Token | ya |
Token ID | 3972 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
eatures | +0.486 |
heres | +0.446 |
uration | +0.422 |
etheless | +0.420 |
urations | +0.410 |
Neg logit contributions | |
boy | -0.576 |
boys | -0.546 |
PLEASE | -0.524 |
pun | -0.520 |
answered | -0.517 |
Token | bean |
Token ID | 26394 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
boy | +2.651 |
boys | +2.522 |
PLEASE | +2.412 |
answered | +2.373 |
pun | +2.348 |
Neg logit contributions | |
eatures | -2.131 |
heres | -1.915 |
etheless | -1.793 |
uration | -1.777 |
urations | -1.743 |
Token | and |
Token ID | 290 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
eatures | +0.657 |
heres | +0.606 |
uration | +0.570 |
etheless | +0.569 |
urations | +0.553 |
Neg logit contributions | |
boy | -0.783 |
boys | -0.744 |
PLEASE | -0.712 |
pun | -0.705 |
answered | -0.703 |
Token | so |
Token ID | 523 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
boy | +1.547 |
boys | +1.453 |
PLEASE | +1.386 |
pun | +1.364 |
answered | +1.351 |
Neg logit contributions | |
eatures | -1.672 |
heres | -1.534 |
etheless | -1.468 |
uration | -1.464 |
urations | -1.432 |
Token | ya |
Token ID | 3972 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
eatures | +5.985 |
heres | +5.728 |
uration | +5.416 |
etheless | +5.293 |
cluded | +5.232 |
Neg logit contributions | |
boy | -5.426 |
boys | -5.156 |
answered | -4.948 |
PLEASE | -4.919 |
pun | -4.887 |
Token | bean |
Token ID | 26394 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
eatures | +6.165 |
heres | +5.946 |
uration | +5.748 |
occurred | +5.621 |
conjunction | +5.614 |
Neg logit contributions | |
boy | -6.550 |
boys | -6.280 |
answered | -6.115 |
pun | -6.106 |
PLEASE | -5.936 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
occurred | +12.409 |
eatures | +12.383 |
uration | +11.736 |
heres | +11.642 |
guiActiveUnfocused | +11.426 |
Neg logit contributions | |
boy | -12.656 |
boys | -12.061 |
pun | -11.971 |
answered | -11.882 |
bern | -11.702 |
Token | prices |
Token ID | 4536 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
eatures | +3.256 |
heres | +3.030 |
uration | +2.878 |
etheless | +2.790 |
urations | +2.769 |
Neg logit contributions | |
boy | -4.346 |
boys | -4.151 |
pun | -3.967 |
PLEASE | -3.960 |
answered | -3.951 |
Token | kept |
Token ID | 4030 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
eatures | +2.246 |
heres | +2.102 |
uration | +1.984 |
etheless | +1.969 |
cluded | +1.920 |
Neg logit contributions | |
boy | -2.710 |
boys | -2.584 |
PLEASE | -2.455 |
pun | -2.432 |
answered | -2.430 |
Token | Argentina |
Token ID | 16519 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
eatures | +1.730 |
heres | +1.600 |
uration | +1.503 |
etheless | +1.493 |
urations | +1.452 |
Neg logit contributions | |
boy | -2.185 |
boys | -2.082 |
PLEASE | -1.998 |
pun | -1.985 |
answered | -1.976 |
Token | � |
Token ID | 447 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
eatures | +0.710 |
heres | +0.672 |
uration | +0.640 |
etheless | +0.637 |
urations | +0.625 |
Neg logit contributions | |
boy | -0.523 |
boys | -0.490 |
PLEASE | -0.464 |
pun | -0.459 |
answered | -0.457 |
Token | his |
Token ID | 465 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
eatures | +1.499 |
heres | +1.403 |
uration | +1.336 |
etheless | +1.330 |
urations | +1.296 |
Neg logit contributions | |
boy | -1.338 |
boys | -1.263 |
PLEASE | -1.199 |
pun | -1.189 |
answered | -1.185 |
Token | lack |
Token ID | 3092 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eatures | +0.210 |
heres | +0.195 |
uration | +0.185 |
etheless | +0.184 |
urations | +0.180 |
Neg logit contributions | |
boy | -0.206 |
boys | -0.195 |
PLEASE | -0.186 |
pun | -0.185 |
answered | -0.184 |
Token | thereof |
Token ID | 15370 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
eatures | +4.021 |
heres | +3.734 |
uration | +3.541 |
etheless | +3.520 |
urations | +3.436 |
Neg logit contributions | |
boy | -4.206 |
boys | -3.987 |
PLEASE | -3.805 |
pun | -3.772 |
answered | -3.759 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
eatures | +8.972 |
heres | +8.569 |
etheless | +8.056 |
uration | +8.037 |
occurred | +7.959 |
Neg logit contributions | |
boy | -8.507 |
boys | -8.112 |
answered | -7.619 |
PLEASE | -7.561 |
pun | -7.553 |
Token | More |
Token ID | 3125 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
boy | +0.044 |
boys | +0.041 |
answered | +0.039 |
pun | +0.038 |
PLEASE | +0.038 |
Neg logit contributions | |
eatures | -0.060 |
heres | -0.058 |
uration | -0.055 |
etheless | -0.054 |
conjunction | -0.054 |
Token | specifically |
Token ID | 5734 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
eatures | +1.031 |
heres | +0.967 |
uration | +0.915 |
etheless | +0.909 |
urations | +0.886 |
Neg logit contributions | |
boy | -1.020 |
boys | -0.964 |
PLEASE | -0.916 |
pun | -0.913 |
answered | -0.909 |
Token | : |
Token ID | 25 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
eatures | +13.978 |
heres | +13.343 |
etheless | +12.603 |
uration | +12.515 |
occurred | +12.512 |
Neg logit contributions | |
boy | -13.388 |
boys | -12.663 |
answered | -11.845 |
pun | -11.783 |
PLEASE | -11.656 |
Token | 18 |
Token ID | 1248 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
eatures | +1.471 |
heres | +1.378 |
uration | +1.313 |
etheless | +1.308 |
urations | +1.277 |
Neg logit contributions | |
boy | -1.267 |
boys | -1.193 |
PLEASE | -1.129 |
pun | -1.122 |
answered | -1.116 |
Token | yards |
Token ID | 5695 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
eatures | +1.499 |
heres | +1.393 |
uration | +1.328 |
etheless | +1.323 |
urations | +1.290 |
Neg logit contributions | |
boy | -1.459 |
boys | -1.380 |
PLEASE | -1.316 |
pun | -1.302 |
answered | -1.299 |
Token | on |
Token ID | 319 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
boy | +2.152 |
boys | +2.027 |
PLEASE | +1.947 |
pun | +1.933 |
answered | +1.912 |
Neg logit contributions | |
eatures | -2.272 |
heres | -2.094 |
uration | -2.001 |
etheless | -1.987 |
urations | -1.951 |
Token | nine |
Token ID | 5193 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
eatures | +1.080 |
heres | +1.003 |
uration | +0.947 |
etheless | +0.941 |
urations | +0.917 |
Neg logit contributions | |
boy | -1.207 |
boys | -1.146 |
PLEASE | -1.097 |
pun | -1.087 |
answered | -1.087 |
Token | subtly |
Token ID | 37847 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
eatures | +1.047 |
heres | +0.988 |
uration | +0.938 |
etheless | +0.927 |
conjunction | +0.913 |
Neg logit contributions | |
boy | -1.017 |
boys | -0.965 |
PLEASE | -0.914 |
answered | -0.906 |
pun | -0.905 |
Token | — |
Token ID | 960 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
eatures | +4.317 |
heres | +4.196 |
uration | +4.003 |
conjunction | +3.980 |
occurred | +3.937 |
Neg logit contributions | |
boy | -3.968 |
boys | -3.792 |
PLEASE | -3.601 |
answered | -3.543 |
pun | -3.501 |
Token | and |
Token ID | 392 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
boy | +4.051 |
boys | +3.781 |
pun | +3.582 |
answered | +3.510 |
PLEASE | +3.502 |
Neg logit contributions | |
eatures | -5.358 |
heres | -4.906 |
uration | -4.775 |
etheless | -4.724 |
urations | -4.702 |
Token | not |
Token ID | 407 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
eatures | +0.149 |
heres | +0.140 |
uration | +0.133 |
etheless | +0.133 |
urations | +0.129 |
Neg logit contributions | |
boy | -0.128 |
boys | -0.121 |
PLEASE | -0.114 |
answered | -0.114 |
pun | -0.113 |
Token | so |
Token ID | 523 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
boy | +1.441 |
boys | +1.358 |
PLEASE | +1.291 |
pun | +1.279 |
answered | +1.272 |
Neg logit contributions | |
eatures | -1.654 |
heres | -1.545 |
uration | -1.472 |
etheless | -1.464 |
urations | -1.434 |
Token | subtly |
Token ID | 37847 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
eatures | +2.023 |
heres | +1.879 |
uration | +1.797 |
etheless | +1.783 |
conjunction | +1.722 |
Neg logit contributions | |
boy | -2.136 |
boys | -2.032 |
answered | -1.931 |
PLEASE | -1.927 |
pun | -1.913 |
Token | — |
Token ID | 960 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
heres | +14.082 |
eatures | +14.004 |
occurred | +13.444 |
conjunction | +13.432 |
uration | +13.360 |
Neg logit contributions | |
boy | -10.357 |
boys | -9.806 |
answered | -9.072 |
money | -8.893 |
PLEASE | -8.799 |
Token | enc |
Token ID | 12685 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
eatures | +4.589 |
heres | +4.496 |
etheless | +4.204 |
uration | +4.204 |
cluded | +4.144 |
Neg logit contributions | |
boy | -3.315 |
boys | -3.098 |
PLEASE | -3.094 |
sacrific | -2.889 |
answered | -2.846 |
Token | our |
Token ID | 454 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
eatures | +5.830 |
heres | +5.744 |
uration | +5.225 |
cluded | +5.083 |
urations | +4.935 |
Neg logit contributions | |
boy | -10.831 |
boys | -10.434 |
PLEASE | -10.178 |
sacrific | -9.861 |
pun | -9.785 |
Token | aging |
Token ID | 3039 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
eatures | +1.822 |
heres | +1.677 |
uration | +1.579 |
etheless | +1.567 |
urations | +1.525 |
Neg logit contributions | |
boy | -2.364 |
boys | -2.252 |
PLEASE | -2.161 |
pun | -2.144 |
answered | -2.136 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
eatures | +3.798 |
heres | +3.646 |
uration | +3.464 |
etheless | +3.425 |
conjunction | +3.392 |
Neg logit contributions | |
boy | -3.116 |
boys | -2.918 |
PLEASE | -2.788 |
answered | -2.762 |
pun | -2.750 |
Token | removed |
Token ID | 4615 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
eatures | +3.105 |
heres | +2.939 |
etheless | +2.793 |
uration | +2.787 |
cluded | +2.741 |
Neg logit contributions | |
boy | -2.298 |
boys | -2.162 |
PLEASE | -2.048 |
answered | -2.023 |
pun | -2.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
eatures | +1.338 |
heres | +1.249 |
uration | +1.199 |
etheless | +1.198 |
urations | +1.168 |
Neg logit contributions | |
boy | -0.920 |
boys | -0.852 |
PLEASE | -0.811 |
pun | -0.798 |
answered | -0.784 |
Token | physically |
Token ID | 10170 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
boy | +3.582 |
boys | +3.365 |
PLEASE | +3.228 |
pun | +3.191 |
answered | +3.150 |
Neg logit contributions | |
eatures | -4.079 |
heres | -3.784 |
etheless | -3.623 |
uration | -3.617 |
urations | -3.523 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
eatures | +1.040 |
heres | +0.963 |
uration | +0.920 |
etheless | +0.917 |
urations | +0.896 |
Neg logit contributions | |
boy | -0.980 |
boys | -0.924 |
PLEASE | -0.881 |
pun | -0.873 |
answered | -0.867 |
Token | electr |
Token ID | 30880 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
eatures | +1.013 |
heres | +0.950 |
uration | +0.906 |
etheless | +0.900 |
urations | +0.882 |
Neg logit contributions | |
boy | -0.850 |
boys | -0.802 |
PLEASE | -0.758 |
pun | -0.753 |
answered | -0.752 |
Token | ically |
Token ID | 1146 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
eatures | +4.231 |
heres | +3.927 |
uration | +3.701 |
etheless | +3.694 |
urations | +3.577 |
Neg logit contributions | |
boy | -4.942 |
boys | -4.711 |
PLEASE | -4.512 |
pun | -4.456 |
answered | -4.443 |
Token | from |
Token ID | 422 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
eatures | +12.998 |
heres | +12.848 |
cluded | +12.114 |
uration | +11.946 |
conjunction | +11.935 |
Neg logit contributions | |
boy | -12.478 |
boys | -12.143 |
answered | -11.488 |
ocracy | -11.292 |
PLEASE | -11.275 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
eatures | +3.182 |
heres | +2.894 |
uration | +2.650 |
etheless | +2.627 |
conjunction | +2.546 |
Neg logit contributions | |
boy | -5.996 |
boys | -5.769 |
PLEASE | -5.553 |
pun | -5.519 |
answered | -5.517 |
Token | R |
Token ID | 371 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
eatures | +0.644 |
heres | +0.601 |
uration | +0.571 |
etheless | +0.567 |
urations | +0.554 |
Neg logit contributions | |
boy | -0.623 |
boys | -0.589 |
PLEASE | -0.561 |
pun | -0.556 |
answered | -0.554 |
Token | FI |
Token ID | 11674 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
eatures | +3.191 |
heres | +3.001 |
uration | +2.873 |
etheless | +2.860 |
urations | +2.804 |
Neg logit contributions | |
boy | -2.251 |
boys | -2.105 |
PLEASE | -1.986 |
pun | -1.964 |
answered | -1.954 |
Token | source |
Token ID | 2723 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
eatures | +8.335 |
heres | +7.991 |
uration | +7.846 |
conjunction | +7.669 |
occurred | +7.575 |
Neg logit contributions | |
boy | -4.919 |
boys | -4.643 |
answered | -4.408 |
pun | -4.370 |
PLEASE | -4.283 |
Token | , |
Token ID | 837 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
eatures | +8.388 |
heres | +7.948 |
uration | +7.532 |
urations | +7.366 |
etheless | +7.106 |
Neg logit contributions | |
boy | -10.789 |
boys | -10.431 |
PLEASE | -10.004 |
answered | -9.984 |
pun | -9.903 |
Token | depth |
Token ID | 6795 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
eatures | +0.259 |
heres | +0.239 |
uration | +0.228 |
etheless | +0.227 |
urations | +0.221 |
Neg logit contributions | |
boy | -0.273 |
boys | -0.259 |
PLEASE | -0.249 |
pun | -0.244 |
answered | -0.244 |
Token | : |
Token ID | 1058 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
heres | +0.371 |
eatures | +0.363 |
uration | +0.348 |
urations | +0.337 |
cluded | +0.337 |
Neg logit contributions | |
boy | -0.583 |
boys | -0.558 |
sacrific | -0.542 |
answered | -0.539 |
PLEASE | -0.538 |
Token | self |
Token ID | 2116 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
boy | +1.553 |
boys | +1.462 |
PLEASE | +1.411 |
pun | +1.377 |
answered | +1.350 |
Neg logit contributions | |
eatures | -1.270 |
heres | -1.167 |
etheless | -1.130 |
uration | -1.093 |
urations | -1.063 |
Token | . |
Token ID | 764 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
heres | +1.524 |
eatures | +1.429 |
uration | +1.422 |
cluded | +1.379 |
conjunction | +1.359 |
Neg logit contributions | |
boy | -2.966 |
boys | -2.890 |
pun | -2.783 |
answered | -2.778 |
sacrific | -2.772 |
Token | depth |
Token ID | 18053 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
eatures | +2.889 |
heres | +2.685 |
uration | +2.568 |
etheless | +2.547 |
urations | +2.493 |
Neg logit contributions | |
boy | -2.679 |
boys | -2.525 |
PLEASE | -2.397 |
pun | -2.378 |
answered | -2.372 |
Token | , |
Token ID | 837 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
eatures | +12.131 |
heres | +11.715 |
uration | +11.317 |
urations | +10.973 |
conjunction | +10.612 |
Neg logit contributions | |
boy | -12.888 |
boys | -12.627 |
PLEASE | -11.670 |
pun | -11.599 |
answered | -11.593 |
Token | check |
Token ID | 2198 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
eatures | +1.150 |
heres | +1.069 |
uration | +1.017 |
etheless | +1.011 |
urations | +0.987 |
Neg logit contributions | |
boy | -1.137 |
boys | -1.076 |
PLEASE | -1.027 |
pun | -1.016 |
answered | -1.013 |
Token | : |
Token ID | 1058 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
boy | +3.354 |
boys | +3.176 |
PLEASE | +3.001 |
pun | +2.990 |
answered | +2.978 |
Neg logit contributions | |
eatures | -3.156 |
heres | -2.824 |
etheless | -2.729 |
uration | -2.656 |
urations | -2.570 |
Token | self |
Token ID | 2116 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
boy | +4.113 |
PLEASE | +3.841 |
boys | +3.808 |
pun | +3.616 |
answered | +3.584 |
Neg logit contributions | |
eatures | -4.239 |
heres | -3.929 |
etheless | -3.838 |
uration | -3.662 |
urations | -3.637 |
Token | . |
Token ID | 764 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
eatures | +0.379 |
heres | +0.355 |
etheless | +0.337 |
uration | +0.337 |
urations | +0.330 |
Neg logit contributions | |
boy | -0.411 |
boys | -0.380 |
PLEASE | -0.367 |
pun | -0.365 |
answered | -0.359 |
Token | Internet |
Token ID | 4455 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
eatures | +0.737 |
heres | +0.687 |
uration | +0.653 |
etheless | +0.649 |
urations | +0.634 |
Neg logit contributions | |
boy | -0.723 |
boys | -0.684 |
PLEASE | -0.651 |
pun | -0.646 |
answered | -0.644 |
Token | Explorer |
Token ID | 19142 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
boy | +0.111 |
boys | +0.106 |
PLEASE | +0.102 |
pun | +0.101 |
answered | +0.101 |
Neg logit contributions | |
eatures | -0.067 |
heres | -0.060 |
uration | -0.056 |
etheless | -0.056 |
urations | -0.054 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
eatures | +2.145 |
heres | +2.037 |
uration | +1.947 |
etheless | +1.919 |
conjunction | +1.887 |
Neg logit contributions | |
boy | -1.756 |
boys | -1.658 |
pun | -1.561 |
answered | -1.559 |
PLEASE | -1.559 |
Token | ( |
Token ID | 357 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
eatures | +5.910 |
heres | +5.705 |
uration | +5.457 |
conjunction | +5.314 |
etheless | +5.268 |
Neg logit contributions | |
boy | -4.784 |
boys | -4.548 |
answered | -4.373 |
pun | -4.293 |
PLEASE | -4.267 |
Token | IE |
Token ID | 10008 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
eatures | +1.840 |
heres | +1.742 |
uration | +1.675 |
etheless | +1.667 |
urations | +1.639 |
Neg logit contributions | |
boy | -0.995 |
boys | -0.920 |
PLEASE | -0.857 |
pun | -0.846 |
answered | -0.841 |
Token | 6 |
Token ID | 21 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
eatures | +8.772 |
heres | +8.346 |
uration | +8.150 |
etheless | +7.939 |
conjunction | +7.885 |
Neg logit contributions | |
boy | -6.274 |
boys | -5.930 |
answered | -5.828 |
pun | -5.646 |
PLEASE | -5.464 |
Token | ) |
Token ID | 8 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
eatures | +13.560 |
heres | +13.304 |
uration | +12.845 |
conjunction | +12.474 |
cluded | +12.377 |
Neg logit contributions | |
boy | -11.242 |
answered | -10.846 |
boys | -10.803 |
pun | -10.183 |
PLEASE | -10.089 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
eatures | +5.421 |
heres | +5.254 |
uration | +4.991 |
conjunction | +4.957 |
etheless | +4.825 |
Neg logit contributions | |
boy | -4.626 |
boys | -4.417 |
answered | -4.250 |
pun | -4.177 |
PLEASE | -4.105 |
Token | move |
Token ID | 1445 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
eatures | +3.392 |
heres | +3.197 |
uration | +3.028 |
etheless | +2.977 |
conjunction | +2.976 |
Neg logit contributions | |
boy | -3.003 |
boys | -2.865 |
answered | -2.705 |
pun | -2.687 |
PLEASE | -2.666 |
Token | to |
Token ID | 284 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
boy | +0.344 |
boys | +0.322 |
PLEASE | +0.307 |
pun | +0.302 |
answered | +0.298 |
Neg logit contributions | |
eatures | -0.443 |
heres | -0.415 |
uration | -0.397 |
etheless | -0.394 |
urations | -0.389 |
Token | a |
Token ID | 257 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
eatures | +0.509 |
heres | +0.467 |
uration | +0.442 |
etheless | +0.441 |
urations | +0.428 |
Neg logit contributions | |
boy | -0.645 |
boys | -0.612 |
PLEASE | -0.591 |
pun | -0.584 |
answered | -0.579 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
eatures | +3.445 |
heres | +3.173 |
uration | +2.987 |
etheless | +2.965 |
urations | +2.883 |
Neg logit contributions | |
boy | -4.456 |
boys | -4.245 |
PLEASE | -4.070 |
pun | -4.040 |
answered | -4.028 |
Token | players |
Token ID | 1938 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
eatures | +3.149 |
heres | +2.967 |
uration | +2.815 |
etheless | +2.766 |
conjunction | +2.758 |
Neg logit contributions | |
boy | -3.207 |
boys | -3.033 |
PLEASE | -2.892 |
pun | -2.868 |
answered | -2.867 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
boy | +4.934 |
boys | +4.627 |
PLEASE | +4.457 |
pun | +4.456 |
answered | +4.379 |
Neg logit contributions | |
eatures | -5.273 |
heres | -4.792 |
etheless | -4.624 |
uration | -4.589 |
urations | -4.542 |
Token | and |
Token ID | 290 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
boy | +6.592 |
boys | +6.273 |
PLEASE | +6.046 |
pun | +5.919 |
answered | +5.787 |
Neg logit contributions | |
eatures | -4.913 |
heres | -4.423 |
etheless | -4.359 |
uration | -4.235 |
urations | -4.120 |
Token | more |
Token ID | 517 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
boy | +1.461 |
boys | +1.393 |
PLEASE | +1.347 |
pun | +1.326 |
answered | +1.313 |
Neg logit contributions | |
eatures | -1.038 |
heres | -0.944 |
etheless | -0.893 |
uration | -0.890 |
urations | -0.866 |
Token | specifically |
Token ID | 5734 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
eatures | +0.278 |
heres | +0.256 |
uration | +0.242 |
etheless | +0.241 |
urations | +0.235 |
Neg logit contributions | |
boy | -0.327 |
boys | -0.311 |
PLEASE | -0.298 |
pun | -0.295 |
answered | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
eatures | +13.044 |
heres | +12.340 |
uration | +11.894 |
conjunction | +11.661 |
etheless | +11.422 |
Neg logit contributions | |
boy | -11.577 |
answered | -10.864 |
boys | -10.818 |
pun | -10.379 |
bern | -10.316 |
Token | players |
Token ID | 1938 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
eatures | +5.008 |
heres | +4.745 |
uration | +4.520 |
conjunction | +4.476 |
etheless | +4.400 |
Neg logit contributions | |
boy | -4.694 |
boys | -4.406 |
answered | -4.253 |
PLEASE | -4.229 |
pun | -4.226 |
Token | on |
Token ID | 319 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
eatures | +6.523 |
heres | +6.189 |
uration | +5.923 |
etheless | +5.871 |
cluded | +5.802 |
Neg logit contributions | |
boy | -4.555 |
boys | -4.286 |
answered | -4.053 |
pun | -4.048 |
PLEASE | -3.995 |
Token | social |
Token ID | 1919 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
eatures | +2.290 |
heres | +2.078 |
uration | +1.934 |
etheless | +1.918 |
urations | +1.855 |
Neg logit contributions | |
boy | -3.820 |
boys | -3.658 |
PLEASE | -3.523 |
pun | -3.499 |
answered | -3.490 |
Token | media |
Token ID | 2056 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
boy | +4.573 |
boys | +4.192 |
PLEASE | +3.944 |
answered | +3.776 |
pun | +3.762 |
Neg logit contributions | |
eatures | -7.738 |
heres | -7.039 |
etheless | -6.934 |
urations | -6.923 |
uration | -6.872 |
Token | named |
Token ID | 3706 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
boy | +4.247 |
boys | +3.971 |
PLEASE | +3.761 |
pun | +3.689 |
answered | +3.688 |
Neg logit contributions | |
eatures | -4.201 |
heres | -3.792 |
etheless | -3.673 |
uration | -3.657 |
urations | -3.556 |
Token | Jim |
Token ID | 5395 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
eatures | +1.295 |
heres | +1.225 |
uration | +1.173 |
etheless | +1.159 |
urations | +1.144 |
Neg logit contributions | |
boy | -0.887 |
boys | -0.831 |
PLEASE | -0.783 |
pun | -0.776 |
answered | -0.774 |
Token | Hut |
Token ID | 32767 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
boy | +2.289 |
boys | +2.081 |
PLEASE | +1.937 |
pun | +1.930 |
answered | +1.885 |
Neg logit contributions | |
eatures | -3.372 |
heres | -3.108 |
etheless | -3.019 |
uration | -3.007 |
urations | -2.940 |
Token | chens |
Token ID | 29937 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
eatures | +2.270 |
heres | +2.115 |
uration | +2.009 |
etheless | +1.996 |
urations | +1.951 |
Neg logit contributions | |
boy | -2.214 |
boys | -2.094 |
PLEASE | -1.996 |
pun | -1.978 |
answered | -1.970 |
Token | . |
Token ID | 13 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
eatures | +3.733 |
heres | +3.514 |
uration | +3.334 |
etheless | +3.305 |
urations | +3.243 |
Neg logit contributions | |
boy | -3.420 |
boys | -3.249 |
PLEASE | -3.093 |
answered | -3.062 |
pun | -3.049 |
Token | Hut |
Token ID | 32767 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
boy | +1.893 |
boys | +1.766 |
PLEASE | +1.674 |
pun | +1.644 |
answered | +1.630 |
Neg logit contributions | |
eatures | -2.753 |
heres | -2.570 |
etheless | -2.469 |
uration | -2.467 |
urations | -2.408 |
Token | chens |
Token ID | 29937 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
heres | +7.712 |
cluded | +5.846 |
urations | +5.793 |
occurred | +5.778 |
uration | +5.368 |
Neg logit contributions | |
sacrific | -16.493 |
boy | -16.290 |
PLEASE | -15.956 |
bye | -15.280 |
boys | -14.993 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
heres | +8.864 |
occurred | +8.722 |
eatures | +8.507 |
uration | +8.154 |
cluded | +7.909 |
Neg logit contributions | |
boy | -10.162 |
boys | -9.951 |
PLEASE | -9.262 |
pun | -9.137 |
answered | -9.012 |
Token | Josh |
Token ID | 8518 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
boy | +0.218 |
boys | +0.206 |
PLEASE | +0.195 |
pun | +0.194 |
answered | +0.193 |
Neg logit contributions | |
eatures | -0.237 |
heres | -0.219 |
uration | -0.210 |
etheless | -0.209 |
urations | -0.205 |
Token | a |
Token ID | 257 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
boy | +3.744 |
boys | +3.578 |
pun | +3.415 |
PLEASE | +3.402 |
answered | +3.359 |
Neg logit contributions | |
eatures | -2.657 |
heres | -2.365 |
etheless | -2.288 |
uration | -2.265 |
urations | -2.179 |
Token | � |
Token ID | 564 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
boy | +1.924 |
boys | +1.808 |
PLEASE | +1.712 |
pun | +1.695 |
answered | +1.688 |
Neg logit contributions | |
eatures | -2.433 |
heres | -2.283 |
uration | -2.181 |
etheless | -2.168 |
urations | -2.125 |
Token | right |
Token ID | 826 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
eatures | +3.658 |
heres | +3.457 |
uration | +3.333 |
conjunction | +3.326 |
cluded | +3.283 |
Neg logit contributions | |
boy | -2.286 |
boys | -2.135 |
PLEASE | -2.032 |
answered | -2.023 |
pun | -1.965 |
Token | guard |
Token ID | 4860 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
eatures | +0.272 |
heres | +0.256 |
uration | +0.246 |
etheless | +0.245 |
urations | +0.240 |
Neg logit contributions | |
boy | -0.154 |
boys | -0.143 |
PLEASE | -0.133 |
pun | -0.132 |
answered | -0.131 |
Token | as |
Token ID | 355 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
eatures | +4.634 |
heres | +4.459 |
uration | +4.229 |
conjunction | +4.158 |
occurred | +4.136 |
Neg logit contributions | |
boy | -4.131 |
boys | -3.950 |
answered | -3.751 |
PLEASE | -3.726 |
pun | -3.683 |
Token | needed |
Token ID | 2622 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
eatures | +3.617 |
heres | +3.376 |
uration | +3.208 |
etheless | +3.167 |
urations | +3.119 |
Neg logit contributions | |
boy | -3.620 |
boys | -3.433 |
PLEASE | -3.291 |
answered | -3.258 |
pun | -3.245 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
eatures | +0.263 |
heres | +0.241 |
etheless | +0.230 |
uration | +0.229 |
urations | +0.222 |
Neg logit contributions | |
boy | -0.276 |
boys | -0.260 |
PLEASE | -0.249 |
pun | -0.247 |
answered | -0.244 |
Token | Hare |
Token ID | 42285 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
boy | +0.015 |
boys | +0.014 |
PLEASE | +0.014 |
pun | +0.013 |
answered | +0.013 |
Neg logit contributions | |
eatures | -0.024 |
heres | -0.023 |
uration | -0.022 |
etheless | -0.022 |
urations | -0.021 |
Token | wood |
Token ID | 3822 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
heres | +9.043 |
cluded | +7.975 |
occurred | +7.676 |
clude | +6.711 |
urations | +6.710 |
Neg logit contributions | |
sacrific | -15.624 |
Citiz | -13.903 |
PLEASE | -13.613 |
seiz | -12.890 |
pestic | -12.833 |
Token | has |
Token ID | 468 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
occurred | +8.209 |
heres | +8.116 |
eatures | +7.997 |
comprises | +7.655 |
cluded | +7.624 |
Neg logit contributions | |
boy | -10.801 |
boys | -10.526 |
PLEASE | -9.864 |
answered | -9.801 |
pun | -9.543 |
Token | excellent |
Token ID | 6275 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
eatures | +0.928 |
heres | +0.856 |
uration | +0.808 |
etheless | +0.803 |
urations | +0.781 |
Neg logit contributions | |
boy | -1.119 |
boys | -1.064 |
PLEASE | -1.019 |
pun | -1.011 |
answered | -1.007 |
Token | size |
Token ID | 2546 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
eatures | +1.761 |
heres | +1.644 |
uration | +1.572 |
etheless | +1.558 |
conjunction | +1.540 |
Neg logit contributions | |
boy | -1.622 |
boys | -1.536 |
PLEASE | -1.470 |
pun | -1.455 |
answered | -1.454 |
Token | at |
Token ID | 379 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
eatures | +2.570 |
heres | +2.440 |
uration | +2.345 |
etheless | +2.321 |
urations | +2.288 |
Neg logit contributions | |
boy | -1.667 |
boys | -1.560 |
PLEASE | -1.473 |
answered | -1.447 |
pun | -1.447 |
Token | of |
Token ID | 286 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
eatures | +5.109 |
heres | +4.736 |
uration | +4.477 |
etheless | +4.445 |
conjunction | +4.389 |
Neg logit contributions | |
boy | -7.425 |
boys | -7.158 |
pun | -6.826 |
answered | -6.762 |
PLEASE | -6.750 |
Token | these |
Token ID | 777 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
eatures | +5.865 |
heres | +5.393 |
uration | +4.938 |
etheless | +4.868 |
conjunction | +4.820 |
Neg logit contributions | |
boy | -10.405 |
boys | -9.985 |
pun | -9.613 |
PLEASE | -9.555 |
answered | -9.503 |
Token | three |
Token ID | 1115 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
eatures | +5.978 |
heres | +5.556 |
uration | +5.131 |
conjunction | +5.089 |
etheless | +5.055 |
Neg logit contributions | |
boy | -10.355 |
boys | -9.883 |
pun | -9.495 |
answered | -9.450 |
PLEASE | -9.388 |
Token | OS |
Token ID | 7294 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
eatures | +5.048 |
heres | +4.714 |
uration | +4.370 |
conjunction | +4.297 |
etheless | +4.272 |
Neg logit contributions | |
boy | -8.703 |
boys | -8.309 |
pun | -8.009 |
answered | -7.966 |
PLEASE | -7.913 |
Token | I |
Token ID | 40 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
heres | +9.125 |
uration | +8.707 |
conjunction | +8.688 |
urations | +8.624 |
occurred | +8.289 |
Neg logit contributions | |
boy | -7.848 |
sacrific | -7.784 |
boys | -7.230 |
pun | -7.077 |
answered | -6.986 |
Token | layers |
Token ID | 11685 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
eatures | +8.563 |
heres | +8.037 |
uration | +7.668 |
etheless | +7.412 |
urations | +7.356 |
Neg logit contributions | |
boy | -12.628 |
boys | -11.944 |
pun | -11.509 |
answered | -11.386 |
PLEASE | -11.276 |
Token | D |
Token ID | 360 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
eatures | +12.927 |
heres | +12.554 |
uration | +11.990 |
occurred | +11.851 |
conjunction | +11.833 |
Neg logit contributions | |
boy | -11.620 |
boys | -10.887 |
answered | -10.461 |
pun | -10.291 |
PLEASE | -10.005 |
Token | DoS |
Token ID | 46498 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
heres | +5.286 |
uration | +4.903 |
urations | +4.838 |
occurred | +4.722 |
conjunction | +4.601 |
Neg logit contributions | |
sacrific | -7.783 |
boy | -7.703 |
boys | -7.311 |
PLEASE | -7.230 |
answered | -7.175 |
Token | attacks |
Token ID | 3434 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
eatures | +5.697 |
heres | +5.300 |
uration | +5.044 |
urations | +4.891 |
etheless | +4.887 |
Neg logit contributions | |
boy | -8.650 |
boys | -8.184 |
PLEASE | -7.962 |
pun | -7.936 |
answered | -7.860 |
Token | take |
Token ID | 1011 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
eatures | +8.726 |
heres | +8.618 |
occurred | +8.573 |
uration | +8.234 |
conjunction | +8.023 |
Neg logit contributions | |
boy | -9.215 |
boys | -8.819 |
answered | -8.576 |
pun | -8.373 |
bern | -8.294 |
Token | many |
Token ID | 867 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
eatures | +4.275 |
heres | +4.084 |
uration | +3.823 |
conjunction | +3.783 |
etheless | +3.752 |
Neg logit contributions | |
boy | -4.490 |
boys | -4.227 |
PLEASE | -4.075 |
pun | -4.039 |
answered | -4.022 |
Token | limited |
Token ID | 3614 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
eatures | +3.806 |
heres | +3.599 |
uration | +3.456 |
etheless | +3.401 |
urations | +3.365 |
Neg logit contributions | |
boy | -3.358 |
boys | -3.167 |
pun | -2.993 |
PLEASE | -2.989 |
answered | -2.981 |
Token | visibility |
Token ID | 20742 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
eatures | +2.918 |
heres | +2.753 |
uration | +2.654 |
conjunction | +2.594 |
etheless | +2.593 |
Neg logit contributions | |
boy | -3.089 |
boys | -2.936 |
PLEASE | -2.778 |
pun | -2.766 |
answered | -2.740 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
boy | +0.533 |
boys | +0.500 |
PLEASE | +0.474 |
pun | +0.469 |
answered | +0.466 |
Neg logit contributions | |
eatures | -0.682 |
heres | -0.639 |
uration | -0.608 |
etheless | -0.608 |
urations | -0.594 |
Token | D |
Token ID | 360 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
eatures | +2.722 |
heres | +2.556 |
uration | +2.405 |
etheless | +2.376 |
urations | +2.324 |
Neg logit contributions | |
boy | -3.302 |
boys | -3.135 |
PLEASE | -2.999 |
pun | -2.982 |
answered | -2.962 |
Token | DoS |
Token ID | 46498 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
heres | +4.564 |
uration | +4.326 |
urations | +4.250 |
occurred | +4.126 |
conjunction | +3.946 |
Neg logit contributions | |
boy | -6.640 |
sacrific | -6.603 |
boys | -6.305 |
PLEASE | -6.233 |
answered | -6.203 |
Token | gaps |
Token ID | 17332 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
eatures | +7.602 |
heres | +7.308 |
uration | +7.017 |
occurred | +7.007 |
conjunction | +6.840 |
Neg logit contributions | |
boy | -8.181 |
boys | -7.633 |
PLEASE | -7.524 |
pun | -7.353 |
answered | -7.303 |
Token | without |
Token ID | 1231 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
heres | +13.645 |
occurred | +13.358 |
eatures | +13.048 |
uration | +12.704 |
cluded | +12.519 |
Neg logit contributions | |
boy | -9.615 |
boys | -8.986 |
bern | -8.241 |
PLEASE | -8.106 |
answered | -8.046 |
Token | in |
Token ID | 287 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
eatures | +4.617 |
heres | +4.357 |
uration | +4.136 |
etheless | +4.116 |
conjunction | +4.043 |
Neg logit contributions | |
boy | -4.943 |
boys | -4.652 |
PLEASE | -4.398 |
pun | -4.398 |
answered | -4.356 |
Token | - |
Token ID | 12 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
eatures | +3.139 |
heres | +2.931 |
uration | +2.789 |
etheless | +2.772 |
urations | +2.711 |
Neg logit contributions | |
boy | -2.888 |
boys | -2.728 |
PLEASE | -2.595 |
pun | -2.571 |
answered | -2.560 |
Token | depth |
Token ID | 18053 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
boy | +3.968 |
boys | +3.702 |
answered | +3.515 |
pun | +3.443 |
PLEASE | +3.403 |
Neg logit contributions | |
eatures | -5.236 |
heres | -4.692 |
etheless | -4.691 |
uration | -4.516 |
urations | -4.470 |
Token | analysis |
Token ID | 3781 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
eatures | +3.432 |
heres | +3.205 |
uration | +3.083 |
conjunction | +3.039 |
etheless | +3.002 |
Neg logit contributions | |
boy | -3.720 |
boys | -3.521 |
PLEASE | -3.333 |
pun | -3.316 |
answered | -3.296 |
Token | - |
Token ID | 12 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
boy | +0.902 |
boys | +0.846 |
PLEASE | +0.808 |
pun | +0.799 |
answered | +0.786 |
Neg logit contributions | |
eatures | -0.972 |
heres | -0.887 |
etheless | -0.855 |
uration | -0.846 |
urations | -0.822 |
Token | breaking |
Token ID | 13395 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
boy | +1.384 |
boys | +1.287 |
pun | +1.216 |
PLEASE | +1.200 |
answered | +1.176 |
Neg logit contributions | |
eatures | -1.983 |
heres | -1.817 |
etheless | -1.773 |
uration | -1.759 |
urations | -1.717 |
Token | � |
Token ID | 447 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
eatures | +3.948 |
heres | +3.742 |
uration | +3.585 |
etheless | +3.570 |
urations | +3.504 |
Neg logit contributions | |
boy | -2.464 |
boys | -2.297 |
PLEASE | -2.147 |
pun | -2.128 |
answered | -2.124 |
Token | � |
Token ID | 251 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
eatures | +3.063 |
heres | +2.839 |
uration | +2.694 |
etheless | +2.675 |
urations | +2.606 |
Neg logit contributions | |
boy | -3.406 |
boys | -3.235 |
PLEASE | -3.087 |
pun | -3.059 |
answered | -3.047 |
Token | , |
Token ID | 11 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
eatures | +5.665 |
heres | +5.371 |
uration | +5.120 |
etheless | +5.078 |
urations | +4.989 |
Neg logit contributions | |
boy | -4.210 |
boys | -3.939 |
PLEASE | -3.714 |
answered | -3.684 |
pun | -3.653 |
Token | Rou |
Token ID | 13876 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
eatures | +1.609 |
heres | +1.495 |
uration | +1.419 |
etheless | +1.411 |
urations | +1.378 |
Neg logit contributions | |
boy | -1.629 |
boys | -1.541 |
PLEASE | -1.473 |
pun | -1.461 |
answered | -1.453 |
Token | pen |
Token ID | 3617 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
heres | +9.660 |
cluded | +9.182 |
uration | +8.828 |
occurred | +8.501 |
urations | +8.428 |
Neg logit contributions | |
sacrific | -14.190 |
boys | -12.791 |
boy | -12.757 |
PLEASE | -12.243 |
answered | -11.801 |
Token | ian |
Token ID | 666 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
heres | +3.263 |
uration | +2.947 |
cluded | +2.860 |
occurred | +2.683 |
urations | +2.551 |
Neg logit contributions | |
sacrific | -12.390 |
PLEASE | -11.789 |
boy | -11.748 |
boys | -11.729 |
answered | -11.508 |
Token | � |
Token ID | 447 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
eatures | +8.391 |
heres | +8.080 |
uration | +7.591 |
cluded | +7.520 |
occurred | +7.505 |
Neg logit contributions | |
boy | -7.285 |
boys | -6.964 |
PLEASE | -6.565 |
pun | -6.419 |
answered | -6.322 |
Token | � |
Token ID | 247 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
eatures | +1.848 |
heres | +1.847 |
uration | +1.781 |
cluded | +1.677 |
urations | +1.676 |
Neg logit contributions | |
boy | -2.838 |
boys | -2.723 |
PLEASE | -2.644 |
pun | -2.593 |
sacrific | -2.592 |
Token | s |
Token ID | 82 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
eatures | +4.515 |
heres | +4.230 |
uration | +4.031 |
etheless | +4.002 |
urations | +3.922 |
Neg logit contributions | |
boy | -3.847 |
boys | -3.625 |
PLEASE | -3.445 |
pun | -3.407 |
answered | -3.387 |
Token | officers |
Token ID | 3790 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eatures | +2.604 |
heres | +2.490 |
uration | +2.328 |
conjunction | +2.315 |
cluded | +2.292 |
Neg logit contributions | |
boy | -2.660 |
boys | -2.526 |
PLEASE | -2.434 |
pun | -2.428 |
answered | -2.401 |
Token | learned |
Token ID | 4499 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
eatures | +3.370 |
heres | +3.291 |
occurred | +3.143 |
cluded | +3.034 |
uration | +3.033 |
Neg logit contributions | |
boy | -4.428 |
boys | -4.237 |
PLEASE | -4.074 |
pun | -4.037 |
bern | -3.970 |
Token | his |
Token ID | 465 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
boy | +0.862 |
boys | +0.814 |
PLEASE | +0.774 |
answered | +0.760 |
pun | +0.754 |
Neg logit contributions | |
eatures | -0.858 |
heres | -0.792 |
uration | -0.761 |
etheless | -0.753 |
urations | -0.740 |
Token | name |
Token ID | 1438 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
boy | +1.392 |
boys | +1.304 |
PLEASE | +1.233 |
pun | +1.217 |
answered | +1.211 |
Neg logit contributions | |
eatures | -1.816 |
heres | -1.693 |
uration | -1.620 |
etheless | -1.619 |
urations | -1.580 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
boy | +4.912 |
boys | +4.511 |
PLEASE | +4.469 |
pun | +4.366 |
answered | +4.305 |
Neg logit contributions | |
eatures | -4.289 |
etheless | -3.724 |
heres | -3.672 |
uration | -3.555 |
guiActiveUnfocused | -3.514 |
Token | Di |
Token ID | 6031 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
boy | +1.161 |
boys | +1.096 |
PLEASE | +1.050 |
answered | +1.033 |
pun | +1.024 |
Neg logit contributions | |
eatures | -1.082 |
heres | -0.984 |
etheless | -0.946 |
uration | -0.944 |
urations | -0.919 |
Token | allo |
Token ID | 49457 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
heres | +6.991 |
cluded | +6.337 |
aga | +6.251 |
uration | +6.176 |
agic | +6.042 |
Neg logit contributions | |
sacrific | -14.682 |
PLEASE | -14.034 |
pun | -13.792 |
boys | -13.590 |
boy | -13.571 |
Token | 's |
Token ID | 338 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
heres | +8.550 |
occurred | +8.283 |
eatures | +7.879 |
uration | +7.658 |
cluded | +7.640 |
Neg logit contributions | |
boy | -8.817 |
boys | -8.665 |
pun | -8.181 |
PLEASE | -8.147 |
answered | -8.069 |
Token | lawyer |
Token ID | 6853 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
eatures | +4.741 |
heres | +4.607 |
uration | +4.337 |
occurred | +4.334 |
conjunction | +4.329 |
Neg logit contributions | |
boy | -3.829 |
boys | -3.677 |
pun | -3.600 |
PLEASE | -3.540 |
answered | -3.537 |
Token | said |
Token ID | 531 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
boy | +5.577 |
boys | +5.213 |
PLEASE | +5.017 |
answered | +4.963 |
pun | +4.950 |
Neg logit contributions | |
eatures | -5.206 |
etheless | -4.665 |
heres | -4.563 |
uration | -4.439 |
urations | -4.358 |
Token | in |
Token ID | 287 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
boy | +1.278 |
boys | +1.213 |
PLEASE | +1.141 |
answered | +1.108 |
pun | +1.097 |
Neg logit contributions | |
eatures | -1.153 |
heres | -1.033 |
etheless | -1.017 |
uration | -1.012 |
urations | -1.000 |
Token | ( |
Token ID | 357 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
boy | +3.029 |
boys | +2.851 |
pun | +2.754 |
PLEASE | +2.734 |
answered | +2.713 |
Neg logit contributions | |
eatures | -2.698 |
heres | -2.403 |
uration | -2.317 |
etheless | -2.308 |
urations | -2.270 |
Token | certain |
Token ID | 39239 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
boy | +2.932 |
boys | +2.761 |
pun | +2.640 |
answered | +2.591 |
PLEASE | +2.567 |
Neg logit contributions | |
eatures | -3.584 |
heres | -3.265 |
uration | -3.174 |
etheless | -3.161 |
urations | -3.100 |
Token | ly |
Token ID | 306 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
eatures | +3.241 |
heres | +3.034 |
etheless | +2.885 |
uration | +2.869 |
conjunction | +2.785 |
Neg logit contributions | |
boy | -3.347 |
boys | -3.151 |
PLEASE | -3.043 |
answered | -2.999 |
pun | -2.993 |
Token | but |
Token ID | 475 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
eatures | +4.467 |
heres | +4.253 |
uration | +3.986 |
etheless | +3.957 |
conjunction | +3.921 |
Neg logit contributions | |
boy | -4.476 |
boys | -4.240 |
PLEASE | -4.008 |
answered | -3.979 |
pun | -3.969 |
Token | hardly |
Token ID | 8941 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
eatures | +2.419 |
heres | +2.271 |
uration | +2.153 |
etheless | +2.141 |
urations | +2.090 |
Neg logit contributions | |
boy | -2.300 |
boys | -2.172 |
PLEASE | -2.064 |
pun | -2.047 |
answered | -2.042 |
Token | exclusively |
Token ID | 11541 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
eatures | +4.985 |
heres | +4.759 |
uration | +4.504 |
etheless | +4.488 |
conjunction | +4.466 |
Neg logit contributions | |
boy | -4.907 |
boys | -4.681 |
answered | -4.376 |
pun | -4.349 |
PLEASE | -4.344 |
Token | to |
Token ID | 284 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
eatures | +12.382 |
heres | +12.267 |
occurred | +11.719 |
cluded | +11.531 |
conjunction | +11.510 |
Neg logit contributions | |
boy | -10.371 |
boys | -9.789 |
sacrific | -9.203 |
PLEASE | -9.190 |
answered | -9.043 |
Token | female |
Token ID | 4048 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
eatures | +2.970 |
heres | +2.809 |
uration | +2.659 |
etheless | +2.621 |
conjunction | +2.582 |
Neg logit contributions | |
boy | -2.778 |
boys | -2.617 |
PLEASE | -2.492 |
pun | -2.473 |
answered | -2.467 |
Token | veterans |
Token ID | 11255 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
boy | +5.631 |
boys | +5.365 |
PLEASE | +5.054 |
answered | +4.944 |
pun | +4.926 |
Neg logit contributions | |
eatures | -6.808 |
heres | -6.235 |
etheless | -6.028 |
uration | -5.958 |
urations | -5.882 |
Token | and |
Token ID | 290 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
boy | +6.803 |
boys | +6.440 |
PLEASE | +6.082 |
pun | +6.027 |
answered | +5.907 |
Neg logit contributions | |
eatures | -7.260 |
heres | -6.532 |
etheless | -6.346 |
uration | -6.313 |
urations | -6.206 |
Token | female |
Token ID | 4048 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
boy | +0.892 |
boys | +0.846 |
PLEASE | +0.806 |
pun | +0.798 |
answered | +0.793 |
Neg logit contributions | |
eatures | -0.872 |
heres | -0.804 |
uration | -0.766 |
etheless | -0.764 |
urations | -0.745 |
Token | shared |
Token ID | 4888 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
eatures | +1.602 |
heres | +1.467 |
uration | +1.382 |
etheless | +1.371 |
urations | +1.333 |
Neg logit contributions | |
boy | -2.194 |
boys | -2.092 |
PLEASE | -2.012 |
pun | -1.994 |
answered | -1.987 |
Token | data |
Token ID | 1366 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
eatures | +6.448 |
heres | +6.238 |
conjunction | +5.819 |
uration | +5.768 |
occurred | +5.756 |
Neg logit contributions | |
boy | -6.861 |
boys | -6.520 |
pun | -6.208 |
PLEASE | -6.159 |
answered | -6.148 |
Token | that |
Token ID | 326 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
boy | +0.429 |
boys | +0.408 |
PLEASE | +0.390 |
pun | +0.384 |
answered | +0.381 |
Neg logit contributions | |
eatures | -0.399 |
heres | -0.361 |
uration | -0.345 |
etheless | -0.344 |
urations | -0.335 |
Token | may |
Token ID | 743 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
eatures | +2.657 |
heres | +2.433 |
uration | +2.266 |
etheless | +2.243 |
urations | +2.176 |
Neg logit contributions | |
boy | -4.124 |
boys | -3.944 |
PLEASE | -3.793 |
pun | -3.770 |
answered | -3.760 |
Token | or |
Token ID | 393 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
eatures | +1.796 |
heres | +1.683 |
uration | +1.607 |
etheless | +1.600 |
urations | +1.567 |
Neg logit contributions | |
boy | -1.420 |
boys | -1.334 |
PLEASE | -1.264 |
pun | -1.251 |
answered | -1.244 |
Token | may |
Token ID | 743 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
eatures | +0.240 |
heres | +0.210 |
etheless | +0.203 |
uration | +0.198 |
urations | +0.194 |
Neg logit contributions | |
boy | -0.331 |
boys | -0.313 |
PLEASE | -0.304 |
pun | -0.297 |
answered | -0.296 |
Token | not |
Token ID | 407 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
heres | +7.648 |
occurred | +7.248 |
conjunction | +7.180 |
cluded | +6.654 |
bidden | +6.599 |
Neg logit contributions | |
sacrific | -15.259 |
answered | -14.265 |
boy | -14.042 |
boys | -13.909 |
bern | -13.357 |
Token | be |
Token ID | 307 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
eatures | +6.410 |
heres | +6.101 |
uration | +5.780 |
etheless | +5.751 |
conjunction | +5.600 |
Neg logit contributions | |
boy | -5.966 |
boys | -5.666 |
answered | -5.395 |
pun | -5.353 |
PLEASE | -5.321 |
Token | reach |
Token ID | 3151 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
eatures | +2.819 |
heres | +2.653 |
etheless | +2.454 |
uration | +2.450 |
conjunction | +2.399 |
Neg logit contributions | |
boy | -3.827 |
boys | -3.674 |
pun | -3.509 |
PLEASE | -3.503 |
answered | -3.489 |
Token | able |
Token ID | 540 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
boy | +0.311 |
boys | +0.289 |
PLEASE | +0.270 |
pun | +0.268 |
answered | +0.265 |
Neg logit contributions | |
eatures | -0.498 |
heres | -0.466 |
uration | -0.450 |
etheless | -0.447 |
urations | -0.440 |
Token | from |
Token ID | 422 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
eatures | +2.059 |
heres | +1.957 |
uration | +1.853 |
etheless | +1.842 |
conjunction | +1.806 |
Neg logit contributions | |
boy | -1.840 |
boys | -1.744 |
pun | -1.641 |
PLEASE | -1.636 |
answered | -1.634 |
Token | wave |
Token ID | 6769 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
eatures | +3.146 |
heres | +2.978 |
uration | +2.839 |
conjunction | +2.773 |
etheless | +2.721 |
Neg logit contributions | |
boy | -3.679 |
boys | -3.507 |
answered | -3.350 |
PLEASE | -3.338 |
pun | -3.333 |
Token | fluctuations |
Token ID | 31101 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
eatures | +1.482 |
heres | +1.365 |
uration | +1.288 |
etheless | +1.281 |
urations | +1.247 |
Neg logit contributions | |
boy | -1.826 |
boys | -1.737 |
PLEASE | -1.664 |
pun | -1.652 |
answered | -1.645 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
eatures | +8.198 |
heres | +8.147 |
occurred | +7.731 |
uration | +7.694 |
conjunction | +7.626 |
Neg logit contributions | |
boy | -5.727 |
boys | -5.422 |
PLEASE | -5.118 |
answered | -5.020 |
pun | -4.931 |
Token | These |
Token ID | 2312 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
eatures | +0.335 |
heres | +0.315 |
uration | +0.302 |
etheless | +0.300 |
urations | +0.294 |
Neg logit contributions | |
boy | -0.236 |
boys | -0.220 |
PLEASE | -0.208 |
pun | -0.205 |
answered | -0.204 |
Token | periodic |
Token ID | 27458 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
eatures | +5.566 |
heres | +5.263 |
uration | +5.003 |
occurred | +4.971 |
conjunction | +4.902 |
Neg logit contributions | |
boy | -7.759 |
boys | -7.425 |
answered | -7.144 |
pun | -7.136 |
PLEASE | -7.024 |
Token | fluctuations |
Token ID | 31101 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
eatures | +5.012 |
heres | +4.797 |
uration | +4.540 |
conjunction | +4.481 |
occurred | +4.350 |
Neg logit contributions | |
boy | -7.393 |
boys | -7.072 |
PLEASE | -6.852 |
answered | -6.829 |
pun | -6.819 |
Token | in |
Token ID | 287 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
occurred | +12.050 |
heres | +11.517 |
eatures | +11.205 |
conjunction | +11.045 |
uration | +10.907 |
Neg logit contributions | |
boy | -10.767 |
boys | -10.399 |
answered | -10.041 |
bern | -9.766 |
pun | -9.553 |
Token | the |
Token ID | 262 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
eatures | +7.129 |
heres | +6.881 |
conjunction | +6.496 |
uration | +6.487 |
etheless | +6.277 |
Neg logit contributions | |
boy | -8.286 |
boys | -7.934 |
PLEASE | -7.563 |
pun | -7.552 |
answered | -7.509 |
Token | distribution |
Token ID | 6082 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
eatures | +2.287 |
heres | +2.173 |
uration | +2.056 |
etheless | +2.011 |
conjunction | +1.994 |
Neg logit contributions | |
boy | -2.711 |
boys | -2.582 |
PLEASE | -2.463 |
pun | -2.459 |
answered | -2.451 |
Token | of |
Token ID | 286 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
eatures | +1.894 |
heres | +1.763 |
uration | +1.679 |
etheless | +1.675 |
urations | +1.639 |
Neg logit contributions | |
boy | -1.686 |
boys | -1.587 |
PLEASE | -1.510 |
pun | -1.494 |
answered | -1.482 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
eatures | +2.665 |
heres | +2.473 |
uration | +2.336 |
etheless | +2.316 |
urations | +2.260 |
Neg logit contributions | |
boy | -3.088 |
boys | -2.934 |
PLEASE | -2.808 |
pun | -2.787 |
answered | -2.777 |
Token | might |
Token ID | 1244 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
boy | +3.322 |
boys | +3.137 |
PLEASE | +3.005 |
pun | +2.961 |
answered | +2.932 |
Neg logit contributions | |
eatures | -3.327 |
heres | -3.069 |
uration | -2.912 |
etheless | -2.906 |
urations | -2.842 |
Token | imagine |
Token ID | 5967 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
eatures | +3.749 |
heres | +3.584 |
uration | +3.498 |
etheless | +3.447 |
conjunction | +3.384 |
Neg logit contributions | |
boy | -2.245 |
boys | -2.107 |
answered | -1.988 |
pun | -1.948 |
PLEASE | -1.933 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
eatures | +4.755 |
heres | +4.369 |
uration | +4.111 |
etheless | +4.086 |
urations | +3.972 |
Neg logit contributions | |
boy | -6.254 |
boys | -5.959 |
PLEASE | -5.717 |
pun | -5.672 |
answered | -5.649 |
Token | And |
Token ID | 843 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
boy | +0.282 |
boys | +0.267 |
PLEASE | +0.256 |
pun | +0.253 |
answered | +0.251 |
Neg logit contributions | |
eatures | -0.257 |
heres | -0.237 |
etheless | -0.225 |
uration | -0.225 |
urations | -0.219 |
Token | ro |
Token ID | 305 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
heres | +5.044 |
uration | +4.677 |
eatures | +4.634 |
urations | +4.555 |
ulic | +4.382 |
Neg logit contributions | |
sacrific | -5.351 |
boy | -5.247 |
boys | -5.139 |
answered | -5.073 |
PLEASE | -5.054 |
Token | Pan |
Token ID | 15730 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
eatures | +10.159 |
heres | +9.680 |
uration | +9.245 |
etheless | +9.167 |
urations | +9.016 |
Neg logit contributions | |
boy | -6.302 |
boys | -5.928 |
PLEASE | -5.581 |
answered | -5.534 |
pun | -5.451 |
Token | takes |
Token ID | 2753 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
heres | +10.941 |
eatures | +10.708 |
uration | +10.130 |
occurred | +10.102 |
comprises | +9.911 |
Neg logit contributions | |
boy | -11.873 |
answered | -11.660 |
boys | -11.615 |
PLEASE | -10.968 |
bern | -10.962 |
Token | photos |
Token ID | 5205 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
eatures | +1.945 |
heres | +1.812 |
uration | +1.709 |
etheless | +1.664 |
conjunction | +1.650 |
Neg logit contributions | |
boy | -2.342 |
boys | -2.234 |
answered | -2.132 |
pun | -2.130 |
PLEASE | -2.129 |
Token | that |
Token ID | 326 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
boy | +3.639 |
boys | +3.399 |
PLEASE | +3.228 |
pun | +3.222 |
answered | +3.145 |
Neg logit contributions | |
eatures | -4.510 |
heres | -4.131 |
etheless | -4.024 |
uration | -3.962 |
urations | -3.889 |
Token | you |
Token ID | 345 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
eatures | +1.507 |
heres | +1.419 |
uration | +1.356 |
etheless | +1.336 |
urations | +1.315 |
Neg logit contributions | |
boy | -1.231 |
boys | -1.161 |
answered | -1.094 |
PLEASE | -1.094 |
pun | -1.087 |
Token | 've |
Token ID | 1053 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
boy | +2.409 |
boys | +2.267 |
PLEASE | +2.148 |
pun | +2.128 |
answered | +2.119 |
Neg logit contributions | |
eatures | -2.934 |
heres | -2.749 |
uration | -2.623 |
etheless | -2.609 |
urations | -2.555 |
Token | we |
Token ID | 356 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
eatures | +4.556 |
heres | +4.281 |
uration | +4.158 |
etheless | +4.014 |
occurred | +3.996 |
Neg logit contributions | |
boy | -4.695 |
boys | -4.450 |
PLEASE | -4.212 |
pun | -4.211 |
answered | -4.198 |
Token | need |
Token ID | 761 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
boy | +0.168 |
boys | +0.159 |
pun | +0.151 |
answered | +0.151 |
PLEASE | +0.151 |
Neg logit contributions | |
eatures | -0.176 |
heres | -0.166 |
uration | -0.158 |
etheless | -0.156 |
conjunction | -0.153 |
Token | called |
Token ID | 1444 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
boy | +0.046 |
boys | +0.043 |
PLEASE | +0.040 |
answered | +0.040 |
pun | +0.039 |
Neg logit contributions | |
eatures | -0.080 |
heres | -0.075 |
uration | -0.072 |
etheless | -0.072 |
urations | -0.071 |
Token | pop |
Token ID | 1461 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
eatures | +5.301 |
heres | +4.970 |
uration | +4.787 |
etheless | +4.689 |
conjunction | +4.689 |
Neg logit contributions | |
boy | -4.269 |
boys | -4.056 |
answered | -3.788 |
pun | -3.777 |
PLEASE | -3.771 |
Token | / |
Token ID | 14 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
boy | +2.594 |
boys | +2.424 |
pun | +2.301 |
PLEASE | +2.279 |
answered | +2.261 |
Neg logit contributions | |
eatures | -2.834 |
heres | -2.619 |
etheless | -2.544 |
uration | -2.472 |
urations | -2.409 |
Token | pop |
Token ID | 12924 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
boy | +0.290 |
boys | +0.271 |
pun | +0.256 |
PLEASE | +0.255 |
answered | +0.253 |
Neg logit contributions | |
eatures | -0.384 |
heres | -0.358 |
etheless | -0.344 |
uration | -0.343 |
urations | -0.335 |
Token | / |
Token ID | 14 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
eatures | +13.953 |
heres | +13.145 |
uration | +12.954 |
conjunction | +12.813 |
urations | +12.461 |
Neg logit contributions | |
boy | -8.711 |
boys | -8.514 |
PLEASE | -8.076 |
answered | -8.059 |
pun | -7.639 |
Token | ret |
Token ID | 1186 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
eatures | +5.034 |
heres | +4.835 |
uration | +4.612 |
etheless | +4.539 |
urations | +4.489 |
Neg logit contributions | |
boy | -3.426 |
boys | -3.231 |
PLEASE | -3.068 |
answered | -2.990 |
pun | -2.947 |
Token | . |
Token ID | 764 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
eatures | +0.614 |
heres | +0.567 |
etheless | +0.537 |
uration | +0.536 |
urations | +0.522 |
Neg logit contributions | |
boy | -0.621 |
boys | -0.587 |
PLEASE | -0.559 |
pun | -0.554 |
answered | -0.550 |
Token | In |
Token ID | 554 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
eatures | +3.441 |
heres | +3.363 |
uration | +3.191 |
conjunction | +3.135 |
occurred | +3.106 |
Neg logit contributions | |
boy | -2.698 |
boys | -2.557 |
answered | -2.406 |
pun | -2.368 |
PLEASE | -2.298 |
Token | this |
Token ID | 428 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eatures | +7.336 |
heres | +7.004 |
conjunction | +6.637 |
cluded | +6.518 |
uration | +6.507 |
Neg logit contributions | |
boy | -8.460 |
boys | -8.126 |
answered | -7.702 |
PLEASE | -7.694 |
pun | -7.553 |
Token | server |
Token ID | 4382 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
eatures | +1.617 |
heres | +1.517 |
uration | +1.440 |
etheless | +1.426 |
conjunction | +1.398 |
Neg logit contributions | |
boy | -1.614 |
boys | -1.534 |
pun | -1.456 |
PLEASE | -1.447 |
answered | -1.435 |
Token | . |
Token ID | 13 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
boy | +0.884 |
boys | +0.835 |
PLEASE | +0.800 |
answered | +0.789 |
pun | +0.789 |
Neg logit contributions | |
eatures | -0.849 |
heres | -0.784 |
uration | -0.742 |
etheless | -0.739 |
urations | -0.724 |
Token | This |
Token ID | 770 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
eatures | +0.195 |
heres | +0.185 |
uration | +0.177 |
etheless | +0.175 |
urations | +0.173 |
Neg logit contributions | |
boy | -0.147 |
boys | -0.138 |
pun | -0.129 |
answered | -0.129 |
PLEASE | -0.128 |
Token | I |
Token ID | 314 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
eatures | +5.632 |
heres | +5.235 |
uration | +5.006 |
occurred | +4.934 |
conjunction | +4.929 |
Neg logit contributions | |
boy | -7.053 |
boys | -6.774 |
pun | -6.510 |
answered | -6.509 |
PLEASE | -6.354 |
Token | PC |
Token ID | 5662 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
eatures | +2.489 |
heres | +2.338 |
uration | +2.234 |
etheless | +2.221 |
urations | +2.176 |
Neg logit contributions | |
boy | -1.929 |
boys | -1.812 |
PLEASE | -1.714 |
pun | -1.695 |
answered | -1.687 |
Token | primitive |
Token ID | 20049 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
eatures | +7.250 |
heres | +6.952 |
uration | +6.772 |
conjunction | +6.526 |
occurred | +6.480 |
Neg logit contributions | |
boy | -8.543 |
boys | -8.231 |
answered | -8.098 |
pun | -7.942 |
PLEASE | -7.811 |
Token | is |
Token ID | 318 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
heres | +11.193 |
eatures | +11.045 |
occurred | +10.791 |
comprises | +10.645 |
uration | +10.470 |
Neg logit contributions | |
boy | -11.381 |
boys | -10.915 |
answered | -10.780 |
pun | -10.503 |
bern | -10.108 |
Token | called |
Token ID | 1444 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
eatures | +3.061 |
heres | +2.865 |
uration | +2.696 |
etheless | +2.682 |
conjunction | +2.636 |
Neg logit contributions | |
boy | -3.627 |
boys | -3.464 |
PLEASE | -3.293 |
answered | -3.285 |
pun | -3.270 |
Token | Remote |
Token ID | 21520 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
eatures | +4.247 |
heres | +3.935 |
uration | +3.755 |
etheless | +3.692 |
conjunction | +3.669 |
Neg logit contributions | |
boy | -4.617 |
boys | -4.420 |
pun | -4.187 |
PLEASE | -4.155 |
answered | -4.151 |
Token | Procedure |
Token ID | 34997 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
boy | +0.131 |
boys | +0.124 |
PLEASE | +0.118 |
pun | +0.117 |
answered | +0.116 |
Neg logit contributions | |
eatures | -0.146 |
heres | -0.136 |
uration | -0.130 |
etheless | -0.129 |
urations | -0.126 |
Token | Call |
Token ID | 4889 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
eatures | +1.220 |
heres | +1.155 |
uration | +1.109 |
etheless | +1.101 |
urations | +1.083 |
Neg logit contributions | |
boy | -0.752 |
boys | -0.702 |
PLEASE | -0.653 |
pun | -0.650 |
answered | -0.647 |
Token | onen |
Token ID | 34481 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
boy | +0.628 |
boys | +0.562 |
pun | +0.505 |
PLEASE | +0.491 |
answered | +0.474 |
Neg logit contributions | |
eatures | -1.773 |
heres | -1.641 |
etheless | -1.618 |
uration | -1.607 |
urations | -1.579 |
Token | ( |
Token ID | 357 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
eatures | +1.715 |
heres | +1.564 |
uration | +1.496 |
etheless | +1.485 |
urations | +1.457 |
Neg logit contributions | |
boy | -1.907 |
boys | -1.779 |
pun | -1.715 |
PLEASE | -1.715 |
answered | -1.674 |
Token | who |
Token ID | 8727 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
boy | +0.141 |
boys | +0.126 |
PLEASE | +0.113 |
pun | +0.111 |
answered | +0.110 |
Neg logit contributions | |
eatures | -0.428 |
heres | -0.407 |
uration | -0.394 |
etheless | -0.393 |
urations | -0.387 |
Token | may |
Token ID | 743 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
eatures | +3.448 |
heres | +3.240 |
uration | +3.017 |
etheless | +2.945 |
conjunction | +2.913 |
Neg logit contributions | |
boy | -4.472 |
boys | -4.269 |
PLEASE | -4.075 |
pun | -4.064 |
answered | -4.061 |
Token | or |
Token ID | 393 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
eatures | +1.997 |
heres | +1.897 |
uration | +1.821 |
etheless | +1.794 |
conjunction | +1.775 |
Neg logit contributions | |
boy | -1.421 |
boys | -1.338 |
answered | -1.261 |
pun | -1.243 |
PLEASE | -1.238 |
Token | may |
Token ID | 743 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
eatures | +0.879 |
heres | +0.839 |
uration | +0.772 |
conjunction | +0.738 |
cluded | +0.736 |
Neg logit contributions | |
boy | -1.733 |
boys | -1.671 |
pun | -1.610 |
PLEASE | -1.609 |
answered | -1.604 |
Token | not |
Token ID | 407 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
heres | +7.040 |
conjunction | +6.702 |
occurred | +6.619 |
cluded | +6.286 |
itself | +6.213 |
Neg logit contributions | |
sacrific | -15.643 |
answered | -14.912 |
boy | -14.098 |
boys | -14.059 |
bern | -13.790 |
Token | take |
Token ID | 1011 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
eatures | +5.413 |
heres | +5.252 |
uration | +4.984 |
conjunction | +4.931 |
occurred | +4.878 |
Neg logit contributions | |
boy | -5.143 |
boys | -4.951 |
answered | -4.805 |
pun | -4.639 |
PLEASE | -4.495 |
Token | an |
Token ID | 281 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
boy | +2.023 |
boys | +1.929 |
PLEASE | +1.853 |
pun | +1.826 |
answered | +1.818 |
Neg logit contributions | |
eatures | -1.422 |
heres | -1.294 |
uration | -1.223 |
etheless | -1.221 |
urations | -1.173 |
Token | actual |
Token ID | 4036 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
boy | +3.168 |
boys | +3.003 |
PLEASE | +2.863 |
pun | +2.827 |
answered | +2.822 |
Neg logit contributions | |
eatures | -2.754 |
heres | -2.538 |
uration | -2.406 |
etheless | -2.399 |
urations | -2.332 |
Token | roster |
Token ID | 9354 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
eatures | +0.654 |
heres | +0.620 |
uration | +0.591 |
etheless | +0.581 |
conjunction | +0.576 |
Neg logit contributions | |
boy | -0.511 |
boys | -0.483 |
PLEASE | -0.459 |
pun | -0.454 |
answered | -0.452 |
Token | information |
Token ID | 1321 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
boy | +1.227 |
boys | +1.151 |
PLEASE | +1.096 |
pun | +1.081 |
answered | +1.077 |
Neg logit contributions | |
eatures | -1.521 |
heres | -1.423 |
uration | -1.359 |
etheless | -1.351 |
urations | -1.326 |
Token | ? |
Token ID | 30 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
boy | +0.522 |
boys | +0.493 |
pun | +0.462 |
PLEASE | +0.456 |
answered | +0.455 |
Neg logit contributions | |
eatures | -0.671 |
heres | -0.640 |
uration | -0.611 |
etheless | -0.606 |
conjunction | -0.592 |
Token |
|
Token ID | 198 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
boy | +2.707 |
boys | +2.515 |
PLEASE | +2.389 |
pun | +2.333 |
answered | +2.330 |
Neg logit contributions | |
eatures | -4.238 |
heres | -3.970 |
uration | -3.814 |
etheless | -3.808 |
urations | -3.729 |
Token |
|
Token ID | 198 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
boy | +1.560 |
boys | +1.482 |
sacrific | +1.415 |
answered | +1.396 |
PLEASE | +1.393 |
Neg logit contributions | |
heres | -1.978 |
eatures | -1.916 |
uration | -1.880 |
cluded | -1.833 |
urations | -1.830 |
Token | With |
Token ID | 3152 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
boy | +0.760 |
boys | +0.703 |
PLEASE | +0.658 |
pun | +0.650 |
answered | +0.650 |
Neg logit contributions | |
eatures | -1.271 |
heres | -1.188 |
etheless | -1.145 |
uration | -1.145 |
urations | -1.119 |
Token | love |
Token ID | 1842 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
boy | +1.036 |
boys | +0.911 |
PLEASE | +0.854 |
answered | +0.846 |
pun | +0.835 |
Neg logit contributions | |
eatures | -2.373 |
heres | -2.212 |
etheless | -2.144 |
uration | -2.142 |
urations | -2.128 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
boy | +8.938 |
PLEASE | +7.745 |
boys | +7.553 |
answered | +7.513 |
pun | +7.048 |
Neg logit contributions | |
eatures | -16.768 |
heres | -14.848 |
guiActiveUnfocused | -14.697 |
uration | -14.649 |
cluded | -14.436 |
Token | light |
Token ID | 1657 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
boy | +6.075 |
PLEASE | +5.469 |
boys | +5.372 |
sacrific | +5.058 |
thank | +4.997 |
Neg logit contributions | |
eatures | -9.001 |
heres | -7.933 |
etheless | -7.891 |
cluded | -7.725 |
urations | -7.685 |
Token |
|
Token ID | 198 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
boy | +2.923 |
boys | +2.633 |
PLEASE | +2.585 |
answered | +2.427 |
pun | +2.348 |
Neg logit contributions | |
eatures | -5.326 |
heres | -4.904 |
uration | -4.763 |
etheless | -4.689 |
urations | -4.686 |
Token |
|
Token ID | 198 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
boy | +6.140 |
boys | +5.411 |
PLEASE | +5.038 |
pun | +4.841 |
answered | +4.694 |
Neg logit contributions | |
eatures | -14.797 |
etheless | -13.157 |
heres | -12.192 |
uration | -11.877 |
urations | -11.651 |
Token | George |
Token ID | 20191 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
boy | +5.358 |
boys | +4.830 |
answered | +4.496 |
PLEASE | +4.422 |
pun | +4.405 |
Neg logit contributions | |
eatures | -8.706 |
etheless | -7.804 |
heres | -7.649 |
uration | -7.517 |
conjunction | -7.389 |
Token | point |
Token ID | 966 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
boy | +4.065 |
boys | +3.786 |
pun | +3.640 |
PLEASE | +3.628 |
answered | +3.553 |
Neg logit contributions | |
eatures | -5.415 |
heres | -5.026 |
etheless | -4.810 |
uration | -4.788 |
urations | -4.699 |
Token | of |
Token ID | 286 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
boy | +1.623 |
boys | +1.491 |
pun | +1.416 |
PLEASE | +1.375 |
answered | +1.338 |
Neg logit contributions | |
eatures | -2.443 |
heres | -2.298 |
uration | -2.166 |
urations | -2.152 |
etheless | -2.129 |
Token | view |
Token ID | 1570 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
eatures | +0.485 |
heres | +0.445 |
etheless | +0.425 |
uration | +0.423 |
urations | +0.413 |
Neg logit contributions | |
boy | -0.467 |
boys | -0.440 |
PLEASE | -0.422 |
pun | -0.418 |
answered | -0.413 |
Token | of |
Token ID | 286 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
boy | +2.965 |
boys | +2.732 |
pun | +2.504 |
PLEASE | +2.450 |
answered | +2.407 |
Neg logit contributions | |
eatures | -4.638 |
heres | -4.381 |
uration | -4.199 |
etheless | -4.161 |
urations | -4.153 |
Token | the |
Token ID | 262 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
boy | +2.174 |
boys | +2.077 |
pun | +1.985 |
PLEASE | +1.982 |
answered | +1.981 |
Neg logit contributions | |
eatures | -1.192 |
heres | -1.059 |
uration | -0.980 |
etheless | -0.979 |
urations | -0.949 |
Token | public |
Token ID | 1171 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
boy | +3.967 |
boys | +3.708 |
PLEASE | +3.479 |
pun | +3.471 |
answered | +3.448 |
Neg logit contributions | |
eatures | -5.430 |
heres | -5.008 |
etheless | -4.815 |
uration | -4.782 |
urations | -4.714 |
Token | as |
Token ID | 355 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
boy | +10.177 |
boys | +9.123 |
or | +8.809 |
PLEASE | +8.788 |
pun | +8.357 |
Neg logit contributions | |
eatures | -13.846 |
heres | -12.706 |
uration | -12.483 |
urations | -12.319 |
etheless | -12.154 |
Token | well |
Token ID | 880 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
boy | +3.624 |
boys | +3.332 |
PLEASE | +3.134 |
pun | +3.115 |
answered | +3.063 |
Neg logit contributions | |
eatures | -6.209 |
heres | -5.621 |
uration | -5.486 |
etheless | -5.466 |
urations | -5.413 |
Token | as |
Token ID | 355 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
boy | +1.650 |
boys | +1.562 |
PLEASE | +1.482 |
pun | +1.474 |
answered | +1.467 |
Neg logit contributions | |
eatures | -1.840 |
heres | -1.761 |
uration | -1.674 |
etheless | -1.639 |
urations | -1.627 |
Token | the |
Token ID | 262 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
boy | +4.580 |
boys | +4.373 |
PLEASE | +4.172 |
answered | +4.153 |
pun | +4.144 |
Neg logit contributions | |
eatures | -2.590 |
heres | -2.313 |
uration | -2.119 |
etheless | -2.077 |
guiActiveUnfocused | -2.048 |
Token | scientific |
Token ID | 5654 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
boy | +1.671 |
boys | +1.572 |
PLEASE | +1.485 |
pun | +1.480 |
answered | +1.478 |
Neg logit contributions | |
eatures | -1.893 |
heres | -1.738 |
etheless | -1.660 |
uration | -1.655 |
urations | -1.612 |
Token | run |
Token ID | 1057 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
eatures | +2.203 |
heres | +2.086 |
uration | +1.985 |
etheless | +1.982 |
conjunction | +1.957 |
Neg logit contributions | |
boy | -1.901 |
boys | -1.803 |
answered | -1.691 |
pun | -1.675 |
PLEASE | -1.674 |
Token | constant |
Token ID | 6937 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
boy | +0.931 |
boys | +0.886 |
PLEASE | +0.853 |
pun | +0.845 |
answered | +0.839 |
Neg logit contributions | |
eatures | -0.701 |
heres | -0.637 |
etheless | -0.605 |
uration | -0.605 |
urations | -0.577 |
Token | deficits |
Token ID | 22729 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
boy | +0.054 |
boys | +0.052 |
PLEASE | +0.049 |
pun | +0.049 |
answered | +0.049 |
Neg logit contributions | |
eatures | -0.044 |
heres | -0.041 |
uration | -0.038 |
etheless | -0.038 |
urations | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
eatures | +3.018 |
heres | +2.917 |
uration | +2.735 |
conjunction | +2.713 |
occurred | +2.701 |
Neg logit contributions | |
boy | -2.887 |
boys | -2.758 |
answered | -2.608 |
PLEASE | -2.575 |
pun | -2.568 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
eatures | +0.449 |
heres | +0.422 |
uration | +0.402 |
etheless | +0.398 |
urations | +0.392 |
Neg logit contributions | |
boy | -0.368 |
boys | -0.347 |
PLEASE | -0.327 |
answered | -0.324 |
pun | -0.324 |
Token | votes |
Token ID | 5690 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
boy | +5.307 |
boys | +4.997 |
PLEASE | +4.790 |
pun | +4.743 |
answered | +4.708 |
Neg logit contributions | |
eatures | -5.239 |
heres | -4.751 |
etheless | -4.642 |
uration | -4.640 |
urations | -4.412 |
Token | find |
Token ID | 1064 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
boy | +11.981 |
boys | +11.026 |
PLEASE | +10.981 |
pun | +10.825 |
or | +10.675 |
Neg logit contributions | |
eatures | -13.063 |
heres | -11.142 |
etheless | -11.121 |
uration | -11.049 |
urations | -10.618 |
Token | it |
Token ID | 340 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
eatures | +0.961 |
heres | +0.891 |
uration | +0.841 |
etheless | +0.836 |
urations | +0.815 |
Neg logit contributions | |
boy | -1.111 |
boys | -1.055 |
PLEASE | -1.010 |
pun | -1.002 |
answered | -0.998 |
Token | difficult |
Token ID | 2408 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
boy | +0.198 |
boys | +0.187 |
PLEASE | +0.178 |
pun | +0.177 |
answered | +0.175 |
Neg logit contributions | |
eatures | -0.222 |
heres | -0.206 |
uration | -0.197 |
etheless | -0.196 |
urations | -0.191 |
Token | to |
Token ID | 284 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
boy | +0.831 |
boys | +0.754 |
PLEASE | +0.709 |
pun | +0.706 |
answered | +0.684 |
Neg logit contributions | |
eatures | -1.686 |
heres | -1.572 |
uration | -1.521 |
etheless | -1.519 |
urations | -1.490 |
Token | attract |
Token ID | 4729 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
boy | +2.214 |
boys | +2.080 |
PLEASE | +1.968 |
pun | +1.949 |
answered | +1.940 |
Neg logit contributions | |
eatures | -2.813 |
heres | -2.638 |
uration | -2.521 |
etheless | -2.507 |
urations | -2.456 |
Token | time |
Token ID | 640 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
boy | +1.729 |
boys | +1.639 |
PLEASE | +1.575 |
answered | +1.561 |
pun | +1.556 |
Neg logit contributions | |
eatures | -1.863 |
heres | -1.800 |
uration | -1.729 |
etheless | -1.671 |
urations | -1.667 |
Token | I |
Token ID | 314 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
boy | +1.907 |
boys | +1.770 |
PLEASE | +1.649 |
pun | +1.639 |
answered | +1.628 |
Neg logit contributions | |
eatures | -3.422 |
heres | -3.280 |
uration | -3.146 |
etheless | -3.106 |
urations | -3.078 |
Token | don |
Token ID | 836 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
boy | +3.593 |
boys | +3.362 |
PLEASE | +3.159 |
answered | +3.115 |
pun | +3.091 |
Neg logit contributions | |
eatures | -6.000 |
heres | -5.757 |
uration | -5.535 |
etheless | -5.455 |
urations | -5.401 |
Token | 't |
Token ID | 470 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
boy | +5.463 |
boys | +5.025 |
PLEASE | +4.672 |
pun | +4.634 |
answered | +4.539 |
Neg logit contributions | |
eatures | -9.229 |
etheless | -8.212 |
heres | -8.169 |
uration | -7.863 |
urations | -7.673 |
Token | even |
Token ID | 772 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
boy | +5.239 |
boys | +4.852 |
PLEASE | +4.583 |
pun | +4.510 |
answered | +4.489 |
Neg logit contributions | |
eatures | -7.364 |
heres | -6.771 |
etheless | -6.527 |
uration | -6.506 |
urations | -6.363 |
Token | play |
Token ID | 711 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
boy | +3.885 |
boys | +3.640 |
PLEASE | +3.426 |
pun | +3.404 |
answered | +3.391 |
Neg logit contributions | |
eatures | -5.595 |
heres | -5.294 |
uration | -5.062 |
etheless | -5.021 |
urations | -4.941 |
Token | games |
Token ID | 1830 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
boy | +9.766 |
boys | +9.169 |
PLEASE | +8.279 |
answered | +7.370 |
or | +7.342 |
Neg logit contributions | |
eatures | -16.786 |
etheless | -15.014 |
heres | -14.056 |
uration | -13.889 |
terness | -13.842 |
Token | with |
Token ID | 351 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
boy | +7.635 |
boys | +6.632 |
PLEASE | +6.106 |
pun | +5.787 |
answered | +5.625 |
Neg logit contributions | |
eatures | -18.907 |
etheless | -16.518 |
heres | -15.680 |
uration | -15.400 |
urations | -15.088 |
Token | AA |
Token ID | 15923 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
boy | +4.091 |
boys | +3.853 |
PLEASE | +3.656 |
pun | +3.609 |
answered | +3.600 |
Neg logit contributions | |
eatures | -4.773 |
heres | -4.438 |
uration | -4.229 |
etheless | -4.222 |
urations | -4.121 |
Token | on |
Token ID | 319 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
boy | +3.698 |
boys | +3.438 |
PLEASE | +3.234 |
pun | +3.188 |
answered | +3.168 |
Neg logit contributions | |
eatures | -5.890 |
heres | -5.486 |
etheless | -5.279 |
uration | -5.261 |
urations | -5.145 |
Token | ( |
Token ID | 357 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
boy | +2.496 |
boys | +2.388 |
pun | +2.281 |
PLEASE | +2.278 |
answered | +2.270 |
Neg logit contributions | |
eatures | -1.940 |
heres | -1.860 |
uration | -1.753 |
etheless | -1.698 |
conjunction | -1.693 |
Token | the |
Token ID | 262 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
eatures | +2.610 |
heres | +2.405 |
uration | +2.264 |
etheless | +2.253 |
urations | +2.188 |
Neg logit contributions | |
boy | -3.303 |
boys | -3.146 |
PLEASE | -3.016 |
pun | -2.992 |
answered | -2.983 |
Token | head |
Token ID | 1182 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
boy | +0.095 |
boys | +0.089 |
PLEASE | +0.085 |
pun | +0.085 |
answered | +0.084 |
Neg logit contributions | |
eatures | -0.091 |
heres | -0.085 |
uration | -0.080 |
etheless | -0.080 |
urations | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
boy | +4.242 |
boys | +3.764 |
pun | +3.675 |
answered | +3.344 |
doctor | +3.306 |
Neg logit contributions | |
eatures | -6.524 |
heres | -6.249 |
etheless | -5.977 |
uration | -5.873 |
urations | -5.773 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
boy | +4.543 |
boys | +4.255 |
pun | +4.146 |
PLEASE | +4.136 |
answered | +4.117 |
Neg logit contributions | |
eatures | -2.766 |
heres | -2.564 |
uration | -2.372 |
etheless | -2.361 |
urations | -2.342 |
Token | U |
Token ID | 471 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
boy | +3.185 |
boys | +2.987 |
PLEASE | +2.855 |
pun | +2.840 |
answered | +2.783 |
Neg logit contributions | |
eatures | -3.527 |
heres | -3.259 |
etheless | -3.122 |
uration | -3.109 |
urations | -3.060 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
boy | +5.488 |
boys | +4.992 |
pun | +4.677 |
bern | +4.551 |
answered | +4.469 |
Neg logit contributions | |
eatures | -6.771 |
etheless | -6.303 |
heres | -5.765 |
bidden | -5.625 |
uration | -5.571 |
Token | S |
Token ID | 50 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
boy | +5.812 |
pun | +4.887 |
boys | +4.663 |
answered | +4.508 |
PLEASE | +4.366 |
Neg logit contributions | |
eatures | -17.350 |
etheless | -16.599 |
uration | -16.183 |
heres | -16.101 |
guiActiveUnfocused | -16.101 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
boy | +6.923 |
pun | +6.116 |
PLEASE | +5.972 |
boys | +5.952 |
answered | +5.821 |
Neg logit contributions | |
eatures | -11.241 |
etheless | -10.273 |
heres | -10.165 |
guiActiveUnfocused | -9.728 |
urations | -9.536 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
boy | +9.424 |
pun | +8.634 |
answered | +8.537 |
boys | +8.517 |
PLEASE | +8.467 |
Neg logit contributions | |
eatures | -12.365 |
heres | -11.095 |
etheless | -10.900 |
urations | -10.761 |
uration | -10.672 |
Token | regulatory |
Token ID | 11344 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
eatures | +0.878 |
heres | +0.828 |
uration | +0.790 |
etheless | +0.781 |
conjunction | +0.775 |
Neg logit contributions | |
boy | -0.646 |
boys | -0.608 |
PLEASE | -0.574 |
pun | -0.566 |
answered | -0.565 |
Token | body |
Token ID | 1767 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
eatures | +2.527 |
heres | +2.378 |
uration | +2.276 |
etheless | +2.238 |
conjunction | +2.233 |
Neg logit contributions | |
boy | -2.274 |
boys | -2.146 |
PLEASE | -2.040 |
pun | -2.019 |
answered | -2.002 |
Token | I |
Token ID | 314 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
boy | +1.907 |
boys | +1.770 |
PLEASE | +1.649 |
pun | +1.639 |
answered | +1.628 |
Neg logit contributions | |
eatures | -3.422 |
heres | -3.280 |
uration | -3.146 |
etheless | -3.106 |
urations | -3.078 |
Token | don |
Token ID | 836 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
boy | +3.593 |
boys | +3.362 |
PLEASE | +3.159 |
answered | +3.115 |
pun | +3.091 |
Neg logit contributions | |
eatures | -6.000 |
heres | -5.757 |
uration | -5.535 |
etheless | -5.455 |
urations | -5.401 |
Token | 't |
Token ID | 470 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
boy | +5.463 |
boys | +5.025 |
PLEASE | +4.672 |
pun | +4.634 |
answered | +4.539 |
Neg logit contributions | |
eatures | -9.229 |
etheless | -8.212 |
heres | -8.169 |
uration | -7.863 |
urations | -7.673 |
Token | even |
Token ID | 772 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
boy | +5.239 |
boys | +4.852 |
PLEASE | +4.583 |
pun | +4.510 |
answered | +4.489 |
Neg logit contributions | |
eatures | -7.364 |
heres | -6.771 |
etheless | -6.527 |
uration | -6.506 |
urations | -6.363 |
Token | play |
Token ID | 711 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
boy | +3.885 |
boys | +3.640 |
PLEASE | +3.426 |
pun | +3.404 |
answered | +3.391 |
Neg logit contributions | |
eatures | -5.595 |
heres | -5.294 |
uration | -5.062 |
etheless | -5.021 |
urations | -4.941 |
Token | games |
Token ID | 1830 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
boy | +9.766 |
boys | +9.169 |
PLEASE | +8.279 |
answered | +7.370 |
or | +7.342 |
Neg logit contributions | |
eatures | -16.786 |
etheless | -15.014 |
heres | -14.056 |
uration | -13.889 |
terness | -13.842 |
Token | with |
Token ID | 351 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
boy | +7.635 |
boys | +6.632 |
PLEASE | +6.106 |
pun | +5.787 |
answered | +5.625 |
Neg logit contributions | |
eatures | -18.907 |
etheless | -16.518 |
heres | -15.680 |
uration | -15.400 |
urations | -15.088 |
Token | AA |
Token ID | 15923 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
boy | +4.091 |
boys | +3.853 |
PLEASE | +3.656 |
pun | +3.609 |
answered | +3.600 |
Neg logit contributions | |
eatures | -4.773 |
heres | -4.438 |
uration | -4.229 |
etheless | -4.222 |
urations | -4.121 |
Token | on |
Token ID | 319 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
boy | +3.698 |
boys | +3.438 |
PLEASE | +3.234 |
pun | +3.188 |
answered | +3.168 |
Neg logit contributions | |
eatures | -5.890 |
heres | -5.486 |
etheless | -5.279 |
uration | -5.261 |
urations | -5.145 |
Token | ( |
Token ID | 357 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
boy | +2.496 |
boys | +2.388 |
pun | +2.281 |
PLEASE | +2.278 |
answered | +2.270 |
Neg logit contributions | |
eatures | -1.940 |
heres | -1.860 |
uration | -1.753 |
etheless | -1.698 |
conjunction | -1.693 |
Token | Anti |
Token ID | 28795 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
boy | +6.780 |
boys | +6.262 |
PLEASE | +5.818 |
pun | +5.749 |
answered | +5.658 |
Neg logit contributions | |
eatures | -11.708 |
etheless | -10.476 |
heres | -10.208 |
uration | -9.729 |
urations | -9.628 |
Token | plan |
Token ID | 1410 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
eatures | +0.296 |
heres | +0.277 |
uration | +0.263 |
etheless | +0.261 |
urations | +0.255 |
Neg logit contributions | |
boy | -0.281 |
boys | -0.266 |
PLEASE | -0.254 |
pun | -0.251 |
answered | -0.250 |
Token | to |
Token ID | 284 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
boy | +0.302 |
boys | +0.281 |
pun | +0.265 |
PLEASE | +0.264 |
answered | +0.259 |
Neg logit contributions | |
eatures | -0.402 |
heres | -0.368 |
etheless | -0.355 |
uration | -0.354 |
urations | -0.348 |
Token | bomb |
Token ID | 5194 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
eatures | +1.573 |
heres | +1.491 |
uration | +1.423 |
etheless | +1.403 |
conjunction | +1.385 |
Neg logit contributions | |
boy | -1.240 |
boys | -1.174 |
answered | -1.103 |
PLEASE | -1.099 |
pun | -1.096 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
boy | +1.395 |
boys | +1.319 |
PLEASE | +1.274 |
pun | +1.262 |
answered | +1.248 |
Neg logit contributions | |
eatures | -1.037 |
heres | -0.930 |
etheless | -0.896 |
uration | -0.890 |
urations | -0.863 |
Token | U |
Token ID | 471 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
boy | +3.512 |
boys | +3.282 |
PLEASE | +3.135 |
pun | +3.076 |
answered | +3.044 |
Neg logit contributions | |
eatures | -3.967 |
heres | -3.642 |
etheless | -3.524 |
uration | -3.520 |
urations | -3.451 |
Token | . |
Token ID | 13 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
boy | +6.166 |
boys | +5.692 |
pun | +5.273 |
PLEASE | +5.104 |
bern | +5.083 |
Neg logit contributions | |
eatures | -7.254 |
etheless | -6.825 |
heres | -6.445 |
bidden | -6.320 |
uration | -6.249 |
Token | S |
Token ID | 50 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
boy | +5.832 |
boys | +5.051 |
PLEASE | +4.700 |
pun | +4.537 |
bern | +4.312 |
Neg logit contributions | |
eatures | -16.221 |
etheless | -15.599 |
heres | -15.385 |
guiActiveUnfocused | -15.253 |
uration | -15.048 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
boy | +7.703 |
boys | +6.799 |
PLEASE | +6.747 |
pun | +6.575 |
answered | +6.328 |
Neg logit contributions | |
eatures | -9.971 |
heres | -9.168 |
etheless | -9.073 |
bidden | -8.682 |
guiActiveUnfocused | -8.667 |
Token | Cons |
Token ID | 3515 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
boy | +7.780 |
PLEASE | +7.118 |
boys | +6.982 |
answered | +6.701 |
pun | +6.544 |
Neg logit contributions | |
eatures | -12.455 |
heres | -11.542 |
etheless | -11.252 |
uration | -11.074 |
urations | -11.044 |
Token | ulate |
Token ID | 5039 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
boy | +1.461 |
boys | +1.381 |
PLEASE | +1.311 |
pun | +1.307 |
answered | +1.275 |
Neg logit contributions | |
eatures | -1.244 |
heres | -1.100 |
etheless | -1.094 |
uration | -1.015 |
conjunction | -1.013 |
Token | in |
Token ID | 287 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
boy | +2.433 |
boys | +2.265 |
PLEASE | +2.155 |
pun | +2.109 |
answered | +2.088 |
Neg logit contributions | |
eatures | -3.041 |
heres | -2.802 |
etheless | -2.696 |
uration | -2.681 |
urations | -2.636 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
boy | +3.013 |
boys | +2.836 |
PLEASE | +2.726 |
pun | +2.659 |
answered | +2.630 |
Neg logit contributions | |
eatures | -3.591 |
heres | -3.303 |
etheless | -3.183 |
uration | -3.169 |
urations | -3.096 |
Token |
|
Token ID | 198 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
boy | +2.712 |
boys | +2.550 |
PLEASE | +2.401 |
pun | +2.384 |
answered | +2.384 |
Neg logit contributions | |
eatures | -3.771 |
heres | -3.701 |
uration | -3.526 |
urations | -3.437 |
cluded | -3.426 |
Token | These |
Token ID | 4711 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
boy | +1.916 |
boys | +1.792 |
pun | +1.678 |
PLEASE | +1.664 |
answered | +1.648 |
Neg logit contributions | |
eatures | -2.693 |
heres | -2.429 |
etheless | -2.413 |
uration | -2.365 |
urations | -2.321 |
Token | people |
Token ID | 661 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
eatures | +1.448 |
heres | +1.356 |
uration | +1.286 |
etheless | +1.274 |
urations | +1.251 |
Neg logit contributions | |
boy | -1.391 |
boys | -1.314 |
PLEASE | -1.250 |
pun | -1.246 |
answered | -1.244 |
Token | want |
Token ID | 765 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
boy | +3.814 |
boys | +3.597 |
PLEASE | +3.493 |
pun | +3.397 |
answered | +3.367 |
Neg logit contributions | |
eatures | -3.588 |
heres | -3.251 |
uration | -3.116 |
etheless | -3.113 |
urations | -3.036 |
Token | jobs |
Token ID | 3946 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
boy | +4.508 |
boys | +4.253 |
PLEASE | +4.131 |
pun | +4.062 |
answered | +3.936 |
Neg logit contributions | |
eatures | -4.720 |
heres | -4.222 |
etheless | -4.183 |
uration | -4.083 |
urations | -3.984 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
boy | +11.228 |
PLEASE | +10.420 |
pun | +10.349 |
boys | +10.326 |
answered | +9.462 |
Neg logit contributions | |
eatures | -12.735 |
etheless | -11.317 |
heres | -10.949 |
guiActiveUnfocused | -10.707 |
uration | -10.664 |
Token | Respect |
Token ID | 42153 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
boy | +4.618 |
boys | +4.304 |
PLEASE | +4.170 |
pun | +3.977 |
answered | +3.861 |
Neg logit contributions | |
eatures | -7.418 |
heres | -6.738 |
etheless | -6.689 |
uration | -6.506 |
urations | -6.352 |
Token | ful |
Token ID | 913 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
boy | +6.545 |
boys | +6.222 |
PLEASE | +5.962 |
pun | +5.957 |
answered | +5.748 |
Neg logit contributions | |
eatures | -5.155 |
etheless | -4.552 |
heres | -4.535 |
uration | -4.329 |
urations | -4.315 |
Token | jobs |
Token ID | 3946 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
boy | +2.244 |
boys | +2.113 |
PLEASE | +2.013 |
pun | +1.982 |
answered | +1.959 |
Neg logit contributions | |
eatures | -2.646 |
heres | -2.467 |
etheless | -2.359 |
uration | -2.350 |
urations | -2.298 |
Token | that |
Token ID | 326 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
eatures | +0.538 |
heres | +0.496 |
uration | +0.470 |
etheless | +0.470 |
urations | +0.457 |
Neg logit contributions | |
boy | -0.577 |
boys | -0.546 |
PLEASE | -0.523 |
pun | -0.518 |
answered | -0.513 |
Token | , |
Token ID | 11 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
eatures | +2.718 |
heres | +2.573 |
uration | +2.456 |
etheless | +2.429 |
urations | +2.377 |
Neg logit contributions | |
boy | -2.325 |
boys | -2.196 |
PLEASE | -2.090 |
answered | -2.063 |
pun | -2.060 |
Token | quick |
Token ID | 2068 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
boy | +0.814 |
boys | +0.760 |
PLEASE | +0.717 |
pun | +0.710 |
answered | +0.706 |
Neg logit contributions | |
eatures | -1.160 |
heres | -1.088 |
uration | -1.043 |
etheless | -1.038 |
urations | -1.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
eatures | +7.510 |
heres | +7.157 |
uration | +6.798 |
etheless | +6.792 |
cluded | +6.646 |
Neg logit contributions | |
boy | -5.177 |
boys | -4.860 |
PLEASE | -4.618 |
answered | -4.553 |
pun | -4.498 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
eatures | +3.862 |
heres | +3.734 |
uration | +3.555 |
conjunction | +3.501 |
etheless | +3.490 |
Neg logit contributions | |
boy | -2.601 |
boys | -2.462 |
answered | -2.346 |
PLEASE | -2.274 |
pun | -2.257 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
boy | +4.187 |
boys | +3.972 |
pun | +3.746 |
PLEASE | +3.674 |
answered | +3.632 |
Neg logit contributions | |
eatures | -3.475 |
heres | -3.092 |
etheless | -3.063 |
uration | -3.015 |
urations | -2.941 |
Token | job |
Token ID | 1693 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
boy | +2.840 |
boys | +2.634 |
PLEASE | +2.489 |
pun | +2.460 |
answered | +2.438 |
Neg logit contributions | |
eatures | -4.123 |
heres | -3.842 |
etheless | -3.691 |
uration | -3.685 |
urations | -3.604 |
Token | or |
Token ID | 393 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
boy | +11.286 |
boys | +9.944 |
pun | +9.723 |
laughing | +9.419 |
or | +9.411 |
Neg logit contributions | |
eatures | -13.577 |
etheless | -11.616 |
heres | -11.521 |
urations | -10.952 |
uration | -10.854 |
Token | abuse |
Token ID | 5076 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
boy | +1.400 |
boys | +1.316 |
PLEASE | +1.250 |
pun | +1.237 |
answered | +1.228 |
Neg logit contributions | |
eatures | -1.654 |
heres | -1.543 |
uration | -1.473 |
etheless | -1.469 |
urations | -1.435 |
Token | a |
Token ID | 257 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
eatures | +0.060 |
heres | +0.055 |
uration | +0.052 |
etheless | +0.051 |
urations | +0.050 |
Neg logit contributions | |
boy | -0.078 |
boys | -0.075 |
PLEASE | -0.072 |
pun | -0.071 |
answered | -0.071 |
Token | wife |
Token ID | 3656 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
boy | +0.127 |
boys | +0.121 |
answered | +0.114 |
PLEASE | +0.114 |
pun | +0.113 |
Neg logit contributions | |
eatures | -0.164 |
heres | -0.156 |
uration | -0.150 |
etheless | -0.147 |
conjunction | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
boy | +6.670 |
boys | +6.185 |
pun | +5.865 |
PLEASE | +5.860 |
answered | +5.671 |
Neg logit contributions | |
eatures | -7.465 |
heres | -6.454 |
etheless | -6.245 |
uration | -6.229 |
urations | -6.161 |
Token | would |
Token ID | 561 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
boy | +0.780 |
boys | +0.744 |
PLEASE | +0.711 |
pun | +0.707 |
answered | +0.707 |
Neg logit contributions | |
eatures | -0.614 |
heres | -0.570 |
uration | -0.535 |
etheless | -0.532 |
urations | -0.516 |
Token | decide |
Token ID | 5409 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
boy | +2.624 |
boys | +2.444 |
PLEASE | +2.338 |
pun | +2.299 |
answered | +2.246 |
Neg logit contributions | |
eatures | -3.509 |
heres | -3.266 |
uration | -3.128 |
etheless | -3.117 |
urations | -3.068 |
Token | to |
Token ID | 284 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
boy | +4.374 |
boys | +4.019 |
PLEASE | +3.861 |
pun | +3.754 |
answered | +3.532 |
Neg logit contributions | |
eatures | -6.644 |
heres | -6.087 |
uration | -5.990 |
etheless | -5.842 |
urations | -5.836 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
boy | +2.180 |
boys | +2.044 |
PLEASE | +1.946 |
pun | +1.923 |
answered | +1.905 |
Neg logit contributions | |
eatures | -2.693 |
heres | -2.515 |
uration | -2.404 |
etheless | -2.395 |
urations | -2.345 |
Token | an |
Token ID | 281 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
boy | +4.193 |
boys | +3.981 |
PLEASE | +3.814 |
pun | +3.774 |
answered | +3.734 |
Neg logit contributions | |
eatures | -3.149 |
heres | -2.829 |
uration | -2.711 |
etheless | -2.681 |
urations | -2.621 |
Token | American |
Token ID | 1605 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
boy | +4.832 |
boys | +4.481 |
PLEASE | +4.228 |
pun | +4.152 |
answered | +4.110 |
Neg logit contributions | |
eatures | -6.047 |
heres | -5.578 |
etheless | -5.360 |
uration | -5.356 |
urations | -5.273 |
Token | tourist |
Token ID | 18473 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
boy | +10.825 |
boys | +9.390 |
PLEASE | +9.341 |
pun | +8.866 |
laughing | +8.631 |
Neg logit contributions | |
eatures | -13.826 |
etheless | -12.148 |
heres | -12.010 |
uration | -11.941 |
urations | -11.909 |
Token | on |
Token ID | 319 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
boy | +4.076 |
boys | +3.801 |
PLEASE | +3.631 |
pun | +3.570 |
answered | +3.528 |
Neg logit contributions | |
eatures | -4.645 |
heres | -4.233 |
etheless | -4.092 |
uration | -4.082 |
urations | -3.985 |
Token | their |
Token ID | 511 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
boy | +1.954 |
boys | +1.852 |
PLEASE | +1.787 |
pun | +1.775 |
answered | +1.745 |
Neg logit contributions | |
eatures | -1.223 |
heres | -1.097 |
uration | -1.040 |
etheless | -1.014 |
urations | -1.004 |
Token | territory |
Token ID | 7674 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
boy | +3.209 |
boys | +2.996 |
PLEASE | +2.849 |
pun | +2.804 |
answered | +2.765 |
Neg logit contributions | |
eatures | -4.111 |
heres | -3.782 |
uration | -3.640 |
etheless | -3.622 |
urations | -3.568 |
Token | for |
Token ID | 329 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
boy | +2.338 |
boys | +2.198 |
PLEASE | +2.097 |
pun | +2.073 |
answered | +2.053 |
Neg logit contributions | |
eatures | -2.569 |
heres | -2.358 |
uration | -2.263 |
etheless | -2.249 |
urations | -2.207 |
Token | has |
Token ID | 468 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
eatures | +2.162 |
heres | +2.001 |
uration | +1.872 |
etheless | +1.856 |
urations | +1.804 |
Neg logit contributions | |
boy | -2.829 |
boys | -2.699 |
PLEASE | -2.582 |
pun | -2.568 |
answered | -2.563 |
Token | been |
Token ID | 587 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
eatures | +2.811 |
heres | +2.620 |
uration | +2.446 |
etheless | +2.404 |
occurred | +2.375 |
Neg logit contributions | |
boy | -3.625 |
boys | -3.459 |
PLEASE | -3.298 |
pun | -3.267 |
answered | -3.266 |
Token | supported |
Token ID | 4855 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
eatures | +1.843 |
heres | +1.714 |
uration | +1.602 |
etheless | +1.596 |
conjunction | +1.552 |
Neg logit contributions | |
boy | -2.308 |
boys | -2.203 |
PLEASE | -2.111 |
pun | -2.089 |
answered | -2.087 |
Token | by |
Token ID | 416 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
eatures | +1.066 |
heres | +0.988 |
uration | +0.958 |
etheless | +0.951 |
urations | +0.935 |
Neg logit contributions | |
boy | -0.783 |
boys | -0.726 |
PLEASE | -0.689 |
pun | -0.684 |
answered | -0.672 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
eatures | +3.168 |
heres | +2.943 |
etheless | +2.749 |
uration | +2.744 |
conjunction | +2.663 |
Neg logit contributions | |
boy | -3.948 |
boys | -3.766 |
PLEASE | -3.615 |
answered | -3.578 |
pun | -3.576 |
Token | US |
Token ID | 1294 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
boy | +0.577 |
boys | +0.543 |
PLEASE | +0.516 |
pun | +0.513 |
answered | +0.508 |
Neg logit contributions | |
eatures | -0.646 |
heres | -0.599 |
uration | -0.573 |
etheless | -0.570 |
urations | -0.559 |
Token | - |
Token ID | 532 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
boy | +10.875 |
pun | +9.906 |
boys | +9.731 |
answered | +9.438 |
PLEASE | +9.430 |
Neg logit contributions | |
eatures | -12.723 |
urations | -10.746 |
uration | -10.528 |
heres | -10.509 |
etheless | -9.988 |
Token | who |
Token ID | 508 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
boy | +8.542 |
boys | +8.030 |
PLEASE | +7.790 |
pun | +7.783 |
answered | +7.668 |
Neg logit contributions | |
eatures | -6.248 |
heres | -5.432 |
uration | -5.388 |
urations | -5.223 |
etheless | -5.101 |
Token | are |
Token ID | 389 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
boy | +2.625 |
boys | +2.479 |
PLEASE | +2.388 |
pun | +2.365 |
answered | +2.344 |
Neg logit contributions | |
eatures | -2.118 |
heres | -1.913 |
uration | -1.842 |
etheless | -1.838 |
urations | -1.792 |
Token | partners |
Token ID | 4887 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
boy | +2.270 |
boys | +2.143 |
PLEASE | +2.044 |
pun | +2.027 |
answered | +1.993 |
Neg logit contributions | |
eatures | -2.336 |
heres | -2.138 |
uration | -2.069 |
etheless | -2.052 |
urations | -1.998 |
Token | in |
Token ID | 287 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
boy | +2.431 |
boys | +2.246 |
pun | +2.182 |
PLEASE | +2.180 |
answered | +2.117 |
Neg logit contributions | |
eatures | -3.179 |
heres | -2.899 |
uration | -2.824 |
etheless | -2.763 |
urations | -2.751 |
Token | � |
Token ID | 247 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
eatures | +2.906 |
heres | +2.701 |
uration | +2.564 |
etheless | +2.547 |
urations | +2.487 |
Neg logit contributions | |
boy | -2.982 |
boys | -2.826 |
PLEASE | -2.697 |
pun | -2.673 |
answered | -2.662 |
Token | . |
Token ID | 13 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
eatures | +5.176 |
heres | +4.909 |
uration | +4.669 |
etheless | +4.636 |
cluded | +4.537 |
Neg logit contributions | |
boy | -4.014 |
boys | -3.805 |
PLEASE | -3.599 |
answered | -3.556 |
pun | -3.546 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
boy | +0.616 |
boys | +0.569 |
PLEASE | +0.541 |
pun | +0.527 |
answered | +0.524 |
Neg logit contributions | |
eatures | -1.034 |
heres | -0.963 |
etheless | -0.931 |
uration | -0.926 |
urations | -0.905 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
heres | +0.524 |
uration | +0.492 |
cluded | +0.488 |
urations | +0.480 |
conjunction | +0.479 |
Neg logit contributions | |
sacrific | -0.465 |
boy | -0.462 |
boys | -0.445 |
answered | -0.430 |
PLEASE | -0.422 |
Token | We |
Token ID | 1135 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
eatures | +1.567 |
heres | +1.514 |
uration | +1.439 |
urations | +1.403 |
cluded | +1.399 |
Neg logit contributions | |
boy | -1.181 |
boys | -1.114 |
PLEASE | -1.058 |
answered | -1.036 |
pun | -1.035 |
Token | pay |
Token ID | 1414 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
boy | +3.560 |
boys | +3.357 |
PLEASE | +3.205 |
pun | +3.163 |
answered | +3.157 |
Neg logit contributions | |
eatures | -3.598 |
heres | -3.339 |
etheless | -3.209 |
uration | -3.186 |
urations | -3.127 |
Token | for |
Token ID | 329 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
boy | +5.352 |
PLEASE | +4.806 |
boys | +4.409 |
pun | +4.329 |
or | +3.896 |
Neg logit contributions | |
eatures | -18.285 |
etheless | -17.528 |
guiActiveUnfocused | -16.442 |
heres | -16.381 |
terness | -15.766 |
Token | your |
Token ID | 534 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
boy | +5.686 |
boys | +5.429 |
PLEASE | +5.280 |
pun | +5.194 |
answered | +5.000 |
Neg logit contributions | |
eatures | -7.324 |
heres | -6.676 |
uration | -6.606 |
etheless | -6.539 |
urations | -6.303 |
Token | stories |
Token ID | 3923 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
boy | +5.482 |
PLEASE | +5.089 |
boys | +4.976 |
laughing | +4.888 |
doctor | +4.735 |
Neg logit contributions | |
eatures | -16.499 |
etheless | -15.126 |
heres | -15.043 |
ulic | -14.573 |
terness | -14.550 |
Token | ! |
Token ID | 0 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
PLEASE | +4.240 |
boy | +4.201 |
boys | +3.697 |
answered | +3.194 |
Beat | +2.887 |
Neg logit contributions | |
eatures | -16.812 |
guiActiveUnfocused | -14.341 |
etheless | -14.334 |
heres | -14.253 |
urations | -14.030 |
Token | Do |
Token ID | 2141 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
boy | +4.024 |
PLEASE | +3.781 |
boys | +3.554 |
answered | +3.101 |
pun | +3.073 |
Neg logit contributions | |
eatures | -10.418 |
etheless | -9.495 |
heres | -9.488 |
uration | -9.263 |
urations | -9.136 |
Token | culture |
Token ID | 3968 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
boy | +0.650 |
boys | +0.609 |
PLEASE | +0.578 |
pun | +0.571 |
answered | +0.567 |
Neg logit contributions | |
eatures | -0.829 |
heres | -0.772 |
uration | -0.739 |
etheless | -0.737 |
urations | -0.721 |
Token | .' |
Token ID | 2637 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
boy | +1.907 |
boys | +1.744 |
PLEASE | +1.649 |
pun | +1.628 |
answered | +1.595 |
Neg logit contributions | |
eatures | -2.968 |
heres | -2.697 |
etheless | -2.646 |
uration | -2.626 |
urations | -2.586 |
Token |
|
Token ID | 198 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
boy | +0.859 |
boys | +0.769 |
PLEASE | +0.746 |
answered | +0.713 |
pun | +0.713 |
Neg logit contributions | |
eatures | -1.731 |
heres | -1.605 |
uration | -1.572 |
etheless | -1.569 |
urations | -1.535 |
Token |
|
Token ID | 198 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
boy | +1.483 |
boys | +1.407 |
sacrific | +1.358 |
PLEASE | +1.334 |
answered | +1.333 |
Neg logit contributions | |
heres | -1.892 |
eatures | -1.832 |
uration | -1.797 |
cluded | -1.756 |
urations | -1.754 |
Token | The |
Token ID | 464 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
eatures | +0.253 |
heres | +0.233 |
etheless | +0.226 |
uration | +0.224 |
urations | +0.218 |
Neg logit contributions | |
boy | -0.195 |
boys | -0.182 |
PLEASE | -0.172 |
pun | -0.171 |
answered | -0.170 |
Token | BBC |
Token ID | 7823 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
eatures | +0.952 |
heres | +0.900 |
uration | +0.856 |
etheless | +0.847 |
conjunction | +0.833 |
Neg logit contributions | |
boy | -0.755 |
boys | -0.712 |
PLEASE | -0.673 |
answered | -0.666 |
pun | -0.666 |
Token | understands |
Token ID | 14759 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
boy | +11.145 |
boys | +10.372 |
PLEASE | +9.828 |
pun | +9.323 |
answered | +9.291 |
Neg logit contributions | |
eatures | -12.160 |
etheless | -10.999 |
urations | -10.829 |
uration | -10.801 |
heres | -10.369 |
Token | there |
Token ID | 612 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
eatures | +3.577 |
heres | +3.376 |
uration | +3.206 |
etheless | +3.177 |
urations | +3.118 |
Neg logit contributions | |
boy | -2.995 |
boys | -2.828 |
PLEASE | -2.682 |
pun | -2.664 |
answered | -2.658 |
Token | are |
Token ID | 389 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eatures | +1.520 |
heres | +1.362 |
uration | +1.281 |
etheless | +1.272 |
urations | +1.242 |
Neg logit contributions | |
boy | -2.150 |
boys | -2.042 |
PLEASE | -1.948 |
answered | -1.920 |
pun | -1.918 |
Token | more |
Token ID | 517 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
boy | +0.367 |
boys | +0.349 |
PLEASE | +0.334 |
pun | +0.331 |
answered | +0.330 |
Neg logit contributions | |
eatures | -0.319 |
heres | -0.295 |
uration | -0.279 |
etheless | -0.277 |
urations | -0.270 |
Token | than |
Token ID | 621 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
boy | +3.938 |
boys | +3.683 |
PLEASE | +3.529 |
answered | +3.478 |
pun | +3.469 |
Neg logit contributions | |
eatures | -4.604 |
heres | -4.185 |
uration | -4.058 |
etheless | -4.051 |
urations | -3.923 |
Token | unless |
Token ID | 4556 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
boy | +0.931 |
boys | +0.881 |
PLEASE | +0.839 |
pun | +0.832 |
answered | +0.829 |
Neg logit contributions | |
eatures | -0.961 |
heres | -0.896 |
uration | -0.851 |
etheless | -0.846 |
urations | -0.827 |
Token | they |
Token ID | 484 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
eatures | +3.532 |
heres | +3.339 |
uration | +3.157 |
etheless | +3.122 |
conjunction | +3.073 |
Neg logit contributions | |
boy | -3.269 |
boys | -3.088 |
PLEASE | -2.949 |
answered | -2.943 |
pun | -2.902 |
Token | yes |
Token ID | 3763 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
boy | +1.189 |
boys | +1.120 |
PLEASE | +1.047 |
answered | +1.046 |
pun | +1.041 |
Neg logit contributions | |
eatures | -1.592 |
heres | -1.510 |
uration | -1.446 |
etheless | -1.430 |
conjunction | -1.405 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
eatures | +0.538 |
heres | +0.499 |
uration | +0.470 |
etheless | +0.467 |
urations | +0.455 |
Neg logit contributions | |
boy | -0.639 |
boys | -0.608 |
PLEASE | -0.581 |
pun | -0.577 |
answered | -0.576 |
Token | the |
Token ID | 262 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
boy | +4.817 |
boys | +4.543 |
PLEASE | +4.399 |
pun | +4.310 |
answered | +4.212 |
Neg logit contributions | |
eatures | -4.743 |
heres | -4.296 |
etheless | -4.178 |
uration | -4.107 |
urations | -3.993 |
Token | fans |
Token ID | 3296 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
boy | +2.097 |
boys | +1.979 |
PLEASE | +1.871 |
pun | +1.862 |
answered | +1.846 |
Neg logit contributions | |
eatures | -2.286 |
heres | -2.119 |
etheless | -2.021 |
uration | -2.020 |
urations | -1.963 |
Token | won |
Token ID | 1839 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
boy | +11.766 |
boys | +10.930 |
PLEASE | +10.378 |
pun | +10.221 |
answered | +9.688 |
Neg logit contributions | |
eatures | -12.851 |
etheless | -10.901 |
heres | -10.845 |
uration | -10.623 |
urations | -10.563 |
Token | 't |
Token ID | 470 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
boy | +5.040 |
boys | +4.681 |
PLEASE | +4.394 |
pun | +4.313 |
answered | +4.242 |
Neg logit contributions | |
eatures | -8.439 |
heres | -7.547 |
etheless | -7.494 |
uration | -7.256 |
urations | -7.081 |
Token | be |
Token ID | 307 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
boy | +3.634 |
boys | +3.340 |
PLEASE | +3.179 |
pun | +3.081 |
answered | +2.997 |
Neg logit contributions | |
eatures | -6.377 |
heres | -5.953 |
etheless | -5.718 |
uration | -5.700 |
urations | -5.617 |
Token | able |
Token ID | 1498 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
boy | +4.565 |
boys | +4.258 |
PLEASE | +4.028 |
pun | +3.979 |
answered | +3.943 |
Neg logit contributions | |
eatures | -6.274 |
heres | -5.808 |
etheless | -5.580 |
uration | -5.562 |
urations | -5.433 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
boy | +0.621 |
boys | +0.586 |
pun | +0.546 |
answered | +0.544 |
PLEASE | +0.542 |
Neg logit contributions | |
eatures | -0.828 |
heres | -0.801 |
uration | -0.768 |
conjunction | -0.754 |
urations | -0.746 |
Token | prayers |
Token ID | 15707 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
boy | +2.088 |
boys | +1.944 |
PLEASE | +1.865 |
pun | +1.835 |
answered | +1.823 |
Neg logit contributions | |
eatures | -2.696 |
heres | -2.491 |
etheless | -2.415 |
uration | -2.397 |
urations | -2.336 |
Token | go |
Token ID | 467 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
boy | +5.494 |
PLEASE | +5.029 |
boys | +4.996 |
answered | +4.774 |
pun | +4.640 |
Neg logit contributions | |
eatures | -7.373 |
heres | -6.478 |
etheless | -6.378 |
uration | -6.238 |
urations | -6.219 |
Token | out |
Token ID | 503 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
boy | +3.322 |
boys | +2.941 |
PLEASE | +2.881 |
answered | +2.830 |
pun | +2.731 |
Neg logit contributions | |
eatures | -7.215 |
uration | -6.463 |
heres | -6.449 |
etheless | -6.433 |
urations | -6.260 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
boy | +3.143 |
PLEASE | +2.688 |
boys | +2.663 |
answered | +2.584 |
pun | +2.450 |
Neg logit contributions | |
eatures | -7.643 |
heres | -7.047 |
etheless | -6.951 |
uration | -6.765 |
urations | -6.689 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
boy | +5.877 |
boys | +5.556 |
PLEASE | +5.295 |
answered | +5.177 |
pun | +5.136 |
Neg logit contributions | |
eatures | -3.655 |
heres | -3.135 |
etheless | -3.058 |
urations | -2.962 |
uration | -2.961 |
Token | families |
Token ID | 4172 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
boy | +5.128 |
boys | +4.843 |
PLEASE | +4.527 |
pun | +4.479 |
answered | +4.446 |
Neg logit contributions | |
eatures | -5.203 |
heres | -4.733 |
etheless | -4.551 |
uration | -4.491 |
urations | -4.448 |
Token | of |
Token ID | 286 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
boy | +9.119 |
pun | +7.984 |
PLEASE | +7.905 |
boys | +7.875 |
or | +7.681 |
Neg logit contributions | |
eatures | -13.945 |
etheless | -12.578 |
urations | -12.146 |
heres | -12.098 |
uration | -12.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
boy | +5.495 |
boys | +5.219 |
PLEASE | +4.966 |
answered | +4.882 |
pun | +4.836 |
Neg logit contributions | |
eatures | -3.530 |
heres | -3.041 |
etheless | -2.939 |
uration | -2.872 |
urations | -2.867 |
Token | U |
Token ID | 471 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
boy | +4.362 |
boys | +4.110 |
PLEASE | +3.861 |
pun | +3.787 |
answered | +3.771 |
Neg logit contributions | |
eatures | -4.882 |
heres | -4.481 |
etheless | -4.279 |
uration | -4.234 |
urations | -4.180 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
boy | +6.372 |
boys | +6.041 |
PLEASE | +5.751 |
pun | +5.726 |
answered | +5.679 |
Neg logit contributions | |
eatures | -5.609 |
heres | -4.938 |
etheless | -4.859 |
uration | -4.678 |
urations | -4.537 |
Token | S |
Token ID | 50 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
boy | +6.635 |
boys | +6.072 |
PLEASE | +5.640 |
pun | +5.605 |
answered | +5.430 |
Neg logit contributions | |
eatures | -13.600 |
etheless | -12.303 |
heres | -11.844 |
uration | -11.508 |
urations | -11.201 |
Token | � |
Token ID | 247 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
boy | +3.573 |
boys | +3.386 |
PLEASE | +3.226 |
pun | +3.205 |
answered | +3.197 |
Neg logit contributions | |
eatures | -3.570 |
heres | -3.284 |
etheless | -3.129 |
uration | -3.109 |
urations | -3.033 |
Token | ll |
Token ID | 297 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
eatures | +0.376 |
heres | +0.363 |
uration | +0.343 |
urations | +0.331 |
etheless | +0.330 |
Neg logit contributions | |
boy | -0.358 |
boys | -0.336 |
PLEASE | -0.325 |
pun | -0.321 |
answered | -0.319 |
Token | show |
Token ID | 905 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
eatures | +0.456 |
heres | +0.439 |
uration | +0.420 |
etheless | +0.417 |
conjunction | +0.410 |
Neg logit contributions | |
boy | -0.312 |
boys | -0.293 |
answered | -0.276 |
PLEASE | -0.271 |
pun | -0.270 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
boy | +6.685 |
boys | +6.318 |
pun | +6.010 |
PLEASE | +5.946 |
answered | +5.817 |
Neg logit contributions | |
eatures | -5.843 |
heres | -5.178 |
etheless | -5.020 |
uration | -4.975 |
urations | -4.892 |
Token | U |
Token ID | 471 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
boy | +3.411 |
boys | +3.190 |
PLEASE | +3.013 |
pun | +3.008 |
answered | +2.964 |
Neg logit contributions | |
eatures | -4.411 |
heres | -4.106 |
etheless | -3.953 |
uration | -3.932 |
urations | -3.846 |
Token | . |
Token ID | 13 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
boy | +7.539 |
boys | +7.126 |
PLEASE | +6.787 |
pun | +6.753 |
answered | +6.681 |
Neg logit contributions | |
eatures | -7.215 |
etheless | -6.307 |
heres | -6.247 |
uration | -5.946 |
urations | -5.764 |
Token | S |
Token ID | 50 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
boy | +5.169 |
pun | +4.600 |
PLEASE | +4.402 |
boys | +4.216 |
answered | +4.157 |
Neg logit contributions | |
eatures | -16.147 |
etheless | -15.475 |
guiActiveUnfocused | -15.320 |
bidden | -15.239 |
heres | -15.229 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
boy | +7.754 |
boys | +7.113 |
pun | +6.974 |
PLEASE | +6.713 |
answered | +6.527 |
Neg logit contributions | |
eatures | -10.597 |
bidden | -9.700 |
guiActiveUnfocused | -9.682 |
heres | -9.679 |
etheless | -9.566 |
Token | President |
Token ID | 1992 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
boy | +11.700 |
boys | +11.113 |
pun | +10.588 |
PLEASE | +10.585 |
answered | +10.387 |
Neg logit contributions | |
eatures | -9.145 |
heres | -7.878 |
etheless | -7.846 |
uration | -7.836 |
urations | -7.781 |
Token | exactly |
Token ID | 3446 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
boy | +5.829 |
boys | +5.549 |
PLEASE | +5.300 |
pun | +5.266 |
answered | +5.195 |
Neg logit contributions | |
eatures | -3.985 |
heres | -3.558 |
etheless | -3.408 |
uration | -3.405 |
urations | -3.292 |
Token | how |
Token ID | 703 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
eatures | +0.247 |
heres | +0.231 |
uration | +0.220 |
etheless | +0.218 |
urations | +0.213 |
Neg logit contributions | |
boy | -0.230 |
boys | -0.217 |
PLEASE | -0.206 |
pun | -0.204 |
answered | -0.204 |
Token | to |
Token ID | 284 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
heres | +3.374 |
eatures | +3.305 |
uration | +3.180 |
conjunction | +3.167 |
cluded | +3.104 |
Neg logit contributions | |
boy | -3.002 |
boys | -2.847 |
answered | -2.651 |
PLEASE | -2.643 |
pun | -2.597 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
eatures | +2.320 |
heres | +2.236 |
uration | +2.146 |
conjunction | +2.116 |
etheless | +2.086 |
Neg logit contributions | |
boy | -1.829 |
boys | -1.740 |
answered | -1.641 |
pun | -1.587 |
PLEASE | -1.571 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
boy | +4.231 |
boys | +3.970 |
PLEASE | +3.781 |
pun | +3.768 |
answered | +3.725 |
Neg logit contributions | |
eatures | -4.824 |
heres | -4.377 |
uration | -4.215 |
etheless | -4.191 |
urations | -4.116 |
Token | touch |
Token ID | 3638 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
boy | +0.379 |
boys | +0.359 |
PLEASE | +0.346 |
pun | +0.343 |
answered | +0.342 |
Neg logit contributions | |
eatures | -0.296 |
heres | -0.266 |
etheless | -0.253 |
uration | -0.253 |
urations | -0.245 |
Token | with |
Token ID | 351 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
boy | +4.049 |
boys | +3.722 |
PLEASE | +3.590 |
pun | +3.488 |
answered | +3.408 |
Neg logit contributions | |
eatures | -6.477 |
heres | -5.890 |
etheless | -5.631 |
uration | -5.631 |
urations | -5.525 |
Token | family |
Token ID | 1641 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
eatures | +0.516 |
heres | +0.485 |
uration | +0.455 |
etheless | +0.448 |
urations | +0.439 |
Neg logit contributions | |
boy | -0.641 |
boys | -0.610 |
PLEASE | -0.582 |
pun | -0.579 |
answered | -0.576 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
boy | +10.528 |
boys | +9.918 |
PLEASE | +9.472 |
pun | +9.183 |
answered | +9.016 |
Neg logit contributions | |
eatures | -12.259 |
heres | -10.589 |
uration | -10.427 |
etheless | -10.373 |
urations | -10.279 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
boy | +1.584 |
boys | +1.428 |
PLEASE | +1.326 |
pun | +1.281 |
answered | +1.260 |
Neg logit contributions | |
eatures | -4.099 |
heres | -3.866 |
etheless | -3.754 |
uration | -3.746 |
urations | -3.677 |
Token | , |
Token ID | 11 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
boy | +1.173 |
boys | +1.110 |
PLEASE | +1.062 |
pun | +1.049 |
answered | +1.045 |
Neg logit contributions | |
eatures | -1.171 |
heres | -1.079 |
uration | -1.027 |
etheless | -1.018 |
urations | -0.998 |
Token | it |
Token ID | 340 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
boy | +2.140 |
boys | +2.016 |
PLEASE | +1.897 |
pun | +1.890 |
answered | +1.889 |
Neg logit contributions | |
eatures | -2.549 |
heres | -2.403 |
uration | -2.285 |
etheless | -2.265 |
urations | -2.220 |
Token | � |
Token ID | 447 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
eatures | +2.906 |
heres | +2.718 |
uration | +2.624 |
etheless | +2.613 |
urations | +2.571 |
Neg logit contributions | |
boy | -1.876 |
boys | -1.743 |
PLEASE | -1.636 |
pun | -1.625 |
answered | -1.610 |
Token | apps |
Token ID | 6725 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
boy | +5.747 |
boys | +5.446 |
PLEASE | +5.159 |
pun | +5.136 |
answered | +5.065 |
Neg logit contributions | |
eatures | -5.001 |
heres | -4.493 |
etheless | -4.405 |
uration | -4.279 |
urations | -4.165 |
Token | we |
Token ID | 356 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
boy | +1.627 |
boys | +1.519 |
PLEASE | +1.442 |
pun | +1.427 |
answered | +1.414 |
Neg logit contributions | |
eatures | -2.201 |
heres | -2.043 |
uration | -1.959 |
etheless | -1.955 |
urations | -1.915 |
Token | missed |
Token ID | 6825 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
boy | +2.904 |
boys | +2.725 |
PLEASE | +2.587 |
pun | +2.554 |
answered | +2.539 |
Neg logit contributions | |
eatures | -3.573 |
heres | -3.335 |
uration | -3.180 |
etheless | -3.163 |
urations | -3.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
boy | +4.293 |
boys | +4.000 |
PLEASE | +3.879 |
pun | +3.781 |
answered | +3.718 |
Neg logit contributions | |
eatures | -4.984 |
heres | -4.493 |
etheless | -4.365 |
uration | -4.292 |
urations | -4.206 |
Token | Tell |
Token ID | 14026 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
boy | +3.299 |
boys | +3.071 |
PLEASE | +2.924 |
pun | +2.859 |
answered | +2.821 |
Neg logit contributions | |
eatures | -5.022 |
heres | -4.692 |
etheless | -4.525 |
uration | -4.495 |
urations | -4.388 |
Token | us |
Token ID | 514 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
boy | +5.022 |
boys | +4.742 |
PLEASE | +4.441 |
pun | +4.409 |
answered | +4.349 |
Neg logit contributions | |
eatures | -5.610 |
heres | -5.253 |
etheless | -5.094 |
uration | -4.971 |
urations | -4.832 |
Token | what |
Token ID | 644 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
boy | +9.894 |
boys | +9.273 |
PLEASE | +9.152 |
laughing | +8.465 |
pun | +8.216 |
Neg logit contributions | |
eatures | -12.838 |
etheless | -11.639 |
heres | -11.395 |
uration | -11.270 |
ulic | -11.132 |
Token | you |
Token ID | 345 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
boy | +3.692 |
boys | +3.427 |
PLEASE | +3.334 |
pun | +3.164 |
answered | +3.112 |
Neg logit contributions | |
eatures | -5.665 |
heres | -5.254 |
etheless | -5.132 |
uration | -5.103 |
urations | -4.997 |
Token | 'd |
Token ID | 1549 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
boy | +4.451 |
boys | +4.082 |
PLEASE | +3.916 |
pun | +3.760 |
answered | +3.677 |
Neg logit contributions | |
eatures | -8.148 |
heres | -7.580 |
uration | -7.323 |
etheless | -7.305 |
urations | -7.210 |
Token | recommend |
Token ID | 4313 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
boy | +3.160 |
boys | +2.898 |
PLEASE | +2.753 |
pun | +2.668 |
answered | +2.592 |
Neg logit contributions | |
eatures | -5.995 |
heres | -5.657 |
uration | -5.426 |
etheless | -5.404 |
urations | -5.333 |
Token | in |
Token ID | 287 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
boy | +2.800 |
boys | +2.635 |
PLEASE | +2.532 |
pun | +2.485 |
answered | +2.464 |
Neg logit contributions | |
eatures | -3.186 |
heres | -2.950 |
etheless | -2.821 |
uration | -2.816 |
urations | -2.743 |
Token | know |
Token ID | 760 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
boy | +3.488 |
boys | +3.116 |
PLEASE | +3.014 |
pun | +2.906 |
answered | +2.757 |
Neg logit contributions | |
eatures | -7.337 |
heres | -6.830 |
etheless | -6.673 |
uration | -6.597 |
urations | -6.539 |
Token | if |
Token ID | 611 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
boy | +6.239 |
boys | +5.771 |
PLEASE | +5.573 |
pun | +5.333 |
answered | +5.265 |
Neg logit contributions | |
eatures | -7.352 |
heres | -6.553 |
etheless | -6.477 |
uration | -6.301 |
urations | -6.238 |
Token | I |
Token ID | 314 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
boy | +1.124 |
boys | +1.060 |
PLEASE | +1.011 |
pun | +0.995 |
answered | +0.989 |
Neg logit contributions | |
eatures | -1.230 |
heres | -1.137 |
etheless | -1.089 |
uration | -1.085 |
urations | -1.060 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
boy | +4.014 |
boys | +3.745 |
PLEASE | +3.607 |
pun | +3.540 |
answered | +3.524 |
Neg logit contributions | |
eatures | -4.710 |
heres | -4.334 |
etheless | -4.121 |
uration | -4.118 |
urations | -4.044 |
Token | making |
Token ID | 1642 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
boy | +6.810 |
boys | +6.342 |
PLEASE | +6.121 |
pun | +6.076 |
answered | +5.952 |
Neg logit contributions | |
eatures | -6.705 |
heres | -5.994 |
etheless | -5.871 |
uration | -5.702 |
urations | -5.534 |
Token | news |
Token ID | 1705 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
boy | +5.526 |
boys | +5.248 |
PLEASE | +5.031 |
pun | +4.907 |
poke | +4.880 |
Neg logit contributions | |
eatures | -4.236 |
etheless | -3.711 |
heres | -3.704 |
uration | -3.482 |
urations | -3.424 |
Token | here |
Token ID | 994 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
boy | +10.973 |
boys | +10.153 |
PLEASE | +9.223 |
pun | +9.152 |
poke | +8.851 |
Neg logit contributions | |
eatures | -12.936 |
etheless | -11.369 |
heres | -11.098 |
urations | -10.858 |
uration | -10.793 |
Token | ," |
Token ID | 553 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
boy | +3.991 |
boys | +3.721 |
PLEASE | +3.519 |
pun | +3.470 |
answered | +3.375 |
Neg logit contributions | |
eatures | -4.726 |
heres | -4.227 |
etheless | -4.114 |
uration | -4.069 |
urations | -4.011 |
Token | National |
Token ID | 2351 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
boy | +5.026 |
boys | +4.620 |
PLEASE | +4.405 |
answered | +4.381 |
pun | +4.307 |
Neg logit contributions | |
eatures | -5.736 |
etheless | -5.186 |
heres | -5.119 |
uration | -4.946 |
urations | -4.883 |
Token | Review |
Token ID | 6602 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
boy | +1.782 |
boys | +1.652 |
PLEASE | +1.551 |
pun | +1.548 |
answered | +1.530 |
Neg logit contributions | |
eatures | -2.538 |
heres | -2.367 |
etheless | -2.280 |
uration | -2.249 |
urations | -2.204 |
Token | 's |
Token ID | 338 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
boy | +2.281 |
boys | +2.121 |
PLEASE | +1.987 |
pun | +1.972 |
answered | +1.952 |
Neg logit contributions | |
eatures | -3.172 |
heres | -2.942 |
etheless | -2.844 |
uration | -2.821 |
urations | -2.760 |
Token | Google |
Token ID | 3012 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
boy | +2.038 |
boys | +1.927 |
PLEASE | +1.868 |
pun | +1.862 |
answered | +1.831 |
Neg logit contributions | |
eatures | -1.473 |
heres | -1.338 |
uration | -1.269 |
etheless | -1.257 |
urations | -1.232 |
Token | disclosed |
Token ID | 16404 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
boy | +1.178 |
boys | +1.112 |
pun | +1.063 |
PLEASE | +1.062 |
answered | +1.054 |
Neg logit contributions | |
eatures | -1.076 |
heres | -0.983 |
uration | -0.936 |
etheless | -0.933 |
urations | -0.915 |
Token | that |
Token ID | 326 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
eatures | +0.673 |
heres | +0.621 |
uration | +0.592 |
etheless | +0.586 |
urations | +0.575 |
Neg logit contributions | |
boy | -0.770 |
boys | -0.729 |
PLEASE | -0.698 |
pun | -0.695 |
answered | -0.687 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
eatures | +1.130 |
heres | +1.046 |
uration | +1.000 |
etheless | +0.992 |
urations | +0.975 |
Neg logit contributions | |
boy | -1.136 |
boys | -1.074 |
PLEASE | -1.025 |
pun | -1.016 |
answered | -1.006 |
Token | U |
Token ID | 471 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
boy | +0.320 |
boys | +0.301 |
PLEASE | +0.285 |
pun | +0.282 |
answered | +0.280 |
Neg logit contributions | |
eatures | -0.413 |
heres | -0.387 |
uration | -0.370 |
etheless | -0.368 |
urations | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
boy | +5.471 |
boys | +5.184 |
PLEASE | +4.937 |
pun | +4.921 |
answered | +4.868 |
Neg logit contributions | |
eatures | -4.772 |
heres | -4.239 |
etheless | -4.165 |
uration | -4.010 |
urations | -3.895 |
Token | S |
Token ID | 50 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
boy | +4.963 |
pun | +4.161 |
boys | +4.012 |
PLEASE | +3.858 |
Beat | +3.626 |
Neg logit contributions | |
eatures | -16.302 |
etheless | -16.202 |
guiActiveUnfocused | -15.504 |
uration | -15.332 |
heres | -15.303 |
Token | . |
Token ID | 13 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
boy | +6.465 |
pun | +5.805 |
boys | +5.544 |
PLEASE | +5.519 |
beat | +5.340 |
Neg logit contributions | |
eatures | -9.456 |
etheless | -8.773 |
heres | -8.493 |
guiActiveUnfocused | -8.260 |
urations | -8.153 |
Token | Federal |
Token ID | 5618 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
boy | +8.569 |
pun | +7.729 |
boys | +7.674 |
PLEASE | +7.589 |
answered | +7.324 |
Neg logit contributions | |
eatures | -10.999 |
etheless | -9.554 |
heres | -9.526 |
urations | -9.443 |
uration | -9.277 |
Token | Trade |
Token ID | 9601 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
boy | +1.787 |
boys | +1.656 |
PLEASE | +1.554 |
pun | +1.553 |
answered | +1.523 |
Neg logit contributions | |
eatures | -3.074 |
heres | -2.893 |
etheless | -2.754 |
uration | -2.749 |
urations | -2.706 |
Token | Commission |
Token ID | 4513 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
boy | +2.263 |
boys | +2.099 |
pun | +1.966 |
PLEASE | +1.963 |
answered | +1.932 |
Neg logit contributions | |
eatures | -3.681 |
heres | -3.459 |
etheless | -3.319 |
uration | -3.303 |
urations | -3.236 |
Token | long |
Token ID | 890 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
boy | +5.402 |
boys | +5.071 |
PLEASE | +4.904 |
pun | +4.790 |
answered | +4.677 |
Neg logit contributions | |
eatures | -4.975 |
etheless | -4.437 |
heres | -4.325 |
uration | -4.085 |
urations | -4.063 |
Token | - |
Token ID | 12 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
boy | +0.660 |
boys | +0.618 |
PLEASE | +0.581 |
pun | +0.576 |
answered | +0.572 |
Neg logit contributions | |
eatures | -0.849 |
heres | -0.785 |
etheless | -0.753 |
uration | -0.752 |
urations | -0.732 |
Token | prom |
Token ID | 16963 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
boy | +0.664 |
boys | +0.624 |
pun | +0.589 |
PLEASE | +0.586 |
answered | +0.585 |
Neg logit contributions | |
eatures | -0.755 |
heres | -0.694 |
uration | -0.666 |
etheless | -0.660 |
conjunction | -0.647 |
Token | ised |
Token ID | 1417 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
boy | +1.092 |
boys | +1.024 |
pun | +0.974 |
answered | +0.974 |
PLEASE | +0.974 |
Neg logit contributions | |
eatures | -1.047 |
heres | -0.964 |
etheless | -0.920 |
uration | -0.904 |
urations | -0.882 |
Token | wall |
Token ID | 3355 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
eatures | +3.461 |
heres | +3.322 |
uration | +3.148 |
conjunction | +3.094 |
urations | +3.048 |
Neg logit contributions | |
boy | -3.071 |
boys | -2.913 |
answered | -2.817 |
PLEASE | -2.761 |
pun | -2.760 |
Token | along |
Token ID | 1863 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
boy | +3.430 |
boys | +3.183 |
PLEASE | +3.041 |
pun | +2.960 |
answered | +2.893 |
Neg logit contributions | |
eatures | -4.482 |
heres | -4.135 |
etheless | -4.019 |
urations | -3.940 |
uration | -3.927 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
eatures | +4.385 |
heres | +4.022 |
uration | +3.662 |
conjunction | +3.467 |
cluded | +3.375 |
Neg logit contributions | |
boy | -12.021 |
boys | -11.712 |
pun | -11.313 |
PLEASE | -11.283 |
answered | -11.261 |
Token | U |
Token ID | 471 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
eatures | +0.647 |
heres | +0.596 |
etheless | +0.570 |
uration | +0.568 |
urations | +0.555 |
Neg logit contributions | |
boy | -0.613 |
boys | -0.578 |
PLEASE | -0.553 |
pun | -0.545 |
answered | -0.541 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
boy | +2.199 |
boys | +2.104 |
PLEASE | +2.029 |
answered | +2.015 |
pun | +2.008 |
Neg logit contributions | |
eatures | -1.532 |
heres | -1.476 |
uration | -1.383 |
urations | -1.328 |
cluded | -1.321 |
Token | S |
Token ID | 50 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
boy | +4.822 |
boys | +4.457 |
PLEASE | +4.201 |
pun | +4.142 |
answered | +4.081 |
Neg logit contributions | |
eatures | -8.374 |
heres | -7.617 |
etheless | -7.582 |
uration | -7.336 |
urations | -7.155 |
Token | .- |
Token ID | 7874 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
eatures | +0.043 |
heres | +0.040 |
etheless | +0.039 |
uration | +0.038 |
urations | +0.038 |
Neg logit contributions | |
boy | -0.024 |
boys | -0.022 |
PLEASE | -0.021 |
pun | -0.021 |
answered | -0.020 |
Token | movie |
Token ID | 3807 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
eatures | +3.097 |
heres | +2.935 |
uration | +2.789 |
conjunction | +2.755 |
occurred | +2.717 |
Neg logit contributions | |
boy | -2.613 |
boys | -2.517 |
pun | -2.343 |
PLEASE | -2.317 |
answered | -2.304 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
boy | +1.157 |
boys | +1.080 |
PLEASE | +1.041 |
pun | +1.024 |
answered | +1.019 |
Neg logit contributions | |
eatures | -1.233 |
heres | -1.143 |
etheless | -1.097 |
uration | -1.089 |
urations | -1.066 |
Token | Sn |
Token ID | 5489 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
boy | +0.703 |
boys | +0.640 |
PLEASE | +0.606 |
pun | +0.589 |
answered | +0.585 |
Neg logit contributions | |
eatures | -1.454 |
heres | -1.372 |
etheless | -1.325 |
uration | -1.325 |
urations | -1.299 |
Token | atched |
Token ID | 14265 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
eatures | +1.296 |
heres | +1.180 |
uration | +1.094 |
etheless | +1.073 |
urations | +1.048 |
Neg logit contributions | |
boy | -2.276 |
boys | -2.183 |
PLEASE | -2.107 |
pun | -2.091 |
answered | -2.090 |
Token | , |
Token ID | 11 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
eatures | +2.229 |
heres | +2.048 |
uration | +1.936 |
etheless | +1.930 |
urations | +1.873 |
Neg logit contributions | |
boy | -2.738 |
boys | -2.603 |
PLEASE | -2.496 |
pun | -2.477 |
answered | -2.463 |
Token | Schumer |
Token ID | 26107 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
eatures | +1.657 |
heres | +1.557 |
uration | +1.490 |
etheless | +1.481 |
urations | +1.453 |
Neg logit contributions | |
boy | -1.210 |
boys | -1.134 |
PLEASE | -1.070 |
pun | -1.059 |
answered | -1.054 |
Token | is |
Token ID | 318 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
heres | +7.599 |
eatures | +7.596 |
occurred | +7.150 |
conjunction | +6.930 |
uration | +6.907 |
Neg logit contributions | |
boy | -8.041 |
boys | -7.768 |
PLEASE | -7.262 |
answered | -7.212 |
pun | -7.177 |
Token | featured |
Token ID | 8096 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
eatures | +2.001 |
heres | +1.885 |
uration | +1.769 |
etheless | +1.756 |
cluded | +1.736 |
Neg logit contributions | |
boy | -1.930 |
boys | -1.843 |
PLEASE | -1.746 |
answered | -1.744 |
pun | -1.726 |
Token | wielding |
Token ID | 33949 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
eatures | +2.404 |
heres | +2.252 |
uration | +2.145 |
etheless | +2.131 |
urations | +2.087 |
Neg logit contributions | |
boy | -2.028 |
boys | -1.913 |
PLEASE | -1.814 |
pun | -1.795 |
answered | -1.791 |
Token | a |
Token ID | 257 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
eatures | +2.322 |
heres | +2.116 |
uration | +1.979 |
etheless | +1.966 |
urations | +1.904 |
Neg logit contributions | |
boy | -3.543 |
boys | -3.386 |
PLEASE | -3.257 |
pun | -3.234 |
answered | -3.222 |
Token | gun |
Token ID | 2485 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
boy | +0.682 |
boys | +0.644 |
PLEASE | +0.617 |
pun | +0.610 |
answered | +0.606 |
Neg logit contributions | |
eatures | -0.670 |
heres | -0.619 |
etheless | -0.586 |
uration | -0.586 |
urations | -0.570 |
Token | Ban |
Token ID | 10274 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
boy | +0.273 |
boys | +0.258 |
PLEASE | +0.245 |
pun | +0.243 |
answered | +0.242 |
Neg logit contributions | |
eatures | -0.306 |
heres | -0.285 |
uration | -0.272 |
etheless | -0.271 |
urations | -0.265 |
Token | u |
Token ID | 84 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
boy | +1.354 |
boys | +1.263 |
pun | +1.230 |
PLEASE | +1.200 |
answered | +1.194 |
Neg logit contributions | |
eatures | -1.609 |
etheless | -1.488 |
heres | -1.482 |
uration | -1.422 |
guiActiveUnfocused | -1.399 |
Token | Qur |
Token ID | 17599 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
eatures | +2.426 |
heres | +2.278 |
uration | +2.180 |
etheless | +2.172 |
urations | +2.127 |
Neg logit contributions | |
boy | -1.773 |
boys | -1.662 |
PLEASE | -1.570 |
pun | -1.553 |
answered | -1.545 |
Token | ay |
Token ID | 323 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
eatures | +0.501 |
heres | +0.449 |
etheless | +0.438 |
uration | +0.420 |
conjunction | +0.416 |
Neg logit contributions | |
boy | -0.654 |
boys | -0.622 |
answered | -0.596 |
pun | -0.593 |
PLEASE | -0.589 |
Token | za |
Token ID | 4496 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
eatures | +1.713 |
heres | +1.625 |
uration | +1.525 |
urations | +1.470 |
cluded | +1.464 |
Neg logit contributions | |
boy | -2.801 |
boys | -2.676 |
PLEASE | -2.617 |
answered | -2.593 |
pun | -2.577 |
Token | which |
Token ID | 543 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
eatures | +3.105 |
heres | +2.931 |
uration | +2.765 |
etheless | +2.738 |
urations | +2.692 |
Neg logit contributions | |
boy | -2.940 |
boys | -2.772 |
PLEASE | -2.644 |
pun | -2.621 |
answered | -2.620 |
Token | consisted |
Token ID | 19954 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
eatures | +6.986 |
heres | +6.634 |
occurred | +6.160 |
uration | +6.135 |
etheless | +6.025 |
Neg logit contributions | |
boy | -8.537 |
boys | -8.156 |
PLEASE | -7.757 |
answered | -7.730 |
pun | -7.687 |
Token | of |
Token ID | 286 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
eatures | +8.350 |
heres | +7.786 |
uration | +7.382 |
etheless | +7.358 |
urations | +7.137 |
Neg logit contributions | |
boy | -8.040 |
boys | -7.629 |
PLEASE | -7.299 |
answered | -7.295 |
pun | -7.209 |
Token | 1500 |
Token ID | 20007 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
eatures | +4.905 |
heres | +4.733 |
uration | +4.407 |
conjunction | +4.352 |
etheless | +4.336 |
Neg logit contributions | |
boy | -5.154 |
boys | -4.869 |
answered | -4.730 |
PLEASE | -4.705 |
pun | -4.655 |
Token | swords |
Token ID | 19735 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
eatures | +0.632 |
heres | +0.594 |
uration | +0.564 |
etheless | +0.559 |
urations | +0.548 |
Neg logit contributions | |
boy | -0.555 |
boys | -0.523 |
PLEASE | -0.497 |
pun | -0.492 |
answered | -0.491 |
Token | , |
Token ID | 11 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
boy | +0.288 |
boys | +0.272 |
pun | +0.259 |
PLEASE | +0.257 |
answered | +0.254 |
Neg logit contributions | |
eatures | -0.317 |
heres | -0.289 |
uration | -0.278 |
etheless | -0.277 |
urations | -0.272 |
Token | is |
Token ID | 318 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
eatures | +4.392 |
heres | +4.173 |
conjunction | +3.905 |
uration | +3.871 |
occurred | +3.851 |
Neg logit contributions | |
boy | -5.752 |
boys | -5.513 |
pun | -5.341 |
answered | -5.289 |
PLEASE | -5.281 |
Token | not |
Token ID | 407 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
eatures | +2.151 |
heres | +2.007 |
uration | +1.910 |
etheless | +1.899 |
urations | +1.857 |
Neg logit contributions | |
boy | -1.978 |
boys | -1.868 |
PLEASE | -1.777 |
pun | -1.761 |
answered | -1.753 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
eatures | +0.044 |
heres | +0.038 |
uration | +0.036 |
etheless | +0.035 |
urations | +0.034 |
Neg logit contributions | |
boy | -0.073 |
boys | -0.070 |
PLEASE | -0.068 |
answered | -0.067 |
pun | -0.067 |
Token | case |
Token ID | 1339 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
boy | +1.226 |
boys | +1.161 |
PLEASE | +1.104 |
pun | +1.093 |
answered | +1.088 |
Neg logit contributions | |
eatures | -1.204 |
heres | -1.103 |
uration | -1.054 |
etheless | -1.050 |
urations | -1.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
eatures | +6.184 |
heres | +6.107 |
etheless | +5.665 |
uration | +5.621 |
occurred | +5.490 |
Neg logit contributions | |
boy | -7.121 |
boys | -6.787 |
pun | -6.494 |
answered | -6.493 |
PLEASE | -6.448 |
Token | Instead |
Token ID | 5455 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
eatures | +0.481 |
heres | +0.460 |
uration | +0.438 |
etheless | +0.433 |
urations | +0.429 |
Neg logit contributions | |
boy | -0.357 |
boys | -0.333 |
pun | -0.314 |
answered | -0.313 |
PLEASE | -0.313 |
Token | , |
Token ID | 11 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
eatures | +7.044 |
heres | +6.466 |
uration | +6.030 |
etheless | +6.003 |
urations | +5.824 |
Neg logit contributions | |
boy | -9.763 |
boys | -9.294 |
PLEASE | -8.950 |
pun | -8.904 |
answered | -8.889 |
Token | the |
Token ID | 262 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
eatures | +1.349 |
heres | +1.244 |
uration | +1.178 |
etheless | +1.170 |
urations | +1.139 |
Neg logit contributions | |
boy | -1.591 |
boys | -1.513 |
PLEASE | -1.449 |
pun | -1.435 |
answered | -1.430 |
Token | greater |
Token ID | 3744 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
eatures | +2.539 |
heres | +2.400 |
uration | +2.257 |
etheless | +2.246 |
conjunction | +2.221 |
Neg logit contributions | |
boy | -2.526 |
boys | -2.374 |
PLEASE | -2.273 |
pun | -2.264 |
answered | -2.242 |
Token | the |
Token ID | 262 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
eatures | +1.361 |
heres | +1.236 |
uration | +1.172 |
etheless | +1.157 |
urations | +1.122 |
Neg logit contributions | |
boy | -1.869 |
boys | -1.785 |
PLEASE | -1.709 |
pun | -1.693 |
answered | -1.683 |
Token | age |
Token ID | 2479 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
eatures | +2.605 |
heres | +2.483 |
uration | +2.343 |
etheless | +2.329 |
conjunction | +2.323 |
Neg logit contributions | |
boy | -2.371 |
boys | -2.240 |
PLEASE | -2.136 |
answered | -2.133 |
pun | -2.125 |
Token | military |
Token ID | 2422 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
eatures | +0.256 |
heres | +0.237 |
uration | +0.224 |
etheless | +0.223 |
urations | +0.217 |
Neg logit contributions | |
boy | -0.297 |
boys | -0.282 |
PLEASE | -0.270 |
pun | -0.268 |
answered | -0.267 |
Token | forces |
Token ID | 3386 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
eatures | +0.073 |
heres | +0.067 |
uration | +0.062 |
etheless | +0.062 |
urations | +0.060 |
Neg logit contributions | |
boy | -0.119 |
boys | -0.114 |
PLEASE | -0.110 |
pun | -0.109 |
answered | -0.109 |
Token | in |
Token ID | 287 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
eatures | +1.383 |
heres | +1.276 |
uration | +1.199 |
etheless | +1.190 |
urations | +1.158 |
Neg logit contributions | |
boy | -1.819 |
boys | -1.734 |
PLEASE | -1.662 |
pun | -1.651 |
answered | -1.646 |
Token | the |
Token ID | 262 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
eatures | +2.915 |
heres | +2.711 |
uration | +2.507 |
etheless | +2.482 |
conjunction | +2.444 |
Neg logit contributions | |
boy | -4.347 |
boys | -4.162 |
PLEASE | -3.998 |
pun | -3.967 |
answered | -3.962 |
Token | R |
Token ID | 371 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
boy | +0.187 |
boys | +0.177 |
PLEASE | +0.168 |
pun | +0.167 |
answered | +0.166 |
Neg logit contributions | |
eatures | -0.197 |
heres | -0.184 |
uration | -0.175 |
etheless | -0.174 |
urations | -0.170 |
Token | SI |
Token ID | 11584 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
heres | +2.687 |
eatures | +2.587 |
uration | +2.501 |
urations | +2.416 |
cluded | +2.383 |
Neg logit contributions | |
boy | -2.953 |
boys | -2.860 |
answered | -2.736 |
sacrific | -2.717 |
PLEASE | -2.715 |
Token | also |
Token ID | 635 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
eatures | +7.063 |
heres | +6.940 |
occurred | +6.724 |
cluded | +6.460 |
conjunction | +6.451 |
Neg logit contributions | |
boy | -8.018 |
boys | -7.681 |
pun | -7.429 |
answered | -7.340 |
PLEASE | -7.270 |
Token | fought |
Token ID | 8350 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
eatures | +4.225 |
heres | +4.038 |
occurred | +3.817 |
uration | +3.713 |
etheless | +3.698 |
Neg logit contributions | |
boy | -6.107 |
boys | -5.876 |
PLEASE | -5.612 |
answered | -5.582 |
pun | -5.568 |
Token | against |
Token ID | 1028 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
boy | +3.735 |
boys | +3.473 |
PLEASE | +3.333 |
pun | +3.276 |
answered | +3.201 |
Neg logit contributions | |
eatures | -4.278 |
heres | -3.889 |
etheless | -3.803 |
uration | -3.796 |
urations | -3.693 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
eatures | +0.575 |
heres | +0.515 |
uration | +0.489 |
etheless | +0.487 |
urations | +0.471 |
Neg logit contributions | |
boy | -0.836 |
boys | -0.794 |
PLEASE | -0.765 |
pun | -0.764 |
answered | -0.754 |
Token | Allies |
Token ID | 32430 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
boy | +2.510 |
boys | +2.357 |
PLEASE | +2.251 |
pun | +2.239 |
answered | +2.195 |
Neg logit contributions | |
eatures | -2.825 |
heres | -2.570 |
etheless | -2.483 |
uration | -2.476 |
urations | -2.408 |
Token | of |
Token ID | 286 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
boy | +1.918 |
boys | +1.780 |
PLEASE | +1.675 |
pun | +1.660 |
answered | +1.616 |
Neg logit contributions | |
eatures | -2.378 |
heres | -2.168 |
etheless | -2.087 |
uration | -2.067 |
urations | -2.053 |
Token | corn |
Token ID | 11676 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
eatures | +2.095 |
heres | +1.985 |
uration | +1.885 |
etheless | +1.866 |
urations | +1.827 |
Neg logit contributions | |
boy | -1.769 |
boys | -1.664 |
PLEASE | -1.585 |
pun | -1.573 |
answered | -1.568 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
eatures | +1.432 |
heres | +1.344 |
uration | +1.284 |
etheless | +1.277 |
urations | +1.251 |
Neg logit contributions | |
boy | -1.115 |
boys | -1.047 |
PLEASE | -0.991 |
pun | -0.981 |
answered | -0.976 |
Token | However |
Token ID | 2102 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
boy | +1.081 |
boys | +1.013 |
answered | +0.952 |
pun | +0.952 |
PLEASE | +0.942 |
Neg logit contributions | |
eatures | -1.486 |
heres | -1.426 |
uration | -1.363 |
etheless | -1.335 |
cluded | -1.329 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
eatures | +6.170 |
heres | +5.783 |
uration | +5.438 |
etheless | +5.353 |
urations | +5.227 |
Neg logit contributions | |
boy | -7.549 |
boys | -7.185 |
pun | -6.860 |
answered | -6.859 |
PLEASE | -6.798 |
Token | very |
Token ID | 845 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
boy | +0.123 |
boys | +0.117 |
PLEASE | +0.110 |
pun | +0.110 |
answered | +0.110 |
Neg logit contributions | |
eatures | -0.121 |
heres | -0.114 |
uration | -0.108 |
etheless | -0.107 |
urations | -0.104 |
Token | few |
Token ID | 1178 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
eatures | +3.601 |
heres | +3.418 |
uration | +3.262 |
etheless | +3.187 |
conjunction | +3.180 |
Neg logit contributions | |
boy | -3.801 |
boys | -3.613 |
pun | -3.467 |
answered | -3.461 |
PLEASE | -3.397 |
Token | will |
Token ID | 481 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
eatures | +2.647 |
heres | +2.498 |
uration | +2.371 |
etheless | +2.358 |
conjunction | +2.318 |
Neg logit contributions | |
boy | -2.293 |
boys | -2.161 |
pun | -2.060 |
answered | -2.042 |
PLEASE | -2.023 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
boy | +2.891 |
boys | +2.668 |
PLEASE | +2.593 |
pun | +2.497 |
answered | +2.434 |
Neg logit contributions | |
eatures | -4.175 |
heres | -3.835 |
etheless | -3.669 |
uration | -3.662 |
urations | -3.636 |
Token | be |
Token ID | 307 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
boy | +2.941 |
boys | +2.702 |
PLEASE | +2.629 |
pun | +2.516 |
answered | +2.441 |
Neg logit contributions | |
eatures | -4.706 |
heres | -4.338 |
etheless | -4.162 |
uration | -4.147 |
urations | -4.125 |
Token | able |
Token ID | 1498 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
boy | +2.840 |
boys | +2.644 |
PLEASE | +2.472 |
pun | +2.459 |
answered | +2.433 |
Neg logit contributions | |
eatures | -4.065 |
heres | -3.750 |
etheless | -3.618 |
uration | -3.609 |
urations | -3.540 |
Token | this |
Token ID | 428 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
eatures | +0.596 |
heres | +0.542 |
etheless | +0.515 |
uration | +0.514 |
urations | +0.498 |
Neg logit contributions | |
boy | -0.771 |
boys | -0.731 |
PLEASE | -0.702 |
pun | -0.696 |
answered | -0.689 |
Token | little |
Token ID | 1310 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
eatures | +0.881 |
heres | +0.821 |
uration | +0.779 |
etheless | +0.774 |
urations | +0.756 |
Neg logit contributions | |
boy | -0.878 |
boys | -0.831 |
PLEASE | -0.793 |
pun | -0.786 |
answered | -0.783 |
Token | Sh |
Token ID | 911 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
boy | +0.677 |
boys | +0.637 |
PLEASE | +0.605 |
pun | +0.599 |
answered | +0.595 |
Neg logit contributions | |
eatures | -0.772 |
heres | -0.719 |
uration | -0.686 |
etheless | -0.683 |
urations | -0.669 |
Token | akespe |
Token ID | 20621 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
boy | +0.559 |
boys | +0.528 |
PLEASE | +0.502 |
pun | +0.501 |
answered | +0.495 |
Neg logit contributions | |
eatures | -0.516 |
heres | -0.473 |
etheless | -0.458 |
uration | -0.448 |
urations | -0.437 |
Token | arian |
Token ID | 3699 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
eatures | +0.184 |
heres | +0.167 |
etheless | +0.165 |
uration | +0.157 |
conjunction | +0.155 |
Neg logit contributions | |
boy | -0.216 |
boys | -0.203 |
pun | -0.195 |
PLEASE | -0.193 |
answered | -0.191 |
Token | drama |
Token ID | 10512 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
eatures | +1.721 |
heres | +1.608 |
uration | +1.529 |
etheless | +1.516 |
conjunction | +1.487 |
Neg logit contributions | |
boy | -1.634 |
boys | -1.551 |
PLEASE | -1.477 |
answered | -1.461 |
pun | -1.461 |
Token | : |
Token ID | 25 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
eatures | +2.827 |
heres | +2.620 |
uration | +2.468 |
etheless | +2.452 |
urations | +2.385 |
Neg logit contributions | |
boy | -3.355 |
boys | -3.192 |
PLEASE | -3.056 |
pun | -3.034 |
answered | -3.024 |
Token | the |
Token ID | 262 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
eatures | +1.003 |
heres | +0.931 |
uration | +0.881 |
etheless | +0.876 |
urations | +0.854 |
Neg logit contributions | |
boy | -1.093 |
boys | -1.037 |
PLEASE | -0.991 |
pun | -0.983 |
answered | -0.979 |
Token | 1950 |
Token ID | 11445 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
eatures | +1.409 |
heres | +1.320 |
uration | +1.255 |
etheless | +1.241 |
urations | +1.217 |
Neg logit contributions | |
boy | -1.345 |
boys | -1.271 |
PLEASE | -1.209 |
pun | -1.201 |
answered | -1.199 |
Token | NFL |
Token ID | 5134 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
boy | +1.158 |
boys | +1.084 |
PLEASE | +1.020 |
pun | +1.006 |
answered | +0.988 |
Neg logit contributions | |
eatures | -1.600 |
heres | -1.492 |
etheless | -1.436 |
uration | -1.426 |
urations | -1.398 |
Token | Championship |
Token ID | 10749 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
boy | +3.994 |
boys | +3.724 |
PLEASE | +3.516 |
pun | +3.454 |
answered | +3.321 |
Neg logit contributions | |
eatures | -5.710 |
heres | -5.331 |
etheless | -5.163 |
uration | -5.071 |
urations | -5.022 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
eatures | +2.088 |
heres | +2.014 |
uration | +1.919 |
conjunction | +1.879 |
cluded | +1.878 |
Neg logit contributions | |
boy | -1.873 |
boys | -1.789 |
answered | -1.704 |
pun | -1.686 |
PLEASE | -1.654 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
boy | +3.534 |
boys | +3.223 |
PLEASE | +3.070 |
pun | +2.993 |
answered | +2.929 |
Neg logit contributions | |
eatures | -5.204 |
etheless | -4.784 |
heres | -4.781 |
uration | -4.618 |
urations | -4.508 |
Token | The |
Token ID | 383 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
boy | +0.738 |
boys | +0.692 |
PLEASE | +0.657 |
pun | +0.645 |
answered | +0.644 |
Neg logit contributions | |
eatures | -0.958 |
heres | -0.897 |
etheless | -0.855 |
uration | -0.854 |
urations | -0.834 |
Token | 57 |
Token ID | 7632 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
eatures | +0.968 |
heres | +0.914 |
uration | +0.875 |
etheless | +0.855 |
conjunction | +0.849 |
Neg logit contributions | |
boy | -0.907 |
boys | -0.858 |
PLEASE | -0.818 |
pun | -0.814 |
answered | -0.813 |
Token | - |
Token ID | 12 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
boy | +0.055 |
boys | +0.051 |
PLEASE | +0.048 |
pun | +0.047 |
answered | +0.047 |
Neg logit contributions | |
eatures | -0.083 |
heres | -0.076 |
etheless | -0.073 |
uration | -0.072 |
conjunction | -0.071 |
Token | year |
Token ID | 1941 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
boy | +1.431 |
boys | +1.346 |
PLEASE | +1.299 |
sacrific | +1.274 |
pun | +1.248 |
Neg logit contributions | |
eatures | -2.544 |
heres | -2.512 |
uration | -2.413 |
urations | -2.345 |
cluded | -2.339 |
Token | - |
Token ID | 12 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
eatures | +0.547 |
heres | +0.547 |
uration | +0.515 |
conjunction | +0.504 |
occurred | +0.495 |
Neg logit contributions | |
boy | -0.589 |
boys | -0.565 |
pun | -0.544 |
PLEASE | -0.542 |
answered | -0.535 |
Token | old |
Token ID | 727 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
boy | +4.305 |
boys | +4.131 |
PLEASE | +4.000 |
pun | +3.964 |
answered | +3.950 |
Neg logit contributions | |
eatures | -2.526 |
heres | -2.352 |
uration | -2.183 |
etheless | -2.129 |
urations | -2.091 |
Token | retired |
Token ID | 9880 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
eatures | +2.376 |
heres | +2.234 |
uration | +2.121 |
etheless | +2.075 |
urations | +2.051 |
Neg logit contributions | |
boy | -2.616 |
boys | -2.499 |
pun | -2.381 |
PLEASE | -2.377 |
answered | -2.357 |
Token | lieutenant |
Token ID | 30269 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
boy | +0.643 |
boys | +0.604 |
PLEASE | +0.572 |
pun | +0.566 |
answered | +0.564 |
Neg logit contributions | |
eatures | -0.806 |
heres | -0.755 |
uration | -0.721 |
etheless | -0.718 |
urations | -0.703 |
Token | general |
Token ID | 2276 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
eatures | +1.493 |
heres | +1.399 |
uration | +1.322 |
etheless | +1.313 |
urations | +1.282 |
Neg logit contributions | |
boy | -1.557 |
boys | -1.485 |
PLEASE | -1.410 |
pun | -1.404 |
answered | -1.398 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
eatures | +8.028 |
heres | +7.763 |
uration | +7.315 |
etheless | +7.279 |
urations | +7.113 |
Neg logit contributions | |
boy | -6.151 |
boys | -5.882 |
answered | -5.499 |
PLEASE | -5.495 |
pun | -5.446 |
Token | Since |
Token ID | 4619 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
eatures | +0.450 |
heres | +0.439 |
uration | +0.418 |
cluded | +0.411 |
urations | +0.409 |
Neg logit contributions | |
boy | -0.320 |
boys | -0.302 |
answered | -0.285 |
pun | -0.284 |
PLEASE | -0.278 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
eatures | +4.967 |
heres | +4.704 |
uration | +4.462 |
conjunction | +4.341 |
cluded | +4.301 |
Neg logit contributions | |
boy | -5.050 |
boys | -4.809 |
answered | -4.653 |
pun | -4.644 |
PLEASE | -4.637 |
Token | early |
Token ID | 1903 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
eatures | +0.283 |
heres | +0.264 |
uration | +0.249 |
etheless | +0.245 |
urations | +0.241 |
Neg logit contributions | |
boy | -0.323 |
boys | -0.307 |
PLEASE | -0.294 |
answered | -0.292 |
pun | -0.292 |
Token | days |
Token ID | 1528 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
eatures | +4.008 |
heres | +3.818 |
uration | +3.535 |
conjunction | +3.454 |
etheless | +3.438 |
Neg logit contributions | |
boy | -4.446 |
boys | -4.252 |
answered | -4.141 |
PLEASE | -4.121 |
pun | -4.080 |
Token | of |
Token ID | 286 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
eatures | +2.937 |
heres | +2.738 |
uration | +2.608 |
etheless | +2.597 |
urations | +2.539 |
Neg logit contributions | |
boy | -2.740 |
boys | -2.582 |
PLEASE | -2.454 |
pun | -2.435 |
answered | -2.414 |
Token | modern |
Token ID | 3660 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
eatures | +3.994 |
heres | +3.766 |
uration | +3.568 |
etheless | +3.508 |
conjunction | +3.464 |
Neg logit contributions | |
boy | -3.935 |
boys | -3.756 |
PLEASE | -3.589 |
answered | -3.565 |
pun | -3.548 |
Token | ism |
Token ID | 1042 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
eatures | +0.656 |
heres | +0.609 |
uration | +0.579 |
etheless | +0.577 |
urations | +0.564 |
Neg logit contributions | |
boy | -0.628 |
boys | -0.594 |
PLEASE | -0.565 |
pun | -0.560 |
answered | -0.557 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
eatures | +1.382 |
heres | +1.265 |
etheless | +1.206 |
uration | +1.204 |
urations | +1.172 |
Neg logit contributions | |
boy | -1.587 |
boys | -1.502 |
PLEASE | -1.439 |
pun | -1.424 |
answered | -1.415 |
Token | there |
Token ID | 612 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
boy | +1.532 |
boys | +1.448 |
PLEASE | +1.383 |
pun | +1.369 |
answered | +1.360 |
Neg logit contributions | |
eatures | -1.553 |
heres | -1.441 |
uration | -1.372 |
etheless | -1.367 |
urations | -1.334 |
Token | has |
Token ID | 468 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
eatures | +1.156 |
heres | +1.059 |
uration | +0.999 |
etheless | +0.998 |
urations | +0.972 |
Neg logit contributions | |
boy | -1.387 |
boys | -1.318 |
PLEASE | -1.254 |
pun | -1.241 |
answered | -1.235 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
eatures | +1.173 |
heres | +1.084 |
etheless | +1.052 |
uration | +1.051 |
urations | +1.029 |
Neg logit contributions | |
boy | -0.656 |
boys | -0.605 |
PLEASE | -0.574 |
pun | -0.553 |
answered | -0.549 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
heres | +0.495 |
uration | +0.467 |
cluded | +0.461 |
urations | +0.455 |
conjunction | +0.454 |
Neg logit contributions | |
sacrific | -0.447 |
boy | -0.446 |
boys | -0.429 |
answered | -0.412 |
pun | -0.407 |
Token | D |
Token ID | 35 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
eatures | +1.020 |
heres | +1.011 |
uration | +0.950 |
urations | +0.926 |
cluded | +0.926 |
Neg logit contributions | |
boy | -0.854 |
boys | -0.806 |
PLEASE | -0.776 |
pun | -0.759 |
answered | -0.759 |
Token | ella |
Token ID | 12627 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
heres | +2.109 |
eatures | +2.095 |
uration | +2.028 |
urations | +1.963 |
cluded | +1.808 |
Neg logit contributions | |
boy | -5.080 |
boys | -4.992 |
sacrific | -4.907 |
pun | -4.843 |
answered | -4.832 |
Token | Vol |
Token ID | 4709 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
heres | +2.948 |
uration | +2.759 |
eatures | +2.741 |
conjunction | +2.680 |
urations | +2.653 |
Neg logit contributions | |
boy | -4.245 |
boys | -4.099 |
answered | -4.037 |
sacrific | -3.976 |
pun | -3.972 |
Token | pe |
Token ID | 431 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
heres | +2.587 |
uration | +2.437 |
eatures | +2.385 |
cluded | +2.370 |
urations | +2.352 |
Neg logit contributions | |
sacrific | -2.286 |
boy | -2.255 |
boys | -2.196 |
PLEASE | -2.157 |
answered | -2.113 |
Token | agrees |
Token ID | 14386 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
eatures | +2.645 |
heres | +2.549 |
uration | +2.400 |
etheless | +2.340 |
urations | +2.331 |
Neg logit contributions | |
boy | -2.394 |
boys | -2.273 |
PLEASE | -2.170 |
answered | -2.145 |
pun | -2.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
boy | +1.141 |
boys | +1.082 |
PLEASE | +1.019 |
pun | +1.011 |
answered | +0.989 |
Neg logit contributions | |
eatures | -1.089 |
heres | -0.984 |
etheless | -0.944 |
uration | -0.940 |
urations | -0.924 |
Token | " |
Token ID | 366 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
boy | +2.256 |
boys | +2.109 |
PLEASE | +1.991 |
pun | +1.963 |
answered | +1.952 |
Neg logit contributions | |
eatures | -3.242 |
heres | -3.039 |
uration | -2.912 |
etheless | -2.906 |
urations | -2.843 |
Token | A |
Token ID | 32 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
boy | +1.867 |
boys | +1.752 |
PLEASE | +1.660 |
pun | +1.643 |
answered | +1.636 |
Neg logit contributions | |
eatures | -2.429 |
heres | -2.296 |
uration | -2.191 |
etheless | -2.169 |
urations | -2.137 |
Token | lot |
Token ID | 1256 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
eatures | +2.960 |
heres | +2.866 |
uration | +2.761 |
etheless | +2.721 |
urations | +2.701 |
Neg logit contributions | |
boy | -1.427 |
boys | -1.329 |
PLEASE | -1.235 |
pun | -1.230 |
answered | -1.216 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
boy | +0.323 |
boys | +0.297 |
pun | +0.281 |
answered | +0.280 |
PLEASE | +0.274 |
Neg logit contributions | |
eatures | -0.454 |
heres | -0.413 |
uration | -0.403 |
etheless | -0.396 |
urations | -0.393 |
Token | empt |
Token ID | 1791 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
boy | +3.158 |
boys | +2.970 |
pun | +2.866 |
answered | +2.857 |
PLEASE | +2.792 |
Neg logit contributions | |
eatures | -3.052 |
heres | -2.750 |
uration | -2.668 |
etheless | -2.616 |
urations | -2.584 |
Token | ed |
Token ID | 276 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
eatures | +0.189 |
heres | +0.184 |
uration | +0.179 |
urations | +0.172 |
cluded | +0.171 |
Neg logit contributions | |
boy | -0.205 |
boys | -0.197 |
PLEASE | -0.186 |
pun | -0.184 |
answered | -0.181 |
Token | at |
Token ID | 379 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
boy | +0.973 |
boys | +0.909 |
PLEASE | +0.869 |
pun | +0.856 |
answered | +0.846 |
Neg logit contributions | |
eatures | -1.267 |
heres | -1.170 |
uration | -1.127 |
etheless | -1.124 |
urations | -1.096 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
eatures | +1.821 |
heres | +1.712 |
uration | +1.619 |
etheless | +1.604 |
urations | +1.575 |
Neg logit contributions | |
boy | -1.791 |
boys | -1.694 |
PLEASE | -1.608 |
pun | -1.598 |
answered | -1.596 |
Token | a |
Token ID | 257 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
boy | +3.218 |
boys | +3.024 |
PLEASE | +2.939 |
pun | +2.900 |
answered | +2.858 |
Neg logit contributions | |
eatures | -3.447 |
heres | -3.075 |
etheless | -2.982 |
uration | -2.979 |
urations | -2.894 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
boy | +3.711 |
boys | +3.532 |
PLEASE | +3.386 |
pun | +3.360 |
answered | +3.347 |
Neg logit contributions | |
eatures | -2.946 |
heres | -2.703 |
uration | -2.548 |
etheless | -2.537 |
urations | -2.463 |
Token | m |
Token ID | 76 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
boy | +4.757 |
boys | +4.256 |
pun | +3.843 |
PLEASE | +3.804 |
answered | +3.694 |
Neg logit contributions | |
eatures | -12.412 |
etheless | -11.130 |
heres | -10.975 |
uration | -10.622 |
urations | -10.408 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
boy | +0.249 |
boys | +0.234 |
PLEASE | +0.231 |
pun | +0.230 |
answered | +0.223 |
Neg logit contributions | |
eatures | -0.237 |
heres | -0.216 |
etheless | -0.207 |
uration | -0.204 |
urations | -0.198 |
Token | ET |
Token ID | 12152 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
boy | +3.378 |
boys | +3.194 |
PLEASE | +3.109 |
pun | +3.064 |
answered | +3.034 |
Neg logit contributions | |
eatures | -3.398 |
heres | -3.129 |
uration | -2.988 |
etheless | -2.955 |
urations | -2.896 |
Token | for |
Token ID | 329 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
eatures | +5.432 |
heres | +5.305 |
uration | +4.973 |
etheless | +4.863 |
conjunction | +4.847 |
Neg logit contributions | |
boy | -5.131 |
boys | -4.897 |
answered | -4.587 |
pun | -4.562 |
PLEASE | -4.524 |
Token | live |
Token ID | 2107 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
boy | +3.454 |
boys | +3.272 |
PLEASE | +3.042 |
pun | +3.038 |
answered | +2.965 |
Neg logit contributions | |
eatures | -4.082 |
heres | -3.722 |
etheless | -3.589 |
uration | -3.574 |
urations | -3.530 |
Token | women |
Token ID | 1466 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
boy | +3.405 |
boys | +3.227 |
PLEASE | +3.007 |
pun | +3.003 |
answered | +2.914 |
Neg logit contributions | |
eatures | -3.983 |
heres | -3.615 |
etheless | -3.512 |
uration | -3.461 |
urations | -3.422 |
Token | he |
Token ID | 339 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
boy | +0.831 |
boys | +0.786 |
PLEASE | +0.752 |
pun | +0.740 |
answered | +0.733 |
Neg logit contributions | |
eatures | -0.838 |
heres | -0.766 |
etheless | -0.730 |
uration | -0.730 |
urations | -0.713 |
Token | could |
Token ID | 714 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
eatures | +1.526 |
heres | +1.494 |
uration | +1.406 |
occurred | +1.367 |
etheless | +1.361 |
Neg logit contributions | |
boy | -1.604 |
boys | -1.527 |
PLEASE | -1.476 |
answered | -1.472 |
pun | -1.461 |
Token | easily |
Token ID | 3538 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
boy | +0.045 |
boys | +0.042 |
answered | +0.040 |
pun | +0.039 |
PLEASE | +0.039 |
Neg logit contributions | |
eatures | -0.060 |
heres | -0.057 |
uration | -0.055 |
etheless | -0.054 |
conjunction | -0.053 |
Token | be |
Token ID | 307 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
eatures | +3.953 |
heres | +3.891 |
uration | +3.739 |
conjunction | +3.707 |
etheless | +3.662 |
Neg logit contributions | |
boy | -2.734 |
boys | -2.601 |
answered | -2.539 |
pun | -2.383 |
PLEASE | -2.341 |
Token | fl |
Token ID | 781 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
boy | +1.148 |
boys | +1.082 |
PLEASE | +1.027 |
pun | +1.017 |
answered | +1.013 |
Neg logit contributions | |
eatures | -1.338 |
heres | -1.251 |
uration | -1.193 |
etheless | -1.186 |
urations | -1.161 |
Token | irting |
Token ID | 35355 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
boy | +1.284 |
boys | +1.214 |
PLEASE | +1.150 |
pun | +1.149 |
answered | +1.137 |
Neg logit contributions | |
eatures | -1.115 |
heres | -1.030 |
etheless | -0.990 |
uration | -0.969 |
conjunction | -0.944 |
Token | with |
Token ID | 351 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
boy | +1.577 |
boys | +1.462 |
PLEASE | +1.376 |
pun | +1.350 |
answered | +1.329 |
Neg logit contributions | |
eatures | -2.441 |
heres | -2.262 |
uration | -2.181 |
etheless | -2.166 |
urations | -2.134 |
Token | one |
Token ID | 530 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
eatures | +0.640 |
heres | +0.592 |
uration | +0.559 |
etheless | +0.555 |
urations | +0.541 |
Neg logit contributions | |
boy | -0.761 |
boys | -0.723 |
PLEASE | -0.692 |
pun | -0.687 |
answered | -0.685 |
Token | at |
Token ID | 379 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
boy | +1.759 |
boys | +1.647 |
PLEASE | +1.579 |
pun | +1.550 |
answered | +1.534 |
Neg logit contributions | |
eatures | -1.875 |
heres | -1.718 |
uration | -1.638 |
etheless | -1.629 |
urations | -1.603 |
Token | onia |
Token ID | 11339 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
eatures | +1.894 |
heres | +1.770 |
uration | +1.662 |
etheless | +1.647 |
urations | +1.604 |
Neg logit contributions | |
boy | -2.309 |
boys | -2.202 |
PLEASE | -2.109 |
pun | -2.094 |
answered | -2.087 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
eatures | +3.076 |
heres | +2.849 |
uration | +2.702 |
etheless | +2.692 |
urations | +2.622 |
Neg logit contributions | |
boy | -3.254 |
boys | -3.083 |
PLEASE | -2.947 |
pun | -2.918 |
answered | -2.908 |
Token | Allen |
Token ID | 9659 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
eatures | +1.919 |
heres | +1.796 |
uration | +1.706 |
etheless | +1.689 |
urations | +1.656 |
Neg logit contributions | |
boy | -1.802 |
boys | -1.705 |
pun | -1.611 |
PLEASE | -1.603 |
answered | -1.596 |
Token | and |
Token ID | 290 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
eatures | +1.933 |
heres | +1.826 |
uration | +1.749 |
etheless | +1.741 |
urations | +1.708 |
Neg logit contributions | |
boy | -1.313 |
boys | -1.228 |
PLEASE | -1.155 |
pun | -1.139 |
answered | -1.134 |
Token | editor |
Token ID | 5464 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
boy | +0.060 |
boys | +0.056 |
PLEASE | +0.054 |
answered | +0.053 |
pun | +0.053 |
Neg logit contributions | |
eatures | -0.065 |
heres | -0.060 |
etheless | -0.058 |
uration | -0.057 |
urations | -0.056 |
Token | Ralph |
Token ID | 20993 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
boy | +1.851 |
boys | +1.722 |
PLEASE | +1.612 |
pun | +1.585 |
answered | +1.574 |
Neg logit contributions | |
eatures | -2.635 |
heres | -2.455 |
etheless | -2.367 |
uration | -2.350 |
urations | -2.300 |
Token | Rosen |
Token ID | 15564 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
boy | +0.829 |
boys | +0.772 |
PLEASE | +0.730 |
pun | +0.721 |
answered | +0.718 |
Neg logit contributions | |
eatures | -1.011 |
heres | -0.943 |
etheless | -0.900 |
uration | -0.900 |
urations | -0.878 |
Token | bl |
Token ID | 2436 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
eatures | +2.235 |
heres | +2.095 |
uration | +1.989 |
etheless | +1.980 |
urations | +1.931 |
Neg logit contributions | |
boy | -1.992 |
boys | -1.883 |
PLEASE | -1.800 |
answered | -1.769 |
pun | -1.765 |
Token | um |
Token ID | 388 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
eatures | +2.874 |
heres | +2.653 |
uration | +2.480 |
urations | +2.360 |
etheless | +2.348 |
Neg logit contributions | |
boy | -5.304 |
boys | -5.111 |
PLEASE | -4.953 |
answered | -4.910 |
pun | -4.880 |
Token | re |
Token ID | 302 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
eatures | +5.118 |
heres | +4.800 |
uration | +4.610 |
etheless | +4.533 |
occurred | +4.508 |
Neg logit contributions | |
boy | -5.049 |
boys | -4.808 |
PLEASE | -4.560 |
pun | -4.532 |
answered | -4.516 |
Token | worked |
Token ID | 32931 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
eatures | +2.211 |
heres | +2.082 |
uration | +1.984 |
etheless | +1.967 |
cluded | +1.931 |
Neg logit contributions | |
boy | -1.704 |
boys | -1.604 |
PLEASE | -1.517 |
pun | -1.490 |
answered | -1.486 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
boy | +0.687 |
boys | +0.646 |
PLEASE | +0.612 |
pun | +0.606 |
answered | +0.604 |
Neg logit contributions | |
eatures | -0.841 |
heres | -0.787 |
uration | -0.752 |
etheless | -0.748 |
urations | -0.732 |
Token | Pretty |
Token ID | 20090 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
boy | +2.070 |
boys | +1.931 |
pun | +1.808 |
answered | +1.807 |
PLEASE | +1.791 |
Neg logit contributions | |
eatures | -3.172 |
heres | -3.042 |
uration | -2.916 |
etheless | -2.855 |
urations | -2.844 |
Token | much |
Token ID | 881 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
boy | +0.107 |
boys | +0.101 |
PLEASE | +0.096 |
pun | +0.095 |
answered | +0.094 |
Neg logit contributions | |
eatures | -0.117 |
heres | -0.109 |
uration | -0.104 |
etheless | -0.103 |
urations | -0.101 |
Token | every |
Token ID | 790 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
eatures | +2.920 |
heres | +2.816 |
uration | +2.633 |
conjunction | +2.560 |
etheless | +2.556 |
Neg logit contributions | |
boy | -3.035 |
boys | -2.881 |
answered | -2.756 |
pun | -2.734 |
PLEASE | -2.718 |
Token | other |
Token ID | 584 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
eatures | +2.515 |
heres | +2.363 |
uration | +2.281 |
conjunction | +2.237 |
etheless | +2.230 |
Neg logit contributions | |
boy | -2.091 |
boys | -1.998 |
pun | -1.888 |
answered | -1.884 |
PLEASE | -1.882 |
Token | day |
Token ID | 1110 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
boy | +0.016 |
boys | +0.015 |
PLEASE | +0.014 |
pun | +0.014 |
answered | +0.014 |
Neg logit contributions | |
eatures | -0.021 |
heres | -0.020 |
uration | -0.019 |
etheless | -0.019 |
urations | -0.018 |
Token | I |
Token ID | 314 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
boy | +1.974 |
boys | +1.861 |
PLEASE | +1.771 |
pun | +1.739 |
answered | +1.723 |
Neg logit contributions | |
eatures | -2.221 |
heres | -2.043 |
etheless | -1.971 |
uration | -1.955 |
urations | -1.914 |
Token | can |
Token ID | 460 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
boy | +0.386 |
boys | +0.365 |
answered | +0.342 |
pun | +0.339 |
PLEASE | +0.332 |
Neg logit contributions | |
eatures | -0.619 |
heres | -0.601 |
uration | -0.575 |
etheless | -0.565 |
conjunction | -0.563 |
Token | get |
Token ID | 651 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
boy | +2.036 |
boys | +1.866 |
PLEASE | +1.773 |
pun | +1.728 |
answered | +1.687 |
Neg logit contributions | |
eatures | -3.838 |
heres | -3.589 |
etheless | -3.466 |
uration | -3.460 |
urations | -3.400 |
Token | up |
Token ID | 510 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
boy | +4.451 |
boys | +4.225 |
PLEASE | +4.045 |
pun | +3.958 |
answered | +3.952 |
Neg logit contributions | |
eatures | -4.345 |
heres | -3.933 |
etheless | -3.799 |
uration | -3.769 |
urations | -3.674 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
boy | +4.407 |
boys | +4.125 |
PLEASE | +3.948 |
pun | +3.867 |
answered | +3.845 |
Neg logit contributions | |
eatures | -5.917 |
heres | -5.405 |
etheless | -5.250 |
uration | -5.222 |
urations | -5.100 |
Token | to |
Token ID | 284 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
eatures | +3.310 |
heres | +3.128 |
uration | +2.974 |
etheless | +2.954 |
urations | +2.883 |
Neg logit contributions | |
boy | -2.870 |
boys | -2.721 |
PLEASE | -2.566 |
pun | -2.545 |
answered | -2.539 |
Token | take |
Token ID | 1011 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
eatures | +2.738 |
heres | +2.671 |
uration | +2.559 |
conjunction | +2.504 |
cluded | +2.474 |
Neg logit contributions | |
boy | -1.850 |
boys | -1.751 |
answered | -1.646 |
pun | -1.592 |
PLEASE | -1.579 |
Token | shelter |
Token ID | 11772 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
boy | +1.933 |
boys | +1.818 |
PLEASE | +1.728 |
pun | +1.706 |
answered | +1.691 |
Neg logit contributions | |
eatures | -2.385 |
heres | -2.225 |
etheless | -2.127 |
uration | -2.125 |
urations | -2.076 |
Token | ." |
Token ID | 526 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
boy | +2.982 |
boys | +2.797 |
PLEASE | +2.681 |
pun | +2.638 |
answered | +2.603 |
Neg logit contributions | |
eatures | -3.471 |
heres | -3.167 |
uration | -3.038 |
etheless | -3.036 |
urations | -2.958 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
boy | +2.276 |
answered | +1.999 |
boys | +1.964 |
PLEASE | +1.958 |
pun | +1.843 |
Neg logit contributions | |
eatures | -4.708 |
heres | -4.363 |
etheless | -4.222 |
uration | -4.083 |
urations | -4.046 |
Token |
|
Token ID | 198 |
Feature activation | +5.90e-03 |
Pos logit contributions | |
boy | +0.679 |
boys | +0.649 |
sacrific | +0.648 |
answered | +0.615 |
PLEASE | +0.611 |
Neg logit contributions | |
heres | -0.804 |
uration | -0.763 |
cluded | -0.750 |
eatures | -0.747 |
urations | -0.745 |
Token | 「 |
Token ID | 13697 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
eatures | +0.015 |
heres | +0.014 |
uration | +0.014 |
etheless | +0.014 |
urations | +0.013 |
Neg logit contributions | |
boy | -0.015 |
boys | -0.014 |
PLEASE | -0.014 |
pun | -0.014 |
answered | -0.014 |
Token | Oh |
Token ID | 5812 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
boy | +1.485 |
boys | +1.386 |
PLEASE | +1.304 |
pun | +1.289 |
answered | +1.282 |
Neg logit contributions | |
eatures | -2.244 |
heres | -2.113 |
uration | -2.025 |
etheless | -2.017 |
urations | -1.978 |
Token | my |
Token ID | 616 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
boy | +1.629 |
boys | +1.529 |
PLEASE | +1.472 |
pun | +1.446 |
answered | +1.439 |
Neg logit contributions | |
eatures | -1.588 |
heres | -1.444 |
etheless | -1.383 |
uration | -1.369 |
urations | -1.338 |
Token | …. |
Token ID | 11580 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
boy | +2.851 |
boys | +2.627 |
PLEASE | +2.548 |
pun | +2.474 |
answered | +2.443 |
Neg logit contributions | |
eatures | -3.305 |
heres | -3.039 |
etheless | -2.908 |
uration | -2.857 |
urations | -2.839 |
Token | How |
Token ID | 1374 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
boy | +3.335 |
boys | +3.099 |
PLEASE | +2.965 |
pun | +2.921 |
answered | +2.905 |
Neg logit contributions | |
eatures | -4.418 |
heres | -4.067 |
etheless | -3.940 |
uration | -3.899 |
urations | -3.822 |
Token | I |
Token ID | 314 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
boy | +1.863 |
boys | +1.745 |
PLEASE | +1.659 |
pun | +1.626 |
answered | +1.619 |
Neg logit contributions | |
eatures | -2.357 |
heres | -2.189 |
uration | -2.102 |
etheless | -2.098 |
urations | -2.055 |
Token | can |
Token ID | 460 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
eatures | +1.207 |
heres | +1.156 |
uration | +1.105 |
etheless | +1.101 |
urations | +1.074 |
Neg logit contributions | |
boy | -0.914 |
boys | -0.866 |
PLEASE | -0.819 |
pun | -0.807 |
answered | -0.803 |
Token | � |
Token ID | 447 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
boy | +1.136 |
boys | +1.054 |
PLEASE | +0.988 |
pun | +0.977 |
answered | +0.967 |
Neg logit contributions | |
eatures | -1.931 |
heres | -1.818 |
uration | -1.747 |
etheless | -1.742 |
urations | -1.708 |
Token | � |
Token ID | 247 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
boy | +1.227 |
boys | +1.176 |
PLEASE | +1.125 |
pun | +1.110 |
answered | +1.101 |
Neg logit contributions | |
eatures | -0.945 |
heres | -0.902 |
uration | -0.862 |
etheless | -0.821 |
urations | -0.820 |
Token | t |
Token ID | 83 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eatures | +0.892 |
heres | +0.858 |
uration | +0.828 |
urations | +0.807 |
cluded | +0.804 |
Neg logit contributions | |
boy | -0.515 |
boys | -0.480 |
PLEASE | -0.457 |
answered | -0.442 |
pun | -0.436 |
Token | help |
Token ID | 1037 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
boy | +2.159 |
boys | +1.987 |
PLEASE | +1.867 |
pun | +1.830 |
answered | +1.811 |
Neg logit contributions | |
eatures | -4.024 |
heres | -3.794 |
uration | -3.649 |
etheless | -3.644 |
urations | -3.577 |
Token | but |
Token ID | 475 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
boy | +6.065 |
boys | +5.660 |
PLEASE | +5.408 |
laughing | +5.127 |
pun | +5.099 |
Neg logit contributions | |
eatures | -9.380 |
heres | -8.695 |
uration | -8.316 |
urations | -8.200 |
etheless | -8.086 |
Token | remember |
Token ID | 3505 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
eatures | +3.535 |
heres | +3.457 |
etheless | +3.305 |
uration | +3.303 |
conjunction | +3.266 |
Neg logit contributions | |
boy | -1.716 |
boys | -1.609 |
answered | -1.487 |
pun | -1.445 |
PLEASE | -1.424 |
Token | the |
Token ID | 262 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
boy | +2.907 |
boys | +2.747 |
PLEASE | +2.630 |
pun | +2.582 |
answered | +2.566 |
Neg logit contributions | |
eatures | -2.516 |
heres | -2.272 |
uration | -2.159 |
etheless | -2.155 |
urations | -2.094 |
Token | difficult |
Token ID | 2408 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
boy | +1.160 |
boys | +1.093 |
PLEASE | +1.031 |
pun | +1.024 |
answered | +1.017 |
Neg logit contributions | |
eatures | -1.342 |
heres | -1.248 |
uration | -1.193 |
etheless | -1.189 |
urations | -1.161 |
Token | times |
Token ID | 1661 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
boy | +1.127 |
boys | +1.072 |
PLEASE | +1.022 |
pun | +1.015 |
answered | +1.011 |
Neg logit contributions | |
eatures | -0.943 |
heres | -0.870 |
uration | -0.823 |
etheless | -0.817 |
urations | -0.796 |
Token | ago |
Token ID | 2084 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
boy | +3.748 |
boys | +3.435 |
PLEASE | +3.243 |
answered | +3.237 |
pun | +3.236 |
Neg logit contributions | |
eatures | -5.015 |
heres | -4.536 |
uration | -4.476 |
etheless | -4.387 |
urations | -4.320 |
Token | — |
Token ID | 851 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
eatures | +1.645 |
heres | +1.499 |
uration | +1.421 |
etheless | +1.416 |
urations | +1.375 |
Neg logit contributions | |
boy | -2.099 |
boys | -1.994 |
PLEASE | -1.927 |
pun | -1.901 |
answered | -1.898 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
boy | +4.156 |
boys | +3.924 |
PLEASE | +3.762 |
pun | +3.733 |
answered | +3.708 |
Neg logit contributions | |
eatures | -4.120 |
heres | -3.787 |
uration | -3.626 |
etheless | -3.598 |
urations | -3.521 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
boy | +1.129 |
boys | +1.062 |
PLEASE | +1.012 |
pun | +1.001 |
answered | +0.997 |
Neg logit contributions | |
eatures | -1.247 |
heres | -1.159 |
uration | -1.104 |
etheless | -1.097 |
urations | -1.076 |
Token | in |
Token ID | 287 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
boy | +1.468 |
boys | +1.370 |
PLEASE | +1.306 |
pun | +1.301 |
answered | +1.284 |
Neg logit contributions | |
eatures | -1.655 |
heres | -1.533 |
uration | -1.470 |
etheless | -1.454 |
urations | -1.438 |
Token | politics |
Token ID | 4819 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
eatures | +1.109 |
heres | +1.013 |
etheless | +0.958 |
uration | +0.956 |
urations | +0.926 |
Neg logit contributions | |
boy | -1.384 |
boys | -1.315 |
PLEASE | -1.259 |
pun | -1.256 |
answered | -1.245 |
Token | — |
Token ID | 851 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
boy | +8.355 |
boys | +7.596 |
pun | +7.358 |
PLEASE | +7.183 |
answered | +7.088 |
Neg logit contributions | |
eatures | -9.932 |
heres | -8.690 |
etheless | -8.642 |
uration | -8.607 |
bidden | -8.387 |
Token | the |
Token ID | 262 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
eatures | +0.351 |
heres | +0.326 |
uration | +0.309 |
etheless | +0.307 |
urations | +0.300 |
Neg logit contributions | |
boy | -0.364 |
boys | -0.344 |
PLEASE | -0.329 |
pun | -0.326 |
answered | -0.325 |
Token | city |
Token ID | 1748 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
eatures | +0.228 |
heres | +0.214 |
uration | +0.204 |
etheless | +0.202 |
urations | +0.198 |
Neg logit contributions | |
boy | -0.202 |
boys | -0.191 |
PLEASE | -0.181 |
pun | -0.180 |
answered | -0.179 |
Token | controller |
Token ID | 10444 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
boy | +4.701 |
boys | +4.437 |
pun | +4.289 |
answered | +4.236 |
PLEASE | +4.212 |
Neg logit contributions | |
eatures | -3.803 |
heres | -3.464 |
etheless | -3.317 |
uration | -3.248 |
urations | -3.197 |
Token | called |
Token ID | 1444 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
boy | +0.646 |
boys | +0.613 |
PLEASE | +0.585 |
pun | +0.580 |
answered | +0.578 |
Neg logit contributions | |
eatures | -0.610 |
heres | -0.566 |
uration | -0.537 |
etheless | -0.533 |
urations | -0.521 |
Token | card |
Token ID | 2657 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
boy | +3.673 |
boys | +3.353 |
pun | +3.183 |
PLEASE | +3.176 |
answered | +3.026 |
Neg logit contributions | |
eatures | -6.966 |
heres | -6.321 |
etheless | -6.280 |
uration | -6.157 |
urations | -6.102 |
Token | companies |
Token ID | 2706 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
boy | +0.038 |
boys | +0.036 |
PLEASE | +0.034 |
pun | +0.034 |
answered | +0.034 |
Neg logit contributions | |
eatures | -0.034 |
heres | -0.032 |
uration | -0.030 |
etheless | -0.030 |
urations | -0.029 |
Token | ; |
Token ID | 26 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
eatures | +0.797 |
heres | +0.748 |
uration | +0.711 |
etheless | +0.707 |
urations | +0.692 |
Neg logit contributions | |
boy | -0.709 |
boys | -0.670 |
PLEASE | -0.635 |
pun | -0.630 |
answered | -0.629 |
Token | now |
Token ID | 783 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
boy | +0.962 |
boys | +0.902 |
PLEASE | +0.858 |
pun | +0.842 |
answered | +0.838 |
Neg logit contributions | |
eatures | -1.259 |
heres | -1.174 |
uration | -1.124 |
etheless | -1.119 |
urations | -1.096 |
Token | i |
Token ID | 1312 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
eatures | +2.341 |
heres | +2.186 |
uration | +2.075 |
etheless | +2.062 |
urations | +2.014 |
Neg logit contributions | |
boy | -2.267 |
boys | -2.145 |
PLEASE | -2.040 |
pun | -2.026 |
answered | -2.020 |
Token | ... |
Token ID | 986 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
boy | +2.120 |
boys | +1.977 |
PLEASE | +1.881 |
pun | +1.859 |
answered | +1.833 |
Neg logit contributions | |
eatures | -2.587 |
heres | -2.369 |
etheless | -2.291 |
uration | -2.265 |
urations | -2.225 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
boy | +5.428 |
boys | +4.931 |
PLEASE | +4.756 |
pun | +4.514 |
answered | +4.494 |
Neg logit contributions | |
eatures | -10.941 |
heres | -9.853 |
uration | -9.789 |
etheless | -9.773 |
urations | -9.548 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
heres | +0.073 |
uration | +0.068 |
cluded | +0.067 |
urations | +0.067 |
conjunction | +0.066 |
Neg logit contributions | |
boy | -0.064 |
sacrific | -0.063 |
boys | -0.062 |
answered | -0.059 |
PLEASE | -0.058 |
Token | Although |
Token ID | 7003 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
eatures | +0.493 |
heres | +0.473 |
uration | +0.450 |
etheless | +0.443 |
urations | +0.440 |
Neg logit contributions | |
boy | -0.345 |
boys | -0.323 |
PLEASE | -0.306 |
answered | -0.300 |
pun | -0.300 |
Token | this |
Token ID | 428 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
eatures | +5.686 |
heres | +5.445 |
uration | +5.179 |
etheless | +5.067 |
conjunction | +5.034 |
Neg logit contributions | |
boy | -4.736 |
boys | -4.443 |
answered | -4.257 |
pun | -4.190 |
PLEASE | -4.183 |
Token | one |
Token ID | 530 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
eatures | +2.076 |
heres | +1.940 |
uration | +1.839 |
etheless | +1.816 |
urations | +1.779 |
Neg logit contributions | |
boy | -2.119 |
boys | -2.015 |
PLEASE | -1.915 |
pun | -1.908 |
answered | -1.907 |
Token | very |
Token ID | 845 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
eatures | +0.660 |
heres | +0.619 |
uration | +0.585 |
etheless | +0.581 |
urations | +0.568 |
Neg logit contributions | |
boy | -0.661 |
boys | -0.624 |
PLEASE | -0.594 |
pun | -0.591 |
answered | -0.588 |
Token | numerous |
Token ID | 6409 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
eatures | +0.307 |
heres | +0.290 |
uration | +0.276 |
etheless | +0.272 |
urations | +0.268 |
Neg logit contributions | |
boy | -0.253 |
boys | -0.238 |
PLEASE | -0.224 |
pun | -0.223 |
answered | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
boy | +0.340 |
boys | +0.323 |
PLEASE | +0.308 |
pun | +0.304 |
answered | +0.302 |
Neg logit contributions | |
eatures | -0.341 |
heres | -0.311 |
uration | -0.298 |
etheless | -0.295 |
urations | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
boy | +3.376 |
boys | +3.171 |
PLEASE | +3.046 |
pun | +2.931 |
answered | +2.915 |
Neg logit contributions | |
eatures | -4.706 |
heres | -4.306 |
etheless | -4.185 |
uration | -4.151 |
urations | -4.042 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
boy | +0.429 |
sacrific | +0.413 |
boys | +0.409 |
answered | +0.391 |
pun | +0.388 |
Neg logit contributions | |
heres | -0.495 |
uration | -0.469 |
cluded | -0.460 |
urations | -0.457 |
eatures | -0.457 |
Token | Read |
Token ID | 5569 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
boy | +0.009 |
boys | +0.009 |
PLEASE | +0.008 |
pun | +0.008 |
answered | +0.008 |
Neg logit contributions | |
eatures | -0.011 |
heres | -0.011 |
uration | -0.010 |
etheless | -0.010 |
urations | -0.010 |
Token | more |
Token ID | 517 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
boy | +6.605 |
boys | +6.125 |
PLEASE | +5.700 |
answered | +5.640 |
pun | +5.625 |
Neg logit contributions | |
eatures | -7.852 |
heres | -7.340 |
uration | -7.227 |
etheless | -7.141 |
urations | -6.999 |
Token | on |
Token ID | 319 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
boy | +8.479 |
boys | +8.042 |
PLEASE | +7.660 |
pun | +7.424 |
answered | +7.183 |
Neg logit contributions | |
eatures | -8.415 |
heres | -7.588 |
uration | -7.559 |
etheless | -7.384 |
urations | -7.165 |
Token | Pent |
Token ID | 9696 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
boy | +2.937 |
boys | +2.787 |
PLEASE | +2.666 |
pun | +2.634 |
answered | +2.595 |
Neg logit contributions | |
eatures | -2.594 |
heres | -2.341 |
uration | -2.270 |
etheless | -2.235 |
urations | -2.206 |
Token | ec |
Token ID | 721 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
heres | +0.640 |
eatures | +0.630 |
uration | +0.578 |
urations | +0.531 |
cluded | +0.513 |
Neg logit contributions | |
boy | -2.088 |
boys | -2.028 |
PLEASE | -1.994 |
answered | -1.949 |
pun | -1.948 |
Token | ost |
Token ID | 455 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
eatures | +0.452 |
heres | +0.433 |
uration | +0.402 |
urations | +0.382 |
etheless | +0.378 |
Neg logit contributions | |
boy | -0.839 |
boys | -0.806 |
PLEASE | -0.785 |
pun | -0.776 |
answered | -0.772 |
Token | ance |
Token ID | 590 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
boy | +4.560 |
boys | +4.323 |
PLEASE | +4.162 |
pun | +4.153 |
answered | +4.135 |
Neg logit contributions | |
eatures | -2.953 |
heres | -2.605 |
etheless | -2.498 |
uration | -2.403 |
urations | -2.325 |
Token | at |
Token ID | 379 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
boy | +2.656 |
boys | +2.447 |
pun | +2.308 |
PLEASE | +2.286 |
answered | +2.184 |
Neg logit contributions | |
eatures | -3.795 |
heres | -3.479 |
etheless | -3.377 |
uration | -3.311 |
urations | -3.259 |
Token | Bad |
Token ID | 7772 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
eatures | +1.600 |
heres | +1.481 |
etheless | +1.449 |
uration | +1.435 |
urations | +1.390 |
Neg logit contributions | |
boy | -1.075 |
boys | -1.001 |
PLEASE | -0.934 |
pun | -0.928 |
answered | -0.901 |
Token | Hab |
Token ID | 19654 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
boy | +4.761 |
boys | +4.438 |
PLEASE | +4.163 |
pun | +4.133 |
answered | +4.049 |
Neg logit contributions | |
eatures | -6.651 |
etheless | -6.019 |
heres | -6.004 |
uration | -5.848 |
urations | -5.631 |
Token | its |
Token ID | 896 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
boy | +2.921 |
boys | +2.799 |
PLEASE | +2.699 |
pun | +2.685 |
answered | +2.671 |
Neg logit contributions | |
eatures | -1.628 |
heres | -1.460 |
uration | -1.360 |
etheless | -1.357 |
urations | -1.300 |
Token | , |
Token ID | 11 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
boy | +2.651 |
boys | +2.502 |
PLEASE | +2.410 |
pun | +2.391 |
answered | +2.301 |
Neg logit contributions | |
eatures | -2.437 |
etheless | -2.236 |
heres | -2.233 |
uration | -2.118 |
conjunction | -2.066 |
Token | 18 |
Token ID | 1248 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
boy | +7.612 |
boys | +7.248 |
PLEASE | +7.113 |
pun | +6.758 |
answered | +6.497 |
Neg logit contributions | |
eatures | -7.094 |
etheless | -6.527 |
heres | -6.343 |
uration | -5.995 |
bidden | -5.945 |
Token | 44 |
Token ID | 2598 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
boy | +2.354 |
boys | +2.121 |
PLEASE | +1.976 |
pun | +1.891 |
answered | +1.813 |
Neg logit contributions | |
eatures | -4.337 |
heres | -4.003 |
etheless | -3.976 |
uration | -3.804 |
urations | -3.737 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
boy | +1.708 |
boys | +1.574 |
PLEASE | +1.538 |
pun | +1.505 |
answered | +1.448 |
Neg logit contributions | |
eatures | -1.805 |
heres | -1.654 |
etheless | -1.633 |
uration | -1.575 |
urations | -1.540 |
Token |
|
Token ID | 198 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
boy | +2.129 |
boys | +1.914 |
PLEASE | +1.897 |
pun | +1.781 |
answered | +1.768 |
Neg logit contributions | |
eatures | -4.430 |
heres | -4.166 |
uration | -4.099 |
etheless | -4.052 |
urations | -4.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
boy | +1.280 |
boys | +1.217 |
sacrific | +1.180 |
answered | +1.158 |
PLEASE | +1.148 |
Neg logit contributions | |
heres | -1.593 |
eatures | -1.527 |
uration | -1.510 |
cluded | -1.479 |
urations | -1.472 |