Token | ors |
Token ID | 669 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
stein | +1.185 |
strings | +1.180 |
uterus | +1.124 |
chairs | +1.120 |
(£ | +1.100 |
Neg logit contributions | |
arij | -1.745 |
typ | -1.483 |
PHOTO | -1.344 |
onel | -1.321 |
adier | -1.271 |
Token | of |
Token ID | 286 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
stein | +1.493 |
strings | +1.465 |
uterus | +1.414 |
(£ | +1.411 |
chairs | +1.383 |
Neg logit contributions | |
arij | -2.493 |
typ | -2.112 |
PHOTO | -1.920 |
onel | -1.903 |
actionDate | -1.825 |
Token | the |
Token ID | 262 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
stein | +3.440 |
strings | +3.320 |
uterus | +3.304 |
(£ | +3.192 |
chairs | +3.157 |
Neg logit contributions | |
arij | -5.731 |
typ | -4.867 |
PHOTO | -4.477 |
onel | -4.464 |
actionDate | -4.238 |
Token | 60 |
Token ID | 3126 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
stein | +3.376 |
strings | +3.314 |
uterus | +3.303 |
(£ | +3.243 |
Shades | +3.107 |
Neg logit contributions | |
arij | -5.499 |
typ | -4.574 |
onel | -4.214 |
PHOTO | -4.155 |
actionDate | -4.037 |
Token | s |
Token ID | 82 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
stein | +1.390 |
strings | +1.367 |
uterus | +1.311 |
(£ | +1.289 |
chairs | +1.272 |
Neg logit contributions | |
arij | -2.881 |
typ | -2.475 |
PHOTO | -2.277 |
onel | -2.262 |
Picture | -2.173 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
stein | +2.776 |
strings | +2.681 |
(£ | +2.643 |
uterus | +2.625 |
chairs | +2.533 |
Neg logit contributions | |
arij | -5.360 |
typ | -4.504 |
onel | -4.181 |
PHOTO | -4.098 |
actionDate | -4.001 |
Token | 70 |
Token ID | 4317 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
(£ | +7.056 |
stein | +6.983 |
spirits | +6.947 |
horns | +6.779 |
strings | +6.742 |
Neg logit contributions | |
arij | -19.199 |
typ | -15.360 |
onel | -15.171 |
actionDate | -14.885 |
yip | -14.842 |
Token | s |
Token ID | 82 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
stein | +2.724 |
strings | +2.603 |
(£ | +2.423 |
chairs | +2.409 |
chair | +2.257 |
Neg logit contributions | |
arij | -7.592 |
typ | -6.395 |
PHOTO | -6.117 |
onel | -5.995 |
allery | -5.937 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
stein | +2.366 |
strings | +2.284 |
(£ | +2.255 |
uterus | +2.234 |
chairs | +2.155 |
Neg logit contributions | |
arij | -3.988 |
typ | -3.356 |
onel | -3.041 |
PHOTO | -3.027 |
actionDate | -2.927 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
arij | +1.356 |
typ | +1.151 |
PHOTO | +1.036 |
onel | +1.035 |
adier | +0.991 |
Neg logit contributions | |
stein | -0.874 |
strings | -0.863 |
uterus | -0.833 |
(£ | -0.815 |
chairs | -0.812 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
arij | +1.527 |
typ | +1.299 |
PHOTO | +1.180 |
onel | +1.169 |
Picture | +1.122 |
Neg logit contributions | |
stein | -0.958 |
strings | -0.945 |
uterus | -0.914 |
(£ | -0.890 |
chairs | -0.889 |
Token | risk |
Token ID | 2526 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
arij | +2.654 |
typ | +2.200 |
PHOTO | +1.924 |
onel | +1.912 |
Picture | +1.823 |
Neg logit contributions | |
stein | -2.669 |
strings | -2.628 |
uterus | -2.547 |
chairs | -2.535 |
(£ | -2.498 |
Token | of |
Token ID | 286 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
arij | +5.888 |
typ | +4.971 |
onel | +4.463 |
PHOTO | +4.431 |
ativity | +4.358 |
Neg logit contributions | |
stein | -4.443 |
strings | -4.401 |
uterus | -4.239 |
chairs | -4.208 |
chair | -4.136 |
Token | decreasing |
Token ID | 24030 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
arij | +5.250 |
typ | +4.498 |
PHOTO | +4.101 |
onel | +4.049 |
Picture | +3.941 |
Neg logit contributions | |
stein | -3.326 |
strings | -3.283 |
chairs | -3.143 |
uterus | -3.141 |
chair | -3.067 |
Token | , |
Token ID | 11 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
arij | +0.619 |
typ | +0.525 |
PHOTO | +0.474 |
onel | +0.469 |
adier | +0.449 |
Neg logit contributions | |
stein | -0.431 |
strings | -0.426 |
uterus | -0.414 |
(£ | -0.403 |
chairs | -0.402 |
Token | rather |
Token ID | 2138 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
strings | +4.021 |
stein | +3.990 |
uterus | +3.947 |
(£ | +3.730 |
yre | +3.598 |
Neg logit contributions | |
arij | -7.505 |
typ | -6.191 |
PHOTO | -5.667 |
onel | -5.569 |
adier | -5.553 |
Token | than |
Token ID | 621 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
arij | +2.164 |
typ | +1.900 |
PHOTO | +1.735 |
onel | +1.724 |
ativity | +1.673 |
Neg logit contributions | |
stein | -0.988 |
strings | -0.969 |
uterus | -0.928 |
chairs | -0.919 |
chair | -0.887 |
Token | increasing |
Token ID | 3649 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
stein | +6.966 |
(£ | +6.619 |
uterus | +6.547 |
strings | +6.243 |
feathers | +6.036 |
Neg logit contributions | |
arij | -17.945 |
typ | -14.424 |
actionDate | -13.954 |
onel | -13.563 |
allery | -13.430 |
Token | their |
Token ID | 511 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
arij | +0.540 |
typ | +0.459 |
PHOTO | +0.415 |
onel | +0.411 |
Picture | +0.394 |
Neg logit contributions | |
stein | -0.365 |
strings | -0.360 |
uterus | -0.349 |
chairs | -0.340 |
(£ | -0.340 |
Token | immersion |
Token ID | 36375 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
stein | +1.028 |
strings | +1.019 |
uterus | +0.994 |
(£ | +0.962 |
chairs | +0.950 |
Neg logit contributions | |
arij | -1.741 |
typ | -1.489 |
PHOTO | -1.348 |
onel | -1.339 |
adier | -1.289 |
Token | and |
Token ID | 290 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
strings | +1.370 |
stein | +1.366 |
uterus | +1.300 |
(£ | +1.298 |
chairs | +1.268 |
Neg logit contributions | |
arij | -2.193 |
typ | -1.847 |
PHOTO | -1.697 |
onel | -1.682 |
adier | -1.604 |
Token | engagement |
Token ID | 12352 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
stein | +1.680 |
strings | +1.660 |
uterus | +1.631 |
(£ | +1.581 |
chairs | +1.559 |
Neg logit contributions | |
arij | -2.820 |
typ | -2.386 |
PHOTO | -2.172 |
onel | -2.155 |
adier | -2.076 |
Token | he |
Token ID | 339 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
stein | +0.266 |
strings | +0.262 |
uterus | +0.257 |
(£ | +0.252 |
chairs | +0.248 |
Neg logit contributions | |
arij | -0.404 |
typ | -0.340 |
PHOTO | -0.309 |
onel | -0.307 |
ativity | -0.293 |
Token | warned |
Token ID | 7728 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
stein | +1.740 |
strings | +1.684 |
(£ | +1.625 |
uterus | +1.606 |
chairs | +1.595 |
Neg logit contributions | |
arij | -2.979 |
typ | -2.538 |
PHOTO | -2.308 |
onel | -2.275 |
actionDate | -2.258 |
Token | other |
Token ID | 584 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
stein | +3.899 |
(£ | +3.845 |
strings | +3.791 |
uterus | +3.714 |
horns | +3.538 |
Neg logit contributions | |
arij | -6.915 |
typ | -5.950 |
onel | -5.469 |
PHOTO | -5.428 |
adier | -5.191 |
Token | countries |
Token ID | 2678 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
stein | +2.833 |
strings | +2.792 |
(£ | +2.718 |
uterus | +2.663 |
chairs | +2.620 |
Neg logit contributions | |
arij | -5.999 |
typ | -5.120 |
onel | -4.752 |
PHOTO | -4.725 |
actionDate | -4.512 |
Token | may |
Token ID | 743 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
stein | +4.936 |
strings | +4.818 |
(£ | +4.732 |
uterus | +4.595 |
chairs | +4.317 |
Neg logit contributions | |
arij | -9.594 |
typ | -8.228 |
onel | -7.682 |
PHOTO | -7.405 |
ativity | -7.331 |
Token | follow |
Token ID | 1061 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
stein | +4.280 |
strings | +4.059 |
(£ | +4.045 |
uterus | +4.006 |
regenerate | +3.783 |
Neg logit contributions | |
arij | -8.303 |
typ | -7.251 |
onel | -6.546 |
PHOTO | -6.415 |
allery | -6.389 |
Token | Britain |
Token ID | 5491 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
(£ | +7.757 |
stein | +7.577 |
strings | +7.325 |
Fifa | +6.924 |
Farage | +6.889 |
Neg logit contributions | |
arij | -15.375 |
typ | -12.782 |
onel | -12.487 |
PHOTO | -11.402 |
cade | -11.288 |
Token | of |
Token ID | 286 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
stein | +0.985 |
strings | +0.974 |
uterus | +0.929 |
(£ | +0.927 |
chairs | +0.889 |
Neg logit contributions | |
arij | -2.002 |
typ | -1.710 |
onel | -1.589 |
PHOTO | -1.569 |
ativity | -1.507 |
Token | out |
Token ID | 503 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
stein | +3.635 |
strings | +3.516 |
(£ | +3.513 |
uterus | +3.474 |
chairs | +3.279 |
Neg logit contributions | |
arij | -6.125 |
typ | -5.250 |
PHOTO | -4.863 |
onel | -4.861 |
adier | -4.589 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
stein | +1.938 |
strings | +1.916 |
uterus | +1.802 |
(£ | +1.798 |
chairs | +1.765 |
Neg logit contributions | |
arij | -3.422 |
typ | -2.873 |
PHOTO | -2.671 |
onel | -2.649 |
adier | -2.577 |
Token | door |
Token ID | 3420 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
stein | +0.742 |
strings | +0.734 |
uterus | +0.723 |
(£ | +0.708 |
chairs | +0.688 |
Neg logit contributions | |
arij | -1.120 |
typ | -0.947 |
onel | -0.859 |
PHOTO | -0.854 |
adier | -0.821 |
Token | . |
Token ID | 13 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
stein | +3.312 |
strings | +3.167 |
(£ | +3.103 |
uterus | +3.085 |
chair | +2.847 |
Neg logit contributions | |
arij | -6.324 |
typ | -5.159 |
PHOTO | -4.903 |
onel | -4.869 |
actionDate | -4.785 |
Token | Sexual |
Token ID | 19536 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
arij | +0.494 |
typ | +0.411 |
onel | +0.372 |
PHOTO | +0.371 |
adier | +0.357 |
Neg logit contributions | |
stein | -0.320 |
strings | -0.315 |
uterus | -0.303 |
(£ | -0.299 |
chairs | -0.294 |
Token | orientation |
Token ID | 12852 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
stein | +0.592 |
strings | +0.575 |
uterus | +0.561 |
(£ | +0.539 |
chairs | +0.535 |
Neg logit contributions | |
arij | -1.338 |
typ | -1.143 |
PHOTO | -1.066 |
onel | -1.047 |
adier | -1.018 |
Token | has |
Token ID | 468 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
arij | +1.194 |
typ | +1.034 |
PHOTO | +0.946 |
onel | +0.937 |
Picture | +0.904 |
Neg logit contributions | |
stein | -0.606 |
strings | -0.597 |
uterus | -0.576 |
chairs | -0.557 |
(£ | -0.557 |
Token | nothing |
Token ID | 2147 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
arij | +0.379 |
typ | +0.322 |
PHOTO | +0.292 |
onel | +0.289 |
Picture | +0.278 |
Neg logit contributions | |
stein | -0.242 |
strings | -0.240 |
uterus | -0.234 |
(£ | -0.226 |
chairs | -0.226 |
Token | to |
Token ID | 284 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
strings | +4.564 |
stein | +4.521 |
uterus | +4.421 |
(£ | +4.255 |
chairs | +4.073 |
Neg logit contributions | |
arij | -8.589 |
typ | -7.285 |
PHOTO | -6.797 |
onel | -6.558 |
chel | -6.483 |
Token | do |
Token ID | 466 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
stein | +5.784 |
uterus | +5.611 |
strings | +5.230 |
(£ | +5.150 |
figure | +5.149 |
Neg logit contributions | |
arij | -16.872 |
typ | -14.430 |
PHOTO | -13.308 |
chel | -13.124 |
onel | -12.837 |
Token | with |
Token ID | 351 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
stein | +1.003 |
strings | +0.984 |
uterus | +0.917 |
(£ | +0.886 |
chairs | +0.868 |
Neg logit contributions | |
arij | -4.272 |
typ | -3.725 |
PHOTO | -3.508 |
onel | -3.458 |
allery | -3.403 |
Token | gender |
Token ID | 5279 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
arij | +2.288 |
typ | +1.964 |
PHOTO | +1.786 |
onel | +1.771 |
Picture | +1.703 |
Neg logit contributions | |
stein | -1.344 |
strings | -1.325 |
uterus | -1.280 |
chairs | -1.245 |
(£ | -1.244 |
Token | identity |
Token ID | 5369 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
arij | +2.788 |
typ | +2.423 |
PHOTO | +2.184 |
onel | +2.164 |
Picture | +2.087 |
Neg logit contributions | |
stein | -1.671 |
strings | -1.645 |
uterus | -1.595 |
chairs | -1.547 |
(£ | -1.547 |
Token | or |
Token ID | 393 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
arij | +5.950 |
typ | +5.181 |
PHOTO | +4.537 |
onel | +4.494 |
ativity | +4.428 |
Neg logit contributions | |
stein | -4.808 |
strings | -4.738 |
uterus | -4.588 |
chairs | -4.533 |
ドラ | -4.500 |
Token | ( |
Token ID | 357 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
arij | +0.538 |
typ | +0.454 |
PHOTO | +0.411 |
onel | +0.409 |
adier | +0.390 |
Neg logit contributions | |
stein | -0.356 |
strings | -0.347 |
uterus | -0.339 |
(£ | -0.332 |
chairs | -0.329 |
Token | HP |
Token ID | 14082 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
stein | +0.516 |
strings | +0.509 |
uterus | +0.491 |
chairs | +0.484 |
chair | +0.482 |
Neg logit contributions | |
arij | -0.666 |
typ | -0.543 |
PHOTO | -0.495 |
onel | -0.488 |
adier | -0.466 |
Token | ) |
Token ID | 8 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
arij | +1.201 |
typ | +1.026 |
PHOTO | +0.932 |
onel | +0.923 |
Picture | +0.887 |
Neg logit contributions | |
stein | -0.739 |
strings | -0.729 |
uterus | -0.707 |
(£ | -0.686 |
chairs | -0.686 |
Token | from |
Token ID | 422 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
stein | +0.812 |
strings | +0.792 |
uterus | +0.774 |
(£ | +0.756 |
chairs | +0.753 |
Neg logit contributions | |
arij | -1.300 |
typ | -1.096 |
PHOTO | -0.990 |
onel | -0.990 |
adier | -0.950 |
Token | 1964 |
Token ID | 17575 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
stein | +0.521 |
strings | +0.508 |
uterus | +0.503 |
(£ | +0.493 |
chairs | +0.484 |
Neg logit contributions | |
arij | -0.685 |
typ | -0.570 |
PHOTO | -0.514 |
onel | -0.508 |
adier | -0.483 |
Token | to |
Token ID | 284 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
arij | +3.859 |
typ | +3.263 |
PHOTO | +2.941 |
onel | +2.902 |
Picture | +2.796 |
Neg logit contributions | |
strings | -2.819 |
stein | -2.806 |
uterus | -2.712 |
chairs | -2.641 |
(£ | -2.609 |
Token | 1977 |
Token ID | 15589 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
stein | +7.806 |
(£ | +7.509 |
uterus | +7.330 |
Slate | +6.918 |
Seas | +6.862 |
Neg logit contributions | |
arij | -14.609 |
typ | -11.759 |
yip | -11.159 |
allery | -10.867 |
PHOTO | -10.784 |
Token | . |
Token ID | 13 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
arij | +0.346 |
typ | +0.294 |
PHOTO | +0.267 |
onel | +0.264 |
Picture | +0.253 |
Neg logit contributions | |
stein | -0.225 |
strings | -0.222 |
uterus | -0.216 |
(£ | -0.209 |
chairs | -0.209 |
Token | Today |
Token ID | 6288 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
stein | +2.600 |
strings | +2.542 |
(£ | +2.482 |
uterus | +2.479 |
chairs | +2.399 |
Neg logit contributions | |
arij | -4.080 |
typ | -3.379 |
onel | -3.086 |
PHOTO | -2.956 |
ativity | -2.952 |
Token | one |
Token ID | 530 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
stein | +3.593 |
(£ | +3.432 |
strings | +3.424 |
uterus | +3.419 |
chair | +3.289 |
Neg logit contributions | |
arij | -5.532 |
typ | -4.565 |
onel | -4.179 |
PHOTO | -4.110 |
actionDate | -4.016 |
Token | of |
Token ID | 286 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
stein | +2.860 |
strings | +2.786 |
uterus | +2.718 |
(£ | +2.644 |
chairs | +2.623 |
Neg logit contributions | |
arij | -5.623 |
typ | -4.833 |
PHOTO | -4.428 |
onel | -4.373 |
adier | -4.225 |
Token | essentially |
Token ID | 6986 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
stein | +2.321 |
strings | +2.299 |
uterus | +2.246 |
(£ | +2.183 |
chairs | +2.139 |
Neg logit contributions | |
arij | -3.911 |
typ | -3.262 |
PHOTO | -2.970 |
onel | -2.959 |
adier | -2.846 |
Token | that |
Token ID | 326 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
arij | +4.396 |
typ | +3.808 |
PHOTO | +3.426 |
onel | +3.389 |
Picture | +3.278 |
Neg logit contributions | |
stein | -2.961 |
strings | -2.940 |
uterus | -2.823 |
chairs | -2.781 |
(£ | -2.730 |
Token | his |
Token ID | 465 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
arij | +1.851 |
typ | +1.550 |
PHOTO | +1.387 |
onel | +1.372 |
Picture | +1.311 |
Neg logit contributions | |
stein | -1.509 |
strings | -1.493 |
uterus | -1.453 |
chairs | -1.419 |
(£ | -1.416 |
Token | ends |
Token ID | 5645 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
stein | +0.388 |
strings | +0.383 |
uterus | +0.375 |
(£ | +0.363 |
chairs | +0.358 |
Neg logit contributions | |
arij | -0.637 |
typ | -0.542 |
PHOTO | -0.492 |
onel | -0.489 |
ativity | -0.468 |
Token | justify |
Token ID | 12051 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
stein | +5.198 |
(£ | +5.103 |
strings | +4.950 |
uterus | +4.670 |
chair | +4.660 |
Neg logit contributions | |
arij | -11.921 |
typ | -10.095 |
PHOTO | -9.235 |
allery | -8.910 |
onel | -8.901 |
Token | his |
Token ID | 465 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
stein | +5.393 |
strings | +5.321 |
(£ | +5.278 |
uterus | +5.189 |
chairs | +5.072 |
Neg logit contributions | |
arij | -8.284 |
typ | -7.091 |
PHOTO | -6.399 |
onel | -6.284 |
adier | -6.143 |
Token | means |
Token ID | 1724 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
uterus | +6.084 |
(£ | +6.063 |
stein | +5.733 |
horns | +5.676 |
digs | +5.516 |
Neg logit contributions | |
arij | -16.560 |
typ | -14.099 |
onel | -12.867 |
PHOTO | -12.751 |
yip | -12.645 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
arij | +1.160 |
typ | +0.979 |
PHOTO | +0.884 |
onel | +0.875 |
Picture | +0.837 |
Neg logit contributions | |
stein | -0.826 |
strings | -0.816 |
uterus | -0.792 |
(£ | -0.773 |
chairs | -0.771 |
Token | not |
Token ID | 407 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
stein | +1.241 |
strings | +1.222 |
uterus | +1.199 |
(£ | +1.166 |
chairs | +1.139 |
Neg logit contributions | |
arij | -2.087 |
typ | -1.750 |
PHOTO | -1.600 |
onel | -1.589 |
adier | -1.531 |
Token | a |
Token ID | 257 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
arij | +1.709 |
typ | +1.442 |
PHOTO | +1.300 |
onel | +1.286 |
Picture | +1.230 |
Neg logit contributions | |
stein | -1.237 |
strings | -1.222 |
uterus | -1.188 |
(£ | -1.158 |
chairs | -1.155 |
Token | bad |
Token ID | 2089 |
Feature activation | +9.86e-05 |
Pos logit contributions | |
arij | +0.404 |
typ | +0.342 |
PHOTO | +0.312 |
onel | +0.310 |
adier | +0.297 |
Neg logit contributions | |
stein | -0.257 |
strings | -0.252 |
uterus | -0.246 |
(£ | -0.238 |
chairs | -0.236 |
Token | s |
Token ID | 82 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
stein | +0.013 |
strings | +0.013 |
uterus | +0.012 |
chairs | +0.012 |
(£ | +0.012 |
Neg logit contributions | |
arij | -0.027 |
typ | -0.024 |
PHOTO | -0.022 |
onel | -0.022 |
Picture | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
stein | +0.921 |
strings | +0.888 |
uterus | +0.862 |
(£ | +0.848 |
chairs | +0.829 |
Neg logit contributions | |
arij | -1.598 |
typ | -1.354 |
PHOTO | -1.239 |
onel | -1.235 |
ativity | -1.187 |
Token | � |
Token ID | 447 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
stein | +1.392 |
strings | +1.339 |
uterus | +1.309 |
(£ | +1.272 |
chairs | +1.268 |
Neg logit contributions | |
arij | -2.267 |
typ | -1.901 |
PHOTO | -1.737 |
onel | -1.723 |
chel | -1.671 |
Token | � |
Token ID | 251 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
stein | +0.671 |
strings | +0.656 |
uterus | +0.633 |
chairs | +0.619 |
(£ | +0.612 |
Neg logit contributions | |
arij | -0.944 |
typ | -0.800 |
PHOTO | -0.717 |
onel | -0.713 |
chel | -0.685 |
Token | Ad |
Token ID | 1215 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
arij | +1.598 |
typ | +1.302 |
PHOTO | +1.142 |
onel | +1.128 |
Picture | +1.066 |
Neg logit contributions | |
stein | -1.710 |
strings | -1.696 |
uterus | -1.657 |
(£ | -1.621 |
chairs | -1.621 |
Token | el |
Token ID | 417 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
stein | +2.295 |
strings | +2.178 |
chairs | +2.061 |
(£ | +2.058 |
chair | +2.040 |
Neg logit contributions | |
arij | -2.718 |
typ | -2.280 |
PHOTO | -2.128 |
actionDate | -1.956 |
Picture | -1.955 |
Token | stein |
Token ID | 5714 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
stein | +2.818 |
strings | -0.188 |
chair | -0.742 |
chairs | -0.942 |
figure | -0.976 |
Neg logit contributions | |
arij | -22.481 |
PHOTO | -19.641 |
conflic | -19.409 |
typ | -19.372 |
ailability | -19.344 |
Token | said |
Token ID | 531 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
arij | +2.376 |
typ | +2.009 |
PHOTO | +1.811 |
onel | +1.792 |
Picture | +1.715 |
Neg logit contributions | |
stein | -1.717 |
strings | -1.703 |
uterus | -1.656 |
chairs | -1.610 |
(£ | -1.609 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-04 |
Pos logit contributions | |
stein | +3.190 |
strings | +3.065 |
(£ | +2.947 |
uterus | +2.935 |
chair | +2.819 |
Neg logit contributions | |
arij | -5.267 |
typ | -4.453 |
PHOTO | -4.113 |
onel | -4.012 |
Picture | -3.874 |
Token | � |
Token ID | 564 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
arij | +0.008 |
typ | +0.007 |
onel | +0.006 |
PHOTO | +0.006 |
ativity | +0.006 |
Neg logit contributions | |
stein | -0.005 |
strings | -0.005 |
uterus | -0.005 |
(£ | -0.005 |
chairs | -0.005 |
Token | � |
Token ID | 250 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
stein | +0.801 |
strings | +0.781 |
uterus | +0.737 |
chairs | +0.714 |
(£ | +0.713 |
Neg logit contributions | |
arij | -1.645 |
typ | -1.429 |
PHOTO | -1.311 |
onel | -1.302 |
chel | -1.262 |
Token | or |
Token ID | 393 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
stein | +3.665 |
strings | +3.622 |
(£ | +3.500 |
uterus | +3.400 |
chairs | +3.240 |
Neg logit contributions | |
arij | -7.465 |
typ | -6.243 |
PHOTO | -5.839 |
onel | -5.749 |
adier | -5.589 |
Token | ' |
Token ID | 705 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
(£ | +6.701 |
strings | +6.625 |
stein | +6.540 |
uterus | +6.446 |
¶ | +6.190 |
Neg logit contributions | |
arij | -13.303 |
typ | -11.075 |
onel | -10.324 |
PHOTO | -10.122 |
allery | -10.098 |
Token | model |
Token ID | 19849 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
strings | +5.508 |
stein | +5.419 |
figure | +5.042 |
chairs | +5.028 |
chair | +4.969 |
Neg logit contributions | |
arij | -7.563 |
typ | -5.895 |
PHOTO | -5.836 |
onel | -5.678 |
ativity | -5.554 |
Token | ines |
Token ID | 1127 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
strings | +2.827 |
stein | +2.793 |
chairs | +2.532 |
uterus | +2.527 |
(£ | +2.507 |
Neg logit contributions | |
arij | -7.310 |
typ | -6.339 |
PHOTO | -5.957 |
onel | -5.809 |
Picture | -5.712 |
Token | ' |
Token ID | 6 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
strings | +3.644 |
stein | +3.629 |
(£ | +3.377 |
uterus | +3.344 |
chairs | +3.316 |
Neg logit contributions | |
arij | -7.387 |
typ | -6.213 |
PHOTO | -5.831 |
onel | -5.774 |
adier | -5.570 |
Token | is |
Token ID | 318 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
strings | +4.491 |
stein | +4.351 |
(£ | +4.158 |
uterus | +4.091 |
¶ | +3.915 |
Neg logit contributions | |
arij | -10.146 |
typ | -8.550 |
onel | -7.828 |
PHOTO | -7.827 |
adier | -7.754 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
stein | +6.862 |
(£ | +6.700 |
strings | +6.662 |
uterus | +6.612 |
horns | +6.121 |
Neg logit contributions | |
arij | -14.817 |
typ | -12.389 |
actionDate | -11.181 |
ativity | -11.162 |
adier | -11.160 |
Token | no |
Token ID | 645 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
strings | +5.440 |
(£ | +5.323 |
stein | +5.311 |
¶ | +4.824 |
Shades | +4.721 |
Neg logit contributions | |
arij | -12.121 |
typ | -10.083 |
PHOTO | -9.641 |
actionDate | -9.391 |
onel | -9.340 |
Token | lines |
Token ID | 3951 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
strings | +0.371 |
stein | +0.370 |
uterus | +0.355 |
(£ | +0.347 |
chairs | +0.342 |
Neg logit contributions | |
arij | -0.545 |
typ | -0.460 |
PHOTO | -0.420 |
onel | -0.416 |
ativity | -0.395 |
Token | are |
Token ID | 389 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
strings | +1.263 |
stein | +1.263 |
uterus | +1.197 |
(£ | +1.188 |
chairs | +1.144 |
Neg logit contributions | |
arij | -2.504 |
typ | -2.170 |
PHOTO | -1.995 |
onel | -1.971 |
adier | -1.896 |
Token | checked |
Token ID | 10667 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
arij | +4.038 |
typ | +3.447 |
PHOTO | +3.121 |
onel | +3.086 |
Picture | +2.954 |
Neg logit contributions | |
stein | -2.684 |
strings | -2.634 |
uterus | -2.559 |
chairs | -2.538 |
chair | -2.490 |
Token | Kan |
Token ID | 14248 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
arij | +3.247 |
typ | +2.757 |
PHOTO | +2.494 |
onel | +2.464 |
Picture | +2.394 |
Neg logit contributions | |
stein | -2.195 |
strings | -2.191 |
uterus | -2.111 |
chairs | -2.071 |
(£ | -2.049 |
Token | asis |
Token ID | 17765 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
stein | +0.689 |
strings | +0.673 |
uterus | +0.647 |
(£ | +0.637 |
chairs | +0.633 |
Neg logit contributions | |
arij | -0.833 |
typ | -0.698 |
PHOTO | -0.632 |
onel | -0.606 |
adier | -0.587 |
Token | in |
Token ID | 287 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
arij | +2.931 |
typ | +2.507 |
PHOTO | +2.265 |
onel | +2.250 |
Picture | +2.165 |
Neg logit contributions | |
stein | -1.850 |
strings | -1.832 |
uterus | -1.772 |
chairs | -1.729 |
(£ | -1.723 |
Token | Un |
Token ID | 791 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
stein | +2.160 |
strings | +2.146 |
uterus | +2.078 |
(£ | +2.013 |
chairs | +2.005 |
Neg logit contributions | |
arij | -3.195 |
typ | -2.674 |
PHOTO | -2.417 |
onel | -2.388 |
chel | -2.300 |
Token | break |
Token ID | 9032 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
stein | +1.422 |
strings | +1.391 |
chairs | +1.306 |
uterus | +1.299 |
chair | +1.297 |
Neg logit contributions | |
arij | -2.620 |
typ | -2.196 |
PHOTO | -2.073 |
onel | -2.020 |
adier | -1.976 |
Token | able |
Token ID | 540 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
stein | +3.318 |
strings | +3.227 |
chair | +2.905 |
uterus | +2.885 |
(£ | +2.877 |
Neg logit contributions | |
arij | -9.046 |
typ | -7.732 |
PHOTO | -7.245 |
onel | -6.996 |
adier | -6.988 |
Token | Kim |
Token ID | 6502 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
(£ | +4.212 |
strings | +4.057 |
uterus | +3.993 |
stein | +3.955 |
chair | +3.774 |
Neg logit contributions | |
arij | -18.026 |
typ | -16.556 |
yip | -15.948 |
chel | -15.199 |
actionDate | -15.074 |
Token | my |
Token ID | 1820 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
arij | +2.946 |
typ | +2.469 |
PHOTO | +2.209 |
onel | +2.173 |
Picture | +2.079 |
Neg logit contributions | |
strings | -2.721 |
stein | -2.714 |
uterus | -2.663 |
chairs | -2.590 |
(£ | -2.590 |
Token | Schmidt |
Token ID | 24740 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
arij | +0.666 |
typ | +0.578 |
PHOTO | +0.530 |
onel | +0.525 |
Picture | +0.507 |
Neg logit contributions | |
stein | -0.326 |
strings | -0.320 |
uterus | -0.309 |
chairs | -0.299 |
(£ | -0.298 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
stein | +1.612 |
strings | +1.585 |
uterus | +1.536 |
(£ | +1.500 |
chairs | +1.488 |
Neg logit contributions | |
arij | -2.697 |
typ | -2.263 |
PHOTO | -2.044 |
onel | -2.030 |
adier | -1.959 |
Token | or |
Token ID | 393 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
arij | +0.163 |
typ | +0.137 |
PHOTO | +0.124 |
onel | +0.122 |
adier | +0.117 |
Neg logit contributions | |
stein | -0.113 |
strings | -0.111 |
uterus | -0.109 |
(£ | -0.105 |
chairs | -0.105 |
Token | Think |
Token ID | 22073 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
stein | +0.219 |
strings | +0.216 |
uterus | +0.206 |
chairs | +0.204 |
(£ | +0.203 |
Neg logit contributions | |
arij | -0.275 |
typ | -0.225 |
PHOTO | -0.205 |
onel | -0.201 |
adier | -0.194 |
Token | about |
Token ID | 546 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
arij | +1.012 |
typ | +0.859 |
PHOTO | +0.781 |
onel | +0.776 |
adier | +0.744 |
Neg logit contributions | |
stein | -0.656 |
strings | -0.645 |
uterus | -0.625 |
chairs | -0.602 |
(£ | -0.602 |
Token | it |
Token ID | 340 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
arij | +3.639 |
typ | +3.060 |
PHOTO | +2.743 |
onel | +2.697 |
Picture | +2.600 |
Neg logit contributions | |
stein | -2.987 |
strings | -2.957 |
uterus | -2.870 |
chairs | -2.824 |
(£ | -2.816 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
arij | +2.586 |
typ | +2.193 |
PHOTO | +1.981 |
onel | +1.958 |
Picture | +1.881 |
Neg logit contributions | |
stein | -1.801 |
strings | -1.780 |
uterus | -1.728 |
chairs | -1.685 |
(£ | -1.683 |
Token | - |
Token ID | 532 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
arij | +2.050 |
typ | +1.735 |
PHOTO | +1.567 |
onel | +1.557 |
adier | +1.492 |
Neg logit contributions | |
stein | -1.364 |
strings | -1.345 |
uterus | -1.305 |
(£ | -1.270 |
chairs | -1.265 |
Token | December |
Token ID | 3426 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
stein | +3.050 |
strings | +2.993 |
(£ | +2.886 |
uterus | +2.862 |
yre | +2.717 |
Neg logit contributions | |
arij | -4.119 |
typ | -3.310 |
onel | -3.001 |
chel | -2.923 |
PHOTO | -2.920 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
stein | +4.349 |
strings | +4.115 |
(£ | +3.792 |
¶ | +3.686 |
Shades | +3.642 |
Neg logit contributions | |
arij | -18.357 |
typ | -15.454 |
ailability | -15.329 |
allery | -15.136 |
yip | -14.724 |
Token | , |
Token ID | 11 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
arij | +2.932 |
typ | +2.505 |
PHOTO | +2.262 |
onel | +2.236 |
Picture | +2.150 |
Neg logit contributions | |
stein | -1.985 |
strings | -1.967 |
uterus | -1.922 |
chairs | -1.861 |
(£ | -1.854 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
stein | +2.503 |
strings | +2.458 |
(£ | +2.455 |
uterus | +2.401 |
Shades | +2.097 |
Neg logit contributions | |
arij | -11.604 |
typ | -10.008 |
onel | -9.409 |
allery | -9.253 |
cade | -9.132 |
Token | Que |
Token ID | 15681 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
stein | +0.536 |
strings | +0.530 |
uterus | +0.491 |
chairs | +0.486 |
(£ | +0.482 |
Neg logit contributions | |
arij | -1.077 |
typ | -0.912 |
PHOTO | -0.844 |
onel | -0.831 |
adier | -0.812 |
Token | ers |
Token ID | 364 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
stein | +1.028 |
strings | +1.027 |
chairs | +0.951 |
(£ | +0.941 |
uterus | +0.934 |
Neg logit contributions | |
arij | -2.655 |
typ | -2.344 |
PHOTO | -2.183 |
onel | -2.126 |
Picture | -2.083 |
Token | of |
Token ID | 286 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
stein | +2.172 |
strings | +2.106 |
uterus | +2.053 |
(£ | +2.004 |
chairs | +1.970 |
Neg logit contributions | |
arij | -4.162 |
typ | -3.593 |
PHOTO | -3.292 |
onel | -3.246 |
adier | -3.137 |
Token | many |
Token ID | 867 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
arij | +1.335 |
typ | +1.125 |
PHOTO | +1.013 |
onel | +1.002 |
Picture | +0.959 |
Neg logit contributions | |
stein | -0.997 |
strings | -0.986 |
uterus | -0.960 |
chairs | -0.934 |
(£ | -0.933 |
Token | economic |
Token ID | 3034 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
stein | +2.269 |
strings | +2.238 |
uterus | +2.154 |
(£ | +2.150 |
chairs | +2.077 |
Neg logit contributions | |
arij | -3.794 |
typ | -3.191 |
PHOTO | -2.898 |
onel | -2.891 |
ativity | -2.784 |
Token | indicators |
Token ID | 21337 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
stein | +3.999 |
strings | +3.962 |
(£ | +3.783 |
uterus | +3.776 |
chairs | +3.672 |
Neg logit contributions | |
arij | -5.228 |
typ | -4.254 |
PHOTO | -3.826 |
onel | -3.772 |
actionDate | -3.707 |
Token | that |
Token ID | 326 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
stein | +0.862 |
strings | +0.844 |
uterus | +0.816 |
(£ | +0.804 |
chairs | +0.783 |
Neg logit contributions | |
arij | -1.536 |
typ | -1.310 |
PHOTO | -1.197 |
onel | -1.196 |
adier | -1.142 |
Token | inter |
Token ID | 987 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
stein | +0.994 |
strings | +0.959 |
uterus | +0.935 |
(£ | +0.921 |
chairs | +0.899 |
Neg logit contributions | |
arij | -1.890 |
typ | -1.624 |
onel | -1.471 |
PHOTO | -1.463 |
adier | -1.412 |
Token | play |
Token ID | 1759 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
stein | +9.056 |
strings | +8.701 |
figure | +8.502 |
chair | +8.298 |
¶ | +8.267 |
Neg logit contributions | |
arij | -12.528 |
typ | -10.215 |
PHOTO | -9.474 |
EVA | -9.193 |
onel | -9.134 |
Token | to |
Token ID | 284 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
arij | +1.045 |
typ | +0.913 |
PHOTO | +0.843 |
onel | +0.836 |
Picture | +0.809 |
Neg logit contributions | |
stein | -0.412 |
strings | -0.405 |
uterus | -0.388 |
(£ | -0.372 |
chairs | -0.372 |
Token | create |
Token ID | 2251 |
Feature activation | +3.04e-04 |
Pos logit contributions | |
arij | +2.111 |
typ | +1.798 |
PHOTO | +1.631 |
onel | +1.614 |
Picture | +1.549 |
Neg logit contributions | |
stein | -1.373 |
strings | -1.357 |
uterus | -1.315 |
chairs | -1.279 |
(£ | -1.278 |
Token | a |
Token ID | 257 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
stein | +0.002 |
strings | +0.002 |
uterus | +0.002 |
(£ | +0.002 |
chairs | +0.002 |
Neg logit contributions | |
arij | -0.003 |
typ | -0.002 |
PHOTO | -0.002 |
onel | -0.002 |
adier | -0.002 |
Token | judgement |
Token ID | 23071 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
stein | +0.192 |
strings | +0.188 |
uterus | +0.185 |
(£ | +0.179 |
chairs | +0.175 |
Neg logit contributions | |
arij | -0.323 |
typ | -0.272 |
onel | -0.249 |
PHOTO | -0.248 |
adier | -0.238 |
Token | between |
Token ID | 1022 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
(£ | +2.918 |
stein | +2.887 |
strings | +2.825 |
£ | +2.691 |
uterus | +2.659 |
Neg logit contributions | |
arij | -6.833 |
typ | -5.772 |
onel | -5.398 |
PHOTO | -5.363 |
actionDate | -5.272 |
Token | £ |
Token ID | 4248 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
(£ | +1.646 |
£ | +1.592 |
stein | +1.427 |
strings | +1.397 |
uterus | +1.094 |
Neg logit contributions | |
arij | -11.783 |
typ | -10.219 |
onel | -9.708 |
actionDate | -9.698 |
PHOTO | -9.615 |
Token | 200 |
Token ID | 2167 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
stein | +0.225 |
strings | +0.222 |
(£ | +0.211 |
chairs | +0.209 |
uterus | +0.209 |
Neg logit contributions | |
arij | -0.302 |
typ | -0.245 |
PHOTO | -0.224 |
onel | -0.222 |
ativity | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
(£ | +4.497 |
stein | +4.370 |
strings | +4.226 |
uterus | +4.085 |
chairs | +4.017 |
Neg logit contributions | |
arij | -8.695 |
typ | -7.523 |
PHOTO | -6.887 |
onel | -6.834 |
adier | -6.561 |
Token | 000 |
Token ID | 830 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
stein | +2.186 |
(£ | +2.182 |
strings | +2.001 |
uterus | +1.700 |
chair | +1.696 |
Neg logit contributions | |
arij | -11.971 |
typ | -10.462 |
PHOTO | -9.896 |
onel | -9.724 |
ativity | -9.606 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
stein | +2.390 |
(£ | +2.371 |
strings | +2.310 |
uterus | +2.260 |
chairs | +2.190 |
Neg logit contributions | |
arij | -4.679 |
typ | -4.004 |
onel | -3.660 |
PHOTO | -3.652 |
adier | -3.534 |
Token | £ |
Token ID | 4248 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
£ | +4.748 |
(£ | +4.479 |
stein | +3.913 |
strings | +3.410 |
uterus | +3.392 |
Neg logit contributions | |
arij | -17.719 |
typ | -14.985 |
actionDate | -14.707 |
onel | -14.414 |
PHOTO | -14.050 |
Token | 700 |
Token ID | 9879 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
stein | +5.091 |
strings | +4.878 |
(£ | +4.649 |
chair | +4.549 |
chairs | +4.363 |
Neg logit contributions | |
arij | -9.519 |
typ | -7.272 |
onel | -7.196 |
PHOTO | -6.982 |
allery | -6.959 |
Token | , |
Token ID | 11 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
stein | +1.992 |
(£ | +1.960 |
strings | +1.916 |
uterus | +1.768 |
chairs | +1.758 |
Neg logit contributions | |
arij | -4.094 |
typ | -3.469 |
PHOTO | -3.174 |
onel | -3.171 |
allery | -3.138 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
stein | +1.590 |
strings | +1.538 |
(£ | +1.492 |
figure | +1.274 |
uterus | +1.270 |
Neg logit contributions | |
arij | -7.267 |
typ | -6.381 |
PHOTO | -5.951 |
onel | -5.871 |
allery | -5.866 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
stein | +0.894 |
(£ | +0.874 |
strings | +0.867 |
uterus | +0.847 |
chairs | +0.821 |
Neg logit contributions | |
arij | -1.394 |
typ | -1.181 |
PHOTO | -1.066 |
onel | -1.063 |
adier | -1.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-04 |
Pos logit contributions | |
stein | +2.243 |
strings | +2.186 |
uterus | +2.113 |
(£ | +2.097 |
chairs | +1.998 |
Neg logit contributions | |
arij | -3.703 |
typ | -3.138 |
onel | -2.855 |
PHOTO | -2.825 |
adier | -2.734 |
Token |
|
Token ID | 198 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
arij | +0.004 |
typ | +0.004 |
PHOTO | +0.003 |
onel | +0.003 |
adier | +0.003 |
Neg logit contributions | |
stein | -0.003 |
strings | -0.003 |
uterus | -0.003 |
(£ | -0.002 |
chairs | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
stein | +0.415 |
strings | +0.407 |
(£ | +0.383 |
uterus | +0.382 |
chairs | +0.378 |
Neg logit contributions | |
arij | -0.749 |
typ | -0.628 |
PHOTO | -0.575 |
onel | -0.574 |
allery | -0.554 |
Token | Qu |
Token ID | 4507 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
stein | +2.060 |
strings | +2.030 |
chair | +1.898 |
chairs | +1.898 |
uterus | +1.883 |
Neg logit contributions | |
arij | -2.902 |
typ | -2.341 |
PHOTO | -2.175 |
onel | -2.129 |
adier | -2.046 |
Token | inn |
Token ID | 3732 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
stein | +2.926 |
strings | +2.350 |
yre | +2.171 |
chair | +2.139 |
chairs | +2.089 |
Neg logit contributions | |
arij | -11.332 |
typ | -10.180 |
actionDate | -9.475 |
PHOTO | -9.324 |
onel | -9.195 |
Token | ip |
Token ID | 541 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
stein | +0.265 |
strings | +0.257 |
uterus | +0.246 |
(£ | +0.242 |
chairs | +0.240 |
Neg logit contributions | |
arij | -0.439 |
typ | -0.375 |
PHOTO | -0.343 |
onel | -0.339 |
Picture | -0.325 |
Token | iac |
Token ID | 9607 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
stein | +10.237 |
strings | +8.976 |
yre | +8.912 |
idis | +8.755 |
(£ | +8.617 |
Neg logit contributions | |
arij | -11.459 |
typ | -9.314 |
PHOTO | -9.160 |
allery | -8.908 |
Picture | -8.827 |
Token | also |
Token ID | 635 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
stein | +2.924 |
strings | +2.792 |
uterus | +2.748 |
(£ | +2.678 |
chairs | +2.598 |
Neg logit contributions | |
arij | -5.938 |
typ | -5.046 |
onel | -4.640 |
PHOTO | -4.536 |
actionDate | -4.501 |
Token | conducted |
Token ID | 5952 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
stein | +0.083 |
strings | +0.081 |
uterus | +0.078 |
(£ | +0.076 |
chairs | +0.076 |
Neg logit contributions | |
arij | -0.161 |
typ | -0.139 |
PHOTO | -0.127 |
onel | -0.126 |
adier | -0.121 |
Token | a |
Token ID | 257 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
arij | +0.256 |
typ | +0.214 |
PHOTO | +0.192 |
onel | +0.190 |
adier | +0.181 |
Neg logit contributions | |
stein | -0.204 |
strings | -0.201 |
uterus | -0.196 |
(£ | -0.191 |
chairs | -0.190 |
Token | state |
Token ID | 1181 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
stein | +0.245 |
strings | +0.240 |
uterus | +0.235 |
(£ | +0.228 |
chairs | +0.223 |
Neg logit contributions | |
arij | -0.408 |
typ | -0.346 |
PHOTO | -0.315 |
onel | -0.315 |
adier | -0.300 |
Token | Women |
Token ID | 6926 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
arij | +0.932 |
typ | +0.786 |
PHOTO | +0.707 |
onel | +0.700 |
Picture | +0.669 |
Neg logit contributions | |
stein | -0.687 |
strings | -0.679 |
uterus | -0.660 |
chairs | -0.643 |
(£ | -0.643 |
Token | in |
Token ID | 287 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
stein | +3.209 |
strings | +3.135 |
uterus | +3.086 |
chairs | +3.005 |
(£ | +2.991 |
Neg logit contributions | |
arij | -5.847 |
typ | -5.056 |
onel | -4.552 |
PHOTO | -4.493 |
actionDate | -4.342 |
Token | politics |
Token ID | 4819 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
arij | +0.897 |
typ | +0.759 |
PHOTO | +0.683 |
onel | +0.677 |
adier | +0.647 |
Neg logit contributions | |
stein | -0.642 |
strings | -0.634 |
uterus | -0.618 |
chairs | -0.600 |
(£ | -0.600 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
arij | +1.278 |
typ | +1.087 |
PHOTO | +0.983 |
onel | +0.975 |
adier | +0.934 |
Neg logit contributions | |
stein | -0.844 |
strings | -0.832 |
uterus | -0.809 |
(£ | -0.788 |
chairs | -0.785 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
arij | +1.383 |
typ | +1.170 |
PHOTO | +1.057 |
onel | +1.045 |
Picture | +1.002 |
Neg logit contributions | |
stein | -0.981 |
strings | -0.970 |
uterus | -0.943 |
chairs | -0.917 |
(£ | -0.917 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
arij | +1.767 |
typ | +1.148 |
PHOTO | +0.852 |
onel | +0.739 |
Picture | +0.679 |
Neg logit contributions | |
stein | -5.454 |
strings | -5.421 |
uterus | -5.368 |
chairs | -5.301 |
(£ | -5.254 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
stein | +4.004 |
strings | +3.430 |
Seas | +3.361 |
(£ | +3.315 |
Slate | +3.057 |
Neg logit contributions | |
arij | -18.428 |
typ | -15.553 |
yip | -15.542 |
ailability | -15.520 |
allery | -15.171 |
Token | of |
Token ID | 286 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
arij | +4.394 |
typ | +3.833 |
PHOTO | +3.447 |
onel | +3.400 |
Picture | +3.328 |
Neg logit contributions | |
stein | -2.920 |
strings | -2.908 |
uterus | -2.889 |
chairs | -2.764 |
(£ | -2.718 |
Token | 15 |
Token ID | 1315 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
stein | +2.116 |
strings | +1.959 |
(£ | +1.930 |
chairs | +1.825 |
uterus | +1.817 |
Neg logit contributions | |
arij | -4.614 |
typ | -3.946 |
onel | -3.633 |
allery | -3.567 |
ativity | -3.508 |
Token | Photos |
Token ID | 9434 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
arij | +2.842 |
typ | +2.070 |
PHOTO | +1.827 |
Picture | +1.664 |
onel | +1.539 |
Neg logit contributions | |
uterus | -6.972 |
stein | -6.945 |
strings | -6.883 |
chairs | -6.718 |
yre | -6.689 |
Token | : |
Token ID | 25 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
stein | +2.313 |
strings | +2.172 |
(£ | +2.043 |
chairs | +1.933 |
¶ | +1.919 |
Neg logit contributions | |
arij | -6.140 |
typ | -5.144 |
allery | -4.858 |
onel | -4.857 |
PHOTO | -4.742 |
Token | was |
Token ID | 373 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
arij | +2.600 |
typ | +2.235 |
PHOTO | +2.035 |
onel | +2.014 |
Picture | +1.941 |
Neg logit contributions | |
stein | -1.515 |
strings | -1.496 |
uterus | -1.449 |
(£ | -1.405 |
chairs | -1.404 |
Token | made |
Token ID | 925 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
stein | +2.447 |
strings | +2.342 |
uterus | +2.338 |
(£ | +2.245 |
chairs | +2.181 |
Neg logit contributions | |
arij | -3.979 |
typ | -3.300 |
onel | -3.059 |
PHOTO | -2.994 |
actionDate | -2.935 |
Token | in |
Token ID | 287 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
arij | +3.969 |
typ | +3.407 |
PHOTO | +3.076 |
onel | +3.021 |
Picture | +2.942 |
Neg logit contributions | |
stein | -2.767 |
strings | -2.762 |
uterus | -2.675 |
chairs | -2.614 |
(£ | -2.594 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
stein | +2.449 |
strings | +2.338 |
uterus | +2.324 |
chairs | +2.231 |
(£ | +2.228 |
Neg logit contributions | |
arij | -3.840 |
typ | -3.197 |
onel | -2.911 |
PHOTO | -2.864 |
adier | -2.760 |
Token | - |
Token ID | 532 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
stein | +0.334 |
strings | +0.326 |
uterus | +0.315 |
(£ | +0.308 |
chairs | +0.308 |
Neg logit contributions | |
arij | -0.553 |
typ | -0.466 |
onel | -0.421 |
PHOTO | -0.421 |
adier | -0.406 |
Token | December |
Token ID | 3426 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
stein | +2.670 |
strings | +2.610 |
(£ | +2.534 |
uterus | +2.496 |
chairs | +2.416 |
Neg logit contributions | |
arij | -3.511 |
typ | -2.814 |
onel | -2.547 |
PHOTO | -2.469 |
chel | -2.457 |
Token | 13 |
Token ID | 1511 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
stein | +4.789 |
(£ | +4.042 |
strings | +3.843 |
Slate | +3.656 |
Seas | +3.474 |
Neg logit contributions | |
arij | -17.944 |
ailability | -15.356 |
typ | -15.287 |
allery | -15.178 |
yip | -14.980 |
Token | , |
Token ID | 11 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
arij | +4.207 |
typ | +3.638 |
PHOTO | +3.246 |
onel | +3.213 |
Picture | +3.087 |
Neg logit contributions | |
stein | -3.112 |
strings | -3.098 |
uterus | -3.074 |
chairs | -2.956 |
(£ | -2.926 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
strings | +0.511 |
stein | +0.510 |
uterus | +0.493 |
(£ | +0.475 |
chairs | +0.466 |
Neg logit contributions | |
arij | -0.964 |
typ | -0.816 |
onel | -0.740 |
PHOTO | -0.739 |
adier | -0.712 |
Token | boys |
Token ID | 13202 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
stein | +1.302 |
strings | +1.301 |
chairs | +1.249 |
chair | +1.213 |
(£ | +1.191 |
Neg logit contributions | |
arij | -1.743 |
typ | -1.401 |
PHOTO | -1.327 |
Picture | -1.263 |
onel | -1.252 |
Token | beware |
Token ID | 40600 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
stein | +3.374 |
strings | +3.318 |
(£ | +3.290 |
chair | +3.121 |
yre | +3.113 |
Neg logit contributions | |
arij | -8.415 |
typ | -7.346 |
PHOTO | -6.753 |
actionDate | -6.597 |
onel | -6.541 |
Token | media |
Token ID | 2056 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
stein | +0.284 |
strings | +0.279 |
uterus | +0.274 |
(£ | +0.264 |
chairs | +0.263 |
Neg logit contributions | |
arij | -0.421 |
typ | -0.355 |
PHOTO | -0.324 |
onel | -0.318 |
adier | -0.307 |
Token | lying |
Token ID | 9105 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
stein | +1.016 |
strings | +0.997 |
uterus | +0.984 |
chairs | +0.946 |
(£ | +0.939 |
Neg logit contributions | |
arij | -1.558 |
typ | -1.290 |
PHOTO | -1.184 |
onel | -1.182 |
adier | -1.129 |
Token | � |
Token ID | 447 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
stein | +0.186 |
strings | +0.182 |
uterus | +0.177 |
chairs | +0.171 |
(£ | +0.171 |
Neg logit contributions | |
arij | -0.292 |
typ | -0.247 |
PHOTO | -0.226 |
onel | -0.225 |
adier | -0.214 |
Token | � |
Token ID | 251 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
stein | +2.098 |
strings | +2.047 |
uterus | +1.978 |
chairs | +1.946 |
chair | +1.913 |
Neg logit contributions | |
arij | -2.606 |
typ | -2.191 |
PHOTO | -1.957 |
onel | -1.943 |
chel | -1.854 |
Token | to |
Token ID | 284 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
stein | +1.373 |
strings | +1.343 |
uterus | +1.307 |
(£ | +1.266 |
chairs | +1.262 |
Neg logit contributions | |
arij | -2.189 |
typ | -1.850 |
PHOTO | -1.686 |
onel | -1.683 |
adier | -1.612 |
Token | follow |
Token ID | 1061 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
stein | +4.295 |
uterus | +4.281 |
strings | +4.136 |
(£ | +4.088 |
horns | +3.857 |
Neg logit contributions | |
arij | -7.389 |
typ | -6.398 |
onel | -5.684 |
PHOTO | -5.509 |
allery | -5.490 |
Token | the |
Token ID | 262 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
stein | +7.864 |
strings | +7.841 |
uterus | +7.773 |
Slate | +7.378 |
(£ | +7.301 |
Neg logit contributions | |
arij | -12.990 |
typ | -10.799 |
onel | -10.051 |
actionDate | -9.696 |
PHOTO | -9.656 |
Token | hashtag |
Token ID | 23950 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
uterus | +3.947 |
strings | +3.897 |
stein | +3.892 |
chair | +3.670 |
(£ | +3.632 |
Neg logit contributions | |
arij | -6.410 |
typ | -5.250 |
PHOTO | -4.831 |
onel | -4.827 |
actionDate | -4.660 |
Token | # |
Token ID | 1303 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
arij | +6.479 |
typ | +5.556 |
PHOTO | +5.063 |
onel | +5.012 |
Picture | +4.922 |
Neg logit contributions | |
stein | -3.974 |
strings | -3.894 |
chairs | -3.689 |
uterus | -3.689 |
(£ | -3.621 |
Token | femin |
Token ID | 33594 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
arij | +5.997 |
typ | +5.204 |
onel | +4.585 |
PHOTO | +4.516 |
Picture | +4.371 |
Neg logit contributions | |
stein | -4.390 |
strings | -4.334 |
uterus | -4.281 |
(£ | -4.191 |
chairs | -4.147 |
Token | in |
Token ID | 259 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
arij | +0.182 |
typ | +0.158 |
PHOTO | +0.146 |
onel | +0.144 |
Picture | +0.140 |
Neg logit contributions | |
stein | -0.082 |
strings | -0.080 |
uterus | -0.077 |
chairs | -0.074 |
(£ | -0.074 |
Token | ? |
Token ID | 30 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
stein | +1.091 |
strings | +1.069 |
uterus | +1.040 |
(£ | +1.012 |
chairs | +0.994 |
Neg logit contributions | |
arij | -1.935 |
typ | -1.646 |
PHOTO | -1.503 |
onel | -1.490 |
adier | -1.425 |
Token |
|
Token ID | 198 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
arij | +0.368 |
typ | +0.311 |
PHOTO | +0.281 |
onel | +0.279 |
adier | +0.267 |
Neg logit contributions | |
stein | -0.247 |
strings | -0.244 |
uterus | -0.237 |
(£ | -0.231 |
chairs | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
stein | +1.789 |
strings | +1.719 |
(£ | +1.641 |
chairs | +1.590 |
chair | +1.563 |
Neg logit contributions | |
arij | -3.780 |
typ | -3.128 |
onel | -2.908 |
allery | -2.896 |
PHOTO | -2.874 |
Token | T |
Token ID | 51 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
stein | +2.571 |
strings | +2.527 |
(£ | +2.447 |
uterus | +2.429 |
chairs | +2.416 |
Neg logit contributions | |
arij | -3.177 |
typ | -2.591 |
onel | -2.312 |
PHOTO | -2.298 |
ativity | -2.214 |
Token | K |
Token ID | 42 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
stein | +0.584 |
strings | +0.576 |
uterus | +0.560 |
(£ | +0.548 |
chairs | +0.546 |
Neg logit contributions | |
arij | -0.772 |
typ | -0.650 |
PHOTO | -0.582 |
onel | -0.577 |
Picture | -0.551 |
Token | : |
Token ID | 25 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
stein | +1.738 |
strings | +1.655 |
(£ | +1.569 |
chairs | +1.505 |
¶ | +1.489 |
Neg logit contributions | |
arij | -4.137 |
typ | -3.445 |
onel | -3.224 |
allery | -3.152 |
PHOTO | -3.143 |
Token | To |
Token ID | 1675 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
stein | +6.831 |
(£ | +6.457 |
strings | +6.423 |
Shades | +6.406 |
Slate | +6.295 |
Neg logit contributions | |
arij | -14.778 |
typ | -11.557 |
idav | -11.088 |
onel | -11.065 |
allery | -10.982 |
Token | begin |
Token ID | 2221 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
stein | +2.733 |
uterus | +2.605 |
strings | +2.591 |
(£ | +2.467 |
chairs | +2.416 |
Neg logit contributions | |
arij | -4.751 |
typ | -4.056 |
PHOTO | -3.693 |
onel | -3.656 |
actionDate | -3.499 |
Token | , |
Token ID | 11 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
stein | +1.864 |
strings | +1.756 |
uterus | +1.683 |
(£ | +1.603 |
chairs | +1.547 |
Neg logit contributions | |
arij | -6.004 |
typ | -5.205 |
PHOTO | -4.841 |
onel | -4.823 |
adier | -4.684 |
Token | Hunt |
Token ID | 12937 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
stein | +4.357 |
uterus | +4.243 |
strings | +4.175 |
(£ | +4.074 |
horns | +3.941 |
Neg logit contributions | |
arij | -8.352 |
typ | -6.841 |
PHOTO | -6.282 |
onel | -6.271 |
allery | -6.097 |
Token | ress |
Token ID | 601 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
stein | +2.697 |
strings | +2.556 |
uterus | +2.362 |
(£ | +2.257 |
chairs | +2.254 |
Neg logit contributions | |
arij | -6.120 |
typ | -5.231 |
PHOTO | -4.891 |
onel | -4.677 |
Picture | -4.603 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
stein | +2.881 |
(£ | +2.743 |
strings | +2.740 |
uterus | +2.612 |
¶ | +2.542 |
Neg logit contributions | |
arij | -5.541 |
typ | -4.477 |
allery | -4.118 |
ativity | -4.116 |
onel | -4.047 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
arij | +3.141 |
typ | +2.693 |
PHOTO | +2.426 |
onel | +2.397 |
Picture | +2.302 |
Neg logit contributions | |
stein | -2.172 |
strings | -2.153 |
uterus | -2.111 |
chairs | -2.042 |
(£ | -2.030 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
stein | +0.969 |
strings | +0.967 |
uterus | +0.935 |
(£ | +0.899 |
chairs | +0.880 |
Neg logit contributions | |
arij | -1.940 |
typ | -1.635 |
onel | -1.492 |
PHOTO | -1.474 |
adier | -1.435 |
Token | R |
Token ID | 49 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
arij | +2.928 |
typ | +2.428 |
PHOTO | +2.126 |
onel | +2.100 |
Picture | +1.989 |
Neg logit contributions | |
stein | -3.029 |
strings | -2.999 |
uterus | -2.976 |
(£ | -2.879 |
chairs | -2.878 |
Token | iff |
Token ID | 733 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
arij | +3.928 |
typ | +2.680 |
onel | +1.960 |
ativity | +1.794 |
PHOTO | +1.728 |
Neg logit contributions | |
uterus | -11.052 |
strings | -10.954 |
ドラ | -10.898 |
stein | -10.838 |
chairs | -10.792 |
Token | Tra |
Token ID | 15721 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
arij | +2.473 |
typ | +2.047 |
PHOTO | +1.774 |
onel | +1.764 |
Picture | +1.672 |
Neg logit contributions | |
stein | -2.664 |
strings | -2.632 |
uterus | -2.602 |
(£ | -2.528 |
chairs | -2.525 |
Token | x |
Token ID | 87 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
stein | +3.455 |
strings | +3.339 |
xon | +2.654 |
figure | +2.497 |
yre | +2.448 |
Neg logit contributions | |
arij | -18.242 |
ailability | -16.477 |
conflic | -16.280 |
oreAnd | -16.008 |
adolesc | -15.458 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
stein | +1.683 |
strings | +1.626 |
uterus | +1.589 |
(£ | +1.565 |
chairs | +1.523 |
Neg logit contributions | |
arij | -2.784 |
typ | -2.374 |
PHOTO | -2.143 |
onel | -2.132 |
chel | -2.061 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
stein | +1.604 |
strings | +1.542 |
(£ | +1.462 |
chairs | +1.411 |
chair | +1.401 |
Neg logit contributions | |
arij | -3.388 |
typ | -2.805 |
PHOTO | -2.595 |
onel | -2.589 |
allery | -2.580 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
stein | +1.559 |
strings | +1.518 |
chairs | +1.425 |
uterus | +1.417 |
chair | +1.417 |
Neg logit contributions | |
arij | -2.374 |
typ | -1.960 |
PHOTO | -1.839 |
onel | -1.779 |
Picture | -1.734 |
Token | : |
Token ID | 25 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
stein | +2.328 |
strings | +2.227 |
(£ | +2.036 |
chairs | +1.991 |
chair | +1.955 |
Neg logit contributions | |
arij | -5.958 |
typ | -4.951 |
allery | -4.683 |
onel | -4.651 |
PHOTO | -4.640 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
arij | +1.079 |
typ | +0.914 |
PHOTO | +0.831 |
onel | +0.826 |
adier | +0.790 |
Neg logit contributions | |
stein | -0.699 |
strings | -0.691 |
uterus | -0.676 |
(£ | -0.660 |
chairs | -0.651 |
Token | Things |
Token ID | 11597 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
arij | +0.933 |
typ | +0.786 |
onel | +0.709 |
PHOTO | +0.708 |
adier | +0.678 |
Neg logit contributions | |
stein | -0.619 |
strings | -0.611 |
uterus | -0.588 |
(£ | -0.580 |
chairs | -0.573 |
Token | improved |
Token ID | 6596 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
stein | +0.182 |
strings | +0.179 |
uterus | +0.175 |
(£ | +0.170 |
chairs | +0.167 |
Neg logit contributions | |
arij | -0.294 |
typ | -0.250 |
PHOTO | -0.227 |
onel | -0.227 |
adier | -0.215 |
Token | in |
Token ID | 287 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
stein | +0.247 |
strings | +0.243 |
uterus | +0.234 |
(£ | +0.231 |
chairs | +0.226 |
Neg logit contributions | |
arij | -0.462 |
typ | -0.395 |
PHOTO | -0.362 |
onel | -0.360 |
adier | -0.345 |
Token | June |
Token ID | 2795 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
stein | +1.627 |
strings | +1.620 |
uterus | +1.597 |
(£ | +1.550 |
chairs | +1.524 |
Neg logit contributions | |
arij | -2.084 |
typ | -1.722 |
PHOTO | -1.552 |
onel | -1.550 |
adier | -1.472 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
stein | +4.649 |
strings | +4.517 |
(£ | +4.366 |
uterus | +4.099 |
chairs | +4.026 |
Neg logit contributions | |
arij | -10.195 |
typ | -8.520 |
onel | -8.027 |
PHOTO | -7.940 |
actionDate | -7.690 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
uterus | +8.208 |
stein | +8.166 |
(£ | +7.937 |
strings | +7.844 |
horns | +7.739 |
Neg logit contributions | |
arij | -12.707 |
typ | -10.471 |
onel | -9.925 |
actionDate | -9.520 |
PHOTO | -9.441 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
arij | +0.178 |
typ | +0.149 |
PHOTO | +0.135 |
onel | +0.134 |
adier | +0.128 |
Neg logit contributions | |
stein | -0.124 |
strings | -0.123 |
uterus | -0.121 |
(£ | -0.117 |
chairs | -0.116 |
Token | campaign |
Token ID | 1923 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
arij | +3.781 |
typ | +3.197 |
PHOTO | +2.862 |
onel | +2.810 |
Picture | +2.721 |
Neg logit contributions | |
stein | -2.979 |
strings | -2.952 |
uterus | -2.865 |
chairs | -2.795 |
(£ | -2.783 |
Token | almost |
Token ID | 2048 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
arij | +0.407 |
typ | +0.344 |
PHOTO | +0.312 |
onel | +0.311 |
actionDate | +0.296 |
Neg logit contributions | |
stein | -0.266 |
strings | -0.261 |
uterus | -0.254 |
(£ | -0.248 |
chairs | -0.246 |
Token | matched |
Token ID | 14451 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
arij | +1.018 |
typ | +0.862 |
PHOTO | +0.789 |
onel | +0.780 |
Picture | +0.749 |
Neg logit contributions | |
stein | -0.610 |
strings | -0.602 |
uterus | -0.582 |
(£ | -0.571 |
chairs | -0.563 |
Token | a |
Token ID | 257 |
Feature activation | -9.06e-04 |
Pos logit contributions | |
stein | +2.198 |
strings | +2.162 |
uterus | +2.083 |
(£ | +2.035 |
chairs | +2.020 |
Neg logit contributions | |
arij | -3.599 |
typ | -3.028 |
PHOTO | -2.722 |
onel | -2.706 |
actionDate | -2.677 |
Token | ute |
Token ID | 1133 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
arij | +0.007 |
typ | +0.006 |
PHOTO | +0.006 |
onel | +0.005 |
adier | +0.005 |
Neg logit contributions | |
stein | -0.006 |
strings | -0.006 |
uterus | -0.006 |
(£ | -0.006 |
chairs | -0.006 |
Token | urs |
Token ID | 1834 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
strings | +2.119 |
stein | +2.117 |
uterus | +2.024 |
chairs | +2.018 |
(£ | +1.994 |
Neg logit contributions | |
arij | -2.086 |
typ | -1.649 |
onel | -1.479 |
PHOTO | -1.463 |
adier | -1.395 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
stein | +1.671 |
strings | +1.623 |
uterus | +1.566 |
(£ | +1.544 |
chairs | +1.533 |
Neg logit contributions | |
arij | -2.618 |
typ | -2.216 |
PHOTO | -2.029 |
onel | -2.001 |
actionDate | -1.936 |
Token |
|
Token ID | 198 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
stein | +0.750 |
strings | +0.732 |
(£ | +0.698 |
uterus | +0.696 |
chairs | +0.685 |
Neg logit contributions | |
arij | -1.256 |
typ | -1.058 |
onel | -0.956 |
PHOTO | -0.947 |
ativity | -0.918 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
stein | +2.424 |
strings | +2.324 |
(£ | +2.174 |
chairs | +2.111 |
chair | +2.095 |
Neg logit contributions | |
arij | -5.608 |
typ | -4.624 |
allery | -4.371 |
onel | -4.309 |
PHOTO | -4.288 |
Token | 11 |
Token ID | 1157 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
stein | +7.719 |
strings | +7.506 |
chair | +6.854 |
figure | +6.814 |
(£ | +6.712 |
Neg logit contributions | |
arij | -13.694 |
typ | -11.505 |
actionDate | -10.511 |
adier | -10.420 |
PHOTO | -10.410 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
arij | +1.895 |
typ | +1.591 |
PHOTO | +1.433 |
onel | +1.420 |
adier | +1.355 |
Neg logit contributions | |
stein | -1.390 |
strings | -1.369 |
uterus | -1.324 |
(£ | -1.296 |
chairs | -1.294 |
Token | The |
Token ID | 383 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
arij | +0.529 |
typ | +0.449 |
PHOTO | +0.408 |
onel | +0.404 |
adier | +0.387 |
Neg logit contributions | |
stein | -0.334 |
strings | -0.328 |
uterus | -0.318 |
(£ | -0.310 |
chairs | -0.308 |
Token | Legend |
Token ID | 9883 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
stein | +1.379 |
strings | +1.322 |
uterus | +1.280 |
(£ | +1.262 |
chairs | +1.227 |
Neg logit contributions | |
arij | -2.571 |
typ | -2.196 |
PHOTO | -2.012 |
onel | -1.975 |
actionDate | -1.926 |
Token | of |
Token ID | 286 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
stein | +2.214 |
strings | +2.095 |
(£ | +2.033 |
uterus | +1.933 |
chair | +1.898 |
Neg logit contributions | |
arij | -5.375 |
typ | -4.622 |
PHOTO | -4.225 |
onel | -4.188 |
chel | -4.108 |
Token | ] |
Token ID | 60 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
arij | +4.296 |
typ | +3.794 |
onel | +3.462 |
PHOTO | +3.456 |
Picture | +3.338 |
Neg logit contributions | |
strings | -1.866 |
stein | -1.853 |
uterus | -1.796 |
chairs | -1.746 |
(£ | -1.691 |
Token | NBC |
Token ID | 9716 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
arij | +2.847 |
typ | +2.427 |
PHOTO | +2.203 |
onel | +2.180 |
Picture | +2.101 |
Neg logit contributions | |
stein | -1.859 |
strings | -1.842 |
uterus | -1.781 |
chairs | -1.733 |
(£ | -1.725 |
Token | Sports |
Token ID | 18153 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
stein | +1.535 |
strings | +1.475 |
uterus | +1.449 |
(£ | +1.444 |
chair | +1.385 |
Neg logit contributions | |
arij | -2.598 |
typ | -2.186 |
onel | -1.999 |
PHOTO | -1.987 |
actionDate | -1.896 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
arij | +0.056 |
typ | +0.047 |
PHOTO | +0.043 |
onel | +0.042 |
Picture | +0.040 |
Neg logit contributions | |
stein | -0.040 |
strings | -0.039 |
uterus | -0.038 |
chairs | -0.037 |
(£ | -0.037 |
Token | com |
Token ID | 785 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arij | +3.185 |
typ | +2.733 |
PHOTO | +2.482 |
onel | +2.459 |
Picture | +2.369 |
Neg logit contributions | |
stein | -1.915 |
strings | -1.894 |
uterus | -1.840 |
(£ | -1.782 |
chairs | -1.777 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
stein | +1.347 |
strings | +1.281 |
(£ | +1.244 |
uterus | +1.233 |
chairs | +1.175 |
Neg logit contributions | |
arij | -3.783 |
typ | -3.289 |
PHOTO | -3.027 |
onel | -3.021 |
actionDate | -2.918 |
Token | 92 |
Token ID | 5892 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
arij | +10.700 |
typ | +9.202 |
onel | +7.353 |
AA | +7.171 |
TW | +7.077 |
Neg logit contributions | |
uterus | -17.585 |
(£ | -16.703 |
ドラ | -16.582 |
strings | -16.411 |
Shades | -16.256 |
Token | ] |
Token ID | 60 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
arij | +3.633 |
typ | +3.181 |
onel | +2.922 |
PHOTO | +2.908 |
Picture | +2.812 |
Neg logit contributions | |
strings | -1.519 |
stein | -1.513 |
uterus | -1.445 |
chairs | -1.423 |
(£ | -1.378 |
Token | SB |
Token ID | 18056 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
arij | +1.167 |
typ | +1.001 |
PHOTO | +0.911 |
onel | +0.903 |
Picture | +0.868 |
Neg logit contributions | |
stein | -0.678 |
strings | -0.669 |
uterus | -0.647 |
(£ | -0.628 |
chairs | -0.627 |
Token | Nation |
Token ID | 8741 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
arij | +1.226 |
typ | +1.037 |
PHOTO | +0.939 |
onel | +0.937 |
adier | +0.899 |
Neg logit contributions | |
stein | -0.784 |
strings | -0.768 |
uterus | -0.746 |
(£ | -0.729 |
chairs | -0.719 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
arij | +2.374 |
typ | +2.100 |
PHOTO | +1.953 |
onel | +1.937 |
Picture | +1.889 |
Neg logit contributions | |
stein | -0.718 |
strings | -0.713 |
uterus | -0.674 |
chairs | -0.643 |
(£ | -0.625 |
Token | image |
Token ID | 2939 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
arij | +2.907 |
typ | +2.428 |
PHOTO | +2.175 |
onel | +2.137 |
Picture | +2.052 |
Neg logit contributions | |
stein | -2.507 |
strings | -2.484 |
uterus | -2.413 |
chairs | -2.369 |
(£ | -2.359 |
Token | , |
Token ID | 837 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
arij | +2.875 |
typ | +2.477 |
PHOTO | +2.253 |
onel | +2.221 |
Picture | +2.145 |
Neg logit contributions | |
stein | -1.751 |
strings | -1.729 |
uterus | -1.692 |
chairs | -1.633 |
(£ | -1.632 |
Token | c |
Token ID | 269 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
arij | +3.753 |
typ | +3.051 |
PHOTO | +2.661 |
onel | +2.515 |
Picture | +2.479 |
Neg logit contributions | |
stein | -5.048 |
strings | -5.004 |
uterus | -4.892 |
chairs | -4.848 |
yre | -4.780 |
Token | v |
Token ID | 85 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
stein | +1.589 |
strings | +1.553 |
chairs | +1.407 |
(£ | +1.402 |
uterus | +1.390 |
Neg logit contributions | |
arij | -2.713 |
typ | -2.255 |
PHOTO | -2.152 |
onel | -2.078 |
allery | -2.050 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
arij | +6.229 |
typ | +5.533 |
onel | +4.682 |
PHOTO | +4.655 |
chel | +4.504 |
Neg logit contributions | |
uterus | -6.623 |
stein | -6.449 |
strings | -6.291 |
chairs | -6.197 |
(£ | -6.155 |
Token | . |
Token ID | 764 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
arij | +5.926 |
typ | +5.213 |
PHOTO | +4.684 |
onel | +4.564 |
Picture | +4.440 |
Neg logit contributions | |
uterus | -5.269 |
stein | -5.183 |
strings | -5.160 |
chairs | -4.989 |
ドラ | -4.961 |
Token | COL |
Token ID | 20444 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
arij | +12.633 |
PHOTO | +11.724 |
typ | +10.663 |
COL | +10.164 |
Picture | +10.060 |
Neg logit contributions | |
chairs | -14.320 |
stein | -14.068 |
strings | -13.748 |
chair | -13.588 |
ドラ | -13.359 |
Token | OR |
Token ID | 1581 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
arij | +0.293 |
typ | +0.237 |
PHOTO | +0.205 |
onel | +0.203 |
chel | +0.195 |
Neg logit contributions | |
stein | -0.287 |
strings | -0.285 |
uterus | -0.274 |
(£ | -0.271 |
chairs | -0.270 |
Token | _ |
Token ID | 62 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
arij | +2.513 |
typ | +2.177 |
PHOTO | +1.997 |
onel | +1.973 |
Picture | +1.905 |
Neg logit contributions | |
stein | -1.298 |
strings | -1.281 |
uterus | -1.244 |
chairs | -1.197 |
(£ | -1.196 |
Token | B |
Token ID | 33 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
arij | +4.036 |
typ | +3.365 |
PHOTO | +2.997 |
onel | +2.802 |
Picture | +2.649 |
Neg logit contributions | |
stein | -5.526 |
uterus | -5.509 |
strings | -5.480 |
chairs | -5.315 |
(£ | -5.252 |
Token | GR |
Token ID | 10761 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
arij | +2.025 |
typ | +1.562 |
PHOTO | +1.318 |
onel | +1.265 |
Picture | +1.167 |
Neg logit contributions | |
stein | -3.439 |
strings | -3.412 |
uterus | -3.377 |
chairs | -3.303 |
(£ | -3.285 |
Token | with |
Token ID | 351 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
stein | +0.447 |
strings | +0.432 |
uterus | +0.415 |
(£ | +0.406 |
chairs | +0.398 |
Neg logit contributions | |
arij | -1.088 |
typ | -0.946 |
PHOTO | -0.880 |
onel | -0.863 |
Picture | -0.836 |
Token | Germany |
Token ID | 4486 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
arij | +2.156 |
typ | +1.804 |
onel | +1.603 |
PHOTO | +1.603 |
Picture | +1.529 |
Neg logit contributions | |
stein | -1.795 |
strings | -1.790 |
uterus | -1.729 |
chairs | -1.698 |
(£ | -1.688 |
Token | and |
Token ID | 290 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
stein | +1.647 |
strings | +1.570 |
(£ | +1.521 |
uterus | +1.515 |
chairs | +1.381 |
Neg logit contributions | |
arij | -4.784 |
typ | -4.142 |
PHOTO | -3.894 |
onel | -3.800 |
ativity | -3.728 |
Token | its |
Token ID | 663 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
arij | +0.419 |
typ | +0.356 |
PHOTO | +0.322 |
onel | +0.319 |
adier | +0.305 |
Neg logit contributions | |
stein | -0.272 |
strings | -0.265 |
uterus | -0.261 |
(£ | -0.254 |
chairs | -0.251 |
Token | allies |
Token ID | 7681 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
arij | +0.910 |
typ | +0.794 |
PHOTO | +0.732 |
onel | +0.726 |
Picture | +0.700 |
Neg logit contributions | |
stein | -0.377 |
strings | -0.368 |
uterus | -0.355 |
(£ | -0.342 |
chairs | -0.340 |
Token | ."[ |
Token ID | 18161 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
stein | +0.473 |
strings | +0.457 |
uterus | +0.440 |
(£ | +0.432 |
chairs | +0.420 |
Neg logit contributions | |
arij | -1.135 |
typ | -0.986 |
PHOTO | -0.917 |
onel | -0.897 |
ativity | -0.871 |
Token | 22 |
Token ID | 1828 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
arij | +12.411 |
typ | +11.429 |
chel | +9.480 |
onel | +9.400 |
PHOTO | +9.150 |
Neg logit contributions | |
uterus | -13.609 |
strings | -12.604 |
stein | -12.568 |
feathers | -12.540 |
ドラ | -12.440 |
Token | ] |
Token ID | 60 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
arij | +3.866 |
typ | +3.404 |
PHOTO | +3.112 |
onel | +3.106 |
Picture | +3.015 |
Neg logit contributions | |
strings | -1.620 |
stein | -1.611 |
uterus | -1.546 |
chairs | -1.507 |
(£ | -1.463 |
Token | The |
Token ID | 383 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
arij | +2.756 |
typ | +2.350 |
PHOTO | +2.133 |
onel | +2.109 |
Picture | +2.030 |
Neg logit contributions | |
stein | -1.782 |
strings | -1.761 |
uterus | -1.711 |
chairs | -1.660 |
(£ | -1.659 |
Token | plan |
Token ID | 1410 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
arij | +3.141 |
typ | +2.690 |
PHOTO | +2.440 |
onel | +2.424 |
Picture | +2.341 |
Neg logit contributions | |
stein | -1.983 |
strings | -1.970 |
uterus | -1.910 |
chairs | -1.854 |
(£ | -1.851 |
Token | was |
Token ID | 373 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
arij | +4.826 |
typ | +4.119 |
PHOTO | +3.691 |
onel | +3.688 |
Picture | +3.557 |
Neg logit contributions | |
strings | -3.341 |
stein | -3.333 |
uterus | -3.230 |
chairs | -3.140 |
(£ | -3.097 |
Token | Bay |
Token ID | 15262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
stein | +0.371 |
strings | +0.365 |
uterus | +0.348 |
chairs | +0.348 |
(£ | +0.345 |
Neg logit contributions | |
arij | -0.453 |
typ | -0.369 |
PHOTO | -0.335 |
onel | -0.331 |
Picture | -0.315 |
Token | ern |
Token ID | 1142 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
stein | +2.094 |
strings | +2.041 |
(£ | +1.939 |
uterus | +1.841 |
chairs | +1.822 |
Neg logit contributions | |
arij | -3.994 |
typ | -3.356 |
PHOTO | -3.189 |
onel | -3.045 |
ativity | -3.008 |
Token | Munich |
Token ID | 22418 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
stein | +1.705 |
strings | +1.632 |
(£ | +1.597 |
uterus | +1.579 |
chairs | +1.552 |
Neg logit contributions | |
arij | -2.287 |
typ | -1.912 |
onel | -1.716 |
PHOTO | -1.700 |
actionDate | -1.635 |
Token | Jun |
Token ID | 7653 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
arij | +3.729 |
typ | +3.193 |
PHOTO | +2.931 |
onel | +2.843 |
Picture | +2.800 |
Neg logit contributions | |
strings | -2.444 |
stein | -2.437 |
uterus | -2.363 |
chairs | -2.285 |
(£ | -2.231 |
Token | iors |
Token ID | 12706 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
stein | +2.723 |
strings | +2.584 |
(£ | +2.349 |
chair | +2.308 |
chairs | +2.302 |
Neg logit contributions | |
arij | -4.493 |
typ | -3.718 |
PHOTO | -3.455 |
onel | -3.358 |
actionDate | -3.357 |
Token | [ |
Token ID | 58 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
stein | +0.941 |
strings | +0.915 |
(£ | +0.892 |
uterus | +0.888 |
chairs | +0.868 |
Neg logit contributions | |
arij | -1.485 |
typ | -1.263 |
onel | -1.141 |
PHOTO | -1.133 |
ativity | -1.083 |
Token | 92 |
Token ID | 5892 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
arij | +12.449 |
typ | +11.024 |
onel | +9.317 |
chel | +9.206 |
TW | +8.950 |
Neg logit contributions | |
uterus | -12.912 |
stein | -12.339 |
strings | -12.323 |
ドラ | -12.202 |
(£ | -11.915 |
Token | ][ |
Token ID | 7131 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
arij | +5.411 |
typ | +4.753 |
onel | +4.354 |
PHOTO | +4.346 |
Picture | +4.195 |
Neg logit contributions | |
strings | -2.375 |
stein | -2.329 |
uterus | -2.287 |
chairs | -2.192 |
(£ | -2.120 |
Token | 93 |
Token ID | 6052 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
arij | +3.854 |
typ | +3.193 |
PHOTO | +2.579 |
onel | +2.550 |
chel | +2.434 |
Neg logit contributions | |
uterus | -5.877 |
strings | -5.792 |
stein | -5.764 |
chairs | -5.598 |
(£ | -5.581 |
Token | ] |
Token ID | 60 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
arij | +4.540 |
typ | +3.988 |
PHOTO | +3.653 |
onel | +3.641 |
Picture | +3.535 |
Neg logit contributions | |
strings | -2.027 |
stein | -2.007 |
uterus | -1.954 |
chairs | -1.877 |
(£ | -1.788 |
Token |
|
Token ID | 198 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
arij | +2.586 |
typ | +2.203 |
PHOTO | +2.004 |
onel | +1.973 |
Picture | +1.906 |
Neg logit contributions | |
stein | -1.707 |
strings | -1.692 |
uterus | -1.643 |
chairs | -1.592 |
(£ | -1.581 |
Token | in |
Token ID | 259 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
arij | +1.671 |
typ | +1.421 |
PHOTO | +1.291 |
onel | +1.269 |
Picture | +1.234 |
Neg logit contributions | |
stein | -1.118 |
strings | -1.108 |
uterus | -1.085 |
chairs | -1.049 |
(£ | -1.047 |
Token | - |
Token ID | 12 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
stein | +4.498 |
strings | +4.374 |
uterus | +4.162 |
chairs | +4.153 |
chair | +4.128 |
Neg logit contributions | |
arij | -6.150 |
typ | -5.191 |
onel | -4.682 |
PHOTO | -4.569 |
chel | -4.431 |
Token | Sl |
Token ID | 11122 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
arij | +4.098 |
typ | +3.507 |
PHOTO | +3.078 |
onel | +3.049 |
Picture | +2.926 |
Neg logit contributions | |
stein | -3.568 |
strings | -3.534 |
uterus | -3.510 |
(£ | -3.407 |
chairs | -3.369 |
Token | ash |
Token ID | 1077 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
arij | +0.583 |
typ | +0.492 |
PHOTO | +0.443 |
onel | +0.435 |
chel | +0.416 |
Neg logit contributions | |
stein | -0.447 |
strings | -0.435 |
uterus | -0.425 |
chairs | -0.413 |
(£ | -0.413 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
arij | +3.698 |
typ | +3.145 |
PHOTO | +2.849 |
onel | +2.800 |
Picture | +2.717 |
Neg logit contributions | |
stein | -2.537 |
strings | -2.530 |
uterus | -2.470 |
(£ | -2.391 |
chairs | -2.378 |
Token | 01 |
Token ID | 486 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
stein | +1.643 |
strings | +1.566 |
uterus | +1.428 |
(£ | +1.398 |
chairs | +1.336 |
Neg logit contributions | |
arij | -5.411 |
typ | -4.671 |
PHOTO | -4.396 |
onel | -4.344 |
adier | -4.233 |
Token | 22 |
Token ID | 1828 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
arij | +7.976 |
typ | +5.650 |
ART | +4.976 |
AA | +4.911 |
actionDate | +4.430 |
Neg logit contributions | |
uterus | -17.142 |
strings | -16.085 |
foss | -16.016 |
idis | -16.007 |
ドラ | -16.007 |
Token | O |
Token ID | 440 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
arij | +2.796 |
typ | +2.337 |
PHOTO | +2.088 |
onel | +2.026 |
Picture | +1.977 |
Neg logit contributions | |
stein | -2.791 |
strings | -2.786 |
uterus | -2.718 |
chairs | -2.673 |
(£ | -2.632 |
Token | & |
Token ID | 5 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
arij | +1.881 |
typ | +1.549 |
PHOTO | +1.367 |
onel | +1.350 |
Picture | +1.282 |
Neg logit contributions | |
stein | -1.839 |
strings | -1.821 |
uterus | -1.781 |
chairs | -1.739 |
(£ | -1.739 |
Token | A |
Token ID | 32 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
arij | +2.569 |
typ | +2.117 |
PHOTO | +1.867 |
onel | +1.834 |
Picture | +1.754 |
Neg logit contributions | |
stein | -2.690 |
strings | -2.674 |
uterus | -2.632 |
chairs | -2.551 |
(£ | -2.546 |
Token | - |
Token ID | 12 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
stein | +1.505 |
strings | +1.435 |
(£ | +1.329 |
chairs | +1.302 |
chair | +1.291 |
Neg logit contributions | |
arij | -3.979 |
typ | -3.341 |
onel | -3.119 |
PHOTO | -3.096 |
allery | -3.081 |
Token | x |
Token ID | 2124 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
arij | +1.534 |
typ | +1.302 |
PHOTO | +1.181 |
onel | +1.175 |
adier | +1.125 |
Neg logit contributions | |
stein | -0.959 |
strings | -0.946 |
uterus | -0.917 |
(£ | -0.894 |
chairs | -0.886 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
stein | +0.831 |
strings | +0.814 |
(£ | +0.769 |
uterus | +0.760 |
chairs | +0.757 |
Neg logit contributions | |
arij | -1.281 |
typ | -1.055 |
PHOTO | -0.971 |
onel | -0.960 |
allery | -0.931 |
Token | x |
Token ID | 87 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
stein | +1.527 |
strings | +1.478 |
(£ | +1.307 |
chairs | +1.306 |
chair | +1.304 |
Neg logit contributions | |
arij | -4.307 |
typ | -3.598 |
PHOTO | -3.484 |
onel | -3.410 |
allery | -3.407 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
arij | +1.373 |
typ | +1.156 |
PHOTO | +1.039 |
onel | +1.028 |
Picture | +0.984 |
Neg logit contributions | |
stein | -1.036 |
strings | -1.024 |
uterus | -0.996 |
(£ | -0.970 |
chairs | -0.970 |
Token | x |
Token ID | 87 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
stein | +2.158 |
strings | +2.057 |
chair | +1.804 |
(£ | +1.802 |
chairs | +1.785 |
Neg logit contributions | |
arij | -6.580 |
typ | -5.433 |
PHOTO | -5.355 |
allery | -5.265 |
onel | -5.209 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
arij | +4.713 |
typ | +4.097 |
onel | +3.542 |
PHOTO | +3.538 |
Picture | +3.394 |
Neg logit contributions | |
uterus | -4.457 |
strings | -4.426 |
stein | -4.407 |
chairs | -4.275 |
(£ | -4.183 |
Token | 92 |
Token ID | 5892 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
arij | +8.188 |
typ | +6.988 |
onel | +5.833 |
chel | +5.301 |
pas | +4.585 |
Neg logit contributions | |
ドラ | -16.454 |
uterus | -16.322 |
foss | -16.006 |
Shades | -15.715 |
Ic | -15.647 |
Token | 105 |
Token ID | 13343 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
arij | +0.230 |
typ | +0.190 |
PHOTO | +0.169 |
onel | +0.168 |
adier | +0.160 |
Neg logit contributions | |
stein | -0.198 |
strings | -0.196 |
uterus | -0.190 |
(£ | -0.187 |
chairs | -0.186 |
Token | 70 |
Token ID | 2154 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
arij | +2.244 |
typ | +1.878 |
PHOTO | +1.683 |
onel | +1.666 |
Picture | +1.590 |
Neg logit contributions | |
stein | -1.786 |
strings | -1.765 |
uterus | -1.716 |
(£ | -1.675 |
chairs | -1.675 |
Token | 58 |
Token ID | 3365 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
arij | +3.629 |
typ | +3.041 |
PHOTO | +2.692 |
onel | +2.651 |
Picture | +2.533 |
Neg logit contributions | |
stein | -3.308 |
strings | -3.286 |
uterus | -3.218 |
chairs | -3.136 |
(£ | -3.124 |
Token | x |
Token ID | 2124 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
arij | +2.406 |
typ | +2.048 |
PHOTO | +1.856 |
onel | +1.835 |
Picture | +1.764 |
Neg logit contributions | |
stein | -1.587 |
strings | -1.568 |
uterus | -1.521 |
chairs | -1.479 |
(£ | -1.477 |
Token | ) |
Token ID | 8 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
arij | +3.338 |
typ | +2.864 |
PHOTO | +2.587 |
onel | +2.545 |
Picture | +2.461 |
Neg logit contributions | |
stein | -2.363 |
strings | -2.345 |
uterus | -2.309 |
chairs | -2.221 |
(£ | -2.215 |
Token | s |
Token ID | 264 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
arij | +1.465 |
typ | +1.216 |
PHOTO | +1.106 |
onel | +1.083 |
Picture | +1.045 |
Neg logit contributions | |
stein | -1.222 |
strings | -1.202 |
uterus | -1.172 |
chairs | -1.146 |
(£ | -1.133 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
arij | +2.621 |
typ | +2.219 |
PHOTO | +1.986 |
onel | +1.965 |
Picture | +1.877 |
Neg logit contributions | |
stein | -2.082 |
strings | -2.065 |
uterus | -2.028 |
chairs | -1.965 |
(£ | -1.959 |
Token | t |
Token ID | 83 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
stein | +1.288 |
strings | +1.259 |
chairs | +1.167 |
(£ | +1.165 |
uterus | +1.153 |
Neg logit contributions | |
arij | -1.922 |
typ | -1.567 |
PHOTO | -1.472 |
onel | -1.429 |
allery | -1.401 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
arij | +4.797 |
typ | +4.103 |
PHOTO | +3.683 |
onel | +3.600 |
Picture | +3.474 |
Neg logit contributions | |
strings | -4.490 |
uterus | -4.478 |
stein | -4.472 |
chairs | -4.300 |
(£ | -4.213 |
Token | BEL |
Token ID | 29991 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
arij | +8.311 |
typ | +7.008 |
PHOTO | +6.919 |
Picture | +6.395 |
onel | +6.235 |
Neg logit contributions | |
stein | -8.390 |
strings | -8.170 |
uterus | -8.054 |
chairs | -8.027 |
yre | -7.913 |
Token | 22 |
Token ID | 2534 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
arij | +8.055 |
PHOTO | +5.489 |
typ | +5.203 |
onel | +4.555 |
Picture | +4.510 |
Neg logit contributions | |
stein | -15.640 |
uterus | -15.594 |
strings | -15.527 |
ドラ | -15.377 |
figure | -15.313 |
Token | Krist |
Token ID | 14912 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
arij | +3.300 |
typ | +2.792 |
PHOTO | +2.541 |
onel | +2.502 |
Picture | +2.422 |
Neg logit contributions | |
stein | -2.372 |
strings | -2.365 |
uterus | -2.300 |
chairs | -2.249 |
(£ | -2.205 |
Token | of |
Token ID | 1659 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
arij | +1.835 |
typ | +1.550 |
PHOTO | +1.398 |
onel | +1.374 |
Picture | +1.322 |
Neg logit contributions | |
stein | -1.390 |
strings | -1.371 |
uterus | -1.330 |
(£ | -1.302 |
chairs | -1.296 |
Token | God |
Token ID | 1793 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
arij | +2.071 |
typ | +1.748 |
PHOTO | +1.582 |
onel | +1.566 |
Picture | +1.504 |
Neg logit contributions | |
stein | -1.476 |
strings | -1.471 |
uterus | -1.433 |
chairs | -1.394 |
(£ | -1.382 |
Token | da |
Token ID | 6814 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
arij | +0.433 |
typ | +0.364 |
PHOTO | +0.336 |
onel | +0.326 |
actionDate | +0.323 |
Neg logit contributions | |
stein | -0.275 |
strings | -0.265 |
(£ | -0.248 |
chairs | -0.247 |
uterus | -0.246 |
Token | by |
Token ID | 416 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
arij | +3.200 |
typ | +2.747 |
PHOTO | +2.502 |
onel | +2.476 |
Picture | +2.382 |
Neg logit contributions | |
stein | -1.889 |
strings | -1.869 |
uterus | -1.806 |
chairs | -1.759 |
(£ | -1.745 |
Token | the |
Token ID | 262 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
arij | +1.853 |
typ | +1.549 |
PHOTO | +1.389 |
onel | +1.368 |
Picture | +1.312 |
Neg logit contributions | |
stein | -1.522 |
strings | -1.504 |
uterus | -1.463 |
chairs | -1.433 |
(£ | -1.430 |
Token | Chemistry |
Token ID | 27867 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
arij | +5.171 |
typ | +4.385 |
PHOTO | +3.969 |
onel | +3.827 |
Picture | +3.757 |
Neg logit contributions | |
stein | -4.145 |
strings | -4.083 |
chairs | -3.926 |
uterus | -3.916 |
(£ | -3.856 |
Token | and |
Token ID | 290 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
arij | +5.543 |
typ | +4.763 |
PHOTO | +4.395 |
onel | +4.335 |
Picture | +4.278 |
Neg logit contributions | |
stein | -3.656 |
strings | -3.638 |
uterus | -3.556 |
chairs | -3.473 |
(£ | -3.393 |
Token | Camera |
Token ID | 20432 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
arij | +6.705 |
typ | +5.644 |
PHOTO | +5.240 |
Picture | +5.062 |
onel | +5.049 |
Neg logit contributions | |
stein | -6.241 |
strings | -6.120 |
uterus | -6.077 |
chairs | -6.028 |
(£ | -5.821 |
Token | ( |
Token ID | 357 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
arij | +3.125 |
typ | +2.662 |
PHOTO | +2.414 |
onel | +2.371 |
Picture | +2.328 |
Neg logit contributions | |
stein | -2.489 |
strings | -2.488 |
uterus | -2.388 |
chairs | -2.355 |
(£ | -2.319 |
Token | Chem |
Token ID | 41829 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
arij | +8.777 |
typ | +7.344 |
Chem | +6.946 |
chel | +6.843 |
PHOTO | +6.774 |
Neg logit contributions | |
stein | -14.926 |
uterus | -14.764 |
strings | -14.707 |
(£ | -14.534 |
yre | -14.451 |
Token | Cam |
Token ID | 21701 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
arij | +6.495 |
typ | +5.442 |
PHOTO | +4.922 |
onel | +4.834 |
cade | +4.705 |
Neg logit contributions | |
stein | -5.465 |
strings | -5.413 |
uterus | -5.383 |
(£ | -5.203 |
chairs | -5.191 |
Token | ) |
Token ID | 8 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
arij | +3.020 |
typ | +2.561 |
PHOTO | +2.338 |
onel | +2.270 |
Picture | +2.218 |
Neg logit contributions | |
strings | -2.256 |
stein | -2.251 |
uterus | -2.174 |
chairs | -2.127 |
(£ | -2.113 |
Token | instrument |
Token ID | 8875 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
arij | +3.873 |
typ | +3.287 |
PHOTO | +2.986 |
onel | +2.924 |
Picture | +2.833 |
Neg logit contributions | |
stein | -2.820 |
strings | -2.793 |
uterus | -2.699 |
chairs | -2.649 |
(£ | -2.625 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
arij | +4.728 |
typ | +4.012 |
PHOTO | +3.637 |
onel | +3.584 |
Picture | +3.456 |
Neg logit contributions | |
stein | -3.372 |
strings | -3.343 |
uterus | -3.254 |
chairs | -3.172 |
(£ | -3.131 |
Token | ) |
Token ID | 8 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
arij | +2.328 |
typ | +2.004 |
PHOTO | +1.822 |
onel | +1.804 |
Picture | +1.741 |
Neg logit contributions | |
stein | -1.366 |
strings | -1.349 |
uterus | -1.319 |
chairs | -1.269 |
(£ | -1.269 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
arij | +2.582 |
typ | +2.213 |
PHOTO | +2.014 |
onel | +1.991 |
Picture | +1.922 |
Neg logit contributions | |
stein | -1.555 |
strings | -1.529 |
uterus | -1.482 |
chairs | -1.443 |
(£ | -1.441 |
Token | 18 |
Token ID | 1248 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
arij | +0.268 |
typ | +0.225 |
PHOTO | +0.205 |
onel | +0.204 |
adier | +0.195 |
Neg logit contributions | |
stein | -0.172 |
strings | -0.172 |
uterus | -0.163 |
(£ | -0.160 |
chairs | -0.160 |
Token | 19 |
Token ID | 678 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
strings | +2.767 |
stein | +2.728 |
uterus | +2.609 |
(£ | +2.554 |
chairs | +2.462 |
Neg logit contributions | |
arij | -4.995 |
typ | -4.194 |
onel | -3.852 |
ativity | -3.723 |
PHOTO | -3.702 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
arij | +5.254 |
typ | +4.496 |
PHOTO | +4.124 |
onel | +3.910 |
Picture | +3.904 |
Neg logit contributions | |
stein | -4.338 |
strings | -4.139 |
uterus | -4.112 |
chairs | -4.074 |
(£ | -4.026 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
arij | +1.483 |
typ | +1.218 |
PHOTO | +1.097 |
onel | +1.056 |
Picture | +1.031 |
Neg logit contributions | |
stein | -1.540 |
strings | -1.517 |
uterus | -1.483 |
chairs | -1.464 |
(£ | -1.460 |
Token | 22 |
Token ID | 2534 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
arij | +9.920 |
typ | +7.681 |
PHOTO | +7.625 |
Picture | +7.014 |
onel | +6.655 |
Neg logit contributions | |
stein | -12.755 |
yre | -12.203 |
uterus | -12.009 |
ドラ | -11.987 |
chair | -11.984 |
Token | 23 |
Token ID | 2242 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
arij | +0.241 |
typ | +0.199 |
PHOTO | +0.181 |
onel | +0.174 |
Picture | +0.169 |
Neg logit contributions | |
stein | -0.222 |
strings | -0.218 |
uterus | -0.214 |
chairs | -0.210 |
(£ | -0.208 |
Token | 24 |
Token ID | 1987 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
arij | +6.919 |
typ | +5.528 |
PHOTO | +5.217 |
Picture | +4.789 |
onel | +4.458 |
Neg logit contributions | |
stein | -9.718 |
strings | -9.267 |
chair | -9.150 |
ドラ | -9.140 |
chairs | -9.113 |
Token | 25 |
Token ID | 1679 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
arij | +1.961 |
typ | +1.639 |
PHOTO | +1.504 |
onel | +1.428 |
Picture | +1.403 |
Neg logit contributions | |
stein | -1.789 |
strings | -1.752 |
uterus | -1.729 |
chairs | -1.702 |
(£ | -1.687 |
Token | 26 |
Token ID | 2608 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
arij | +3.964 |
typ | +3.189 |
PHOTO | +2.941 |
Picture | +2.714 |
onel | +2.549 |
Neg logit contributions | |
stein | -6.695 |
strings | -6.644 |
chairs | -6.589 |
uterus | -6.444 |
chair | -6.441 |
Token | , |
Token ID | 11 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
stein | +1.699 |
strings | +1.646 |
(£ | +1.599 |
uterus | +1.587 |
chairs | +1.521 |
Neg logit contributions | |
arij | -3.013 |
typ | -2.578 |
PHOTO | -2.351 |
onel | -2.342 |
adier | -2.250 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
stein | +2.648 |
strings | +2.544 |
uterus | +2.479 |
(£ | +2.443 |
chairs | +2.342 |
Neg logit contributions | |
arij | -5.693 |
typ | -4.877 |
onel | -4.482 |
PHOTO | -4.386 |
adier | -4.321 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
stein | +3.842 |
strings | +3.740 |
(£ | +3.711 |
uterus | +3.611 |
chairs | +3.436 |
Neg logit contributions | |
arij | -6.919 |
typ | -6.000 |
PHOTO | -5.419 |
onel | -5.384 |
adier | -5.184 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
stein | +0.119 |
strings | +0.117 |
uterus | +0.113 |
(£ | +0.110 |
chairs | +0.110 |
Neg logit contributions | |
arij | -0.189 |
typ | -0.161 |
PHOTO | -0.146 |
onel | -0.145 |
adier | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
stein | +0.168 |
strings | +0.165 |
uterus | +0.156 |
(£ | +0.155 |
chairs | +0.153 |
Neg logit contributions | |
arij | -0.296 |
typ | -0.249 |
PHOTO | -0.228 |
onel | -0.227 |
ativity | -0.218 |
Token | [ |
Token ID | 58 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
arij | +0.603 |
typ | +0.536 |
PHOTO | +0.507 |
onel | +0.501 |
Picture | +0.490 |
Neg logit contributions | |
stein | -0.079 |
strings | -0.074 |
uterus | -0.060 |
chairs | -0.057 |
(£ | -0.055 |
Token | 22 |
Token ID | 1828 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
arij | +6.777 |
typ | +5.450 |
actionDate | +4.422 |
ART | +4.278 |
onel | +4.216 |
Neg logit contributions | |
uterus | -15.539 |
foss | -15.074 |
strings | -14.602 |
ドラ | -14.590 |
stein | -14.546 |
Token | ] |
Token ID | 60 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
arij | +0.284 |
typ | +0.248 |
PHOTO | +0.231 |
onel | +0.230 |
adier | +0.222 |
Neg logit contributions | |
stein | -0.085 |
strings | -0.082 |
uterus | -0.076 |
(£ | -0.074 |
chairs | -0.073 |
Token | Literally |
Token ID | 48414 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
arij | +0.548 |
typ | +0.464 |
PHOTO | +0.420 |
onel | +0.417 |
adier | +0.399 |
Neg logit contributions | |
stein | -0.366 |
strings | -0.359 |
uterus | -0.349 |
(£ | -0.339 |
chairs | -0.338 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
stein | +0.151 |
strings | +0.149 |
uterus | +0.145 |
(£ | +0.141 |
chairs | +0.138 |
Neg logit contributions | |
arij | -0.270 |
typ | -0.230 |
PHOTO | -0.211 |
onel | -0.209 |
adier | -0.201 |
Token | R |
Token ID | 371 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
stein | +0.077 |
strings | +0.075 |
uterus | +0.074 |
(£ | +0.071 |
chairs | +0.071 |
Neg logit contributions | |
arij | -0.125 |
typ | -0.106 |
PHOTO | -0.097 |
onel | -0.096 |
adier | -0.092 |
Token | 6 |
Token ID | 21 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
arij | +2.301 |
typ | +1.992 |
PHOTO | +1.815 |
onel | +1.803 |
adier | +1.736 |
Neg logit contributions | |
stein | -1.198 |
strings | -1.181 |
uterus | -1.149 |
chairs | -1.106 |
(£ | -1.104 |
Token | { |
Token ID | 1391 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
arij | +5.497 |
typ | +4.785 |
PHOTO | +4.322 |
onel | +4.225 |
Picture | +4.145 |
Neg logit contributions | |
stein | -3.950 |
strings | -3.877 |
uterus | -3.829 |
chairs | -3.716 |
yre | -3.625 |
Token | ( |
Token ID | 7 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
arij | +3.691 |
typ | +3.224 |
PHOTO | +2.911 |
onel | +2.895 |
Picture | +2.794 |
Neg logit contributions | |
stein | -2.112 |
strings | -2.088 |
uterus | -2.073 |
chairs | -1.964 |
(£ | -1.949 |
Token | 44 |
Token ID | 2598 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
arij | +2.461 |
typ | +2.079 |
PHOTO | +1.873 |
onel | +1.853 |
Picture | +1.774 |
Neg logit contributions | |
stein | -1.791 |
strings | -1.770 |
uterus | -1.722 |
(£ | -1.676 |
chairs | -1.675 |
Token | s |
Token ID | 82 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
stein | +1.358 |
strings | +1.337 |
uterus | +1.286 |
chairs | +1.249 |
(£ | +1.248 |
Neg logit contributions | |
arij | -2.627 |
typ | -2.266 |
PHOTO | -2.077 |
onel | -2.055 |
Picture | -1.982 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
arij | +3.662 |
typ | +3.050 |
PHOTO | +2.673 |
onel | +2.656 |
Picture | +2.526 |
Neg logit contributions | |
stein | -3.586 |
strings | -3.563 |
uterus | -3.541 |
chairs | -3.418 |
(£ | -3.415 |
Token | 22 |
Token ID | 2534 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
arij | +8.310 |
typ | +5.778 |
PHOTO | +5.687 |
onel | +5.090 |
Picture | +5.040 |
Neg logit contributions | |
stein | -13.904 |
uterus | -13.425 |
ドラ | -13.204 |
yre | -13.152 |
strings | -13.143 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
arij | +1.894 |
typ | +1.597 |
PHOTO | +1.434 |
onel | +1.418 |
Picture | +1.359 |
Neg logit contributions | |
stein | -1.452 |
strings | -1.437 |
uterus | -1.402 |
chairs | -1.363 |
(£ | -1.361 |
Token | R |
Token ID | 371 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
arij | +4.714 |
typ | +3.964 |
PHOTO | +3.580 |
onel | +3.482 |
Picture | +3.418 |
Neg logit contributions | |
stein | -3.745 |
strings | -3.683 |
uterus | -3.586 |
chairs | -3.528 |
(£ | -3.446 |
Token | c |
Token ID | 66 |
Feature activation | -1.35e-04 |
Pos logit contributions | |
arij | +6.780 |
typ | +5.850 |
onel | +5.163 |
PHOTO | +5.066 |
adier | +4.965 |
Neg logit contributions | |
uterus | -4.735 |
stein | -4.694 |
strings | -4.656 |
chairs | -4.393 |
(£ | -4.367 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
arij | +0.001 |
typ | +0.001 |
PHOTO | +0.001 |
onel | +0.001 |
Picture | +0.001 |
Neg logit contributions | |
stein | -0.001 |
strings | -0.001 |
uterus | -0.001 |
(£ | -0.001 |
chairs | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
arij | +2.225 |
typ | +1.884 |
PHOTO | +1.722 |
onel | +1.691 |
Picture | +1.656 |
Neg logit contributions | |
strings | -1.509 |
stein | -1.508 |
uterus | -1.457 |
chairs | -1.412 |
(£ | -1.393 |
Token | Law |
Token ID | 3854 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
stein | +0.132 |
strings | +0.129 |
uterus | +0.126 |
(£ | +0.123 |
chairs | +0.122 |
Neg logit contributions | |
arij | -0.197 |
typ | -0.168 |
PHOTO | -0.152 |
onel | -0.151 |
adier | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
arij | +0.148 |
typ | +0.126 |
PHOTO | +0.114 |
onel | +0.114 |
adier | +0.109 |
Neg logit contributions | |
stein | -0.090 |
strings | -0.088 |
uterus | -0.086 |
(£ | -0.084 |
chairs | -0.083 |
Token | at |
Token ID | 379 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
arij | +2.279 |
typ | +1.933 |
PHOTO | +1.752 |
onel | +1.729 |
Picture | +1.667 |
Neg logit contributions | |
stein | -1.624 |
strings | -1.609 |
uterus | -1.556 |
chairs | -1.519 |
(£ | -1.513 |
Token | the |
Token ID | 262 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
stein | +2.993 |
strings | +2.891 |
uterus | +2.825 |
(£ | +2.787 |
chairs | +2.720 |
Neg logit contributions | |
arij | -4.200 |
typ | -3.527 |
PHOTO | -3.179 |
onel | -3.134 |
adier | -2.995 |
Token | McM |
Token ID | 15359 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
arij | +3.271 |
typ | +2.779 |
PHOTO | +2.523 |
onel | +2.488 |
Picture | +2.406 |
Neg logit contributions | |
stein | -2.284 |
strings | -2.255 |
uterus | -2.166 |
chairs | -2.137 |
(£ | -2.118 |
Token | urt |
Token ID | 3325 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
arij | +12.465 |
typ | +9.516 |
onel | +8.801 |
Picture | +8.524 |
adier | +8.321 |
Neg logit contributions | |
ドラ | -10.645 |
uterus | -10.631 |
stein | -10.605 |
strings | -10.563 |
王 | -10.117 |
Token | ry |
Token ID | 563 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
arij | +2.205 |
typ | +1.902 |
PHOTO | +1.734 |
onel | +1.728 |
Picture | +1.662 |
Neg logit contributions | |
stein | -1.209 |
strings | -1.196 |
uterus | -1.160 |
(£ | -1.120 |
chairs | -1.118 |
Token | Gardens |
Token ID | 29330 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
arij | +7.643 |
typ | +6.495 |
PHOTO | +6.066 |
Picture | +5.940 |
onel | +5.764 |
Neg logit contributions | |
strings | -5.475 |
stein | -5.254 |
uterus | -5.150 |
chairs | -5.072 |
ドラ | -4.915 |
Token | of |
Token ID | 286 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
arij | +4.918 |
typ | +4.168 |
PHOTO | +3.840 |
onel | +3.719 |
Picture | +3.685 |
Neg logit contributions | |
strings | -3.446 |
stein | -3.445 |
uterus | -3.320 |
chairs | -3.225 |
(£ | -3.176 |
Token | Justice |
Token ID | 4796 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
arij | +0.884 |
typ | +0.748 |
PHOTO | +0.674 |
onel | +0.668 |
adier | +0.639 |
Neg logit contributions | |
stein | -0.624 |
strings | -0.615 |
uterus | -0.598 |
(£ | -0.582 |
chairs | -0.582 |
Token | days |
Token ID | 1528 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
arij | +2.307 |
typ | +1.957 |
PHOTO | +1.769 |
onel | +1.756 |
Picture | +1.681 |
Neg logit contributions | |
stein | -1.580 |
strings | -1.562 |
uterus | -1.514 |
chairs | -1.478 |
(£ | -1.473 |
Token | of |
Token ID | 286 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
arij | +1.893 |
typ | +1.636 |
PHOTO | +1.502 |
onel | +1.482 |
Picture | +1.434 |
Neg logit contributions | |
stein | -0.932 |
strings | -0.915 |
uterus | -0.883 |
(£ | -0.857 |
chairs | -0.852 |
Token | fighting |
Token ID | 4330 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
arij | +3.825 |
typ | +3.250 |
PHOTO | +2.951 |
onel | +2.949 |
Picture | +2.819 |
Neg logit contributions | |
stein | -2.516 |
strings | -2.508 |
uterus | -2.404 |
chairs | -2.362 |
(£ | -2.344 |
Token | .[ |
Token ID | 3693 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
arij | +7.537 |
typ | +6.599 |
onel | +6.001 |
PHOTO | +5.940 |
adier | +5.738 |
Neg logit contributions | |
strings | -3.872 |
stein | -3.857 |
uterus | -3.722 |
chairs | -3.587 |
chair | -3.508 |
Token | 31 |
Token ID | 3132 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
arij | +7.065 |
typ | +6.258 |
PHOTO | +5.456 |
onel | +5.428 |
ART | +5.127 |
Neg logit contributions | |
uterus | -7.089 |
stein | -6.906 |
strings | -6.891 |
(£ | -6.659 |
chairs | -6.647 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
arij | +3.971 |
typ | +3.521 |
PHOTO | +3.228 |
onel | +3.212 |
Picture | +3.114 |
Neg logit contributions | |
stein | -1.686 |
strings | -1.668 |
uterus | -1.625 |
chairs | -1.566 |
(£ | -1.515 |
Token | 32 |
Token ID | 2624 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
arij | +8.742 |
typ | +7.931 |
onel | +6.519 |
adier | +5.797 |
TW | +5.766 |
Neg logit contributions | |
uterus | -12.746 |
stein | -12.128 |
ドラ | -11.998 |
(£ | -11.784 |
strings | -11.771 |
Token | ][ |
Token ID | 7131 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
arij | +0.538 |
typ | +0.473 |
PHOTO | +0.435 |
onel | +0.433 |
Picture | +0.419 |
Neg logit contributions | |
stein | -0.212 |
strings | -0.209 |
uterus | -0.202 |
chairs | -0.194 |
(£ | -0.191 |
Token | 33 |
Token ID | 2091 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
arij | +3.012 |
typ | +2.534 |
onel | +2.138 |
PHOTO | +2.071 |
adier | +1.996 |
Neg logit contributions | |
stein | -3.678 |
uterus | -3.649 |
strings | -3.625 |
(£ | -3.535 |
chairs | -3.507 |
Token | ] |
Token ID | 60 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
arij | +2.434 |
typ | +2.140 |
PHOTO | +1.956 |
onel | +1.944 |
adier | +1.887 |
Neg logit contributions | |
stein | -1.070 |
strings | -1.058 |
uterus | -1.024 |
chairs | -0.994 |
(£ | -0.963 |
Token |
|
Token ID | 198 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
arij | +3.112 |
typ | +2.661 |
PHOTO | +2.419 |
onel | +2.394 |
Picture | +2.307 |
Neg logit contributions | |
stein | -2.048 |
strings | -2.025 |
uterus | -1.978 |
chairs | -1.919 |
(£ | -1.906 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
stein | +1.148 |
strings | +1.122 |
uterus | +1.080 |
chairs | +1.072 |
(£ | +1.052 |
Neg logit contributions | |
arij | -1.618 |
typ | -1.349 |
PHOTO | -1.224 |
onel | -1.214 |
ativity | -1.153 |
Token | switch |
Token ID | 5078 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
stein | +0.885 |
strings | +0.851 |
uterus | +0.848 |
(£ | +0.820 |
chairs | +0.811 |
Neg logit contributions | |
arij | -1.328 |
typ | -1.110 |
PHOTO | -1.003 |
onel | -1.001 |
adier | -0.956 |
Token | , |
Token ID | 11 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
arij | +0.695 |
typ | +0.590 |
PHOTO | +0.540 |
onel | +0.536 |
adier | +0.514 |
Neg logit contributions | |
stein | -0.410 |
strings | -0.403 |
uterus | -0.388 |
(£ | -0.379 |
chairs | -0.378 |
Token | just |
Token ID | 655 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
arij | +0.928 |
typ | +0.782 |
PHOTO | +0.708 |
onel | +0.704 |
adier | +0.674 |
Neg logit contributions | |
stein | -0.597 |
strings | -0.588 |
uterus | -0.575 |
(£ | -0.556 |
chairs | -0.555 |
Token | leave |
Token ID | 2666 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
arij | +5.550 |
typ | +4.735 |
PHOTO | +4.296 |
onel | +4.212 |
Picture | +4.087 |
Neg logit contributions | |
stein | -4.116 |
strings | -4.115 |
uterus | -3.900 |
chairs | -3.864 |
(£ | -3.840 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
arij | +5.498 |
typ | +4.671 |
PHOTO | +4.147 |
onel | +4.079 |
Picture | +3.941 |
Neg logit contributions | |
stein | -5.093 |
strings | -5.059 |
uterus | -4.913 |
chairs | -4.820 |
(£ | -4.800 |
Token | alone |
Token ID | 3436 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
arij | +11.766 |
typ | +10.220 |
onel | +9.405 |
PHOTO | +9.313 |
Picture | +8.927 |
Neg logit contributions | |
strings | -9.743 |
stein | -9.254 |
uterus | -9.178 |
chairs | -9.141 |
ドラ | -9.099 |
Token | ). |
Token ID | 737 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
arij | +5.943 |
typ | +5.132 |
PHOTO | +4.602 |
onel | +4.550 |
Picture | +4.398 |
Neg logit contributions | |
strings | -4.018 |
stein | -4.010 |
uterus | -3.882 |
chairs | -3.772 |
(£ | -3.749 |
Token | We |
Token ID | 775 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
stein | +2.274 |
strings | +2.223 |
(£ | +2.110 |
uterus | +2.056 |
Shades | +2.049 |
Neg logit contributions | |
arij | -4.090 |
typ | -3.358 |
onel | -3.068 |
allery | -2.996 |
PHOTO | -2.983 |
Token | also |
Token ID | 635 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
arij | +2.910 |
typ | +2.480 |
PHOTO | +2.249 |
onel | +2.230 |
Picture | +2.141 |
Neg logit contributions | |
stein | -1.848 |
strings | -1.827 |
uterus | -1.772 |
chairs | -1.720 |
(£ | -1.719 |
Token | discussed |
Token ID | 6693 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
arij | +2.388 |
typ | +2.057 |
PHOTO | +1.879 |
onel | +1.862 |
Picture | +1.793 |
Neg logit contributions | |
stein | -1.287 |
strings | -1.267 |
uterus | -1.225 |
(£ | -1.186 |
chairs | -1.185 |
Token | ) |
Token ID | 8 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
arij | +0.986 |
typ | +0.832 |
PHOTO | +0.758 |
onel | +0.753 |
ativity | +0.722 |
Neg logit contributions | |
stein | -0.603 |
strings | -0.592 |
uterus | -0.565 |
(£ | -0.555 |
chairs | -0.555 |
Token | ( |
Token ID | 357 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
stein | +1.165 |
strings | +1.122 |
(£ | +1.099 |
uterus | +1.044 |
chairs | +1.017 |
Neg logit contributions | |
arij | -3.056 |
typ | -2.602 |
onel | -2.408 |
PHOTO | -2.376 |
allery | -2.348 |
Token | 25 |
Token ID | 1495 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
arij | +3.282 |
typ | +2.770 |
PHOTO | +2.463 |
onel | +2.435 |
Picture | +2.324 |
Neg logit contributions | |
stein | -2.741 |
strings | -2.715 |
uterus | -2.675 |
(£ | -2.586 |
chairs | -2.584 |
Token | ) |
Token ID | 8 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
arij | +1.552 |
typ | +1.314 |
PHOTO | +1.195 |
onel | +1.186 |
adier | +1.135 |
Neg logit contributions | |
stein | -0.975 |
strings | -0.959 |
uterus | -0.923 |
(£ | -0.902 |
chairs | -0.902 |
Token |
|
Token ID | 198 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
arij | +0.857 |
typ | +0.724 |
PHOTO | +0.665 |
onel | +0.644 |
Picture | +0.634 |
Neg logit contributions | |
stein | -0.633 |
strings | -0.622 |
uterus | -0.605 |
chairs | -0.590 |
(£ | -0.585 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
stein | +0.311 |
strings | +0.305 |
uterus | +0.287 |
(£ | +0.287 |
chairs | +0.284 |
Neg logit contributions | |
arij | -0.555 |
typ | -0.467 |
PHOTO | -0.428 |
onel | -0.425 |
ativity | -0.410 |
Token | 22 |
Token ID | 1828 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
arij | +9.733 |
typ | +8.609 |
TW | +7.696 |
PHOTO | +7.589 |
ART | +7.332 |
Neg logit contributions | |
uterus | -11.302 |
stein | -10.870 |
feathers | -10.455 |
strings | -10.443 |
Ic | -10.426 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
stein | +0.565 |
strings | +0.549 |
(£ | +0.523 |
uterus | +0.520 |
chairs | +0.514 |
Neg logit contributions | |
arij | -0.867 |
typ | -0.723 |
onel | -0.651 |
PHOTO | -0.651 |
ativity | -0.628 |
Token | Nick |
Token ID | 8047 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
stein | +0.172 |
strings | +0.169 |
uterus | +0.163 |
(£ | +0.161 |
chairs | +0.158 |
Neg logit contributions | |
arij | -0.266 |
typ | -0.227 |
PHOTO | -0.205 |
onel | -0.203 |
ativity | -0.194 |
Token | Gr |
Token ID | 1902 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
stein | +1.243 |
strings | +1.216 |
(£ | +1.173 |
uterus | +1.170 |
chairs | +1.148 |
Neg logit contributions | |
arij | -1.658 |
typ | -1.405 |
PHOTO | -1.257 |
onel | -1.243 |
ativity | -1.195 |
Token | igg |
Token ID | 6950 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
stein | +0.011 |
strings | +0.011 |
uterus | +0.010 |
(£ | +0.010 |
chairs | +0.010 |
Neg logit contributions | |
arij | -0.021 |
typ | -0.018 |
PHOTO | -0.017 |
onel | -0.016 |
Picture | -0.016 |
Token | x |
Token ID | 2124 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
arij | +2.919 |
typ | +2.488 |
PHOTO | +2.254 |
onel | +2.217 |
Picture | +2.148 |
Neg logit contributions | |
stein | -2.003 |
strings | -1.981 |
uterus | -1.922 |
chairs | -1.879 |
(£ | -1.861 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
stein | +0.637 |
strings | +0.624 |
(£ | +0.591 |
uterus | +0.587 |
chairs | +0.583 |
Neg logit contributions | |
arij | -0.968 |
typ | -0.800 |
PHOTO | -0.733 |
onel | -0.725 |
ativity | -0.700 |
Token | x |
Token ID | 87 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
stein | +2.652 |
strings | +2.515 |
chair | +2.199 |
chairs | +2.150 |
(£ | +2.145 |
Neg logit contributions | |
arij | -8.881 |
typ | -7.238 |
PHOTO | -7.234 |
allery | -7.222 |
ailability | -7.077 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
arij | +1.442 |
typ | +1.215 |
PHOTO | +1.092 |
onel | +1.081 |
Picture | +1.033 |
Neg logit contributions | |
stein | -1.091 |
strings | -1.079 |
uterus | -1.050 |
chairs | -1.022 |
(£ | -1.022 |
Token | x |
Token ID | 87 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
stein | +1.630 |
strings | +1.567 |
(£ | +1.392 |
chair | +1.389 |
chairs | +1.384 |
Neg logit contributions | |
arij | -4.708 |
typ | -3.929 |
PHOTO | -3.828 |
onel | -3.728 |
allery | -3.727 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
arij | +6.700 |
typ | +6.020 |
onel | +4.990 |
PHOTO | +4.980 |
chel | +4.872 |
Neg logit contributions | |
uterus | -8.103 |
strings | -7.885 |
ドラ | -7.758 |
stein | -7.678 |
chairs | -7.672 |
Token | 94 |
Token ID | 5824 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
arij | +5.580 |
typ | +4.914 |
cade | +3.040 |
onel | +3.008 |
chel | +2.917 |
Neg logit contributions | |
ドラ | -15.972 |
strings | -15.816 |
uterus | -15.768 |
stein | -15.447 |
horns | -15.290 |
Token | 112 |
Token ID | 13539 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
arij | +2.380 |
typ | +1.977 |
PHOTO | +1.761 |
onel | +1.727 |
Picture | +1.660 |
Neg logit contributions | |
stein | -2.217 |
strings | -2.196 |
uterus | -2.155 |
chairs | -2.104 |
(£ | -2.089 |
Token | 89 |
Token ID | 4531 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
arij | +1.161 |
typ | +0.965 |
PHOTO | +0.870 |
onel | +0.865 |
adier | +0.825 |
Neg logit contributions | |
stein | -0.884 |
strings | -0.872 |
uterus | -0.836 |
(£ | -0.826 |
chairs | -0.822 |
Token | 62 |
Token ID | 5237 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
arij | +0.987 |
typ | +0.818 |
PHOTO | +0.738 |
onel | +0.734 |
adier | +0.703 |
Neg logit contributions | |
stein | -0.743 |
strings | -0.731 |
uterus | -0.705 |
(£ | -0.695 |
chairs | -0.691 |
Token | x |
Token ID | 2124 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
arij | +1.206 |
typ | +1.024 |
PHOTO | +0.928 |
onel | +0.924 |
adier | +0.885 |
Neg logit contributions | |
stein | -0.753 |
strings | -0.743 |
uterus | -0.720 |
(£ | -0.702 |
chairs | -0.696 |
Token | hi |
Token ID | 5303 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
arij | +6.774 |
typ | +5.882 |
onel | +5.341 |
PHOTO | +5.323 |
adier | +5.137 |
Neg logit contributions | |
strings | -3.233 |
stein | -3.226 |
uterus | -3.186 |
chairs | -3.039 |
(£ | -3.014 |
Token | w |
Token ID | 86 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
arij | +2.776 |
typ | +2.357 |
PHOTO | +2.116 |
onel | +2.104 |
adier | +2.018 |
Neg logit contributions | |
stein | -1.927 |
strings | -1.912 |
uterus | -1.871 |
chairs | -1.822 |
(£ | -1.810 |
Token | ani |
Token ID | 3216 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
arij | +0.045 |
typ | +0.038 |
PHOTO | +0.035 |
onel | +0.034 |
Picture | +0.033 |
Neg logit contributions | |
stein | -0.030 |
strings | -0.029 |
uterus | -0.028 |
(£ | -0.028 |
chairs | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
arij | +1.306 |
typ | +1.113 |
PHOTO | +1.009 |
onel | +0.997 |
Picture | +0.962 |
Neg logit contributions | |
stein | -0.848 |
strings | -0.839 |
uterus | -0.813 |
chairs | -0.792 |
(£ | -0.787 |
Token | J |
Token ID | 449 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
arij | +4.960 |
typ | +4.174 |
PHOTO | +3.748 |
onel | +3.682 |
Picture | +3.600 |
Neg logit contributions | |
strings | -4.344 |
stein | -4.322 |
uterus | -4.191 |
chairs | -4.123 |
(£ | -4.056 |
Token | h |
Token ID | 71 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
stein | +1.228 |
strings | +1.205 |
uterus | +1.152 |
chairs | +1.123 |
(£ | +1.120 |
Neg logit contributions | |
arij | -2.012 |
typ | -1.726 |
PHOTO | -1.585 |
onel | -1.544 |
Picture | -1.495 |
Token | aj |
Token ID | 1228 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
arij | +7.657 |
typ | +4.939 |
onel | +4.157 |
adier | +4.008 |
PHOTO | +3.754 |
Neg logit contributions | |
strings | -15.213 |
stein | -14.968 |
uterus | -14.896 |
ドラ | -14.827 |
chairs | -14.479 |
Token | jar |
Token ID | 9491 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
stein | +2.464 |
strings | +2.353 |
yre | +2.167 |
(£ | +2.129 |
chair | +2.116 |
Neg logit contributions | |
arij | -6.485 |
typ | -5.800 |
PHOTO | -5.389 |
ativity | -5.268 |
onel | -5.263 |
Token | and |
Token ID | 290 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
stein | +1.982 |
strings | +1.925 |
uterus | +1.869 |
(£ | +1.828 |
chairs | +1.772 |
Neg logit contributions | |
arij | -3.450 |
typ | -2.978 |
PHOTO | -2.733 |
onel | -2.692 |
adier | -2.570 |
Token | His |
Token ID | 2399 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
arij | +1.753 |
typ | +1.475 |
PHOTO | +1.325 |
onel | +1.311 |
adier | +1.252 |
Neg logit contributions | |
stein | -1.322 |
strings | -1.305 |
uterus | -1.272 |
(£ | -1.239 |
chairs | -1.236 |
Token | ar |
Token ID | 283 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
arij | +2.413 |
typ | +2.062 |
PHOTO | +1.877 |
onel | +1.852 |
Picture | +1.785 |
Neg logit contributions | |
stein | -1.519 |
strings | -1.493 |
uterus | -1.442 |
(£ | -1.406 |
chairs | -1.404 |
Token | final |
Token ID | 2457 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
arij | +1.639 |
typ | +1.379 |
PHOTO | +1.239 |
onel | +1.224 |
Picture | +1.169 |
Neg logit contributions | |
stein | -1.252 |
strings | -1.234 |
uterus | -1.203 |
(£ | -1.173 |
chairs | -1.169 |
Token | defeat |
Token ID | 7433 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
arij | +0.229 |
typ | +0.194 |
PHOTO | +0.176 |
onel | +0.172 |
adier | +0.167 |
Neg logit contributions | |
stein | -0.148 |
strings | -0.144 |
uterus | -0.141 |
(£ | -0.138 |
chairs | -0.135 |
Token | at |
Token ID | 379 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
arij | +3.207 |
typ | +2.725 |
PHOTO | +2.457 |
onel | +2.438 |
Picture | +2.338 |
Neg logit contributions | |
stein | -2.204 |
strings | -2.183 |
uterus | -2.123 |
chairs | -2.070 |
(£ | -2.053 |
Token | Lub |
Token ID | 40753 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
arij | +2.364 |
typ | +1.994 |
PHOTO | +1.796 |
onel | +1.779 |
Picture | +1.705 |
Neg logit contributions | |
stein | -1.730 |
strings | -1.714 |
uterus | -1.664 |
chairs | -1.623 |
(£ | -1.620 |
Token | lin |
Token ID | 2815 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
arij | +1.520 |
typ | +1.264 |
PHOTO | +1.107 |
onel | +1.103 |
adier | +1.050 |
Neg logit contributions | |
strings | -1.409 |
stein | -1.407 |
uterus | -1.377 |
(£ | -1.339 |
chairs | -1.338 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
arij | +1.259 |
typ | +1.085 |
PHOTO | +0.994 |
onel | +0.983 |
Picture | +0.947 |
Neg logit contributions | |
stein | -0.653 |
strings | -0.640 |
uterus | -0.619 |
(£ | -0.601 |
chairs | -0.596 |
Token | 23 |
Token ID | 1954 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
arij | +9.464 |
typ | +8.284 |
PHOTO | +6.929 |
ART | +6.675 |
chel | +6.623 |
Neg logit contributions | |
uterus | -11.533 |
stein | -11.111 |
strings | -11.096 |
ドラ | -10.902 |
Shades | -10.707 |
Token | ] |
Token ID | 60 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
arij | +4.176 |
typ | +3.676 |
PHOTO | +3.369 |
onel | +3.338 |
Picture | +3.260 |
Neg logit contributions | |
strings | -1.777 |
stein | -1.770 |
uterus | -1.693 |
chairs | -1.664 |
(£ | -1.579 |
Token |
|
Token ID | 198 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
arij | +2.948 |
typ | +2.510 |
PHOTO | +2.276 |
onel | +2.252 |
Picture | +2.163 |
Neg logit contributions | |
stein | -1.920 |
strings | -1.896 |
uterus | -1.841 |
chairs | -1.788 |
(£ | -1.787 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
arij | +0.785 |
typ | +0.665 |
PHOTO | +0.606 |
onel | +0.601 |
adier | +0.576 |
Neg logit contributions | |
stein | -0.472 |
strings | -0.464 |
uterus | -0.445 |
(£ | -0.437 |
chairs | -0.435 |
Token | Hist |
Token ID | 13749 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
arij | +1.551 |
typ | +1.287 |
PHOTO | +1.166 |
onel | +1.146 |
Picture | +1.098 |
Neg logit contributions | |
stein | -1.210 |
strings | -1.194 |
uterus | -1.149 |
chairs | -1.131 |
(£ | -1.126 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
arij | +4.319 |
typ | +3.609 |
PHOTO | +3.265 |
onel | +3.089 |
Picture | +3.030 |
Neg logit contributions | |
stein | -4.531 |
strings | -4.369 |
uterus | -4.304 |
chairs | -4.268 |
yre | -4.238 |
Token | 17 |
Token ID | 1596 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
strings | +2.414 |
stein | +2.401 |
uterus | +2.293 |
(£ | +2.222 |
chairs | +2.187 |
Neg logit contributions | |
arij | -5.164 |
typ | -4.441 |
onel | -4.062 |
PHOTO | -4.043 |
adier | -3.925 |
Token | 18 |
Token ID | 1248 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
arij | +2.869 |
typ | +2.400 |
PHOTO | +2.196 |
onel | +2.073 |
Picture | +2.031 |
Neg logit contributions | |
stein | -2.822 |
strings | -2.720 |
uterus | -2.654 |
chairs | -2.647 |
chair | -2.609 |
Token | 19 |
Token ID | 678 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
stein | +1.558 |
strings | +1.536 |
uterus | +1.483 |
(£ | +1.435 |
chairs | +1.433 |
Neg logit contributions | |
arij | -2.995 |
typ | -2.582 |
PHOTO | -2.360 |
onel | -2.342 |
Picture | -2.255 |
Token | 20 |
Token ID | 1160 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
arij | +5.579 |
typ | +4.870 |
PHOTO | +4.494 |
Picture | +4.094 |
onel | +4.054 |
Neg logit contributions | |
stein | -5.792 |
strings | -5.444 |
uterus | -5.439 |
chairs | -5.373 |
yre | -5.358 |
Token | 21 |
Token ID | 2310 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
arij | +3.303 |
typ | +2.716 |
PHOTO | +2.475 |
onel | +2.308 |
Picture | +2.270 |
Neg logit contributions | |
stein | -4.012 |
strings | -3.950 |
uterus | -3.846 |
chairs | -3.824 |
(£ | -3.820 |
Token | 22 |
Token ID | 2534 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
arij | +8.956 |
typ | +7.087 |
PHOTO | +7.051 |
onel | +6.094 |
Picture | +6.061 |
Neg logit contributions | |
stein | -11.643 |
yre | -11.370 |
uterus | -11.219 |
ドラ | -11.195 |
王 | -11.154 |
Token | 23 |
Token ID | 2242 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
arij | +4.369 |
typ | +3.556 |
PHOTO | +3.404 |
Picture | +3.011 |
onel | +2.979 |
Neg logit contributions | |
stein | -4.929 |
strings | -4.843 |
uterus | -4.764 |
chairs | -4.698 |
ドラ | -4.634 |
Token | 24 |
Token ID | 1987 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
arij | +8.183 |
typ | +6.720 |
PHOTO | +6.627 |
Picture | +5.809 |
actionDate | +5.786 |
Neg logit contributions | |
stein | -10.403 |
strings | -9.924 |
ドラ | -9.906 |
uterus | -9.898 |
chair | -9.699 |
Token | 25 |
Token ID | 1679 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
arij | +4.535 |
typ | +3.831 |
PHOTO | +3.658 |
onel | +3.255 |
Picture | +3.243 |
Neg logit contributions | |
stein | -4.698 |
uterus | -4.584 |
strings | -4.567 |
chairs | -4.499 |
(£ | -4.422 |
Token | 26 |
Token ID | 2608 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
arij | +4.616 |
typ | +3.804 |
PHOTO | +3.568 |
onel | +3.116 |
Picture | +3.112 |
Neg logit contributions | |
stein | -6.863 |
strings | -6.804 |
uterus | -6.708 |
chairs | -6.658 |
(£ | -6.526 |
Token | it |
Token ID | 270 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
arij | +1.882 |
typ | +1.547 |
PHOTO | +1.364 |
onel | +1.352 |
adier | +1.287 |
Neg logit contributions | |
stein | -1.801 |
strings | -1.786 |
uterus | -1.746 |
chairs | -1.705 |
(£ | -1.702 |
Token | en |
Token ID | 551 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
stein | +0.250 |
strings | +0.246 |
uterus | +0.240 |
(£ | +0.236 |
chairs | +0.233 |
Neg logit contributions | |
arij | -0.308 |
typ | -0.255 |
PHOTO | -0.232 |
onel | -0.227 |
Picture | -0.219 |
Token | vers |
Token ID | 690 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
stein | +2.287 |
strings | +2.248 |
uterus | +2.199 |
(£ | +2.135 |
chairs | +2.091 |
Neg logit contributions | |
arij | -3.163 |
typ | -2.620 |
PHOTO | -2.396 |
onel | -2.346 |
Picture | -2.277 |
Token | vot |
Token ID | 1993 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
stein | +2.481 |
strings | +2.407 |
uterus | +2.383 |
(£ | +2.337 |
chairs | +2.280 |
Neg logit contributions | |
arij | -3.411 |
typ | -2.822 |
PHOTO | -2.574 |
onel | -2.507 |
Picture | -2.435 |
Token | re |
Token ID | 260 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
arij | +2.635 |
typ | +2.264 |
PHOTO | +2.061 |
onel | +2.047 |
Picture | +1.966 |
Neg logit contributions | |
stein | -1.494 |
strings | -1.474 |
uterus | -1.427 |
(£ | -1.382 |
chairs | -1.381 |
Token | p |
Token ID | 279 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
arij | +3.229 |
typ | +2.745 |
PHOTO | +2.468 |
onel | +2.450 |
Picture | +2.339 |
Neg logit contributions | |
stein | -2.375 |
strings | -2.357 |
uterus | -2.271 |
chairs | -2.221 |
(£ | -2.215 |
Token | ère |
Token ID | 35979 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
arij | +11.559 |
typ | +9.747 |
onel | +8.802 |
adier | +8.678 |
chel | +8.271 |
Neg logit contributions | |
uterus | -9.562 |
strings | -9.459 |
stein | -9.379 |
Ic | -9.325 |
Shades | -9.245 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
arij | +3.676 |
typ | +3.143 |
PHOTO | +2.815 |
onel | +2.797 |
adier | +2.666 |
Neg logit contributions | |
stein | -2.730 |
strings | -2.705 |
uterus | -2.632 |
chairs | -2.563 |
(£ | -2.548 |
Token | v |
Token ID | 410 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
arij | +3.586 |
typ | +3.021 |
PHOTO | +2.692 |
onel | +2.681 |
Picture | +2.543 |
Neg logit contributions | |
stein | -3.004 |
strings | -2.979 |
uterus | -2.885 |
chairs | -2.828 |
(£ | -2.806 |
Token | ous |
Token ID | 516 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
stein | +1.081 |
strings | +1.053 |
uterus | +1.017 |
(£ | +1.002 |
chairs | +0.993 |
Neg logit contributions | |
arij | -1.317 |
typ | -1.094 |
PHOTO | -1.007 |
onel | -0.953 |
Picture | -0.938 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
stein | +1.183 |
strings | +1.158 |
uterus | +1.143 |
(£ | +1.115 |
chairs | +1.096 |
Neg logit contributions | |
arij | -1.601 |
typ | -1.337 |
PHOTO | -1.216 |
onel | -1.185 |
adier | -1.145 |
Token | Kop |
Token ID | 40500 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
arij | +6.335 |
typ | +5.245 |
PHOTO | +4.646 |
onel | +4.611 |
Picture | +4.394 |
Neg logit contributions | |
stein | -5.844 |
strings | -5.802 |
uterus | -5.674 |
chairs | -5.552 |
(£ | -5.478 |
Token | onen |
Token ID | 34481 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
arij | +5.443 |
typ | +4.742 |
onel | +4.280 |
PHOTO | +4.258 |
chel | +4.127 |
Neg logit contributions | |
strings | -2.730 |
stein | -2.710 |
uterus | -2.677 |
chairs | -2.542 |
(£ | -2.542 |
Token | ( |
Token ID | 357 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
stein | +0.573 |
strings | +0.565 |
uterus | +0.548 |
(£ | +0.533 |
chairs | +0.532 |
Neg logit contributions | |
arij | -0.902 |
typ | -0.769 |
PHOTO | -0.698 |
onel | -0.691 |
Picture | -0.663 |
Token | who |
Token ID | 8727 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
stein | +0.744 |
strings | +0.731 |
chairs | +0.687 |
uterus | +0.687 |
chair | +0.678 |
Neg logit contributions | |
arij | -1.331 |
typ | -1.118 |
PHOTO | -1.046 |
onel | -1.023 |
Picture | -0.993 |
Token | may |
Token ID | 743 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
arij | +0.669 |
typ | +0.572 |
PHOTO | +0.520 |
onel | +0.515 |
Picture | +0.494 |
Neg logit contributions | |
stein | -0.403 |
strings | -0.396 |
uterus | -0.384 |
(£ | -0.374 |
chairs | -0.372 |
Token | or |
Token ID | 393 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
stein | +2.448 |
strings | +2.391 |
uterus | +2.290 |
(£ | +2.260 |
chairs | +2.222 |
Neg logit contributions | |
arij | -3.899 |
typ | -3.256 |
PHOTO | -2.972 |
onel | -2.897 |
adier | -2.834 |
Token | may |
Token ID | 743 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
stein | +2.823 |
strings | +2.776 |
uterus | +2.720 |
(£ | +2.671 |
spirits | +2.445 |
Neg logit contributions | |
arij | -14.703 |
typ | -12.630 |
PHOTO | -11.903 |
actionDate | -11.749 |
allery | -11.640 |
Token | not |
Token ID | 407 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
stein | +0.714 |
strings | +0.705 |
uterus | +0.669 |
(£ | +0.645 |
chairs | +0.642 |
Neg logit contributions | |
arij | -1.756 |
typ | -1.510 |
PHOTO | -1.399 |
onel | -1.377 |
allery | -1.333 |
Token | take |
Token ID | 1011 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
stein | +2.527 |
strings | +2.439 |
uterus | +2.385 |
(£ | +2.330 |
chairs | +2.284 |
Neg logit contributions | |
arij | -3.748 |
typ | -3.155 |
PHOTO | -2.853 |
onel | -2.798 |
allery | -2.722 |
Token | an |
Token ID | 281 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
strings | +3.314 |
stein | +3.305 |
uterus | +3.128 |
(£ | +3.102 |
chair | +3.062 |
Neg logit contributions | |
arij | -4.842 |
typ | -4.055 |
onel | -3.675 |
PHOTO | -3.656 |
cade | -3.555 |
Token | actual |
Token ID | 4036 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
strings | +2.780 |
stein | +2.739 |
uterus | +2.628 |
(£ | +2.620 |
appendix | +2.485 |
Neg logit contributions | |
arij | -4.758 |
typ | -4.041 |
PHOTO | -3.657 |
onel | -3.621 |
cade | -3.532 |
Token |
|
Token ID | 198 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
stein | +1.323 |
strings | +1.301 |
uterus | +1.262 |
(£ | +1.229 |
chairs | +1.226 |
Neg logit contributions | |
arij | -2.137 |
typ | -1.822 |
PHOTO | -1.654 |
onel | -1.637 |
Picture | -1.572 |
Token |
|
Token ID | 198 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
stein | +0.212 |
strings | +0.208 |
uterus | +0.197 |
(£ | +0.197 |
chairs | +0.194 |
Neg logit contributions | |
arij | -0.377 |
typ | -0.316 |
PHOTO | -0.289 |
onel | -0.289 |
ativity | -0.278 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
stein | +2.069 |
strings | +2.030 |
(£ | +1.921 |
chair | +1.911 |
chairs | +1.911 |
Neg logit contributions | |
arij | -2.900 |
typ | -2.308 |
PHOTO | -2.149 |
onel | -2.112 |
allery | -2.048 |
Token | teens |
Token ID | 15508 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
arij | +1.950 |
typ | +1.665 |
PHOTO | +1.515 |
onel | +1.499 |
Picture | +1.443 |
Neg logit contributions | |
stein | -1.198 |
strings | -1.184 |
uterus | -1.147 |
chairs | -1.113 |
(£ | -1.112 |
Token | robbed |
Token ID | 26773 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
stein | +0.285 |
strings | +0.279 |
uterus | +0.272 |
(£ | +0.267 |
chairs | +0.263 |
Neg logit contributions | |
arij | -0.488 |
typ | -0.418 |
onel | -0.377 |
PHOTO | -0.376 |
adier | -0.361 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
arij | +1.366 |
typ | +1.158 |
PHOTO | +1.046 |
onel | +1.035 |
Picture | +0.993 |
Neg logit contributions | |
stein | -0.944 |
strings | -0.932 |
uterus | -0.905 |
chairs | -0.881 |
(£ | -0.880 |
Token | assaulted |
Token ID | 18513 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
stein | +5.418 |
uterus | +5.357 |
strings | +5.297 |
(£ | +5.195 |
horns | +5.129 |
Neg logit contributions | |
arij | -9.352 |
typ | -7.911 |
onel | -7.177 |
PHOTO | -6.977 |
allery | -6.916 |
Token | to |
Token ID | 284 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
stein | +0.258 |
strings | +0.253 |
uterus | +0.247 |
(£ | +0.242 |
chairs | +0.237 |
Neg logit contributions | |
arij | -0.436 |
typ | -0.371 |
onel | -0.338 |
PHOTO | -0.337 |
adier | -0.323 |
Token | death |
Token ID | 1918 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
stein | +1.008 |
strings | +0.989 |
uterus | +0.960 |
(£ | +0.939 |
chairs | +0.924 |
Neg logit contributions | |
arij | -1.474 |
typ | -1.253 |
PHOTO | -1.121 |
onel | -1.113 |
adier | -1.065 |
Token | Del |
Token ID | 4216 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
stein | +1.629 |
strings | +1.562 |
(£ | +1.527 |
uterus | +1.514 |
chairs | +1.455 |
Neg logit contributions | |
arij | -2.886 |
typ | -2.458 |
onel | -2.249 |
PHOTO | -2.216 |
adier | -2.170 |
Token | bert |
Token ID | 4835 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
stein | +0.051 |
strings | +0.049 |
uterus | +0.048 |
(£ | +0.047 |
chairs | +0.047 |
Neg logit contributions | |
arij | -0.066 |
typ | -0.055 |
PHOTO | -0.049 |
onel | -0.049 |
Picture | -0.047 |
Token | muscle |
Token ID | 8280 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
uterus | +1.525 |
stein | +1.521 |
strings | +1.489 |
(£ | +1.429 |
chairs | +1.391 |
Neg logit contributions | |
arij | -2.562 |
typ | -2.155 |
onel | -1.969 |
PHOTO | -1.960 |
allery | -1.884 |
Token | relax |
Token ID | 8960 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
arij | +4.752 |
typ | +4.086 |
PHOTO | +3.703 |
onel | +3.616 |
Picture | +3.462 |
Neg logit contributions | |
stein | -3.705 |
strings | -3.682 |
(£ | -3.525 |
uterus | -3.514 |
chairs | -3.495 |
Token | ant |
Token ID | 415 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
arij | +1.290 |
typ | +1.063 |
PHOTO | +0.944 |
onel | +0.928 |
adier | +0.880 |
Neg logit contributions | |
stein | -1.226 |
strings | -1.208 |
uterus | -1.184 |
chairs | -1.153 |
(£ | -1.153 |
Token | effects |
Token ID | 3048 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
stein | +0.179 |
strings | +0.176 |
uterus | +0.171 |
(£ | +0.165 |
chairs | +0.163 |
Neg logit contributions | |
arij | -0.371 |
typ | -0.321 |
PHOTO | -0.294 |
onel | -0.292 |
adier | -0.282 |
Token | for |
Token ID | 329 |
Feature activation | +3.80e-03 |
Pos logit contributions | |
stein | +0.968 |
strings | +0.951 |
uterus | +0.923 |
(£ | +0.907 |
chairs | +0.873 |
Neg logit contributions | |
arij | -1.553 |
typ | -1.317 |
PHOTO | -1.207 |
onel | -1.183 |
adier | -1.150 |
Token | doses |
Token ID | 16376 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
stein | +0.024 |
strings | +0.023 |
uterus | +0.023 |
(£ | +0.022 |
chairs | +0.022 |
Neg logit contributions | |
arij | -0.035 |
typ | -0.030 |
PHOTO | -0.027 |
onel | -0.027 |
adier | -0.026 |
Token | up |
Token ID | 510 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
stein | +4.590 |
uterus | +4.431 |
strings | +4.291 |
(£ | +4.234 |
¶ | +3.924 |
Neg logit contributions | |
arij | -10.321 |
typ | -8.560 |
onel | -8.252 |
PHOTO | -8.136 |
actionDate | -8.058 |
Token | to |
Token ID | 284 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
stein | +3.350 |
strings | +3.228 |
uterus | +3.182 |
(£ | +3.146 |
¶ | +3.028 |
Neg logit contributions | |
arij | -6.688 |
typ | -5.692 |
onel | -5.303 |
PHOTO | -5.248 |
ativity | -5.212 |
Token | 100 |
Token ID | 1802 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
stein | +3.342 |
strings | +3.293 |
uterus | +3.273 |
(£ | +3.153 |
¶ | +3.003 |
Neg logit contributions | |
arij | -6.346 |
typ | -5.343 |
onel | -5.006 |
adier | -4.879 |
PHOTO | -4.854 |
Token | mg |
Token ID | 11296 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
stein | +4.147 |
strings | +4.076 |
uterus | +4.026 |
(£ | +3.888 |
chairs | +3.715 |
Neg logit contributions | |
arij | -8.045 |
typ | -6.805 |
PHOTO | -6.382 |
adier | -6.246 |
onel | -6.239 |
Token | / |
Token ID | 14 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
arij | +1.305 |
typ | +1.135 |
PHOTO | +1.044 |
onel | +1.035 |
Picture | +1.001 |
Neg logit contributions | |
stein | -0.574 |
strings | -0.566 |
uterus | -0.540 |
chairs | -0.526 |
(£ | -0.520 |
Token | | |
Token ID | 930 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
strings | +2.215 |
stein | +2.214 |
(£ | +2.086 |
uterus | +2.076 |
chairs | +2.010 |
Neg logit contributions | |
arij | -4.292 |
typ | -3.676 |
onel | -3.355 |
PHOTO | -3.309 |
actionDate | -3.234 |
Token | void |
Token ID | 7951 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
strings | +0.893 |
stein | +0.892 |
uterus | +0.854 |
(£ | +0.835 |
chairs | +0.820 |
Neg logit contributions | |
arij | -1.659 |
typ | -1.410 |
PHOTO | -1.290 |
onel | -1.289 |
adier | -1.244 |
Token | * |
Token ID | 1635 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
stein | +3.840 |
strings | +3.818 |
(£ | +3.686 |
uterus | +3.664 |
chairs | +3.467 |
Neg logit contributions | |
arij | -5.995 |
typ | -5.021 |
onel | -4.575 |
PHOTO | -4.478 |
actionDate | -4.448 |
Token | arg |
Token ID | 853 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
strings | +3.026 |
stein | +3.025 |
uterus | +2.845 |
(£ | +2.823 |
chairs | +2.754 |
Neg logit contributions | |
arij | -4.634 |
typ | -3.869 |
PHOTO | -3.575 |
onel | -3.546 |
ativity | -3.412 |
Token | | |
Token ID | 930 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
stein | +1.566 |
strings | +1.549 |
uterus | +1.446 |
(£ | +1.442 |
chairs | +1.426 |
Neg logit contributions | |
arij | -2.862 |
typ | -2.415 |
PHOTO | -2.245 |
onel | -2.199 |
Picture | -2.145 |
Token | - |
Token ID | 532 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
stein | +0.493 |
strings | +0.489 |
uterus | +0.471 |
(£ | +0.461 |
chairs | +0.451 |
Neg logit contributions | |
arij | -0.865 |
typ | -0.737 |
PHOTO | -0.672 |
onel | -0.667 |
adier | -0.645 |
Token | our |
Token ID | 674 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
strings | +5.993 |
stein | +5.896 |
(£ | +5.566 |
uterus | +5.481 |
¶ | +5.382 |
Neg logit contributions | |
arij | -8.701 |
typ | -7.052 |
PHOTO | -6.687 |
onel | -6.518 |
actionDate | -6.431 |
Token | buffer |
Token ID | 11876 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
arij | +0.035 |
typ | +0.030 |
PHOTO | +0.027 |
onel | +0.027 |
adier | +0.026 |
Neg logit contributions | |
stein | -0.023 |
strings | -0.023 |
uterus | -0.022 |
(£ | -0.021 |
chairs | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
stein | +4.395 |
strings | +4.375 |
(£ | +4.095 |
uterus | +4.009 |
chairs | +3.922 |
Neg logit contributions | |
arij | -7.579 |
typ | -6.380 |
onel | -5.859 |
PHOTO | -5.802 |
actionDate | -5.715 |
Token | 0 |
Token ID | 657 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
strings | +2.162 |
stein | +2.148 |
uterus | +2.086 |
(£ | +2.036 |
chairs | +1.982 |
Neg logit contributions | |
arij | -3.460 |
typ | -2.896 |
PHOTO | -2.633 |
onel | -2.625 |
chel | -2.537 |
Token | x |
Token ID | 87 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
strings | +3.866 |
stein | +3.824 |
(£ | +3.647 |
uterus | +3.433 |
chairs | +3.349 |
Neg logit contributions | |
arij | -9.087 |
typ | -7.645 |
PHOTO | -7.232 |
actionDate | -7.102 |
onel | -7.032 |
Token | team |
Token ID | 1074 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
strings | +2.416 |
stein | +2.399 |
uterus | +2.393 |
(£ | +2.245 |
chairs | +2.211 |
Neg logit contributions | |
arij | -4.194 |
typ | -3.578 |
PHOTO | -3.247 |
onel | -3.242 |
actionDate | -3.143 |
Token | ," |
Token ID | 553 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
stein | +0.202 |
strings | +0.201 |
uterus | +0.193 |
chairs | +0.188 |
(£ | +0.188 |
Neg logit contributions | |
arij | -0.337 |
typ | -0.286 |
PHOTO | -0.262 |
onel | -0.258 |
adier | -0.248 |
Token | C |
Token ID | 327 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
arij | +1.732 |
typ | +1.406 |
PHOTO | +1.233 |
onel | +1.210 |
Picture | +1.154 |
Neg logit contributions | |
stein | -2.003 |
strings | -1.990 |
uterus | -1.943 |
chairs | -1.903 |
(£ | -1.901 |
Token | ough |
Token ID | 619 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
stein | +2.252 |
strings | +2.142 |
uterus | +2.006 |
chair | +1.983 |
(£ | +1.963 |
Neg logit contributions | |
arij | -5.421 |
typ | -4.693 |
PHOTO | -4.476 |
onel | -4.308 |
actionDate | -4.243 |
Token | lin |
Token ID | 2815 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
arij | +3.733 |
typ | +3.168 |
onel | +2.733 |
PHOTO | +2.672 |
chel | +2.574 |
Neg logit contributions | |
uterus | -3.928 |
strings | -3.884 |
stein | -3.851 |
(£ | -3.783 |
chairs | -3.738 |
Token | said |
Token ID | 531 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
stein | +1.815 |
strings | +1.744 |
uterus | +1.681 |
(£ | +1.677 |
chairs | +1.637 |
Neg logit contributions | |
arij | -2.921 |
typ | -2.492 |
PHOTO | -2.243 |
onel | -2.209 |
actionDate | -2.160 |
Token | in |
Token ID | 287 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
stein | +5.565 |
(£ | +5.221 |
strings | +5.190 |
uterus | +4.851 |
digs | +4.781 |
Neg logit contributions | |
arij | -11.619 |
typ | -10.144 |
PHOTO | -9.314 |
allery | -9.097 |
actionDate | -9.065 |
Token | a |
Token ID | 257 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
stein | +5.165 |
strings | +5.145 |
uterus | +5.014 |
(£ | +5.007 |
Slate | +4.902 |
Neg logit contributions | |
arij | -8.247 |
typ | -7.094 |
onel | -6.365 |
PHOTO | -6.329 |
adier | -6.226 |
Token | statement |
Token ID | 2643 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
stein | +4.323 |
strings | +4.254 |
uterus | +4.197 |
(£ | +4.090 |
Slate | +4.025 |
Neg logit contributions | |
arij | -8.146 |
typ | -6.832 |
onel | -6.348 |
allery | -6.282 |
ativity | -6.154 |
Token | released |
Token ID | 2716 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
stein | +3.100 |
strings | +3.034 |
(£ | +2.967 |
uterus | +2.889 |
chairs | +2.810 |
Neg logit contributions | |
arij | -5.350 |
typ | -4.671 |
PHOTO | -4.182 |
onel | -4.136 |
actionDate | -4.065 |
Token | by |
Token ID | 416 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
stein | +2.589 |
strings | +2.486 |
(£ | +2.434 |
uterus | +2.402 |
chairs | +2.306 |
Neg logit contributions | |
arij | -5.278 |
typ | -4.605 |
onel | -4.161 |
PHOTO | -4.137 |
actionDate | -4.057 |
Token | 's |
Token ID | 338 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
stein | +0.969 |
strings | +0.940 |
uterus | +0.912 |
(£ | +0.902 |
chairs | +0.892 |
Neg logit contributions | |
arij | -1.662 |
typ | -1.419 |
onel | -1.286 |
PHOTO | -1.285 |
adier | -1.225 |
Token | Environmental |
Token ID | 13272 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
arij | +1.282 |
typ | +1.072 |
PHOTO | +0.960 |
onel | +0.948 |
Picture | +0.906 |
Neg logit contributions | |
stein | -1.052 |
strings | -1.042 |
uterus | -1.013 |
chairs | -0.989 |
(£ | -0.988 |
Token | Grant |
Token ID | 12181 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
stein | +1.540 |
strings | +1.463 |
uterus | +1.447 |
(£ | +1.432 |
chairs | +1.413 |
Neg logit contributions | |
arij | -1.800 |
typ | -1.485 |
onel | -1.317 |
PHOTO | -1.306 |
actionDate | -1.246 |
Token | makers |
Token ID | 6620 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
arij | +0.631 |
typ | +0.520 |
PHOTO | +0.459 |
onel | +0.455 |
adier | +0.428 |
Neg logit contributions | |
stein | -0.601 |
strings | -0.591 |
uterus | -0.577 |
(£ | -0.566 |
chairs | -0.565 |
Token | Association |
Token ID | 5396 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
stein | +1.376 |
strings | +1.334 |
uterus | +1.309 |
(£ | +1.292 |
chairs | +1.285 |
Neg logit contributions | |
arij | -1.706 |
typ | -1.429 |
onel | -1.271 |
PHOTO | -1.264 |
adier | -1.188 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
stein | +3.703 |
strings | +3.527 |
(£ | +3.504 |
uterus | +3.466 |
chairs | +3.419 |
Neg logit contributions | |
arij | -6.710 |
typ | -5.782 |
onel | -5.286 |
PHOTO | -5.131 |
actionDate | -5.003 |
Token | also |
Token ID | 635 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
arij | +0.211 |
typ | +0.178 |
PHOTO | +0.160 |
onel | +0.160 |
adier | +0.152 |
Neg logit contributions | |
stein | -0.143 |
strings | -0.140 |
uterus | -0.137 |
(£ | -0.133 |
chairs | -0.133 |
Token | an |
Token ID | 281 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
arij | +1.027 |
typ | +0.870 |
PHOTO | +0.785 |
onel | +0.779 |
Picture | +0.743 |
Neg logit contributions | |
stein | -0.707 |
strings | -0.696 |
uterus | -0.678 |
chairs | -0.660 |
(£ | -0.660 |
Token | occasional |
Token ID | 12209 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
stein | +0.373 |
strings | +0.366 |
uterus | +0.357 |
(£ | +0.348 |
chairs | +0.347 |
Neg logit contributions | |
arij | -0.566 |
typ | -0.482 |
PHOTO | -0.436 |
onel | -0.431 |
Picture | -0.413 |
Token | donor |
Token ID | 17052 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
stein | +1.009 |
strings | +0.979 |
uterus | +0.964 |
(£ | +0.935 |
chairs | +0.929 |
Neg logit contributions | |
arij | -1.718 |
typ | -1.471 |
PHOTO | -1.330 |
onel | -1.326 |
ativity | -1.274 |
Token | to |
Token ID | 284 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
stein | +2.653 |
strings | +2.588 |
(£ | +2.499 |
uterus | +2.489 |
chair | +2.396 |
Neg logit contributions | |
arij | -4.536 |
typ | -3.836 |
PHOTO | -3.492 |
onel | -3.480 |
Picture | -3.333 |
Token | Seattle |
Token ID | 7312 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
stein | +2.006 |
uterus | +1.928 |
strings | +1.924 |
(£ | +1.856 |
chairs | +1.818 |
Neg logit contributions | |
arij | -2.911 |
typ | -2.452 |
PHOTO | -2.206 |
onel | -2.198 |
chel | -2.107 |
Token | Children |
Token ID | 8990 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
arij | +3.508 |
typ | +2.920 |
PHOTO | +2.602 |
onel | +2.546 |
Picture | +2.489 |
Neg logit contributions | |
strings | -3.445 |
stein | -3.396 |
uterus | -3.298 |
chairs | -3.268 |
(£ | -3.211 |
Token | 's |
Token ID | 338 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
stein | +1.005 |
strings | +0.993 |
uterus | +0.959 |
(£ | +0.923 |
chairs | +0.923 |
Neg logit contributions | |
arij | -2.068 |
typ | -1.793 |
PHOTO | -1.645 |
onel | -1.630 |
Picture | -1.576 |
Token | Hospital |
Token ID | 9256 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
arij | +1.237 |
typ | +1.052 |
PHOTO | +0.944 |
onel | +0.935 |
Picture | +0.901 |
Neg logit contributions | |
stein | -0.954 |
strings | -0.949 |
uterus | -0.918 |
chairs | -0.898 |
(£ | -0.894 |
Token | . |
Token ID | 13 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
stein | +1.828 |
strings | +1.734 |
uterus | +1.727 |
(£ | +1.688 |
chairs | +1.645 |
Neg logit contributions | |
arij | -2.913 |
typ | -2.473 |
PHOTO | -2.224 |
onel | -2.222 |
chel | -2.158 |
Token | " |
Token ID | 366 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
arij | +0.339 |
typ | +0.287 |
PHOTO | +0.259 |
onel | +0.258 |
adier | +0.247 |
Neg logit contributions | |
stein | -0.229 |
strings | -0.225 |
uterus | -0.219 |
(£ | -0.213 |
chairs | -0.213 |
Token | We |
Token ID | 1135 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
stein | +1.590 |
strings | +1.568 |
chairs | +1.484 |
chair | +1.460 |
uterus | +1.446 |
Neg logit contributions | |
arij | -2.382 |
typ | -1.902 |
PHOTO | -1.753 |
onel | -1.736 |
allery | -1.693 |
Token | truly |
Token ID | 4988 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
arij | +0.660 |
typ | +0.569 |
PHOTO | +0.519 |
onel | +0.514 |
adier | +0.495 |
Neg logit contributions | |
stein | -0.349 |
strings | -0.342 |
uterus | -0.332 |
chairs | -0.321 |
(£ | -0.321 |
Token | believe |
Token ID | 1975 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
arij | +4.406 |
typ | +3.755 |
PHOTO | +3.433 |
onel | +3.409 |
Picture | +3.295 |
Neg logit contributions | |
strings | -2.858 |
stein | -2.856 |
uterus | -2.721 |
(£ | -2.660 |
chairs | -2.656 |
Token | that |
Token ID | 326 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
stein | +1.344 |
strings | +1.311 |
uterus | +1.294 |
(£ | +1.248 |
chairs | +1.231 |
Neg logit contributions | |
arij | -2.316 |
typ | -1.953 |
PHOTO | -1.783 |
onel | -1.776 |
adier | -1.715 |
Token | our |
Token ID | 674 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
stein | +2.407 |
strings | +2.325 |
uterus | +2.324 |
(£ | +2.247 |
chairs | +2.206 |
Neg logit contributions | |
arij | -4.017 |
typ | -3.352 |
PHOTO | -3.057 |
onel | -3.048 |
actionDate | -2.955 |
Token | lead |
Token ID | 1085 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
stein | +0.521 |
strings | +0.514 |
uterus | +0.500 |
(£ | +0.486 |
chairs | +0.485 |
Neg logit contributions | |
arij | -0.732 |
typ | -0.618 |
PHOTO | -0.561 |
onel | -0.550 |
ativity | -0.528 |
Token | blocks |
Token ID | 7021 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
stein | +0.670 |
strings | +0.661 |
uterus | +0.637 |
chairs | +0.626 |
(£ | +0.622 |
Neg logit contributions | |
arij | -0.884 |
typ | -0.741 |
PHOTO | -0.669 |
onel | -0.660 |
Picture | -0.633 |
Token | and |
Token ID | 290 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
arij | +2.051 |
typ | +1.749 |
PHOTO | +1.588 |
onel | +1.573 |
Picture | +1.510 |
Neg logit contributions | |
stein | -1.290 |
strings | -1.273 |
uterus | -1.234 |
(£ | -1.199 |
chairs | -1.198 |
Token | fantastic |
Token ID | 9623 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
stein | +0.926 |
strings | +0.911 |
uterus | +0.885 |
(£ | +0.860 |
chairs | +0.851 |
Neg logit contributions | |
arij | -1.462 |
typ | -1.244 |
PHOTO | -1.124 |
onel | -1.119 |
ativity | -1.074 |
Token | runners |
Token ID | 19323 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
arij | +0.379 |
typ | +0.322 |
PHOTO | +0.292 |
onel | +0.289 |
adier | +0.277 |
Neg logit contributions | |
stein | -0.240 |
strings | -0.237 |
uterus | -0.230 |
(£ | -0.224 |
chairs | -0.223 |
Token | : |
Token ID | 25 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
stein | +2.339 |
strings | +2.293 |
(£ | +2.193 |
uterus | +2.180 |
chairs | +2.118 |
Neg logit contributions | |
arij | -4.103 |
typ | -3.502 |
PHOTO | -3.206 |
onel | -3.189 |
actionDate | -3.132 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
stein | +1.308 |
strings | +1.282 |
uterus | +1.236 |
(£ | +1.211 |
chairs | +1.206 |
Neg logit contributions | |
arij | -1.914 |
typ | -1.622 |
PHOTO | -1.457 |
onel | -1.444 |
actionDate | -1.396 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
stein | +1.534 |
strings | +1.487 |
(£ | +1.396 |
chairs | +1.366 |
chair | +1.353 |
Neg logit contributions | |
arij | -3.137 |
typ | -2.598 |
PHOTO | -2.412 |
onel | -2.406 |
allery | -2.383 |
Token | This |
Token ID | 1212 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
stein | +2.334 |
strings | +2.296 |
chairs | +2.172 |
chair | +2.147 |
uterus | +2.117 |
Neg logit contributions | |
arij | -3.075 |
typ | -2.472 |
PHOTO | -2.302 |
onel | -2.227 |
actionDate | -2.174 |
Token | play |
Token ID | 711 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
arij | +0.201 |
typ | +0.171 |
PHOTO | +0.155 |
onel | +0.155 |
adier | +0.148 |
Neg logit contributions | |
stein | -0.122 |
strings | -0.120 |
uterus | -0.117 |
(£ | -0.113 |
chairs | -0.113 |
Token | has |
Token ID | 468 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
stein | +2.014 |
strings | +2.012 |
uterus | +1.874 |
(£ | +1.865 |
chairs | +1.825 |
Neg logit contributions | |
arij | -3.643 |
typ | -3.101 |
PHOTO | -2.865 |
onel | -2.848 |
actionDate | -2.797 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
stein | +1.073 |
strings | +1.054 |
uterus | +1.016 |
(£ | +0.996 |
chairs | +0.987 |
Neg logit contributions | |
arij | -1.779 |
typ | -1.523 |
PHOTO | -1.380 |
onel | -1.374 |
adier | -1.313 |
Token | 01 |
Token ID | 486 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
stein | +2.043 |
strings | +1.911 |
(£ | +1.735 |
uterus | +1.709 |
chairs | +1.599 |
Neg logit contributions | |
arij | -7.249 |
typ | -6.229 |
PHOTO | -5.849 |
onel | -5.814 |
adier | -5.672 |
Token | 30 |
Token ID | 1270 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
arij | +4.731 |
typ | +3.887 |
onel | +3.125 |
PHOTO | +3.075 |
ART | +3.052 |
Neg logit contributions | |
uterus | -7.566 |
stein | -7.427 |
strings | -7.265 |
chairs | -7.228 |
ドラ | -7.211 |
Token | O |
Token ID | 440 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
arij | +2.709 |
typ | +2.256 |
PHOTO | +2.015 |
onel | +1.966 |
Picture | +1.903 |
Neg logit contributions | |
stein | -2.637 |
strings | -2.626 |
uterus | -2.565 |
chairs | -2.513 |
(£ | -2.484 |
Token | & |
Token ID | 5 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
arij | +1.642 |
typ | +1.350 |
PHOTO | +1.195 |
onel | +1.180 |
Picture | +1.120 |
Neg logit contributions | |
stein | -1.583 |
strings | -1.566 |
uterus | -1.528 |
(£ | -1.495 |
chairs | -1.494 |
Token | A |
Token ID | 32 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
arij | +2.042 |
typ | +1.678 |
PHOTO | +1.482 |
onel | +1.462 |
Picture | +1.389 |
Neg logit contributions | |
stein | -2.034 |
strings | -2.015 |
uterus | -1.972 |
chairs | -1.923 |
(£ | -1.923 |
Token | - |
Token ID | 12 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
stein | +1.256 |
strings | +1.205 |
(£ | +1.118 |
chairs | +1.096 |
chair | +1.082 |
Neg logit contributions | |
arij | -3.216 |
typ | -2.716 |
onel | -2.525 |
PHOTO | -2.504 |
allery | -2.479 |
Token | M |
Token ID | 44 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
arij | +4.546 |
typ | +3.936 |
PHOTO | +3.458 |
onel | +3.442 |
Picture | +3.300 |
Neg logit contributions | |
stein | -3.618 |
strings | -3.583 |
uterus | -3.561 |
(£ | -3.447 |
chairs | -3.402 |
Token | anc |
Token ID | 1192 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
arij | +4.355 |
typ | +3.599 |
onel | +3.210 |
PHOTO | +3.207 |
adier | +3.065 |
Neg logit contributions | |
stein | -3.437 |
strings | -3.427 |
uterus | -3.331 |
(£ | -3.255 |
chairs | -3.251 |
Token | rus |
Token ID | 14932 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
arij | +8.069 |
typ | +6.902 |
onel | +6.227 |
PHOTO | +6.205 |
adier | +5.898 |
Neg logit contributions | |
strings | -5.019 |
uterus | -4.896 |
stein | -4.853 |
(£ | -4.790 |
chairs | -4.671 |
Token | hes |
Token ID | 956 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
arij | +4.665 |
typ | +3.887 |
PHOTO | +3.458 |
onel | +3.412 |
Picture | +3.282 |
Neg logit contributions | |
strings | -4.151 |
stein | -4.131 |
uterus | -4.054 |
chairs | -3.950 |
(£ | -3.924 |
Token | � |
Token ID | 447 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
arij | +4.682 |
typ | +4.024 |
PHOTO | +3.610 |
onel | +3.601 |
Picture | +3.474 |
Neg logit contributions | |
stein | -2.924 |
strings | -2.914 |
uterus | -2.863 |
chairs | -2.763 |
(£ | -2.745 |
Token | � |
Token ID | 247 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
arij | +0.230 |
typ | +0.183 |
PHOTO | +0.156 |
onel | +0.153 |
chel | +0.143 |
Neg logit contributions | |
stein | -0.302 |
strings | -0.297 |
uterus | -0.291 |
chairs | -0.284 |
(£ | -0.283 |
Token | King |
Token ID | 2677 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
arij | +1.619 |
typ | +1.393 |
PHOTO | +1.274 |
onel | +1.262 |
Picture | +1.215 |
Neg logit contributions | |
stein | -0.878 |
strings | -0.865 |
uterus | -0.835 |
chairs | -0.810 |
(£ | -0.809 |
Token | makers |
Token ID | 6620 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
arij | +0.138 |
typ | +0.117 |
PHOTO | +0.107 |
onel | +0.105 |
adier | +0.101 |
Neg logit contributions | |
stein | -0.089 |
strings | -0.087 |
uterus | -0.084 |
chairs | -0.082 |
(£ | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
stein | +0.606 |
strings | +0.594 |
uterus | +0.571 |
(£ | +0.566 |
chairs | +0.556 |
Neg logit contributions | |
arij | -1.027 |
typ | -0.872 |
PHOTO | -0.800 |
onel | -0.790 |
adier | -0.756 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
arij | +2.348 |
typ | +1.987 |
PHOTO | +1.791 |
onel | +1.772 |
Picture | +1.701 |
Neg logit contributions | |
stein | -1.701 |
strings | -1.683 |
uterus | -1.636 |
chairs | -1.592 |
(£ | -1.590 |
Token | crew |
Token ID | 5462 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
stein | +0.349 |
strings | +0.342 |
uterus | +0.334 |
(£ | +0.326 |
chairs | +0.323 |
Neg logit contributions | |
arij | -0.518 |
typ | -0.437 |
PHOTO | -0.396 |
onel | -0.393 |
adier | -0.376 |
Token | of |
Token ID | 286 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
arij | +1.349 |
typ | +1.156 |
PHOTO | +1.056 |
onel | +1.045 |
Picture | +1.005 |
Neg logit contributions | |
stein | -0.762 |
strings | -0.752 |
uterus | -0.725 |
chairs | -0.706 |
(£ | -0.704 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
stein | +0.415 |
strings | +0.407 |
uterus | +0.397 |
(£ | +0.387 |
chairs | +0.387 |
Neg logit contributions | |
arij | -0.594 |
typ | -0.502 |
PHOTO | -0.453 |
onel | -0.447 |
adier | -0.429 |
Token | Tal |
Token ID | 7193 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
stein | +0.358 |
strings | +0.351 |
uterus | +0.344 |
(£ | +0.335 |
chairs | +0.331 |
Neg logit contributions | |
arij | -0.521 |
typ | -0.440 |
PHOTO | -0.396 |
onel | -0.394 |
adier | -0.377 |
Token | ion |
Token ID | 295 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
stein | +1.057 |
strings | +1.016 |
uterus | +0.979 |
chairs | +0.970 |
(£ | +0.968 |
Neg logit contributions | |
arij | -1.533 |
typ | -1.306 |
PHOTO | -1.197 |
onel | -1.155 |
Picture | -1.132 |
Token | Bernie |
Token ID | 33433 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
stein | +0.499 |
strings | +0.490 |
uterus | +0.463 |
chairs | +0.461 |
(£ | +0.456 |
Neg logit contributions | |
arij | -0.672 |
typ | -0.545 |
PHOTO | -0.502 |
onel | -0.494 |
adier | -0.473 |
Token | � |
Token ID | 447 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
stein | +0.037 |
strings | +0.036 |
uterus | +0.035 |
chairs | +0.034 |
(£ | +0.034 |
Neg logit contributions | |
arij | -0.060 |
typ | -0.051 |
PHOTO | -0.046 |
onel | -0.046 |
adier | -0.044 |
Token | � |
Token ID | 247 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
arij | +0.572 |
typ | +0.454 |
PHOTO | +0.389 |
onel | +0.382 |
Picture | +0.357 |
Neg logit contributions | |
stein | -0.754 |
strings | -0.742 |
uterus | -0.725 |
chairs | -0.712 |
(£ | -0.707 |
Token | s |
Token ID | 82 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
stein | +1.736 |
strings | +1.679 |
uterus | +1.583 |
chairs | +1.554 |
(£ | +1.531 |
Neg logit contributions | |
arij | -3.515 |
typ | -3.031 |
PHOTO | -2.804 |
onel | -2.770 |
adier | -2.668 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
stein | +0.354 |
strings | +0.346 |
uterus | +0.342 |
(£ | +0.329 |
chairs | +0.326 |
Neg logit contributions | |
arij | -0.547 |
typ | -0.463 |
onel | -0.419 |
PHOTO | -0.419 |
adier | -0.399 |
Token | st |
Token ID | 301 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
arij | +0.121 |
typ | +0.103 |
PHOTO | +0.094 |
onel | +0.093 |
adier | +0.090 |
Neg logit contributions | |
stein | -0.074 |
strings | -0.072 |
uterus | -0.070 |
(£ | -0.068 |
chairs | -0.067 |
Token | Big |
Token ID | 4403 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
arij | +2.969 |
typ | +2.526 |
PHOTO | +2.296 |
onel | +2.259 |
Picture | +2.184 |
Neg logit contributions | |
stein | -2.014 |
strings | -2.003 |
uterus | -1.927 |
chairs | -1.890 |
(£ | -1.877 |
Token | Lie |
Token ID | 12060 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
stein | +0.141 |
strings | +0.138 |
uterus | +0.134 |
(£ | +0.131 |
chairs | +0.130 |
Neg logit contributions | |
arij | -0.185 |
typ | -0.155 |
PHOTO | -0.139 |
onel | -0.137 |
adier | -0.131 |
Token | : |
Token ID | 25 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
stein | +0.923 |
strings | +0.897 |
uterus | +0.869 |
(£ | +0.849 |
chairs | +0.829 |
Neg logit contributions | |
arij | -1.552 |
typ | -1.319 |
PHOTO | -1.196 |
onel | -1.196 |
adier | -1.143 |
Token | Free |
Token ID | 3232 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
stein | +0.638 |
strings | +0.625 |
uterus | +0.611 |
(£ | +0.598 |
chairs | +0.585 |
Neg logit contributions | |
arij | -0.956 |
typ | -0.802 |
PHOTO | -0.723 |
onel | -0.720 |
adier | -0.692 |
Token | Tu |
Token ID | 16749 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
stein | +2.611 |
strings | +2.556 |
uterus | +2.525 |
(£ | +2.448 |
chairs | +2.373 |
Neg logit contributions | |
arij | -5.270 |
typ | -4.555 |
onel | -4.181 |
PHOTO | -4.124 |
adier | -4.015 |
Token | m |
Token ID | 76 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
arij | +1.421 |
typ | +1.200 |
PHOTO | +1.082 |
onel | +1.071 |
Picture | +1.025 |
Neg logit contributions | |
stein | -1.022 |
strings | -1.009 |
uterus | -0.981 |
(£ | -0.955 |
chairs | -0.955 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
arij | +6.064 |
typ | +5.112 |
PHOTO | +4.677 |
onel | +4.575 |
Picture | +4.535 |
Neg logit contributions | |
strings | -4.013 |
stein | -3.935 |
uterus | -3.915 |
chairs | -3.767 |
(£ | -3.715 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
arij | +2.187 |
typ | +1.858 |
PHOTO | +1.684 |
onel | +1.662 |
Picture | +1.604 |
Neg logit contributions | |
stein | -1.519 |
strings | -1.503 |
uterus | -1.455 |
chairs | -1.420 |
(£ | -1.414 |
Token | St |
Token ID | 520 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
arij | +1.418 |
typ | +1.199 |
PHOTO | +1.082 |
onel | +1.071 |
Picture | +1.026 |
Neg logit contributions | |
stein | -1.011 |
strings | -1.000 |
uterus | -0.971 |
chairs | -0.945 |
(£ | -0.945 |
Token | . |
Token ID | 13 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
arij | +1.383 |
typ | +1.167 |
PHOTO | +1.049 |
onel | +1.038 |
Picture | +0.993 |
Neg logit contributions | |
stein | -1.016 |
strings | -1.004 |
uterus | -0.976 |
(£ | -0.953 |
chairs | -0.951 |
Token | Clair |
Token ID | 48195 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
arij | +0.776 |
typ | +0.655 |
PHOTO | +0.587 |
onel | +0.586 |
adier | +0.561 |
Neg logit contributions | |
stein | -0.540 |
strings | -0.534 |
uterus | -0.518 |
(£ | -0.508 |
chairs | -0.506 |
Token | West |
Token ID | 2688 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
arij | +4.720 |
typ | +3.973 |
PHOTO | +3.581 |
onel | +3.467 |
Picture | +3.412 |
Neg logit contributions | |
strings | -4.150 |
stein | -4.122 |
uterus | -4.052 |
chairs | -3.936 |
(£ | -3.863 |
Token |
|
Token ID | 198 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
arij | +0.934 |
typ | +0.795 |
PHOTO | +0.718 |
onel | +0.715 |
adier | +0.686 |
Neg logit contributions | |
stein | -0.593 |
strings | -0.583 |
uterus | -0.565 |
(£ | -0.553 |
chairs | -0.551 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
arij | +0.535 |
typ | +0.452 |
PHOTO | +0.412 |
onel | +0.410 |
adier | +0.393 |
Neg logit contributions | |
stein | -0.318 |
strings | -0.313 |
uterus | -0.299 |
(£ | -0.295 |
chairs | -0.293 |
Token | UK |
Token ID | 15039 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
stein | +1.015 |
strings | +1.004 |
chairs | +0.952 |
uterus | +0.952 |
(£ | +0.946 |
Neg logit contributions | |
arij | -1.345 |
typ | -1.092 |
PHOTO | -0.997 |
onel | -0.986 |
ativity | -0.947 |
Token | street |
Token ID | 4675 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
arij | +0.907 |
typ | +0.771 |
PHOTO | +0.699 |
onel | +0.694 |
adier | +0.664 |
Neg logit contributions | |
stein | -0.578 |
strings | -0.571 |
uterus | -0.554 |
(£ | -0.539 |
chairs | -0.538 |
Token | year |
Token ID | 1941 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
strings | +1.548 |
stein | +1.543 |
uterus | +1.474 |
chair | +1.468 |
chairs | +1.457 |
Neg logit contributions | |
arij | -1.794 |
typ | -1.443 |
PHOTO | -1.312 |
onel | -1.287 |
ativity | -1.246 |
Token | - |
Token ID | 12 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
stein | +1.604 |
strings | +1.575 |
uterus | +1.539 |
(£ | +1.475 |
chairs | +1.462 |
Neg logit contributions | |
arij | -3.211 |
typ | -2.773 |
PHOTO | -2.542 |
onel | -2.510 |
Picture | -2.423 |
Token | old |
Token ID | 727 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
stein | +2.867 |
strings | +2.827 |
chair | +2.660 |
chairs | +2.655 |
uterus | +2.597 |
Neg logit contributions | |
arij | -2.739 |
typ | -2.119 |
PHOTO | -1.999 |
allery | -1.874 |
Picture | -1.859 |
Token | woman |
Token ID | 2415 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
stein | +1.135 |
uterus | +1.123 |
strings | +1.101 |
(£ | +1.083 |
chair | +1.040 |
Neg logit contributions | |
arij | -1.672 |
typ | -1.388 |
PHOTO | -1.261 |
onel | -1.257 |
ativity | -1.208 |
Token | 's |
Token ID | 338 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
stein | +3.270 |
uterus | +3.213 |
strings | +3.114 |
(£ | +3.076 |
chair | +2.945 |
Neg logit contributions | |
arij | -6.276 |
typ | -5.226 |
PHOTO | -4.844 |
onel | -4.772 |
allery | -4.716 |
Token | cause |
Token ID | 2728 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
arij | +1.208 |
typ | +1.023 |
PHOTO | +0.924 |
onel | +0.914 |
Picture | +0.876 |
Neg logit contributions | |
stein | -0.844 |
strings | -0.834 |
uterus | -0.810 |
chairs | -0.788 |
(£ | -0.788 |
Token | of |
Token ID | 286 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
arij | +1.838 |
typ | +1.561 |
PHOTO | +1.411 |
onel | +1.397 |
Picture | +1.340 |
Neg logit contributions | |
stein | -1.248 |
strings | -1.232 |
uterus | -1.196 |
chairs | -1.164 |
(£ | -1.163 |
Token | death |
Token ID | 1918 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
arij | +4.923 |
typ | +4.174 |
PHOTO | +3.773 |
onel | +3.745 |
adier | +3.609 |
Neg logit contributions | |
stein | -3.366 |
strings | -3.310 |
chairs | -3.119 |
uterus | -3.105 |
(£ | -3.100 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
stein | +1.856 |
strings | +1.821 |
uterus | +1.801 |
(£ | +1.767 |
chairs | +1.703 |
Neg logit contributions | |
arij | -3.046 |
typ | -2.571 |
PHOTO | -2.330 |
onel | -2.325 |
actionDate | -2.267 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
stein | +0.241 |
strings | +0.238 |
uterus | +0.230 |
(£ | +0.225 |
chairs | +0.223 |
Neg logit contributions | |
arij | -0.397 |
typ | -0.337 |
onel | -0.305 |
PHOTO | -0.305 |
adier | -0.293 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
stein | +1.209 |
strings | +1.179 |
(£ | +1.109 |
uterus | +1.088 |
chairs | +1.082 |
Neg logit contributions | |
arij | -2.418 |
typ | -2.010 |
onel | -1.856 |
PHOTO | -1.850 |
allery | -1.831 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
stein | +1.044 |
strings | +1.012 |
uterus | +0.998 |
(£ | +0.982 |
chairs | +0.957 |
Neg logit contributions | |
arij | -1.693 |
typ | -1.437 |
PHOTO | -1.304 |
onel | -1.299 |
actionDate | -1.262 |
Token | The |
Token ID | 383 |
Feature activation | +6.30e-04 |
Pos logit contributions | |
stein | +1.418 |
strings | +1.378 |
uterus | +1.316 |
(£ | +1.305 |
chairs | +1.277 |
Neg logit contributions | |
arij | -2.555 |
typ | -2.166 |
onel | -1.972 |
PHOTO | -1.931 |
ativity | -1.923 |
Token | v |
Token ID | 410 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
stein | +0.004 |
strings | +0.004 |
uterus | +0.004 |
(£ | +0.004 |
chairs | +0.004 |
Neg logit contributions | |
arij | -0.005 |
typ | -0.005 |
PHOTO | -0.004 |
onel | -0.004 |
adier | -0.004 |
Token | istas |
Token ID | 37503 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
arij | +2.470 |
typ | +2.133 |
PHOTO | +1.950 |
onel | +1.938 |
adier | +1.867 |
Neg logit contributions | |
stein | -1.252 |
strings | -1.234 |
uterus | -1.194 |
(£ | -1.153 |
chairs | -1.151 |
Token | got |
Token ID | 1392 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
arij | +2.682 |
typ | +2.288 |
PHOTO | +2.075 |
onel | +2.043 |
Picture | +1.981 |
Neg logit contributions | |
stein | -1.750 |
strings | -1.736 |
uterus | -1.676 |
chairs | -1.637 |
(£ | -1.623 |
Token | better |
Token ID | 1365 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
arij | +3.605 |
typ | +3.057 |
PHOTO | +2.768 |
onel | +2.729 |
Picture | +2.638 |
Neg logit contributions | |
stein | -2.522 |
strings | -2.507 |
uterus | -2.400 |
chairs | -2.363 |
(£ | -2.361 |
Token | as |
Token ID | 355 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
arij | +3.061 |
typ | +2.643 |
PHOTO | +2.409 |
onel | +2.383 |
Picture | +2.306 |
Neg logit contributions | |
stein | -1.717 |
strings | -1.699 |
uterus | -1.644 |
chairs | -1.593 |
(£ | -1.585 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
stein | +2.058 |
strings | +2.023 |
uterus | +1.988 |
(£ | +1.901 |
chairs | +1.896 |
Neg logit contributions | |
arij | -3.580 |
typ | -3.077 |
PHOTO | -2.797 |
onel | -2.771 |
actionDate | -2.691 |
Token | hike |
Token ID | 18390 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
arij | +2.789 |
typ | +2.360 |
PHOTO | +2.135 |
onel | +2.113 |
Picture | +2.031 |
Neg logit contributions | |
stein | -2.013 |
strings | -1.990 |
uterus | -1.914 |
chairs | -1.880 |
(£ | -1.870 |
Token | progressed |
Token ID | 28775 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
stein | +0.046 |
strings | +0.045 |
uterus | +0.044 |
chairs | +0.043 |
(£ | +0.043 |
Neg logit contributions | |
arij | -0.075 |
typ | -0.064 |
PHOTO | -0.058 |
onel | -0.058 |
actionDate | -0.055 |
Token | leaving |
Token ID | 4305 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
stein | +0.694 |
strings | +0.677 |
uterus | +0.662 |
(£ | +0.652 |
chairs | +0.640 |
Neg logit contributions | |
arij | -1.141 |
typ | -0.969 |
PHOTO | -0.881 |
onel | -0.881 |
actionDate | -0.846 |
Token | can |
Token ID | 460 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
stein | +2.463 |
strings | +2.445 |
uterus | +2.326 |
(£ | +2.284 |
chairs | +2.262 |
Neg logit contributions | |
arij | -5.879 |
typ | -5.034 |
PHOTO | -4.635 |
onel | -4.620 |
adier | -4.475 |
Token | be |
Token ID | 307 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
stein | +0.714 |
strings | +0.695 |
uterus | +0.668 |
(£ | +0.665 |
chairs | +0.649 |
Neg logit contributions | |
arij | -1.012 |
typ | -0.849 |
PHOTO | -0.765 |
onel | -0.757 |
ativity | -0.723 |
Token | traced |
Token ID | 23246 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
stein | +1.775 |
strings | +1.732 |
uterus | +1.666 |
(£ | +1.600 |
idis | +1.516 |
Neg logit contributions | |
arij | -4.692 |
typ | -4.042 |
PHOTO | -3.790 |
onel | -3.749 |
ativity | -3.640 |
Token | back |
Token ID | 736 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
strings | +1.492 |
stein | +1.482 |
uterus | +1.429 |
(£ | +1.400 |
chairs | +1.338 |
Neg logit contributions | |
arij | -2.735 |
typ | -2.342 |
PHOTO | -2.156 |
onel | -2.145 |
Picture | -2.043 |
Token | to |
Token ID | 284 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
stein | +0.060 |
strings | +0.059 |
uterus | +0.057 |
(£ | +0.056 |
chairs | +0.055 |
Neg logit contributions | |
arij | -0.093 |
typ | -0.078 |
PHOTO | -0.071 |
onel | -0.071 |
ativity | -0.067 |
Token | 1800 |
Token ID | 21431 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
stein | +1.409 |
strings | +1.403 |
uterus | +1.356 |
(£ | +1.326 |
chairs | +1.296 |
Neg logit contributions | |
arij | -2.574 |
typ | -2.211 |
PHOTO | -2.016 |
onel | -1.982 |
adier | -1.920 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
arij | +4.175 |
typ | +3.517 |
PHOTO | +3.112 |
onel | +3.109 |
Picture | +2.962 |
Neg logit contributions | |
strings | -3.802 |
stein | -3.778 |
uterus | -3.715 |
chairs | -3.614 |
(£ | -3.565 |
Token | Learn |
Token ID | 14365 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
arij | +1.449 |
typ | +1.214 |
PHOTO | +1.089 |
onel | +1.068 |
Picture | +1.031 |
Neg logit contributions | |
stein | -1.307 |
strings | -1.305 |
uterus | -1.277 |
chairs | -1.248 |
(£ | -1.237 |
Token | about |
Token ID | 546 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
stein | +0.805 |
strings | +0.785 |
uterus | +0.757 |
(£ | +0.745 |
chairs | +0.719 |
Neg logit contributions | |
arij | -1.366 |
typ | -1.154 |
PHOTO | -1.057 |
onel | -1.051 |
adier | -1.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
arij | +1.764 |
typ | +1.490 |
PHOTO | +1.344 |
onel | +1.330 |
Picture | +1.272 |
Neg logit contributions | |
stein | -1.263 |
strings | -1.247 |
uterus | -1.212 |
(£ | -1.180 |
chairs | -1.179 |
Token | history |
Token ID | 2106 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
arij | +3.744 |
typ | +3.155 |
PHOTO | +2.772 |
onel | +2.725 |
Picture | +2.638 |
Neg logit contributions | |
stein | -3.332 |
strings | -3.286 |
uterus | -3.168 |
chairs | -3.143 |
(£ | -3.107 |
Token | to |
Token ID | 284 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
arij | +2.221 |
typ | +1.887 |
PHOTO | +1.715 |
onel | +1.702 |
adier | +1.631 |
Neg logit contributions | |
stein | -1.409 |
strings | -1.389 |
uterus | -1.349 |
(£ | -1.310 |
chairs | -1.310 |
Token | their |
Token ID | 511 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
arij | +1.644 |
typ | +1.385 |
PHOTO | +1.247 |
onel | +1.235 |
Picture | +1.180 |
Neg logit contributions | |
stein | -1.217 |
strings | -1.202 |
uterus | -1.170 |
chairs | -1.139 |
(£ | -1.138 |
Token | wagon |
Token ID | 31860 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
stein | +0.674 |
strings | +0.665 |
uterus | +0.661 |
chairs | +0.634 |
(£ | +0.629 |
Neg logit contributions | |
arij | -1.063 |
typ | -0.896 |
onel | -0.812 |
PHOTO | -0.812 |
adier | -0.777 |
Token | at |
Token ID | 379 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
stein | +0.411 |
strings | +0.408 |
uterus | +0.392 |
chairs | +0.392 |
(£ | +0.380 |
Neg logit contributions | |
arij | -0.652 |
typ | -0.552 |
PHOTO | -0.502 |
onel | -0.500 |
adier | -0.476 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
arij | +0.189 |
typ | +0.159 |
PHOTO | +0.143 |
onel | +0.143 |
adier | +0.136 |
Neg logit contributions | |
stein | -0.135 |
strings | -0.132 |
uterus | -0.129 |
(£ | -0.125 |
chairs | -0.125 |
Token | p |
Token ID | 279 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
arij | +7.941 |
typ | +6.762 |
PHOTO | +5.969 |
onel | +5.749 |
cade | +5.735 |
Neg logit contributions | |
strings | -6.749 |
stein | -6.711 |
uterus | -6.636 |
chairs | -6.431 |
(£ | -6.421 |
Token | . |
Token ID | 13 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
arij | +7.758 |
typ | +6.761 |
onel | +5.696 |
PHOTO | +5.668 |
chel | +5.641 |
Neg logit contributions | |
uterus | -9.346 |
strings | -9.040 |
stein | -8.953 |
ドラ | -8.942 |
Shades | -8.697 |
Token | m |
Token ID | 76 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
arij | +0.463 |
typ | +0.394 |
PHOTO | +0.362 |
onel | +0.360 |
ativity | +0.348 |
Neg logit contributions | |
stein | -0.231 |
strings | -0.226 |
chairs | -0.211 |
uterus | -0.210 |
(£ | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
arij | +8.309 |
typ | +6.484 |
PHOTO | +5.708 |
onel | +5.588 |
chel | +5.514 |
Neg logit contributions | |
strings | -10.059 |
stein | -9.788 |
uterus | -9.772 |
ドラ | -9.532 |
chairs | -9.449 |
Token | Some |
Token ID | 2773 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
arij | +6.171 |
typ | +5.260 |
PHOTO | +4.833 |
onel | +4.692 |
Picture | +4.602 |
Neg logit contributions | |
stein | -4.222 |
strings | -4.169 |
uterus | -4.018 |
(£ | -3.948 |
chairs | -3.918 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
arij | +1.171 |
typ | +0.995 |
PHOTO | +0.898 |
onel | +0.891 |
Picture | +0.852 |
Neg logit contributions | |
stein | -0.798 |
strings | -0.787 |
uterus | -0.766 |
(£ | -0.744 |
chairs | -0.743 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
arij | +5.070 |
typ | +4.340 |
PHOTO | +3.867 |
onel | +3.825 |
Picture | +3.697 |
Neg logit contributions | |
stein | -3.906 |
strings | -3.845 |
uterus | -3.759 |
chairs | -3.677 |
(£ | -3.664 |
Token | � |
Token ID | 447 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
arij | +0.838 |
typ | +0.707 |
onel | +0.638 |
PHOTO | +0.636 |
adier | +0.612 |
Neg logit contributions | |
stein | -0.533 |
strings | -0.525 |
uterus | -0.507 |
(£ | -0.497 |
chairs | -0.493 |
Token | � |
Token ID | 251 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
stein | +0.659 |
strings | +0.651 |
uterus | +0.634 |
(£ | +0.618 |
chairs | +0.618 |
Neg logit contributions | |
arij | -0.841 |
typ | -0.705 |
PHOTO | -0.633 |
onel | -0.626 |
Picture | -0.598 |
Token | She |
Token ID | 1375 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
stein | +0.125 |
strings | +0.123 |
uterus | +0.118 |
(£ | +0.116 |
chairs | +0.115 |
Neg logit contributions | |
arij | -0.197 |
typ | -0.165 |
onel | -0.149 |
PHOTO | -0.148 |
adier | -0.144 |
Token | was |
Token ID | 373 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
arij | +4.069 |
typ | +3.472 |
PHOTO | +3.142 |
onel | +3.111 |
Picture | +2.985 |
Neg logit contributions | |
stein | -2.721 |
strings | -2.702 |
uterus | -2.621 |
chairs | -2.557 |
(£ | -2.545 |
Token | right |
Token ID | 826 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
arij | +2.990 |
typ | +2.545 |
PHOTO | +2.308 |
onel | +2.277 |
Picture | +2.187 |
Neg logit contributions | |
stein | -2.003 |
strings | -1.982 |
uterus | -1.918 |
chairs | -1.877 |
(£ | -1.865 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
arij | +9.888 |
typ | +8.491 |
onel | +7.459 |
PHOTO | +7.443 |
ativity | +7.224 |
Neg logit contributions | |
strings | -9.129 |
uterus | -8.946 |
chairs | -8.940 |
stein | -8.891 |
ドラ | -8.693 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
arij | +0.591 |
typ | +0.499 |
onel | +0.451 |
PHOTO | +0.450 |
adier | +0.433 |
Neg logit contributions | |
stein | -0.365 |
strings | -0.361 |
uterus | -0.348 |
(£ | -0.340 |
chairs | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
arij | +0.350 |
typ | +0.296 |
PHOTO | +0.270 |
onel | +0.268 |
ativity | +0.258 |
Neg logit contributions | |
stein | -0.205 |
strings | -0.201 |
uterus | -0.191 |
(£ | -0.189 |
chairs | -0.188 |
Token | This |
Token ID | 1212 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
stein | +0.208 |
strings | +0.205 |
uterus | +0.196 |
chairs | +0.194 |
(£ | +0.192 |
Neg logit contributions | |
arij | -0.276 |
typ | -0.226 |
PHOTO | -0.206 |
onel | -0.203 |
adier | -0.195 |
Token | is |
Token ID | 318 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
arij | +1.729 |
typ | +1.471 |
PHOTO | +1.336 |
onel | +1.327 |
adier | +1.272 |
Neg logit contributions | |
stein | -1.077 |
strings | -1.062 |
uterus | -1.034 |
(£ | -1.000 |
chairs | -0.998 |
Token | on |
Token ID | 319 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
stein | +0.208 |
strings | +0.205 |
uterus | +0.200 |
(£ | +0.195 |
chairs | +0.192 |
Neg logit contributions | |
arij | -0.330 |
typ | -0.281 |
onel | -0.253 |
PHOTO | -0.252 |
adier | -0.242 |
Token | natives |
Token ID | 30962 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
stein | +1.481 |
strings | +1.446 |
uterus | +1.443 |
(£ | +1.384 |
chairs | +1.362 |
Neg logit contributions | |
arij | -2.267 |
typ | -1.923 |
onel | -1.737 |
PHOTO | -1.723 |
ativity | -1.669 |
Token | please |
Token ID | 3387 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
stein | +3.058 |
strings | +2.965 |
uterus | +2.943 |
(£ | +2.819 |
chairs | +2.786 |
Neg logit contributions | |
arij | -5.710 |
typ | -4.839 |
onel | -4.466 |
PHOTO | -4.448 |
actionDate | -4.282 |
Token | visit |
Token ID | 3187 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
stein | +3.056 |
uterus | +2.948 |
strings | +2.948 |
(£ | +2.903 |
chairs | +2.779 |
Neg logit contributions | |
arij | -5.708 |
typ | -4.943 |
onel | -4.523 |
cade | -4.360 |
PHOTO | -4.351 |
Token | my |
Token ID | 616 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
stein | +1.114 |
strings | +1.100 |
uterus | +1.081 |
(£ | +1.049 |
chairs | +1.032 |
Neg logit contributions | |
arij | -1.728 |
typ | -1.468 |
onel | -1.317 |
PHOTO | -1.316 |
ativity | -1.273 |
Token | h |
Token ID | 289 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
arij | +4.930 |
typ | +4.195 |
PHOTO | +3.810 |
onel | +3.726 |
Picture | +3.642 |
Neg logit contributions | |
stein | -3.459 |
strings | -3.452 |
uterus | -3.310 |
chairs | -3.267 |
(£ | -3.234 |
Token | ort |
Token ID | 419 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
arij | +10.787 |
typ | +9.101 |
onel | +8.202 |
PHOTO | +8.036 |
cade | +7.807 |
Neg logit contributions | |
strings | -7.551 |
stein | -7.379 |
chairs | -7.364 |
uterus | -7.312 |
ドラ | -7.182 |
Token | iculture |
Token ID | 47428 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
stein | +0.928 |
strings | +0.896 |
uterus | +0.875 |
chairs | +0.831 |
(£ | +0.828 |
Neg logit contributions | |
arij | -1.975 |
typ | -1.703 |
PHOTO | -1.572 |
onel | -1.563 |
adier | -1.510 |
Token | and |
Token ID | 290 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
arij | +3.544 |
typ | +3.005 |
PHOTO | +2.724 |
onel | +2.669 |
Picture | +2.593 |
Neg logit contributions | |
stein | -2.454 |
strings | -2.437 |
uterus | -2.352 |
chairs | -2.309 |
(£ | -2.284 |
Token | Land |
Token ID | 6379 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
arij | +3.709 |
typ | +3.143 |
PHOTO | +2.854 |
onel | +2.786 |
Picture | +2.717 |
Neg logit contributions | |
stein | -2.552 |
strings | -2.541 |
uterus | -2.431 |
chairs | -2.380 |
(£ | -2.375 |
Token | sc |
Token ID | 1416 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
arij | +0.961 |
typ | +0.826 |
PHOTO | +0.755 |
onel | +0.749 |
adier | +0.721 |
Neg logit contributions | |
stein | -0.521 |
strings | -0.512 |
uterus | -0.495 |
(£ | -0.480 |
chairs | -0.480 |
Token | by |
Token ID | 416 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
arij | +3.200 |
typ | +2.747 |
PHOTO | +2.502 |
onel | +2.476 |
Picture | +2.382 |
Neg logit contributions | |
stein | -1.889 |
strings | -1.869 |
uterus | -1.806 |
chairs | -1.759 |
(£ | -1.745 |
Token | the |
Token ID | 262 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
arij | +1.853 |
typ | +1.549 |
PHOTO | +1.389 |
onel | +1.368 |
Picture | +1.312 |
Neg logit contributions | |
stein | -1.522 |
strings | -1.504 |
uterus | -1.463 |
chairs | -1.433 |
(£ | -1.430 |
Token | Chemistry |
Token ID | 27867 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
arij | +5.171 |
typ | +4.385 |
PHOTO | +3.969 |
onel | +3.827 |
Picture | +3.757 |
Neg logit contributions | |
stein | -4.145 |
strings | -4.083 |
chairs | -3.926 |
uterus | -3.916 |
(£ | -3.856 |
Token | and |
Token ID | 290 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
arij | +5.543 |
typ | +4.763 |
PHOTO | +4.395 |
onel | +4.335 |
Picture | +4.278 |
Neg logit contributions | |
stein | -3.656 |
strings | -3.638 |
uterus | -3.556 |
chairs | -3.473 |
(£ | -3.393 |
Token | Camera |
Token ID | 20432 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
arij | +6.705 |
typ | +5.644 |
PHOTO | +5.240 |
Picture | +5.062 |
onel | +5.049 |
Neg logit contributions | |
stein | -6.241 |
strings | -6.120 |
uterus | -6.077 |
chairs | -6.028 |
(£ | -5.821 |
Token | ( |
Token ID | 357 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
arij | +3.125 |
typ | +2.662 |
PHOTO | +2.414 |
onel | +2.371 |
Picture | +2.328 |
Neg logit contributions | |
stein | -2.489 |
strings | -2.488 |
uterus | -2.388 |
chairs | -2.355 |
(£ | -2.319 |
Token | Chem |
Token ID | 41829 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
arij | +8.777 |
typ | +7.344 |
Chem | +6.946 |
chel | +6.843 |
PHOTO | +6.774 |
Neg logit contributions | |
stein | -14.926 |
uterus | -14.764 |
strings | -14.707 |
(£ | -14.534 |
yre | -14.451 |
Token | Cam |
Token ID | 21701 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
arij | +6.495 |
typ | +5.442 |
PHOTO | +4.922 |
onel | +4.834 |
cade | +4.705 |
Neg logit contributions | |
stein | -5.465 |
strings | -5.413 |
uterus | -5.383 |
(£ | -5.203 |
chairs | -5.191 |
Token | ) |
Token ID | 8 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
arij | +3.020 |
typ | +2.561 |
PHOTO | +2.338 |
onel | +2.270 |
Picture | +2.218 |
Neg logit contributions | |
strings | -2.256 |
stein | -2.251 |
uterus | -2.174 |
chairs | -2.127 |
(£ | -2.113 |
Token | instrument |
Token ID | 8875 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
arij | +3.873 |
typ | +3.287 |
PHOTO | +2.986 |
onel | +2.924 |
Picture | +2.833 |
Neg logit contributions | |
stein | -2.820 |
strings | -2.793 |
uterus | -2.699 |
chairs | -2.649 |
(£ | -2.625 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
arij | +4.728 |
typ | +4.012 |
PHOTO | +3.637 |
onel | +3.584 |
Picture | +3.456 |
Neg logit contributions | |
stein | -3.372 |
strings | -3.343 |
uterus | -3.254 |
chairs | -3.172 |
(£ | -3.131 |
Token | Jerome |
Token ID | 33617 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
arij | +1.737 |
typ | +1.491 |
PHOTO | +1.353 |
onel | +1.336 |
Picture | +1.292 |
Neg logit contributions | |
stein | -1.078 |
strings | -1.066 |
uterus | -1.030 |
chairs | -1.004 |
(£ | -1.003 |
Token | Ave |
Token ID | 12761 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
arij | +5.242 |
typ | +4.503 |
PHOTO | +4.065 |
onel | +4.023 |
Picture | +3.929 |
Neg logit contributions | |
strings | -3.689 |
stein | -3.623 |
uterus | -3.566 |
chairs | -3.458 |
(£ | -3.439 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
arij | +7.636 |
typ | +6.602 |
PHOTO | +5.897 |
onel | +5.734 |
Picture | +5.642 |
Neg logit contributions | |
strings | -6.586 |
stein | -6.465 |
uterus | -6.403 |
(£ | -6.225 |
chairs | -6.220 |
Token | home |
Token ID | 1363 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
arij | +4.938 |
typ | +4.172 |
PHOTO | +3.800 |
onel | +3.683 |
Picture | +3.604 |
Neg logit contributions | |
stein | -3.978 |
strings | -3.952 |
uterus | -3.830 |
chairs | -3.747 |
(£ | -3.737 |
Token | at |
Token ID | 379 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
arij | +6.634 |
typ | +5.643 |
PHOTO | +5.100 |
onel | +5.003 |
Picture | +4.864 |
Neg logit contributions | |
stein | -4.951 |
strings | -4.945 |
uterus | -4.820 |
chairs | -4.693 |
(£ | -4.648 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
arij | +0.330 |
typ | +0.279 |
PHOTO | +0.252 |
onel | +0.251 |
adier | +0.240 |
Neg logit contributions | |
stein | -0.217 |
strings | -0.211 |
uterus | -0.206 |
(£ | -0.200 |
chairs | -0.199 |
Token | a |
Token ID | 257 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
arij | +10.345 |
typ | +8.855 |
PHOTO | +7.854 |
Picture | +7.542 |
chel | +7.444 |
Neg logit contributions | |
strings | -8.670 |
uterus | -8.584 |
stein | -8.455 |
chairs | -8.258 |
yre | -8.180 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
arij | +4.775 |
typ | +4.108 |
PHOTO | +3.611 |
onel | +3.551 |
chel | +3.435 |
Neg logit contributions | |
strings | -4.360 |
uterus | -4.310 |
stein | -4.295 |
chairs | -4.148 |
(£ | -4.117 |
Token | m |
Token ID | 76 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
arij | +0.221 |
typ | +0.187 |
PHOTO | +0.173 |
onel | +0.171 |
ativity | +0.167 |
Neg logit contributions | |
stein | -0.108 |
strings | -0.105 |
chairs | -0.098 |
(£ | -0.097 |
uterus | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
arij | +8.745 |
typ | +6.797 |
PHOTO | +6.133 |
onel | +6.007 |
chel | +5.660 |
Neg logit contributions | |
strings | -10.628 |
uterus | -10.241 |
stein | -10.198 |
ドラ | -10.037 |
chairs | -10.022 |
Token | according |
Token ID | 1864 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
arij | +1.348 |
typ | +1.147 |
PHOTO | +1.039 |
onel | +1.031 |
adier | +0.991 |
Neg logit contributions | |
stein | -0.832 |
strings | -0.819 |
uterus | -0.795 |
(£ | -0.773 |
chairs | -0.771 |