Token | encia |
Token ID | 29634 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
IELD | +3.377 |
hips | +3.251 |
Desire | +3.079 |
ymm | +3.061 |
suppose | +2.862 |
Neg logit contributions | |
umn | -3.849 |
cient | -3.661 |
anwhile | -3.540 |
isode | -3.470 |
arch | -3.428 |
Token | ) |
Token ID | 8 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
IELD | +2.429 |
hips | +2.318 |
Desire | +2.201 |
ymm | +2.194 |
suppose | +2.052 |
Neg logit contributions | |
umn | -2.784 |
cient | -2.651 |
anwhile | -2.529 |
isode | -2.496 |
arch | -2.491 |
Token | could |
Token ID | 714 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
IELD | +0.268 |
hips | +0.254 |
Desire | +0.242 |
ymm | +0.242 |
suppose | +0.225 |
Neg logit contributions | |
umn | -0.291 |
cient | -0.273 |
anwhile | -0.263 |
arch | -0.259 |
isode | -0.258 |
Token | be |
Token ID | 307 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
umn | +1.923 |
cient | +1.820 |
anwhile | +1.744 |
isode | +1.709 |
arch | +1.707 |
Neg logit contributions | |
IELD | -1.873 |
hips | -1.737 |
Desire | -1.702 |
ymm | -1.674 |
Darling | -1.548 |
Token | re |
Token ID | 302 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
IELD | +0.856 |
hips | +0.808 |
Desire | +0.774 |
ymm | +0.758 |
suppose | +0.705 |
Neg logit contributions | |
umn | -1.001 |
cient | -0.954 |
anwhile | -0.911 |
arch | -0.899 |
isode | -0.891 |
Token | ph |
Token ID | 746 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
umn | +1.766 |
cient | +1.633 |
arch | +1.538 |
anwhile | +1.490 |
isode | +1.475 |
Neg logit contributions | |
IELD | -2.905 |
hips | -2.744 |
Desire | -2.675 |
ymm | -2.608 |
suppose | -2.494 |
Token | r |
Token ID | 81 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
umn | +5.982 |
cient | +5.568 |
arch | +5.398 |
isode | +5.155 |
iously | +4.961 |
Neg logit contributions | |
IELD | -13.108 |
hips | -12.531 |
WARE | -12.148 |
Desire | -11.947 |
Darling | -11.548 |
Token | ased |
Token ID | 839 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
umn | +1.163 |
cient | +0.957 |
arch | +0.868 |
isode | +0.787 |
ophone | +0.702 |
Neg logit contributions | |
IELD | -4.903 |
hips | -4.733 |
Desire | -4.578 |
ymm | -4.507 |
WARE | -4.362 |
Token | as |
Token ID | 355 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
umn | +3.173 |
cient | +2.998 |
arch | +2.894 |
anwhile | +2.842 |
isode | +2.755 |
Neg logit contributions | |
IELD | -2.678 |
hips | -2.472 |
ymm | -2.372 |
Desire | -2.335 |
suppose | -2.162 |
Token | � |
Token ID | 564 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
IELD | +0.585 |
hips | +0.551 |
Desire | +0.518 |
ymm | +0.517 |
suppose | +0.482 |
Neg logit contributions | |
umn | -0.790 |
cient | -0.750 |
anwhile | -0.723 |
arch | -0.712 |
isode | -0.711 |
Token | � |
Token ID | 246 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
umn | +1.033 |
cient | +0.991 |
arch | +0.925 |
anwhile | +0.923 |
isode | +0.905 |
Neg logit contributions | |
IELD | -0.981 |
hips | -0.936 |
Desire | -0.898 |
ymm | -0.886 |
suppose | -0.845 |
Token | e |
Token ID | 68 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
umn | +2.009 |
cient | +1.846 |
arch | +1.719 |
isode | +1.681 |
ophone | +1.670 |
Neg logit contributions | |
IELD | -3.294 |
hips | -3.099 |
Desire | -3.073 |
ymm | -2.993 |
suppose | -2.913 |
Token | , |
Token ID | 11 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
umn | +3.913 |
cient | +3.687 |
anwhile | +3.534 |
arch | +3.483 |
isode | +3.482 |
Neg logit contributions | |
IELD | -3.191 |
hips | -2.908 |
Desire | -2.876 |
ymm | -2.825 |
suppose | -2.576 |
Token | k |
Token ID | 479 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
umn | +0.974 |
cient | +0.923 |
anwhile | +0.877 |
isode | +0.865 |
arch | +0.864 |
Neg logit contributions | |
IELD | -0.778 |
hips | -0.721 |
Desire | -0.699 |
ymm | -0.692 |
suppose | -0.635 |
Token | omo |
Token ID | 17902 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
umn | +0.277 |
cient | +0.258 |
anwhile | +0.243 |
arch | +0.242 |
isode | +0.240 |
Neg logit contributions | |
IELD | -0.348 |
hips | -0.328 |
Desire | -0.322 |
ymm | -0.312 |
suppose | -0.300 |
Token | i |
Token ID | 1312 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
umn | +7.294 |
cient | +6.872 |
arch | +6.498 |
isode | +6.409 |
ophone | +6.366 |
Neg logit contributions | |
IELD | -6.325 |
Desire | -5.592 |
ymm | -5.554 |
hips | -5.546 |
ENTION | -5.063 |
Token | hol |
Token ID | 3937 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
umn | +0.614 |
cient | +0.579 |
anwhile | +0.549 |
arch | +0.548 |
isode | +0.544 |
Neg logit contributions | |
IELD | -0.565 |
hips | -0.527 |
Desire | -0.515 |
ymm | -0.506 |
suppose | -0.471 |
Token | a |
Token ID | 64 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
umn | +7.374 |
cient | +6.397 |
arch | +6.200 |
ophone | +6.090 |
isode | +5.950 |
Neg logit contributions | |
IELD | -10.298 |
Desire | -9.213 |
hips | -9.211 |
ymm | -9.029 |
WARE | -8.885 |
Token | ka |
Token ID | 38387 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
umn | +2.168 |
cient | +2.056 |
anwhile | +1.938 |
arch | +1.925 |
isode | +1.924 |
Neg logit contributions | |
IELD | -1.887 |
hips | -1.716 |
ymm | -1.685 |
Desire | -1.683 |
suppose | -1.536 |
Token | make |
Token ID | 787 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
umn | +3.041 |
cient | +2.898 |
isode | +2.719 |
anwhile | +2.711 |
arch | +2.701 |
Neg logit contributions | |
IELD | -2.468 |
hips | -2.265 |
ymm | -2.200 |
Desire | -2.182 |
suppose | -2.001 |
Token | make |
Token ID | 15883 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
umn | +1.374 |
cient | +1.308 |
isode | +1.260 |
anwhile | +1.259 |
arch | +1.238 |
Neg logit contributions | |
IELD | -1.270 |
hips | -1.195 |
Desire | -1.143 |
ymm | -1.135 |
suppose | -1.054 |
Token | i |
Token ID | 1312 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
umn | +1.881 |
cient | +1.787 |
anwhile | +1.688 |
arch | +1.683 |
isode | +1.680 |
Neg logit contributions | |
IELD | -1.478 |
hips | -1.361 |
Desire | -1.315 |
ymm | -1.310 |
suppose | -1.197 |
Token | because |
Token ID | 780 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
umn | +0.081 |
cient | +0.079 |
anwhile | +0.074 |
arch | +0.074 |
isode | +0.073 |
Neg logit contributions | |
IELD | -0.055 |
hips | -0.050 |
ymm | -0.047 |
Desire | -0.047 |
suppose | -0.043 |
Token | they |
Token ID | 484 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
umn | +3.938 |
cient | +3.665 |
anwhile | +3.539 |
arch | +3.451 |
iously | +3.361 |
Neg logit contributions | |
IELD | -4.467 |
hips | -4.195 |
ymm | -4.031 |
Desire | -3.960 |
GV | -3.745 |
Token | belonged |
Token ID | 19611 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
umn | +0.723 |
cient | +0.691 |
anwhile | +0.654 |
isode | +0.646 |
arch | +0.644 |
Neg logit contributions | |
IELD | -0.676 |
hips | -0.631 |
Desire | -0.612 |
ymm | -0.607 |
suppose | -0.559 |
Token | to |
Token ID | 284 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
umn | +1.143 |
cient | +1.096 |
arch | +1.018 |
anwhile | +1.001 |
isode | +0.999 |
Neg logit contributions | |
IELD | -1.129 |
hips | -1.034 |
Desire | -1.004 |
ymm | -0.998 |
suppose | -0.931 |
Token | a |
Token ID | 257 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
umn | +2.028 |
cient | +1.922 |
anwhile | +1.858 |
arch | +1.838 |
isode | +1.793 |
Neg logit contributions | |
IELD | -1.444 |
hips | -1.366 |
ymm | -1.292 |
Desire | -1.255 |
suppose | -1.185 |
Token | culture |
Token ID | 3968 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
umn | +0.359 |
cient | +0.343 |
anwhile | +0.324 |
arch | +0.324 |
isode | +0.318 |
Neg logit contributions | |
IELD | -0.319 |
hips | -0.304 |
ymm | -0.287 |
Desire | -0.283 |
suppose | -0.263 |
Token | within |
Token ID | 1626 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
umn | +8.036 |
cient | +7.924 |
arch | +7.228 |
ophone | +7.199 |
anwhile | +7.054 |
Neg logit contributions | |
IELD | -9.099 |
ymm | -7.760 |
Desire | -7.554 |
hips | -7.524 |
ELF | -7.123 |
Token | the |
Token ID | 262 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
umn | +2.688 |
cient | +2.512 |
arch | +2.402 |
anwhile | +2.400 |
ophone | +2.376 |
Neg logit contributions | |
IELD | -2.179 |
hips | -2.013 |
ymm | -1.951 |
Desire | -1.874 |
suppose | -1.825 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
umn | +1.608 |
cient | +1.517 |
arch | +1.445 |
anwhile | +1.438 |
ophone | +1.402 |
Neg logit contributions | |
IELD | -1.407 |
hips | -1.336 |
ymm | -1.277 |
Desire | -1.246 |
suppose | -1.192 |
Token | Hawks |
Token ID | 23445 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
IELD | +3.370 |
hips | +3.211 |
Desire | +3.040 |
ymm | +3.008 |
suppose | +2.802 |
Neg logit contributions | |
umn | -4.541 |
cient | -4.341 |
anwhile | -4.177 |
isode | -4.120 |
arch | -4.097 |
Token | where |
Token ID | 810 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
IELD | +5.463 |
hips | +5.344 |
Desire | +4.989 |
ymm | +4.900 |
suppose | +4.601 |
Neg logit contributions | |
umn | -7.524 |
cient | -7.196 |
anwhile | -7.014 |
isode | -6.892 |
arch | -6.747 |
Token | goes |
Token ID | 2925 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
umn | +1.997 |
cient | +1.937 |
anwhile | +1.857 |
isode | +1.819 |
arch | +1.815 |
Neg logit contributions | |
IELD | -1.501 |
hips | -1.390 |
Desire | -1.338 |
ymm | -1.318 |
Darling | -1.175 |
Token | down |
Token ID | 866 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
umn | +1.457 |
cient | +1.390 |
anwhile | +1.338 |
arch | +1.307 |
isode | +1.300 |
Neg logit contributions | |
IELD | -1.309 |
hips | -1.214 |
Desire | -1.193 |
ymm | -1.150 |
suppose | -1.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
umn | +1.082 |
cient | +1.037 |
anwhile | +0.992 |
isode | +0.982 |
arch | +0.978 |
Neg logit contributions | |
IELD | -0.877 |
hips | -0.824 |
Desire | -0.803 |
ymm | -0.782 |
suppose | -0.726 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
IELD | +0.003 |
hips | +0.003 |
Desire | +0.003 |
ymm | +0.003 |
suppose | +0.002 |
Neg logit contributions | |
umn | -0.004 |
cient | -0.004 |
anwhile | -0.004 |
arch | -0.004 |
isode | -0.004 |
Token | cu |
Token ID | 18912 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
umn | +0.842 |
cient | +0.807 |
anwhile | +0.769 |
isode | +0.760 |
arch | +0.757 |
Neg logit contributions | |
IELD | -0.724 |
hips | -0.679 |
Desire | -0.644 |
ymm | -0.644 |
suppose | -0.599 |
Token | ph |
Token ID | 746 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
umn | +1.471 |
cient | +1.370 |
arch | +1.271 |
anwhile | +1.259 |
isode | +1.251 |
Neg logit contributions | |
IELD | -2.468 |
hips | -2.354 |
Desire | -2.278 |
ymm | -2.226 |
suppose | -2.112 |
Token | old |
Token ID | 727 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
umn | +8.310 |
cient | +7.922 |
ophone | +7.746 |
arch | +7.557 |
isode | +7.457 |
Neg logit contributions | |
IELD | -8.472 |
Desire | -7.902 |
hips | -7.795 |
GV | -7.374 |
ymm | -7.281 |
Token | ers |
Token ID | 364 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
umn | +2.404 |
cient | +2.273 |
arch | +2.145 |
isode | +2.117 |
anwhile | +2.108 |
Neg logit contributions | |
IELD | -2.799 |
hips | -2.650 |
Desire | -2.559 |
ymm | -2.527 |
Darling | -2.364 |
Token | . |
Token ID | 13 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
umn | +2.381 |
cient | +2.322 |
isode | +2.187 |
arch | +2.180 |
anwhile | +2.171 |
Neg logit contributions | |
IELD | -2.186 |
Desire | -1.954 |
hips | -1.930 |
ymm | -1.916 |
suppose | -1.764 |
Token | Open |
Token ID | 11505 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
IELD | +0.147 |
hips | +0.139 |
Desire | +0.131 |
ymm | +0.131 |
suppose | +0.120 |
Neg logit contributions | |
umn | -0.220 |
cient | -0.211 |
anwhile | -0.202 |
isode | -0.200 |
arch | -0.200 |
Token | your |
Token ID | 534 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
umn | +0.823 |
cient | +0.775 |
anwhile | +0.753 |
arch | +0.753 |
isode | +0.751 |
Neg logit contributions | |
IELD | -0.593 |
hips | -0.551 |
ymm | -0.521 |
Desire | -0.518 |
suppose | -0.483 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
umn | +0.394 |
cient | +0.372 |
anwhile | +0.353 |
arch | +0.352 |
isode | +0.350 |
Neg logit contributions | |
IELD | -0.336 |
hips | -0.310 |
Desire | -0.301 |
ymm | -0.299 |
suppose | -0.278 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
umn | +1.065 |
cient | +1.008 |
anwhile | +0.958 |
isode | +0.945 |
arch | +0.945 |
Neg logit contributions | |
IELD | -0.868 |
hips | -0.805 |
Desire | -0.779 |
ymm | -0.776 |
suppose | -0.712 |
Token | k |
Token ID | 479 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
umn | +0.246 |
cient | +0.234 |
anwhile | +0.221 |
isode | +0.220 |
arch | +0.219 |
Neg logit contributions | |
IELD | -0.209 |
hips | -0.195 |
Desire | -0.188 |
ymm | -0.186 |
suppose | -0.173 |
Token | uko |
Token ID | 29794 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
umn | +0.398 |
cient | +0.372 |
arch | +0.348 |
anwhile | +0.346 |
isode | +0.344 |
Neg logit contributions | |
IELD | -0.507 |
hips | -0.477 |
Desire | -0.468 |
ymm | -0.453 |
suppose | -0.438 |
Token | i |
Token ID | 1312 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
umn | +3.248 |
cient | +3.074 |
arch | +2.888 |
anwhile | +2.879 |
isode | +2.867 |
Neg logit contributions | |
IELD | -2.764 |
hips | -2.526 |
Desire | -2.487 |
ymm | -2.454 |
suppose | -2.251 |
Token | hol |
Token ID | 3937 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
umn | +1.104 |
cient | +1.041 |
anwhile | +0.988 |
arch | +0.984 |
isode | +0.976 |
Neg logit contributions | |
IELD | -1.014 |
hips | -0.945 |
Desire | -0.922 |
ymm | -0.908 |
suppose | -0.838 |
Token | a |
Token ID | 64 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
umn | +8.316 |
cient | +7.476 |
ophone | +7.133 |
arch | +7.099 |
isode | +6.901 |
Neg logit contributions | |
IELD | -8.819 |
Desire | -7.838 |
hips | -7.827 |
ymm | -7.657 |
WARE | -7.401 |
Token | |
Token ID | 220 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
umn | +1.798 |
cient | +1.698 |
anwhile | +1.604 |
arch | +1.598 |
isode | +1.594 |
Neg logit contributions | |
IELD | -1.482 |
hips | -1.360 |
ymm | -1.324 |
Desire | -1.324 |
suppose | -1.209 |
Token | � |
Token ID | 134 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
umn | +0.897 |
cient | +0.798 |
arch | +0.710 |
isode | +0.693 |
ophone | +0.690 |
Neg logit contributions | |
IELD | -2.265 |
hips | -2.184 |
Desire | -2.152 |
ymm | -2.119 |
suppose | -2.037 |
Token | � |
Token ID | 119 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
umn | +1.534 |
cient | +1.457 |
arch | +1.374 |
isode | +1.365 |
anwhile | +1.361 |
Neg logit contributions | |
IELD | -1.141 |
hips | -1.077 |
Desire | -1.013 |
ymm | -0.997 |
suppose | -0.933 |
Token | o |
Token ID | 78 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
umn | +2.136 |
cient | +1.970 |
arch | +1.848 |
isode | +1.803 |
ophone | +1.799 |
Neg logit contributions | |
IELD | -3.006 |
hips | -2.822 |
Desire | -2.814 |
ymm | -2.716 |
suppose | -2.645 |
Token | had |
Token ID | 550 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
umn | +1.696 |
cient | +1.629 |
anwhile | +1.534 |
arch | +1.531 |
isode | +1.509 |
Neg logit contributions | |
IELD | -1.513 |
hips | -1.442 |
ymm | -1.370 |
Desire | -1.357 |
suppose | -1.255 |
Token | on |
Token ID | 319 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
IELD | +0.022 |
hips | +0.020 |
Desire | +0.019 |
ymm | +0.019 |
suppose | +0.017 |
Neg logit contributions | |
umn | -0.028 |
cient | -0.027 |
arch | -0.025 |
anwhile | -0.025 |
isode | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
IELD | +0.156 |
hips | +0.148 |
ymm | +0.140 |
Desire | +0.138 |
suppose | +0.127 |
Neg logit contributions | |
umn | -0.207 |
cient | -0.198 |
anwhile | -0.188 |
arch | -0.187 |
ophone | -0.184 |
Token | web |
Token ID | 3992 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
umn | +1.701 |
cient | +1.628 |
arch | +1.531 |
anwhile | +1.524 |
ophone | +1.480 |
Neg logit contributions | |
IELD | -1.746 |
hips | -1.693 |
ymm | -1.616 |
Desire | -1.564 |
suppose | -1.499 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
umn | +4.059 |
cient | +3.923 |
arch | +3.811 |
ophone | +3.738 |
isode | +3.710 |
Neg logit contributions | |
IELD | -3.706 |
hips | -3.557 |
ymm | -3.353 |
Desire | -3.344 |
suppose | -3.075 |
Token | decade |
Token ID | 5707 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
IELD | +0.358 |
hips | +0.344 |
Desire | +0.330 |
ymm | +0.328 |
suppose | +0.309 |
Neg logit contributions | |
umn | -0.291 |
cient | -0.277 |
arch | -0.258 |
anwhile | -0.257 |
isode | -0.256 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
umn | +4.719 |
cient | +4.288 |
arch | +3.927 |
iously | +3.730 |
isode | +3.536 |
Neg logit contributions | |
IELD | -11.829 |
ymm | -10.802 |
Desire | -10.708 |
hips | -10.586 |
GV | -10.236 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
umn | +3.106 |
cient | +3.034 |
arch | +2.810 |
ophone | +2.781 |
isode | +2.757 |
Neg logit contributions | |
IELD | -3.069 |
hips | -2.707 |
Desire | -2.659 |
ymm | -2.658 |
suppose | -2.427 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
IELD | +0.056 |
hips | +0.053 |
ymm | +0.050 |
Desire | +0.050 |
suppose | +0.046 |
Neg logit contributions | |
umn | -0.071 |
cient | -0.067 |
anwhile | -0.065 |
arch | -0.063 |
isode | -0.063 |
Token | now |
Token ID | 783 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
umn | +2.205 |
cient | +2.112 |
anwhile | +2.035 |
arch | +1.991 |
ophone | +1.967 |
Neg logit contributions | |
IELD | -1.929 |
hips | -1.774 |
ymm | -1.684 |
Desire | -1.678 |
ELF | -1.555 |
Token | it |
Token ID | 340 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
IELD | +1.831 |
hips | +1.735 |
Desire | +1.648 |
ymm | +1.638 |
suppose | +1.517 |
Neg logit contributions | |
umn | -2.222 |
cient | -2.125 |
anwhile | -2.040 |
arch | -2.003 |
isode | -1.999 |
Token | � |
Token ID | 247 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
umn | +1.579 |
cient | +1.497 |
arch | +1.396 |
anwhile | +1.352 |
isode | +1.342 |
Neg logit contributions | |
IELD | -1.442 |
hips | -1.363 |
Desire | -1.336 |
ymm | -1.322 |
suppose | -1.241 |
Token | s |
Token ID | 82 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
IELD | +0.751 |
hips | +0.704 |
Desire | +0.684 |
ymm | +0.676 |
suppose | +0.638 |
Neg logit contributions | |
umn | -0.728 |
cient | -0.692 |
anwhile | -0.656 |
arch | -0.645 |
isode | -0.643 |
Token | � |
Token ID | 564 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
IELD | +1.508 |
hips | +1.422 |
ymm | +1.347 |
Desire | +1.344 |
suppose | +1.206 |
Neg logit contributions | |
umn | -2.011 |
cient | -1.935 |
anwhile | -1.844 |
arch | -1.827 |
isode | -1.807 |
Token | � |
Token ID | 250 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
IELD | +0.154 |
hips | +0.148 |
ymm | +0.141 |
Desire | +0.141 |
suppose | +0.130 |
Neg logit contributions | |
umn | -0.188 |
cient | -0.180 |
arch | -0.169 |
anwhile | -0.166 |
isode | -0.166 |
Token | eu |
Token ID | 12496 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
umn | +0.157 |
cient | +0.151 |
anwhile | +0.140 |
arch | +0.140 |
isode | +0.137 |
Neg logit contributions | |
IELD | -0.183 |
hips | -0.174 |
Desire | -0.169 |
ymm | -0.166 |
suppose | -0.157 |
Token | ph |
Token ID | 746 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
umn | +3.221 |
cient | +3.064 |
arch | +2.859 |
anwhile | +2.854 |
isode | +2.778 |
Neg logit contributions | |
IELD | -4.404 |
hips | -4.231 |
Desire | -3.998 |
ymm | -3.873 |
suppose | -3.655 |
Token | oric |
Token ID | 8146 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
umn | +5.274 |
cient | +4.858 |
arch | +4.732 |
isode | +4.421 |
ophone | +4.356 |
Neg logit contributions | |
IELD | -11.349 |
hips | -10.600 |
Desire | -10.511 |
ymm | -10.046 |
GV | -9.908 |
Token | � |
Token ID | 447 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
umn | +2.040 |
cient | +1.962 |
anwhile | +1.845 |
arch | +1.831 |
isode | +1.806 |
Neg logit contributions | |
IELD | -1.796 |
hips | -1.719 |
ymm | -1.641 |
Desire | -1.601 |
suppose | -1.466 |
Token | � |
Token ID | 251 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
IELD | +0.417 |
hips | +0.396 |
ymm | +0.380 |
Desire | +0.379 |
suppose | +0.353 |
Neg logit contributions | |
umn | -0.489 |
cient | -0.465 |
arch | -0.437 |
anwhile | -0.437 |
isode | -0.430 |
Token | effects |
Token ID | 3048 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
IELD | +0.655 |
hips | +0.616 |
Desire | +0.588 |
ymm | +0.585 |
suppose | +0.540 |
Neg logit contributions | |
umn | -0.758 |
cient | -0.727 |
anwhile | -0.694 |
arch | -0.682 |
isode | -0.681 |
Token | are |
Token ID | 389 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
IELD | +1.609 |
hips | +1.511 |
Desire | +1.455 |
ymm | +1.444 |
suppose | +1.324 |
Neg logit contributions | |
umn | -1.929 |
cient | -1.856 |
anwhile | -1.762 |
isode | -1.733 |
arch | -1.731 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
umn | +0.154 |
cient | +0.151 |
arch | +0.142 |
anwhile | +0.139 |
isode | +0.138 |
Neg logit contributions | |
IELD | -0.142 |
hips | -0.132 |
Desire | -0.129 |
ymm | -0.127 |
suppose | -0.116 |
Token | be |
Token ID | 307 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
IELD | +2.192 |
hips | +2.092 |
Desire | +1.995 |
ymm | +1.973 |
suppose | +1.846 |
Neg logit contributions | |
umn | -2.516 |
cient | -2.402 |
anwhile | -2.297 |
isode | -2.266 |
arch | -2.251 |
Token | more |
Token ID | 517 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
IELD | +2.398 |
hips | +2.269 |
Desire | +2.156 |
ymm | +2.123 |
suppose | +1.965 |
Neg logit contributions | |
umn | -3.390 |
cient | -3.260 |
anwhile | -3.121 |
isode | -3.083 |
arch | -3.076 |
Token | of |
Token ID | 286 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
IELD | +0.081 |
hips | +0.075 |
Desire | +0.073 |
ymm | +0.072 |
suppose | +0.066 |
Neg logit contributions | |
umn | -0.098 |
cient | -0.097 |
arch | -0.091 |
anwhile | -0.089 |
ophone | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
IELD | +0.175 |
hips | +0.164 |
ymm | +0.152 |
Desire | +0.151 |
suppose | +0.135 |
Neg logit contributions | |
umn | -0.352 |
cient | -0.343 |
anwhile | -0.325 |
arch | -0.325 |
isode | -0.324 |
Token | socio |
Token ID | 21790 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
IELD | +2.337 |
hips | +2.236 |
Desire | +2.126 |
ymm | +2.117 |
suppose | +1.974 |
Neg logit contributions | |
umn | -2.480 |
cient | -2.369 |
anwhile | -2.254 |
isode | -2.227 |
arch | -2.219 |
Token | - |
Token ID | 12 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
cient | +5.942 |
umn | +5.852 |
arch | +5.617 |
isode | +5.065 |
ocide | +4.936 |
Neg logit contributions | |
IELD | -10.835 |
hips | -10.194 |
Desire | -9.880 |
ymm | -9.653 |
suppose | -9.334 |
Token | economic |
Token ID | 17079 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
umn | +0.407 |
cient | +0.380 |
arch | +0.329 |
isode | +0.313 |
anwhile | +0.312 |
Neg logit contributions | |
IELD | -1.347 |
hips | -1.288 |
Desire | -1.257 |
ymm | -1.242 |
suppose | -1.206 |
Token | construct |
Token ID | 5678 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
umn | +4.332 |
cient | +4.267 |
arch | +3.919 |
isode | +3.869 |
ophone | +3.860 |
Neg logit contributions | |
IELD | -4.685 |
hips | -4.322 |
ymm | -4.195 |
Desire | -4.070 |
GV | -3.867 |
Token | than |
Token ID | 621 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
umn | +0.236 |
cient | +0.228 |
arch | +0.213 |
isode | +0.213 |
anwhile | +0.212 |
Neg logit contributions | |
IELD | -0.197 |
hips | -0.182 |
Desire | -0.177 |
ymm | -0.175 |
suppose | -0.160 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
umn | +1.658 |
cient | +1.622 |
arch | +1.537 |
isode | +1.512 |
anwhile | +1.510 |
Neg logit contributions | |
IELD | -1.016 |
hips | -0.917 |
Desire | -0.867 |
ymm | -0.861 |
Hold | -0.767 |
Token | says |
Token ID | 1139 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
umn | +1.017 |
cient | +0.957 |
anwhile | +0.910 |
arch | +0.897 |
isode | +0.887 |
Neg logit contributions | |
IELD | -1.132 |
hips | -1.056 |
Desire | -1.026 |
ymm | -1.017 |
suppose | -0.952 |
Token | she |
Token ID | 673 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
umn | +1.637 |
cient | +1.543 |
anwhile | +1.448 |
isode | +1.443 |
arch | +1.435 |
Neg logit contributions | |
IELD | -1.826 |
hips | -1.706 |
ymm | -1.655 |
Desire | -1.628 |
suppose | -1.544 |
Token | has |
Token ID | 468 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
umn | +0.692 |
cient | +0.656 |
anwhile | +0.622 |
arch | +0.615 |
isode | +0.608 |
Neg logit contributions | |
IELD | -0.710 |
hips | -0.666 |
Desire | -0.644 |
ymm | -0.641 |
suppose | -0.596 |
Token | been |
Token ID | 587 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
umn | +1.839 |
cient | +1.748 |
isode | +1.641 |
arch | +1.640 |
anwhile | +1.616 |
Neg logit contributions | |
IELD | -1.918 |
hips | -1.753 |
ymm | -1.711 |
Desire | -1.704 |
suppose | -1.583 |
Token | a |
Token ID | 257 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
umn | +1.256 |
cient | +1.186 |
arch | +1.132 |
isode | +1.125 |
anwhile | +1.113 |
Neg logit contributions | |
IELD | -1.160 |
hips | -1.059 |
ymm | -1.018 |
Desire | -1.018 |
suppose | -0.933 |
Token | travel |
Token ID | 3067 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
umn | +1.327 |
cient | +1.246 |
isode | +1.184 |
anwhile | +1.181 |
arch | +1.178 |
Neg logit contributions | |
IELD | -1.362 |
hips | -1.275 |
ymm | -1.231 |
Desire | -1.197 |
suppose | -1.145 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
umn | +5.057 |
cient | +4.694 |
isode | +4.272 |
arch | +4.223 |
ophone | +4.122 |
Neg logit contributions | |
IELD | -11.001 |
hips | -10.466 |
ymm | -10.280 |
Desire | -9.954 |
ENTION | -9.630 |
Token | food |
Token ID | 2057 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
umn | +2.803 |
cient | +2.646 |
isode | +2.526 |
anwhile | +2.512 |
arch | +2.508 |
Neg logit contributions | |
IELD | -2.893 |
hips | -2.686 |
ymm | -2.605 |
Desire | -2.549 |
suppose | -2.369 |
Token | writer |
Token ID | 6260 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
umn | +1.569 |
cient | +1.464 |
isode | +1.340 |
arch | +1.330 |
anwhile | +1.329 |
Neg logit contributions | |
IELD | -2.855 |
hips | -2.743 |
ymm | -2.670 |
Desire | -2.646 |
suppose | -2.505 |
Token | for |
Token ID | 329 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
umn | +2.063 |
cient | +1.950 |
arch | +1.872 |
isode | +1.861 |
anwhile | +1.837 |
Neg logit contributions | |
IELD | -1.592 |
hips | -1.396 |
ymm | -1.376 |
Desire | -1.359 |
suppose | -1.256 |
Token | 22 |
Token ID | 2534 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
umn | +2.882 |
cient | +2.714 |
arch | +2.566 |
isode | +2.566 |
anwhile | +2.543 |
Neg logit contributions | |
IELD | -2.314 |
hips | -2.123 |
ymm | -2.073 |
Desire | -2.013 |
suppose | -1.920 |
Token | high |
Token ID | 8929 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
IELD | +1.635 |
hips | +1.581 |
Desire | +1.459 |
ymm | +1.442 |
suppose | +1.333 |
Neg logit contributions | |
umn | -2.891 |
cient | -2.770 |
anwhile | -2.721 |
isode | -2.672 |
arch | -2.623 |
Token | heat |
Token ID | 4894 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
IELD | +2.780 |
hips | +2.701 |
Desire | +2.558 |
ymm | +2.526 |
suppose | +2.417 |
Neg logit contributions | |
umn | -3.020 |
cient | -2.878 |
anwhile | -2.799 |
isode | -2.739 |
arch | -2.684 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
IELD | +1.767 |
hips | +1.693 |
Desire | +1.596 |
ymm | +1.566 |
suppose | +1.462 |
Neg logit contributions | |
umn | -2.619 |
cient | -2.510 |
anwhile | -2.447 |
isode | -2.400 |
arch | -2.368 |
Token | Place |
Token ID | 8474 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
umn | +0.643 |
cient | +0.617 |
arch | +0.599 |
isode | +0.594 |
ophone | +0.593 |
Neg logit contributions | |
IELD | -0.166 |
hips | -0.143 |
ymm | -0.131 |
Desire | -0.118 |
suppose | -0.095 |
Token | f |
Token ID | 277 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
IELD | +0.880 |
hips | +0.833 |
Desire | +0.796 |
ymm | +0.793 |
suppose | +0.736 |
Neg logit contributions | |
umn | -0.945 |
cient | -0.902 |
anwhile | -0.851 |
isode | -0.845 |
arch | -0.844 |
Token | rit |
Token ID | 799 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
umn | +0.921 |
cient | +0.862 |
anwhile | +0.792 |
isode | +0.786 |
arch | +0.785 |
Neg logit contributions | |
IELD | -1.491 |
hips | -1.429 |
Desire | -1.395 |
ymm | -1.376 |
suppose | -1.313 |
Token | ters |
Token ID | 1010 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
umn | +6.527 |
cient | +5.933 |
arch | +5.495 |
iously | +5.424 |
ophone | +5.093 |
Neg logit contributions | |
IELD | -10.060 |
Desire | -9.213 |
ymm | -8.925 |
hips | -8.885 |
glim | -8.727 |
Token | in |
Token ID | 287 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
umn | +3.181 |
cient | +3.069 |
arch | +2.910 |
iously | +2.823 |
ophone | +2.817 |
Neg logit contributions | |
IELD | -2.647 |
hips | -2.376 |
Desire | -2.318 |
ymm | -2.304 |
glim | -2.099 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
umn | +2.244 |
cient | +2.159 |
arch | +2.054 |
isode | +2.013 |
ophone | +2.012 |
Neg logit contributions | |
IELD | -1.508 |
hips | -1.403 |
Desire | -1.322 |
ymm | -1.321 |
suppose | -1.197 |
Token | skillet |
Token ID | 41306 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
umn | +3.227 |
cient | +3.059 |
ophone | +2.915 |
arch | +2.870 |
anwhile | +2.864 |
Neg logit contributions | |
IELD | -3.873 |
hips | -3.637 |
ymm | -3.517 |
Desire | -3.510 |
suppose | -3.241 |
Token | ( |
Token ID | 357 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
IELD | +0.470 |
hips | +0.445 |
Desire | +0.420 |
ymm | +0.417 |
suppose | +0.388 |
Neg logit contributions | |
umn | -0.607 |
cient | -0.579 |
anwhile | -0.552 |
isode | -0.547 |
arch | -0.546 |
Token | When |
Token ID | 1649 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
umn | +0.419 |
cient | +0.397 |
arch | +0.379 |
anwhile | +0.377 |
isode | +0.372 |
Neg logit contributions | |
IELD | -0.300 |
hips | -0.278 |
ymm | -0.262 |
Desire | -0.257 |
suppose | -0.245 |
Token | Trudeau |
Token ID | 17524 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
umn | +0.532 |
cient | +0.507 |
anwhile | +0.479 |
arch | +0.478 |
isode | +0.466 |
Neg logit contributions | |
IELD | -0.442 |
hips | -0.411 |
Desire | -0.389 |
ymm | -0.383 |
suppose | -0.352 |
Token | chose |
Token ID | 7690 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
IELD | +3.357 |
hips | +3.242 |
Desire | +3.071 |
ymm | +3.042 |
suppose | +2.882 |
Neg logit contributions | |
umn | -3.553 |
cient | -3.397 |
anwhile | -3.258 |
isode | -3.225 |
arch | -3.166 |
Token | St |
Token ID | 520 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
IELD | +0.317 |
hips | +0.293 |
ymm | +0.279 |
Desire | +0.277 |
suppose | +0.259 |
Neg logit contributions | |
umn | -0.403 |
cient | -0.382 |
anwhile | -0.364 |
arch | -0.364 |
isode | -0.356 |
Token | é |
Token ID | 2634 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
IELD | +2.085 |
hips | +1.980 |
ymm | +1.898 |
Desire | +1.891 |
suppose | +1.797 |
Neg logit contributions | |
umn | -1.557 |
cient | -1.455 |
arch | -1.373 |
anwhile | -1.365 |
isode | -1.344 |
Token | ph |
Token ID | 746 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
umn | +2.143 |
cient | +1.919 |
ophone | +1.769 |
arch | +1.752 |
isode | +1.663 |
Neg logit contributions | |
IELD | -5.036 |
hips | -4.769 |
ymm | -4.533 |
Desire | -4.530 |
suppose | -4.351 |
Token | ane |
Token ID | 1531 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
umn | +5.659 |
arch | +5.326 |
cient | +4.986 |
ocide | +4.966 |
ophone | +4.933 |
Neg logit contributions | |
IELD | -10.435 |
WARE | -9.671 |
hips | -9.513 |
GV | -9.125 |
Desire | -9.076 |
Token | Dion |
Token ID | 29628 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
umn | +0.889 |
cient | +0.830 |
anwhile | +0.791 |
arch | +0.787 |
isode | +0.783 |
Neg logit contributions | |
IELD | -0.844 |
hips | -0.806 |
ymm | -0.755 |
Desire | -0.744 |
suppose | -0.700 |
Token | as |
Token ID | 355 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
IELD | +1.289 |
hips | +1.224 |
Desire | +1.164 |
ymm | +1.144 |
suppose | +1.073 |
Neg logit contributions | |
umn | -1.552 |
cient | -1.484 |
anwhile | -1.411 |
arch | -1.410 |
isode | -1.386 |
Token | minister |
Token ID | 5342 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
umn | +0.904 |
cient | +0.842 |
arch | +0.804 |
anwhile | +0.800 |
isode | +0.790 |
Neg logit contributions | |
IELD | -0.761 |
hips | -0.711 |
ymm | -0.676 |
Desire | -0.670 |
suppose | -0.631 |
Token | of |
Token ID | 286 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
umn | +1.503 |
cient | +1.431 |
arch | +1.353 |
isode | +1.341 |
anwhile | +1.335 |
Neg logit contributions | |
IELD | -1.363 |
hips | -1.235 |
Desire | -1.222 |
ymm | -1.201 |
suppose | -1.126 |
Token | mirrors |
Token ID | 22353 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
IELD | +0.955 |
hips | +0.901 |
ymm | +0.846 |
Desire | +0.839 |
suppose | +0.777 |
Neg logit contributions | |
umn | -1.240 |
cient | -1.196 |
anwhile | -1.141 |
arch | -1.127 |
isode | -1.121 |
Token | for |
Token ID | 329 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
umn | +1.470 |
cient | +1.434 |
arch | +1.354 |
anwhile | +1.328 |
isode | +1.318 |
Neg logit contributions | |
IELD | -1.326 |
hips | -1.211 |
Desire | -1.184 |
ymm | -1.184 |
suppose | -1.074 |
Token | primates |
Token ID | 41316 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
IELD | +0.280 |
hips | +0.269 |
Desire | +0.250 |
ymm | +0.248 |
suppose | +0.229 |
Neg logit contributions | |
umn | -0.369 |
cient | -0.355 |
anwhile | -0.339 |
arch | -0.336 |
isode | -0.332 |
Token | , |
Token ID | 11 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
umn | +2.716 |
cient | +2.649 |
arch | +2.528 |
ophone | +2.434 |
anwhile | +2.419 |
Neg logit contributions | |
IELD | -2.495 |
hips | -2.245 |
ymm | -2.238 |
Desire | -2.190 |
Darling | -2.023 |
Token | k |
Token ID | 479 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
umn | +1.059 |
cient | +1.024 |
anwhile | +0.971 |
arch | +0.968 |
isode | +0.954 |
Neg logit contributions | |
IELD | -0.882 |
hips | -0.822 |
Desire | -0.788 |
ymm | -0.774 |
suppose | -0.705 |
Token | ong |
Token ID | 506 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
IELD | +1.876 |
hips | +1.785 |
Desire | +1.728 |
ymm | +1.678 |
suppose | +1.604 |
Neg logit contributions | |
umn | -1.614 |
cient | -1.532 |
arch | -1.432 |
anwhile | -1.422 |
isode | -1.410 |
Token | toys |
Token ID | 14958 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
umn | +7.576 |
arch | +7.206 |
cient | +7.176 |
ophone | +6.737 |
anwhile | +6.666 |
Neg logit contributions | |
IELD | -8.141 |
hips | -7.422 |
Desire | -7.097 |
ymm | -6.927 |
ELF | -6.789 |
Token | and |
Token ID | 290 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
umn | +1.188 |
cient | +1.151 |
arch | +1.084 |
anwhile | +1.076 |
ophone | +1.062 |
Neg logit contributions | |
IELD | -1.155 |
hips | -1.055 |
Desire | -1.042 |
ymm | -1.033 |
suppose | -0.962 |
Token | pr |
Token ID | 778 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
umn | +1.658 |
cient | +1.609 |
anwhile | +1.526 |
arch | +1.511 |
ophone | +1.496 |
Neg logit contributions | |
IELD | -1.454 |
hips | -1.344 |
ymm | -1.289 |
Desire | -1.281 |
suppose | -1.165 |
Token | imate |
Token ID | 1920 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
umn | +1.061 |
cient | +1.021 |
arch | +0.960 |
ophone | +0.933 |
isode | +0.932 |
Neg logit contributions | |
IELD | -0.984 |
hips | -0.905 |
Desire | -0.887 |
ymm | -0.861 |
WARE | -0.811 |
Token | c |
Token ID | 66 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
umn | +0.180 |
cient | +0.172 |
arch | +0.163 |
anwhile | +0.162 |
isode | +0.161 |
Neg logit contributions | |
IELD | -0.170 |
hips | -0.162 |
ymm | -0.154 |
Desire | -0.153 |
suppose | -0.142 |
Token | W |
Token ID | 370 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
umn | +1.574 |
cient | +1.478 |
arch | +1.404 |
isode | +1.384 |
anwhile | +1.379 |
Neg logit contributions | |
IELD | -1.564 |
hips | -1.546 |
Desire | -1.394 |
ymm | -1.383 |
suppose | -1.336 |
Token | ether |
Token ID | 6750 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
IELD | +3.880 |
hips | +3.746 |
Desire | +3.573 |
ymm | +3.544 |
suppose | +3.347 |
Neg logit contributions | |
umn | -3.485 |
cient | -3.305 |
anwhile | -3.171 |
isode | -3.100 |
arch | -3.059 |
Token | s |
Token ID | 82 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
umn | +3.105 |
cient | +2.977 |
isode | +2.872 |
anwhile | +2.837 |
arch | +2.815 |
Neg logit contributions | |
IELD | -3.157 |
hips | -3.002 |
ymm | -2.860 |
Desire | -2.849 |
suppose | -2.711 |
Token | Mysteries |
Token ID | 28298 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
IELD | +0.549 |
hips | +0.506 |
ymm | +0.487 |
Desire | +0.484 |
suppose | +0.463 |
Neg logit contributions | |
umn | -0.638 |
cient | -0.616 |
isode | -0.582 |
anwhile | -0.582 |
arch | -0.580 |
Token | , |
Token ID | 11 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
umn | +0.073 |
cient | +0.071 |
isode | +0.067 |
arch | +0.066 |
anwhile | +0.066 |
Neg logit contributions | |
IELD | -0.063 |
hips | -0.059 |
ymm | -0.057 |
Desire | -0.056 |
suppose | -0.053 |
Token | comic |
Token ID | 9048 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
IELD | +0.795 |
hips | +0.747 |
ymm | +0.697 |
Desire | +0.692 |
suppose | +0.647 |
Neg logit contributions | |
umn | -1.171 |
cient | -1.122 |
anwhile | -1.079 |
isode | -1.070 |
arch | -1.058 |
Token | book |
Token ID | 1492 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
umn | +7.479 |
cient | +7.077 |
isode | +6.959 |
arch | +6.709 |
iously | +6.554 |
Neg logit contributions | |
IELD | -8.186 |
hips | -7.707 |
ymm | -7.353 |
Desire | -7.142 |
ENTION | -6.803 |
Token | short |
Token ID | 1790 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
umn | +3.736 |
cient | +3.534 |
isode | +3.404 |
anwhile | +3.303 |
arch | +3.300 |
Neg logit contributions | |
IELD | -3.703 |
hips | -3.486 |
ymm | -3.332 |
Desire | -3.307 |
suppose | -3.115 |
Token | stories |
Token ID | 3923 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
umn | +0.240 |
cient | +0.227 |
isode | +0.218 |
arch | +0.212 |
anwhile | +0.212 |
Neg logit contributions | |
IELD | -0.244 |
hips | -0.232 |
Desire | -0.220 |
ymm | -0.219 |
suppose | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
umn | +1.831 |
cient | +1.758 |
isode | +1.646 |
arch | +1.638 |
anwhile | +1.629 |
Neg logit contributions | |
IELD | -1.743 |
hips | -1.596 |
ymm | -1.550 |
Desire | -1.531 |
suppose | -1.458 |
Token | prose |
Token ID | 27149 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
IELD | +0.730 |
hips | +0.691 |
ymm | +0.656 |
Desire | +0.653 |
suppose | +0.617 |
Neg logit contributions | |
umn | -0.818 |
cient | -0.781 |
anwhile | -0.743 |
isode | -0.738 |
arch | -0.729 |
Token | : |
Token ID | 25 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
umn | +3.006 |
cient | +2.921 |
anwhile | +2.751 |
arch | +2.729 |
isode | +2.703 |
Neg logit contributions | |
IELD | -2.410 |
hips | -2.219 |
ymm | -2.134 |
Desire | -2.099 |
suppose | -1.936 |
Token | " |
Token ID | 366 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
umn | +0.647 |
cient | +0.617 |
anwhile | +0.587 |
isode | +0.582 |
arch | +0.579 |
Neg logit contributions | |
IELD | -0.577 |
hips | -0.545 |
Desire | -0.522 |
ymm | -0.517 |
suppose | -0.488 |
Token | Supporters |
Token ID | 49422 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
IELD | +0.703 |
hips | +0.664 |
Desire | +0.638 |
ymm | +0.627 |
suppose | +0.594 |
Neg logit contributions | |
umn | -0.939 |
cient | -0.906 |
arch | -0.859 |
isode | -0.854 |
anwhile | -0.840 |
Token | are |
Token ID | 389 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
IELD | +1.899 |
hips | +1.762 |
ymm | +1.694 |
Desire | +1.692 |
suppose | +1.570 |
Neg logit contributions | |
umn | -2.293 |
cient | -2.202 |
anwhile | -2.078 |
arch | -2.071 |
isode | -2.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
umn | +0.603 |
cient | +0.588 |
arch | +0.562 |
anwhile | +0.547 |
isode | +0.543 |
Neg logit contributions | |
IELD | -0.490 |
hips | -0.439 |
ymm | -0.426 |
Desire | -0.422 |
ELF | -0.377 |
Token | life |
Token ID | 1204 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
umn | +2.138 |
cient | +2.069 |
arch | +1.952 |
anwhile | +1.894 |
isode | +1.874 |
Neg logit contributions | |
IELD | -2.087 |
hips | -1.999 |
ymm | -1.884 |
Desire | -1.841 |
suppose | -1.758 |
Token | blood |
Token ID | 18041 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
cient | +4.404 |
umn | +4.360 |
arch | +3.669 |
isode | +3.398 |
iously | +3.200 |
Neg logit contributions | |
IELD | -11.181 |
ymm | -10.517 |
hips | -10.393 |
Desire | -10.376 |
ELF | -10.175 |
Token | of |
Token ID | 286 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
umn | +3.156 |
cient | +2.993 |
isode | +2.839 |
anwhile | +2.827 |
arch | +2.815 |
Neg logit contributions | |
IELD | -3.047 |
hips | -2.851 |
Desire | -2.808 |
ymm | -2.794 |
suppose | -2.600 |
Token | any |
Token ID | 597 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
umn | +0.628 |
cient | +0.600 |
arch | +0.571 |
anwhile | +0.569 |
isode | +0.566 |
Neg logit contributions | |
IELD | -0.400 |
hips | -0.370 |
ymm | -0.351 |
Desire | -0.346 |
suppose | -0.319 |
Token | football |
Token ID | 4346 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
umn | +1.254 |
cient | +1.198 |
arch | +1.130 |
isode | +1.109 |
ophone | +1.100 |
Neg logit contributions | |
IELD | -1.231 |
hips | -1.153 |
ymm | -1.109 |
Desire | -1.089 |
suppose | -1.013 |
Token | club |
Token ID | 3430 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
umn | +2.968 |
cient | +2.908 |
isode | +2.556 |
ophone | +2.554 |
arch | +2.536 |
Neg logit contributions | |
IELD | -5.696 |
hips | -5.295 |
ymm | -5.185 |
Desire | -5.174 |
ELF | -4.866 |
Token | thinks |
Token ID | 6834 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
IELD | +2.160 |
hips | +2.086 |
Desire | +1.983 |
ymm | +1.957 |
suppose | +1.853 |
Neg logit contributions | |
umn | -2.356 |
cient | -2.245 |
anwhile | -2.156 |
isode | -2.120 |
arch | -2.096 |
Token | of |
Token ID | 286 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
IELD | +0.864 |
hips | +0.825 |
Desire | +0.784 |
ymm | +0.776 |
suppose | +0.729 |
Neg logit contributions | |
umn | -0.999 |
cient | -0.952 |
anwhile | -0.910 |
isode | -0.900 |
arch | -0.900 |
Token | when |
Token ID | 618 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
IELD | +1.208 |
hips | +1.137 |
Desire | +1.068 |
ymm | +1.055 |
suppose | +0.974 |
Neg logit contributions | |
umn | -1.933 |
cient | -1.860 |
anwhile | -1.791 |
arch | -1.777 |
isode | -1.773 |
Token | you |
Token ID | 345 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
umn | +2.144 |
cient | +2.037 |
anwhile | +1.949 |
arch | +1.939 |
isode | +1.905 |
Neg logit contributions | |
IELD | -2.120 |
hips | -2.002 |
ymm | -1.918 |
Desire | -1.883 |
suppose | -1.760 |
Token | mention |
Token ID | 3068 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
umn | +0.616 |
cient | +0.587 |
anwhile | +0.564 |
isode | +0.555 |
arch | +0.553 |
Neg logit contributions | |
IELD | -0.538 |
hips | -0.502 |
Desire | -0.482 |
ymm | -0.481 |
Darling | -0.435 |
Token | Psych |
Token ID | 31923 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
IELD | +0.670 |
hips | +0.634 |
Desire | +0.599 |
ymm | +0.595 |
suppose | +0.558 |
Neg logit contributions | |
umn | -0.847 |
cient | -0.811 |
anwhile | -0.775 |
arch | -0.770 |
isode | -0.760 |
Token | o |
Token ID | 78 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
umn | +4.453 |
cient | +3.682 |
arch | +3.660 |
ophone | +3.564 |
ocide | +3.499 |
Neg logit contributions | |
IELD | -11.444 |
hips | -10.818 |
Desire | -10.651 |
ymm | -10.441 |
glim | -10.261 |
Token | , |
Token ID | 11 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
umn | +4.021 |
cient | +3.845 |
arch | +3.640 |
anwhile | +3.633 |
isode | +3.609 |
Neg logit contributions | |
IELD | -3.692 |
hips | -3.535 |
ymm | -3.351 |
Desire | -3.344 |
suppose | -3.065 |
Token | and |
Token ID | 290 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
IELD | +0.636 |
hips | +0.606 |
Desire | +0.575 |
ymm | +0.569 |
suppose | +0.526 |
Neg logit contributions | |
umn | -0.817 |
cient | -0.783 |
anwhile | -0.751 |
arch | -0.744 |
isode | -0.738 |
Token | with |
Token ID | 351 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
umn | +1.422 |
cient | +1.365 |
anwhile | +1.314 |
arch | +1.299 |
isode | +1.280 |
Neg logit contributions | |
IELD | -1.135 |
hips | -1.073 |
ymm | -1.010 |
Desire | -1.004 |
suppose | -0.920 |
Token | good |
Token ID | 922 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
IELD | +2.994 |
hips | +2.850 |
Desire | +2.695 |
ymm | +2.663 |
suppose | +2.478 |
Neg logit contributions | |
umn | -4.179 |
cient | -4.003 |
anwhile | -3.853 |
isode | -3.802 |
arch | -3.776 |
Token | W |
Token ID | 370 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
umn | +2.649 |
cient | +2.532 |
ophone | +2.372 |
arch | +2.370 |
isode | +2.327 |
Neg logit contributions | |
IELD | -2.111 |
hips | -2.012 |
ymm | -1.903 |
Desire | -1.846 |
suppose | -1.783 |
Token | ether |
Token ID | 6750 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
IELD | +3.009 |
hips | +2.961 |
ymm | +2.737 |
Desire | +2.669 |
suppose | +2.534 |
Neg logit contributions | |
umn | -3.768 |
anwhile | -3.626 |
cient | -3.571 |
isode | -3.441 |
arch | -3.353 |
Token | s |
Token ID | 82 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
umn | +3.122 |
cient | +2.914 |
arch | +2.779 |
iously | +2.662 |
isode | +2.635 |
Neg logit contributions | |
IELD | -3.602 |
hips | -3.301 |
Desire | -3.285 |
ymm | -3.218 |
glim | -3.062 |
Token | Mysteries |
Token ID | 28298 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
IELD | +0.237 |
hips | +0.222 |
Desire | +0.213 |
ymm | +0.211 |
suppose | +0.200 |
Neg logit contributions | |
umn | -0.267 |
cient | -0.253 |
arch | -0.238 |
isode | -0.237 |
anwhile | -0.236 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
umn | +0.781 |
cient | +0.747 |
arch | +0.702 |
isode | +0.696 |
anwhile | +0.690 |
Neg logit contributions | |
IELD | -0.710 |
hips | -0.668 |
Desire | -0.641 |
ymm | -0.638 |
suppose | -0.600 |
Token | comic |
Token ID | 9048 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
IELD | +0.577 |
hips | +0.549 |
Desire | +0.523 |
ymm | +0.519 |
suppose | +0.486 |
Neg logit contributions | |
umn | -0.635 |
cient | -0.608 |
anwhile | -0.575 |
isode | -0.573 |
arch | -0.566 |
Token | book |
Token ID | 1492 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
umn | +4.593 |
cient | +4.413 |
arch | +3.924 |
isode | +3.705 |
ophone | +3.650 |
Neg logit contributions | |
IELD | -11.348 |
hips | -10.548 |
ymm | -10.317 |
Desire | -10.245 |
WARE | -9.802 |
Token | short |
Token ID | 1790 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
umn | +5.029 |
cient | +4.822 |
isode | +4.583 |
arch | +4.535 |
ophone | +4.468 |
Neg logit contributions | |
IELD | -3.057 |
hips | -2.806 |
Desire | -2.622 |
ymm | -2.610 |
suppose | -2.309 |
Token | stories |
Token ID | 3923 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
umn | +0.823 |
cient | +0.782 |
arch | +0.724 |
isode | +0.723 |
anwhile | +0.712 |
Neg logit contributions | |
IELD | -0.859 |
hips | -0.803 |
Desire | -0.779 |
ymm | -0.768 |
suppose | -0.716 |
Token | , |
Token ID | 11 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
umn | +2.252 |
cient | +2.160 |
arch | +2.024 |
ophone | +1.968 |
isode | +1.959 |
Neg logit contributions | |
IELD | -2.284 |
hips | -2.111 |
Desire | -2.052 |
ymm | -2.043 |
suppose | -1.919 |
Token | prose |
Token ID | 27149 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
IELD | +0.113 |
hips | +0.107 |
Desire | +0.101 |
ymm | +0.101 |
suppose | +0.093 |
Neg logit contributions | |
umn | -0.152 |
cient | -0.146 |
anwhile | -0.139 |
isode | -0.138 |
arch | -0.137 |
Token | MORE |
Token ID | 12011 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
umn | +1.339 |
cient | +1.276 |
anwhile | +1.220 |
arch | +1.213 |
isode | +1.195 |
Neg logit contributions | |
IELD | -0.712 |
hips | -0.668 |
Desire | -0.610 |
ymm | -0.596 |
suppose | -0.557 |
Token | as |
Token ID | 355 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
IELD | +1.542 |
hips | +1.443 |
Desire | +1.379 |
ymm | +1.362 |
suppose | +1.252 |
Neg logit contributions | |
umn | -1.949 |
cient | -1.869 |
anwhile | -1.797 |
arch | -1.778 |
isode | -1.755 |
Token | a |
Token ID | 257 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
umn | +2.172 |
cient | +2.097 |
anwhile | +2.015 |
arch | +1.985 |
ophone | +1.932 |
Neg logit contributions | |
IELD | -1.603 |
hips | -1.494 |
Desire | -1.428 |
ymm | -1.366 |
GV | -1.267 |
Token | 68 |
Token ID | 8257 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
umn | +1.946 |
cient | +1.844 |
arch | +1.761 |
anwhile | +1.759 |
isode | +1.715 |
Neg logit contributions | |
IELD | -1.456 |
hips | -1.406 |
ymm | -1.292 |
Desire | -1.281 |
WARE | -1.158 |
Token | - |
Token ID | 12 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
umn | +1.392 |
cient | +1.291 |
anwhile | +1.199 |
arch | +1.178 |
isode | +1.169 |
Neg logit contributions | |
IELD | -2.194 |
hips | -2.132 |
Desire | -2.061 |
ymm | -2.041 |
suppose | -1.931 |
Token | year |
Token ID | 1941 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
umn | +1.096 |
cient | +0.959 |
arch | +0.872 |
isode | +0.852 |
anwhile | +0.849 |
Neg logit contributions | |
IELD | -2.915 |
hips | -2.800 |
Desire | -2.740 |
ymm | -2.683 |
suppose | -2.570 |
Token | - |
Token ID | 12 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
umn | +5.365 |
cient | +4.993 |
arch | +4.623 |
anwhile | +4.285 |
isode | +4.275 |
Neg logit contributions | |
IELD | -10.087 |
hips | -9.890 |
ymm | -9.464 |
Desire | -9.290 |
GV | -8.837 |
Token | old |
Token ID | 727 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
umn | +0.160 |
cient | +0.151 |
anwhile | +0.144 |
isode | +0.140 |
arch | +0.137 |
Neg logit contributions | |
IELD | -0.244 |
hips | -0.237 |
Desire | -0.228 |
ymm | -0.226 |
suppose | -0.216 |
Token | woman |
Token ID | 2415 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
umn | +2.652 |
cient | +2.511 |
arch | +2.404 |
anwhile | +2.340 |
ophone | +2.322 |
Neg logit contributions | |
IELD | -2.568 |
hips | -2.415 |
ymm | -2.267 |
Desire | -2.209 |
ELF | -2.066 |
Token | 's |
Token ID | 338 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
umn | +0.911 |
cient | +0.870 |
arch | +0.826 |
anwhile | +0.819 |
isode | +0.811 |
Neg logit contributions | |
IELD | -0.842 |
hips | -0.775 |
ymm | -0.739 |
Desire | -0.738 |
suppose | -0.676 |
Token | cause |
Token ID | 2728 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
IELD | +0.908 |
hips | +0.861 |
ymm | +0.813 |
Desire | +0.805 |
suppose | +0.739 |
Neg logit contributions | |
umn | -1.033 |
cient | -0.993 |
anwhile | -0.937 |
arch | -0.936 |
isode | -0.922 |
Token | was |
Token ID | 373 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
IELD | +1.567 |
hips | +1.491 |
Desire | +1.418 |
ymm | +1.412 |
suppose | +1.318 |
Neg logit contributions | |
umn | -1.712 |
cient | -1.633 |
anwhile | -1.562 |
arch | -1.537 |
isode | -1.531 |
Token | forced |
Token ID | 4137 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
umn | +1.567 |
cient | +1.499 |
arch | +1.431 |
anwhile | +1.409 |
ophone | +1.368 |
Neg logit contributions | |
IELD | -1.608 |
hips | -1.487 |
ymm | -1.440 |
Desire | -1.437 |
Darling | -1.292 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
umn | +0.431 |
cient | +0.410 |
anwhile | +0.391 |
arch | +0.388 |
isode | +0.382 |
Neg logit contributions | |
IELD | -0.405 |
hips | -0.377 |
Desire | -0.364 |
ymm | -0.363 |
suppose | -0.334 |
Token | write |
Token ID | 3551 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
umn | +2.230 |
cient | +2.119 |
arch | +2.019 |
isode | +1.978 |
anwhile | +1.972 |
Neg logit contributions | |
IELD | -2.336 |
hips | -2.163 |
ymm | -2.132 |
Desire | -2.108 |
Darling | -1.939 |
Token | a |
Token ID | 257 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
umn | +4.744 |
cient | +4.616 |
arch | +4.353 |
iously | +4.352 |
anwhile | +4.309 |
Neg logit contributions | |
IELD | -3.445 |
hips | -3.022 |
ymm | -2.947 |
Desire | -2.805 |
WARE | -2.621 |
Token | letter |
Token ID | 3850 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
umn | +1.152 |
cient | +1.097 |
arch | +1.036 |
anwhile | +1.035 |
isode | +1.017 |
Neg logit contributions | |
IELD | -1.284 |
hips | -1.218 |
ymm | -1.164 |
Desire | -1.126 |
suppose | -1.063 |
Token | explaining |
Token ID | 11170 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
umn | +7.435 |
cient | +7.198 |
arch | +6.784 |
iously | +6.566 |
anwhile | +6.559 |
Neg logit contributions | |
IELD | -7.972 |
hips | -7.101 |
ymm | -7.097 |
Desire | -6.772 |
WARE | -6.326 |
Token | her |
Token ID | 607 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
umn | +3.202 |
cient | +3.035 |
arch | +2.893 |
anwhile | +2.869 |
iously | +2.818 |
Neg logit contributions | |
IELD | -2.609 |
hips | -2.444 |
ymm | -2.331 |
Desire | -2.265 |
suppose | -2.110 |
Token | actions |
Token ID | 4028 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
IELD | +1.190 |
hips | +1.137 |
ymm | +1.082 |
Desire | +1.074 |
suppose | +1.005 |
Neg logit contributions | |
umn | -1.221 |
cient | -1.167 |
anwhile | -1.101 |
arch | -1.098 |
isode | -1.072 |
Token | in |
Token ID | 287 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
umn | +0.479 |
cient | +0.464 |
anwhile | +0.440 |
arch | +0.434 |
isode | +0.428 |
Neg logit contributions | |
IELD | -0.406 |
hips | -0.375 |
ymm | -0.361 |
Desire | -0.358 |
suppose | -0.331 |
Token | school |
Token ID | 1524 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
umn | +0.453 |
cient | +0.432 |
anwhile | +0.417 |
arch | +0.415 |
isode | +0.405 |
Neg logit contributions | |
IELD | -0.370 |
hips | -0.351 |
ymm | -0.333 |
Desire | -0.320 |
suppose | -0.304 |
Token | call |
Token ID | 869 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
IELD | +0.306 |
hips | +0.289 |
Desire | +0.277 |
ymm | +0.275 |
suppose | +0.253 |
Neg logit contributions | |
umn | -0.365 |
cient | -0.349 |
anwhile | -0.334 |
arch | -0.330 |
isode | -0.328 |
Token | it |
Token ID | 340 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
umn | +0.456 |
cient | +0.436 |
anwhile | +0.413 |
arch | +0.412 |
isode | +0.405 |
Neg logit contributions | |
IELD | -0.385 |
hips | -0.361 |
ymm | -0.344 |
Desire | -0.337 |
suppose | -0.316 |
Token | a |
Token ID | 257 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
umn | +1.108 |
cient | +1.073 |
arch | +1.018 |
anwhile | +1.014 |
ophone | +1.001 |
Neg logit contributions | |
IELD | -0.783 |
hips | -0.702 |
ymm | -0.679 |
Desire | -0.654 |
suppose | -0.599 |
Token | � |
Token ID | 564 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
IELD | +0.958 |
hips | +0.907 |
ymm | +0.863 |
Desire | +0.860 |
suppose | +0.801 |
Neg logit contributions | |
umn | -1.051 |
cient | -1.008 |
anwhile | -0.957 |
isode | -0.948 |
arch | -0.945 |
Token | � |
Token ID | 246 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
umn | +0.291 |
cient | +0.277 |
arch | +0.259 |
anwhile | +0.256 |
isode | +0.256 |
Neg logit contributions | |
IELD | -0.248 |
hips | -0.237 |
Desire | -0.225 |
ymm | -0.225 |
suppose | -0.209 |
Token | ph |
Token ID | 746 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
umn | +1.486 |
cient | +1.425 |
arch | +1.327 |
anwhile | +1.315 |
isode | +1.308 |
Neg logit contributions | |
IELD | -1.744 |
hips | -1.633 |
Desire | -1.591 |
ymm | -1.577 |
suppose | -1.494 |
Token | o |
Token ID | 78 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
umn | +4.859 |
cient | +4.442 |
ophone | +4.163 |
arch | +4.153 |
ocide | +4.142 |
Neg logit contributions | |
IELD | -10.690 |
hips | -10.190 |
Desire | -9.940 |
ymm | -9.648 |
Darling | -9.368 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
umn | +4.266 |
cient | +4.088 |
isode | +3.881 |
arch | +3.848 |
ophone | +3.838 |
Neg logit contributions | |
IELD | -4.100 |
hips | -3.791 |
ymm | -3.722 |
Desire | -3.613 |
suppose | -3.323 |
Token | � |
Token ID | 447 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
IELD | +0.832 |
hips | +0.794 |
Desire | +0.763 |
ymm | +0.763 |
suppose | +0.708 |
Neg logit contributions | |
umn | -0.756 |
cient | -0.719 |
anwhile | -0.677 |
arch | -0.670 |
isode | -0.666 |
Token | � |
Token ID | 247 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
IELD | +0.213 |
hips | +0.201 |
Desire | +0.194 |
ymm | +0.192 |
suppose | +0.179 |
Neg logit contributions | |
umn | -0.252 |
cient | -0.240 |
anwhile | -0.225 |
arch | -0.224 |
isode | -0.222 |
Token | � |
Token ID | 447 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
IELD | +0.097 |
hips | +0.091 |
ymm | +0.086 |
Desire | +0.085 |
suppose | +0.079 |
Neg logit contributions | |
umn | -0.122 |
cient | -0.117 |
anwhile | -0.112 |
arch | -0.110 |
isode | -0.110 |
Token | this |
Token ID | 428 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
IELD | +0.429 |
hips | +0.399 |
ymm | +0.379 |
Desire | +0.378 |
suppose | +0.337 |
Neg logit contributions | |
umn | -0.633 |
cient | -0.607 |
anwhile | -0.579 |
arch | -0.575 |
isode | -0.572 |
Token | query |
Token ID | 12405 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
umn | +1.784 |
cient | +1.695 |
arch | +1.582 |
anwhile | +1.549 |
isode | +1.545 |
Neg logit contributions | |
IELD | -2.553 |
hips | -2.415 |
ymm | -2.339 |
Desire | -2.301 |
WARE | -2.120 |
Token | to |
Token ID | 284 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
IELD | +0.975 |
hips | +0.920 |
Desire | +0.880 |
ymm | +0.878 |
suppose | +0.796 |
Neg logit contributions | |
umn | -1.239 |
cient | -1.190 |
anwhile | -1.134 |
arch | -1.126 |
isode | -1.117 |
Token | the |
Token ID | 262 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
umn | +0.177 |
cient | +0.168 |
anwhile | +0.160 |
arch | +0.159 |
isode | +0.158 |
Neg logit contributions | |
IELD | -0.175 |
hips | -0.166 |
Desire | -0.160 |
ymm | -0.160 |
suppose | -0.146 |
Token | cl |
Token ID | 537 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
umn | +1.118 |
cient | +1.055 |
arch | +1.004 |
anwhile | +1.003 |
isode | +0.992 |
Neg logit contributions | |
IELD | -1.142 |
hips | -1.073 |
ymm | -1.038 |
Desire | -1.033 |
suppose | -0.963 |
Token | ojure |
Token ID | 32511 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
umn | +2.384 |
cient | +2.215 |
arch | +2.078 |
anwhile | +2.046 |
ophone | +2.043 |
Neg logit contributions | |
IELD | -3.865 |
hips | -3.600 |
Desire | -3.534 |
ymm | -3.422 |
suppose | -3.261 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
umn | +7.541 |
cient | +7.210 |
arch | +7.117 |
anwhile | +6.879 |
isode | +6.626 |
Neg logit contributions | |
IELD | -7.768 |
hips | -7.397 |
Desire | -7.185 |
ymm | -7.048 |
suppose | -6.431 |
Token | files |
Token ID | 16624 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
umn | +0.485 |
cient | +0.443 |
arch | +0.408 |
anwhile | +0.388 |
isode | +0.383 |
Neg logit contributions | |
IELD | -1.162 |
hips | -1.116 |
Desire | -1.092 |
ymm | -1.077 |
suppose | -1.037 |
Token | table |
Token ID | 3084 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
umn | +1.033 |
cient | +0.989 |
arch | +0.931 |
anwhile | +0.918 |
isode | +0.908 |
Neg logit contributions | |
IELD | -0.990 |
hips | -0.910 |
Desire | -0.903 |
ymm | -0.885 |
suppose | -0.825 |
Token | SELECT |
Token ID | 33493 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
umn | +1.540 |
cient | +1.469 |
arch | +1.408 |
anwhile | +1.381 |
isode | +1.371 |
Neg logit contributions | |
IELD | -1.386 |
hips | -1.308 |
ymm | -1.278 |
Desire | -1.261 |
suppose | -1.136 |
Token | * |
Token ID | 1635 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
IELD | +0.275 |
hips | +0.260 |
ymm | +0.252 |
Desire | +0.250 |
suppose | +0.233 |
Neg logit contributions | |
umn | -0.281 |
cient | -0.265 |
arch | -0.252 |
anwhile | -0.251 |
isode | -0.249 |
Token | F |
Token ID | 37 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
umn | +2.648 |
cient | +2.467 |
arch | +2.404 |
isode | +2.343 |
anwhile | +2.317 |
Neg logit contributions | |
IELD | -3.009 |
hips | -2.961 |
ymm | -2.860 |
Desire | -2.810 |
WARE | -2.537 |
Token | ( |
Token ID | 357 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
IELD | +0.048 |
hips | +0.046 |
ymm | +0.044 |
Desire | +0.044 |
suppose | +0.041 |
Neg logit contributions | |
umn | -0.043 |
cient | -0.041 |
anwhile | -0.039 |
isode | -0.039 |
arch | -0.038 |
Token | Low |
Token ID | 20535 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
IELD | +0.296 |
hips | +0.276 |
Desire | +0.267 |
ymm | +0.264 |
suppose | +0.249 |
Neg logit contributions | |
umn | -0.331 |
cient | -0.316 |
arch | -0.300 |
anwhile | -0.298 |
isode | -0.298 |
Token | Carb |
Token ID | 20453 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
IELD | +0.748 |
hips | +0.708 |
ymm | +0.686 |
Desire | +0.668 |
suppose | +0.638 |
Neg logit contributions | |
umn | -0.684 |
cient | -0.650 |
anwhile | -0.619 |
arch | -0.615 |
isode | -0.613 |
Token | High |
Token ID | 3334 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
IELD | +6.391 |
hips | +6.211 |
Desire | +5.984 |
ymm | +5.902 |
suppose | +5.637 |
Neg logit contributions | |
umn | -4.358 |
cient | -4.097 |
anwhile | -3.857 |
isode | -3.787 |
arch | -3.730 |
Token | Fat |
Token ID | 12301 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
IELD | +5.625 |
hips | +5.493 |
Desire | +5.260 |
ymm | +5.009 |
suppose | +4.755 |
Neg logit contributions | |
umn | -6.952 |
cient | -6.671 |
anwhile | -6.409 |
isode | -6.288 |
ophone | -6.150 |
Token | ) |
Token ID | 8 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
hips | +8.494 |
IELD | +8.460 |
Desire | +7.981 |
ymm | +7.394 |
suppose | +7.139 |
Neg logit contributions | |
umn | -11.521 |
cient | -11.120 |
anwhile | -10.566 |
isode | -10.345 |
ophone | -10.219 |
Token | diet |
Token ID | 5496 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
IELD | +1.561 |
hips | +1.482 |
ymm | +1.420 |
Desire | +1.408 |
suppose | +1.309 |
Neg logit contributions | |
umn | -1.502 |
cient | -1.423 |
anwhile | -1.359 |
isode | -1.355 |
arch | -1.345 |
Token | improves |
Token ID | 19575 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
umn | +1.448 |
cient | +1.401 |
anwhile | +1.321 |
arch | +1.316 |
isode | +1.307 |
Neg logit contributions | |
IELD | -1.330 |
hips | -1.206 |
Desire | -1.184 |
ymm | -1.179 |
suppose | -1.077 |
Token | the |
Token ID | 262 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
umn | +1.657 |
cient | +1.576 |
arch | +1.529 |
anwhile | +1.493 |
isode | +1.485 |
Neg logit contributions | |
IELD | -1.546 |
hips | -1.436 |
ymm | -1.416 |
Desire | -1.354 |
WARE | -1.279 |
Token | body |
Token ID | 1767 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
umn | +1.713 |
cient | +1.627 |
arch | +1.558 |
anwhile | +1.535 |
isode | +1.503 |
Neg logit contributions | |
IELD | -1.705 |
hips | -1.599 |
ymm | -1.550 |
Desire | -1.499 |
suppose | -1.421 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
umn | +3.423 |
cient | +3.288 |
arch | +3.128 |
ophone | +3.013 |
iously | +2.995 |
Neg logit contributions | |
IELD | -2.715 |
hips | -2.498 |
ymm | -2.416 |
Desire | -2.400 |
glim | -2.274 |
Token | 3 |
Token ID | 18 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
umn | +2.381 |
cient | +2.286 |
arch | +2.173 |
isode | +2.113 |
ophone | +2.070 |
Neg logit contributions | |
IELD | -1.939 |
hips | -1.837 |
Desire | -1.812 |
ymm | -1.747 |
suppose | -1.667 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
umn | +1.352 |
cient | +1.307 |
anwhile | +1.239 |
arch | +1.227 |
isode | +1.224 |
Neg logit contributions | |
IELD | -1.073 |
hips | -1.024 |
Desire | -0.969 |
ymm | -0.953 |
suppose | -0.908 |
Token | THE |
Token ID | 3336 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
umn | +0.385 |
cient | +0.371 |
arch | +0.351 |
anwhile | +0.349 |
isode | +0.347 |
Neg logit contributions | |
IELD | -0.266 |
hips | -0.253 |
ymm | -0.236 |
Desire | -0.233 |
suppose | -0.223 |
Token | BIG |
Token ID | 26746 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
umn | +1.057 |
cient | +1.022 |
anwhile | +0.977 |
arch | +0.970 |
isode | +0.952 |
Neg logit contributions | |
IELD | -0.751 |
hips | -0.723 |
ymm | -0.675 |
Desire | -0.673 |
suppose | -0.635 |
Token | SH |
Token ID | 6006 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
IELD | +2.350 |
hips | +2.238 |
Desire | +2.113 |
ymm | +2.088 |
suppose | +1.937 |
Neg logit contributions | |
umn | -3.432 |
cient | -3.290 |
anwhile | -3.170 |
isode | -3.131 |
arch | -3.113 |
Token | ORT |
Token ID | 9863 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
IELD | +7.444 |
hips | +6.516 |
Desire | +6.049 |
ymm | +5.859 |
ELF | +5.717 |
Neg logit contributions | |
umn | -11.155 |
anwhile | -10.832 |
cient | -10.744 |
isode | -10.270 |
ophone | -10.133 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
IELD | +0.135 |
hips | +0.133 |
Desire | +0.127 |
ymm | +0.127 |
suppose | +0.117 |
Neg logit contributions | |
umn | -0.194 |
cient | -0.186 |
arch | -0.179 |
anwhile | -0.177 |
isode | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
umn | +0.271 |
cient | +0.261 |
arch | +0.247 |
isode | +0.245 |
anwhile | +0.244 |
Neg logit contributions | |
IELD | -0.178 |
hips | -0.167 |
Desire | -0.158 |
ymm | -0.157 |
suppose | -0.144 |
Token | People |
Token ID | 8061 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
umn | +0.466 |
cient | +0.447 |
arch | +0.424 |
isode | +0.417 |
anwhile | +0.408 |
Neg logit contributions | |
IELD | -0.377 |
hips | -0.359 |
Desire | -0.349 |
ymm | -0.338 |
suppose | -0.321 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
umn | +2.082 |
cient | +2.006 |
anwhile | +1.885 |
arch | +1.880 |
isode | +1.838 |
Neg logit contributions | |
IELD | -1.862 |
hips | -1.691 |
ymm | -1.622 |
Desire | -1.613 |
WARE | -1.483 |
Token | Emirates |
Token ID | 24880 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
IELD | +3.063 |
hips | +2.893 |
Desire | +2.718 |
ymm | +2.682 |
suppose | +2.467 |
Neg logit contributions | |
umn | -5.191 |
cient | -4.987 |
anwhile | -4.815 |
isode | -4.757 |
arch | -4.729 |
Token | and |
Token ID | 290 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
IELD | +3.696 |
hips | +3.535 |
Desire | +3.362 |
ymm | +3.325 |
suppose | +3.116 |
Neg logit contributions | |
umn | -4.370 |
cient | -4.172 |
anwhile | -4.006 |
isode | -3.948 |
arch | -3.916 |
Token | Palestine |
Token ID | 17263 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
umn | +1.724 |
cient | +1.644 |
anwhile | +1.578 |
arch | +1.563 |
isode | +1.541 |
Neg logit contributions | |
IELD | -1.821 |
hips | -1.709 |
ymm | -1.662 |
Desire | -1.598 |
suppose | -1.522 |
Token | in |
Token ID | 287 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
IELD | +1.273 |
hips | +1.204 |
Desire | +1.142 |
ymm | +1.140 |
suppose | +1.053 |
Neg logit contributions | |
umn | -1.601 |
cient | -1.535 |
anwhile | -1.466 |
arch | -1.451 |
isode | -1.450 |
Token | Group |
Token ID | 4912 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
umn | +0.626 |
cient | +0.596 |
arch | +0.564 |
anwhile | +0.563 |
isode | +0.560 |
Neg logit contributions | |
IELD | -0.557 |
hips | -0.529 |
ymm | -0.497 |
Desire | -0.490 |
suppose | -0.462 |
Token | A |
Token ID | 317 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
IELD | +1.568 |
hips | +1.464 |
ymm | +1.387 |
Desire | +1.368 |
suppose | +1.262 |
Neg logit contributions | |
umn | -2.328 |
cient | -2.204 |
anwhile | -2.129 |
isode | -2.128 |
arch | -2.126 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
IELD | +6.864 |
hips | +6.734 |
Desire | +6.189 |
ymm | +6.182 |
suppose | +5.796 |
Neg logit contributions | |
umn | -10.396 |
cient | -10.047 |
anwhile | -9.675 |
isode | -9.523 |
arch | -9.326 |
Token | Here |
Token ID | 3423 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
umn | +0.602 |
cient | +0.576 |
arch | +0.550 |
anwhile | +0.550 |
ophone | +0.541 |
Neg logit contributions | |
IELD | -0.416 |
hips | -0.387 |
ymm | -0.370 |
Desire | -0.361 |
suppose | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
IELD | +1.460 |
hips | +1.393 |
Desire | +1.323 |
ymm | +1.308 |
suppose | +1.219 |
Neg logit contributions | |
umn | -1.667 |
cient | -1.584 |
anwhile | -1.532 |
arch | -1.501 |
isode | -1.497 |
Token | the |
Token ID | 262 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
IELD | +2.275 |
hips | +2.152 |
Desire | +2.044 |
ymm | +2.031 |
suppose | +1.874 |
Neg logit contributions | |
umn | -2.684 |
cient | -2.563 |
anwhile | -2.478 |
arch | -2.426 |
isode | -2.418 |
Token | most |
Token ID | 749 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
IELD | +0.131 |
hips | +0.125 |
ymm | +0.118 |
Desire | +0.118 |
suppose | +0.109 |
Neg logit contributions | |
umn | -0.142 |
cient | -0.136 |
anwhile | -0.130 |
arch | -0.128 |
isode | -0.126 |
Token | � |
Token ID | 126 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
IELD | +0.420 |
hips | +0.391 |
Desire | +0.374 |
ymm | +0.372 |
suppose | +0.346 |
Neg logit contributions | |
umn | -0.475 |
cient | -0.454 |
anwhile | -0.432 |
arch | -0.429 |
isode | -0.426 |
Token | � |
Token ID | 245 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
umn | +1.038 |
cient | +0.982 |
arch | +0.914 |
anwhile | +0.912 |
isode | +0.904 |
Neg logit contributions | |
IELD | -1.094 |
hips | -1.029 |
Desire | -1.001 |
ymm | -0.999 |
suppose | -0.938 |
Token | with |
Token ID | 4480 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
umn | +2.980 |
cient | +2.827 |
arch | +2.733 |
anwhile | +2.650 |
isode | +2.613 |
Neg logit contributions | |
IELD | -3.280 |
hips | -2.977 |
Desire | -2.946 |
ymm | -2.900 |
suppose | -2.716 |
Token | no |
Token ID | 645 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
IELD | +0.641 |
hips | +0.595 |
Desire | +0.564 |
ymm | +0.563 |
suppose | +0.523 |
Neg logit contributions | |
umn | -0.958 |
cient | -0.924 |
anwhile | -0.881 |
arch | -0.878 |
isode | -0.871 |
Token | strings |
Token ID | 13042 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
IELD | +0.148 |
hips | +0.140 |
ymm | +0.134 |
Desire | +0.132 |
suppose | +0.122 |
Neg logit contributions | |
umn | -0.163 |
cient | -0.156 |
anwhile | -0.149 |
arch | -0.148 |
isode | -0.148 |
Token | attached |
Token ID | 7223 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
IELD | +1.080 |
hips | +1.023 |
Desire | +0.991 |
ymm | +0.982 |
suppose | +0.916 |
Neg logit contributions | |
umn | -0.989 |
cient | -0.945 |
anwhile | -0.888 |
arch | -0.877 |
isode | -0.873 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
IELD | +6.422 |
hips | +6.399 |
Desire | +5.792 |
ymm | +5.615 |
suppose | +5.390 |
Neg logit contributions | |
umn | -10.692 |
cient | -10.214 |
anwhile | -10.035 |
isode | -9.953 |
arch | -9.618 |
Token | The |
Token ID | 383 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
IELD | +0.058 |
hips | +0.055 |
ymm | +0.052 |
Desire | +0.051 |
suppose | +0.048 |
Neg logit contributions | |
umn | -0.086 |
cient | -0.082 |
anwhile | -0.078 |
arch | -0.078 |
isode | -0.077 |
Token | hope |
Token ID | 2911 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
IELD | +1.007 |
hips | +0.965 |
ymm | +0.914 |
Desire | +0.913 |
suppose | +0.857 |
Neg logit contributions | |
umn | -1.010 |
cient | -0.960 |
anwhile | -0.918 |
arch | -0.902 |
isode | -0.899 |
Token | is |
Token ID | 318 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
IELD | +0.782 |
hips | +0.746 |
Desire | +0.711 |
ymm | +0.702 |
suppose | +0.653 |
Neg logit contributions | |
umn | -0.890 |
cient | -0.857 |
anwhile | -0.819 |
arch | -0.804 |
isode | -0.798 |
Token | that |
Token ID | 326 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
IELD | +2.174 |
hips | +2.070 |
Desire | +1.965 |
ymm | +1.945 |
suppose | +1.809 |
Neg logit contributions | |
umn | -2.701 |
cient | -2.581 |
anwhile | -2.480 |
isode | -2.436 |
arch | -2.427 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
IELD | +3.738 |
hips | +3.552 |
Desire | +3.389 |
ymm | +3.364 |
suppose | +3.138 |
Neg logit contributions | |
umn | -4.444 |
cient | -4.236 |
anwhile | -4.068 |
isode | -4.006 |
arch | -3.992 |
Token | Arsenal |
Token ID | 13837 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
umn | +0.265 |
cient | +0.256 |
anwhile | +0.246 |
arch | +0.245 |
ophone | +0.239 |
Neg logit contributions | |
IELD | -0.186 |
hips | -0.175 |
ymm | -0.168 |
Desire | -0.161 |
suppose | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
IELD | +5.185 |
hips | +4.961 |
Desire | +4.716 |
ymm | +4.637 |
suppose | +4.344 |
Neg logit contributions | |
umn | -6.464 |
cient | -6.188 |
anwhile | -5.967 |
isode | -5.881 |
arch | -5.805 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
umn | +0.305 |
cient | +0.293 |
anwhile | +0.282 |
arch | +0.280 |
ophone | +0.274 |
Neg logit contributions | |
IELD | -0.219 |
hips | -0.207 |
ymm | -0.198 |
Desire | -0.190 |
suppose | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
IELD | +2.780 |
hips | +2.651 |
Desire | +2.525 |
ymm | +2.512 |
suppose | +2.357 |
Neg logit contributions | |
umn | -3.182 |
cient | -3.033 |
anwhile | -2.909 |
isode | -2.864 |
arch | -2.849 |
Token | Tottenham |
Token ID | 24272 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
umn | +3.508 |
cient | +3.353 |
anwhile | +3.258 |
arch | +3.236 |
ophone | +3.144 |
Neg logit contributions | |
IELD | -2.641 |
hips | -2.480 |
ymm | -2.449 |
Desire | -2.259 |
WARE | -2.149 |
Token | Hots |
Token ID | 41239 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
IELD | +6.859 |
hips | +6.799 |
Desire | +6.272 |
ymm | +6.078 |
suppose | +5.692 |
Neg logit contributions | |
umn | -9.959 |
cient | -9.526 |
anwhile | -9.203 |
isode | -9.172 |
arch | -8.883 |
Token | pur |
Token ID | 14225 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
hips | +7.683 |
IELD | +7.399 |
Desire | +6.880 |
ymm | +6.709 |
suppose | +6.407 |
Neg logit contributions | |
umn | -9.241 |
anwhile | -9.149 |
cient | -8.786 |
isode | -8.597 |
theless | -8.465 |
Token | — |
Token ID | 851 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
IELD | +3.992 |
hips | +3.813 |
Desire | +3.619 |
ymm | +3.578 |
suppose | +3.345 |
Neg logit contributions | |
umn | -5.015 |
cient | -4.794 |
anwhile | -4.608 |
isode | -4.544 |
arch | -4.507 |
Token | stating |
Token ID | 12316 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
umn | +1.180 |
cient | +1.122 |
arch | +1.070 |
anwhile | +1.067 |
isode | +1.042 |
Neg logit contributions | |
IELD | -1.011 |
hips | -0.921 |
ymm | -0.894 |
Desire | -0.890 |
suppose | -0.818 |
Token | the |
Token ID | 262 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
umn | +0.580 |
cient | +0.556 |
arch | +0.526 |
anwhile | +0.524 |
isode | +0.510 |
Neg logit contributions | |
IELD | -0.502 |
hips | -0.476 |
ymm | -0.458 |
Desire | -0.445 |
suppose | -0.417 |
Token | Arsenal |
Token ID | 13837 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
umn | +0.265 |
cient | +0.256 |
anwhile | +0.246 |
arch | +0.245 |
ophone | +0.239 |
Neg logit contributions | |
IELD | -0.186 |
hips | -0.175 |
ymm | -0.168 |
Desire | -0.161 |
suppose | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
IELD | +5.185 |
hips | +4.961 |
Desire | +4.716 |
ymm | +4.637 |
suppose | +4.344 |
Neg logit contributions | |
umn | -6.464 |
cient | -6.188 |
anwhile | -5.967 |
isode | -5.881 |
arch | -5.805 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
umn | +0.305 |
cient | +0.293 |
anwhile | +0.282 |
arch | +0.280 |
ophone | +0.274 |
Neg logit contributions | |
IELD | -0.219 |
hips | -0.207 |
ymm | -0.198 |
Desire | -0.190 |
suppose | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
IELD | +2.780 |
hips | +2.651 |
Desire | +2.525 |
ymm | +2.512 |
suppose | +2.357 |
Neg logit contributions | |
umn | -3.182 |
cient | -3.033 |
anwhile | -2.909 |
isode | -2.864 |
arch | -2.849 |
Token | Tottenham |
Token ID | 24272 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
umn | +3.508 |
cient | +3.353 |
anwhile | +3.258 |
arch | +3.236 |
ophone | +3.144 |
Neg logit contributions | |
IELD | -2.641 |
hips | -2.480 |
ymm | -2.449 |
Desire | -2.259 |
WARE | -2.149 |
Token | Hots |
Token ID | 41239 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
IELD | +6.859 |
hips | +6.799 |
Desire | +6.272 |
ymm | +6.078 |
suppose | +5.692 |
Neg logit contributions | |
umn | -9.959 |
cient | -9.526 |
anwhile | -9.203 |
isode | -9.172 |
arch | -8.883 |
Token | pur |
Token ID | 14225 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
hips | +7.683 |
IELD | +7.399 |
Desire | +6.880 |
ymm | +6.709 |
suppose | +6.407 |
Neg logit contributions | |
umn | -9.241 |
anwhile | -9.149 |
cient | -8.786 |
isode | -8.597 |
theless | -8.465 |
Token | — |
Token ID | 851 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
IELD | +3.992 |
hips | +3.813 |
Desire | +3.619 |
ymm | +3.578 |
suppose | +3.345 |
Neg logit contributions | |
umn | -5.015 |
cient | -4.794 |
anwhile | -4.608 |
isode | -4.544 |
arch | -4.507 |
Token | stating |
Token ID | 12316 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
umn | +1.180 |
cient | +1.122 |
arch | +1.070 |
anwhile | +1.067 |
isode | +1.042 |
Neg logit contributions | |
IELD | -1.011 |
hips | -0.921 |
ymm | -0.894 |
Desire | -0.890 |
suppose | -0.818 |
Token | the |
Token ID | 262 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
umn | +0.580 |
cient | +0.556 |
arch | +0.526 |
anwhile | +0.524 |
isode | +0.510 |
Neg logit contributions | |
IELD | -0.502 |
hips | -0.476 |
ymm | -0.458 |
Desire | -0.445 |
suppose | -0.417 |
Token | existing |
Token ID | 4683 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
umn | +1.638 |
cient | +1.584 |
arch | +1.489 |
anwhile | +1.462 |
ophone | +1.426 |
Neg logit contributions | |
IELD | -1.691 |
hips | -1.645 |
ymm | -1.550 |
Desire | -1.524 |
suppose | -1.442 |
Token | conscious |
Token ID | 6921 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
IELD | +0.240 |
hips | +0.224 |
ymm | +0.213 |
Desire | +0.212 |
suppose | +0.193 |
Neg logit contributions | |
umn | -0.305 |
cient | -0.293 |
arch | -0.277 |
anwhile | -0.277 |
isode | -0.276 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
umn | +0.315 |
cient | +0.303 |
arch | +0.284 |
isode | +0.281 |
anwhile | +0.280 |
Neg logit contributions | |
IELD | -0.321 |
hips | -0.299 |
ymm | -0.291 |
Desire | -0.282 |
suppose | -0.265 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
umn | +0.266 |
cient | +0.256 |
arch | +0.240 |
anwhile | +0.239 |
isode | +0.237 |
Neg logit contributions | |
IELD | -0.266 |
hips | -0.250 |
ymm | -0.242 |
Desire | -0.238 |
suppose | -0.221 |
Token | your |
Token ID | 534 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
umn | +2.178 |
cient | +2.145 |
arch | +2.019 |
isode | +1.981 |
ophone | +1.953 |
Neg logit contributions | |
IELD | -1.998 |
hips | -1.854 |
ymm | -1.780 |
Desire | -1.737 |
Darling | -1.605 |
Token | Inner |
Token ID | 24877 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
IELD | +2.023 |
hips | +1.931 |
Desire | +1.836 |
ymm | +1.832 |
suppose | +1.711 |
Neg logit contributions | |
umn | -2.056 |
cient | -1.972 |
anwhile | -1.860 |
isode | -1.847 |
arch | -1.843 |
Token | Ass |
Token ID | 2195 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
IELD | +0.988 |
hips | +0.926 |
ymm | +0.855 |
Desire | +0.827 |
suppose | +0.790 |
Neg logit contributions | |
umn | -1.584 |
cient | -1.525 |
arch | -1.455 |
isode | -1.440 |
ophone | -1.423 |
Token | hole |
Token ID | 13207 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
IELD | +7.897 |
hips | +7.801 |
ymm | +7.470 |
Desire | +7.434 |
suppose | +6.779 |
Neg logit contributions | |
umn | -8.513 |
cient | -8.050 |
anwhile | -7.987 |
isode | -7.743 |
arch | -7.501 |
Token | that |
Token ID | 326 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
IELD | +2.496 |
hips | +2.362 |
ymm | +2.241 |
Desire | +2.207 |
suppose | +2.062 |
Neg logit contributions | |
umn | -3.122 |
cient | -2.987 |
arch | -2.821 |
anwhile | -2.820 |
isode | -2.814 |
Token | you |
Token ID | 345 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
umn | +1.504 |
cient | +1.417 |
anwhile | +1.358 |
arch | +1.342 |
isode | +1.333 |
Neg logit contributions | |
IELD | -1.367 |
hips | -1.279 |
ymm | -1.212 |
Desire | -1.196 |
GV | -1.097 |
Token | are |
Token ID | 389 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
IELD | +0.567 |
hips | +0.531 |
ymm | +0.506 |
Desire | +0.504 |
suppose | +0.462 |
Neg logit contributions | |
umn | -0.630 |
cient | -0.598 |
anwhile | -0.567 |
isode | -0.558 |
arch | -0.558 |
Token | actually |
Token ID | 1682 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
umn | +0.600 |
cient | +0.576 |
arch | +0.546 |
anwhile | +0.544 |
isode | +0.539 |
Neg logit contributions | |
IELD | -0.453 |
hips | -0.413 |
ymm | -0.395 |
Desire | -0.393 |
GV | -0.351 |
Token | s |
Token ID | 82 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
umn | +0.038 |
cient | +0.035 |
anwhile | +0.034 |
arch | +0.033 |
isode | +0.033 |
Neg logit contributions | |
IELD | -0.039 |
hips | -0.037 |
Desire | -0.036 |
ymm | -0.035 |
suppose | -0.034 |
Token | work |
Token ID | 670 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
IELD | +1.430 |
hips | +1.337 |
Desire | +1.264 |
ymm | +1.259 |
suppose | +1.192 |
Neg logit contributions | |
umn | -1.733 |
cient | -1.662 |
anwhile | -1.572 |
arch | -1.563 |
isode | -1.547 |
Token | on |
Token ID | 319 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
umn | +1.468 |
cient | +1.436 |
arch | +1.344 |
anwhile | +1.339 |
iously | +1.319 |
Neg logit contributions | |
IELD | -1.204 |
hips | -1.071 |
Desire | -1.065 |
ymm | -1.035 |
suppose | -0.958 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
umn | +0.682 |
cient | +0.651 |
arch | +0.617 |
anwhile | +0.615 |
isode | +0.611 |
Neg logit contributions | |
IELD | -0.524 |
hips | -0.485 |
Desire | -0.462 |
ymm | -0.458 |
suppose | -0.427 |
Token | Space |
Token ID | 4687 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
umn | +2.394 |
cient | +2.283 |
arch | +2.178 |
isode | +2.135 |
anwhile | +2.134 |
Neg logit contributions | |
IELD | -1.803 |
hips | -1.642 |
ymm | -1.573 |
Desire | -1.545 |
suppose | -1.525 |
Token | Launch |
Token ID | 21225 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
umn | +3.170 |
cient | +2.992 |
arch | +2.952 |
anwhile | +2.876 |
ophone | +2.855 |
Neg logit contributions | |
IELD | -1.744 |
hips | -1.471 |
ymm | -1.427 |
Desire | -1.399 |
suppose | -1.366 |
Token | System |
Token ID | 4482 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
IELD | +3.623 |
hips | +3.469 |
Desire | +3.023 |
ymm | +2.850 |
Hold | +2.408 |
Neg logit contributions | |
umn | -13.103 |
cient | -12.688 |
isode | -12.327 |
anwhile | -12.311 |
arch | -12.052 |
Token | heavy |
Token ID | 4334 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
IELD | +1.651 |
hips | +1.538 |
Desire | +1.480 |
ymm | +1.469 |
suppose | +1.379 |
Neg logit contributions | |
umn | -1.848 |
cient | -1.753 |
anwhile | -1.683 |
arch | -1.662 |
isode | -1.659 |
Token | - |
Token ID | 12 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
IELD | +1.631 |
hips | +1.538 |
Desire | +1.492 |
ymm | +1.482 |
suppose | +1.393 |
Neg logit contributions | |
umn | -1.498 |
cient | -1.416 |
isode | -1.335 |
arch | -1.335 |
anwhile | -1.331 |
Token | lift |
Token ID | 26282 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
IELD | +2.283 |
hips | +2.111 |
Desire | +2.094 |
ymm | +2.031 |
suppose | +1.926 |
Neg logit contributions | |
umn | -2.285 |
cient | -2.157 |
arch | -2.076 |
anwhile | -2.047 |
isode | -2.046 |
Token | rocket |
Token ID | 10701 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
IELD | +2.099 |
hips | +1.947 |
Desire | +1.869 |
ymm | +1.854 |
suppose | +1.713 |
Neg logit contributions | |
umn | -2.787 |
cient | -2.659 |
anwhile | -2.553 |
arch | -2.526 |
isode | -2.515 |
Token | knowing |
Token ID | 6970 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
IELD | +1.300 |
hips | +1.231 |
ymm | +1.153 |
Desire | +1.147 |
suppose | +1.051 |
Neg logit contributions | |
umn | -1.791 |
cient | -1.724 |
anwhile | -1.639 |
arch | -1.633 |
isode | -1.606 |
Token | exactly |
Token ID | 3446 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
IELD | +0.491 |
hips | +0.457 |
ymm | +0.441 |
Desire | +0.433 |
GV | +0.400 |
Neg logit contributions | |
umn | -0.601 |
cient | -0.578 |
anwhile | -0.548 |
arch | -0.545 |
isode | -0.533 |
Token | what |
Token ID | 644 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
IELD | +0.746 |
hips | +0.687 |
ymm | +0.661 |
Desire | +0.651 |
GV | +0.595 |
Neg logit contributions | |
umn | -1.087 |
cient | -1.038 |
anwhile | -0.989 |
arch | -0.982 |
isode | -0.978 |
Token | the |
Token ID | 262 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
umn | +1.231 |
cient | +1.168 |
arch | +1.102 |
anwhile | +1.097 |
isode | +1.078 |
Neg logit contributions | |
IELD | -1.168 |
hips | -1.126 |
ymm | -1.058 |
Desire | -1.051 |
GV | -0.984 |
Token | future |
Token ID | 2003 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
IELD | +1.125 |
hips | +1.096 |
ymm | +1.030 |
Desire | +1.029 |
suppose | +0.957 |
Neg logit contributions | |
umn | -1.191 |
cient | -1.139 |
anwhile | -1.076 |
arch | -1.068 |
isode | -1.056 |
Token | holds |
Token ID | 6622 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
umn | +1.507 |
cient | +1.439 |
arch | +1.354 |
isode | +1.325 |
iously | +1.312 |
Neg logit contributions | |
IELD | -1.496 |
hips | -1.417 |
ymm | -1.351 |
Desire | -1.312 |
GV | -1.226 |
Token | . |
Token ID | 13 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
IELD | +6.243 |
hips | +6.142 |
Desire | +5.679 |
ymm | +5.512 |
suppose | +5.294 |
Neg logit contributions | |
umn | -9.929 |
cient | -9.408 |
anwhile | -9.326 |
isode | -9.117 |
arch | -8.937 |
Token | It |
Token ID | 632 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
IELD | +0.888 |
hips | +0.839 |
ymm | +0.794 |
Desire | +0.758 |
suppose | +0.727 |
Neg logit contributions | |
umn | -1.408 |
cient | -1.360 |
arch | -1.282 |
isode | -1.277 |
anwhile | -1.273 |
Token | was |
Token ID | 373 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
umn | +0.145 |
cient | +0.139 |
arch | +0.130 |
anwhile | +0.129 |
isode | +0.128 |
Neg logit contributions | |
IELD | -0.141 |
hips | -0.132 |
ymm | -0.127 |
Desire | -0.127 |
WARE | -0.114 |
Token | cruel |
Token ID | 12177 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
IELD | +0.500 |
hips | +0.466 |
ymm | +0.442 |
Desire | +0.438 |
suppose | +0.391 |
Neg logit contributions | |
umn | -0.685 |
cient | -0.671 |
arch | -0.630 |
anwhile | -0.625 |
isode | -0.617 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
umn | +1.176 |
cient | +1.145 |
arch | +1.063 |
isode | +1.046 |
iously | +1.046 |
Neg logit contributions | |
IELD | -1.138 |
hips | -1.053 |
ymm | -1.033 |
Desire | -1.011 |
GV | -0.924 |
Token | Earth |
Token ID | 3668 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
IELD | +0.138 |
hips | +0.132 |
ymm | +0.124 |
Desire | +0.123 |
WARE | +0.115 |
Neg logit contributions | |
umn | -0.147 |
cient | -0.139 |
arch | -0.131 |
anwhile | -0.130 |
isode | -0.129 |
Token | – |
Token ID | 784 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
IELD | +1.974 |
hips | +1.858 |
Desire | +1.780 |
ymm | +1.758 |
suppose | +1.626 |
Neg logit contributions | |
umn | -2.328 |
cient | -2.242 |
arch | -2.107 |
anwhile | -2.105 |
isode | -2.103 |
Token | far |
Token ID | 1290 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
umn | +0.351 |
cient | +0.336 |
anwhile | +0.314 |
arch | +0.313 |
isode | +0.312 |
Neg logit contributions | |
IELD | -0.282 |
hips | -0.260 |
Desire | -0.249 |
ymm | -0.245 |
suppose | -0.224 |
Token | more |
Token ID | 517 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
IELD | +0.699 |
hips | +0.644 |
Desire | +0.619 |
ymm | +0.612 |
suppose | +0.568 |
Neg logit contributions | |
umn | -0.872 |
cient | -0.840 |
isode | -0.790 |
anwhile | -0.788 |
arch | -0.785 |
Token | than |
Token ID | 621 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
IELD | +2.239 |
hips | +2.087 |
Desire | +1.993 |
ymm | +1.961 |
suppose | +1.807 |
Neg logit contributions | |
umn | -3.047 |
cient | -2.958 |
arch | -2.784 |
anwhile | -2.783 |
isode | -2.745 |
Token | expected |
Token ID | 2938 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
umn | +0.523 |
cient | +0.503 |
arch | +0.471 |
anwhile | +0.471 |
isode | +0.462 |
Neg logit contributions | |
IELD | -0.419 |
hips | -0.385 |
ymm | -0.361 |
Desire | -0.359 |
WARE | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
IELD | +6.060 |
hips | +5.899 |
Desire | +5.524 |
ymm | +5.399 |
suppose | +5.183 |
Neg logit contributions | |
umn | -9.913 |
cient | -9.415 |
anwhile | -9.307 |
isode | -9.199 |
ophone | -8.925 |
Token | This |
Token ID | 770 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
IELD | +0.521 |
hips | +0.489 |
ymm | +0.457 |
Desire | +0.452 |
suppose | +0.426 |
Neg logit contributions | |
umn | -0.766 |
cient | -0.735 |
arch | -0.694 |
anwhile | -0.691 |
isode | -0.688 |
Token | shows |
Token ID | 2523 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
umn | +0.528 |
cient | +0.511 |
arch | +0.475 |
anwhile | +0.472 |
isode | +0.467 |
Neg logit contributions | |
IELD | -0.532 |
hips | -0.496 |
Desire | -0.475 |
ymm | -0.464 |
suppose | -0.432 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
IELD | +2.426 |
hips | +2.289 |
Desire | +2.171 |
ymm | +2.132 |
suppose | +1.982 |
Neg logit contributions | |
umn | -3.193 |
cient | -3.057 |
anwhile | -2.912 |
arch | -2.883 |
isode | -2.869 |
Token | the |
Token ID | 262 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
umn | +0.513 |
cient | +0.493 |
arch | +0.470 |
anwhile | +0.468 |
isode | +0.458 |
Neg logit contributions | |
IELD | -0.391 |
hips | -0.357 |
Desire | -0.337 |
ymm | -0.330 |
WARE | -0.302 |
Token | sermon |
Token ID | 39362 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
umn | +0.785 |
cient | +0.749 |
arch | +0.709 |
anwhile | +0.701 |
isode | +0.689 |
Neg logit contributions | |
IELD | -0.807 |
hips | -0.766 |
ymm | -0.742 |
Desire | -0.718 |
suppose | -0.670 |
Token | entitled |
Token ID | 9080 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
umn | +4.966 |
cient | +4.841 |
arch | +4.534 |
ophone | +4.374 |
iously | +4.369 |
Neg logit contributions | |
IELD | -4.655 |
ymm | -4.113 |
hips | -4.028 |
Desire | -3.916 |
GV | -3.702 |
Token | ' |
Token ID | 705 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
IELD | +1.373 |
hips | +1.287 |
ymm | +1.218 |
Desire | +1.201 |
suppose | +1.133 |
Neg logit contributions | |
umn | -1.773 |
cient | -1.699 |
anwhile | -1.618 |
isode | -1.609 |
arch | -1.608 |
Token | Rem |
Token ID | 8413 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
umn | +1.194 |
cient | +1.147 |
arch | +1.108 |
isode | +1.080 |
anwhile | +1.056 |
Neg logit contributions | |
IELD | -0.955 |
hips | -0.895 |
Desire | -0.854 |
ymm | -0.852 |
suppose | -0.796 |
Token | aining |
Token ID | 1397 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
umn | +0.770 |
cient | +0.741 |
arch | +0.710 |
ophone | +0.688 |
isode | +0.688 |
Neg logit contributions | |
IELD | -0.681 |
hips | -0.632 |
Desire | -0.601 |
ymm | -0.598 |
suppose | -0.566 |
Token | Aw |
Token ID | 5851 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
IELD | +0.087 |
hips | +0.079 |
ymm | +0.077 |
Desire | +0.074 |
suppose | +0.069 |
Neg logit contributions | |
umn | -0.118 |
cient | -0.116 |
anwhile | -0.110 |
arch | -0.109 |
isode | -0.107 |
Token | ake |
Token ID | 539 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
IELD | +6.409 |
hips | +6.329 |
Desire | +5.915 |
ymm | +5.814 |
suppose | +5.317 |
Neg logit contributions | |
umn | -9.554 |
cient | -9.051 |
anwhile | -8.892 |
isode | -8.731 |
arch | -8.443 |
Token | through |
Token ID | 832 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
IELD | +2.200 |
hips | +2.085 |
ymm | +1.972 |
Desire | +1.965 |
suppose | +1.831 |
Neg logit contributions | |
umn | -2.800 |
cient | -2.698 |
anwhile | -2.581 |
isode | -2.546 |
arch | -2.538 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
umn | +1.098 |
cient | +1.057 |
arch | +1.018 |
anwhile | +0.998 |
isode | +0.987 |
Neg logit contributions | |
IELD | -0.745 |
hips | -0.675 |
ymm | -0.639 |
Desire | -0.611 |
suppose | -0.601 |
Token | Great |
Token ID | 3878 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
IELD | +1.775 |
hips | +1.673 |
ymm | +1.568 |
Desire | +1.544 |
suppose | +1.456 |
Neg logit contributions | |
umn | -2.481 |
cient | -2.373 |
anwhile | -2.274 |
arch | -2.258 |
isode | -2.245 |
Token | Revolution |
Token ID | 9303 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
IELD | +2.930 |
hips | +2.800 |
Desire | +2.653 |
ymm | +2.609 |
suppose | +2.430 |
Neg logit contributions | |
umn | -4.078 |
cient | -3.908 |
anwhile | -3.765 |
isode | -3.713 |
arch | -3.679 |
Token | , |
Token ID | 11 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
umn | +0.429 |
cient | +0.420 |
arch | +0.392 |
isode | +0.390 |
anwhile | +0.390 |
Neg logit contributions | |
IELD | -0.378 |
hips | -0.349 |
ymm | -0.335 |
Desire | -0.332 |
suppose | -0.306 |
Token | but |
Token ID | 475 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
IELD | +1.169 |
hips | +1.105 |
ymm | +1.047 |
Desire | +1.047 |
suppose | +0.947 |
Neg logit contributions | |
umn | -1.457 |
cient | -1.390 |
anwhile | -1.322 |
arch | -1.305 |
isode | -1.303 |
Token | as |
Token ID | 355 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
umn | +1.503 |
cient | +1.436 |
anwhile | +1.375 |
arch | +1.356 |
isode | +1.351 |
Neg logit contributions | |
IELD | -1.234 |
hips | -1.156 |
ymm | -1.109 |
Desire | -1.081 |
ELF | -0.970 |
Token | you |
Token ID | 345 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
IELD | +1.398 |
hips | +1.326 |
Desire | +1.253 |
ymm | +1.228 |
suppose | +1.153 |
Neg logit contributions | |
umn | -1.675 |
cient | -1.594 |
anwhile | -1.515 |
isode | -1.509 |
arch | -1.502 |
Token | can |
Token ID | 460 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
IELD | +1.731 |
hips | +1.654 |
Desire | +1.580 |
ymm | +1.563 |
suppose | +1.465 |
Neg logit contributions | |
umn | -1.864 |
cient | -1.776 |
anwhile | -1.701 |
isode | -1.672 |
arch | -1.663 |
Token | see |
Token ID | 766 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
IELD | +2.186 |
hips | +2.082 |
Desire | +1.983 |
ymm | +1.964 |
suppose | +1.827 |
Neg logit contributions | |
umn | -2.546 |
cient | -2.429 |
anwhile | -2.331 |
isode | -2.291 |
arch | -2.282 |
Token | from |
Token ID | 422 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
IELD | +6.058 |
hips | +5.948 |
Desire | +5.579 |
ymm | +5.464 |
suppose | +5.239 |
Neg logit contributions | |
umn | -9.434 |
cient | -9.121 |
anwhile | -8.908 |
isode | -8.729 |
arch | -8.634 |
Token | the |
Token ID | 262 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
IELD | +1.421 |
hips | +1.340 |
Desire | +1.246 |
ymm | +1.241 |
suppose | +1.125 |
Neg logit contributions | |
umn | -2.403 |
cient | -2.295 |
anwhile | -2.220 |
isode | -2.181 |
arch | -2.177 |
Token | photos |
Token ID | 5205 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
IELD | +0.107 |
hips | +0.101 |
Desire | +0.096 |
ymm | +0.095 |
suppose | +0.089 |
Neg logit contributions | |
umn | -0.119 |
cient | -0.112 |
anwhile | -0.107 |
arch | -0.105 |
isode | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
umn | +1.380 |
cient | +1.315 |
anwhile | +1.235 |
arch | +1.231 |
isode | +1.228 |
Neg logit contributions | |
IELD | -1.240 |
hips | -1.131 |
Desire | -1.109 |
ymm | -1.102 |
suppose | -1.010 |
Token | M |
Token ID | 337 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
IELD | +1.287 |
hips | +1.219 |
ymm | +1.151 |
Desire | +1.145 |
suppose | +1.041 |
Neg logit contributions | |
umn | -1.718 |
cient | -1.637 |
anwhile | -1.580 |
isode | -1.553 |
arch | -1.545 |
Token | the |
Token ID | 262 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
IELD | +3.656 |
hips | +3.502 |
Desire | +3.332 |
ymm | +3.302 |
suppose | +3.069 |
Neg logit contributions | |
umn | -4.938 |
cient | -4.726 |
anwhile | -4.576 |
isode | -4.505 |
arch | -4.444 |
Token | chaos |
Token ID | 11918 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
IELD | +1.167 |
hips | +1.119 |
Desire | +1.066 |
ymm | +1.060 |
suppose | +0.998 |
Neg logit contributions | |
umn | -1.164 |
cient | -1.107 |
anwhile | -1.056 |
isode | -1.039 |
arch | -1.035 |
Token | ( |
Token ID | 357 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
umn | +1.011 |
cient | +0.967 |
anwhile | +0.912 |
isode | +0.903 |
arch | +0.903 |
Neg logit contributions | |
IELD | -0.947 |
hips | -0.886 |
ymm | -0.856 |
Desire | -0.856 |
suppose | -0.787 |
Token | sp |
Token ID | 2777 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
IELD | +1.982 |
hips | +1.896 |
Desire | +1.828 |
ymm | +1.806 |
suppose | +1.715 |
Neg logit contributions | |
umn | -1.644 |
cient | -1.554 |
anwhile | -1.467 |
arch | -1.453 |
isode | -1.447 |
Token | oiler |
Token ID | 20837 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
umn | +0.197 |
cient | +0.185 |
anwhile | +0.170 |
arch | +0.170 |
isode | +0.169 |
Neg logit contributions | |
IELD | -0.343 |
hips | -0.326 |
Desire | -0.321 |
ymm | -0.315 |
suppose | -0.303 |
Token | alert |
Token ID | 7995 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
IELD | +1.946 |
hips | +1.860 |
Desire | +1.775 |
ymm | +1.760 |
suppose | +1.628 |
Neg logit contributions | |
umn | -2.239 |
cient | -2.129 |
anwhile | -2.038 |
arch | -2.017 |
isode | -2.010 |
Token | ) |
Token ID | 8 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
IELD | +6.221 |
hips | +5.972 |
Desire | +5.609 |
ymm | +5.510 |
suppose | +5.264 |
Neg logit contributions | |
umn | -9.454 |
cient | -9.071 |
anwhile | -8.821 |
isode | -8.615 |
ophone | -8.540 |
Token | that |
Token ID | 326 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
IELD | +2.317 |
hips | +2.213 |
Desire | +2.112 |
ymm | +2.090 |
suppose | +1.957 |
Neg logit contributions | |
umn | -2.558 |
cient | -2.436 |
anwhile | -2.333 |
isode | -2.300 |
arch | -2.286 |
Token | Black |
Token ID | 2619 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
IELD | +1.419 |
hips | +1.357 |
Desire | +1.289 |
ymm | +1.278 |
suppose | +1.196 |
Neg logit contributions | |
umn | -1.571 |
cient | -1.494 |
anwhile | -1.428 |
isode | -1.409 |
arch | -1.403 |
Token | inadvertently |
Token ID | 29243 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
IELD | +2.572 |
hips | +2.468 |
Desire | +2.358 |
ymm | +2.335 |
suppose | +2.201 |
Neg logit contributions | |
umn | -2.582 |
cient | -2.455 |
anwhile | -2.348 |
isode | -2.312 |
arch | -2.292 |
Token | sets |
Token ID | 5621 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
IELD | +0.412 |
hips | +0.388 |
Desire | +0.375 |
ymm | +0.372 |
suppose | +0.347 |
Neg logit contributions | |
umn | -0.404 |
cient | -0.382 |
anwhile | -0.363 |
arch | -0.359 |
isode | -0.358 |
Token | � |
Token ID | 250 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
umn | +0.912 |
cient | +0.875 |
arch | +0.824 |
isode | +0.812 |
anwhile | +0.804 |
Neg logit contributions | |
IELD | -0.723 |
hips | -0.687 |
Desire | -0.656 |
ymm | -0.647 |
suppose | -0.604 |
Token | F |
Token ID | 37 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
umn | +1.583 |
cient | +1.521 |
anwhile | +1.436 |
arch | +1.436 |
isode | +1.432 |
Neg logit contributions | |
IELD | -1.245 |
hips | -1.209 |
Desire | -1.160 |
ymm | -1.143 |
suppose | -1.077 |
Token | TC |
Token ID | 4825 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
IELD | +0.482 |
hips | +0.465 |
Desire | +0.453 |
ymm | +0.446 |
suppose | +0.412 |
Neg logit contributions | |
umn | -0.536 |
cient | -0.519 |
arch | -0.490 |
isode | -0.488 |
anwhile | -0.483 |
Token | Compl |
Token ID | 20011 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
umn | +1.270 |
cient | +1.207 |
anwhile | +1.152 |
isode | +1.145 |
arch | +1.144 |
Neg logit contributions | |
IELD | -0.880 |
hips | -0.838 |
ymm | -0.787 |
Desire | -0.775 |
suppose | -0.727 |
Token | aint |
Token ID | 2913 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
IELD | +2.796 |
hips | +2.679 |
Desire | +2.570 |
ymm | +2.554 |
suppose | +2.400 |
Neg logit contributions | |
umn | -2.564 |
cient | -2.429 |
anwhile | -2.289 |
isode | -2.275 |
arch | -2.256 |
Token | Assistant |
Token ID | 15286 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
IELD | +0.711 |
hips | +0.673 |
ymm | +0.639 |
Desire | +0.628 |
suppose | +0.579 |
Neg logit contributions | |
umn | -1.135 |
cient | -1.084 |
anwhile | -1.040 |
arch | -1.033 |
isode | -1.032 |
Token | � |
Token ID | 447 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
IELD | +7.912 |
hips | +7.678 |
Desire | +7.240 |
ymm | +7.033 |
suppose | +6.768 |
Neg logit contributions | |
umn | -7.801 |
cient | -7.508 |
anwhile | -7.253 |
isode | -7.048 |
arch | -6.914 |
Token | � |
Token ID | 251 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
IELD | +0.833 |
hips | +0.791 |
Desire | +0.759 |
ymm | +0.751 |
suppose | +0.706 |
Neg logit contributions | |
umn | -0.916 |
cient | -0.871 |
anwhile | -0.821 |
arch | -0.820 |
isode | -0.816 |
Token | to |
Token ID | 284 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
umn | +0.465 |
cient | +0.435 |
anwhile | +0.408 |
isode | +0.406 |
arch | +0.402 |
Neg logit contributions | |
IELD | -0.609 |
hips | -0.578 |
ymm | -0.567 |
Desire | -0.562 |
suppose | -0.526 |
Token | report |
Token ID | 989 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
umn | +0.270 |
cient | +0.254 |
anwhile | +0.242 |
arch | +0.238 |
isode | +0.237 |
Neg logit contributions | |
IELD | -0.300 |
hips | -0.289 |
ymm | -0.278 |
Desire | -0.275 |
suppose | -0.256 |
Token | persons |
Token ID | 6506 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
umn | +0.795 |
cient | +0.772 |
isode | +0.724 |
anwhile | +0.724 |
arch | +0.720 |
Neg logit contributions | |
IELD | -0.633 |
hips | -0.584 |
ymm | -0.568 |
Desire | -0.561 |
suppose | -0.507 |
Token | competed |
Token ID | 32440 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
IELD | +1.341 |
hips | +1.275 |
Desire | +1.197 |
ymm | +1.197 |
suppose | +1.117 |
Neg logit contributions | |
umn | -1.522 |
cient | -1.464 |
isode | -1.381 |
anwhile | -1.373 |
arch | -1.372 |
Token | alongside |
Token ID | 7848 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
umn | +1.257 |
cient | +1.243 |
arch | +1.180 |
iously | +1.146 |
anwhile | +1.140 |
Neg logit contributions | |
IELD | -1.037 |
hips | -0.916 |
Desire | -0.909 |
ymm | -0.891 |
suppose | -0.820 |
Token | Chelsea |
Token ID | 12147 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
IELD | +0.465 |
hips | +0.440 |
ymm | +0.420 |
Desire | +0.404 |
suppose | +0.383 |
Neg logit contributions | |
umn | -0.638 |
cient | -0.612 |
arch | -0.588 |
anwhile | -0.587 |
isode | -0.574 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
IELD | +2.058 |
hips | +1.944 |
Desire | +1.851 |
ymm | +1.839 |
suppose | +1.695 |
Neg logit contributions | |
umn | -2.635 |
cient | -2.521 |
anwhile | -2.407 |
arch | -2.403 |
isode | -2.387 |
Token | Tottenham |
Token ID | 24272 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
umn | +4.212 |
cient | +4.066 |
arch | +3.934 |
anwhile | +3.906 |
ophone | +3.793 |
Neg logit contributions | |
IELD | -3.296 |
hips | -3.144 |
ymm | -3.050 |
Desire | -2.838 |
WARE | -2.717 |
Token | Hots |
Token ID | 41239 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
IELD | +5.986 |
hips | +5.845 |
Desire | +5.414 |
ymm | +5.325 |
suppose | +4.994 |
Neg logit contributions | |
umn | -9.083 |
cient | -8.642 |
anwhile | -8.415 |
isode | -8.272 |
arch | -8.079 |
Token | pur |
Token ID | 14225 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
hips | +7.312 |
IELD | +7.113 |
Desire | +6.560 |
ymm | +6.463 |
suppose | +6.123 |
Neg logit contributions | |
umn | -8.526 |
anwhile | -8.310 |
cient | -8.039 |
isode | -7.824 |
theless | -7.654 |
Token | for |
Token ID | 329 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
IELD | +2.975 |
hips | +2.802 |
Desire | +2.669 |
ymm | +2.643 |
suppose | +2.451 |
Neg logit contributions | |
umn | -3.953 |
cient | -3.798 |
anwhile | -3.633 |
isode | -3.597 |
arch | -3.591 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
umn | +1.294 |
cient | +1.252 |
isode | +1.174 |
arch | +1.172 |
ophone | +1.161 |
Neg logit contributions | |
IELD | -0.961 |
hips | -0.903 |
ymm | -0.861 |
Desire | -0.812 |
WARE | -0.776 |
Token | Premier |
Token ID | 9952 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
umn | +2.579 |
cient | +2.498 |
arch | +2.325 |
isode | +2.284 |
anwhile | +2.248 |
Neg logit contributions | |
IELD | -2.299 |
hips | -2.190 |
ymm | -2.093 |
Desire | -2.038 |
suppose | -1.928 |
Token | League |
Token ID | 4041 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
umn | +0.331 |
cient | +0.322 |
arch | +0.308 |
isode | +0.306 |
anwhile | +0.304 |
Neg logit contributions | |
IELD | -0.149 |
hips | -0.138 |
Desire | -0.126 |
ymm | -0.126 |
suppose | -0.112 |
Token | ( |
Token ID | 357 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
umn | +2.044 |
cient | +1.961 |
anwhile | +1.835 |
isode | +1.820 |
arch | +1.806 |
Neg logit contributions | |
IELD | -1.786 |
hips | -1.673 |
ymm | -1.635 |
Desire | -1.551 |
suppose | -1.482 |
Token | contin |
Token ID | 18487 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
umn | +0.022 |
cient | +0.021 |
arch | +0.020 |
isode | +0.020 |
anwhile | +0.020 |
Neg logit contributions | |
IELD | -0.023 |
hips | -0.022 |
Desire | -0.021 |
ymm | -0.021 |
suppose | -0.020 |
Token | ued |
Token ID | 1739 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
umn | +1.027 |
cient | +0.965 |
arch | +0.883 |
isode | +0.880 |
anwhile | +0.876 |
Neg logit contributions | |
IELD | -1.453 |
hips | -1.379 |
Desire | -1.351 |
ymm | -1.332 |
suppose | -1.267 |
Token | ). |
Token ID | 737 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
IELD | +0.881 |
hips | +0.832 |
ymm | +0.793 |
Desire | +0.783 |
suppose | +0.724 |
Neg logit contributions | |
umn | -1.184 |
cient | -1.125 |
anwhile | -1.076 |
arch | -1.070 |
isode | -1.065 |
Token | Extreme |
Token ID | 18111 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
IELD | +0.571 |
hips | +0.532 |
ymm | +0.510 |
Desire | +0.475 |
suppose | +0.459 |
Neg logit contributions | |
umn | -0.912 |
cient | -0.876 |
arch | -0.830 |
isode | -0.828 |
anwhile | -0.825 |
Token | Un |
Token ID | 791 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
IELD | +3.109 |
hips | +2.959 |
ymm | +2.788 |
Desire | +2.782 |
suppose | +2.584 |
Neg logit contributions | |
umn | -3.989 |
cient | -3.809 |
anwhile | -3.628 |
isode | -3.602 |
arch | -3.582 |
Token | ction |
Token ID | 596 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
hips | +7.772 |
IELD | +7.762 |
Desire | +7.370 |
ymm | +7.233 |
suppose | +6.761 |
Neg logit contributions | |
umn | -7.629 |
anwhile | -7.392 |
cient | -7.200 |
isode | -6.873 |
ophone | -6.710 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
umn | +1.752 |
cient | +1.666 |
arch | +1.561 |
anwhile | +1.544 |
isode | +1.536 |
Neg logit contributions | |
IELD | -1.550 |
hips | -1.411 |
ymm | -1.404 |
Desire | -1.338 |
suppose | -1.291 |
Token | Holy |
Token ID | 7439 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
IELD | +0.806 |
hips | +0.755 |
ymm | +0.715 |
Desire | +0.676 |
suppose | +0.651 |
Neg logit contributions | |
umn | -1.286 |
cient | -1.230 |
arch | -1.169 |
isode | -1.165 |
anwhile | -1.162 |
Token | Orders |
Token ID | 30689 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
umn | +1.767 |
cient | +1.683 |
arch | +1.603 |
isode | +1.590 |
ocide | +1.580 |
Neg logit contributions | |
IELD | -1.318 |
hips | -1.219 |
ymm | -1.174 |
Desire | -1.103 |
suppose | -1.079 |
Token | . |
Token ID | 13 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
IELD | +2.022 |
hips | +1.893 |
ymm | +1.808 |
Desire | +1.802 |
suppose | +1.674 |
Neg logit contributions | |
umn | -2.642 |
cient | -2.536 |
anwhile | -2.418 |
isode | -2.381 |
arch | -2.375 |
Token | industrial |
Token ID | 7593 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
umn | +1.010 |
cient | +0.976 |
anwhile | +0.935 |
arch | +0.924 |
isode | +0.908 |
Neg logit contributions | |
IELD | -0.808 |
hips | -0.754 |
Desire | -0.726 |
ymm | -0.723 |
ENTION | -0.655 |
Token | output |
Token ID | 5072 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
umn | +3.186 |
cient | +3.080 |
anwhile | +2.990 |
arch | +2.867 |
iously | +2.864 |
Neg logit contributions | |
IELD | -4.332 |
hips | -4.120 |
ymm | -3.987 |
Desire | -3.908 |
ELF | -3.742 |
Token | rose |
Token ID | 8278 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
IELD | +2.706 |
hips | +2.560 |
Desire | +2.464 |
ymm | +2.431 |
suppose | +2.266 |
Neg logit contributions | |
umn | -2.765 |
cient | -2.640 |
anwhile | -2.525 |
isode | -2.478 |
arch | -2.476 |
Token | more |
Token ID | 517 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
IELD | +0.447 |
hips | +0.411 |
Desire | +0.398 |
ymm | +0.392 |
suppose | +0.354 |
Neg logit contributions | |
umn | -0.568 |
cient | -0.547 |
anwhile | -0.527 |
arch | -0.520 |
isode | -0.514 |
Token | than |
Token ID | 621 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
umn | +0.584 |
cient | +0.564 |
anwhile | +0.542 |
arch | +0.534 |
isode | +0.523 |
Neg logit contributions | |
IELD | -0.540 |
hips | -0.495 |
Desire | -0.491 |
ymm | -0.481 |
suppose | -0.439 |
Token | expected |
Token ID | 2938 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
umn | +3.117 |
cient | +3.033 |
arch | +2.832 |
anwhile | +2.820 |
isode | +2.785 |
Neg logit contributions | |
IELD | -2.561 |
hips | -2.381 |
ymm | -2.253 |
Desire | -2.239 |
GV | -2.076 |
Token | in |
Token ID | 287 |
Feature activation | +5.74e-03 |
Pos logit contributions | |
IELD | +6.002 |
hips | +5.898 |
Desire | +5.433 |
ymm | +5.404 |
suppose | +5.109 |
Neg logit contributions | |
umn | -9.641 |
cient | -9.128 |
anwhile | -8.867 |
isode | -8.852 |
arch | -8.650 |
Token | September |
Token ID | 2693 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
umn | +0.013 |
cient | +0.012 |
arch | +0.011 |
anwhile | +0.011 |
isode | +0.011 |
Neg logit contributions | |
IELD | -0.009 |
hips | -0.009 |
Desire | -0.008 |
ymm | -0.008 |
suppose | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
umn | +2.180 |
cient | +2.060 |
anwhile | +1.970 |
arch | +1.939 |
isode | +1.912 |
Neg logit contributions | |
IELD | -2.095 |
hips | -1.949 |
Desire | -1.905 |
ymm | -1.901 |
ELF | -1.737 |
Token | boosted |
Token ID | 29657 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
IELD | +0.376 |
hips | +0.358 |
Desire | +0.340 |
ymm | +0.334 |
suppose | +0.311 |
Neg logit contributions | |
umn | -0.464 |
cient | -0.444 |
anwhile | -0.422 |
arch | -0.418 |
isode | -0.414 |
Token | by |
Token ID | 416 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
IELD | +0.905 |
hips | +0.855 |
Desire | +0.812 |
ymm | +0.798 |
suppose | +0.737 |
Neg logit contributions | |
umn | -1.198 |
cient | -1.154 |
anwhile | -1.117 |
arch | -1.087 |
isode | -1.080 |
Token | handling |
Token ID | 9041 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
umn | +0.470 |
cient | +0.449 |
anwhile | +0.425 |
arch | +0.419 |
ophone | +0.416 |
Neg logit contributions | |
IELD | -0.435 |
hips | -0.419 |
ymm | -0.398 |
Desire | -0.392 |
suppose | -0.367 |
Token | of |
Token ID | 286 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
IELD | +1.867 |
hips | +1.774 |
ymm | +1.677 |
Desire | +1.676 |
suppose | +1.562 |
Neg logit contributions | |
umn | -2.086 |
cient | -1.988 |
anwhile | -1.898 |
arch | -1.858 |
isode | -1.855 |
Token | Mam |
Token ID | 29926 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
IELD | +1.789 |
hips | +1.722 |
ymm | +1.617 |
Desire | +1.614 |
suppose | +1.505 |
Neg logit contributions | |
umn | -2.004 |
cient | -1.919 |
anwhile | -1.819 |
arch | -1.793 |
isode | -1.780 |
Token | ad |
Token ID | 324 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
IELD | +2.790 |
hips | +2.661 |
Desire | +2.558 |
ymm | +2.545 |
suppose | +2.438 |
Neg logit contributions | |
umn | -1.779 |
cient | -1.681 |
anwhile | -1.554 |
arch | -1.553 |
isode | -1.535 |
Token | ou |
Token ID | 280 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
umn | +1.106 |
cient | +1.050 |
arch | +0.981 |
isode | +0.967 |
ophone | +0.952 |
Neg logit contributions | |
IELD | -1.455 |
hips | -1.344 |
ymm | -1.298 |
Desire | -1.256 |
suppose | -1.229 |
Token | Sak |
Token ID | 13231 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
umn | +0.853 |
cient | +0.812 |
arch | +0.791 |
anwhile | +0.783 |
isode | +0.772 |
Neg logit contributions | |
IELD | -0.710 |
hips | -0.661 |
ymm | -0.661 |
Desire | -0.615 |
GV | -0.583 |
Token | ho |
Token ID | 8873 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
hips | +5.653 |
IELD | +5.543 |
Desire | +5.221 |
ymm | +5.082 |
suppose | +4.536 |
Neg logit contributions | |
umn | -9.660 |
cient | -9.194 |
anwhile | -9.144 |
theless | -8.910 |
isode | -8.834 |
Token | drugs |
Token ID | 5010 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
umn | +0.625 |
cient | +0.597 |
anwhile | +0.576 |
arch | +0.564 |
ophone | +0.557 |
Neg logit contributions | |
IELD | -0.537 |
hips | -0.518 |
ymm | -0.486 |
Desire | -0.483 |
suppose | -0.445 |
Token | test |
Token ID | 1332 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
umn | +4.064 |
cient | +3.884 |
anwhile | +3.753 |
ophone | +3.651 |
arch | +3.639 |
Neg logit contributions | |
IELD | -3.448 |
hips | -3.217 |
ymm | -3.074 |
Desire | -2.991 |
suppose | -2.753 |
Token | Read |
Token ID | 4149 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
IELD | +1.687 |
hips | +1.594 |
Desire | +1.497 |
ymm | +1.493 |
suppose | +1.374 |
Neg logit contributions | |
umn | -2.474 |
cient | -2.376 |
anwhile | -2.296 |
isode | -2.251 |
arch | -2.246 |
Token | more |
Token ID | 517 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
umn | +1.280 |
cient | +1.219 |
arch | +1.153 |
isode | +1.143 |
anwhile | +1.141 |
Neg logit contributions | |
IELD | -1.137 |
hips | -1.066 |
Desire | -1.021 |
ymm | -1.004 |
suppose | -0.937 |
Token | first |
Token ID | 717 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
umn | +2.725 |
cient | +2.633 |
anwhile | +2.466 |
arch | +2.458 |
isode | +2.440 |
Neg logit contributions | |
IELD | -2.365 |
hips | -2.259 |
ymm | -2.123 |
Desire | -2.069 |
suppose | -1.959 |
Token | Thermal |
Token ID | 41590 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
umn | +1.971 |
cient | +1.903 |
anwhile | +1.789 |
arch | +1.782 |
isode | +1.781 |
Neg logit contributions | |
IELD | -1.504 |
hips | -1.426 |
ymm | -1.333 |
Desire | -1.309 |
suppose | -1.229 |
Token | Disc |
Token ID | 8444 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
IELD | +0.678 |
hips | +0.652 |
ymm | +0.605 |
Desire | +0.593 |
suppose | +0.553 |
Neg logit contributions | |
umn | -1.094 |
cient | -1.046 |
anwhile | -1.012 |
isode | -1.004 |
arch | -1.000 |
Token | our |
Token ID | 454 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
IELD | +0.827 |
hips | +0.796 |
Desire | +0.752 |
ymm | +0.747 |
suppose | +0.699 |
Neg logit contributions | |
umn | -0.967 |
cient | -0.916 |
anwhile | -0.878 |
isode | -0.870 |
arch | -0.868 |
Token | agement |
Token ID | 5082 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
IELD | +0.124 |
hips | +0.116 |
ymm | +0.107 |
Desire | +0.106 |
suppose | +0.101 |
Neg logit contributions | |
umn | -0.181 |
cient | -0.172 |
arch | -0.163 |
isode | -0.162 |
anwhile | -0.162 |
Token | Beam |
Token ID | 25855 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
IELD | +1.479 |
hips | +1.402 |
ymm | +1.319 |
Desire | +1.303 |
suppose | +1.211 |
Neg logit contributions | |
umn | -2.107 |
cient | -2.018 |
anwhile | -1.925 |
isode | -1.920 |
arch | -1.908 |
Token | test |
Token ID | 1332 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
IELD | +7.306 |
hips | +7.045 |
Desire | +6.767 |
ymm | +6.570 |
suppose | +6.235 |
Neg logit contributions | |
umn | -8.344 |
cient | -7.930 |
anwhile | -7.688 |
isode | -7.378 |
arch | -7.369 |
Token | ( |
Token ID | 357 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
IELD | +2.285 |
hips | +2.186 |
Desire | +2.057 |
ymm | +2.025 |
suppose | +1.893 |
Neg logit contributions | |
umn | -3.270 |
cient | -3.130 |
anwhile | -3.022 |
isode | -2.973 |
arch | -2.952 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
IELD | +0.710 |
hips | +0.679 |
Desire | +0.650 |
ymm | +0.644 |
suppose | +0.608 |
Neg logit contributions | |
umn | -0.714 |
cient | -0.679 |
anwhile | -0.644 |
isode | -0.638 |
arch | -0.635 |
Token | ) |
Token ID | 8 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
IELD | +0.172 |
hips | +0.162 |
Desire | +0.153 |
ymm | +0.151 |
suppose | +0.139 |
Neg logit contributions | |
umn | -0.267 |
cient | -0.257 |
arch | -0.243 |
anwhile | -0.243 |
isode | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
umn | +0.224 |
cient | +0.215 |
anwhile | +0.207 |
isode | +0.204 |
arch | +0.203 |
Neg logit contributions | |
IELD | -0.143 |
hips | -0.136 |
Desire | -0.128 |
ymm | -0.127 |
suppose | -0.117 |
Token | third |
Token ID | 2368 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
umn | +2.273 |
cient | +2.200 |
arch | +2.050 |
anwhile | +2.017 |
isode | +2.013 |
Neg logit contributions | |
IELD | -2.037 |
hips | -1.914 |
ymm | -1.813 |
Desire | -1.791 |
suppose | -1.728 |
Token | Grav |
Token ID | 32599 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
umn | +3.634 |
cient | +3.499 |
arch | +3.261 |
isode | +3.204 |
ophone | +3.164 |
Neg logit contributions | |
IELD | -3.549 |
hips | -3.283 |
Desire | -3.162 |
ymm | -3.113 |
suppose | -2.913 |
Token | itational |
Token ID | 22181 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
IELD | +1.323 |
hips | +1.269 |
Desire | +1.231 |
ymm | +1.208 |
suppose | +1.163 |
Neg logit contributions | |
umn | -0.967 |
cient | -0.923 |
arch | -0.857 |
isode | -0.851 |
anwhile | -0.843 |
Token | L |
Token ID | 406 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
umn | +0.323 |
cient | +0.307 |
arch | +0.297 |
ophone | +0.284 |
isode | +0.282 |
Neg logit contributions | |
IELD | -0.298 |
hips | -0.280 |
ymm | -0.262 |
Desire | -0.260 |
suppose | -0.252 |
Token | ensing |
Token ID | 26426 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
IELD | +5.384 |
hips | +5.167 |
ymm | +4.891 |
Desire | +4.838 |
suppose | +4.571 |
Neg logit contributions | |
umn | -5.965 |
cient | -5.704 |
anwhile | -5.612 |
isode | -5.449 |
arch | -5.309 |
Token | Accuracy |
Token ID | 33222 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
umn | +0.699 |
cient | +0.667 |
arch | +0.634 |
isode | +0.619 |
ophone | +0.617 |
Neg logit contributions | |
IELD | -0.626 |
hips | -0.583 |
ymm | -0.562 |
Desire | -0.552 |
suppose | -0.528 |
Token | Testing |
Token ID | 23983 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
IELD | +6.257 |
hips | +6.051 |
Desire | +5.768 |
ymm | +5.605 |
suppose | +5.193 |
Neg logit contributions | |
umn | -9.233 |
cient | -8.875 |
anwhile | -8.784 |
isode | -8.559 |
arch | -8.329 |
Token | Challenge |
Token ID | 13879 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
IELD | +5.527 |
hips | +5.372 |
Desire | +5.070 |
ymm | +4.919 |
suppose | +4.610 |
Neg logit contributions | |
umn | -7.685 |
cient | -7.393 |
anwhile | -7.281 |
isode | -7.029 |
arch | -6.947 |
Token | ( |
Token ID | 357 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
IELD | +3.976 |
hips | +3.832 |
Desire | +3.620 |
ymm | +3.563 |
suppose | +3.346 |
Neg logit contributions | |
umn | -5.361 |
cient | -5.123 |
anwhile | -5.005 |
isode | -4.887 |
arch | -4.830 |
Token | GRE |
Token ID | 28934 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
IELD | +1.355 |
hips | +1.285 |
Desire | +1.221 |
ymm | +1.197 |
suppose | +1.109 |
Neg logit contributions | |
umn | -2.104 |
cient | -2.019 |
anwhile | -1.933 |
isode | -1.920 |
arch | -1.910 |
Token | AT |
Token ID | 1404 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
umn | +2.830 |
cient | +2.763 |
arch | +2.651 |
isode | +2.610 |
anwhile | +2.609 |
Neg logit contributions | |
hips | -2.621 |
IELD | -2.601 |
Desire | -2.476 |
ymm | -2.472 |
suppose | -2.290 |
Token | warp |
Token ID | 25825 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
IELD | +0.591 |
hips | +0.552 |
ymm | +0.538 |
Desire | +0.536 |
suppose | +0.498 |
Neg logit contributions | |
umn | -0.637 |
cient | -0.612 |
anwhile | -0.577 |
isode | -0.576 |
arch | -0.575 |
Token | drive |
Token ID | 3708 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
umn | +0.903 |
cient | +0.876 |
arch | +0.821 |
anwhile | +0.818 |
isode | +0.817 |
Neg logit contributions | |
IELD | -0.919 |
hips | -0.873 |
Desire | -0.839 |
ymm | -0.837 |
suppose | -0.773 |
Token | website |
Token ID | 3052 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
IELD | +0.685 |
hips | +0.643 |
Desire | +0.620 |
ymm | +0.619 |
suppose | +0.572 |
Neg logit contributions | |
umn | -0.731 |
cient | -0.701 |
anwhile | -0.665 |
isode | -0.661 |
arch | -0.659 |
Token | for |
Token ID | 329 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
umn | +3.429 |
cient | +3.286 |
isode | +3.112 |
arch | +3.107 |
anwhile | +3.079 |
Neg logit contributions | |
IELD | -2.791 |
hips | -2.562 |
ymm | -2.522 |
Desire | -2.476 |
suppose | -2.260 |
Token | your |
Token ID | 534 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
umn | +0.006 |
cient | +0.006 |
anwhile | +0.005 |
arch | +0.005 |
isode | +0.005 |
Neg logit contributions | |
IELD | -0.005 |
hips | -0.004 |
ymm | -0.004 |
Desire | -0.004 |
suppose | -0.004 |
Token | business |
Token ID | 1597 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
umn | +0.236 |
cient | +0.225 |
anwhile | +0.212 |
isode | +0.211 |
arch | +0.211 |
Neg logit contributions | |
IELD | -0.216 |
hips | -0.205 |
ymm | -0.196 |
Desire | -0.195 |
suppose | -0.183 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
umn | +5.157 |
cient | +4.997 |
arch | +4.716 |
isode | +4.653 |
anwhile | +4.564 |
Neg logit contributions | |
IELD | -4.610 |
hips | -4.084 |
ymm | -4.080 |
Desire | -4.017 |
suppose | -3.736 |
Token | engage |
Token ID | 8209 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
umn | +2.412 |
cient | +2.313 |
arch | +2.176 |
anwhile | +2.172 |
isode | +2.168 |
Neg logit contributions | |
IELD | -2.233 |
hips | -2.060 |
ymm | -2.030 |
Desire | -1.991 |
suppose | -1.831 |
Token | your |
Token ID | 534 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
umn | +0.569 |
cient | +0.557 |
arch | +0.519 |
anwhile | +0.518 |
isode | +0.516 |
Neg logit contributions | |
IELD | -0.457 |
hips | -0.421 |
ymm | -0.408 |
Desire | -0.406 |
suppose | -0.383 |
Token | customers |
Token ID | 4297 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
umn | +0.096 |
cient | +0.093 |
anwhile | +0.087 |
arch | +0.087 |
isode | +0.087 |
Neg logit contributions | |
IELD | -0.075 |
hips | -0.070 |
ymm | -0.067 |
Desire | -0.067 |
suppose | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
IELD | +0.020 |
hips | +0.018 |
ymm | +0.018 |
Desire | +0.018 |
suppose | +0.017 |
Neg logit contributions | |
umn | -0.026 |
cient | -0.026 |
anwhile | -0.024 |
arch | -0.024 |
isode | -0.024 |
Token | child |
Token ID | 1200 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
IELD | +1.150 |
hips | +1.093 |
ymm | +1.033 |
Desire | +1.025 |
suppose | +0.950 |
Neg logit contributions | |
umn | -1.331 |
cient | -1.272 |
anwhile | -1.206 |
isode | -1.197 |
arch | -1.193 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
umn | +3.306 |
cient | +3.173 |
arch | +2.958 |
isode | +2.913 |
ophone | +2.896 |
Neg logit contributions | |
IELD | -3.376 |
hips | -3.091 |
Desire | -2.988 |
ymm | -2.965 |
ELF | -2.785 |
Token | But |
Token ID | 887 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
umn | +0.651 |
cient | +0.627 |
arch | +0.592 |
isode | +0.583 |
ophone | +0.582 |
Neg logit contributions | |
IELD | -0.455 |
hips | -0.424 |
ymm | -0.403 |
Desire | -0.384 |
suppose | -0.372 |
Token | eight |
Token ID | 3624 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
IELD | +0.569 |
hips | +0.525 |
ymm | +0.494 |
Desire | +0.492 |
ELF | +0.443 |
Neg logit contributions | |
umn | -0.753 |
cient | -0.724 |
anwhile | -0.690 |
arch | -0.682 |
isode | -0.673 |
Token | - |
Token ID | 12 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
IELD | +2.195 |
hips | +2.099 |
Desire | +2.037 |
ymm | +2.004 |
suppose | +1.898 |
Neg logit contributions | |
umn | -1.761 |
cient | -1.667 |
anwhile | -1.558 |
isode | -1.536 |
arch | -1.532 |
Token | year |
Token ID | 1941 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
umn | +0.752 |
cient | +0.678 |
arch | +0.593 |
anwhile | +0.588 |
isode | +0.585 |
Neg logit contributions | |
IELD | -2.050 |
hips | -1.964 |
Desire | -1.945 |
ymm | -1.899 |
suppose | -1.839 |
Token | - |
Token ID | 12 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
umn | +3.777 |
cient | +3.528 |
arch | +3.139 |
anwhile | +3.119 |
isode | +3.063 |
Neg logit contributions | |
IELD | -6.748 |
hips | -6.482 |
Desire | -6.381 |
ymm | -6.320 |
suppose | -5.897 |
Token | olds |
Token ID | 10119 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
IELD | +0.916 |
hips | +0.890 |
Desire | +0.847 |
ymm | +0.841 |
suppose | +0.797 |
Neg logit contributions | |
umn | -0.797 |
cient | -0.755 |
anwhile | -0.731 |
isode | -0.712 |
arch | -0.698 |
Token | who |
Token ID | 508 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
umn | +0.136 |
cient | +0.131 |
arch | +0.123 |
anwhile | +0.123 |
isode | +0.121 |
Neg logit contributions | |
IELD | -0.122 |
hips | -0.110 |
ymm | -0.108 |
Desire | -0.107 |
ENTION | -0.098 |
Token | aspire |
Token ID | 42926 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
umn | +1.774 |
cient | +1.688 |
anwhile | +1.596 |
arch | +1.581 |
isode | +1.565 |
Neg logit contributions | |
IELD | -1.675 |
hips | -1.530 |
ymm | -1.480 |
Desire | -1.472 |
WARE | -1.361 |
Token | to |
Token ID | 284 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
IELD | +0.676 |
hips | +0.632 |
Desire | +0.610 |
ymm | +0.608 |
suppose | +0.567 |
Neg logit contributions | |
umn | -0.739 |
cient | -0.711 |
anwhile | -0.669 |
arch | -0.665 |
isode | -0.664 |
Token | 1800 |
Token ID | 21431 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
umn | +0.793 |
cient | +0.776 |
arch | +0.730 |
anwhile | +0.725 |
isode | +0.718 |
Neg logit contributions | |
IELD | -0.591 |
hips | -0.555 |
Desire | -0.518 |
ymm | -0.518 |
suppose | -0.472 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
umn | +2.214 |
cient | +2.114 |
arch | +2.017 |
anwhile | +1.979 |
isode | +1.960 |
Neg logit contributions | |
IELD | -2.049 |
hips | -1.934 |
Desire | -1.865 |
ymm | -1.839 |
suppose | -1.682 |
Token | Learn |
Token ID | 14365 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
IELD | +0.819 |
hips | +0.768 |
ymm | +0.720 |
Desire | +0.713 |
suppose | +0.662 |
Neg logit contributions | |
umn | -1.281 |
cient | -1.239 |
anwhile | -1.173 |
arch | -1.173 |
isode | -1.166 |
Token | about |
Token ID | 546 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
IELD | +0.017 |
hips | +0.016 |
ymm | +0.015 |
Desire | +0.015 |
suppose | +0.014 |
Neg logit contributions | |
umn | -0.021 |
cient | -0.021 |
anwhile | -0.019 |
arch | -0.019 |
isode | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
umn | +1.116 |
cient | +1.093 |
arch | +1.029 |
anwhile | +1.020 |
isode | +0.999 |
Neg logit contributions | |
IELD | -0.785 |
hips | -0.726 |
ymm | -0.688 |
Desire | -0.679 |
suppose | -0.621 |
Token | history |
Token ID | 2106 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
umn | +1.111 |
cient | +1.073 |
arch | +0.994 |
anwhile | +0.991 |
isode | +0.955 |
Neg logit contributions | |
IELD | -1.325 |
hips | -1.261 |
ymm | -1.199 |
Desire | -1.191 |
suppose | -1.132 |
Token | of |
Token ID | 286 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
umn | +5.665 |
cient | +5.459 |
anwhile | +5.042 |
arch | +5.021 |
isode | +4.942 |
Neg logit contributions | |
IELD | -6.053 |
Desire | -5.535 |
ymm | -5.520 |
hips | -5.489 |
suppose | -5.029 |
Token | batteries |
Token ID | 13591 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
umn | +0.442 |
cient | +0.433 |
arch | +0.409 |
anwhile | +0.408 |
isode | +0.399 |
Neg logit contributions | |
IELD | -0.301 |
hips | -0.279 |
Desire | -0.259 |
ymm | -0.259 |
suppose | -0.235 |
Token | and |
Token ID | 290 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
IELD | +0.549 |
hips | +0.502 |
Desire | +0.486 |
ymm | +0.485 |
suppose | +0.442 |
Neg logit contributions | |
umn | -0.686 |
cient | -0.662 |
anwhile | -0.629 |
arch | -0.620 |
isode | -0.615 |
Token | find |
Token ID | 1064 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
umn | +1.557 |
cient | +1.512 |
anwhile | +1.439 |
arch | +1.421 |
isode | +1.405 |
Neg logit contributions | |
IELD | -1.232 |
hips | -1.150 |
Desire | -1.091 |
ymm | -1.091 |
GV | -0.971 |
Token | out |
Token ID | 503 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
IELD | +1.275 |
hips | +1.206 |
ymm | +1.150 |
Desire | +1.145 |
suppose | +1.067 |
Neg logit contributions | |
umn | -1.437 |
cient | -1.394 |
arch | -1.300 |
anwhile | -1.295 |
isode | -1.288 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
IELD | +2.072 |
hips | +1.972 |
Desire | +1.846 |
ymm | +1.820 |
suppose | +1.682 |
Neg logit contributions | |
umn | -3.291 |
cient | -3.160 |
anwhile | -3.051 |
isode | -3.024 |
arch | -2.984 |
Token | dollars |
Token ID | 5054 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
umn | +0.068 |
cient | +0.065 |
anwhile | +0.062 |
arch | +0.061 |
isode | +0.060 |
Neg logit contributions | |
IELD | -0.060 |
hips | -0.057 |
ymm | -0.054 |
Desire | -0.054 |
suppose | -0.050 |
Token | from |
Token ID | 422 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
umn | +0.271 |
cient | +0.259 |
anwhile | +0.247 |
arch | +0.243 |
isode | +0.241 |
Neg logit contributions | |
IELD | -0.251 |
hips | -0.232 |
Desire | -0.227 |
ymm | -0.224 |
suppose | -0.208 |
Token | rem |
Token ID | 816 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
IELD | +2.320 |
hips | +2.203 |
Desire | +2.099 |
ymm | +2.085 |
suppose | +1.947 |
Neg logit contributions | |
umn | -2.746 |
cient | -2.629 |
anwhile | -2.520 |
isode | -2.475 |
arch | -2.471 |
Token | itt |
Token ID | 715 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
umn | +3.264 |
cient | +3.179 |
arch | +3.048 |
anwhile | +2.971 |
ophone | +2.970 |
Neg logit contributions | |
IELD | -2.800 |
Desire | -2.585 |
hips | -2.547 |
ymm | -2.538 |
suppose | -2.343 |
Token | ances |
Token ID | 1817 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
umn | +3.423 |
cient | +3.363 |
anwhile | +3.258 |
arch | +3.201 |
ophone | +3.101 |
Neg logit contributions | |
IELD | -2.143 |
Desire | -1.934 |
ymm | -1.934 |
hips | -1.900 |
suppose | -1.712 |
Token | , |
Token ID | 11 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
umn | +4.934 |
cient | +4.745 |
anwhile | +4.547 |
arch | +4.482 |
isode | +4.369 |
Neg logit contributions | |
IELD | -5.158 |
ymm | -4.634 |
Desire | -4.598 |
hips | -4.494 |
ENTION | -4.207 |
Token | tourism |
Token ID | 19277 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
IELD | +1.564 |
hips | +1.476 |
Desire | +1.422 |
ymm | +1.406 |
suppose | +1.310 |
Neg logit contributions | |
umn | -1.677 |
cient | -1.605 |
anwhile | -1.541 |
isode | -1.505 |
arch | -1.502 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
umn | +3.279 |
cient | +3.122 |
arch | +2.933 |
anwhile | +2.930 |
isode | +2.894 |
Neg logit contributions | |
IELD | -3.465 |
ymm | -3.216 |
Desire | -3.173 |
hips | -3.132 |
suppose | -2.907 |
Token | pal |
Token ID | 6340 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
umn | +2.121 |
cient | +2.061 |
anwhile | +1.948 |
arch | +1.911 |
ophone | +1.883 |
Neg logit contributions | |
IELD | -2.276 |
hips | -2.092 |
Desire | -2.052 |
ymm | -2.049 |
suppose | -1.899 |
Token | ad |
Token ID | 324 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
IELD | +0.982 |
hips | +0.934 |
Desire | +0.909 |
ymm | +0.901 |
suppose | +0.865 |
Neg logit contributions | |
umn | -0.657 |
cient | -0.618 |
arch | -0.569 |
isode | -0.564 |
anwhile | -0.563 |
Token | with |
Token ID | 351 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
IELD | +0.699 |
hips | +0.659 |
Desire | +0.635 |
ymm | +0.631 |
suppose | +0.582 |
Neg logit contributions | |
umn | -0.673 |
cient | -0.635 |
anwhile | -0.605 |
isode | -0.601 |
arch | -0.597 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
IELD | +0.859 |
hips | +0.816 |
ymm | +0.765 |
Desire | +0.759 |
suppose | +0.709 |
Neg logit contributions | |
umn | -0.953 |
cient | -0.911 |
anwhile | -0.861 |
arch | -0.860 |
isode | -0.844 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
IELD | +1.097 |
hips | +1.053 |
ymm | +0.988 |
Desire | +0.985 |
suppose | +0.913 |
Neg logit contributions | |
umn | -1.219 |
cient | -1.164 |
anwhile | -1.112 |
arch | -1.105 |
isode | -1.101 |
Token | Newt |
Token ID | 40893 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
IELD | +4.530 |
hips | +4.355 |
Desire | +4.140 |
ymm | +4.033 |
suppose | +3.771 |
Neg logit contributions | |
umn | -6.616 |
cient | -6.352 |
anwhile | -6.144 |
isode | -6.033 |
arch | -5.965 |
Token | Gingrich |
Token ID | 29855 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
umn | +4.064 |
cient | +3.802 |
arch | +3.762 |
anwhile | +3.622 |
isode | +3.610 |
Neg logit contributions | |
IELD | -3.561 |
hips | -3.507 |
ymm | -3.234 |
Desire | -3.139 |
WARE | -2.888 |
Token | Former |
Token ID | 14466 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
IELD | +0.399 |
hips | +0.374 |
ymm | +0.355 |
Desire | +0.352 |
suppose | +0.326 |
Neg logit contributions | |
umn | -0.484 |
cient | -0.461 |
anwhile | -0.439 |
arch | -0.436 |
isode | -0.435 |
Token | Speaker |
Token ID | 14931 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
umn | +6.388 |
cient | +5.836 |
arch | +5.784 |
anwhile | +5.595 |
isode | +5.554 |
Neg logit contributions | |
IELD | -4.412 |
hips | -4.135 |
ymm | -4.079 |
Desire | -3.672 |
GV | -3.523 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
IELD | +2.555 |
hips | +2.453 |
Desire | +2.329 |
ymm | +2.297 |
suppose | +2.155 |
Neg logit contributions | |
umn | -3.087 |
cient | -2.953 |
anwhile | -2.842 |
isode | -2.793 |
arch | -2.766 |
Token | the |
Token ID | 262 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
umn | +0.270 |
cient | +0.256 |
arch | +0.247 |
isode | +0.244 |
anwhile | +0.244 |
Neg logit contributions | |
IELD | -0.178 |
hips | -0.172 |
ymm | -0.164 |
Desire | -0.159 |
suppose | -0.149 |
Token | House |
Token ID | 2097 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
umn | +1.063 |
cient | +1.009 |
arch | +0.977 |
anwhile | +0.951 |
isode | +0.949 |
Neg logit contributions | |
IELD | -0.700 |
hips | -0.659 |
ymm | -0.634 |
Desire | -0.607 |
suppose | -0.562 |
Token | Newt |
Token ID | 40893 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
IELD | +2.912 |
hips | +2.748 |
Desire | +2.564 |
ymm | +2.516 |
suppose | +2.299 |
Neg logit contributions | |
umn | -5.687 |
cient | -5.480 |
anwhile | -5.305 |
isode | -5.240 |
arch | -5.201 |
Token | � |
Token ID | 247 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
umn | +0.265 |
cient | +0.252 |
arch | +0.234 |
anwhile | +0.232 |
isode | +0.229 |
Neg logit contributions | |
IELD | -0.266 |
hips | -0.251 |
Desire | -0.243 |
ymm | -0.239 |
suppose | -0.226 |
Token | s |
Token ID | 82 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
IELD | +1.339 |
hips | +1.265 |
Desire | +1.227 |
ymm | +1.212 |
suppose | +1.144 |
Neg logit contributions | |
umn | -1.231 |
cient | -1.170 |
anwhile | -1.106 |
arch | -1.088 |
isode | -1.083 |
Token | obviously |
Token ID | 6189 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
IELD | +1.832 |
hips | +1.729 |
Desire | +1.650 |
ymm | +1.626 |
suppose | +1.488 |
Neg logit contributions | |
umn | -2.403 |
cient | -2.301 |
anwhile | -2.201 |
arch | -2.180 |
isode | -2.160 |
Token | not |
Token ID | 407 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
IELD | +2.320 |
hips | +2.202 |
Desire | +2.089 |
ymm | +2.057 |
suppose | +1.897 |
Neg logit contributions | |
umn | -3.163 |
cient | -3.032 |
anwhile | -2.905 |
arch | -2.868 |
isode | -2.859 |
Token | impossible |
Token ID | 5340 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
umn | +0.607 |
cient | +0.586 |
arch | +0.559 |
anwhile | +0.553 |
ophone | +0.544 |
Neg logit contributions | |
IELD | -0.404 |
hips | -0.376 |
Desire | -0.357 |
ymm | -0.350 |
WARE | -0.309 |
Token | that |
Token ID | 326 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
IELD | +1.427 |
hips | +1.352 |
Desire | +1.288 |
ymm | +1.273 |
suppose | +1.169 |
Neg logit contributions | |
umn | -1.824 |
cient | -1.738 |
anwhile | -1.675 |
arch | -1.644 |
isode | -1.641 |
Token | this |
Token ID | 428 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
umn | +0.113 |
cient | +0.107 |
anwhile | +0.103 |
arch | +0.101 |
isode | +0.100 |
Neg logit contributions | |
IELD | -0.108 |
hips | -0.102 |
ymm | -0.096 |
Desire | -0.096 |
suppose | -0.089 |
Token | could |
Token ID | 714 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
umn | +1.401 |
cient | +1.342 |
anwhile | +1.264 |
arch | +1.258 |
isode | +1.235 |
Neg logit contributions | |
IELD | -1.508 |
hips | -1.428 |
Desire | -1.354 |
ymm | -1.333 |
ELF | -1.243 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
IELD | +0.630 |
hips | +0.600 |
Desire | +0.579 |
ymm | +0.569 |
suppose | +0.533 |
Neg logit contributions | |
umn | -0.593 |
cient | -0.560 |
anwhile | -0.534 |
isode | -0.526 |
arch | -0.524 |
Token | again |
Token ID | 757 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
IELD | +0.757 |
hips | +0.701 |
Desire | +0.684 |
ymm | +0.663 |
suppose | +0.616 |
Neg logit contributions | |
umn | -0.932 |
cient | -0.892 |
anwhile | -0.858 |
arch | -0.845 |
isode | -0.839 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
umn | +0.868 |
cient | +0.831 |
anwhile | +0.791 |
arch | +0.790 |
isode | +0.776 |
Neg logit contributions | |
IELD | -0.742 |
hips | -0.678 |
Desire | -0.668 |
ymm | -0.651 |
suppose | -0.593 |
Token | talk |
Token ID | 1561 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
IELD | +0.325 |
hips | +0.307 |
Desire | +0.292 |
ymm | +0.291 |
suppose | +0.268 |
Neg logit contributions | |
umn | -0.371 |
cient | -0.353 |
anwhile | -0.337 |
isode | -0.334 |
arch | -0.333 |
Token | about |
Token ID | 546 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
umn | +1.833 |
cient | +1.760 |
isode | +1.651 |
arch | +1.648 |
anwhile | +1.644 |
Neg logit contributions | |
IELD | -1.847 |
hips | -1.694 |
ymm | -1.647 |
Desire | -1.636 |
suppose | -1.527 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
umn | +0.809 |
cient | +0.773 |
arch | +0.736 |
anwhile | +0.729 |
isode | +0.725 |
Neg logit contributions | |
IELD | -0.656 |
hips | -0.608 |
ymm | -0.576 |
Desire | -0.559 |
suppose | -0.529 |
Token | to |
Token ID | 284 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
umn | +1.048 |
cient | +1.012 |
arch | +0.968 |
ophone | +0.953 |
anwhile | +0.944 |
Neg logit contributions | |
IELD | -0.940 |
hips | -0.875 |
ymm | -0.850 |
Desire | -0.844 |
suppose | -0.809 |
Token | someone |
Token ID | 2130 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
umn | +0.107 |
cient | +0.102 |
anwhile | +0.097 |
isode | +0.097 |
arch | +0.097 |
Neg logit contributions | |
IELD | -0.081 |
hips | -0.076 |
ymm | -0.072 |
Desire | -0.071 |
suppose | -0.065 |
Token | who |
Token ID | 508 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
umn | +0.917 |
cient | +0.898 |
arch | +0.827 |
ophone | +0.822 |
isode | +0.818 |
Neg logit contributions | |
IELD | -0.882 |
hips | -0.802 |
ymm | -0.787 |
Desire | -0.760 |
WARE | -0.699 |
Token | isn |
Token ID | 2125 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
umn | +3.177 |
cient | +3.023 |
arch | +2.860 |
anwhile | +2.845 |
ophone | +2.773 |
Neg logit contributions | |
IELD | -3.368 |
hips | -3.072 |
ymm | -3.008 |
Desire | -2.935 |
WARE | -2.773 |
Token | � |
Token ID | 447 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
umn | +1.066 |
cient | +1.019 |
arch | +0.949 |
isode | +0.934 |
ophone | +0.923 |
Neg logit contributions | |
IELD | -1.157 |
hips | -1.093 |
Desire | -1.060 |
ymm | -1.052 |
suppose | -0.991 |
Token | � |
Token ID | 247 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
umn | +0.692 |
cient | +0.661 |
arch | +0.606 |
anwhile | +0.598 |
isode | +0.593 |
Neg logit contributions | |
IELD | -0.704 |
hips | -0.662 |
Desire | -0.645 |
ymm | -0.636 |
suppose | -0.598 |
Token | t |
Token ID | 83 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
IELD | +1.068 |
hips | +1.008 |
Desire | +0.986 |
ymm | +0.972 |
suppose | +0.920 |
Neg logit contributions | |
umn | -0.862 |
cient | -0.819 |
anwhile | -0.762 |
arch | -0.752 |
isode | -0.745 |
Token | interested |
Token ID | 4609 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
IELD | +0.838 |
hips | +0.779 |
ymm | +0.738 |
Desire | +0.731 |
suppose | +0.658 |
Neg logit contributions | |
umn | -1.155 |
cient | -1.117 |
anwhile | -1.051 |
arch | -1.051 |
isode | -1.042 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
umn | +0.340 |
cient | +0.323 |
anwhile | +0.313 |
arch | +0.305 |
isode | +0.301 |
Neg logit contributions | |
IELD | -0.279 |
hips | -0.261 |
ymm | -0.249 |
Desire | -0.246 |
suppose | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
umn | +2.171 |
cient | +2.072 |
anwhile | +2.015 |
arch | +1.946 |
isode | +1.941 |
Neg logit contributions | |
IELD | -1.893 |
hips | -1.797 |
ymm | -1.697 |
Desire | -1.660 |
suppose | -1.525 |
Token | DOJ |
Token ID | 27055 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
umn | +0.461 |
cient | +0.435 |
anwhile | +0.419 |
arch | +0.410 |
isode | +0.405 |
Neg logit contributions | |
IELD | -0.462 |
hips | -0.444 |
ymm | -0.422 |
Desire | -0.418 |
suppose | -0.393 |
Token | claimed |
Token ID | 4752 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
umn | +0.858 |
cient | +0.813 |
anwhile | +0.782 |
arch | +0.772 |
isode | +0.753 |
Neg logit contributions | |
IELD | -0.864 |
hips | -0.826 |
ymm | -0.792 |
Desire | -0.782 |
suppose | -0.721 |
Token | , |
Token ID | 11 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
IELD | +0.331 |
hips | +0.314 |
ymm | +0.297 |
Desire | +0.295 |
suppose | +0.276 |
Neg logit contributions | |
umn | -0.372 |
cient | -0.354 |
anwhile | -0.338 |
isode | -0.332 |
arch | -0.331 |
Token | flat |
Token ID | 6228 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
IELD | +1.083 |
hips | +1.023 |
Desire | +0.971 |
ymm | +0.962 |
suppose | +0.892 |
Neg logit contributions | |
umn | -1.331 |
cient | -1.273 |
anwhile | -1.221 |
arch | -1.198 |
isode | -1.196 |
Token | out |
Token ID | 503 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
umn | +0.266 |
cient | +0.252 |
iously | +0.235 |
isode | +0.233 |
arch | +0.232 |
Neg logit contributions | |
IELD | -0.401 |
hips | -0.390 |
ymm | -0.374 |
Desire | -0.371 |
suppose | -0.352 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
IELD | +2.876 |
hips | +2.765 |
Desire | +2.612 |
ymm | +2.578 |
suppose | +2.420 |
Neg logit contributions | |
umn | -3.696 |
cient | -3.536 |
anwhile | -3.416 |
isode | -3.363 |
arch | -3.326 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
IELD | +2.155 |
hips | +2.055 |
Desire | +1.949 |
ymm | +1.928 |
suppose | +1.800 |
Neg logit contributions | |
umn | -2.745 |
cient | -2.623 |
anwhile | -2.521 |
isode | -2.486 |
arch | -2.468 |
Token | Kam |
Token ID | 12670 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
umn | +2.257 |
cient | +2.123 |
anwhile | +2.028 |
iously | +2.012 |
arch | +1.992 |
Neg logit contributions | |
IELD | -2.120 |
hips | -1.998 |
ymm | -1.875 |
Desire | -1.823 |
GV | -1.705 |
Token | al |
Token ID | 282 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
IELD | +2.591 |
hips | +2.542 |
ymm | +2.427 |
Desire | +2.424 |
suppose | +2.289 |
Neg logit contributions | |
umn | -2.107 |
cient | -2.007 |
anwhile | -1.988 |
isode | -1.919 |
ophone | -1.840 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
IELD | +0.670 |
hips | +0.635 |
ymm | +0.596 |
Desire | +0.580 |
suppose | +0.553 |
Neg logit contributions | |
umn | -0.885 |
cient | -0.850 |
anwhile | -0.807 |
arch | -0.806 |
isode | -0.805 |
Token | leg |
Token ID | 1232 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
IELD | +1.926 |
hips | +1.843 |
ymm | +1.741 |
Desire | +1.726 |
suppose | +1.614 |
Neg logit contributions | |
umn | -2.274 |
cient | -2.164 |
anwhile | -2.063 |
isode | -2.057 |
arch | -2.042 |
Token | amput |
Token ID | 40338 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
umn | +1.519 |
cient | +1.427 |
isode | +1.365 |
arch | +1.355 |
ophone | +1.334 |
Neg logit contributions | |
IELD | -1.682 |
hips | -1.628 |
ymm | -1.524 |
Desire | -1.520 |
suppose | -1.438 |
Token | ation |
Token ID | 341 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
IELD | +1.471 |
hips | +1.415 |
Desire | +1.373 |
ymm | +1.357 |
suppose | +1.307 |
Neg logit contributions | |
umn | -0.722 |
cient | -0.663 |
anwhile | -0.602 |
isode | -0.601 |
arch | -0.598 |
Token | who |
Token ID | 508 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
umn | +0.679 |
cient | +0.653 |
arch | +0.616 |
anwhile | +0.615 |
isode | +0.614 |
Neg logit contributions | |
IELD | -0.601 |
hips | -0.558 |
ymm | -0.536 |
Desire | -0.526 |
suppose | -0.490 |
Token | was |
Token ID | 373 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
umn | +3.060 |
cient | +2.902 |
anwhile | +2.760 |
arch | +2.753 |
isode | +2.654 |
Neg logit contributions | |
IELD | -3.280 |
hips | -3.084 |
ymm | -2.995 |
Desire | -2.879 |
suppose | -2.699 |
Token | volunteering |
Token ID | 41434 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
IELD | +0.177 |
hips | +0.165 |
ymm | +0.158 |
Desire | +0.157 |
suppose | +0.141 |
Neg logit contributions | |
umn | -0.201 |
cient | -0.193 |
anwhile | -0.182 |
arch | -0.182 |
isode | -0.178 |
Token | at |
Token ID | 379 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
IELD | +1.370 |
hips | +1.289 |
ymm | +1.213 |
Desire | +1.212 |
suppose | +1.118 |
Neg logit contributions | |
umn | -1.973 |
cient | -1.899 |
anwhile | -1.811 |
arch | -1.794 |
isode | -1.784 |
Token | the |
Token ID | 262 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
IELD | +0.170 |
hips | +0.161 |
ymm | +0.149 |
Desire | +0.144 |
suppose | +0.137 |
Neg logit contributions | |
umn | -0.297 |
cient | -0.285 |
anwhile | -0.274 |
isode | -0.272 |
arch | -0.270 |
Token | store |
Token ID | 3650 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
umn | +1.436 |
cient | +1.363 |
anwhile | +1.290 |
arch | +1.272 |
isode | +1.255 |
Neg logit contributions | |
IELD | -1.637 |
hips | -1.578 |
ymm | -1.480 |
Desire | -1.447 |
suppose | -1.411 |
Token | at |
Token ID | 379 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
umn | +0.270 |
cient | +0.259 |
anwhile | +0.246 |
arch | +0.245 |
isode | +0.243 |
Neg logit contributions | |
IELD | -0.218 |
hips | -0.201 |
ymm | -0.193 |
Desire | -0.192 |
suppose | -0.177 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
umn | +2.443 |
cient | +2.333 |
arch | +2.238 |
isode | +2.224 |
anwhile | +2.222 |
Neg logit contributions | |
IELD | -1.777 |
hips | -1.640 |
ymm | -1.621 |
Desire | -1.549 |
suppose | -1.430 |
Token | and |
Token ID | 290 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
IELD | +3.077 |
hips | +2.971 |
Desire | +2.848 |
ymm | +2.832 |
suppose | +2.686 |
Neg logit contributions | |
umn | -2.402 |
cient | -2.266 |
anwhile | -2.143 |
isode | -2.117 |
arch | -2.098 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
umn | +1.860 |
cient | +1.734 |
arch | +1.667 |
isode | +1.656 |
anwhile | +1.642 |
Neg logit contributions | |
IELD | -1.376 |
hips | -1.289 |
ymm | -1.224 |
Desire | -1.187 |
suppose | -1.108 |
Token | were |
Token ID | 547 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
IELD | +3.202 |
hips | +3.053 |
Desire | +2.898 |
ymm | +2.877 |
suppose | +2.685 |
Neg logit contributions | |
umn | -3.878 |
cient | -3.700 |
anwhile | -3.551 |
isode | -3.507 |
arch | -3.479 |
Token | listed |
Token ID | 5610 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
IELD | +0.270 |
hips | +0.252 |
Desire | +0.243 |
ymm | +0.240 |
suppose | +0.221 |
Neg logit contributions | |
umn | -0.254 |
cient | -0.242 |
anwhile | -0.227 |
arch | -0.227 |
isode | -0.224 |
Token | on |
Token ID | 319 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
IELD | +0.878 |
hips | +0.798 |
Desire | +0.769 |
ymm | +0.768 |
suppose | +0.704 |
Neg logit contributions | |
umn | -1.159 |
cient | -1.109 |
arch | -1.060 |
anwhile | -1.059 |
isode | -1.031 |
Token | Y |
Token ID | 575 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
umn | +0.800 |
cient | +0.759 |
arch | +0.733 |
anwhile | +0.728 |
isode | +0.725 |
Neg logit contributions | |
IELD | -0.558 |
hips | -0.527 |
ymm | -0.508 |
Desire | -0.489 |
suppose | -0.464 |
Token | AL |
Token ID | 1847 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
IELD | +2.320 |
hips | +2.250 |
Desire | +2.175 |
ymm | +2.133 |
suppose | +2.036 |
Neg logit contributions | |
umn | -2.236 |
cient | -2.111 |
anwhile | -1.992 |
isode | -1.992 |
arch | -1.991 |
Token | SA |
Token ID | 4090 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
umn | +1.139 |
cient | +1.083 |
anwhile | +1.039 |
arch | +1.036 |
isode | +1.035 |
Neg logit contributions | |
IELD | -0.988 |
hips | -0.967 |
Desire | -0.934 |
ymm | -0.920 |
suppose | -0.845 |
Token | 's |
Token ID | 338 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
IELD | +0.961 |
hips | +0.922 |
ymm | +0.879 |
Desire | +0.875 |
suppose | +0.822 |
Neg logit contributions | |
umn | -1.062 |
cient | -1.007 |
anwhile | -0.963 |
arch | -0.962 |
isode | -0.944 |
Token | " |
Token ID | 366 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
IELD | +2.337 |
hips | +2.243 |
Desire | +2.143 |
ymm | +2.139 |
suppose | +2.020 |
Neg logit contributions | |
umn | -2.086 |
cient | -1.971 |
anwhile | -1.875 |
isode | -1.841 |
arch | -1.839 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
umn | +0.185 |
cient | +0.177 |
arch | +0.167 |
isode | +0.167 |
anwhile | +0.166 |
Neg logit contributions | |
IELD | -0.156 |
hips | -0.143 |
Desire | -0.137 |
ymm | -0.137 |
suppose | -0.126 |
Token | A |
Token ID | 317 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
umn | +0.071 |
cient | +0.068 |
anwhile | +0.065 |
arch | +0.065 |
isode | +0.065 |
Neg logit contributions | |
IELD | -0.046 |
hips | -0.043 |
ymm | -0.041 |
Desire | -0.040 |
suppose | -0.037 |
Token | great |
Token ID | 1049 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
IELD | +4.369 |
hips | +4.175 |
Desire | +3.967 |
ymm | +3.898 |
suppose | +3.660 |
Neg logit contributions | |
umn | -5.772 |
cient | -5.511 |
anwhile | -5.327 |
isode | -5.232 |
arch | -5.182 |
Token | example |
Token ID | 1672 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
IELD | +0.947 |
hips | +0.904 |
Desire | +0.861 |
ymm | +0.860 |
suppose | +0.801 |
Neg logit contributions | |
umn | -0.964 |
cient | -0.916 |
anwhile | -0.870 |
isode | -0.864 |
arch | -0.860 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
IELD | +1.417 |
hips | +1.338 |
Desire | +1.278 |
ymm | +1.271 |
suppose | +1.170 |
Neg logit contributions | |
umn | -1.522 |
cient | -1.460 |
anwhile | -1.382 |
isode | -1.371 |
arch | -1.369 |
Token | this |
Token ID | 428 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
IELD | +1.792 |
hips | +1.693 |
Desire | +1.578 |
ymm | +1.572 |
suppose | +1.428 |
Neg logit contributions | |
umn | -3.019 |
cient | -2.892 |
anwhile | -2.783 |
isode | -2.757 |
arch | -2.750 |
Token | is |
Token ID | 318 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
IELD | +0.532 |
hips | +0.502 |
ymm | +0.476 |
Desire | +0.475 |
suppose | +0.440 |
Neg logit contributions | |
umn | -0.570 |
cient | -0.549 |
anwhile | -0.517 |
isode | -0.516 |
arch | -0.514 |
Token | Robot |
Token ID | 16071 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
IELD | +0.527 |
hips | +0.491 |
ymm | +0.467 |
Desire | +0.457 |
suppose | +0.416 |
Neg logit contributions | |
umn | -0.777 |
cient | -0.741 |
isode | -0.711 |
anwhile | -0.710 |
arch | -0.709 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
umn | +0.246 |
cient | +0.235 |
arch | +0.226 |
isode | +0.222 |
anwhile | +0.218 |
Neg logit contributions | |
IELD | -0.187 |
hips | -0.176 |
ymm | -0.165 |
Desire | -0.162 |
suppose | -0.156 |
Token | : |
Token ID | 25 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
IELD | +0.306 |
hips | +0.288 |
ymm | +0.278 |
Desire | +0.273 |
suppose | +0.257 |
Neg logit contributions | |
umn | -0.316 |
cient | -0.297 |
arch | -0.282 |
anwhile | -0.280 |
isode | -0.277 |
Token | in |
Token ID | 287 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
umn | +0.014 |
cient | +0.013 |
anwhile | +0.013 |
isode | +0.013 |
arch | +0.012 |
Neg logit contributions | |
IELD | -0.010 |
hips | -0.009 |
ymm | -0.009 |
Desire | -0.009 |
suppose | -0.008 |
Token | silence |
Token ID | 9550 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
IELD | +0.788 |
hips | +0.737 |
ymm | +0.690 |
Desire | +0.684 |
suppose | +0.640 |
Neg logit contributions | |
umn | -0.934 |
cient | -0.892 |
anwhile | -0.841 |
arch | -0.839 |
isode | -0.838 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
IELD | +0.450 |
hips | +0.414 |
Desire | +0.401 |
ymm | +0.399 |
suppose | +0.365 |
Neg logit contributions | |
umn | -0.514 |
cient | -0.496 |
anwhile | -0.466 |
isode | -0.464 |
arch | -0.464 |
Token | It |
Token ID | 632 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
IELD | +0.470 |
hips | +0.443 |
ymm | +0.415 |
Desire | +0.403 |
suppose | +0.382 |
Neg logit contributions | |
umn | -0.727 |
cient | -0.693 |
isode | -0.659 |
anwhile | -0.659 |
arch | -0.658 |
Token | � |
Token ID | 447 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
IELD | +0.175 |
hips | +0.165 |
Desire | +0.159 |
ymm | +0.157 |
suppose | +0.146 |
Neg logit contributions | |
umn | -0.178 |
cient | -0.169 |
anwhile | -0.161 |
arch | -0.159 |
isode | -0.158 |
Token | � |
Token ID | 247 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
IELD | +0.580 |
hips | +0.550 |
Desire | +0.526 |
ymm | +0.518 |
suppose | +0.482 |
Neg logit contributions | |
umn | -0.797 |
cient | -0.763 |
anwhile | -0.723 |
arch | -0.719 |
isode | -0.717 |
Token | s |
Token ID | 82 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
IELD | +1.449 |
hips | +1.377 |
Desire | +1.321 |
ymm | +1.308 |
suppose | +1.231 |
Neg logit contributions | |
umn | -1.509 |
cient | -1.435 |
anwhile | -1.370 |
isode | -1.348 |
arch | -1.341 |
Token | enough |
Token ID | 1576 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
IELD | +1.357 |
hips | +1.263 |
Desire | +1.192 |
ymm | +1.180 |
suppose | +1.077 |
Neg logit contributions | |
umn | -1.902 |
cient | -1.826 |
anwhile | -1.737 |
arch | -1.725 |
isode | -1.721 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
IELD | +0.047 |
hips | +0.044 |
Desire | +0.042 |
ymm | +0.041 |
suppose | +0.038 |
Neg logit contributions | |
umn | -0.050 |
cient | -0.048 |
arch | -0.045 |
isode | -0.044 |
anwhile | -0.044 |
Token | trick |
Token ID | 6908 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
IELD | +2.099 |
hips | +2.008 |
Desire | +1.917 |
ymm | +1.900 |
suppose | +1.779 |
Neg logit contributions | |
umn | -2.214 |
cient | -2.109 |
anwhile | -2.015 |
isode | -1.988 |
arch | -1.973 |
Token | me |
Token ID | 502 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
umn | +1.833 |
cient | +1.752 |
arch | +1.658 |
ophone | +1.648 |
anwhile | +1.632 |
Neg logit contributions | |
IELD | -1.337 |
hips | -1.266 |
ymm | -1.178 |
Desire | -1.163 |
suppose | -1.067 |
Token | into |
Token ID | 656 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
IELD | +1.189 |
hips | +1.109 |
Desire | +1.068 |
ymm | +1.050 |
suppose | +0.959 |
Neg logit contributions | |
umn | -1.406 |
cient | -1.354 |
arch | -1.275 |
anwhile | -1.270 |
isode | -1.262 |
Token | when |
Token ID | 618 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
umn | +0.245 |
cient | +0.235 |
arch | +0.222 |
anwhile | +0.221 |
isode | +0.219 |
Neg logit contributions | |
IELD | -0.231 |
hips | -0.218 |
Desire | -0.211 |
ymm | -0.205 |
Darling | -0.189 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
umn | +1.665 |
cient | +1.577 |
arch | +1.513 |
anwhile | +1.497 |
ophone | +1.471 |
Neg logit contributions | |
IELD | -1.250 |
hips | -1.148 |
Desire | -1.118 |
ymm | -1.078 |
ELF | -0.978 |
Token | initial |
Token ID | 4238 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
IELD | +0.350 |
hips | +0.330 |
Desire | +0.313 |
ymm | +0.310 |
suppose | +0.285 |
Neg logit contributions | |
umn | -0.433 |
cient | -0.411 |
anwhile | -0.390 |
arch | -0.390 |
isode | -0.384 |
Token | space |
Token ID | 2272 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
IELD | +3.990 |
hips | +3.822 |
Desire | +3.629 |
ymm | +3.587 |
suppose | +3.364 |
Neg logit contributions | |
umn | -5.070 |
cient | -4.851 |
anwhile | -4.679 |
isode | -4.606 |
arch | -4.550 |
Token | is |
Token ID | 318 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
IELD | +0.689 |
hips | +0.644 |
Desire | +0.619 |
ymm | +0.610 |
suppose | +0.569 |
Neg logit contributions | |
umn | -0.786 |
cient | -0.751 |
anwhile | -0.710 |
arch | -0.710 |
isode | -0.708 |
Token | nearly |
Token ID | 3016 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
IELD | +1.275 |
hips | +1.193 |
Desire | +1.137 |
ymm | +1.109 |
suppose | +1.007 |
Neg logit contributions | |
umn | -1.753 |
cient | -1.686 |
anwhile | -1.590 |
arch | -1.589 |
isode | -1.576 |
Token | cub |
Token ID | 13617 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
IELD | +1.423 |
hips | +1.341 |
Desire | +1.278 |
ymm | +1.253 |
suppose | +1.145 |
Neg logit contributions | |
umn | -1.987 |
cient | -1.919 |
isode | -1.814 |
anwhile | -1.810 |
arch | -1.805 |
Token | oid |
Token ID | 1868 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
IELD | +0.833 |
hips | +0.799 |
Desire | +0.776 |
ymm | +0.762 |
suppose | +0.731 |
Neg logit contributions | |
umn | -0.468 |
cient | -0.432 |
isode | -0.395 |
anwhile | -0.393 |
arch | -0.391 |
Token | , |
Token ID | 11 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
umn | +0.640 |
cient | +0.618 |
arch | +0.577 |
ophone | +0.568 |
isode | +0.566 |
Neg logit contributions | |
IELD | -0.584 |
hips | -0.537 |
Desire | -0.522 |
ymm | -0.510 |
suppose | -0.468 |
Token | for |
Token ID | 329 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
IELD | +0.962 |
hips | +0.913 |
Desire | +0.877 |
ymm | +0.855 |
suppose | +0.780 |
Neg logit contributions | |
umn | -1.179 |
cient | -1.120 |
anwhile | -1.063 |
arch | -1.058 |
isode | -1.045 |
Token | example |
Token ID | 1672 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
IELD | +0.172 |
hips | +0.164 |
Desire | +0.156 |
ymm | +0.153 |
suppose | +0.141 |
Neg logit contributions | |
umn | -0.189 |
cient | -0.180 |
arch | -0.170 |
anwhile | -0.169 |
isode | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
umn | +4.300 |
cient | +4.180 |
arch | +3.958 |
anwhile | +3.862 |
ophone | +3.782 |
Neg logit contributions | |
IELD | -4.252 |
hips | -3.811 |
Desire | -3.800 |
ymm | -3.771 |
ELF | -3.482 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
IELD | +0.447 |
hips | +0.422 |
Desire | +0.394 |
ymm | +0.392 |
suppose | +0.371 |
Neg logit contributions | |
umn | -0.663 |
cient | -0.635 |
anwhile | -0.612 |
arch | -0.606 |
isode | -0.602 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
IELD | +0.235 |
hips | +0.221 |
Desire | +0.209 |
ymm | +0.207 |
suppose | +0.190 |
Neg logit contributions | |
umn | -0.370 |
cient | -0.355 |
arch | -0.337 |
anwhile | -0.337 |
isode | -0.336 |
Token | S |
Token ID | 50 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
IELD | +0.229 |
hips | +0.219 |
Desire | +0.213 |
ymm | +0.207 |
suppose | +0.199 |
Neg logit contributions | |
umn | -0.249 |
cient | -0.239 |
arch | -0.226 |
isode | -0.224 |
anwhile | -0.219 |
Token | BI |
Token ID | 3483 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
IELD | +2.134 |
hips | +1.993 |
Desire | +1.832 |
ymm | +1.802 |
suppose | +1.613 |
Neg logit contributions | |
umn | -5.095 |
cient | -4.917 |
anwhile | -4.772 |
isode | -4.720 |
arch | -4.686 |
Token | Wire |
Token ID | 14712 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
umn | +3.787 |
cient | +3.602 |
anwhile | +3.489 |
arch | +3.434 |
ophone | +3.370 |
Neg logit contributions | |
IELD | -3.077 |
hips | -2.959 |
Desire | -2.761 |
ymm | -2.744 |
suppose | -2.595 |
Token | x |
Token ID | 87 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
IELD | +1.157 |
hips | +1.133 |
Desire | +1.078 |
ymm | +1.076 |
suppose | +1.017 |
Neg logit contributions | |
umn | -0.944 |
cient | -0.896 |
anwhile | -0.882 |
isode | -0.847 |
arch | -0.822 |
Token | Asia |
Token ID | 7229 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
umn | +1.116 |
cient | +1.049 |
anwhile | +0.993 |
arch | +0.991 |
ophone | +0.960 |
Neg logit contributions | |
IELD | -1.376 |
hips | -1.299 |
Desire | -1.254 |
ymm | -1.252 |
suppose | -1.177 |
Token | will |
Token ID | 481 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
IELD | +0.141 |
hips | +0.133 |
Desire | +0.127 |
ymm | +0.127 |
suppose | +0.118 |
Neg logit contributions | |
umn | -0.149 |
cient | -0.140 |
anwhile | -0.133 |
arch | -0.132 |
isode | -0.131 |
Token | deliver |
Token ID | 5203 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
umn | +1.269 |
cient | +1.200 |
anwhile | +1.146 |
arch | +1.132 |
isode | +1.116 |
Neg logit contributions | |
IELD | -1.278 |
hips | -1.182 |
Desire | -1.148 |
ymm | -1.141 |
Darling | -1.049 |
Token | a |
Token ID | 257 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
IELD | +1.715 |
hips | +1.610 |
Desire | +1.534 |
ymm | +1.525 |
suppose | +1.419 |
Neg logit contributions | |
umn | -2.177 |
cient | -2.093 |
anwhile | -2.000 |
arch | -1.979 |
isode | -1.962 |
Token | technical |
Token ID | 6276 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
IELD | +2.492 |
hips | +2.393 |
Desire | +2.267 |
ymm | +2.255 |
suppose | +2.103 |
Neg logit contributions | |
umn | -2.618 |
cient | -2.507 |
anwhile | -2.382 |
isode | -2.348 |
arch | -2.344 |
Token | fault |
Token ID | 8046 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
umn | +0.648 |
cient | +0.621 |
arch | +0.577 |
isode | +0.575 |
ophone | +0.574 |
Neg logit contributions | |
IELD | -0.733 |
hips | -0.703 |
ymm | -0.662 |
Desire | -0.659 |
Darling | -0.615 |
Token | that |
Token ID | 326 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
IELD | +1.092 |
hips | +1.024 |
Desire | +0.977 |
ymm | +0.971 |
suppose | +0.894 |
Neg logit contributions | |
umn | -1.328 |
cient | -1.290 |
anwhile | -1.219 |
isode | -1.210 |
arch | -1.209 |
Token | can |
Token ID | 460 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
umn | +1.584 |
cient | +1.517 |
anwhile | +1.429 |
arch | +1.423 |
isode | +1.395 |
Neg logit contributions | |
IELD | -1.553 |
hips | -1.471 |
Desire | -1.411 |
ymm | -1.395 |
suppose | -1.280 |
Token | be |
Token ID | 307 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
IELD | +0.161 |
hips | +0.152 |
Desire | +0.148 |
ymm | +0.146 |
suppose | +0.134 |
Neg logit contributions | |
umn | -0.166 |
cient | -0.158 |
anwhile | -0.151 |
isode | -0.149 |
arch | -0.147 |
Token | corrected |
Token ID | 19267 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
IELD | +2.582 |
hips | +2.460 |
Desire | +2.340 |
ymm | +2.310 |
suppose | +2.152 |
Neg logit contributions | |
umn | -3.289 |
cient | -3.149 |
anwhile | -3.021 |
isode | -2.979 |
arch | -2.962 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
IELD | +2.154 |
hips | +2.026 |
Desire | +1.934 |
ymm | +1.912 |
suppose | +1.767 |
Neg logit contributions | |
umn | -2.864 |
cient | -2.754 |
anwhile | -2.639 |
arch | -2.596 |
isode | -2.594 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
IELD | +0.728 |
hips | +0.688 |
ymm | +0.649 |
Desire | +0.642 |
suppose | +0.605 |
Neg logit contributions | |
umn | -1.000 |
cient | -0.964 |
anwhile | -0.915 |
arch | -0.911 |
isode | -0.900 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
IELD | +0.024 |
hips | +0.023 |
Desire | +0.022 |
ymm | +0.021 |
suppose | +0.020 |
Neg logit contributions | |
umn | -0.038 |
cient | -0.037 |
arch | -0.035 |
anwhile | -0.034 |
isode | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
umn | +0.223 |
cient | +0.213 |
arch | +0.200 |
isode | +0.196 |
ophone | +0.194 |
Neg logit contributions | |
IELD | -0.238 |
hips | -0.228 |
Desire | -0.222 |
ymm | -0.217 |
suppose | -0.208 |
Token | The |
Token ID | 464 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
IELD | +0.771 |
hips | +0.730 |
Desire | +0.705 |
ymm | +0.695 |
suppose | +0.643 |
Neg logit contributions | |
umn | -1.070 |
cient | -1.033 |
arch | -0.984 |
isode | -0.970 |
anwhile | -0.958 |
Token | remove |
Token ID | 4781 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
umn | +1.596 |
cient | +1.518 |
anwhile | +1.449 |
arch | +1.432 |
isode | +1.401 |
Neg logit contributions | |
IELD | -1.686 |
hips | -1.575 |
Desire | -1.520 |
ymm | -1.510 |
Darling | -1.392 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
IELD | +2.456 |
hips | +2.321 |
Desire | +2.199 |
ymm | +2.178 |
suppose | +2.025 |
Neg logit contributions | |
umn | -3.510 |
cient | -3.368 |
anwhile | -3.239 |
isode | -3.196 |
arch | -3.193 |
Token | MS |
Token ID | 5653 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
IELD | +0.638 |
hips | +0.602 |
Desire | +0.563 |
ymm | +0.559 |
suppose | +0.528 |
Neg logit contributions | |
umn | -0.941 |
cient | -0.904 |
anwhile | -0.866 |
arch | -0.860 |
isode | -0.856 |
Token | I |
Token ID | 40 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
umn | +3.462 |
cient | +3.353 |
arch | +3.225 |
iously | +3.209 |
ophone | +3.167 |
Neg logit contributions | |
IELD | -3.753 |
hips | -3.503 |
Desire | -3.441 |
ymm | -3.406 |
Darling | -3.187 |
Token | exclusive |
Token ID | 8568 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
umn | +0.553 |
cient | +0.529 |
anwhile | +0.514 |
arch | +0.506 |
isode | +0.497 |
Neg logit contributions | |
IELD | -0.427 |
hips | -0.406 |
ymm | -0.378 |
Desire | -0.378 |
suppose | -0.351 |
Token | Un |
Token ID | 791 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
IELD | +2.963 |
hips | +2.824 |
Desire | +2.675 |
ymm | +2.645 |
suppose | +2.468 |
Neg logit contributions | |
umn | -3.909 |
cient | -3.741 |
anwhile | -3.598 |
isode | -3.549 |
arch | -3.524 |
Token | locked |
Token ID | 24162 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
IELD | +3.680 |
hips | +3.457 |
ymm | +3.179 |
Desire | +3.163 |
suppose | +2.762 |
Neg logit contributions | |
umn | -8.490 |
cient | -8.195 |
anwhile | -8.099 |
isode | -7.840 |
ophone | -7.707 |
Token | Digital |
Token ID | 10231 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
IELD | +3.303 |
hips | +3.162 |
Desire | +3.008 |
ymm | +2.979 |
suppose | +2.801 |
Neg logit contributions | |
umn | -3.736 |
cient | -3.566 |
anwhile | -3.417 |
isode | -3.369 |
arch | -3.346 |
Token | Power |
Token ID | 13434 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
IELD | +0.446 |
hips | +0.418 |
Desire | +0.389 |
ymm | +0.385 |
suppose | +0.352 |
Neg logit contributions | |
umn | -0.914 |
cient | -0.883 |
anwhile | -0.851 |
arch | -0.844 |
isode | -0.844 |
Token | is |
Token ID | 318 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
IELD | +1.611 |
hips | +1.524 |
Desire | +1.449 |
ymm | +1.433 |
suppose | +1.339 |
Neg logit contributions | |
umn | -2.076 |
cient | -1.996 |
anwhile | -1.912 |
arch | -1.889 |
isode | -1.883 |
Token | composed |
Token ID | 13160 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
umn | +1.391 |
cient | +1.327 |
arch | +1.274 |
anwhile | +1.269 |
isode | +1.250 |
Neg logit contributions | |
IELD | -1.021 |
hips | -0.943 |
Desire | -0.899 |
ymm | -0.883 |
suppose | -0.797 |
Token | click |
Token ID | 3904 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
umn | +1.588 |
cient | +1.494 |
anwhile | +1.438 |
arch | +1.409 |
isode | +1.402 |
Neg logit contributions | |
IELD | -1.523 |
hips | -1.421 |
ymm | -1.376 |
Desire | -1.360 |
GV | -1.255 |
Token | on |
Token ID | 319 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
umn | +0.786 |
cient | +0.748 |
anwhile | +0.727 |
arch | +0.717 |
isode | +0.712 |
Neg logit contributions | |
IELD | -0.594 |
hips | -0.550 |
ymm | -0.534 |
Desire | -0.530 |
suppose | -0.483 |
Token | Vide |
Token ID | 42551 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
IELD | +0.145 |
hips | +0.135 |
ymm | +0.130 |
Desire | +0.128 |
suppose | +0.117 |
Neg logit contributions | |
umn | -0.209 |
cient | -0.199 |
anwhile | -0.194 |
arch | -0.191 |
isode | -0.191 |
Token | opl |
Token ID | 20106 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
umn | +1.669 |
cient | +1.511 |
ophone | +1.448 |
arch | +1.443 |
isode | +1.371 |
Neg logit contributions | |
IELD | -3.131 |
hips | -3.034 |
Desire | -2.970 |
ymm | -2.944 |
suppose | -2.815 |
Token | ayer |
Token ID | 2794 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
umn | +4.039 |
cient | +3.676 |
isode | +3.543 |
arch | +3.522 |
ophone | +3.452 |
Neg logit contributions | |
IELD | -4.914 |
hips | -4.506 |
Desire | -4.394 |
ymm | -4.304 |
rounded | -4.168 |
Token | Input |
Token ID | 23412 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
umn | +2.255 |
cient | +2.137 |
arch | +2.041 |
anwhile | +2.022 |
isode | +2.010 |
Neg logit contributions | |
IELD | -1.815 |
hips | -1.707 |
ymm | -1.654 |
Desire | -1.612 |
suppose | -1.507 |
Token | Stream |
Token ID | 12124 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
IELD | +4.990 |
hips | +4.763 |
Desire | +4.529 |
ymm | +4.452 |
suppose | +4.164 |
Neg logit contributions | |
umn | -6.548 |
cient | -6.294 |
anwhile | -6.066 |
isode | -5.966 |
arch | -5.895 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
IELD | +2.474 |
hips | +2.364 |
Desire | +2.258 |
ymm | +2.243 |
suppose | +2.100 |
Neg logit contributions | |
umn | -2.800 |
cient | -2.658 |
anwhile | -2.549 |
arch | -2.516 |
isode | -2.516 |
Token | Make |
Token ID | 6889 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
IELD | +1.122 |
hips | +1.053 |
Desire | +0.992 |
ymm | +0.989 |
suppose | +0.918 |
Neg logit contributions | |
umn | -1.686 |
cient | -1.611 |
anwhile | -1.544 |
isode | -1.531 |
arch | -1.524 |
Token | sure |
Token ID | 1654 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
IELD | +0.312 |
hips | +0.288 |
ymm | +0.254 |
Desire | +0.250 |
suppose | +0.207 |
Neg logit contributions | |
umn | -1.000 |
cient | -0.965 |
anwhile | -0.936 |
isode | -0.929 |
arch | -0.926 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
IELD | +0.408 |
hips | +0.388 |
ymm | +0.370 |
Desire | +0.365 |
suppose | +0.339 |
Neg logit contributions | |
umn | -0.503 |
cient | -0.479 |
anwhile | -0.460 |
isode | -0.455 |
arch | -0.452 |
Token | competed |
Token ID | 32440 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
IELD | +1.341 |
hips | +1.275 |
Desire | +1.197 |
ymm | +1.197 |
suppose | +1.117 |
Neg logit contributions | |
umn | -1.522 |
cient | -1.464 |
isode | -1.381 |
anwhile | -1.373 |
arch | -1.372 |
Token | alongside |
Token ID | 7848 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
umn | +1.257 |
cient | +1.243 |
arch | +1.180 |
iously | +1.146 |
anwhile | +1.140 |
Neg logit contributions | |
IELD | -1.037 |
hips | -0.916 |
Desire | -0.909 |
ymm | -0.891 |
suppose | -0.820 |
Token | Chelsea |
Token ID | 12147 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
IELD | +0.465 |
hips | +0.440 |
ymm | +0.420 |
Desire | +0.404 |
suppose | +0.383 |
Neg logit contributions | |
umn | -0.638 |
cient | -0.612 |
arch | -0.588 |
anwhile | -0.587 |
isode | -0.574 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
IELD | +2.058 |
hips | +1.944 |
Desire | +1.851 |
ymm | +1.839 |
suppose | +1.695 |
Neg logit contributions | |
umn | -2.635 |
cient | -2.521 |
anwhile | -2.407 |
arch | -2.403 |
isode | -2.387 |
Token | Tottenham |
Token ID | 24272 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
umn | +4.212 |
cient | +4.066 |
arch | +3.934 |
anwhile | +3.906 |
ophone | +3.793 |
Neg logit contributions | |
IELD | -3.296 |
hips | -3.144 |
ymm | -3.050 |
Desire | -2.838 |
WARE | -2.717 |
Token | Hots |
Token ID | 41239 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
IELD | +5.986 |
hips | +5.845 |
Desire | +5.414 |
ymm | +5.325 |
suppose | +4.994 |
Neg logit contributions | |
umn | -9.083 |
cient | -8.642 |
anwhile | -8.415 |
isode | -8.272 |
arch | -8.079 |
Token | pur |
Token ID | 14225 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
hips | +7.312 |
IELD | +7.113 |
Desire | +6.560 |
ymm | +6.463 |
suppose | +6.123 |
Neg logit contributions | |
umn | -8.526 |
anwhile | -8.310 |
cient | -8.039 |
isode | -7.824 |
theless | -7.654 |
Token | for |
Token ID | 329 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
IELD | +2.975 |
hips | +2.802 |
Desire | +2.669 |
ymm | +2.643 |
suppose | +2.451 |
Neg logit contributions | |
umn | -3.953 |
cient | -3.798 |
anwhile | -3.633 |
isode | -3.597 |
arch | -3.591 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
umn | +1.294 |
cient | +1.252 |
isode | +1.174 |
arch | +1.172 |
ophone | +1.161 |
Neg logit contributions | |
IELD | -0.961 |
hips | -0.903 |
ymm | -0.861 |
Desire | -0.812 |
WARE | -0.776 |
Token | Premier |
Token ID | 9952 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
umn | +2.579 |
cient | +2.498 |
arch | +2.325 |
isode | +2.284 |
anwhile | +2.248 |
Neg logit contributions | |
IELD | -2.299 |
hips | -2.190 |
ymm | -2.093 |
Desire | -2.038 |
suppose | -1.928 |
Token | League |
Token ID | 4041 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
umn | +0.331 |
cient | +0.322 |
arch | +0.308 |
isode | +0.306 |
anwhile | +0.304 |
Neg logit contributions | |
IELD | -0.149 |
hips | -0.138 |
Desire | -0.126 |
ymm | -0.126 |
suppose | -0.112 |
Token | both |
Token ID | 1111 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
umn | +1.141 |
cient | +1.093 |
anwhile | +1.040 |
arch | +1.040 |
isode | +1.030 |
Neg logit contributions | |
IELD | -0.980 |
hips | -0.921 |
Desire | -0.883 |
ymm | -0.859 |
suppose | -0.821 |
Token | Shirt |
Token ID | 45180 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
umn | +0.733 |
cient | +0.705 |
arch | +0.669 |
anwhile | +0.665 |
isode | +0.659 |
Neg logit contributions | |
IELD | -0.515 |
hips | -0.482 |
Desire | -0.459 |
ymm | -0.453 |
suppose | -0.420 |
Token | Arm |
Token ID | 7057 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
IELD | +3.492 |
hips | +3.344 |
Desire | +3.188 |
ymm | +3.159 |
suppose | +2.984 |
Neg logit contributions | |
umn | -3.698 |
cient | -3.515 |
anwhile | -3.350 |
isode | -3.319 |
arch | -3.294 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
IELD | +7.435 |
hips | +7.146 |
Desire | +6.849 |
ymm | +6.833 |
suppose | +6.400 |
Neg logit contributions | |
umn | -6.733 |
cient | -6.433 |
anwhile | -6.181 |
isode | -6.032 |
arch | -5.921 |
Token | Training |
Token ID | 13614 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
IELD | +0.238 |
hips | +0.223 |
ymm | +0.209 |
Desire | +0.207 |
suppose | +0.193 |
Neg logit contributions | |
umn | -0.378 |
cient | -0.362 |
anwhile | -0.347 |
arch | -0.344 |
isode | -0.343 |
Token | Wear |
Token ID | 27539 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
IELD | +2.195 |
hips | +2.073 |
Desire | +1.922 |
ymm | +1.893 |
suppose | +1.732 |
Neg logit contributions | |
umn | -4.296 |
cient | -4.127 |
anwhile | -3.991 |
isode | -3.952 |
arch | -3.934 |
Token | partner |
Token ID | 5212 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
IELD | +5.480 |
hips | +5.301 |
Desire | +5.019 |
ymm | +4.950 |
suppose | +4.659 |
Neg logit contributions | |
umn | -6.349 |
cient | -6.083 |
anwhile | -5.847 |
isode | -5.779 |
arch | -5.675 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
IELD | +1.690 |
hips | +1.586 |
Desire | +1.514 |
ymm | +1.504 |
suppose | +1.406 |
Neg logit contributions | |
umn | -2.282 |
cient | -2.199 |
anwhile | -2.095 |
arch | -2.074 |
isode | -2.068 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
IELD | +0.647 |
hips | +0.609 |
ymm | +0.575 |
Desire | +0.568 |
suppose | +0.545 |
Neg logit contributions | |
umn | -0.927 |
cient | -0.891 |
arch | -0.842 |
isode | -0.841 |
anwhile | -0.836 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
IELD | +0.351 |
hips | +0.330 |
Desire | +0.311 |
ymm | +0.309 |
suppose | +0.284 |
Neg logit contributions | |
umn | -0.555 |
cient | -0.534 |
anwhile | -0.506 |
arch | -0.506 |
isode | -0.505 |
Token | The |
Token ID | 464 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
IELD | +0.402 |
hips | +0.387 |
Desire | +0.371 |
ymm | +0.367 |
suppose | +0.348 |
Neg logit contributions | |
umn | -0.362 |
cient | -0.343 |
anwhile | -0.326 |
isode | -0.322 |
arch | -0.319 |
Token | as |
Token ID | 292 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
IELD | +0.164 |
hips | +0.155 |
Desire | +0.152 |
ymm | +0.149 |
suppose | +0.142 |
Neg logit contributions | |
umn | -0.138 |
cient | -0.131 |
arch | -0.124 |
isode | -0.122 |
anwhile | -0.121 |
Token | well |
Token ID | 880 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
IELD | +0.966 |
hips | +0.910 |
Desire | +0.874 |
ymm | +0.854 |
suppose | +0.803 |
Neg logit contributions | |
umn | -1.172 |
cient | -1.120 |
anwhile | -1.064 |
isode | -1.054 |
arch | -1.051 |
Token | as |
Token ID | 355 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
IELD | +1.811 |
hips | +1.724 |
Desire | +1.622 |
ymm | +1.588 |
suppose | +1.475 |
Neg logit contributions | |
umn | -3.102 |
cient | -2.983 |
anwhile | -2.918 |
isode | -2.857 |
arch | -2.822 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
IELD | +2.345 |
hips | +2.227 |
Desire | +2.107 |
ymm | +2.090 |
suppose | +1.943 |
Neg logit contributions | |
umn | -3.142 |
cient | -3.004 |
anwhile | -2.888 |
isode | -2.852 |
arch | -2.830 |
Token | previously |
Token ID | 4271 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
IELD | +0.338 |
hips | +0.320 |
ymm | +0.305 |
Desire | +0.303 |
suppose | +0.284 |
Neg logit contributions | |
umn | -0.392 |
cient | -0.373 |
anwhile | -0.356 |
isode | -0.352 |
arch | -0.350 |
Token | announced |
Token ID | 3414 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
IELD | +0.951 |
hips | +0.906 |
Desire | +0.871 |
ymm | +0.859 |
suppose | +0.806 |
Neg logit contributions | |
umn | -0.938 |
cient | -0.894 |
anwhile | -0.845 |
isode | -0.836 |
arch | -0.832 |
Token | nominees |
Token ID | 26456 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
IELD | +5.869 |
hips | +5.767 |
Desire | +5.513 |
ymm | +5.213 |
suppose | +4.936 |
Neg logit contributions | |
umn | -7.547 |
cient | -7.240 |
anwhile | -7.113 |
isode | -6.907 |
arch | -6.870 |
Token | ) |
Token ID | 8 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
IELD | +3.263 |
hips | +3.150 |
Desire | +2.944 |
ymm | +2.892 |
suppose | +2.698 |
Neg logit contributions | |
umn | -4.939 |
cient | -4.735 |
anwhile | -4.581 |
isode | -4.508 |
arch | -4.460 |
Token | is |
Token ID | 318 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
IELD | +0.082 |
hips | +0.076 |
Desire | +0.074 |
ymm | +0.073 |
suppose | +0.068 |
Neg logit contributions | |
umn | -0.081 |
cient | -0.077 |
anwhile | -0.074 |
arch | -0.073 |
isode | -0.072 |
Token | below |
Token ID | 2174 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
umn | +1.136 |
cient | +1.091 |
arch | +1.044 |
anwhile | +1.037 |
isode | +1.010 |
Neg logit contributions | |
IELD | -1.003 |
hips | -0.914 |
Desire | -0.913 |
ymm | -0.880 |
Darling | -0.788 |
Token | . |
Token ID | 13 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
umn | +0.238 |
cient | +0.228 |
arch | +0.217 |
isode | +0.215 |
anwhile | +0.215 |
Neg logit contributions | |
IELD | -0.202 |
hips | -0.189 |
Desire | -0.183 |
ymm | -0.183 |
suppose | -0.169 |