Token | week |
Token ID | 1285 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Luke | +0.974 |
ْ | +0.932 |
src | +0.917 |
sky | +0.913 |
cylinders | +0.907 |
Neg logit contributions | |
cair | -1.220 |
AZ | -1.204 |
Yelp | -1.200 |
Auto | -1.136 |
Olympia | -1.115 |
Token | participated |
Token ID | 14888 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
Luke | +0.467 |
ْ | +0.448 |
src | +0.440 |
sky | +0.437 |
Color | +0.436 |
Neg logit contributions | |
cair | -0.542 |
AZ | -0.537 |
Yelp | -0.535 |
Auto | -0.506 |
Olympia | -0.495 |
Token | in |
Token ID | 287 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
cair | +0.507 |
AZ | +0.505 |
Yelp | +0.504 |
Auto | +0.475 |
Olympia | +0.464 |
Neg logit contributions | |
Luke | -0.560 |
ْ | -0.538 |
src | -0.529 |
cylinders | -0.528 |
sky | -0.527 |
Token | a |
Token ID | 257 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
cair | +0.360 |
AZ | +0.359 |
Yelp | +0.358 |
Auto | +0.339 |
Olympia | +0.330 |
Neg logit contributions | |
Luke | -0.341 |
ْ | -0.329 |
src | -0.323 |
sky | -0.322 |
cylinders | -0.321 |
Token | Q |
Token ID | 1195 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Luke | +0.273 |
ْ | +0.263 |
src | +0.259 |
sky | +0.258 |
cylinders | +0.257 |
Neg logit contributions | |
cair | -0.296 |
AZ | -0.294 |
Yelp | -0.293 |
Auto | -0.276 |
Olympia | -0.270 |
Token | & |
Token ID | 5 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
Luke | +0.168 |
ْ | +0.160 |
sky | +0.157 |
src | +0.157 |
cylinders | +0.157 |
Neg logit contributions | |
cair | -0.221 |
AZ | -0.219 |
Yelp | -0.218 |
Auto | -0.208 |
Olympia | -0.203 |
Token | A |
Token ID | 32 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
AZ | +4.564 |
Yelp | +4.496 |
Auto | +4.418 |
cair | +4.366 |
Olympia | +4.102 |
Neg logit contributions | |
cylinders | -4.040 |
Luke | -3.909 |
ْ | -3.868 |
sky | -3.789 |
女 | -3.719 |
Token | session |
Token ID | 6246 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
AZ | +2.560 |
Yelp | +2.549 |
cair | +2.505 |
Auto | +2.446 |
Olympia | +2.340 |
Neg logit contributions | |
Luke | -2.553 |
ْ | -2.443 |
sky | -2.424 |
cylinders | -2.415 |
src | -2.405 |
Token | ― |
Token ID | 21096 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Luke | +0.989 |
ْ | +0.949 |
src | +0.934 |
sky | +0.931 |
cylinders | +0.925 |
Neg logit contributions | |
cair | -1.121 |
AZ | -1.104 |
Yelp | -1.101 |
Auto | -1.038 |
Olympia | -1.019 |
Token | refer |
Token ID | 3522 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Luke | +0.563 |
ْ | +0.542 |
src | +0.533 |
sky | +0.531 |
cylinders | +0.528 |
Neg logit contributions | |
cair | -0.582 |
AZ | -0.574 |
Yelp | -0.573 |
Auto | -0.539 |
Olympia | -0.528 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Luke | +1.254 |
ْ | +1.211 |
src | +1.195 |
sky | +1.191 |
cylinders | +1.186 |
Neg logit contributions | |
cair | -0.999 |
AZ | -0.983 |
Yelp | -0.979 |
Auto | -0.914 |
Olympia | -0.892 |
Token | . |
Token ID | 13 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
AZ | +0.273 |
cair | +0.273 |
Yelp | +0.272 |
Auto | +0.255 |
Olympia | +0.248 |
Neg logit contributions | |
Luke | -0.337 |
ْ | -0.326 |
src | -0.322 |
sky | -0.321 |
Cla | -0.317 |
Token | To |
Token ID | 1675 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
Luke | +0.217 |
ْ | +0.208 |
src | +0.205 |
sky | +0.204 |
cylinders | +0.203 |
Neg logit contributions | |
cair | -0.233 |
AZ | -0.230 |
Yelp | -0.230 |
Auto | -0.217 |
Olympia | -0.212 |
Token | get |
Token ID | 651 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
Luke | +0.699 |
ْ | +0.673 |
src | +0.663 |
sky | +0.661 |
cylinders | +0.657 |
Neg logit contributions | |
cair | -0.679 |
AZ | -0.670 |
Yelp | -0.668 |
Auto | -0.628 |
Olympia | -0.614 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
cair | +0.046 |
AZ | +0.046 |
Yelp | +0.046 |
Auto | +0.043 |
Olympia | +0.042 |
Neg logit contributions | |
Luke | -0.045 |
ْ | -0.043 |
src | -0.043 |
sky | -0.042 |
Color | -0.042 |
Token | better |
Token ID | 1365 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Yelp | +1.234 |
AZ | +1.228 |
cair | +1.216 |
Auto | +1.148 |
Olympia | +1.103 |
Neg logit contributions | |
Luke | -1.515 |
ْ | -1.479 |
src | -1.455 |
Color | -1.438 |
ample | -1.434 |
Token | sense |
Token ID | 2565 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
AZ | +1.276 |
Yelp | +1.276 |
cair | +1.270 |
Auto | +1.191 |
Olympia | +1.148 |
Neg logit contributions | |
Luke | -1.605 |
ْ | -1.567 |
src | -1.533 |
Color | -1.521 |
女 | -1.520 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Yelp | +3.711 |
AZ | +3.706 |
cair | +3.589 |
Auto | +3.487 |
memor | +3.309 |
Neg logit contributions | |
Luke | -4.682 |
ْ | -4.581 |
src | -4.569 |
ample | -4.458 |
女 | -4.451 |
Token | who |
Token ID | 508 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
AZ | +1.183 |
Yelp | +1.182 |
cair | +1.182 |
Auto | +1.117 |
Olympia | +1.087 |
Neg logit contributions | |
Luke | -1.121 |
ْ | -1.083 |
src | -1.061 |
sky | -1.052 |
ample | -1.051 |
Token | keeps |
Token ID | 7622 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Luke | +0.470 |
ْ | +0.453 |
src | +0.445 |
sky | +0.443 |
cylinders | +0.441 |
Neg logit contributions | |
cair | -0.498 |
AZ | -0.495 |
Yelp | -0.493 |
Auto | -0.466 |
Olympia | -0.455 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Yelp | +0.199 |
AZ | +0.199 |
cair | +0.198 |
Auto | +0.187 |
Olympia | +0.182 |
Neg logit contributions | |
Luke | -0.196 |
ْ | -0.190 |
src | -0.186 |
女 | -0.185 |
sky | -0.184 |
Token | angry |
Token ID | 7954 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Luke | +0.766 |
ْ | +0.738 |
src | +0.726 |
sky | +0.722 |
cylinders | +0.718 |
Neg logit contributions | |
cair | -0.760 |
AZ | -0.753 |
Yelp | -0.750 |
Auto | -0.706 |
Olympia | -0.690 |
Token | Bounty |
Token ID | 38166 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Luke | +0.690 |
ْ | +0.660 |
sky | +0.655 |
src | +0.653 |
cylinders | +0.649 |
Neg logit contributions | |
cair | -0.728 |
AZ | -0.712 |
Yelp | -0.711 |
Auto | -0.665 |
Olympia | -0.658 |
Token | gate |
Token ID | 10494 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
Luke | +1.800 |
ْ | +1.720 |
sky | +1.701 |
src | +1.697 |
Color | +1.688 |
Neg logit contributions | |
cair | -1.970 |
AZ | -1.926 |
Yelp | -1.919 |
Auto | -1.801 |
Olympia | -1.780 |
Token | Lit |
Token ID | 25659 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Luke | +0.675 |
ْ | +0.650 |
src | +0.639 |
sky | +0.636 |
cylinders | +0.634 |
Neg logit contributions | |
cair | -0.687 |
AZ | -0.680 |
Yelp | -0.678 |
Auto | -0.639 |
Olympia | -0.624 |
Token | igation |
Token ID | 7065 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
cair | +0.994 |
AZ | +0.986 |
Yelp | +0.982 |
Auto | +0.936 |
Olympia | +0.915 |
Neg logit contributions | |
Luke | -0.677 |
ْ | -0.649 |
src | -0.632 |
cylinders | -0.629 |
sky | -0.625 |
Token | Q |
Token ID | 1195 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Luke | +0.789 |
ْ | +0.760 |
src | +0.746 |
sky | +0.742 |
cylinders | +0.741 |
Neg logit contributions | |
cair | -0.867 |
AZ | -0.859 |
Yelp | -0.856 |
Auto | -0.810 |
Olympia | -0.792 |
Token | & |
Token ID | 5 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Luke | +0.177 |
ْ | +0.170 |
src | +0.166 |
sky | +0.166 |
cylinders | +0.166 |
Neg logit contributions | |
cair | -0.226 |
AZ | -0.224 |
Yelp | -0.222 |
Auto | -0.212 |
Olympia | -0.206 |
Token | As |
Token ID | 1722 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
AZ | +4.404 |
cair | +4.314 |
Yelp | +4.291 |
Auto | +4.222 |
Olympia | +3.943 |
Neg logit contributions | |
Luke | -3.848 |
ْ | -3.759 |
cylinders | -3.708 |
女 | -3.686 |
src | -3.661 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
AZ | +2.615 |
Yelp | +2.572 |
cair | +2.494 |
Auto | +2.492 |
Olympia | +2.383 |
Neg logit contributions | |
Luke | -2.620 |
ْ | -2.564 |
女 | -2.492 |
cylinders | -2.488 |
src | -2.472 |
Token |
|
Token ID | 198 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
AZ | +0.168 |
Yelp | +0.167 |
cair | +0.167 |
Auto | +0.159 |
Olympia | +0.154 |
Neg logit contributions | |
Luke | -0.149 |
ْ | -0.145 |
cylinders | -0.142 |
src | -0.141 |
sky | -0.140 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Luke | +0.419 |
ْ | +0.401 |
src | +0.393 |
sky | +0.392 |
cylinders | +0.391 |
Neg logit contributions | |
cair | -0.546 |
AZ | -0.540 |
Yelp | -0.538 |
Auto | -0.511 |
Olympia | -0.501 |
Token | Maybe |
Token ID | 13300 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
cair | +0.604 |
AZ | +0.601 |
Yelp | +0.598 |
Auto | +0.573 |
Olympia | +0.560 |
Neg logit contributions | |
Luke | -0.360 |
ْ | -0.350 |
cylinders | -0.348 |
sky | -0.339 |
src | -0.339 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
cair | +0.769 |
AZ | +0.764 |
Yelp | +0.760 |
Auto | +0.716 |
Olympia | +0.698 |
Neg logit contributions | |
Luke | -0.781 |
ْ | -0.756 |
src | -0.740 |
sky | -0.735 |
Color | -0.731 |
Token | joke |
Token ID | 9707 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
cair | +0.851 |
AZ | +0.847 |
Yelp | +0.843 |
Auto | +0.790 |
Olympia | +0.772 |
Neg logit contributions | |
Luke | -0.902 |
ْ | -0.874 |
src | -0.857 |
sky | -0.850 |
ample | -0.849 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Luke | +1.545 |
ْ | +1.488 |
sky | +1.472 |
src | +1.471 |
cylinders | +1.460 |
Neg logit contributions | |
cair | -1.461 |
AZ | -1.429 |
Yelp | -1.426 |
Auto | -1.333 |
Olympia | -1.311 |
Token | spend |
Token ID | 4341 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
cair | +0.917 |
AZ | +0.910 |
Yelp | +0.904 |
Auto | +0.854 |
Olympia | +0.831 |
Neg logit contributions | |
Luke | -0.950 |
ْ | -0.915 |
src | -0.899 |
sky | -0.894 |
cylinders | -0.891 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Luke | +0.716 |
ْ | +0.687 |
sky | +0.680 |
src | +0.678 |
cylinders | +0.676 |
Neg logit contributions | |
cair | -0.734 |
AZ | -0.720 |
Yelp | -0.719 |
Auto | -0.676 |
Olympia | -0.665 |
Token | extra |
Token ID | 3131 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
AZ | +2.066 |
cair | +2.055 |
Yelp | +2.052 |
Auto | +1.944 |
Olympia | +1.889 |
Neg logit contributions | |
Luke | -1.901 |
ْ | -1.853 |
src | -1.801 |
女 | -1.781 |
sky | -1.767 |
Token | cash |
Token ID | 5003 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
AZ | +4.354 |
Yelp | +4.277 |
cair | +4.231 |
Auto | +4.061 |
Olympia | +3.888 |
Neg logit contributions | |
Luke | -4.076 |
ْ | -4.008 |
src | -3.922 |
女 | -3.871 |
Cla | -3.818 |
Token | you |
Token ID | 345 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
cair | +1.868 |
AZ | +1.850 |
Yelp | +1.841 |
Auto | +1.733 |
Olympia | +1.671 |
Neg logit contributions | |
Luke | -2.070 |
ْ | -2.002 |
src | -1.968 |
女 | -1.955 |
Color | -1.945 |
Token | will |
Token ID | 481 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
cair | +1.685 |
AZ | +1.656 |
Yelp | +1.643 |
Auto | +1.557 |
Olympia | +1.504 |
Neg logit contributions | |
Luke | -1.637 |
ْ | -1.582 |
sky | -1.537 |
src | -1.536 |
女 | -1.535 |
Token | be |
Token ID | 307 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
cair | +1.324 |
AZ | +1.313 |
Yelp | +1.303 |
Auto | +1.230 |
Olympia | +1.191 |
Neg logit contributions | |
Luke | -1.500 |
ْ | -1.453 |
src | -1.414 |
sky | -1.414 |
Color | -1.410 |
Token | thanking |
Token ID | 41892 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
cair | +1.629 |
AZ | +1.622 |
Yelp | +1.610 |
Auto | +1.506 |
Olympia | +1.461 |
Neg logit contributions | |
Luke | -1.983 |
ْ | -1.924 |
src | -1.887 |
sky | -1.884 |
cylinders | -1.877 |
Token | defense |
Token ID | 3761 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
AZ | +1.636 |
cair | +1.621 |
Yelp | +1.609 |
Auto | +1.536 |
Olympia | +1.481 |
Neg logit contributions | |
Luke | -1.774 |
ْ | -1.725 |
src | -1.705 |
女 | -1.689 |
sky | -1.688 |
Token | , |
Token ID | 11 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
AZ | +1.756 |
Yelp | +1.735 |
cair | +1.725 |
Auto | +1.645 |
Olympia | +1.594 |
Neg logit contributions | |
Luke | -1.869 |
ْ | -1.820 |
src | -1.812 |
ample | -1.787 |
sky | -1.783 |
Token | Manning |
Token ID | 15281 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
cair | +0.542 |
AZ | +0.541 |
Yelp | +0.536 |
Auto | +0.501 |
Olympia | +0.482 |
Neg logit contributions | |
Luke | -0.832 |
ْ | -0.809 |
src | -0.803 |
sky | -0.798 |
Color | -0.792 |
Token | has |
Token ID | 468 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
AZ | +0.929 |
cair | +0.921 |
Yelp | +0.919 |
Auto | +0.875 |
Olympia | +0.846 |
Neg logit contributions | |
Luke | -0.849 |
ْ | -0.820 |
src | -0.808 |
sky | -0.801 |
Cla | -0.799 |
Token | averaged |
Token ID | 16449 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
cair | +0.310 |
AZ | +0.310 |
Yelp | +0.308 |
Auto | +0.293 |
Olympia | +0.286 |
Neg logit contributions | |
Luke | -0.234 |
ْ | -0.224 |
src | -0.220 |
sky | -0.219 |
Color | -0.217 |
Token | 203 |
Token ID | 27408 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
AZ | +0.556 |
cair | +0.556 |
Yelp | +0.553 |
Auto | +0.522 |
Olympia | +0.509 |
Neg logit contributions | |
Luke | -0.542 |
ْ | -0.524 |
src | -0.517 |
sky | -0.512 |
Color | -0.508 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
AZ | +3.589 |
Yelp | +3.555 |
cair | +3.442 |
Auto | +3.389 |
Olympia | +3.205 |
Neg logit contributions | |
Luke | -4.766 |
src | -4.596 |
ْ | -4.566 |
sky | -4.516 |
ample | -4.487 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
cair | +1.145 |
AZ | +1.130 |
Yelp | +1.124 |
Auto | +1.055 |
Olympia | +1.021 |
Neg logit contributions | |
Luke | -1.577 |
ْ | -1.533 |
src | -1.508 |
cylinders | -1.506 |
sky | -1.505 |
Token | passing |
Token ID | 6427 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
AZ | +0.886 |
cair | +0.886 |
Yelp | +0.883 |
Auto | +0.836 |
Olympia | +0.812 |
Neg logit contributions | |
Luke | -0.846 |
ْ | -0.814 |
src | -0.804 |
sky | -0.799 |
ample | -0.793 |
Token | yards |
Token ID | 5695 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
AZ | +0.161 |
cair | +0.161 |
Yelp | +0.160 |
Auto | +0.150 |
Olympia | +0.145 |
Neg logit contributions | |
Luke | -0.188 |
ْ | -0.181 |
src | -0.180 |
sky | -0.179 |
cylinders | -0.177 |
Token | with |
Token ID | 351 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Luke | +1.306 |
ْ | +1.242 |
src | +1.215 |
sky | +1.211 |
cylinders | +1.209 |
Neg logit contributions | |
cair | -1.886 |
AZ | -1.843 |
Yelp | -1.843 |
Auto | -1.743 |
Olympia | -1.717 |
Token | the |
Token ID | 262 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
cair | +0.084 |
AZ | +0.083 |
Yelp | +0.083 |
Auto | +0.079 |
Olympia | +0.077 |
Neg logit contributions | |
Luke | -0.078 |
ْ | -0.075 |
src | -0.074 |
sky | -0.073 |
ample | -0.073 |
Token | party |
Token ID | 2151 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Luke | +0.231 |
ْ | +0.222 |
src | +0.218 |
sky | +0.217 |
cylinders | +0.216 |
Neg logit contributions | |
cair | -0.239 |
AZ | -0.236 |
Yelp | -0.235 |
Auto | -0.223 |
Olympia | -0.218 |
Token | in |
Token ID | 287 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
cair | +1.105 |
AZ | +1.085 |
Yelp | +1.080 |
Auto | +1.025 |
Olympia | +1.002 |
Neg logit contributions | |
Luke | -1.077 |
ْ | -1.040 |
src | -1.025 |
sky | -1.016 |
ample | -1.015 |
Token | unprecedented |
Token ID | 13029 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Luke | +0.351 |
ْ | +0.337 |
src | +0.332 |
sky | +0.331 |
cylinders | +0.329 |
Neg logit contributions | |
cair | -0.388 |
AZ | -0.384 |
Yelp | -0.383 |
Auto | -0.361 |
Olympia | -0.354 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Luke | +0.495 |
ْ | +0.477 |
src | +0.470 |
cylinders | +0.470 |
sky | +0.469 |
Neg logit contributions | |
cair | -0.417 |
AZ | -0.407 |
Yelp | -0.406 |
Auto | -0.379 |
Olympia | -0.370 |
Token | ".[ |
Token ID | 42924 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
cair | +0.989 |
AZ | +0.981 |
Yelp | +0.977 |
Auto | +0.924 |
Olympia | +0.902 |
Neg logit contributions | |
Luke | -1.052 |
ْ | -1.011 |
src | -0.996 |
Cla | -0.991 |
sky | -0.991 |
Token | 35 |
Token ID | 2327 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
AZ | +4.031 |
cair | +4.023 |
Yelp | +3.986 |
Auto | +3.789 |
Olympia | +3.674 |
Neg logit contributions | |
Luke | -3.954 |
ْ | -3.922 |
cylinders | -3.911 |
ample | -3.797 |
女 | -3.776 |
Token | ] |
Token ID | 60 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Luke | +0.057 |
ْ | +0.055 |
src | +0.055 |
sky | +0.055 |
cylinders | +0.054 |
Neg logit contributions | |
cair | -0.034 |
AZ | -0.034 |
Yelp | -0.033 |
Auto | -0.031 |
Olympia | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Yelp | +1.233 |
AZ | +1.230 |
cair | +1.228 |
Auto | +1.166 |
Olympia | +1.144 |
Neg logit contributions | |
Luke | -1.097 |
ْ | -1.063 |
cylinders | -1.054 |
sky | -1.041 |
ample | -1.038 |
Token |
|
Token ID | 198 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
Luke | +0.325 |
ْ | +0.312 |
src | +0.306 |
sky | +0.305 |
cylinders | +0.304 |
Neg logit contributions | |
cair | -0.425 |
AZ | -0.421 |
Yelp | -0.419 |
Auto | -0.398 |
Olympia | -0.390 |
Token | The |
Token ID | 464 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
cair | +0.630 |
AZ | +0.620 |
Yelp | +0.619 |
Auto | +0.592 |
Olympia | +0.582 |
Neg logit contributions | |
Luke | -0.373 |
ْ | -0.361 |
cylinders | -0.358 |
sky | -0.350 |
src | -0.349 |
Token | at |
Token ID | 379 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
cair | +0.364 |
AZ | +0.363 |
Yelp | +0.361 |
Auto | +0.339 |
Olympia | +0.330 |
Neg logit contributions | |
Luke | -0.419 |
ْ | -0.406 |
src | -0.399 |
sky | -0.397 |
cylinders | -0.395 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
cair | +0.168 |
AZ | +0.167 |
Yelp | +0.166 |
Auto | +0.156 |
Olympia | +0.153 |
Neg logit contributions | |
Luke | -0.177 |
ْ | -0.171 |
src | -0.168 |
sky | -0.167 |
cylinders | -0.166 |
Token | expense |
Token ID | 10907 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Luke | +0.061 |
ْ | +0.059 |
src | +0.058 |
sky | +0.058 |
cylinders | +0.058 |
Neg logit contributions | |
cair | -0.058 |
AZ | -0.057 |
Yelp | -0.057 |
Auto | -0.053 |
Olympia | -0.052 |
Token | of |
Token ID | 286 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Luke | +0.857 |
ْ | +0.815 |
src | +0.810 |
sky | +0.808 |
Color | +0.800 |
Neg logit contributions | |
cair | -0.959 |
AZ | -0.940 |
Yelp | -0.935 |
Auto | -0.881 |
Olympia | -0.868 |
Token | common |
Token ID | 2219 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Luke | +0.522 |
ْ | +0.501 |
src | +0.494 |
sky | +0.493 |
cylinders | +0.491 |
Neg logit contributions | |
cair | -0.534 |
AZ | -0.523 |
Yelp | -0.521 |
Auto | -0.490 |
Olympia | -0.481 |
Token | sense |
Token ID | 2565 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
cair | +0.402 |
AZ | +0.397 |
Yelp | +0.395 |
Auto | +0.370 |
Olympia | +0.361 |
Neg logit contributions | |
Luke | -0.484 |
ْ | -0.467 |
src | -0.460 |
sky | -0.459 |
cylinders | -0.457 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
AZ | +3.560 |
Yelp | +3.533 |
cair | +3.327 |
Auto | +3.301 |
Olympia | +3.182 |
Neg logit contributions | |
Luke | -4.551 |
ْ | -4.438 |
src | -4.379 |
Cla | -4.346 |
sky | -4.304 |
Token | The |
Token ID | 383 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
cair | +0.024 |
AZ | +0.024 |
Yelp | +0.024 |
Auto | +0.022 |
Olympia | +0.022 |
Neg logit contributions | |
Luke | -0.024 |
ْ | -0.023 |
src | -0.023 |
sky | -0.023 |
cylinders | -0.023 |
Token | cardinal |
Token ID | 38691 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Luke | +0.315 |
ْ | +0.304 |
src | +0.299 |
sky | +0.298 |
cylinders | +0.297 |
Neg logit contributions | |
cair | -0.306 |
AZ | -0.302 |
Yelp | -0.301 |
Auto | -0.283 |
Olympia | -0.277 |
Token | lesson |
Token ID | 11483 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
cair | +0.390 |
AZ | +0.385 |
Yelp | +0.384 |
Auto | +0.365 |
Olympia | +0.358 |
Neg logit contributions | |
Luke | -0.270 |
ْ | -0.258 |
src | -0.253 |
sky | -0.252 |
cylinders | -0.251 |
Token | is |
Token ID | 318 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Luke | +0.517 |
ْ | +0.499 |
src | +0.491 |
sky | +0.487 |
cylinders | +0.484 |
Neg logit contributions | |
cair | -0.555 |
AZ | -0.552 |
Yelp | -0.550 |
Auto | -0.519 |
Olympia | -0.508 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
cair | +0.539 |
AZ | +0.536 |
Yelp | +0.528 |
Auto | +0.495 |
Olympia | +0.475 |
Neg logit contributions | |
Luke | -0.831 |
ْ | -0.802 |
src | -0.797 |
sky | -0.793 |
ample | -0.791 |
Token | lifetime |
Token ID | 10869 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Luke | +0.364 |
ْ | +0.350 |
src | +0.345 |
sky | +0.344 |
cylinders | +0.342 |
Neg logit contributions | |
cair | -0.349 |
AZ | -0.344 |
Yelp | -0.343 |
Auto | -0.322 |
Olympia | -0.315 |
Token | then |
Token ID | 788 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
AZ | +1.476 |
Yelp | +1.472 |
cair | +1.468 |
Auto | +1.390 |
Olympia | +1.353 |
Neg logit contributions | |
Luke | -1.489 |
ْ | -1.433 |
src | -1.414 |
女 | -1.403 |
Color | -1.401 |
Token | involves |
Token ID | 9018 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
cair | +0.428 |
AZ | +0.424 |
Yelp | +0.423 |
Auto | +0.400 |
Olympia | +0.391 |
Neg logit contributions | |
Luke | -0.397 |
ْ | -0.381 |
src | -0.375 |
sky | -0.373 |
Color | -0.372 |
Token | exchanges |
Token ID | 14525 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
AZ | +1.763 |
cair | +1.761 |
Yelp | +1.748 |
Auto | +1.658 |
Olympia | +1.614 |
Neg logit contributions | |
Luke | -1.838 |
ْ | -1.776 |
src | -1.751 |
Color | -1.728 |
sky | -1.728 |
Token | between |
Token ID | 1022 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
cair | +1.636 |
AZ | +1.631 |
Yelp | +1.615 |
Auto | +1.528 |
Olympia | +1.490 |
Neg logit contributions | |
Luke | -1.672 |
ْ | -1.621 |
src | -1.592 |
sky | -1.587 |
Color | -1.582 |
Token | surface |
Token ID | 4417 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
AZ | +4.002 |
Yelp | +3.896 |
cair | +3.885 |
Auto | +3.741 |
Olympia | +3.622 |
Neg logit contributions | |
Luke | -4.141 |
ْ | -3.959 |
女 | -3.930 |
Color | -3.891 |
src | -3.882 |
Token | ocean |
Token ID | 9151 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Luke | +0.037 |
ْ | +0.036 |
src | +0.035 |
sky | +0.035 |
Color | +0.035 |
Neg logit contributions | |
cair | -0.035 |
AZ | -0.034 |
Yelp | -0.034 |
Auto | -0.032 |
Olympia | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
cair | +0.350 |
AZ | +0.345 |
Yelp | +0.342 |
Auto | +0.324 |
Olympia | +0.316 |
Neg logit contributions | |
Luke | -0.348 |
ْ | -0.334 |
src | -0.329 |
sky | -0.327 |
女 | -0.326 |
Token | deep |
Token ID | 2769 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
Luke | +1.270 |
ْ | +1.225 |
sky | +1.205 |
src | +1.204 |
cylinders | +1.201 |
Neg logit contributions | |
cair | -1.256 |
AZ | -1.233 |
Yelp | -1.233 |
Auto | -1.157 |
Olympia | -1.133 |
Token | oceans |
Token ID | 23744 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Luke | +0.051 |
ْ | +0.049 |
src | +0.048 |
sky | +0.048 |
Color | +0.048 |
Neg logit contributions | |
cair | -0.054 |
AZ | -0.053 |
Yelp | -0.053 |
Auto | -0.050 |
Olympia | -0.049 |
Token | decision |
Token ID | 2551 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Luke | +0.211 |
ْ | +0.203 |
src | +0.199 |
sky | +0.199 |
cylinders | +0.198 |
Neg logit contributions | |
cair | -0.234 |
AZ | -0.231 |
Yelp | -0.230 |
Auto | -0.217 |
Olympia | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Luke | +0.754 |
ْ | +0.727 |
src | +0.716 |
sky | +0.714 |
cylinders | +0.711 |
Neg logit contributions | |
cair | -0.693 |
AZ | -0.683 |
Yelp | -0.680 |
Auto | -0.638 |
Olympia | -0.624 |
Token | according |
Token ID | 1864 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Luke | +0.241 |
ْ | +0.232 |
src | +0.229 |
sky | +0.228 |
cylinders | +0.227 |
Neg logit contributions | |
cair | -0.220 |
AZ | -0.217 |
Yelp | -0.216 |
Auto | -0.203 |
Olympia | -0.198 |
Token | to |
Token ID | 284 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Luke | +0.559 |
src | +0.535 |
ْ | +0.534 |
sky | +0.530 |
Color | +0.526 |
Neg logit contributions | |
cair | -0.488 |
AZ | -0.471 |
Yelp | -0.469 |
Auto | -0.436 |
Olympia | -0.429 |
Token | the |
Token ID | 262 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Luke | +0.220 |
ْ | +0.212 |
src | +0.208 |
sky | +0.208 |
cylinders | +0.207 |
Neg logit contributions | |
cair | -0.220 |
AZ | -0.218 |
Yelp | -0.217 |
Auto | -0.204 |
Olympia | -0.200 |
Token | press |
Token ID | 1803 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
cair | +0.360 |
AZ | +0.357 |
Yelp | +0.355 |
Auto | +0.335 |
Olympia | +0.327 |
Neg logit contributions | |
Luke | -0.394 |
ْ | -0.381 |
src | -0.374 |
sky | -0.373 |
Color | -0.370 |
Token | office |
Token ID | 2607 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
AZ | +3.479 |
Yelp | +3.430 |
cair | +3.418 |
Auto | +3.230 |
Olympia | +3.159 |
Neg logit contributions | |
Luke | -4.503 |
ْ | -4.356 |
sky | -4.288 |
Color | -4.270 |
ample | -4.264 |
Token | of |
Token ID | 286 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
cair | +1.172 |
AZ | +1.166 |
Yelp | +1.158 |
Auto | +1.093 |
Olympia | +1.068 |
Neg logit contributions | |
Luke | -1.187 |
ْ | -1.147 |
src | -1.127 |
sky | -1.120 |
Color | -1.113 |
Token | Romero |
Token ID | 38623 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Luke | +0.571 |
ْ | +0.551 |
src | +0.541 |
sky | +0.538 |
cylinders | +0.535 |
Neg logit contributions | |
cair | -0.555 |
AZ | -0.550 |
Yelp | -0.547 |
Auto | -0.515 |
Olympia | -0.505 |
Token | J |
Token ID | 449 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
cair | +0.259 |
AZ | +0.256 |
Yelp | +0.255 |
Auto | +0.241 |
Olympia | +0.235 |
Neg logit contributions | |
Luke | -0.266 |
ْ | -0.256 |
src | -0.252 |
sky | -0.251 |
cylinders | -0.250 |
Token | uca |
Token ID | 43120 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
cair | +0.181 |
AZ | +0.178 |
Yelp | +0.177 |
Auto | +0.168 |
Olympia | +0.164 |
Neg logit contributions | |
Luke | -0.185 |
ْ | -0.179 |
src | -0.175 |
cylinders | -0.174 |
sky | -0.174 |
Token | ager |
Token ID | 3536 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
cair | +0.447 |
AZ | +0.439 |
Yelp | +0.437 |
Auto | +0.401 |
Olympia | +0.390 |
Neg logit contributions | |
Luke | -0.753 |
ْ | -0.730 |
src | -0.722 |
sky | -0.721 |
cylinders | -0.717 |
Token | : |
Token ID | 25 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
cair | +0.041 |
AZ | +0.041 |
Yelp | +0.041 |
Auto | +0.038 |
Olympia | +0.038 |
Neg logit contributions | |
Luke | -0.043 |
ْ | -0.041 |
src | -0.040 |
sky | -0.040 |
cylinders | -0.040 |
Token | An |
Token ID | 1052 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Luke | +0.861 |
ْ | +0.828 |
src | +0.817 |
sky | +0.814 |
cylinders | +0.810 |
Neg logit contributions | |
cair | -0.834 |
AZ | -0.821 |
Yelp | -0.818 |
Auto | -0.768 |
Olympia | -0.751 |
Token | Aut |
Token ID | 5231 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
cair | +1.155 |
AZ | +1.144 |
Yelp | +1.134 |
Auto | +1.068 |
Olympia | +1.041 |
Neg logit contributions | |
Luke | -1.390 |
ْ | -1.343 |
src | -1.321 |
cylinders | -1.316 |
sky | -1.315 |
Token | obi |
Token ID | 13411 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
cair | +0.117 |
AZ | +0.115 |
Yelp | +0.114 |
Auto | +0.108 |
Olympia | +0.105 |
Neg logit contributions | |
Luke | -0.118 |
ْ | -0.114 |
src | -0.112 |
cylinders | -0.112 |
sky | -0.111 |
Token | ography |
Token ID | 4867 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
Luke | +0.300 |
ْ | +0.289 |
src | +0.284 |
sky | +0.283 |
cylinders | +0.282 |
Neg logit contributions | |
cair | -0.292 |
AZ | -0.288 |
Yelp | -0.287 |
Auto | -0.270 |
Olympia | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
AZ | +3.484 |
cair | +3.399 |
Yelp | +3.398 |
Auto | +3.273 |
Olympia | +3.148 |
Neg logit contributions | |
Luke | -4.538 |
ْ | -4.359 |
cylinders | -4.345 |
src | -4.312 |
女 | -4.311 |
Token | New |
Token ID | 968 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
cair | +0.422 |
AZ | +0.421 |
Yelp | +0.419 |
Auto | +0.396 |
Olympia | +0.388 |
Neg logit contributions | |
Luke | -0.399 |
ْ | -0.384 |
src | -0.377 |
cylinders | -0.377 |
sky | -0.375 |
Token | York |
Token ID | 1971 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Luke | +1.071 |
ْ | +1.032 |
src | +1.020 |
sky | +1.016 |
cylinders | +1.008 |
Neg logit contributions | |
cair | -1.003 |
AZ | -0.988 |
Yelp | -0.986 |
Auto | -0.922 |
Olympia | -0.902 |
Token | : |
Token ID | 25 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Luke | +0.409 |
ْ | +0.392 |
src | +0.386 |
cylinders | +0.384 |
sky | +0.384 |
Neg logit contributions | |
cair | -0.439 |
AZ | -0.436 |
Yelp | -0.432 |
Auto | -0.410 |
Olympia | -0.400 |
Token | B |
Token ID | 347 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Luke | +0.812 |
ْ | +0.783 |
src | +0.769 |
sky | +0.768 |
Color | +0.764 |
Neg logit contributions | |
cair | -0.794 |
AZ | -0.777 |
Yelp | -0.774 |
Auto | -0.726 |
Olympia | -0.710 |
Token | summed |
Token ID | 32794 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Luke | +0.117 |
ْ | +0.112 |
src | +0.110 |
cylinders | +0.109 |
sky | +0.109 |
Neg logit contributions | |
cair | -0.125 |
AZ | -0.123 |
Yelp | -0.123 |
Auto | -0.116 |
Olympia | -0.113 |
Token | up |
Token ID | 510 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
cair | +0.291 |
AZ | +0.289 |
Yelp | +0.288 |
Auto | +0.272 |
Olympia | +0.267 |
Neg logit contributions | |
Luke | -0.253 |
ْ | -0.241 |
src | -0.238 |
sky | -0.237 |
cylinders | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
Luke | +0.518 |
ْ | +0.497 |
src | +0.488 |
sky | +0.486 |
cylinders | +0.483 |
Neg logit contributions | |
cair | -0.595 |
AZ | -0.588 |
Yelp | -0.587 |
Auto | -0.554 |
Olympia | -0.543 |
Token | complicated |
Token ID | 8253 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
cair | +0.639 |
AZ | +0.637 |
Yelp | +0.634 |
Auto | +0.598 |
Olympia | +0.585 |
Neg logit contributions | |
Luke | -0.571 |
ْ | -0.548 |
src | -0.539 |
sky | -0.535 |
Color | -0.531 |
Token | unt |
Token ID | 1418 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
cair | +1.090 |
AZ | +1.089 |
Yelp | +1.086 |
Auto | +1.025 |
Olympia | +1.003 |
Neg logit contributions | |
Luke | -0.940 |
ْ | -0.910 |
src | -0.887 |
sky | -0.878 |
ample | -0.873 |
Token | angling |
Token ID | 27499 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
cair | +0.266 |
AZ | +0.262 |
Yelp | +0.261 |
Auto | +0.250 |
Olympia | +0.245 |
Neg logit contributions | |
Luke | -0.168 |
ْ | -0.162 |
cylinders | -0.157 |
src | -0.157 |
sky | -0.156 |
Token | that |
Token ID | 326 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Yelp | +3.710 |
AZ | +3.709 |
cair | +3.631 |
Auto | +3.501 |
Olympia | +3.375 |
Neg logit contributions | |
Luke | -4.257 |
ْ | -4.209 |
src | -4.059 |
ample | -4.028 |
Cla | -4.003 |
Token | lies |
Token ID | 7363 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
cair | +0.208 |
AZ | +0.207 |
Yelp | +0.207 |
Auto | +0.195 |
Olympia | +0.190 |
Neg logit contributions | |
Luke | -0.196 |
ْ | -0.189 |
src | -0.185 |
sky | -0.185 |
ample | -0.184 |
Token | ahead |
Token ID | 4058 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
cair | +0.538 |
AZ | +0.537 |
Yelp | +0.534 |
Auto | +0.502 |
Olympia | +0.487 |
Neg logit contributions | |
Luke | -0.663 |
ْ | -0.641 |
sky | -0.630 |
src | -0.630 |
Color | -0.625 |
Token | . |
Token ID | 13 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
cair | +0.592 |
AZ | +0.590 |
Yelp | +0.587 |
Auto | +0.553 |
Olympia | +0.540 |
Neg logit contributions | |
Luke | -0.663 |
ْ | -0.640 |
src | -0.627 |
sky | -0.627 |
cylinders | -0.622 |
Token |
|
Token ID | 198 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
cair | +0.049 |
AZ | +0.049 |
Yelp | +0.049 |
Auto | +0.046 |
Olympia | +0.045 |
Neg logit contributions | |
Luke | -0.041 |
ْ | -0.039 |
cylinders | -0.039 |
src | -0.039 |
sky | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
AZ | +0.949 |
Yelp | +0.946 |
cair | +0.937 |
Auto | +0.901 |
Olympia | +0.871 |
Neg logit contributions | |
Luke | -0.812 |
ْ | -0.794 |
cylinders | -0.784 |
ample | -0.765 |
女 | -0.764 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Luke | +0.116 |
ْ | +0.112 |
src | +0.109 |
cylinders | +0.109 |
sky | +0.109 |
Neg logit contributions | |
cair | -0.150 |
AZ | -0.149 |
Yelp | -0.148 |
Auto | -0.141 |
Olympia | -0.138 |
Token | Subject |
Token ID | 19776 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
cair | +1.404 |
AZ | +1.399 |
Yelp | +1.389 |
Auto | +1.337 |
Olympia | +1.299 |
Neg logit contributions | |
Luke | -0.689 |
ْ | -0.669 |
cylinders | -0.662 |
ample | -0.639 |
女 | -0.637 |
Token | : |
Token ID | 25 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
AZ | +2.467 |
Yelp | +2.449 |
cair | +2.433 |
Auto | +2.348 |
Olympia | +2.208 |
Neg logit contributions | |
Luke | -2.739 |
cylinders | -2.722 |
ْ | -2.695 |
ample | -2.601 |
Cla | -2.581 |
Token | User |
Token ID | 11787 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
cair | +0.951 |
AZ | +0.948 |
Yelp | +0.944 |
Auto | +0.888 |
Olympia | +0.863 |
Neg logit contributions | |
Luke | -1.039 |
ْ | -1.006 |
src | -0.988 |
sky | -0.986 |
cylinders | -0.979 |
Token | reviews |
Token ID | 8088 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
cair | +1.924 |
AZ | +1.911 |
Yelp | +1.908 |
Auto | +1.805 |
Olympia | +1.745 |
Neg logit contributions | |
Luke | -1.946 |
ْ | -1.894 |
sky | -1.850 |
cylinders | -1.846 |
src | -1.845 |
Token | are |
Token ID | 389 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Yelp | +3.871 |
AZ | +3.860 |
cair | +3.748 |
Auto | +3.631 |
Olympia | +3.495 |
Neg logit contributions | |
Luke | -4.164 |
ْ | -4.096 |
女 | -3.997 |
sky | -3.983 |
src | -3.974 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
cair | +1.573 |
AZ | +1.567 |
Yelp | +1.564 |
Auto | +1.464 |
Olympia | +1.426 |
Neg logit contributions | |
Luke | -1.712 |
ْ | -1.662 |
src | -1.630 |
sky | -1.622 |
Color | -1.613 |
Token | bad |
Token ID | 2089 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
cair | +0.829 |
AZ | +0.821 |
Yelp | +0.820 |
Auto | +0.768 |
Olympia | +0.750 |
Neg logit contributions | |
Luke | -0.860 |
ْ | -0.830 |
src | -0.818 |
sky | -0.814 |
cylinders | -0.810 |
Token | idea |
Token ID | 2126 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
cair | +0.399 |
AZ | +0.391 |
Yelp | +0.389 |
Auto | +0.368 |
Olympia | +0.361 |
Neg logit contributions | |
Luke | -0.354 |
ْ | -0.339 |
src | -0.334 |
sky | -0.332 |
cylinders | -0.331 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
cair | +0.330 |
AZ | +0.324 |
Yelp | +0.323 |
Auto | +0.303 |
Olympia | +0.297 |
Neg logit contributions | |
Luke | -0.361 |
ْ | -0.348 |
src | -0.343 |
sky | -0.342 |
cylinders | -0.340 |
Token | The |
Token ID | 383 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
cair | +0.205 |
AZ | +0.203 |
Yelp | +0.202 |
Auto | +0.190 |
Olympia | +0.186 |
Neg logit contributions | |
Luke | -0.215 |
ْ | -0.207 |
src | -0.204 |
sky | -0.204 |
cylinders | -0.203 |
Token | exact |
Token ID | 2748 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
cair | +0.240 |
AZ | +0.238 |
Yelp | +0.237 |
Auto | +0.224 |
Olympia | +0.219 |
Neg logit contributions | |
Luke | -0.236 |
ْ | -0.228 |
src | -0.224 |
sky | -0.224 |
ample | -0.221 |
Token | description |
Token ID | 6764 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Luke | +1.130 |
ْ | +1.081 |
src | +1.065 |
sky | +1.062 |
cylinders | +1.059 |
Neg logit contributions | |
cair | -1.399 |
AZ | -1.378 |
Yelp | -1.374 |
Auto | -1.300 |
Olympia | -1.275 |
Token | that |
Token ID | 326 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
AZ | +2.072 |
Yelp | +2.071 |
cair | +2.054 |
Auto | +1.957 |
Olympia | +1.879 |
Neg logit contributions | |
Luke | -2.191 |
ْ | -2.090 |
sky | -2.071 |
src | -2.071 |
Cla | -2.058 |
Token | went |
Token ID | 1816 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
cair | +0.318 |
AZ | +0.317 |
Yelp | +0.316 |
Auto | +0.297 |
Olympia | +0.289 |
Neg logit contributions | |
Luke | -0.339 |
ْ | -0.326 |
src | -0.322 |
sky | -0.321 |
cylinders | -0.318 |
Token | through |
Token ID | 832 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
cair | +0.695 |
AZ | +0.691 |
Yelp | +0.688 |
Auto | +0.647 |
Olympia | +0.631 |
Neg logit contributions | |
Luke | -0.722 |
ْ | -0.697 |
src | -0.686 |
sky | -0.681 |
cylinders | -0.680 |
Token | my |
Token ID | 616 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Yelp | +3.113 |
AZ | +3.045 |
cair | +2.903 |
Auto | +2.814 |
Olympia | +2.718 |
Neg logit contributions | |
Luke | -4.908 |
ْ | -4.801 |
sky | -4.695 |
src | -4.674 |
Cla | -4.674 |
Token | brain |
Token ID | 3632 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Yelp | +0.517 |
AZ | +0.517 |
cair | +0.516 |
Auto | +0.480 |
Olympia | +0.464 |
Neg logit contributions | |
Luke | -0.708 |
ْ | -0.685 |
src | -0.675 |
sky | -0.673 |
女 | -0.670 |
Token | during |
Token ID | 1141 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
cair | +0.601 |
AZ | +0.597 |
Yelp | +0.594 |
Auto | +0.561 |
Olympia | +0.546 |
Neg logit contributions | |
Luke | -0.577 |
ْ | -0.551 |
src | -0.544 |
sky | -0.543 |
cylinders | -0.540 |
Token | my |
Token ID | 616 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
AZ | +0.575 |
cair | +0.573 |
Yelp | +0.573 |
Auto | +0.539 |
Olympia | +0.528 |
Neg logit contributions | |
Luke | -0.656 |
ْ | -0.636 |
src | -0.625 |
sky | -0.625 |
女 | -0.619 |
Token | first |
Token ID | 717 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
Luke | +0.048 |
ْ | +0.046 |
src | +0.045 |
sky | +0.045 |
cylinders | +0.045 |
Neg logit contributions | |
cair | -0.049 |
AZ | -0.048 |
Yelp | -0.048 |
Auto | -0.045 |
Olympia | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
cair | +0.795 |
AZ | +0.794 |
Yelp | +0.785 |
Auto | +0.742 |
Olympia | +0.730 |
Neg logit contributions | |
Luke | -0.793 |
ْ | -0.768 |
src | -0.755 |
sky | -0.750 |
Color | -0.744 |
Token | giant |
Token ID | 6175 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
cair | +0.215 |
AZ | +0.214 |
Yelp | +0.213 |
Auto | +0.200 |
Olympia | +0.196 |
Neg logit contributions | |
Luke | -0.210 |
ْ | -0.202 |
src | -0.200 |
sky | -0.197 |
Color | -0.196 |
Token | lizard |
Token ID | 42406 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
cair | +0.070 |
AZ | +0.070 |
Yelp | +0.069 |
Auto | +0.065 |
Olympia | +0.064 |
Neg logit contributions | |
Luke | -0.075 |
ْ | -0.072 |
src | -0.071 |
sky | -0.070 |
Color | -0.070 |
Token | that |
Token ID | 326 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Luke | +0.583 |
ْ | +0.561 |
src | +0.554 |
sky | +0.551 |
cylinders | +0.548 |
Neg logit contributions | |
cair | -0.573 |
AZ | -0.565 |
Yelp | -0.563 |
Auto | -0.529 |
Olympia | -0.518 |
Token | sw |
Token ID | 1509 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
Luke | +0.266 |
ْ | +0.255 |
src | +0.251 |
sky | +0.250 |
Color | +0.247 |
Neg logit contributions | |
cair | -0.325 |
AZ | -0.322 |
Yelp | -0.321 |
Auto | -0.304 |
Olympia | -0.299 |
Token | am |
Token ID | 321 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
Luke | +0.019 |
ْ | +0.018 |
src | +0.018 |
sky | +0.018 |
cylinders | +0.018 |
Neg logit contributions | |
cair | -0.029 |
AZ | -0.028 |
Yelp | -0.028 |
Auto | -0.027 |
Olympia | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
AZ | +3.802 |
Yelp | +3.754 |
cair | +3.722 |
Auto | +3.558 |
Olympia | +3.556 |
Neg logit contributions | |
Luke | -4.124 |
ْ | -4.007 |
src | -3.934 |
Cla | -3.898 |
Color | -3.892 |
Token | shallow |
Token ID | 19337 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
cair | +0.424 |
AZ | +0.421 |
Yelp | +0.418 |
Auto | +0.395 |
Olympia | +0.390 |
Neg logit contributions | |
Luke | -0.390 |
ْ | -0.375 |
src | -0.371 |
sky | -0.365 |
Color | -0.365 |
Token | ocean |
Token ID | 9151 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Luke | +1.126 |
ْ | +1.084 |
src | +1.069 |
sky | +1.062 |
Color | +1.055 |
Neg logit contributions | |
cair | -1.134 |
AZ | -1.121 |
Yelp | -1.115 |
Auto | -1.050 |
Olympia | -1.029 |
Token | waters |
Token ID | 10150 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Luke | +0.027 |
ْ | +0.026 |
src | +0.026 |
sky | +0.025 |
Color | +0.025 |
Neg logit contributions | |
cair | -0.027 |
AZ | -0.026 |
Yelp | -0.026 |
Auto | -0.025 |
Olympia | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
cair | +0.283 |
AZ | +0.280 |
Yelp | +0.277 |
Auto | +0.261 |
Olympia | +0.256 |
Neg logit contributions | |
Luke | -0.298 |
ْ | -0.288 |
src | -0.283 |
sky | -0.282 |
Color | -0.281 |
Token | framework |
Token ID | 9355 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
Luke | +0.863 |
ْ | +0.830 |
src | +0.818 |
sky | +0.815 |
cylinders | +0.811 |
Neg logit contributions | |
cair | -0.876 |
AZ | -0.863 |
Yelp | -0.860 |
Auto | -0.810 |
Olympia | -0.793 |
Token | from |
Token ID | 422 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
cair | +0.515 |
AZ | +0.512 |
Yelp | +0.510 |
Auto | +0.483 |
Olympia | +0.470 |
Neg logit contributions | |
Luke | -0.474 |
ْ | -0.459 |
src | -0.446 |
sky | -0.445 |
女 | -0.444 |
Token | the |
Token ID | 262 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
Luke | +1.505 |
ْ | +1.446 |
src | +1.427 |
sky | +1.422 |
cylinders | +1.414 |
Neg logit contributions | |
cair | -1.621 |
AZ | -1.596 |
Yelp | -1.591 |
Auto | -1.498 |
Olympia | -1.470 |
Token | associated |
Token ID | 3917 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Luke | +0.332 |
ْ | +0.320 |
src | +0.314 |
sky | +0.314 |
cylinders | +0.312 |
Neg logit contributions | |
cair | -0.322 |
AZ | -0.319 |
Yelp | -0.317 |
Auto | -0.299 |
Olympia | -0.292 |
Token | command |
Token ID | 3141 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Luke | +0.083 |
ْ | +0.080 |
src | +0.079 |
sky | +0.079 |
cylinders | +0.078 |
Neg logit contributions | |
cair | -0.082 |
AZ | -0.081 |
Yelp | -0.081 |
Auto | -0.076 |
Olympia | -0.075 |
Token | line |
Token ID | 1627 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
cair | +0.876 |
AZ | +0.869 |
Yelp | +0.864 |
Auto | +0.818 |
Olympia | +0.796 |
Neg logit contributions | |
Luke | -0.887 |
ْ | -0.854 |
src | -0.834 |
sky | -0.834 |
cylinders | -0.829 |
Token | tool |
Token ID | 2891 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
AZ | +3.269 |
Yelp | +3.224 |
cair | +3.158 |
Auto | +3.080 |
Olympia | +2.929 |
Neg logit contributions | |
Luke | -4.709 |
ْ | -4.573 |
女 | -4.520 |
sky | -4.456 |
Cla | -4.443 |
Token | and |
Token ID | 290 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
cair | +0.356 |
AZ | +0.352 |
Yelp | +0.350 |
Auto | +0.332 |
Olympia | +0.324 |
Neg logit contributions | |
Luke | -0.326 |
ْ | -0.313 |
src | -0.307 |
sky | -0.306 |
cylinders | -0.305 |
Token | the |
Token ID | 262 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Luke | +0.381 |
ْ | +0.367 |
src | +0.363 |
sky | +0.362 |
cylinders | +0.360 |
Neg logit contributions | |
cair | -0.351 |
AZ | -0.344 |
Yelp | -0.343 |
Auto | -0.321 |
Olympia | -0.315 |
Token | package |
Token ID | 5301 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
cair | +0.159 |
AZ | +0.157 |
Yelp | +0.156 |
Auto | +0.147 |
Olympia | +0.143 |
Neg logit contributions | |
Luke | -0.170 |
ْ | -0.164 |
src | -0.161 |
sky | -0.160 |
cylinders | -0.160 |
Token | format |
Token ID | 5794 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
cair | +0.628 |
AZ | +0.621 |
Yelp | +0.618 |
Auto | +0.585 |
Olympia | +0.572 |
Neg logit contributions | |
Luke | -0.567 |
ْ | -0.545 |
src | -0.535 |
sky | -0.535 |
cylinders | -0.531 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
AZ | +0.689 |
cair | +0.688 |
Yelp | +0.688 |
Auto | +0.657 |
Olympia | +0.634 |
Neg logit contributions | |
Luke | -0.648 |
ْ | -0.620 |
sky | -0.611 |
src | -0.611 |
Cla | -0.605 |
Token | Court |
Token ID | 3078 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Luke | +0.730 |
ْ | +0.672 |
src | +0.669 |
Color | +0.667 |
sky | +0.666 |
Neg logit contributions | |
cair | -1.523 |
Yelp | -1.496 |
AZ | -1.495 |
Auto | -1.419 |
Olympia | -1.402 |
Token | case |
Token ID | 1339 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Luke | +2.816 |
ْ | +2.636 |
sky | +2.635 |
src | +2.626 |
Cla | +2.616 |
Neg logit contributions | |
cair | -3.311 |
Yelp | -3.206 |
AZ | -3.176 |
Auto | -3.023 |
Olympia | -2.966 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Luke | +2.166 |
ْ | +2.082 |
sky | +2.059 |
src | +2.055 |
Color | +2.039 |
Neg logit contributions | |
cair | -2.257 |
AZ | -2.184 |
Yelp | -2.175 |
Auto | -2.056 |
Olympia | -2.013 |
Token |
|
Token ID | 198 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
Luke | +1.226 |
ْ | +1.160 |
src | +1.150 |
sky | +1.145 |
Color | +1.137 |
Neg logit contributions | |
cair | -1.716 |
Yelp | -1.681 |
AZ | -1.680 |
Auto | -1.589 |
Olympia | -1.567 |
Token | Santa |
Token ID | 42694 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
Luke | +0.509 |
ْ | +0.484 |
src | +0.475 |
sky | +0.473 |
Color | +0.469 |
Neg logit contributions | |
cair | -0.775 |
AZ | -0.766 |
Yelp | -0.764 |
Auto | -0.727 |
Olympia | -0.714 |
Token | Clara |
Token ID | 27443 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
AZ | +5.291 |
cair | +5.289 |
Yelp | +5.176 |
Auto | +5.086 |
Olympia | +4.968 |
Neg logit contributions | |
Luke | -2.489 |
ْ | -2.445 |
cylinders | -2.428 |
女 | -2.397 |
sky | -2.389 |
Token | County |
Token ID | 3418 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
AZ | +1.162 |
Yelp | +1.148 |
cair | +1.146 |
Auto | +1.095 |
Olympia | +1.049 |
Neg logit contributions | |
Luke | -1.215 |
ْ | -1.176 |
src | -1.150 |
cylinders | -1.148 |
ample | -1.145 |
Token | v |
Token ID | 410 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
Luke | +0.458 |
ْ | +0.442 |
src | +0.434 |
sky | +0.431 |
cylinders | +0.430 |
Neg logit contributions | |
cair | -0.468 |
AZ | -0.465 |
Yelp | -0.462 |
Auto | -0.436 |
Olympia | -0.426 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Luke | +3.133 |
ْ | +3.007 |
sky | +3.003 |
src | +2.982 |
Color | +2.950 |
Neg logit contributions | |
cair | -3.111 |
Yelp | -2.979 |
AZ | -2.973 |
Auto | -2.786 |
Olympia | -2.731 |
Token | Southern |
Token ID | 8050 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Luke | +1.767 |
ْ | +1.693 |
sky | +1.673 |
src | +1.669 |
Color | +1.657 |
Neg logit contributions | |
cair | -1.721 |
AZ | -1.660 |
Yelp | -1.658 |
Auto | -1.555 |
Olympia | -1.523 |
Token | say |
Token ID | 910 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Luke | +0.222 |
ْ | +0.214 |
src | +0.211 |
sky | +0.210 |
Color | +0.209 |
Neg logit contributions | |
cair | -0.196 |
AZ | -0.193 |
Yelp | -0.193 |
Auto | -0.181 |
Olympia | -0.177 |
Token | " |
Token ID | 1 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Luke | +0.866 |
ْ | +0.834 |
src | +0.821 |
sky | +0.819 |
cylinders | +0.816 |
Neg logit contributions | |
cair | -0.821 |
AZ | -0.811 |
Yelp | -0.807 |
Auto | -0.759 |
Olympia | -0.742 |
Token |
|
Token ID | 198 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
cair | +0.253 |
AZ | +0.253 |
Yelp | +0.251 |
Auto | +0.240 |
Olympia | +0.234 |
Neg logit contributions | |
Luke | -0.211 |
ْ | -0.206 |
cylinders | -0.199 |
ample | -0.199 |
sky | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
AZ | +0.496 |
cair | +0.495 |
Yelp | +0.493 |
Auto | +0.470 |
Olympia | +0.457 |
Neg logit contributions | |
Luke | -0.404 |
ْ | -0.393 |
cylinders | -0.386 |
src | -0.380 |
sky | -0.379 |
Token | Lord |
Token ID | 22438 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
cair | +1.947 |
AZ | +1.919 |
Yelp | +1.888 |
Auto | +1.828 |
Olympia | +1.780 |
Neg logit contributions | |
cylinders | -1.210 |
ْ | -1.187 |
Luke | -1.179 |
ample | -1.143 |
src | -1.139 |
Token | Hes |
Token ID | 44773 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
cair | +0.050 |
AZ | +0.049 |
Yelp | +0.049 |
Auto | +0.046 |
Olympia | +0.044 |
Neg logit contributions | |
Luke | -0.082 |
ْ | -0.080 |
src | -0.079 |
cylinders | -0.078 |
ample | -0.078 |
Token | elt |
Token ID | 2120 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
cair | +2.879 |
Yelp | +2.674 |
AZ | +2.603 |
Auto | +2.413 |
Olympia | +2.353 |
Neg logit contributions | |
Luke | -5.112 |
ْ | -5.092 |
女 | -4.993 |
cylinders | -4.972 |
Cla | -4.829 |
Token | ine |
Token ID | 500 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Luke | +0.218 |
ْ | +0.208 |
src | +0.205 |
sky | +0.204 |
cylinders | +0.203 |
Neg logit contributions | |
cair | -0.273 |
AZ | -0.270 |
Yelp | -0.269 |
Auto | -0.255 |
Olympia | -0.250 |
Token | has |
Token ID | 468 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
cair | +1.157 |
AZ | +1.145 |
Yelp | +1.138 |
Auto | +1.077 |
Olympia | +1.043 |
Neg logit contributions | |
Luke | -1.157 |
ْ | -1.121 |
src | -1.105 |
ample | -1.098 |
Color | -1.092 |
Token | criticised |
Token ID | 23894 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
cair | +0.308 |
AZ | +0.305 |
Yelp | +0.305 |
Auto | +0.287 |
Olympia | +0.280 |
Neg logit contributions | |
Luke | -0.312 |
ْ | -0.302 |
src | -0.298 |
Color | -0.295 |
ample | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
AZ | +1.183 |
Yelp | +1.175 |
cair | +1.171 |
Auto | +1.112 |
Olympia | +1.085 |
Neg logit contributions | |
Luke | -1.103 |
ْ | -1.087 |
src | -1.065 |
ample | -1.045 |
Color | -1.043 |
Token | tool |
Token ID | 2891 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
cair | +1.010 |
AZ | +1.000 |
Yelp | +0.997 |
Auto | +0.943 |
Olympia | +0.918 |
Neg logit contributions | |
Luke | -0.988 |
ْ | -0.954 |
src | -0.934 |
sky | -0.933 |
Cla | -0.923 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
cair | +0.823 |
AZ | +0.814 |
Yelp | +0.810 |
Auto | +0.763 |
Olympia | +0.741 |
Neg logit contributions | |
Luke | -0.905 |
ْ | -0.875 |
src | -0.858 |
sky | -0.854 |
cylinders | -0.851 |
Token | get |
Token ID | 651 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Luke | +0.861 |
ْ | +0.826 |
src | +0.818 |
sky | +0.813 |
cylinders | +0.812 |
Neg logit contributions | |
cair | -0.873 |
AZ | -0.859 |
Yelp | -0.853 |
Auto | -0.801 |
Olympia | -0.787 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Luke | +0.324 |
ْ | +0.311 |
src | +0.306 |
sky | +0.305 |
cylinders | +0.304 |
Neg logit contributions | |
cair | -0.357 |
AZ | -0.352 |
Yelp | -0.351 |
Auto | -0.331 |
Olympia | -0.324 |
Token | better |
Token ID | 1365 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
cair | +0.777 |
AZ | +0.774 |
Yelp | +0.771 |
Auto | +0.723 |
Olympia | +0.701 |
Neg logit contributions | |
Luke | -0.862 |
ْ | -0.837 |
src | -0.824 |
cylinders | -0.811 |
sky | -0.810 |
Token | sense |
Token ID | 2565 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
cair | +0.632 |
AZ | +0.630 |
Yelp | +0.625 |
Auto | +0.587 |
Olympia | +0.570 |
Neg logit contributions | |
Luke | -0.757 |
ْ | -0.734 |
src | -0.722 |
sky | -0.715 |
cylinders | -0.713 |
Token | of |
Token ID | 286 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
AZ | +3.437 |
Yelp | +3.375 |
cair | +3.356 |
Auto | +3.221 |
Olympia | +3.073 |
Neg logit contributions | |
Luke | -4.352 |
ْ | -4.273 |
src | -4.194 |
Cla | -4.127 |
ample | -4.094 |
Token | how |
Token ID | 703 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
cair | +1.302 |
AZ | +1.298 |
Yelp | +1.286 |
Auto | +1.217 |
Olympia | +1.198 |
Neg logit contributions | |
Luke | -1.302 |
ْ | -1.256 |
src | -1.234 |
ample | -1.216 |
sky | -1.214 |
Token | much |
Token ID | 881 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
cair | +0.077 |
AZ | +0.076 |
Yelp | +0.076 |
Auto | +0.071 |
Olympia | +0.070 |
Neg logit contributions | |
Luke | -0.081 |
ْ | -0.078 |
src | -0.077 |
sky | -0.076 |
女 | -0.076 |
Token | ice |
Token ID | 4771 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
cair | +0.315 |
AZ | +0.312 |
Yelp | +0.311 |
Auto | +0.293 |
Olympia | +0.287 |
Neg logit contributions | |
Luke | -0.324 |
ْ | -0.314 |
src | -0.309 |
sky | -0.306 |
ample | -0.304 |
Token | broke |
Token ID | 6265 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Luke | +0.599 |
ْ | +0.575 |
src | +0.568 |
sky | +0.564 |
Color | +0.560 |
Neg logit contributions | |
cair | -0.669 |
AZ | -0.663 |
Yelp | -0.660 |
Auto | -0.624 |
Olympia | -0.612 |
Token | model |
Token ID | 2746 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
cair | +0.441 |
AZ | +0.439 |
Yelp | +0.437 |
Auto | +0.419 |
Olympia | +0.413 |
Neg logit contributions | |
Luke | -0.209 |
ْ | -0.199 |
src | -0.192 |
sky | -0.192 |
cylinders | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
cair | +0.410 |
AZ | +0.402 |
Yelp | +0.401 |
Auto | +0.375 |
Olympia | +0.367 |
Neg logit contributions | |
Luke | -0.463 |
ْ | -0.445 |
src | -0.440 |
sky | -0.438 |
Color | -0.435 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Luke | +0.025 |
ْ | +0.024 |
src | +0.023 |
sky | +0.023 |
cylinders | +0.023 |
Neg logit contributions | |
cair | -0.028 |
AZ | -0.027 |
Yelp | -0.027 |
Auto | -0.026 |
Olympia | -0.025 |
Token | Ch |
Token ID | 1925 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
cair | +0.112 |
AZ | +0.111 |
Yelp | +0.110 |
Auto | +0.105 |
Olympia | +0.103 |
Neg logit contributions | |
Luke | -0.072 |
ْ | -0.069 |
cylinders | -0.068 |
src | -0.067 |
sky | -0.067 |
Token | ances |
Token ID | 1817 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
cair | +0.453 |
AZ | +0.446 |
Yelp | +0.444 |
Auto | +0.420 |
Olympia | +0.409 |
Neg logit contributions | |
Luke | -0.429 |
ْ | -0.414 |
src | -0.406 |
cylinders | -0.405 |
sky | -0.404 |
Token | are |
Token ID | 389 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Yelp | +3.463 |
AZ | +3.459 |
cair | +3.390 |
Auto | +3.244 |
Olympia | +3.148 |
Neg logit contributions | |
Luke | -4.006 |
ْ | -3.913 |
src | -3.845 |
cylinders | -3.789 |
sky | -3.756 |
Token | pretty |
Token ID | 2495 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Yelp | +3.557 |
AZ | +3.547 |
cair | +3.407 |
Auto | +3.280 |
Olympia | +3.250 |
Neg logit contributions | |
Luke | -4.333 |
ْ | -4.253 |
src | -4.202 |
cylinders | -4.092 |
Cla | -4.074 |
Token | good |
Token ID | 922 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
AZ | +1.882 |
Yelp | +1.852 |
cair | +1.819 |
Auto | +1.728 |
Olympia | +1.693 |
Neg logit contributions | |
Luke | -2.523 |
src | -2.457 |
ْ | -2.456 |
Cla | -2.384 |
cylinders | -2.376 |
Token | that |
Token ID | 326 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
AZ | +3.192 |
Yelp | +3.187 |
cair | +3.022 |
Auto | +2.952 |
Olympia | +2.888 |
Neg logit contributions | |
Luke | -3.853 |
ْ | -3.797 |
src | -3.775 |
Color | -3.683 |
cylinders | -3.682 |
Token | you |
Token ID | 345 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Yelp | +1.519 |
AZ | +1.514 |
cair | +1.491 |
Auto | +1.429 |
Olympia | +1.389 |
Neg logit contributions | |
Luke | -1.669 |
ْ | -1.635 |
src | -1.596 |
sky | -1.585 |
Color | -1.578 |
Token | � |
Token ID | 447 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
cair | +1.006 |
AZ | +0.997 |
Yelp | +0.995 |
Auto | +0.935 |
Olympia | +0.904 |
Neg logit contributions | |
Luke | -1.203 |
ْ | -1.172 |
src | -1.146 |
ample | -1.142 |
Color | -1.138 |
Token | Important |
Token ID | 28511 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Luke | +0.939 |
ْ | +0.909 |
sky | +0.897 |
Color | +0.896 |
src | +0.894 |
Neg logit contributions | |
cair | -0.768 |
AZ | -0.745 |
Yelp | -0.743 |
Auto | -0.686 |
Olympia | -0.671 |
Token | Figures |
Token ID | 36574 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
AZ | +1.167 |
Yelp | +1.155 |
cair | +1.150 |
Auto | +1.105 |
Olympia | +1.078 |
Neg logit contributions | |
Luke | -1.221 |
ْ | -1.179 |
src | -1.152 |
ample | -1.147 |
sky | -1.143 |
Token | in |
Token ID | 287 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
cair | +0.311 |
AZ | +0.307 |
Yelp | +0.305 |
Auto | +0.288 |
Olympia | +0.281 |
Neg logit contributions | |
Luke | -0.328 |
ْ | -0.316 |
src | -0.311 |
sky | -0.310 |
cylinders | -0.309 |
Token | Black |
Token ID | 2619 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
AZ | +1.628 |
Yelp | +1.616 |
cair | +1.614 |
Auto | +1.553 |
Olympia | +1.506 |
Neg logit contributions | |
Luke | -1.685 |
ْ | -1.607 |
cylinders | -1.573 |
src | -1.573 |
sky | -1.570 |
Token | US |
Token ID | 1294 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
AZ | +1.327 |
Yelp | +1.327 |
cair | +1.326 |
Auto | +1.258 |
Olympia | +1.217 |
Neg logit contributions | |
Luke | -1.769 |
ْ | -1.705 |
cylinders | -1.686 |
src | -1.681 |
Cla | -1.669 |
Token | History |
Token ID | 7443 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
cair | +0.811 |
AZ | +0.803 |
Yelp | +0.801 |
Auto | +0.757 |
Olympia | +0.732 |
Neg logit contributions | |
Luke | -1.062 |
ْ | -1.024 |
cylinders | -1.009 |
src | -1.009 |
sky | -1.007 |
Token | ." |
Token ID | 526 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
AZ | +3.096 |
Yelp | +3.049 |
cair | +3.044 |
Auto | +2.910 |
Olympia | +2.777 |
Neg logit contributions | |
Luke | -4.723 |
ْ | -4.568 |
ample | -4.499 |
src | -4.471 |
sky | -4.466 |
Token | In |
Token ID | 554 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
AZ | +1.603 |
Yelp | +1.602 |
cair | +1.573 |
Auto | +1.511 |
Olympia | +1.484 |
Neg logit contributions | |
Luke | -1.507 |
cylinders | -1.460 |
ْ | -1.454 |
sky | -1.434 |
ample | -1.419 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
cair | +0.660 |
AZ | +0.657 |
Yelp | +0.654 |
Auto | +0.615 |
Olympia | +0.604 |
Neg logit contributions | |
Luke | -0.693 |
ْ | -0.668 |
src | -0.655 |
sky | -0.654 |
cylinders | -0.651 |
Token | , |
Token ID | 11 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Luke | +0.027 |
ْ | +0.026 |
sky | +0.026 |
src | +0.026 |
cylinders | +0.025 |
Neg logit contributions | |
cair | -0.029 |
AZ | -0.029 |
Yelp | -0.029 |
Auto | -0.028 |
Olympia | -0.027 |
Token | Eb |
Token ID | 12119 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Luke | +0.368 |
ْ | +0.353 |
src | +0.345 |
sky | +0.345 |
cylinders | +0.343 |
Neg logit contributions | |
cair | -0.424 |
AZ | -0.422 |
Yelp | -0.422 |
Auto | -0.398 |
Olympia | -0.391 |
Token | for |
Token ID | 329 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Luke | +1.187 |
ْ | +1.145 |
src | +1.127 |
sky | +1.123 |
cylinders | +1.117 |
Neg logit contributions | |
cair | -1.135 |
AZ | -1.122 |
Yelp | -1.119 |
Auto | -1.050 |
Olympia | -1.026 |
Token | virtual |
Token ID | 7166 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Luke | +0.160 |
ْ | +0.154 |
src | +0.152 |
sky | +0.150 |
女 | +0.150 |
Neg logit contributions | |
AZ | -0.164 |
cair | -0.163 |
Yelp | -0.162 |
Auto | -0.153 |
Olympia | -0.149 |
Token | creatures |
Token ID | 8109 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
AZ | +0.968 |
Yelp | +0.959 |
cair | +0.949 |
Auto | +0.901 |
Olympia | +0.877 |
Neg logit contributions | |
Luke | -1.007 |
ْ | -0.983 |
src | -0.971 |
女 | -0.952 |
Color | -0.946 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
AZ | +0.980 |
cair | +0.969 |
Yelp | +0.969 |
Auto | +0.912 |
Olympia | +0.893 |
Neg logit contributions | |
Luke | -1.094 |
ْ | -1.064 |
src | -1.041 |
Color | -1.030 |
sky | -1.030 |
Token | ( |
Token ID | 357 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Luke | +0.217 |
ْ | +0.211 |
cylinders | +0.206 |
src | +0.205 |
sky | +0.204 |
Neg logit contributions | |
cair | -0.235 |
AZ | -0.235 |
Yelp | -0.234 |
Auto | -0.221 |
Olympia | -0.216 |
Token | Photo |
Token ID | 6191 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
Luke | +0.453 |
ْ | +0.415 |
src | +0.405 |
sky | +0.401 |
Color | +0.397 |
Neg logit contributions | |
cair | -1.348 |
AZ | -1.330 |
Yelp | -1.329 |
Auto | -1.275 |
Olympia | -1.260 |
Token | : |
Token ID | 25 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Luke | +3.582 |
src | +3.390 |
sky | +3.354 |
Color | +3.307 |
Cla | +3.264 |
Neg logit contributions | |
cair | -5.527 |
Yelp | -5.122 |
AZ | -5.109 |
Olympia | -4.841 |
Auto | -4.814 |
Token | KY |
Token ID | 33668 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Luke | +1.406 |
ْ | +1.351 |
src | +1.331 |
sky | +1.326 |
cylinders | +1.319 |
Neg logit contributions | |
cair | -1.445 |
AZ | -1.420 |
Yelp | -1.416 |
Auto | -1.333 |
Olympia | -1.305 |
Token | LE |
Token ID | 2538 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
AZ | +1.171 |
cair | +1.167 |
Yelp | +1.159 |
Auto | +1.111 |
Olympia | +1.082 |
Neg logit contributions | |
Luke | -0.524 |
ْ | -0.513 |
女 | -0.489 |
cylinders | -0.484 |
src | -0.481 |
Token | GR |
Token ID | 10863 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Luke | +0.817 |
ْ | +0.788 |
src | +0.781 |
sky | +0.772 |
Color | +0.771 |
Neg logit contributions | |
cair | -0.592 |
Yelp | -0.568 |
AZ | -0.561 |
Auto | -0.523 |
Olympia | -0.515 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Luke | +0.936 |
ْ | +0.897 |
src | +0.883 |
sky | +0.879 |
cylinders | +0.874 |
Neg logit contributions | |
cair | -1.102 |
AZ | -1.087 |
Yelp | -1.084 |
Auto | -1.025 |
Olympia | -1.005 |
Token | anywhere |
Token ID | 6609 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Luke | +2.047 |
ْ | +1.963 |
cylinders | +1.937 |
sky | +1.926 |
src | +1.923 |
Neg logit contributions | |
cair | -2.282 |
Yelp | -2.223 |
AZ | -2.221 |
Auto | -2.080 |
Olympia | -2.053 |
Token | from |
Token ID | 422 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Luke | +1.656 |
ْ | +1.590 |
sky | +1.555 |
src | +1.553 |
cylinders | +1.548 |
Neg logit contributions | |
cair | -2.129 |
AZ | -2.090 |
Yelp | -2.089 |
Auto | -1.971 |
Olympia | -1.936 |
Token | two |
Token ID | 734 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Luke | +0.370 |
ْ | +0.357 |
src | +0.352 |
sky | +0.351 |
Color | +0.348 |
Neg logit contributions | |
cair | -0.333 |
AZ | -0.330 |
Yelp | -0.328 |
Auto | -0.308 |
Olympia | -0.301 |
Token | to |
Token ID | 284 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Luke | +1.129 |
ْ | +1.089 |
src | +1.073 |
sky | +1.070 |
cylinders | +1.066 |
Neg logit contributions | |
cair | -1.011 |
AZ | -0.994 |
Yelp | -0.991 |
Auto | -0.928 |
Olympia | -0.908 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Luke | +0.463 |
ْ | +0.446 |
src | +0.440 |
sky | +0.439 |
cylinders | +0.437 |
Neg logit contributions | |
cair | -0.425 |
AZ | -0.419 |
Yelp | -0.418 |
Auto | -0.392 |
Olympia | -0.383 |
Token | yards |
Token ID | 5695 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
Luke | +1.447 |
ْ | +1.394 |
src | +1.371 |
sky | +1.369 |
cylinders | +1.369 |
Neg logit contributions | |
cair | -1.488 |
AZ | -1.458 |
Yelp | -1.457 |
Auto | -1.368 |
Olympia | -1.344 |
Token | off |
Token ID | 572 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Luke | +4.029 |
ْ | +3.858 |
cylinders | +3.819 |
sky | +3.816 |
ample | +3.792 |
Neg logit contributions | |
cair | -4.812 |
Yelp | -4.652 |
AZ | -4.624 |
Olympia | -4.375 |
Auto | -4.329 |
Token | of |
Token ID | 286 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Luke | +1.718 |
ْ | +1.649 |
src | +1.624 |
sky | +1.618 |
cylinders | +1.607 |
Neg logit contributions | |
cair | -1.834 |
AZ | -1.811 |
Yelp | -1.803 |
Auto | -1.702 |
Olympia | -1.666 |
Token | their |
Token ID | 511 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Luke | +1.314 |
ْ | +1.261 |
src | +1.240 |
sky | +1.235 |
cylinders | +1.229 |
Neg logit contributions | |
cair | -1.515 |
AZ | -1.495 |
Yelp | -1.490 |
Auto | -1.408 |
Olympia | -1.380 |
Token | man |
Token ID | 582 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
Luke | +0.539 |
ْ | +0.518 |
src | +0.510 |
sky | +0.508 |
cylinders | +0.505 |
Neg logit contributions | |
cair | -0.540 |
AZ | -0.534 |
Yelp | -0.531 |
Auto | -0.501 |
Olympia | -0.490 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Luke | +0.614 |
ْ | +0.591 |
src | +0.583 |
sky | +0.580 |
Color | +0.578 |
Neg logit contributions | |
cair | -0.553 |
AZ | -0.546 |
Yelp | -0.543 |
Auto | -0.511 |
Olympia | -0.497 |
Token | t |
Token ID | 83 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
cair | +0.052 |
AZ | +0.051 |
Yelp | +0.051 |
Auto | +0.048 |
Olympia | +0.048 |
Neg logit contributions | |
Luke | -0.038 |
ْ | -0.036 |
src | -0.035 |
sky | -0.035 |
cylinders | -0.035 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Luke | +0.295 |
ْ | +0.285 |
src | +0.282 |
sky | +0.280 |
cylinders | +0.279 |
Neg logit contributions | |
cair | -0.287 |
AZ | -0.280 |
Yelp | -0.279 |
Auto | -0.262 |
Olympia | -0.258 |
Token | away |
Token ID | 1497 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Luke | +0.893 |
ْ | +0.861 |
sky | +0.846 |
src | +0.844 |
cylinders | +0.838 |
Neg logit contributions | |
cair | -1.036 |
AZ | -1.012 |
Yelp | -1.004 |
Auto | -0.952 |
Olympia | -0.934 |
Token | or |
Token ID | 393 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Luke | +1.361 |
ْ | +1.312 |
src | +1.288 |
sky | +1.282 |
cylinders | +1.277 |
Neg logit contributions | |
cair | -1.481 |
AZ | -1.453 |
Yelp | -1.449 |
Auto | -1.366 |
Olympia | -1.340 |
Token | tell |
Token ID | 1560 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Luke | +0.371 |
ْ | +0.357 |
src | +0.352 |
sky | +0.350 |
cylinders | +0.348 |
Neg logit contributions | |
cair | -0.389 |
AZ | -0.383 |
Yelp | -0.381 |
Auto | -0.359 |
Olympia | -0.352 |
Token | me |
Token ID | 502 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
Luke | +0.457 |
ْ | +0.439 |
src | +0.432 |
sky | +0.431 |
cylinders | +0.429 |
Neg logit contributions | |
cair | -0.474 |
AZ | -0.468 |
Yelp | -0.466 |
Auto | -0.440 |
Olympia | -0.430 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Luke | +3.939 |
ْ | +3.812 |
src | +3.765 |
sky | +3.722 |
Color | +3.701 |
Neg logit contributions | |
cair | -4.683 |
AZ | -4.525 |
Yelp | -4.486 |
Auto | -4.246 |
Olympia | -4.235 |
Token | get |
Token ID | 651 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Luke | +1.062 |
ْ | +1.026 |
src | +1.010 |
sky | +1.006 |
cylinders | +0.998 |
Neg logit contributions | |
cair | -1.056 |
AZ | -1.031 |
Yelp | -1.025 |
Auto | -0.966 |
Olympia | -0.949 |
Token | out |
Token ID | 503 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Luke | +1.444 |
ْ | +1.390 |
sky | +1.356 |
src | +1.356 |
ample | +1.350 |
Neg logit contributions | |
cair | -1.736 |
AZ | -1.685 |
Yelp | -1.666 |
Auto | -1.582 |
Olympia | -1.559 |
Token | of |
Token ID | 286 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Luke | +0.346 |
ْ | +0.333 |
src | +0.328 |
sky | +0.327 |
cylinders | +0.325 |
Neg logit contributions | |
cair | -0.354 |
AZ | -0.349 |
Yelp | -0.348 |
Auto | -0.328 |
Olympia | -0.321 |
Token | here |
Token ID | 994 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
Luke | +0.296 |
ْ | +0.286 |
src | +0.282 |
sky | +0.280 |
cylinders | +0.279 |
Neg logit contributions | |
cair | -0.288 |
AZ | -0.283 |
Yelp | -0.281 |
Auto | -0.265 |
Olympia | -0.259 |
Token | T |
Token ID | 309 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Luke | +2.550 |
src | +2.458 |
ْ | +2.451 |
Color | +2.429 |
sky | +2.419 |
Neg logit contributions | |
cair | -1.967 |
Yelp | -1.894 |
AZ | -1.873 |
Olympia | -1.727 |
Auto | -1.724 |
Token | > |
Token ID | 1875 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Luke | +0.992 |
ْ | +0.955 |
src | +0.943 |
sky | +0.939 |
Color | +0.934 |
Neg logit contributions | |
cair | -0.918 |
AZ | -0.904 |
Yelp | -0.901 |
Auto | -0.843 |
Olympia | -0.826 |
Token | D |
Token ID | 360 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Luke | +2.480 |
src | +2.370 |
ْ | +2.369 |
Color | +2.338 |
sky | +2.330 |
Neg logit contributions | |
cair | -2.200 |
Yelp | -2.126 |
AZ | -2.116 |
Olympia | -1.960 |
Auto | -1.946 |
Token | ere |
Token ID | 567 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
Luke | +0.979 |
ْ | +0.938 |
src | +0.926 |
sky | +0.923 |
Color | +0.917 |
Neg logit contributions | |
cair | -1.054 |
AZ | -1.044 |
Yelp | -1.040 |
Auto | -0.975 |
Olympia | -0.961 |
Token | f |
Token ID | 69 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Luke | +2.300 |
src | +2.233 |
ample | +2.183 |
sky | +2.174 |
ْ | +2.171 |
Neg logit contributions | |
cair | -3.072 |
AZ | -3.067 |
Yelp | -3.031 |
Olympia | -2.859 |
Auto | -2.830 |
Token | Mut |
Token ID | 41603 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
Luke | +0.972 |
ْ | +0.937 |
src | +0.922 |
sky | +0.920 |
cylinders | +0.915 |
Neg logit contributions | |
cair | -0.937 |
AZ | -0.924 |
Yelp | -0.920 |
Auto | -0.866 |
Olympia | -0.846 |
Token | for |
Token ID | 329 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Luke | +4.402 |
Color | +4.236 |
src | +4.206 |
ْ | +4.169 |
sky | +4.153 |
Neg logit contributions | |
cair | -4.232 |
Yelp | -4.217 |
AZ | -4.178 |
Olympia | -3.859 |
Auto | -3.790 |
Token | Own |
Token ID | 11744 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
Luke | +2.126 |
ْ | +2.066 |
src | +2.052 |
sky | +2.039 |
Color | +2.031 |
Neg logit contributions | |
cair | -0.849 |
Yelp | -0.815 |
AZ | -0.813 |
Auto | -0.716 |
Olympia | -0.702 |
Token | ed |
Token ID | 276 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Luke | +0.028 |
ْ | +0.027 |
src | +0.026 |
cylinders | +0.026 |
sky | +0.026 |
Neg logit contributions | |
cair | -0.047 |
AZ | -0.047 |
Yelp | -0.047 |
Auto | -0.045 |
Olympia | -0.044 |
Token | < |
Token ID | 1279 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Luke | +0.312 |
ْ | +0.299 |
src | +0.293 |
sky | +0.292 |
cylinders | +0.291 |
Neg logit contributions | |
cair | -0.407 |
AZ | -0.403 |
Yelp | -0.402 |
Auto | -0.382 |
Olympia | -0.373 |
Token | T |
Token ID | 309 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Luke | +1.910 |
src | +1.855 |
ْ | +1.826 |
Color | +1.819 |
sky | +1.817 |
Neg logit contributions | |
cair | -1.524 |
Yelp | -1.436 |
AZ | -1.422 |
Olympia | -1.314 |
Auto | -1.295 |
Token | ale |
Token ID | 1000 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
cair | +0.737 |
AZ | +0.722 |
Yelp | +0.720 |
Auto | +0.689 |
Olympia | +0.674 |
Neg logit contributions | |
Luke | -0.546 |
ْ | -0.523 |
cylinders | -0.511 |
src | -0.509 |
sky | -0.507 |
Token | otti |
Token ID | 26380 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
cair | +0.335 |
AZ | +0.330 |
Yelp | +0.329 |
Auto | +0.311 |
Olympia | +0.304 |
Neg logit contributions | |
Luke | -0.297 |
ْ | -0.286 |
src | -0.280 |
sky | -0.279 |
cylinders | -0.279 |
Token | agrees |
Token ID | 14386 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Luke | +0.007 |
ْ | +0.007 |
src | +0.007 |
sky | +0.007 |
cylinders | +0.007 |
Neg logit contributions | |
cair | -0.008 |
AZ | -0.008 |
Yelp | -0.008 |
Auto | -0.007 |
Olympia | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Luke | +0.949 |
ْ | +0.914 |
src | +0.900 |
sky | +0.897 |
cylinders | +0.892 |
Neg logit contributions | |
cair | -0.931 |
AZ | -0.917 |
Yelp | -0.913 |
Auto | -0.859 |
Olympia | -0.841 |
Token | telling |
Token ID | 5149 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
cair | +0.077 |
AZ | +0.076 |
Yelp | +0.075 |
Auto | +0.071 |
Olympia | +0.069 |
Neg logit contributions | |
Luke | -0.089 |
ْ | -0.086 |
src | -0.085 |
sky | -0.084 |
cylinders | -0.084 |
Token | me |
Token ID | 502 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
cair | +0.217 |
AZ | +0.214 |
Yelp | +0.213 |
Auto | +0.200 |
Olympia | +0.196 |
Neg logit contributions | |
Luke | -0.234 |
ْ | -0.225 |
src | -0.222 |
sky | -0.221 |
cylinders | -0.220 |
Token | that |
Token ID | 326 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Luke | +3.845 |
ْ | +3.754 |
sky | +3.656 |
src | +3.654 |
Color | +3.608 |
Neg logit contributions | |
cair | -4.620 |
Yelp | -4.434 |
AZ | -4.433 |
Auto | -4.159 |
Olympia | -4.125 |
Token | when |
Token ID | 618 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Luke | +0.720 |
ْ | +0.692 |
src | +0.682 |
sky | +0.680 |
cylinders | +0.676 |
Neg logit contributions | |
cair | -0.772 |
AZ | -0.760 |
Yelp | -0.757 |
Auto | -0.713 |
Olympia | -0.699 |
Token | Vladimir |
Token ID | 14840 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Luke | +0.795 |
ْ | +0.765 |
src | +0.753 |
sky | +0.752 |
cylinders | +0.748 |
Neg logit contributions | |
cair | -0.801 |
AZ | -0.787 |
Yelp | -0.784 |
Auto | -0.737 |
Olympia | -0.722 |
Token | Putin |
Token ID | 8144 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Luke | +1.080 |
ْ | +1.029 |
src | +1.013 |
sky | +1.004 |
cylinders | +1.002 |
Neg logit contributions | |
cair | -1.491 |
AZ | -1.477 |
Yelp | -1.471 |
Auto | -1.399 |
Olympia | -1.371 |
Token | � |
Token ID | 564 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Luke | +0.674 |
ْ | +0.645 |
src | +0.635 |
sky | +0.631 |
cylinders | +0.629 |
Neg logit contributions | |
cair | -0.786 |
AZ | -0.777 |
Yelp | -0.774 |
Auto | -0.733 |
Olympia | -0.717 |
Token | active |
Token ID | 4075 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Luke | +0.552 |
ْ | +0.532 |
src | +0.524 |
sky | +0.522 |
cylinders | +0.520 |
Neg logit contributions | |
cair | -0.521 |
AZ | -0.514 |
Yelp | -0.512 |
Auto | -0.480 |
Olympia | -0.470 |
Token | � |
Token ID | 447 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Luke | +0.500 |
ْ | +0.482 |
src | +0.475 |
sky | +0.473 |
cylinders | +0.471 |
Neg logit contributions | |
cair | -0.496 |
AZ | -0.489 |
Yelp | -0.487 |
Auto | -0.458 |
Olympia | -0.449 |
Token | � |
Token ID | 251 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Luke | +1.322 |
ْ | +1.277 |
src | +1.263 |
sky | +1.248 |
Color | +1.243 |
Neg logit contributions | |
cair | -1.440 |
Yelp | -1.400 |
AZ | -1.399 |
Auto | -1.318 |
Olympia | -1.300 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Luke | +0.704 |
ْ | +0.676 |
src | +0.670 |
sky | +0.665 |
cylinders | +0.663 |
Neg logit contributions | |
cair | -0.744 |
AZ | -0.730 |
Yelp | -0.729 |
Auto | -0.684 |
Olympia | -0.675 |
Token | a |
Token ID | 257 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
cair | +0.198 |
AZ | +0.196 |
Yelp | +0.195 |
Auto | +0.184 |
Olympia | +0.179 |
Neg logit contributions | |
Luke | -0.196 |
ْ | -0.189 |
src | -0.186 |
sky | -0.186 |
cylinders | -0.184 |
Token | borrow |
Token ID | 8804 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Luke | +0.330 |
ْ | +0.318 |
src | +0.313 |
sky | +0.312 |
cylinders | +0.311 |
Neg logit contributions | |
cair | -0.323 |
AZ | -0.318 |
Yelp | -0.317 |
Auto | -0.298 |
Olympia | -0.291 |
Token | & |
Token ID | 1222 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Luke | +4.013 |
ْ | +3.829 |
src | +3.829 |
sky | +3.789 |
Color | +3.786 |
Neg logit contributions | |
cair | -4.396 |
Yelp | -4.315 |
AZ | -4.250 |
Olympia | -4.000 |
Auto | -3.916 |
Token | ' |
Token ID | 6 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Luke | +1.259 |
ْ | +1.205 |
src | +1.203 |
sky | +1.190 |
Color | +1.183 |
Neg logit contributions | |
cair | -1.179 |
Yelp | -1.161 |
AZ | -1.157 |
Auto | -1.076 |
Olympia | -1.069 |
Token | a |
Token ID | 64 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Luke | +1.903 |
ْ | +1.830 |
src | +1.812 |
sky | +1.786 |
Color | +1.775 |
Neg logit contributions | |
cair | -2.433 |
AZ | -2.397 |
Yelp | -2.396 |
Olympia | -2.243 |
Auto | -2.240 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Luke | +1.022 |
ْ | +0.978 |
src | +0.966 |
sky | +0.958 |
Color | +0.955 |
Neg logit contributions | |
cair | -1.170 |
AZ | -1.150 |
Yelp | -1.150 |
Auto | -1.078 |
Olympia | -1.068 |
Token | guarantees |
Token ID | 19026 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Luke | +1.073 |
ْ | +1.030 |
src | +1.014 |
sky | +1.008 |
Color | +1.007 |
Neg logit contributions | |
cair | -1.181 |
AZ | -1.159 |
Yelp | -1.159 |
Auto | -1.082 |
Olympia | -1.074 |
Token | { |
Token ID | 1391 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Luke | +1.850 |
src | +1.744 |
ْ | +1.740 |
cylinders | +1.715 |
ample | +1.713 |
Neg logit contributions | |
cair | -2.803 |
Yelp | -2.744 |
AZ | -2.728 |
Olympia | -2.581 |
Auto | -2.548 |
Token | pub |
Token ID | 2240 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
AZ | +1.000 |
cair | +0.989 |
Yelp | +0.980 |
Auto | +0.957 |
Olympia | +0.906 |
Neg logit contributions | |
Luke | -0.828 |
ْ | -0.803 |
sky | -0.786 |
女 | -0.780 |
cylinders | -0.773 |
Token | fn |
Token ID | 24714 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Luke | +1.121 |
ْ | +1.065 |
src | +1.037 |
sky | +1.035 |
cylinders | +1.029 |
Neg logit contributions | |
cair | -1.979 |
AZ | -1.963 |
Yelp | -1.956 |
Auto | -1.871 |
Olympia | -1.833 |
Token | load |
Token ID | 3440 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Luke | +1.677 |
ْ | +1.610 |
src | +1.595 |
sky | +1.583 |
cylinders | +1.580 |
Neg logit contributions | |
cair | -1.695 |
AZ | -1.663 |
Yelp | -1.659 |
Auto | -1.557 |
Olympia | -1.532 |
Token | < |
Token ID | 1279 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Luke | +2.076 |
ْ | +1.991 |
src | +1.960 |
sky | +1.951 |
cylinders | +1.940 |
Neg logit contributions | |
cair | -2.411 |
AZ | -2.379 |
Yelp | -2.371 |
Auto | -2.239 |
Olympia | -2.196 |
Token | ' |
Token ID | 705 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
Luke | +2.963 |
src | +2.881 |
Color | +2.833 |
ْ | +2.803 |
sky | +2.783 |
Neg logit contributions | |
cair | -2.851 |
Yelp | -2.709 |
AZ | -2.663 |
Olympia | -2.525 |
Auto | -2.467 |
Token | a |
Token ID | 64 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Luke | +3.378 |
src | +3.303 |
ْ | +3.240 |
sky | +3.190 |
Color | +3.181 |
Neg logit contributions | |
cair | -4.969 |
Yelp | -4.814 |
AZ | -4.785 |
Olympia | -4.582 |
Auto | -4.499 |
Token | > |
Token ID | 1875 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Luke | +1.803 |
src | +1.732 |
ْ | +1.728 |
Color | +1.708 |
cylinders | +1.702 |
Neg logit contributions | |
cair | -2.033 |
AZ | -1.969 |
Yelp | -1.963 |
Auto | -1.836 |
Olympia | -1.834 |
Token | ( |
Token ID | 357 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Luke | +2.040 |
ْ | +1.953 |
src | +1.933 |
sky | +1.916 |
cylinders | +1.909 |
Neg logit contributions | |
cair | -2.339 |
AZ | -2.297 |
Yelp | -2.289 |
Auto | -2.152 |
Olympia | -2.126 |
Token | & |
Token ID | 1222 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Luke | +0.882 |
ْ | +0.851 |
sky | +0.834 |
src | +0.833 |
cylinders | +0.829 |
Neg logit contributions | |
cair | -0.860 |
AZ | -0.850 |
Yelp | -0.846 |
Auto | -0.798 |
Olympia | -0.777 |
Token | self |
Token ID | 2116 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Luke | +2.960 |
src | +2.901 |
ْ | +2.855 |
sky | +2.852 |
Color | +2.840 |
Neg logit contributions | |
cair | -1.615 |
Yelp | -1.534 |
AZ | -1.527 |
Olympia | -1.396 |
Auto | -1.357 |
Token | sleep |
Token ID | 3993 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Luke | +0.274 |
ْ | +0.265 |
src | +0.259 |
sky | +0.257 |
cylinders | +0.255 |
Neg logit contributions | |
cair | -0.350 |
AZ | -0.349 |
Yelp | -0.348 |
Auto | -0.329 |
Olympia | -0.324 |
Token | researcher |
Token ID | 13453 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
AZ | +1.267 |
cair | +1.262 |
Yelp | +1.256 |
Auto | +1.186 |
Olympia | +1.164 |
Neg logit contributions | |
Luke | -1.168 |
ْ | -1.126 |
src | -1.110 |
sky | -1.096 |
cylinders | -1.092 |
Token | at |
Token ID | 379 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Luke | +1.561 |
ْ | +1.491 |
sky | +1.467 |
src | +1.466 |
cylinders | +1.458 |
Neg logit contributions | |
cair | -1.885 |
AZ | -1.847 |
Yelp | -1.843 |
Auto | -1.739 |
Olympia | -1.705 |
Token | Children |
Token ID | 8990 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Luke | +0.445 |
ْ | +0.429 |
src | +0.422 |
sky | +0.420 |
cylinders | +0.418 |
Neg logit contributions | |
cair | -0.456 |
AZ | -0.451 |
Yelp | -0.449 |
Auto | -0.423 |
Olympia | -0.415 |
Token | 's |
Token ID | 338 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Luke | +0.551 |
ْ | +0.534 |
src | +0.525 |
cylinders | +0.523 |
sky | +0.522 |
Neg logit contributions | |
cair | -0.481 |
AZ | -0.475 |
Yelp | -0.471 |
Auto | -0.444 |
Olympia | -0.431 |
Token | National |
Token ID | 2351 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
cair | +0.708 |
AZ | +0.705 |
Yelp | +0.696 |
Auto | +0.646 |
Olympia | +0.619 |
Neg logit contributions | |
Luke | -1.358 |
ْ | -1.327 |
src | -1.307 |
cylinders | -1.306 |
sky | -1.301 |
Token | Medical |
Token ID | 8366 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Luke | +4.587 |
sky | +4.444 |
Pr | +4.387 |
Color | +4.305 |
src | +4.285 |
Neg logit contributions | |
cair | -3.850 |
Yelp | -3.628 |
AZ | -3.559 |
Auto | -3.270 |
Olympia | -3.255 |
Token | Center |
Token ID | 3337 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Luke | +0.815 |
sky | +0.777 |
ْ | +0.776 |
src | +0.774 |
Color | +0.767 |
Neg logit contributions | |
cair | -0.756 |
Yelp | -0.723 |
AZ | -0.723 |
Auto | -0.673 |
Olympia | -0.665 |
Token | in |
Token ID | 287 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
cair | +0.166 |
AZ | +0.163 |
Yelp | +0.163 |
Auto | +0.153 |
Olympia | +0.150 |
Neg logit contributions | |
Luke | -0.179 |
ْ | -0.173 |
src | -0.170 |
cylinders | -0.169 |
sky | -0.169 |
Token | Washington |
Token ID | 2669 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Luke | +0.416 |
ْ | +0.403 |
src | +0.395 |
sky | +0.394 |
cylinders | +0.393 |
Neg logit contributions | |
cair | -0.380 |
AZ | -0.379 |
Yelp | -0.375 |
Auto | -0.354 |
Olympia | -0.349 |
Token | , |
Token ID | 11 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Luke | +0.099 |
ْ | +0.096 |
src | +0.094 |
cylinders | +0.094 |
sky | +0.093 |
Neg logit contributions | |
cair | -0.093 |
AZ | -0.092 |
Yelp | -0.091 |
Auto | -0.086 |
Olympia | -0.085 |
Token | lot |
Token ID | 1256 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Luke | +0.259 |
ْ | +0.249 |
src | +0.245 |
sky | +0.244 |
cylinders | +0.243 |
Neg logit contributions | |
cair | -0.278 |
AZ | -0.275 |
Yelp | -0.274 |
Auto | -0.258 |
Olympia | -0.253 |
Token | of |
Token ID | 286 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Luke | +0.413 |
ْ | +0.399 |
src | +0.394 |
ample | +0.391 |
cylinders | +0.390 |
Neg logit contributions | |
cair | -0.412 |
AZ | -0.409 |
Yelp | -0.407 |
Auto | -0.384 |
Olympia | -0.373 |
Token | people |
Token ID | 661 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
AZ | +0.293 |
cair | +0.293 |
Yelp | +0.291 |
Auto | +0.275 |
Olympia | +0.268 |
Neg logit contributions | |
Luke | -0.274 |
ْ | -0.267 |
src | -0.260 |
女 | -0.258 |
sky | -0.258 |
Token | have |
Token ID | 423 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Luke | +1.879 |
ْ | +1.792 |
sky | +1.780 |
src | +1.778 |
cylinders | +1.762 |
Neg logit contributions | |
cair | -2.014 |
AZ | -1.966 |
Yelp | -1.962 |
Auto | -1.844 |
Olympia | -1.816 |
Token | told |
Token ID | 1297 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Luke | +0.161 |
ْ | +0.156 |
src | +0.153 |
sky | +0.152 |
Color | +0.151 |
Neg logit contributions | |
cair | -0.174 |
AZ | -0.173 |
Yelp | -0.172 |
Auto | -0.163 |
Olympia | -0.159 |
Token | me |
Token ID | 502 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
Luke | +0.312 |
ْ | +0.302 |
src | +0.297 |
sky | +0.296 |
cylinders | +0.295 |
Neg logit contributions | |
cair | -0.295 |
AZ | -0.292 |
Yelp | -0.291 |
Auto | -0.273 |
Olympia | -0.267 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Luke | +3.873 |
sky | +3.671 |
cylinders | +3.632 |
ْ | +3.632 |
src | +3.591 |
Neg logit contributions | |
cair | -4.515 |
AZ | -4.301 |
Yelp | -4.249 |
Auto | -4.022 |
Olympia | -3.974 |
Token | cash |
Token ID | 5003 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Luke | +1.022 |
ْ | +0.977 |
src | +0.970 |
sky | +0.969 |
cylinders | +0.963 |
Neg logit contributions | |
cair | -1.038 |
AZ | -1.017 |
Yelp | -1.012 |
Auto | -0.953 |
Olympia | -0.937 |
Token | out |
Token ID | 503 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Luke | +0.643 |
ْ | +0.615 |
sky | +0.604 |
src | +0.604 |
cylinders | +0.601 |
Neg logit contributions | |
cair | -0.788 |
AZ | -0.777 |
Yelp | -0.773 |
Auto | -0.732 |
Olympia | -0.720 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Luke | +1.054 |
ْ | +1.012 |
src | +1.000 |
sky | +0.996 |
cylinders | +0.993 |
Neg logit contributions | |
cair | -1.052 |
AZ | -1.025 |
Yelp | -1.021 |
Auto | -0.959 |
Olympia | -0.944 |
Token | But |
Token ID | 887 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Luke | +0.840 |
ْ | +0.805 |
src | +0.796 |
sky | +0.794 |
Color | +0.786 |
Neg logit contributions | |
cair | -0.820 |
AZ | -0.800 |
Yelp | -0.798 |
Auto | -0.748 |
Olympia | -0.736 |
Token | US |
Token ID | 1294 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Luke | +1.595 |
ْ | +1.533 |
src | +1.518 |
sky | +1.512 |
Color | +1.508 |
Neg logit contributions | |
cair | -1.280 |
Yelp | -1.225 |
AZ | -1.223 |
Auto | -1.130 |
Olympia | -1.107 |
Token | Department |
Token ID | 2732 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Luke | +0.112 |
ْ | +0.109 |
sky | +0.107 |
src | +0.107 |
cylinders | +0.106 |
Neg logit contributions | |
cair | -0.089 |
AZ | -0.088 |
Yelp | -0.088 |
Auto | -0.083 |
Olympia | -0.080 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Luke | +1.368 |
src | +1.300 |
sky | +1.299 |
Color | +1.285 |
ْ | +1.285 |
Neg logit contributions | |
cair | -1.635 |
AZ | -1.599 |
Yelp | -1.591 |
Auto | -1.486 |
Olympia | -1.483 |
Token | Transportation |
Token ID | 15198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Luke | +1.443 |
ْ | +1.393 |
src | +1.375 |
sky | +1.371 |
Color | +1.362 |
Neg logit contributions | |
cair | -1.297 |
AZ | -1.267 |
Yelp | -1.266 |
Auto | -1.170 |
Olympia | -1.154 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Luke | +0.699 |
ْ | +0.672 |
src | +0.661 |
sky | +0.658 |
cylinders | +0.655 |
Neg logit contributions | |
cair | -0.746 |
AZ | -0.737 |
Yelp | -0.734 |
Auto | -0.694 |
Olympia | -0.679 |
Token | National |
Token ID | 2351 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
Luke | +0.798 |
ْ | +0.767 |
src | +0.757 |
sky | +0.754 |
cylinders | +0.749 |
Neg logit contributions | |
cair | -0.826 |
AZ | -0.811 |
Yelp | -0.809 |
Auto | -0.760 |
Olympia | -0.745 |
Token | Highway |
Token ID | 14914 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Luke | +3.713 |
sky | +3.664 |
src | +3.551 |
Color | +3.541 |
Pr | +3.515 |
Neg logit contributions | |
cair | -4.372 |
Yelp | -4.155 |
AZ | -4.076 |
Olympia | -3.826 |
eware | -3.790 |
Token | Traffic |
Token ID | 23624 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
cair | +1.458 |
AZ | +1.447 |
Yelp | +1.442 |
Auto | +1.371 |
Olympia | +1.337 |
Neg logit contributions | |
Luke | -1.207 |
ْ | -1.160 |
src | -1.136 |
sky | -1.130 |
cylinders | -1.129 |
Token | Safety |
Token ID | 11233 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Luke | +0.338 |
ْ | +0.326 |
src | +0.322 |
sky | +0.322 |
Color | +0.320 |
Neg logit contributions | |
cair | -0.259 |
AZ | -0.253 |
Yelp | -0.252 |
Auto | -0.233 |
Olympia | -0.229 |
Token | Administration |
Token ID | 8694 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
Luke | +0.295 |
ْ | +0.285 |
src | +0.283 |
sky | +0.282 |
cylinders | +0.281 |
Neg logit contributions | |
cair | -0.178 |
AZ | -0.174 |
Yelp | -0.173 |
Auto | -0.158 |
Olympia | -0.154 |
Token | ; |
Token ID | 26 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Luke | +0.580 |
ْ | +0.557 |
src | +0.546 |
sky | +0.543 |
cylinders | +0.543 |
Neg logit contributions | |
cair | -0.673 |
AZ | -0.668 |
Yelp | -0.664 |
Auto | -0.631 |
Olympia | -0.616 |
Token | d |
Token ID | 67 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Luke | +0.149 |
ْ | +0.141 |
src | +0.137 |
sky | +0.137 |
cylinders | +0.137 |
Neg logit contributions | |
cair | -0.262 |
AZ | -0.259 |
Yelp | -0.259 |
Auto | -0.247 |
Olympia | -0.242 |
Token | rel |
Token ID | 823 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
cair | +0.312 |
AZ | +0.308 |
Yelp | +0.307 |
Auto | +0.290 |
Olympia | +0.284 |
Neg logit contributions | |
Luke | -0.269 |
ْ | -0.258 |
src | -0.254 |
sky | -0.253 |
cylinders | -0.252 |
Token | apsed |
Token ID | 28361 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
cair | +0.259 |
AZ | +0.257 |
Yelp | +0.255 |
Auto | +0.244 |
Olympia | +0.239 |
Neg logit contributions | |
Luke | -0.151 |
ْ | -0.145 |
cylinders | -0.141 |
src | -0.140 |
sky | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
cair | +0.123 |
AZ | +0.121 |
Yelp | +0.121 |
Auto | +0.114 |
Olympia | +0.111 |
Neg logit contributions | |
Luke | -0.132 |
ْ | -0.127 |
src | -0.125 |
sky | -0.125 |
cylinders | -0.124 |
Token | telling |
Token ID | 5149 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
cair | +0.108 |
AZ | +0.106 |
Yelp | +0.106 |
Auto | +0.100 |
Olympia | +0.098 |
Neg logit contributions | |
Luke | -0.103 |
ْ | -0.099 |
src | -0.098 |
sky | -0.098 |
cylinders | -0.097 |
Token | me |
Token ID | 502 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
cair | +0.002 |
AZ | +0.002 |
Yelp | +0.002 |
Auto | +0.002 |
Olympia | +0.001 |
Neg logit contributions | |
Luke | -0.002 |
ْ | -0.002 |
src | -0.002 |
sky | -0.001 |
cylinders | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Luke | +3.835 |
ْ | +3.718 |
cylinders | +3.629 |
src | +3.628 |
sky | +3.623 |
Neg logit contributions | |
cair | -4.289 |
AZ | -4.091 |
Yelp | -4.045 |
Auto | -3.809 |
Olympia | -3.766 |
Token | a |
Token ID | 257 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
AZ | +0.379 |
cair | +0.378 |
Yelp | +0.377 |
Auto | +0.356 |
Olympia | +0.347 |
Neg logit contributions | |
Luke | -0.360 |
ْ | -0.346 |
src | -0.342 |
sky | -0.341 |
Color | -0.338 |
Token | resigned |
Token ID | 16542 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Luke | +0.582 |
ْ | +0.558 |
src | +0.553 |
sky | +0.550 |
cylinders | +0.547 |
Neg logit contributions | |
cair | -0.628 |
AZ | -0.624 |
Yelp | -0.623 |
Auto | -0.586 |
Olympia | -0.573 |
Token | shake |
Token ID | 13279 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Luke | +1.252 |
ْ | +1.202 |
src | +1.178 |
sky | +1.176 |
cylinders | +1.171 |
Neg logit contributions | |
cair | -1.410 |
AZ | -1.385 |
Yelp | -1.378 |
Auto | -1.303 |
Olympia | -1.280 |
Token | of |
Token ID | 286 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Luke | +1.239 |
ْ | +1.190 |
src | +1.173 |
sky | +1.170 |
cylinders | +1.164 |
Neg logit contributions | |
cair | -1.285 |
AZ | -1.268 |
Yelp | -1.264 |
Auto | -1.192 |
Olympia | -1.165 |
Token | / |
Token ID | 14 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
cair | +1.601 |
AZ | +1.555 |
Yelp | +1.517 |
Auto | +1.468 |
Olympia | +1.421 |
Neg logit contributions | |
Luke | -1.723 |
ْ | -1.664 |
cylinders | -1.657 |
Cla | -1.623 |
Color | -1.621 |
Token | plan |
Token ID | 11578 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
cair | +0.082 |
AZ | +0.081 |
Yelp | +0.080 |
Auto | +0.076 |
Olympia | +0.074 |
Neg logit contributions | |
Luke | -0.084 |
ْ | -0.081 |
cylinders | -0.079 |
src | -0.079 |
sky | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
cair | +0.495 |
AZ | +0.488 |
Yelp | +0.482 |
Auto | +0.457 |
Olympia | +0.447 |
Neg logit contributions | |
Luke | -0.513 |
ْ | -0.493 |
cylinders | -0.486 |
src | -0.484 |
sky | -0.484 |
Token | pdf |
Token ID | 12315 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Luke | +0.624 |
ْ | +0.593 |
src | +0.583 |
sky | +0.580 |
cylinders | +0.574 |
Neg logit contributions | |
cair | -1.024 |
AZ | -1.012 |
Yelp | -1.010 |
Auto | -0.961 |
Olympia | -0.945 |
Token | . |
Token ID | 13 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Luke | +0.836 |
ْ | +0.805 |
src | +0.795 |
sky | +0.793 |
cylinders | +0.787 |
Neg logit contributions | |
cair | -0.740 |
AZ | -0.726 |
Yelp | -0.724 |
Auto | -0.677 |
Olympia | -0.662 |
Token | National |
Token ID | 2351 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
Luke | +0.469 |
ْ | +0.452 |
src | +0.446 |
sky | +0.444 |
cylinders | +0.442 |
Neg logit contributions | |
cair | -0.428 |
AZ | -0.421 |
Yelp | -0.420 |
Auto | -0.393 |
Olympia | -0.385 |
Token | Highway |
Token ID | 14914 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Luke | +4.014 |
sky | +3.904 |
Color | +3.816 |
src | +3.814 |
Pr | +3.808 |
Neg logit contributions | |
cair | -4.039 |
Yelp | -3.880 |
AZ | -3.797 |
Olympia | -3.551 |
Auto | -3.536 |
Token | Traffic |
Token ID | 23624 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
cair | +1.067 |
AZ | +1.043 |
Yelp | +1.041 |
Auto | +0.978 |
Olympia | +0.970 |
Neg logit contributions | |
Luke | -0.795 |
ْ | -0.757 |
src | -0.747 |
sky | -0.745 |
cylinders | -0.741 |
Token | Safety |
Token ID | 11233 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
Luke | +0.031 |
ْ | +0.030 |
src | +0.029 |
sky | +0.029 |
cylinders | +0.029 |
Neg logit contributions | |
cair | -0.022 |
AZ | -0.022 |
Yelp | -0.022 |
Auto | -0.020 |
Olympia | -0.020 |
Token | Administration |
Token ID | 8694 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Luke | +0.743 |
ْ | +0.718 |
sky | +0.709 |
src | +0.709 |
cylinders | +0.707 |
Neg logit contributions | |
cair | -0.470 |
AZ | -0.455 |
Yelp | -0.453 |
Auto | -0.411 |
Olympia | -0.406 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Luke | +1.646 |
ْ | +1.587 |
src | +1.567 |
sky | +1.567 |
cylinders | +1.556 |
Neg logit contributions | |
cair | -1.553 |
Yelp | -1.514 |
AZ | -1.512 |
Auto | -1.410 |
Olympia | -1.387 |
Token | scaff |
Token ID | 41498 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Luke | +0.085 |
ْ | +0.082 |
src | +0.080 |
sky | +0.080 |
女 | +0.079 |
Neg logit contributions | |
AZ | -0.091 |
cair | -0.091 |
Yelp | -0.090 |
Auto | -0.085 |
Olympia | -0.083 |
Token | old |
Token ID | 727 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
cair | +0.133 |
AZ | +0.131 |
Yelp | +0.130 |
Auto | +0.123 |
Olympia | +0.121 |
Neg logit contributions | |
Luke | -0.112 |
ْ | -0.108 |
src | -0.106 |
sky | -0.105 |
cylinders | -0.105 |
Token | into |
Token ID | 656 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
cair | +0.230 |
AZ | +0.228 |
Yelp | +0.226 |
Auto | +0.213 |
Olympia | +0.207 |
Neg logit contributions | |
Luke | -0.274 |
ْ | -0.264 |
src | -0.260 |
sky | -0.259 |
ample | -0.258 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
cair | +0.091 |
AZ | +0.091 |
Yelp | +0.091 |
Auto | +0.086 |
Olympia | +0.084 |
Neg logit contributions | |
Luke | -0.086 |
ْ | -0.082 |
src | -0.081 |
sky | -0.081 |
女 | -0.080 |
Token | per |
Token ID | 583 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
AZ | +0.729 |
Yelp | +0.719 |
cair | +0.718 |
Auto | +0.682 |
Olympia | +0.665 |
Neg logit contributions | |
Luke | -0.744 |
ْ | -0.715 |
src | -0.704 |
女 | -0.702 |
ample | -0.698 |
Token | ov |
Token ID | 709 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
Luke | +1.003 |
ْ | +0.971 |
src | +0.942 |
cylinders | +0.939 |
Color | +0.936 |
Neg logit contributions | |
cair | -1.203 |
AZ | -1.187 |
Yelp | -1.180 |
Auto | -1.121 |
Olympia | -1.099 |
Token | sk |
Token ID | 8135 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Luke | +2.685 |
sky | +2.683 |
src | +2.530 |
ْ | +2.428 |
ample | +2.400 |
Neg logit contributions | |
AZ | -5.327 |
cair | -5.315 |
Yelp | -5.309 |
Auto | -5.043 |
Olympia | -4.964 |
Token | ite |
Token ID | 578 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Luke | +1.581 |
ْ | +1.479 |
sky | +1.472 |
src | +1.463 |
ample | +1.435 |
Neg logit contributions | |
cair | -3.530 |
AZ | -3.495 |
Yelp | -3.485 |
Auto | -3.327 |
Olympia | -3.273 |
Token | - |
Token ID | 12 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Luke | +0.212 |
ْ | +0.204 |
src | +0.201 |
sky | +0.199 |
ample | +0.198 |
Neg logit contributions | |
cair | -0.209 |
AZ | -0.207 |
Yelp | -0.206 |
Auto | -0.194 |
Olympia | -0.190 |
Token | f |
Token ID | 69 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Luke | +0.142 |
ْ | +0.137 |
cylinders | +0.133 |
src | +0.132 |
女 | +0.132 |
Neg logit contributions | |
cair | -0.186 |
AZ | -0.183 |
Yelp | -0.181 |
Auto | -0.173 |
Olympia | -0.169 |
Token | lled |
Token ID | 3353 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
cair | +1.106 |
AZ | +1.084 |
Yelp | +1.080 |
Auto | +1.019 |
Olympia | +0.995 |
Neg logit contributions | |
Luke | -1.134 |
ْ | -1.097 |
src | -1.076 |
cylinders | -1.071 |
sky | -1.068 |
Token | separation |
Token ID | 14139 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Luke | +0.373 |
ْ | +0.358 |
src | +0.353 |
sky | +0.351 |
cylinders | +0.348 |
Neg logit contributions | |
cair | -0.435 |
AZ | -0.430 |
Yelp | -0.428 |
Auto | -0.405 |
Olympia | -0.397 |
Token | than |
Token ID | 621 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
cair | +0.225 |
AZ | +0.224 |
Yelp | +0.223 |
Auto | +0.210 |
Olympia | +0.204 |
Neg logit contributions | |
Luke | -0.253 |
ْ | -0.245 |
src | -0.241 |
sky | -0.240 |
Color | -0.240 |
Token | when |
Token ID | 618 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
Luke | +1.339 |
ْ | +1.289 |
src | +1.269 |
sky | +1.267 |
cylinders | +1.264 |
Neg logit contributions | |
cair | -1.281 |
AZ | -1.256 |
Yelp | -1.253 |
Auto | -1.176 |
Olympia | -1.149 |
Token | before |
Token ID | 878 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Luke | +0.549 |
ْ | +0.530 |
src | +0.523 |
sky | +0.521 |
cylinders | +0.518 |
Neg logit contributions | |
cair | -0.476 |
AZ | -0.470 |
Yelp | -0.468 |
Auto | -0.438 |
Olympia | -0.428 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Luke | +0.285 |
ْ | +0.275 |
src | +0.272 |
sky | +0.271 |
cylinders | +0.268 |
Neg logit contributions | |
cair | -0.251 |
AZ | -0.248 |
Yelp | -0.247 |
Auto | -0.232 |
Olympia | -0.226 |
Token | ball |
Token ID | 2613 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
Luke | +1.169 |
ْ | +1.118 |
cylinders | +1.107 |
src | +1.096 |
Color | +1.095 |
Neg logit contributions | |
cair | -1.342 |
Yelp | -1.309 |
AZ | -1.306 |
Auto | -1.231 |
Olympia | -1.210 |
Token | was |
Token ID | 373 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Luke | +2.962 |
ْ | +2.815 |
sky | +2.779 |
cylinders | +2.744 |
src | +2.731 |
Neg logit contributions | |
cair | -5.083 |
Yelp | -4.973 |
AZ | -4.946 |
Auto | -4.700 |
Olympia | -4.688 |
Token | snapped |
Token ID | 20821 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Luke | +0.504 |
ْ | +0.483 |
src | +0.475 |
sky | +0.472 |
cylinders | +0.470 |
Neg logit contributions | |
cair | -0.638 |
AZ | -0.631 |
Yelp | -0.628 |
Auto | -0.596 |
Olympia | -0.584 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
AZ | +0.600 |
cair | +0.597 |
Yelp | +0.590 |
Auto | +0.558 |
Olympia | +0.541 |
Neg logit contributions | |
Luke | -0.749 |
ْ | -0.718 |
src | -0.712 |
sky | -0.708 |
Color | -0.708 |
Token |
|
Token ID | 198 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
cair | +0.510 |
AZ | +0.505 |
Yelp | +0.503 |
Auto | +0.476 |
Olympia | +0.467 |
Neg logit contributions | |
Luke | -0.439 |
ْ | -0.422 |
src | -0.414 |
sky | -0.413 |
cylinders | -0.412 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
Luke | +0.574 |
ْ | +0.548 |
src | +0.539 |
sky | +0.537 |
cylinders | +0.533 |
Neg logit contributions | |
cair | -0.764 |
AZ | -0.753 |
Yelp | -0.751 |
Auto | -0.712 |
Olympia | -0.699 |
Token | cases |
Token ID | 2663 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
cair | +2.415 |
Yelp | +2.402 |
AZ | +2.399 |
Auto | +2.294 |
Olympia | +2.232 |
Neg logit contributions | |
Luke | -2.191 |
ْ | -2.117 |
src | -2.089 |
女 | -2.055 |
Color | -2.048 |
Token | involved |
Token ID | 2950 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Luke | +0.165 |
ْ | +0.159 |
src | +0.156 |
Color | +0.155 |
Cla | +0.154 |
Neg logit contributions | |
Yelp | -0.205 |
cair | -0.205 |
AZ | -0.204 |
Auto | -0.193 |
Olympia | -0.189 |
Token | permits |
Token ID | 13892 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Luke | +0.152 |
ْ | +0.146 |
src | +0.144 |
sky | +0.143 |
Color | +0.142 |
Neg logit contributions | |
cair | -0.166 |
AZ | -0.164 |
Yelp | -0.164 |
Auto | -0.155 |
Olympia | -0.152 |
Token | where |
Token ID | 810 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
cair | +0.525 |
AZ | +0.524 |
Yelp | +0.522 |
Auto | +0.489 |
Olympia | +0.478 |
Neg logit contributions | |
Luke | -0.603 |
ْ | -0.582 |
src | -0.577 |
sky | -0.573 |
Color | -0.569 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Luke | +0.080 |
ْ | +0.077 |
src | +0.076 |
sky | +0.076 |
Color | +0.075 |
Neg logit contributions | |
cair | -0.085 |
AZ | -0.084 |
Yelp | -0.084 |
Auto | -0.079 |
Olympia | -0.078 |
Token | National |
Token ID | 2351 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
Luke | +1.047 |
ْ | +1.007 |
src | +0.991 |
sky | +0.988 |
cylinders | +0.986 |
Neg logit contributions | |
cair | -1.093 |
AZ | -1.076 |
Yelp | -1.073 |
Auto | -1.010 |
Olympia | -0.989 |
Token | Energy |
Token ID | 6682 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Luke | +3.929 |
ْ | +3.817 |
sky | +3.800 |
ample | +3.778 |
Color | +3.735 |
Neg logit contributions | |
cair | -4.014 |
Yelp | -3.859 |
AZ | -3.839 |
Olympia | -3.497 |
eware | -3.470 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Luke | +0.231 |
ْ | +0.222 |
src | +0.218 |
sky | +0.217 |
cylinders | +0.216 |
Neg logit contributions | |
cair | -0.269 |
AZ | -0.265 |
Yelp | -0.264 |
Auto | -0.250 |
Olympia | -0.245 |
Token | ( |
Token ID | 357 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Luke | +1.655 |
ْ | +1.587 |
src | +1.556 |
sky | +1.554 |
cylinders | +1.546 |
Neg logit contributions | |
cair | -2.092 |
AZ | -2.066 |
Yelp | -2.057 |
Auto | -1.948 |
Olympia | -1.912 |
Token | NE |
Token ID | 12161 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Luke | +1.245 |
ْ | +1.199 |
src | +1.186 |
sky | +1.183 |
Color | +1.177 |
Neg logit contributions | |
cair | -0.744 |
AZ | -0.732 |
Yelp | -0.726 |
Auto | -0.671 |
Olympia | -0.648 |
Token | B |
Token ID | 33 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Luke | +0.511 |
ْ | +0.483 |
src | +0.473 |
sky | +0.470 |
cylinders | +0.467 |
Neg logit contributions | |
cair | -0.945 |
AZ | -0.935 |
Yelp | -0.932 |
Auto | -0.889 |
Olympia | -0.876 |
Token | ь |
Token ID | 45367 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
Luke | +0.982 |
ْ | +0.943 |
src | +0.927 |
sky | +0.925 |
cylinders | +0.918 |
Neg logit contributions | |
cair | -1.149 |
AZ | -1.132 |
Yelp | -1.129 |
Auto | -1.066 |
Olympia | -1.046 |
Token | � |
Token ID | 12466 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
cair | +0.062 |
AZ | +0.062 |
Yelp | +0.061 |
Auto | +0.058 |
Olympia | +0.057 |
Neg logit contributions | |
Luke | -0.047 |
ْ | -0.045 |
src | -0.044 |
sky | -0.043 |
cylinders | -0.043 |
Token | � |
Token ID | 116 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
Luke | +0.826 |
ْ | +0.801 |
src | +0.792 |
sky | +0.790 |
cylinders | +0.785 |
Neg logit contributions | |
cair | -0.543 |
AZ | -0.533 |
Yelp | -0.531 |
Auto | -0.490 |
Olympia | -0.477 |
Token | � |
Token ID | 12466 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Luke | +0.511 |
ْ | +0.488 |
src | +0.479 |
sky | +0.477 |
cylinders | +0.474 |
Neg logit contributions | |
cair | -0.733 |
AZ | -0.725 |
Yelp | -0.722 |
Auto | -0.687 |
Olympia | -0.674 |
Token | � |
Token ID | 109 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Luke | +2.047 |
ْ | +1.995 |
src | +1.968 |
sky | +1.960 |
Color | +1.943 |
Neg logit contributions | |
cair | -1.501 |
AZ | -1.466 |
Yelp | -1.462 |
Auto | -1.356 |
Olympia | -1.321 |
Token | о� |
Token ID | 25443 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
Luke | +0.843 |
ْ | +0.804 |
src | +0.787 |
sky | +0.785 |
cylinders | +0.775 |
Neg logit contributions | |
cair | -1.391 |
AZ | -1.373 |
Yelp | -1.370 |
Auto | -1.304 |
Olympia | -1.282 |
Token | � |
Token ID | 119 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Luke | +4.201 |
ْ | +4.139 |
src | +4.036 |
sky | +4.023 |
女 | +3.980 |
Neg logit contributions | |
cair | -3.789 |
AZ | -3.632 |
Yelp | -3.625 |
Auto | -3.350 |
Olympia | -3.301 |
Token | е |
Token ID | 16843 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Luke | +0.721 |
ْ | +0.692 |
src | +0.680 |
sky | +0.678 |
cylinders | +0.674 |
Neg logit contributions | |
cair | -0.831 |
AZ | -0.820 |
Yelp | -0.817 |
Auto | -0.772 |
Olympia | -0.756 |
Token | е |
Token ID | 16843 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Luke | +0.310 |
ْ | +0.295 |
src | +0.289 |
sky | +0.288 |
cylinders | +0.287 |
Neg logit contributions | |
cair | -0.450 |
AZ | -0.445 |
Yelp | -0.443 |
Auto | -0.422 |
Olympia | -0.414 |
Token | ), |
Token ID | 828 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Luke | +0.314 |
ْ | +0.300 |
src | +0.294 |
sky | +0.293 |
cylinders | +0.292 |
Neg logit contributions | |
cair | -0.444 |
AZ | -0.439 |
Yelp | -0.438 |
Auto | -0.416 |
Olympia | -0.408 |
Token | � |
Token ID | 12466 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
AZ | +1.728 |
Yelp | +1.708 |
cair | +1.707 |
Auto | +1.631 |
Olympia | +1.591 |
Neg logit contributions | |
Luke | -1.386 |
ْ | -1.322 |
src | -1.306 |
Color | -1.292 |
ample | -1.291 |
Token | guidelines |
Token ID | 9949 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Luke | +0.968 |
ْ | +0.925 |
src | +0.911 |
sky | +0.909 |
cylinders | +0.906 |
Neg logit contributions | |
cair | -1.245 |
AZ | -1.225 |
Yelp | -1.218 |
Auto | -1.156 |
Olympia | -1.136 |
Token | such |
Token ID | 884 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
Luke | +1.385 |
ْ | +1.333 |
src | +1.316 |
sky | +1.314 |
cylinders | +1.306 |
Neg logit contributions | |
cair | -1.314 |
AZ | -1.292 |
Yelp | -1.285 |
Auto | -1.209 |
Olympia | -1.182 |
Token | as |
Token ID | 355 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
cair | +0.068 |
Yelp | +0.068 |
AZ | +0.068 |
Auto | +0.064 |
Olympia | +0.063 |
Neg logit contributions | |
Luke | -0.052 |
ْ | -0.051 |
src | -0.049 |
sky | -0.049 |
cylinders | -0.049 |
Token | no |
Token ID | 645 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
cair | +0.422 |
Yelp | +0.420 |
AZ | +0.419 |
Auto | +0.395 |
Olympia | +0.384 |
Neg logit contributions | |
Luke | -0.413 |
ْ | -0.398 |
src | -0.389 |
sky | -0.389 |
cylinders | -0.385 |
Token | child |
Token ID | 1200 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Luke | +0.129 |
ْ | +0.124 |
src | +0.122 |
sky | +0.122 |
cylinders | +0.121 |
Neg logit contributions | |
cair | -0.144 |
AZ | -0.142 |
Yelp | -0.142 |
Auto | -0.134 |
Olympia | -0.131 |
Token | pornography |
Token ID | 18384 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
Luke | +1.431 |
ْ | +1.346 |
src | +1.327 |
sky | +1.318 |
Color | +1.307 |
Neg logit contributions | |
cair | -2.595 |
AZ | -2.570 |
Yelp | -2.560 |
Auto | -2.440 |
Olympia | -2.411 |
Token | or |
Token ID | 393 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Luke | +3.473 |
ْ | +3.299 |
sky | +3.296 |
cylinders | +3.286 |
src | +3.272 |
Neg logit contributions | |
cair | -4.418 |
AZ | -4.288 |
Yelp | -4.269 |
Auto | -4.009 |
Olympia | -3.968 |
Token | spam |
Token ID | 18084 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Luke | +0.901 |
ْ | +0.862 |
src | +0.852 |
sky | +0.849 |
cylinders | +0.845 |
Neg logit contributions | |
cair | -1.025 |
AZ | -1.007 |
Yelp | -1.002 |
Auto | -0.947 |
Olympia | -0.930 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Luke | +1.990 |
ْ | +1.926 |
src | +1.887 |
sky | +1.869 |
cylinders | +1.864 |
Neg logit contributions | |
cair | -2.705 |
AZ | -2.687 |
Yelp | -2.665 |
Auto | -2.513 |
Olympia | -2.510 |
Token | The |
Token ID | 383 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Luke | +0.118 |
ْ | +0.114 |
cylinders | +0.112 |
src | +0.112 |
sky | +0.112 |
Neg logit contributions | |
cair | -0.124 |
Yelp | -0.124 |
AZ | -0.124 |
Auto | -0.116 |
Olympia | -0.114 |
Token | change |
Token ID | 1487 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Luke | +0.271 |
ْ | +0.262 |
src | +0.258 |
sky | +0.257 |
cylinders | +0.255 |
Neg logit contributions | |
cair | -0.246 |
AZ | -0.243 |
Yelp | -0.243 |
Auto | -0.228 |
Olympia | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Luke | +1.495 |
ْ | +1.438 |
sky | +1.418 |
src | +1.417 |
cylinders | +1.413 |
Neg logit contributions | |
cair | -1.609 |
AZ | -1.580 |
Yelp | -1.574 |
Auto | -1.483 |
Olympia | -1.457 |
Token | of |
Token ID | 286 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Luke | +0.720 |
ْ | +0.693 |
src | +0.682 |
sky | +0.680 |
cylinders | +0.678 |
Neg logit contributions | |
cair | -0.711 |
AZ | -0.699 |
Yelp | -0.697 |
Auto | -0.655 |
Olympia | -0.642 |
Token | course |
Token ID | 1781 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Luke | +0.606 |
ْ | +0.582 |
src | +0.572 |
sky | +0.570 |
cylinders | +0.567 |
Neg logit contributions | |
cair | -0.682 |
AZ | -0.673 |
Yelp | -0.671 |
Auto | -0.634 |
Olympia | -0.621 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Luke | +0.075 |
ْ | +0.072 |
src | +0.071 |
sky | +0.071 |
Color | +0.070 |
Neg logit contributions | |
cair | -0.074 |
AZ | -0.073 |
Yelp | -0.073 |
Auto | -0.069 |
Olympia | -0.067 |
Token | tell |
Token ID | 1560 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Luke | +0.160 |
ْ | +0.154 |
src | +0.152 |
sky | +0.151 |
Color | +0.150 |
Neg logit contributions | |
cair | -0.165 |
AZ | -0.164 |
Yelp | -0.163 |
Auto | -0.154 |
Olympia | -0.150 |
Token | me |
Token ID | 502 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
cair | +0.290 |
AZ | +0.287 |
Yelp | +0.286 |
Auto | +0.269 |
Olympia | +0.262 |
Neg logit contributions | |
Luke | -0.320 |
ْ | -0.308 |
src | -0.304 |
sky | -0.303 |
Color | -0.301 |
Token | they |
Token ID | 484 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Luke | +3.619 |
ْ | +3.520 |
cylinders | +3.467 |
sky | +3.445 |
src | +3.412 |
Neg logit contributions | |
cair | -4.209 |
AZ | -4.055 |
Yelp | -4.044 |
Auto | -3.798 |
Olympia | -3.771 |
Token | have |
Token ID | 423 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Luke | +0.034 |
ْ | +0.033 |
src | +0.032 |
sky | +0.032 |
Color | +0.032 |
Neg logit contributions | |
cair | -0.034 |
AZ | -0.034 |
Yelp | -0.034 |
Auto | -0.032 |
Olympia | -0.031 |
Token | placed |
Token ID | 4624 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Luke | +0.099 |
ْ | +0.095 |
src | +0.094 |
sky | +0.093 |
Color | +0.093 |
Neg logit contributions | |
cair | -0.098 |
AZ | -0.097 |
Yelp | -0.097 |
Auto | -0.091 |
Olympia | -0.089 |
Token | big |
Token ID | 1263 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
cair | +0.909 |
AZ | +0.902 |
Yelp | +0.898 |
Auto | +0.849 |
Olympia | +0.829 |
Neg logit contributions | |
Luke | -0.815 |
ْ | -0.783 |
src | -0.773 |
sky | -0.766 |
Color | -0.761 |
Token | w |
Token ID | 266 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
cair | +1.103 |
AZ | +1.098 |
Yelp | +1.095 |
Auto | +1.039 |
Olympia | +1.019 |
Neg logit contributions | |
Luke | -0.816 |
ْ | -0.783 |
src | -0.765 |
sky | -0.758 |
Color | -0.755 |
Token | Hop |
Token ID | 23483 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
AZ | +1.856 |
cair | +1.846 |
Yelp | +1.828 |
Auto | +1.738 |
Olympia | +1.686 |
Neg logit contributions | |
Luke | -1.909 |
ْ | -1.862 |
src | -1.840 |
cylinders | -1.822 |
女 | -1.816 |
Token | 's |
Token ID | 338 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
AZ | +0.489 |
cair | +0.488 |
Yelp | +0.487 |
Auto | +0.458 |
Olympia | +0.447 |
Neg logit contributions | |
Luke | -0.492 |
ْ | -0.478 |
src | -0.469 |
cylinders | -0.465 |
sky | -0.465 |
Token | beer |
Token ID | 6099 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Luke | +0.341 |
ْ | +0.330 |
src | +0.325 |
sky | +0.323 |
cylinders | +0.321 |
Neg logit contributions | |
cair | -0.332 |
AZ | -0.331 |
Yelp | -0.331 |
Auto | -0.310 |
Olympia | -0.303 |
Token | names |
Token ID | 3891 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Luke | +1.218 |
ْ | +1.168 |
src | +1.151 |
sky | +1.148 |
cylinders | +1.142 |
Neg logit contributions | |
cair | -1.392 |
AZ | -1.370 |
Yelp | -1.364 |
Auto | -1.291 |
Olympia | -1.264 |
Token | give |
Token ID | 1577 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
cair | +0.147 |
AZ | +0.147 |
Yelp | +0.146 |
Auto | +0.138 |
Olympia | +0.134 |
Neg logit contributions | |
Luke | -0.142 |
ْ | -0.137 |
src | -0.134 |
sky | -0.134 |
cylinders | -0.133 |
Token | me |
Token ID | 502 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
AZ | +0.695 |
cair | +0.692 |
Yelp | +0.691 |
Auto | +0.648 |
Olympia | +0.629 |
Neg logit contributions | |
Luke | -0.724 |
ْ | -0.699 |
src | -0.693 |
sky | -0.684 |
女 | -0.681 |
Token | one |
Token ID | 530 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Luke | +3.618 |
cylinders | +3.468 |
ْ | +3.439 |
ample | +3.418 |
sky | +3.416 |
Neg logit contributions | |
cair | -4.212 |
AZ | -4.037 |
Yelp | -4.005 |
Auto | -3.809 |
Olympia | -3.780 |
Token | easy |
Token ID | 2562 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Yelp | +0.840 |
AZ | +0.838 |
cair | +0.831 |
Auto | +0.786 |
Olympia | +0.765 |
Neg logit contributions | |
Luke | -0.828 |
ْ | -0.796 |
src | -0.795 |
sky | -0.778 |
女 | -0.777 |
Token | se |
Token ID | 384 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Luke | +0.800 |
ْ | +0.770 |
src | +0.758 |
sky | +0.755 |
cylinders | +0.752 |
Neg logit contributions | |
cair | -0.819 |
AZ | -0.809 |
Yelp | -0.807 |
Auto | -0.759 |
Olympia | -0.743 |
Token | gue |
Token ID | 18701 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Luke | +1.044 |
ْ | +1.002 |
src | +0.987 |
sky | +0.983 |
cylinders | +0.976 |
Neg logit contributions | |
cair | -1.184 |
AZ | -1.168 |
Yelp | -1.164 |
Auto | -1.099 |
Olympia | -1.078 |
Token | into |
Token ID | 656 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
Luke | +0.142 |
ْ | +0.138 |
src | +0.136 |
sky | +0.135 |
cylinders | +0.134 |
Neg logit contributions | |
cair | -0.125 |
AZ | -0.123 |
Yelp | -0.123 |
Auto | -0.116 |
Olympia | -0.112 |
Token | – |
Token ID | 784 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Luke | +0.381 |
ْ | +0.366 |
src | +0.360 |
sky | +0.359 |
cylinders | +0.357 |
Neg logit contributions | |
cair | -0.424 |
AZ | -0.419 |
Yelp | -0.417 |
Auto | -0.394 |
Olympia | -0.386 |
Token | drib |
Token ID | 35003 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Luke | +0.828 |
ْ | +0.796 |
src | +0.782 |
sky | +0.782 |
cylinders | +0.780 |
Neg logit contributions | |
cair | -0.830 |
AZ | -0.814 |
Yelp | -0.814 |
Auto | -0.764 |
Olympia | -0.749 |
Token | bling |
Token ID | 11108 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Luke | +2.421 |
ْ | +2.343 |
src | +2.317 |
sky | +2.300 |
ample | +2.269 |
Neg logit contributions | |
cair | -3.150 |
Yelp | -3.113 |
AZ | -3.098 |
Auto | -2.908 |
Olympia | -2.907 |
Token | with |
Token ID | 351 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
Luke | +1.005 |
ْ | +0.966 |
src | +0.950 |
sky | +0.948 |
cylinders | +0.944 |
Neg logit contributions | |
cair | -1.080 |
AZ | -1.062 |
Yelp | -1.060 |
Auto | -0.999 |
Olympia | -0.979 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Luke | +0.531 |
ْ | +0.510 |
src | +0.502 |
sky | +0.500 |
cylinders | +0.498 |
Neg logit contributions | |
cair | -0.563 |
AZ | -0.554 |
Yelp | -0.553 |
Auto | -0.521 |
Olympia | -0.511 |
Token | ball |
Token ID | 2613 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
Luke | +0.934 |
ْ | +0.890 |
cylinders | +0.876 |
src | +0.874 |
sky | +0.873 |
Neg logit contributions | |
cair | -1.261 |
Yelp | -1.237 |
AZ | -1.233 |
Auto | -1.169 |
Olympia | -1.148 |
Token | at |
Token ID | 379 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Luke | +3.572 |
ْ | +3.434 |
sky | +3.361 |
cylinders | +3.355 |
src | +3.329 |
Neg logit contributions | |
cair | -4.246 |
Yelp | -4.161 |
AZ | -4.100 |
Auto | -3.868 |
Olympia | -3.824 |
Token | speed |
Token ID | 2866 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Luke | +0.719 |
ْ | +0.691 |
src | +0.681 |
sky | +0.678 |
cylinders | +0.674 |
Neg logit contributions | |
cair | -0.753 |
AZ | -0.745 |
Yelp | -0.740 |
Auto | -0.699 |
Olympia | -0.684 |
Token | , |
Token ID | 11 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
Luke | +1.232 |
ْ | +1.184 |
src | +1.165 |
sky | +1.163 |
cylinders | +1.157 |
Neg logit contributions | |
cair | -1.310 |
AZ | -1.291 |
Yelp | -1.287 |
Auto | -1.212 |
Olympia | -1.189 |
Token | crossing |
Token ID | 12538 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Luke | +0.067 |
ْ | +0.064 |
src | +0.064 |
sky | +0.063 |
Color | +0.063 |
Neg logit contributions | |
cair | -0.061 |
AZ | -0.061 |
Yelp | -0.061 |
Auto | -0.057 |
Olympia | -0.056 |
Token | for |
Token ID | 329 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Luke | +1.857 |
ْ | +1.787 |
cylinders | +1.769 |
sky | +1.756 |
src | +1.747 |
Neg logit contributions | |
cair | -2.047 |
Yelp | -1.998 |
AZ | -1.991 |
Auto | -1.875 |
Olympia | -1.843 |
Token | on |
Token ID | 319 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Luke | +1.552 |
ْ | +1.488 |
src | +1.461 |
sky | +1.458 |
cylinders | +1.457 |
Neg logit contributions | |
cair | -2.071 |
AZ | -2.045 |
Yelp | -2.042 |
Auto | -1.933 |
Olympia | -1.901 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Luke | +0.175 |
ْ | +0.168 |
src | +0.166 |
sky | +0.165 |
Color | +0.164 |
Neg logit contributions | |
cair | -0.153 |
AZ | -0.152 |
Yelp | -0.151 |
Auto | -0.142 |
Olympia | -0.138 |
Token | table |
Token ID | 3084 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Luke | +0.881 |
ْ | +0.844 |
src | +0.831 |
sky | +0.826 |
cylinders | +0.820 |
Neg logit contributions | |
cair | -1.099 |
AZ | -1.087 |
Yelp | -1.084 |
Auto | -1.026 |
Olympia | -1.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Luke | +1.155 |
ْ | +1.112 |
src | +1.095 |
sky | +1.090 |
cylinders | +1.085 |
Neg logit contributions | |
cair | -1.245 |
AZ | -1.231 |
Yelp | -1.230 |
Auto | -1.156 |
Olympia | -1.136 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Luke | +0.992 |
ْ | +0.957 |
src | +0.940 |
cylinders | +0.937 |
sky | +0.937 |
Neg logit contributions | |
cair | -0.937 |
AZ | -0.920 |
Yelp | -0.914 |
Auto | -0.859 |
Olympia | -0.842 |
Token | luckily |
Token ID | 45120 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Luke | +1.052 |
ْ | +1.016 |
src | +1.002 |
cylinders | +0.998 |
sky | +0.998 |
Neg logit contributions | |
cair | -0.901 |
AZ | -0.884 |
Yelp | -0.879 |
Auto | -0.822 |
Olympia | -0.804 |
Token | I |
Token ID | 314 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Yelp | +2.004 |
AZ | +1.992 |
cair | +1.983 |
Auto | +1.861 |
Olympia | +1.804 |
Neg logit contributions | |
Luke | -2.546 |
ْ | -2.450 |
src | -2.431 |
sky | -2.405 |
ample | -2.404 |
Token | found |
Token ID | 1043 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
cair | +1.821 |
AZ | +1.794 |
Yelp | +1.792 |
Auto | +1.692 |
Olympia | +1.640 |
Neg logit contributions | |
Luke | -1.818 |
ْ | -1.734 |
src | -1.716 |
sky | -1.715 |
cylinders | -1.704 |
Token | like |
Token ID | 588 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
cair | +0.910 |
Yelp | +0.904 |
AZ | +0.903 |
Auto | +0.854 |
Olympia | +0.830 |
Neg logit contributions | |
Luke | -0.864 |
ْ | -0.829 |
src | -0.816 |
sky | -0.813 |
女 | -0.807 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
cair | +0.798 |
AZ | +0.792 |
Yelp | +0.791 |
Auto | +0.744 |
Olympia | +0.724 |
Neg logit contributions | |
Luke | -0.791 |
ْ | -0.758 |
src | -0.747 |
sky | -0.745 |
Color | -0.738 |
Token | piece |
Token ID | 3704 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
cair | +1.116 |
Yelp | +1.112 |
AZ | +1.110 |
Auto | +1.043 |
Olympia | +1.013 |
Neg logit contributions | |
Luke | -1.121 |
ْ | -1.078 |
src | -1.063 |
sky | -1.058 |
ample | -1.054 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
cair | +0.609 |
AZ | +0.602 |
Yelp | +0.596 |
Auto | +0.564 |
Olympia | +0.549 |
Neg logit contributions | |
Luke | -0.747 |
ْ | -0.726 |
src | -0.710 |
sky | -0.710 |
cylinders | -0.708 |
Token | This |
Token ID | 770 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
cair | +0.277 |
AZ | +0.276 |
Yelp | +0.274 |
Auto | +0.261 |
Olympia | +0.255 |
Neg logit contributions | |
Luke | -0.249 |
ْ | -0.240 |
cylinders | -0.235 |
sky | -0.235 |
src | -0.235 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
AZ | +0.127 |
cair | +0.127 |
Yelp | +0.126 |
Auto | +0.120 |
Olympia | +0.117 |
Neg logit contributions | |
Luke | -0.109 |
ْ | -0.105 |
sky | -0.103 |
src | -0.103 |
女 | -0.102 |
Token | because |
Token ID | 780 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
AZ | +1.115 |
Yelp | +1.100 |
cair | +1.098 |
Auto | +1.043 |
Olympia | +1.024 |
Neg logit contributions | |
Luke | -1.319 |
ْ | -1.276 |
src | -1.252 |
Cla | -1.246 |
sky | -1.245 |
Token | many |
Token ID | 867 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
cair | +0.017 |
AZ | +0.017 |
Yelp | +0.017 |
Auto | +0.016 |
Olympia | +0.015 |
Neg logit contributions | |
Luke | -0.016 |
ْ | -0.016 |
sky | -0.016 |
src | -0.016 |
Color | -0.015 |
Token | Nort |
Token ID | 15209 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Luke | +0.664 |
ْ | +0.639 |
src | +0.629 |
sky | +0.627 |
cylinders | +0.622 |
Neg logit contributions | |
cair | -0.686 |
AZ | -0.679 |
Yelp | -0.675 |
Auto | -0.637 |
Olympia | -0.624 |
Token | her |
Token ID | 372 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
cair | +1.833 |
AZ | +1.806 |
Yelp | +1.748 |
Auto | +1.656 |
Olympia | +1.557 |
Neg logit contributions | |
Luke | -3.595 |
ْ | -3.537 |
cylinders | -3.503 |
女 | -3.470 |
Color | -3.453 |
Token | ners |
Token ID | 2741 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
cair | +0.295 |
AZ | +0.290 |
Yelp | +0.288 |
Auto | +0.267 |
Olympia | +0.258 |
Neg logit contributions | |
Luke | -0.489 |
ْ | -0.475 |
src | -0.468 |
sky | -0.468 |
cylinders | -0.466 |
Token | feared |
Token ID | 15240 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Luke | +0.123 |
ْ | +0.119 |
src | +0.116 |
sky | +0.115 |
Color | +0.115 |
Neg logit contributions | |
cair | -0.151 |
AZ | -0.149 |
Yelp | -0.149 |
Auto | -0.141 |
Olympia | -0.139 |
Token | that |
Token ID | 326 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
cair | +0.691 |
AZ | +0.688 |
Yelp | +0.681 |
Auto | +0.645 |
Olympia | +0.631 |
Neg logit contributions | |
Luke | -0.703 |
ْ | -0.676 |
src | -0.667 |
sky | -0.665 |
女 | -0.658 |
Token | if |
Token ID | 611 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
cair | +0.123 |
AZ | +0.122 |
Yelp | +0.121 |
Auto | +0.115 |
Olympia | +0.113 |
Neg logit contributions | |
Luke | -0.112 |
ْ | -0.108 |
src | -0.106 |
sky | -0.106 |
Color | -0.105 |
Token | well |
Token ID | 880 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Luke | +0.083 |
ْ | +0.080 |
src | +0.078 |
sky | +0.078 |
cylinders | +0.077 |
Neg logit contributions | |
cair | -0.091 |
AZ | -0.091 |
Yelp | -0.090 |
Auto | -0.085 |
Olympia | -0.083 |
Token | as |
Token ID | 355 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Luke | +0.120 |
ْ | +0.113 |
src | +0.113 |
sky | +0.111 |
女 | +0.111 |
Neg logit contributions | |
AZ | -0.147 |
Yelp | -0.146 |
cair | -0.146 |
Auto | -0.140 |
Olympia | -0.137 |
Token | mitigation |
Token ID | 33585 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Luke | +0.107 |
ْ | +0.103 |
src | +0.102 |
sky | +0.101 |
Color | +0.101 |
Neg logit contributions | |
cair | -0.113 |
AZ | -0.113 |
Yelp | -0.112 |
Auto | -0.106 |
Olympia | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
AZ | +1.418 |
cair | +1.410 |
Yelp | +1.407 |
Auto | +1.335 |
Olympia | +1.297 |
Neg logit contributions | |
Luke | -1.544 |
ْ | -1.488 |
src | -1.475 |
sky | -1.465 |
ample | -1.458 |
Token | the |
Token ID | 262 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
AZ | +0.807 |
cair | +0.802 |
Yelp | +0.799 |
Auto | +0.759 |
Olympia | +0.740 |
Neg logit contributions | |
Luke | -0.756 |
ْ | -0.723 |
src | -0.714 |
sky | -0.711 |
女 | -0.708 |
Token | greenhouse |
Token ID | 16325 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
cair | +0.341 |
AZ | +0.339 |
Yelp | +0.337 |
Auto | +0.318 |
Olympia | +0.311 |
Neg logit contributions | |
Luke | -0.331 |
ْ | -0.318 |
src | -0.313 |
sky | -0.312 |
cylinders | -0.310 |
Token | gas |
Token ID | 3623 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
AZ | +2.273 |
cair | +2.246 |
Yelp | +2.241 |
Auto | +2.157 |
Olympia | +2.077 |
Neg logit contributions | |
Luke | -2.224 |
src | -2.131 |
ample | -2.102 |
ْ | -2.088 |
sky | -2.075 |
Token | emissions |
Token ID | 8971 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
cair | +0.177 |
AZ | +0.175 |
Yelp | +0.174 |
Auto | +0.164 |
Olympia | +0.161 |
Neg logit contributions | |
Luke | -0.158 |
ْ | -0.152 |
src | -0.150 |
sky | -0.149 |
cylinders | -0.148 |
Token | that |
Token ID | 326 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
cair | +0.164 |
AZ | +0.163 |
Yelp | +0.162 |
Auto | +0.154 |
Olympia | +0.150 |
Neg logit contributions | |
Luke | -0.153 |
ْ | -0.147 |
src | -0.145 |
sky | -0.145 |
Color | -0.143 |
Token | would |
Token ID | 561 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
cair | +0.324 |
AZ | +0.322 |
Yelp | +0.321 |
Auto | +0.303 |
Olympia | +0.295 |
Neg logit contributions | |
Luke | -0.337 |
ْ | -0.324 |
src | -0.319 |
sky | -0.319 |
cylinders | -0.317 |
Token | make |
Token ID | 787 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
cair | +1.108 |
Yelp | +1.102 |
AZ | +1.098 |
Auto | +1.038 |
Olympia | +1.005 |
Neg logit contributions | |
Luke | -1.131 |
ْ | -1.084 |
src | -1.064 |
sky | -1.063 |
Color | -1.057 |
Token | become |
Token ID | 1716 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
cair | +0.205 |
AZ | +0.202 |
Yelp | +0.202 |
Auto | +0.190 |
Olympia | +0.186 |
Neg logit contributions | |
Luke | -0.198 |
ْ | -0.191 |
src | -0.187 |
Color | -0.186 |
sky | -0.185 |
Token | entangled |
Token ID | 47446 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Luke | +0.323 |
ْ | +0.311 |
src | +0.307 |
sky | +0.306 |
Color | +0.303 |
Neg logit contributions | |
cair | -0.334 |
AZ | -0.330 |
Yelp | -0.329 |
Auto | -0.310 |
Olympia | -0.304 |
Token | , |
Token ID | 11 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
cair | +0.295 |
AZ | +0.292 |
Yelp | +0.290 |
Auto | +0.273 |
Olympia | +0.267 |
Neg logit contributions | |
Luke | -0.316 |
ْ | -0.303 |
sky | -0.299 |
src | -0.299 |
Color | -0.296 |
Token | with |
Token ID | 351 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
cair | +0.028 |
AZ | +0.027 |
Yelp | +0.027 |
Auto | +0.026 |
Olympia | +0.025 |
Neg logit contributions | |
Luke | -0.028 |
ْ | -0.027 |
src | -0.027 |
sky | -0.026 |
cylinders | -0.026 |
Token | Republican |
Token ID | 3415 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Luke | +0.407 |
ْ | +0.393 |
src | +0.387 |
sky | +0.385 |
Color | +0.382 |
Neg logit contributions | |
cair | -0.403 |
AZ | -0.400 |
Yelp | -0.397 |
Auto | -0.375 |
Olympia | -0.368 |
Token | opponents |
Token ID | 7691 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
cair | +0.235 |
AZ | +0.233 |
Yelp | +0.232 |
Auto | +0.220 |
Olympia | +0.217 |
Neg logit contributions | |
Luke | -0.174 |
ْ | -0.167 |
src | -0.164 |
sky | -0.163 |
Color | -0.161 |
Token | of |
Token ID | 286 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
AZ | +2.279 |
cair | +2.266 |
Yelp | +2.265 |
Auto | +2.121 |
Olympia | +2.092 |
Neg logit contributions | |
Luke | -2.677 |
ْ | -2.585 |
src | -2.551 |
Color | -2.524 |
ample | -2.517 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
cair | +0.335 |
AZ | +0.333 |
Yelp | +0.331 |
Auto | +0.312 |
Olympia | +0.307 |
Neg logit contributions | |
Luke | -0.334 |
ْ | -0.321 |
src | -0.316 |
sky | -0.314 |
Color | -0.314 |
Token | debt |
Token ID | 5057 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Luke | +0.097 |
ْ | +0.093 |
src | +0.092 |
sky | +0.092 |
cylinders | +0.091 |
Neg logit contributions | |
cair | -0.093 |
AZ | -0.092 |
Yelp | -0.092 |
Auto | -0.086 |
Olympia | -0.085 |
Token | ceiling |
Token ID | 13387 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Luke | +0.568 |
ْ | +0.540 |
src | +0.534 |
sky | +0.530 |
cylinders | +0.527 |
Neg logit contributions | |
cair | -0.814 |
AZ | -0.806 |
Yelp | -0.803 |
Auto | -0.765 |
Olympia | -0.752 |
Token | increase |
Token ID | 2620 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
cair | +0.788 |
AZ | +0.782 |
Yelp | +0.778 |
Auto | +0.731 |
Olympia | +0.718 |
Neg logit contributions | |
Luke | -0.825 |
ْ | -0.794 |
src | -0.785 |
sky | -0.777 |
cylinders | -0.777 |
Token | ence |
Token ID | 594 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
cair | +1.029 |
AZ | +1.011 |
Yelp | +1.006 |
Auto | +0.932 |
Olympia | +0.902 |
Neg logit contributions | |
Luke | -1.601 |
ْ | -1.552 |
src | -1.529 |
sky | -1.527 |
cylinders | -1.523 |
Token | to |
Token ID | 284 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
cair | +0.230 |
AZ | +0.228 |
Yelp | +0.227 |
Auto | +0.212 |
Olympia | +0.206 |
Neg logit contributions | |
Luke | -0.302 |
ْ | -0.291 |
src | -0.288 |
sky | -0.287 |
cylinders | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
cair | +0.498 |
AZ | +0.494 |
Yelp | +0.492 |
Auto | +0.463 |
Olympia | +0.454 |
Neg logit contributions | |
Luke | -0.483 |
ْ | -0.465 |
src | -0.458 |
sky | -0.456 |
cylinders | -0.453 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
cair | +0.386 |
AZ | +0.380 |
Yelp | +0.379 |
Auto | +0.357 |
Olympia | +0.350 |
Neg logit contributions | |
Luke | -0.369 |
ْ | -0.354 |
src | -0.349 |
sky | -0.348 |
cylinders | -0.346 |
Token | . |
Token ID | 13 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
AZ | +0.866 |
cair | +0.863 |
Yelp | +0.859 |
Auto | +0.805 |
Olympia | +0.792 |
Neg logit contributions | |
Luke | -0.989 |
ْ | -0.961 |
src | -0.945 |
sky | -0.937 |
Color | -0.936 |
Token | Plus |
Token ID | 8227 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
cair | +0.563 |
AZ | +0.554 |
Yelp | +0.552 |
Auto | +0.522 |
Olympia | +0.511 |
Neg logit contributions | |
Luke | -0.497 |
ْ | -0.476 |
src | -0.469 |
sky | -0.467 |
Color | -0.464 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
AZ | +2.651 |
Yelp | +2.619 |
cair | +2.596 |
Auto | +2.458 |
Olympia | +2.418 |
Neg logit contributions | |
Luke | -2.896 |
ْ | -2.785 |
src | -2.773 |
sky | -2.731 |
Cla | -2.722 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
cair | +0.989 |
AZ | +0.982 |
Yelp | +0.977 |
Auto | +0.919 |
Olympia | +0.901 |
Neg logit contributions | |
Luke | -1.021 |
ْ | -0.985 |
src | -0.970 |
sky | -0.965 |
Color | -0.958 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
cair | +0.925 |
AZ | +0.918 |
Yelp | +0.915 |
Auto | +0.862 |
Olympia | +0.843 |
Neg logit contributions | |
Luke | -0.904 |
ْ | -0.873 |
src | -0.860 |
sky | -0.854 |
cylinders | -0.850 |
Token | evaluation |
Token ID | 12660 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
Luke | +0.830 |
ْ | +0.788 |
sky | +0.786 |
src | +0.783 |
cylinders | +0.779 |
Neg logit contributions | |
cair | -0.945 |
AZ | -0.918 |
Yelp | -0.912 |
Auto | -0.866 |
Olympia | -0.846 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
cair | +0.039 |
AZ | +0.038 |
Yelp | +0.038 |
Auto | +0.036 |
Olympia | +0.035 |
Neg logit contributions | |
Luke | -0.038 |
ْ | -0.036 |
src | -0.036 |
sky | -0.036 |
cylinders | -0.035 |
Token | trying |
Token ID | 2111 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Luke | +0.935 |
ْ | +0.899 |
src | +0.885 |
sky | +0.882 |
cylinders | +0.879 |
Neg logit contributions | |
cair | -0.988 |
AZ | -0.974 |
Yelp | -0.970 |
Auto | -0.915 |
Olympia | -0.895 |
Token | to |
Token ID | 284 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
Luke | +1.111 |
ْ | +1.071 |
src | +1.060 |
sky | +1.059 |
cylinders | +1.052 |
Neg logit contributions | |
cair | -0.952 |
AZ | -0.932 |
Yelp | -0.930 |
Auto | -0.866 |
Olympia | -0.847 |
Token | reach |
Token ID | 3151 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
cair | +0.031 |
AZ | +0.031 |
Yelp | +0.031 |
Auto | +0.029 |
Olympia | +0.028 |
Neg logit contributions | |
Luke | -0.035 |
ْ | -0.034 |
src | -0.033 |
sky | -0.033 |
cylinders | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Luke | +0.647 |
ْ | +0.622 |
src | +0.612 |
sky | +0.610 |
cylinders | +0.608 |
Neg logit contributions | |
cair | -0.686 |
AZ | -0.673 |
Yelp | -0.672 |
Auto | -0.633 |
Olympia | -0.619 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
Luke | +0.165 |
ْ | +0.158 |
src | +0.156 |
sky | +0.155 |
cylinders | +0.154 |
Neg logit contributions | |
cair | -0.192 |
AZ | -0.189 |
Yelp | -0.189 |
Auto | -0.178 |
Olympia | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
Luke | +0.482 |
ْ | +0.464 |
src | +0.458 |
sky | +0.457 |
cylinders | +0.455 |
Neg logit contributions | |
cair | -0.444 |
AZ | -0.437 |
Yelp | -0.436 |
Auto | -0.409 |
Olympia | -0.399 |
Token |
|
Token ID | 198 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
cair | +0.074 |
AZ | +0.073 |
Yelp | +0.073 |
Auto | +0.069 |
Olympia | +0.067 |
Neg logit contributions | |
Luke | -0.061 |
ْ | -0.059 |
src | -0.058 |
sky | -0.057 |
cylinders | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Luke | +0.006 |
ْ | +0.006 |
cylinders | +0.006 |
src | +0.006 |
sky | +0.006 |
Neg logit contributions | |
cair | -0.008 |
AZ | -0.008 |
Yelp | -0.008 |
Auto | -0.007 |
Olympia | -0.007 |
Token | Of |
Token ID | 5189 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
cair | +0.958 |
AZ | +0.950 |
Yelp | +0.943 |
Auto | +0.900 |
Olympia | +0.883 |
Neg logit contributions | |
Luke | -0.649 |
ْ | -0.629 |
cylinders | -0.625 |
src | -0.610 |
sky | -0.610 |
Token | course |
Token ID | 1781 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
cair | +0.576 |
AZ | +0.573 |
Yelp | +0.569 |
Auto | +0.536 |
Olympia | +0.528 |
Neg logit contributions | |
Luke | -0.540 |
ْ | -0.521 |
src | -0.510 |
cylinders | -0.505 |
sky | -0.504 |
Token | , |
Token ID | 11 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Luke | +0.364 |
ْ | +0.351 |
src | +0.345 |
sky | +0.344 |
cylinders | +0.342 |
Neg logit contributions | |
cair | -0.374 |
AZ | -0.372 |
Yelp | -0.370 |
Auto | -0.349 |
Olympia | -0.342 |
Token | don |
Token ID | 836 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Luke | +0.879 |
ْ | +0.840 |
src | +0.830 |
sky | +0.830 |
cylinders | +0.827 |
Neg logit contributions | |
cair | -0.913 |
AZ | -0.896 |
Yelp | -0.892 |
Auto | -0.841 |
Olympia | -0.824 |
Token | 't |
Token ID | 470 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
cair | +0.602 |
AZ | +0.592 |
Yelp | +0.589 |
Auto | +0.547 |
Olympia | +0.531 |
Neg logit contributions | |
Luke | -0.884 |
ْ | -0.857 |
src | -0.845 |
sky | -0.843 |
cylinders | -0.840 |
Token | forget |
Token ID | 6044 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Luke | +0.008 |
ْ | +0.008 |
src | +0.007 |
sky | +0.007 |
Color | +0.007 |
Neg logit contributions | |
cair | -0.009 |
AZ | -0.009 |
Yelp | -0.009 |
Auto | -0.008 |
Olympia | -0.008 |
Token | Spielberg |
Token ID | 41151 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Luke | +0.110 |
ْ | +0.106 |
src | +0.105 |
sky | +0.104 |
Color | +0.104 |
Neg logit contributions | |
cair | -0.102 |
AZ | -0.102 |
Yelp | -0.101 |
Auto | -0.095 |
Olympia | -0.093 |
Token | 's |
Token ID | 338 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
Luke | +1.269 |
ْ | +1.221 |
sky | +1.205 |
src | +1.205 |
cylinders | +1.196 |
Neg logit contributions | |
cair | -1.276 |
AZ | -1.250 |
Yelp | -1.250 |
Auto | -1.170 |
Olympia | -1.151 |
Token | classic |
Token ID | 6833 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
cair | +0.528 |
AZ | +0.526 |
Yelp | +0.524 |
Auto | +0.495 |
Olympia | +0.483 |
Neg logit contributions | |
Luke | -0.515 |
ْ | -0.497 |
src | -0.487 |
sky | -0.485 |
女 | -0.483 |
Token | film |
Token ID | 2646 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
cair | +0.356 |
AZ | +0.353 |
Yelp | +0.350 |
Auto | +0.333 |
Olympia | +0.324 |
Neg logit contributions | |
Luke | -0.344 |
ْ | -0.331 |
src | -0.325 |
sky | -0.323 |
cylinders | -0.321 |
Token | J |
Token ID | 449 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
cair | +0.568 |
AZ | +0.564 |
Yelp | +0.559 |
Auto | +0.532 |
Olympia | +0.519 |
Neg logit contributions | |
Luke | -0.568 |
ْ | -0.547 |
src | -0.539 |
sky | -0.534 |
cylinders | -0.532 |
Token | aws |
Token ID | 8356 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Luke | +0.670 |
ْ | +0.640 |
src | +0.632 |
sky | +0.627 |
cylinders | +0.625 |
Neg logit contributions | |
cair | -0.863 |
AZ | -0.853 |
Yelp | -0.849 |
Auto | -0.806 |
Olympia | -0.792 |
Token | in |
Token ID | 287 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
cair | +1.052 |
AZ | +1.044 |
Yelp | +1.038 |
Auto | +0.980 |
Olympia | +0.951 |
Neg logit contributions | |
Luke | -1.148 |
ْ | -1.105 |
src | -1.089 |
sky | -1.081 |
ample | -1.077 |
Token | which |
Token ID | 543 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
cair | +0.565 |
AZ | +0.558 |
Yelp | +0.555 |
Auto | +0.519 |
Olympia | +0.507 |
Neg logit contributions | |
Luke | -0.682 |
ْ | -0.659 |
src | -0.649 |
sky | -0.647 |
cylinders | -0.643 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
AZ | +1.181 |
cair | +1.175 |
Yelp | +1.169 |
Auto | +1.103 |
Olympia | +1.080 |
Neg logit contributions | |
Luke | -1.275 |
ْ | -1.227 |
src | -1.217 |
sky | -1.207 |
ample | -1.196 |
Token | / |
Token ID | 14 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Luke | +0.134 |
ْ | +0.128 |
src | +0.127 |
sky | +0.126 |
Color | +0.125 |
Neg logit contributions | |
cair | -0.132 |
AZ | -0.131 |
Yelp | -0.130 |
Auto | -0.123 |
Olympia | -0.120 |
Token | or |
Token ID | 273 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
cair | +1.764 |
AZ | +1.748 |
Yelp | +1.738 |
Auto | +1.661 |
Olympia | +1.618 |
Neg logit contributions | |
Luke | -1.213 |
ْ | -1.167 |
cylinders | -1.152 |
sky | -1.124 |
src | -1.123 |
Token | che |
Token ID | 1125 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Luke | +0.211 |
ْ | +0.203 |
src | +0.200 |
sky | +0.199 |
cylinders | +0.197 |
Neg logit contributions | |
cair | -0.210 |
AZ | -0.208 |
Yelp | -0.207 |
Auto | -0.195 |
Olympia | -0.191 |
Token | wy |
Token ID | 21768 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
cair | +0.151 |
AZ | +0.149 |
Yelp | +0.149 |
Auto | +0.140 |
Olympia | +0.136 |
Neg logit contributions | |
Luke | -0.167 |
ْ | -0.161 |
src | -0.158 |
sky | -0.158 |
cylinders | -0.158 |
Token | baking |
Token ID | 16871 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
cair | +1.007 |
AZ | +1.005 |
Yelp | +0.998 |
Auto | +0.942 |
Olympia | +0.920 |
Neg logit contributions | |
Luke | -1.092 |
ْ | -1.050 |
src | -1.041 |
sky | -1.032 |
ample | -1.024 |
Token | recipes |
Token ID | 14296 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
cair | +0.281 |
AZ | +0.278 |
Yelp | +0.276 |
Auto | +0.261 |
Olympia | +0.255 |
Neg logit contributions | |
Luke | -0.275 |
ْ | -0.264 |
src | -0.260 |
sky | -0.259 |
ample | -0.257 |
Token | and |
Token ID | 290 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
cair | +0.345 |
AZ | +0.341 |
Yelp | +0.340 |
Auto | +0.320 |
Olympia | +0.312 |
Neg logit contributions | |
Luke | -0.365 |
ْ | -0.352 |
src | -0.346 |
sky | -0.345 |
cylinders | -0.344 |
Token | not |
Token ID | 407 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
cair | +0.438 |
AZ | +0.433 |
Yelp | +0.432 |
Auto | +0.407 |
Olympia | +0.397 |
Neg logit contributions | |
Luke | -0.445 |
ْ | -0.428 |
src | -0.422 |
sky | -0.420 |
Color | -0.416 |
Token | as |
Token ID | 355 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
cair | +0.659 |
AZ | +0.653 |
Yelp | +0.651 |
Auto | +0.614 |
Olympia | +0.598 |
Neg logit contributions | |
Luke | -0.674 |
ْ | -0.647 |
src | -0.638 |
sky | -0.635 |
Color | -0.630 |
Token | well |
Token ID | 880 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Luke | +0.159 |
ْ | +0.154 |
src | +0.151 |
cylinders | +0.151 |
sky | +0.151 |
Neg logit contributions | |
cair | -0.148 |
AZ | -0.145 |
Yelp | -0.145 |
Auto | -0.136 |
Olympia | -0.133 |
Token | but |
Token ID | 475 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Luke | +0.266 |
ْ | +0.256 |
src | +0.252 |
sky | +0.251 |
cylinders | +0.250 |
Neg logit contributions | |
cair | -0.253 |
AZ | -0.250 |
Yelp | -0.249 |
Auto | -0.234 |
Olympia | -0.228 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Luke | +0.408 |
ْ | +0.392 |
src | +0.386 |
sky | +0.385 |
cylinders | +0.383 |
Neg logit contributions | |
cair | -0.413 |
AZ | -0.407 |
Yelp | -0.406 |
Auto | -0.382 |
Olympia | -0.374 |
Token | says |
Token ID | 1139 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
cair | +0.751 |
AZ | +0.746 |
Yelp | +0.743 |
Auto | +0.700 |
Olympia | +0.685 |
Neg logit contributions | |
Luke | -0.780 |
ْ | -0.749 |
src | -0.739 |
sky | -0.737 |
Color | -0.734 |
Token | Gale |
Token ID | 36483 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Luke | +0.624 |
ْ | +0.600 |
src | +0.590 |
sky | +0.588 |
cylinders | +0.585 |
Neg logit contributions | |
cair | -0.680 |
AZ | -0.671 |
Yelp | -0.669 |
Auto | -0.631 |
Olympia | -0.618 |
Token | otti |
Token ID | 26380 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
cair | +2.609 |
AZ | +2.549 |
Yelp | +2.539 |
Auto | +2.427 |
Olympia | +2.326 |
Neg logit contributions | |
Luke | -2.701 |
ْ | -2.674 |
cylinders | -2.580 |
Color | -2.561 |
Cla | -2.547 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
cair | +1.972 |
AZ | +1.965 |
Yelp | +1.927 |
Auto | +1.848 |
Olympia | +1.763 |
Neg logit contributions | |
Luke | -2.154 |
ample | -2.041 |
ْ | -2.037 |
src | -2.029 |
cylinders | -2.020 |
Token | � |
Token ID | 564 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
cair | +1.021 |
AZ | +1.018 |
Yelp | +1.012 |
Auto | +0.961 |
Olympia | +0.940 |
Neg logit contributions | |
Luke | -0.935 |
ْ | -0.887 |
src | -0.877 |
sky | -0.875 |
Color | -0.872 |
Token | � |
Token ID | 250 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
cair | +0.975 |
AZ | +0.970 |
Yelp | +0.964 |
Auto | +0.900 |
Olympia | +0.874 |
Neg logit contributions | |
Luke | -1.422 |
ْ | -1.372 |
src | -1.360 |
sky | -1.358 |
cylinders | -1.357 |
Token | Putin |
Token ID | 17060 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
cair | +1.254 |
AZ | +1.227 |
Yelp | +1.224 |
Auto | +1.164 |
Olympia | +1.141 |
Neg logit contributions | |
Luke | -0.940 |
ْ | -0.907 |
cylinders | -0.892 |
src | -0.885 |
sky | -0.875 |
Token | is |
Token ID | 318 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Luke | +0.349 |
ْ | +0.334 |
src | +0.329 |
sky | +0.327 |
cylinders | +0.326 |
Neg logit contributions | |
cair | -0.397 |
AZ | -0.392 |
Yelp | -0.391 |
Auto | -0.370 |
Olympia | -0.362 |
Token | clearly |
Token ID | 4084 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
cair | +0.156 |
AZ | +0.154 |
Yelp | +0.154 |
Auto | +0.145 |
Olympia | +0.142 |
Neg logit contributions | |
Luke | -0.163 |
ْ | -0.156 |
src | -0.154 |
sky | -0.153 |
cylinders | -0.153 |
Token | any |
Token ID | 597 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
cair | +0.453 |
AZ | +0.449 |
Yelp | +0.448 |
Auto | +0.419 |
Olympia | +0.410 |
Neg logit contributions | |
Luke | -0.526 |
ْ | -0.509 |
src | -0.501 |
sky | -0.498 |
cylinders | -0.496 |
Token | refund |
Token ID | 12929 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
cair | +0.266 |
AZ | +0.263 |
Yelp | +0.262 |
Auto | +0.246 |
Olympia | +0.241 |
Neg logit contributions | |
Luke | -0.272 |
ْ | -0.263 |
src | -0.259 |
sky | -0.257 |
cylinders | -0.256 |
Token | from |
Token ID | 422 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Luke | +0.224 |
ْ | +0.215 |
src | +0.213 |
sky | +0.210 |
Color | +0.210 |
Neg logit contributions | |
cair | -0.254 |
AZ | -0.252 |
Yelp | -0.251 |
Auto | -0.237 |
Olympia | -0.232 |
Token | developer |
Token ID | 8517 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Luke | +0.126 |
ْ | +0.122 |
src | +0.120 |
sky | +0.120 |
cylinders | +0.120 |
Neg logit contributions | |
cair | -0.073 |
AZ | -0.071 |
Yelp | -0.071 |
Auto | -0.065 |
Olympia | -0.063 |
Token | Winter |
Token ID | 10633 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Luke | +0.480 |
ْ | +0.463 |
src | +0.457 |
sky | +0.456 |
cylinders | +0.453 |
Neg logit contributions | |
cair | -0.397 |
AZ | -0.389 |
Yelp | -0.387 |
Auto | -0.362 |
Olympia | -0.354 |
Token | ke |
Token ID | 365 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
Luke | +0.122 |
sky | +0.117 |
ْ | +0.116 |
src | +0.116 |
ample | +0.115 |
Neg logit contributions | |
cair | -0.111 |
AZ | -0.110 |
Yelp | -0.110 |
Auto | -0.103 |
Olympia | -0.100 |
Token | wl |
Token ID | 40989 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
cair | +0.531 |
AZ | +0.522 |
Yelp | +0.520 |
Auto | +0.484 |
Olympia | +0.471 |
Neg logit contributions | |
Luke | -0.731 |
ْ | -0.707 |
src | -0.698 |
sky | -0.696 |
cylinders | -0.692 |
Token | Games |
Token ID | 5776 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
cair | +0.908 |
AZ | +0.906 |
Yelp | +0.903 |
Auto | +0.855 |
Olympia | +0.838 |
Neg logit contributions | |
Luke | -0.853 |
ْ | -0.821 |
src | -0.803 |
Cla | -0.797 |
ample | -0.797 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Luke | +0.396 |
ْ | +0.380 |
src | +0.374 |
sky | +0.372 |
cylinders | +0.370 |
Neg logit contributions | |
cair | -0.428 |
AZ | -0.424 |
Yelp | -0.423 |
Auto | -0.399 |
Olympia | -0.391 |
Token | remote |
Token ID | 6569 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Luke | +1.202 |
ْ | +1.155 |
src | +1.137 |
sky | +1.134 |
cylinders | +1.128 |
Neg logit contributions | |
cair | -1.253 |
AZ | -1.234 |
Yelp | -1.229 |
Auto | -1.159 |
Olympia | -1.134 |
Token | , |
Token ID | 11 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
AZ | +0.421 |
cair | +0.421 |
Yelp | +0.419 |
Auto | +0.395 |
Olympia | +0.386 |
Neg logit contributions | |
Luke | -0.460 |
ْ | -0.446 |
src | -0.437 |
cylinders | -0.434 |
Color | -0.434 |
Token | Adam |
Token ID | 7244 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
AZ | +1.562 |
Yelp | +1.543 |
cair | +1.531 |
Auto | +1.450 |
Olympia | +1.421 |
Neg logit contributions | |
Luke | -1.678 |
ْ | -1.618 |
sky | -1.595 |
cylinders | -1.583 |
src | -1.582 |
Token | and |
Token ID | 290 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
AZ | +0.956 |
cair | +0.945 |
Yelp | +0.942 |
Auto | +0.899 |
Olympia | +0.865 |
Neg logit contributions | |
Luke | -0.868 |
ْ | -0.828 |
src | -0.819 |
cylinders | -0.816 |
sky | -0.814 |
Token | Steve |
Token ID | 6542 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
cair | +0.256 |
AZ | +0.255 |
Yelp | +0.253 |
Auto | +0.238 |
Olympia | +0.233 |
Neg logit contributions | |
Luke | -0.283 |
ْ | -0.275 |
src | -0.272 |
sky | -0.270 |
cylinders | -0.270 |
Token | get |
Token ID | 651 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Luke | +0.366 |
ْ | +0.353 |
src | +0.346 |
sky | +0.343 |
cylinders | +0.343 |
Neg logit contributions | |
cair | -0.398 |
AZ | -0.396 |
Yelp | -0.395 |
Auto | -0.373 |
Olympia | -0.364 |
Token | married |
Token ID | 6405 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Luke | +0.452 |
ْ | +0.434 |
src | +0.428 |
sky | +0.425 |
cylinders | +0.422 |
Neg logit contributions | |
cair | -0.545 |
AZ | -0.544 |
Yelp | -0.543 |
Auto | -0.513 |
Olympia | -0.502 |
Token | in |
Token ID | 287 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Luke | +0.125 |
ْ | +0.121 |
src | +0.119 |
sky | +0.119 |
cylinders | +0.118 |
Neg logit contributions | |
cair | -0.116 |
AZ | -0.115 |
Yelp | -0.114 |
Auto | -0.108 |
Olympia | -0.105 |
Token | California |
Token ID | 3442 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Luke | +0.219 |
ْ | +0.211 |
src | +0.207 |
sky | +0.206 |
cylinders | +0.205 |
Neg logit contributions | |
cair | -0.221 |
AZ | -0.220 |
Yelp | -0.219 |
Auto | -0.206 |
Olympia | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Luke | +0.047 |
ْ | +0.045 |
src | +0.045 |
sky | +0.044 |
cylinders | +0.044 |
Neg logit contributions | |
cair | -0.043 |
AZ | -0.042 |
Yelp | -0.042 |
Auto | -0.039 |
Olympia | -0.038 |
Token | Steve |
Token ID | 6542 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
cair | +0.198 |
AZ | +0.198 |
Yelp | +0.197 |
Auto | +0.186 |
Olympia | +0.182 |
Neg logit contributions | |
Luke | -0.190 |
ْ | -0.183 |
cylinders | -0.180 |
sky | -0.179 |
src | -0.179 |
Token | then |
Token ID | 788 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
cair | +0.388 |
AZ | +0.388 |
Yelp | +0.386 |
Auto | +0.364 |
Olympia | +0.356 |
Neg logit contributions | |
Luke | -0.377 |
ْ | -0.364 |
src | -0.357 |
sky | -0.354 |
ample | -0.354 |
Token | gets |
Token ID | 3011 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
AZ | +0.834 |
cair | +0.833 |
Yelp | +0.829 |
Auto | +0.784 |
Olympia | +0.765 |
Neg logit contributions | |
Luke | -0.788 |
ْ | -0.765 |
src | -0.747 |
Cla | -0.742 |
ample | -0.741 |
Token | in |
Token ID | 287 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Luke | +0.652 |
ْ | +0.629 |
src | +0.619 |
sky | +0.617 |
cylinders | +0.615 |
Neg logit contributions | |
cair | -0.608 |
AZ | -0.599 |
Yelp | -0.597 |
Auto | -0.561 |
Olympia | -0.548 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Luke | +0.090 |
ْ | +0.087 |
src | +0.085 |
sky | +0.085 |
cylinders | +0.084 |
Neg logit contributions | |
cair | -0.101 |
AZ | -0.101 |
Yelp | -0.101 |
Auto | -0.096 |
Olympia | -0.093 |
Token | justice |
Token ID | 5316 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Luke | +0.824 |
ْ | +0.790 |
src | +0.779 |
sky | +0.777 |
cylinders | +0.771 |
Neg logit contributions | |
cair | -0.910 |
AZ | -0.895 |
Yelp | -0.892 |
Auto | -0.840 |
Olympia | -0.824 |
Token | system |
Token ID | 1080 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Luke | +1.581 |
ْ | +1.518 |
sky | +1.502 |
cylinders | +1.495 |
src | +1.494 |
Neg logit contributions | |
cair | -1.362 |
AZ | -1.327 |
Yelp | -1.319 |
Auto | -1.227 |
Olympia | -1.198 |
Token | ( |
Token ID | 357 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Luke | +0.916 |
ْ | +0.879 |
src | +0.867 |
sky | +0.864 |
cylinders | +0.860 |
Neg logit contributions | |
cair | -0.959 |
AZ | -0.944 |
Yelp | -0.941 |
Auto | -0.886 |
Olympia | -0.869 |
Token | prison |
Token ID | 35156 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Luke | +0.191 |
ْ | +0.184 |
src | +0.181 |
sky | +0.180 |
cylinders | +0.180 |
Neg logit contributions | |
cair | -0.218 |
AZ | -0.215 |
Yelp | -0.214 |
Auto | -0.202 |
Olympia | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
Luke | +1.478 |
ْ | +1.418 |
src | +1.395 |
sky | +1.391 |
cylinders | +1.383 |
Neg logit contributions | |
cair | -1.702 |
AZ | -1.676 |
Yelp | -1.671 |
Auto | -1.577 |
Olympia | -1.550 |
Token | probation |
Token ID | 19660 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Luke | +0.664 |
ْ | +0.640 |
src | +0.628 |
sky | +0.624 |
Color | +0.622 |
Neg logit contributions | |
cair | -0.701 |
AZ | -0.696 |
Yelp | -0.694 |
Auto | -0.656 |
Olympia | -0.640 |
Token | , |
Token ID | 11 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Luke | +1.020 |
ْ | +0.980 |
src | +0.965 |
sky | +0.960 |
cylinders | +0.956 |
Neg logit contributions | |
cair | -1.097 |
AZ | -1.085 |
Yelp | -1.080 |
Auto | -1.020 |
Olympia | -0.998 |
Token | parole |
Token ID | 25450 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
Luke | +0.502 |
ْ | +0.479 |
src | +0.469 |
sky | +0.465 |
Color | +0.462 |
Neg logit contributions | |
cair | -0.811 |
AZ | -0.806 |
Yelp | -0.804 |
Auto | -0.767 |
Olympia | -0.752 |
Token | ) |
Token ID | 8 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Luke | +2.782 |
ْ | +2.669 |
sky | +2.611 |
cylinders | +2.611 |
src | +2.610 |
Neg logit contributions | |
cair | -3.461 |
Yelp | -3.397 |
AZ | -3.388 |
Auto | -3.193 |
Olympia | -3.151 |
Token | the |
Token ID | 262 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Luke | +0.950 |
ْ | +0.914 |
src | +0.900 |
sky | +0.896 |
cylinders | +0.891 |
Neg logit contributions | |
cair | -0.908 |
AZ | -0.897 |
Yelp | -0.894 |
Auto | -0.840 |
Olympia | -0.820 |
Token | CM |
Token ID | 16477 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
Luke | +0.251 |
ْ | +0.241 |
src | +0.237 |
sky | +0.236 |
Color | +0.234 |
Neg logit contributions | |
cair | -0.275 |
AZ | -0.272 |
Yelp | -0.271 |
Auto | -0.256 |
Olympia | -0.251 |
Token | cannot |
Token ID | 2314 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
cair | +0.596 |
AZ | +0.587 |
Yelp | +0.583 |
Auto | +0.559 |
Olympia | +0.544 |
Neg logit contributions | |
Luke | -0.463 |
ْ | -0.443 |
src | -0.436 |
sky | -0.433 |
女 | -0.430 |
Token | bend |
Token ID | 19396 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
Luke | +0.173 |
ْ | +0.166 |
src | +0.164 |
sky | +0.162 |
Color | +0.162 |
Neg logit contributions | |
cair | -0.168 |
AZ | -0.166 |
Yelp | -0.166 |
Auto | -0.156 |
Olympia | -0.152 |
Token | or |
Token ID | 393 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Luke | +0.573 |
ْ | +0.551 |
src | +0.543 |
sky | +0.542 |
Color | +0.538 |
Neg logit contributions | |
cair | -0.531 |
AZ | -0.525 |
Yelp | -0.523 |
Auto | -0.492 |
Olympia | -0.481 |
Token | bypass |
Token ID | 17286 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Luke | +0.819 |
ْ | +0.788 |
src | +0.775 |
sky | +0.770 |
Color | +0.767 |
Neg logit contributions | |
cair | -0.848 |
AZ | -0.840 |
Yelp | -0.837 |
Auto | -0.789 |
Olympia | -0.772 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Luke | +1.425 |
ْ | +1.369 |
src | +1.347 |
sky | +1.342 |
cylinders | +1.338 |
Neg logit contributions | |
cair | -1.624 |
AZ | -1.600 |
Yelp | -1.594 |
Auto | -1.506 |
Olympia | -1.477 |
Token | to |
Token ID | 284 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Luke | +0.738 |
ْ | +0.710 |
src | +0.700 |
sky | +0.698 |
cylinders | +0.694 |
Neg logit contributions | |
cair | -0.705 |
AZ | -0.695 |
Yelp | -0.693 |
Auto | -0.651 |
Olympia | -0.636 |
Token | give |
Token ID | 1577 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Luke | +0.436 |
ْ | +0.420 |
src | +0.414 |
sky | +0.413 |
cylinders | +0.410 |
Neg logit contributions | |
cair | -0.418 |
AZ | -0.412 |
Yelp | -0.410 |
Auto | -0.386 |
Olympia | -0.377 |
Token | away |
Token ID | 1497 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
cair | +0.202 |
AZ | +0.201 |
Yelp | +0.200 |
Auto | +0.189 |
Olympia | +0.184 |
Neg logit contributions | |
Luke | -0.190 |
ْ | -0.182 |
src | -0.180 |
sky | -0.178 |
女 | -0.177 |
Token | government |
Token ID | 1230 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Luke | +1.767 |
ْ | +1.701 |
cylinders | +1.683 |
src | +1.675 |
sky | +1.672 |
Neg logit contributions | |
cair | -1.976 |
AZ | -1.929 |
Yelp | -1.927 |
Auto | -1.815 |
Olympia | -1.786 |
Token | merged |
Token ID | 23791 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
Luke | +0.043 |
ْ | +0.041 |
src | +0.040 |
sky | +0.040 |
cylinders | +0.040 |
Neg logit contributions | |
cair | -0.045 |
AZ | -0.045 |
Yelp | -0.045 |
Auto | -0.042 |
Olympia | -0.041 |
Token | with |
Token ID | 351 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Luke | +0.046 |
ْ | +0.045 |
src | +0.044 |
sky | +0.044 |
cylinders | +0.043 |
Neg logit contributions | |
cair | -0.038 |
AZ | -0.038 |
Yelp | -0.037 |
Auto | -0.035 |
Olympia | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Luke | +0.529 |
ْ | +0.508 |
src | +0.500 |
sky | +0.499 |
Color | +0.495 |
Neg logit contributions | |
cair | -0.569 |
AZ | -0.563 |
Yelp | -0.561 |
Auto | -0.530 |
Olympia | -0.518 |
Token | performers |
Token ID | 23827 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Luke | +0.958 |
ْ | +0.922 |
src | +0.909 |
cylinders | +0.906 |
sky | +0.906 |
Neg logit contributions | |
cair | -0.921 |
AZ | -0.902 |
Yelp | -0.901 |
Auto | -0.845 |
Olympia | -0.826 |
Token | to |
Token ID | 284 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Luke | +0.779 |
ْ | +0.750 |
src | +0.742 |
cylinders | +0.737 |
sky | +0.736 |
Neg logit contributions | |
cair | -0.734 |
AZ | -0.721 |
Yelp | -0.719 |
Auto | -0.674 |
Olympia | -0.657 |
Token | complete |
Token ID | 1844 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Luke | +1.423 |
ْ | +1.361 |
src | +1.346 |
cylinders | +1.341 |
sky | +1.334 |
Neg logit contributions | |
cair | -1.667 |
AZ | -1.633 |
Yelp | -1.629 |
Auto | -1.533 |
Olympia | -1.508 |
Token | the |
Token ID | 262 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Luke | +1.182 |
ْ | +1.135 |
src | +1.117 |
sky | +1.112 |
cylinders | +1.107 |
Neg logit contributions | |
cair | -1.343 |
AZ | -1.325 |
Yelp | -1.321 |
Auto | -1.247 |
Olympia | -1.222 |
Token | effect |
Token ID | 1245 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Luke | +0.344 |
ْ | +0.333 |
src | +0.329 |
sky | +0.328 |
cylinders | +0.326 |
Neg logit contributions | |
cair | -0.233 |
AZ | -0.229 |
Yelp | -0.228 |
Auto | -0.212 |
Olympia | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Luke | +0.372 |
ْ | +0.359 |
src | +0.354 |
sky | +0.353 |
cylinders | +0.351 |
Neg logit contributions | |
cair | -0.339 |
AZ | -0.334 |
Yelp | -0.333 |
Auto | -0.313 |
Olympia | -0.306 |
Token |
|
Token ID | 198 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
Luke | +0.298 |
ْ | +0.286 |
src | +0.281 |
sky | +0.280 |
cylinders | +0.279 |
Neg logit contributions | |
cair | -0.356 |
AZ | -0.353 |
Yelp | -0.351 |
Auto | -0.333 |
Olympia | -0.326 |
Token |
|
Token ID | 198 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Luke | +0.554 |
ْ | +0.529 |
src | +0.520 |
sky | +0.518 |
cylinders | +0.514 |
Neg logit contributions | |
cair | -0.736 |
AZ | -0.727 |
Yelp | -0.724 |
Auto | -0.687 |
Olympia | -0.674 |
Token | too |
Token ID | 1165 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
cair | +0.492 |
AZ | +0.488 |
Yelp | +0.486 |
Auto | +0.457 |
Olympia | +0.446 |
Neg logit contributions | |
Luke | -0.516 |
ْ | -0.499 |
src | -0.491 |
sky | -0.488 |
cylinders | -0.486 |
Token | shy |
Token ID | 15800 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Luke | +0.590 |
ْ | +0.565 |
src | +0.555 |
sky | +0.554 |
cylinders | +0.551 |
Neg logit contributions | |
cair | -0.663 |
AZ | -0.651 |
Yelp | -0.649 |
Auto | -0.612 |
Olympia | -0.600 |
Token | to |
Token ID | 284 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Luke | +0.243 |
ْ | +0.234 |
src | +0.231 |
sky | +0.230 |
cylinders | +0.230 |
Neg logit contributions | |
cair | -0.202 |
AZ | -0.199 |
Yelp | -0.198 |
Auto | -0.185 |
Olympia | -0.180 |
Token | do |
Token ID | 466 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Luke | +0.104 |
ْ | +0.100 |
src | +0.099 |
sky | +0.098 |
cylinders | +0.098 |
Neg logit contributions | |
cair | -0.109 |
AZ | -0.107 |
Yelp | -0.107 |
Auto | -0.101 |
Olympia | -0.099 |
Token | so |
Token ID | 523 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
cair | +0.155 |
AZ | +0.153 |
Yelp | +0.152 |
Auto | +0.143 |
Olympia | +0.139 |
Neg logit contributions | |
Luke | -0.176 |
ْ | -0.170 |
src | -0.167 |
sky | -0.167 |
cylinders | -0.166 |
Token | on |
Token ID | 319 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Luke | +0.236 |
ْ | +0.227 |
src | +0.224 |
sky | +0.223 |
cylinders | +0.222 |
Neg logit contributions | |
cair | -0.218 |
AZ | -0.215 |
Yelp | -0.214 |
Auto | -0.201 |
Olympia | -0.196 |
Token | his |
Token ID | 465 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Luke | +0.295 |
ْ | +0.283 |
src | +0.279 |
sky | +0.277 |
cylinders | +0.276 |
Neg logit contributions | |
cair | -0.325 |
AZ | -0.322 |
Yelp | -0.321 |
Auto | -0.303 |
Olympia | -0.296 |
Token | own |
Token ID | 898 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Luke | +0.989 |
ْ | +0.950 |
src | +0.940 |
sky | +0.939 |
cylinders | +0.936 |
Neg logit contributions | |
cair | -0.805 |
AZ | -0.787 |
Yelp | -0.783 |
Auto | -0.733 |
Olympia | -0.717 |
Token | . |
Token ID | 13 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
cair | +0.948 |
AZ | +0.945 |
Yelp | +0.940 |
Auto | +0.883 |
Olympia | +0.852 |
Neg logit contributions | |
Luke | -1.106 |
ْ | -1.071 |
src | -1.051 |
sky | -1.047 |
cylinders | -1.042 |
Token | We |
Token ID | 775 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Luke | +0.462 |
ْ | +0.445 |
src | +0.439 |
sky | +0.437 |
Color | +0.434 |
Neg logit contributions | |
cair | -0.437 |
AZ | -0.429 |
Yelp | -0.427 |
Auto | -0.401 |
Olympia | -0.392 |
Token | taught |
Token ID | 7817 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Luke | +0.395 |
ْ | +0.377 |
src | +0.372 |
sky | +0.371 |
cylinders | +0.368 |
Neg logit contributions | |
cair | -0.507 |
AZ | -0.500 |
Yelp | -0.499 |
Auto | -0.473 |
Olympia | -0.465 |
Token | with |
Token ID | 351 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Luke | +1.044 |
ْ | +0.992 |
src | +0.988 |
cylinders | +0.977 |
Color | +0.976 |
Neg logit contributions | |
cair | -1.331 |
AZ | -1.304 |
Yelp | -1.303 |
Auto | -1.228 |
Olympia | -1.221 |
Token | \ |
Token ID | 3467 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
Luke | +0.539 |
ْ | +0.518 |
src | +0.510 |
sky | +0.508 |
cylinders | +0.506 |
Neg logit contributions | |
cair | -0.585 |
AZ | -0.578 |
Yelp | -0.576 |
Auto | -0.543 |
Olympia | -0.532 |
Token | und |
Token ID | 3318 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Luke | +1.862 |
ْ | +1.773 |
src | +1.771 |
sky | +1.757 |
Color | +1.754 |
Neg logit contributions | |
cair | -2.183 |
AZ | -2.145 |
Yelp | -2.143 |
Auto | -2.012 |
Olympia | -1.995 |
Token | irect |
Token ID | 1060 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Luke | +1.360 |
ْ | +1.307 |
src | +1.289 |
sky | +1.289 |
cylinders | +1.280 |
Neg logit contributions | |
cair | -1.285 |
AZ | -1.268 |
Yelp | -1.262 |
Auto | -1.184 |
Olympia | -1.162 |
Token | ed |
Token ID | 276 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
cair | +0.377 |
Yelp | +0.373 |
AZ | +0.373 |
Auto | +0.354 |
Olympia | +0.343 |
Neg logit contributions | |
Luke | -0.322 |
ْ | -0.310 |
src | -0.304 |
sky | -0.303 |
cylinders | -0.301 |
Token | edges |
Token ID | 13015 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Luke | +0.496 |
ْ | +0.477 |
src | +0.469 |
sky | +0.468 |
cylinders | +0.464 |
Neg logit contributions | |
cair | -0.565 |
AZ | -0.558 |
Yelp | -0.557 |
Auto | -0.526 |
Olympia | -0.514 |
Token | *) |
Token ID | 31936 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
Luke | +2.304 |
ْ | +2.186 |
src | +2.181 |
cylinders | +2.170 |
Color | +2.170 |
Neg logit contributions | |
cair | -2.558 |
AZ | -2.496 |
Yelp | -2.493 |
Olympia | -2.342 |
Auto | -2.341 |
Token | graph |
Token ID | 4823 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
cair | +0.043 |
AZ | +0.043 |
Yelp | +0.043 |
Auto | +0.041 |
Olympia | +0.039 |
Neg logit contributions | |
Luke | -0.040 |
ْ | -0.039 |
sky | -0.038 |
src | -0.038 |
cylinders | -0.037 |
Token | = |
Token ID | 796 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Luke | +0.899 |
ْ | +0.837 |
src | +0.815 |
sky | +0.809 |
cylinders | +0.801 |
Neg logit contributions | |
cair | -2.313 |
AZ | -2.290 |
Yelp | -2.284 |
Auto | -2.191 |
Olympia | -2.160 |
Token | Fl |
Token ID | 1610 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Luke | +0.550 |
ْ | +0.528 |
src | +0.518 |
sky | +0.518 |
cylinders | +0.514 |
Neg logit contributions | |
cair | -0.586 |
AZ | -0.582 |
Yelp | -0.580 |
Auto | -0.550 |
Olympia | -0.533 |
Token | atten |
Token ID | 41769 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Luke | +1.349 |
ْ | +1.288 |
src | +1.269 |
sky | +1.262 |
Color | +1.253 |
Neg logit contributions | |
cair | -1.846 |
AZ | -1.827 |
Yelp | -1.820 |
Auto | -1.724 |
Olympia | -1.698 |
Token | vert |
Token ID | 9421 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Luke | +0.222 |
ْ | +0.215 |
src | +0.211 |
sky | +0.211 |
cylinders | +0.210 |
Neg logit contributions | |
cair | -0.179 |
AZ | -0.176 |
Yelp | -0.176 |
Auto | -0.164 |
Olympia | -0.160 |
Token | ( |
Token ID | 357 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Luke | +1.164 |
ْ | +1.099 |
src | +1.096 |
sky | +1.093 |
Color | +1.084 |
Neg logit contributions | |
cair | -1.424 |
AZ | -1.403 |
Yelp | -1.397 |
Auto | -1.313 |
Olympia | -1.301 |
Token | in |
Token ID | 287 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Luke | +0.963 |
ْ | +0.929 |
src | +0.913 |
sky | +0.911 |
cylinders | +0.906 |
Neg logit contributions | |
cair | -0.905 |
AZ | -0.893 |
Yelp | -0.889 |
Auto | -0.836 |
Olympia | -0.816 |
Token | out |
Token ID | 448 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Luke | +1.031 |
ْ | +0.972 |
src | +0.969 |
sky | +0.963 |
cylinders | +0.948 |
Neg logit contributions | |
cair | -1.783 |
AZ | -1.765 |
Yelp | -1.763 |
Auto | -1.677 |
Olympia | -1.654 |
Token | app |
Token ID | 598 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Luke | +3.243 |
src | +3.169 |
cylinders | +3.141 |
ample | +3.132 |
sky | +3.115 |
Neg logit contributions | |
cair | -2.249 |
AZ | -2.173 |
Yelp | -2.132 |
Olympia | -1.993 |
Auto | -1.977 |
Token | data |
Token ID | 7890 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Luke | +0.916 |
ْ | +0.864 |
src | +0.844 |
sky | +0.840 |
cylinders | +0.834 |
Neg logit contributions | |
cair | -1.804 |
AZ | -1.785 |
Yelp | -1.780 |
Auto | -1.701 |
Olympia | -1.674 |
Token | _ |
Token ID | 4808 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Luke | +1.869 |
src | +1.764 |
ْ | +1.737 |
Color | +1.711 |
sky | +1.707 |
Neg logit contributions | |
cair | -3.284 |
AZ | -3.156 |
Yelp | -3.154 |
Olympia | -2.990 |
Auto | -2.965 |
Token | full |
Token ID | 1336 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Luke | +1.717 |
ْ | +1.651 |
src | +1.626 |
sky | +1.620 |
cylinders | +1.612 |
Neg logit contributions | |
cair | -1.749 |
AZ | -1.724 |
Yelp | -1.718 |
Auto | -1.618 |
Olympia | -1.583 |
Token | v |
Token ID | 410 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Luke | +1.693 |
ْ | +1.638 |
src | +1.603 |
sky | +1.601 |
cylinders | +1.597 |
Neg logit contributions | |
cair | -1.447 |
AZ | -1.429 |
Yelp | -1.421 |
Auto | -1.333 |
Olympia | -1.291 |
Token | ) |
Token ID | 1267 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Luke | +2.130 |
src | +2.003 |
sky | +1.986 |
ْ | +1.979 |
cylinders | +1.958 |
Neg logit contributions | |
cair | -3.693 |
AZ | -3.633 |
Yelp | -3.621 |
Auto | -3.431 |
Olympia | -3.413 |
Token | { |
Token ID | 1391 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Luke | +0.509 |
ْ | +0.486 |
src | +0.475 |
sky | +0.472 |
cylinders | +0.469 |
Neg logit contributions | |
cair | -0.778 |
AZ | -0.771 |
Yelp | -0.768 |
Auto | -0.732 |
Olympia | -0.718 |
Token | ared |
Token ID | 1144 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
cair | +1.009 |
AZ | +0.995 |
Yelp | +0.988 |
Auto | +0.947 |
Olympia | +0.920 |
Neg logit contributions | |
Luke | -0.781 |
ْ | -0.749 |
sky | -0.731 |
cylinders | -0.729 |
src | -0.728 |
Token | Anton |
Token ID | 9261 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Luke | +0.397 |
ْ | +0.382 |
src | +0.376 |
sky | +0.374 |
Color | +0.372 |
Neg logit contributions | |
cair | -0.426 |
AZ | -0.423 |
Yelp | -0.420 |
Auto | -0.397 |
Olympia | -0.389 |
Token | Ferdinand |
Token ID | 44312 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Luke | +0.366 |
ْ | +0.352 |
src | +0.347 |
sky | +0.346 |
cylinders | +0.344 |
Neg logit contributions | |
cair | -0.359 |
AZ | -0.354 |
Yelp | -0.353 |
Auto | -0.332 |
Olympia | -0.325 |
Token | 's |
Token ID | 338 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Luke | +0.795 |
ْ | +0.766 |
src | +0.755 |
sky | +0.752 |
cylinders | +0.749 |
Neg logit contributions | |
cair | -0.769 |
AZ | -0.757 |
Yelp | -0.755 |
Auto | -0.709 |
Olympia | -0.694 |
Token | deep |
Token ID | 2769 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
cair | +1.171 |
AZ | +1.170 |
Yelp | +1.163 |
Auto | +1.097 |
Olympia | +1.070 |
Neg logit contributions | |
Luke | -1.192 |
ْ | -1.152 |
src | -1.136 |
sky | -1.123 |
Color | -1.120 |
Token | cross |
Token ID | 3272 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
Luke | +1.410 |
ْ | +1.354 |
sky | +1.340 |
cylinders | +1.333 |
src | +1.323 |
Neg logit contributions | |
cair | -1.546 |
AZ | -1.498 |
Yelp | -1.498 |
Auto | -1.405 |
Olympia | -1.391 |
Token | , |
Token ID | 11 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Luke | +2.521 |
ْ | +2.401 |
sky | +2.367 |
cylinders | +2.349 |
ample | +2.343 |
Neg logit contributions | |
cair | -2.817 |
Yelp | -2.709 |
AZ | -2.701 |
Auto | -2.547 |
Olympia | -2.511 |
Token | Lor |
Token ID | 26068 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Luke | +0.146 |
ْ | +0.141 |
src | +0.139 |
sky | +0.138 |
Color | +0.137 |
Neg logit contributions | |
cair | -0.162 |
AZ | -0.162 |
Yelp | -0.161 |
Auto | -0.152 |
Olympia | -0.149 |
Token | ik |
Token ID | 1134 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Luke | +0.121 |
ْ | +0.116 |
src | +0.115 |
sky | +0.114 |
Color | +0.113 |
Neg logit contributions | |
cair | -0.138 |
AZ | -0.136 |
Yelp | -0.135 |
Auto | -0.128 |
Olympia | -0.125 |
Token | Can |
Token ID | 1680 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
Luke | +1.028 |
ْ | +0.988 |
src | +0.975 |
sky | +0.972 |
cylinders | +0.966 |
Neg logit contributions | |
cair | -1.020 |
AZ | -1.002 |
Yelp | -1.000 |
Auto | -0.940 |
Olympia | -0.920 |
Token | a |
Token ID | 64 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Luke | +0.002 |
ْ | +0.002 |
src | +0.002 |
sky | +0.002 |
cylinders | +0.002 |
Neg logit contributions | |
cair | -0.002 |
AZ | -0.002 |
Yelp | -0.002 |
Auto | -0.002 |
Olympia | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Luke | +0.874 |
ْ | +0.841 |
src | +0.828 |
sky | +0.825 |
cylinders | +0.821 |
Neg logit contributions | |
cair | -0.918 |
AZ | -0.905 |
Yelp | -0.902 |
Auto | -0.849 |
Olympia | -0.832 |
Token | Wiz |
Token ID | 41122 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Luke | +0.080 |
ْ | +0.077 |
src | +0.076 |
sky | +0.075 |
cylinders | +0.075 |
Neg logit contributions | |
cair | -0.081 |
AZ | -0.080 |
Yelp | -0.080 |
Auto | -0.075 |
Olympia | -0.074 |
Token | Kids |
Token ID | 40229 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Luke | +0.464 |
ْ | +0.421 |
src | +0.404 |
sky | +0.401 |
Color | +0.395 |
Neg logit contributions | |
cair | -1.827 |
AZ | -1.807 |
Yelp | -1.805 |
Auto | -1.738 |
Olympia | -1.715 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Luke | +0.939 |
ْ | +0.903 |
src | +0.887 |
sky | +0.886 |
cylinders | +0.882 |
Neg logit contributions | |
cair | -1.061 |
AZ | -1.041 |
Yelp | -1.038 |
Auto | -0.979 |
Olympia | -0.960 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Luke | +0.769 |
ْ | +0.741 |
src | +0.728 |
sky | +0.725 |
cylinders | +0.723 |
Neg logit contributions | |
cair | -0.786 |
AZ | -0.773 |
Yelp | -0.770 |
Auto | -0.725 |
Olympia | -0.710 |
Token | ban |
Token ID | 3958 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
Luke | +0.973 |
ْ | +0.933 |
src | +0.926 |
sky | +0.922 |
cylinders | +0.918 |
Neg logit contributions | |
cair | -1.047 |
AZ | -1.027 |
Yelp | -1.024 |
Auto | -0.964 |
Olympia | -0.947 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Luke | +2.474 |
ْ | +2.397 |
ample | +2.369 |
src | +2.368 |
sky | +2.357 |
Neg logit contributions | |
cair | -2.577 |
Yelp | -2.515 |
AZ | -2.509 |
Auto | -2.363 |
Olympia | -2.314 |
Token | These |
Token ID | 2312 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Luke | +0.729 |
ْ | +0.701 |
src | +0.693 |
sky | +0.689 |
Color | +0.686 |
Neg logit contributions | |
cair | -0.722 |
AZ | -0.703 |
Yelp | -0.701 |
Auto | -0.659 |
Olympia | -0.644 |
Token | happen |
Token ID | 1645 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Luke | +0.214 |
ْ | +0.205 |
src | +0.202 |
sky | +0.201 |
cylinders | +0.200 |
Neg logit contributions | |
cair | -0.224 |
AZ | -0.222 |
Yelp | -0.221 |
Auto | -0.208 |
Olympia | -0.204 |
Token | in |
Token ID | 287 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
cair | +0.315 |
AZ | +0.311 |
Yelp | +0.309 |
Auto | +0.291 |
Olympia | +0.284 |
Neg logit contributions | |
Luke | -0.355 |
ْ | -0.342 |
src | -0.337 |
sky | -0.335 |
cylinders | -0.335 |
Token | the |
Token ID | 262 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Luke | +0.521 |
ْ | +0.501 |
src | +0.494 |
sky | +0.493 |
cylinders | +0.490 |
Neg logit contributions | |
cair | -0.529 |
AZ | -0.520 |
Yelp | -0.519 |
Auto | -0.488 |
Olympia | -0.477 |
Token | out |
Token ID | 448 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Luke | +0.853 |
src | +0.807 |
sky | +0.801 |
ْ | +0.795 |
ample | +0.781 |
Neg logit contributions | |
cair | -1.537 |
Yelp | -1.522 |
AZ | -1.522 |
Auto | -1.446 |
Olympia | -1.429 |
Token | app |
Token ID | 598 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Luke | +3.193 |
src | +3.118 |
cylinders | +3.083 |
ample | +3.077 |
sky | +3.068 |
Neg logit contributions | |
cair | -2.259 |
AZ | -2.159 |
Yelp | -2.122 |
Olympia | -1.985 |
Auto | -1.959 |
Token | data |
Token ID | 7890 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Luke | +0.744 |
ْ | +0.711 |
cylinders | +0.684 |
sky | +0.681 |
src | +0.680 |
Neg logit contributions | |
cair | -1.420 |
AZ | -1.401 |
Yelp | -1.398 |
Auto | -1.337 |
Olympia | -1.313 |
Token | _ |
Token ID | 4808 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Luke | +2.457 |
src | +2.353 |
ْ | +2.348 |
sky | +2.321 |
Color | +2.318 |
Neg logit contributions | |
cair | -2.051 |
AZ | -1.962 |
Yelp | -1.951 |
Auto | -1.803 |
Olympia | -1.801 |
Token | full |
Token ID | 1336 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Luke | +1.577 |
ْ | +1.517 |
src | +1.489 |
sky | +1.486 |
cylinders | +1.477 |
Neg logit contributions | |
cair | -1.690 |
AZ | -1.669 |
Yelp | -1.663 |
Auto | -1.571 |
Olympia | -1.536 |
Token | v |
Token ID | 410 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
Luke | +1.494 |
ْ | +1.422 |
src | +1.416 |
sky | +1.404 |
cylinders | +1.399 |
Neg logit contributions | |
cair | -1.768 |
AZ | -1.723 |
Yelp | -1.719 |
Auto | -1.622 |
Olympia | -1.604 |
Token | ) |
Token ID | 1267 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Luke | +1.721 |
src | +1.615 |
sky | +1.602 |
ْ | +1.598 |
Color | +1.576 |
Neg logit contributions | |
cair | -3.031 |
AZ | -2.966 |
Yelp | -2.957 |
Auto | -2.805 |
Olympia | -2.787 |
Token | { |
Token ID | 1391 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Luke | +0.382 |
ْ | +0.362 |
src | +0.356 |
sky | +0.355 |
Color | +0.351 |
Neg logit contributions | |
cair | -0.615 |
AZ | -0.606 |
Yelp | -0.605 |
Auto | -0.575 |
Olympia | -0.566 |
Token | // |
Token ID | 3373 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
AZ | +1.610 |
cair | +1.596 |
Yelp | +1.596 |
Auto | +1.540 |
Olympia | +1.475 |
Neg logit contributions | |
Luke | -1.355 |
ْ | -1.308 |
src | -1.271 |
女 | -1.265 |
Cla | -1.263 |
Token | Time |
Token ID | 3862 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
AZ | +0.671 |
Yelp | +0.670 |
cair | +0.668 |
Auto | +0.640 |
Olympia | +0.612 |
Neg logit contributions | |
Luke | -0.766 |
ْ | -0.740 |
src | -0.728 |
cylinders | -0.727 |
sky | -0.723 |
Token | component |
Token ID | 7515 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Luke | +0.836 |
ْ | +0.806 |
src | +0.798 |
sky | +0.793 |
Color | +0.791 |
Neg logit contributions | |
cair | -0.663 |
AZ | -0.652 |
Yelp | -0.648 |
Auto | -0.604 |
Olympia | -0.592 |