3724 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
bilt | +0.255 |
NESS | +0.219 |
hess | +0.217 |
�� | +0.205 |
ewater | +0.205 |
Neg logit contributions | |
idates | -0.218 |
los | -0.217 |
ependence | -0.217 |
ogh | -0.216 |
yg | -0.204 |
Token | Monday |
Token ID | 3321 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
bilt | +0.169 |
NESS | +0.146 |
hess | +0.144 |
�� | +0.136 |
ewater | +0.136 |
Neg logit contributions | |
idates | -0.133 |
los | -0.133 |
ependence | -0.133 |
ogh | -0.132 |
yg | -0.124 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
bilt | +0.636 |
NESS | +0.544 |
hess | +0.539 |
ewater | +0.509 |
�� | +0.506 |
Neg logit contributions | |
idates | -0.562 |
ependence | -0.560 |
los | -0.560 |
ogh | -0.555 |
yg | -0.526 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
bilt | +0.436 |
NESS | +0.375 |
hess | +0.371 |
ewater | +0.351 |
�� | +0.350 |
Neg logit contributions | |
idates | -0.362 |
ependence | -0.361 |
los | -0.361 |
ogh | -0.358 |
yg | -0.338 |
Token | secondary |
Token ID | 9233 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ependence | +2.090 |
los | +2.078 |
idates | +2.078 |
ogh | +2.068 |
yg | +1.966 |
Neg logit contributions | |
bilt | -2.273 |
NESS | -1.938 |
hess | -1.924 |
ewater | -1.822 |
�� | -1.806 |
Token | function |
Token ID | 2163 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
los | +1.616 |
idates | +1.610 |
ependence | +1.606 |
ogh | +1.584 |
yg | +1.504 |
Neg logit contributions | |
bilt | -1.665 |
NESS | -1.405 |
hess | -1.399 |
�� | -1.325 |
ewater | -1.322 |
Token | to |
Token ID | 284 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
ependence | +0.763 |
idates | +0.763 |
los | +0.760 |
ogh | +0.754 |
yg | +0.712 |
Neg logit contributions | |
bilt | -0.923 |
NESS | -0.789 |
hess | -0.781 |
�� | -0.738 |
ewater | -0.737 |
Token | monitor |
Token ID | 5671 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
idates | +0.286 |
los | +0.282 |
ependence | +0.281 |
ogh | +0.280 |
yg | +0.265 |
Neg logit contributions | |
bilt | -0.311 |
NESS | -0.265 |
hess | -0.261 |
ewater | -0.247 |
�� | -0.246 |
Token | such |
Token ID | 884 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
los | +1.030 |
idates | +1.027 |
ependence | +1.020 |
ogh | +1.007 |
yg | +0.962 |
Neg logit contributions | |
bilt | -1.196 |
NESS | -1.025 |
hess | -1.020 |
ewater | -0.968 |
�� | -0.958 |
Token | effects |
Token ID | 3048 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
idates | +0.523 |
ependence | +0.523 |
los | +0.522 |
ogh | +0.514 |
yg | +0.492 |
Neg logit contributions | |
bilt | -0.538 |
NESS | -0.452 |
hess | -0.452 |
ewater | -0.428 |
�� | -0.426 |
Token | from |
Token ID | 422 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
bilt | +0.152 |
NESS | +0.130 |
hess | +0.129 |
ewater | +0.122 |
�� | +0.121 |
Neg logit contributions | |
idates | -0.126 |
ependence | -0.126 |
los | -0.125 |
ogh | -0.124 |
yg | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
bilt | +1.026 |
NESS | +0.878 |
hess | +0.872 |
ewater | +0.823 |
�� | +0.813 |
Neg logit contributions | |
idates | -0.893 |
ependence | -0.890 |
los | -0.884 |
ogh | -0.880 |
yg | -0.833 |
Token | engine |
Token ID | 3113 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
bilt | +1.202 |
NESS | +1.016 |
hess | +1.009 |
ewater | +0.948 |
�� | +0.936 |
Neg logit contributions | |
idates | -1.203 |
ependence | -1.200 |
los | -1.192 |
ogh | -1.187 |
yg | -1.128 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
bilt | +0.475 |
NESS | +0.408 |
hess | +0.406 |
ewater | +0.384 |
�� | +0.379 |
Neg logit contributions | |
idates | -0.393 |
ependence | -0.392 |
los | -0.390 |
ogh | -0.388 |
yg | -0.366 |
Token | No |
Token ID | 1400 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
bilt | +1.442 |
NESS | +1.248 |
hess | +1.242 |
ewater | +1.178 |
�� | +1.167 |
Neg logit contributions | |
idates | -1.063 |
ependence | -1.059 |
los | -1.053 |
ogh | -1.046 |
yg | -0.985 |
Token | as |
Token ID | 355 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
bilt | +1.879 |
NESS | +1.585 |
hess | +1.583 |
ewater | +1.476 |
�� | +1.456 |
Neg logit contributions | |
idates | -1.872 |
ependence | -1.866 |
los | -1.855 |
ogh | -1.845 |
yg | -1.760 |
Token | a |
Token ID | 257 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
idates | +1.620 |
ependence | +1.607 |
los | +1.601 |
ogh | +1.590 |
yg | +1.488 |
Neg logit contributions | |
bilt | -2.013 |
NESS | -1.716 |
hess | -1.713 |
ewater | -1.619 |
�� | -1.614 |
Token | " |
Token ID | 366 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
bilt | +0.207 |
NESS | +0.178 |
hess | +0.177 |
ewater | +0.167 |
�� | +0.166 |
Neg logit contributions | |
idates | -0.175 |
ependence | -0.174 |
los | -0.173 |
ogh | -0.172 |
yg | -0.163 |
Token | def |
Token ID | 4299 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
los | +2.179 |
ependence | +2.138 |
idates | +2.127 |
ogh | +2.097 |
bu | +2.012 |
Neg logit contributions | |
bilt | -2.754 |
NESS | -2.382 |
hess | -2.370 |
�� | -2.290 |
ewater | -2.262 |
Token | ining |
Token ID | 3191 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
bilt | +0.179 |
NESS | +0.157 |
hess | +0.156 |
ewater | +0.149 |
�� | +0.147 |
Neg logit contributions | |
idates | -0.113 |
ependence | -0.112 |
los | -0.111 |
ogh | -0.111 |
yg | -0.104 |
Token | moment |
Token ID | 2589 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
bilt | +2.781 |
NESS | +2.342 |
hess | +2.298 |
ewater | +2.146 |
�� | +2.085 |
Neg logit contributions | |
idates | -3.143 |
ependence | -3.143 |
los | -3.105 |
ogh | -3.104 |
ochond | -2.950 |
Token | in |
Token ID | 287 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
idates | +1.600 |
los | +1.597 |
ependence | +1.589 |
ogh | +1.575 |
ochond | +1.467 |
Neg logit contributions | |
bilt | -2.432 |
NESS | -2.102 |
hess | -2.088 |
�� | -2.009 |
ewater | -2.007 |
Token | solid |
Token ID | 4735 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
bilt | +2.957 |
NESS | +2.508 |
hess | +2.479 |
ewater | +2.346 |
�� | +2.279 |
Neg logit contributions | |
idates | -2.920 |
ependence | -2.903 |
los | -2.897 |
ogh | -2.879 |
yg | -2.756 |
Token | , |
Token ID | 11 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
bilt | +3.121 |
NESS | +2.693 |
hess | +2.677 |
ewater | +2.526 |
�� | +2.440 |
Neg logit contributions | |
idates | -2.707 |
ependence | -2.683 |
los | -2.678 |
ogh | -2.658 |
yg | -2.522 |
Token | strategic |
Token ID | 10039 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
idates | +2.367 |
ependence | +2.351 |
ogh | +2.351 |
los | +2.348 |
yg | +2.223 |
Neg logit contributions | |
bilt | -2.590 |
NESS | -2.208 |
hess | -2.163 |
�� | -2.077 |
ewater | -2.052 |
Token | partnership |
Token ID | 10413 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
bilt | +1.084 |
NESS | +0.909 |
hess | +0.903 |
ewater | +0.848 |
�� | +0.847 |
Neg logit contributions | |
idates | -1.123 |
ependence | -1.123 |
los | -1.116 |
ogh | -1.111 |
yg | -1.057 |
Token | School |
Token ID | 3961 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
idates | +1.356 |
ependence | +1.354 |
los | +1.335 |
ogh | +1.332 |
yg | +1.259 |
Neg logit contributions | |
bilt | -1.572 |
NESS | -1.345 |
hess | -1.338 |
�� | -1.265 |
ewater | -1.264 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
idates | +2.254 |
ependence | +2.246 |
los | +2.225 |
ogh | +2.201 |
yg | +2.069 |
Neg logit contributions | |
bilt | -3.029 |
hess | -2.622 |
NESS | -2.613 |
�� | -2.496 |
ewater | -2.491 |
Token | Los |
Token ID | 5401 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
ependence | +1.191 |
idates | +1.187 |
los | +1.178 |
ogh | +1.169 |
yg | +1.106 |
Neg logit contributions | |
bilt | -1.473 |
NESS | -1.274 |
hess | -1.264 |
�� | -1.195 |
ewater | -1.195 |
Token | Angeles |
Token ID | 5652 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
idates | +0.529 |
los | +0.526 |
ependence | +0.524 |
ogh | +0.518 |
yg | +0.497 |
Neg logit contributions | |
bilt | -0.551 |
NESS | -0.475 |
hess | -0.462 |
�� | -0.440 |
ewater | -0.436 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
bilt | +0.710 |
NESS | +0.610 |
hess | +0.607 |
ewater | +0.572 |
�� | +0.562 |
Neg logit contributions | |
idates | -0.638 |
ependence | -0.633 |
los | -0.633 |
ogh | -0.630 |
yg | -0.598 |
Token | children |
Token ID | 1751 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
idates | +1.425 |
los | +1.417 |
ependence | +1.417 |
ogh | +1.398 |
yg | +1.330 |
Neg logit contributions | |
bilt | -1.729 |
hess | -1.474 |
NESS | -1.464 |
ewater | -1.389 |
�� | -1.384 |
Token | will |
Token ID | 481 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
bilt | +2.141 |
NESS | +1.825 |
hess | +1.810 |
ewater | +1.712 |
�� | +1.678 |
Neg logit contributions | |
ependence | -1.927 |
idates | -1.924 |
los | -1.904 |
ogh | -1.898 |
yg | -1.797 |
Token | work |
Token ID | 670 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
bilt | +0.040 |
hess | +0.034 |
NESS | +0.034 |
ewater | +0.032 |
�� | +0.032 |
Neg logit contributions | |
idates | -0.036 |
ependence | -0.036 |
los | -0.036 |
ogh | -0.036 |
yg | -0.034 |
Token | on |
Token ID | 319 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
bilt | +2.227 |
NESS | +1.910 |
hess | +1.890 |
ewater | +1.795 |
�� | +1.757 |
Neg logit contributions | |
idates | -1.941 |
ependence | -1.935 |
los | -1.919 |
ogh | -1.913 |
yg | -1.805 |
Token | " |
Token ID | 366 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
idates | +0.291 |
ependence | +0.289 |
los | +0.289 |
ogh | +0.287 |
yg | +0.272 |
Neg logit contributions | |
bilt | -0.333 |
NESS | -0.285 |
hess | -0.285 |
ewater | -0.267 |
�� | -0.265 |
Token | action |
Token ID | 2673 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
bilt | +1.194 |
NESS | +1.034 |
hess | +1.028 |
ewater | +0.975 |
�� | +0.961 |
Neg logit contributions | |
idates | -0.894 |
ependence | -0.891 |
los | -0.881 |
ogh | -0.880 |
yg | -0.826 |
Token | described |
Token ID | 3417 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
bilt | +2.781 |
NESS | +2.379 |
hess | +2.359 |
ewater | +2.236 |
�� | +2.192 |
Neg logit contributions | |
idates | -2.431 |
ependence | -2.429 |
los | -2.409 |
ogh | -2.394 |
yg | -2.270 |
Token | in |
Token ID | 287 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
bilt | +2.219 |
NESS | +1.904 |
hess | +1.893 |
ewater | +1.791 |
�� | +1.760 |
Neg logit contributions | |
idates | -1.914 |
ependence | -1.913 |
los | -1.886 |
ogh | -1.869 |
yg | -1.777 |
Token | this |
Token ID | 428 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
bilt | +1.490 |
NESS | +1.245 |
hess | +1.233 |
ewater | +1.151 |
�� | +1.120 |
Neg logit contributions | |
idates | -1.790 |
ependence | -1.784 |
los | -1.772 |
ogh | -1.765 |
yg | -1.687 |
Token | document |
Token ID | 3188 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
bilt | +1.754 |
NESS | +1.449 |
hess | +1.431 |
ewater | +1.333 |
�� | +1.298 |
Neg logit contributions | |
idates | -2.244 |
ependence | -2.234 |
los | -2.212 |
ogh | -2.208 |
yg | -2.105 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
bilt | +0.512 |
NESS | +0.438 |
hess | +0.435 |
ewater | +0.412 |
�� | +0.406 |
Neg logit contributions | |
idates | -0.445 |
ependence | -0.444 |
los | -0.441 |
ogh | -0.438 |
yg | -0.416 |
Token | you |
Token ID | 345 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
bilt | +3.727 |
NESS | +3.148 |
hess | +3.098 |
ewater | +2.963 |
�� | +2.861 |
Neg logit contributions | |
idates | -3.758 |
ependence | -3.744 |
los | -3.702 |
ogh | -3.674 |
yg | -3.504 |
Token | 'll |
Token ID | 1183 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
bilt | +2.949 |
NESS | +2.502 |
hess | +2.467 |
ewater | +2.349 |
�� | +2.287 |
Neg logit contributions | |
idates | -2.915 |
ependence | -2.908 |
los | -2.878 |
ogh | -2.870 |
yg | -2.727 |
Token | find |
Token ID | 1064 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
bilt | +4.534 |
NESS | +3.900 |
hess | +3.746 |
ewater | +3.668 |
�� | +3.460 |
Neg logit contributions | |
ependence | -4.600 |
idates | -4.575 |
los | -4.500 |
ogh | -4.492 |
yg | -4.272 |
Token | that |
Token ID | 326 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
bilt | +3.068 |
NESS | +2.643 |
hess | +2.616 |
ewater | +2.483 |
�� | +2.425 |
Neg logit contributions | |
ependence | -2.684 |
idates | -2.678 |
los | -2.649 |
ogh | -2.631 |
yg | -2.496 |
Token | claim |
Token ID | 1624 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
bilt | +3.438 |
NESS | +2.922 |
hess | +2.894 |
ewater | +2.744 |
�� | +2.673 |
Neg logit contributions | |
ependence | -3.360 |
idates | -3.359 |
los | -3.316 |
ogh | -3.294 |
yg | -3.131 |
Token | is |
Token ID | 318 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bilt | +3.572 |
NESS | +3.030 |
hess | +3.004 |
ewater | +2.851 |
�� | +2.743 |
Neg logit contributions | |
idates | -3.715 |
ependence | -3.709 |
los | -3.659 |
ogh | -3.657 |
yg | -3.484 |
Token | straight |
Token ID | 3892 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
idates | +1.262 |
los | +1.255 |
ependence | +1.237 |
ogh | +1.225 |
yg | +1.175 |
Neg logit contributions | |
bilt | -1.584 |
hess | -1.361 |
NESS | -1.356 |
�� | -1.292 |
ewater | -1.285 |
Token | away |
Token ID | 1497 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
bilt | +1.193 |
NESS | +1.019 |
hess | +1.013 |
ewater | +0.952 |
�� | +0.949 |
Neg logit contributions | |
idates | -1.071 |
ependence | -1.067 |
los | -1.062 |
ogh | -1.055 |
yg | -1.003 |
Token | I |
Token ID | 314 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
idates | +1.662 |
los | +1.656 |
ependence | +1.632 |
ogh | +1.614 |
yg | +1.542 |
Neg logit contributions | |
bilt | -2.206 |
hess | -1.898 |
NESS | -1.892 |
�� | -1.822 |
ewater | -1.800 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
los | +1.349 |
idates | +1.349 |
ependence | +1.330 |
ogh | +1.303 |
yg | +1.250 |
Neg logit contributions | |
bilt | -1.936 |
NESS | -1.686 |
hess | -1.681 |
�� | -1.635 |
ewater | -1.595 |
Token | quite |
Token ID | 2407 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
bilt | +0.890 |
NESS | +0.764 |
hess | +0.759 |
ewater | +0.717 |
�� | +0.709 |
Neg logit contributions | |
idates | -0.745 |
ependence | -0.743 |
los | -0.738 |
ogh | -0.734 |
yg | -0.694 |
Token | decent |
Token ID | 7709 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
idates | +0.889 |
los | +0.886 |
ependence | +0.882 |
ogh | +0.880 |
yg | +0.829 |
Neg logit contributions | |
bilt | -1.044 |
hess | -0.895 |
NESS | -0.891 |
�� | -0.841 |
ewater | -0.838 |
Token | in |
Token ID | 287 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
bilt | +0.540 |
NESS | +0.464 |
hess | +0.462 |
ewater | +0.437 |
�� | +0.436 |
Neg logit contributions | |
idates | -0.431 |
ependence | -0.430 |
los | -0.428 |
ogh | -0.424 |
yg | -0.401 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
idates | +2.164 |
los | +2.160 |
ependence | +2.141 |
ogh | +2.110 |
yg | +2.034 |
Neg logit contributions | |
bilt | -2.717 |
NESS | -2.335 |
hess | -2.318 |
ewater | -2.212 |
�� | -2.204 |
Token | car |
Token ID | 1097 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
idates | +0.109 |
los | +0.108 |
ependence | +0.108 |
ogh | +0.107 |
yg | +0.102 |
Neg logit contributions | |
bilt | -0.122 |
NESS | -0.104 |
hess | -0.104 |
�� | -0.099 |
ewater | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
los | +2.309 |
ependence | +2.289 |
idates | +2.276 |
ogh | +2.251 |
bu | +2.126 |
Neg logit contributions | |
bilt | -3.118 |
NESS | -2.695 |
hess | -2.672 |
�� | -2.593 |
ewater | -2.531 |
Token | Then |
Token ID | 3244 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
bilt | +0.855 |
NESS | +0.731 |
hess | +0.725 |
ewater | +0.682 |
�� | +0.671 |
Neg logit contributions | |
idates | -0.768 |
ependence | -0.767 |
los | -0.760 |
ogh | -0.759 |
yg | -0.717 |
Token | should |
Token ID | 815 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
bilt | +0.590 |
NESS | +0.498 |
hess | +0.497 |
ewater | +0.467 |
�� | +0.465 |
Neg logit contributions | |
ependence | -0.561 |
idates | -0.560 |
los | -0.559 |
ogh | -0.555 |
yg | -0.524 |
Token | our |
Token ID | 674 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
bilt | +0.723 |
NESS | +0.624 |
hess | +0.621 |
ewater | +0.588 |
�� | +0.583 |
Neg logit contributions | |
idates | -0.548 |
ependence | -0.547 |
los | -0.544 |
ogh | -0.541 |
yg | -0.509 |
Token | souls |
Token ID | 15625 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
idates | +2.357 |
ependence | +2.341 |
los | +2.325 |
ogh | +2.285 |
yg | +2.186 |
Neg logit contributions | |
bilt | -3.655 |
hess | -3.220 |
NESS | -3.170 |
�� | -3.075 |
ewater | -3.071 |
Token | cheat |
Token ID | 22705 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ependence | +0.084 |
idates | +0.084 |
los | +0.083 |
ogh | +0.083 |
yg | +0.078 |
Neg logit contributions | |
bilt | -0.099 |
NESS | -0.085 |
hess | -0.085 |
ewater | -0.080 |
�� | -0.079 |
Token | us |
Token ID | 514 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ependence | +0.157 |
idates | +0.156 |
los | +0.155 |
ogh | +0.155 |
yg | +0.147 |
Neg logit contributions | |
bilt | -0.184 |
NESS | -0.157 |
hess | -0.156 |
ewater | -0.148 |
�� | -0.147 |
Token | one |
Token ID | 530 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
bilt | +1.368 |
NESS | +1.167 |
hess | +1.160 |
ewater | +1.095 |
�� | +1.085 |
Neg logit contributions | |
idates | -1.201 |
ependence | -1.200 |
los | -1.192 |
ogh | -1.187 |
yg | -1.124 |
Token | more |
Token ID | 517 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
bilt | +0.489 |
NESS | +0.418 |
hess | +0.416 |
ewater | +0.392 |
�� | +0.390 |
Neg logit contributions | |
idates | -0.423 |
ependence | -0.422 |
los | -0.420 |
ogh | -0.417 |
yg | -0.395 |
Token | time |
Token ID | 640 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
bilt | +2.347 |
NESS | +1.973 |
hess | +1.958 |
ewater | +1.836 |
�� | +1.802 |
Neg logit contributions | |
idates | -2.443 |
ependence | -2.430 |
los | -2.410 |
ogh | -2.401 |
yg | -2.279 |
Token | now |
Token ID | 783 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
ependence | +0.692 |
idates | +0.685 |
los | +0.683 |
ogh | +0.681 |
yg | +0.645 |
Neg logit contributions | |
bilt | -0.905 |
NESS | -0.776 |
hess | -0.773 |
ewater | -0.735 |
�� | -0.734 |
Token | when |
Token ID | 618 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
bilt | +0.039 |
NESS | +0.033 |
hess | +0.033 |
ewater | +0.031 |
�� | +0.031 |
Neg logit contributions | |
ependence | -0.031 |
idates | -0.031 |
los | -0.031 |
ogh | -0.031 |
yg | -0.029 |
Token | we |
Token ID | 356 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
idates | +1.916 |
ependence | +1.911 |
los | +1.906 |
ogh | +1.895 |
yg | +1.799 |
Neg logit contributions | |
bilt | -2.189 |
NESS | -1.856 |
hess | -1.848 |
ewater | -1.771 |
�� | -1.750 |
Token | was |
Token ID | 373 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
idates | +1.405 |
ependence | +1.401 |
los | +1.390 |
ogh | +1.388 |
yg | +1.312 |
Neg logit contributions | |
bilt | -1.620 |
NESS | -1.388 |
hess | -1.380 |
ewater | -1.296 |
�� | -1.282 |
Token | any |
Token ID | 597 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ependence | +1.025 |
ogh | +1.023 |
los | +1.021 |
idates | +1.020 |
yg | +0.967 |
Neg logit contributions | |
bilt | -1.176 |
NESS | -0.996 |
hess | -0.993 |
ewater | -0.931 |
�� | -0.928 |
Token | need |
Token ID | 761 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
ependence | +0.951 |
los | +0.947 |
idates | +0.945 |
ogh | +0.943 |
yg | +0.895 |
Neg logit contributions | |
bilt | -1.106 |
NESS | -0.945 |
hess | -0.943 |
�� | -0.892 |
ewater | -0.889 |
Token | to |
Token ID | 284 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
bilt | +0.172 |
NESS | +0.144 |
hess | +0.143 |
ewater | +0.134 |
�� | +0.132 |
Neg logit contributions | |
idates | -0.184 |
ependence | -0.183 |
los | -0.182 |
ogh | -0.181 |
yg | -0.174 |
Token | repair |
Token ID | 9185 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
idates | +0.445 |
los | +0.437 |
ependence | +0.437 |
ogh | +0.433 |
yg | +0.410 |
Neg logit contributions | |
bilt | -0.746 |
NESS | -0.655 |
hess | -0.653 |
�� | -0.619 |
ewater | -0.619 |
Token | ties |
Token ID | 8470 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
bilt | +1.598 |
NESS | +1.360 |
hess | +1.344 |
ewater | +1.274 |
�� | +1.255 |
Neg logit contributions | |
idates | -1.506 |
ependence | -1.496 |
los | -1.487 |
ogh | -1.482 |
yg | -1.403 |
Token | between |
Token ID | 1022 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
bilt | +0.615 |
NESS | +0.530 |
hess | +0.527 |
ewater | +0.499 |
�� | +0.494 |
Neg logit contributions | |
idates | -0.481 |
ependence | -0.480 |
los | -0.477 |
ogh | -0.474 |
yg | -0.448 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
bilt | +1.473 |
NESS | +1.267 |
hess | +1.252 |
ewater | +1.193 |
�� | +1.176 |
Neg logit contributions | |
idates | -1.180 |
ependence | -1.178 |
los | -1.171 |
ogh | -1.163 |
yg | -1.098 |
Token | and |
Token ID | 290 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
bilt | +0.606 |
NESS | +0.517 |
hess | +0.513 |
ewater | +0.486 |
�� | +0.477 |
Neg logit contributions | |
idates | -0.556 |
ependence | -0.555 |
los | -0.553 |
ogh | -0.547 |
yg | -0.519 |
Token | top |
Token ID | 1353 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
bilt | +0.995 |
NESS | +0.858 |
hess | +0.851 |
ewater | +0.809 |
�� | +0.799 |
Neg logit contributions | |
idates | -0.765 |
ependence | -0.763 |
los | -0.758 |
ogh | -0.753 |
yg | -0.710 |
Token | Republican |
Token ID | 3415 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
bilt | +1.983 |
NESS | +1.705 |
hess | +1.692 |
ewater | +1.608 |
�� | +1.581 |
Neg logit contributions | |
idates | -1.582 |
ependence | -1.581 |
los | -1.570 |
ogh | -1.561 |
yg | -1.471 |
Token | operator |
Token ID | 10088 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
bilt | +3.463 |
hess | +2.820 |
NESS | +2.774 |
ewater | +2.500 |
td | +2.436 |
Neg logit contributions | |
idates | -5.978 |
ependence | -5.933 |
ogh | -5.840 |
los | -5.839 |
igree | -5.724 |
Token | to |
Token ID | 284 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
bilt | +5.454 |
hess | +4.596 |
NESS | +4.477 |
ewater | +4.067 |
td | +3.948 |
Neg logit contributions | |
idates | -7.766 |
ependence | -7.759 |
ogh | -7.683 |
los | -7.556 |
igree | -7.541 |
Token | find |
Token ID | 1064 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
bilt | +2.994 |
NESS | +2.502 |
hess | +2.458 |
ewater | +2.280 |
�� | +2.225 |
Neg logit contributions | |
ependence | -3.842 |
idates | -3.838 |
ogh | -3.789 |
los | -3.785 |
yg | -3.630 |
Token | dark |
Token ID | 3223 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
bilt | +4.264 |
hess | +2.816 |
NESS | +2.777 |
darker | +2.737 |
td | +2.511 |
Neg logit contributions | |
ependence | -19.817 |
idates | -19.575 |
ocrates | -19.293 |
los | -19.127 |
igree | -18.968 |
Token | regions |
Token ID | 7652 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
bilt | +5.657 |
NESS | +5.064 |
hess | +4.694 |
ewater | +4.083 |
td | +3.858 |
Neg logit contributions | |
ependence | -12.407 |
idates | -12.012 |
los | -11.918 |
ogh | -11.813 |
igree | -11.791 |
Token | on |
Token ID | 319 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
bilt | +3.882 |
NESS | +3.377 |
hess | +3.374 |
ewater | +3.186 |
�� | +3.096 |
Neg logit contributions | |
ependence | -2.868 |
idates | -2.865 |
los | -2.815 |
ogh | -2.796 |
igree | -2.660 |
Token | a |
Token ID | 257 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
bilt | +6.362 |
NESS | +5.152 |
hess | +5.126 |
td | +4.752 |
ewater | +4.703 |
Neg logit contributions | |
idates | -9.295 |
ependence | -9.290 |
los | -9.119 |
ogh | -9.035 |
igree | -8.830 |
Token | light |
Token ID | 1657 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
bilt | +3.993 |
NESS | +3.243 |
hess | +3.142 |
ewater | +2.899 |
dime | +2.826 |
Neg logit contributions | |
idates | -7.221 |
ependence | -7.206 |
los | -7.075 |
ogh | -6.950 |
ocrates | -6.830 |
Token | background |
Token ID | 4469 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
bilt | +3.332 |
NESS | +2.934 |
hess | +2.905 |
ewater | +2.775 |
�� | +2.704 |
Neg logit contributions | |
idates | -2.170 |
ependence | -2.161 |
los | -2.158 |
ogh | -2.127 |
yg | -1.976 |
Token | gray |
Token ID | 12768 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
bilt | +2.773 |
NESS | +2.179 |
hess | +2.100 |
ewater | +1.793 |
td | +1.641 |
Neg logit contributions | |
ependence | -7.421 |
idates | -7.411 |
los | -7.363 |
ogh | -7.331 |
ochond | -7.067 |
Token | = |
Token ID | 796 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
bilt | +1.536 |
NESS | +1.258 |
hess | +1.249 |
ewater | +1.159 |
�� | +1.145 |
Neg logit contributions | |
idates | -2.019 |
ependence | -2.014 |
los | -2.007 |
ogh | -1.995 |
yg | -1.911 |
Token | struggling |
Token ID | 9648 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
bilt | +0.872 |
NESS | +0.744 |
hess | +0.740 |
ewater | +0.697 |
�� | +0.691 |
Neg logit contributions | |
idates | -0.771 |
ependence | -0.768 |
los | -0.766 |
ogh | -0.761 |
yg | -0.720 |
Token | – |
Token ID | 784 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
bilt | +0.026 |
NESS | +0.022 |
hess | +0.022 |
ewater | +0.021 |
�� | +0.021 |
Neg logit contributions | |
idates | -0.021 |
ependence | -0.021 |
los | -0.021 |
ogh | -0.021 |
yg | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
idates | +1.232 |
los | +1.232 |
ependence | +1.225 |
ogh | +1.223 |
yg | +1.148 |
Neg logit contributions | |
bilt | -1.527 |
hess | -1.307 |
NESS | -1.298 |
ewater | -1.230 |
�� | -1.226 |
Token | I |
Token ID | 314 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
idates | +0.535 |
ependence | +0.533 |
los | +0.532 |
ogh | +0.528 |
yg | +0.500 |
Neg logit contributions | |
bilt | -0.642 |
NESS | -0.548 |
hess | -0.548 |
ewater | -0.518 |
�� | -0.515 |
Token | cannot |
Token ID | 2314 |
Feature activation | -1.21e-04 |
Pos logit contributions | |
idates | +0.648 |
los | +0.648 |
ependence | +0.647 |
ogh | +0.643 |
yg | +0.611 |
Neg logit contributions | |
bilt | -0.801 |
hess | -0.687 |
NESS | -0.685 |
ewater | -0.647 |
�� | -0.644 |
Token | f |
Token ID | 277 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
bilt | +0.001 |
NESS | +0.001 |
hess | +0.001 |
ewater | +0.001 |
�� | +0.001 |
Neg logit contributions | |
idates | -0.001 |
los | -0.001 |
ependence | -0.001 |
ogh | -0.001 |
yg | -0.001 |
Token | athom |
Token ID | 32910 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
bilt | +5.860 |
hess | +4.994 |
NESS | +4.662 |
�� | +4.362 |
ewater | +4.360 |
Neg logit contributions | |
idates | -7.894 |
los | -7.631 |
ependence | -7.609 |
ogh | -7.605 |
ocrates | -7.411 |
Token | why |
Token ID | 1521 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
bilt | +0.982 |
NESS | +0.844 |
hess | +0.841 |
ewater | +0.795 |
�� | +0.786 |
Neg logit contributions | |
idates | -0.788 |
ependence | -0.785 |
los | -0.781 |
ogh | -0.777 |
yg | -0.734 |
Token | you |
Token ID | 345 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
los | +2.211 |
idates | +2.196 |
ogh | +2.184 |
ependence | +2.169 |
yg | +2.043 |
Neg logit contributions | |
bilt | -2.795 |
hess | -2.383 |
NESS | -2.349 |
ewater | -2.251 |
�� | -2.233 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
bilt | +0.854 |
NESS | +0.729 |
hess | +0.725 |
ewater | +0.683 |
�� | +0.675 |
Neg logit contributions | |
idates | -0.758 |
ependence | -0.757 |
los | -0.753 |
ogh | -0.748 |
yg | -0.709 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
los | +1.776 |
idates | +1.775 |
ependence | +1.766 |
ogh | +1.742 |
yg | +1.650 |
Neg logit contributions | |
bilt | -2.303 |
hess | -1.996 |
NESS | -1.967 |
ewater | -1.847 |
�� | -1.840 |
Token | The |
Token ID | 383 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
bilt | +4.694 |
NESS | +4.058 |
hess | +3.997 |
ewater | +3.708 |
td | +3.550 |
Neg logit contributions | |
ependence | -4.516 |
idates | -4.492 |
ogh | -4.474 |
los | -4.443 |
ochond | -4.263 |
Token | child |
Token ID | 1200 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
idates | +0.213 |
ependence | +0.211 |
los | +0.211 |
ogh | +0.209 |
yg | +0.199 |
Neg logit contributions | |
bilt | -0.232 |
NESS | -0.198 |
hess | -0.197 |
ewater | -0.186 |
�� | -0.185 |
Token | was |
Token ID | 373 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
bilt | +4.995 |
NESS | +4.204 |
hess | +4.191 |
ewater | +3.869 |
�� | +3.760 |
Neg logit contributions | |
ependence | -4.712 |
idates | -4.693 |
los | -4.691 |
ogh | -4.614 |
ocrates | -4.416 |
Token | called |
Token ID | 1444 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
bilt | +3.504 |
NESS | +3.024 |
hess | +3.015 |
ewater | +2.837 |
�� | +2.776 |
Neg logit contributions | |
idates | -2.950 |
ependence | -2.939 |
los | -2.897 |
ogh | -2.862 |
yg | -2.719 |
Token | � |
Token ID | 564 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
bilt | +6.496 |
NESS | +5.630 |
hess | +5.612 |
ewater | +5.296 |
td | +5.179 |
Neg logit contributions | |
idates | -5.914 |
ependence | -5.902 |
los | -5.866 |
ogh | -5.844 |
igree | -5.536 |
Token | � |
Token ID | 250 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
bilt | +0.257 |
NESS | +0.209 |
hess | +0.206 |
�� | +0.194 |
ewater | +0.191 |
Neg logit contributions | |
ependence | -0.363 |
idates | -0.362 |
los | -0.360 |
ogh | -0.359 |
yg | -0.344 |
Token | Re |
Token ID | 3041 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
bilt | +7.771 |
NESS | +6.731 |
hess | +6.693 |
ewater | +6.234 |
Per | +6.114 |
Neg logit contributions | |
idates | -6.507 |
ependence | -6.443 |
ogh | -6.409 |
los | -6.209 |
igree | -6.172 |
Token | id |
Token ID | 312 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
bilt | +0.914 |
NESS | +0.782 |
hess | +0.780 |
ewater | +0.736 |
�� | +0.727 |
Neg logit contributions | |
idates | -0.773 |
ependence | -0.771 |
los | -0.767 |
ogh | -0.762 |
yg | -0.721 |
Token | , |
Token ID | 11 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
bilt | +5.671 |
hess | +4.851 |
NESS | +4.812 |
ewater | +4.528 |
�� | +4.381 |
Neg logit contributions | |
ependence | -4.873 |
los | -4.801 |
ogh | -4.797 |
idates | -4.795 |
igree | -4.571 |
Token | � |
Token ID | 447 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
bilt | +5.741 |
NESS | +4.953 |
hess | +4.916 |
ewater | +4.642 |
�� | +4.571 |
Neg logit contributions | |
idates | -5.037 |
ependence | -5.027 |
los | -4.976 |
ogh | -4.922 |
yg | -4.707 |
Token | � |
Token ID | 251 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
bilt | +0.910 |
NESS | +0.737 |
hess | +0.723 |
�� | +0.675 |
ewater | +0.659 |
Neg logit contributions | |
ependence | -1.458 |
idates | -1.456 |
los | -1.448 |
ogh | -1.437 |
ochond | -1.383 |
Token | acs |
Token ID | 16436 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
bilt | +3.934 |
hess | +3.380 |
NESS | +3.379 |
ewater | +3.192 |
�� | +3.101 |
Neg logit contributions | |
idates | -3.045 |
ependence | -3.042 |
ogh | -3.006 |
los | -2.972 |
ochond | -2.823 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
idates | +0.360 |
ependence | +0.358 |
los | +0.357 |
ogh | +0.354 |
yg | +0.335 |
Neg logit contributions | |
bilt | -0.481 |
NESS | -0.417 |
hess | -0.414 |
ewater | -0.392 |
�� | -0.389 |
Token | / |
Token ID | 14 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
bilt | +2.888 |
hess | +2.453 |
NESS | +2.443 |
ewater | +2.336 |
�� | +2.266 |
Neg logit contributions | |
idates | -2.464 |
ependence | -2.444 |
los | -2.413 |
ogh | -2.410 |
ocrates | -2.281 |
Token | profile |
Token ID | 13317 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
bilt | +6.111 |
hess | +5.262 |
NESS | +5.250 |
ewater | +4.996 |
�� | +4.789 |
Neg logit contributions | |
idates | -4.696 |
ependence | -4.666 |
ogh | -4.638 |
los | -4.557 |
ochond | -4.374 |
Token | ? |
Token ID | 30 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
bilt | +2.337 |
NESS | +2.004 |
hess | +2.002 |
ewater | +1.889 |
�� | +1.848 |
Neg logit contributions | |
idates | -1.967 |
ependence | -1.963 |
los | -1.945 |
ogh | -1.943 |
yg | -1.830 |
Token | get |
Token ID | 1136 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
bilt | +1.284 |
NESS | +1.107 |
hess | +1.101 |
ewater | +1.043 |
�� | +1.029 |
Neg logit contributions | |
idates | -1.006 |
ependence | -1.003 |
los | -0.997 |
ogh | -0.992 |
yg | -0.935 |
Token | = |
Token ID | 28 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
bilt | +7.637 |
hess | +6.611 |
NESS | +6.578 |
ewater | +6.148 |
Per | +6.038 |
Neg logit contributions | |
idates | -6.721 |
ependence | -6.718 |
los | -6.656 |
ogh | -6.637 |
ocrates | -6.389 |
Token | NAME |
Token ID | 20608 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
bilt | +1.844 |
NESS | +1.590 |
hess | +1.581 |
ewater | +1.496 |
�� | +1.471 |
Neg logit contributions | |
idates | -1.451 |
ependence | -1.446 |
los | -1.436 |
ogh | -1.430 |
yg | -1.340 |
Token | , |
Token ID | 11 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
bilt | +2.182 |
NESS | +1.940 |
hess | +1.927 |
ewater | +1.839 |
�� | +1.821 |
Neg logit contributions | |
idates | -1.034 |
ependence | -1.029 |
los | -1.019 |
ogh | -1.010 |
yg | -0.932 |
Token | DP |
Token ID | 6322 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
bilt | +6.291 |
NESS | +5.533 |
hess | +5.410 |
ewater | +5.104 |
�� | +4.962 |
Neg logit contributions | |
ependence | -4.715 |
idates | -4.675 |
ogh | -4.673 |
los | -4.626 |
ochond | -4.434 |
Token | 02 |
Token ID | 2999 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
bilt | +0.670 |
NESS | +0.578 |
hess | +0.575 |
ewater | +0.545 |
�� | +0.539 |
Neg logit contributions | |
idates | -0.516 |
ependence | -0.514 |
los | -0.511 |
ogh | -0.508 |
yg | -0.479 |
Token | of |
Token ID | 286 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
bilt | +0.224 |
NESS | +0.192 |
hess | +0.191 |
ewater | +0.181 |
�� | +0.179 |
Neg logit contributions | |
idates | -0.186 |
ependence | -0.185 |
los | -0.184 |
ogh | -0.183 |
yg | -0.173 |
Token | view |
Token ID | 1570 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ependence | +3.580 |
ogh | +3.521 |
idates | +3.417 |
los | +3.286 |
yg | +3.002 |
Neg logit contributions | |
bilt | -11.684 |
NESS | -10.584 |
hess | -10.563 |
�� | -10.132 |
ewater | -9.842 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ependence | +1.794 |
los | +1.791 |
ogh | +1.779 |
idates | +1.779 |
yg | +1.678 |
Neg logit contributions | |
bilt | -2.439 |
NESS | -2.091 |
hess | -2.086 |
ewater | -1.973 |
�� | -1.968 |
Token | that |
Token ID | 326 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
idates | +1.979 |
ependence | +1.969 |
los | +1.952 |
ogh | +1.945 |
yg | +1.831 |
Neg logit contributions | |
bilt | -2.579 |
hess | -2.192 |
NESS | -2.185 |
ewater | -2.078 |
�� | -2.047 |
Token | may |
Token ID | 743 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
idates | +1.175 |
ependence | +1.161 |
los | +1.158 |
ogh | +1.154 |
yg | +1.085 |
Neg logit contributions | |
bilt | -1.441 |
hess | -1.234 |
NESS | -1.232 |
ewater | -1.158 |
�� | -1.149 |
Token | or |
Token ID | 393 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
idates | +2.614 |
los | +2.610 |
ogh | +2.597 |
ependence | +2.560 |
yg | +2.456 |
Neg logit contributions | |
bilt | -3.498 |
hess | -3.002 |
NESS | -2.963 |
�� | -2.818 |
ewater | -2.776 |
Token | may |
Token ID | 743 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
bilt | +6.359 |
NESS | +5.084 |
hess | +5.051 |
ewater | +4.559 |
td | +4.368 |
Neg logit contributions | |
idates | -11.173 |
ogh | -10.962 |
ependence | -10.951 |
los | -10.858 |
ocrates | -10.731 |
Token | not |
Token ID | 407 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
bilt | +1.453 |
NESS | +1.226 |
hess | +1.216 |
ewater | +1.141 |
�� | +1.125 |
Neg logit contributions | |
idates | -1.508 |
ependence | -1.504 |
los | -1.495 |
ogh | -1.488 |
yg | -1.416 |
Token | agree |
Token ID | 4236 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
los | +3.734 |
idates | +3.727 |
ogh | +3.670 |
ependence | +3.624 |
yg | +3.533 |
Neg logit contributions | |
bilt | -5.328 |
hess | -4.613 |
NESS | -4.565 |
�� | -4.335 |
�� | -4.257 |
Token | with |
Token ID | 351 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ependence | +2.492 |
idates | +2.473 |
los | +2.463 |
ogh | +2.458 |
yg | +2.355 |
Neg logit contributions | |
bilt | -3.567 |
hess | -3.097 |
NESS | -3.073 |
�� | -2.903 |
ewater | -2.893 |
Token | my |
Token ID | 616 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
idates | +1.254 |
ependence | +1.248 |
los | +1.241 |
ogh | +1.240 |
yg | +1.166 |
Neg logit contributions | |
bilt | -1.562 |
hess | -1.352 |
NESS | -1.336 |
�� | -1.254 |
ewater | -1.254 |