Token | 15 |
Token ID | 1315 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
Malik | +0.382 |
ANS | +0.382 |
amb | +0.360 |
subtitles | +0.345 |
SPD | +0.329 |
Neg logit contributions | |
aukee | -0.647 |
nesday | -0.554 |
tnc | -0.522 |
ngth | -0.506 |
akespe | -0.501 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
aukee | +0.244 |
nesday | +0.215 |
tnc | +0.200 |
ngth | +0.195 |
akespe | +0.194 |
Neg logit contributions | |
ANS | -0.106 |
Malik | -0.102 |
amb | -0.097 |
subtitles | -0.091 |
シ | -0.088 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
aukee | +0.493 |
nesday | +0.429 |
tnc | +0.396 |
icum | +0.377 |
agara | +0.374 |
Neg logit contributions | |
ANS | -0.379 |
Malik | -0.373 |
amb | -0.361 |
oteric | -0.346 |
subtitles | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
aukee | +0.782 |
nesday | +0.673 |
tnc | +0.613 |
ngth | +0.591 |
akespe | +0.589 |
Neg logit contributions | |
ANS | -0.574 |
Malik | -0.562 |
amb | -0.542 |
subtitles | -0.519 |
シ | -0.507 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
aukee | +0.123 |
nesday | +0.107 |
tnc | +0.097 |
ngth | +0.095 |
akespe | +0.094 |
Neg logit contributions | |
ANS | -0.088 |
Malik | -0.086 |
amb | -0.084 |
subtitles | -0.080 |
シ | -0.078 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
aukee | +0.102 |
nesday | +0.086 |
tnc | +0.079 |
ngth | +0.074 |
akespe | +0.074 |
Neg logit contributions | |
ANS | -0.092 |
Malik | -0.088 |
amb | -0.086 |
subtitles | -0.083 |
シ | -0.082 |
Token | : |
Token ID | 25 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
aukee | +3.815 |
nesday | +3.247 |
tnc | +3.105 |
agara | +2.887 |
icum | +2.885 |
Neg logit contributions | |
ANS | -2.578 |
Malik | -2.505 |
amb | -2.435 |
subtitles | -2.322 |
シ | -2.259 |
Token | Que |
Token ID | 4670 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
aukee | +0.515 |
nesday | +0.440 |
tnc | +0.422 |
icum | +0.392 |
agara | +0.392 |
Neg logit contributions | |
ANS | -0.335 |
Malik | -0.326 |
amb | -0.317 |
subtitles | -0.302 |
headphone | -0.292 |
Token | er |
Token ID | 263 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
aukee | +1.272 |
nesday | +1.048 |
tnc | +0.995 |
agara | +0.908 |
icum | +0.908 |
Neg logit contributions | |
ANS | -1.251 |
Malik | -1.222 |
amb | -1.194 |
subtitles | -1.151 |
シ | -1.126 |
Token | magnet |
Token ID | 19972 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ANS | +0.111 |
Malik | +0.108 |
amb | +0.105 |
subtitles | +0.100 |
headphone | +0.097 |
Neg logit contributions | |
aukee | -0.185 |
nesday | -0.158 |
tnc | -0.152 |
agara | -0.141 |
icum | -0.141 |
Token | ? |
Token ID | 30 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ANS | +0.316 |
Malik | +0.308 |
amb | +0.301 |
subtitles | +0.286 |
headphone | +0.277 |
Neg logit contributions | |
aukee | -0.462 |
nesday | -0.391 |
tnc | -0.378 |
agara | -0.348 |
icum | -0.347 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
aukee | +0.011 |
nesday | +0.009 |
tnc | +0.009 |
ngth | +0.009 |
akespe | +0.008 |
Neg logit contributions | |
ANS | -0.007 |
Malik | -0.007 |
amb | -0.006 |
subtitles | -0.006 |
SPD | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
aukee | +0.501 |
nesday | +0.442 |
tnc | +0.413 |
ngth | +0.398 |
akespe | +0.397 |
Neg logit contributions | |
ANS | -0.222 |
Malik | -0.214 |
amb | -0.205 |
subtitles | -0.192 |
シ | -0.186 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aukee | +0.697 |
nesday | +0.602 |
tnc | +0.553 |
icum | +0.535 |
agara | +0.521 |
Neg logit contributions | |
ANS | -0.549 |
Malik | -0.536 |
amb | -0.522 |
oteric | -0.504 |
subtitles | -0.494 |
Token |
|
Token ID | 198 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
aukee | +0.997 |
nesday | +0.857 |
tnc | +0.780 |
ngth | +0.756 |
akespe | +0.751 |
Neg logit contributions | |
ANS | -0.730 |
Malik | -0.717 |
amb | -0.692 |
subtitles | -0.663 |
シ | -0.646 |
Token |
|
Token ID | 198 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
aukee | +0.114 |
nesday | +0.098 |
tnc | +0.090 |
ngth | +0.087 |
akespe | +0.086 |
Neg logit contributions | |
ANS | -0.082 |
Malik | -0.080 |
amb | -0.078 |
subtitles | -0.074 |
シ | -0.072 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
aukee | +0.139 |
nesday | +0.117 |
tnc | +0.106 |
ngth | +0.101 |
akespe | +0.100 |
Neg logit contributions | |
ANS | -0.127 |
Malik | -0.122 |
amb | -0.119 |
subtitles | -0.114 |
シ | -0.114 |
Token | : |
Token ID | 25 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
aukee | +3.791 |
nesday | +3.226 |
tnc | +3.086 |
agara | +2.868 |
icum | +2.866 |
Neg logit contributions | |
ANS | -2.565 |
Malik | -2.492 |
amb | -2.422 |
subtitles | -2.310 |
シ | -2.247 |
Token | Que |
Token ID | 4670 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
aukee | +0.608 |
nesday | +0.518 |
tnc | +0.497 |
icum | +0.462 |
agara | +0.462 |
Neg logit contributions | |
ANS | -0.396 |
Malik | -0.386 |
amb | -0.375 |
subtitles | -0.357 |
headphone | -0.346 |
Token | ers |
Token ID | 364 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
aukee | +1.164 |
nesday | +0.949 |
tnc | +0.886 |
agara | +0.811 |
icum | +0.807 |
Neg logit contributions | |
ANS | -1.348 |
Malik | -1.315 |
amb | -1.281 |
subtitles | -1.247 |
シ | -1.232 |
Token | are |
Token ID | 389 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ANS | +0.176 |
Malik | +0.172 |
amb | +0.168 |
subtitles | +0.158 |
headphone | +0.153 |
Neg logit contributions | |
aukee | -0.286 |
nesday | -0.244 |
tnc | -0.237 |
agara | -0.219 |
icum | -0.219 |
Token | Here |
Token ID | 3423 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
aukee | +0.488 |
nesday | +0.422 |
tnc | +0.406 |
icum | +0.380 |
agara | +0.380 |
Neg logit contributions | |
ANS | -0.254 |
Malik | -0.246 |
amb | -0.239 |
subtitles | -0.225 |
headphone | -0.217 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
aukee | +0.767 |
nesday | +0.670 |
tnc | +0.639 |
ngth | +0.605 |
agara | +0.599 |
Neg logit contributions | |
ANS | -0.390 |
Malik | -0.388 |
amb | -0.370 |
subtitles | -0.350 |
シ | -0.340 |
Token | United |
Token ID | 1578 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
aukee | +1.305 |
nesday | +1.097 |
tnc | +1.045 |
agara | +0.964 |
icum | +0.964 |
Neg logit contributions | |
ANS | -1.049 |
Malik | -1.024 |
amb | -0.996 |
subtitles | -0.955 |
シ | -0.931 |
Token | States |
Token ID | 1829 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
aukee | +1.344 |
nesday | +1.154 |
tnc | +1.098 |
agara | +1.055 |
rique | +1.042 |
Neg logit contributions | |
ANS | -0.627 |
Malik | -0.596 |
amb | -0.573 |
subtitles | -0.543 |
headphone | -0.532 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
aukee | +0.211 |
nesday | +0.179 |
tnc | +0.170 |
icum | +0.158 |
agara | +0.158 |
Neg logit contributions | |
ANS | -0.158 |
Malik | -0.156 |
amb | -0.150 |
subtitles | -0.144 |
シ | -0.140 |
Token | 472 |
Token ID | 37856 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
aukee | +0.578 |
nesday | +0.494 |
tnc | +0.470 |
icum | +0.439 |
agara | +0.438 |
Neg logit contributions | |
ANS | -0.390 |
Malik | -0.379 |
amb | -0.368 |
subtitles | -0.352 |
シ | -0.344 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
aukee | +0.237 |
nesday | +0.205 |
tnc | +0.188 |
akespe | +0.180 |
ngth | +0.180 |
Neg logit contributions | |
ANS | -0.171 |
Malik | -0.169 |
amb | -0.162 |
subtitles | -0.158 |
SPD | -0.152 |
Token | # |
Token ID | 1303 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
aukee | +2.349 |
nesday | +1.867 |
tnc | +1.678 |
agara | +1.500 |
icum | +1.469 |
Neg logit contributions | |
ANS | -3.854 |
Malik | -3.764 |
amb | -3.668 |
subtitles | -3.575 |
シ | -3.547 |
Token | 11 |
Token ID | 1157 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
aukee | +2.772 |
nesday | +2.428 |
tnc | +2.351 |
agara | +2.214 |
icum | +2.213 |
Neg logit contributions | |
ANS | -1.085 |
Malik | -1.044 |
amb | -1.001 |
subtitles | -0.934 |
シ | -0.893 |
Token | On |
Token ID | 1550 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
aukee | +1.385 |
nesday | +1.180 |
tnc | +1.134 |
icum | +1.052 |
agara | +1.052 |
Neg logit contributions | |
ANS | -0.900 |
Malik | -0.876 |
amb | -0.851 |
subtitles | -0.811 |
headphone | -0.786 |
Token | September |
Token ID | 2693 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
aukee | +0.212 |
nesday | +0.178 |
tnc | +0.171 |
icum | +0.158 |
agara | +0.157 |
Neg logit contributions | |
ANS | -0.159 |
Malik | -0.155 |
amb | -0.152 |
subtitles | -0.144 |
headphone | -0.141 |
Token | 20 |
Token ID | 1160 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aukee | +0.090 |
nesday | +0.076 |
tnc | +0.072 |
ngth | +0.069 |
agara | +0.068 |
Neg logit contributions | |
ANS | -0.060 |
Malik | -0.059 |
amb | -0.056 |
subtitles | -0.054 |
シ | -0.052 |
Token | 4 |
Token ID | 604 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
Malik | +0.233 |
ANS | +0.232 |
amb | +0.220 |
subtitles | +0.212 |
SPD | +0.202 |
Neg logit contributions | |
aukee | -0.391 |
nesday | -0.334 |
tnc | -0.315 |
ngth | -0.305 |
akespe | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ANS | +0.113 |
Malik | +0.108 |
amb | +0.103 |
subtitles | +0.096 |
シ | +0.093 |
Neg logit contributions | |
aukee | -0.268 |
nesday | -0.237 |
tnc | -0.219 |
ngth | -0.215 |
akespe | -0.214 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
aukee | +0.443 |
nesday | +0.382 |
tnc | +0.366 |
agara | +0.341 |
icum | +0.340 |
Neg logit contributions | |
ANS | -0.251 |
Malik | -0.243 |
amb | -0.236 |
subtitles | -0.223 |
シ | -0.216 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
aukee | +0.806 |
nesday | +0.695 |
tnc | +0.632 |
ngth | +0.611 |
akespe | +0.608 |
Neg logit contributions | |
ANS | -0.588 |
Malik | -0.577 |
amb | -0.557 |
subtitles | -0.533 |
シ | -0.520 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
ANS | +0.045 |
Malik | +0.044 |
amb | +0.043 |
subtitles | +0.041 |
シ | +0.040 |
Neg logit contributions | |
aukee | -0.064 |
nesday | -0.055 |
tnc | -0.050 |
ngth | -0.049 |
akespe | -0.048 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ANS | +0.003 |
Malik | +0.003 |
amb | +0.003 |
subtitles | +0.003 |
シ | +0.003 |
Neg logit contributions | |
aukee | -0.003 |
nesday | -0.003 |
tnc | -0.003 |
ngth | -0.002 |
akespe | -0.002 |
Token | : |
Token ID | 25 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
aukee | +3.727 |
nesday | +3.173 |
tnc | +3.033 |
agara | +2.821 |
icum | +2.819 |
Neg logit contributions | |
ANS | -2.514 |
Malik | -2.442 |
amb | -2.374 |
subtitles | -2.263 |
シ | -2.202 |
Token | User |
Token ID | 11787 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
aukee | +0.622 |
nesday | +0.530 |
tnc | +0.509 |
icum | +0.473 |
agara | +0.473 |
Neg logit contributions | |
ANS | -0.405 |
Malik | -0.394 |
amb | -0.383 |
subtitles | -0.365 |
headphone | -0.353 |
Token | reviews |
Token ID | 8088 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
aukee | +0.636 |
nesday | +0.542 |
tnc | +0.523 |
icum | +0.485 |
agara | +0.485 |
Neg logit contributions | |
ANS | -0.390 |
Malik | -0.379 |
amb | -0.369 |
subtitles | -0.350 |
headphone | -0.339 |
Token | are |
Token ID | 389 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
aukee | +1.043 |
nesday | +0.889 |
tnc | +0.855 |
agara | +0.792 |
icum | +0.791 |
Neg logit contributions | |
ANS | -0.684 |
Malik | -0.667 |
amb | -0.649 |
subtitles | -0.618 |
headphone | -0.599 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
aukee | +0.700 |
nesday | +0.605 |
tnc | +0.582 |
icum | +0.545 |
agara | +0.545 |
Neg logit contributions | |
ANS | -0.367 |
Malik | -0.356 |
amb | -0.344 |
subtitles | -0.325 |
シ | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ANS | +0.050 |
Malik | +0.049 |
amb | +0.047 |
subtitles | +0.045 |
headphone | +0.043 |
Neg logit contributions | |
aukee | -0.085 |
nesday | -0.074 |
tnc | -0.071 |
icum | -0.066 |
agara | -0.066 |
Token | Flag |
Token ID | 19762 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aukee | +0.811 |
nesday | +0.690 |
tnc | +0.656 |
agara | +0.610 |
icum | +0.608 |
Neg logit contributions | |
ANS | -0.584 |
Malik | -0.572 |
amb | -0.553 |
subtitles | -0.529 |
シ | -0.513 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
aukee | +0.341 |
nesday | +0.288 |
tnc | +0.273 |
agara | +0.254 |
icum | +0.253 |
Neg logit contributions | |
ANS | -0.279 |
Malik | -0.273 |
amb | -0.265 |
subtitles | -0.253 |
シ | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
aukee | +1.194 |
nesday | +1.028 |
tnc | +0.936 |
ngth | +0.907 |
akespe | +0.898 |
Neg logit contributions | |
ANS | -0.886 |
Malik | -0.866 |
amb | -0.842 |
subtitles | -0.802 |
シ | -0.784 |
Token | Flag |
Token ID | 34227 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aukee | +1.171 |
nesday | +1.015 |
tnc | +0.900 |
ngth | +0.899 |
akespe | +0.884 |
Neg logit contributions | |
ANS | -0.873 |
Malik | -0.825 |
amb | -0.796 |
シ | -0.773 |
subtitles | -0.761 |
Token | Reply |
Token ID | 14883 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aukee | +1.021 |
nesday | +0.871 |
tnc | +0.820 |
agara | +0.776 |
icum | +0.773 |
Neg logit contributions | |
Malik | -0.684 |
ANS | -0.682 |
amb | -0.652 |
subtitles | -0.618 |
SPD | -0.598 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
aukee | +3.385 |
nesday | +2.845 |
tnc | +2.669 |
agara | +2.478 |
icum | +2.474 |
Neg logit contributions | |
ANS | -2.856 |
Malik | -2.797 |
amb | -2.717 |
subtitles | -2.609 |
シ | -2.545 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
aukee | +0.952 |
nesday | +0.823 |
tnc | +0.748 |
ngth | +0.727 |
akespe | +0.718 |
Neg logit contributions | |
ANS | -0.694 |
Malik | -0.680 |
amb | -0.658 |
subtitles | -0.626 |
シ | -0.614 |
Token | 19 |
Token ID | 1129 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
aukee | +0.889 |
nesday | +0.776 |
tnc | +0.732 |
agara | +0.699 |
icum | +0.698 |
Neg logit contributions | |
ANS | -0.433 |
Malik | -0.413 |
amb | -0.394 |
subtitles | -0.373 |
シ | -0.368 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Malik | +0.351 |
ANS | +0.349 |
amb | +0.332 |
subtitles | +0.310 |
SPD | +0.307 |
Neg logit contributions | |
aukee | -0.597 |
nesday | -0.510 |
tnc | -0.486 |
ngth | -0.462 |
akespe | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
aukee | +1.717 |
nesday | +1.468 |
tnc | +1.355 |
ngth | +1.289 |
akespe | +1.274 |
Neg logit contributions | |
ANS | -1.320 |
Malik | -1.302 |
amb | -1.260 |
subtitles | -1.200 |
シ | -1.171 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
ANS | +0.336 |
Malik | +0.336 |
amb | +0.317 |
subtitles | +0.304 |
SPD | +0.290 |
Neg logit contributions | |
aukee | -0.577 |
nesday | -0.494 |
tnc | -0.467 |
ngth | -0.450 |
akespe | -0.446 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ANS | +0.055 |
Malik | +0.053 |
amb | +0.051 |
subtitles | +0.047 |
シ | +0.046 |
Neg logit contributions | |
aukee | -0.128 |
nesday | -0.113 |
tnc | -0.105 |
ngth | -0.102 |
akespe | -0.102 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
aukee | +0.650 |
nesday | +0.560 |
tnc | +0.523 |
icum | +0.498 |
agara | +0.497 |
Neg logit contributions | |
ANS | -0.497 |
Malik | -0.488 |
amb | -0.471 |
oteric | -0.450 |
subtitles | -0.450 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
aukee | +0.751 |
nesday | +0.646 |
tnc | +0.588 |
ngth | +0.568 |
akespe | +0.566 |
Neg logit contributions | |
ANS | -0.553 |
Malik | -0.542 |
amb | -0.523 |
subtitles | -0.501 |
シ | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
aukee | +0.060 |
nesday | +0.052 |
tnc | +0.047 |
ngth | +0.046 |
akespe | +0.045 |
Neg logit contributions | |
ANS | -0.043 |
Malik | -0.042 |
amb | -0.041 |
subtitles | -0.039 |
シ | -0.038 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aukee | +0.078 |
nesday | +0.066 |
tnc | +0.060 |
ngth | +0.056 |
akespe | +0.056 |
Neg logit contributions | |
ANS | -0.070 |
Malik | -0.067 |
amb | -0.065 |
subtitles | -0.063 |
シ | -0.062 |
Token | : |
Token ID | 25 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
aukee | +3.698 |
nesday | +3.150 |
tnc | +3.008 |
agara | +2.800 |
icum | +2.797 |
Neg logit contributions | |
ANS | -2.478 |
Malik | -2.407 |
amb | -2.340 |
subtitles | -2.229 |
シ | -2.171 |
Token | R |
Token ID | 371 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
aukee | +0.471 |
nesday | +0.401 |
tnc | +0.385 |
icum | +0.358 |
agara | +0.358 |
Neg logit contributions | |
ANS | -0.305 |
Malik | -0.297 |
amb | -0.288 |
subtitles | -0.275 |
headphone | -0.266 |
Token | ipe |
Token ID | 3757 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
aukee | +0.504 |
nesday | +0.422 |
tnc | +0.403 |
agara | +0.371 |
icum | +0.371 |
Neg logit contributions | |
ANS | -0.416 |
Malik | -0.406 |
amb | -0.396 |
subtitles | -0.379 |
シ | -0.370 |
Token | for |
Token ID | 329 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
aukee | +0.580 |
nesday | +0.496 |
tnc | +0.477 |
agara | +0.444 |
icum | +0.444 |
Neg logit contributions | |
ANS | -0.356 |
Malik | -0.346 |
amb | -0.336 |
subtitles | -0.319 |
シ | -0.309 |
Token | M |
Token ID | 337 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
aukee | +0.175 |
nesday | +0.150 |
tnc | +0.145 |
icum | +0.135 |
agara | +0.135 |
Neg logit contributions | |
ANS | -0.100 |
Malik | -0.098 |
amb | -0.095 |
subtitles | -0.090 |
headphone | -0.087 |
Token | 13 |
Token ID | 1511 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
Malik | +0.416 |
ANS | +0.414 |
amb | +0.389 |
subtitles | +0.374 |
SPD | +0.357 |
Neg logit contributions | |
aukee | -0.715 |
nesday | -0.615 |
tnc | -0.576 |
ngth | -0.561 |
akespe | -0.556 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
aukee | +0.184 |
nesday | +0.163 |
tnc | +0.153 |
akespe | +0.148 |
ngth | +0.147 |
Neg logit contributions | |
ANS | -0.077 |
Malik | -0.075 |
amb | -0.071 |
subtitles | -0.067 |
シ | -0.064 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
aukee | +0.685 |
nesday | +0.587 |
tnc | +0.567 |
agara | +0.526 |
icum | +0.525 |
Neg logit contributions | |
ANS | -0.380 |
Malik | -0.369 |
amb | -0.356 |
subtitles | -0.339 |
シ | -0.327 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
aukee | +0.448 |
nesday | +0.386 |
tnc | +0.350 |
ngth | +0.340 |
akespe | +0.339 |
Neg logit contributions | |
ANS | -0.328 |
Malik | -0.324 |
amb | -0.311 |
subtitles | -0.298 |
シ | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
ANS | +0.054 |
Malik | +0.053 |
amb | +0.051 |
subtitles | +0.048 |
シ | +0.047 |
Neg logit contributions | |
aukee | -0.075 |
nesday | -0.065 |
tnc | -0.059 |
ngth | -0.058 |
akespe | -0.057 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aukee | +0.025 |
nesday | +0.021 |
tnc | +0.020 |
agara | +0.018 |
akespe | +0.018 |
Neg logit contributions | |
ANS | -0.023 |
Malik | -0.023 |
amb | -0.022 |
subtitles | -0.021 |
headphone | -0.021 |
Token | : |
Token ID | 25 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
aukee | +3.705 |
nesday | +3.161 |
tnc | +3.013 |
agara | +2.810 |
icum | +2.804 |
Neg logit contributions | |
ANS | -2.450 |
Malik | -2.380 |
amb | -2.315 |
subtitles | -2.205 |
シ | -2.144 |
Token | boys |
Token ID | 6510 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
aukee | +0.590 |
nesday | +0.503 |
tnc | +0.483 |
icum | +0.448 |
agara | +0.448 |
Neg logit contributions | |
ANS | -0.386 |
Malik | -0.376 |
amb | -0.365 |
subtitles | -0.348 |
headphone | -0.337 |
Token | beware |
Token ID | 40600 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
ANS | +0.185 |
Malik | +0.179 |
amb | +0.175 |
subtitles | +0.165 |
headphone | +0.160 |
Neg logit contributions | |
aukee | -0.316 |
nesday | -0.271 |
tnc | -0.262 |
icum | -0.243 |
agara | -0.243 |
Token | This |
Token ID | 770 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
aukee | +0.245 |
nesday | +0.209 |
tnc | +0.200 |
agara | +0.186 |
icum | +0.186 |
Neg logit contributions | |
ANS | -0.158 |
Malik | -0.153 |
amb | -0.149 |
subtitles | -0.142 |
headphone | -0.137 |
Token | film |
Token ID | 2646 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
aukee | +0.465 |
nesday | +0.400 |
tnc | +0.384 |
agara | +0.359 |
icum | +0.359 |
Neg logit contributions | |
ANS | -0.264 |
Malik | -0.255 |
amb | -0.248 |
subtitles | -0.235 |
シ | -0.227 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ANS | +0.638 |
Malik | +0.637 |
amb | +0.599 |
subtitles | +0.576 |
SPD | +0.549 |
Neg logit contributions | |
aukee | -1.092 |
nesday | -0.940 |
tnc | -0.878 |
ngth | -0.859 |
akespe | -0.847 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ANS | +0.055 |
Malik | +0.052 |
amb | +0.050 |
subtitles | +0.047 |
シ | +0.046 |
Neg logit contributions | |
aukee | -0.126 |
nesday | -0.111 |
tnc | -0.103 |
ngth | -0.100 |
akespe | -0.100 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
aukee | +0.744 |
nesday | +0.647 |
tnc | +0.597 |
icum | +0.573 |
agara | +0.568 |
Neg logit contributions | |
ANS | -0.588 |
Malik | -0.575 |
amb | -0.554 |
oteric | -0.534 |
subtitles | -0.527 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
aukee | +0.641 |
nesday | +0.549 |
tnc | +0.503 |
ngth | +0.482 |
akespe | +0.481 |
Neg logit contributions | |
ANS | -0.476 |
Malik | -0.467 |
amb | -0.451 |
subtitles | -0.431 |
シ | -0.421 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
aukee | +0.096 |
nesday | +0.083 |
tnc | +0.076 |
ngth | +0.073 |
akespe | +0.073 |
Neg logit contributions | |
ANS | -0.070 |
Malik | -0.068 |
amb | -0.066 |
subtitles | -0.063 |
シ | -0.062 |
Token | Subject |
Token ID | 19776 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aukee | +0.146 |
nesday | +0.123 |
tnc | +0.113 |
akespe | +0.105 |
ngth | +0.105 |
Neg logit contributions | |
ANS | -0.134 |
Malik | -0.128 |
amb | -0.125 |
subtitles | -0.120 |
シ | -0.119 |
Token | : |
Token ID | 25 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
aukee | +3.672 |
nesday | +3.127 |
tnc | +2.988 |
agara | +2.780 |
icum | +2.777 |
Neg logit contributions | |
ANS | -2.470 |
Malik | -2.399 |
amb | -2.332 |
subtitles | -2.223 |
シ | -2.163 |
Token | R |
Token ID | 371 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
aukee | +0.645 |
nesday | +0.551 |
tnc | +0.529 |
icum | +0.492 |
agara | +0.492 |
Neg logit contributions | |
ANS | -0.413 |
Malik | -0.401 |
amb | -0.390 |
subtitles | -0.371 |
シ | -0.359 |
Token | iff |
Token ID | 733 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
aukee | +0.532 |
nesday | +0.452 |
tnc | +0.433 |
icum | +0.401 |
agara | +0.401 |
Neg logit contributions | |
ANS | -0.374 |
Malik | -0.362 |
amb | -0.352 |
subtitles | -0.336 |
シ | -0.326 |
Token | Tra |
Token ID | 15721 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
aukee | +0.220 |
nesday | +0.186 |
tnc | +0.178 |
agara | +0.164 |
icum | +0.164 |
Neg logit contributions | |
ANS | -0.164 |
Malik | -0.159 |
amb | -0.155 |
subtitles | -0.148 |
シ | -0.144 |
Token | x |
Token ID | 87 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
aukee | +0.212 |
nesday | +0.179 |
tnc | +0.171 |
agara | +0.158 |
icum | +0.158 |
Neg logit contributions | |
ANS | -0.159 |
Malik | -0.155 |
amb | -0.151 |
subtitles | -0.144 |
シ | -0.140 |
Token | June |
Token ID | 2795 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
aukee | +1.299 |
nesday | +1.087 |
tnc | +1.041 |
agara | +0.962 |
icum | +0.960 |
Neg logit contributions | |
ANS | -1.011 |
Malik | -0.997 |
amb | -0.968 |
subtitles | -0.928 |
シ | -0.901 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
aukee | +0.259 |
nesday | +0.226 |
tnc | +0.215 |
ngth | +0.204 |
agara | +0.203 |
Neg logit contributions | |
Malik | -0.135 |
ANS | -0.135 |
amb | -0.127 |
subtitles | -0.122 |
シ | -0.117 |
Token | Canada |
Token ID | 3340 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
aukee | +0.989 |
nesday | +0.829 |
tnc | +0.790 |
icum | +0.727 |
agara | +0.727 |
Neg logit contributions | |
ANS | -0.817 |
Malik | -0.798 |
amb | -0.777 |
subtitles | -0.745 |
シ | -0.727 |
Token | 16 |
Token ID | 1467 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
aukee | +0.895 |
nesday | +0.764 |
tnc | +0.722 |
agara | +0.676 |
ngth | +0.669 |
Neg logit contributions | |
ANS | -0.646 |
Malik | -0.637 |
amb | -0.612 |
subtitles | -0.589 |
シ | -0.569 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
aukee | +1.442 |
nesday | +1.238 |
tnc | +1.187 |
icum | +1.109 |
agara | +1.109 |
Neg logit contributions | |
ANS | -0.853 |
Malik | -0.828 |
amb | -0.801 |
subtitles | -0.762 |
シ | -0.739 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
aukee | +0.504 |
nesday | +0.432 |
tnc | +0.401 |
icum | +0.380 |
akespe | +0.378 |
Neg logit contributions | |
ANS | -0.377 |
Malik | -0.371 |
amb | -0.356 |
subtitles | -0.345 |
シ | -0.336 |
Token | # |
Token ID | 1303 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
aukee | +2.184 |
nesday | +1.734 |
tnc | +1.520 |
agara | +1.360 |
icum | +1.327 |
Neg logit contributions | |
ANS | -3.785 |
Malik | -3.677 |
amb | -3.581 |
subtitles | -3.475 |
シ | -3.457 |
Token | 14 |
Token ID | 1415 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
aukee | +2.156 |
nesday | +1.875 |
tnc | +1.794 |
agara | +1.692 |
icum | +1.692 |
Neg logit contributions | |
ANS | -0.990 |
Malik | -0.946 |
amb | -0.916 |
subtitles | -0.864 |
シ | -0.832 |
Token | On |
Token ID | 1550 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aukee | +0.929 |
nesday | +0.793 |
tnc | +0.763 |
icum | +0.709 |
agara | +0.708 |
Neg logit contributions | |
ANS | -0.577 |
Malik | -0.563 |
amb | -0.546 |
subtitles | -0.520 |
headphone | -0.503 |
Token | September |
Token ID | 2693 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
aukee | +0.372 |
nesday | +0.311 |
tnc | +0.296 |
ngth | +0.282 |
agara | +0.279 |
Neg logit contributions | |
ANS | -0.249 |
Malik | -0.248 |
amb | -0.241 |
subtitles | -0.228 |
シ | -0.221 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
aukee | +0.082 |
nesday | +0.070 |
tnc | +0.066 |
agara | +0.060 |
icum | +0.058 |
Neg logit contributions | |
ANS | -0.077 |
Malik | -0.075 |
amb | -0.073 |
subtitles | -0.070 |
シ | -0.070 |
Token | TL |
Token ID | 24811 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
aukee | +1.080 |
nesday | +0.899 |
tnc | +0.860 |
agara | +0.789 |
icum | +0.787 |
Neg logit contributions | |
ANS | -0.927 |
Malik | -0.899 |
amb | -0.881 |
subtitles | -0.845 |
headphone | -0.827 |
Token | AD |
Token ID | 2885 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
ANS | +0.017 |
Malik | +0.017 |
amb | +0.016 |
subtitles | +0.016 |
シ | +0.015 |
Neg logit contributions | |
aukee | -0.030 |
nesday | -0.026 |
tnc | -0.025 |
icum | -0.023 |
agara | -0.023 |
Token | T |
Token ID | 51 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ANS | +0.091 |
Malik | +0.087 |
amb | +0.085 |
subtitles | +0.080 |
シ | +0.077 |
Neg logit contributions | |
aukee | -0.176 |
nesday | -0.151 |
tnc | -0.146 |
agara | -0.137 |
icum | -0.137 |
Token | 235 |
Token ID | 28878 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
aukee | +0.373 |
nesday | +0.312 |
tnc | +0.298 |
agara | +0.273 |
icum | +0.273 |
Neg logit contributions | |
ANS | -0.317 |
Malik | -0.307 |
amb | -0.300 |
subtitles | -0.288 |
シ | -0.282 |
Token | 21 |
Token ID | 2481 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
aukee | +1.022 |
nesday | +0.883 |
tnc | +0.849 |
agara | +0.795 |
icum | +0.795 |
Neg logit contributions | |
ANS | -0.544 |
Malik | -0.527 |
amb | -0.509 |
subtitles | -0.482 |
シ | -0.466 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
aukee | +0.840 |
nesday | +0.713 |
tnc | +0.671 |
akespe | +0.628 |
icum | +0.628 |
Neg logit contributions | |
ANS | -0.648 |
Malik | -0.636 |
amb | -0.612 |
subtitles | -0.591 |
シ | -0.578 |
Token | # |
Token ID | 1303 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
aukee | +2.103 |
nesday | +1.671 |
tnc | +1.457 |
agara | +1.291 |
icum | +1.253 |
Neg logit contributions | |
ANS | -3.768 |
Malik | -3.673 |
amb | -3.575 |
subtitles | -3.478 |
シ | -3.462 |
Token | 18 |
Token ID | 1507 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
aukee | +2.137 |
nesday | +1.855 |
tnc | +1.767 |
agara | +1.675 |
icum | +1.670 |
Neg logit contributions | |
ANS | -0.962 |
Malik | -0.906 |
amb | -0.880 |
subtitles | -0.823 |
シ | -0.797 |
Token | Good |
Token ID | 4599 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
aukee | +1.112 |
nesday | +0.948 |
tnc | +0.914 |
icum | +0.848 |
agara | +0.848 |
Neg logit contributions | |
ANS | -0.692 |
Malik | -0.675 |
amb | -0.655 |
subtitles | -0.623 |
headphone | -0.604 |
Token | stuff |
Token ID | 3404 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
aukee | +1.080 |
nesday | +0.938 |
tnc | +0.899 |
agara | +0.845 |
icum | +0.844 |
Neg logit contributions | |
ANS | -0.558 |
Malik | -0.539 |
amb | -0.519 |
subtitles | -0.491 |
シ | -0.475 |
Token | ! |
Token ID | 0 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aukee | +0.313 |
nesday | +0.268 |
tnc | +0.258 |
icum | +0.240 |
agara | +0.240 |
Neg logit contributions | |
ANS | -0.184 |
Malik | -0.179 |
amb | -0.174 |
subtitles | -0.165 |
シ | -0.159 |
Token | uck |
Token ID | 1347 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
ANS | +0.161 |
Malik | +0.157 |
amb | +0.152 |
subtitles | +0.145 |
シ | +0.142 |
Neg logit contributions | |
aukee | -0.203 |
nesday | -0.171 |
tnc | -0.162 |
icum | -0.150 |
agara | -0.150 |
Token | ley |
Token ID | 1636 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ANS | +0.114 |
Malik | +0.110 |
amb | +0.107 |
subtitles | +0.102 |
headphone | +0.099 |
Neg logit contributions | |
aukee | -0.164 |
nesday | -0.139 |
tnc | -0.134 |
agara | -0.124 |
icum | -0.123 |
Token | NBA |
Token ID | 32470 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
ANS | +0.239 |
Malik | +0.232 |
amb | +0.224 |
subtitles | +0.214 |
headphone | +0.208 |
Neg logit contributions | |
aukee | -0.339 |
nesday | -0.289 |
tnc | -0.276 |
agara | -0.257 |
icum | -0.256 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
aukee | +0.129 |
nesday | +0.108 |
tnc | +0.103 |
icum | +0.094 |
agara | +0.094 |
Neg logit contributions | |
ANS | -0.114 |
Malik | -0.111 |
amb | -0.108 |
subtitles | -0.104 |
headphone | -0.101 |
Token | Ted |
Token ID | 38972 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
aukee | +0.035 |
nesday | +0.029 |
tnc | +0.028 |
agara | +0.026 |
icum | +0.026 |
Neg logit contributions | |
ANS | -0.027 |
Malik | -0.026 |
amb | -0.025 |
subtitles | -0.024 |
シ | -0.024 |
Token | Nug |
Token ID | 45777 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ANS | +0.170 |
Malik | +0.167 |
amb | +0.161 |
subtitles | +0.155 |
シ | +0.151 |
Neg logit contributions | |
aukee | -0.198 |
nesday | -0.164 |
tnc | -0.157 |
agara | -0.144 |
icum | -0.144 |
Token | ent |
Token ID | 298 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
aukee | +1.949 |
nesday | +1.442 |
tnc | +1.320 |
agara | +1.103 |
icum | +1.076 |
Neg logit contributions | |
ANS | -3.995 |
Malik | -3.914 |
amb | -3.865 |
subtitles | -3.737 |
シ | -3.679 |
Token | promised |
Token ID | 8072 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ANS | +0.062 |
Malik | +0.061 |
amb | +0.059 |
subtitles | +0.055 |
シ | +0.054 |
Neg logit contributions | |
aukee | -0.099 |
nesday | -0.085 |
tnc | -0.082 |
agara | -0.076 |
icum | -0.076 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
aukee | +0.630 |
nesday | +0.538 |
tnc | +0.519 |
agara | +0.482 |
icum | +0.481 |
Neg logit contributions | |
ANS | -0.403 |
Malik | -0.395 |
amb | -0.384 |
subtitles | -0.365 |
headphone | -0.353 |
Token | that |
Token ID | 326 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
aukee | +0.732 |
nesday | +0.626 |
tnc | +0.603 |
agara | +0.561 |
icum | +0.559 |
Neg logit contributions | |
ANS | -0.460 |
Malik | -0.450 |
amb | -0.436 |
subtitles | -0.414 |
headphone | -0.400 |
Token | he |
Token ID | 339 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
ANS | +0.093 |
Malik | +0.091 |
amb | +0.088 |
subtitles | +0.084 |
headphone | +0.081 |
Neg logit contributions | |
aukee | -0.149 |
nesday | -0.128 |
tnc | -0.123 |
agara | -0.114 |
icum | -0.114 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
aukee | +0.779 |
nesday | +0.681 |
tnc | +0.647 |
agara | +0.613 |
ngth | +0.612 |
Neg logit contributions | |
Malik | -0.403 |
ANS | -0.401 |
amb | -0.378 |
subtitles | -0.361 |
シ | -0.348 |
Token | United |
Token ID | 1578 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
aukee | +1.392 |
nesday | +1.166 |
tnc | +1.113 |
agara | +1.025 |
icum | +1.024 |
Neg logit contributions | |
ANS | -1.141 |
Malik | -1.112 |
amb | -1.084 |
subtitles | -1.040 |
シ | -1.014 |
Token | States |
Token ID | 1829 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
aukee | +1.269 |
nesday | +1.095 |
tnc | +1.041 |
agara | +0.997 |
icum | +0.984 |
Neg logit contributions | |
ANS | -0.580 |
Malik | -0.549 |
amb | -0.530 |
subtitles | -0.502 |
headphone | -0.494 |
Token | 228 |
Token ID | 29041 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
aukee | +0.315 |
nesday | +0.267 |
tnc | +0.253 |
agara | +0.236 |
icum | +0.235 |
Neg logit contributions | |
ANS | -0.232 |
Malik | -0.229 |
amb | -0.221 |
subtitles | -0.212 |
シ | -0.205 |
Token | 65 |
Token ID | 2996 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
aukee | +0.355 |
nesday | +0.307 |
tnc | +0.294 |
icum | +0.277 |
agara | +0.277 |
Neg logit contributions | |
ANS | -0.190 |
Malik | -0.183 |
amb | -0.176 |
subtitles | -0.168 |
シ | -0.162 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aukee | +0.235 |
nesday | +0.201 |
tnc | +0.188 |
icum | +0.177 |
ngth | +0.177 |
Neg logit contributions | |
ANS | -0.174 |
Malik | -0.169 |
amb | -0.163 |
subtitles | -0.159 |
シ | -0.155 |
Token | # |
Token ID | 1303 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
aukee | +2.135 |
nesday | +1.700 |
tnc | +1.495 |
agara | +1.341 |
icum | +1.304 |
Neg logit contributions | |
ANS | -3.677 |
Malik | -3.579 |
amb | -3.488 |
subtitles | -3.392 |
シ | -3.370 |
Token | 13 |
Token ID | 1485 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
aukee | +2.067 |
nesday | +1.796 |
tnc | +1.684 |
ngth | +1.611 |
akespe | +1.611 |
Neg logit contributions | |
ANS | -1.093 |
Malik | -1.044 |
amb | -1.009 |
subtitles | -0.964 |
シ | -0.925 |
Token | On |
Token ID | 1550 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
aukee | +0.921 |
nesday | +0.786 |
tnc | +0.757 |
icum | +0.703 |
agara | +0.702 |
Neg logit contributions | |
ANS | -0.579 |
Malik | -0.564 |
amb | -0.548 |
subtitles | -0.521 |
headphone | -0.505 |
Token | September |
Token ID | 2693 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
aukee | +0.258 |
nesday | +0.215 |
tnc | +0.205 |
ngth | +0.195 |
agara | +0.193 |
Neg logit contributions | |
ANS | -0.174 |
Malik | -0.172 |
amb | -0.168 |
subtitles | -0.159 |
シ | -0.154 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
aukee | +0.053 |
nesday | +0.045 |
tnc | +0.042 |
agara | +0.039 |
icum | +0.038 |
Neg logit contributions | |
ANS | -0.046 |
Malik | -0.044 |
amb | -0.043 |
subtitles | -0.042 |
シ | -0.041 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
aukee | +1.044 |
nesday | +0.909 |
tnc | +0.868 |
ngth | +0.823 |
agara | +0.817 |
Neg logit contributions | |
ANS | -0.539 |
Malik | -0.536 |
amb | -0.511 |
subtitles | -0.487 |
シ | -0.469 |
Token | United |
Token ID | 1578 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
aukee | +1.570 |
nesday | +1.313 |
tnc | +1.255 |
agara | +1.155 |
icum | +1.154 |
Neg logit contributions | |
ANS | -1.295 |
Malik | -1.260 |
amb | -1.230 |
subtitles | -1.180 |
シ | -1.150 |
Token | States |
Token ID | 1829 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
aukee | +1.266 |
nesday | +1.089 |
tnc | +1.037 |
agara | +0.994 |
icum | +0.983 |
Neg logit contributions | |
ANS | -0.583 |
Malik | -0.551 |
amb | -0.531 |
subtitles | -0.501 |
headphone | -0.496 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
aukee | +0.396 |
nesday | +0.337 |
tnc | +0.319 |
agara | +0.297 |
icum | +0.296 |
Neg logit contributions | |
ANS | -0.291 |
Malik | -0.287 |
amb | -0.277 |
subtitles | -0.265 |
シ | -0.257 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
aukee | +0.452 |
nesday | +0.388 |
tnc | +0.370 |
icum | +0.347 |
agara | +0.347 |
Neg logit contributions | |
ANS | -0.273 |
Malik | -0.264 |
amb | -0.255 |
subtitles | -0.244 |
シ | -0.238 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aukee | +0.619 |
nesday | +0.528 |
tnc | +0.492 |
icum | +0.467 |
agara | +0.464 |
Neg logit contributions | |
ANS | -0.465 |
Malik | -0.455 |
amb | -0.438 |
subtitles | -0.424 |
シ | -0.413 |
Token | # |
Token ID | 1303 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
aukee | +2.051 |
nesday | +1.617 |
tnc | +1.417 |
agara | +1.253 |
icum | +1.226 |
Neg logit contributions | |
ANS | -3.718 |
Malik | -3.626 |
amb | -3.525 |
subtitles | -3.427 |
シ | -3.415 |
Token | 17 |
Token ID | 1558 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aukee | +2.098 |
nesday | +1.835 |
tnc | +1.736 |
icum | +1.657 |
akespe | +1.656 |
Neg logit contributions | |
ANS | -0.869 |
Malik | -0.825 |
amb | -0.793 |
subtitles | -0.732 |
シ | -0.710 |
Token | Good |
Token ID | 4599 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
aukee | +1.048 |
nesday | +0.894 |
tnc | +0.862 |
icum | +0.800 |
agara | +0.799 |
Neg logit contributions | |
ANS | -0.645 |
Malik | -0.628 |
amb | -0.610 |
subtitles | -0.580 |
headphone | -0.562 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
aukee | +1.195 |
nesday | +1.036 |
tnc | +0.995 |
agara | +0.934 |
icum | +0.933 |
Neg logit contributions | |
ANS | -0.619 |
Malik | -0.597 |
amb | -0.576 |
subtitles | -0.545 |
シ | -0.527 |
Token | hear |
Token ID | 3285 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
aukee | +0.455 |
nesday | +0.386 |
tnc | +0.370 |
agara | +0.342 |
icum | +0.342 |
Neg logit contributions | |
ANS | -0.318 |
Malik | -0.309 |
amb | -0.301 |
subtitles | -0.287 |
シ | -0.279 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
aukee | +0.889 |
nesday | +0.772 |
tnc | +0.737 |
agara | +0.695 |
ngth | +0.690 |
Neg logit contributions | |
ANS | -0.477 |
Malik | -0.474 |
amb | -0.448 |
subtitles | -0.428 |
シ | -0.413 |
Token | United |
Token ID | 1578 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
aukee | +1.081 |
nesday | +0.907 |
tnc | +0.866 |
agara | +0.797 |
icum | +0.797 |
Neg logit contributions | |
ANS | -0.878 |
Malik | -0.855 |
amb | -0.834 |
subtitles | -0.799 |
シ | -0.779 |
Token | States |
Token ID | 1829 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
aukee | +1.107 |
nesday | +0.975 |
tnc | +0.942 |
icum | +0.890 |
agara | +0.889 |
Neg logit contributions | |
ANS | -0.396 |
Malik | -0.381 |
amb | -0.363 |
subtitles | -0.338 |
シ | -0.322 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
aukee | +0.357 |
nesday | +0.303 |
tnc | +0.287 |
agara | +0.266 |
icum | +0.266 |
Neg logit contributions | |
ANS | -0.270 |
Malik | -0.266 |
amb | -0.257 |
subtitles | -0.247 |
シ | -0.239 |
Token | 83 |
Token ID | 5999 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
aukee | +0.565 |
nesday | +0.487 |
tnc | +0.467 |
icum | +0.438 |
agara | +0.437 |
Neg logit contributions | |
ANS | -0.317 |
Malik | -0.307 |
amb | -0.296 |
subtitles | -0.282 |
シ | -0.274 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
aukee | +0.337 |
nesday | +0.289 |
tnc | +0.267 |
icum | +0.255 |
agara | +0.252 |
Neg logit contributions | |
ANS | -0.255 |
Malik | -0.249 |
amb | -0.240 |
subtitles | -0.233 |
シ | -0.226 |
Token | Last |
Token ID | 4586 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
aukee | +2.067 |
nesday | +1.636 |
tnc | +1.436 |
agara | +1.274 |
icum | +1.244 |
Neg logit contributions | |
ANS | -3.672 |
Malik | -3.568 |
amb | -3.477 |
subtitles | -3.382 |
シ | -3.365 |
Token | Edited |
Token ID | 34212 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
aukee | +0.015 |
nesday | +0.013 |
tnc | +0.012 |
akespe | +0.012 |
ngth | +0.012 |
Neg logit contributions | |
ANS | -0.004 |
Malik | -0.004 |
amb | -0.004 |
subtitles | -0.004 |
SPD | -0.003 |
Token | : |
Token ID | 25 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
aukee | +1.031 |
nesday | +0.886 |
tnc | +0.836 |
ngth | +0.803 |
akespe | +0.798 |
Neg logit contributions | |
ANS | -0.574 |
Malik | -0.559 |
amb | -0.538 |
subtitles | -0.511 |
シ | -0.502 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Malik | +0.051 |
ANS | +0.051 |
amb | +0.049 |
subtitles | +0.046 |
シ | +0.045 |
Neg logit contributions | |
aukee | -0.086 |
nesday | -0.073 |
tnc | -0.069 |
ngth | -0.068 |
akespe | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
aukee | +0.633 |
nesday | +0.555 |
tnc | +0.516 |
ngth | +0.505 |
agara | +0.499 |
Neg logit contributions | |
ANS | -0.258 |
Malik | -0.248 |
amb | -0.235 |
subtitles | -0.221 |
シ | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
aukee | +0.671 |
nesday | +0.576 |
tnc | +0.554 |
icum | +0.516 |
agara | +0.516 |
Neg logit contributions | |
ANS | -0.403 |
Malik | -0.391 |
amb | -0.379 |
subtitles | -0.360 |
シ | -0.349 |
Token | Flag |
Token ID | 19762 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
aukee | +0.365 |
nesday | +0.312 |
tnc | +0.298 |
agara | +0.279 |
akespe | +0.277 |
Neg logit contributions | |
ANS | -0.244 |
Malik | -0.242 |
amb | -0.229 |
subtitles | -0.220 |
SPD | -0.213 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
aukee | +0.062 |
nesday | +0.051 |
tnc | +0.049 |
icum | +0.045 |
agara | +0.045 |
Neg logit contributions | |
ANS | -0.056 |
Malik | -0.055 |
amb | -0.053 |
subtitles | -0.051 |
シ | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
aukee | +0.746 |
nesday | +0.644 |
tnc | +0.585 |
ngth | +0.571 |
akespe | +0.564 |
Neg logit contributions | |
ANS | -0.542 |
Malik | -0.530 |
amb | -0.514 |
subtitles | -0.489 |
シ | -0.478 |
Token | Flag |
Token ID | 34227 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
aukee | +0.633 |
nesday | +0.549 |
tnc | +0.491 |
ngth | +0.487 |
agara | +0.480 |
Neg logit contributions | |
ANS | -0.475 |
Malik | -0.451 |
amb | -0.434 |
シ | -0.418 |
subtitles | -0.415 |
Token | Reply |
Token ID | 14883 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
aukee | +0.538 |
nesday | +0.459 |
tnc | +0.436 |
agara | +0.411 |
icum | +0.409 |
Neg logit contributions | |
Malik | -0.354 |
ANS | -0.353 |
amb | -0.339 |
subtitles | -0.321 |
dispatch | -0.310 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
aukee | +3.162 |
nesday | +2.659 |
tnc | +2.497 |
agara | +2.320 |
icum | +2.318 |
Neg logit contributions | |
ANS | -2.632 |
Malik | -2.588 |
amb | -2.504 |
subtitles | -2.409 |
シ | -2.340 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
aukee | +0.676 |
nesday | +0.584 |
tnc | +0.531 |
ngth | +0.518 |
akespe | +0.511 |
Neg logit contributions | |
ANS | -0.489 |
Malik | -0.479 |
amb | -0.463 |
subtitles | -0.440 |
シ | -0.432 |
Token | 55 |
Token ID | 2816 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
aukee | +0.560 |
nesday | +0.489 |
tnc | +0.463 |
agara | +0.442 |
icum | +0.441 |
Neg logit contributions | |
ANS | -0.260 |
Malik | -0.248 |
amb | -0.237 |
subtitles | -0.224 |
シ | -0.219 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Malik | +0.542 |
ANS | +0.534 |
amb | +0.507 |
SPD | +0.476 |
subtitles | +0.476 |
Neg logit contributions | |
aukee | -0.967 |
nesday | -0.838 |
tnc | -0.788 |
ngth | -0.754 |
akespe | -0.750 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
aukee | +1.375 |
nesday | +1.178 |
tnc | +1.086 |
ngth | +1.036 |
akespe | +1.022 |
Neg logit contributions | |
ANS | -1.047 |
Malik | -1.032 |
amb | -0.997 |
subtitles | -0.951 |
シ | -0.927 |
Token | June |
Token ID | 2795 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
aukee | +1.416 |
nesday | +1.185 |
tnc | +1.134 |
agara | +1.046 |
icum | +1.044 |
Neg logit contributions | |
ANS | -1.127 |
Malik | -1.108 |
amb | -1.076 |
subtitles | -1.032 |
シ | -1.003 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
aukee | +0.301 |
nesday | +0.263 |
tnc | +0.250 |
ngth | +0.237 |
agara | +0.236 |
Neg logit contributions | |
Malik | -0.156 |
ANS | -0.155 |
amb | -0.147 |
subtitles | -0.141 |
シ | -0.135 |
Token | Germany |
Token ID | 4486 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
aukee | +1.131 |
nesday | +0.948 |
tnc | +0.904 |
agara | +0.832 |
icum | +0.832 |
Neg logit contributions | |
ANS | -0.934 |
Malik | -0.911 |
amb | -0.887 |
subtitles | -0.852 |
シ | -0.830 |
Token | 247 |
Token ID | 30179 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
aukee | +0.956 |
nesday | +0.812 |
tnc | +0.771 |
agara | +0.717 |
icum | +0.714 |
Neg logit contributions | |
ANS | -0.703 |
Malik | -0.689 |
amb | -0.664 |
subtitles | -0.639 |
シ | -0.621 |
Token | 34 |
Token ID | 2682 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
aukee | +1.245 |
nesday | +1.067 |
tnc | +1.021 |
icum | +0.953 |
agara | +0.953 |
Neg logit contributions | |
ANS | -0.779 |
Malik | -0.757 |
amb | -0.732 |
subtitles | -0.698 |
シ | -0.678 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ANS | +0.151 |
Malik | +0.148 |
amb | +0.141 |
subtitles | +0.138 |
シ | +0.135 |
Neg logit contributions | |
aukee | -0.212 |
nesday | -0.183 |
tnc | -0.168 |
ngth | -0.162 |
akespe | -0.161 |
Token | # |
Token ID | 1303 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
aukee | +2.033 |
nesday | +1.615 |
tnc | +1.424 |
agara | +1.264 |
icum | +1.231 |
Neg logit contributions | |
ANS | -3.536 |
Malik | -3.447 |
amb | -3.354 |
subtitles | -3.254 |
シ | -3.237 |
Token | 20 |
Token ID | 1238 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
aukee | +2.215 |
nesday | +1.907 |
tnc | +1.794 |
agara | +1.723 |
ngth | +1.708 |
Neg logit contributions | |
ANS | -1.117 |
Malik | -1.043 |
amb | -1.016 |
subtitles | -0.964 |
シ | -0.936 |
Token | Nice |
Token ID | 18460 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
aukee | +0.786 |
nesday | +0.669 |
tnc | +0.644 |
icum | +0.597 |
agara | +0.597 |
Neg logit contributions | |
ANS | -0.506 |
Malik | -0.493 |
amb | -0.479 |
subtitles | -0.456 |
headphone | -0.442 |
Token | , |
Token ID | 11 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
aukee | +0.901 |
nesday | +0.775 |
tnc | +0.745 |
agara | +0.696 |
icum | +0.696 |
Neg logit contributions | |
ANS | -0.513 |
Malik | -0.497 |
amb | -0.481 |
subtitles | -0.456 |
シ | -0.442 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
aukee | +0.562 |
nesday | +0.481 |
tnc | +0.465 |
icum | +0.433 |
agara | +0.432 |
Neg logit contributions | |
ANS | -0.316 |
Malik | -0.308 |
amb | -0.300 |
subtitles | -0.284 |
headphone | -0.274 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
aukee | +0.843 |
nesday | +0.729 |
tnc | +0.701 |
icum | +0.655 |
ngth | +0.655 |
Neg logit contributions | |
ANS | -0.458 |
Malik | -0.449 |
amb | -0.428 |
subtitles | -0.409 |
シ | -0.395 |
Token | United |
Token ID | 1578 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
aukee | +0.975 |
nesday | +0.821 |
tnc | +0.780 |
icum | +0.719 |
agara | +0.718 |
Neg logit contributions | |
ANS | -0.794 |
Malik | -0.777 |
amb | -0.754 |
subtitles | -0.724 |
シ | -0.706 |
Token | States |
Token ID | 1829 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
aukee | +0.946 |
nesday | +0.820 |
tnc | +0.788 |
agara | +0.751 |
icum | +0.746 |
Neg logit contributions | |
ANS | -0.397 |
Malik | -0.377 |
amb | -0.361 |
subtitles | -0.339 |
headphone | -0.327 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
aukee | +0.452 |
nesday | +0.384 |
tnc | +0.365 |
icum | +0.339 |
agara | +0.338 |
Neg logit contributions | |
ANS | -0.332 |
Malik | -0.327 |
amb | -0.315 |
subtitles | -0.303 |
シ | -0.294 |
Token | 240 |
Token ID | 16102 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
aukee | +0.439 |
nesday | +0.372 |
tnc | +0.353 |
icum | +0.327 |
agara | +0.327 |
Neg logit contributions | |
ANS | -0.340 |
Malik | -0.331 |
amb | -0.323 |
subtitles | -0.309 |
シ | -0.302 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aukee | +0.443 |
nesday | +0.381 |
tnc | +0.360 |
icum | +0.335 |
ngth | +0.332 |
Neg logit contributions | |
ANS | -0.331 |
Malik | -0.323 |
amb | -0.317 |
subtitles | -0.303 |
シ | -0.295 |
Token | # |
Token ID | 1303 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
aukee | +2.295 |
nesday | +1.840 |
tnc | +1.693 |
agara | +1.523 |
icum | +1.516 |
Neg logit contributions | |
ANS | -3.241 |
Malik | -3.169 |
amb | -3.094 |
subtitles | -3.008 |
シ | -2.966 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
aukee | +2.047 |
nesday | +1.777 |
tnc | +1.717 |
icum | +1.608 |
agara | +1.607 |
Neg logit contributions | |
ANS | -0.992 |
Malik | -0.960 |
amb | -0.928 |
subtitles | -0.873 |
headphone | -0.842 |
Token | Happy |
Token ID | 14628 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
aukee | +0.823 |
nesday | +0.701 |
tnc | +0.672 |
agara | +0.623 |
icum | +0.623 |
Neg logit contributions | |
ANS | -0.556 |
Malik | -0.541 |
amb | -0.525 |
subtitles | -0.501 |
シ | -0.487 |
Token | it |
Token ID | 340 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
aukee | +0.337 |
nesday | +0.287 |
tnc | +0.276 |
agara | +0.256 |
icum | +0.256 |
Neg logit contributions | |
ANS | -0.223 |
Malik | -0.217 |
amb | -0.211 |
subtitles | -0.201 |
シ | -0.195 |
Token | worked |
Token ID | 3111 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
aukee | +0.696 |
nesday | +0.591 |
tnc | +0.570 |
icum | +0.529 |
agara | +0.529 |
Neg logit contributions | |
ANS | -0.449 |
Malik | -0.436 |
amb | -0.424 |
subtitles | -0.403 |
シ | -0.392 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
aukee | +0.738 |
nesday | +0.648 |
tnc | +0.614 |
ngth | +0.587 |
agara | +0.581 |
Neg logit contributions | |
Malik | -0.368 |
ANS | -0.366 |
amb | -0.346 |
subtitles | -0.329 |
シ | -0.315 |
Token | United |
Token ID | 1578 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
aukee | +0.730 |
nesday | +0.615 |
tnc | +0.583 |
icum | +0.538 |
agara | +0.538 |
Neg logit contributions | |
ANS | -0.595 |
Malik | -0.583 |
amb | -0.566 |
subtitles | -0.543 |
シ | -0.530 |
Token | States |
Token ID | 1829 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
aukee | +0.824 |
nesday | +0.707 |
tnc | +0.673 |
agara | +0.645 |
icum | +0.638 |
Neg logit contributions | |
ANS | -0.380 |
Malik | -0.362 |
amb | -0.347 |
subtitles | -0.329 |
headphone | -0.325 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
aukee | +0.293 |
nesday | +0.249 |
tnc | +0.236 |
agara | +0.220 |
icum | +0.220 |
Neg logit contributions | |
ANS | -0.216 |
Malik | -0.212 |
amb | -0.205 |
subtitles | -0.197 |
シ | -0.191 |
Token | 667 |
Token ID | 28933 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
aukee | +0.649 |
nesday | +0.558 |
tnc | +0.534 |
icum | +0.500 |
agara | +0.500 |
Neg logit contributions | |
ANS | -0.380 |
Malik | -0.368 |
amb | -0.356 |
subtitles | -0.339 |
シ | -0.330 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ANS | +0.131 |
Malik | +0.128 |
amb | +0.124 |
subtitles | +0.120 |
シ | +0.117 |
Neg logit contributions | |
aukee | -0.178 |
nesday | -0.154 |
tnc | -0.143 |
icum | -0.135 |
ngth | -0.135 |
Token | # |
Token ID | 1303 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
aukee | +2.063 |
nesday | +1.643 |
tnc | +1.457 |
agara | +1.302 |
icum | +1.280 |
Neg logit contributions | |
ANS | -3.454 |
Malik | -3.363 |
amb | -3.284 |
subtitles | -3.194 |
シ | -3.165 |
Token | 12 |
Token ID | 1065 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
aukee | +1.987 |
nesday | +1.744 |
tnc | +1.676 |
agara | +1.588 |
icum | +1.586 |
Neg logit contributions | |
ANS | -0.711 |
Malik | -0.672 |
amb | -0.646 |
subtitles | -0.598 |
シ | -0.572 |
Token | I |
Token ID | 314 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
aukee | +0.755 |
nesday | +0.645 |
tnc | +0.621 |
icum | +0.577 |
agara | +0.576 |
Neg logit contributions | |
ANS | -0.471 |
Malik | -0.459 |
amb | -0.446 |
subtitles | -0.424 |
headphone | -0.411 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
aukee | +0.467 |
nesday | +0.400 |
tnc | +0.385 |
icum | +0.356 |
agara | +0.355 |
Neg logit contributions | |
ANS | -0.290 |
Malik | -0.279 |
amb | -0.274 |
subtitles | -0.258 |
headphone | -0.250 |
Token | glad |
Token ID | 9675 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
aukee | +0.814 |
nesday | +0.704 |
tnc | +0.680 |
agara | +0.634 |
icum | +0.634 |
Neg logit contributions | |
ANS | -0.419 |
Malik | -0.406 |
amb | -0.398 |
subtitles | -0.373 |
headphone | -0.358 |
Token | ? |
Token ID | 30 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aukee | +0.026 |
nesday | +0.022 |
tnc | +0.021 |
agara | +0.019 |
icum | +0.019 |
Neg logit contributions | |
ANS | -0.017 |
Malik | -0.017 |
amb | -0.016 |
subtitles | -0.015 |
シ | -0.015 |
Token | Flag |
Token ID | 19762 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
aukee | +0.375 |
nesday | +0.320 |
tnc | +0.305 |
agara | +0.285 |
icum | +0.283 |
Neg logit contributions | |
ANS | -0.258 |
Malik | -0.252 |
amb | -0.243 |
subtitles | -0.232 |
シ | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
ANS | +0.044 |
Malik | +0.043 |
amb | +0.041 |
subtitles | +0.040 |
シ | +0.039 |
Neg logit contributions | |
aukee | -0.052 |
nesday | -0.044 |
tnc | -0.042 |
agara | -0.039 |
icum | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
aukee | +0.229 |
nesday | +0.198 |
tnc | +0.179 |
ngth | +0.176 |
akespe | +0.174 |
Neg logit contributions | |
ANS | -0.161 |
Malik | -0.158 |
amb | -0.153 |
subtitles | -0.145 |
シ | -0.142 |
Token | Flag |
Token ID | 34227 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
aukee | +0.261 |
nesday | +0.227 |
ngth | +0.203 |
tnc | +0.199 |
akespe | +0.198 |
Neg logit contributions | |
ANS | -0.189 |
Malik | -0.177 |
amb | -0.171 |
シ | -0.166 |
subtitles | -0.163 |
Token | Reply |
Token ID | 14883 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aukee | +0.511 |
nesday | +0.436 |
tnc | +0.409 |
agara | +0.389 |
akespe | +0.387 |
Neg logit contributions | |
Malik | -0.336 |
ANS | -0.334 |
amb | -0.320 |
subtitles | -0.303 |
SPD | -0.293 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
aukee | +3.099 |
nesday | +2.614 |
tnc | +2.438 |
agara | +2.275 |
icum | +2.271 |
Neg logit contributions | |
ANS | -2.556 |
Malik | -2.505 |
amb | -2.429 |
subtitles | -2.333 |
シ | -2.274 |
Token |
|
Token ID | 198 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
aukee | +0.335 |
nesday | +0.291 |
tnc | +0.263 |
ngth | +0.258 |
akespe | +0.255 |
Neg logit contributions | |
ANS | -0.237 |
Malik | -0.232 |
amb | -0.224 |
subtitles | -0.213 |
シ | -0.209 |
Token | 27 |
Token ID | 1983 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
aukee | +0.170 |
nesday | +0.148 |
tnc | +0.139 |
agara | +0.134 |
icum | +0.134 |
Neg logit contributions | |
ANS | -0.079 |
Malik | -0.075 |
amb | -0.072 |
subtitles | -0.068 |
シ | -0.067 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Malik | +0.584 |
ANS | +0.576 |
amb | +0.541 |
subtitles | +0.512 |
SPD | +0.512 |
Neg logit contributions | |
aukee | -1.030 |
nesday | -0.898 |
tnc | -0.831 |
ngth | -0.811 |
akespe | -0.807 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
aukee | +1.398 |
nesday | +1.200 |
tnc | +1.103 |
ngth | +1.056 |
akespe | +1.043 |
Neg logit contributions | |
ANS | -1.051 |
Malik | -1.038 |
amb | -1.003 |
subtitles | -0.955 |
シ | -0.930 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
aukee | +0.490 |
nesday | +0.425 |
tnc | +0.406 |
ngth | +0.382 |
agara | +0.381 |
Neg logit contributions | |
ANS | -0.270 |
Malik | -0.267 |
amb | -0.254 |
subtitles | -0.242 |
シ | -0.234 |
Token | United |
Token ID | 1578 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aukee | +1.068 |
nesday | +0.896 |
tnc | +0.853 |
agara | +0.786 |
icum | +0.785 |
Neg logit contributions | |
ANS | -0.883 |
Malik | -0.862 |
amb | -0.840 |
subtitles | -0.806 |
シ | -0.786 |
Token | States |
Token ID | 1829 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
aukee | +1.255 |
nesday | +1.084 |
tnc | +1.021 |
agara | +0.984 |
icum | +0.972 |
Neg logit contributions | |
ANS | -0.582 |
Malik | -0.552 |
amb | -0.533 |
subtitles | -0.508 |
headphone | -0.497 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
aukee | +0.247 |
nesday | +0.210 |
tnc | +0.199 |
agara | +0.185 |
icum | +0.185 |
Neg logit contributions | |
ANS | -0.183 |
Malik | -0.180 |
amb | -0.174 |
subtitles | -0.166 |
シ | -0.161 |
Token | 53 |
Token ID | 4310 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
aukee | +0.671 |
nesday | +0.579 |
tnc | +0.554 |
icum | +0.520 |
agara | +0.519 |
Neg logit contributions | |
ANS | -0.377 |
Malik | -0.365 |
amb | -0.353 |
subtitles | -0.335 |
シ | -0.325 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
aukee | +0.521 |
nesday | +0.446 |
tnc | +0.415 |
icum | +0.394 |
akespe | +0.391 |
Neg logit contributions | |
ANS | -0.394 |
Malik | -0.386 |
amb | -0.372 |
subtitles | -0.361 |
シ | -0.351 |
Token | # |
Token ID | 1303 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
aukee | +2.030 |
nesday | +1.617 |
tnc | +1.422 |
agara | +1.275 |
icum | +1.248 |
Neg logit contributions | |
ANS | -3.446 |
Malik | -3.352 |
amb | -3.264 |
subtitles | -3.172 |
シ | -3.149 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
aukee | +2.085 |
nesday | +1.812 |
tnc | +1.718 |
icum | +1.623 |
agara | +1.621 |
Neg logit contributions | |
ANS | -1.015 |
Malik | -0.972 |
amb | -0.943 |
subtitles | -0.886 |
シ | -0.857 |
Token | honestly |
Token ID | 12698 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
aukee | +0.935 |
nesday | +0.798 |
tnc | +0.768 |
icum | +0.714 |
agara | +0.713 |
Neg logit contributions | |
ANS | -0.582 |
Malik | -0.567 |
amb | -0.550 |
subtitles | -0.523 |
headphone | -0.507 |
Token | if |
Token ID | 611 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
aukee | +1.850 |
nesday | +1.587 |
tnc | +1.522 |
agara | +1.421 |
icum | +1.421 |
Neg logit contributions | |
ANS | -1.120 |
Malik | -1.085 |
amb | -1.050 |
subtitles | -1.000 |
シ | -0.971 |
Token | we |
Token ID | 356 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
aukee | +0.485 |
nesday | +0.415 |
tnc | +0.400 |
icum | +0.372 |
agara | +0.372 |
Neg logit contributions | |
ANS | -0.283 |
Malik | -0.275 |
amb | -0.267 |
subtitles | -0.254 |
headphone | -0.245 |
Token | cases |
Token ID | 2663 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ANS | +0.007 |
Malik | +0.006 |
amb | +0.006 |
subtitles | +0.006 |
headphone | +0.006 |
Neg logit contributions | |
aukee | -0.014 |
nesday | -0.012 |
tnc | -0.012 |
icum | -0.011 |
agara | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ANS | +0.954 |
Malik | +0.936 |
amb | +0.912 |
subtitles | +0.854 |
dispatch | +0.831 |
Neg logit contributions | |
aukee | -1.556 |
nesday | -1.341 |
tnc | -1.296 |
agara | -1.191 |
icum | -1.186 |
Token | since |
Token ID | 1201 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ANS | +0.403 |
Malik | +0.398 |
amb | +0.387 |
subtitles | +0.366 |
headphone | +0.353 |
Neg logit contributions | |
aukee | -0.664 |
nesday | -0.572 |
tnc | -0.549 |
icum | -0.508 |
agara | -0.505 |
Token | Dartmouth |
Token ID | 47888 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
ANS | +0.502 |
Malik | +0.492 |
amb | +0.472 |
subtitles | +0.446 |
headphone | +0.427 |
Neg logit contributions | |
aukee | -0.911 |
nesday | -0.788 |
tnc | -0.758 |
icum | -0.706 |
agara | -0.705 |
Token | College |
Token ID | 5535 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
aukee | +0.318 |
nesday | +0.273 |
tnc | +0.262 |
agara | +0.242 |
icum | +0.242 |
Neg logit contributions | |
ANS | -0.196 |
Malik | -0.191 |
amb | -0.184 |
subtitles | -0.175 |
headphone | -0.169 |
Token | v |
Token ID | 410 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ANS | +0.404 |
Malik | +0.393 |
amb | +0.380 |
subtitles | +0.358 |
headphone | +0.346 |
Neg logit contributions | |
aukee | -0.696 |
nesday | -0.600 |
tnc | -0.577 |
agara | -0.535 |
icum | -0.533 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Malik | +2.227 |
ANS | +2.097 |
amb | +1.841 |
SPD | +1.777 |
subtitles | +1.772 |
Neg logit contributions | |
aukee | -5.124 |
nesday | -4.699 |
ngth | -4.292 |
tnc | -4.246 |
akespe | -4.204 |
Token | Woodward |
Token ID | 40782 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ANS | +0.521 |
Malik | +0.518 |
amb | +0.492 |
subtitles | +0.471 |
シ | +0.462 |
Neg logit contributions | |
aukee | -0.637 |
nesday | -0.545 |
tnc | -0.509 |
icum | -0.474 |
agara | -0.470 |
Token | in |
Token ID | 287 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
aukee | +0.459 |
nesday | +0.394 |
tnc | +0.379 |
agara | +0.353 |
icum | +0.353 |
Neg logit contributions | |
ANS | -0.269 |
Malik | -0.260 |
amb | -0.252 |
subtitles | -0.240 |
シ | -0.232 |
Token | 18 |
Token ID | 1248 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
ANS | +0.363 |
Malik | +0.355 |
amb | +0.343 |
subtitles | +0.319 |
headphone | +0.312 |
Neg logit contributions | |
aukee | -0.653 |
nesday | -0.567 |
tnc | -0.541 |
ngth | -0.507 |
agara | -0.504 |
Token | 19 |
Token ID | 1129 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
aukee | +0.380 |
nesday | +0.335 |
tnc | +0.313 |
ngth | +0.303 |
akespe | +0.301 |
Neg logit contributions | |
ANS | -0.178 |
Malik | -0.169 |
amb | -0.161 |
subtitles | -0.151 |
シ | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
ANS | +0.541 |
Malik | +0.533 |
amb | +0.511 |
subtitles | +0.489 |
headphone | +0.470 |
Neg logit contributions | |
aukee | -0.845 |
nesday | -0.728 |
tnc | -0.695 |
icum | -0.650 |
agara | -0.646 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ANS | +0.218 |
Malik | +0.210 |
amb | +0.201 |
subtitles | +0.190 |
シ | +0.190 |
Neg logit contributions | |
aukee | -0.298 |
nesday | -0.261 |
tnc | -0.233 |
ngth | -0.231 |
akespe | -0.227 |
Token | Santa |
Token ID | 42694 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
ANS | +0.433 |
Malik | +0.418 |
amb | +0.407 |
subtitles | +0.389 |
シ | +0.381 |
Neg logit contributions | |
aukee | -0.558 |
nesday | -0.473 |
tnc | -0.447 |
icum | -0.414 |
agara | -0.414 |
Token | Clara |
Token ID | 27443 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ANS | +0.077 |
Malik | +0.076 |
amb | +0.074 |
subtitles | +0.071 |
シ | +0.069 |
Neg logit contributions | |
aukee | -0.080 |
nesday | -0.067 |
tnc | -0.063 |
agara | -0.058 |
icum | -0.057 |
Token | County |
Token ID | 3418 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ANS | +0.164 |
Malik | +0.160 |
amb | +0.156 |
subtitles | +0.150 |
シ | +0.146 |
Neg logit contributions | |
aukee | -0.193 |
nesday | -0.161 |
tnc | -0.153 |
icum | -0.141 |
agara | -0.141 |
Token | v |
Token ID | 410 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aukee | +0.550 |
nesday | +0.471 |
tnc | +0.452 |
agara | +0.421 |
icum | +0.421 |
Neg logit contributions | |
ANS | -0.340 |
Malik | -0.330 |
amb | -0.320 |
subtitles | -0.304 |
シ | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ANS | +2.437 |
Malik | +2.358 |
amb | +2.295 |
subtitles | +2.183 |
シ | +2.115 |
Neg logit contributions | |
aukee | -4.002 |
nesday | -3.428 |
tnc | -3.295 |
agara | -3.068 |
icum | -3.068 |
Token | Southern |
Token ID | 8050 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
ANS | +0.465 |
Malik | +0.455 |
amb | +0.439 |
subtitles | +0.420 |
シ | +0.408 |
Neg logit contributions | |
aukee | -0.685 |
nesday | -0.584 |
tnc | -0.557 |
icum | -0.519 |
agara | -0.518 |
Token | Pacific |
Token ID | 8211 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
aukee | +0.208 |
nesday | +0.177 |
tnc | +0.170 |
agara | +0.157 |
icum | +0.156 |
Neg logit contributions | |
ANS | -0.145 |
Malik | -0.141 |
amb | -0.137 |
subtitles | -0.131 |
シ | -0.127 |
Token | Railroad |
Token ID | 36289 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
aukee | +0.966 |
nesday | +0.830 |
tnc | +0.798 |
agara | +0.745 |
icum | +0.745 |
Neg logit contributions | |
ANS | -0.554 |
Malik | -0.537 |
amb | -0.520 |
subtitles | -0.493 |
シ | -0.478 |
Token | Company |
Token ID | 5834 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ANS | +0.167 |
Malik | +0.162 |
amb | +0.157 |
subtitles | +0.150 |
headphone | +0.146 |
Neg logit contributions | |
aukee | -0.245 |
nesday | -0.210 |
tnc | -0.200 |
icum | -0.186 |
agara | -0.186 |
Token | not |
Token ID | 407 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ANS | +0.106 |
Malik | +0.104 |
amb | +0.102 |
subtitles | +0.095 |
headphone | +0.093 |
Neg logit contributions | |
aukee | -0.189 |
nesday | -0.162 |
tnc | -0.157 |
icum | -0.146 |
agara | -0.146 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ANS | +0.067 |
Malik | +0.065 |
amb | +0.065 |
subtitles | +0.060 |
headphone | +0.059 |
Neg logit contributions | |
aukee | -0.123 |
nesday | -0.106 |
tnc | -0.103 |
icum | -0.096 |
agara | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
ANS | +0.270 |
Malik | +0.265 |
amb | +0.257 |
subtitles | +0.241 |
headphone | +0.235 |
Neg logit contributions | |
aukee | -0.494 |
nesday | -0.426 |
tnc | -0.411 |
icum | -0.384 |
agara | -0.384 |
Token | total |
Token ID | 2472 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ANS | +0.135 |
Malik | +0.132 |
amb | +0.129 |
subtitles | +0.120 |
headphone | +0.117 |
Neg logit contributions | |
aukee | -0.252 |
nesday | -0.219 |
tnc | -0.209 |
agara | -0.197 |
icum | -0.196 |
Token | Loving |
Token ID | 39202 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
aukee | +1.098 |
nesday | +0.948 |
tnc | +0.911 |
agara | +0.849 |
icum | +0.849 |
Neg logit contributions | |
ANS | -0.602 |
Malik | -0.586 |
amb | -0.571 |
subtitles | -0.534 |
headphone | -0.520 |
Token | v |
Token ID | 410 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ANS | +1.365 |
Malik | +1.326 |
amb | +1.290 |
subtitles | +1.185 |
headphone | +1.179 |
Neg logit contributions | |
aukee | -2.550 |
nesday | -2.219 |
tnc | -2.140 |
icum | -2.013 |
agara | -2.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Malik | +1.969 |
ANS | +1.931 |
amb | +1.800 |
シ | +1.648 |
dispatch | +1.642 |
Neg logit contributions | |
aukee | -4.214 |
nesday | -3.755 |
tnc | -3.535 |
ngth | -3.453 |
akespe | -3.362 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
ANS | +0.092 |
Malik | +0.091 |
amb | +0.089 |
subtitles | +0.083 |
シ | +0.083 |
Neg logit contributions | |
aukee | -0.098 |
nesday | -0.084 |
tnc | -0.078 |
ngth | -0.072 |
icum | -0.072 |
Token | victory |
Token ID | 5373 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
aukee | +0.147 |
nesday | +0.128 |
tnc | +0.123 |
agara | +0.116 |
icum | +0.115 |
Neg logit contributions | |
ANS | -0.075 |
Malik | -0.073 |
amb | -0.071 |
subtitles | -0.066 |
headphone | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
ANS | +0.170 |
Malik | +0.166 |
amb | +0.160 |
subtitles | +0.152 |
headphone | +0.147 |
Neg logit contributions | |
aukee | -0.295 |
nesday | -0.253 |
tnc | -0.244 |
agara | -0.228 |
icum | -0.227 |
Token | gay |
Token ID | 5650 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
aukee | +0.188 |
nesday | +0.161 |
tnc | +0.156 |
icum | +0.146 |
agara | +0.146 |
Neg logit contributions | |
ANS | -0.105 |
Malik | -0.103 |
amb | -0.100 |
subtitles | -0.094 |
headphone | -0.091 |
Token | 150 |
Token ID | 6640 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ANS | +0.513 |
Malik | +0.503 |
amb | +0.491 |
subtitles | +0.466 |
headphone | +0.457 |
Neg logit contributions | |
aukee | -0.675 |
nesday | -0.568 |
tnc | -0.546 |
icum | -0.505 |
agara | -0.504 |
Token | th |
Token ID | 400 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ANS | +0.349 |
Malik | +0.341 |
amb | +0.332 |
subtitles | +0.320 |
シ | +0.312 |
Neg logit contributions | |
aukee | -0.400 |
nesday | -0.334 |
tnc | -0.318 |
icum | -0.292 |
agara | -0.292 |
Token | birthday |
Token ID | 10955 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
ANS | +0.564 |
Malik | +0.549 |
amb | +0.534 |
subtitles | +0.511 |
シ | +0.497 |
Neg logit contributions | |
aukee | -0.768 |
nesday | -0.649 |
tnc | -0.621 |
agara | -0.575 |
icum | -0.574 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
aukee | +0.208 |
nesday | +0.182 |
tnc | +0.168 |
icum | +0.153 |
agara | +0.152 |
Neg logit contributions | |
ANS | -0.170 |
Malik | -0.163 |
amb | -0.159 |
subtitles | -0.154 |
シ | -0.149 |
Token | Frank |
Token ID | 5278 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ANS | +0.252 |
Malik | +0.243 |
amb | +0.237 |
subtitles | +0.226 |
シ | +0.219 |
Neg logit contributions | |
aukee | -0.407 |
nesday | -0.349 |
tnc | -0.335 |
agara | -0.312 |
icum | -0.311 |
Token | Lloyd |
Token ID | 22361 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ANS | +0.314 |
Malik | +0.311 |
amb | +0.299 |
subtitles | +0.286 |
headphone | +0.276 |
Neg logit contributions | |
aukee | -0.463 |
nesday | -0.392 |
tnc | -0.377 |
agara | -0.350 |
icum | -0.347 |
Token | Wright |
Token ID | 12206 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Malik | +2.821 |
ANS | +2.801 |
amb | +2.703 |
subtitles | +2.621 |
headphone | +2.537 |
Neg logit contributions | |
aukee | -3.233 |
nesday | -2.763 |
tnc | -2.616 |
agara | -2.477 |
ngth | -2.436 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ANS | +0.355 |
Malik | +0.345 |
amb | +0.334 |
subtitles | +0.317 |
シ | +0.308 |
Neg logit contributions | |
aukee | -0.590 |
nesday | -0.506 |
tnc | -0.487 |
agara | -0.453 |
icum | -0.453 |
Token | America |
Token ID | 2253 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
ANS | +0.243 |
Malik | +0.236 |
amb | +0.229 |
subtitles | +0.217 |
headphone | +0.210 |
Neg logit contributions | |
aukee | -0.413 |
nesday | -0.354 |
tnc | -0.341 |
agara | -0.318 |
icum | -0.318 |
Token | � |
Token ID | 447 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ANS | +0.184 |
Malik | +0.181 |
amb | +0.175 |
subtitles | +0.164 |
headphone | +0.160 |
Neg logit contributions | |
aukee | -0.297 |
nesday | -0.255 |
tnc | -0.246 |
icum | -0.227 |
agara | -0.227 |
Token | � |
Token ID | 247 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ANS | +0.293 |
Malik | +0.289 |
amb | +0.281 |
subtitles | +0.272 |
シ | +0.267 |
Neg logit contributions | |
aukee | -0.264 |
nesday | -0.217 |
tnc | -0.203 |
icum | -0.184 |
agara | -0.183 |
Token | 32 |
Token ID | 2624 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ANS | +0.017 |
Malik | +0.016 |
amb | +0.015 |
subtitles | +0.014 |
シ | +0.014 |
Neg logit contributions | |
aukee | -0.035 |
nesday | -0.030 |
tnc | -0.029 |
icum | -0.027 |
agara | -0.027 |
Token | ) |
Token ID | 8 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ANS | +0.282 |
Malik | +0.270 |
amb | +0.260 |
subtitles | +0.245 |
シ | +0.239 |
Neg logit contributions | |
aukee | -0.626 |
nesday | -0.552 |
tnc | -0.511 |
ngth | -0.494 |
akespe | -0.491 |
Token |
|
Token ID | 198 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
aukee | +0.040 |
nesday | +0.033 |
tnc | +0.031 |
agara | +0.028 |
icum | +0.028 |
Neg logit contributions | |
ANS | -0.042 |
Malik | -0.041 |
amb | -0.040 |
subtitles | -0.038 |
シ | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
ANS | +0.230 |
Malik | +0.225 |
amb | +0.218 |
subtitles | +0.206 |
シ | +0.204 |
Neg logit contributions | |
aukee | -0.334 |
nesday | -0.290 |
tnc | -0.261 |
ngth | -0.257 |
akespe | -0.254 |
Token | Ref |
Token ID | 8134 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ANS | +0.234 |
Malik | +0.224 |
amb | +0.219 |
subtitles | +0.209 |
シ | +0.207 |
Neg logit contributions | |
aukee | -0.310 |
nesday | -0.265 |
tnc | -0.248 |
agara | -0.231 |
icum | -0.231 |
Token | use |
Token ID | 1904 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ANS | +0.839 |
Malik | +0.819 |
amb | +0.804 |
subtitles | +0.755 |
headphone | +0.732 |
Neg logit contributions | |
aukee | -1.200 |
nesday | -1.016 |
tnc | -0.975 |
icum | -0.897 |
agara | -0.897 |
Token | to |
Token ID | 284 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
ANS | +2.082 |
Malik | +2.022 |
amb | +1.965 |
subtitles | +1.864 |
シ | +1.801 |
Neg logit contributions | |
aukee | -3.539 |
nesday | -3.041 |
tnc | -2.921 |
icum | -2.727 |
agara | -2.725 |
Token | solve |
Token ID | 8494 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ANS | +0.146 |
Malik | +0.141 |
amb | +0.140 |
subtitles | +0.131 |
headphone | +0.127 |
Neg logit contributions | |
aukee | -0.263 |
nesday | -0.227 |
tnc | -0.217 |
icum | -0.204 |
agara | -0.203 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
ANS | +0.410 |
Malik | +0.399 |
amb | +0.387 |
subtitles | +0.367 |
headphone | +0.354 |
Neg logit contributions | |
aukee | -0.723 |
nesday | -0.623 |
tnc | -0.598 |
icum | -0.559 |
agara | -0.559 |
Token | first |
Token ID | 717 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
aukee | +0.146 |
nesday | +0.125 |
tnc | +0.120 |
agara | +0.111 |
icum | +0.111 |
Neg logit contributions | |
ANS | -0.094 |
Malik | -0.091 |
amb | -0.089 |
subtitles | -0.084 |
headphone | -0.082 |
Token | test |
Token ID | 1332 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
ANS | +0.101 |
Malik | +0.099 |
amb | +0.097 |
subtitles | +0.092 |
headphone | +0.090 |
Neg logit contributions | |
aukee | -0.140 |
nesday | -0.119 |
tnc | -0.114 |
agara | -0.105 |
icum | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ANS | +0.146 |
Malik | +0.143 |
amb | +0.138 |
subtitles | +0.132 |
シ | +0.127 |
Neg logit contributions | |
aukee | -0.221 |
nesday | -0.189 |
tnc | -0.181 |
icum | -0.168 |
agara | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ANS | +0.143 |
Malik | +0.139 |
amb | +0.136 |
subtitles | +0.127 |
シ | +0.126 |
Neg logit contributions | |
aukee | -0.208 |
nesday | -0.180 |
tnc | -0.163 |
ngth | -0.161 |
��� | -0.158 |
Token | Santa |
Token ID | 42694 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ANS | +0.268 |
Malik | +0.258 |
amb | +0.252 |
subtitles | +0.240 |
シ | +0.236 |
Neg logit contributions | |
aukee | -0.347 |
nesday | -0.294 |
tnc | -0.279 |
agara | -0.258 |
icum | -0.257 |
Token | Clara |
Token ID | 27443 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
aukee | +0.056 |
nesday | +0.047 |
tnc | +0.043 |
ngth | +0.040 |
agara | +0.039 |
Neg logit contributions | |
Malik | -0.059 |
ANS | -0.058 |
amb | -0.058 |
subtitles | -0.055 |
シ | -0.053 |
Token | County |
Token ID | 3418 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
aukee | +0.123 |
nesday | +0.100 |
tnc | +0.096 |
icum | +0.088 |
agara | +0.088 |
Neg logit contributions | |
ANS | -0.116 |
Malik | -0.112 |
amb | -0.110 |
subtitles | -0.106 |
シ | -0.103 |
Token | v |
Token ID | 410 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
aukee | +0.511 |
nesday | +0.439 |
tnc | +0.421 |
agara | +0.391 |
icum | +0.391 |
Neg logit contributions | |
ANS | -0.321 |
Malik | -0.312 |
amb | -0.303 |
subtitles | -0.288 |
headphone | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Malik | +1.749 |
ANS | +1.684 |
amb | +1.523 |
subtitles | +1.476 |
SPD | +1.451 |
Neg logit contributions | |
aukee | -3.893 |
nesday | -3.489 |
tnc | -3.182 |
ngth | -3.171 |
akespe | -3.132 |
Token | Southern |
Token ID | 8050 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ANS | +0.083 |
Malik | +0.078 |
amb | +0.076 |
subtitles | +0.071 |
headphone | +0.069 |
Neg logit contributions | |
aukee | -0.190 |
nesday | -0.165 |
tnc | -0.160 |
agara | -0.151 |
icum | -0.150 |
Token | Pacific |
Token ID | 8211 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aukee | +0.387 |
nesday | +0.342 |
tnc | +0.321 |
ngth | +0.303 |
agara | +0.302 |
Neg logit contributions | |
ANS | -0.187 |
Malik | -0.183 |
amb | -0.175 |
subtitles | -0.163 |
シ | -0.160 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
aukee | +1.108 |
nesday | +0.936 |
tnc | +0.899 |
agara | +0.842 |
icum | +0.838 |
Neg logit contributions | |
ANS | -0.720 |
Malik | -0.695 |
amb | -0.682 |
subtitles | -0.652 |
シ | -0.627 |
Token | Company |
Token ID | 5834 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
aukee | +0.305 |
nesday | +0.259 |
tnc | +0.250 |
icum | +0.236 |
agara | +0.235 |
Neg logit contributions | |
ANS | -0.172 |
Malik | -0.166 |
amb | -0.163 |
subtitles | -0.155 |
シ | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
ANS | +1.031 |
Malik | +1.022 |
amb | +1.002 |
subtitles | +0.903 |
headphone | +0.869 |
Neg logit contributions | |
aukee | -2.152 |
nesday | -1.884 |
tnc | -1.802 |
ngth | -1.682 |
icum | -1.676 |
Token | U |
Token ID | 471 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
aukee | +0.315 |
nesday | +0.273 |
tnc | +0.262 |
icum | +0.246 |
agara | +0.245 |
Neg logit contributions | |
ANS | -0.160 |
Malik | -0.158 |
amb | -0.154 |
subtitles | -0.142 |
headphone | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
aukee | +0.220 |
nesday | +0.190 |
tnc | +0.183 |
icum | +0.171 |
agara | +0.170 |
Neg logit contributions | |
ANS | -0.126 |
Malik | -0.122 |
amb | -0.117 |
subtitles | -0.111 |
シ | -0.108 |
Token | S |
Token ID | 50 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ANS | +0.336 |
Malik | +0.325 |
amb | +0.305 |
シ | +0.293 |
subtitles | +0.288 |
Neg logit contributions | |
aukee | -0.535 |
nesday | -0.469 |
tnc | -0.427 |
ngth | -0.420 |
akespe | -0.416 |
Token | . |
Token ID | 13 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
ANS | +0.355 |
Malik | +0.341 |
amb | +0.326 |
subtitles | +0.302 |
SPD | +0.290 |
Neg logit contributions | |
aukee | -0.726 |
nesday | -0.644 |
tnc | -0.608 |
ngth | -0.585 |
akespe | -0.580 |
Token | v |
Token ID | 410 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
aukee | +0.212 |
nesday | +0.185 |
tnc | +0.178 |
icum | +0.167 |
agara | +0.166 |
Neg logit contributions | |
ANS | -0.109 |
Malik | -0.106 |
amb | -0.103 |
subtitles | -0.096 |
シ | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
Malik | +1.764 |
ANS | +1.634 |
amb | +1.497 |
subtitles | +1.406 |
SPD | +1.401 |
Neg logit contributions | |
aukee | -3.793 |
nesday | -3.387 |
tnc | -3.156 |
ngth | -3.125 |
akespe | -3.060 |
Token | Windsor |
Token ID | 31561 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Malik | +0.048 |
ANS | +0.047 |
amb | +0.045 |
subtitles | +0.043 |
シ | +0.042 |
Neg logit contributions | |
aukee | -0.059 |
nesday | -0.050 |
tnc | -0.047 |
icum | -0.044 |
agara | -0.044 |
Token | struck |
Token ID | 7425 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ANS | +0.259 |
Malik | +0.253 |
amb | +0.246 |
subtitles | +0.231 |
headphone | +0.225 |
Neg logit contributions | |
aukee | -0.415 |
nesday | -0.356 |
tnc | -0.343 |
ngth | -0.319 |
agara | -0.319 |
Token | down |
Token ID | 866 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Malik | +1.171 |
ANS | +1.143 |
amb | +1.131 |
subtitles | +1.055 |
headphone | +1.041 |
Neg logit contributions | |
aukee | -1.987 |
nesday | -1.724 |
tnc | -1.606 |
icum | -1.541 |
ngth | -1.541 |
Token | Section |
Token ID | 7275 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ANS | +0.049 |
Malik | +0.048 |
amb | +0.047 |
subtitles | +0.044 |
headphone | +0.042 |
Neg logit contributions | |
aukee | -0.091 |
nesday | -0.079 |
tnc | -0.075 |
icum | -0.071 |
ngth | -0.070 |
Token | be |
Token ID | 307 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
aukee | +0.068 |
nesday | +0.058 |
tnc | +0.055 |
icum | +0.052 |
agara | +0.051 |
Neg logit contributions | |
ANS | -0.046 |
Malik | -0.045 |
amb | -0.044 |
subtitles | -0.042 |
headphone | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
ANS | +0.026 |
Malik | +0.025 |
amb | +0.025 |
subtitles | +0.023 |
headphone | +0.022 |
Neg logit contributions | |
aukee | -0.049 |
nesday | -0.043 |
tnc | -0.041 |
ngth | -0.039 |
icum | -0.039 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ANS | +0.002 |
Malik | +0.002 |
amb | +0.002 |
subtitles | +0.002 |
headphone | +0.002 |
Neg logit contributions | |
aukee | -0.004 |
nesday | -0.003 |
tnc | -0.003 |
agara | -0.003 |
icum | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
aukee | +1.246 |
nesday | +1.037 |
tnc | +0.988 |
agara | +0.903 |
icum | +0.902 |
Neg logit contributions | |
ANS | -0.985 |
Malik | -0.947 |
amb | -0.907 |
subtitles | -0.891 |
シ | -0.860 |
Token | Loving |
Token ID | 39202 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ANS | +0.200 |
Malik | +0.196 |
amb | +0.190 |
subtitles | +0.179 |
headphone | +0.173 |
Neg logit contributions | |
aukee | -0.345 |
nesday | -0.297 |
tnc | -0.286 |
icum | -0.267 |
agara | -0.267 |
Token | v |
Token ID | 410 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ANS | +1.428 |
Malik | +1.385 |
amb | +1.341 |
subtitles | +1.266 |
headphone | +1.235 |
Neg logit contributions | |
aukee | -2.310 |
nesday | -1.985 |
tnc | -1.928 |
icum | -1.798 |
agara | -1.791 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
Malik | +1.734 |
ANS | +1.675 |
amb | +1.519 |
subtitles | +1.425 |
シ | +1.413 |
Neg logit contributions | |
aukee | -3.769 |
nesday | -3.353 |
tnc | -3.089 |
ngth | -3.078 |
akespe | -3.014 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ANS | +0.072 |
Malik | +0.072 |
amb | +0.070 |
subtitles | +0.066 |
シ | +0.065 |
Neg logit contributions | |
aukee | -0.076 |
nesday | -0.064 |
tnc | -0.059 |
ngth | -0.055 |
icum | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
aukee | +0.550 |
nesday | +0.472 |
tnc | +0.454 |
agara | +0.423 |
icum | +0.423 |
Neg logit contributions | |
ANS | -0.334 |
Malik | -0.324 |
amb | -0.315 |
subtitles | -0.298 |
headphone | -0.289 |
Token | which |
Token ID | 543 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
aukee | +0.063 |
nesday | +0.054 |
tnc | +0.051 |
agara | +0.048 |
icum | +0.048 |
Neg logit contributions | |
ANS | -0.038 |
Malik | -0.037 |
amb | -0.036 |
subtitles | -0.034 |
headphone | -0.033 |
Token | declared |
Token ID | 6875 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
aukee | +0.236 |
nesday | +0.202 |
tnc | +0.196 |
icum | +0.182 |
agara | +0.181 |
Neg logit contributions | |
ANS | -0.140 |
Malik | -0.138 |
amb | -0.133 |
subtitles | -0.125 |
headphone | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ANS | +1.340 |
Malik | +1.325 |
amb | +1.273 |
subtitles | +1.222 |
シ | +1.179 |
Neg logit contributions | |
aukee | -1.738 |
nesday | -1.482 |
tnc | -1.416 |
agara | -1.301 |
icum | -1.294 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ANS | +0.436 |
Malik | +0.427 |
amb | +0.411 |
subtitles | +0.387 |
シ | +0.384 |
Neg logit contributions | |
aukee | -0.644 |
nesday | -0.560 |
tnc | -0.504 |
ngth | -0.501 |
��� | -0.494 |
Token | V |
Token ID | 53 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ANS | +0.405 |
Malik | +0.388 |
amb | +0.377 |
subtitles | +0.361 |
シ | +0.356 |
Neg logit contributions | |
aukee | -0.521 |
nesday | -0.442 |
tnc | -0.415 |
agara | -0.389 |
icum | -0.386 |
Token | il |
Token ID | 346 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ANS | +0.541 |
Malik | +0.527 |
amb | +0.514 |
subtitles | +0.494 |
シ | +0.479 |
Neg logit contributions | |
aukee | -0.736 |
nesday | -0.622 |
tnc | -0.595 |
icum | -0.553 |
agara | -0.551 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
Malik | +0.114 |
ANS | +0.113 |
amb | +0.108 |
bane | +0.102 |
subtitles | +0.098 |
Neg logit contributions | |
aukee | -0.232 |
nesday | -0.202 |
tnc | -0.191 |
ngth | -0.186 |
��� | -0.185 |
Token | v |
Token ID | 410 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
aukee | +0.117 |
nesday | +0.099 |
tnc | +0.095 |
icum | +0.088 |
agara | +0.087 |
Neg logit contributions | |
ANS | -0.082 |
Malik | -0.079 |
amb | -0.078 |
subtitles | -0.074 |
シ | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
Malik | +1.671 |
ANS | +1.601 |
amb | +1.472 |
SPD | +1.430 |
subtitles | +1.419 |
Neg logit contributions | |
aukee | -3.582 |
nesday | -3.161 |
tnc | -2.922 |
akespe | -2.881 |
ngth | -2.879 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ANS | +0.301 |
Malik | +0.292 |
amb | +0.288 |
subtitles | +0.279 |
シ | +0.274 |
Neg logit contributions | |
aukee | -0.228 |
nesday | -0.182 |
tnc | -0.170 |
agara | -0.151 |
icum | -0.150 |
Token | Supplemental |
Token ID | 48165 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
aukee | +0.372 |
nesday | +0.319 |
tnc | +0.307 |
agara | +0.286 |
icum | +0.285 |
Neg logit contributions | |
ANS | -0.228 |
Malik | -0.223 |
amb | -0.215 |
subtitles | -0.204 |
headphone | -0.198 |
Token | Mem |
Token ID | 4942 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
aukee | +0.300 |
nesday | +0.256 |
tnc | +0.246 |
agara | +0.229 |
icum | +0.228 |
Neg logit contributions | |
ANS | -0.198 |
Malik | -0.194 |
amb | -0.188 |
subtitles | -0.179 |
headphone | -0.174 |
Token | o |
Token ID | 78 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ANS | +0.258 |
Malik | +0.258 |
amb | +0.244 |
subtitles | +0.226 |
シ | +0.223 |
Neg logit contributions | |
aukee | -0.531 |
nesday | -0.467 |
tnc | -0.442 |
agara | -0.417 |
icum | -0.415 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
aukee | +0.860 |
nesday | +0.741 |
tnc | +0.710 |
agara | +0.662 |
icum | +0.660 |
Neg logit contributions | |
ANS | -0.503 |
Malik | -0.490 |
amb | -0.472 |
subtitles | -0.448 |
シ | -0.435 |
Token | Company |
Token ID | 5834 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
aukee | +0.173 |
nesday | +0.149 |
tnc | +0.143 |
agara | +0.133 |
icum | +0.133 |
Neg logit contributions | |
ANS | -0.103 |
Malik | -0.100 |
amb | -0.097 |
subtitles | -0.092 |
シ | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ANS | +0.337 |
Malik | +0.328 |
amb | +0.318 |
subtitles | +0.304 |
シ | +0.296 |
Neg logit contributions | |
aukee | -0.479 |
nesday | -0.407 |
tnc | -0.389 |
icum | -0.360 |
agara | -0.360 |
Token |
|
Token ID | 198 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ANS | +0.745 |
Malik | +0.731 |
amb | +0.710 |
subtitles | +0.667 |
シ | +0.660 |
Neg logit contributions | |
aukee | -1.149 |
nesday | -1.004 |
ngth | -0.903 |
��� | -0.902 |
tnc | -0.898 |
Token | California |
Token ID | 25284 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ANS | +0.820 |
Malik | +0.787 |
amb | +0.765 |
subtitles | +0.731 |
シ | +0.725 |
Neg logit contributions | |
aukee | -1.032 |
nesday | -0.879 |
tnc | -0.821 |
icum | -0.761 |
agara | -0.760 |
Token | v |
Token ID | 410 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
ANS | +0.025 |
Malik | +0.024 |
amb | +0.024 |
subtitles | +0.022 |
シ | +0.022 |
Neg logit contributions | |
aukee | -0.040 |
nesday | -0.034 |
tnc | -0.033 |
agara | -0.030 |
icum | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Malik | +1.599 |
ANS | +1.562 |
amb | +1.394 |
subtitles | +1.353 |
SPD | +1.317 |
Neg logit contributions | |
aukee | -3.599 |
nesday | -3.229 |
ngth | -2.950 |
tnc | -2.920 |
akespe | -2.906 |
Token | Southern |
Token ID | 8050 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
aukee | +0.091 |
nesday | +0.078 |
tnc | +0.075 |
icum | +0.070 |
agara | +0.070 |
Neg logit contributions | |
ANS | -0.054 |
Malik | -0.053 |
amb | -0.051 |
subtitles | -0.049 |
シ | -0.047 |
Token | Pacific |
Token ID | 8211 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
aukee | +0.273 |
nesday | +0.231 |
tnc | +0.222 |
icum | +0.208 |
agara | +0.207 |
Neg logit contributions | |
ANS | -0.180 |
Malik | -0.174 |
amb | -0.170 |
subtitles | -0.162 |
シ | -0.157 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aukee | +0.906 |
nesday | +0.771 |
tnc | +0.740 |
agara | +0.691 |
icum | +0.691 |
Neg logit contributions | |
ANS | -0.569 |
Malik | -0.550 |
amb | -0.538 |
subtitles | -0.512 |
シ | -0.495 |
Token | Company |
Token ID | 5834 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
aukee | +0.047 |
nesday | +0.040 |
tnc | +0.039 |
icum | +0.036 |
agara | +0.036 |
Neg logit contributions | |
ANS | -0.026 |
Malik | -0.025 |
amb | -0.025 |
subtitles | -0.023 |
シ | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ANS | +0.049 |
Malik | +0.048 |
amb | +0.047 |
subtitles | +0.044 |
シ | +0.043 |
Neg logit contributions | |
aukee | -0.068 |
nesday | -0.059 |
tnc | -0.054 |
ngth | -0.052 |
akespe | -0.052 |
Token | TABLE |
Token ID | 38148 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ANS | +0.094 |
Malik | +0.090 |
amb | +0.087 |
subtitles | +0.083 |
シ | +0.081 |
Neg logit contributions | |
aukee | -0.140 |
nesday | -0.121 |
tnc | -0.114 |
agara | -0.107 |
icum | -0.107 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ANS | +1.456 |
Malik | +1.419 |
amb | +1.378 |
subtitles | +1.321 |
headphone | +1.285 |
Neg logit contributions | |
aukee | -1.788 |
nesday | -1.501 |
tnc | -1.436 |
icum | -1.319 |
agara | -1.319 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aukee | +0.722 |
nesday | +0.610 |
tnc | +0.585 |
agara | +0.541 |
icum | +0.541 |
Neg logit contributions | |
ANS | -0.519 |
Malik | -0.504 |
amb | -0.491 |
subtitles | -0.469 |
シ | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
aukee | +0.374 |
nesday | +0.323 |
tnc | +0.293 |
ngth | +0.285 |
akespe | +0.282 |
Neg logit contributions | |
ANS | -0.268 |
Malik | -0.261 |
amb | -0.253 |
subtitles | -0.240 |
シ | -0.236 |
Token | Table |
Token ID | 10962 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
aukee | +0.153 |
nesday | +0.131 |
tnc | +0.124 |
agara | +0.116 |
icum | +0.115 |
Neg logit contributions | |
ANS | -0.105 |
Malik | -0.101 |
amb | -0.098 |
subtitles | -0.094 |
シ | -0.092 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ANS | +2.379 |
Malik | +2.311 |
amb | +2.255 |
subtitles | +2.166 |
シ | +2.121 |
Neg logit contributions | |
aukee | -2.674 |
nesday | -2.233 |
tnc | -2.112 |
agara | -1.948 |
icum | -1.947 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
aukee | +0.475 |
nesday | +0.406 |
tnc | +0.389 |
icum | +0.362 |
agara | +0.362 |
Neg logit contributions | |
ANS | -0.304 |
Malik | -0.294 |
amb | -0.286 |
subtitles | -0.272 |
シ | -0.265 |
Token | El |
Token ID | 2574 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
aukee | +1.120 |
nesday | +0.953 |
tnc | +0.913 |
agara | +0.848 |
icum | +0.848 |
Neg logit contributions | |
ANS | -0.757 |
Malik | -0.737 |
amb | -0.715 |
subtitles | -0.682 |
シ | -0.663 |
Token | abor |
Token ID | 4820 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
aukee | +0.258 |
nesday | +0.209 |
tnc | +0.197 |
agara | +0.178 |
icum | +0.178 |
Neg logit contributions | |
ANS | -0.292 |
Malik | -0.286 |
amb | -0.280 |
subtitles | -0.270 |
シ | -0.264 |
Token | ations |
Token ID | 602 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
aukee | +2.175 |
nesday | +1.833 |
tnc | +1.746 |
icum | +1.629 |
agara | +1.617 |
Neg logit contributions | |
ANS | -1.665 |
Malik | -1.619 |
amb | -1.574 |
subtitles | -1.511 |
headphone | -1.472 |
Token | of |
Token ID | 286 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
ANS | +0.303 |
Malik | +0.294 |
amb | +0.285 |
subtitles | +0.272 |
シ | +0.264 |
Neg logit contributions | |
aukee | -0.472 |
nesday | -0.403 |
tnc | -0.387 |
icum | -0.360 |
agara | -0.360 |
Token | his |
Token ID | 465 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ANS | +0.099 |
Malik | +0.095 |
amb | +0.092 |
subtitles | +0.088 |
シ | +0.086 |
Neg logit contributions | |
aukee | -0.161 |
nesday | -0.138 |
tnc | -0.132 |
icum | -0.123 |
agara | -0.123 |
Token | production |
Token ID | 3227 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
aukee | +0.127 |
nesday | +0.109 |
tnc | +0.105 |
agara | +0.098 |
icum | +0.097 |
Neg logit contributions | |
ANS | -0.079 |
Malik | -0.077 |
amb | -0.076 |
subtitles | -0.072 |
headphone | -0.070 |
Token | company |
Token ID | 1664 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
ANS | +0.177 |
Malik | +0.172 |
amb | +0.170 |
subtitles | +0.161 |
headphone | +0.156 |
Neg logit contributions | |
aukee | -0.246 |
nesday | -0.209 |
tnc | -0.200 |
agara | -0.185 |
icum | -0.183 |
Token | , |
Token ID | 11 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
ANS | +0.157 |
Malik | +0.153 |
amb | +0.148 |
subtitles | +0.141 |
シ | +0.136 |
Neg logit contributions | |
aukee | -0.273 |
nesday | -0.235 |
tnc | -0.226 |
agara | -0.211 |
icum | -0.211 |
Token | Zero |
Token ID | 12169 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ANS | +0.018 |
Malik | +0.017 |
amb | +0.017 |
subtitles | +0.016 |
シ | +0.015 |
Neg logit contributions | |
aukee | -0.028 |
nesday | -0.024 |
tnc | -0.023 |
icum | -0.021 |
agara | -0.021 |
Token | Point |
Token ID | 6252 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ANS | +1.956 |
Malik | +1.917 |
amb | +1.870 |
subtitles | +1.773 |
シ | +1.709 |
Neg logit contributions | |
aukee | -3.059 |
nesday | -2.617 |
tnc | -2.522 |
agara | -2.329 |
icum | -2.318 |
Token | Zero |
Token ID | 12169 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ANS | +0.319 |
Malik | +0.310 |
amb | +0.301 |
subtitles | +0.288 |
シ | +0.280 |
Neg logit contributions | |
aukee | -0.461 |
nesday | -0.392 |
tnc | -0.376 |
agara | -0.348 |
icum | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
ANS | +1.614 |
Malik | +1.575 |
amb | +1.532 |
subtitles | +1.455 |
シ | +1.406 |
Neg logit contributions | |
aukee | -2.608 |
nesday | -2.243 |
tnc | -2.158 |
agara | -2.004 |
icum | -1.997 |
Token | have |
Token ID | 423 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
aukee | +0.225 |
nesday | +0.193 |
tnc | +0.185 |
agara | +0.172 |
icum | +0.172 |
Neg logit contributions | |
ANS | -0.136 |
Malik | -0.132 |
amb | -0.128 |
subtitles | -0.122 |
シ | -0.118 |
Token | worked |
Token ID | 3111 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
aukee | +0.106 |
nesday | +0.091 |
tnc | +0.087 |
agara | +0.081 |
icum | +0.081 |
Neg logit contributions | |
ANS | -0.063 |
Malik | -0.062 |
amb | -0.060 |
subtitles | -0.057 |
headphone | -0.055 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
aukee | +1.108 |
nesday | +0.936 |
tnc | +0.899 |
agara | +0.842 |
icum | +0.838 |
Neg logit contributions | |
ANS | -0.720 |
Malik | -0.695 |
amb | -0.682 |
subtitles | -0.652 |
シ | -0.627 |
Token | Company |
Token ID | 5834 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
aukee | +0.305 |
nesday | +0.259 |
tnc | +0.250 |
icum | +0.236 |
agara | +0.235 |
Neg logit contributions | |
ANS | -0.172 |
Malik | -0.166 |
amb | -0.163 |
subtitles | -0.155 |
シ | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ANS | +0.186 |
Malik | +0.180 |
amb | +0.174 |
subtitles | +0.164 |
シ | +0.159 |
Neg logit contributions | |
aukee | -0.346 |
nesday | -0.300 |
tnc | -0.289 |
icum | -0.269 |
agara | -0.269 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ANS | +0.693 |
Malik | +0.674 |
amb | +0.655 |
subtitles | +0.615 |
シ | +0.612 |
Neg logit contributions | |
aukee | -1.039 |
nesday | -0.908 |
ngth | -0.814 |
tnc | -0.812 |
��� | -0.805 |
Token | California |
Token ID | 25284 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
ANS | +0.721 |
Malik | +0.689 |
amb | +0.671 |
subtitles | +0.639 |
シ | +0.632 |
Neg logit contributions | |
aukee | -0.996 |
nesday | -0.852 |
tnc | -0.804 |
agara | -0.745 |
icum | -0.743 |
Token | v |
Token ID | 410 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
aukee | +0.150 |
nesday | +0.129 |
tnc | +0.123 |
agara | +0.114 |
icum | +0.114 |
Neg logit contributions | |
ANS | -0.093 |
Malik | -0.090 |
amb | -0.087 |
subtitles | -0.083 |
headphone | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
Malik | +1.603 |
ANS | +1.552 |
amb | +1.399 |
subtitles | +1.353 |
SPD | +1.322 |
Neg logit contributions | |
aukee | -3.523 |
nesday | -3.163 |
ngth | -2.889 |
tnc | -2.876 |
akespe | -2.836 |
Token | Central |
Token ID | 5694 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
aukee | +0.152 |
nesday | +0.130 |
tnc | +0.124 |
icum | +0.116 |
agara | +0.116 |
Neg logit contributions | |
ANS | -0.095 |
Malik | -0.093 |
amb | -0.089 |
subtitles | -0.085 |
シ | -0.083 |
Token | Pacific |
Token ID | 8211 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
aukee | +0.611 |
nesday | +0.528 |
tnc | +0.505 |
agara | +0.468 |
icum | +0.466 |
Neg logit contributions | |
ANS | -0.366 |
Malik | -0.357 |
amb | -0.344 |
subtitles | -0.327 |
シ | -0.318 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
aukee | +0.860 |
nesday | +0.741 |
tnc | +0.710 |
agara | +0.662 |
icum | +0.660 |
Neg logit contributions | |
ANS | -0.503 |
Malik | -0.490 |
amb | -0.472 |
subtitles | -0.448 |
シ | -0.435 |
Token | Company |
Token ID | 5834 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
aukee | +0.173 |
nesday | +0.149 |
tnc | +0.143 |
agara | +0.133 |
icum | +0.133 |
Neg logit contributions | |
ANS | -0.103 |
Malik | -0.100 |
amb | -0.097 |
subtitles | -0.092 |
シ | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ANS | +0.630 |
Malik | +0.610 |
amb | +0.591 |
subtitles | +0.563 |
シ | +0.546 |
Neg logit contributions | |
aukee | -1.053 |
nesday | -0.902 |
tnc | -0.867 |
agara | -0.809 |
icum | -0.808 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ANS | +0.074 |
Malik | +0.074 |
amb | +0.070 |
subtitles | +0.067 |
シ | +0.066 |
Neg logit contributions | |
aukee | -0.104 |
nesday | -0.089 |
tnc | -0.084 |
agara | -0.079 |
icum | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ANS | +0.378 |
Malik | +0.370 |
amb | +0.359 |
subtitles | +0.337 |
シ | +0.333 |
Neg logit contributions | |
aukee | -0.548 |
nesday | -0.475 |
tnc | -0.430 |
ngth | -0.422 |
akespe | -0.418 |
Token | � |
Token ID | 447 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ANS | +0.291 |
Malik | +0.275 |
amb | +0.266 |
シ | +0.252 |
subtitles | +0.252 |
Neg logit contributions | |
aukee | -0.450 |
nesday | -0.390 |
tnc | -0.362 |
agara | -0.345 |
ngth | -0.343 |
Token | � |
Token ID | 250 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ANS | +0.529 |
Malik | +0.515 |
amb | +0.503 |
subtitles | +0.484 |
headphone | +0.473 |
Neg logit contributions | |
aukee | -0.562 |
nesday | -0.463 |
tnc | -0.442 |
agara | -0.404 |
icum | -0.402 |
Token | Zero |
Token ID | 28667 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
ANS | +0.077 |
Malik | +0.075 |
amb | +0.073 |
subtitles | +0.069 |
シ | +0.068 |
Neg logit contributions | |
aukee | -0.106 |
nesday | -0.090 |
tnc | -0.085 |
agara | -0.079 |
icum | -0.079 |
Token | poverty |
Token ID | 8098 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ANS | +1.888 |
Malik | +1.840 |
amb | +1.788 |
subtitles | +1.686 |
headphone | +1.633 |
Neg logit contributions | |
aukee | -3.112 |
nesday | -2.662 |
tnc | -2.564 |
agara | -2.376 |
icum | -2.348 |
Token | in |
Token ID | 287 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
aukee | +1.004 |
nesday | +0.858 |
tnc | +0.824 |
icum | +0.767 |
agara | +0.766 |
Neg logit contributions | |
ANS | -0.635 |
Malik | -0.617 |
amb | -0.599 |
subtitles | -0.570 |
シ | -0.553 |
Token | four |
Token ID | 1440 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
aukee | +0.220 |
nesday | +0.186 |
tnc | +0.178 |
icum | +0.165 |
agara | +0.165 |
Neg logit contributions | |
ANS | -0.156 |
Malik | -0.153 |
amb | -0.149 |
subtitles | -0.142 |
シ | -0.137 |
Token | years |
Token ID | 812 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ANS | +0.036 |
Malik | +0.035 |
amb | +0.033 |
subtitles | +0.031 |
oteric | +0.030 |
Neg logit contributions | |
aukee | -0.085 |
nesday | -0.074 |
tnc | -0.072 |
icum | -0.068 |
agara | -0.067 |
Token | � |
Token ID | 447 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
aukee | +0.068 |
nesday | +0.059 |
tnc | +0.056 |
icum | +0.052 |
agara | +0.052 |
Neg logit contributions | |
ANS | -0.042 |
Malik | -0.041 |
amb | -0.040 |
subtitles | -0.038 |
シ | -0.037 |
Token | 247 |
Token ID | 23753 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ANS | +1.102 |
Malik | +1.068 |
amb | +1.039 |
subtitles | +0.971 |
シ | +0.942 |
Neg logit contributions | |
aukee | -2.041 |
nesday | -1.720 |
tnc | -1.661 |
icum | -1.568 |
agara | -1.563 |
Token | 409 |
Token ID | 29416 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ANS | +0.653 |
Malik | +0.633 |
amb | +0.622 |
subtitles | +0.582 |
headphone | +0.562 |
Neg logit contributions | |
aukee | -1.136 |
nesday | -0.968 |
tnc | -0.925 |
agara | -0.869 |
icum | -0.869 |
Token | bd |
Token ID | 17457 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ANS | +0.398 |
Malik | +0.386 |
amb | +0.379 |
subtitles | +0.354 |
headphone | +0.342 |
Neg logit contributions | |
aukee | -0.691 |
nesday | -0.588 |
tnc | -0.563 |
icum | -0.529 |
agara | -0.528 |
Token | 28 |
Token ID | 2078 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ANS | +0.426 |
Malik | +0.413 |
amb | +0.403 |
subtitles | +0.377 |
シ | +0.366 |
Neg logit contributions | |
aukee | -0.785 |
nesday | -0.667 |
tnc | -0.641 |
icum | -0.604 |
agara | -0.602 |
Token | f |
Token ID | 69 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ANS | +0.227 |
Malik | +0.220 |
amb | +0.216 |
subtitles | +0.203 |
headphone | +0.196 |
Neg logit contributions | |
aukee | -0.387 |
nesday | -0.328 |
tnc | -0.314 |
icum | -0.295 |
agara | -0.295 |
Token | — |
Token ID | 851 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
ANS | +0.827 |
Malik | +0.795 |
amb | +0.779 |
subtitles | +0.724 |
シ | +0.705 |
Neg logit contributions | |
aukee | -1.479 |
nesday | -1.250 |
tnc | -1.204 |
icum | -1.140 |
agara | -1.125 |
Token | / |
Token ID | 14 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ANS | +1.972 |
Malik | +1.935 |
amb | +1.874 |
subtitles | +1.782 |
headphone | +1.720 |
Neg logit contributions | |
aukee | -3.000 |
nesday | -2.534 |
tnc | -2.438 |
agara | -2.280 |
icum | -2.274 |
Token | prom |
Token ID | 16963 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ANS | +1.034 |
Malik | +1.000 |
amb | +0.977 |
subtitles | +0.932 |
シ | +0.908 |
Neg logit contributions | |
aukee | -1.407 |
nesday | -1.193 |
tnc | -1.136 |
agara | -1.055 |
icum | -1.053 |
Token | pt |
Token ID | 457 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
aukee | +0.770 |
nesday | +0.639 |
tnc | +0.607 |
agara | +0.556 |
icum | +0.556 |
Neg logit contributions | |
ANS | -0.707 |
Malik | -0.691 |
amb | -0.674 |
subtitles | -0.648 |
シ | -0.633 |
Token | log |
Token ID | 6404 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
ANS | +1.114 |
Malik | +1.080 |
amb | +1.052 |
subtitles | +1.005 |
シ | +0.973 |
Neg logit contributions | |
aukee | -1.640 |
nesday | -1.390 |
tnc | -1.332 |
agara | -1.239 |
icum | -1.239 |
Token |
|
Token ID | 198 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ANS | +0.110 |
Malik | +0.107 |
amb | +0.104 |
subtitles | +0.100 |
シ | +0.097 |
Neg logit contributions | |
aukee | -0.156 |
nesday | -0.132 |
tnc | -0.127 |
agara | -0.118 |
icum | -0.117 |
Token | Reporter |
Token ID | 25869 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ANS | +0.287 |
Malik | +0.283 |
amb | +0.274 |
subtitles | +0.259 |
dispatch | +0.249 |
Neg logit contributions | |
aukee | -0.509 |
nesday | -0.437 |
tnc | -0.427 |
icum | -0.394 |
ngth | -0.393 |
Token | claimed |
Token ID | 4752 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
ANS | +0.761 |
Malik | +0.754 |
amb | +0.724 |
subtitles | +0.686 |
dispatch | +0.658 |
Neg logit contributions | |
aukee | -1.361 |
nesday | -1.162 |
tnc | -1.136 |
ngth | -1.049 |
icum | -1.041 |
Token | to |
Token ID | 284 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
ANS | +0.142 |
Malik | +0.138 |
amb | +0.134 |
subtitles | +0.128 |
シ | +0.124 |
Neg logit contributions | |
aukee | -0.213 |
nesday | -0.182 |
tnc | -0.175 |
icum | -0.162 |
agara | -0.162 |
Token | state |
Token ID | 1181 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
ANS | +0.009 |
Malik | +0.009 |
amb | +0.009 |
subtitles | +0.008 |
dispatch | +0.008 |
Neg logit contributions | |
aukee | -0.014 |
nesday | -0.012 |
tnc | -0.011 |
icum | -0.011 |
agara | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
ANS | +0.166 |
Malik | +0.162 |
amb | +0.157 |
subtitles | +0.150 |
headphone | +0.145 |
Neg logit contributions | |
aukee | -0.252 |
nesday | -0.216 |
tnc | -0.207 |
icum | -0.193 |
agara | -0.192 |
Token | sense |
Token ID | 2565 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ANS | +0.156 |
Malik | +0.151 |
amb | +0.147 |
subtitles | +0.138 |
headphone | +0.133 |
Neg logit contributions | |
aukee | -0.311 |
nesday | -0.272 |
tnc | -0.260 |
icum | -0.245 |
agara | -0.243 |
Token | of |
Token ID | 286 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
ANS | +1.825 |
Malik | +1.784 |
amb | +1.753 |
subtitles | +1.628 |
シ | +1.598 |
Neg logit contributions | |
aukee | -3.058 |
nesday | -2.642 |
tnc | -2.535 |
icum | -2.359 |
agara | -2.343 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ANS | +0.195 |
Malik | +0.190 |
amb | +0.186 |
subtitles | +0.174 |
headphone | +0.168 |
Neg logit contributions | |
aukee | -0.356 |
nesday | -0.308 |
tnc | -0.296 |
icum | -0.277 |
agara | -0.275 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ANS | +0.287 |
Malik | +0.278 |
amb | +0.270 |
subtitles | +0.255 |
headphone | +0.246 |
Neg logit contributions | |
aukee | -0.523 |
nesday | -0.454 |
tnc | -0.434 |
icum | -0.407 |
agara | -0.405 |
Token | regarding |
Token ID | 5115 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ANS | +0.246 |
Malik | +0.240 |
amb | +0.234 |
subtitles | +0.220 |
シ | +0.214 |
Neg logit contributions | |
aukee | -0.391 |
nesday | -0.334 |
tnc | -0.320 |
icum | -0.298 |
agara | -0.298 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
aukee | +0.099 |
nesday | +0.085 |
tnc | +0.082 |
icum | +0.077 |
agara | +0.076 |
Neg logit contributions | |
ANS | -0.054 |
Malik | -0.053 |
amb | -0.051 |
subtitles | -0.048 |
headphone | -0.047 |
Token | ( |
Token ID | 357 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ANS | +0.198 |
Malik | +0.193 |
amb | +0.188 |
subtitles | +0.179 |
シ | +0.174 |
Neg logit contributions | |
aukee | -0.300 |
nesday | -0.256 |
tnc | -0.245 |
icum | -0.228 |
agara | -0.228 |
Token | 1979 |
Token ID | 33581 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
aukee | +0.514 |
nesday | +0.444 |
tnc | +0.422 |
agara | +0.397 |
icum | +0.395 |
Neg logit contributions | |
ANS | -0.301 |
Malik | -0.289 |
amb | -0.280 |
subtitles | -0.267 |
シ | -0.262 |
Token | ) |
Token ID | 8 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
aukee | +0.480 |
nesday | +0.406 |
tnc | +0.397 |
icum | +0.370 |
agara | +0.369 |
Neg logit contributions | |
ANS | -0.323 |
Malik | -0.313 |
amb | -0.305 |
subtitles | -0.286 |
headphone | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
aukee | +0.312 |
nesday | +0.254 |
tnc | +0.241 |
icum | +0.222 |
agara | +0.220 |
Neg logit contributions | |
ANS | -0.328 |
Malik | -0.317 |
amb | -0.312 |
subtitles | -0.298 |
headphone | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
ANS | +0.127 |
Malik | +0.124 |
amb | +0.120 |
subtitles | +0.113 |
シ | +0.112 |
Neg logit contributions | |
aukee | -0.181 |
nesday | -0.157 |
tnc | -0.141 |
ngth | -0.138 |
akespe | -0.137 |
Token | Grade |
Token ID | 42233 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
ANS | +0.153 |
Malik | +0.153 |
amb | +0.149 |
subtitles | +0.139 |
headphone | +0.137 |
Neg logit contributions | |
aukee | -0.322 |
nesday | -0.276 |
tnc | -0.273 |
icum | -0.255 |
agara | -0.253 |
Token | : |
Token ID | 25 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
ANS | +1.666 |
Malik | +1.659 |
amb | +1.558 |
シ | +1.460 |
subtitles | +1.459 |
Neg logit contributions | |
aukee | -3.294 |
nesday | -2.962 |
tnc | -2.658 |
ngth | -2.602 |
��� | -2.601 |
Token | A |
Token ID | 317 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
aukee | +0.316 |
nesday | +0.271 |
tnc | +0.259 |
agara | +0.241 |
icum | +0.241 |
Neg logit contributions | |
ANS | -0.202 |
Malik | -0.197 |
amb | -0.191 |
subtitles | -0.182 |
シ | -0.176 |
Token | + |
Token ID | 10 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
aukee | +0.025 |
nesday | +0.021 |
tnc | +0.020 |
icum | +0.019 |
ngth | +0.018 |
Neg logit contributions | |
ANS | -0.022 |
Malik | -0.021 |
amb | -0.021 |
subtitles | -0.020 |
シ | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ANS | +0.216 |
Malik | +0.210 |
amb | +0.208 |
subtitles | +0.198 |
シ | +0.196 |
Neg logit contributions | |
aukee | -0.211 |
nesday | -0.171 |
tnc | -0.163 |
icum | -0.150 |
agara | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
aukee | +0.102 |
nesday | +0.088 |
tnc | +0.080 |
ngth | +0.078 |
akespe | +0.077 |
Neg logit contributions | |
ANS | -0.072 |
Malik | -0.070 |
amb | -0.068 |
subtitles | -0.064 |
シ | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ANS | +1.131 |
Malik | +1.127 |
amb | +1.069 |
subtitles | +1.025 |
SPD | +0.989 |
Neg logit contributions | |
aukee | -1.807 |
nesday | -1.559 |
tnc | -1.501 |
icum | -1.389 |
agara | -1.387 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ANS | +0.508 |
Malik | +0.496 |
amb | +0.479 |
subtitles | +0.452 |
シ | +0.448 |
Neg logit contributions | |
aukee | -0.749 |
nesday | -0.650 |
tnc | -0.585 |
ngth | -0.581 |
��� | -0.572 |
Token | V |
Token ID | 53 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ANS | +0.499 |
Malik | +0.479 |
amb | +0.465 |
subtitles | +0.446 |
シ | +0.439 |
Neg logit contributions | |
aukee | -0.647 |
nesday | -0.549 |
tnc | -0.517 |
agara | -0.482 |
icum | -0.479 |
Token | il |
Token ID | 346 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ANS | +0.400 |
Malik | +0.389 |
amb | +0.384 |
subtitles | +0.373 |
headphone | +0.357 |
Neg logit contributions | |
aukee | -0.527 |
nesday | -0.447 |
tnc | -0.427 |
icum | -0.402 |
agara | -0.393 |
Token | ma |
Token ID | 2611 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aukee | +0.041 |
nesday | +0.036 |
tnc | +0.034 |
ngth | +0.033 |
��� | +0.032 |
Neg logit contributions | |
ANS | -0.020 |
Malik | -0.020 |
amb | -0.019 |
bane | -0.018 |
subtitles | -0.017 |
Token | v |
Token ID | 410 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
aukee | +0.374 |
nesday | +0.317 |
tnc | +0.304 |
icum | +0.282 |
agara | +0.281 |
Neg logit contributions | |
ANS | -0.256 |
Malik | -0.248 |
amb | -0.242 |
subtitles | -0.231 |
シ | -0.225 |
Token | . |
Token ID | 13 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
Malik | +2.293 |
ANS | +2.230 |
amb | +2.124 |
subtitles | +2.066 |
SPD | +2.063 |
Neg logit contributions | |
aukee | -2.648 |
nesday | -2.217 |
tnc | -2.037 |
akespe | -1.948 |
ngth | -1.945 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ANS | +0.258 |
Malik | +0.251 |
amb | +0.247 |
subtitles | +0.239 |
シ | +0.234 |
Neg logit contributions | |
aukee | -0.201 |
nesday | -0.160 |
tnc | -0.151 |
agara | -0.134 |
icum | -0.134 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
aukee | +0.728 |
nesday | +0.621 |
tnc | +0.595 |
agara | +0.553 |
icum | +0.552 |
Neg logit contributions | |
ANS | -0.488 |
Malik | -0.478 |
amb | -0.461 |
subtitles | -0.441 |
headphone | -0.427 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ANS | +0.071 |
Malik | +0.071 |
amb | +0.068 |
subtitles | +0.065 |
headphone | +0.063 |
Neg logit contributions | |
aukee | -0.104 |
nesday | -0.089 |
tnc | -0.085 |
agara | -0.078 |
icum | -0.078 |
Token | 's |
Token ID | 338 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aukee | +0.894 |
nesday | +0.762 |
tnc | +0.731 |
agara | +0.679 |
icum | +0.677 |
Neg logit contributions | |
ANS | -0.601 |
Malik | -0.589 |
amb | -0.569 |
subtitles | -0.542 |
headphone | -0.526 |
Token | said |
Token ID | 531 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aukee | +0.359 |
nesday | +0.310 |
tnc | +0.298 |
agara | +0.279 |
icum | +0.279 |
Neg logit contributions | |
ANS | -0.199 |
Malik | -0.191 |
amb | -0.184 |
subtitles | -0.176 |
シ | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ANS | +0.314 |
Malik | +0.303 |
amb | +0.293 |
subtitles | +0.280 |
シ | +0.273 |
Neg logit contributions | |
aukee | -0.510 |
nesday | -0.436 |
tnc | -0.418 |
icum | -0.390 |
agara | -0.390 |
Token | " |
Token ID | 366 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ANS | +0.058 |
Malik | +0.056 |
amb | +0.056 |
subtitles | +0.054 |
シ | +0.053 |
Neg logit contributions | |
aukee | -0.047 |
nesday | -0.038 |
tnc | -0.035 |
agara | -0.032 |
icum | -0.031 |
Token | I |
Token ID | 40 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
aukee | +0.387 |
nesday | +0.330 |
tnc | +0.308 |
agara | +0.290 |
icum | +0.288 |
Neg logit contributions | |
ANS | -0.300 |
Malik | -0.288 |
amb | -0.276 |
subtitles | -0.265 |
シ | -0.262 |
Token | love |
Token ID | 1842 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
aukee | +0.354 |
nesday | +0.305 |
tnc | +0.294 |
icum | +0.274 |
agara | +0.272 |
Neg logit contributions | |
ANS | -0.193 |
Malik | -0.188 |
amb | -0.185 |
subtitles | -0.171 |
headphone | -0.166 |
Token | Hels |
Token ID | 33889 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
aukee | +0.637 |
nesday | +0.547 |
tnc | +0.525 |
icum | +0.490 |
agara | +0.490 |
Neg logit contributions | |
ANS | -0.380 |
Malik | -0.372 |
amb | -0.361 |
subtitles | -0.342 |
headphone | -0.330 |
Token | ing |
Token ID | 278 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ANS | +2.042 |
Malik | +2.008 |
amb | +1.930 |
subtitles | +1.859 |
headphone | +1.800 |
Neg logit contributions | |
aukee | -2.731 |
nesday | -2.327 |
tnc | -2.224 |
icum | -2.061 |
agara | -2.042 |
Token | borg |
Token ID | 23297 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ANS | +0.309 |
Malik | +0.300 |
amb | +0.290 |
subtitles | +0.272 |
シ | +0.264 |
Neg logit contributions | |
aukee | -0.577 |
nesday | -0.499 |
tnc | -0.480 |
agara | -0.445 |
icum | -0.445 |
Token | and |
Token ID | 290 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
aukee | +0.185 |
nesday | +0.158 |
tnc | +0.152 |
agara | +0.142 |
icum | +0.142 |
Neg logit contributions | |
ANS | -0.112 |
Malik | -0.109 |
amb | -0.106 |
subtitles | -0.100 |
シ | -0.097 |
Token | Sweden |
Token ID | 10710 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ANS | +0.049 |
Malik | +0.048 |
amb | +0.047 |
subtitles | +0.044 |
headphone | +0.043 |
Neg logit contributions | |
aukee | -0.075 |
nesday | -0.064 |
tnc | -0.062 |
agara | -0.057 |
icum | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
aukee | +0.445 |
nesday | +0.381 |
tnc | +0.367 |
icum | +0.341 |
agara | +0.340 |
Neg logit contributions | |
ANS | -0.272 |
Malik | -0.264 |
amb | -0.256 |
subtitles | -0.243 |
シ | -0.235 |
Token | Vector |
Token ID | 20650 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
ANS | +0.848 |
Malik | +0.824 |
amb | +0.799 |
subtitles | +0.752 |
シ | +0.723 |
Neg logit contributions | |
aukee | -1.597 |
nesday | -1.381 |
tnc | -1.329 |
agara | -1.243 |
icum | -1.239 |
Token | < |
Token ID | 27 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ANS | +0.102 |
Malik | +0.098 |
amb | +0.096 |
subtitles | +0.090 |
シ | +0.087 |
Neg logit contributions | |
aukee | -0.188 |
nesday | -0.163 |
tnc | -0.156 |
agara | -0.146 |
icum | -0.146 |
Token | Part |
Token ID | 2142 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ANS | +0.289 |
Malik | +0.278 |
amb | +0.267 |
subtitles | +0.247 |
シ | +0.237 |
Neg logit contributions | |
aukee | -0.740 |
nesday | -0.649 |
tnc | -0.626 |
agara | -0.591 |
icum | -0.588 |
Token | icle |
Token ID | 1548 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ANS | +0.554 |
Malik | +0.543 |
amb | +0.532 |
subtitles | +0.512 |
シ | +0.502 |
Neg logit contributions | |
aukee | -0.526 |
nesday | -0.430 |
tnc | -0.408 |
agara | -0.370 |
icum | -0.367 |
Token | > |
Token ID | 1875 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ANS | +0.891 |
Malik | +0.874 |
amb | +0.857 |
subtitles | +0.825 |
シ | +0.812 |
Neg logit contributions | |
aukee | -0.735 |
nesday | -0.600 |
tnc | -0.561 |
agara | -0.502 |
icum | -0.498 |
Token | & |
Token ID | 1222 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
ANS | +1.312 |
Malik | +1.285 |
amb | +1.266 |
subtitles | +1.211 |
シ | +1.175 |
Neg logit contributions | |
aukee | -1.535 |
nesday | -1.295 |
tnc | -1.230 |
icum | -1.122 |
agara | -1.122 |
Token | particles |
Token ID | 13166 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ANS | +1.695 |
Malik | +1.638 |
amb | +1.611 |
subtitles | +1.531 |
dispatch | +1.462 |
Neg logit contributions | |
aukee | -3.093 |
nesday | -2.678 |
tnc | -2.562 |
icum | -2.392 |
agara | -2.388 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ANS | +1.422 |
Malik | +1.377 |
amb | +1.348 |
subtitles | +1.291 |
シ | +1.266 |
Neg logit contributions | |
aukee | -1.695 |
nesday | -1.444 |
tnc | -1.359 |
agara | -1.249 |
icum | -1.248 |
Token | { |
Token ID | 1391 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ANS | +0.731 |
Malik | +0.705 |
amb | +0.689 |
subtitles | +0.653 |
headphone | +0.630 |
Neg logit contributions | |
aukee | -1.223 |
nesday | -1.051 |
tnc | -1.006 |
icum | -0.938 |
agara | -0.937 |
Token | density |
Token ID | 12109 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
ANS | +0.651 |
Malik | +0.631 |
amb | +0.617 |
subtitles | +0.584 |
headphone | +0.563 |
Neg logit contributions | |
aukee | -1.078 |
nesday | -0.928 |
tnc | -0.886 |
agara | -0.828 |
icum | -0.827 |
Token | Grid |
Token ID | 41339 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ANS | +0.111 |
Malik | +0.109 |
amb | +0.104 |
subtitles | +0.099 |
headphone | +0.096 |
Neg logit contributions | |
aukee | -0.216 |
nesday | -0.185 |
tnc | -0.180 |
agara | -0.167 |
icum | -0.167 |
Token | chairman |
Token ID | 8900 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
ANS | +0.178 |
Malik | +0.176 |
amb | +0.171 |
subtitles | +0.160 |
headphone | +0.156 |
Neg logit contributions | |
aukee | -0.292 |
nesday | -0.250 |
tnc | -0.242 |
agara | -0.223 |
icum | -0.223 |
Token | of |
Token ID | 286 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
ANS | +0.228 |
Malik | +0.218 |
amb | +0.212 |
subtitles | +0.207 |
シ | +0.200 |
Neg logit contributions | |
aukee | -0.294 |
nesday | -0.249 |
tnc | -0.234 |
icum | -0.221 |
agara | -0.220 |
Token | the |
Token ID | 262 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
ANS | +0.061 |
Malik | +0.059 |
amb | +0.057 |
subtitles | +0.055 |
シ | +0.053 |
Neg logit contributions | |
aukee | -0.108 |
nesday | -0.093 |
tnc | -0.089 |
icum | -0.084 |
agara | -0.083 |
Token | Senate |
Token ID | 3845 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ANS | +0.019 |
Malik | +0.018 |
amb | +0.018 |
subtitles | +0.017 |
headphone | +0.016 |
Neg logit contributions | |
aukee | -0.029 |
nesday | -0.025 |
tnc | -0.024 |
agara | -0.022 |
icum | -0.022 |
Token | Finance |
Token ID | 15007 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
aukee | +0.548 |
nesday | +0.474 |
tnc | +0.456 |
agara | +0.427 |
icum | +0.427 |
Neg logit contributions | |
ANS | -0.288 |
Malik | -0.279 |
amb | -0.269 |
subtitles | -0.255 |
シ | -0.246 |
Token | Committee |
Token ID | 4606 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
aukee | +0.875 |
nesday | +0.766 |
tnc | +0.740 |
icum | +0.698 |
agara | +0.698 |
Neg logit contributions | |
ANS | -0.348 |
Malik | -0.334 |
amb | -0.320 |
subtitles | -0.299 |
シ | -0.287 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
aukee | +1.953 |
nesday | +1.671 |
tnc | +1.589 |
icum | +1.508 |
agara | +1.500 |
Neg logit contributions | |
ANS | -1.232 |
Malik | -1.197 |
amb | -1.150 |
subtitles | -1.123 |
シ | -1.089 |
Token | F |
Token ID | 376 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
aukee | +0.111 |
nesday | +0.095 |
tnc | +0.091 |
icum | +0.085 |
agara | +0.085 |
Neg logit contributions | |
ANS | -0.073 |
Malik | -0.072 |
amb | -0.068 |
subtitles | -0.065 |
シ | -0.063 |
Token | ess |
Token ID | 408 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ANS | +0.304 |
Malik | +0.286 |
amb | +0.284 |
subtitles | +0.270 |
oteric | +0.268 |
Neg logit contributions | |
aukee | -0.277 |
nesday | -0.233 |
tnc | -0.211 |
��� | -0.201 |
ngth | -0.192 |
Token | end |
Token ID | 437 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ANS | +0.029 |
amb | +0.028 |
Malik | +0.028 |
subtitles | +0.026 |
シ | +0.026 |
Neg logit contributions | |
aukee | -0.039 |
nesday | -0.033 |
tnc | -0.030 |
��� | -0.029 |
ngth | -0.028 |
Token | en |
Token ID | 268 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ANS | +0.611 |
amb | +0.584 |
Malik | +0.573 |
シ | +0.532 |
dispatch | +0.521 |
Neg logit contributions | |
aukee | -1.036 |
nesday | -0.902 |
��� | -0.854 |
tnc | -0.838 |
ngth | -0.835 |
Token | dread |
Token ID | 15157 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ANS | +0.463 |
Malik | +0.450 |
amb | +0.444 |
subtitles | +0.410 |
headphone | +0.393 |
Neg logit contributions | |
aukee | -1.053 |
nesday | -0.921 |
tnc | -0.888 |
agara | -0.834 |
icum | -0.833 |
Token | and |
Token ID | 290 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
aukee | +0.570 |
nesday | +0.487 |
tnc | +0.467 |
icum | +0.435 |
agara | +0.435 |
Neg logit contributions | |
ANS | -0.368 |
Malik | -0.356 |
amb | -0.345 |
subtitles | -0.330 |
シ | -0.320 |
Token | height |
Token ID | 6001 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
aukee | +0.166 |
nesday | +0.145 |
tnc | +0.140 |
agara | +0.131 |
icum | +0.131 |
Neg logit contributions | |
ANS | -0.077 |
Malik | -0.074 |
amb | -0.071 |
subtitles | -0.067 |
シ | -0.065 |
Token | en |
Token ID | 268 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
aukee | +0.747 |
nesday | +0.612 |
tnc | +0.578 |
icum | +0.534 |
agara | +0.531 |
Neg logit contributions | |
ANS | -0.755 |
Malik | -0.740 |
amb | -0.715 |
subtitles | -0.700 |
シ | -0.678 |
Token | the |
Token ID | 262 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
aukee | +0.333 |
nesday | +0.288 |
tnc | +0.277 |
icum | +0.260 |
agara | +0.260 |
Neg logit contributions | |
ANS | -0.174 |
Malik | -0.166 |
amb | -0.158 |
subtitles | -0.151 |
シ | -0.147 |
Token | action |
Token ID | 2223 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ANS | +0.013 |
Malik | +0.012 |
amb | +0.012 |
subtitles | +0.011 |
シ | +0.011 |
Neg logit contributions | |
aukee | -0.031 |
nesday | -0.027 |
tnc | -0.026 |
agara | -0.025 |
icum | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
aukee | +1.881 |
nesday | +1.602 |
tnc | +1.530 |
icum | +1.456 |
agara | +1.450 |
Neg logit contributions | |
ANS | -1.087 |
Malik | -1.051 |
amb | -0.993 |
subtitles | -0.961 |
シ | -0.930 |
Token | introduced |
Token ID | 5495 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
ANS | +0.168 |
Malik | +0.163 |
amb | +0.158 |
subtitles | +0.150 |
シ | +0.145 |
Neg logit contributions | |
aukee | -0.295 |
nesday | -0.254 |
tnc | -0.245 |
agara | -0.228 |
icum | -0.228 |
Token | plenty |
Token ID | 6088 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ANS | +0.101 |
Malik | +0.097 |
amb | +0.094 |
subtitles | +0.089 |
シ | +0.086 |
Neg logit contributions | |
aukee | -0.180 |
nesday | -0.155 |
tnc | -0.149 |
agara | -0.139 |
icum | -0.139 |
Token | of |
Token ID | 286 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
aukee | +0.920 |
nesday | +0.764 |
tnc | +0.715 |
icum | +0.684 |
agara | +0.669 |
Neg logit contributions | |
ANS | -0.740 |
Malik | -0.709 |
amb | -0.671 |
subtitles | -0.657 |
oteric | -0.639 |
Token | young |
Token ID | 1862 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ANS | +0.664 |
Malik | +0.651 |
amb | +0.641 |
subtitles | +0.602 |
headphone | +0.578 |
Neg logit contributions | |
aukee | -1.266 |
nesday | -1.100 |
tnc | -1.056 |
agara | -0.989 |
icum | -0.986 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
aukee | +0.266 |
nesday | +0.230 |
tnc | +0.221 |
agara | +0.206 |
icum | +0.206 |
Neg logit contributions | |
ANS | -0.146 |
Malik | -0.141 |
amb | -0.139 |
subtitles | -0.130 |
headphone | -0.126 |
Token | their |
Token ID | 511 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ANS | +0.313 |
Malik | +0.307 |
amb | +0.300 |
subtitles | +0.283 |
headphone | +0.272 |
Neg logit contributions | |
aukee | -0.579 |
nesday | -0.499 |
tnc | -0.481 |
agara | -0.449 |
icum | -0.448 |
Token | own |
Token ID | 898 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
aukee | +0.501 |
nesday | +0.435 |
tnc | +0.419 |
agara | +0.393 |
icum | +0.392 |
Neg logit contributions | |
ANS | -0.241 |
Malik | -0.234 |
amb | -0.227 |
subtitles | -0.214 |
headphone | -0.206 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
ANS | +0.286 |
Malik | +0.279 |
amb | +0.273 |
subtitles | +0.257 |
headphone | +0.247 |
Neg logit contributions | |
aukee | -0.587 |
nesday | -0.511 |
tnc | -0.491 |
agara | -0.460 |
icum | -0.459 |
Token | - |
Token ID | 12 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ANS | +0.005 |
Malik | +0.005 |
amb | +0.005 |
subtitles | +0.004 |
headphone | +0.004 |
Neg logit contributions | |
aukee | -0.010 |
nesday | -0.009 |
tnc | -0.008 |
agara | -0.008 |
icum | -0.008 |
Token | liter |
Token ID | 17201 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
aukee | +0.183 |
nesday | +0.156 |
tnc | +0.149 |
agara | +0.139 |
icum | +0.139 |
Neg logit contributions | |
ANS | -0.125 |
Malik | -0.121 |
amb | -0.118 |
subtitles | -0.113 |
シ | -0.109 |
Token | of |
Token ID | 286 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
aukee | +2.168 |
nesday | +1.866 |
tnc | +1.794 |
agara | +1.683 |
icum | +1.682 |
Neg logit contributions | |
ANS | -1.170 |
Malik | -1.130 |
amb | -1.091 |
subtitles | -1.034 |
シ | -1.008 |
Token | Coke |
Token ID | 34723 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
aukee | +0.079 |
nesday | +0.069 |
tnc | +0.066 |
agara | +0.062 |
icum | +0.062 |
Neg logit contributions | |
ANS | -0.042 |
Malik | -0.041 |
amb | -0.040 |
subtitles | -0.038 |
headphone | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
aukee | +1.370 |
nesday | +1.174 |
tnc | +1.129 |
icum | +1.049 |
agara | +1.049 |
Neg logit contributions | |
ANS | -0.852 |
Malik | -0.827 |
amb | -0.805 |
subtitles | -0.766 |
headphone | -0.740 |
Token | some |
Token ID | 617 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
aukee | +0.190 |
nesday | +0.163 |
tnc | +0.157 |
agara | +0.146 |
icum | +0.146 |
Neg logit contributions | |
ANS | -0.111 |
Malik | -0.109 |
amb | -0.106 |
subtitles | -0.100 |
headphone | -0.097 |
Token | red |
Token ID | 2266 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
aukee | +0.160 |
nesday | +0.138 |
tnc | +0.132 |
agara | +0.124 |
icum | +0.123 |
Neg logit contributions | |
ANS | -0.090 |
Malik | -0.088 |
amb | -0.085 |
subtitles | -0.080 |
headphone | -0.078 |
Token | 27 |
Token ID | 1983 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
aukee | +0.170 |
nesday | +0.148 |
tnc | +0.139 |
agara | +0.134 |
icum | +0.134 |
Neg logit contributions | |
ANS | -0.079 |
Malik | -0.075 |
amb | -0.072 |
subtitles | -0.068 |
シ | -0.067 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Malik | +0.584 |
ANS | +0.576 |
amb | +0.541 |
subtitles | +0.512 |
SPD | +0.512 |
Neg logit contributions | |
aukee | -1.030 |
nesday | -0.898 |
tnc | -0.831 |
ngth | -0.811 |
akespe | -0.807 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
aukee | +1.398 |
nesday | +1.200 |
tnc | +1.103 |
ngth | +1.056 |
akespe | +1.043 |
Neg logit contributions | |
ANS | -1.051 |
Malik | -1.038 |
amb | -1.003 |
subtitles | -0.955 |
シ | -0.930 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
aukee | +0.569 |
nesday | +0.491 |
tnc | +0.448 |
ngth | +0.434 |
akespe | +0.429 |
Neg logit contributions | |
ANS | -0.416 |
Malik | -0.408 |
amb | -0.396 |
subtitles | -0.375 |
シ | -0.367 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
aukee | +0.442 |
nesday | +0.395 |
tnc | +0.372 |
ngth | +0.361 |
agara | +0.361 |
Neg logit contributions | |
ANS | -0.135 |
Malik | -0.124 |
amb | -0.115 |
シ | -0.105 |
subtitles | -0.103 |
Token | Share |
Token ID | 8734 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Malik | +0.407 |
ANS | +0.406 |
amb | +0.382 |
SPD | +0.361 |
subtitles | +0.360 |
Neg logit contributions | |
aukee | -0.783 |
nesday | -0.687 |
tnc | -0.651 |
ngth | -0.619 |
agara | -0.614 |
Token | this |
Token ID | 428 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
aukee | +1.911 |
nesday | +1.641 |
tnc | +1.554 |
agara | +1.467 |
ngth | +1.462 |
Neg logit contributions | |
ANS | -1.125 |
Malik | -1.105 |
amb | -1.079 |
subtitles | -1.019 |
headphone | -0.979 |
Token | comment |
Token ID | 2912 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
aukee | +0.103 |
nesday | +0.090 |
tnc | +0.085 |
ngth | +0.083 |
akespe | +0.082 |
Neg logit contributions | |
Malik | -0.041 |
ANS | -0.041 |
amb | -0.040 |
subtitles | -0.037 |
headphone | -0.036 |
Token | on |
Token ID | 319 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
aukee | +1.306 |
nesday | +1.126 |
tnc | +1.055 |
ngth | +1.012 |
akespe | +0.999 |
Neg logit contributions | |
ANS | -0.781 |
Malik | -0.761 |
amb | -0.743 |
subtitles | -0.712 |
dispatch | -0.686 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
ANS | +0.266 |
Malik | +0.264 |
amb | +0.247 |
subtitles | +0.226 |
SPD | +0.221 |
Neg logit contributions | |
aukee | -0.796 |
nesday | -0.708 |
tnc | -0.668 |
ngth | -0.648 |
akespe | -0.646 |
Token | Share |
Token ID | 8734 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
aukee | +0.026 |
nesday | +0.022 |
tnc | +0.021 |
ngth | +0.020 |
akespe | +0.020 |
Neg logit contributions | |
Malik | -0.014 |
ANS | -0.014 |
amb | -0.013 |
subtitles | -0.013 |
SPD | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
aukee | +0.441 |
nesday | +0.369 |
tnc | +0.348 |
icum | +0.326 |
agara | +0.323 |
Neg logit contributions | |
ANS | -0.361 |
Malik | -0.347 |
amb | -0.337 |
subtitles | -0.327 |
シ | -0.316 |
Token | the |
Token ID | 262 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
ANS | +0.095 |
Malik | +0.093 |
amb | +0.091 |
subtitles | +0.086 |
headphone | +0.083 |
Neg logit contributions | |
aukee | -0.166 |
nesday | -0.143 |
tnc | -0.138 |
agara | -0.128 |
icum | -0.128 |
Token | announcement |
Token ID | 8009 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
ANS | +0.094 |
Malik | +0.093 |
amb | +0.090 |
subtitles | +0.084 |
headphone | +0.082 |
Neg logit contributions | |
aukee | -0.177 |
nesday | -0.153 |
tnc | -0.147 |
agara | -0.137 |
icum | -0.137 |
Token | that |
Token ID | 326 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ANS | +0.047 |
Malik | +0.045 |
amb | +0.044 |
subtitles | +0.042 |
シ | +0.041 |
Neg logit contributions | |
aukee | -0.078 |
nesday | -0.066 |
tnc | -0.064 |
agara | -0.060 |
icum | -0.060 |
Token | went |
Token ID | 1816 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ANS | +0.029 |
Malik | +0.029 |
amb | +0.028 |
subtitles | +0.026 |
headphone | +0.026 |
Neg logit contributions | |
aukee | -0.049 |
nesday | -0.042 |
tnc | -0.040 |
agara | -0.037 |
icum | -0.037 |
Token | undone |
Token ID | 45171 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
aukee | +0.222 |
nesday | +0.191 |
tnc | +0.184 |
agara | +0.172 |
icum | +0.172 |
Neg logit contributions | |
ANS | -0.122 |
Malik | -0.116 |
amb | -0.113 |
subtitles | -0.108 |
シ | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
aukee | +2.061 |
nesday | +1.763 |
tnc | +1.690 |
icum | +1.574 |
agara | +1.573 |
Neg logit contributions | |
ANS | -1.291 |
Malik | -1.249 |
amb | -1.212 |
subtitles | -1.155 |
シ | -1.121 |
Token | There |
Token ID | 1318 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ANS | +0.132 |
Malik | +0.131 |
amb | +0.125 |
subtitles | +0.120 |
シ | +0.117 |
Neg logit contributions | |
aukee | -0.191 |
nesday | -0.163 |
tnc | -0.155 |
agara | -0.145 |
icum | -0.145 |
Token | was |
Token ID | 373 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
aukee | +0.421 |
nesday | +0.355 |
tnc | +0.341 |
agara | +0.315 |
icum | +0.314 |
Neg logit contributions | |
ANS | -0.310 |
Malik | -0.302 |
amb | -0.294 |
subtitles | -0.281 |
シ | -0.274 |
Token | no |
Token ID | 645 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ANS | +0.378 |
Malik | +0.369 |
amb | +0.358 |
subtitles | +0.338 |
headphone | +0.325 |
Neg logit contributions | |
aukee | -0.698 |
nesday | -0.601 |
tnc | -0.580 |
icum | -0.541 |
agara | -0.541 |
Token | announcement |
Token ID | 8009 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
ANS | +0.119 |
Malik | +0.116 |
amb | +0.113 |
subtitles | +0.107 |
headphone | +0.103 |
Neg logit contributions | |
aukee | -0.235 |
nesday | -0.203 |
tnc | -0.197 |
agara | -0.183 |
icum | -0.183 |
Token | up |
Token ID | 510 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
ANS | +0.237 |
Malik | +0.233 |
amb | +0.229 |
subtitles | +0.217 |
headphone | +0.210 |
Neg logit contributions | |
aukee | -0.344 |
nesday | -0.293 |
tnc | -0.280 |
agara | -0.260 |
icum | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
ANS | +0.205 |
Malik | +0.201 |
amb | +0.196 |
subtitles | +0.187 |
headphone | +0.181 |
Neg logit contributions | |
aukee | -0.284 |
nesday | -0.240 |
tnc | -0.230 |
agara | -0.213 |
icum | -0.212 |
Token | Her |
Token ID | 2332 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ANS | +0.116 |
Malik | +0.114 |
amb | +0.110 |
subtitles | +0.106 |
シ | +0.103 |
Neg logit contributions | |
aukee | -0.135 |
nesday | -0.113 |
tnc | -0.107 |
icum | -0.099 |
agara | -0.099 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ANS | +0.446 |
Malik | +0.433 |
amb | +0.423 |
subtitles | +0.400 |
headphone | +0.386 |
Neg logit contributions | |
aukee | -0.820 |
nesday | -0.711 |
tnc | -0.680 |
agara | -0.637 |
icum | -0.637 |
Token | were |
Token ID | 547 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
ANS | +0.310 |
Malik | +0.302 |
amb | +0.296 |
subtitles | +0.280 |
シ | +0.272 |
Neg logit contributions | |
aukee | -0.458 |
nesday | -0.390 |
tnc | -0.373 |
icum | -0.347 |
agara | -0.346 |
Token | still |
Token ID | 991 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
aukee | +0.340 |
nesday | +0.293 |
tnc | +0.281 |
icum | +0.263 |
agara | +0.263 |
Neg logit contributions | |
ANS | -0.190 |
Malik | -0.185 |
amb | -0.179 |
subtitles | -0.170 |
シ | -0.164 |
Token | red |
Token ID | 2266 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ANS | +0.076 |
Malik | +0.074 |
amb | +0.073 |
subtitles | +0.068 |
シ | +0.066 |
Neg logit contributions | |
aukee | -0.140 |
nesday | -0.121 |
tnc | -0.116 |
icum | -0.109 |
agara | -0.108 |
Token | from |
Token ID | 422 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ANS | +0.302 |
Malik | +0.293 |
amb | +0.283 |
subtitles | +0.269 |
シ | +0.260 |
Neg logit contributions | |
aukee | -0.522 |
nesday | -0.449 |
tnc | -0.431 |
agara | -0.403 |
icum | -0.402 |
Token | cutting |
Token ID | 7720 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ANS | +0.279 |
Malik | +0.271 |
amb | +0.264 |
subtitles | +0.249 |
headphone | +0.241 |
Neg logit contributions | |
aukee | -0.494 |
nesday | -0.425 |
tnc | -0.409 |
icum | -0.382 |
agara | -0.382 |
Token | up |
Token ID | 510 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
ANS | +0.580 |
Malik | +0.565 |
amb | +0.551 |
subtitles | +0.522 |
シ | +0.502 |
Neg logit contributions | |
aukee | -1.057 |
nesday | -0.912 |
tnc | -0.877 |
agara | -0.821 |
icum | -0.818 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
ANS | +0.166 |
Malik | +0.160 |
amb | +0.156 |
subtitles | +0.147 |
シ | +0.142 |
Neg logit contributions | |
aukee | -0.305 |
nesday | -0.264 |
tnc | -0.253 |
agara | -0.237 |
icum | -0.237 |
Token | k |
Token ID | 479 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
aukee | +0.720 |
nesday | +0.625 |
tnc | +0.602 |
icum | +0.564 |
agara | +0.564 |
Neg logit contributions | |
ANS | -0.356 |
Malik | -0.344 |
amb | -0.333 |
subtitles | -0.313 |
シ | -0.302 |
Token | ona |
Token ID | 4450 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
aukee | +0.272 |
nesday | +0.229 |
tnc | +0.217 |
agara | +0.198 |
icum | +0.198 |
Neg logit contributions | |
ANS | -0.229 |
Malik | -0.223 |
amb | -0.219 |
subtitles | -0.208 |
シ | -0.204 |
Token | w |
Token ID | 266 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
aukee | +0.861 |
nesday | +0.744 |
tnc | +0.714 |
agara | +0.666 |
icum | +0.666 |
Neg logit contributions | |
ANS | -0.478 |
Malik | -0.464 |
amb | -0.451 |
subtitles | -0.425 |
シ | -0.411 |
Token | ā |
Token ID | 10235 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
aukee | +0.486 |
nesday | +0.419 |
tnc | +0.402 |
icum | +0.375 |
agara | +0.375 |
Neg logit contributions | |
ANS | -0.274 |
Malik | -0.265 |
amb | -0.257 |
subtitles | -0.243 |
シ | -0.236 |
Token | he |
Token ID | 339 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ANS | +0.176 |
Malik | +0.171 |
amb | +0.167 |
subtitles | +0.157 |
シ | +0.153 |
Neg logit contributions | |
aukee | -0.283 |
nesday | -0.243 |
tnc | -0.232 |
agara | -0.216 |
icum | -0.216 |
Token | u |
Token ID | 84 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ANS | +0.325 |
Malik | +0.316 |
amb | +0.310 |
subtitles | +0.290 |
シ | +0.282 |
Neg logit contributions | |
aukee | -0.575 |
nesday | -0.498 |
tnc | -0.477 |
icum | -0.444 |
agara | -0.444 |
Token | |
Token ID | 220 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
aukee | +0.475 |
nesday | +0.410 |
tnc | +0.393 |
icum | +0.366 |
agara | +0.365 |
Neg logit contributions | |
ANS | -0.270 |
Malik | -0.263 |
amb | -0.256 |
subtitles | -0.240 |
シ | -0.234 |
Token | � |
Token ID | 134 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
aukee | +0.245 |
nesday | +0.210 |
tnc | +0.197 |
agara | +0.183 |
icum | +0.183 |
Neg logit contributions | |
ANS | -0.183 |
Malik | -0.178 |
amb | -0.174 |
subtitles | -0.165 |
シ | -0.163 |
Token | � |
Token ID | 119 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ANS | +0.317 |
Malik | +0.314 |
amb | +0.307 |
subtitles | +0.292 |
シ | +0.288 |
Neg logit contributions | |
aukee | -0.423 |
nesday | -0.374 |
tnc | -0.337 |
agara | -0.316 |
icum | -0.314 |
Token | ole |
Token ID | 2305 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ANS | +0.082 |
Malik | +0.080 |
amb | +0.078 |
subtitles | +0.074 |
シ | +0.073 |
Neg logit contributions | |
aukee | -0.108 |
nesday | -0.092 |
tnc | -0.087 |
agara | -0.081 |
icum | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
ANS | +0.258 |
Malik | +0.251 |
amb | +0.245 |
subtitles | +0.231 |
headphone | +0.225 |
Neg logit contributions | |
aukee | -0.427 |
nesday | -0.368 |
tnc | -0.352 |
icum | -0.328 |
agara | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
ANS | +0.572 |
Malik | +0.568 |
amb | +0.543 |
subtitles | +0.513 |
headphone | +0.491 |
Neg logit contributions | |
aukee | -1.076 |
nesday | -0.923 |
tnc | -0.899 |
agara | -0.833 |
icum | -0.828 |
Token |
|
Token ID | 198 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
ANS | +0.019 |
Malik | +0.019 |
amb | +0.019 |
subtitles | +0.018 |
シ | +0.017 |
Neg logit contributions | |
aukee | -0.021 |
nesday | -0.018 |
tnc | -0.017 |
agara | -0.015 |
icum | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
aukee | +0.296 |
nesday | +0.255 |
tnc | +0.231 |
ngth | +0.225 |
akespe | +0.223 |
Neg logit contributions | |
ANS | -0.213 |
Malik | -0.208 |
amb | -0.202 |
subtitles | -0.190 |
シ | -0.188 |
Token | K |
Token ID | 42 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
aukee | +0.290 |
nesday | +0.246 |
tnc | +0.235 |
agara | +0.218 |
icum | +0.217 |
Neg logit contributions | |
ANS | -0.210 |
Malik | -0.204 |
amb | -0.198 |
subtitles | -0.190 |
シ | -0.185 |
Token | had |
Token ID | 18108 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ANS | +0.017 |
Malik | +0.016 |
amb | +0.016 |
subtitles | +0.015 |
headphone | +0.015 |
Neg logit contributions | |
aukee | -0.025 |
nesday | -0.021 |
tnc | -0.020 |
agara | -0.019 |
icum | -0.019 |
Token | r |
Token ID | 81 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
ANS | +0.055 |
Malik | +0.054 |
amb | +0.053 |
subtitles | +0.047 |
シ | +0.046 |
Neg logit contributions | |
aukee | -0.143 |
nesday | -0.124 |
tnc | -0.119 |
ngth | -0.115 |
akespe | -0.112 |
Token | first |
Token ID | 717 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
aukee | +0.009 |
nesday | +0.008 |
tnc | +0.008 |
agara | +0.007 |
icum | +0.007 |
Neg logit contributions | |
ANS | -0.006 |
Malik | -0.006 |
amb | -0.005 |
subtitles | -0.005 |
シ | -0.005 |
Token | lost |
Token ID | 2626 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
aukee | +0.215 |
nesday | +0.187 |
tnc | +0.180 |
icum | +0.167 |
ngth | +0.167 |
Neg logit contributions | |
ANS | -0.111 |
Malik | -0.110 |
amb | -0.108 |
subtitles | -0.100 |
headphone | -0.095 |
Token | his |
Token ID | 465 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ANS | +0.180 |
Malik | +0.179 |
amb | +0.173 |
subtitles | +0.164 |
headphone | +0.158 |
Neg logit contributions | |
aukee | -0.294 |
nesday | -0.253 |
tnc | -0.243 |
agara | -0.225 |
icum | -0.224 |
Token | bid |
Token ID | 8406 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aukee | +0.874 |
nesday | +0.760 |
tnc | +0.731 |
agara | +0.684 |
icum | +0.680 |
Neg logit contributions | |
ANS | -0.449 |
Malik | -0.438 |
amb | -0.426 |
subtitles | -0.400 |
headphone | -0.386 |
Token | for |
Token ID | 329 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
aukee | +1.085 |
nesday | +0.918 |
tnc | +0.874 |
icum | +0.816 |
agara | +0.812 |
Neg logit contributions | |
ANS | -0.747 |
Malik | -0.719 |
amb | -0.699 |
subtitles | -0.673 |
headphone | -0.652 |
Token | generated |
Token ID | 7560 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ANS | +0.025 |
Malik | +0.025 |
amb | +0.024 |
subtitles | +0.023 |
シ | +0.022 |
Neg logit contributions | |
aukee | -0.042 |
nesday | -0.036 |
tnc | -0.035 |
icum | -0.032 |
agara | -0.032 |
Token | electricity |
Token ID | 8744 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
aukee | +0.238 |
nesday | +0.205 |
tnc | +0.197 |
agara | +0.183 |
icum | +0.183 |
Neg logit contributions | |
ANS | -0.141 |
Malik | -0.137 |
amb | -0.134 |
subtitles | -0.127 |
headphone | -0.123 |
Token | to |
Token ID | 284 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
aukee | +0.335 |
nesday | +0.286 |
tnc | +0.275 |
agara | +0.255 |
icum | +0.255 |
Neg logit contributions | |
ANS | -0.218 |
Malik | -0.212 |
amb | -0.207 |
subtitles | -0.196 |
headphone | -0.190 |
Token | deliver |
Token ID | 5203 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ANS | +0.108 |
Malik | +0.105 |
amb | +0.102 |
subtitles | +0.096 |
headphone | +0.093 |
Neg logit contributions | |
aukee | -0.199 |
nesday | -0.172 |
tnc | -0.165 |
agara | -0.154 |
icum | -0.154 |
Token | 34 |
Token ID | 4974 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
aukee | +0.606 |
nesday | +0.528 |
tnc | +0.509 |
agara | +0.478 |
icum | +0.478 |
Neg logit contributions | |
ANS | -0.279 |
Malik | -0.270 |
amb | -0.261 |
subtitles | -0.245 |
headphone | -0.235 |
Token | MW |
Token ID | 29961 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
ANS | +0.126 |
Malik | +0.123 |
amb | +0.119 |
subtitles | +0.113 |
headphone | +0.109 |
Neg logit contributions | |
aukee | -0.218 |
nesday | -0.188 |
tnc | -0.180 |
agara | -0.168 |
icum | -0.168 |
Token | at |
Token ID | 379 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
aukee | +0.134 |
nesday | +0.115 |
tnc | +0.110 |
icum | +0.103 |
agara | +0.102 |
Neg logit contributions | |
ANS | -0.086 |
Malik | -0.084 |
amb | -0.081 |
subtitles | -0.077 |
シ | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ANS | +0.156 |
Malik | +0.152 |
amb | +0.148 |
subtitles | +0.140 |
headphone | +0.136 |
Neg logit contributions | |
aukee | -0.247 |
nesday | -0.211 |
tnc | -0.203 |
agara | -0.188 |
icum | -0.188 |
Token | prope |
Token ID | 44408 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ANS | +0.310 |
Malik | +0.301 |
amb | +0.292 |
subtitles | +0.274 |
headphone | +0.264 |
Neg logit contributions | |
aukee | -0.622 |
nesday | -0.542 |
tnc | -0.523 |
icum | -0.491 |
agara | -0.487 |
Token | llers |
Token ID | 13802 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
aukee | +1.553 |
nesday | +1.298 |
tnc | +1.238 |
agara | +1.140 |
icum | +1.138 |
Neg logit contributions | |
ANS | -1.279 |
Malik | -1.245 |
amb | -1.213 |
subtitles | -1.168 |
シ | -1.138 |
Token | . |
Token ID | 13 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
aukee | +1.172 |
nesday | +1.003 |
tnc | +0.962 |
agara | +0.897 |
icum | +0.896 |
Neg logit contributions | |
ANS | -0.729 |
Malik | -0.707 |
amb | -0.685 |
subtitles | -0.653 |
シ | -0.633 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ANS | +0.217 |
Malik | +0.212 |
amb | +0.206 |
subtitles | +0.194 |
headphone | +0.187 |
Neg logit contributions | |
aukee | -0.411 |
nesday | -0.355 |
tnc | -0.341 |
icum | -0.319 |
agara | -0.319 |
Token | possibility |
Token ID | 5885 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ANS | +0.020 |
Malik | +0.020 |
amb | +0.019 |
subtitles | +0.018 |
headphone | +0.017 |
Neg logit contributions | |
aukee | -0.042 |
nesday | -0.037 |
tnc | -0.035 |
agara | -0.033 |
icum | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
aukee | +0.284 |
nesday | +0.240 |
tnc | +0.229 |
icum | +0.213 |
agara | +0.212 |
Neg logit contributions | |
ANS | -0.218 |
Malik | -0.208 |
amb | -0.201 |
subtitles | -0.195 |
シ | -0.191 |
Token | prisoners |
Token ID | 10577 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
ANS | +0.075 |
Malik | +0.074 |
amb | +0.072 |
subtitles | +0.068 |
headphone | +0.065 |
Neg logit contributions | |
aukee | -0.142 |
nesday | -0.123 |
tnc | -0.118 |
agara | -0.110 |
icum | -0.110 |
Token | would |
Token ID | 561 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
ANS | +0.144 |
Malik | +0.142 |
amb | +0.139 |
subtitles | +0.130 |
headphone | +0.126 |
Neg logit contributions | |
aukee | -0.226 |
nesday | -0.194 |
tnc | -0.187 |
agara | -0.173 |
icum | -0.172 |
Token | be |
Token ID | 307 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
ANS | +0.009 |
Malik | +0.009 |
amb | +0.009 |
subtitles | +0.008 |
dispatch | +0.008 |
Neg logit contributions | |
aukee | -0.014 |
nesday | -0.012 |
tnc | -0.012 |
icum | -0.011 |
agara | -0.011 |
Token | used |
Token ID | 973 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ANS | +0.066 |
Malik | +0.065 |
amb | +0.064 |
subtitles | +0.059 |
dispatch | +0.056 |
Neg logit contributions | |
aukee | -0.135 |
nesday | -0.117 |
tnc | -0.113 |
agara | -0.106 |
icum | -0.106 |
Token | in |
Token ID | 287 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
aukee | +0.565 |
nesday | +0.486 |
tnc | +0.469 |
icum | +0.436 |
agara | +0.435 |
Neg logit contributions | |
ANS | -0.323 |
Malik | -0.317 |
amb | -0.309 |
subtitles | -0.291 |
headphone | -0.280 |
Token | the |
Token ID | 262 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
aukee | +0.214 |
nesday | +0.185 |
tnc | +0.178 |
icum | +0.167 |
agara | +0.166 |
Neg logit contributions | |
ANS | -0.112 |
Malik | -0.110 |
amb | -0.107 |
subtitles | -0.100 |
headphone | -0.097 |
Token | manufacture |
Token ID | 6161 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ANS | +0.160 |
Malik | +0.158 |
amb | +0.155 |
subtitles | +0.143 |
headphone | +0.140 |
Neg logit contributions | |
aukee | -0.328 |
nesday | -0.286 |
tnc | -0.275 |
agara | -0.259 |
icum | -0.258 |
Token | of |
Token ID | 286 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ANS | +0.054 |
Malik | +0.052 |
amb | +0.050 |
subtitles | +0.048 |
シ | +0.047 |
Neg logit contributions | |
aukee | -0.070 |
nesday | -0.059 |
tnc | -0.056 |
icum | -0.052 |
agara | -0.052 |
Token | as |
Token ID | 355 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ANS | +0.035 |
Malik | +0.034 |
amb | +0.033 |
subtitles | +0.032 |
headphone | +0.030 |
Neg logit contributions | |
aukee | -0.062 |
nesday | -0.053 |
tnc | -0.051 |
agara | -0.048 |
icum | -0.048 |
Token | mayor |
Token ID | 9591 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
aukee | +0.834 |
nesday | +0.717 |
tnc | +0.691 |
icum | +0.645 |
agara | +0.645 |
Neg logit contributions | |
ANS | -0.461 |
Malik | -0.445 |
amb | -0.431 |
subtitles | -0.410 |
シ | -0.396 |
Token | of |
Token ID | 286 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ANS | +0.627 |
Malik | +0.614 |
amb | +0.596 |
subtitles | +0.562 |
シ | +0.548 |
Neg logit contributions | |
aukee | -1.029 |
nesday | -0.887 |
tnc | -0.853 |
icum | -0.793 |
agara | -0.790 |
Token | Newark |
Token ID | 30970 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ANS | +0.739 |
Malik | +0.728 |
amb | +0.708 |
subtitles | +0.672 |
headphone | +0.656 |
Neg logit contributions | |
aukee | -0.978 |
nesday | -0.833 |
tnc | -0.787 |
icum | -0.732 |
agara | -0.728 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aukee | +0.718 |
nesday | +0.617 |
tnc | +0.593 |
agara | +0.554 |
icum | +0.554 |
Neg logit contributions | |
ANS | -0.412 |
Malik | -0.399 |
amb | -0.387 |
subtitles | -0.367 |
シ | -0.355 |
Token | The |
Token ID | 383 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ANS | +0.240 |
Malik | +0.237 |
amb | +0.224 |
subtitles | +0.215 |
シ | +0.210 |
Neg logit contributions | |
aukee | -0.368 |
nesday | -0.316 |
tnc | -0.299 |
icum | -0.283 |
agara | -0.281 |
Token | Times |
Token ID | 3782 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ANS | +0.211 |
Malik | +0.205 |
amb | +0.198 |
subtitles | +0.186 |
headphone | +0.179 |
Neg logit contributions | |
aukee | -0.445 |
nesday | -0.387 |
tnc | -0.373 |
icum | -0.351 |
agara | -0.350 |
Token | article |
Token ID | 2708 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ANS | +0.628 |
Malik | +0.606 |
amb | +0.584 |
subtitles | +0.542 |
headphone | +0.515 |
Neg logit contributions | |
aukee | -1.644 |
nesday | -1.441 |
tnc | -1.400 |
icum | -1.317 |
agara | -1.313 |
Token | made |
Token ID | 925 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ANS | +0.626 |
Malik | +0.616 |
amb | +0.602 |
subtitles | +0.566 |
headphone | +0.538 |
Neg logit contributions | |
aukee | -1.211 |
nesday | -1.044 |
tnc | -1.020 |
icum | -0.946 |
agara | -0.940 |
Token | clear |
Token ID | 1598 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
ANS | +0.249 |
Malik | +0.246 |
amb | +0.239 |
subtitles | +0.226 |
headphone | +0.216 |
Neg logit contributions | |
aukee | -0.478 |
nesday | -0.413 |
tnc | -0.398 |
icum | -0.374 |
agara | -0.371 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ANS | +0.006 |
Malik | +0.005 |
amb | +0.005 |
subtitles | +0.005 |
シ | +0.005 |
Neg logit contributions | |
aukee | -0.008 |
nesday | -0.007 |
tnc | -0.007 |
icum | -0.006 |
agara | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ANS | +0.037 |
Malik | +0.036 |
amb | +0.035 |
subtitles | +0.034 |
シ | +0.032 |
Neg logit contributions | |
aukee | -0.062 |
nesday | -0.053 |
tnc | -0.051 |
icum | -0.047 |
agara | -0.047 |
Token | other |
Token ID | 584 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
aukee | +0.492 |
nesday | +0.424 |
tnc | +0.407 |
icum | +0.381 |
agara | +0.380 |
Neg logit contributions | |
ANS | -0.278 |
Malik | -0.270 |
amb | -0.262 |
subtitles | -0.248 |
headphone | -0.239 |
Token | social |
Token ID | 1919 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
aukee | +0.347 |
nesday | +0.303 |
tnc | +0.288 |
icum | +0.271 |
agara | +0.270 |
Neg logit contributions | |
ANS | -0.178 |
Malik | -0.173 |
amb | -0.169 |
subtitles | -0.158 |
headphone | -0.153 |
Token | costs |
Token ID | 3484 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ANS | +0.649 |
Malik | +0.632 |
amb | +0.622 |
subtitles | +0.580 |
headphone | +0.562 |
Neg logit contributions | |
aukee | -1.244 |
nesday | -1.086 |
tnc | -1.035 |
icum | -0.971 |
agara | -0.966 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ANS | +0.283 |
Malik | +0.275 |
amb | +0.268 |
subtitles | +0.253 |
headphone | +0.246 |
Neg logit contributions | |
aukee | -0.460 |
nesday | -0.395 |
tnc | -0.378 |
icum | -0.352 |
agara | -0.351 |
Token |
|
Token ID | 198 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
ANS | +0.067 |
Malik | +0.065 |
amb | +0.064 |
subtitles | +0.062 |
headphone | +0.060 |
Neg logit contributions | |
aukee | -0.073 |
nesday | -0.060 |
tnc | -0.058 |
agara | -0.053 |
icum | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
ANS | +0.203 |
Malik | +0.197 |
amb | +0.192 |
subtitles | +0.180 |
シ | +0.178 |
Neg logit contributions | |
aukee | -0.298 |
nesday | -0.260 |
tnc | -0.234 |
ngth | -0.231 |
��� | -0.229 |
Token | " |
Token ID | 1 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ANS | +0.176 |
Malik | +0.168 |
amb | +0.163 |
subtitles | +0.155 |
シ | +0.155 |
Neg logit contributions | |
aukee | -0.248 |
nesday | -0.212 |
tnc | -0.198 |
agara | -0.186 |
icum | -0.186 |
Token | Putting |
Token ID | 46399 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
aukee | +0.359 |
nesday | +0.308 |
tnc | +0.286 |
agara | +0.269 |
ngth | +0.269 |
Neg logit contributions | |
ANS | -0.261 |
Malik | -0.247 |
amb | -0.239 |
シ | -0.228 |
subtitles | -0.228 |
Token | values |
Token ID | 3815 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
aukee | +0.463 |
nesday | +0.401 |
tnc | +0.384 |
icum | +0.360 |
agara | +0.358 |
Neg logit contributions | |
ANS | -0.250 |
Malik | -0.244 |
amb | -0.237 |
subtitles | -0.224 |
headphone | -0.217 |
Token | on |
Token ID | 319 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
aukee | +0.408 |
nesday | +0.349 |
tnc | +0.334 |
agara | +0.307 |
icum | +0.307 |
Neg logit contributions | |
ANS | -0.269 |
Malik | -0.263 |
amb | -0.257 |
subtitles | -0.245 |
headphone | -0.236 |
Token | T |
Token ID | 309 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
ANS | +0.085 |
Malik | +0.082 |
amb | +0.079 |
subtitles | +0.075 |
シ | +0.072 |
Neg logit contributions | |
aukee | -0.165 |
nesday | -0.143 |
tnc | -0.137 |
icum | -0.129 |
agara | -0.129 |
Token | PA |
Token ID | 4537 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ANS | +0.250 |
Malik | +0.233 |
amb | +0.230 |
subtitles | +0.217 |
シ | +0.216 |
Neg logit contributions | |
aukee | -0.252 |
nesday | -0.217 |
tnc | -0.195 |
ngth | -0.184 |
icum | -0.180 |
Token | will |
Token ID | 481 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
ANS | +0.348 |
Malik | +0.338 |
amb | +0.329 |
subtitles | +0.310 |
headphone | +0.299 |
Neg logit contributions | |
aukee | -0.595 |
nesday | -0.514 |
tnc | -0.497 |
icum | -0.460 |
agara | -0.459 |
Token | ask |
Token ID | 1265 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
ANS | +0.087 |
Malik | +0.083 |
amb | +0.082 |
subtitles | +0.077 |
dispatch | +0.075 |
Neg logit contributions | |
aukee | -0.167 |
nesday | -0.143 |
tnc | -0.140 |
icum | -0.130 |
agara | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ANS | +0.187 |
Malik | +0.182 |
amb | +0.176 |
subtitles | +0.167 |
シ | +0.162 |
Neg logit contributions | |
aukee | -0.319 |
nesday | -0.274 |
tnc | -0.263 |
agara | -0.246 |
icum | -0.245 |
Token | court |
Token ID | 2184 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aukee | +0.661 |
nesday | +0.566 |
tnc | +0.543 |
agara | +0.506 |
icum | +0.506 |
Neg logit contributions | |
ANS | -0.407 |
Malik | -0.395 |
amb | -0.383 |
subtitles | -0.365 |
シ | -0.354 |
Token | during |
Token ID | 1141 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ANS | +0.285 |
Malik | +0.276 |
amb | +0.267 |
subtitles | +0.256 |
シ | +0.248 |
Neg logit contributions | |
aukee | -0.451 |
nesday | -0.385 |
tnc | -0.367 |
agara | -0.344 |
icum | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
aukee | +0.087 |
nesday | +0.075 |
tnc | +0.072 |
icum | +0.067 |
agara | +0.067 |
Neg logit contributions | |
ANS | -0.047 |
Malik | -0.045 |
amb | -0.044 |
subtitles | -0.042 |
シ | -0.040 |
Token | hearing |
Token ID | 4854 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
aukee | +0.184 |
nesday | +0.159 |
tnc | +0.153 |
agara | +0.143 |
icum | +0.142 |
Neg logit contributions | |
ANS | -0.102 |
Malik | -0.099 |
amb | -0.097 |
subtitles | -0.091 |
headphone | -0.088 |
Token | set |
Token ID | 900 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
aukee | +1.403 |
nesday | +1.198 |
tnc | +1.140 |
icum | +1.062 |
agara | +1.061 |
Neg logit contributions | |
ANS | -0.931 |
Malik | -0.898 |
amb | -0.873 |
subtitles | -0.837 |
シ | -0.811 |
Token | for |
Token ID | 329 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
aukee | +0.575 |
nesday | +0.488 |
tnc | +0.465 |
agara | +0.432 |
icum | +0.431 |
Neg logit contributions | |
ANS | -0.404 |
Malik | -0.391 |
amb | -0.379 |
subtitles | -0.363 |
シ | -0.354 |
Token | pointed |
Token ID | 6235 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ANS | +0.347 |
Malik | +0.339 |
amb | +0.328 |
subtitles | +0.309 |
headphone | +0.296 |
Neg logit contributions | |
aukee | -0.706 |
nesday | -0.612 |
tnc | -0.593 |
agara | -0.553 |
icum | -0.551 |
Token | out |
Token ID | 503 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ANS | +0.714 |
Malik | +0.708 |
amb | +0.690 |
subtitles | +0.644 |
headphone | +0.623 |
Neg logit contributions | |
aukee | -1.429 |
nesday | -1.241 |
tnc | -1.194 |
agara | -1.121 |
icum | -1.111 |
Token | recently |
Token ID | 2904 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
aukee | +0.114 |
nesday | +0.098 |
tnc | +0.093 |
icum | +0.087 |
agara | +0.087 |
Neg logit contributions | |
ANS | -0.068 |
Malik | -0.066 |
amb | -0.064 |
subtitles | -0.061 |
シ | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
aukee | +0.013 |
nesday | +0.012 |
tnc | +0.011 |
icum | +0.010 |
agara | +0.010 |
Neg logit contributions | |
ANS | -0.008 |
Malik | -0.008 |
amb | -0.007 |
subtitles | -0.007 |
headphone | -0.007 |
Token | Time |
Token ID | 3862 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
ANS | +0.012 |
Malik | +0.011 |
amb | +0.011 |
subtitles | +0.010 |
シ | +0.010 |
Neg logit contributions | |
aukee | -0.019 |
nesday | -0.016 |
tnc | -0.015 |
icum | -0.014 |
agara | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ANS | +0.190 |
Malik | +0.183 |
amb | +0.177 |
subtitles | +0.168 |
シ | +0.162 |
Neg logit contributions | |
aukee | -0.353 |
nesday | -0.304 |
tnc | -0.292 |
icum | -0.274 |
agara | -0.273 |
Token | has |
Token ID | 468 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ANS | +0.254 |
Malik | +0.247 |
amb | +0.242 |
subtitles | +0.229 |
シ | +0.222 |
Neg logit contributions | |
aukee | -0.420 |
nesday | -0.360 |
tnc | -0.346 |
agara | -0.322 |
icum | -0.322 |
Token | ironically |
Token ID | 32532 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
aukee | +0.139 |
nesday | +0.119 |
tnc | +0.115 |
icum | +0.107 |
agara | +0.107 |
Neg logit contributions | |
ANS | -0.081 |
Malik | -0.079 |
amb | -0.077 |
subtitles | -0.073 |
headphone | -0.070 |
Token | only |
Token ID | 691 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
aukee | +1.198 |
nesday | +1.028 |
tnc | +0.987 |
icum | +0.919 |
agara | +0.918 |
Neg logit contributions | |
ANS | -0.727 |
Malik | -0.707 |
amb | -0.690 |
subtitles | -0.653 |
シ | -0.633 |
Token | increased |
Token ID | 3220 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ANS | +0.023 |
Malik | +0.022 |
amb | +0.022 |
subtitles | +0.021 |
headphone | +0.020 |
Neg logit contributions | |
aukee | -0.040 |
nesday | -0.035 |
tnc | -0.033 |
agara | -0.031 |
icum | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
aukee | +0.926 |
nesday | +0.792 |
tnc | +0.760 |
agara | +0.707 |
icum | +0.707 |
Neg logit contributions | |
ANS | -0.588 |
Malik | -0.571 |
amb | -0.554 |
subtitles | -0.527 |
シ | -0.512 |
Token | its |
Token ID | 663 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
aukee | +0.350 |
nesday | +0.302 |
tnc | +0.290 |
icum | +0.272 |
agara | +0.270 |
Neg logit contributions | |
ANS | -0.197 |
Malik | -0.192 |
amb | -0.186 |
subtitles | -0.176 |
headphone | -0.170 |
Token | population |
Token ID | 3265 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
aukee | +0.147 |
nesday | +0.128 |
tnc | +0.124 |
icum | +0.116 |
agara | +0.116 |
Neg logit contributions | |
ANS | -0.070 |
Malik | -0.068 |
amb | -0.066 |
subtitles | -0.062 |
headphone | -0.059 |
Token | grow |
Token ID | 1663 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ANS | +0.096 |
Malik | +0.092 |
amb | +0.089 |
subtitles | +0.082 |
headphone | +0.079 |
Neg logit contributions | |
aukee | -0.251 |
nesday | -0.222 |
tnc | -0.215 |
icum | -0.202 |
agara | -0.201 |
Token | from |
Token ID | 422 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
aukee | +0.621 |
nesday | +0.533 |
tnc | +0.514 |
icum | +0.479 |
agara | +0.479 |
Neg logit contributions | |
ANS | -0.364 |
Malik | -0.354 |
amb | -0.343 |
subtitles | -0.325 |
headphone | -0.315 |
Token | 186 |
Token ID | 28481 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
aukee | +0.257 |
nesday | +0.218 |
tnc | +0.210 |
agara | +0.194 |
icum | +0.194 |
Neg logit contributions | |
ANS | -0.174 |
Malik | -0.171 |
amb | -0.166 |
subtitles | -0.158 |
headphone | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
ANS | +0.175 |
Malik | +0.170 |
amb | +0.164 |
subtitles | +0.155 |
シ | +0.150 |
Neg logit contributions | |
aukee | -0.332 |
nesday | -0.287 |
tnc | -0.276 |
agara | -0.258 |
icum | -0.258 |
Token | 000 |
Token ID | 830 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
ANS | +0.248 |
Malik | +0.242 |
amb | +0.235 |
subtitles | +0.227 |
headphone | +0.221 |
Neg logit contributions | |
aukee | -0.277 |
nesday | -0.233 |
tnc | -0.221 |
icum | -0.203 |
agara | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
ANS | +0.135 |
Malik | +0.131 |
amb | +0.127 |
subtitles | +0.121 |
headphone | +0.117 |
Neg logit contributions | |
aukee | -0.228 |
nesday | -0.195 |
tnc | -0.188 |
icum | -0.175 |
agara | -0.175 |
Token | 300 |
Token ID | 5867 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
aukee | +0.096 |
nesday | +0.080 |
tnc | +0.077 |
agara | +0.071 |
icum | +0.071 |
Neg logit contributions | |
ANS | -0.076 |
Malik | -0.074 |
amb | -0.073 |
subtitles | -0.069 |
headphone | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aukee | +0.024 |
nesday | +0.021 |
tnc | +0.020 |
akespe | +0.019 |
ngth | +0.018 |
Neg logit contributions | |
ANS | -0.010 |
Malik | -0.010 |
amb | -0.010 |
subtitles | -0.009 |
headphone | -0.008 |
Token | 000 |
Token ID | 830 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ANS | +0.123 |
Malik | +0.119 |
amb | +0.117 |
シ | +0.111 |
subtitles | +0.110 |
Neg logit contributions | |
aukee | -0.166 |
nesday | -0.138 |
tnc | -0.130 |
ngth | -0.123 |
akespe | -0.122 |
Token | did |
Token ID | 750 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ANS | +0.278 |
Malik | +0.273 |
amb | +0.268 |
subtitles | +0.251 |
headphone | +0.244 |
Neg logit contributions | |
aukee | -0.429 |
nesday | -0.366 |
tnc | -0.354 |
icum | -0.328 |
agara | -0.326 |
Token | not |
Token ID | 407 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ANS | +0.106 |
Malik | +0.104 |
amb | +0.102 |
subtitles | +0.095 |
headphone | +0.093 |
Neg logit contributions | |
aukee | -0.189 |
nesday | -0.162 |
tnc | -0.157 |
icum | -0.146 |
agara | -0.146 |
Token | issue |
Token ID | 2071 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ANS | +0.067 |
Malik | +0.065 |
amb | +0.065 |
subtitles | +0.060 |
headphone | +0.059 |
Neg logit contributions | |
aukee | -0.123 |
nesday | -0.106 |
tnc | -0.103 |
icum | -0.096 |
agara | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
ANS | +0.270 |
Malik | +0.265 |
amb | +0.257 |
subtitles | +0.241 |
headphone | +0.235 |
Neg logit contributions | |
aukee | -0.494 |
nesday | -0.426 |
tnc | -0.411 |
icum | -0.384 |
agara | -0.384 |
Token | total |
Token ID | 2472 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ANS | +0.135 |
Malik | +0.132 |
amb | +0.129 |
subtitles | +0.120 |
headphone | +0.117 |
Neg logit contributions | |
aukee | -0.252 |
nesday | -0.219 |
tnc | -0.209 |
agara | -0.197 |
icum | -0.196 |
Token | Loving |
Token ID | 39202 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
aukee | +1.098 |
nesday | +0.948 |
tnc | +0.911 |
agara | +0.849 |
icum | +0.849 |
Neg logit contributions | |
ANS | -0.602 |
Malik | -0.586 |
amb | -0.571 |
subtitles | -0.534 |
headphone | -0.520 |
Token | v |
Token ID | 410 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ANS | +1.365 |
Malik | +1.326 |
amb | +1.290 |
subtitles | +1.185 |
headphone | +1.179 |
Neg logit contributions | |
aukee | -2.550 |
nesday | -2.219 |
tnc | -2.140 |
icum | -2.013 |
agara | -2.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Malik | +1.969 |
ANS | +1.931 |
amb | +1.800 |
シ | +1.648 |
dispatch | +1.642 |
Neg logit contributions | |
aukee | -4.214 |
nesday | -3.755 |
tnc | -3.535 |
ngth | -3.453 |
akespe | -3.362 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
ANS | +0.092 |
Malik | +0.091 |
amb | +0.089 |
subtitles | +0.083 |
シ | +0.083 |
Neg logit contributions | |
aukee | -0.098 |
nesday | -0.084 |
tnc | -0.078 |
ngth | -0.072 |
icum | -0.072 |
Token | victory |
Token ID | 5373 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
aukee | +0.147 |
nesday | +0.128 |
tnc | +0.123 |
agara | +0.116 |
icum | +0.115 |
Neg logit contributions | |
ANS | -0.075 |
Malik | -0.073 |
amb | -0.071 |
subtitles | -0.066 |
headphone | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
ANS | +0.170 |
Malik | +0.166 |
amb | +0.160 |
subtitles | +0.152 |
headphone | +0.147 |
Neg logit contributions | |
aukee | -0.295 |
nesday | -0.253 |
tnc | -0.244 |
agara | -0.228 |
icum | -0.227 |
Token | Performance |
Token ID | 15193 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
ANS | +0.237 |
Malik | +0.231 |
amb | +0.225 |
subtitles | +0.213 |
シ | +0.208 |
Neg logit contributions | |
aukee | -0.357 |
nesday | -0.305 |
tnc | -0.292 |
icum | -0.272 |
agara | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ANS | +0.012 |
Malik | +0.012 |
amb | +0.012 |
subtitles | +0.011 |
headphone | +0.011 |
Neg logit contributions | |
aukee | -0.019 |
nesday | -0.017 |
tnc | -0.016 |
agara | -0.015 |
icum | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ANS | +0.582 |
Malik | +0.568 |
amb | +0.557 |
subtitles | +0.540 |
シ | +0.529 |
Neg logit contributions | |
aukee | -0.477 |
nesday | -0.380 |
tnc | -0.358 |
agara | -0.322 |
icum | -0.317 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ANS | +0.398 |
Malik | +0.387 |
amb | +0.376 |
subtitles | +0.352 |
シ | +0.350 |
Neg logit contributions | |
aukee | -0.596 |
nesday | -0.520 |
tnc | -0.466 |
ngth | -0.466 |
��� | -0.462 |
Token | R |
Token ID | 49 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
ANS | +0.421 |
Malik | +0.400 |
amb | +0.392 |
subtitles | +0.373 |
シ | +0.371 |
Neg logit contributions | |
aukee | -0.526 |
nesday | -0.449 |
tnc | -0.417 |
icum | -0.392 |
agara | -0.390 |
Token | apt |
Token ID | 2373 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ANS | +0.275 |
Malik | +0.264 |
amb | +0.262 |
subtitles | +0.253 |
シ | +0.250 |
Neg logit contributions | |
aukee | -0.164 |
nesday | -0.128 |
tnc | -0.116 |
agara | -0.100 |
icum | -0.100 |
Token | or |
Token ID | 273 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ANS | +1.330 |
Malik | +1.319 |
amb | +1.299 |
シ | +1.198 |
subtitles | +1.175 |
Neg logit contributions | |
aukee | -2.460 |
nesday | -2.171 |
tnc | -2.028 |
��� | -1.964 |
ngth | -1.954 |
Token | 's |
Token ID | 338 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ANS | +0.393 |
Malik | +0.382 |
amb | +0.374 |
subtitles | +0.354 |
headphone | +0.343 |
Neg logit contributions | |
aukee | -0.643 |
nesday | -0.552 |
tnc | -0.530 |
agara | -0.494 |
icum | -0.494 |
Token | pioneering |
Token ID | 36304 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
ANS | +0.431 |
Malik | +0.421 |
amb | +0.416 |
subtitles | +0.387 |
headphone | +0.378 |
Neg logit contributions | |
aukee | -0.753 |
nesday | -0.654 |
tnc | -0.626 |
icum | -0.589 |
agara | -0.585 |
Token | off |
Token ID | 572 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ANS | +0.454 |
Malik | +0.444 |
amb | +0.443 |
subtitles | +0.408 |
headphone | +0.399 |
Neg logit contributions | |
aukee | -0.793 |
nesday | -0.696 |
tnc | -0.664 |
icum | -0.626 |
agara | -0.623 |
Token | - |
Token ID | 12 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
ANS | +0.497 |
Malik | +0.491 |
amb | +0.456 |
subtitles | +0.448 |
シ | +0.428 |
Neg logit contributions | |
aukee | -0.839 |
nesday | -0.711 |
tnc | -0.694 |
icum | -0.649 |
agara | -0.643 |
Token | Nick |
Token ID | 8047 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ANS | +0.413 |
Malik | +0.409 |
amb | +0.392 |
subtitles | +0.375 |
シ | +0.362 |
Neg logit contributions | |
aukee | -0.602 |
nesday | -0.508 |
tnc | -0.490 |
icum | -0.451 |
agara | -0.450 |
Token | all |
Token ID | 439 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
ANS | +0.319 |
Malik | +0.315 |
amb | +0.304 |
subtitles | +0.292 |
シ | +0.284 |
Neg logit contributions | |
aukee | -0.377 |
nesday | -0.317 |
tnc | -0.303 |
agara | -0.277 |
icum | -0.275 |
Token | ini |
Token ID | 5362 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
ANS | +0.121 |
Malik | +0.119 |
amb | +0.115 |
subtitles | +0.109 |
シ | +0.106 |
Neg logit contributions | |
aukee | -0.184 |
nesday | -0.157 |
tnc | -0.151 |
icum | -0.139 |
agara | -0.139 |
Token | - |
Token ID | 12 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ANS | +0.129 |
Malik | +0.124 |
amb | +0.121 |
subtitles | +0.116 |
シ | +0.113 |
Neg logit contributions | |
aukee | -0.198 |
nesday | -0.169 |
tnc | -0.161 |
agara | -0.151 |
icum | -0.151 |
Token | Jim |
Token ID | 18050 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
ANS | +1.031 |
Malik | +0.994 |
amb | +0.964 |
subtitles | +0.923 |
シ | +0.911 |
Neg logit contributions | |
aukee | -1.328 |
nesday | -1.121 |
tnc | -1.059 |
agara | -0.987 |
icum | -0.984 |
Token | Vs |
Token ID | 31280 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
aukee | +0.295 |
nesday | +0.251 |
tnc | +0.241 |
agara | +0.225 |
icum | +0.224 |
Neg logit contributions | |
ANS | -0.193 |
Malik | -0.189 |
amb | -0.181 |
subtitles | -0.174 |
シ | -0.168 |
Token | Colin |
Token ID | 18373 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
ANS | +1.564 |
Malik | +1.548 |
amb | +1.481 |
subtitles | +1.416 |
headphone | +1.367 |
Neg logit contributions | |
aukee | -2.401 |
nesday | -2.035 |
tnc | -1.959 |
icum | -1.821 |
agara | -1.818 |
Token | - |
Token ID | 12 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
aukee | +0.164 |
nesday | +0.140 |
tnc | +0.135 |
agara | +0.125 |
icum | +0.124 |
Neg logit contributions | |
ANS | -0.102 |
Malik | -0.101 |
amb | -0.096 |
subtitles | -0.092 |
シ | -0.089 |
Token | Ant |
Token ID | 13217 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
ANS | +0.772 |
Malik | +0.746 |
amb | +0.723 |
subtitles | +0.693 |
シ | +0.683 |
Neg logit contributions | |
aukee | -0.996 |
nesday | -0.841 |
tnc | -0.795 |
agara | -0.740 |
icum | -0.739 |
Token | W |
Token ID | 370 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aukee | +0.332 |
nesday | +0.282 |
tnc | +0.271 |
agara | +0.252 |
icum | +0.252 |
Neg logit contributions | |
ANS | -0.218 |
Malik | -0.213 |
amb | -0.207 |
subtitles | -0.197 |
シ | -0.191 |
Token | ears |
Token ID | 4127 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
aukee | +0.959 |
nesday | +0.809 |
tnc | +0.773 |
agara | +0.714 |
icum | +0.714 |
Neg logit contributions | |
ANS | -0.731 |
Malik | -0.711 |
amb | -0.693 |
subtitles | -0.663 |
シ | -0.646 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ANS | +1.340 |
Malik | +1.325 |
amb | +1.273 |
subtitles | +1.222 |
シ | +1.179 |
Neg logit contributions | |
aukee | -1.738 |
nesday | -1.482 |
tnc | -1.416 |
agara | -1.301 |
icum | -1.294 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ANS | +0.436 |
Malik | +0.427 |
amb | +0.411 |
subtitles | +0.387 |
シ | +0.384 |
Neg logit contributions | |
aukee | -0.644 |
nesday | -0.560 |
tnc | -0.504 |
ngth | -0.501 |
��� | -0.494 |
Token | V |
Token ID | 53 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ANS | +0.405 |
Malik | +0.388 |
amb | +0.377 |
subtitles | +0.361 |
シ | +0.356 |
Neg logit contributions | |
aukee | -0.521 |
nesday | -0.442 |
tnc | -0.415 |
agara | -0.389 |
icum | -0.386 |
Token | il |
Token ID | 346 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ANS | +0.541 |
Malik | +0.527 |
amb | +0.514 |
subtitles | +0.494 |
シ | +0.479 |
Neg logit contributions | |
aukee | -0.736 |
nesday | -0.622 |
tnc | -0.595 |
icum | -0.553 |
agara | -0.551 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
Malik | +0.114 |
ANS | +0.113 |
amb | +0.108 |
bane | +0.102 |
subtitles | +0.098 |
Neg logit contributions | |
aukee | -0.232 |
nesday | -0.202 |
tnc | -0.191 |
ngth | -0.186 |
��� | -0.185 |
Token | v |
Token ID | 410 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
aukee | +0.117 |
nesday | +0.099 |
tnc | +0.095 |
icum | +0.088 |
agara | +0.087 |
Neg logit contributions | |
ANS | -0.082 |
Malik | -0.079 |
amb | -0.078 |
subtitles | -0.074 |
シ | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
Malik | +1.671 |
ANS | +1.601 |
amb | +1.472 |
SPD | +1.430 |
subtitles | +1.419 |
Neg logit contributions | |
aukee | -3.582 |
nesday | -3.161 |
tnc | -2.922 |
akespe | -2.881 |
ngth | -2.879 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ANS | +0.301 |
Malik | +0.292 |
amb | +0.288 |
subtitles | +0.279 |
シ | +0.274 |
Neg logit contributions | |
aukee | -0.228 |
nesday | -0.182 |
tnc | -0.170 |
agara | -0.151 |
icum | -0.150 |
Token | Supplemental |
Token ID | 48165 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
aukee | +0.372 |
nesday | +0.319 |
tnc | +0.307 |
agara | +0.286 |
icum | +0.285 |
Neg logit contributions | |
ANS | -0.228 |
Malik | -0.223 |
amb | -0.215 |
subtitles | -0.204 |
headphone | -0.198 |
Token | Mem |
Token ID | 4942 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
aukee | +0.300 |
nesday | +0.256 |
tnc | +0.246 |
agara | +0.229 |
icum | +0.228 |
Neg logit contributions | |
ANS | -0.198 |
Malik | -0.194 |
amb | -0.188 |
subtitles | -0.179 |
headphone | -0.174 |
Token | o |
Token ID | 78 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ANS | +0.258 |
Malik | +0.258 |
amb | +0.244 |
subtitles | +0.226 |
シ | +0.223 |
Neg logit contributions | |
aukee | -0.531 |
nesday | -0.467 |
tnc | -0.442 |
agara | -0.417 |
icum | -0.415 |
Token | pillars |
Token ID | 30485 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ANS | +0.144 |
Malik | +0.140 |
amb | +0.136 |
subtitles | +0.128 |
シ | +0.123 |
Neg logit contributions | |
aukee | -0.281 |
nesday | -0.244 |
tnc | -0.234 |
icum | -0.220 |
agara | -0.220 |
Token | of |
Token ID | 286 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
aukee | +0.457 |
nesday | +0.390 |
tnc | +0.374 |
agara | +0.348 |
icum | +0.348 |
Neg logit contributions | |
ANS | -0.296 |
Malik | -0.288 |
amb | -0.279 |
subtitles | -0.266 |
シ | -0.258 |
Token | his |
Token ID | 465 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
ANS | +0.207 |
Malik | +0.204 |
amb | +0.198 |
subtitles | +0.185 |
シ | +0.179 |
Neg logit contributions | |
aukee | -0.385 |
nesday | -0.332 |
tnc | -0.318 |
icum | -0.299 |
agara | -0.298 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ANS | +0.112 |
Malik | +0.110 |
amb | +0.108 |
subtitles | +0.098 |
headphone | +0.096 |
Neg logit contributions | |
aukee | -0.218 |
nesday | -0.190 |
tnc | -0.181 |
agara | -0.172 |
ngth | -0.170 |
Token | — |
Token ID | 960 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
ANS | +0.482 |
Malik | +0.469 |
amb | +0.456 |
subtitles | +0.429 |
シ | +0.417 |
Neg logit contributions | |
aukee | -0.835 |
nesday | -0.721 |
tnc | -0.692 |
agara | -0.646 |
icum | -0.645 |
Token | zero |
Token ID | 22570 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
aukee | +0.165 |
nesday | +0.140 |
tnc | +0.132 |
agara | +0.122 |
icum | +0.122 |
Neg logit contributions | |
ANS | -0.130 |
Malik | -0.126 |
amb | -0.123 |
subtitles | -0.117 |
シ | -0.115 |
Token | poverty |
Token ID | 8098 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ANS | +1.378 |
Malik | +1.327 |
amb | +1.313 |
subtitles | +1.209 |
headphone | +1.175 |
Neg logit contributions | |
aukee | -2.677 |
nesday | -2.326 |
tnc | -2.236 |
icum | -2.071 |
agara | -2.070 |
Token | in |
Token ID | 287 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
aukee | +0.768 |
nesday | +0.656 |
tnc | +0.632 |
agara | +0.593 |
icum | +0.591 |
Neg logit contributions | |
ANS | -0.434 |
Malik | -0.419 |
amb | -0.404 |
subtitles | -0.386 |
headphone | -0.373 |
Token | four |
Token ID | 1440 |
Feature activation | -7.15e-04 |
Pos logit contributions | |
aukee | +0.053 |
nesday | +0.045 |
tnc | +0.044 |
icum | +0.041 |
agara | +0.041 |
Neg logit contributions | |
ANS | -0.031 |
Malik | -0.031 |
amb | -0.030 |
subtitles | -0.028 |
シ | -0.027 |
Token | years |
Token ID | 812 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
ANS | +0.001 |
Malik | +0.001 |
amb | +0.001 |
subtitles | +0.001 |
シ | +0.001 |
Neg logit contributions | |
aukee | -0.003 |
nesday | -0.002 |
tnc | -0.002 |
agara | -0.002 |
icum | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
ANS | +0.129 |
Malik | +0.124 |
amb | +0.120 |
subtitles | +0.114 |
シ | +0.110 |
Neg logit contributions | |
aukee | -0.238 |
nesday | -0.205 |
tnc | -0.197 |
agara | -0.185 |
icum | -0.185 |