Token |
|
Token ID | 198 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
jj | +0.003 |
sson | +0.003 |
andem | +0.003 |
zai | +0.003 |
hamm | +0.002 |
Neg logit contributions | |
�� | -0.006 |
LEY | -0.005 |
YL | -0.005 |
AF | -0.005 |
SAM | -0.005 |
Token | pur |
Token ID | 14225 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
jj | +0.375 |
sson | +0.369 |
andem | +0.351 |
zai | +0.337 |
hamm | +0.336 |
Neg logit contributions | |
�� | -0.359 |
LEY | -0.308 |
YL | -0.285 |
AF | -0.278 |
SAM | -0.277 |
Token | ak |
Token ID | 461 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
�� | +1.164 |
LEY | +1.046 |
YL | +0.987 |
AF | +0.975 |
AH | +0.972 |
Neg logit contributions | |
jj | -0.683 |
sson | -0.673 |
andem | -0.628 |
hamm | -0.594 |
zai | -0.586 |
Token | ushi |
Token ID | 17731 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
jj | +1.251 |
sson | +1.227 |
andem | +1.154 |
zai | +1.095 |
hamm | +1.089 |
Neg logit contributions | |
�� | -1.752 |
LEY | -1.541 |
YL | -1.447 |
AF | -1.417 |
SAM | -1.411 |
Token | Profile |
Token ID | 13118 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
jj | +0.520 |
sson | +0.511 |
andem | +0.482 |
zai | +0.459 |
hamm | +0.456 |
Neg logit contributions | |
�� | -0.674 |
LEY | -0.590 |
YL | -0.553 |
AF | -0.541 |
SAM | -0.538 |
Token | Joined |
Token ID | 16709 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
�� | +2.743 |
LEY | +2.327 |
YL | +2.058 |
AF | +2.006 |
AH | +1.964 |
Neg logit contributions | |
jj | -4.709 |
sson | -4.631 |
andem | -4.476 |
itle | -4.308 |
zai | -4.275 |
Token | August |
Token ID | 2932 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
�� | +5.666 |
LEY | +5.402 |
YL | +4.991 |
AF | +4.846 |
AH | +4.803 |
Neg logit contributions | |
jj | -4.732 |
sson | -4.642 |
andem | -4.617 |
itle | -4.315 |
rupal | -4.172 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
�� | +0.448 |
LEY | +0.397 |
YL | +0.375 |
AF | +0.368 |
SAM | +0.366 |
Neg logit contributions | |
jj | -0.269 |
sson | -0.263 |
andem | -0.246 |
zai | -0.232 |
hamm | -0.230 |
Token | United |
Token ID | 1578 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
�� | +0.535 |
LEY | +0.464 |
YL | +0.432 |
AF | +0.422 |
SAM | +0.419 |
Neg logit contributions | |
jj | -0.498 |
sson | -0.489 |
andem | -0.466 |
zai | -0.444 |
hamm | -0.442 |
Token | States |
Token ID | 1829 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
�� | +0.565 |
LEY | +0.461 |
YL | +0.414 |
AF | +0.400 |
SAM | +0.396 |
Neg logit contributions | |
jj | -0.951 |
sson | -0.939 |
andem | -0.903 |
zai | -0.874 |
hamm | -0.868 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
�� | +0.570 |
LEY | +0.496 |
YL | +0.464 |
AF | +0.453 |
SAM | +0.451 |
Neg logit contributions | |
jj | -0.476 |
sson | -0.467 |
andem | -0.442 |
zai | -0.421 |
hamm | -0.419 |
Token | P |
Token ID | 350 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
jj | +0.004 |
sson | +0.004 |
andem | +0.004 |
zai | +0.004 |
hamm | +0.004 |
Neg logit contributions | |
�� | -0.004 |
LEY | -0.003 |
YL | -0.003 |
AF | -0.003 |
SAM | -0.003 |
Token | ORT |
Token ID | 9863 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
�� | +0.019 |
LEY | +0.016 |
YL | +0.015 |
AF | +0.014 |
AH | +0.014 |
Neg logit contributions | |
jj | -0.028 |
sson | -0.028 |
andem | -0.027 |
zai | -0.026 |
hamm | -0.026 |
Token | ON |
Token ID | 6177 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
�� | +1.701 |
LEY | +1.509 |
YL | +1.407 |
AF | +1.371 |
SAM | +1.361 |
Neg logit contributions | |
jj | -1.590 |
sson | -1.554 |
andem | -1.490 |
zai | -1.427 |
hamm | -1.409 |
Token | A |
Token ID | 317 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
�� | +1.446 |
LEY | +1.275 |
YL | +1.186 |
AF | +1.159 |
AH | +1.147 |
Neg logit contributions | |
jj | -1.411 |
sson | -1.387 |
andem | -1.337 |
zai | -1.270 |
hamm | -1.263 |
Token | COMP |
Token ID | 24301 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
jj | +0.053 |
sson | +0.052 |
andem | +0.049 |
zai | +0.048 |
hamm | +0.047 |
Neg logit contributions | |
�� | -0.048 |
LEY | -0.041 |
YL | -0.038 |
AF | -0.037 |
SAM | -0.036 |
Token | UT |
Token ID | 3843 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
�� | +1.189 |
LEY | +1.007 |
YL | +0.907 |
AF | +0.881 |
AH | +0.872 |
Neg logit contributions | |
jj | -2.187 |
sson | -2.157 |
andem | -2.096 |
zai | -2.037 |
hamm | -2.015 |
Token | ER |
Token ID | 1137 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�� | +2.329 |
LEY | +1.869 |
YL | +1.569 |
AF | +1.527 |
AH | +1.460 |
Neg logit contributions | |
jj | -8.337 |
sson | -8.265 |
andem | -8.206 |
zai | -7.920 |
hamm | -7.795 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
�� | +0.939 |
LEY | +0.820 |
YL | +0.765 |
AF | +0.747 |
SAM | +0.743 |
Neg logit contributions | |
jj | -0.847 |
sson | -0.832 |
andem | -0.792 |
zai | -0.757 |
hamm | -0.751 |
Token | THIS |
Token ID | 12680 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
�� | +0.807 |
LEY | +0.701 |
YL | +0.649 |
AF | +0.634 |
SAM | +0.628 |
Neg logit contributions | |
jj | -0.878 |
sson | -0.863 |
andem | -0.825 |
zai | -0.789 |
hamm | -0.784 |
Token | W |
Token ID | 370 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�� | +1.185 |
LEY | +1.027 |
YL | +0.944 |
AF | +0.923 |
SAM | +0.912 |
Neg logit contributions | |
jj | -1.448 |
sson | -1.425 |
andem | -1.372 |
zai | -1.316 |
hamm | -1.297 |
Token | ON |
Token ID | 1340 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�� | +0.728 |
LEY | +0.608 |
YL | +0.552 |
AF | +0.536 |
AH | +0.530 |
Neg logit contributions | |
jj | -1.098 |
sson | -1.083 |
andem | -1.038 |
zai | -1.004 |
hamm | -1.000 |
Token | James |
Token ID | 3700 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
�� | +0.594 |
LEY | +0.523 |
YL | +0.489 |
AF | +0.481 |
AH | +0.477 |
Neg logit contributions | |
jj | -0.453 |
sson | -0.445 |
andem | -0.423 |
zai | -0.400 |
itle | -0.394 |
Token | Gunn |
Token ID | 40837 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
�� | +0.153 |
LEY | +0.133 |
YL | +0.122 |
AF | +0.120 |
SAM | +0.119 |
Neg logit contributions | |
jj | -0.149 |
sson | -0.146 |
andem | -0.139 |
zai | -0.133 |
hamm | -0.132 |
Token | 's |
Token ID | 338 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
�� | +1.281 |
LEY | +1.138 |
YL | +1.068 |
AF | +1.060 |
AH | +1.047 |
Neg logit contributions | |
jj | -0.775 |
sson | -0.752 |
andem | -0.722 |
zai | -0.681 |
itle | -0.667 |
Token | GU |
Token ID | 19348 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
�� | +1.088 |
LEY | +0.955 |
YL | +0.883 |
AF | +0.876 |
AH | +0.862 |
Neg logit contributions | |
jj | -0.986 |
sson | -0.972 |
andem | -0.928 |
zai | -0.894 |
itle | -0.871 |
Token | ARD |
Token ID | 9795 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
jj | +0.286 |
sson | +0.285 |
andem | +0.271 |
zai | +0.265 |
hamm | +0.260 |
Neg logit contributions | |
�� | -0.203 |
LEY | -0.170 |
YL | -0.157 |
AF | -0.152 |
AH | -0.150 |
Token | I |
Token ID | 40 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
�� | +1.638 |
LEY | +1.426 |
YL | +1.332 |
AF | +1.295 |
AH | +1.291 |
Neg logit contributions | |
jj | -1.525 |
sson | -1.499 |
andem | -1.418 |
zai | -1.366 |
hamm | -1.352 |
Token | ANS |
Token ID | 15037 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
�� | +4.400 |
LEY | +3.852 |
YL | +3.809 |
ICE | +3.685 |
AF | +3.670 |
Neg logit contributions | |
jj | -5.406 |
sson | -5.244 |
andem | -5.039 |
zai | -4.947 |
rupal | -4.823 |
Token | OF |
Token ID | 3963 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
�� | +1.890 |
LEY | +1.627 |
YL | +1.486 |
AF | +1.455 |
AH | +1.440 |
Neg logit contributions | |
jj | -2.290 |
sson | -2.255 |
andem | -2.158 |
zai | -2.074 |
itle | -2.054 |
Token | THE |
Token ID | 3336 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
�� | +0.111 |
LEY | +0.097 |
YL | +0.091 |
AF | +0.089 |
SAM | +0.088 |
Neg logit contributions | |
jj | -0.091 |
sson | -0.090 |
andem | -0.085 |
zai | -0.081 |
hamm | -0.080 |
Token | G |
Token ID | 402 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
�� | +0.904 |
LEY | +0.736 |
YL | +0.662 |
AF | +0.638 |
SAM | +0.636 |
Neg logit contributions | |
jj | -1.429 |
sson | -1.410 |
andem | -1.353 |
zai | -1.306 |
hamm | -1.305 |
Token | AL |
Token ID | 1847 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
�� | +0.798 |
LEY | +0.609 |
YL | +0.531 |
SAM | +0.505 |
AF | +0.495 |
Neg logit contributions | |
jj | -1.612 |
sson | -1.582 |
andem | -1.524 |
hamm | -1.480 |
zai | -1.474 |
Token | apparently |
Token ID | 5729 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
jj | +0.409 |
sson | +0.401 |
andem | +0.380 |
zai | +0.355 |
itle | +0.351 |
Neg logit contributions | |
�� | -0.603 |
LEY | -0.533 |
YL | -0.503 |
AF | -0.494 |
AH | -0.491 |
Token | did |
Token ID | 750 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
�� | +1.278 |
LEY | +1.134 |
YL | +1.065 |
AF | +1.052 |
AH | +1.044 |
Neg logit contributions | |
jj | -0.935 |
sson | -0.921 |
andem | -0.876 |
zai | -0.818 |
itle | -0.810 |
Token | not |
Token ID | 407 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
jj | +0.702 |
sson | +0.690 |
andem | +0.651 |
zai | +0.621 |
hamm | +0.616 |
Neg logit contributions | |
�� | -0.864 |
LEY | -0.753 |
YL | -0.706 |
AF | -0.691 |
SAM | -0.687 |
Token | learn |
Token ID | 2193 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
jj | +0.311 |
sson | +0.306 |
andem | +0.290 |
zai | +0.276 |
hamm | +0.273 |
Neg logit contributions | |
�� | -0.359 |
LEY | -0.313 |
YL | -0.293 |
AF | -0.287 |
AH | -0.285 |
Token | a |
Token ID | 257 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
jj | +0.922 |
sson | +0.903 |
andem | +0.848 |
zai | +0.803 |
hamm | +0.798 |
Neg logit contributions | |
�� | -1.352 |
LEY | -1.191 |
YL | -1.121 |
AF | -1.098 |
SAM | -1.094 |
Token | single |
Token ID | 2060 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
�� | +2.100 |
LEY | +1.831 |
YL | +1.699 |
AF | +1.677 |
SAM | +1.659 |
Neg logit contributions | |
jj | -1.943 |
sson | -1.917 |
andem | -1.829 |
zai | -1.738 |
itle | -1.724 |
Token | damn |
Token ID | 12270 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
�� | +4.617 |
LEY | +4.099 |
AF | +3.807 |
YL | +3.784 |
SAM | +3.740 |
Neg logit contributions | |
jj | -4.297 |
sson | -4.280 |
andem | -4.132 |
zai | -3.819 |
itle | -3.767 |
Token | thing |
Token ID | 1517 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
�� | +3.810 |
LEY | +3.360 |
YL | +3.140 |
AF | +3.107 |
AH | +3.080 |
Neg logit contributions | |
jj | -3.514 |
sson | -3.479 |
andem | -3.325 |
zai | -3.105 |
hamm | -3.080 |
Token | from |
Token ID | 422 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
�� | +4.540 |
LEY | +3.960 |
YL | +3.741 |
AF | +3.689 |
AH | +3.643 |
Neg logit contributions | |
jj | -3.906 |
sson | -3.851 |
andem | -3.690 |
zai | -3.411 |
itle | -3.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.582 |
LEY | +0.511 |
YL | +0.479 |
AF | +0.470 |
AH | +0.467 |
Neg logit contributions | |
jj | -0.448 |
sson | -0.441 |
andem | -0.417 |
zai | -0.396 |
hamm | -0.391 |
Token | embarrassment |
Token ID | 24655 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
jj | +0.561 |
sson | +0.551 |
andem | +0.522 |
zai | +0.498 |
hamm | +0.496 |
Neg logit contributions | |
�� | -0.645 |
LEY | -0.560 |
YL | -0.523 |
AF | -0.510 |
SAM | -0.508 |
Token | k |
Token ID | 74 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
jj | +0.417 |
sson | +0.401 |
andem | +0.355 |
zai | +0.318 |
hamm | +0.314 |
Neg logit contributions | |
�� | -1.468 |
LEY | -1.334 |
YL | -1.276 |
AF | -1.256 |
SAM | -1.253 |
Token | [ |
Token ID | 685 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
jj | +0.225 |
sson | +0.221 |
andem | +0.207 |
zai | +0.199 |
hamm | +0.199 |
Neg logit contributions | |
�� | -0.262 |
LEY | -0.224 |
YL | -0.209 |
AF | -0.204 |
SAM | -0.204 |
Token | 10 |
Token ID | 940 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
�� | +1.734 |
LEY | +1.571 |
YL | +1.487 |
AF | +1.463 |
SAM | +1.453 |
Neg logit contributions | |
jj | -1.125 |
sson | -1.104 |
andem | -1.048 |
hamm | -0.987 |
zai | -0.986 |
Token | : |
Token ID | 25 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
�� | +0.614 |
LEY | +0.558 |
YL | +0.532 |
AF | +0.524 |
SAM | +0.522 |
Neg logit contributions | |
jj | -0.234 |
sson | -0.226 |
andem | -0.208 |
zai | -0.190 |
hamm | -0.189 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
�� | +0.820 |
LEY | +0.714 |
YL | +0.662 |
AF | +0.646 |
SAM | +0.643 |
Neg logit contributions | |
jj | -0.804 |
sson | -0.795 |
andem | -0.759 |
zai | -0.725 |
hamm | -0.723 |
Token | ] |
Token ID | 60 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
�� | +1.706 |
LEY | +1.489 |
YL | +1.384 |
AF | +1.352 |
SAM | +1.344 |
Neg logit contributions | |
jj | -1.666 |
sson | -1.639 |
andem | -1.567 |
zai | -1.494 |
hamm | -1.490 |
Token | < |
Token ID | 1279 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
�� | +3.921 |
LEY | +3.465 |
YL | +3.188 |
AF | +3.085 |
AH | +3.064 |
Neg logit contributions | |
jj | -5.027 |
sson | -4.944 |
andem | -4.783 |
zai | -4.531 |
itle | -4.519 |
Token | j |
Token ID | 73 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
�� | +2.386 |
LEY | +2.137 |
YL | +2.015 |
AF | +1.983 |
SAM | +1.978 |
Neg logit contributions | |
jj | -1.476 |
sson | -1.467 |
andem | -1.375 |
hamm | -1.306 |
zai | -1.284 |
Token | th |
Token ID | 400 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
�� | +1.442 |
LEY | +1.288 |
YL | +1.207 |
AF | +1.189 |
AH | +1.183 |
Neg logit contributions | |
jj | -1.037 |
sson | -1.023 |
andem | -0.962 |
hamm | -0.922 |
zai | -0.917 |
Token | w |
Token ID | 86 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
�� | +1.326 |
LEY | +1.184 |
YL | +1.119 |
AF | +1.109 |
AH | +1.093 |
Neg logit contributions | |
jj | -0.832 |
sson | -0.823 |
andem | -0.767 |
hamm | -0.739 |
zai | -0.728 |
Token | > |
Token ID | 29 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
�� | +0.309 |
LEY | +0.273 |
YL | +0.256 |
AF | +0.252 |
AH | +0.250 |
Neg logit contributions | |
jj | -0.222 |
sson | -0.220 |
andem | -0.206 |
hamm | -0.197 |
zai | -0.197 |
Token | is |
Token ID | 318 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
jj | +0.512 |
sson | +0.500 |
andem | +0.469 |
zai | +0.440 |
hamm | +0.435 |
Neg logit contributions | |
�� | -0.866 |
LEY | -0.770 |
YL | -0.729 |
AF | -0.715 |
SAM | -0.713 |
Token | ). |
Token ID | 737 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
�� | +1.151 |
LEY | +1.017 |
YL | +0.961 |
AF | +0.943 |
AH | +0.938 |
Neg logit contributions | |
jj | -0.808 |
sson | -0.789 |
andem | -0.745 |
zai | -0.705 |
hamm | -0.698 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
�� | +0.885 |
LEY | +0.783 |
YL | +0.740 |
AF | +0.729 |
SAM | +0.724 |
Neg logit contributions | |
jj | -0.593 |
sson | -0.582 |
andem | -0.545 |
zai | -0.515 |
hamm | -0.511 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
�� | +0.669 |
LEY | +0.599 |
YL | +0.567 |
AF | +0.557 |
SAM | +0.554 |
Neg logit contributions | |
jj | -0.380 |
sson | -0.372 |
andem | -0.348 |
zai | -0.326 |
hamm | -0.325 |
Token | sudo |
Token ID | 24032 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
�� | +0.776 |
LEY | +0.682 |
YL | +0.640 |
AF | +0.633 |
AH | +0.626 |
Neg logit contributions | |
jj | -0.676 |
sson | -0.671 |
andem | -0.637 |
hamm | -0.610 |
zai | -0.607 |
Token | system |
Token ID | 1080 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
�� | +3.386 |
LEY | +2.954 |
YL | +2.810 |
AF | +2.756 |
SAM | +2.728 |
Neg logit contributions | |
jj | -2.730 |
sson | -2.698 |
andem | -2.568 |
zai | -2.416 |
itle | -2.357 |
Token | ctl |
Token ID | 34168 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
�� | +3.658 |
LEY | +3.181 |
AF | +2.957 |
YL | +2.847 |
AH | +2.839 |
Neg logit contributions | |
sson | -5.092 |
jj | -5.053 |
andem | -4.849 |
zai | -4.696 |
rupal | -4.616 |
Token | restart |
Token ID | 15765 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
�� | +2.029 |
LEY | +1.777 |
YL | +1.670 |
AF | +1.644 |
SAM | +1.615 |
Neg logit contributions | |
jj | -1.809 |
sson | -1.782 |
andem | -1.703 |
zai | -1.628 |
itle | -1.599 |
Token | network |
Token ID | 3127 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
�� | +2.577 |
LEY | +2.252 |
YL | +2.156 |
AF | +2.099 |
AH | +2.078 |
Neg logit contributions | |
jj | -2.204 |
sson | -2.173 |
andem | -2.102 |
itle | -1.957 |
zai | -1.950 |
Token | - |
Token ID | 12 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�� | +1.725 |
LEY | +1.495 |
YL | +1.383 |
AF | +1.371 |
AH | +1.348 |
Neg logit contributions | |
jj | -1.770 |
sson | -1.742 |
andem | -1.688 |
zai | -1.606 |
itle | -1.582 |
Token | manager |
Token ID | 37153 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
�� | +0.812 |
LEY | +0.701 |
YL | +0.641 |
AF | +0.641 |
SAM | +0.635 |
Neg logit contributions | |
jj | -0.941 |
sson | -0.923 |
andem | -0.892 |
zai | -0.859 |
hamm | -0.849 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
�� | +1.729 |
LEY | +1.572 |
YL | +1.484 |
AF | +1.462 |
SAM | +1.453 |
Neg logit contributions | |
jj | -1.050 |
sson | -1.025 |
andem | -0.978 |
zai | -0.912 |
hamm | -0.909 |
Token | re |
Token ID | 260 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
�� | +2.055 |
LEY | +1.827 |
YL | +1.716 |
AF | +1.690 |
AH | +1.677 |
Neg logit contributions | |
jj | -1.751 |
sson | -1.748 |
andem | -1.663 |
hamm | -1.613 |
zai | -1.580 |
Token | i |
Token ID | 72 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
jj | +0.601 |
sson | +0.591 |
andem | +0.555 |
hamm | +0.527 |
zai | +0.526 |
Neg logit contributions | |
�� | -0.838 |
LEY | -0.737 |
YL | -0.693 |
AF | -0.679 |
SAM | -0.675 |
Token | Profile |
Token ID | 13118 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
jj | +1.460 |
sson | +1.431 |
andem | +1.355 |
zai | +1.293 |
hamm | +1.283 |
Neg logit contributions | |
�� | -1.674 |
LEY | -1.448 |
YL | -1.350 |
AF | -1.317 |
SAM | -1.315 |
Token | Blog |
Token ID | 14001 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
�� | +1.354 |
LEY | +1.140 |
YL | +1.026 |
AF | +0.999 |
AH | +0.982 |
Neg logit contributions | |
jj | -2.040 |
sson | -2.011 |
andem | -1.935 |
zai | -1.859 |
itle | -1.859 |
Token | Joined |
Token ID | 16709 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
�� | +1.764 |
LEY | +1.448 |
YL | +1.313 |
AF | +1.267 |
SAM | +1.261 |
Neg logit contributions | |
jj | -2.636 |
sson | -2.602 |
andem | -2.491 |
zai | -2.409 |
hamm | -2.399 |
Token | October |
Token ID | 3267 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
�� | +4.888 |
LEY | +4.573 |
YL | +4.268 |
AF | +4.138 |
AH | +4.114 |
Neg logit contributions | |
jj | -3.796 |
sson | -3.719 |
andem | -3.639 |
itle | -3.416 |
zai | -3.306 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
jj | +0.135 |
sson | +0.134 |
andem | +0.121 |
hamm | +0.115 |
zai | +0.115 |
Neg logit contributions | |
�� | -0.248 |
LEY | -0.218 |
YL | -0.207 |
AF | -0.202 |
SAM | -0.202 |
Token | United |
Token ID | 1578 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
jj | +0.758 |
sson | +0.747 |
andem | +0.700 |
zai | +0.673 |
hamm | +0.671 |
Neg logit contributions | |
�� | -0.864 |
LEY | -0.735 |
YL | -0.687 |
SAM | -0.670 |
AF | -0.667 |
Token | States |
Token ID | 1829 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
�� | +0.018 |
LEY | +0.014 |
YL | +0.013 |
AF | +0.012 |
SAM | +0.012 |
Neg logit contributions | |
jj | -0.030 |
sson | -0.030 |
andem | -0.029 |
zai | -0.028 |
hamm | -0.028 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
�� | +0.012 |
LEY | +0.010 |
YL | +0.010 |
AF | +0.010 |
SAM | +0.009 |
Neg logit contributions | |
jj | -0.010 |
sson | -0.010 |
andem | -0.009 |
zai | -0.009 |
hamm | -0.009 |
Token | k |
Token ID | 74 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
jj | +0.560 |
sson | +0.538 |
andem | +0.472 |
zai | +0.424 |
hamm | +0.417 |
Neg logit contributions | |
�� | -2.012 |
LEY | -1.822 |
YL | -1.744 |
AF | -1.717 |
SAM | -1.714 |
Token | [ |
Token ID | 685 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
jj | +0.544 |
sson | +0.535 |
andem | +0.497 |
zai | +0.480 |
hamm | +0.479 |
Neg logit contributions | |
�� | -0.653 |
LEY | -0.554 |
YL | -0.518 |
SAM | -0.505 |
AF | -0.505 |
Token | 10 |
Token ID | 940 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
�� | +1.526 |
LEY | +1.382 |
YL | +1.308 |
AF | +1.287 |
SAM | +1.278 |
Neg logit contributions | |
jj | -0.989 |
sson | -0.970 |
andem | -0.921 |
hamm | -0.867 |
zai | -0.867 |
Token | : |
Token ID | 25 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
�� | +0.564 |
LEY | +0.512 |
YL | +0.488 |
AF | +0.480 |
SAM | +0.479 |
Neg logit contributions | |
jj | -0.214 |
sson | -0.207 |
andem | -0.190 |
zai | -0.174 |
hamm | -0.172 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
�� | +0.910 |
LEY | +0.792 |
YL | +0.735 |
AF | +0.716 |
SAM | +0.714 |
Neg logit contributions | |
jj | -0.892 |
sson | -0.882 |
andem | -0.841 |
zai | -0.804 |
hamm | -0.802 |
Token | ] |
Token ID | 60 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +1.990 |
LEY | +1.748 |
YL | +1.623 |
AF | +1.588 |
SAM | +1.577 |
Neg logit contributions | |
jj | -1.993 |
sson | -1.962 |
andem | -1.884 |
zai | -1.793 |
hamm | -1.791 |
Token | < |
Token ID | 1279 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
�� | +3.925 |
LEY | +3.383 |
YL | +3.120 |
AF | +3.010 |
AH | +2.991 |
Neg logit contributions | |
jj | -4.882 |
sson | -4.837 |
andem | -4.611 |
itle | -4.389 |
zai | -4.382 |
Token | mad |
Token ID | 9937 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
�� | +2.424 |
LEY | +2.174 |
YL | +2.051 |
AF | +2.020 |
SAM | +2.016 |
Neg logit contributions | |
jj | -1.481 |
sson | -1.476 |
andem | -1.379 |
hamm | -1.311 |
zai | -1.288 |
Token | ag |
Token ID | 363 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
�� | +0.516 |
LEY | +0.456 |
YL | +0.428 |
AF | +0.420 |
SAM | +0.418 |
Neg logit contributions | |
jj | -0.358 |
sson | -0.352 |
andem | -0.331 |
hamm | -0.314 |
zai | -0.313 |
Token | ast |
Token ID | 459 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
�� | +0.090 |
LEY | +0.080 |
YL | +0.075 |
AF | +0.074 |
AH | +0.073 |
Neg logit contributions | |
jj | -0.064 |
sson | -0.063 |
andem | -0.059 |
hamm | -0.056 |
zai | -0.056 |
Token | > |
Token ID | 29 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
�� | +1.846 |
LEY | +1.650 |
YL | +1.546 |
AF | +1.533 |
AH | +1.514 |
Neg logit contributions | |
jj | -1.347 |
sson | -1.328 |
andem | -1.252 |
hamm | -1.204 |
zai | -1.200 |
Token | bullying |
Token ID | 20714 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
jj | +0.539 |
sson | +0.528 |
andem | +0.498 |
zai | +0.472 |
hamm | +0.469 |
Neg logit contributions | |
�� | -0.712 |
LEY | -0.624 |
YL | -0.586 |
AF | -0.574 |
SAM | -0.571 |
Token | in |
Token ID | 287 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
jj | +0.345 |
sson | +0.338 |
andem | +0.317 |
zai | +0.299 |
hamm | +0.298 |
Neg logit contributions | |
�� | -0.509 |
LEY | -0.450 |
YL | -0.424 |
AF | -0.415 |
AH | -0.413 |
Token | schools |
Token ID | 4266 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
jj | +0.474 |
sson | +0.464 |
andem | +0.439 |
zai | +0.418 |
hamm | +0.415 |
Neg logit contributions | |
�� | -0.550 |
LEY | -0.481 |
YL | -0.450 |
AF | -0.440 |
SAM | -0.438 |
Token | : |
Token ID | 25 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
jj | +0.290 |
sson | +0.284 |
andem | +0.263 |
zai | +0.247 |
hamm | +0.246 |
Neg logit contributions | |
�� | -0.528 |
LEY | -0.471 |
YL | -0.445 |
AF | -0.438 |
SAM | -0.436 |
Token | The |
Token ID | 383 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
jj | +0.174 |
sson | +0.170 |
andem | +0.162 |
zai | +0.154 |
hamm | +0.153 |
Neg logit contributions | |
�� | -0.194 |
LEY | -0.168 |
YL | -0.157 |
AF | -0.154 |
SAM | -0.153 |
Token | oret |
Token ID | 9997 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
�� | +1.003 |
LEY | +0.887 |
YL | +0.833 |
AF | +0.817 |
SAM | +0.811 |
Neg logit contributions | |
jj | -0.719 |
sson | -0.702 |
andem | -0.661 |
zai | -0.627 |
itle | -0.622 |
Token | ical |
Token ID | 605 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
�� | +4.481 |
LEY | +3.854 |
YL | +3.641 |
ICE | +3.628 |
AF | +3.609 |
Neg logit contributions | |
jj | -4.127 |
sson | -3.916 |
andem | -3.749 |
hamm | -3.681 |
zai | -3.625 |
Token | perspectives |
Token ID | 22582 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
jj | +0.139 |
sson | +0.136 |
andem | +0.128 |
zai | +0.121 |
hamm | +0.120 |
Neg logit contributions | |
�� | -0.196 |
LEY | -0.172 |
YL | -0.162 |
AF | -0.159 |
SAM | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
jj | +0.605 |
sson | +0.594 |
andem | +0.560 |
zai | +0.533 |
hamm | +0.530 |
Neg logit contributions | |
�� | -0.773 |
LEY | -0.676 |
YL | -0.633 |
AF | -0.619 |
SAM | -0.617 |
Token | their |
Token ID | 511 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
�� | +0.671 |
LEY | +0.588 |
YL | +0.549 |
AF | +0.540 |
SAM | +0.537 |
Neg logit contributions | |
jj | -0.530 |
sson | -0.518 |
andem | -0.492 |
zai | -0.467 |
itle | -0.461 |
Token | implications |
Token ID | 10939 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
jj | +1.002 |
sson | +0.985 |
andem | +0.928 |
hamm | +0.886 |
zai | +0.885 |
Neg logit contributions | |
�� | -1.246 |
LEY | -1.082 |
YL | -1.015 |
AF | -0.987 |
SAM | -0.987 |
Token | J |
Token ID | 41 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
�� | +1.642 |
LEY | +1.452 |
YL | +1.362 |
AF | +1.338 |
AH | +1.332 |
Neg logit contributions | |
jj | -1.377 |
sson | -1.367 |
andem | -1.299 |
hamm | -1.252 |
zai | -1.233 |
Token | aaaa |
Token ID | 24794 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
�� | +0.366 |
LEY | +0.322 |
YL | +0.302 |
AF | +0.296 |
AH | +0.294 |
Neg logit contributions | |
jj | -0.295 |
sson | -0.290 |
andem | -0.274 |
zai | -0.262 |
hamm | -0.261 |
Token | asper |
Token ID | 32981 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
�� | +1.174 |
LEY | +1.033 |
YL | +0.972 |
AF | +0.957 |
AH | +0.954 |
Neg logit contributions | |
jj | -0.903 |
sson | -0.897 |
andem | -0.841 |
hamm | -0.804 |
zai | -0.803 |
Token | Profile |
Token ID | 13118 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
�� | +0.532 |
LEY | +0.454 |
YL | +0.417 |
AF | +0.407 |
AH | +0.404 |
Neg logit contributions | |
jj | -0.629 |
sson | -0.621 |
andem | -0.595 |
hamm | -0.571 |
zai | -0.570 |
Token | Blog |
Token ID | 14001 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
�� | +2.142 |
LEY | +1.811 |
YL | +1.623 |
AF | +1.582 |
AH | +1.550 |
Neg logit contributions | |
jj | -3.257 |
sson | -3.213 |
andem | -3.089 |
zai | -2.968 |
itle | -2.967 |
Token | Joined |
Token ID | 16709 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
�� | +2.096 |
LEY | +1.734 |
YL | +1.561 |
AF | +1.511 |
SAM | +1.495 |
Neg logit contributions | |
jj | -3.333 |
sson | -3.283 |
andem | -3.169 |
zai | -3.047 |
hamm | -3.037 |
Token | April |
Token ID | 3035 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
�� | +4.701 |
LEY | +4.402 |
YL | +4.101 |
AF | +3.994 |
AH | +3.949 |
Neg logit contributions | |
jj | -3.699 |
sson | -3.614 |
andem | -3.556 |
itle | -3.328 |
zai | -3.227 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
jj | +0.292 |
sson | +0.291 |
andem | +0.262 |
zai | +0.248 |
hamm | +0.247 |
Neg logit contributions | |
�� | -0.547 |
LEY | -0.475 |
YL | -0.453 |
SAM | -0.443 |
AF | -0.441 |
Token | United |
Token ID | 1578 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
jj | +1.137 |
sson | +1.121 |
andem | +1.047 |
zai | +1.009 |
hamm | +1.005 |
Neg logit contributions | |
�� | -1.295 |
LEY | -1.100 |
YL | -1.030 |
SAM | -1.003 |
AF | -0.999 |
Token | States |
Token ID | 1829 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
jj | +1.430 |
sson | +1.412 |
andem | +1.353 |
zai | +1.308 |
hamm | +1.306 |
Neg logit contributions | |
�� | -0.884 |
LEY | -0.716 |
YL | -0.647 |
SAM | -0.617 |
AF | -0.617 |
Token | 5 |
Token ID | 642 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
jj | +0.604 |
sson | +0.594 |
andem | +0.556 |
zai | +0.533 |
hamm | +0.532 |
Neg logit contributions | |
�� | -0.734 |
LEY | -0.630 |
YL | -0.591 |
SAM | -0.576 |
AF | -0.575 |
Token | left |
Token ID | 1364 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
�� | +0.598 |
LEY | +0.527 |
YL | +0.496 |
AF | +0.485 |
AH | +0.480 |
Neg logit contributions | |
jj | -0.488 |
sson | -0.475 |
andem | -0.455 |
zai | -0.434 |
itle | -0.423 |
Token | Scotland |
Token ID | 8838 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
�� | +1.181 |
LEY | +1.051 |
YL | +0.986 |
AF | +0.969 |
AH | +0.958 |
Neg logit contributions | |
jj | -0.952 |
sson | -0.929 |
andem | -0.885 |
zai | -0.845 |
itle | -0.828 |
Token | without |
Token ID | 1231 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
jj | +0.035 |
sson | +0.034 |
andem | +0.032 |
zai | +0.030 |
hamm | +0.030 |
Neg logit contributions | |
�� | -0.050 |
LEY | -0.045 |
YL | -0.042 |
AF | -0.041 |
AH | -0.041 |
Token | making |
Token ID | 1642 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
�� | +0.660 |
LEY | +0.581 |
YL | +0.543 |
AF | +0.531 |
AH | +0.529 |
Neg logit contributions | |
jj | -0.563 |
sson | -0.550 |
andem | -0.525 |
zai | -0.501 |
hamm | -0.493 |
Token | a |
Token ID | 257 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
�� | +0.083 |
LEY | +0.073 |
YL | +0.069 |
AF | +0.068 |
SAM | +0.067 |
Neg logit contributions | |
jj | -0.056 |
sson | -0.055 |
andem | -0.052 |
zai | -0.049 |
hamm | -0.048 |
Token | single |
Token ID | 2060 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
�� | +2.322 |
LEY | +2.057 |
YL | +1.923 |
AF | +1.907 |
SAM | +1.883 |
Neg logit contributions | |
jj | -1.702 |
sson | -1.676 |
andem | -1.593 |
zai | -1.517 |
itle | -1.480 |
Token | first |
Token ID | 717 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
�� | +4.243 |
LEY | +3.793 |
AF | +3.588 |
ICE | +3.464 |
YL | +3.457 |
Neg logit contributions | |
jj | -4.162 |
sson | -4.041 |
andem | -3.999 |
zai | -3.828 |
itle | -3.656 |
Token | - |
Token ID | 12 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
�� | +0.101 |
LEY | +0.089 |
YL | +0.084 |
AF | +0.083 |
ICE | +0.082 |
Neg logit contributions | |
jj | -0.072 |
sson | -0.071 |
andem | -0.069 |
zai | -0.065 |
hamm | -0.063 |
Token | team |
Token ID | 15097 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
�� | +0.119 |
LEY | +0.102 |
AF | +0.095 |
YL | +0.093 |
SAM | +0.093 |
Neg logit contributions | |
jj | -0.132 |
sson | -0.132 |
andem | -0.128 |
zai | -0.123 |
hamm | -0.122 |
Token | appearance |
Token ID | 5585 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
�� | +2.399 |
LEY | +2.062 |
AF | +1.931 |
YL | +1.908 |
ICE | +1.889 |
Neg logit contributions | |
jj | -2.630 |
sson | -2.575 |
andem | -2.512 |
zai | -2.440 |
hamm | -2.359 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
�� | +1.699 |
LEY | +1.517 |
YL | +1.429 |
AF | +1.418 |
AH | +1.397 |
Neg logit contributions | |
jj | -1.308 |
sson | -1.267 |
andem | -1.214 |
zai | -1.152 |
hamm | -1.145 |
Token | lol |
Token ID | 19462 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
jj | +0.464 |
sson | +0.457 |
andem | +0.433 |
zai | +0.413 |
hamm | +0.410 |
Neg logit contributions | |
�� | -0.525 |
LEY | -0.456 |
YL | -0.426 |
AF | -0.416 |
AH | -0.414 |
Token | [ |
Token ID | 685 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
�� | +0.392 |
LEY | +0.340 |
YL | +0.316 |
AF | +0.307 |
AH | +0.306 |
Neg logit contributions | |
jj | -0.377 |
sson | -0.375 |
andem | -0.356 |
zai | -0.339 |
hamm | -0.337 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
�� | +1.119 |
LEY | +1.007 |
YL | +0.953 |
AF | +0.937 |
SAM | +0.932 |
Neg logit contributions | |
jj | -0.706 |
sson | -0.693 |
andem | -0.654 |
zai | -0.616 |
hamm | -0.615 |
Token | : |
Token ID | 25 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
�� | +0.152 |
LEY | +0.138 |
YL | +0.131 |
AF | +0.129 |
SAM | +0.129 |
Neg logit contributions | |
jj | -0.057 |
sson | -0.055 |
andem | -0.050 |
zai | -0.046 |
hamm | -0.045 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
�� | +0.724 |
LEY | +0.630 |
YL | +0.584 |
AF | +0.570 |
SAM | +0.568 |
Neg logit contributions | |
jj | -0.713 |
sson | -0.706 |
andem | -0.673 |
zai | -0.643 |
hamm | -0.642 |
Token | ] |
Token ID | 60 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
�� | +1.535 |
LEY | +1.337 |
YL | +1.243 |
AF | +1.214 |
SAM | +1.208 |
Neg logit contributions | |
jj | -1.488 |
sson | -1.464 |
andem | -1.398 |
zai | -1.333 |
hamm | -1.330 |
Token | < |
Token ID | 1279 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
�� | +3.800 |
LEY | +3.279 |
YL | +3.029 |
AF | +2.918 |
AH | +2.901 |
Neg logit contributions | |
jj | -4.754 |
sson | -4.700 |
andem | -4.490 |
itle | -4.280 |
zai | -4.271 |
Token | m |
Token ID | 76 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
�� | +2.145 |
LEY | +1.920 |
YL | +1.812 |
AF | +1.782 |
SAM | +1.775 |
Neg logit contributions | |
jj | -1.332 |
sson | -1.324 |
andem | -1.242 |
hamm | -1.181 |
zai | -1.160 |
Token | ik |
Token ID | 1134 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
�� | +1.851 |
LEY | +1.654 |
YL | +1.559 |
AF | +1.553 |
AH | +1.545 |
Neg logit contributions | |
jj | -1.188 |
sson | -1.186 |
andem | -1.092 |
hamm | -1.063 |
zai | -1.048 |
Token | et |
Token ID | 316 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
jj | +0.891 |
sson | +0.876 |
andem | +0.825 |
hamm | +0.787 |
zai | +0.782 |
Neg logit contributions | |
�� | -1.235 |
LEY | -1.092 |
YL | -1.026 |
AF | -1.008 |
AH | -1.003 |
Token | hem |
Token ID | 4411 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
�� | +1.158 |
LEY | +1.033 |
YL | +0.971 |
AF | +0.956 |
AH | +0.949 |
Neg logit contributions | |
jj | -0.810 |
sson | -0.793 |
andem | -0.747 |
hamm | -0.716 |
zai | -0.710 |
Token | not |
Token ID | 407 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
jj | +0.702 |
sson | +0.690 |
andem | +0.651 |
zai | +0.621 |
hamm | +0.616 |
Neg logit contributions | |
�� | -0.864 |
LEY | -0.753 |
YL | -0.706 |
AF | -0.691 |
SAM | -0.687 |
Token | learn |
Token ID | 2193 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
jj | +0.311 |
sson | +0.306 |
andem | +0.290 |
zai | +0.276 |
hamm | +0.273 |
Neg logit contributions | |
�� | -0.359 |
LEY | -0.313 |
YL | -0.293 |
AF | -0.287 |
AH | -0.285 |
Token | a |
Token ID | 257 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
jj | +0.922 |
sson | +0.903 |
andem | +0.848 |
zai | +0.803 |
hamm | +0.798 |
Neg logit contributions | |
�� | -1.352 |
LEY | -1.191 |
YL | -1.121 |
AF | -1.098 |
SAM | -1.094 |
Token | single |
Token ID | 2060 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
�� | +2.100 |
LEY | +1.831 |
YL | +1.699 |
AF | +1.677 |
SAM | +1.659 |
Neg logit contributions | |
jj | -1.943 |
sson | -1.917 |
andem | -1.829 |
zai | -1.738 |
itle | -1.724 |
Token | damn |
Token ID | 12270 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
�� | +4.617 |
LEY | +4.099 |
AF | +3.807 |
YL | +3.784 |
SAM | +3.740 |
Neg logit contributions | |
jj | -4.297 |
sson | -4.280 |
andem | -4.132 |
zai | -3.819 |
itle | -3.767 |
Token | thing |
Token ID | 1517 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
�� | +3.810 |
LEY | +3.360 |
YL | +3.140 |
AF | +3.107 |
AH | +3.080 |
Neg logit contributions | |
jj | -3.514 |
sson | -3.479 |
andem | -3.325 |
zai | -3.105 |
hamm | -3.080 |
Token | from |
Token ID | 422 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
�� | +4.540 |
LEY | +3.960 |
YL | +3.741 |
AF | +3.689 |
AH | +3.643 |
Neg logit contributions | |
jj | -3.906 |
sson | -3.851 |
andem | -3.690 |
zai | -3.411 |
itle | -3.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +0.582 |
LEY | +0.511 |
YL | +0.479 |
AF | +0.470 |
AH | +0.467 |
Neg logit contributions | |
jj | -0.448 |
sson | -0.441 |
andem | -0.417 |
zai | -0.396 |
hamm | -0.391 |
Token | embarrassment |
Token ID | 24655 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
jj | +0.561 |
sson | +0.551 |
andem | +0.522 |
zai | +0.498 |
hamm | +0.496 |
Neg logit contributions | |
�� | -0.645 |
LEY | -0.560 |
YL | -0.523 |
AF | -0.510 |
SAM | -0.508 |
Token | he |
Token ID | 339 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
�� | +1.998 |
LEY | +1.762 |
YL | +1.647 |
AF | +1.630 |
AH | +1.625 |
Neg logit contributions | |
jj | -1.407 |
sson | -1.390 |
andem | -1.309 |
zai | -1.235 |
itle | -1.227 |
Token | suffered |
Token ID | 6989 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
�� | +1.295 |
LEY | +1.160 |
YL | +1.085 |
AF | +1.084 |
AH | +1.072 |
Neg logit contributions | |
jj | -0.970 |
sson | -0.940 |
andem | -0.909 |
zai | -0.850 |
itle | -0.846 |
Token | save |
Token ID | 3613 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
�� | +0.423 |
LEY | +0.371 |
YL | +0.347 |
AF | +0.339 |
SAM | +0.338 |
Neg logit contributions | |
jj | -0.339 |
sson | -0.334 |
andem | -0.315 |
zai | -0.300 |
hamm | -0.297 |
Token | [ |
Token ID | 685 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
�� | +0.549 |
LEY | +0.483 |
YL | +0.454 |
AF | +0.445 |
AH | +0.443 |
Neg logit contributions | |
jj | -0.399 |
sson | -0.393 |
andem | -0.371 |
zai | -0.350 |
hamm | -0.347 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
�� | +0.967 |
LEY | +0.869 |
YL | +0.822 |
AF | +0.808 |
SAM | +0.805 |
Neg logit contributions | |
jj | -0.607 |
sson | -0.596 |
andem | -0.559 |
hamm | -0.527 |
zai | -0.526 |
Token | : |
Token ID | 25 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
jj | +0.058 |
sson | +0.057 |
andem | +0.051 |
zai | +0.047 |
hamm | +0.047 |
Neg logit contributions | |
�� | -0.160 |
LEY | -0.144 |
YL | -0.137 |
AF | -0.135 |
SAM | -0.135 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
�� | +0.467 |
LEY | +0.405 |
YL | +0.376 |
AF | +0.367 |
SAM | +0.365 |
Neg logit contributions | |
jj | -0.451 |
sson | -0.445 |
andem | -0.423 |
zai | -0.405 |
hamm | -0.403 |
Token | ] |
Token ID | 60 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
�� | +1.339 |
LEY | +1.164 |
YL | +1.082 |
AF | +1.057 |
SAM | +1.051 |
Neg logit contributions | |
jj | -1.287 |
sson | -1.266 |
andem | -1.207 |
zai | -1.152 |
hamm | -1.148 |
Token | < |
Token ID | 1279 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
�� | +3.790 |
LEY | +3.264 |
YL | +3.011 |
AF | +2.910 |
AH | +2.889 |
Neg logit contributions | |
jj | -4.736 |
sson | -4.685 |
andem | -4.485 |
itle | -4.267 |
zai | -4.254 |
Token | f |
Token ID | 69 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
�� | +2.092 |
LEY | +1.871 |
YL | +1.765 |
AF | +1.738 |
SAM | +1.731 |
Neg logit contributions | |
jj | -1.307 |
sson | -1.299 |
andem | -1.218 |
hamm | -1.158 |
zai | -1.140 |
Token | gt |
Token ID | 13655 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
�� | +0.453 |
LEY | +0.400 |
YL | +0.377 |
AF | +0.369 |
AH | +0.366 |
Neg logit contributions | |
jj | -0.335 |
sson | -0.330 |
andem | -0.310 |
hamm | -0.297 |
zai | -0.296 |
Token | ve |
Token ID | 303 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
jj | +0.043 |
sson | +0.043 |
andem | +0.040 |
hamm | +0.038 |
zai | +0.038 |
Neg logit contributions | |
�� | -0.066 |
LEY | -0.058 |
YL | -0.055 |
AF | -0.054 |
AH | -0.054 |
Token | ass |
Token ID | 562 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
�� | +1.806 |
LEY | +1.628 |
YL | +1.536 |
AF | +1.515 |
AH | +1.498 |
Neg logit contributions | |
jj | -1.106 |
sson | -1.101 |
andem | -1.025 |
hamm | -0.980 |
zai | -0.961 |
Token | k |
Token ID | 74 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
jj | +0.558 |
sson | +0.535 |
andem | +0.470 |
zai | +0.422 |
hamm | +0.415 |
Neg logit contributions | |
�� | -2.016 |
LEY | -1.824 |
YL | -1.747 |
AF | -1.720 |
SAM | -1.718 |
Token | [ |
Token ID | 685 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
jj | +0.792 |
sson | +0.782 |
andem | +0.741 |
zai | +0.710 |
hamm | +0.703 |
Neg logit contributions | |
�� | -0.838 |
LEY | -0.724 |
YL | -0.674 |
AF | -0.657 |
AH | -0.654 |
Token | 10 |
Token ID | 940 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
�� | +1.368 |
LEY | +1.236 |
YL | +1.170 |
AF | +1.150 |
SAM | +1.143 |
Neg logit contributions | |
jj | -0.878 |
sson | -0.862 |
andem | -0.817 |
zai | -0.769 |
hamm | -0.768 |
Token | : |
Token ID | 25 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
�� | +0.039 |
LEY | +0.035 |
YL | +0.033 |
AF | +0.033 |
SAM | +0.033 |
Neg logit contributions | |
jj | -0.014 |
sson | -0.014 |
andem | -0.013 |
zai | -0.012 |
hamm | -0.011 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
�� | +0.614 |
LEY | +0.534 |
YL | +0.495 |
AF | +0.483 |
SAM | +0.481 |
Neg logit contributions | |
jj | -0.605 |
sson | -0.598 |
andem | -0.570 |
zai | -0.545 |
hamm | -0.544 |
Token | ] |
Token ID | 60 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
�� | +1.572 |
LEY | +1.370 |
YL | +1.273 |
AF | +1.244 |
SAM | +1.238 |
Neg logit contributions | |
jj | -1.530 |
sson | -1.505 |
andem | -1.438 |
zai | -1.371 |
hamm | -1.368 |
Token | < |
Token ID | 1279 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
�� | +3.822 |
LEY | +3.304 |
YL | +3.044 |
AF | +2.943 |
AH | +2.924 |
Neg logit contributions | |
jj | -4.684 |
sson | -4.646 |
andem | -4.425 |
itle | -4.211 |
zai | -4.202 |
Token | met |
Token ID | 4164 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
�� | +2.392 |
LEY | +2.143 |
YL | +2.021 |
AF | +1.991 |
SAM | +1.984 |
Neg logit contributions | |
jj | -1.468 |
sson | -1.464 |
andem | -1.368 |
hamm | -1.300 |
zai | -1.278 |
Token | ros |
Token ID | 4951 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
jj | +0.461 |
sson | +0.447 |
andem | +0.415 |
hamm | +0.387 |
zai | +0.387 |
Neg logit contributions | |
�� | -0.944 |
LEY | -0.846 |
YL | -0.804 |
AF | -0.792 |
SAM | -0.787 |
Token | xual |
Token ID | 5541 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
�� | +0.884 |
LEY | +0.776 |
YL | +0.729 |
AF | +0.712 |
SAM | +0.709 |
Neg logit contributions | |
jj | -0.670 |
sson | -0.659 |
andem | -0.621 |
zai | -0.591 |
hamm | -0.589 |
Token | th |
Token ID | 400 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
�� | +0.775 |
LEY | +0.707 |
YL | +0.674 |
AF | +0.661 |
AH | +0.661 |
Neg logit contributions | |
jj | -0.344 |
sson | -0.333 |
andem | -0.314 |
hamm | -0.291 |
zai | -0.287 |
Token | k |
Token ID | 74 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
jj | +0.382 |
sson | +0.368 |
andem | +0.326 |
zai | +0.292 |
hamm | +0.288 |
Neg logit contributions | |
�� | -1.345 |
LEY | -1.222 |
YL | -1.169 |
AF | -1.151 |
SAM | -1.148 |
Token | [ |
Token ID | 685 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
jj | +0.230 |
sson | +0.226 |
andem | +0.213 |
zai | +0.204 |
hamm | +0.204 |
Neg logit contributions | |
�� | -0.261 |
LEY | -0.225 |
YL | -0.210 |
AF | -0.205 |
SAM | -0.204 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
�� | +1.919 |
LEY | +1.742 |
YL | +1.650 |
AF | +1.623 |
SAM | +1.613 |
Neg logit contributions | |
jj | -1.261 |
sson | -1.238 |
andem | -1.177 |
hamm | -1.110 |
zai | -1.107 |
Token | : |
Token ID | 25 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�� | +0.682 |
LEY | +0.619 |
YL | +0.590 |
AF | +0.581 |
SAM | +0.579 |
Neg logit contributions | |
jj | -0.259 |
sson | -0.251 |
andem | -0.231 |
zai | -0.211 |
hamm | -0.209 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
�� | +0.854 |
LEY | +0.743 |
YL | +0.689 |
AF | +0.672 |
SAM | +0.670 |
Neg logit contributions | |
jj | -0.839 |
sson | -0.830 |
andem | -0.792 |
zai | -0.756 |
hamm | -0.755 |
Token | ] |
Token ID | 60 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
�� | +1.737 |
LEY | +1.517 |
YL | +1.410 |
AF | +1.378 |
SAM | +1.370 |
Neg logit contributions | |
jj | -1.705 |
sson | -1.677 |
andem | -1.605 |
zai | -1.529 |
hamm | -1.527 |
Token | < |
Token ID | 1279 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
�� | +3.769 |
LEY | +3.242 |
YL | +2.992 |
AF | +2.884 |
AH | +2.866 |
Neg logit contributions | |
jj | -4.713 |
sson | -4.674 |
andem | -4.454 |
itle | -4.244 |
zai | -4.237 |
Token | sh |
Token ID | 1477 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
�� | +2.449 |
LEY | +2.193 |
YL | +2.069 |
AF | +2.037 |
SAM | +2.028 |
Neg logit contributions | |
jj | -1.502 |
sson | -1.497 |
andem | -1.399 |
hamm | -1.329 |
zai | -1.307 |
Token | o |
Token ID | 78 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
jj | +0.165 |
sson | +0.163 |
andem | +0.152 |
hamm | +0.145 |
zai | +0.145 |
Neg logit contributions | |
�� | -0.222 |
LEY | -0.196 |
YL | -0.184 |
AF | -0.181 |
AH | -0.179 |
Token | ja |
Token ID | 6592 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
jj | +1.038 |
sson | +1.016 |
andem | +0.958 |
zai | +0.912 |
hamm | +0.905 |
Neg logit contributions | |
�� | -1.364 |
LEY | -1.193 |
YL | -1.119 |
AF | -1.093 |
SAM | -1.091 |
Token | > |
Token ID | 29 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
jj | +0.808 |
sson | +0.795 |
andem | +0.750 |
zai | +0.713 |
hamm | +0.710 |
Neg logit contributions | |
�� | -1.031 |
LEY | -0.901 |
YL | -0.844 |
AF | -0.826 |
SAM | -0.823 |
Token | time |
Token ID | 640 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
�� | +1.045 |
LEY | +0.920 |
YL | +0.861 |
AF | +0.844 |
SAM | +0.837 |
Neg logit contributions | |
jj | -0.820 |
sson | -0.807 |
andem | -0.765 |
zai | -0.725 |
hamm | -0.713 |
Token | [ |
Token ID | 685 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
�� | +0.140 |
LEY | +0.122 |
YL | +0.115 |
AF | +0.113 |
AH | +0.112 |
Neg logit contributions | |
jj | -0.107 |
sson | -0.106 |
andem | -0.100 |
zai | -0.095 |
hamm | -0.094 |
Token | 10 |
Token ID | 940 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
�� | +0.428 |
LEY | +0.381 |
YL | +0.356 |
AF | +0.352 |
SAM | +0.348 |
Neg logit contributions | |
jj | -0.328 |
sson | -0.324 |
andem | -0.306 |
zai | -0.290 |
hamm | -0.290 |
Token | : |
Token ID | 25 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
�� | +0.476 |
LEY | +0.430 |
YL | +0.410 |
AF | +0.404 |
AH | +0.402 |
Neg logit contributions | |
jj | -0.183 |
sson | -0.179 |
andem | -0.162 |
zai | -0.149 |
hamm | -0.147 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
�� | +0.711 |
LEY | +0.628 |
YL | +0.584 |
AF | +0.574 |
SAM | +0.570 |
Neg logit contributions | |
jj | -0.656 |
sson | -0.648 |
andem | -0.620 |
zai | -0.590 |
hamm | -0.588 |
Token | ] |
Token ID | 60 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
�� | +1.999 |
LEY | +1.784 |
YL | +1.690 |
AF | +1.657 |
AH | +1.652 |
Neg logit contributions | |
jj | -1.189 |
sson | -1.180 |
andem | -1.095 |
zai | -1.026 |
itle | -1.015 |
Token | < |
Token ID | 1279 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
�� | +4.061 |
LEY | +3.491 |
YL | +3.300 |
AF | +3.168 |
SAM | +3.145 |
Neg logit contributions | |
jj | -4.414 |
sson | -4.399 |
andem | -4.170 |
zai | -4.010 |
itle | -3.970 |
Token | met |
Token ID | 4164 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
�� | +3.869 |
LEY | +3.454 |
YL | +3.268 |
AF | +3.236 |
AH | +3.212 |
Neg logit contributions | |
sson | -2.942 |
jj | -2.918 |
andem | -2.785 |
hamm | -2.673 |
itle | -2.621 |
Token | ros |
Token ID | 4951 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
jj | +0.270 |
sson | +0.265 |
andem | +0.250 |
zai | +0.238 |
hamm | +0.237 |
Neg logit contributions | |
�� | -0.350 |
LEY | -0.307 |
YL | -0.288 |
AF | -0.283 |
AH | -0.281 |
Token | xual |
Token ID | 5541 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
�� | +1.025 |
LEY | +0.910 |
YL | +0.857 |
AF | +0.841 |
AH | +0.836 |
Neg logit contributions | |
jj | -0.707 |
sson | -0.701 |
andem | -0.655 |
hamm | -0.622 |
zai | -0.621 |
Token | th |
Token ID | 400 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
�� | +1.659 |
LEY | +1.455 |
YL | +1.368 |
AF | +1.347 |
SAM | +1.338 |
Neg logit contributions | |
jj | -1.252 |
sson | -1.244 |
andem | -1.170 |
hamm | -1.119 |
zai | -1.115 |
Token | k |
Token ID | 74 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
jj | +0.567 |
sson | +0.545 |
andem | +0.479 |
zai | +0.430 |
hamm | +0.424 |
Neg logit contributions | |
�� | -2.036 |
LEY | -1.845 |
YL | -1.766 |
AF | -1.739 |
SAM | -1.737 |
Token | [ |
Token ID | 685 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
jj | +0.426 |
sson | +0.422 |
andem | +0.400 |
zai | +0.383 |
hamm | +0.379 |
Neg logit contributions | |
�� | -0.447 |
LEY | -0.386 |
YL | -0.359 |
AF | -0.350 |
AH | -0.349 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
�� | +1.261 |
LEY | +1.138 |
YL | +1.077 |
AF | +1.058 |
SAM | +1.052 |
Neg logit contributions | |
jj | -0.804 |
sson | -0.789 |
andem | -0.746 |
zai | -0.703 |
hamm | -0.702 |
Token | : |
Token ID | 25 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
jj | +0.110 |
sson | +0.106 |
andem | +0.096 |
zai | +0.088 |
hamm | +0.087 |
Neg logit contributions | |
�� | -0.301 |
LEY | -0.272 |
YL | -0.259 |
AF | -0.255 |
SAM | -0.254 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
�� | +0.392 |
LEY | +0.339 |
YL | +0.315 |
AF | +0.307 |
SAM | +0.306 |
Neg logit contributions | |
jj | -0.376 |
sson | -0.371 |
andem | -0.353 |
zai | -0.337 |
hamm | -0.336 |
Token | ] |
Token ID | 60 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
�� | +1.328 |
LEY | +1.153 |
YL | +1.072 |
AF | +1.047 |
SAM | +1.042 |
Neg logit contributions | |
jj | -1.270 |
sson | -1.249 |
andem | -1.189 |
zai | -1.136 |
hamm | -1.132 |
Token | < |
Token ID | 1279 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
�� | +3.771 |
LEY | +3.252 |
YL | +3.001 |
AF | +2.896 |
AH | +2.879 |
Neg logit contributions | |
jj | -4.680 |
sson | -4.622 |
andem | -4.416 |
itle | -4.202 |
zai | -4.200 |
Token | mom |
Token ID | 32542 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
�� | +2.095 |
LEY | +1.873 |
YL | +1.768 |
AF | +1.739 |
SAM | +1.732 |
Neg logit contributions | |
jj | -1.309 |
sson | -1.300 |
andem | -1.219 |
hamm | -1.159 |
zai | -1.141 |
Token | per |
Token ID | 525 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
�� | +0.490 |
LEY | +0.428 |
YL | +0.401 |
AF | +0.393 |
SAM | +0.390 |
Neg logit contributions | |
jj | -0.391 |
sson | -0.384 |
andem | -0.363 |
zai | -0.346 |
hamm | -0.344 |
Token | > |
Token ID | 29 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
�� | +2.759 |
LEY | +2.484 |
YL | +2.330 |
AF | +2.292 |
AH | +2.279 |
Neg logit contributions | |
jj | -2.044 |
sson | -2.008 |
andem | -1.928 |
hamm | -1.822 |
zai | -1.812 |
Token | lol |
Token ID | 19462 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
�� | +0.479 |
LEY | +0.421 |
YL | +0.394 |
AF | +0.384 |
AH | +0.383 |
Neg logit contributions | |
jj | -0.386 |
sson | -0.381 |
andem | -0.360 |
zai | -0.342 |
hamm | -0.338 |
Token | C |
Token ID | 34 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
�� | +1.938 |
LEY | +1.710 |
YL | +1.582 |
AF | +1.562 |
AH | +1.552 |
Neg logit contributions | |
jj | -1.974 |
sson | -1.953 |
andem | -1.879 |
zai | -1.799 |
hamm | -1.787 |
Token | AS |
Token ID | 1921 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
�� | +1.739 |
LEY | +1.542 |
YL | +1.458 |
AF | +1.427 |
AH | +1.414 |
Neg logit contributions | |
jj | -1.213 |
sson | -1.188 |
andem | -1.112 |
zai | -1.059 |
hamm | -1.056 |
Token | INO |
Token ID | 46016 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
�� | +0.154 |
LEY | +0.129 |
YL | +0.119 |
AF | +0.115 |
SAM | +0.115 |
Neg logit contributions | |
jj | -0.178 |
sson | -0.176 |
andem | -0.167 |
zai | -0.161 |
hamm | -0.160 |
Token | RO |
Token ID | 15107 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
�� | +2.247 |
LEY | +1.971 |
YL | +1.825 |
AF | +1.790 |
AH | +1.776 |
Neg logit contributions | |
jj | -2.214 |
sson | -2.178 |
andem | -2.084 |
zai | -1.986 |
itle | -1.976 |
Token | Y |
Token ID | 56 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
�� | +2.318 |
LEY | +2.067 |
YL | +1.882 |
AF | +1.835 |
AH | +1.815 |
Neg logit contributions | |
jj | -2.962 |
sson | -2.951 |
andem | -2.849 |
hamm | -2.734 |
itle | -2.712 |
Token | ALE |
Token ID | 21358 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
�� | +1.335 |
LEY | +1.091 |
YL | +0.973 |
AF | +0.939 |
AH | +0.931 |
Neg logit contributions | |
jj | -2.368 |
sson | -2.334 |
andem | -2.254 |
zai | -2.184 |
hamm | -2.170 |
Token | " |
Token ID | 1 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
�� | +4.357 |
LEY | +3.924 |
YL | +3.628 |
AF | +3.577 |
AH | +3.550 |
Neg logit contributions | |
jj | -4.043 |
sson | -3.972 |
andem | -3.827 |
hamm | -3.630 |
itle | -3.626 |
Token | - |
Token ID | 532 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
�� | +3.528 |
LEY | +3.124 |
YL | +2.944 |
AF | +2.888 |
AH | +2.868 |
Neg logit contributions | |
jj | -2.986 |
sson | -2.939 |
andem | -2.793 |
zai | -2.657 |
hamm | -2.634 |
Token | starring |
Token ID | 20495 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
�� | +2.975 |
LEY | +2.634 |
YL | +2.453 |
AF | +2.419 |
SAM | +2.396 |
Neg logit contributions | |
jj | -2.558 |
sson | -2.507 |
andem | -2.382 |
zai | -2.283 |
hamm | -2.251 |
Token | Barry |
Token ID | 14488 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
�� | +0.127 |
LEY | +0.109 |
YL | +0.101 |
AF | +0.099 |
SAM | +0.098 |
Neg logit contributions | |
jj | -0.130 |
sson | -0.128 |
andem | -0.122 |
zai | -0.117 |
hamm | -0.116 |
Token | Nelson |
Token ID | 12996 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
�� | +0.604 |
LEY | +0.531 |
YL | +0.495 |
AF | +0.484 |
SAM | +0.482 |
Neg logit contributions | |
jj | -0.533 |
sson | -0.524 |
andem | -0.495 |
zai | -0.476 |
hamm | -0.470 |
Token | k |
Token ID | 74 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
jj | +0.836 |
sson | +0.798 |
andem | +0.691 |
zai | +0.624 |
hamm | +0.610 |
Neg logit contributions | |
�� | -3.116 |
LEY | -2.810 |
YL | -2.695 |
SAM | -2.653 |
AF | -2.652 |
Token | [ |
Token ID | 685 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
jj | +0.917 |
sson | +0.904 |
andem | +0.858 |
zai | +0.821 |
hamm | +0.814 |
Neg logit contributions | |
�� | -0.976 |
LEY | -0.843 |
YL | -0.785 |
AF | -0.766 |
AH | -0.762 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
�� | +0.789 |
LEY | +0.710 |
YL | +0.671 |
AF | +0.660 |
SAM | +0.656 |
Neg logit contributions | |
jj | -0.495 |
sson | -0.485 |
andem | -0.458 |
zai | -0.431 |
hamm | -0.430 |
Token | : |
Token ID | 25 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
jj | +0.039 |
sson | +0.038 |
andem | +0.035 |
zai | +0.032 |
hamm | +0.031 |
Neg logit contributions | |
�� | -0.107 |
LEY | -0.096 |
YL | -0.092 |
AF | -0.090 |
SAM | -0.090 |
Token | 47 |
Token ID | 2857 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
�� | +0.483 |
LEY | +0.419 |
YL | +0.389 |
AF | +0.379 |
SAM | +0.378 |
Neg logit contributions | |
jj | -0.467 |
sson | -0.460 |
andem | -0.438 |
zai | -0.419 |
hamm | -0.417 |
Token | ] |
Token ID | 60 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
�� | +1.507 |
LEY | +1.312 |
YL | +1.220 |
AF | +1.192 |
SAM | +1.186 |
Neg logit contributions | |
jj | -1.461 |
sson | -1.437 |
andem | -1.372 |
zai | -1.309 |
hamm | -1.305 |
Token | < |
Token ID | 1279 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
�� | +3.761 |
LEY | +3.243 |
YL | +2.993 |
AF | +2.888 |
AH | +2.871 |
Neg logit contributions | |
jj | -4.661 |
sson | -4.612 |
andem | -4.398 |
itle | -4.189 |
zai | -4.180 |
Token | ok |
Token ID | 482 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
�� | +2.449 |
LEY | +2.195 |
YL | +2.071 |
AF | +2.039 |
SAM | +2.031 |
Neg logit contributions | |
jj | -1.524 |
sson | -1.517 |
andem | -1.422 |
hamm | -1.353 |
zai | -1.328 |
Token | clock |
Token ID | 15750 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
jj | +0.163 |
sson | +0.161 |
andem | +0.154 |
hamm | +0.149 |
zai | +0.149 |
Neg logit contributions | |
�� | -0.101 |
LEY | -0.083 |
YL | -0.074 |
AF | -0.072 |
AH | -0.071 |
Token | zy |
Token ID | 7357 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
jj | +0.244 |
sson | +0.239 |
andem | +0.225 |
zai | +0.216 |
hamm | +0.212 |
Neg logit contributions | |
�� | -0.308 |
LEY | -0.267 |
YL | -0.250 |
AF | -0.245 |
SAM | -0.244 |
Token | > |
Token ID | 29 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
�� | +0.187 |
LEY | +0.164 |
YL | +0.154 |
AF | +0.151 |
SAM | +0.150 |
Neg logit contributions | |
jj | -0.122 |
sson | -0.119 |
andem | -0.110 |
zai | -0.105 |
hamm | -0.104 |
Token | , |
Token ID | 837 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
sson | +1.681 |
jj | +1.675 |
andem | +1.483 |
zai | +1.416 |
hamm | +1.409 |
Neg logit contributions | |
�� | -3.137 |
LEY | -2.721 |
YL | -2.567 |
�� | -2.532 |
SAM | -2.518 |
Token | T |
Token ID | 309 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
jj | +0.024 |
sson | +0.024 |
andem | +0.022 |
zai | +0.021 |
hamm | +0.021 |
Neg logit contributions | |
�� | -0.031 |
LEY | -0.027 |
YL | -0.025 |
SAM | -0.025 |
AF | -0.025 |
Token | > |
Token ID | 1875 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
jj | +2.068 |
sson | +2.063 |
andem | +1.909 |
zai | +1.799 |
itle | +1.789 |
Neg logit contributions | |
�� | -2.736 |
LEY | -2.294 |
YL | -2.156 |
SAM | -2.093 |
�� | -2.092 |
Token | { |
Token ID | 1391 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
jj | +0.466 |
sson | +0.456 |
andem | +0.414 |
zai | +0.387 |
hamm | +0.383 |
Neg logit contributions | |
�� | -1.036 |
LEY | -0.925 |
YL | -0.879 |
AF | -0.862 |
SAM | -0.861 |
Token | type |
Token ID | 2099 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
jj | +0.745 |
sson | +0.735 |
andem | +0.686 |
zai | +0.655 |
hamm | +0.650 |
Neg logit contributions | |
�� | -1.047 |
LEY | -0.914 |
YL | -0.856 |
AF | -0.837 |
SAM | -0.835 |
Token | Target |
Token ID | 12744 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
jj | +1.700 |
sson | +1.675 |
andem | +1.562 |
zai | +1.473 |
hamm | +1.460 |
Neg logit contributions | |
�� | -2.764 |
LEY | -2.451 |
YL | -2.302 |
AF | -2.251 |
AH | -2.248 |
Token | = |
Token ID | 796 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
sson | +2.757 |
jj | +2.733 |
andem | +2.237 |
zai | +2.211 |
itle | +2.176 |
Neg logit contributions | |
�� | -6.789 |
LEY | -5.841 |
�� | -5.627 |
YL | -5.460 |
AH | -5.407 |
Token | & |
Token ID | 1222 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
�� | +0.160 |
LEY | +0.138 |
YL | +0.129 |
AF | +0.127 |
SAM | +0.126 |
Neg logit contributions | |
jj | -0.140 |
sson | -0.137 |
andem | -0.129 |
zai | -0.124 |
hamm | -0.123 |
Token | ' |
Token ID | 705 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
jj | +0.723 |
sson | +0.710 |
andem | +0.665 |
zai | +0.629 |
hamm | +0.625 |
Neg logit contributions | |
�� | -1.083 |
LEY | -0.957 |
YL | -0.901 |
AF | -0.886 |
SAM | -0.882 |
Token | a |
Token ID | 64 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
�� | +0.031 |
LEY | +0.027 |
YL | +0.025 |
SAM | +0.024 |
AF | +0.024 |
Neg logit contributions | |
jj | -0.022 |
sson | -0.022 |
andem | -0.020 |
zai | -0.019 |
hamm | -0.019 |
Token | T |
Token ID | 309 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
�� | +0.222 |
LEY | +0.192 |
YL | +0.181 |
AF | +0.177 |
SAM | +0.176 |
Neg logit contributions | |
jj | -0.183 |
sson | -0.178 |
andem | -0.168 |
zai | -0.161 |
hamm | -0.159 |
Token | on |
Token ID | 319 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
�� | +0.593 |
LEY | +0.522 |
YL | +0.490 |
AF | +0.481 |
SAM | +0.477 |
Neg logit contributions | |
jj | -0.445 |
sson | -0.434 |
andem | -0.412 |
zai | -0.390 |
hamm | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
�� | +0.966 |
LEY | +0.854 |
YL | +0.803 |
AF | +0.794 |
AH | +0.787 |
Neg logit contributions | |
jj | -0.674 |
sson | -0.661 |
andem | -0.623 |
zai | -0.584 |
hamm | -0.576 |
Token | front |
Token ID | 2166 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
�� | +1.472 |
LEY | +1.296 |
YL | +1.208 |
AF | +1.189 |
SAM | +1.177 |
Neg logit contributions | |
jj | -1.179 |
sson | -1.157 |
andem | -1.103 |
zai | -1.042 |
hamm | -1.022 |
Token | page |
Token ID | 2443 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
�� | +2.586 |
LEY | +2.225 |
YL | +1.976 |
ICE | +1.973 |
AF | +1.965 |
Neg logit contributions | |
jj | -3.222 |
sson | -3.171 |
andem | -3.096 |
zai | -2.923 |
hamm | -2.868 |
Token | but |
Token ID | 475 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
�� | +2.188 |
LEY | +1.948 |
YL | +1.817 |
AF | +1.795 |
AH | +1.782 |
Neg logit contributions | |
jj | -1.571 |
sson | -1.548 |
andem | -1.471 |
zai | -1.362 |
itle | -1.353 |
Token | rather |
Token ID | 2138 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
jj | +0.605 |
sson | +0.590 |
andem | +0.553 |
zai | +0.517 |
hamm | +0.511 |
Neg logit contributions | |
�� | -1.038 |
LEY | -0.927 |
YL | -0.876 |
AF | -0.860 |
AH | -0.854 |
Token | that |
Token ID | 326 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
jj | +3.090 |
sson | +3.038 |
andem | +2.778 |
hamm | +2.664 |
zai | +2.653 |
Neg logit contributions | |
�� | -6.230 |
LEY | -5.510 |
YL | -5.231 |
SAM | -5.130 |
AF | -5.103 |
Token | they |
Token ID | 484 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
jj | +1.473 |
sson | +1.445 |
andem | +1.358 |
zai | +1.295 |
hamm | +1.289 |
Neg logit contributions | |
�� | -1.994 |
LEY | -1.743 |
YL | -1.637 |
AF | -1.600 |
SAM | -1.596 |
Token | were |
Token ID | 547 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
�� | +0.625 |
LEY | +0.556 |
YL | +0.520 |
AF | +0.514 |
AH | +0.509 |
Neg logit contributions | |
jj | -0.469 |
sson | -0.459 |
andem | -0.435 |
zai | -0.411 |
itle | -0.404 |
Token | stupid |
Token ID | 8531 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
jj | +0.115 |
sson | +0.113 |
andem | +0.107 |
zai | +0.101 |
hamm | +0.100 |
Neg logit contributions | |
�� | -0.146 |
LEY | -0.128 |
YL | -0.120 |
AF | -0.117 |
SAM | -0.117 |
Token | enough |
Token ID | 1576 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
�� | +1.705 |
LEY | +1.519 |
YL | +1.423 |
AF | +1.402 |
AH | +1.386 |
Neg logit contributions | |
jj | -1.244 |
sson | -1.209 |
andem | -1.151 |
zai | -1.089 |
hamm | -1.073 |
Token | 96 |
Token ID | 4846 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
�� | +0.385 |
LEY | +0.334 |
YL | +0.312 |
AF | +0.305 |
SAM | +0.302 |
Neg logit contributions | |
jj | -0.353 |
sson | -0.347 |
andem | -0.330 |
zai | -0.315 |
hamm | -0.314 |
Token | 275 |
Token ID | 23195 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
�� | +0.325 |
LEY | +0.283 |
YL | +0.264 |
AF | +0.258 |
SAM | +0.256 |
Neg logit contributions | |
jj | -0.301 |
sson | -0.295 |
andem | -0.282 |
zai | -0.268 |
hamm | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
jj | +0.922 |
sson | +0.906 |
andem | +0.810 |
zai | +0.777 |
itle | +0.756 |
Neg logit contributions | |
�� | -1.670 |
LEY | -1.465 |
YL | -1.379 |
SAM | -1.364 |
AF | -1.361 |
Token | g |
Token ID | 70 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
jj | +2.772 |
sson | +2.753 |
andem | +2.518 |
zai | +2.415 |
hamm | +2.381 |
Neg logit contributions | |
�� | -4.754 |
LEY | -4.252 |
YL | -3.970 |
AF | -3.877 |
SAM | -3.864 |
Token | 001 |
Token ID | 8298 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
�� | +1.311 |
LEY | +1.135 |
YL | +1.065 |
AF | +1.062 |
SAM | +1.054 |
Neg logit contributions | |
jj | -1.230 |
sson | -1.180 |
andem | -1.141 |
zai | -1.087 |
itle | -1.072 |
Token | Pre |
Token ID | 3771 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
jj | +1.176 |
sson | +1.155 |
andem | +1.091 |
zai | +1.039 |
hamm | +1.034 |
Neg logit contributions | |
�� | -1.458 |
LEY | -1.273 |
YL | -1.191 |
AF | -1.165 |
SAM | -1.160 |
Token | - |
Token ID | 12 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
jj | +3.762 |
sson | +3.657 |
andem | +3.425 |
zai | +3.296 |
itle | +3.224 |
Neg logit contributions | |
�� | -5.562 |
LEY | -4.875 |
YL | -4.576 |
SAM | -4.434 |
AF | -4.431 |
Token | training |
Token ID | 34409 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
�� | +0.417 |
LEY | +0.367 |
YL | +0.345 |
AF | +0.342 |
SAM | +0.340 |
Neg logit contributions | |
jj | -0.326 |
sson | -0.321 |
andem | -0.303 |
hamm | -0.288 |
zai | -0.287 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
jj | +0.915 |
sson | +0.896 |
andem | +0.841 |
zai | +0.794 |
hamm | +0.786 |
Neg logit contributions | |
�� | -1.391 |
LEY | -1.230 |
YL | -1.160 |
AF | -1.137 |
SAM | -1.132 |
Token | In |
Token ID | 554 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
jj | +0.577 |
sson | +0.567 |
andem | +0.534 |
zai | +0.507 |
hamm | +0.505 |
Neg logit contributions | |
�� | -0.748 |
LEY | -0.658 |
YL | -0.617 |
AF | -0.604 |
SAM | -0.601 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
jj | +0.727 |
sson | +0.713 |
andem | +0.666 |
zai | +0.631 |
hamm | +0.625 |
Neg logit contributions | |
�� | -1.086 |
LEY | -0.962 |
YL | -0.905 |
AF | -0.890 |
AH | -0.885 |
Token | that |
Token ID | 326 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
jj | +0.277 |
sson | +0.272 |
andem | +0.254 |
zai | +0.237 |
hamm | +0.236 |
Neg logit contributions | |
�� | -0.466 |
LEY | -0.413 |
YL | -0.391 |
AF | -0.384 |
AH | -0.382 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
jj | +0.705 |
sson | +0.691 |
andem | +0.649 |
zai | +0.613 |
hamm | +0.609 |
Neg logit contributions | |
�� | -1.041 |
LEY | -0.917 |
YL | -0.864 |
AF | -0.847 |
SAM | -0.843 |
Token | after |
Token ID | 706 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
jj | +1.114 |
sson | +1.092 |
andem | +1.019 |
zai | +0.973 |
hamm | +0.968 |
Neg logit contributions | |
�� | -1.687 |
LEY | -1.482 |
YL | -1.393 |
AF | -1.363 |
SAM | -1.362 |
Token | hearing |
Token ID | 4854 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
jj | +0.650 |
sson | +0.638 |
andem | +0.601 |
zai | +0.569 |
hamm | +0.566 |
Neg logit contributions | |
�� | -0.889 |
LEY | -0.780 |
YL | -0.733 |
AF | -0.717 |
SAM | -0.714 |
Token | Repe |
Token ID | 30558 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
jj | +0.304 |
sson | +0.298 |
andem | +0.281 |
zai | +0.264 |
hamm | +0.262 |
Neg logit contributions | |
�� | -0.447 |
LEY | -0.393 |
YL | -0.370 |
AF | -0.363 |
SAM | -0.361 |
Token | al |
Token ID | 282 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
jj | +0.970 |
sson | +0.957 |
andem | +0.907 |
zai | +0.863 |
hamm | +0.860 |
Neg logit contributions | |
�� | -1.078 |
LEY | -0.932 |
YL | -0.867 |
AF | -0.849 |
AH | -0.846 |
Token | & |
Token ID | 1222 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
jj | +3.449 |
sson | +3.304 |
andem | +3.173 |
zai | +3.017 |
hamm | +2.949 |
Neg logit contributions | |
�� | -5.628 |
LEY | -4.975 |
YL | -4.781 |
SAM | -4.623 |
AF | -4.564 |
Token | Replace |
Token ID | 40177 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
jj | +1.572 |
sson | +1.539 |
andem | +1.450 |
zai | +1.380 |
hamm | +1.372 |
Neg logit contributions | |
�� | -2.072 |
LEY | -1.810 |
YL | -1.702 |
SAM | -1.653 |
AF | -1.649 |
Token | for |
Token ID | 329 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
jj | +0.945 |
sson | +0.929 |
andem | +0.871 |
zai | +0.828 |
hamm | +0.825 |
Neg logit contributions | |
�� | -1.357 |
LEY | -1.195 |
YL | -1.121 |
AF | -1.098 |
SAM | -1.096 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
jj | +0.535 |
sson | +0.525 |
andem | +0.494 |
zai | +0.469 |
hamm | +0.466 |
Neg logit contributions | |
�� | -0.706 |
LEY | -0.619 |
YL | -0.582 |
AF | -0.569 |
AH | -0.566 |
Token | years |
Token ID | 812 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
jj | +0.888 |
sson | +0.872 |
andem | +0.823 |
zai | +0.783 |
hamm | +0.778 |
Neg logit contributions | |
�� | -1.118 |
LEY | -0.975 |
YL | -0.915 |
AF | -0.894 |
SAM | -0.890 |
Token | sn |
Token ID | 16184 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
jj | +0.388 |
sson | +0.381 |
andem | +0.359 |
zai | +0.342 |
hamm | +0.341 |
Neg logit contributions | |
�� | -0.513 |
LEY | -0.450 |
YL | -0.423 |
AF | -0.415 |
SAM | -0.414 |
Token | ipp |
Token ID | 3974 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�� | +0.447 |
LEY | +0.398 |
YL | +0.377 |
AF | +0.371 |
AH | +0.369 |
Neg logit contributions | |
jj | -0.254 |
sson | -0.250 |
andem | -0.232 |
zai | -0.219 |
hamm | -0.218 |
Token | et |
Token ID | 316 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
�� | +1.033 |
LEY | +0.923 |
YL | +0.861 |
AF | +0.847 |
AH | +0.844 |
Neg logit contributions | |
jj | -0.731 |
sson | -0.721 |
andem | -0.675 |
hamm | -0.639 |
zai | -0.635 |
Token | }} |
Token ID | 34949 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
�� | +1.341 |
LEY | +1.192 |
YL | +1.133 |
AF | +1.115 |
SAM | +1.108 |
Neg logit contributions | |
jj | -0.767 |
sson | -0.747 |
andem | -0.705 |
zai | -0.662 |
hamm | -0.655 |
Token |
|
Token ID | 3556 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
�� | +0.719 |
LEY | +0.632 |
YL | +0.589 |
AF | +0.576 |
AH | +0.575 |
Neg logit contributions | |
jj | -0.628 |
sson | -0.616 |
andem | -0.588 |
zai | -0.559 |
hamm | -0.554 |
Token | p |
Token ID | 79 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
�� | +0.290 |
LEY | +0.261 |
YL | +0.245 |
AF | +0.241 |
AH | +0.241 |
Neg logit contributions | |
jj | -0.173 |
sson | -0.168 |
andem | -0.161 |
hamm | -0.151 |
zai | -0.149 |
Token | > |
Token ID | 29 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
jj | +3.439 |
sson | +3.336 |
andem | +3.123 |
zai | +2.935 |
hamm | +2.924 |
Neg logit contributions | |
�� | -5.451 |
LEY | -4.844 |
YL | -4.576 |
AF | -4.457 |
SAM | -4.450 |
Token | |
Token ID | 7359 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
jj | +1.966 |
sson | +1.935 |
andem | +1.842 |
zai | +1.764 |
hamm | +1.753 |
Neg logit contributions | |
�� | -1.973 |
LEY | -1.698 |
YL | -1.576 |
AF | -1.537 |
SAM | -1.529 |
Token | li |
Token ID | 4528 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
jj | +0.168 |
sson | +0.166 |
andem | +0.158 |
hamm | +0.150 |
zai | +0.149 |
Neg logit contributions | |
�� | -0.227 |
LEY | -0.201 |
YL | -0.187 |
AH | -0.185 |
AF | -0.184 |
Token | > |
Token ID | 29 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
jj | +1.903 |
sson | +1.868 |
andem | +1.721 |
itle | +1.627 |
zai | +1.626 |
Neg logit contributions | |
�� | -3.067 |
LEY | -2.691 |
YL | -2.539 |
AF | -2.479 |
SAM | -2.472 |
Token | |
Token ID | 7359 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
jj | +2.388 |
sson | +2.350 |
andem | +2.231 |
zai | +2.138 |
hamm | +2.128 |
Neg logit contributions | |
�� | -2.424 |
LEY | -2.082 |
YL | -1.934 |
AF | -1.885 |
SAM | -1.877 |
Token | : |
Token ID | 25 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
jj | +1.947 |
sson | +1.908 |
andem | +1.786 |
zai | +1.697 |
hamm | +1.691 |
Neg logit contributions | |
�� | -2.842 |
LEY | -2.504 |
YL | -2.353 |
AF | -2.301 |
SAM | -2.294 |
Token | visually |
Token ID | 22632 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
�� | +0.459 |
LEY | +0.401 |
YL | +0.378 |
AF | +0.370 |
SAM | +0.368 |
Neg logit contributions | |
jj | -0.364 |
sson | -0.356 |
andem | -0.337 |
zai | -0.320 |
hamm | -0.317 |
Token | pleasing |
Token ID | 28790 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
�� | +1.407 |
LEY | +1.238 |
YL | +1.159 |
AF | +1.140 |
SAM | +1.137 |
Neg logit contributions | |
jj | -1.118 |
sson | -1.105 |
andem | -1.044 |
zai | -0.987 |
hamm | -0.965 |
Token | placeholder |
Token ID | 46076 |
Feature activation | -9.57e-03 |
Pos logit contributions | |
jj | +0.507 |
sson | +0.497 |
andem | +0.470 |
zai | +0.444 |
hamm | +0.439 |
Neg logit contributions | |
�� | -0.691 |
LEY | -0.609 |
YL | -0.571 |
AF | -0.560 |
SAM | -0.557 |
Token |
|
Token ID | 3556 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
jj | +0.041 |
sson | +0.040 |
andem | +0.038 |
zai | +0.035 |
hamm | +0.035 |
Neg logit contributions | |
�� | -0.057 |
LEY | -0.051 |
YL | -0.048 |
AF | -0.047 |
AH | -0.047 |
Token | p |
Token ID | 79 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
�� | +1.805 |
LEY | +1.628 |
YL | +1.538 |
AF | +1.524 |
AH | +1.509 |
Neg logit contributions | |
jj | -1.149 |
sson | -1.118 |
andem | -1.091 |
hamm | -1.014 |
zai | -0.998 |
Token | > |
Token ID | 29 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
jj | +3.334 |
sson | +3.223 |
andem | +3.027 |
zai | +2.848 |
hamm | +2.823 |
Neg logit contributions | |
�� | -5.514 |
LEY | -4.902 |
YL | -4.603 |
AF | -4.486 |
SAM | -4.482 |
Token | |
Token ID | 7359 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
jj | +2.115 |
sson | +2.079 |
andem | +1.980 |
zai | +1.898 |
hamm | +1.883 |
Neg logit contributions | |
�� | -2.081 |
LEY | -1.791 |
YL | -1.664 |
AF | -1.620 |
AH | -1.612 |
Token | li |
Token ID | 4528 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
�� | +0.521 |
LEY | +0.466 |
YL | +0.434 |
AH | +0.429 |
AF | +0.428 |
Neg logit contributions | |
jj | -0.389 |
sson | -0.384 |
andem | -0.367 |
hamm | -0.351 |
zai | -0.346 |
Token | > |
Token ID | 29 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
jj | +2.205 |
sson | +2.169 |
andem | +1.980 |
itle | +1.884 |
zai | +1.881 |
Neg logit contributions | |
�� | -3.774 |
LEY | -3.280 |
YL | -3.091 |
AF | -3.013 |
�� | -3.007 |
Token | |
Token ID | 7359 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
jj | +1.919 |
sson | +1.887 |
andem | +1.797 |
zai | +1.721 |
hamm | +1.711 |
Neg logit contributions | |
�� | -1.891 |
LEY | -1.624 |
YL | -1.509 |
AF | -1.469 |
SAM | -1.462 |
Token | path |
Token ID | 6978 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
�� | +0.653 |
LEY | +0.570 |
YL | +0.532 |
AF | +0.523 |
SAM | +0.521 |
Neg logit contributions | |
jj | -0.574 |
sson | -0.565 |
andem | -0.539 |
zai | -0.514 |
hamm | -0.514 |
Token | to |
Token ID | 284 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
jj | +0.698 |
sson | +0.682 |
andem | +0.647 |
zai | +0.615 |
hamm | +0.606 |
Neg logit contributions | |
�� | -0.989 |
LEY | -0.871 |
YL | -0.818 |
AF | -0.803 |
SAM | -0.801 |
Token | images |
Token ID | 4263 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
�� | +1.182 |
LEY | +1.054 |
YL | +0.996 |
AF | +0.981 |
SAM | +0.975 |
Neg logit contributions | |
jj | -0.747 |
sson | -0.725 |
andem | -0.698 |
zai | -0.655 |
hamm | -0.639 |
Token | directory |
Token ID | 8619 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
jj | +1.010 |
sson | +0.993 |
andem | +0.939 |
zai | +0.897 |
hamm | +0.894 |
Neg logit contributions | |
�� | -1.144 |
LEY | -0.990 |
YL | -0.923 |
AF | -0.900 |
SAM | -0.898 |
Token | ") |
Token ID | 4943 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
jj | +1.030 |
sson | +1.013 |
andem | +0.961 |
zai | +0.920 |
hamm | +0.916 |
Neg logit contributions | |
�� | -1.067 |
LEY | -0.918 |
YL | -0.854 |
AF | -0.832 |
SAM | -0.829 |
Token | args |
Token ID | 26498 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
jj | +0.537 |
sson | +0.526 |
andem | +0.501 |
zai | +0.480 |
hamm | +0.473 |
Neg logit contributions | |
�� | -0.590 |
LEY | -0.510 |
YL | -0.475 |
AF | -0.466 |
AH | -0.462 |
Token | = |
Token ID | 796 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
jj | +3.072 |
sson | +2.988 |
andem | +2.749 |
zai | +2.603 |
itle | +2.568 |
Neg logit contributions | |
�� | -5.722 |
LEY | -5.083 |
YL | -4.834 |
AF | -4.702 |
SAM | -4.698 |
Token | v |
Token ID | 410 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
�� | +2.059 |
LEY | +1.791 |
AF | +1.676 |
YL | +1.666 |
SAM | +1.656 |
Neg logit contributions | |
jj | -1.543 |
sson | -1.505 |
andem | -1.434 |
zai | -1.367 |
hamm | -1.333 |
Token | ars |
Token ID | 945 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
jj | +0.027 |
sson | +0.027 |
andem | +0.025 |
hamm | +0.023 |
zai | +0.023 |
Neg logit contributions | |
�� | -0.059 |
LEY | -0.053 |
YL | -0.051 |
AF | -0.050 |
SAM | -0.050 |
Token | ( |
Token ID | 7 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
jj | +0.647 |
sson | +0.632 |
andem | +0.587 |
zai | +0.552 |
hamm | +0.549 |
Neg logit contributions | |
�� | -1.177 |
LEY | -1.046 |
YL | -0.991 |
AF | -0.970 |
SAM | -0.969 |
Token | ap |
Token ID | 499 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
jj | +0.118 |
sson | +0.116 |
andem | +0.110 |
zai | +0.104 |
hamm | +0.104 |
Neg logit contributions | |
�� | -0.159 |
LEY | -0.140 |
YL | -0.131 |
AF | -0.129 |
SAM | -0.128 |
Token | < |
Token ID | 1279 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
jj | +1.591 |
sson | +1.565 |
andem | +1.493 |
zai | +1.434 |
hamm | +1.428 |
Neg logit contributions | |
�� | -1.435 |
LEY | -1.221 |
YL | -1.129 |
AF | -1.099 |
SAM | -1.092 |
Token | T |
Token ID | 309 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
jj | +1.630 |
sson | +1.597 |
andem | +1.513 |
zai | +1.444 |
hamm | +1.436 |
Neg logit contributions | |
�� | -1.909 |
LEY | -1.658 |
YL | -1.550 |
AF | -1.517 |
SAM | -1.507 |
Token | > |
Token ID | 1875 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
jj | +3.223 |
sson | +3.172 |
andem | +3.006 |
zai | +2.855 |
hamm | +2.837 |
Neg logit contributions | |
�� | -3.723 |
LEY | -3.227 |
YL | -3.014 |
SAM | -2.935 |
AF | -2.932 |
Token | { |
Token ID | 1391 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
jj | +0.728 |
sson | +0.707 |
andem | +0.660 |
zai | +0.618 |
hamm | +0.612 |
Neg logit contributions | |
�� | -1.443 |
LEY | -1.294 |
YL | -1.230 |
AF | -1.210 |
SAM | -1.201 |
Token | type |
Token ID | 2099 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
jj | +0.146 |
sson | +0.143 |
andem | +0.133 |
zai | +0.128 |
hamm | +0.127 |
Neg logit contributions | |
�� | -0.203 |
LEY | -0.177 |
YL | -0.168 |
AF | -0.165 |
SAM | -0.163 |
Token | Target |
Token ID | 12744 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
jj | +1.138 |
sson | +1.117 |
andem | +1.059 |
zai | +1.012 |
hamm | +1.007 |
Neg logit contributions | |
�� | -1.258 |
LEY | -1.089 |
YL | -1.017 |
AF | -0.993 |
SAM | -0.988 |
Token | = |
Token ID | 796 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
jj | +3.567 |
sson | +3.531 |
andem | +3.265 |
zai | +3.126 |
hamm | +3.075 |
Neg logit contributions | |
�� | -5.164 |
LEY | -4.547 |
YL | -4.235 |
AH | -4.132 |
SAM | -4.110 |
Token | T |
Token ID | 309 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
jj | +0.349 |
sson | +0.342 |
andem | +0.324 |
zai | +0.309 |
hamm | +0.307 |
Neg logit contributions | |
�� | -0.412 |
LEY | -0.358 |
YL | -0.335 |
AF | -0.327 |
SAM | -0.326 |
Token | ; |
Token ID | 2162 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
jj | +1.932 |
sson | +1.899 |
andem | +1.785 |
zai | +1.692 |
hamm | +1.677 |
Neg logit contributions | |
�� | -2.714 |
LEY | -2.382 |
YL | -2.233 |
AF | -2.181 |
SAM | -2.180 |
Token | ... |
Token ID | 2644 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
jj | +0.364 |
sson | +0.354 |
andem | +0.334 |
zai | +0.314 |
hamm | +0.310 |
Neg logit contributions | |
�� | -0.552 |
LEY | -0.488 |
YL | -0.463 |
AF | -0.455 |
SAM | -0.452 |
Token | } |
Token ID | 1782 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
jj | +1.236 |
sson | +1.200 |
andem | +1.106 |
zai | +1.029 |
hamm | +1.017 |
Neg logit contributions | |
�� | -2.672 |
LEY | -2.393 |
YL | -2.277 |
AF | -2.242 |
SAM | -2.230 |
Token | { |
Token ID | 1391 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
jj | +0.628 |
sson | +0.610 |
andem | +0.563 |
zai | +0.527 |
hamm | +0.520 |
Neg logit contributions | |
�� | -1.290 |
LEY | -1.155 |
YL | -1.097 |
AF | -1.079 |
SAM | -1.075 |
Token | // |
Token ID | 3373 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
�� | +0.110 |
LEY | +0.097 |
YL | +0.092 |
AF | +0.090 |
SAM | +0.090 |
Neg logit contributions | |
jj | -0.075 |
sson | -0.073 |
andem | -0.069 |
zai | -0.065 |
hamm | -0.065 |
Token | Time |
Token ID | 3862 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
jj | +0.467 |
sson | +0.459 |
andem | +0.433 |
zai | +0.412 |
hamm | +0.409 |
Neg logit contributions | |
�� | -0.609 |
LEY | -0.532 |
YL | -0.499 |
AF | -0.488 |
SAM | -0.486 |
Token | component |
Token ID | 7515 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
�� | +0.031 |
LEY | +0.027 |
YL | +0.025 |
AF | +0.025 |
SAM | +0.025 |
Neg logit contributions | |
jj | -0.023 |
sson | -0.022 |
andem | -0.021 |
zai | -0.020 |
hamm | -0.020 |
Token | const |
Token ID | 1500 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
�� | +0.774 |
LEY | +0.682 |
YL | +0.643 |
AF | +0.629 |
SAM | +0.627 |
Neg logit contributions | |
jj | -0.552 |
sson | -0.539 |
andem | -0.508 |
zai | -0.482 |
hamm | -0.477 |
Token | float |
Token ID | 12178 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
jj | +1.613 |
sson | +1.612 |
andem | +1.502 |
hamm | +1.413 |
zai | +1.407 |
Neg logit contributions | |
�� | -2.489 |
LEY | -2.173 |
YL | -2.047 |
AF | -1.985 |
AH | -1.983 |
Token | TA |
Token ID | 21664 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
sson | +3.870 |
jj | +3.857 |
andem | +3.644 |
hamm | +3.489 |
itle | +3.447 |
Neg logit contributions | |
�� | -4.770 |
LEY | -4.141 |
YL | -3.793 |
AF | -3.679 |
AH | -3.678 |
Token | U |
Token ID | 52 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
jj | +1.911 |
sson | +1.874 |
andem | +1.766 |
zai | +1.683 |
hamm | +1.672 |
Neg logit contributions | |
�� | -2.386 |
LEY | -2.074 |
YL | -1.939 |
AF | -1.896 |
SAM | -1.896 |
Token | = |
Token ID | 796 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
jj | +0.850 |
sson | +0.834 |
andem | +0.786 |
zai | +0.747 |
hamm | +0.743 |
Neg logit contributions | |
�� | -1.129 |
LEY | -0.989 |
YL | -0.929 |
AF | -0.908 |
SAM | -0.905 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
�� | +3.255 |
LEY | +2.862 |
YL | +2.672 |
AF | +2.632 |
SAM | +2.621 |
Neg logit contributions | |
jj | -2.744 |
sson | -2.678 |
andem | -2.533 |
zai | -2.412 |
hamm | -2.388 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
�� | +1.573 |
LEY | +1.393 |
YL | +1.309 |
AF | +1.291 |
AH | +1.282 |
Neg logit contributions | |
jj | -1.061 |
sson | -1.049 |
andem | -0.980 |
zai | -0.929 |
hamm | -0.922 |
Token | { |
Token ID | 1391 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
jj | +1.154 |
sson | +1.129 |
andem | +1.001 |
zai | +0.940 |
hamm | +0.937 |
Neg logit contributions | |
�� | -2.761 |
LEY | -2.454 |
YL | -2.336 |
SAM | -2.284 |
AF | -2.284 |
Token | // |
Token ID | 3373 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
jj | +1.564 |
sson | +1.535 |
andem | +1.446 |
zai | +1.372 |
hamm | +1.366 |
Neg logit contributions | |
�� | -2.138 |
LEY | -1.875 |
YL | -1.762 |
AF | -1.719 |
SAM | -1.715 |
Token | Time |
Token ID | 3862 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
jj | +1.848 |
sson | +1.820 |
andem | +1.731 |
zai | +1.659 |
hamm | +1.651 |
Neg logit contributions | |
�� | -1.805 |
LEY | -1.546 |
YL | -1.432 |
AF | -1.394 |
SAM | -1.388 |
Token | component |
Token ID | 7515 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
jj | +0.194 |
sson | +0.191 |
andem | +0.178 |
hamm | +0.167 |
zai | +0.166 |
Neg logit contributions | |
�� | -0.318 |
LEY | -0.280 |
YL | -0.264 |
AF | -0.259 |
AH | -0.258 |
Token | const |
Token ID | 1500 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
�� | +0.588 |
LEY | +0.525 |
YL | +0.497 |
AF | +0.489 |
SAM | +0.487 |
Neg logit contributions | |
jj | -0.311 |
sson | -0.303 |
andem | -0.281 |
zai | -0.264 |
hamm | -0.261 |
Token | float |
Token ID | 12178 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
sson | +0.982 |
jj | +0.954 |
andem | +0.879 |
hamm | +0.852 |
tug | +0.845 |
Neg logit contributions | |
�� | -1.925 |
LEY | -1.671 |
YL | -1.584 |
SAM | -1.547 |
AF | -1.537 |
Token | TA |
Token ID | 21664 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
sson | +4.042 |
jj | +3.958 |
andem | +3.694 |
zai | +3.685 |
tug | +3.648 |
Neg logit contributions | |
�� | -4.553 |
LEY | -3.741 |
YL | -3.491 |
AH | -3.400 |
SAM | -3.399 |
Token | U |
Token ID | 52 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
jj | +2.757 |
sson | +2.740 |
andem | +2.430 |
itle | +2.402 |
zai | +2.379 |
Neg logit contributions | |
�� | -3.256 |
LEY | -2.599 |
�� | -2.468 |
physic | -2.406 |
YL | -2.379 |
Token | = |
Token ID | 796 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
jj | +1.674 |
sson | +1.674 |
zai | +1.368 |
andem | +1.346 |
hamm | +1.320 |
Neg logit contributions | |
�� | -4.109 |
LEY | -3.456 |
�� | -3.378 |
YL | -3.265 |
SAM | -3.214 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
�� | +2.630 |
LEY | +2.278 |
YL | +2.100 |
AF | +2.090 |
AH | +2.068 |
Neg logit contributions | |
jj | -2.670 |
sson | -2.588 |
andem | -2.499 |
hamm | -2.344 |
zai | -2.337 |
Token | . |
Token ID | 13 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
�� | +1.823 |
LEY | +1.608 |
YL | +1.511 |
AF | +1.481 |
SAM | +1.474 |
Neg logit contributions | |
jj | -1.300 |
sson | -1.274 |
andem | -1.203 |
zai | -1.139 |
hamm | -1.132 |
Token | out |
Token ID | 448 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
�� | +0.929 |
LEY | +0.810 |
YL | +0.757 |
AF | +0.742 |
SAM | +0.738 |
Neg logit contributions | |
jj | -0.790 |
sson | -0.774 |
andem | -0.733 |
zai | -0.699 |
hamm | -0.697 |
Token | app |
Token ID | 598 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
jj | +0.995 |
sson | +0.989 |
andem | +0.929 |
hamm | +0.897 |
zai | +0.882 |
Neg logit contributions | |
�� | -1.351 |
LEY | -1.156 |
YL | -1.097 |
SAM | -1.050 |
AF | -1.048 |
Token | data |
Token ID | 7890 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
jj | +1.531 |
sson | +1.497 |
andem | +1.393 |
zai | +1.322 |
itle | +1.297 |
Neg logit contributions | |
�� | -2.341 |
LEY | -1.996 |
YL | -1.901 |
AH | -1.836 |
AF | -1.835 |
Token | _ |
Token ID | 4808 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
jj | +0.207 |
sson | +0.206 |
andem | +0.193 |
hamm | +0.188 |
zai | +0.188 |
Neg logit contributions | |
�� | -0.179 |
LEY | -0.146 |
YL | -0.134 |
AH | -0.130 |
SAM | -0.130 |
Token | full |
Token ID | 1336 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
jj | +1.213 |
sson | +1.203 |
andem | +1.107 |
hamm | +1.052 |
zai | +1.051 |
Neg logit contributions | |
�� | -2.188 |
LEY | -1.941 |
YL | -1.828 |
AH | -1.803 |
AF | -1.794 |
Token | v |
Token ID | 410 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
jj | +0.816 |
sson | +0.806 |
andem | +0.736 |
hamm | +0.699 |
zai | +0.695 |
Neg logit contributions | |
�� | -1.486 |
LEY | -1.301 |
YL | -1.230 |
AF | -1.203 |
SAM | -1.201 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
jj | +2.989 |
sson | +2.975 |
andem | +2.586 |
zai | +2.515 |
hamm | +2.512 |
Neg logit contributions | |
�� | -5.799 |
LEY | -4.983 |
YL | -4.721 |
�� | -4.638 |
SAM | -4.558 |
Token | { |
Token ID | 1391 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
jj | +1.154 |
sson | +1.129 |
andem | +1.001 |
zai | +0.940 |
hamm | +0.937 |
Neg logit contributions | |
�� | -2.761 |
LEY | -2.454 |
YL | -2.336 |
SAM | -2.284 |
AF | -2.284 |
Token | // |
Token ID | 3373 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
jj | +1.564 |
sson | +1.535 |
andem | +1.446 |
zai | +1.372 |
hamm | +1.366 |
Neg logit contributions | |
�� | -2.138 |
LEY | -1.875 |
YL | -1.762 |
AF | -1.719 |
SAM | -1.715 |
Token | Time |
Token ID | 3862 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
jj | +1.848 |
sson | +1.820 |
andem | +1.731 |
zai | +1.659 |
hamm | +1.651 |
Neg logit contributions | |
�� | -1.805 |
LEY | -1.546 |
YL | -1.432 |
AF | -1.394 |
SAM | -1.388 |
Token | component |
Token ID | 7515 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
jj | +0.194 |
sson | +0.191 |
andem | +0.178 |
hamm | +0.167 |
zai | +0.166 |
Neg logit contributions | |
�� | -0.318 |
LEY | -0.280 |
YL | -0.264 |
AF | -0.259 |
AH | -0.258 |
Token | out |
Token ID | 448 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
�� | +0.243 |
LEY | +0.212 |
YL | +0.198 |
AF | +0.194 |
SAM | +0.193 |
Neg logit contributions | |
jj | -0.200 |
sson | -0.197 |
andem | -0.186 |
zai | -0.177 |
hamm | -0.176 |
Token | app |
Token ID | 598 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
jj | +1.456 |
sson | +1.450 |
andem | +1.362 |
hamm | +1.314 |
zai | +1.290 |
Neg logit contributions | |
�� | -1.998 |
LEY | -1.716 |
YL | -1.629 |
SAM | -1.556 |
AF | -1.554 |
Token | data |
Token ID | 7890 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
jj | +1.608 |
sson | +1.569 |
andem | +1.450 |
zai | +1.385 |
itle | +1.359 |
Neg logit contributions | |
�� | -2.518 |
LEY | -2.134 |
YL | -2.031 |
�� | -1.979 |
AF | -1.965 |
Token | _ |
Token ID | 4808 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
jj | +0.188 |
sson | +0.186 |
andem | +0.170 |
zai | +0.166 |
hamm | +0.164 |
Neg logit contributions | |
�� | -0.217 |
LEY | -0.180 |
YL | -0.167 |
�� | -0.165 |
AH | -0.163 |
Token | full |
Token ID | 1336 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
jj | +1.783 |
sson | +1.762 |
andem | +1.638 |
zai | +1.558 |
hamm | +1.546 |
Neg logit contributions | |
�� | -2.792 |
LEY | -2.449 |
YL | -2.315 |
AH | -2.263 |
AF | -2.252 |
Token | v |
Token ID | 410 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
jj | +1.889 |
sson | +1.863 |
andem | +1.771 |
zai | +1.698 |
hamm | +1.685 |
Neg logit contributions | |
�� | -1.888 |
LEY | -1.605 |
YL | -1.493 |
AF | -1.445 |
SAM | -1.439 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
jj | +3.046 |
sson | +3.020 |
andem | +2.702 |
hamm | +2.638 |
zai | +2.631 |
Neg logit contributions | |
�� | -5.617 |
LEY | -4.925 |
YL | -4.637 |
SAM | -4.486 |
AH | -4.478 |
Token | { |
Token ID | 1391 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
jj | +1.152 |
sson | +1.124 |
andem | +1.020 |
zai | +0.956 |
hamm | +0.955 |
Neg logit contributions | |
�� | -2.617 |
LEY | -2.337 |
YL | -2.220 |
AF | -2.175 |
AH | -2.175 |
Token | v |
Token ID | 410 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
jj | +0.783 |
sson | +0.767 |
andem | +0.717 |
zai | +0.678 |
hamm | +0.674 |
Neg logit contributions | |
�� | -1.224 |
LEY | -1.081 |
YL | -1.019 |
AF | -0.998 |
SAM | -0.995 |
Token | . |
Token ID | 764 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
sson | +2.620 |
jj | +2.619 |
andem | +2.308 |
hamm | +2.306 |
zai | +2.297 |
Neg logit contributions | |
�� | -3.495 |
LEY | -2.883 |
�� | -2.734 |
YL | -2.686 |
SAM | -2.629 |
Token | vertex |
Token ID | 37423 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
jj | +1.127 |
sson | +1.113 |
andem | +1.035 |
hamm | +0.980 |
zai | +0.974 |
Neg logit contributions | |
�� | -1.877 |
LEY | -1.656 |
YL | -1.566 |
AF | -1.530 |
AH | -1.526 |
Token | decent |
Token ID | 7709 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
�� | +0.899 |
LEY | +0.795 |
YL | +0.748 |
AF | +0.737 |
AH | +0.731 |
Neg logit contributions | |
jj | -0.677 |
sson | -0.665 |
andem | -0.634 |
zai | -0.599 |
itle | -0.594 |
Token | . |
Token ID | 13 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
�� | +0.111 |
LEY | +0.099 |
YL | +0.093 |
AF | +0.091 |
AH | +0.091 |
Neg logit contributions | |
jj | -0.082 |
sson | -0.080 |
andem | -0.076 |
zai | -0.072 |
itle | -0.071 |
Token | I |
Token ID | 314 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
jj | +0.284 |
sson | +0.279 |
andem | +0.263 |
zai | +0.250 |
hamm | +0.248 |
Neg logit contributions | |
�� | -0.384 |
LEY | -0.337 |
YL | -0.317 |
AF | -0.310 |
SAM | -0.309 |
Token | think |
Token ID | 892 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
�� | +0.516 |
LEY | +0.458 |
YL | +0.430 |
AF | +0.423 |
AH | +0.421 |
Neg logit contributions | |
jj | -0.388 |
sson | -0.379 |
andem | -0.360 |
zai | -0.342 |
itle | -0.337 |
Token | P |
Token ID | 350 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
�� | +1.330 |
LEY | +1.184 |
YL | +1.118 |
AF | +1.099 |
AH | +1.091 |
Neg logit contributions | |
jj | -0.961 |
sson | -0.940 |
andem | -0.905 |
zai | -0.841 |
itle | -0.836 |
Token | 1 |
Token ID | 16 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
jj | +1.758 |
sson | +1.724 |
andem | +1.618 |
zai | +1.536 |
hamm | +1.528 |
Neg logit contributions | |
�� | -2.519 |
LEY | -2.218 |
YL | -2.088 |
AF | -2.044 |
SAM | -2.034 |
Token | was |
Token ID | 373 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
jj | +3.349 |
sson | +3.285 |
andem | +3.029 |
hamm | +2.889 |
zai | +2.859 |
Neg logit contributions | |
�� | -5.128 |
LEY | -4.477 |
YL | -4.205 |
SAM | -4.158 |
AF | -4.085 |
Token | good |
Token ID | 922 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
jj | +1.695 |
sson | +1.665 |
andem | +1.555 |
hamm | +1.486 |
zai | +1.483 |
Neg logit contributions | |
�� | -2.350 |
LEY | -2.054 |
YL | -1.929 |
SAM | -1.881 |
AF | -1.880 |
Token | , |
Token ID | 11 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
jj | +0.418 |
sson | +0.409 |
andem | +0.385 |
zai | +0.363 |
hamm | +0.359 |
Neg logit contributions | |
�� | -0.646 |
LEY | -0.575 |
YL | -0.542 |
AF | -0.532 |
AH | -0.529 |
Token | and |
Token ID | 290 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
jj | +0.030 |
sson | +0.030 |
andem | +0.028 |
zai | +0.026 |
itle | +0.026 |
Neg logit contributions | |
�� | -0.045 |
LEY | -0.040 |
YL | -0.038 |
AF | -0.037 |
AH | -0.037 |
Token | straight |
Token ID | 3892 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
jj | +0.794 |
sson | +0.779 |
andem | +0.735 |
zai | +0.696 |
hamm | +0.690 |
Neg logit contributions | |
�� | -1.108 |
LEY | -0.976 |
YL | -0.918 |
AF | -0.899 |
SAM | -0.894 |
Token | 4 |
Token ID | 604 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
�� | +0.329 |
LEY | +0.281 |
YL | +0.263 |
AF | +0.259 |
SAM | +0.257 |
Neg logit contributions | |
jj | -0.295 |
sson | -0.291 |
andem | -0.275 |
zai | -0.262 |
hamm | -0.260 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
�� | +0.184 |
LEY | +0.159 |
YL | +0.149 |
AF | +0.147 |
AH | +0.145 |
Neg logit contributions | |
jj | -0.164 |
sson | -0.159 |
andem | -0.152 |
zai | -0.143 |
itle | -0.142 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
�� | +0.255 |
LEY | +0.218 |
YL | +0.205 |
AF | +0.201 |
AH | +0.199 |
Neg logit contributions | |
jj | -0.238 |
sson | -0.233 |
andem | -0.222 |
zai | -0.211 |
hamm | -0.210 |
Token | 7 |
Token ID | 767 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
�� | +0.391 |
LEY | +0.345 |
YL | +0.327 |
AF | +0.326 |
AH | +0.323 |
Neg logit contributions | |
jj | -0.272 |
sson | -0.263 |
andem | -0.248 |
itle | -0.235 |
zai | -0.232 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
jj | +0.258 |
sson | +0.255 |
andem | +0.237 |
zai | +0.226 |
hamm | +0.223 |
Neg logit contributions | |
�� | -0.354 |
LEY | -0.309 |
YL | -0.293 |
AF | -0.290 |
SAM | -0.287 |
Token | void |
Token ID | 7951 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
�� | +0.683 |
LEY | +0.606 |
YL | +0.578 |
AF | +0.574 |
AH | +0.565 |
Neg logit contributions | |
jj | -0.458 |
sson | -0.448 |
andem | -0.414 |
zai | -0.390 |
hamm | -0.386 |
Token | vert |
Token ID | 9421 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
sson | +2.958 |
jj | +2.833 |
andem | +2.633 |
hamm | +2.550 |
zai | +2.516 |
Neg logit contributions | |
�� | -5.624 |
LEY | -4.907 |
YL | -4.634 |
AF | -4.574 |
AH | -4.507 |
Token | ( |
Token ID | 357 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
jj | +0.790 |
sson | +0.780 |
andem | +0.712 |
zai | +0.682 |
hamm | +0.677 |
Neg logit contributions | |
�� | -1.280 |
LEY | -1.105 |
YL | -1.041 |
SAM | -1.017 |
AF | -1.016 |
Token | in |
Token ID | 287 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
�� | +0.279 |
LEY | +0.243 |
YL | +0.227 |
SAM | +0.221 |
AH | +0.221 |
Neg logit contributions | |
jj | -0.212 |
sson | -0.210 |
andem | -0.196 |
zai | -0.188 |
hamm | -0.188 |
Token | out |
Token ID | 448 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
�� | +0.929 |
LEY | +0.810 |
YL | +0.757 |
AF | +0.742 |
SAM | +0.738 |
Neg logit contributions | |
jj | -0.790 |
sson | -0.774 |
andem | -0.733 |
zai | -0.699 |
hamm | -0.697 |
Token | app |
Token ID | 598 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
jj | +0.995 |
sson | +0.989 |
andem | +0.929 |
hamm | +0.897 |
zai | +0.882 |
Neg logit contributions | |
�� | -1.351 |
LEY | -1.156 |
YL | -1.097 |
SAM | -1.050 |
AF | -1.048 |
Token | Silver |
Token ID | 26766 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
jj | +0.324 |
sson | +0.318 |
andem | +0.300 |
zai | +0.285 |
hamm | +0.284 |
Neg logit contributions | |
�� | -0.425 |
LEY | -0.371 |
YL | -0.348 |
AF | -0.341 |
SAM | -0.340 |
Token | Bullet |
Token ID | 18003 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
jj | +0.634 |
sson | +0.625 |
andem | +0.596 |
zai | +0.572 |
hamm | +0.570 |
Neg logit contributions | |
�� | -0.529 |
LEY | -0.444 |
YL | -0.407 |
AF | -0.397 |
AH | -0.395 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
jj | +0.265 |
sson | +0.260 |
andem | +0.245 |
zai | +0.233 |
hamm | +0.232 |
Neg logit contributions | |
�� | -0.338 |
LEY | -0.295 |
YL | -0.277 |
AF | -0.272 |
SAM | -0.270 |
Token | � |
Token ID | 251 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
�� | +0.499 |
LEY | +0.406 |
YL | +0.371 |
AF | +0.356 |
AH | +0.356 |
Neg logit contributions | |
jj | -0.665 |
sson | -0.658 |
andem | -0.633 |
zai | -0.606 |
hamm | -0.605 |
Token | but |
Token ID | 475 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
jj | +0.111 |
sson | +0.108 |
andem | +0.101 |
zai | +0.096 |
hamm | +0.096 |
Neg logit contributions | |
�� | -0.162 |
LEY | -0.142 |
YL | -0.134 |
AF | -0.132 |
SAM | -0.131 |
Token | rather |
Token ID | 2138 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
jj | +0.677 |
sson | +0.657 |
andem | +0.620 |
zai | +0.583 |
itle | +0.579 |
Neg logit contributions | |
�� | -1.027 |
LEY | -0.911 |
YL | -0.860 |
AF | -0.841 |
SAM | -0.839 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
jj | +3.238 |
sson | +3.221 |
andem | +2.999 |
hamm | +2.856 |
zai | +2.850 |
Neg logit contributions | |
�� | -5.164 |
LEY | -4.559 |
YL | -4.294 |
AF | -4.200 |
AH | -4.189 |
Token | combination |
Token ID | 6087 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
jj | +0.691 |
sson | +0.677 |
andem | +0.633 |
zai | +0.601 |
hamm | +0.594 |
Neg logit contributions | |
�� | -1.018 |
LEY | -0.899 |
YL | -0.846 |
AF | -0.830 |
SAM | -0.826 |
Token | of |
Token ID | 286 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
�� | +0.156 |
LEY | +0.137 |
YL | +0.128 |
AF | +0.126 |
AH | +0.126 |
Neg logit contributions | |
jj | -0.113 |
sson | -0.111 |
andem | -0.103 |
zai | -0.098 |
hamm | -0.097 |
Token | D |
Token ID | 360 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
jj | +0.201 |
sson | +0.196 |
andem | +0.184 |
zai | +0.175 |
hamm | +0.172 |
Neg logit contributions | |
�� | -0.296 |
LEY | -0.261 |
YL | -0.245 |
AF | -0.241 |
SAM | -0.240 |
Token | DoS |
Token ID | 46498 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
jj | +0.214 |
sson | +0.211 |
andem | +0.201 |
zai | +0.196 |
hamm | +0.194 |
Neg logit contributions | |
�� | -0.150 |
LEY | -0.127 |
YL | -0.115 |
AF | -0.113 |
ICE | -0.111 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
�� | +1.522 |
LEY | +1.351 |
YL | +1.275 |
AH | +1.250 |
AF | +1.244 |
Neg logit contributions | |
jj | -1.124 |
sson | -1.103 |
andem | -1.035 |
zai | -0.982 |
hamm | -0.970 |
Token | . |
Token ID | 13 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
�� | +0.099 |
LEY | +0.088 |
YL | +0.083 |
AF | +0.082 |
AH | +0.081 |
Neg logit contributions | |
jj | -0.065 |
sson | -0.064 |
andem | -0.060 |
hamm | -0.057 |
zai | -0.056 |
Token | 800 |
Token ID | 7410 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
jj | +0.392 |
sson | +0.385 |
andem | +0.363 |
zai | +0.346 |
hamm | +0.344 |
Neg logit contributions | |
�� | -0.489 |
LEY | -0.427 |
YL | -0.400 |
AF | -0.391 |
SAM | -0.390 |
Token | . |
Token ID | 13 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
�� | +0.365 |
LEY | +0.322 |
YL | +0.304 |
AF | +0.298 |
AH | +0.296 |
Neg logit contributions | |
jj | -0.262 |
sson | -0.254 |
andem | -0.240 |
zai | -0.227 |
hamm | -0.227 |
Token | 366 |
Token ID | 32459 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
jj | +2.159 |
sson | +2.123 |
andem | +1.999 |
zai | +1.933 |
hamm | +1.908 |
Neg logit contributions | |
�� | -2.085 |
LEY | -1.732 |
YL | -1.607 |
AF | -1.555 |
AH | -1.554 |
Token | . |
Token ID | 13 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
jj | +0.587 |
sson | +0.575 |
andem | +0.516 |
zai | +0.498 |
hamm | +0.489 |
Neg logit contributions | |
�� | -1.032 |
LEY | -0.889 |
YL | -0.841 |
�� | -0.827 |
SAM | -0.820 |
Token | 44 |
Token ID | 2598 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
jj | +3.764 |
sson | +3.668 |
zai | +3.237 |
andem | +3.221 |
ama | +3.153 |
Neg logit contributions | |
�� | -4.913 |
LEY | -3.871 |
�� | -3.789 |
YL | -3.638 |
physic | -3.590 |
Token | 84 |
Token ID | 5705 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
jj | +0.096 |
sson | +0.094 |
andem | +0.089 |
zai | +0.085 |
hamm | +0.085 |
Neg logit contributions | |
�� | -0.101 |
LEY | -0.088 |
YL | -0.082 |
AF | -0.080 |
SAM | -0.079 |
Token | or |
Token ID | 393 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
�� | +0.238 |
LEY | +0.211 |
YL | +0.198 |
AF | +0.195 |
AH | +0.193 |
Neg logit contributions | |
jj | -0.159 |
sson | -0.156 |
andem | -0.146 |
zai | -0.138 |
hamm | -0.138 |
Token | by |
Token ID | 416 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
�� | +0.199 |
LEY | +0.174 |
YL | +0.163 |
AF | +0.160 |
SAM | +0.159 |
Neg logit contributions | |
jj | -0.168 |
sson | -0.164 |
andem | -0.156 |
zai | -0.148 |
hamm | -0.146 |
Token | using |
Token ID | 1262 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
jj | +1.581 |
sson | +1.554 |
andem | +1.469 |
zai | +1.403 |
hamm | +1.399 |
Neg logit contributions | |
�� | -1.865 |
LEY | -1.619 |
YL | -1.511 |
AF | -1.475 |
SAM | -1.471 |
Token | of |
Token ID | 286 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
�� | +1.105 |
LEY | +0.961 |
YL | +0.904 |
AF | +0.893 |
AH | +0.892 |
Neg logit contributions | |
jj | -0.848 |
sson | -0.829 |
andem | -0.781 |
zai | -0.737 |
itle | -0.733 |
Token | beauty |
Token ID | 8737 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
�� | +0.041 |
LEY | +0.036 |
YL | +0.034 |
AF | +0.033 |
AH | +0.033 |
Neg logit contributions | |
jj | -0.033 |
sson | -0.033 |
andem | -0.031 |
zai | -0.029 |
hamm | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
�� | +0.229 |
LEY | +0.202 |
YL | +0.191 |
AF | +0.188 |
AH | +0.188 |
Neg logit contributions | |
jj | -0.156 |
sson | -0.153 |
andem | -0.144 |
itle | -0.135 |
zai | -0.135 |
Token | In |
Token ID | 554 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
jj | +0.316 |
sson | +0.309 |
andem | +0.293 |
zai | +0.277 |
hamm | +0.275 |
Neg logit contributions | |
�� | -0.449 |
LEY | -0.397 |
YL | -0.373 |
AF | -0.366 |
SAM | -0.364 |
Token | some |
Token ID | 617 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
jj | +0.815 |
sson | +0.797 |
andem | +0.749 |
zai | +0.710 |
hamm | +0.705 |
Neg logit contributions | |
�� | -1.193 |
LEY | -1.051 |
YL | -0.990 |
AF | -0.969 |
SAM | -0.965 |
Token | senses |
Token ID | 17627 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
jj | +0.283 |
sson | +0.278 |
andem | +0.262 |
zai | +0.249 |
hamm | +0.248 |
Neg logit contributions | |
�� | -0.369 |
LEY | -0.323 |
YL | -0.303 |
AF | -0.296 |
SAM | -0.295 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
jj | +3.236 |
sson | +3.183 |
andem | +2.942 |
hamm | +2.809 |
zai | +2.809 |
Neg logit contributions | |
�� | -5.162 |
LEY | -4.536 |
YL | -4.282 |
SAM | -4.212 |
AF | -4.190 |
Token | it |
Token ID | 340 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
jj | +0.720 |
sson | +0.706 |
andem | +0.667 |
zai | +0.632 |
hamm | +0.627 |
Neg logit contributions | |
�� | -0.967 |
LEY | -0.851 |
YL | -0.799 |
AF | -0.782 |
AH | -0.778 |
Token | is |
Token ID | 318 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
jj | +0.700 |
sson | +0.678 |
andem | +0.648 |
zai | +0.602 |
itle | +0.600 |
Neg logit contributions | |
�� | -1.064 |
LEY | -0.946 |
YL | -0.901 |
AF | -0.881 |
AH | -0.877 |
Token | as |
Token ID | 355 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
jj | +0.138 |
sson | +0.135 |
andem | +0.128 |
zai | +0.120 |
itle | +0.119 |
Neg logit contributions | |
�� | -0.198 |
LEY | -0.176 |
YL | -0.166 |
AF | -0.163 |
AH | -0.162 |
Token | if |
Token ID | 611 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
�� | +1.040 |
LEY | +0.916 |
YL | +0.874 |
AF | +0.852 |
SAM | +0.843 |
Neg logit contributions | |
jj | -0.749 |
sson | -0.733 |
andem | -0.695 |
zai | -0.656 |
itle | -0.650 |
Token | what |
Token ID | 644 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
�� | +0.038 |
LEY | +0.033 |
YL | +0.031 |
AF | +0.031 |
SAM | +0.031 |
Neg logit contributions | |
jj | -0.025 |
sson | -0.024 |
andem | -0.023 |
zai | -0.022 |
hamm | -0.021 |
Token | you |
Token ID | 345 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
�� | +0.398 |
LEY | +0.346 |
YL | +0.322 |
AF | +0.315 |
AH | +0.313 |
Neg logit contributions | |
jj | -0.354 |
sson | -0.347 |
andem | -0.330 |
zai | -0.314 |
hamm | -0.311 |
Token | � |
Token ID | 447 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
jj | +1.569 |
sson | +1.535 |
andem | +1.437 |
zai | +1.357 |
hamm | +1.347 |
Neg logit contributions | |
�� | -2.509 |
LEY | -2.220 |
YL | -2.094 |
AF | -2.055 |
SAM | -2.047 |
Token | � |
Token ID | 247 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
jj | +1.325 |
sson | +1.304 |
andem | +1.242 |
zai | +1.196 |
hamm | +1.194 |
Neg logit contributions | |
�� | -0.972 |
LEY | -0.823 |
YL | -0.751 |
AF | -0.729 |
SAM | -0.725 |
Token | re |
Token ID | 260 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
jj | +1.035 |
sson | +1.015 |
andem | +0.955 |
zai | +0.907 |
hamm | +0.902 |
Neg logit contributions | |
�� | -1.419 |
LEY | -1.246 |
YL | -1.170 |
AF | -1.146 |
SAM | -1.141 |
Token | thinking |
Token ID | 3612 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
jj | +0.351 |
sson | +0.345 |
andem | +0.328 |
zai | +0.313 |
hamm | +0.311 |
Neg logit contributions | |
�� | -0.380 |
LEY | -0.328 |
YL | -0.305 |
AF | -0.300 |
AH | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
jj | +2.985 |
sson | +2.913 |
andem | +2.670 |
zai | +2.560 |
hamm | +2.527 |
Neg logit contributions | |
�� | -5.420 |
LEY | -4.802 |
YL | -4.552 |
SAM | -4.464 |
AF | -4.443 |
Token | � |
Token ID | 564 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
jj | +0.564 |
sson | +0.555 |
andem | +0.521 |
zai | +0.499 |
hamm | +0.496 |
Neg logit contributions | |
�� | -0.703 |
LEY | -0.608 |
YL | -0.570 |
AF | -0.555 |
SAM | -0.554 |
Token | � |
Token ID | 250 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
jj | +0.760 |
sson | +0.751 |
andem | +0.723 |
zai | +0.699 |
hamm | +0.697 |
Neg logit contributions | |
�� | -0.447 |
LEY | -0.356 |
YL | -0.318 |
AF | -0.307 |
SAM | -0.305 |
Token | Roger |
Token ID | 43719 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
jj | +0.082 |
sson | +0.081 |
andem | +0.076 |
zai | +0.072 |
hamm | +0.072 |
Neg logit contributions | |
�� | -0.112 |
LEY | -0.098 |
YL | -0.092 |
AF | -0.090 |
SAM | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
�� | +1.851 |
LEY | +1.624 |
YL | +1.523 |
AF | +1.503 |
AH | +1.489 |
Neg logit contributions | |
jj | -1.489 |
sson | -1.429 |
andem | -1.382 |
zai | -1.301 |
itle | -1.294 |
Token | Mut |
Token ID | 41603 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
jj | +1.963 |
sson | +1.935 |
andem | +1.824 |
zai | +1.731 |
hamm | +1.725 |
Neg logit contributions | |
�� | -2.438 |
LEY | -2.128 |
YL | -1.984 |
AH | -1.931 |
AF | -1.930 |
Token | for |
Token ID | 329 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
�� | +0.182 |
LEY | +0.160 |
YL | +0.151 |
AF | +0.149 |
SAM | +0.147 |
Neg logit contributions | |
jj | -0.142 |
sson | -0.138 |
andem | -0.130 |
zai | -0.126 |
hamm | -0.124 |
Token | Own |
Token ID | 11744 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
jj | +0.608 |
sson | +0.593 |
andem | +0.562 |
zai | +0.536 |
hamm | +0.533 |
Neg logit contributions | |
�� | -0.737 |
LEY | -0.641 |
YL | -0.601 |
AF | -0.587 |
SAM | -0.584 |
Token | ed |
Token ID | 276 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
jj | +1.462 |
sson | +1.441 |
andem | +1.323 |
zai | +1.272 |
itle | +1.263 |
Neg logit contributions | |
�� | -1.888 |
LEY | -1.569 |
YL | -1.465 |
�� | -1.444 |
AH | -1.431 |
Token | < |
Token ID | 1279 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
sson | +2.295 |
jj | +2.294 |
andem | +2.102 |
zai | +2.045 |
hamm | +2.011 |
Neg logit contributions | |
�� | -2.633 |
LEY | -2.179 |
YL | -2.008 |
�� | -1.997 |
SAM | -1.964 |
Token | T |
Token ID | 309 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
jj | +1.897 |
sson | +1.892 |
andem | +1.750 |
zai | +1.680 |
hamm | +1.666 |
Neg logit contributions | |
�� | -2.617 |
LEY | -2.259 |
YL | -2.113 |
AH | -2.073 |
SAM | -2.071 |
Token | > |
Token ID | 1875 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
sson | +3.457 |
jj | +3.443 |
andem | +3.191 |
zai | +2.962 |
itle | +2.950 |
Neg logit contributions | |
�� | -4.940 |
LEY | -4.135 |
YL | -3.882 |
SAM | -3.792 |
�� | -3.784 |
Token | { |
Token ID | 1391 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
jj | +0.863 |
sson | +0.849 |
andem | +0.761 |
zai | +0.712 |
hamm | +0.702 |
Neg logit contributions | |
�� | -2.037 |
LEY | -1.809 |
YL | -1.716 |
SAM | -1.683 |
AF | -1.681 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
jj | +0.372 |
sson | +0.363 |
andem | +0.343 |
zai | +0.329 |
hamm | +0.326 |
Neg logit contributions | |
�� | -0.439 |
LEY | -0.380 |
YL | -0.359 |
AF | -0.352 |
SAM | -0.349 |
Token | } |
Token ID | 1782 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
jj | +1.438 |
sson | +1.410 |
andem | +1.289 |
zai | +1.205 |
hamm | +1.197 |
Neg logit contributions | |
�� | -3.192 |
LEY | -2.850 |
YL | -2.700 |
AF | -2.649 |
SAM | -2.648 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
�� | +0.217 |
LEY | +0.194 |
YL | +0.185 |
AF | +0.182 |
AH | +0.181 |
Neg logit contributions | |
jj | -0.122 |
sson | -0.118 |
andem | -0.111 |
zai | -0.104 |
hamm | -0.102 |
Token | even |
Token ID | 772 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
jj | +0.068 |
sson | +0.067 |
andem | +0.063 |
zai | +0.061 |
hamm | +0.059 |
Neg logit contributions | |
�� | -0.080 |
LEY | -0.070 |
YL | -0.066 |
AF | -0.064 |
AH | -0.064 |
Token | tell |
Token ID | 1560 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
jj | +0.078 |
sson | +0.077 |
andem | +0.073 |
zai | +0.069 |
hamm | +0.068 |
Neg logit contributions | |
�� | -0.095 |
LEY | -0.083 |
YL | -0.078 |
AF | -0.076 |
AH | -0.076 |
Token | what |
Token ID | 644 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
jj | +0.899 |
sson | +0.880 |
andem | +0.821 |
zai | +0.774 |
hamm | +0.767 |
Neg logit contributions | |
�� | -1.509 |
LEY | -1.340 |
YL | -1.266 |
AF | -1.241 |
SAM | -1.236 |
Token | you |
Token ID | 345 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
�� | +0.510 |
LEY | +0.456 |
YL | +0.431 |
AF | +0.420 |
AH | +0.419 |
Neg logit contributions | |
jj | -0.337 |
sson | -0.330 |
andem | -0.312 |
zai | -0.294 |
itle | -0.287 |
Token | 're |
Token ID | 821 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
jj | +1.096 |
sson | +1.074 |
andem | +1.006 |
zai | +0.955 |
hamm | +0.943 |
Neg logit contributions | |
�� | -1.670 |
LEY | -1.480 |
YL | -1.393 |
AF | -1.368 |
SAM | -1.362 |
Token | looking |
Token ID | 2045 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
jj | +2.277 |
sson | +2.238 |
andem | +2.108 |
hamm | +2.008 |
zai | +2.005 |
Neg logit contributions | |
�� | -2.907 |
LEY | -2.527 |
YL | -2.370 |
AF | -2.309 |
SAM | -2.307 |
Token | at |
Token ID | 379 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
jj | +3.581 |
sson | +3.516 |
andem | +3.308 |
zai | +3.145 |
hamm | +3.133 |
Neg logit contributions | |
�� | -4.701 |
LEY | -4.108 |
YL | -3.853 |
SAM | -3.766 |
AF | -3.753 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
jj | +0.530 |
sson | +0.520 |
andem | +0.488 |
zai | +0.462 |
hamm | +0.457 |
Neg logit contributions | |
�� | -0.797 |
LEY | -0.707 |
YL | -0.666 |
AF | -0.654 |
AH | -0.650 |
Token | much |
Token ID | 881 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
jj | +0.638 |
sson | +0.625 |
andem | +0.586 |
zai | +0.554 |
hamm | +0.550 |
Neg logit contributions | |
�� | -0.972 |
LEY | -0.858 |
YL | -0.809 |
AF | -0.792 |
SAM | -0.789 |
Token | less |
Token ID | 1342 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
jj | +1.616 |
sson | +1.591 |
andem | +1.507 |
zai | +1.448 |
hamm | +1.445 |
Neg logit contributions | |
�� | -1.581 |
LEY | -1.348 |
YL | -1.251 |
SAM | -1.216 |
AF | -1.215 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
jj | +2.048 |
sson | +2.004 |
andem | +1.863 |
hamm | +1.782 |
zai | +1.771 |
Neg logit contributions | |
�� | -3.199 |
LEY | -2.808 |
YL | -2.650 |
SAM | -2.593 |
AF | -2.590 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
�� | +1.729 |
LEY | +1.572 |
YL | +1.484 |
AF | +1.462 |
SAM | +1.453 |
Neg logit contributions | |
jj | -1.050 |
sson | -1.025 |
andem | -0.978 |
zai | -0.912 |
hamm | -0.909 |
Token | re |
Token ID | 260 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
�� | +2.055 |
LEY | +1.827 |
YL | +1.716 |
AF | +1.690 |
AH | +1.677 |
Neg logit contributions | |
jj | -1.751 |
sson | -1.748 |
andem | -1.663 |
hamm | -1.613 |
zai | -1.580 |
Token | i |
Token ID | 72 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
jj | +0.601 |
sson | +0.591 |
andem | +0.555 |
hamm | +0.527 |
zai | +0.526 |
Neg logit contributions | |
�� | -0.838 |
LEY | -0.737 |
YL | -0.693 |
AF | -0.679 |
SAM | -0.675 |
Token | Profile |
Token ID | 13118 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
jj | +1.460 |
sson | +1.431 |
andem | +1.355 |
zai | +1.293 |
hamm | +1.283 |
Neg logit contributions | |
�� | -1.674 |
LEY | -1.448 |
YL | -1.350 |
AF | -1.317 |
SAM | -1.315 |
Token | Blog |
Token ID | 14001 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
�� | +1.354 |
LEY | +1.140 |
YL | +1.026 |
AF | +0.999 |
AH | +0.982 |
Neg logit contributions | |
jj | -2.040 |
sson | -2.011 |
andem | -1.935 |
zai | -1.859 |
itle | -1.859 |
Token | Joined |
Token ID | 16709 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
�� | +1.764 |
LEY | +1.448 |
YL | +1.313 |
AF | +1.267 |
SAM | +1.261 |
Neg logit contributions | |
jj | -2.636 |
sson | -2.602 |
andem | -2.491 |
zai | -2.409 |
hamm | -2.399 |
Token | October |
Token ID | 3267 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
�� | +4.888 |
LEY | +4.573 |
YL | +4.268 |
AF | +4.138 |
AH | +4.114 |
Neg logit contributions | |
jj | -3.796 |
sson | -3.719 |
andem | -3.639 |
itle | -3.416 |
zai | -3.306 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
jj | +0.135 |
sson | +0.134 |
andem | +0.121 |
hamm | +0.115 |
zai | +0.115 |
Neg logit contributions | |
�� | -0.248 |
LEY | -0.218 |
YL | -0.207 |
AF | -0.202 |
SAM | -0.202 |
Token | United |
Token ID | 1578 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
jj | +0.758 |
sson | +0.747 |
andem | +0.700 |
zai | +0.673 |
hamm | +0.671 |
Neg logit contributions | |
�� | -0.864 |
LEY | -0.735 |
YL | -0.687 |
SAM | -0.670 |
AF | -0.667 |
Token | States |
Token ID | 1829 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
�� | +0.018 |
LEY | +0.014 |
YL | +0.013 |
AF | +0.012 |
SAM | +0.012 |
Neg logit contributions | |
jj | -0.030 |
sson | -0.030 |
andem | -0.029 |
zai | -0.028 |
hamm | -0.028 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
�� | +0.012 |
LEY | +0.010 |
YL | +0.010 |
AF | +0.010 |
SAM | +0.009 |
Neg logit contributions | |
jj | -0.010 |
sson | -0.010 |
andem | -0.009 |
zai | -0.009 |
hamm | -0.009 |
Token | housing |
Token ID | 5627 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
�� | +1.421 |
LEY | +1.260 |
YL | +1.185 |
AF | +1.169 |
AH | +1.164 |
Neg logit contributions | |
jj | -1.019 |
sson | -1.002 |
andem | -0.941 |
zai | -0.895 |
itle | -0.879 |
Token | market |
Token ID | 1910 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
�� | +0.826 |
LEY | +0.748 |
YL | +0.707 |
AF | +0.698 |
AH | +0.696 |
Neg logit contributions | |
jj | -0.377 |
sson | -0.367 |
andem | -0.340 |
zai | -0.314 |
itle | -0.309 |
Token | has |
Token ID | 468 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
�� | +1.741 |
LEY | +1.544 |
YL | +1.448 |
AH | +1.426 |
AF | +1.424 |
Neg logit contributions | |
jj | -1.405 |
sson | -1.370 |
andem | -1.324 |
zai | -1.243 |
itle | -1.238 |
Token | paused |
Token ID | 24487 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
�� | +0.529 |
LEY | +0.467 |
YL | +0.439 |
AF | +0.430 |
AH | +0.429 |
Neg logit contributions | |
jj | -0.394 |
sson | -0.385 |
andem | -0.367 |
zai | -0.347 |
itle | -0.344 |
Token | for |
Token ID | 329 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
jj | +0.075 |
sson | +0.073 |
andem | +0.070 |
zai | +0.066 |
hamm | +0.065 |
Neg logit contributions | |
�� | -0.100 |
LEY | -0.088 |
YL | -0.083 |
AF | -0.082 |
AH | -0.081 |
Token | breath |
Token ID | 8033 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
�� | +0.836 |
LEY | +0.732 |
YL | +0.691 |
AF | +0.680 |
AH | +0.676 |
Neg logit contributions | |
jj | -0.628 |
sson | -0.619 |
andem | -0.583 |
zai | -0.552 |
itle | -0.548 |
Token | ( |
Token ID | 357 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
�� | +3.285 |
LEY | +2.888 |
YL | +2.695 |
AF | +2.657 |
AH | +2.630 |
Neg logit contributions | |
jj | -2.734 |
sson | -2.701 |
andem | -2.578 |
zai | -2.430 |
hamm | -2.422 |
Token | after |
Token ID | 8499 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
�� | +0.782 |
LEY | +0.690 |
YL | +0.647 |
AF | +0.637 |
AH | +0.633 |
Neg logit contributions | |
jj | -0.636 |
sson | -0.628 |
andem | -0.594 |
hamm | -0.565 |
zai | -0.564 |
Token | a |
Token ID | 257 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
�� | +1.145 |
LEY | +1.012 |
YL | +0.953 |
AF | +0.933 |
AH | +0.930 |
Neg logit contributions | |
jj | -0.831 |
sson | -0.815 |
andem | -0.773 |
zai | -0.725 |
hamm | -0.716 |
Token | steep |
Token ID | 14559 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
�� | +0.275 |
LEY | +0.242 |
YL | +0.228 |
AF | +0.223 |
AH | +0.222 |
Neg logit contributions | |
jj | -0.200 |
sson | -0.197 |
andem | -0.185 |
zai | -0.175 |
hamm | -0.173 |
Token | climb |
Token ID | 12080 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
jj | +0.601 |
sson | +0.588 |
andem | +0.551 |
zai | +0.518 |
hamm | +0.515 |
Neg logit contributions | |
�� | -0.989 |
LEY | -0.879 |
YL | -0.829 |
AF | -0.813 |
AH | -0.809 |
Token | member |
Token ID | 2888 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
�� | +0.191 |
LEY | +0.166 |
YL | +0.155 |
AF | +0.151 |
SAM | +0.150 |
Neg logit contributions | |
jj | -0.166 |
sson | -0.164 |
andem | -0.155 |
zai | -0.148 |
hamm | -0.147 |
Token | while |
Token ID | 981 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
�� | +0.356 |
LEY | +0.314 |
YL | +0.296 |
AF | +0.291 |
AH | +0.289 |
Neg logit contributions | |
jj | -0.243 |
sson | -0.237 |
andem | -0.224 |
zai | -0.210 |
hamm | -0.210 |
Token | drunk |
Token ID | 10785 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
�� | +1.072 |
LEY | +0.943 |
YL | +0.890 |
AF | +0.866 |
AH | +0.859 |
Neg logit contributions | |
jj | -0.852 |
sson | -0.838 |
andem | -0.795 |
zai | -0.747 |
hamm | -0.744 |
Token | . |
Token ID | 13 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
jj | +0.791 |
sson | +0.775 |
andem | +0.726 |
zai | +0.687 |
hamm | +0.682 |
Neg logit contributions | |
�� | -1.210 |
LEY | -1.069 |
YL | -1.007 |
AF | -0.986 |
SAM | -0.983 |
Token | Cl |
Token ID | 1012 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
�� | +0.192 |
LEY | +0.168 |
YL | +0.157 |
AF | +0.154 |
SAM | +0.153 |
Neg logit contributions | |
jj | -0.151 |
sson | -0.148 |
andem | -0.140 |
zai | -0.133 |
hamm | -0.133 |
Token | ad |
Token ID | 324 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
jj | +0.555 |
sson | +0.546 |
andem | +0.512 |
zai | +0.489 |
hamm | +0.488 |
Neg logit contributions | |
�� | -0.755 |
LEY | -0.664 |
YL | -0.624 |
AF | -0.616 |
AH | -0.611 |
Token | in |
Token ID | 287 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
�� | +3.684 |
LEY | +3.148 |
AF | +2.822 |
ICE | +2.819 |
YL | +2.810 |
Neg logit contributions | |
jj | -3.570 |
sson | -3.512 |
andem | -3.367 |
itle | -3.282 |
zai | -3.272 |
Token | a |
Token ID | 257 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
�� | +1.481 |
LEY | +1.296 |
YL | +1.225 |
AF | +1.196 |
SAM | +1.185 |
Neg logit contributions | |
jj | -1.098 |
sson | -1.083 |
andem | -1.012 |
zai | -0.963 |
itle | -0.955 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
�� | +0.194 |
LEY | +0.170 |
YL | +0.160 |
AF | +0.157 |
SAM | +0.156 |
Neg logit contributions | |
jj | -0.142 |
sson | -0.140 |
andem | -0.132 |
zai | -0.125 |
itle | -0.123 |
Token | Argon |
Token ID | 49974 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
�� | +2.220 |
LEY | +1.916 |
YL | +1.793 |
AF | +1.772 |
ICE | +1.739 |
Neg logit contributions | |
jj | -2.024 |
sson | -1.992 |
andem | -1.903 |
itle | -1.798 |
zai | -1.789 |
Token | auts |
Token ID | 17712 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
jj | +1.083 |
sson | +1.058 |
andem | +0.990 |
zai | +0.948 |
hamm | +0.939 |
Neg logit contributions | |
�� | -1.695 |
LEY | -1.476 |
YL | -1.399 |
SAM | -1.369 |
AF | -1.360 |
Token | security |
Token ID | 2324 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
�� | +0.199 |
LEY | +0.174 |
YL | +0.163 |
AF | +0.160 |
SAM | +0.159 |
Neg logit contributions | |
jj | -0.165 |
sson | -0.161 |
andem | -0.153 |
zai | -0.146 |
hamm | -0.144 |
Token | functions |
Token ID | 5499 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
�� | +0.109 |
LEY | +0.097 |
YL | +0.091 |
AF | +0.089 |
SAM | +0.089 |
Neg logit contributions | |
jj | -0.073 |
sson | -0.072 |
andem | -0.068 |
zai | -0.064 |
hamm | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
�� | +0.096 |
LEY | +0.085 |
YL | +0.080 |
AF | +0.079 |
AH | +0.079 |
Neg logit contributions | |
jj | -0.061 |
sson | -0.059 |
andem | -0.056 |
zai | -0.052 |
hamm | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
�� | +0.425 |
LEY | +0.376 |
YL | +0.356 |
AF | +0.350 |
AH | +0.348 |
Neg logit contributions | |
jj | -0.293 |
sson | -0.288 |
andem | -0.273 |
zai | -0.256 |
hamm | -0.252 |
Token | care |
Token ID | 1337 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
jj | +1.833 |
sson | +1.793 |
andem | +1.680 |
zai | +1.602 |
hamm | +1.601 |
Neg logit contributions | |
�� | -2.517 |
LEY | -2.206 |
YL | -2.064 |
AF | -2.015 |
SAM | -2.014 |
Token | for |
Token ID | 329 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
jj | +0.107 |
sson | +0.105 |
andem | +0.099 |
zai | +0.094 |
hamm | +0.093 |
Neg logit contributions | |
�� | -0.145 |
LEY | -0.127 |
YL | -0.119 |
AF | -0.117 |
SAM | -0.116 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
�� | +3.544 |
LEY | +3.165 |
YL | +3.012 |
AF | +2.953 |
ICE | +2.940 |
Neg logit contributions | |
jj | -2.707 |
sson | -2.681 |
andem | -2.586 |
zai | -2.425 |
itle | -2.360 |
Token | being |
Token ID | 852 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
�� | +0.139 |
LEY | +0.122 |
YL | +0.115 |
AF | +0.113 |
SAM | +0.112 |
Neg logit contributions | |
jj | -0.094 |
sson | -0.093 |
andem | -0.087 |
zai | -0.082 |
hamm | -0.082 |
Token | used |
Token ID | 973 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
�� | +0.467 |
LEY | +0.409 |
YL | +0.381 |
AF | +0.373 |
SAM | +0.372 |
Neg logit contributions | |
jj | -0.402 |
sson | -0.394 |
andem | -0.373 |
zai | -0.356 |
hamm | -0.351 |
Token | in |
Token ID | 287 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
�� | +0.060 |
LEY | +0.053 |
YL | +0.050 |
AF | +0.049 |
SAM | +0.049 |
Neg logit contributions | |
jj | -0.042 |
sson | -0.041 |
andem | -0.039 |
zai | -0.037 |
hamm | -0.037 |
Token | studies |
Token ID | 3640 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
jj | +0.139 |
sson | +0.136 |
andem | +0.128 |
zai | +0.122 |
hamm | +0.121 |
Neg logit contributions | |
�� | -0.179 |
LEY | -0.157 |
YL | -0.147 |
AF | -0.144 |
SAM | -0.144 |
Token | u |
Token ID | 334 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
�� | +1.200 |
LEY | +1.065 |
YL | +1.009 |
AF | +0.992 |
SAM | +0.985 |
Neg logit contributions | |
jj | -0.777 |
sson | -0.755 |
andem | -0.714 |
zai | -0.672 |
hamm | -0.662 |
Token | = |
Token ID | 796 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
jj | +1.182 |
sson | +1.157 |
andem | +1.079 |
zai | +1.019 |
hamm | +1.015 |
Neg logit contributions | |
�� | -1.908 |
LEY | -1.685 |
YL | -1.590 |
AF | -1.556 |
SAM | -1.553 |
Token | [ |
Token ID | 685 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
�� | +1.536 |
LEY | +1.353 |
YL | +1.268 |
AF | +1.247 |
SAM | +1.241 |
Neg logit contributions | |
jj | -1.206 |
sson | -1.181 |
andem | -1.121 |
zai | -1.068 |
hamm | -1.054 |
Token | CO |
Token ID | 8220 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
�� | +1.135 |
LEY | +1.002 |
YL | +0.943 |
AF | +0.928 |
SAM | +0.922 |
Neg logit contributions | |
jj | -0.834 |
sson | -0.819 |
andem | -0.773 |
zai | -0.736 |
hamm | -0.731 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
�� | +2.320 |
LEY | +2.024 |
YL | +1.900 |
AF | +1.837 |
SAM | +1.833 |
Neg logit contributions | |
jj | -2.182 |
sson | -2.164 |
andem | -2.042 |
zai | -1.970 |
hamm | -1.942 |
Token | ] |
Token ID | 2361 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
�� | +1.050 |
LEY | +0.911 |
YL | +0.849 |
AF | +0.830 |
SAM | +0.825 |
Neg logit contributions | |
jj | -0.966 |
sson | -0.950 |
andem | -0.900 |
zai | -0.863 |
hamm | -0.855 |
Token | / |
Token ID | 14 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
�� | +3.728 |
LEY | +3.329 |
YL | +3.128 |
AF | +3.094 |
AH | +3.069 |
Neg logit contributions | |
jj | -2.561 |
sson | -2.516 |
andem | -2.370 |
zai | -2.254 |
hamm | -2.222 |
Token | f |
Token ID | 277 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
�� | +4.043 |
LEY | +3.593 |
YL | +3.352 |
AF | +3.330 |
SAM | +3.313 |
Neg logit contributions | |
jj | -3.417 |
sson | -3.409 |
andem | -3.259 |
zai | -3.125 |
hamm | -3.115 |
Token | absorbed |
Token ID | 19233 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
�� | +0.821 |
LEY | +0.720 |
YL | +0.676 |
AF | +0.664 |
SAM | +0.661 |
Neg logit contributions | |
jj | -0.612 |
sson | -0.598 |
andem | -0.565 |
zai | -0.537 |
hamm | -0.533 |
Token | be |
Token ID | 307 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
�� | +1.661 |
LEY | +1.463 |
YL | +1.374 |
AF | +1.354 |
AH | +1.342 |
Neg logit contributions | |
jj | -1.232 |
sson | -1.201 |
andem | -1.136 |
zai | -1.083 |
hamm | -1.072 |
Token | constant |
Token ID | 6937 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
�� | +3.575 |
LEY | +3.197 |
YL | +2.999 |
AF | +2.962 |
SAM | +2.928 |
Neg logit contributions | |
jj | -2.609 |
sson | -2.577 |
andem | -2.432 |
zai | -2.299 |
hamm | -2.286 |
Token | of |
Token ID | 286 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
�� | +0.915 |
LEY | +0.801 |
YL | +0.752 |
AF | +0.744 |
AH | +0.737 |
Neg logit contributions | |
jj | -0.680 |
sson | -0.668 |
andem | -0.629 |
zai | -0.596 |
hamm | -0.592 |
Token | publicity |
Token ID | 19403 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
jj | +0.821 |
sson | +0.805 |
andem | +0.759 |
zai | +0.721 |
hamm | +0.717 |
Neg logit contributions | |
�� | -1.091 |
LEY | -0.956 |
YL | -0.897 |
AF | -0.878 |
SAM | -0.874 |
Token | stunts |
Token ID | 49772 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
�� | +0.566 |
LEY | +0.497 |
YL | +0.467 |
AF | +0.457 |
AH | +0.455 |
Neg logit contributions | |
jj | -0.465 |
sson | -0.458 |
andem | -0.432 |
zai | -0.413 |
itle | -0.405 |
Token | promoting |
Token ID | 11560 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
�� | +0.827 |
LEY | +0.733 |
YL | +0.693 |
AF | +0.686 |
AH | +0.679 |
Neg logit contributions | |
jj | -0.608 |
sson | -0.596 |
andem | -0.565 |
zai | -0.532 |
itle | -0.527 |
Token | its |
Token ID | 663 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
�� | +0.900 |
LEY | +0.797 |
YL | +0.751 |
AF | +0.736 |
SAM | +0.732 |
Neg logit contributions | |
jj | -0.615 |
sson | -0.600 |
andem | -0.568 |
zai | -0.540 |
itle | -0.527 |
Token | new |
Token ID | 649 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
�� | +0.781 |
LEY | +0.689 |
YL | +0.642 |
AF | +0.632 |
SAM | +0.626 |
Neg logit contributions | |
jj | -0.636 |
sson | -0.622 |
andem | -0.589 |
zai | -0.566 |
itle | -0.555 |
Token | G |
Token ID | 402 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
�� | +1.423 |
LEY | +1.250 |
YL | +1.160 |
AF | +1.143 |
AH | +1.133 |
Neg logit contributions | |
jj | -1.195 |
sson | -1.155 |
andem | -1.110 |
zai | -1.064 |
itle | -1.041 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
�� | +0.838 |
LEY | +0.723 |
YL | +0.674 |
AF | +0.664 |
AH | +0.656 |
Neg logit contributions | |
jj | -0.823 |
sson | -0.809 |
andem | -0.775 |
zai | -0.743 |
hamm | -0.735 |
Token | smartphone |
Token ID | 11745 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
jj | +1.778 |
sson | +1.750 |
andem | +1.637 |
zai | +1.555 |
hamm | +1.552 |
Neg logit contributions | |
�� | -2.497 |
LEY | -2.190 |
YL | -2.056 |
AF | -2.008 |
SAM | -2.004 |
Token | after |
Token ID | 706 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
�� | +1.025 |
LEY | +0.903 |
YL | +0.853 |
AF | +0.838 |
AH | +0.832 |
Neg logit contributions | |
jj | -0.695 |
sson | -0.678 |
andem | -0.645 |
zai | -0.603 |
itle | -0.599 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
�� | +1.006 |
LEY | +0.888 |
YL | +0.834 |
AF | +0.817 |
AH | +0.812 |
Neg logit contributions | |
jj | -0.777 |
sson | -0.755 |
andem | -0.724 |
zai | -0.677 |
itle | -0.674 |
Token | May |
Token ID | 1737 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
�� | +0.870 |
LEY | +0.774 |
YL | +0.730 |
AF | +0.716 |
SAM | +0.714 |
Neg logit contributions | |
jj | -0.559 |
sson | -0.547 |
andem | -0.516 |
zai | -0.484 |
hamm | -0.480 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
�� | +1.418 |
LEY | +1.252 |
YL | +1.168 |
AF | +1.144 |
SAM | +1.138 |
Neg logit contributions | |
jj | -1.181 |
sson | -1.157 |
andem | -1.105 |
zai | -1.046 |
hamm | -1.040 |
Token | , |
Token ID | 11 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
jj | +0.189 |
sson | +0.186 |
andem | +0.170 |
zai | +0.161 |
hamm | +0.159 |
Neg logit contributions | |
�� | -0.339 |
LEY | -0.298 |
YL | -0.282 |
AF | -0.277 |
SAM | -0.276 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
jj | +0.241 |
sson | +0.234 |
andem | +0.213 |
zai | +0.195 |
hamm | +0.193 |
Neg logit contributions | |
�� | -0.639 |
LEY | -0.577 |
YL | -0.550 |
AF | -0.541 |
SAM | -0.539 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
jj | +0.905 |
sson | +0.883 |
andem | +0.821 |
zai | +0.776 |
hamm | +0.769 |
Neg logit contributions | |
�� | -1.614 |
LEY | -1.434 |
YL | -1.356 |
AF | -1.327 |
SAM | -1.327 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
�� | +1.346 |
LEY | +1.213 |
YL | +1.146 |
AF | +1.127 |
SAM | +1.122 |
Neg logit contributions | |
jj | -0.785 |
sson | -0.765 |
andem | -0.722 |
zai | -0.676 |
hamm | -0.673 |
Token | This |
Token ID | 1212 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
�� | +1.154 |
LEY | +1.014 |
YL | +0.943 |
AF | +0.930 |
AH | +0.926 |
Neg logit contributions | |
jj | -1.128 |
sson | -1.119 |
andem | -1.072 |
hamm | -1.018 |
zai | -1.016 |
Token | is |
Token ID | 318 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
�� | +0.428 |
LEY | +0.378 |
YL | +0.355 |
AF | +0.349 |
AH | +0.347 |
Neg logit contributions | |
jj | -0.290 |
sson | -0.284 |
andem | -0.267 |
zai | -0.252 |
hamm | -0.249 |
Token | meant |
Token ID | 4001 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
jj | +0.388 |
sson | +0.381 |
andem | +0.359 |
zai | +0.340 |
hamm | +0.336 |
Neg logit contributions | |
�� | -0.537 |
LEY | -0.473 |
YL | -0.443 |
AF | -0.435 |
SAM | -0.433 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
�� | +0.817 |
LEY | +0.719 |
YL | +0.676 |
AF | +0.671 |
AH | +0.662 |
Neg logit contributions | |
jj | -0.547 |
sson | -0.532 |
andem | -0.499 |
zai | -0.471 |
itle | -0.470 |
Token | underscore |
Token ID | 44810 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
jj | +0.101 |
sson | +0.099 |
andem | +0.094 |
zai | +0.090 |
itle | +0.088 |
Neg logit contributions | |
�� | -0.119 |
LEY | -0.104 |
YL | -0.098 |
AF | -0.096 |
SAM | -0.095 |
Token | ay |
Token ID | 323 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
�� | +1.806 |
LEY | +1.630 |
AF | +1.534 |
AH | +1.528 |
YL | +1.527 |
Neg logit contributions | |
jj | -1.208 |
sson | -1.193 |
andem | -1.104 |
zai | -1.056 |
hamm | -1.049 |
Token | ! |
Token ID | 0 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
�� | +1.068 |
LEY | +0.946 |
YL | +0.896 |
AF | +0.877 |
SAM | +0.873 |
Neg logit contributions | |
jj | -0.756 |
sson | -0.745 |
andem | -0.701 |
zai | -0.663 |
hamm | -0.657 |
Token | For |
Token ID | 1114 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
jj | +0.339 |
sson | +0.334 |
andem | +0.312 |
zai | +0.296 |
hamm | +0.293 |
Neg logit contributions | |
�� | -0.502 |
LEY | -0.443 |
YL | -0.418 |
AF | -0.409 |
SAM | -0.408 |
Token | free |
Token ID | 1479 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
�� | +0.446 |
LEY | +0.392 |
YL | +0.368 |
AF | +0.360 |
AH | +0.358 |
Neg logit contributions | |
jj | -0.327 |
sson | -0.320 |
andem | -0.301 |
zai | -0.286 |
hamm | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
�� | +0.381 |
LEY | +0.335 |
YL | +0.318 |
AF | +0.311 |
SAM | +0.310 |
Neg logit contributions | |
jj | -0.257 |
sson | -0.252 |
andem | -0.237 |
zai | -0.223 |
hamm | -0.221 |
Token | hur |
Token ID | 6990 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
jj | +0.328 |
sson | +0.322 |
andem | +0.304 |
zai | +0.289 |
hamm | +0.287 |
Neg logit contributions | |
�� | -0.424 |
LEY | -0.371 |
YL | -0.348 |
AF | -0.340 |
SAM | -0.338 |
Token | ray |
Token ID | 2433 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
�� | +1.681 |
LEY | +1.498 |
YL | +1.372 |
AH | +1.345 |
AF | +1.333 |
Neg logit contributions | |
sson | -1.729 |
jj | -1.728 |
andem | -1.633 |
zai | -1.556 |
hamm | -1.555 |
Token | ! |
Token ID | 0 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
�� | +0.513 |
LEY | +0.454 |
YL | +0.429 |
AF | +0.419 |
AH | +0.418 |
Neg logit contributions | |
jj | -0.356 |
sson | -0.351 |
andem | -0.330 |
zai | -0.312 |
itle | -0.309 |
Token | Your |
Token ID | 3406 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
�� | +0.912 |
LEY | +0.808 |
YL | +0.764 |
AF | +0.747 |
SAM | +0.744 |
Neg logit contributions | |
jj | -0.626 |
sson | -0.615 |
andem | -0.578 |
zai | -0.548 |
hamm | -0.541 |
Token | beloved |
Token ID | 14142 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
�� | +1.050 |
LEY | +0.920 |
YL | +0.867 |
AF | +0.849 |
SAM | +0.847 |
Neg logit contributions | |
jj | -0.800 |
sson | -0.782 |
andem | -0.745 |
zai | -0.707 |
hamm | -0.695 |
Token | lic |
Token ID | 3476 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
jj | +0.068 |
sson | +0.067 |
andem | +0.063 |
zai | +0.060 |
hamm | +0.060 |
Neg logit contributions | |
�� | -0.081 |
LEY | -0.071 |
YL | -0.066 |
AF | -0.065 |
SAM | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
�� | +0.838 |
LEY | +0.737 |
YL | +0.697 |
AF | +0.686 |
AH | +0.679 |
Neg logit contributions | |
jj | -0.591 |
sson | -0.582 |
andem | -0.555 |
zai | -0.518 |
itle | -0.510 |
Token | their |
Token ID | 511 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
jj | +0.270 |
sson | +0.265 |
andem | +0.251 |
zai | +0.237 |
hamm | +0.235 |
Neg logit contributions | |
�� | -0.360 |
LEY | -0.316 |
YL | -0.297 |
AF | -0.291 |
AH | -0.289 |
Token | battles |
Token ID | 10181 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
�� | +0.911 |
LEY | +0.803 |
YL | +0.754 |
AF | +0.741 |
SAM | +0.735 |
Neg logit contributions | |
jj | -0.652 |
sson | -0.641 |
andem | -0.602 |
zai | -0.572 |
itle | -0.563 |
Token | are |
Token ID | 389 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
�� | +0.981 |
LEY | +0.860 |
YL | +0.805 |
AF | +0.795 |
AH | +0.790 |
Neg logit contributions | |
jj | -0.725 |
sson | -0.710 |
andem | -0.670 |
zai | -0.637 |
hamm | -0.632 |
Token | all |
Token ID | 477 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
jj | +0.891 |
sson | +0.874 |
andem | +0.823 |
zai | +0.783 |
hamm | +0.778 |
Neg logit contributions | |
�� | -1.183 |
LEY | -1.036 |
YL | -0.972 |
AF | -0.951 |
SAM | -0.947 |
Token | uphill |
Token ID | 35256 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
jj | +0.036 |
sson | +0.035 |
andem | +0.033 |
zai | +0.032 |
itle | +0.031 |
Neg logit contributions | |
�� | -0.047 |
LEY | -0.041 |
YL | -0.039 |
AF | -0.038 |
AH | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
�� | +0.701 |
LEY | +0.620 |
YL | +0.584 |
AF | +0.577 |
AH | +0.569 |
Neg logit contributions | |
jj | -0.473 |
sson | -0.463 |
andem | -0.437 |
zai | -0.414 |
hamm | -0.411 |
Token | Democrats |
Token ID | 4956 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
jj | +0.205 |
sson | +0.201 |
andem | +0.189 |
zai | +0.178 |
hamm | +0.177 |
Neg logit contributions | |
�� | -0.316 |
LEY | -0.280 |
YL | -0.264 |
AF | -0.259 |
SAM | -0.258 |
Token | now |
Token ID | 783 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
�� | +0.504 |
LEY | +0.440 |
YL | +0.412 |
AF | +0.405 |
AH | +0.402 |
Neg logit contributions | |
jj | -0.401 |
sson | -0.394 |
andem | -0.373 |
zai | -0.354 |
hamm | -0.351 |
Token | are |
Token ID | 389 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
�� | +1.114 |
LEY | +0.957 |
YL | +0.891 |
AF | +0.875 |
AH | +0.868 |
Neg logit contributions | |
jj | -1.082 |
sson | -1.065 |
andem | -1.013 |
zai | -0.966 |
hamm | -0.959 |
Token | struggling |
Token ID | 9648 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
�� | +0.683 |
LEY | +0.598 |
YL | +0.561 |
AF | +0.551 |
SAM | +0.547 |
Neg logit contributions | |
jj | -0.527 |
sson | -0.518 |
andem | -0.488 |
zai | -0.463 |
hamm | -0.459 |
Token | non |
Token ID | 1729 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
�� | +1.226 |
LEY | +1.059 |
YL | +0.991 |
AF | +0.969 |
AH | +0.960 |
Neg logit contributions | |
jj | -1.128 |
sson | -1.100 |
andem | -1.047 |
zai | -1.003 |
itle | -0.990 |
Token | - |
Token ID | 12 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
�� | +1.490 |
LEY | +1.304 |
YL | +1.234 |
AF | +1.217 |
SAM | +1.204 |
Neg logit contributions | |
jj | -1.032 |
sson | -1.008 |
andem | -0.946 |
zai | -0.902 |
hamm | -0.890 |
Token | native |
Token ID | 30191 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
�� | +0.676 |
LEY | +0.584 |
YL | +0.542 |
AF | +0.536 |
SAM | +0.530 |
Neg logit contributions | |
jj | -0.727 |
sson | -0.714 |
andem | -0.683 |
hamm | -0.655 |
zai | -0.654 |
Token | , |
Token ID | 11 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
�� | +2.830 |
LEY | +2.471 |
YL | +2.318 |
AF | +2.265 |
SAM | +2.222 |
Neg logit contributions | |
jj | -2.652 |
sson | -2.557 |
andem | -2.483 |
zai | -2.355 |
itle | -2.301 |
Token | wildlife |
Token ID | 15599 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
�� | +0.303 |
LEY | +0.266 |
YL | +0.250 |
AF | +0.244 |
SAM | +0.243 |
Neg logit contributions | |
jj | -0.231 |
sson | -0.226 |
andem | -0.214 |
zai | -0.203 |
itle | -0.200 |
Token | habitats |
Token ID | 35308 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
�� | +1.195 |
LEY | +1.049 |
YL | +0.987 |
AF | +0.970 |
AH | +0.964 |
Neg logit contributions | |
jj | -0.851 |
sson | -0.829 |
andem | -0.788 |
zai | -0.744 |
itle | -0.732 |
Token | and |
Token ID | 290 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
�� | +2.232 |
LEY | +1.974 |
YL | +1.869 |
AF | +1.833 |
AH | +1.819 |
Neg logit contributions | |
jj | -1.522 |
sson | -1.480 |
andem | -1.402 |
zai | -1.326 |
itle | -1.299 |
Token | urban |
Token ID | 7876 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
�� | +0.503 |
LEY | +0.440 |
YL | +0.414 |
AF | +0.405 |
AH | +0.402 |
Neg logit contributions | |
jj | -0.396 |
sson | -0.388 |
andem | -0.369 |
zai | -0.350 |
itle | -0.345 |
Token | environments |
Token ID | 12493 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
�� | +0.113 |
LEY | +0.099 |
YL | +0.093 |
AF | +0.092 |
AH | +0.091 |
Neg logit contributions | |
jj | -0.083 |
sson | -0.081 |
andem | -0.077 |
zai | -0.073 |
hamm | -0.072 |
Token | can |
Token ID | 460 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
�� | +0.945 |
LEY | +0.835 |
YL | +0.791 |
AF | +0.777 |
AH | +0.771 |
Neg logit contributions | |
jj | -0.615 |
sson | -0.599 |
andem | -0.564 |
zai | -0.534 |
itle | -0.523 |
Token | not |
Token ID | 407 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
�� | +0.063 |
LEY | +0.056 |
YL | +0.052 |
AF | +0.051 |
AH | +0.051 |
Neg logit contributions | |
jj | -0.046 |
sson | -0.045 |
andem | -0.043 |
zai | -0.041 |
hamm | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
jj | +0.589 |
sson | +0.577 |
andem | +0.540 |
zai | +0.510 |
hamm | +0.505 |
Neg logit contributions | |
�� | -0.936 |
LEY | -0.831 |
YL | -0.783 |
AF | -0.768 |
SAM | -0.764 |
Token | players |
Token ID | 1938 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
jj | +0.506 |
sson | +0.497 |
andem | +0.469 |
zai | +0.447 |
hamm | +0.444 |
Neg logit contributions | |
�� | -0.636 |
LEY | -0.556 |
YL | -0.520 |
AF | -0.509 |
SAM | -0.507 |
Token | involved |
Token ID | 2950 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
jj | +0.144 |
sson | +0.141 |
andem | +0.132 |
zai | +0.125 |
hamm | +0.124 |
Neg logit contributions | |
�� | -0.209 |
LEY | -0.185 |
YL | -0.174 |
AF | -0.171 |
SAM | -0.170 |
Token | might |
Token ID | 1244 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
�� | +0.868 |
LEY | +0.776 |
YL | +0.725 |
AF | +0.717 |
AH | +0.708 |
Neg logit contributions | |
jj | -0.613 |
sson | -0.598 |
andem | -0.567 |
zai | -0.533 |
itle | -0.527 |
Token | imply |
Token ID | 20135 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
jj | +0.166 |
sson | +0.162 |
andem | +0.154 |
zai | +0.146 |
hamm | +0.144 |
Neg logit contributions | |
�� | -0.196 |
LEY | -0.172 |
YL | -0.161 |
AF | -0.159 |
SAM | -0.156 |
Token | something |
Token ID | 1223 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
jj | +0.934 |
sson | +0.914 |
andem | +0.856 |
zai | +0.804 |
hamm | +0.794 |
Neg logit contributions | |
�� | -1.576 |
LEY | -1.402 |
YL | -1.326 |
AF | -1.300 |
SAM | -1.294 |
Token | may |
Token ID | 743 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
jj | +0.103 |
sson | +0.101 |
andem | +0.096 |
zai | +0.089 |
itle | +0.087 |
Neg logit contributions | |
�� | -0.149 |
LEY | -0.133 |
YL | -0.126 |
AF | -0.123 |
AH | -0.122 |
Token | be |
Token ID | 307 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
jj | +0.150 |
sson | +0.147 |
andem | +0.140 |
zai | +0.134 |
hamm | +0.132 |
Neg logit contributions | |
�� | -0.157 |
LEY | -0.137 |
YL | -0.128 |
AF | -0.125 |
AH | -0.124 |
Token | in |
Token ID | 287 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
jj | +0.175 |
sson | +0.171 |
andem | +0.161 |
zai | +0.153 |
hamm | +0.151 |
Neg logit contributions | |
�� | -0.240 |
LEY | -0.212 |
YL | -0.199 |
AF | -0.195 |
SAM | -0.194 |
Token | the |
Token ID | 262 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
�� | +0.299 |
LEY | +0.259 |
YL | +0.242 |
AF | +0.236 |
AH | +0.235 |
Neg logit contributions | |
jj | -0.272 |
sson | -0.268 |
andem | -0.254 |
zai | -0.242 |
hamm | -0.240 |
Token | works |
Token ID | 2499 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
�� | +0.297 |
LEY | +0.260 |
YL | +0.246 |
AF | +0.240 |
SAM | +0.239 |
Neg logit contributions | |
jj | -0.217 |
sson | -0.214 |
andem | -0.201 |
zai | -0.192 |
hamm | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
jj | +1.401 |
sson | +1.373 |
andem | +1.286 |
zai | +1.219 |
hamm | +1.214 |
Neg logit contributions | |
�� | -2.153 |
LEY | -1.900 |
YL | -1.787 |
AF | -1.750 |
SAM | -1.743 |
Token | So |
Token ID | 1406 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
jj | +0.816 |
sson | +0.801 |
andem | +0.755 |
zai | +0.719 |
hamm | +0.715 |
Neg logit contributions | |
�� | -1.055 |
LEY | -0.922 |
YL | -0.864 |
AF | -0.845 |
SAM | -0.842 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
jj | +0.287 |
sson | +0.282 |
andem | +0.265 |
zai | +0.248 |
hamm | +0.247 |
Neg logit contributions | |
�� | -0.435 |
LEY | -0.384 |
YL | -0.363 |
AF | -0.356 |
SAM | -0.354 |
Token | you |
Token ID | 345 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
jj | +0.545 |
sson | +0.535 |
andem | +0.506 |
zai | +0.478 |
hamm | +0.475 |
Neg logit contributions | |
�� | -0.710 |
LEY | -0.622 |
YL | -0.586 |
AF | -0.573 |
SAM | -0.570 |
Token | need |
Token ID | 761 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
�� | +0.238 |
LEY | +0.207 |
YL | +0.195 |
AF | +0.192 |
SAM | +0.191 |
Neg logit contributions | |
jj | -0.208 |
sson | -0.204 |
andem | -0.195 |
zai | -0.183 |
itle | -0.181 |
Token | to |
Token ID | 284 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
�� | +0.463 |
LEY | +0.405 |
YL | +0.386 |
AF | +0.380 |
SAM | +0.377 |
Neg logit contributions | |
jj | -0.328 |
sson | -0.325 |
andem | -0.307 |
zai | -0.288 |
itle | -0.284 |
Token | have |
Token ID | 423 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
jj | +0.396 |
sson | +0.389 |
andem | +0.369 |
zai | +0.350 |
hamm | +0.347 |
Neg logit contributions | |
�� | -0.456 |
LEY | -0.396 |
YL | -0.375 |
AF | -0.366 |
SAM | -0.364 |
Token | Node |
Token ID | 19081 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
�� | +0.182 |
LEY | +0.159 |
YL | +0.151 |
AF | +0.148 |
SAM | +0.148 |
Neg logit contributions | |
jj | -0.130 |
sson | -0.129 |
andem | -0.121 |
zai | -0.114 |
hamm | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
jj | +0.813 |
sson | +0.798 |
andem | +0.750 |
zai | +0.713 |
hamm | +0.708 |
Neg logit contributions | |
�� | -1.139 |
LEY | -0.999 |
YL | -0.941 |
AF | -0.922 |
SAM | -0.917 |
Token | js |
Token ID | 8457 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
jj | +0.507 |
sson | +0.487 |
andem | +0.437 |
zai | +0.398 |
hamm | +0.392 |
Neg logit contributions | |
�� | -1.566 |
LEY | -1.420 |
YL | -1.353 |
AF | -1.329 |
SAM | -1.328 |
Token | and |
Token ID | 290 |
Feature activation | +8.33e-03 |
Pos logit contributions | |
jj | +0.637 |
sson | +0.625 |
andem | +0.589 |
zai | +0.560 |
hamm | +0.558 |
Neg logit contributions | |
�� | -0.843 |
LEY | -0.738 |
YL | -0.692 |
AF | -0.676 |
SAM | -0.674 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
jj | +1.081 |
sson | +1.060 |
andem | +0.991 |
zai | +0.942 |
hamm | +0.941 |
Neg logit contributions | |
�� | -1.603 |
LEY | -1.409 |
YL | -1.324 |
AF | -1.293 |
SAM | -1.291 |
Token | cubes |
Token ID | 34896 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
jj | +0.699 |
sson | +0.686 |
andem | +0.645 |
hamm | +0.620 |
zai | +0.616 |
Neg logit contributions | |
�� | -0.877 |
LEY | -0.762 |
YL | -0.713 |
AH | -0.692 |
AF | -0.692 |
Token | at |
Token ID | 265 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
�� | +0.016 |
LEY | +0.014 |
YL | +0.013 |
AF | +0.013 |
SAM | +0.012 |
Neg logit contributions | |
jj | -0.019 |
sson | -0.019 |
andem | -0.018 |
zai | -0.017 |
hamm | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
�� | +0.782 |
LEY | +0.691 |
YL | +0.651 |
AF | +0.639 |
SAM | +0.636 |
Neg logit contributions | |
jj | -0.515 |
sson | -0.503 |
andem | -0.472 |
zai | -0.447 |
hamm | -0.443 |
Token | This |
Token ID | 770 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
jj | +0.355 |
sson | +0.350 |
andem | +0.325 |
zai | +0.310 |
hamm | +0.307 |
Neg logit contributions | |
�� | -0.540 |
LEY | -0.474 |
YL | -0.445 |
AF | -0.436 |
SAM | -0.435 |
Token | is |
Token ID | 318 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
�� | +0.458 |
LEY | +0.405 |
YL | +0.382 |
AF | +0.375 |
SAM | +0.373 |
Neg logit contributions | |
jj | -0.294 |
sson | -0.287 |
andem | -0.270 |
zai | -0.254 |
hamm | -0.252 |
Token | simply |
Token ID | 2391 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
�� | +0.093 |
LEY | +0.083 |
YL | +0.078 |
AF | +0.077 |
SAM | +0.076 |
Neg logit contributions | |
jj | -0.063 |
sson | -0.061 |
andem | -0.058 |
zai | -0.055 |
hamm | -0.054 |
Token | one |
Token ID | 530 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
�� | +1.487 |
LEY | +1.328 |
YL | +1.241 |
AF | +1.222 |
AH | +1.211 |
Neg logit contributions | |
jj | -1.100 |
sson | -1.076 |
andem | -1.023 |
zai | -0.957 |
itle | -0.951 |
Token | possible |
Token ID | 1744 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
�� | +0.880 |
LEY | +0.774 |
YL | +0.727 |
AF | +0.713 |
SAM | +0.709 |
Neg logit contributions | |
jj | -0.651 |
sson | -0.637 |
andem | -0.600 |
zai | -0.568 |
hamm | -0.562 |
Token | option |
Token ID | 3038 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
jj | +0.377 |
sson | +0.373 |
andem | +0.355 |
zai | +0.342 |
hamm | +0.342 |
Neg logit contributions | |
�� | -0.319 |
LEY | -0.269 |
YL | -0.247 |
AF | -0.239 |
SAM | -0.239 |
Token | among |
Token ID | 1871 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
jj | +0.355 |
sson | +0.348 |
andem | +0.325 |
zai | +0.307 |
hamm | +0.305 |
Neg logit contributions | |
�� | -0.562 |
LEY | -0.497 |
YL | -0.469 |
AF | -0.459 |
SAM | -0.458 |
Token | out |
Token ID | 503 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
jj | +0.274 |
sson | +0.269 |
andem | +0.256 |
zai | +0.243 |
hamm | +0.242 |
Neg logit contributions | |
�� | -0.314 |
LEY | -0.273 |
YL | -0.255 |
AF | -0.249 |
AH | -0.247 |
Token | to |
Token ID | 284 |
Feature activation | +8.62e-03 |
Pos logit contributions | |
�� | +0.086 |
LEY | +0.076 |
YL | +0.071 |
AF | +0.070 |
AH | +0.070 |
Neg logit contributions | |
jj | -0.062 |
sson | -0.060 |
andem | -0.057 |
zai | -0.054 |
hamm | -0.053 |
Token | you |
Token ID | 345 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
�� | +0.050 |
LEY | +0.044 |
YL | +0.041 |
AF | +0.040 |
AH | +0.040 |
Neg logit contributions | |
jj | -0.039 |
sson | -0.038 |
andem | -0.036 |
zai | -0.034 |
hamm | -0.034 |
Token | ? |
Token ID | 30 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
jj | +0.248 |
sson | +0.242 |
andem | +0.228 |
zai | +0.216 |
hamm | +0.215 |
Neg logit contributions | |
�� | -0.352 |
LEY | -0.310 |
YL | -0.292 |
AF | -0.286 |
SAM | -0.284 |
Token | � |
Token ID | 447 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
jj | +0.047 |
sson | +0.046 |
andem | +0.044 |
zai | +0.042 |
hamm | +0.041 |
Neg logit contributions | |
�� | -0.063 |
LEY | -0.056 |
YL | -0.052 |
AF | -0.051 |
AH | -0.051 |
Token | � |
Token ID | 251 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
jj | +0.895 |
sson | +0.885 |
andem | +0.848 |
zai | +0.810 |
hamm | +0.808 |
Neg logit contributions | |
�� | -0.755 |
LEY | -0.631 |
YL | -0.580 |
AF | -0.562 |
AH | -0.560 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
jj | +0.552 |
sson | +0.541 |
andem | +0.508 |
zai | +0.481 |
hamm | +0.478 |
Neg logit contributions | |
�� | -0.823 |
LEY | -0.726 |
YL | -0.684 |
AF | -0.670 |
SAM | -0.667 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
jj | +0.956 |
sson | +0.940 |
andem | +0.843 |
zai | +0.802 |
hamm | +0.791 |
Neg logit contributions | |
�� | -1.927 |
LEY | -1.682 |
YL | -1.593 |
�� | -1.559 |
SAM | -1.557 |
Token | Doctors |
Token ID | 47087 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
jj | +0.697 |
sson | +0.685 |
andem | +0.649 |
zai | +0.621 |
hamm | +0.617 |
Neg logit contributions | |
�� | -0.752 |
LEY | -0.647 |
YL | -0.602 |
AF | -0.587 |
SAM | -0.585 |
Token | have |
Token ID | 423 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
jj | +1.090 |
sson | +1.070 |
andem | +1.006 |
zai | +0.958 |
hamm | +0.953 |
Neg logit contributions | |
�� | -1.462 |
LEY | -1.279 |
YL | -1.202 |
AF | -1.174 |
SAM | -1.171 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
�� | +0.056 |
LEY | +0.049 |
YL | +0.046 |
AF | +0.045 |
AH | +0.045 |
Neg logit contributions | |
jj | -0.042 |
sson | -0.041 |
andem | -0.039 |
zai | -0.037 |
itle | -0.037 |
Token | meant |
Token ID | 4001 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
jj | +0.383 |
sson | +0.371 |
andem | +0.345 |
zai | +0.325 |
hamm | +0.321 |
Neg logit contributions | |
�� | -0.682 |
LEY | -0.608 |
YL | -0.577 |
AF | -0.568 |
AH | -0.565 |
Token | to |
Token ID | 284 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
�� | +0.274 |
LEY | +0.241 |
YL | +0.227 |
AF | +0.224 |
SAM | +0.223 |
Neg logit contributions | |
jj | -0.186 |
sson | -0.182 |
andem | -0.171 |
zai | -0.162 |
itle | -0.161 |
Token | work |
Token ID | 670 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
jj | +0.393 |
sson | +0.384 |
andem | +0.363 |
zai | +0.344 |
hamm | +0.340 |
Neg logit contributions | |
�� | -0.507 |
LEY | -0.445 |
YL | -0.418 |
AF | -0.410 |
SAM | -0.408 |
Token | together |
Token ID | 1978 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
jj | +1.246 |
sson | +1.224 |
andem | +1.149 |
zai | +1.089 |
hamm | +1.088 |
Neg logit contributions | |
�� | -1.861 |
LEY | -1.636 |
YL | -1.534 |
AF | -1.501 |
SAM | -1.500 |
Token | : |
Token ID | 25 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
jj | +0.087 |
sson | +0.084 |
andem | +0.079 |
zai | +0.074 |
hamm | +0.074 |
Neg logit contributions | |
�� | -0.143 |
LEY | -0.128 |
YL | -0.121 |
AF | -0.119 |
SAM | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
�� | +0.843 |
LEY | +0.749 |
YL | +0.705 |
AF | +0.696 |
SAM | +0.691 |
Neg logit contributions | |
jj | -0.567 |
sson | -0.548 |
andem | -0.515 |
zai | -0.487 |
itle | -0.479 |
Token |
|
Token ID | 198 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
jj | +0.169 |
sson | +0.166 |
andem | +0.153 |
zai | +0.144 |
hamm | +0.143 |
Neg logit contributions | |
�� | -0.316 |
LEY | -0.280 |
YL | -0.265 |
AF | -0.260 |
SAM | -0.259 |
Token | Own |
Token ID | 23858 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
�� | +0.521 |
LEY | +0.461 |
YL | +0.433 |
AF | +0.429 |
SAM | +0.426 |
Neg logit contributions | |
jj | -0.398 |
sson | -0.391 |
andem | -0.370 |
hamm | -0.353 |
zai | -0.351 |
Token | ed |
Token ID | 276 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
�� | +0.109 |
LEY | +0.096 |
YL | +0.090 |
AF | +0.088 |
SAM | +0.088 |
Neg logit contributions | |
jj | -0.080 |
sson | -0.078 |
andem | -0.074 |
zai | -0.070 |
hamm | -0.070 |
Token | < |
Token ID | 27 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
jj | +0.760 |
sson | +0.744 |
andem | +0.701 |
zai | +0.666 |
hamm | +0.659 |
Neg logit contributions | |
�� | -1.038 |
LEY | -0.913 |
YL | -0.858 |
AF | -0.840 |
SAM | -0.838 |
Token | T |
Token ID | 51 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
jj | +0.558 |
sson | +0.549 |
andem | +0.520 |
zai | +0.496 |
hamm | +0.495 |
Neg logit contributions | |
�� | -0.646 |
LEY | -0.562 |
YL | -0.525 |
AF | -0.515 |
SAM | -0.512 |
Token | op |
Token ID | 404 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
�� | +0.792 |
LEY | +0.704 |
YL | +0.663 |
AF | +0.653 |
AH | +0.650 |
Neg logit contributions | |
jj | -0.543 |
sson | -0.537 |
andem | -0.503 |
hamm | -0.478 |
zai | -0.473 |
Token | ā |
Token ID | 10235 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
jj | +0.350 |
sson | +0.345 |
andem | +0.320 |
zai | +0.301 |
hamm | +0.301 |
Neg logit contributions | |
�� | -0.585 |
LEY | -0.520 |
YL | -0.490 |
AF | -0.486 |
AH | -0.484 |
Token | p |
Token ID | 79 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
jj | +0.341 |
sson | +0.336 |
andem | +0.316 |
hamm | +0.294 |
zai | +0.292 |
Neg logit contributions | |
�� | -0.577 |
LEY | -0.515 |
YL | -0.484 |
AF | -0.478 |
SAM | -0.476 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
jj | +1.151 |
sson | +1.125 |
andem | +1.044 |
zai | +0.980 |
hamm | +0.973 |
Neg logit contributions | |
�� | -2.146 |
LEY | -1.913 |
YL | -1.811 |
AF | -1.778 |
SAM | -1.772 |
Token | m |
Token ID | 285 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
jj | +0.628 |
sson | +0.617 |
andem | +0.578 |
zai | +0.545 |
hamm | +0.542 |
Neg logit contributions | |
�� | -0.935 |
LEY | -0.827 |
YL | -0.778 |
AF | -0.764 |
AH | -0.760 |
Token | ai |
Token ID | 1872 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
jj | +0.596 |
sson | +0.587 |
andem | +0.548 |
zai | +0.518 |
hamm | +0.516 |
Neg logit contributions | |
�� | -0.898 |
LEY | -0.796 |
YL | -0.748 |
AF | -0.737 |
AH | -0.734 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
jj | +2.248 |
sson | +2.196 |
andem | +2.071 |
zai | +1.975 |
hamm | +1.969 |
Neg logit contributions | |
�� | -3.224 |
LEY | -2.827 |
YL | -2.661 |
AF | -2.594 |
SAM | -2.590 |
Token | Hal |
Token ID | 11023 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
jj | +0.835 |
sson | +0.820 |
andem | +0.770 |
zai | +0.729 |
hamm | +0.724 |
Neg logit contributions | |
�� | -1.207 |
LEY | -1.064 |
YL | -1.001 |
AF | -0.981 |
SAM | -0.977 |
Token | ep |
Token ID | 538 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
jj | +1.762 |
sson | +1.723 |
andem | +1.612 |
zai | +1.522 |
hamm | +1.509 |
Neg logit contributions | |
�� | -2.858 |
LEY | -2.527 |
YL | -2.387 |
AF | -2.337 |
SAM | -2.332 |
Token | ā |
Token ID | 10235 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
jj | +1.336 |
sson | +1.308 |
andem | +1.219 |
zai | +1.146 |
hamm | +1.142 |
Neg logit contributions | |
�� | -2.284 |
LEY | -2.029 |
YL | -1.916 |
AF | -1.883 |
AH | -1.874 |
Token | iw |
Token ID | 14246 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
jj | +0.225 |
sson | +0.222 |
andem | +0.206 |
hamm | +0.181 |
zai | +0.180 |
Neg logit contributions | |
�� | -0.648 |
LEY | -0.589 |
YL | -0.559 |
AF | -0.551 |
AH | -0.551 |
Token | is |
Token ID | 318 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
jj | +0.261 |
sson | +0.254 |
andem | +0.240 |
zai | +0.223 |
itle | +0.221 |
Neg logit contributions | |
�� | -0.433 |
LEY | -0.385 |
YL | -0.366 |
AF | -0.359 |
AH | -0.356 |
Token | clear |
Token ID | 1598 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
�� | +0.696 |
LEY | +0.613 |
YL | +0.576 |
AF | +0.563 |
AH | +0.560 |
Neg logit contributions | |
jj | -0.537 |
sson | -0.528 |
andem | -0.502 |
zai | -0.474 |
hamm | -0.467 |
Token | that |
Token ID | 326 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
�� | +0.150 |
LEY | +0.133 |
YL | +0.125 |
AF | +0.123 |
SAM | +0.122 |
Neg logit contributions | |
jj | -0.094 |
sson | -0.092 |
andem | -0.087 |
zai | -0.081 |
hamm | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
jj | +0.401 |
sson | +0.395 |
andem | +0.374 |
zai | +0.352 |
hamm | +0.348 |
Neg logit contributions | |
�� | -0.524 |
LEY | -0.463 |
YL | -0.434 |
AF | -0.424 |
AH | -0.421 |
Token | some |
Token ID | 617 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
jj | +0.827 |
sson | +0.811 |
andem | +0.762 |
zai | +0.724 |
hamm | +0.719 |
Neg logit contributions | |
�� | -1.162 |
LEY | -1.021 |
YL | -0.960 |
AF | -0.940 |
SAM | -0.936 |
Token | large |
Token ID | 1588 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
jj | +1.290 |
sson | +1.267 |
andem | +1.199 |
zai | +1.145 |
hamm | +1.139 |
Neg logit contributions | |
�� | -1.506 |
LEY | -1.307 |
YL | -1.221 |
AF | -1.192 |
SAM | -1.188 |
Token | extent |
Token ID | 6287 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
jj | +1.871 |
sson | +1.825 |
andem | +1.714 |
hamm | +1.636 |
zai | +1.635 |
Neg logit contributions | |
�� | -2.617 |
LEY | -2.291 |
YL | -2.155 |
AF | -2.106 |
SAM | -2.105 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
jj | +0.885 |
sson | +0.871 |
andem | +0.822 |
zai | +0.775 |
hamm | +0.766 |
Neg logit contributions | |
�� | -1.223 |
LEY | -1.080 |
YL | -1.015 |
AF | -0.992 |
AH | -0.987 |
Token | controversy |
Token ID | 10386 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
jj | +0.551 |
sson | +0.542 |
andem | +0.512 |
zai | +0.489 |
hamm | +0.485 |
Neg logit contributions | |
�� | -0.644 |
LEY | -0.561 |
YL | -0.524 |
AF | -0.512 |
SAM | -0.509 |
Token | between |
Token ID | 1022 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
�� | +0.926 |
LEY | +0.815 |
YL | +0.767 |
AF | +0.753 |
AH | +0.750 |
Neg logit contributions | |
jj | -0.774 |
sson | -0.757 |
andem | -0.719 |
zai | -0.681 |
itle | -0.675 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
jj | +0.497 |
sson | +0.488 |
andem | +0.458 |
zai | +0.434 |
hamm | +0.427 |
Neg logit contributions | |
�� | -0.723 |
LEY | -0.639 |
YL | -0.601 |
AF | -0.588 |
AH | -0.584 |
Token | would |
Token ID | 561 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
jj | +0.383 |
sson | +0.375 |
andem | +0.348 |
zai | +0.327 |
hamm | +0.326 |
Neg logit contributions | |
�� | -0.696 |
LEY | -0.619 |
YL | -0.585 |
AF | -0.573 |
SAM | -0.572 |
Token | like |
Token ID | 588 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
jj | +0.214 |
sson | +0.210 |
andem | +0.196 |
zai | +0.185 |
hamm | +0.184 |
Neg logit contributions | |
�� | -0.340 |
LEY | -0.300 |
YL | -0.283 |
AF | -0.277 |
SAM | -0.277 |
Token | to |
Token ID | 284 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
�� | +0.654 |
LEY | +0.576 |
YL | +0.544 |
SAM | +0.532 |
AF | +0.531 |
Neg logit contributions | |
jj | -0.385 |
sson | -0.379 |
andem | -0.349 |
zai | -0.333 |
hamm | -0.330 |
Token | remind |
Token ID | 7101 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
jj | +1.512 |
sson | +1.486 |
andem | +1.410 |
zai | +1.360 |
hamm | +1.356 |
Neg logit contributions | |
�� | -1.786 |
LEY | -1.518 |
YL | -1.425 |
AH | -1.401 |
SAM | -1.386 |
Token | you |
Token ID | 345 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
jj | +2.377 |
sson | +2.344 |
andem | +2.135 |
hamm | +2.082 |
zai | +2.073 |
Neg logit contributions | |
�� | -3.296 |
LEY | -2.835 |
YL | -2.622 |
AH | -2.574 |
�� | -2.571 |
Token | once |
Token ID | 1752 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
jj | +1.767 |
sson | +1.735 |
andem | +1.586 |
zai | +1.495 |
hamm | +1.489 |
Neg logit contributions | |
�� | -3.526 |
LEY | -3.131 |
YL | -2.972 |
AF | -2.920 |
AH | -2.916 |
Token | again |
Token ID | 757 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
jj | +1.790 |
sson | +1.742 |
andem | +1.590 |
zai | +1.496 |
hamm | +1.493 |
Neg logit contributions | |
�� | -3.668 |
LEY | -3.240 |
YL | -3.066 |
AF | -3.048 |
AH | -3.032 |
Token | that |
Token ID | 326 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
jj | +1.699 |
sson | +1.679 |
andem | +1.487 |
zai | +1.415 |
hamm | +1.412 |
Neg logit contributions | |
�� | -3.982 |
LEY | -3.544 |
YL | -3.340 |
AH | -3.270 |
SAM | -3.270 |
Token | the |
Token ID | 262 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
jj | +1.564 |
sson | +1.554 |
andem | +1.379 |
zai | +1.326 |
hamm | +1.323 |
Neg logit contributions | |
�� | -3.302 |
LEY | -2.921 |
YL | -2.753 |
SAM | -2.711 |
AF | -2.698 |
Token | old |
Token ID | 1468 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
�� | +0.129 |
LEY | +0.108 |
YL | +0.099 |
AF | +0.096 |
SAM | +0.096 |
Neg logit contributions | |
jj | -0.159 |
sson | -0.157 |
andem | -0.150 |
zai | -0.144 |
hamm | -0.144 |
Token | address |
Token ID | 2209 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
�� | +0.028 |
LEY | +0.023 |
YL | +0.021 |
SAM | +0.021 |
AF | +0.021 |
Neg logit contributions | |
jj | -0.034 |
sson | -0.033 |
andem | -0.032 |
zai | -0.031 |
hamm | -0.031 |
Token | S |
Token ID | 311 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
�� | +0.115 |
LEY | +0.102 |
YL | +0.095 |
AF | +0.093 |
SAM | +0.093 |
Neg logit contributions | |
jj | -0.083 |
sson | -0.081 |
andem | -0.076 |
zai | -0.072 |
hamm | -0.072 |
Token | ada |
Token ID | 4763 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
jj | +1.231 |
sson | +1.210 |
andem | +1.147 |
zai | +1.097 |
hamm | +1.091 |
Neg logit contributions | |
�� | -1.343 |
LEY | -1.159 |
YL | -1.080 |
AF | -1.053 |
SAM | -1.050 |
Token | o |
Token ID | 78 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
jj | +0.948 |
sson | +0.930 |
andem | +0.875 |
zai | +0.831 |
hamm | +0.827 |
Neg logit contributions | |
�� | -1.297 |
LEY | -1.138 |
YL | -1.068 |
AF | -1.045 |
SAM | -1.042 |
Token | Turner |
Token ID | 15406 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
jj | +1.524 |
sson | +1.496 |
andem | +1.400 |
zai | +1.338 |
hamm | +1.328 |
Neg logit contributions | |
�� | -2.103 |
LEY | -1.839 |
YL | -1.729 |
AF | -1.688 |
SAM | -1.686 |
Token | Es |
Token ID | 8678 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
jj | +0.036 |
sson | +0.035 |
andem | +0.033 |
zai | +0.031 |
hamm | +0.031 |
Neg logit contributions | |
�� | -0.055 |
LEY | -0.048 |
YL | -0.045 |
AF | -0.045 |
AH | -0.044 |
Token | q |
Token ID | 80 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
�� | +1.706 |
LEY | +1.515 |
YL | +1.410 |
AF | +1.409 |
SAM | +1.399 |
Neg logit contributions | |
jj | -1.058 |
sson | -1.047 |
andem | -0.983 |
hamm | -0.929 |
zai | -0.920 |
Token | , |
Token ID | 11 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
jj | +2.296 |
sson | +2.271 |
andem | +2.100 |
zai | +1.993 |
hamm | +1.974 |
Neg logit contributions | |
�� | -3.496 |
LEY | -3.055 |
YL | -2.894 |
SAM | -2.834 |
AF | -2.818 |
Token | director |
Token ID | 3437 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
�� | +0.331 |
LEY | +0.291 |
YL | +0.274 |
AF | +0.268 |
SAM | +0.266 |
Neg logit contributions | |
jj | -0.246 |
sson | -0.240 |
andem | -0.228 |
zai | -0.215 |
hamm | -0.213 |
Token | of |
Token ID | 286 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
�� | +0.786 |
LEY | +0.690 |
YL | +0.648 |
AF | +0.636 |
SAM | +0.632 |
Neg logit contributions | |
jj | -0.548 |
sson | -0.535 |
andem | -0.506 |
zai | -0.476 |
hamm | -0.475 |
Token | new |
Token ID | 649 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
�� | +0.182 |
LEY | +0.160 |
YL | +0.149 |
AF | +0.146 |
SAM | +0.145 |
Neg logit contributions | |
jj | -0.152 |
sson | -0.149 |
andem | -0.141 |
zai | -0.135 |
hamm | -0.133 |
Token | media |
Token ID | 2056 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
jj | +0.341 |
sson | +0.334 |
andem | +0.316 |
zai | +0.300 |
hamm | +0.298 |
Neg logit contributions | |
�� | -0.452 |
LEY | -0.396 |
YL | -0.371 |
AF | -0.364 |
SAM | -0.362 |
Token | not |
Token ID | 407 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
�� | +0.405 |
LEY | +0.352 |
YL | +0.330 |
AF | +0.322 |
SAM | +0.321 |
Neg logit contributions | |
jj | -0.322 |
sson | -0.317 |
andem | -0.298 |
zai | -0.284 |
hamm | -0.282 |
Token | be |
Token ID | 307 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
jj | +0.969 |
sson | +0.959 |
andem | +0.894 |
zai | +0.859 |
hamm | +0.845 |
Neg logit contributions | |
�� | -1.335 |
LEY | -1.161 |
YL | -1.090 |
AF | -1.072 |
SAM | -1.071 |
Token | published |
Token ID | 3199 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
jj | +0.068 |
sson | +0.067 |
andem | +0.063 |
zai | +0.060 |
hamm | +0.060 |
Neg logit contributions | |
�� | -0.084 |
LEY | -0.073 |
YL | -0.068 |
SAM | -0.067 |
AF | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
jj | +0.305 |
sson | +0.302 |
andem | +0.276 |
zai | +0.262 |
hamm | +0.260 |
Neg logit contributions | |
�� | -0.567 |
LEY | -0.501 |
YL | -0.474 |
SAM | -0.468 |
AH | -0.464 |
Token | broadcast |
Token ID | 7025 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
jj | +1.786 |
sson | +1.776 |
andem | +1.682 |
zai | +1.627 |
hamm | +1.622 |
Neg logit contributions | |
�� | -1.712 |
LEY | -1.421 |
YL | -1.312 |
SAM | -1.288 |
AH | -1.278 |
Token | , |
Token ID | 11 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
�� | +0.750 |
LEY | +0.666 |
YL | +0.629 |
AF | +0.617 |
SAM | +0.614 |
Neg logit contributions | |
jj | -0.450 |
sson | -0.440 |
andem | -0.412 |
zai | -0.387 |
hamm | -0.385 |
Token | rewritten |
Token ID | 30101 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
jj | +2.718 |
sson | +2.669 |
andem | +2.550 |
hamm | +2.474 |
zai | +2.466 |
Neg logit contributions | |
�� | -2.375 |
LEY | -1.972 |
YL | -1.820 |
AF | -1.769 |
SAM | -1.760 |
Token | or |
Token ID | 393 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
jj | +1.309 |
sson | +1.280 |
andem | +1.187 |
zai | +1.115 |
hamm | +1.096 |
Neg logit contributions | |
�� | -2.639 |
LEY | -2.328 |
YL | -2.205 |
SAM | -2.175 |
AF | -2.158 |
Token | redistributed |
Token ID | 38913 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
sson | +1.327 |
jj | +1.307 |
andem | +1.205 |
hamm | +1.161 |
zai | +1.134 |
Neg logit contributions | |
�� | -2.738 |
LEY | -2.383 |
SAM | -2.257 |
YL | -2.257 |
AH | -2.211 |
Token | .) |
Token ID | 2014 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
jj | +1.749 |
sson | +1.724 |
andem | +1.603 |
zai | +1.531 |
hamm | +1.498 |
Neg logit contributions | |
�� | -2.735 |
LEY | -2.413 |
YL | -2.266 |
SAM | -2.227 |
AF | -2.211 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
jj | +1.535 |
sson | +1.505 |
andem | +1.413 |
zai | +1.339 |
hamm | +1.330 |
Neg logit contributions | |
�� | -2.238 |
LEY | -1.968 |
YL | -1.853 |
AF | -1.813 |
SAM | -1.808 |