Token | ri |
Token ID | 380 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
proport | +1.760 |
suspic | +1.711 |
comr | +1.469 |
fortun | +1.393 |
stress | +1.281 |
Neg logit contributions | |
llah | -1.783 |
ible | -1.668 |
enegger | -1.654 |
IPM | -1.612 |
esters | -1.600 |
Token | va |
Token ID | 6862 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
proport | +1.509 |
suspic | +1.472 |
comr | +1.287 |
fortun | +1.230 |
stress | +1.146 |
Neg logit contributions | |
llah | -1.207 |
ible | -1.117 |
enegger | -1.111 |
IPM | -1.079 |
esters | -1.068 |
Token | have |
Token ID | 423 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
llah | +0.990 |
ible | +0.915 |
enegger | +0.898 |
IPM | +0.871 |
esters | +0.868 |
Neg logit contributions | |
proport | -1.300 |
suspic | -1.274 |
comr | -1.118 |
fortun | -1.053 |
stress | -0.987 |
Token | se |
Token ID | 384 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
llah | +0.086 |
ible | +0.081 |
enegger | +0.079 |
IPM | +0.078 |
esters | +0.077 |
Neg logit contributions | |
proport | -0.101 |
suspic | -0.099 |
comr | -0.086 |
fortun | -0.081 |
stress | -0.076 |
Token | perate |
Token ID | 30052 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
llah | +0.468 |
ible | +0.439 |
enegger | +0.433 |
IPM | +0.425 |
esters | +0.423 |
Neg logit contributions | |
proport | -0.440 |
suspic | -0.431 |
comr | -0.369 |
fortun | -0.347 |
�� | -0.316 |
Token | shr |
Token ID | 10157 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
llah | +0.693 |
ible | +0.657 |
enegger | +0.637 |
IPM | +0.632 |
esters | +0.628 |
Neg logit contributions | |
proport | -0.674 |
suspic | -0.660 |
comr | -0.566 |
fortun | -0.525 |
stress | -0.490 |
Token | ines |
Token ID | 1127 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
proport | +5.076 |
suspic | +4.786 |
comr | +3.814 |
fortun | +3.662 |
stress | +3.412 |
Neg logit contributions | |
llah | -8.913 |
enegger | -8.660 |
ible | -8.381 |
️ | -8.260 |
IPM | -8.251 |
Token | here |
Token ID | 994 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
proport | +1.919 |
suspic | +1.873 |
comr | +1.645 |
fortun | +1.579 |
stress | +1.477 |
Neg logit contributions | |
llah | -1.406 |
ible | -1.293 |
enegger | -1.289 |
IPM | -1.249 |
esters | -1.234 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
llah | +0.295 |
ible | +0.272 |
enegger | +0.268 |
IPM | +0.261 |
esters | +0.258 |
Neg logit contributions | |
proport | -0.417 |
suspic | -0.409 |
comr | -0.361 |
fortun | -0.344 |
stress | -0.322 |
Token | where |
Token ID | 810 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
llah | +0.131 |
ible | +0.122 |
enegger | +0.120 |
IPM | +0.117 |
esters | +0.116 |
Neg logit contributions | |
proport | -0.172 |
suspic | -0.168 |
comr | -0.148 |
fortun | -0.140 |
stress | -0.131 |
Token | p |
Token ID | 279 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
llah | +1.435 |
ible | +1.336 |
enegger | +1.291 |
IPM | +1.278 |
esters | +1.266 |
Neg logit contributions | |
proport | -1.951 |
suspic | -1.912 |
comr | -1.676 |
fortun | -1.581 |
stress | -1.478 |
Token | skipped |
Token ID | 26684 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
llah | +0.739 |
ible | +0.693 |
enegger | +0.676 |
osal | +0.654 |
IPM | +0.653 |
Neg logit contributions | |
proport | -0.995 |
suspic | -0.964 |
comr | -0.857 |
fortun | -0.808 |
�� | -0.751 |
Token | payments |
Token ID | 7524 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
llah | +0.186 |
ible | +0.172 |
enegger | +0.171 |
IPM | +0.167 |
esters | +0.165 |
Neg logit contributions | |
proport | -0.230 |
suspic | -0.225 |
comr | -0.197 |
fortun | -0.188 |
stress | -0.175 |
Token | on |
Token ID | 319 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
proport | +0.248 |
suspic | +0.243 |
comr | +0.215 |
fortun | +0.205 |
stress | +0.192 |
Neg logit contributions | |
llah | -0.173 |
ible | -0.160 |
enegger | -0.158 |
IPM | -0.153 |
esters | -0.152 |
Token | non |
Token ID | 1729 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
proport | +0.323 |
suspic | +0.314 |
comr | +0.276 |
fortun | +0.262 |
stress | +0.244 |
Neg logit contributions | |
llah | -0.258 |
ible | -0.241 |
enegger | -0.236 |
IPM | -0.231 |
esters | -0.229 |
Token | - |
Token ID | 12 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
llah | +0.158 |
ible | +0.147 |
enegger | +0.145 |
esters | +0.141 |
IPM | +0.141 |
Neg logit contributions | |
proport | -0.183 |
suspic | -0.177 |
comr | -0.154 |
fortun | -0.148 |
�� | -0.135 |
Token | deb |
Token ID | 11275 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
proport | +0.491 |
suspic | +0.476 |
comr | +0.406 |
fortun | +0.385 |
stress | +0.349 |
Neg logit contributions | |
llah | -0.544 |
ible | -0.511 |
enegger | -0.507 |
IPM | -0.495 |
esters | -0.493 |
Token | t |
Token ID | 83 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
proport | +5.500 |
suspic | +5.224 |
comr | +4.276 |
fortun | +4.095 |
stress | +3.880 |
Neg logit contributions | |
llah | -7.997 |
enegger | -7.709 |
IPM | -7.532 |
ible | -7.362 |
esters | -7.317 |
Token | obligations |
Token ID | 13675 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
proport | +0.517 |
suspic | +0.504 |
comr | +0.438 |
fortun | +0.418 |
stress | +0.388 |
Neg logit contributions | |
llah | -0.449 |
ible | -0.418 |
enegger | -0.414 |
IPM | -0.403 |
esters | -0.399 |
Token | if |
Token ID | 611 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
proport | +0.923 |
suspic | +0.903 |
comr | +0.797 |
fortun | +0.764 |
stress | +0.715 |
Neg logit contributions | |
llah | -0.637 |
ible | -0.586 |
enegger | -0.581 |
IPM | -0.563 |
esters | -0.557 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
proport | +0.066 |
suspic | +0.065 |
comr | +0.057 |
fortun | +0.054 |
stress | +0.050 |
Neg logit contributions | |
llah | -0.051 |
ible | -0.048 |
enegger | -0.047 |
IPM | -0.046 |
esters | -0.045 |
Token | government |
Token ID | 1230 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
llah | +0.135 |
ible | +0.127 |
enegger | +0.124 |
IPM | +0.122 |
esters | +0.120 |
Neg logit contributions | |
proport | -0.157 |
suspic | -0.153 |
comr | -0.133 |
fortun | -0.126 |
stress | -0.117 |
Token | only |
Token ID | 691 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
llah | +0.073 |
ible | +0.068 |
enegger | +0.067 |
IPM | +0.066 |
esters | +0.065 |
Neg logit contributions | |
proport | -0.083 |
suspic | -0.081 |
comr | -0.071 |
fortun | -0.066 |
stress | -0.062 |
Token | temple |
Token ID | 12505 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
proport | +1.298 |
suspic | +1.263 |
comr | +1.095 |
fortun | +1.037 |
stress | +0.965 |
Neg logit contributions | |
llah | -1.185 |
ible | -1.110 |
enegger | -1.098 |
IPM | -1.075 |
esters | -1.059 |
Token | which |
Token ID | 543 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
proport | +4.906 |
suspic | +4.769 |
comr | +4.155 |
fortun | +4.028 |
stress | +3.741 |
Neg logit contributions | |
llah | -3.959 |
enegger | -3.649 |
ible | -3.598 |
IPM | -3.491 |
esters | -3.490 |
Token | has |
Token ID | 468 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
llah | +0.704 |
ible | +0.651 |
enegger | +0.638 |
IPM | +0.627 |
esters | +0.617 |
Neg logit contributions | |
proport | -1.013 |
suspic | -0.992 |
comr | -0.878 |
fortun | -0.830 |
stress | -0.783 |
Token | a |
Token ID | 257 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
proport | +0.950 |
suspic | +0.927 |
comr | +0.811 |
fortun | +0.773 |
stress | +0.724 |
Neg logit contributions | |
llah | -0.750 |
ible | -0.698 |
enegger | -0.688 |
IPM | -0.675 |
esters | -0.663 |
Token | shrine |
Token ID | 29981 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
proport | +0.322 |
suspic | +0.313 |
comr | +0.272 |
fortun | +0.256 |
stress | +0.240 |
Neg logit contributions | |
llah | -0.288 |
ible | -0.270 |
enegger | -0.265 |
IPM | -0.261 |
esters | -0.256 |
Token | for |
Token ID | 329 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
proport | +7.388 |
suspic | +7.120 |
comr | +6.227 |
fortun | +6.072 |
stress | +5.707 |
Neg logit contributions | |
llah | -6.131 |
enegger | -5.723 |
ible | -5.598 |
esters | -5.483 |
IPM | -5.480 |
Token | Kar |
Token ID | 9375 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
llah | +0.548 |
ible | +0.510 |
enegger | +0.500 |
IPM | +0.492 |
esters | +0.485 |
Neg logit contributions | |
proport | -0.697 |
suspic | -0.680 |
comr | -0.594 |
fortun | -0.562 |
stress | -0.529 |
Token | th |
Token ID | 400 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
proport | +1.484 |
suspic | +1.455 |
comr | +1.296 |
fortun | +1.248 |
stress | +1.172 |
Neg logit contributions | |
llah | -0.813 |
ible | -0.734 |
enegger | -0.730 |
IPM | -0.700 |
esters | -0.696 |
Token | ave |
Token ID | 1015 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
proport | +0.762 |
suspic | +0.749 |
comr | +0.685 |
fortun | +0.664 |
stress | +0.633 |
Neg logit contributions | |
llah | -0.178 |
ible | -0.151 |
enegger | -0.144 |
osal | -0.132 |
esters | -0.132 |
Token | ery |
Token ID | 1924 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
llah | +1.394 |
ible | +1.325 |
enegger | +1.316 |
IPM | +1.290 |
esters | +1.283 |
Neg logit contributions | |
proport | -0.780 |
suspic | -0.750 |
comr | -0.601 |
fortun | -0.550 |
stress | -0.476 |
Token | nu |
Token ID | 28803 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
proport | +2.735 |
suspic | +2.665 |
comr | +2.308 |
fortun | +2.200 |
stress | +2.038 |
Neg logit contributions | |
llah | -2.483 |
ible | -2.310 |
enegger | -2.297 |
IPM | -2.235 |
esters | -2.213 |
Token | D |
Token ID | 360 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
llah | +0.158 |
ible | +0.145 |
enegger | +0.144 |
IPM | +0.139 |
osal | +0.138 |
Neg logit contributions | |
proport | -0.228 |
suspic | -0.223 |
comr | -0.196 |
fortun | -0.187 |
stress | -0.176 |
Token | urga |
Token ID | 45098 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
llah | +0.382 |
ible | +0.357 |
enegger | +0.352 |
IPM | +0.343 |
esters | +0.342 |
Neg logit contributions | |
proport | -0.422 |
suspic | -0.412 |
comr | -0.356 |
fortun | -0.339 |
stress | -0.311 |
Token | also |
Token ID | 635 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
proport | +1.447 |
suspic | +1.415 |
comr | +1.248 |
fortun | +1.195 |
stress | +1.119 |
Neg logit contributions | |
llah | -1.005 |
ible | -0.925 |
enegger | -0.917 |
IPM | -0.888 |
esters | -0.879 |
Token | have |
Token ID | 423 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
proport | +0.761 |
suspic | +0.745 |
comr | +0.658 |
fortun | +0.626 |
stress | +0.587 |
Neg logit contributions | |
llah | -0.538 |
ible | -0.497 |
enegger | -0.490 |
IPM | -0.476 |
esters | -0.471 |
Token | shr |
Token ID | 10157 |
Feature activation | +7.94e+00 |
Pos logit contributions | |
llah | +0.190 |
ible | +0.180 |
enegger | +0.175 |
IPM | +0.174 |
osal | +0.171 |
Neg logit contributions | |
proport | -0.214 |
suspic | -0.209 |
comr | -0.181 |
fortun | -0.171 |
stress | -0.160 |
Token | ines |
Token ID | 1127 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
proport | +4.539 |
suspic | +4.260 |
comr | +3.400 |
fortun | +3.294 |
stress | +3.221 |
Neg logit contributions | |
llah | -8.382 |
enegger | -8.217 |
IPM | -7.851 |
ible | -7.844 |
️ | -7.810 |
Token | here |
Token ID | 994 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
proport | +1.841 |
suspic | +1.799 |
comr | +1.584 |
fortun | +1.518 |
stress | +1.421 |
Neg logit contributions | |
llah | -1.312 |
ible | -1.208 |
enegger | -1.200 |
IPM | -1.164 |
esters | -1.151 |
Token | . |
Token ID | 13 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
llah | +0.266 |
ible | +0.245 |
enegger | +0.241 |
IPM | +0.234 |
esters | +0.231 |
Neg logit contributions | |
proport | -0.397 |
suspic | -0.388 |
comr | -0.344 |
fortun | -0.328 |
stress | -0.308 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
llah | +0.038 |
ible | +0.035 |
enegger | +0.035 |
IPM | +0.034 |
esters | +0.033 |
Neg logit contributions | |
proport | -0.051 |
suspic | -0.049 |
comr | -0.043 |
fortun | -0.041 |
stress | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
llah | +0.221 |
enegger | +0.207 |
ible | +0.202 |
esters | +0.197 |
IPM | +0.197 |
Neg logit contributions | |
proport | -0.251 |
suspic | -0.246 |
comr | -0.214 |
fortun | -0.209 |
stress | -0.203 |
Token | echoes |
Token ID | 30346 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
llah | +0.567 |
ible | +0.529 |
enegger | +0.521 |
IPM | +0.504 |
esters | +0.503 |
Neg logit contributions | |
proport | -0.741 |
suspic | -0.720 |
comr | -0.631 |
fortun | -0.603 |
stress | -0.564 |
Token | of |
Token ID | 286 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
proport | +1.116 |
suspic | +1.089 |
comr | +0.954 |
fortun | +0.914 |
stress | +0.854 |
Neg logit contributions | |
llah | -0.849 |
ible | -0.782 |
enegger | -0.779 |
IPM | -0.758 |
esters | -0.747 |
Token | M |
Token ID | 337 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
proport | +0.033 |
suspic | +0.032 |
comr | +0.028 |
fortun | +0.027 |
stress | +0.025 |
Neg logit contributions | |
llah | -0.026 |
ible | -0.025 |
enegger | -0.024 |
IPM | -0.024 |
esters | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
llah | +0.676 |
ible | +0.634 |
enegger | +0.623 |
esters | +0.606 |
IPM | +0.604 |
Neg logit contributions | |
proport | -0.815 |
suspic | -0.790 |
comr | -0.691 |
fortun | -0.657 |
stress | -0.610 |
Token | Night |
Token ID | 5265 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
proport | +0.582 |
suspic | +0.568 |
comr | +0.498 |
fortun | +0.479 |
stress | +0.446 |
Neg logit contributions | |
llah | -0.432 |
ible | -0.398 |
enegger | -0.398 |
IPM | -0.385 |
esters | -0.382 |
Token | Shy |
Token ID | 36838 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
llah | +1.083 |
ible | +1.012 |
enegger | +1.000 |
IPM | +0.968 |
esters | +0.964 |
Neg logit contributions | |
proport | -1.282 |
suspic | -1.246 |
comr | -1.090 |
fortun | -1.033 |
stress | -0.951 |
Token | am |
Token ID | 321 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
proport | +5.804 |
suspic | +5.664 |
comr | +4.729 |
fortun | +4.434 |
stress | +4.173 |
Neg logit contributions | |
llah | -7.574 |
enegger | -7.235 |
ible | -7.204 |
IPM | -7.030 |
RESULTS | -6.910 |
Token | alan |
Token ID | 25786 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
proport | +0.766 |
suspic | +0.749 |
comr | +0.662 |
fortun | +0.642 |
�� | +0.576 |
Neg logit contributions | |
llah | -0.453 |
ible | -0.424 |
esters | -0.424 |
osal | -0.413 |
enegger | -0.413 |
Token | � |
Token ID | 447 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
proport | +0.847 |
suspic | +0.825 |
comr | +0.723 |
fortun | +0.689 |
stress | +0.640 |
Neg logit contributions | |
llah | -0.687 |
ible | -0.637 |
enegger | -0.635 |
IPM | -0.613 |
esters | -0.610 |
Token | � |
Token ID | 247 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
llah | +0.201 |
enegger | +0.192 |
ible | +0.191 |
IPM | +0.188 |
esters | +0.186 |
Neg logit contributions | |
proport | -0.107 |
suspic | -0.102 |
comr | -0.081 |
fortun | -0.075 |
stress | -0.066 |
Token | s |
Token ID | 82 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
proport | +0.369 |
suspic | +0.361 |
comr | +0.325 |
fortun | +0.313 |
stress | +0.296 |
Neg logit contributions | |
llah | -0.171 |
ible | -0.153 |
enegger | -0.151 |
IPM | -0.144 |
esters | -0.143 |
Token | Vish |
Token ID | 36900 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
proport | +0.077 |
suspic | +0.075 |
comr | +0.065 |
fortun | +0.061 |
stress | +0.057 |
Neg logit contributions | |
llah | -0.066 |
ible | -0.062 |
enegger | -0.061 |
IPM | -0.059 |
esters | -0.059 |
Token | nu |
Token ID | 28803 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
proport | +3.801 |
suspic | +3.699 |
comr | +3.203 |
fortun | +3.051 |
stress | +2.829 |
Neg logit contributions | |
llah | -3.572 |
ible | -3.329 |
enegger | -3.316 |
IPM | -3.241 |
esters | -3.198 |
Token | temple |
Token ID | 12505 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
proport | +0.210 |
suspic | +0.205 |
comr | +0.178 |
fortun | +0.169 |
stress | +0.158 |
Neg logit contributions | |
llah | -0.176 |
ible | -0.162 |
enegger | -0.161 |
IPM | -0.156 |
esters | -0.156 |
Token | have |
Token ID | 423 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
proport | +4.611 |
suspic | +4.496 |
comr | +3.934 |
fortun | +3.784 |
stress | +3.530 |
Neg logit contributions | |
llah | -3.612 |
ible | -3.341 |
enegger | -3.338 |
IPM | -3.239 |
esters | -3.180 |
Token | a |
Token ID | 257 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
proport | +0.467 |
suspic | +0.457 |
comr | +0.399 |
fortun | +0.378 |
stress | +0.355 |
Neg logit contributions | |
llah | -0.370 |
ible | -0.345 |
enegger | -0.338 |
IPM | -0.333 |
esters | -0.327 |
Token | shrine |
Token ID | 29981 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
proport | +0.402 |
suspic | +0.392 |
comr | +0.338 |
fortun | +0.317 |
stress | +0.295 |
Neg logit contributions | |
llah | -0.385 |
ible | -0.360 |
enegger | -0.353 |
IPM | -0.348 |
osal | -0.345 |
Token | for |
Token ID | 329 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
proport | +6.900 |
suspic | +6.635 |
comr | +5.803 |
fortun | +5.635 |
stress | +5.271 |
Neg logit contributions | |
llah | -5.926 |
enegger | -5.548 |
ible | -5.460 |
IPM | -5.333 |
esters | -5.294 |
Token | Bh |
Token ID | 16581 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
llah | +0.526 |
ible | +0.486 |
enegger | +0.474 |
IPM | +0.471 |
esters | +0.463 |
Neg logit contributions | |
proport | -0.726 |
suspic | -0.711 |
comr | -0.622 |
fortun | -0.590 |
stress | -0.559 |
Token | air |
Token ID | 958 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
llah | +0.177 |
enegger | +0.162 |
ible | +0.161 |
IPM | +0.156 |
esters | +0.154 |
Neg logit contributions | |
proport | -0.263 |
suspic | -0.257 |
comr | -0.227 |
fortun | -0.219 |
stress | -0.206 |
Token | ava |
Token ID | 4170 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
llah | +0.780 |
ible | +0.715 |
enegger | +0.710 |
IPM | +0.688 |
esters | +0.679 |
Neg logit contributions | |
proport | -1.183 |
suspic | -1.156 |
comr | -1.023 |
fortun | -0.982 |
stress | -0.922 |
Token | . |
Token ID | 13 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
llah | +0.704 |
ible | +0.642 |
enegger | +0.635 |
IPM | +0.613 |
osal | +0.610 |
Neg logit contributions | |
proport | -1.091 |
suspic | -1.071 |
comr | -0.949 |
fortun | -0.900 |
stress | -0.844 |
Token | ansky |
Token ID | 49792 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
llah | +2.549 |
ible | +2.423 |
enegger | +2.358 |
osal | +2.278 |
esters | +2.275 |
Neg logit contributions | |
proport | -2.949 |
suspic | -2.884 |
comr | -2.516 |
fortun | -2.379 |
�� | -2.160 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
llah | +0.151 |
ible | +0.139 |
enegger | +0.138 |
IPM | +0.134 |
esters | +0.132 |
Neg logit contributions | |
proport | -0.207 |
suspic | -0.202 |
comr | -0.178 |
fortun | -0.170 |
stress | -0.159 |
Token | � |
Token ID | 564 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
llah | +0.098 |
ible | +0.091 |
enegger | +0.090 |
IPM | +0.088 |
esters | +0.086 |
Neg logit contributions | |
proport | -0.125 |
suspic | -0.122 |
comr | -0.107 |
fortun | -0.102 |
stress | -0.095 |
Token | � |
Token ID | 250 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
llah | +0.045 |
ible | +0.041 |
enegger | +0.040 |
IPM | +0.039 |
esters | +0.039 |
Neg logit contributions | |
proport | -0.072 |
suspic | -0.070 |
comr | -0.062 |
fortun | -0.060 |
stress | -0.056 |
Token | The |
Token ID | 464 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
llah | +0.608 |
ible | +0.558 |
enegger | +0.548 |
IPM | +0.533 |
esters | +0.528 |
Neg logit contributions | |
proport | -0.927 |
suspic | -0.907 |
comr | -0.801 |
fortun | -0.767 |
stress | -0.717 |
Token | Deb |
Token ID | 8965 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
proport | +0.377 |
suspic | +0.368 |
comr | +0.323 |
fortun | +0.308 |
stress | +0.287 |
Neg logit contributions | |
llah | -0.290 |
ible | -0.268 |
enegger | -0.265 |
IPM | -0.258 |
esters | -0.255 |
Token | as |
Token ID | 292 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
proport | +6.342 |
suspic | +6.114 |
comr | +5.203 |
fortun | +5.054 |
stress | +4.793 |
Neg logit contributions | |
llah | -6.201 |
enegger | -5.950 |
IPM | -5.741 |
ible | -5.617 |
️ | -5.554 |
Token | ement |
Token ID | 972 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
proport | +1.550 |
suspic | +1.502 |
comr | +1.292 |
fortun | +1.234 |
stress | +1.151 |
Neg logit contributions | |
llah | -1.556 |
enegger | -1.452 |
ible | -1.440 |
IPM | -1.411 |
esters | -1.405 |
Token | of |
Token ID | 286 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
proport | +1.030 |
suspic | +1.008 |
comr | +0.883 |
fortun | +0.843 |
stress | +0.783 |
Neg logit contributions | |
llah | -0.796 |
ible | -0.740 |
enegger | -0.725 |
IPM | -0.708 |
osal | -0.700 |
Token | Din |
Token ID | 23448 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
proport | +0.044 |
suspic | +0.043 |
comr | +0.038 |
fortun | +0.036 |
stress | +0.034 |
Neg logit contributions | |
llah | -0.031 |
ible | -0.029 |
enegger | -0.028 |
IPM | -0.028 |
esters | -0.028 |
Token | ah |
Token ID | 993 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
proport | +1.696 |
suspic | +1.653 |
comr | +1.449 |
fortun | +1.389 |
stress | +1.300 |
Neg logit contributions | |
llah | -1.318 |
ible | -1.214 |
enegger | -1.212 |
IPM | -1.176 |
esters | -1.164 |
Token | : |
Token ID | 1058 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
proport | +1.436 |
suspic | +1.398 |
comr | +1.209 |
fortun | +1.147 |
stress | +1.061 |
Neg logit contributions | |
llah | -1.352 |
ible | -1.260 |
enegger | -1.248 |
IPM | -1.220 |
esters | -1.207 |
Token | There |
Token ID | 1318 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
proport | +0.894 |
suspic | +0.874 |
comr | +0.764 |
fortun | +0.729 |
stress | +0.680 |
Neg logit contributions | |
llah | -0.699 |
ible | -0.648 |
enegger | -0.641 |
IPM | -0.627 |
esters | -0.618 |
Token | is |
Token ID | 318 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
proport | +2.060 |
suspic | +2.016 |
comr | +1.794 |
fortun | +1.723 |
stress | +1.623 |
Neg logit contributions | |
llah | -1.210 |
ible | -1.102 |
enegger | -1.092 |
IPM | -1.053 |
esters | -1.042 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
proport | +0.525 |
suspic | +0.513 |
comr | +0.445 |
fortun | +0.423 |
stress | +0.395 |
Neg logit contributions | |
llah | -0.462 |
ible | -0.433 |
enegger | -0.426 |
IPM | -0.420 |
esters | -0.412 |
Token | special |
Token ID | 2041 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
proport | +0.156 |
suspic | +0.152 |
comr | +0.132 |
fortun | +0.125 |
stress | +0.116 |
Neg logit contributions | |
llah | -0.145 |
ible | -0.136 |
enegger | -0.133 |
IPM | -0.131 |
osal | -0.129 |
Token | shrine |
Token ID | 29981 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
proport | +0.687 |
suspic | +0.670 |
comr | +0.576 |
fortun | +0.545 |
stress | +0.505 |
Neg logit contributions | |
llah | -0.666 |
ible | -0.625 |
enegger | -0.618 |
IPM | -0.607 |
esters | -0.597 |
Token | for |
Token ID | 329 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
proport | +6.807 |
suspic | +6.564 |
comr | +5.700 |
fortun | +5.571 |
stress | +5.198 |
Neg logit contributions | |
llah | -5.762 |
enegger | -5.362 |
ible | -5.231 |
IPM | -5.108 |
esters | -5.071 |
Token | Lord |
Token ID | 4453 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
llah | +0.551 |
ible | +0.509 |
enegger | +0.500 |
IPM | +0.494 |
esters | +0.485 |
Neg logit contributions | |
proport | -0.751 |
suspic | -0.736 |
comr | -0.643 |
fortun | -0.611 |
stress | -0.575 |
Token | of |
Token ID | 286 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
proport | +0.028 |
suspic | +0.028 |
comr | +0.024 |
fortun | +0.023 |
stress | +0.021 |
Neg logit contributions | |
llah | -0.022 |
ible | -0.020 |
enegger | -0.020 |
IPM | -0.020 |
osal | -0.019 |
Token | medicine |
Token ID | 9007 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
proport | +0.493 |
suspic | +0.482 |
comr | +0.420 |
fortun | +0.400 |
stress | +0.373 |
Neg logit contributions | |
llah | -0.400 |
ible | -0.372 |
enegger | -0.368 |
IPM | -0.360 |
esters | -0.356 |
Token | and |
Token ID | 290 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
proport | +3.453 |
suspic | +3.364 |
comr | +2.953 |
fortun | +2.852 |
stress | +2.658 |
Neg logit contributions | |
llah | -2.610 |
enegger | -2.407 |
ible | -2.407 |
IPM | -2.318 |
esters | -2.303 |
Token | i |
Token ID | 72 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
llah | +3.112 |
ible | +2.899 |
enegger | +2.838 |
osal | +2.782 |
IPM | +2.775 |
Neg logit contributions | |
proport | -3.293 |
suspic | -3.232 |
comr | -2.769 |
fortun | -2.625 |
�� | -2.406 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
proport | +1.355 |
suspic | +1.323 |
comr | +1.160 |
fortun | +1.108 |
stress | +1.035 |
Neg logit contributions | |
llah | -1.036 |
ible | -0.957 |
enegger | -0.950 |
IPM | -0.923 |
esters | -0.913 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
llah | +0.118 |
ible | +0.110 |
enegger | +0.108 |
IPM | +0.105 |
esters | +0.105 |
Neg logit contributions | |
proport | -0.158 |
suspic | -0.154 |
comr | -0.135 |
fortun | -0.129 |
stress | -0.121 |
Token | have |
Token ID | 423 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
llah | +0.874 |
ible | +0.802 |
enegger | +0.790 |
IPM | +0.766 |
esters | +0.757 |
Neg logit contributions | |
proport | -1.345 |
suspic | -1.323 |
comr | -1.173 |
fortun | -1.118 |
stress | -1.049 |
Token | a |
Token ID | 257 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
llah | +0.257 |
ible | +0.241 |
enegger | +0.237 |
IPM | +0.233 |
esters | +0.229 |
Neg logit contributions | |
proport | -0.312 |
suspic | -0.306 |
comr | -0.266 |
fortun | -0.254 |
stress | -0.238 |
Token | shrine |
Token ID | 29981 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
proport | +0.067 |
suspic | +0.066 |
comr | +0.057 |
fortun | +0.054 |
stress | +0.050 |
Neg logit contributions | |
llah | -0.064 |
ible | -0.060 |
enegger | -0.059 |
IPM | -0.058 |
osal | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
proport | +6.813 |
suspic | +6.584 |
comr | +5.709 |
fortun | +5.535 |
stress | +5.192 |
Neg logit contributions | |
llah | -5.670 |
enegger | -5.296 |
ible | -5.171 |
IPM | -5.091 |
esters | -5.052 |
Token | this |
Token ID | 428 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
llah | +0.070 |
ible | +0.065 |
enegger | +0.064 |
IPM | +0.063 |
esters | +0.062 |
Neg logit contributions | |
proport | -0.088 |
suspic | -0.086 |
comr | -0.075 |
fortun | -0.072 |
stress | -0.067 |
Token | temple |
Token ID | 12505 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
llah | +0.686 |
ible | +0.648 |
enegger | +0.635 |
IPM | +0.626 |
esters | +0.616 |
Neg logit contributions | |
proport | -0.665 |
suspic | -0.647 |
comr | -0.557 |
fortun | -0.525 |
stress | -0.487 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
proport | +4.637 |
suspic | +4.513 |
comr | +3.902 |
fortun | +3.783 |
stress | +3.519 |
Neg logit contributions | |
llah | -3.887 |
enegger | -3.648 |
ible | -3.575 |
IPM | -3.501 |
esters | -3.474 |
Token | A |
Token ID | 317 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
proport | +0.213 |
suspic | +0.208 |
comr | +0.181 |
fortun | +0.173 |
stress | +0.161 |
Neg logit contributions | |
llah | -0.176 |
ible | -0.163 |
enegger | -0.162 |
IPM | -0.158 |
esters | -0.156 |
Token | of |
Token ID | 286 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
llah | +0.132 |
ible | +0.122 |
enegger | +0.120 |
IPM | +0.117 |
osal | +0.116 |
Neg logit contributions | |
proport | -0.177 |
suspic | -0.174 |
comr | -0.153 |
fortun | -0.146 |
stress | -0.136 |
Token | these |
Token ID | 777 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
llah | +0.066 |
ible | +0.061 |
enegger | +0.060 |
IPM | +0.059 |
esters | +0.058 |
Neg logit contributions | |
proport | -0.086 |
suspic | -0.084 |
comr | -0.074 |
fortun | -0.070 |
stress | -0.066 |
Token | three |
Token ID | 1115 |
Feature activation | +7.14e-03 |
Pos logit contributions | |
llah | +0.320 |
ible | +0.296 |
enegger | +0.290 |
IPM | +0.284 |
esters | +0.281 |
Neg logit contributions | |
proport | -0.439 |
suspic | -0.426 |
comr | -0.376 |
fortun | -0.359 |
stress | -0.337 |
Token | � |
Token ID | 564 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
proport | +0.007 |
suspic | +0.007 |
comr | +0.006 |
fortun | +0.006 |
stress | +0.006 |
Neg logit contributions | |
llah | -0.005 |
ible | -0.005 |
enegger | -0.005 |
IPM | -0.005 |
esters | -0.004 |
Token | � |
Token ID | 250 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
proport | +0.968 |
suspic | +0.943 |
comr | +0.822 |
fortun | +0.784 |
stress | +0.728 |
Neg logit contributions | |
llah | -0.827 |
ible | -0.768 |
enegger | -0.759 |
IPM | -0.740 |
esters | -0.735 |
Token | deb |
Token ID | 11275 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
proport | +0.078 |
suspic | +0.076 |
comr | +0.067 |
fortun | +0.064 |
stress | +0.059 |
Neg logit contributions | |
llah | -0.063 |
ible | -0.059 |
enegger | -0.058 |
esters | -0.056 |
IPM | -0.056 |
Token | t |
Token ID | 83 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
proport | +5.214 |
suspic | +4.997 |
comr | +4.111 |
fortun | +3.961 |
stress | +3.693 |
Neg logit contributions | |
llah | -7.050 |
enegger | -6.776 |
IPM | -6.679 |
ible | -6.524 |
esters | -6.443 |
Token | free |
Token ID | 1479 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
proport | +0.474 |
suspic | +0.463 |
comr | +0.406 |
fortun | +0.388 |
stress | +0.362 |
Neg logit contributions | |
llah | -0.360 |
ible | -0.334 |
enegger | -0.329 |
IPM | -0.320 |
esters | -0.317 |
Token | � |
Token ID | 447 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
llah | +1.373 |
ible | +1.261 |
enegger | +1.224 |
IPM | +1.208 |
esters | +1.207 |
Neg logit contributions | |
proport | -2.034 |
suspic | -1.985 |
comr | -1.761 |
fortun | -1.672 |
stress | -1.576 |
Token | � |
Token ID | 251 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
proport | +0.499 |
suspic | +0.489 |
comr | +0.431 |
fortun | +0.413 |
stress | +0.387 |
Neg logit contributions | |
llah | -0.346 |
ible | -0.317 |
enegger | -0.314 |
IPM | -0.306 |
esters | -0.303 |
Token | countries |
Token ID | 2678 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
proport | +0.623 |
suspic | +0.609 |
comr | +0.537 |
fortun | +0.514 |
stress | +0.481 |
Neg logit contributions | |
llah | -0.440 |
ible | -0.405 |
enegger | -0.402 |
IPM | -0.389 |
esters | -0.385 |
Token | to |
Token ID | 284 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
llah | +1.522 |
ible | +1.402 |
enegger | +1.367 |
IPM | +1.323 |
esters | +1.321 |
Neg logit contributions | |
proport | -2.491 |
suspic | -2.445 |
comr | -2.176 |
fortun | -2.081 |
stress | -1.947 |
Token | come |
Token ID | 1282 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
llah | +0.038 |
ible | +0.035 |
enegger | +0.035 |
esters | +0.033 |
IPM | +0.033 |
Neg logit contributions | |
proport | -0.059 |
suspic | -0.057 |
comr | -0.051 |
fortun | -0.049 |
stress | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
llah | +0.349 |
ible | +0.321 |
enegger | +0.318 |
IPM | +0.306 |
esters | +0.304 |
Neg logit contributions | |
proport | -0.522 |
suspic | -0.511 |
comr | -0.452 |
fortun | -0.432 |
stress | -0.405 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
llah | +0.021 |
ible | +0.019 |
enegger | +0.019 |
IPM | +0.019 |
esters | +0.018 |
Neg logit contributions | |
proport | -0.024 |
suspic | -0.023 |
comr | -0.020 |
fortun | -0.019 |
stress | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
llah | +0.309 |
enegger | +0.289 |
ible | +0.282 |
esters | +0.275 |
IPM | +0.275 |
Neg logit contributions | |
proport | -0.351 |
suspic | -0.343 |
comr | -0.299 |
fortun | -0.292 |
stress | -0.283 |
Token | Deb |
Token ID | 16587 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
llah | +0.126 |
ible | +0.117 |
enegger | +0.115 |
IPM | +0.112 |
esters | +0.111 |
Neg logit contributions | |
proport | -0.155 |
suspic | -0.150 |
comr | -0.131 |
fortun | -0.125 |
stress | -0.115 |
Token | t |
Token ID | 83 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
proport | +5.121 |
suspic | +4.888 |
comr | +4.062 |
fortun | +3.858 |
stress | +3.627 |
Neg logit contributions | |
llah | -7.024 |
enegger | -6.685 |
IPM | -6.563 |
ible | -6.529 |
esters | -6.437 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
proport | +0.747 |
suspic | +0.731 |
comr | +0.646 |
fortun | +0.620 |
stress | +0.582 |
Neg logit contributions | |
llah | -0.483 |
ible | -0.445 |
enegger | -0.440 |
IPM | -0.426 |
esters | -0.421 |
Token | fund |
Token ID | 1814 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
llah | +0.212 |
ible | +0.196 |
enegger | +0.192 |
IPM | +0.187 |
esters | +0.184 |
Neg logit contributions | |
proport | -0.325 |
suspic | -0.319 |
comr | -0.283 |
fortun | -0.271 |
stress | -0.255 |
Token | infrastructure |
Token ID | 6884 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
proport | +0.705 |
suspic | +0.687 |
comr | +0.599 |
fortun | +0.572 |
stress | +0.532 |
Neg logit contributions | |
llah | -0.590 |
ible | -0.548 |
enegger | -0.544 |
IPM | -0.530 |
esters | -0.524 |
Token | projects |
Token ID | 4493 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
llah | +0.453 |
ible | +0.422 |
enegger | +0.415 |
IPM | +0.404 |
esters | +0.396 |
Neg logit contributions | |
proport | -0.672 |
suspic | -0.656 |
comr | -0.580 |
fortun | -0.554 |
stress | -0.520 |
Token | being |
Token ID | 852 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
proport | +0.596 |
suspic | +0.581 |
comr | +0.509 |
fortun | +0.485 |
stress | +0.454 |
Neg logit contributions | |
llah | -0.467 |
ible | -0.434 |
enegger | -0.431 |
IPM | -0.418 |
esters | -0.414 |
Token | paired |
Token ID | 20312 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
llah | +0.276 |
ible | +0.256 |
enegger | +0.254 |
IPM | +0.248 |
esters | +0.244 |
Neg logit contributions | |
proport | -0.364 |
suspic | -0.355 |
comr | -0.312 |
fortun | -0.298 |
stress | -0.279 |
Token | with |
Token ID | 351 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
proport | +0.661 |
suspic | +0.646 |
comr | +0.565 |
fortun | +0.534 |
stress | +0.496 |
Neg logit contributions | |
llah | -0.566 |
ible | -0.527 |
enegger | -0.522 |
IPM | -0.508 |
esters | -0.503 |
Token | " |
Token ID | 366 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
proport | +0.679 |
suspic | +0.660 |
comr | +0.578 |
fortun | +0.550 |
stress | +0.513 |
Neg logit contributions | |
llah | -0.545 |
ible | -0.507 |
enegger | -0.503 |
IPM | -0.488 |
esters | -0.483 |
Token | The |
Token ID | 464 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
proport | +1.155 |
suspic | +1.127 |
comr | +0.984 |
fortun | +0.940 |
stress | +0.874 |
Neg logit contributions | |
llah | -0.945 |
ible | -0.876 |
enegger | -0.870 |
IPM | -0.846 |
esters | -0.838 |
Token | Doors |
Token ID | 33775 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
proport | +0.924 |
suspic | +0.900 |
comr | +0.784 |
fortun | +0.747 |
stress | +0.694 |
Neg logit contributions | |
llah | -0.779 |
ible | -0.725 |
enegger | -0.720 |
IPM | -0.700 |
esters | -0.693 |
Token | "? |
Token ID | 13984 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
proport | +6.202 |
suspic | +6.008 |
comr | +5.160 |
fortun | +5.016 |
stress | +4.698 |
Neg logit contributions | |
llah | -5.991 |
enegger | -5.534 |
ible | -5.477 |
IPM | -5.363 |
esters | -5.306 |
Token | Yeah |
Token ID | 9425 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
llah | +0.761 |
ible | +0.709 |
enegger | +0.704 |
IPM | +0.686 |
esters | +0.675 |
Neg logit contributions | |
proport | -0.969 |
suspic | -0.945 |
comr | -0.828 |
fortun | -0.784 |
stress | -0.727 |
Token | , |
Token ID | 11 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
llah | +1.170 |
ible | +1.091 |
enegger | +1.070 |
esters | +1.028 |
IPM | +1.026 |
Neg logit contributions | |
proport | -1.745 |
suspic | -1.700 |
comr | -1.507 |
fortun | -1.439 |
stress | -1.339 |
Token | dude |
Token ID | 18396 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
proport | +0.487 |
suspic | +0.475 |
comr | +0.418 |
fortun | +0.399 |
stress | +0.374 |
Neg logit contributions | |
llah | -0.353 |
ible | -0.327 |
enegger | -0.324 |
IPM | -0.315 |
esters | -0.311 |
Token | , |
Token ID | 11 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
proport | +0.333 |
suspic | +0.326 |
comr | +0.287 |
fortun | +0.275 |
stress | +0.257 |
Neg logit contributions | |
llah | -0.232 |
ible | -0.214 |
enegger | -0.212 |
IPM | -0.205 |
esters | -0.203 |
Token | great |
Token ID | 1049 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
llah | +0.083 |
ible | +0.077 |
enegger | +0.077 |
IPM | +0.075 |
esters | +0.074 |
Neg logit contributions | |
proport | -0.106 |
suspic | -0.103 |
comr | -0.090 |
fortun | -0.086 |
stress | -0.080 |
Token | things |
Token ID | 1243 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
proport | +0.648 |
suspic | +0.631 |
comr | +0.544 |
fortun | +0.517 |
stress | +0.478 |
Neg logit contributions | |
llah | -0.628 |
ible | -0.586 |
enegger | -0.583 |
IPM | -0.568 |
esters | -0.563 |
Token | : |
Token ID | 25 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
proport | +2.029 |
suspic | +1.978 |
comr | +1.732 |
fortun | +1.662 |
stress | +1.554 |
Neg logit contributions | |
llah | -1.565 |
ible | -1.442 |
enegger | -1.435 |
IPM | -1.397 |
esters | -1.381 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
proport | +1.616 |
suspic | +1.582 |
comr | +1.387 |
fortun | +1.326 |
stress | +1.237 |
Neg logit contributions | |
llah | -1.207 |
ible | -1.117 |
enegger | -1.105 |
IPM | -1.076 |
esters | -1.063 |
Token |
|
Token ID | 198 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
llah | +0.203 |
enegger | +0.189 |
ible | +0.185 |
esters | +0.180 |
IPM | +0.180 |
Neg logit contributions | |
proport | -0.227 |
suspic | -0.220 |
comr | -0.193 |
fortun | -0.188 |
stress | -0.183 |
Token | Decre |
Token ID | 43198 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
llah | +0.050 |
ible | +0.047 |
enegger | +0.047 |
IPM | +0.045 |
esters | +0.045 |
Neg logit contributions | |
proport | -0.054 |
suspic | -0.052 |
comr | -0.045 |
fortun | -0.043 |
stress | -0.039 |
Token | ases |
Token ID | 1386 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
proport | +4.921 |
suspic | +4.647 |
comr | +3.894 |
fortun | +3.742 |
stress | +3.561 |
Neg logit contributions | |
llah | -6.969 |
enegger | -6.612 |
ible | -6.458 |
IPM | -6.420 |
esters | -6.288 |
Token | blood |
Token ID | 2910 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
proport | +1.263 |
suspic | +1.234 |
comr | +1.074 |
fortun | +1.026 |
stress | +0.949 |
Neg logit contributions | |
llah | -1.065 |
ible | -0.991 |
enegger | -0.982 |
IPM | -0.957 |
esters | -0.947 |
Token | glucose |
Token ID | 15701 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
llah | +0.223 |
ible | +0.206 |
enegger | +0.199 |
esters | +0.194 |
IPM | +0.192 |
Neg logit contributions | |
proport | -0.403 |
suspic | -0.396 |
comr | -0.352 |
fortun | -0.339 |
�� | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
llah | +0.423 |
ible | +0.392 |
enegger | +0.382 |
IPM | +0.373 |
esters | +0.371 |
Neg logit contributions | |
proport | -0.670 |
suspic | -0.660 |
comr | -0.586 |
fortun | -0.563 |
stress | -0.521 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
proport | +0.718 |
suspic | +0.701 |
comr | +0.611 |
fortun | +0.582 |
stress | +0.539 |
Neg logit contributions | |
llah | -0.592 |
ible | -0.551 |
enegger | -0.547 |
IPM | -0.533 |
esters | -0.526 |
Token | Chan |
Token ID | 18704 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
llah | +0.265 |
ible | +0.246 |
enegger | +0.244 |
IPM | +0.236 |
esters | +0.234 |
Neg logit contributions | |
proport | -0.341 |
suspic | -0.334 |
comr | -0.292 |
fortun | -0.279 |
stress | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
proport | +1.714 |
suspic | +1.675 |
comr | +1.466 |
fortun | +1.403 |
stress | +1.317 |
Neg logit contributions | |
llah | -1.327 |
ible | -1.225 |
enegger | -1.217 |
IPM | -1.186 |
esters | -1.172 |
Token | an |
Token ID | 281 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
llah | +0.175 |
ible | +0.163 |
enegger | +0.162 |
IPM | +0.158 |
esters | +0.155 |
Neg logit contributions | |
proport | -0.207 |
suspic | -0.201 |
comr | -0.176 |
fortun | -0.167 |
stress | -0.155 |
Token | official |
Token ID | 1743 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
llah | +0.853 |
ible | +0.793 |
enegger | +0.788 |
IPM | +0.768 |
esters | +0.759 |
Neg logit contributions | |
proport | -1.001 |
suspic | -0.976 |
comr | -0.850 |
fortun | -0.810 |
stress | -0.753 |
Token | with |
Token ID | 351 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
llah | +0.294 |
ible | +0.270 |
enegger | +0.265 |
IPM | +0.259 |
esters | +0.255 |
Neg logit contributions | |
proport | -0.459 |
suspic | -0.448 |
comr | -0.398 |
fortun | -0.380 |
stress | -0.356 |
Token | Greenpeace |
Token ID | 42793 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
proport | +0.387 |
suspic | +0.377 |
comr | +0.329 |
fortun | +0.314 |
stress | +0.292 |
Neg logit contributions | |
llah | -0.322 |
ible | -0.299 |
enegger | -0.298 |
IPM | -0.290 |
esters | -0.286 |
Token | in |
Token ID | 287 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
proport | +6.390 |
suspic | +6.277 |
comr | +5.409 |
fortun | +5.174 |
stress | +4.981 |
Neg logit contributions | |
llah | -5.571 |
ible | -5.045 |
enegger | -5.027 |
osal | -4.944 |
IPM | -4.935 |
Token | southern |
Token ID | 8372 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
llah | +0.132 |
ible | +0.123 |
enegger | +0.121 |
IPM | +0.118 |
esters | +0.116 |
Neg logit contributions | |
proport | -0.201 |
suspic | -0.196 |
comr | -0.174 |
fortun | -0.166 |
stress | -0.155 |
Token | China |
Token ID | 2807 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
llah | +1.456 |
ible | +1.352 |
enegger | +1.318 |
IPM | +1.290 |
esters | +1.279 |
Neg logit contributions | |
proport | -2.425 |
suspic | -2.375 |
comr | -2.100 |
fortun | -2.009 |
stress | -1.891 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
proport | +0.668 |
suspic | +0.654 |
comr | +0.579 |
fortun | +0.554 |
stress | +0.517 |
Neg logit contributions | |
llah | -0.444 |
ible | -0.411 |
enegger | -0.405 |
IPM | -0.391 |
esters | -0.389 |
Token |
|
Token ID | 198 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
llah | +0.194 |
ible | +0.178 |
enegger | +0.178 |
IPM | +0.174 |
esters | +0.170 |
Neg logit contributions | |
proport | -0.279 |
suspic | -0.273 |
comr | -0.241 |
fortun | -0.230 |
stress | -0.213 |
Token | s |
Token ID | 82 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
llah | +0.072 |
ible | +0.066 |
enegger | +0.065 |
IPM | +0.061 |
esters | +0.061 |
Neg logit contributions | |
proport | -0.140 |
suspic | -0.137 |
comr | -0.123 |
fortun | -0.118 |
stress | -0.111 |
Token | just |
Token ID | 655 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
llah | +0.501 |
ible | +0.465 |
enegger | +0.456 |
IPM | +0.443 |
esters | +0.435 |
Neg logit contributions | |
proport | -0.775 |
suspic | -0.753 |
comr | -0.670 |
fortun | -0.641 |
stress | -0.603 |
Token | like |
Token ID | 588 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
llah | +0.250 |
ible | +0.233 |
enegger | +0.230 |
IPM | +0.225 |
esters | +0.221 |
Neg logit contributions | |
proport | -0.338 |
suspic | -0.329 |
comr | -0.291 |
fortun | -0.277 |
stress | -0.260 |
Token | using |
Token ID | 1262 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
proport | +0.331 |
suspic | +0.322 |
comr | +0.283 |
fortun | +0.269 |
stress | +0.252 |
Neg logit contributions | |
llah | -0.259 |
ible | -0.241 |
enegger | -0.237 |
IPM | -0.233 |
esters | -0.229 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
proport | +0.504 |
suspic | +0.491 |
comr | +0.430 |
fortun | +0.408 |
stress | +0.383 |
Neg logit contributions | |
llah | -0.409 |
ible | -0.384 |
enegger | -0.376 |
IPM | -0.371 |
esters | -0.364 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +7.10e+00 |
Pos logit contributions | |
llah | +0.082 |
ible | +0.077 |
enegger | +0.075 |
IPM | +0.074 |
esters | +0.072 |
Neg logit contributions | |
proport | -0.107 |
suspic | -0.104 |
comr | -0.091 |
fortun | -0.087 |
stress | -0.082 |
Token | store |
Token ID | 3650 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
proport | +6.197 |
suspic | +6.100 |
comr | +5.234 |
fortun | +5.053 |
stress | +4.655 |
Neg logit contributions | |
llah | -5.842 |
enegger | -5.493 |
ible | -5.286 |
esters | -5.224 |
IPM | -5.189 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
proport | +4.692 |
suspic | +4.572 |
comr | +4.002 |
fortun | +3.859 |
stress | +3.624 |
Neg logit contributions | |
llah | -3.592 |
enegger | -3.295 |
ible | -3.264 |
IPM | -3.174 |
esters | -3.149 |
Token | only |
Token ID | 691 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
proport | +0.141 |
suspic | +0.138 |
comr | +0.121 |
fortun | +0.116 |
stress | +0.109 |
Neg logit contributions | |
llah | -0.100 |
ible | -0.092 |
enegger | -0.091 |
IPM | -0.088 |
esters | -0.087 |
Token | free |
Token ID | 1479 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
proport | +0.983 |
suspic | +0.960 |
comr | +0.845 |
fortun | +0.808 |
stress | +0.756 |
Neg logit contributions | |
llah | -0.726 |
ible | -0.671 |
enegger | -0.665 |
IPM | -0.646 |
esters | -0.639 |
Token | ! |
Token ID | 0 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
llah | +1.288 |
ible | +1.212 |
enegger | +1.168 |
IPM | +1.137 |
osal | +1.120 |
Neg logit contributions | |
proport | -1.988 |
suspic | -1.957 |
comr | -1.727 |
fortun | -1.643 |
stress | -1.557 |
Token | support |
Token ID | 1104 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
proport | +0.872 |
suspic | +0.851 |
comr | +0.753 |
fortun | +0.722 |
stress | +0.678 |
Neg logit contributions | |
llah | -0.573 |
ible | -0.527 |
enegger | -0.522 |
IPM | -0.506 |
esters | -0.499 |
Token | Sunday |
Token ID | 3502 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
llah | +0.508 |
ible | +0.472 |
enegger | +0.461 |
IPM | +0.445 |
esters | +0.444 |
Neg logit contributions | |
proport | -0.745 |
suspic | -0.731 |
comr | -0.649 |
fortun | -0.615 |
stress | -0.575 |
Token | for |
Token ID | 329 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
llah | +0.038 |
ible | +0.035 |
enegger | +0.035 |
IPM | +0.034 |
esters | +0.033 |
Neg logit contributions | |
proport | -0.054 |
suspic | -0.052 |
comr | -0.046 |
fortun | -0.044 |
stress | -0.041 |
Token | Senate |
Token ID | 3845 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
llah | +1.070 |
ible | +0.999 |
enegger | +0.988 |
IPM | +0.960 |
esters | +0.951 |
Neg logit contributions | |
proport | -1.336 |
suspic | -1.297 |
comr | -1.140 |
fortun | -1.076 |
stress | -1.008 |
Token | candidate |
Token ID | 4540 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
proport | +2.065 |
suspic | +2.014 |
comr | +1.756 |
fortun | +1.678 |
stress | +1.564 |
Neg logit contributions | |
llah | -1.722 |
ible | -1.590 |
enegger | -1.584 |
IPM | -1.540 |
esters | -1.526 |
Token | Deb |
Token ID | 8965 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
llah | +1.232 |
ible | +1.157 |
enegger | +1.122 |
IPM | +1.116 |
esters | +1.094 |
Neg logit contributions | |
proport | -1.655 |
suspic | -1.603 |
comr | -1.414 |
fortun | -1.348 |
stress | -1.259 |
Token | ra |
Token ID | 430 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
proport | +5.271 |
suspic | +4.903 |
comr | +4.260 |
fortun | +3.987 |
stress | +3.826 |
Neg logit contributions | |
llah | -6.542 |
enegger | -6.222 |
IPM | -6.044 |
️ | -5.940 |
RESULTS | -5.900 |
Token | Ross |
Token ID | 9847 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
proport | +1.702 |
suspic | +1.661 |
comr | +1.445 |
fortun | +1.379 |
stress | +1.279 |
Neg logit contributions | |
llah | -1.454 |
ible | -1.352 |
enegger | -1.341 |
IPM | -1.306 |
esters | -1.292 |
Token | , |
Token ID | 11 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
llah | +1.248 |
ible | +1.162 |
enegger | +1.155 |
IPM | +1.118 |
esters | +1.104 |
Neg logit contributions | |
proport | -1.698 |
suspic | -1.663 |
comr | -1.461 |
fortun | -1.398 |
stress | -1.295 |
Token | attorney |
Token ID | 6136 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
llah | +0.283 |
ible | +0.262 |
enegger | +0.260 |
IPM | +0.252 |
esters | +0.249 |
Neg logit contributions | |
proport | -0.378 |
suspic | -0.369 |
comr | -0.324 |
fortun | -0.310 |
stress | -0.289 |
Token | general |
Token ID | 2276 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
llah | +0.075 |
ible | +0.071 |
enegger | +0.070 |
IPM | +0.069 |
osal | +0.068 |
Neg logit contributions | |
proport | -0.069 |
suspic | -0.068 |
comr | -0.058 |
fortun | -0.054 |
stress | -0.050 |
Token | failed |
Token ID | 4054 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
proport | +0.313 |
suspic | +0.304 |
comr | +0.268 |
fortun | +0.256 |
stress | +0.239 |
Neg logit contributions | |
llah | -0.228 |
ible | -0.212 |
enegger | -0.209 |
IPM | -0.203 |
esters | -0.202 |
Token | attempt |
Token ID | 2230 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
proport | +0.723 |
suspic | +0.707 |
comr | +0.624 |
fortun | +0.599 |
stress | +0.561 |
Neg logit contributions | |
llah | -0.493 |
ible | -0.452 |
enegger | -0.450 |
IPM | -0.436 |
esters | -0.431 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
llah | +0.473 |
ible | +0.438 |
enegger | +0.429 |
esters | +0.417 |
IPM | +0.416 |
Neg logit contributions | |
proport | -0.745 |
suspic | -0.728 |
comr | -0.647 |
fortun | -0.616 |
stress | -0.580 |
Token | cross |
Token ID | 3272 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
proport | +0.216 |
suspic | +0.211 |
comr | +0.185 |
fortun | +0.177 |
stress | +0.166 |
Neg logit contributions | |
llah | -0.160 |
ible | -0.147 |
enegger | -0.147 |
IPM | -0.142 |
esters | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
proport | +0.386 |
suspic | +0.377 |
comr | +0.329 |
fortun | +0.314 |
stress | +0.293 |
Neg logit contributions | |
llah | -0.311 |
ible | -0.289 |
enegger | -0.285 |
IPM | -0.278 |
esters | -0.276 |
Token | Misty |
Token ID | 47330 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
proport | +0.216 |
suspic | +0.211 |
comr | +0.184 |
fortun | +0.175 |
stress | +0.164 |
Neg logit contributions | |
llah | -0.179 |
ible | -0.166 |
enegger | -0.164 |
IPM | -0.160 |
esters | -0.159 |
Token | Mountains |
Token ID | 21124 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
proport | +7.580 |
suspic | +7.502 |
comr | +6.665 |
fortun | +6.356 |
stress | +6.018 |
Neg logit contributions | |
llah | -4.456 |
ible | -4.017 |
enegger | -4.000 |
osal | -3.824 |
IPM | -3.794 |
Token | through |
Token ID | 832 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
proport | +0.627 |
suspic | +0.612 |
comr | +0.539 |
fortun | +0.515 |
stress | +0.482 |
Neg logit contributions | |
llah | -0.457 |
ible | -0.422 |
enegger | -0.418 |
IPM | -0.406 |
esters | -0.402 |
Token | the |
Token ID | 262 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
proport | +0.823 |
suspic | +0.802 |
comr | +0.701 |
fortun | +0.668 |
stress | +0.624 |
Neg logit contributions | |
llah | -0.665 |
ible | -0.619 |
enegger | -0.612 |
IPM | -0.595 |
esters | -0.592 |
Token | Red |
Token ID | 2297 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
proport | +0.265 |
suspic | +0.258 |
comr | +0.225 |
fortun | +0.214 |
stress | +0.199 |
Neg logit contributions | |
llah | -0.223 |
ible | -0.208 |
enegger | -0.205 |
IPM | -0.200 |
esters | -0.198 |
Token | horn |
Token ID | 25311 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
proport | +2.885 |
suspic | +2.836 |
comr | +2.522 |
fortun | +2.426 |
stress | +2.300 |
Neg logit contributions | |
llah | -1.707 |
enegger | -1.539 |
ible | -1.532 |
IPM | -1.497 |
esters | -1.466 |
Token | pre |
Token ID | 662 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
llah | +0.002 |
ible | +0.002 |
enegger | +0.002 |
IPM | +0.002 |
esters | +0.002 |
Neg logit contributions | |
proport | -0.003 |
suspic | -0.003 |
comr | -0.003 |
fortun | -0.003 |
stress | -0.003 |
Token | z |
Token ID | 89 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
proport | +1.679 |
suspic | +1.642 |
comr | +1.444 |
fortun | +1.385 |
stress | +1.293 |
Neg logit contributions | |
llah | -1.207 |
ible | -1.110 |
enegger | -1.102 |
IPM | -1.070 |
esters | -1.060 |
Token | debate |
Token ID | 4384 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
proport | +0.497 |
suspic | +0.485 |
comr | +0.425 |
fortun | +0.407 |
stress | +0.380 |
Neg logit contributions | |
llah | -0.382 |
ible | -0.353 |
enegger | -0.351 |
IPM | -0.341 |
esters | -0.337 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
proport | +0.627 |
suspic | +0.613 |
comr | +0.538 |
fortun | +0.517 |
stress | +0.485 |
Neg logit contributions | |
llah | -0.446 |
ible | -0.409 |
enegger | -0.408 |
IPM | -0.395 |
esters | -0.391 |
Token | # |
Token ID | 1303 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
proport | +0.121 |
suspic | +0.118 |
comr | +0.103 |
fortun | +0.099 |
stress | +0.092 |
Neg logit contributions | |
llah | -0.090 |
ible | -0.083 |
enegger | -0.082 |
IPM | -0.080 |
esters | -0.079 |
Token | Deb |
Token ID | 16587 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
llah | +0.494 |
ible | +0.464 |
enegger | +0.460 |
IPM | +0.448 |
esters | +0.445 |
Neg logit contributions | |
proport | -0.465 |
suspic | -0.451 |
comr | -0.385 |
fortun | -0.366 |
stress | -0.333 |
Token | ate |
Token ID | 378 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
proport | +4.391 |
suspic | +4.314 |
comr | +3.519 |
fortun | +3.304 |
stress | +3.275 |
Neg logit contributions | |
llah | -6.886 |
enegger | -6.679 |
IPM | -6.488 |
ible | -6.286 |
RESULTS | -6.184 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
llah | +0.928 |
ible | +0.860 |
enegger | +0.849 |
IPM | +0.820 |
esters | +0.818 |
Neg logit contributions | |
proport | -1.286 |
suspic | -1.255 |
comr | -1.104 |
fortun | -1.057 |
stress | -0.986 |
Token | pic |
Token ID | 8301 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
llah | +0.281 |
ible | +0.257 |
enegger | +0.255 |
IPM | +0.247 |
esters | +0.244 |
Neg logit contributions | |
proport | -0.431 |
suspic | -0.421 |
comr | -0.373 |
fortun | -0.357 |
stress | -0.335 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
proport | +0.811 |
suspic | +0.792 |
comr | +0.692 |
fortun | +0.675 |
stress | +0.661 |
Neg logit contributions | |
llah | -0.695 |
enegger | -0.646 |
ible | -0.634 |
esters | -0.620 |
IPM | -0.618 |
Token | twitter |
Token ID | 6956 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
proport | +0.890 |
suspic | +0.868 |
comr | +0.748 |
fortun | +0.726 |
stress | +0.701 |
Neg logit contributions | |
llah | -0.817 |
enegger | -0.768 |
ible | -0.761 |
IPM | -0.742 |
esters | -0.732 |
Token | , |
Token ID | 11 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
proport | +0.349 |
suspic | +0.341 |
comr | +0.300 |
fortun | +0.287 |
stress | +0.266 |
Neg logit contributions | |
llah | -0.259 |
ible | -0.239 |
enegger | -0.237 |
IPM | -0.229 |
esters | -0.227 |
Token | head |
Token ID | 1182 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
llah | +0.215 |
ible | +0.200 |
enegger | +0.199 |
IPM | +0.194 |
esters | +0.191 |
Neg logit contributions | |
proport | -0.259 |
suspic | -0.252 |
comr | -0.221 |
fortun | -0.210 |
stress | -0.195 |
Token | of |
Token ID | 286 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
llah | +0.899 |
ible | +0.827 |
enegger | +0.812 |
IPM | +0.804 |
esters | +0.787 |
Neg logit contributions | |
proport | -1.233 |
suspic | -1.209 |
comr | -1.064 |
fortun | -1.016 |
�� | -0.941 |
Token | environmental |
Token ID | 6142 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
llah | +0.502 |
ible | +0.467 |
enegger | +0.463 |
IPM | +0.455 |
esters | +0.447 |
Neg logit contributions | |
proport | -0.613 |
suspic | -0.596 |
comr | -0.523 |
fortun | -0.498 |
stress | -0.463 |
Token | group |
Token ID | 1448 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
proport | +0.612 |
suspic | +0.599 |
comr | +0.526 |
fortun | +0.504 |
stress | +0.471 |
Neg logit contributions | |
llah | -0.453 |
ible | -0.417 |
enegger | -0.416 |
IPM | -0.402 |
esters | -0.398 |
Token | Greenpeace |
Token ID | 42793 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
proport | +0.423 |
suspic | +0.412 |
comr | +0.361 |
fortun | +0.345 |
stress | +0.321 |
Neg logit contributions | |
llah | -0.336 |
ible | -0.312 |
enegger | -0.310 |
IPM | -0.303 |
esters | -0.299 |
Token | � |
Token ID | 447 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
proport | +6.264 |
suspic | +6.184 |
comr | +5.308 |
fortun | +5.085 |
stress | +4.863 |
Neg logit contributions | |
llah | -5.388 |
enegger | -4.909 |
ible | -4.874 |
osal | -4.738 |
IPM | -4.728 |
Token | � |
Token ID | 247 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
llah | +0.293 |
ible | +0.271 |
enegger | +0.267 |
IPM | +0.262 |
esters | +0.260 |
Neg logit contributions | |
proport | -0.298 |
suspic | -0.292 |
comr | -0.251 |
fortun | -0.241 |
stress | -0.221 |
Token | s |
Token ID | 82 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
llah | +0.096 |
ible | +0.087 |
enegger | +0.086 |
IPM | +0.083 |
esters | +0.082 |
Neg logit contributions | |
proport | -0.193 |
suspic | -0.189 |
comr | -0.169 |
fortun | -0.163 |
stress | -0.153 |
Token | International |
Token ID | 4037 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
llah | +0.520 |
ible | +0.484 |
enegger | +0.481 |
IPM | +0.469 |
esters | +0.461 |
Neg logit contributions | |
proport | -0.687 |
suspic | -0.669 |
comr | -0.588 |
fortun | -0.562 |
stress | -0.524 |
Token | Nuclear |
Token ID | 19229 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
proport | +1.987 |
suspic | +1.940 |
comr | +1.708 |
fortun | +1.639 |
stress | +1.543 |
Neg logit contributions | |
llah | -1.409 |
ible | -1.286 |
enegger | -1.282 |
IPM | -1.235 |
esters | -1.229 |
Token | licensed |
Token ID | 11971 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
proport | +0.349 |
suspic | +0.343 |
comr | +0.301 |
fortun | +0.292 |
stress | +0.274 |
Neg logit contributions | |
llah | -0.234 |
ible | -0.216 |
enegger | -0.211 |
IPM | -0.210 |
esters | -0.203 |
Token | under |
Token ID | 739 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
proport | +0.351 |
suspic | +0.345 |
comr | +0.305 |
fortun | +0.293 |
stress | +0.275 |
Neg logit contributions | |
llah | -0.223 |
ible | -0.204 |
enegger | -0.199 |
IPM | -0.196 |
esters | -0.192 |
Token | a |
Token ID | 257 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
proport | +1.067 |
suspic | +1.035 |
comr | +0.902 |
fortun | +0.862 |
stress | +0.799 |
Neg logit contributions | |
llah | -0.938 |
ible | -0.877 |
enegger | -0.862 |
IPM | -0.852 |
esters | -0.835 |
Token | Creative |
Token ID | 17404 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
proport | +0.198 |
suspic | +0.193 |
comr | +0.171 |
fortun | +0.164 |
stress | +0.155 |
Neg logit contributions | |
llah | -0.125 |
ible | -0.115 |
enegger | -0.112 |
IPM | -0.111 |
esters | -0.108 |
Token | Commons |
Token ID | 13815 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
proport | +1.569 |
suspic | +1.523 |
comr | +1.282 |
fortun | +1.208 |
stress | +1.099 |
Neg logit contributions | |
llah | -1.954 |
ible | -1.844 |
enegger | -1.827 |
IPM | -1.795 |
esters | -1.776 |
Token | Attribution |
Token ID | 45336 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
proport | +1.751 |
suspic | +1.700 |
comr | +1.441 |
fortun | +1.362 |
stress | +1.245 |
Neg logit contributions | |
llah | -2.048 |
ible | -1.923 |
enegger | -1.912 |
IPM | -1.870 |
esters | -1.853 |
Token | - |
Token ID | 12 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
proport | +6.511 |
suspic | +6.362 |
comr | +5.587 |
fortun | +5.337 |
stress | +5.012 |
Neg logit contributions | |
llah | -5.210 |
enegger | -4.770 |
ible | -4.674 |
esters | -4.582 |
IPM | -4.572 |
Token | Non |
Token ID | 15419 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
proport | +0.827 |
suspic | +0.807 |
comr | +0.699 |
fortun | +0.664 |
stress | +0.613 |
Neg logit contributions | |
llah | -0.775 |
ible | -0.730 |
enegger | -0.714 |
IPM | -0.702 |
esters | -0.694 |
Token | Commercial |
Token ID | 48401 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
proport | +0.483 |
suspic | +0.471 |
comr | +0.397 |
fortun | +0.374 |
stress | +0.338 |
Neg logit contributions | |
llah | -0.560 |
ible | -0.536 |
enegger | -0.524 |
IPM | -0.521 |
esters | -0.514 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
llah | +0.764 |
ible | +0.708 |
enegger | +0.695 |
IPM | +0.677 |
esters | +0.660 |
Neg logit contributions | |
proport | -1.187 |
suspic | -1.164 |
comr | -1.027 |
fortun | -0.988 |
stress | -0.926 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
llah | +0.331 |
ible | +0.304 |
enegger | +0.302 |
IPM | +0.293 |
esters | +0.289 |
Neg logit contributions | |
proport | -0.477 |
suspic | -0.466 |
comr | -0.411 |
fortun | -0.395 |
stress | -0.370 |
Token | Three |
Token ID | 12510 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
llah | +0.164 |
ible | +0.152 |
enegger | +0.150 |
IPM | +0.146 |
esters | +0.145 |
Neg logit contributions | |
proport | -0.203 |
suspic | -0.198 |
comr | -0.173 |
fortun | -0.166 |
stress | -0.154 |
Token | months |
Token ID | 1933 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
llah | +0.439 |
ible | +0.402 |
enegger | +0.397 |
IPM | +0.383 |
esters | +0.380 |
Neg logit contributions | |
proport | -0.719 |
suspic | -0.704 |
comr | -0.625 |
fortun | -0.600 |
stress | -0.565 |
Token | ago |
Token ID | 2084 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
llah | +1.241 |
ible | +1.115 |
enegger | +1.105 |
esters | +1.050 |
IPM | +1.047 |
Neg logit contributions | |
proport | -2.460 |
suspic | -2.408 |
comr | -2.172 |
fortun | -2.082 |
stress | -1.958 |
Token | students |
Token ID | 2444 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
llah | +0.778 |
ible | +0.717 |
enegger | +0.712 |
IPM | +0.690 |
esters | +0.683 |
Neg logit contributions | |
proport | -1.104 |
suspic | -1.079 |
comr | -0.952 |
fortun | -0.915 |
stress | -0.848 |
Token | at |
Token ID | 379 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
llah | +2.515 |
ible | +2.317 |
enegger | +2.284 |
IPM | +2.213 |
esters | +2.191 |
Neg logit contributions | |
proport | -3.932 |
suspic | -3.860 |
comr | -3.436 |
fortun | -3.284 |
stress | -3.084 |
Token | Ober |
Token ID | 33753 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
llah | +0.851 |
ible | +0.796 |
enegger | +0.786 |
IPM | +0.768 |
esters | +0.761 |
Neg logit contributions | |
proport | -0.936 |
suspic | -0.915 |
comr | -0.794 |
fortun | -0.757 |
stress | -0.697 |
Token | lin |
Token ID | 2815 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
llah | +4.143 |
ible | +3.866 |
esters | +3.859 |
enegger | +3.637 |
obic | +3.627 |
Neg logit contributions | |
proport | -10.158 |
suspic | -9.968 |
comr | -9.014 |
fortun | -8.708 |
�� | -8.309 |
Token | College |
Token ID | 5535 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
llah | +2.640 |
enegger | +2.423 |
ible | +2.421 |
IPM | +2.324 |
esters | +2.306 |
Neg logit contributions | |
proport | -4.114 |
suspic | -4.047 |
comr | -3.586 |
fortun | -3.473 |
stress | -3.219 |
Token | in |
Token ID | 287 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
llah | +1.580 |
ible | +1.455 |
enegger | +1.447 |
IPM | +1.396 |
esters | +1.391 |
Neg logit contributions | |
proport | -2.305 |
suspic | -2.255 |
comr | -1.999 |
fortun | -1.920 |
stress | -1.787 |
Token | Ohio |
Token ID | 6835 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
llah | +0.350 |
ible | +0.328 |
enegger | +0.323 |
IPM | +0.315 |
esters | +0.313 |
Neg logit contributions | |
proport | -0.398 |
suspic | -0.388 |
comr | -0.337 |
fortun | -0.322 |
stress | -0.298 |
Token | objected |
Token ID | 29811 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
llah | +0.643 |
ible | +0.589 |
enegger | +0.585 |
IPM | +0.567 |
esters | +0.561 |
Neg logit contributions | |
proport | -0.941 |
suspic | -0.921 |
comr | -0.815 |
fortun | -0.781 |
stress | -0.731 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
proport | +0.160 |
suspic | +0.155 |
comr | +0.136 |
fortun | +0.130 |
stress | +0.121 |
Neg logit contributions | |
llah | -0.129 |
ible | -0.120 |
enegger | -0.118 |
IPM | -0.116 |
esters | -0.114 |
Token | pot |
Token ID | 1787 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
proport | +0.211 |
suspic | +0.205 |
comr | +0.180 |
fortun | +0.172 |
stress | +0.161 |
Neg logit contributions | |
llah | -0.161 |
ible | -0.150 |
enegger | -0.147 |
IPM | -0.144 |
osal | -0.142 |
Token | - |
Token ID | 12 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
proport | +0.545 |
suspic | +0.532 |
comr | +0.464 |
fortun | +0.441 |
stress | +0.410 |
Neg logit contributions | |
llah | -0.460 |
ible | -0.430 |
enegger | -0.423 |
IPM | -0.412 |
esters | -0.409 |
Token | add |
Token ID | 2860 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
proport | +0.374 |
suspic | +0.362 |
comr | +0.310 |
fortun | +0.292 |
stress | +0.265 |
Neg logit contributions | |
llah | -0.406 |
ible | -0.382 |
enegger | -0.377 |
IPM | -0.369 |
esters | -0.367 |
Token | led |
Token ID | 992 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
proport | +0.762 |
suspic | +0.744 |
comr | +0.642 |
fortun | +0.607 |
stress | +0.560 |
Neg logit contributions | |
llah | -0.725 |
ible | -0.681 |
enegger | -0.673 |
IPM | -0.656 |
esters | -0.652 |
Token | Ober |
Token ID | 33753 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
llah | +0.411 |
ible | +0.384 |
enegger | +0.378 |
IPM | +0.370 |
esters | +0.363 |
Neg logit contributions | |
proport | -0.539 |
suspic | -0.525 |
comr | -0.459 |
fortun | -0.438 |
stress | -0.411 |
Token | lin |
Token ID | 2815 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
llah | +4.599 |
ible | +4.303 |
enegger | +4.112 |
esters | +4.105 |
obic | +4.072 |
Neg logit contributions | |
proport | -8.281 |
suspic | -8.194 |
comr | -7.285 |
fortun | -6.908 |
�� | -6.538 |
Token | College |
Token ID | 5535 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
llah | +2.758 |
ible | +2.609 |
enegger | +2.568 |
IPM | +2.480 |
osal | +2.454 |
Neg logit contributions | |
proport | -4.031 |
suspic | -3.967 |
comr | -3.476 |
fortun | -3.313 |
stress | -3.125 |
Token | freshman |
Token ID | 18621 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
llah | +1.568 |
ible | +1.467 |
enegger | +1.440 |
IPM | +1.410 |
esters | +1.386 |
Neg logit contributions | |
proport | -2.321 |
suspic | -2.275 |
comr | -2.002 |
fortun | -1.913 |
stress | -1.801 |
Token | 's |
Token ID | 338 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
llah | +0.058 |
ible | +0.054 |
enegger | +0.053 |
IPM | +0.052 |
esters | +0.052 |
Neg logit contributions | |
proport | -0.073 |
suspic | -0.071 |
comr | -0.062 |
fortun | -0.059 |
stress | -0.055 |
Token | — |
Token ID | 851 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
llah | +0.492 |
ible | +0.459 |
enegger | +0.452 |
IPM | +0.442 |
esters | +0.434 |
Neg logit contributions | |
proport | -0.649 |
suspic | -0.632 |
comr | -0.555 |
fortun | -0.529 |
stress | -0.496 |
Token | rate |
Token ID | 4873 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
proport | +0.000 |
suspic | +0.000 |
comr | +0.000 |
fortun | +0.000 |
�� | +0.000 |
Neg logit contributions | |
llah | -0.000 |
ible | -0.000 |
enegger | -0.000 |
esters | -0.000 |
osal | -0.000 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
proport | +0.224 |
suspic | +0.219 |
comr | +0.190 |
fortun | +0.182 |
stress | +0.168 |
Neg logit contributions | |
llah | -0.190 |
ible | -0.178 |
enegger | -0.175 |
IPM | -0.172 |
esters | -0.170 |
Token | / |
Token ID | 14 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
llah | +5.217 |
ible | +4.999 |
enegger | +4.830 |
IPM | +4.779 |
esters | +4.758 |
Neg logit contributions | |
proport | -7.193 |
suspic | -7.036 |
comr | -6.279 |
fortun | -5.953 |
stress | -5.426 |
Token | s |
Token ID | 82 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
llah | +0.902 |
ible | +0.832 |
enegger | +0.816 |
IPM | +0.797 |
esters | +0.789 |
Neg logit contributions | |
proport | -1.477 |
suspic | -1.447 |
comr | -1.286 |
fortun | -1.235 |
stress | -1.152 |
Token | 72 |
Token ID | 7724 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
llah | +0.570 |
ible | +0.529 |
enegger | +0.519 |
IPM | +0.510 |
esters | +0.497 |
Neg logit contributions | |
proport | -0.862 |
suspic | -0.847 |
comr | -0.749 |
fortun | -0.718 |
stress | -0.674 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
proport | +0.226 |
suspic | +0.221 |
comr | +0.193 |
fortun | +0.185 |
stress | +0.172 |
Neg logit contributions | |
llah | -0.179 |
ible | -0.166 |
enegger | -0.164 |
IPM | -0.160 |
esters | -0.158 |
Token | / |
Token ID | 14 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
llah | +4.872 |
ible | +4.620 |
IPM | +4.477 |
enegger | +4.383 |
esters | +4.377 |
Neg logit contributions | |
proport | -7.679 |
suspic | -7.555 |
comr | -6.755 |
fortun | -6.476 |
stress | -5.934 |
Token | s |
Token ID | 82 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
llah | +0.746 |
ible | +0.672 |
enegger | +0.646 |
IPM | +0.629 |
esters | +0.627 |
Neg logit contributions | |
proport | -1.792 |
suspic | -1.758 |
comr | -1.595 |
fortun | -1.534 |
stress | -1.430 |
Token | 109 |
Token ID | 16003 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
llah | +0.947 |
ible | +0.886 |
enegger | +0.874 |
IPM | +0.862 |
esters | +0.844 |
Neg logit contributions | |
proport | -1.099 |
suspic | -1.075 |
comr | -0.934 |
fortun | -0.891 |
stress | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
proport | +0.048 |
suspic | +0.047 |
comr | +0.043 |
fortun | +0.041 |
stress | +0.039 |
Neg logit contributions | |
llah | -0.015 |
ible | -0.013 |
enegger | -0.012 |
IPM | -0.012 |
esters | -0.011 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
proport | +0.375 |
suspic | +0.367 |
comr | +0.322 |
fortun | +0.310 |
stress | +0.292 |
Neg logit contributions | |
llah | -0.273 |
ible | -0.251 |
enegger | -0.250 |
IPM | -0.242 |
esters | -0.241 |
Token | / |
Token ID | 14 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
llah | +4.872 |
ible | +4.620 |
IPM | +4.477 |
enegger | +4.383 |
esters | +4.377 |
Neg logit contributions | |
proport | -7.679 |
suspic | -7.555 |
comr | -6.755 |
fortun | -6.476 |
stress | -5.934 |
Token | s |
Token ID | 82 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
llah | +0.746 |
ible | +0.672 |
enegger | +0.646 |
IPM | +0.629 |
esters | +0.627 |
Neg logit contributions | |
proport | -1.792 |
suspic | -1.758 |
comr | -1.595 |
fortun | -1.534 |
stress | -1.430 |
Token | 109 |
Token ID | 16003 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
llah | +0.947 |
ible | +0.886 |
enegger | +0.874 |
IPM | +0.862 |
esters | +0.844 |
Neg logit contributions | |
proport | -1.099 |
suspic | -1.075 |
comr | -0.934 |
fortun | -0.891 |
stress | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
proport | +0.048 |
suspic | +0.047 |
comr | +0.043 |
fortun | +0.041 |
stress | +0.039 |
Neg logit contributions | |
llah | -0.015 |
ible | -0.013 |
enegger | -0.012 |
IPM | -0.012 |
esters | -0.011 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
proport | +0.375 |
suspic | +0.367 |
comr | +0.322 |
fortun | +0.310 |
stress | +0.292 |
Neg logit contributions | |
llah | -0.273 |
ible | -0.251 |
enegger | -0.250 |
IPM | -0.242 |
esters | -0.241 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
proport | +0.045 |
suspic | +0.044 |
comr | +0.040 |
fortun | +0.039 |
stress | +0.037 |
Neg logit contributions | |
llah | -0.013 |
ible | -0.011 |
enegger | -0.011 |
IPM | -0.010 |
esters | -0.010 |
Token | / |
Token ID | 14 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
llah | +5.292 |
ible | +4.981 |
IPM | +4.801 |
enegger | +4.789 |
osal | +4.671 |
Neg logit contributions | |
proport | -7.762 |
suspic | -7.614 |
comr | -6.714 |
fortun | -6.331 |
�� | -5.725 |
Token | s |
Token ID | 82 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
llah | +0.942 |
enegger | +0.847 |
ible | +0.838 |
IPM | +0.808 |
esters | +0.788 |
Neg logit contributions | |
proport | -1.896 |
suspic | -1.861 |
comr | -1.665 |
fortun | -1.615 |
stress | -1.554 |
Token | 120 |
Token ID | 7982 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
llah | +1.248 |
ible | +1.172 |
enegger | +1.158 |
IPM | +1.143 |
esters | +1.117 |
Neg logit contributions | |
proport | -1.322 |
suspic | -1.289 |
comr | -1.112 |
fortun | -1.054 |
stress | -0.969 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
llah | +0.560 |
ible | +0.512 |
enegger | +0.504 |
IPM | +0.491 |
esters | +0.480 |
Neg logit contributions | |
proport | -1.010 |
suspic | -0.994 |
comr | -0.884 |
fortun | -0.853 |
stress | -0.802 |
Token | 5 |
Token ID | 20 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
proport | +0.278 |
suspic | +0.272 |
comr | +0.240 |
fortun | +0.231 |
stress | +0.218 |
Neg logit contributions | |
llah | -0.186 |
ible | -0.170 |
enegger | -0.169 |
IPM | -0.163 |
esters | -0.162 |
Token | a |
Token ID | 257 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
llah | +0.425 |
ible | +0.396 |
enegger | +0.393 |
IPM | +0.381 |
esters | +0.378 |
Neg logit contributions | |
proport | -0.546 |
suspic | -0.531 |
comr | -0.465 |
fortun | -0.443 |
stress | -0.414 |
Token | model |
Token ID | 2746 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
proport | +0.169 |
suspic | +0.164 |
comr | +0.144 |
fortun | +0.137 |
stress | +0.129 |
Neg logit contributions | |
llah | -0.127 |
ible | -0.119 |
enegger | -0.117 |
IPM | -0.114 |
osal | -0.112 |
Token | of |
Token ID | 286 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
llah | +0.882 |
ible | +0.824 |
enegger | +0.813 |
IPM | +0.789 |
esters | +0.778 |
Neg logit contributions | |
proport | -1.247 |
suspic | -1.220 |
comr | -1.066 |
fortun | -1.019 |
stress | -0.956 |
Token | Pont |
Token ID | 26345 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
llah | +0.071 |
ible | +0.066 |
enegger | +0.066 |
IPM | +0.064 |
esters | +0.063 |
Neg logit contributions | |
proport | -0.091 |
suspic | -0.089 |
comr | -0.078 |
fortun | -0.074 |
stress | -0.070 |
Token | iac |
Token ID | 9607 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
llah | +1.702 |
ible | +1.614 |
enegger | +1.596 |
IPM | +1.554 |
esters | +1.549 |
Neg logit contributions | |
proport | -1.665 |
suspic | -1.612 |
comr | -1.379 |
fortun | -1.300 |
�� | -1.203 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
llah | +0.702 |
ible | +0.657 |
enegger | +0.647 |
IPM | +0.631 |
esters | +0.623 |
Neg logit contributions | |
proport | -0.932 |
suspic | -0.912 |
comr | -0.796 |
fortun | -0.762 |
stress | -0.713 |
Token | O |
Token ID | 46 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
llah | +5.015 |
ible | +4.800 |
enegger | +4.651 |
esters | +4.623 |
IPM | +4.491 |
Neg logit contributions | |
proport | -7.460 |
suspic | -7.324 |
comr | -6.414 |
fortun | -6.108 |
stress | -5.700 |
Token | sold |
Token ID | 2702 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
llah | +0.383 |
ible | +0.355 |
enegger | +0.352 |
IPM | +0.343 |
esters | +0.339 |
Neg logit contributions | |
proport | -0.517 |
suspic | -0.505 |
comr | -0.443 |
fortun | -0.424 |
stress | -0.397 |
Token | from |
Token ID | 422 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
proport | +0.566 |
suspic | +0.554 |
comr | +0.489 |
fortun | +0.466 |
stress | +0.435 |
Neg logit contributions | |
llah | -0.404 |
ible | -0.376 |
enegger | -0.372 |
IPM | -0.358 |
esters | -0.357 |
Token | 1969 |
Token ID | 16450 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
proport | +0.383 |
suspic | +0.373 |
comr | +0.327 |
fortun | +0.313 |
stress | +0.292 |
Neg logit contributions | |
llah | -0.293 |
ible | -0.271 |
enegger | -0.269 |
IPM | -0.262 |
esters | -0.259 |
Token | till |
Token ID | 10597 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
llah | +2.166 |
ible | +2.033 |
enegger | +1.993 |
IPM | +1.919 |
esters | +1.909 |
Neg logit contributions | |
proport | -3.665 |
suspic | -3.579 |
comr | -3.195 |
fortun | -3.041 |
stress | -2.847 |
Token | 160 |
Token ID | 13454 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
llah | +0.172 |
ible | +0.159 |
enegger | +0.158 |
IPM | +0.153 |
esters | +0.151 |
Neg logit contributions | |
proport | -0.237 |
suspic | -0.232 |
comr | -0.204 |
fortun | -0.196 |
stress | -0.183 |
Token | Texture |
Token ID | 44409 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
llah | +0.697 |
ible | +0.647 |
enegger | +0.637 |
IPM | +0.624 |
esters | +0.611 |
Neg logit contributions | |
proport | -0.933 |
suspic | -0.913 |
comr | -0.802 |
fortun | -0.766 |
stress | -0.715 |
Token | fill |
Token ID | 6070 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
llah | +1.959 |
ible | +1.850 |
cible | +1.723 |
IPM | +1.718 |
RESULTS | +1.706 |
Neg logit contributions | |
proport | -3.502 |
suspic | -3.450 |
comr | -3.068 |
fortun | -2.923 |
�� | -2.733 |
Token | - |
Token ID | 12 |
Feature activation | +3.79e-04 |
Pos logit contributions | |
llah | +0.953 |
ible | +0.905 |
enegger | +0.872 |
esters | +0.865 |
IPM | +0.863 |
Neg logit contributions | |
proport | -1.193 |
suspic | -1.171 |
comr | -1.029 |
fortun | -0.976 |
�� | -0.891 |
Token | rate |
Token ID | 4873 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
proport | +0.000 |
suspic | +0.000 |
comr | +0.000 |
fortun | +0.000 |
�� | +0.000 |
Neg logit contributions | |
llah | -0.000 |
ible | -0.000 |
enegger | -0.000 |
esters | -0.000 |
osal | -0.000 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
proport | +0.224 |
suspic | +0.219 |
comr | +0.190 |
fortun | +0.182 |
stress | +0.168 |
Neg logit contributions | |
llah | -0.190 |
ible | -0.178 |
enegger | -0.175 |
IPM | -0.172 |
esters | -0.170 |
Token | / |
Token ID | 14 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
llah | +5.217 |
ible | +4.999 |
enegger | +4.830 |
IPM | +4.779 |
esters | +4.758 |
Neg logit contributions | |
proport | -7.193 |
suspic | -7.036 |
comr | -6.279 |
fortun | -5.953 |
stress | -5.426 |
Token | s |
Token ID | 82 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
llah | +0.902 |
ible | +0.832 |
enegger | +0.816 |
IPM | +0.797 |
esters | +0.789 |
Neg logit contributions | |
proport | -1.477 |
suspic | -1.447 |
comr | -1.286 |
fortun | -1.235 |
stress | -1.152 |
Token | 72 |
Token ID | 7724 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
llah | +0.570 |
ible | +0.529 |
enegger | +0.519 |
IPM | +0.510 |
esters | +0.497 |
Neg logit contributions | |
proport | -0.862 |
suspic | -0.847 |
comr | -0.749 |
fortun | -0.718 |
stress | -0.674 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
proport | +0.226 |
suspic | +0.221 |
comr | +0.193 |
fortun | +0.185 |
stress | +0.172 |
Neg logit contributions | |
llah | -0.179 |
ible | -0.166 |
enegger | -0.164 |
IPM | -0.160 |
esters | -0.158 |
Token | / |
Token ID | 14 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
llah | +4.872 |
ible | +4.620 |
IPM | +4.477 |
enegger | +4.383 |
esters | +4.377 |
Neg logit contributions | |
proport | -7.679 |
suspic | -7.555 |
comr | -6.755 |
fortun | -6.476 |
stress | -5.934 |
Token | / |
Token ID | 14 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
llah | +5.292 |
ible | +4.981 |
IPM | +4.801 |
enegger | +4.789 |
osal | +4.671 |
Neg logit contributions | |
proport | -7.762 |
suspic | -7.614 |
comr | -6.714 |
fortun | -6.331 |
�� | -5.725 |
Token | s |
Token ID | 82 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
llah | +0.942 |
enegger | +0.847 |
ible | +0.838 |
IPM | +0.808 |
esters | +0.788 |
Neg logit contributions | |
proport | -1.896 |
suspic | -1.861 |
comr | -1.665 |
fortun | -1.615 |
stress | -1.554 |
Token | 120 |
Token ID | 7982 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
llah | +1.248 |
ible | +1.172 |
enegger | +1.158 |
IPM | +1.143 |
esters | +1.117 |
Neg logit contributions | |
proport | -1.322 |
suspic | -1.289 |
comr | -1.112 |
fortun | -1.054 |
stress | -0.969 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
llah | +0.560 |
ible | +0.512 |
enegger | +0.504 |
IPM | +0.491 |
esters | +0.480 |
Neg logit contributions | |
proport | -1.010 |
suspic | -0.994 |
comr | -0.884 |
fortun | -0.853 |
stress | -0.802 |
Token | 5 |
Token ID | 20 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
proport | +0.278 |
suspic | +0.272 |
comr | +0.240 |
fortun | +0.231 |
stress | +0.218 |
Neg logit contributions | |
llah | -0.186 |
ible | -0.170 |
enegger | -0.169 |
IPM | -0.163 |
esters | -0.162 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
llah | +0.120 |
ible | +0.102 |
enegger | +0.100 |
IPM | +0.095 |
esters | +0.091 |
Neg logit contributions | |
proport | -0.460 |
suspic | -0.453 |
comr | -0.414 |
fortun | -0.402 |
stress | -0.383 |
Token | / |
Token ID | 14 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
llah | +5.132 |
ible | +4.858 |
IPM | +4.663 |
enegger | +4.645 |
osal | +4.530 |
Neg logit contributions | |
proport | -7.688 |
suspic | -7.532 |
comr | -6.630 |
fortun | -6.224 |
�� | -5.658 |
Token | s |
Token ID | 82 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
llah | +0.971 |
enegger | +0.878 |
ible | +0.862 |
IPM | +0.837 |
esters | +0.812 |
Neg logit contributions | |
proport | -1.903 |
suspic | -1.866 |
comr | -1.669 |
fortun | -1.624 |
stress | -1.574 |
Token | 180 |
Token ID | 11546 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
llah | +1.221 |
ible | +1.146 |
enegger | +1.134 |
IPM | +1.116 |
esters | +1.093 |
Neg logit contributions | |
proport | -1.323 |
suspic | -1.292 |
comr | -1.118 |
fortun | -1.060 |
stress | -0.976 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
proport | +1.133 |
suspic | +1.108 |
comr | +0.984 |
fortun | +0.946 |
stress | +0.890 |
Neg logit contributions | |
llah | -0.688 |
ible | -0.628 |
enegger | -0.624 |
IPM | -0.602 |
esters | -0.595 |
Token | 7 |
Token ID | 22 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
proport | +0.348 |
suspic | +0.340 |
comr | +0.300 |
fortun | +0.288 |
stress | +0.271 |
Neg logit contributions | |
llah | -0.242 |
ible | -0.222 |
enegger | -0.221 |
IPM | -0.214 |
esters | -0.212 |
Token | family |
Token ID | 1641 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
proport | +0.206 |
suspic | +0.201 |
comr | +0.175 |
fortun | +0.168 |
stress | +0.157 |
Neg logit contributions | |
llah | -0.166 |
ible | -0.154 |
enegger | -0.153 |
IPM | -0.148 |
esters | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
llah | +1.202 |
ible | +1.101 |
enegger | +1.087 |
esters | +1.041 |
️ | +1.040 |
Neg logit contributions | |
proport | -1.799 |
suspic | -1.756 |
comr | -1.539 |
fortun | -1.486 |
stress | -1.399 |
Token | fighting |
Token ID | 4330 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
llah | +0.009 |
ible | +0.009 |
enegger | +0.009 |
IPM | +0.008 |
esters | +0.008 |
Neg logit contributions | |
proport | -0.012 |
suspic | -0.012 |
comr | -0.011 |
fortun | -0.010 |
stress | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
proport | +0.744 |
suspic | +0.725 |
comr | +0.634 |
fortun | +0.606 |
stress | +0.564 |
Neg logit contributions | |
llah | -0.601 |
ible | -0.557 |
enegger | -0.554 |
IPM | -0.538 |
esters | -0.532 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
proport | +0.086 |
suspic | +0.084 |
comr | +0.073 |
fortun | +0.070 |
stress | +0.066 |
Neg logit contributions | |
llah | -0.066 |
ible | -0.061 |
enegger | -0.060 |
IPM | -0.058 |
esters | -0.058 |
Token | FO |
Token ID | 11895 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
llah | +0.095 |
ible | +0.088 |
enegger | +0.087 |
IPM | +0.085 |
esters | +0.084 |
Neg logit contributions | |
proport | -0.124 |
suspic | -0.121 |
comr | -0.105 |
fortun | -0.101 |
stress | -0.095 |
Token | OD |
Token ID | 3727 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
llah | +4.886 |
ible | +4.501 |
enegger | +4.338 |
IPM | +4.240 |
osal | +4.236 |
Neg logit contributions | |
proport | -7.310 |
suspic | -7.138 |
comr | -6.362 |
fortun | -6.011 |
stress | -5.736 |
Token | ! |
Token ID | 0 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
llah | +1.495 |
ible | +1.378 |
enegger | +1.364 |
IPM | +1.315 |
esters | +1.303 |
Neg logit contributions | |
proport | -2.238 |
suspic | -2.184 |
comr | -1.924 |
fortun | -1.846 |
stress | -1.732 |
Token | Oh |
Token ID | 3966 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
llah | +1.562 |
ible | +1.445 |
enegger | +1.433 |
IPM | +1.397 |
️ | +1.377 |
Neg logit contributions | |
proport | -1.858 |
suspic | -1.812 |
comr | -1.574 |
fortun | -1.497 |
stress | -1.390 |
Token | crap |
Token ID | 18824 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
llah | +1.434 |
ible | +1.325 |
enegger | +1.305 |
IPM | +1.247 |
esters | +1.243 |
Neg logit contributions | |
proport | -2.243 |
suspic | -2.170 |
comr | -1.925 |
fortun | -1.834 |
stress | -1.731 |
Token | … |
Token ID | 1399 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
llah | +0.803 |
ible | +0.739 |
enegger | +0.732 |
IPM | +0.703 |
esters | +0.700 |
Neg logit contributions | |
proport | -1.148 |
suspic | -1.118 |
comr | -0.986 |
fortun | -0.943 |
stress | -0.880 |
Token | k |
Token ID | 74 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
llah | +0.104 |
ible | +0.095 |
enegger | +0.095 |
IPM | +0.090 |
esters | +0.090 |
Neg logit contributions | |
proport | -0.162 |
suspic | -0.158 |
comr | -0.140 |
fortun | -0.134 |
stress | -0.125 |
Token | ong |
Token ID | 506 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
proport | +0.453 |
suspic | +0.447 |
comr | +0.396 |
fortun | +0.388 |
stress | +0.381 |
Neg logit contributions | |
llah | -0.297 |
enegger | -0.278 |
IPM | -0.269 |
ible | -0.266 |
esters | -0.259 |
Token | / |
Token ID | 14 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
proport | +1.305 |
suspic | +1.272 |
comr | +1.113 |
fortun | +1.063 |
stress | +0.987 |
Neg logit contributions | |
llah | -1.048 |
ible | -0.973 |
enegger | -0.965 |
IPM | -0.939 |
esters | -0.929 |
Token | a |
Token ID | 64 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
llah | +1.455 |
ible | +1.377 |
enegger | +1.356 |
IPM | +1.329 |
osal | +1.320 |
Neg logit contributions | |
proport | -1.315 |
suspic | -1.271 |
comr | -1.090 |
fortun | -1.025 |
�� | -0.922 |
Token | - |
Token ID | 12 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
proport | +1.180 |
suspic | +1.152 |
comr | +1.012 |
fortun | +0.969 |
stress | +0.904 |
Neg logit contributions | |
llah | -0.878 |
ible | -0.811 |
enegger | -0.803 |
IPM | -0.781 |
esters | -0.773 |
Token | flex |
Token ID | 32880 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
llah | +0.226 |
ible | +0.213 |
enegger | +0.209 |
IPM | +0.205 |
esters | +0.203 |
Neg logit contributions | |
proport | -0.221 |
suspic | -0.215 |
comr | -0.184 |
fortun | -0.175 |
stress | -0.158 |
Token | ible |
Token ID | 856 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ible | +4.906 |
llah | +4.853 |
osal | +4.493 |
enegger | +4.493 |
obic | +4.367 |
Neg logit contributions | |
proport | -6.990 |
suspic | -6.918 |
comr | -6.120 |
fortun | -5.783 |
�� | -5.472 |
Token | - |
Token ID | 12 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
llah | +1.430 |
ible | +1.346 |
enegger | +1.291 |
IPM | +1.263 |
osal | +1.255 |
Neg logit contributions | |
proport | -2.272 |
suspic | -2.231 |
comr | -1.969 |
fortun | -1.893 |
�� | -1.764 |
Token | limit |
Token ID | 32374 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
llah | +0.241 |
ible | +0.226 |
enegger | +0.222 |
IPM | +0.217 |
esters | +0.216 |
Neg logit contributions | |
proport | -0.272 |
suspic | -0.265 |
comr | -0.230 |
fortun | -0.219 |
stress | -0.200 |
Token | - |
Token ID | 12 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
proport | +0.075 |
suspic | +0.073 |
comr | +0.065 |
fortun | +0.062 |
stress | +0.058 |
Neg logit contributions | |
llah | -0.050 |
ible | -0.047 |
enegger | -0.046 |
IPM | -0.045 |
osal | -0.044 |
Token | tr |
Token ID | 2213 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
llah | +0.309 |
ible | +0.293 |
enegger | +0.288 |
IPM | +0.282 |
osal | +0.281 |
Neg logit contributions | |
proport | -0.283 |
suspic | -0.275 |
comr | -0.235 |
fortun | -0.221 |
�� | -0.199 |
Token | / |
Token ID | 14 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
llah | +5.132 |
ible | +4.858 |
IPM | +4.663 |
enegger | +4.645 |
osal | +4.530 |
Neg logit contributions | |
proport | -7.688 |
suspic | -7.532 |
comr | -6.630 |
fortun | -6.224 |
�� | -5.658 |
Token | s |
Token ID | 82 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
llah | +0.971 |
enegger | +0.878 |
ible | +0.862 |
IPM | +0.837 |
esters | +0.812 |
Neg logit contributions | |
proport | -1.903 |
suspic | -1.866 |
comr | -1.669 |
fortun | -1.624 |
stress | -1.574 |
Token | 180 |
Token ID | 11546 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
llah | +1.221 |
ible | +1.146 |
enegger | +1.134 |
IPM | +1.116 |
esters | +1.093 |
Neg logit contributions | |
proport | -1.323 |
suspic | -1.292 |
comr | -1.118 |
fortun | -1.060 |
stress | -0.976 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
proport | +1.133 |
suspic | +1.108 |
comr | +0.984 |
fortun | +0.946 |
stress | +0.890 |
Neg logit contributions | |
llah | -0.688 |
ible | -0.628 |
enegger | -0.624 |
IPM | -0.602 |
esters | -0.595 |
Token | 7 |
Token ID | 22 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
proport | +0.348 |
suspic | +0.340 |
comr | +0.300 |
fortun | +0.288 |
stress | +0.271 |
Neg logit contributions | |
llah | -0.242 |
ible | -0.222 |
enegger | -0.221 |
IPM | -0.214 |
esters | -0.212 |
Token | GT |
Token ID | 7963 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
llah | +0.231 |
ible | +0.197 |
enegger | +0.192 |
IPM | +0.183 |
esters | +0.173 |
Neg logit contributions | |
proport | -0.920 |
suspic | -0.909 |
comr | -0.829 |
fortun | -0.805 |
stress | -0.769 |
Token | / |
Token ID | 14 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
llah | +4.999 |
ible | +4.727 |
IPM | +4.535 |
enegger | +4.523 |
osal | +4.410 |
Neg logit contributions | |
proport | -7.447 |
suspic | -7.293 |
comr | -6.412 |
fortun | -6.011 |
�� | -5.471 |
Token | s |
Token ID | 82 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
llah | +0.980 |
enegger | +0.887 |
ible | +0.871 |
IPM | +0.845 |
osal | +0.820 |
Neg logit contributions | |
proport | -1.914 |
suspic | -1.877 |
comr | -1.680 |
fortun | -1.635 |
stress | -1.586 |
Token | 257 |
Token ID | 36100 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
llah | +1.003 |
ible | +0.940 |
enegger | +0.930 |
IPM | +0.913 |
esters | +0.893 |
Neg logit contributions | |
proport | -1.149 |
suspic | -1.124 |
comr | -0.977 |
fortun | -0.929 |
stress | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
proport | +0.395 |
suspic | +0.387 |
comr | +0.343 |
fortun | +0.330 |
stress | +0.310 |
Neg logit contributions | |
llah | -0.245 |
ible | -0.225 |
enegger | -0.222 |
IPM | -0.215 |
esters | -0.212 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
proport | +0.203 |
suspic | +0.198 |
comr | +0.175 |
fortun | +0.168 |
stress | +0.158 |
Neg logit contributions | |
llah | -0.134 |
ible | -0.123 |
enegger | -0.122 |
IPM | -0.119 |
esters | -0.117 |
Token | scale |
Token ID | 5046 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
llah | +0.237 |
ible | +0.220 |
enegger | +0.216 |
IPM | +0.211 |
osal | +0.208 |
Neg logit contributions | |
proport | -0.305 |
suspic | -0.298 |
comr | -0.260 |
fortun | -0.249 |
stress | -0.233 |
Token | and |
Token ID | 290 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
llah | +0.320 |
ible | +0.299 |
enegger | +0.288 |
IPM | +0.284 |
esters | +0.280 |
Neg logit contributions | |
proport | -0.446 |
suspic | -0.439 |
comr | -0.384 |
fortun | -0.370 |
stress | -0.345 |
Token | violence |
Token ID | 3685 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
proport | +0.497 |
suspic | +0.487 |
comr | +0.424 |
fortun | +0.405 |
stress | +0.379 |
Neg logit contributions | |
llah | -0.395 |
ible | -0.367 |
enegger | -0.360 |
IPM | -0.353 |
esters | -0.348 |
Token | of |
Token ID | 286 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
proport | +0.547 |
suspic | +0.536 |
comr | +0.470 |
fortun | +0.450 |
stress | +0.420 |
Neg logit contributions | |
llah | -0.407 |
ible | -0.376 |
enegger | -0.372 |
IPM | -0.362 |
esters | -0.358 |
Token | the |
Token ID | 262 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
llah | +0.171 |
ible | +0.159 |
enegger | +0.157 |
IPM | +0.154 |
esters | +0.152 |
Neg logit contributions | |
proport | -0.203 |
suspic | -0.198 |
comr | -0.173 |
fortun | -0.165 |
stress | -0.153 |
Token | forc |
Token ID | 24686 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
llah | +0.128 |
ible | +0.119 |
enegger | +0.118 |
IPM | +0.115 |
esters | +0.114 |
Neg logit contributions | |
proport | -0.155 |
suspic | -0.151 |
comr | -0.132 |
fortun | -0.126 |
stress | -0.118 |
Token | ible |
Token ID | 856 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ible | +0.009 |
llah | -0.140 |
enegger | -0.538 |
cible | -0.555 |
osal | -0.629 |
Neg logit contributions | |
proport | -12.135 |
suspic | -11.995 |
comr | -11.275 |
fortun | -10.904 |
�� | -10.518 |
Token | recruitment |
Token ID | 19624 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
llah | +1.564 |
ible | +1.451 |
enegger | +1.413 |
IPM | +1.387 |
esters | +1.370 |
Neg logit contributions | |
proport | -2.215 |
suspic | -2.164 |
comr | -1.904 |
fortun | -1.832 |
stress | -1.719 |
Token | by |
Token ID | 416 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
proport | +0.071 |
suspic | +0.070 |
comr | +0.061 |
fortun | +0.058 |
stress | +0.054 |
Neg logit contributions | |
llah | -0.054 |
ible | -0.050 |
enegger | -0.050 |
IPM | -0.049 |
esters | -0.048 |
Token | al |
Token ID | 435 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
proport | +0.649 |
suspic | +0.634 |
comr | +0.559 |
fortun | +0.537 |
stress | +0.502 |
Neg logit contributions | |
llah | -0.448 |
ible | -0.411 |
enegger | -0.410 |
IPM | -0.396 |
esters | -0.392 |
Token | - |
Token ID | 12 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
proport | +0.614 |
suspic | +0.598 |
comr | +0.526 |
fortun | +0.509 |
stress | +0.480 |
Neg logit contributions | |
llah | -0.481 |
enegger | -0.446 |
ible | -0.440 |
IPM | -0.427 |
esters | -0.426 |
Token | David |
Token ID | 3271 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
proport | +1.045 |
suspic | +1.020 |
comr | +0.897 |
fortun | +0.860 |
stress | +0.804 |
Neg logit contributions | |
llah | -0.762 |
ible | -0.702 |
enegger | -0.699 |
IPM | -0.677 |
esters | -0.669 |
Token | De |
Token ID | 1024 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
proport | +0.393 |
suspic | +0.384 |
comr | +0.329 |
fortun | +0.313 |
stress | +0.287 |
Neg logit contributions | |
llah | -0.386 |
ible | -0.361 |
enegger | -0.357 |
IPM | -0.349 |
esters | -0.346 |
Token | Cast |
Token ID | 19248 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
proport | +2.220 |
suspic | +2.171 |
comr | +1.927 |
fortun | +1.856 |
stress | +1.747 |
Neg logit contributions | |
llah | -1.388 |
ible | -1.266 |
enegger | -1.262 |
IPM | -1.222 |
esters | -1.201 |
Token | ro |
Token ID | 305 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
llah | +0.936 |
ible | +0.870 |
enegger | +0.847 |
IPM | +0.826 |
osal | +0.825 |
Neg logit contributions | |
proport | -1.177 |
suspic | -1.158 |
comr | -1.013 |
fortun | -0.966 |
�� | -0.893 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
llah | +0.901 |
ible | +0.825 |
enegger | +0.818 |
IPM | +0.788 |
esters | +0.787 |
Neg logit contributions | |
proport | -1.391 |
suspic | -1.362 |
comr | -1.207 |
fortun | -1.157 |
stress | -1.081 |
Token | Maur |
Token ID | 18867 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
llah | +0.108 |
ible | +0.100 |
enegger | +0.099 |
IPM | +0.096 |
esters | +0.095 |
Neg logit contributions | |
proport | -0.146 |
suspic | -0.142 |
comr | -0.125 |
fortun | -0.119 |
stress | -0.112 |
Token | k |
Token ID | 74 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
llah | +4.512 |
ible | +4.079 |
esters | +3.912 |
enegger | +3.904 |
obic | +3.880 |
Neg logit contributions | |
proport | -7.408 |
suspic | -7.404 |
comr | -6.549 |
fortun | -6.304 |
�� | -5.910 |
Token | ice |
Token ID | 501 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
proport | +0.570 |
suspic | +0.556 |
comr | +0.473 |
fortun | +0.452 |
stress | +0.408 |
Neg logit contributions | |
llah | -0.607 |
ible | -0.571 |
enegger | -0.566 |
IPM | -0.548 |
osal | -0.547 |
Token | P |
Token ID | 350 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
llah | +0.108 |
ible | +0.100 |
enegger | +0.099 |
IPM | +0.097 |
esters | +0.096 |
Neg logit contributions | |
proport | -0.140 |
suspic | -0.136 |
comr | -0.119 |
fortun | -0.114 |
stress | -0.106 |
Token | ounce |
Token ID | 8652 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
proport | +0.214 |
suspic | +0.209 |
comr | +0.180 |
fortun | +0.171 |
stress | +0.157 |
Neg logit contributions | |
llah | -0.208 |
ible | -0.194 |
enegger | -0.193 |
IPM | -0.188 |
esters | -0.187 |
Token | y |
Token ID | 88 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
llah | +1.935 |
ible | +1.780 |
enegger | +1.775 |
IPM | +1.717 |
esters | +1.696 |
Neg logit contributions | |
proport | -2.866 |
suspic | -2.800 |
comr | -2.477 |
fortun | -2.377 |
stress | -2.229 |
Token | / |
Token ID | 14 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
llah | +4.999 |
ible | +4.727 |
IPM | +4.535 |
enegger | +4.523 |
osal | +4.410 |
Neg logit contributions | |
proport | -7.447 |
suspic | -7.293 |
comr | -6.412 |
fortun | -6.011 |
�� | -5.471 |
Token | s |
Token ID | 82 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
llah | +0.980 |
enegger | +0.887 |
ible | +0.871 |
IPM | +0.845 |
osal | +0.820 |
Neg logit contributions | |
proport | -1.914 |
suspic | -1.877 |
comr | -1.680 |
fortun | -1.635 |
stress | -1.586 |
Token | 257 |
Token ID | 36100 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
llah | +1.003 |
ible | +0.940 |
enegger | +0.930 |
IPM | +0.913 |
esters | +0.893 |
Neg logit contributions | |
proport | -1.149 |
suspic | -1.124 |
comr | -0.977 |
fortun | -0.929 |
stress | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
proport | +0.395 |
suspic | +0.387 |
comr | +0.343 |
fortun | +0.330 |
stress | +0.310 |
Neg logit contributions | |
llah | -0.245 |
ible | -0.225 |
enegger | -0.222 |
IPM | -0.215 |
esters | -0.212 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
proport | +0.203 |
suspic | +0.198 |
comr | +0.175 |
fortun | +0.168 |
stress | +0.158 |
Neg logit contributions | |
llah | -0.134 |
ible | -0.123 |
enegger | -0.122 |
IPM | -0.119 |
esters | -0.117 |
Token | GT |
Token ID | 7963 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
llah | +0.023 |
ible | +0.020 |
enegger | +0.019 |
IPM | +0.019 |
esters | +0.018 |
Neg logit contributions | |
proport | -0.081 |
suspic | -0.080 |
comr | -0.073 |
fortun | -0.070 |
stress | -0.067 |
Token | / |
Token ID | 14 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
llah | +4.968 |
ible | +4.695 |
enegger | +4.513 |
IPM | +4.511 |
osal | +4.381 |
Neg logit contributions | |
proport | -7.239 |
suspic | -7.084 |
comr | -6.225 |
fortun | -5.844 |
�� | -5.319 |
Token | s |
Token ID | 82 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
llah | +0.908 |
enegger | +0.822 |
ible | +0.805 |
IPM | +0.784 |
osal | +0.761 |
Neg logit contributions | |
proport | -1.754 |
suspic | -1.721 |
comr | -1.539 |
fortun | -1.500 |
stress | -1.459 |
Token | Memory |
Token ID | 14059 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
llah | +1.125 |
ible | +1.060 |
enegger | +1.045 |
IPM | +1.032 |
osal | +1.003 |
Neg logit contributions | |
proport | -1.279 |
suspic | -1.253 |
comr | -1.089 |
fortun | -1.031 |
stress | -0.953 |
Token | Clock |
Token ID | 21328 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
proport | +1.532 |
suspic | +1.482 |
comr | +1.293 |
fortun | +1.239 |
stress | +1.157 |
Neg logit contributions | |
llah | -1.314 |
enegger | -1.216 |
ible | -1.192 |
osal | -1.154 |
esters | -1.153 |
Token | 7000 |
Token ID | 50205 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
proport | +1.859 |
suspic | +1.806 |
comr | +1.580 |
fortun | +1.510 |
stress | +1.423 |
Neg logit contributions | |
llah | -1.561 |
enegger | -1.438 |
ible | -1.432 |
IPM | -1.382 |
esters | -1.376 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
llah | +0.526 |
ible | +0.485 |
enegger | +0.480 |
IPM | +0.468 |
esters | +0.461 |
Neg logit contributions | |
proport | -0.763 |
suspic | -0.746 |
comr | -0.658 |
fortun | -0.631 |
stress | -0.591 |
Token | a |
Token ID | 257 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
llah | +0.081 |
ible | +0.075 |
enegger | +0.075 |
IPM | +0.072 |
esters | +0.072 |
Neg logit contributions | |
proport | -0.112 |
suspic | -0.110 |
comr | -0.097 |
fortun | -0.093 |
stress | -0.087 |
Token | major |
Token ID | 1688 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
llah | +0.363 |
ible | +0.339 |
enegger | +0.335 |
IPM | +0.324 |
esters | +0.323 |
Neg logit contributions | |
proport | -0.449 |
suspic | -0.438 |
comr | -0.382 |
fortun | -0.364 |
stress | -0.341 |
Token | maker |
Token ID | 16009 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
llah | +0.930 |
ible | +0.872 |
enegger | +0.859 |
IPM | +0.835 |
esters | +0.826 |
Neg logit contributions | |
proport | -1.264 |
suspic | -1.237 |
comr | -1.085 |
fortun | -1.034 |
stress | -0.974 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
proport | +1.210 |
suspic | +1.185 |
comr | +1.037 |
fortun | +0.993 |
stress | +0.929 |
Neg logit contributions | |
llah | -0.919 |
ible | -0.856 |
enegger | -0.843 |
IPM | -0.819 |
esters | -0.814 |
Token | Honey |
Token ID | 21788 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
llah | +0.114 |
ible | +0.105 |
enegger | +0.103 |
IPM | +0.101 |
esters | +0.099 |
Neg logit contributions | |
proport | -0.176 |
suspic | -0.172 |
comr | -0.152 |
fortun | -0.146 |
stress | -0.137 |
Token | comb |
Token ID | 24011 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
llah | +4.269 |
ible | +4.009 |
enegger | +3.877 |
cible | +3.759 |
esters | +3.739 |
Neg logit contributions | |
proport | -7.539 |
suspic | -7.377 |
comr | -6.557 |
fortun | -6.322 |
�� | -5.805 |
Token | tablets |
Token ID | 17255 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
llah | +0.024 |
ible | +0.022 |
enegger | +0.022 |
IPM | +0.022 |
esters | +0.021 |
Neg logit contributions | |
proport | -0.032 |
suspic | -0.031 |
comr | -0.027 |
fortun | -0.026 |
stress | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
proport | +1.792 |
suspic | +1.744 |
comr | +1.528 |
fortun | +1.464 |
stress | +1.369 |
Neg logit contributions | |
llah | -1.378 |
ible | -1.266 |
enegger | -1.261 |
IPM | -1.228 |
esters | -1.210 |
Token | argue |
Token ID | 7267 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
llah | +0.163 |
ible | +0.150 |
enegger | +0.149 |
IPM | +0.144 |
esters | +0.142 |
Neg logit contributions | |
proport | -0.238 |
suspic | -0.233 |
comr | -0.205 |
fortun | -0.197 |
stress | -0.185 |
Token | they |
Token ID | 484 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
llah | +1.103 |
ible | +1.029 |
enegger | +1.006 |
IPM | +0.987 |
esters | +0.972 |
Neg logit contributions | |
proport | -1.561 |
suspic | -1.527 |
comr | -1.350 |
fortun | -1.288 |
stress | -1.208 |
Token | � |
Token ID | 250 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
proport | +0.192 |
suspic | +0.187 |
comr | +0.164 |
fortun | +0.156 |
stress | +0.145 |
Neg logit contributions | |
llah | -0.162 |
ible | -0.151 |
enegger | -0.149 |
IPM | -0.144 |
esters | -0.143 |
Token | great |
Token ID | 18223 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
llah | +0.030 |
ible | +0.028 |
enegger | +0.028 |
IPM | +0.027 |
esters | +0.027 |
Neg logit contributions | |
proport | -0.030 |
suspic | -0.029 |
comr | -0.025 |
fortun | -0.024 |
stress | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
proport | +2.570 |
suspic | +2.508 |
comr | +2.198 |
fortun | +2.109 |
stress | +1.965 |
Neg logit contributions | |
llah | -1.979 |
ible | -1.823 |
enegger | -1.820 |
IPM | -1.771 |
esters | -1.751 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
llah | +0.121 |
ible | +0.112 |
enegger | +0.111 |
IPM | +0.108 |
esters | +0.107 |
Neg logit contributions | |
proport | -0.167 |
suspic | -0.163 |
comr | -0.144 |
fortun | -0.137 |
stress | -0.128 |
Token | � |
Token ID | 251 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
llah | +0.152 |
ible | +0.141 |
enegger | +0.140 |
IPM | +0.136 |
esters | +0.135 |
Neg logit contributions | |
proport | -0.173 |
suspic | -0.170 |
comr | -0.148 |
fortun | -0.141 |
stress | -0.130 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
proport | +0.234 |
suspic | +0.229 |
comr | +0.205 |
fortun | +0.198 |
stress | +0.187 |
Neg logit contributions | |
llah | -0.115 |
ible | -0.104 |
enegger | -0.103 |
IPM | -0.099 |
esters | -0.098 |
Token | said |
Token ID | 531 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
llah | +3.934 |
enegger | +3.826 |
ible | +3.643 |
️ | +3.390 |
esters | +3.376 |
Neg logit contributions | |
proport | -7.560 |
suspic | -7.433 |
comr | -6.663 |
fortun | -6.406 |
�� | -6.039 |
Token | in |
Token ID | 287 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
llah | +0.859 |
ible | +0.792 |
enegger | +0.790 |
IPM | +0.754 |
esters | +0.749 |
Neg logit contributions | |
proport | -1.316 |
suspic | -1.292 |
comr | -1.149 |
fortun | -1.095 |
stress | -1.020 |
Token | response |
Token ID | 2882 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
llah | +0.619 |
ible | +0.577 |
enegger | +0.576 |
IPM | +0.556 |
esters | +0.550 |
Neg logit contributions | |
proport | -0.726 |
suspic | -0.706 |
comr | -0.615 |
fortun | -0.586 |
stress | -0.538 |
Token | to |
Token ID | 284 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
llah | +0.021 |
ible | +0.019 |
enegger | +0.019 |
IPM | +0.018 |
esters | +0.018 |
Neg logit contributions | |
proport | -0.033 |
suspic | -0.033 |
comr | -0.029 |
fortun | -0.028 |
stress | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
llah | +0.258 |
ible | +0.239 |
enegger | +0.238 |
IPM | +0.231 |
esters | +0.229 |
Neg logit contributions | |
proport | -0.305 |
suspic | -0.296 |
comr | -0.258 |
fortun | -0.247 |
stress | -0.228 |
Token | of |
Token ID | 286 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
llah | +0.828 |
ible | +0.776 |
enegger | +0.756 |
IPM | +0.739 |
esters | +0.731 |
Neg logit contributions | |
proport | -1.145 |
suspic | -1.124 |
comr | -0.985 |
fortun | -0.943 |
�� | -0.875 |
Token | Stamford |
Token ID | 47604 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
llah | +0.219 |
ible | +0.203 |
enegger | +0.201 |
IPM | +0.196 |
esters | +0.194 |
Neg logit contributions | |
proport | -0.277 |
suspic | -0.269 |
comr | -0.236 |
fortun | -0.225 |
stress | -0.210 |
Token | Bridge |
Token ID | 10290 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
proport | +3.680 |
suspic | +3.585 |
comr | +3.079 |
fortun | +2.925 |
stress | +2.706 |
Neg logit contributions | |
llah | -3.678 |
ible | -3.440 |
enegger | -3.430 |
IPM | -3.326 |
esters | -3.295 |
Token | , |
Token ID | 11 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
llah | +0.554 |
ible | +0.509 |
enegger | +0.501 |
IPM | +0.497 |
esters | +0.488 |
Neg logit contributions | |
proport | -0.719 |
suspic | -0.698 |
comr | -0.616 |
fortun | -0.585 |
stress | -0.545 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
proport | +0.086 |
suspic | +0.084 |
comr | +0.074 |
fortun | +0.070 |
stress | +0.066 |
Neg logit contributions | |
llah | -0.062 |
ible | -0.057 |
enegger | -0.056 |
IPM | -0.055 |
esters | -0.054 |
Token | nort |
Token ID | 17605 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
llah | +0.802 |
ible | +0.739 |
enegger | +0.724 |
IPM | +0.717 |
esters | +0.701 |
Neg logit contributions | |
proport | -1.065 |
suspic | -1.037 |
comr | -0.912 |
fortun | -0.868 |
stress | -0.813 |
Token | her |
Token ID | 372 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
llah | +4.886 |
ible | +4.547 |
enegger | +4.454 |
esters | +4.429 |
osal | +4.288 |
Neg logit contributions | |
proport | -6.911 |
suspic | -6.847 |
comr | -5.988 |
fortun | -5.724 |
�� | -5.279 |
Token | ners |
Token ID | 2741 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
llah | +0.331 |
ible | +0.306 |
enegger | +0.304 |
IPM | +0.296 |
esters | +0.292 |
Neg logit contributions | |
proport | -0.415 |
suspic | -0.404 |
comr | -0.354 |
fortun | -0.338 |
stress | -0.316 |
Token | were |
Token ID | 547 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
llah | +1.245 |
ible | +1.145 |
enegger | +1.128 |
IPM | +1.106 |
esters | +1.089 |
Neg logit contributions | |
proport | -1.857 |
suspic | -1.817 |
comr | -1.606 |
fortun | -1.535 |
stress | -1.442 |
Token | remarkably |
Token ID | 21196 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
llah | +0.497 |
ible | +0.459 |
enegger | +0.454 |
IPM | +0.443 |
esters | +0.438 |
Neg logit contributions | |
proport | -0.709 |
suspic | -0.691 |
comr | -0.610 |
fortun | -0.583 |
stress | -0.549 |
Token | absent |
Token ID | 13717 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
llah | +0.372 |
ible | +0.344 |
enegger | +0.342 |
IPM | +0.332 |
esters | +0.329 |
Neg logit contributions | |
proport | -0.472 |
suspic | -0.461 |
comr | -0.404 |
fortun | -0.386 |
stress | -0.360 |
Token | frequent |
Token ID | 10792 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
proport | +0.441 |
suspic | +0.431 |
comr | +0.376 |
fortun | +0.359 |
stress | +0.334 |
Neg logit contributions | |
llah | -0.360 |
ible | -0.336 |
enegger | -0.332 |
IPM | -0.324 |
esters | -0.319 |
Token | Dinosaur |
Token ID | 47808 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
llah | +1.628 |
ible | +1.542 |
enegger | +1.518 |
IPM | +1.480 |
esters | +1.468 |
Neg logit contributions | |
proport | -1.720 |
suspic | -1.684 |
comr | -1.445 |
fortun | -1.371 |
stress | -1.274 |
Token | Jr |
Token ID | 7504 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
proport | +2.615 |
suspic | +2.562 |
comr | +2.283 |
fortun | +2.199 |
stress | +2.073 |
Neg logit contributions | |
llah | -1.458 |
ible | -1.324 |
enegger | -1.312 |
IPM | -1.265 |
esters | -1.249 |
Token | . |
Token ID | 13 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
llah | +2.080 |
ible | +1.925 |
enegger | +1.885 |
esters | +1.821 |
osal | +1.792 |
Neg logit contributions | |
proport | -3.218 |
suspic | -3.169 |
comr | -2.793 |
fortun | -2.683 |
stress | -2.516 |
Token | collaborator |
Token ID | 50160 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
proport | +0.820 |
suspic | +0.800 |
comr | +0.697 |
fortun | +0.666 |
stress | +0.620 |
Neg logit contributions | |
llah | -0.675 |
ible | -0.627 |
enegger | -0.622 |
IPM | -0.604 |
esters | -0.599 |
Token | Maur |
Token ID | 18867 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
llah | +1.615 |
ible | +1.507 |
enegger | +1.469 |
IPM | +1.451 |
esters | +1.418 |
Neg logit contributions | |
proport | -2.260 |
suspic | -2.207 |
comr | -1.935 |
fortun | -1.844 |
stress | -1.717 |
Token | a |
Token ID | 64 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
llah | +4.936 |
ible | +4.576 |
enegger | +4.349 |
esters | +4.306 |
osal | +4.294 |
Neg logit contributions | |
proport | -6.785 |
suspic | -6.782 |
comr | -5.821 |
fortun | -5.614 |
�� | -5.186 |
Token | Jasper |
Token ID | 42992 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
proport | +1.641 |
suspic | +1.603 |
comr | +1.403 |
fortun | +1.341 |
stress | +1.248 |
Neg logit contributions | |
llah | -1.287 |
ible | -1.194 |
enegger | -1.184 |
IPM | -1.149 |
esters | -1.139 |
Token | , |
Token ID | 11 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
proport | +1.250 |
suspic | +1.221 |
comr | +1.073 |
fortun | +1.027 |
stress | +0.958 |
Neg logit contributions | |
llah | -0.930 |
ible | -0.859 |
enegger | -0.853 |
IPM | -0.826 |
esters | -0.818 |
Token | an |
Token ID | 281 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
llah | +0.167 |
ible | +0.156 |
enegger | +0.154 |
IPM | +0.151 |
osal | +0.147 |
Neg logit contributions | |
proport | -0.231 |
suspic | -0.226 |
comr | -0.198 |
fortun | -0.190 |
stress | -0.177 |
Token | essay |
Token ID | 14268 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
llah | +0.933 |
ible | +0.864 |
enegger | +0.853 |
IPM | +0.834 |
osal | +0.820 |
Neg logit contributions | |
proport | -1.305 |
suspic | -1.275 |
comr | -1.125 |
fortun | -1.075 |
stress | -1.010 |
Token | traffic |
Token ID | 4979 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
proport | +1.150 |
suspic | +1.120 |
comr | +0.975 |
fortun | +0.930 |
stress | +0.865 |
Neg logit contributions | |
llah | -0.983 |
ible | -0.914 |
enegger | -0.907 |
IPM | -0.884 |
esters | -0.874 |
Token | control |
Token ID | 1630 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
llah | +0.236 |
ible | +0.222 |
enegger | +0.218 |
IPM | +0.213 |
esters | +0.211 |
Neg logit contributions | |
proport | -0.267 |
suspic | -0.258 |
comr | -0.224 |
fortun | -0.213 |
stress | -0.197 |
Token | and |
Token ID | 290 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
proport | +0.349 |
suspic | +0.341 |
comr | +0.301 |
fortun | +0.288 |
stress | +0.270 |
Neg logit contributions | |
llah | -0.237 |
ible | -0.220 |
enegger | -0.216 |
IPM | -0.211 |
esters | -0.208 |
Token | surveillance |
Token ID | 8452 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
proport | +0.080 |
suspic | +0.078 |
comr | +0.068 |
fortun | +0.065 |
stress | +0.060 |
Neg logit contributions | |
llah | -0.067 |
ible | -0.062 |
enegger | -0.061 |
IPM | -0.061 |
esters | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
proport | +2.987 |
suspic | +2.914 |
comr | +2.563 |
fortun | +2.456 |
stress | +2.293 |
Neg logit contributions | |
llah | -2.261 |
enegger | -2.081 |
ible | -2.065 |
IPM | -2.003 |
esters | -1.998 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
llah | +0.359 |
ible | +0.332 |
enegger | +0.330 |
IPM | +0.321 |
esters | +0.317 |
Neg logit contributions | |
proport | -0.464 |
suspic | -0.454 |
comr | -0.397 |
fortun | -0.380 |
stress | -0.353 |
Token | � |
Token ID | 447 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
llah | +4.610 |
enegger | +4.442 |
ible | +4.339 |
esters | +4.069 |
IPM | +4.050 |
Neg logit contributions | |
proport | -6.843 |
suspic | -6.660 |
comr | -5.986 |
fortun | -5.659 |
�� | -5.315 |
Token | � |
Token ID | 247 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
llah | +0.526 |
ible | +0.497 |
enegger | +0.493 |
IPM | +0.484 |
esters | +0.481 |
Neg logit contributions | |
proport | -0.323 |
suspic | -0.313 |
comr | -0.255 |
fortun | -0.238 |
stress | -0.210 |
Token | s |
Token ID | 82 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
llah | +0.213 |
ible | +0.192 |
enegger | +0.191 |
IPM | +0.182 |
esters | +0.181 |
Neg logit contributions | |
proport | -0.416 |
suspic | -0.408 |
comr | -0.365 |
fortun | -0.352 |
stress | -0.331 |
Token | office |
Token ID | 2607 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
llah | +0.615 |
ible | +0.571 |
enegger | +0.568 |
IPM | +0.550 |
esters | +0.543 |
Neg logit contributions | |
proport | -0.786 |
suspic | -0.766 |
comr | -0.669 |
fortun | -0.641 |
stress | -0.599 |
Token | later |
Token ID | 1568 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
proport | +1.045 |
suspic | +1.021 |
comr | +0.898 |
fortun | +0.861 |
stress | +0.806 |
Neg logit contributions | |
llah | -0.749 |
ible | -0.690 |
enegger | -0.686 |
IPM | -0.665 |
esters | -0.658 |
Token | an |
Token ID | 281 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
proport | +0.592 |
suspic | +0.576 |
comr | +0.502 |
fortun | +0.479 |
stress | +0.445 |
Neg logit contributions | |
llah | -0.506 |
ible | -0.471 |
enegger | -0.467 |
IPM | -0.455 |
esters | -0.450 |
Token | incompetent |
Token ID | 33840 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
llah | +0.399 |
ible | +0.372 |
enegger | +0.368 |
IPM | +0.359 |
esters | +0.354 |
Neg logit contributions | |
proport | -0.478 |
suspic | -0.465 |
comr | -0.407 |
fortun | -0.387 |
stress | -0.361 |
Token | fool |
Token ID | 9192 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
llah | +0.117 |
ible | +0.109 |
enegger | +0.108 |
IPM | +0.105 |
esters | +0.104 |
Neg logit contributions | |
proport | -0.142 |
suspic | -0.139 |
comr | -0.121 |
fortun | -0.115 |
stress | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
llah | +1.153 |
ible | +1.070 |
enegger | +1.061 |
IPM | +1.017 |
esters | +1.010 |
Neg logit contributions | |
proport | -1.669 |
suspic | -1.631 |
comr | -1.444 |
fortun | -1.374 |
stress | -1.284 |
Token | Even |
Token ID | 3412 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
llah | +0.037 |
ible | +0.034 |
enegger | +0.034 |
IPM | +0.033 |
esters | +0.033 |
Neg logit contributions | |
proport | -0.044 |
suspic | -0.043 |
comr | -0.037 |
fortun | -0.036 |
stress | -0.033 |
Token | GT |
Token ID | 7963 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
llah | +0.914 |
ible | +0.854 |
enegger | +0.848 |
IPM | +0.824 |
esters | +0.808 |
Neg logit contributions | |
proport | -1.262 |
suspic | -1.225 |
comr | -1.086 |
fortun | -1.029 |
stress | -0.968 |
Token | did |
Token ID | 750 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
llah | +4.717 |
ible | +4.387 |
enegger | +4.340 |
esters | +4.175 |
IPM | +4.174 |
Neg logit contributions | |
proport | -6.833 |
suspic | -6.610 |
comr | -5.870 |
fortun | -5.539 |
stress | -5.210 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
proport | +0.287 |
suspic | +0.280 |
comr | +0.246 |
fortun | +0.236 |
stress | +0.220 |
Neg logit contributions | |
llah | -0.215 |
ible | -0.199 |
enegger | -0.197 |
IPM | -0.192 |
esters | -0.190 |
Token | better |
Token ID | 1365 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
llah | +0.101 |
ible | +0.093 |
enegger | +0.092 |
IPM | +0.090 |
esters | +0.089 |
Neg logit contributions | |
proport | -0.128 |
suspic | -0.125 |
comr | -0.110 |
fortun | -0.104 |
stress | -0.098 |
Token | job |
Token ID | 1693 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
llah | +0.949 |
ible | +0.894 |
enegger | +0.881 |
IPM | +0.863 |
esters | +0.854 |
Neg logit contributions | |
proport | -1.007 |
suspic | -0.978 |
comr | -0.851 |
fortun | -0.802 |
stress | -0.746 |
Token | at |
Token ID | 379 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
llah | +0.008 |
ible | +0.007 |
enegger | +0.007 |
IPM | +0.007 |
esters | +0.007 |
Neg logit contributions | |
proport | -0.011 |
suspic | -0.011 |
comr | -0.009 |
fortun | -0.009 |
stress | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
llah | +0.617 |
ible | +0.574 |
enegger | +0.561 |
IPM | +0.551 |
esters | +0.544 |
Neg logit contributions | |
proport | -0.858 |
suspic | -0.840 |
comr | -0.739 |
fortun | -0.709 |
stress | -0.657 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
proport | +0.015 |
suspic | +0.015 |
comr | +0.013 |
fortun | +0.013 |
stress | +0.012 |
Neg logit contributions | |
llah | -0.012 |
ible | -0.011 |
enegger | -0.011 |
IPM | -0.011 |
esters | -0.011 |
Token | city |
Token ID | 1748 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
proport | +0.022 |
suspic | +0.021 |
comr | +0.019 |
fortun | +0.018 |
stress | +0.017 |
Neg logit contributions | |
llah | -0.015 |
ible | -0.014 |
enegger | -0.014 |
IPM | -0.014 |
osal | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
proport | +0.033 |
suspic | +0.033 |
comr | +0.028 |
fortun | +0.027 |
�� | +0.025 |
Neg logit contributions | |
llah | -0.029 |
ible | -0.027 |
enegger | -0.027 |
IPM | -0.026 |
esters | -0.026 |
Token | famous |
Token ID | 5863 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
llah | +0.201 |
ible | +0.187 |
enegger | +0.185 |
IPM | +0.180 |
osal | +0.177 |
Neg logit contributions | |
proport | -0.263 |
suspic | -0.257 |
comr | -0.224 |
fortun | -0.214 |
stress | -0.202 |
Token | Cock |
Token ID | 23769 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
proport | +0.762 |
suspic | +0.744 |
comr | +0.650 |
fortun | +0.621 |
stress | +0.581 |
Neg logit contributions | |
llah | -0.596 |
ible | -0.552 |
enegger | -0.548 |
IPM | -0.533 |
esters | -0.527 |
Token | ers |
Token ID | 364 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
llah | +5.143 |
ible | +4.872 |
enegger | +4.683 |
osal | +4.585 |
esters | +4.582 |
Neg logit contributions | |
proport | -6.390 |
suspic | -6.238 |
comr | -5.433 |
fortun | -5.124 |
�� | -4.786 |
Token | Roses |
Token ID | 41244 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
llah | +0.478 |
ible | +0.443 |
enegger | +0.439 |
IPM | +0.425 |
esters | +0.421 |
Neg logit contributions | |
proport | -0.625 |
suspic | -0.610 |
comr | -0.535 |
fortun | -0.511 |
stress | -0.477 |
Token | business |
Token ID | 1597 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
proport | +0.745 |
suspic | +0.727 |
comr | +0.635 |
fortun | +0.607 |
stress | +0.565 |
Neg logit contributions | |
llah | -0.611 |
ible | -0.566 |
enegger | -0.563 |
IPM | -0.547 |
esters | -0.541 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
llah | +0.133 |
ible | +0.123 |
enegger | +0.122 |
IPM | +0.119 |
esters | +0.117 |
Neg logit contributions | |
proport | -0.180 |
suspic | -0.176 |
comr | -0.154 |
fortun | -0.148 |
stress | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
proport | +0.173 |
suspic | +0.170 |
comr | +0.149 |
fortun | +0.143 |
stress | +0.133 |
Neg logit contributions | |
llah | -0.124 |
ible | -0.114 |
enegger | -0.113 |
IPM | -0.110 |
esters | -0.109 |
Token | also |
Token ID | 635 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
proport | +1.652 |
suspic | +1.596 |
comr | +1.384 |
fortun | +1.324 |
stress | +1.210 |
Neg logit contributions | |
llah | -1.542 |
ible | -1.449 |
enegger | -1.426 |
IPM | -1.394 |
osal | -1.374 |
Token | Trump |
Token ID | 1301 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
proport | +1.033 |
suspic | +1.002 |
comr | +0.878 |
fortun | +0.836 |
stress | +0.778 |
Neg logit contributions | |
llah | -0.851 |
ible | -0.789 |
enegger | -0.783 |
IPM | -0.763 |
osal | -0.752 |
Token | hints |
Token ID | 20269 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
proport | +0.063 |
suspic | +0.062 |
comr | +0.054 |
fortun | +0.052 |
stress | +0.048 |
Neg logit contributions | |
llah | -0.052 |
ible | -0.048 |
enegger | -0.048 |
IPM | -0.047 |
osal | -0.046 |
Token | he |
Token ID | 339 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
llah | +2.300 |
ible | +2.088 |
enegger | +2.024 |
IPM | +1.978 |
osal | +1.970 |
Neg logit contributions | |
proport | -3.791 |
suspic | -3.651 |
comr | -3.290 |
fortun | -3.148 |
stress | -2.948 |
Token | taped |
Token ID | 36114 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
proport | +0.577 |
suspic | +0.564 |
comr | +0.499 |
fortun | +0.478 |
stress | +0.449 |
Neg logit contributions | |
llah | -0.386 |
ible | -0.354 |
enegger | -0.352 |
IPM | -0.341 |
esters | -0.337 |
Token | Comey |
Token ID | 12388 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
llah | +0.970 |
ible | +0.895 |
enegger | +0.877 |
IPM | +0.864 |
esters | +0.855 |
Neg logit contributions | |
proport | -1.192 |
suspic | -1.148 |
comr | -1.012 |
fortun | -0.955 |
stress | -0.893 |
Token | conversations |
Token ID | 10275 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
proport | +4.326 |
suspic | +4.265 |
comr | +3.687 |
fortun | +3.548 |
stress | +3.302 |
Neg logit contributions | |
llah | -3.423 |
ible | -3.197 |
enegger | -3.189 |
IPM | -3.072 |
esters | -3.049 |
Token | in |
Token ID | 287 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
llah | +0.335 |
ible | +0.309 |
enegger | +0.306 |
IPM | +0.299 |
esters | +0.295 |
Neg logit contributions | |
proport | -0.439 |
suspic | -0.428 |
comr | -0.377 |
fortun | -0.360 |
stress | -0.335 |
Token | veiled |
Token ID | 45694 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
llah | +0.069 |
ible | +0.064 |
enegger | +0.063 |
IPM | +0.062 |
esters | +0.061 |
Neg logit contributions | |
proport | -0.091 |
suspic | -0.089 |
comr | -0.078 |
fortun | -0.075 |
stress | -0.069 |
Token | threat |
Token ID | 2372 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
llah | +0.384 |
ible | +0.363 |
enegger | +0.354 |
IPM | +0.346 |
osal | +0.343 |
Neg logit contributions | |
proport | -0.476 |
suspic | -0.460 |
comr | -0.404 |
fortun | -0.386 |
stress | -0.358 |
Token | President |
Token ID | 1992 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
proport | +0.952 |
suspic | +0.930 |
comr | +0.819 |
fortun | +0.784 |
stress | +0.732 |
Neg logit contributions | |
llah | -0.687 |
ible | -0.633 |
enegger | -0.627 |
IPM | -0.609 |
esters | -0.602 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
proport | +2.497 |
suspic | +2.433 |
comr | +2.134 |
fortun | +2.058 |
stress | +1.927 |
Neg logit contributions | |
llah | -1.819 |
ible | -1.664 |
enegger | -1.663 |
IPM | -1.614 |
osal | -1.593 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
llah | +0.259 |
ible | +0.239 |
enegger | +0.238 |
IPM | +0.232 |
esters | +0.229 |
Neg logit contributions | |
proport | -0.343 |
suspic | -0.335 |
comr | -0.294 |
fortun | -0.281 |
stress | -0.261 |
Token | Ill |
Token ID | 21478 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
proport | +0.139 |
suspic | +0.135 |
comr | +0.118 |
fortun | +0.113 |
stress | +0.104 |
Neg logit contributions | |
llah | -0.110 |
ible | -0.102 |
enegger | -0.101 |
IPM | -0.098 |
esters | -0.098 |
Token | ust |
Token ID | 436 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
proport | +2.897 |
suspic | +2.793 |
comr | +2.291 |
fortun | +2.158 |
stress | +1.934 |
Neg logit contributions | |
llah | -4.450 |
enegger | -4.194 |
ible | -4.184 |
IPM | -4.117 |
esters | -4.068 |
Token | rious |
Token ID | 32527 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
proport | +0.776 |
suspic | +0.755 |
comr | +0.622 |
fortun | +0.579 |
stress | +0.517 |
Neg logit contributions | |
llah | -1.148 |
ible | -1.091 |
enegger | -1.080 |
IPM | -1.054 |
esters | -1.052 |
Token | Illum |
Token ID | 39256 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
llah | +0.412 |
ible | +0.382 |
enegger | +0.378 |
IPM | +0.370 |
esters | +0.364 |
Neg logit contributions | |
proport | -0.538 |
suspic | -0.525 |
comr | -0.460 |
fortun | -0.438 |
stress | -0.411 |
Token | ination |
Token ID | 1883 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
proport | +3.544 |
suspic | +3.416 |
comr | +2.760 |
fortun | +2.605 |
stress | +2.343 |
Neg logit contributions | |
llah | -5.909 |
enegger | -5.558 |
ible | -5.543 |
IPM | -5.458 |
esters | -5.378 |
Token | : |
Token ID | 25 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
llah | +0.264 |
ible | +0.246 |
enegger | +0.240 |
IPM | +0.237 |
esters | +0.233 |
Neg logit contributions | |
proport | -0.354 |
suspic | -0.345 |
comr | -0.304 |
fortun | -0.288 |
stress | -0.268 |
Token | Incredible |
Token ID | 33832 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
proport | +1.403 |
suspic | +1.368 |
comr | +1.196 |
fortun | +1.141 |
stress | +1.063 |
Neg logit contributions | |
llah | -1.133 |
ible | -1.050 |
enegger | -1.043 |
IPM | -1.016 |
esters | -1.004 |
Token | TR |
Token ID | 7579 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
proport | +2.286 |
suspic | +2.231 |
comr | +1.952 |
fortun | +1.871 |
stress | +1.743 |
Neg logit contributions | |
llah | -1.797 |
ible | -1.657 |
enegger | -1.652 |
IPM | -1.599 |
esters | -1.587 |
Token | ON |
Token ID | 1340 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
llah | +0.487 |
ible | +0.450 |
enegger | +0.441 |
esters | +0.429 |
IPM | +0.429 |
Neg logit contributions | |
proport | -0.726 |
suspic | -0.710 |
comr | -0.627 |
fortun | -0.597 |
stress | -0.562 |
Token | pair |
Token ID | 24874 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
llah | +0.571 |
ible | +0.528 |
enegger | +0.521 |
IPM | +0.509 |
esters | +0.504 |
Neg logit contributions | |
proport | -0.776 |
suspic | -0.757 |
comr | -0.664 |
fortun | -0.637 |
stress | -0.591 |
Token | but |
Token ID | 475 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
proport | +0.342 |
suspic | +0.334 |
comr | +0.294 |
fortun | +0.282 |
stress | +0.264 |
Neg logit contributions | |
llah | -0.244 |
ible | -0.224 |
enegger | -0.223 |
IPM | -0.216 |
esters | -0.214 |
Token | require |
Token ID | 2421 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
proport | +2.069 |
suspic | +2.014 |
comr | +1.779 |
fortun | +1.710 |
stress | +1.601 |
Neg logit contributions | |
llah | -1.441 |
enegger | -1.314 |
ible | -1.305 |
IPM | -1.254 |
esters | -1.248 |
Token | out |
Token ID | 503 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
llah | +0.536 |
ible | +0.499 |
enegger | +0.490 |
IPM | +0.484 |
esters | +0.475 |
Neg logit contributions | |
proport | -0.687 |
suspic | -0.671 |
comr | -0.587 |
fortun | -0.560 |
stress | -0.524 |
Token | board |
Token ID | 3526 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
proport | +0.566 |
suspic | +0.555 |
comr | +0.488 |
fortun | +0.467 |
stress | +0.434 |
Neg logit contributions | |
llah | -0.397 |
ible | -0.367 |
enegger | -0.362 |
IPM | -0.353 |
esters | -0.349 |
Token | amplification |
Token ID | 50250 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
llah | +1.261 |
ible | +1.174 |
enegger | +1.158 |
IPM | +1.140 |
esters | +1.120 |
Neg logit contributions | |
proport | -1.504 |
suspic | -1.467 |
comr | -1.276 |
fortun | -1.219 |
stress | -1.136 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
proport | +4.250 |
suspic | +4.118 |
comr | +3.610 |
fortun | +3.488 |
stress | +3.251 |
Neg logit contributions | |
llah | -3.411 |
enegger | -3.180 |
ible | -3.068 |
esters | -3.001 |
osal | -2.986 |
Token | electronics |
Token ID | 17075 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
proport | +0.119 |
suspic | +0.116 |
comr | +0.102 |
fortun | +0.097 |
stress | +0.091 |
Neg logit contributions | |
llah | -0.092 |
ible | -0.085 |
enegger | -0.084 |
IPM | -0.082 |
esters | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
proport | +0.250 |
suspic | +0.244 |
comr | +0.215 |
fortun | +0.206 |
stress | +0.193 |
Neg logit contributions | |
llah | -0.177 |
ible | -0.163 |
enegger | -0.162 |
IPM | -0.157 |
esters | -0.155 |
Token | A |
Token ID | 317 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
llah | +0.278 |
ible | +0.257 |
enegger | +0.257 |
IPM | +0.248 |
esters | +0.247 |
Neg logit contributions | |
proport | -0.306 |
suspic | -0.298 |
comr | -0.259 |
fortun | -0.248 |
stress | -0.230 |
Token | pair |
Token ID | 5166 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
llah | +0.114 |
ible | +0.106 |
enegger | +0.105 |
IPM | +0.102 |
esters | +0.101 |
Neg logit contributions | |
proport | -0.145 |
suspic | -0.141 |
comr | -0.124 |
fortun | -0.118 |
stress | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
llah | +0.058 |
ible | +0.053 |
enegger | +0.052 |
IPM | +0.051 |
osal | +0.050 |
Neg logit contributions | |
proport | -0.086 |
suspic | -0.085 |
comr | -0.075 |
fortun | -0.072 |
stress | -0.067 |
Token | An |
Token ID | 1052 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
proport | +0.039 |
suspic | +0.038 |
comr | +0.033 |
fortun | +0.031 |
stress | +0.029 |
Neg logit contributions | |
llah | -0.034 |
ible | -0.031 |
enegger | -0.031 |
IPM | -0.030 |
esters | -0.030 |
Token | array |
Token ID | 7177 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
llah | +0.225 |
ible | +0.206 |
enegger | +0.205 |
IPM | +0.199 |
esters | +0.196 |
Neg logit contributions | |
proport | -0.335 |
suspic | -0.328 |
comr | -0.290 |
fortun | -0.278 |
stress | -0.261 |
Token | of |
Token ID | 286 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
proport | +0.835 |
suspic | +0.814 |
comr | +0.703 |
fortun | +0.682 |
stress | +0.643 |
Neg logit contributions | |
llah | -0.754 |
enegger | -0.706 |
ible | -0.690 |
IPM | -0.683 |
esters | -0.680 |
Token | online |
Token ID | 2691 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
llah | +0.144 |
ible | +0.133 |
enegger | +0.132 |
IPM | +0.128 |
esters | +0.126 |
Neg logit contributions | |
proport | -0.201 |
suspic | -0.195 |
comr | -0.173 |
fortun | -0.165 |
stress | -0.154 |
Token | stores |
Token ID | 7000 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
proport | +1.364 |
suspic | +1.326 |
comr | +1.133 |
fortun | +1.075 |
stress | +0.988 |
Neg logit contributions | |
llah | -1.459 |
ible | -1.365 |
enegger | -1.359 |
IPM | -1.326 |
esters | -1.315 |
Token | offer |
Token ID | 2897 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
proport | +5.307 |
suspic | +5.193 |
comr | +4.528 |
fortun | +4.417 |
stress | +4.168 |
Neg logit contributions | |
llah | -3.759 |
enegger | -3.441 |
ible | -3.362 |
IPM | -3.304 |
obic | -3.273 |
Token | a |
Token ID | 257 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
llah | +1.367 |
ible | +1.275 |
enegger | +1.244 |
IPM | +1.219 |
osal | +1.196 |
Neg logit contributions | |
proport | -1.874 |
suspic | -1.819 |
comr | -1.606 |
fortun | -1.529 |
�� | -1.434 |
Token | huge |
Token ID | 3236 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
proport | +0.329 |
suspic | +0.320 |
comr | +0.278 |
fortun | +0.265 |
stress | +0.246 |
Neg logit contributions | |
llah | -0.293 |
ible | -0.272 |
enegger | -0.271 |
IPM | -0.264 |
esters | -0.261 |
Token | range |
Token ID | 2837 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
proport | +0.888 |
suspic | +0.867 |
comr | +0.756 |
fortun | +0.724 |
stress | +0.674 |
Neg logit contributions | |
llah | -0.723 |
ible | -0.667 |
enegger | -0.666 |
IPM | -0.646 |
esters | -0.641 |
Token | of |
Token ID | 286 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
proport | +1.041 |
suspic | +1.019 |
comr | +0.893 |
fortun | +0.855 |
stress | +0.795 |
Neg logit contributions | |
llah | -0.800 |
ible | -0.742 |
enegger | -0.735 |
IPM | -0.711 |
osal | -0.707 |
Token | I |
Token ID | 40 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
proport | +0.048 |
suspic | +0.047 |
comr | +0.041 |
fortun | +0.039 |
stress | +0.036 |
Neg logit contributions | |
llah | -0.038 |
ible | -0.036 |
enegger | -0.035 |
IPM | -0.034 |
esters | -0.034 |
Token | liked |
Token ID | 8288 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
proport | +0.690 |
suspic | +0.675 |
comr | +0.593 |
fortun | +0.570 |
stress | +0.537 |
Neg logit contributions | |
llah | -0.472 |
ible | -0.435 |
enegger | -0.432 |
IPM | -0.420 |
esters | -0.415 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
llah | +0.551 |
ible | +0.512 |
enegger | +0.501 |
IPM | +0.493 |
esters | +0.486 |
Neg logit contributions | |
proport | -0.758 |
suspic | -0.737 |
comr | -0.649 |
fortun | -0.617 |
stress | -0.582 |
Token | movie |
Token ID | 3807 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
llah | +0.151 |
ible | +0.140 |
enegger | +0.138 |
IPM | +0.135 |
esters | +0.132 |
Neg logit contributions | |
proport | -0.208 |
suspic | -0.203 |
comr | -0.178 |
fortun | -0.171 |
stress | -0.160 |
Token | The |
Token ID | 383 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
proport | +2.411 |
suspic | +2.354 |
comr | +2.061 |
fortun | +1.973 |
stress | +1.841 |
Neg logit contributions | |
llah | -1.878 |
ible | -1.736 |
enegger | -1.726 |
IPM | -1.676 |
esters | -1.658 |
Token | Pur |
Token ID | 9330 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
proport | +1.068 |
suspic | +1.037 |
comr | +0.885 |
fortun | +0.836 |
stress | +0.767 |
Neg logit contributions | |
llah | -1.158 |
ible | -1.088 |
enegger | -1.078 |
IPM | -1.055 |
esters | -1.044 |
Token | ge |
Token ID | 469 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
proport | +3.932 |
suspic | +3.848 |
comr | +3.366 |
fortun | +3.268 |
stress | +3.252 |
Neg logit contributions | |
llah | -3.683 |
enegger | -3.504 |
IPM | -3.350 |
ible | -3.335 |
RESULTS | -3.225 |
Token | but |
Token ID | 475 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
llah | +0.454 |
ible | +0.420 |
enegger | +0.417 |
IPM | +0.402 |
esters | +0.401 |
Neg logit contributions | |
proport | -0.623 |
suspic | -0.605 |
comr | -0.533 |
fortun | -0.510 |
stress | -0.474 |
Token | with |
Token ID | 351 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
proport | +2.247 |
suspic | +2.200 |
comr | +1.937 |
fortun | +1.865 |
stress | +1.742 |
Neg logit contributions | |
llah | -1.530 |
ible | -1.403 |
enegger | -1.397 |
IPM | -1.352 |
esters | -1.339 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
proport | +0.185 |
suspic | +0.180 |
comr | +0.158 |
fortun | +0.150 |
stress | +0.141 |
Neg logit contributions | |
llah | -0.148 |
ible | -0.137 |
enegger | -0.136 |
IPM | -0.132 |
esters | -0.130 |
Token | it |
Token ID | 340 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
proport | +1.624 |
suspic | +1.588 |
comr | +1.393 |
fortun | +1.336 |
stress | +1.248 |
Neg logit contributions | |
llah | -1.185 |
ible | -1.093 |
enegger | -1.088 |
IPM | -1.054 |
esters | -1.043 |
Token | Italian |
Token ID | 8200 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
proport | +2.688 |
suspic | +2.622 |
comr | +2.307 |
fortun | +2.205 |
stress | +2.062 |
Neg logit contributions | |
llah | -2.027 |
ible | -1.863 |
enegger | -1.858 |
IPM | -1.795 |
esters | -1.780 |
Token | volunteers |
Token ID | 11661 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
llah | +1.622 |
ible | +1.530 |
enegger | +1.510 |
IPM | +1.485 |
esters | +1.459 |
Neg logit contributions | |
proport | -2.084 |
suspic | -2.042 |
comr | -1.773 |
fortun | -1.708 |
stress | -1.575 |
Token | Storm |
Token ID | 8865 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
proport | +0.964 |
suspic | +0.941 |
comr | +0.832 |
fortun | +0.799 |
stress | +0.750 |
Neg logit contributions | |
llah | -0.654 |
ible | -0.599 |
enegger | -0.596 |
IPM | -0.576 |
esters | -0.570 |
Token | Brigade |
Token ID | 26012 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
llah | +1.211 |
ible | +1.131 |
enegger | +1.121 |
IPM | +1.080 |
osal | +1.073 |
Neg logit contributions | |
proport | -1.596 |
suspic | -1.560 |
comr | -1.363 |
fortun | -1.305 |
stress | -1.206 |
Token | were |
Token ID | 547 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
llah | +0.142 |
ible | +0.131 |
enegger | +0.130 |
IPM | +0.126 |
esters | +0.124 |
Neg logit contributions | |
proport | -0.206 |
suspic | -0.201 |
comr | -0.177 |
fortun | -0.170 |
stress | -0.159 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
llah | +0.228 |
ible | +0.211 |
enegger | +0.210 |
IPM | +0.204 |
esters | +0.202 |
Neg logit contributions | |
proport | -0.292 |
suspic | -0.285 |
comr | -0.250 |
fortun | -0.239 |
stress | -0.223 |
Token | to |
Token ID | 284 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
proport | +1.408 |
suspic | +1.377 |
comr | +1.217 |
fortun | +1.169 |
stress | +1.096 |
Neg logit contributions | |
llah | -0.929 |
ible | -0.852 |
enegger | -0.846 |
IPM | -0.819 |
esters | -0.810 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
proport | +0.297 |
suspic | +0.291 |
comr | +0.255 |
fortun | +0.245 |
stress | +0.228 |
Neg logit contributions | |
llah | -0.217 |
ible | -0.201 |
enegger | -0.199 |
IPM | -0.194 |
esters | -0.191 |
Token | An |
Token ID | 1052 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
proport | +0.123 |
suspic | +0.121 |
comr | +0.105 |
fortun | +0.101 |
stress | +0.094 |
Neg logit contributions | |
llah | -0.093 |
ible | -0.086 |
enegger | -0.085 |
IPM | -0.083 |
esters | -0.082 |
Token | z |
Token ID | 89 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
proport | +0.432 |
suspic | +0.421 |
comr | +0.367 |
fortun | +0.349 |
stress | +0.324 |
Neg logit contributions | |
llah | -0.363 |
ible | -0.338 |
enegger | -0.334 |
IPM | -0.325 |
esters | -0.323 |
Token | io |
Token ID | 952 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
proport | +0.520 |
suspic | +0.507 |
comr | +0.444 |
fortun | +0.424 |
stress | +0.394 |
Neg logit contributions | |
llah | -0.414 |
ible | -0.386 |
enegger | -0.382 |
IPM | -0.370 |
esters | -0.368 |
Token | the |
Token ID | 262 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
proport | +0.018 |
suspic | +0.017 |
comr | +0.015 |
fortun | +0.015 |
stress | +0.014 |
Neg logit contributions | |
llah | -0.014 |
ible | -0.013 |
enegger | -0.013 |
IPM | -0.013 |
esters | -0.012 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
llah | +0.040 |
ible | +0.037 |
enegger | +0.036 |
IPM | +0.035 |
esters | +0.035 |
Neg logit contributions | |
proport | -0.051 |
suspic | -0.050 |
comr | -0.044 |
fortun | -0.042 |
stress | -0.039 |
Token | Party |
Token ID | 3615 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
proport | +2.114 |
suspic | +2.056 |
comr | +1.763 |
fortun | +1.673 |
stress | +1.537 |
Neg logit contributions | |
llah | -2.185 |
enegger | -2.039 |
ible | -2.036 |
IPM | -1.977 |
esters | -1.964 |
Token | was |
Token ID | 373 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
proport | +0.553 |
suspic | +0.541 |
comr | +0.478 |
fortun | +0.458 |
stress | +0.430 |
Neg logit contributions | |
llah | -0.368 |
ible | -0.339 |
enegger | -0.335 |
IPM | -0.327 |
esters | -0.322 |
Token | going |
Token ID | 1016 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
proport | +0.454 |
suspic | +0.443 |
comr | +0.392 |
fortun | +0.372 |
stress | +0.349 |
Neg logit contributions | |
llah | -0.339 |
ible | -0.315 |
enegger | -0.310 |
IPM | -0.302 |
esters | -0.299 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
proport | +1.183 |
suspic | +1.154 |
comr | +1.038 |
fortun | +0.994 |
stress | +0.935 |
Neg logit contributions | |
llah | -0.711 |
ible | -0.659 |
enegger | -0.642 |
IPM | -0.623 |
esters | -0.620 |
Token | come |
Token ID | 1282 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
proport | +0.160 |
suspic | +0.157 |
comr | +0.137 |
fortun | +0.131 |
stress | +0.122 |
Neg logit contributions | |
llah | -0.129 |
ible | -0.119 |
enegger | -0.117 |
IPM | -0.115 |
esters | -0.113 |
Token | down |
Token ID | 866 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
llah | +0.077 |
ible | +0.071 |
enegger | +0.069 |
esters | +0.067 |
IPM | +0.067 |
Neg logit contributions | |
proport | -0.125 |
suspic | -0.122 |
comr | -0.109 |
fortun | -0.104 |
stress | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
proport | +0.770 |
suspic | +0.758 |
comr | +0.673 |
fortun | +0.645 |
stress | +0.608 |
Neg logit contributions | |
llah | -0.476 |
ible | -0.440 |
enegger | -0.428 |
IPM | -0.417 |
esters | -0.414 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
proport | +0.013 |
suspic | +0.012 |
comr | +0.011 |
fortun | +0.010 |
stress | +0.010 |
Neg logit contributions | |
llah | -0.010 |
ible | -0.009 |
enegger | -0.009 |
IPM | -0.009 |
osal | -0.008 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
proport | +1.438 |
suspic | +1.403 |
comr | +1.221 |
fortun | +1.163 |
stress | +1.079 |
Neg logit contributions | |
llah | -1.259 |
ible | -1.171 |
enegger | -1.160 |
IPM | -1.135 |
esters | -1.122 |
Token | booth |
Token ID | 18600 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
llah | +0.957 |
ible | +0.885 |
enegger | +0.862 |
IPM | +0.839 |
cible | +0.829 |
Neg logit contributions | |
proport | -1.418 |
suspic | -1.379 |
comr | -1.222 |
fortun | -1.173 |
�� | -1.100 |
Token | , |
Token ID | 11 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
proport | +1.657 |
suspic | +1.618 |
comr | +1.420 |
fortun | +1.360 |
stress | +1.271 |
Neg logit contributions | |
llah | -1.243 |
ible | -1.146 |
enegger | -1.141 |
IPM | -1.107 |
esters | -1.095 |
Token | Bour |
Token ID | 20576 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
proport | +0.365 |
suspic | +0.355 |
comr | +0.312 |
fortun | +0.299 |
stress | +0.279 |
Neg logit contributions | |
llah | -0.272 |
ible | -0.251 |
enegger | -0.249 |
IPM | -0.243 |
esters | -0.239 |
Token | dain |
Token ID | 27162 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
proport | +0.337 |
suspic | +0.332 |
comr | +0.295 |
fortun | +0.284 |
stress | +0.278 |
Neg logit contributions | |
llah | -0.225 |
ible | -0.205 |
enegger | -0.205 |
IPM | -0.203 |
esters | -0.197 |
Token | puts |
Token ID | 7584 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
llah | +0.536 |
ible | +0.498 |
enegger | +0.494 |
IPM | +0.480 |
esters | +0.476 |
Neg logit contributions | |
proport | -0.683 |
suspic | -0.665 |
comr | -0.584 |
fortun | -0.556 |
stress | -0.519 |
Token | on |
Token ID | 319 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
proport | +0.964 |
suspic | +0.938 |
comr | +0.825 |
fortun | +0.789 |
stress | +0.735 |
Neg logit contributions | |
llah | -0.731 |
ible | -0.677 |
enegger | -0.671 |
IPM | -0.654 |
esters | -0.645 |
Token | a |
Token ID | 257 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
proport | +0.701 |
suspic | +0.682 |
comr | +0.594 |
fortun | +0.566 |
stress | +0.525 |
Neg logit contributions | |
llah | -0.596 |
ible | -0.557 |
enegger | -0.552 |
IPM | -0.539 |
esters | -0.534 |
Token | pair |
Token ID | 5166 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
proport | +0.261 |
suspic | +0.255 |
comr | +0.223 |
fortun | +0.213 |
stress | +0.199 |
Neg logit contributions | |
llah | -0.203 |
ible | -0.189 |
enegger | -0.187 |
IPM | -0.182 |
esters | -0.180 |
Token | of |
Token ID | 286 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
proport | +0.368 |
suspic | +0.360 |
comr | +0.313 |
fortun | +0.302 |
stress | +0.286 |
Neg logit contributions | |
llah | -0.326 |
enegger | -0.304 |
ible | -0.300 |
IPM | -0.292 |
esters | -0.292 |
Token | reading |
Token ID | 3555 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
proport | +0.293 |
suspic | +0.285 |
comr | +0.249 |
fortun | +0.238 |
stress | +0.221 |
Neg logit contributions | |
llah | -0.239 |
ible | -0.223 |
enegger | -0.221 |
IPM | -0.215 |
esters | -0.212 |
Token | glasses |
Token ID | 15232 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
proport | +1.658 |
suspic | +1.613 |
comr | +1.391 |
fortun | +1.322 |
stress | +1.221 |
Neg logit contributions | |
llah | -1.587 |
ible | -1.487 |
enegger | -1.472 |
IPM | -1.440 |
esters | -1.427 |
Token | a |
Token ID | 257 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
llah | +0.907 |
ible | +0.846 |
enegger | +0.842 |
IPM | +0.819 |
esters | +0.816 |
Neg logit contributions | |
proport | -0.947 |
suspic | -0.920 |
comr | -0.797 |
fortun | -0.756 |
stress | -0.697 |
Token | Dream |
Token ID | 7610 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
proport | +0.482 |
suspic | +0.471 |
comr | +0.422 |
fortun | +0.406 |
stress | +0.381 |
Neg logit contributions | |
llah | -0.260 |
ible | -0.235 |
enegger | -0.232 |
IPM | -0.224 |
esters | -0.222 |
Token | … |
Token ID | 1399 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
proport | +1.109 |
suspic | +1.084 |
comr | +0.954 |
fortun | +0.915 |
stress | +0.853 |
Neg logit contributions | |
llah | -0.797 |
ible | -0.735 |
enegger | -0.730 |
IPM | -0.705 |
esters | -0.699 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
proport | +0.365 |
suspic | +0.356 |
comr | +0.313 |
fortun | +0.299 |
stress | +0.279 |
Neg logit contributions | |
llah | -0.278 |
ible | -0.257 |
enegger | -0.255 |
IPM | -0.247 |
esters | -0.245 |
Token | kick |
Token ID | 4829 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
proport | +0.013 |
suspic | +0.012 |
comr | +0.011 |
fortun | +0.010 |
stress | +0.010 |
Neg logit contributions | |
llah | -0.010 |
ible | -0.009 |
enegger | -0.009 |
IPM | -0.009 |
esters | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
llah | +0.501 |
ible | +0.467 |
enegger | +0.464 |
IPM | +0.450 |
osal | +0.445 |
Neg logit contributions | |
proport | -0.587 |
suspic | -0.574 |
comr | -0.499 |
fortun | -0.476 |
stress | -0.438 |
Token | as |
Token ID | 292 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
proport | +0.390 |
suspic | +0.379 |
comr | +0.325 |
fortun | +0.309 |
stress | +0.284 |
Neg logit contributions | |
llah | -0.404 |
ible | -0.378 |
enegger | -0.376 |
IPM | -0.366 |
esters | -0.363 |
Token | movie |
Token ID | 3807 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
proport | +2.255 |
suspic | +2.208 |
comr | +1.939 |
fortun | +1.861 |
stress | +1.748 |
Neg logit contributions | |
llah | -1.650 |
ible | -1.505 |
enegger | -1.503 |
IPM | -1.461 |
esters | -1.442 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
proport | +2.508 |
suspic | +2.438 |
comr | +2.139 |
fortun | +2.049 |
stress | +1.922 |
Neg logit contributions | |
llah | -1.925 |
ible | -1.769 |
enegger | -1.757 |
IPM | -1.715 |
esters | -1.700 |
Token | And |
Token ID | 843 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
llah | +0.004 |
ible | +0.004 |
enegger | +0.004 |
IPM | +0.004 |
esters | +0.004 |
Neg logit contributions | |
proport | -0.005 |
suspic | -0.005 |
comr | -0.004 |
fortun | -0.004 |
stress | -0.004 |
Token | who |
Token ID | 508 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
proport | +0.603 |
suspic | +0.589 |
comr | +0.518 |
fortun | +0.496 |
stress | +0.464 |
Neg logit contributions | |
llah | -0.440 |
ible | -0.406 |
enegger | -0.404 |
IPM | -0.391 |
esters | -0.387 |
Token | rise |
Token ID | 4485 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
llah | +0.169 |
ible | +0.158 |
enegger | +0.156 |
IPM | +0.153 |
esters | +0.151 |
Neg logit contributions | |
proport | -0.186 |
suspic | -0.183 |
comr | -0.159 |
fortun | -0.151 |
stress | -0.138 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
llah | +0.564 |
ible | +0.526 |
enegger | +0.515 |
IPM | +0.501 |
esters | +0.497 |
Neg logit contributions | |
proport | -0.802 |
suspic | -0.787 |
comr | -0.695 |
fortun | -0.664 |
stress | -0.619 |
Token | that |
Token ID | 326 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
llah | +0.090 |
ible | +0.083 |
enegger | +0.082 |
IPM | +0.080 |
esters | +0.079 |
Neg logit contributions | |
proport | -0.123 |
suspic | -0.120 |
comr | -0.105 |
fortun | -0.101 |
stress | -0.094 |
Token | 's |
Token ID | 338 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
llah | +0.433 |
ible | +0.406 |
enegger | +0.398 |
IPM | +0.389 |
esters | +0.386 |
Neg logit contributions | |
proport | -0.546 |
suspic | -0.535 |
comr | -0.468 |
fortun | -0.447 |
�� | -0.417 |
Token | a |
Token ID | 257 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
llah | +0.895 |
ible | +0.837 |
enegger | +0.821 |
IPM | +0.809 |
esters | +0.799 |
Neg logit contributions | |
proport | -1.149 |
suspic | -1.123 |
comr | -0.986 |
fortun | -0.940 |
stress | -0.878 |
Token | huge |
Token ID | 3236 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
llah | +0.054 |
ible | +0.050 |
enegger | +0.049 |
IPM | +0.048 |
esters | +0.048 |
Neg logit contributions | |
proport | -0.064 |
suspic | -0.062 |
comr | -0.055 |
fortun | -0.052 |
stress | -0.048 |
Token | rise |
Token ID | 4485 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
proport | +0.246 |
suspic | +0.241 |
comr | +0.212 |
fortun | +0.203 |
stress | +0.189 |
Neg logit contributions | |
llah | -0.184 |
ible | -0.170 |
enegger | -0.169 |
IPM | -0.164 |
esters | -0.162 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
llah | +0.222 |
ible | +0.205 |
enegger | +0.203 |
IPM | +0.196 |
esters | +0.194 |
Neg logit contributions | |
proport | -0.317 |
suspic | -0.311 |
comr | -0.274 |
fortun | -0.262 |
stress | -0.245 |
Token | if |
Token ID | 611 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
llah | +0.076 |
ible | +0.070 |
enegger | +0.070 |
IPM | +0.068 |
esters | +0.067 |
Neg logit contributions | |
proport | -0.103 |
suspic | -0.101 |
comr | -0.089 |
fortun | -0.085 |
stress | -0.079 |
Token | you |
Token ID | 345 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
llah | +0.341 |
ible | +0.316 |
enegger | +0.312 |
IPM | +0.305 |
esters | +0.300 |
Neg logit contributions | |
proport | -0.462 |
suspic | -0.452 |
comr | -0.396 |
fortun | -0.380 |
stress | -0.355 |
Token | think |
Token ID | 892 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
llah | +0.693 |
enegger | +0.635 |
ible | +0.633 |
IPM | +0.610 |
esters | +0.605 |
Neg logit contributions | |
proport | -1.032 |
suspic | -1.007 |
comr | -0.888 |
fortun | -0.855 |
stress | -0.802 |
Token | have |
Token ID | 423 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
proport | +1.492 |
suspic | +1.455 |
comr | +1.274 |
fortun | +1.218 |
stress | +1.137 |
Neg logit contributions | |
llah | -1.176 |
ible | -1.088 |
enegger | -1.081 |
IPM | -1.050 |
esters | -1.039 |
Token | deemed |
Token ID | 10762 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
proport | +0.270 |
suspic | +0.263 |
comr | +0.231 |
fortun | +0.220 |
stress | +0.205 |
Neg logit contributions | |
llah | -0.218 |
ible | -0.203 |
enegger | -0.201 |
IPM | -0.195 |
esters | -0.193 |
Token | UN |
Token ID | 4725 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
llah | +1.259 |
ible | +1.181 |
enegger | +1.152 |
osal | +1.122 |
IPM | +1.122 |
Neg logit contributions | |
proport | -1.676 |
suspic | -1.618 |
comr | -1.432 |
fortun | -1.376 |
stress | -1.276 |
Token | FOR |
Token ID | 13775 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
proport | +2.202 |
suspic | +2.159 |
comr | +1.890 |
fortun | +1.813 |
stress | +1.698 |
Neg logit contributions | |
llah | -1.624 |
ible | -1.496 |
enegger | -1.492 |
IPM | -1.444 |
esters | -1.432 |
Token | G |
Token ID | 38 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
proport | +1.353 |
suspic | +1.333 |
comr | +1.157 |
fortun | +1.123 |
stress | +1.037 |
Neg logit contributions | |
llah | -1.012 |
enegger | -0.922 |
ible | -0.906 |
IPM | -0.880 |
esters | -0.879 |
Token | IV |
Token ID | 3824 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
llah | +0.100 |
enegger | +0.090 |
ible | +0.089 |
IPM | +0.087 |
esters | +0.087 |
Neg logit contributions | |
proport | -0.142 |
suspic | -0.140 |
comr | -0.122 |
fortun | -0.118 |
stress | -0.110 |
Token | ABLE |
Token ID | 17534 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
llah | +0.598 |
enegger | +0.535 |
ible | +0.534 |
IPM | +0.511 |
esters | +0.508 |
Neg logit contributions | |
proport | -1.173 |
suspic | -1.149 |
comr | -1.029 |
fortun | -0.993 |
stress | -0.938 |
Token | ( |
Token ID | 357 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
llah | +1.051 |
ible | +0.972 |
enegger | +0.964 |
IPM | +0.927 |
osal | +0.916 |
Neg logit contributions | |
proport | -1.575 |
suspic | -1.541 |
comr | -1.365 |
fortun | -1.302 |
stress | -1.224 |
Token | though |
Token ID | 2016 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
llah | +1.010 |
ible | +0.945 |
enegger | +0.938 |
IPM | +0.911 |
esters | +0.908 |
Neg logit contributions | |
proport | -1.018 |
suspic | -0.986 |
comr | -0.851 |
fortun | -0.805 |
stress | -0.736 |
Token | that |
Token ID | 326 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
proport | +0.832 |
suspic | +0.812 |
comr | +0.715 |
fortun | +0.686 |
stress | +0.642 |
Neg logit contributions | |
llah | -0.590 |
ible | -0.543 |
enegger | -0.540 |
IPM | -0.523 |
esters | -0.517 |
Token | hasn |
Token ID | 5818 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
llah | +0.303 |
ible | +0.280 |
enegger | +0.278 |
IPM | +0.269 |
esters | +0.266 |
Neg logit contributions | |
proport | -0.413 |
suspic | -0.402 |
comr | -0.355 |
fortun | -0.339 |
stress | -0.317 |
Token | UR |
Token ID | 4261 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
proport | +0.835 |
suspic | +0.812 |
comr | +0.708 |
fortun | +0.691 |
stress | +0.649 |
Neg logit contributions | |
llah | -0.650 |
enegger | -0.610 |
ible | -0.603 |
cible | -0.578 |
IPM | -0.572 |
Token | -- |
Token ID | 1377 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
proport | +0.502 |
suspic | +0.491 |
comr | +0.431 |
fortun | +0.410 |
stress | +0.383 |
Neg logit contributions | |
llah | -0.384 |
ible | -0.354 |
enegger | -0.349 |
IPM | -0.344 |
esters | -0.336 |
Token | With |
Token ID | 2080 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
proport | +1.403 |
suspic | +1.371 |
comr | +1.206 |
fortun | +1.156 |
stress | +1.082 |
Neg logit contributions | |
llah | -1.013 |
ible | -0.933 |
enegger | -0.927 |
IPM | -0.899 |
esters | -0.890 |
Token | barely |
Token ID | 8523 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
proport | +0.190 |
suspic | +0.185 |
comr | +0.163 |
fortun | +0.155 |
stress | +0.145 |
Neg logit contributions | |
llah | -0.144 |
ible | -0.133 |
enegger | -0.132 |
IPM | -0.129 |
esters | -0.127 |
Token | a |
Token ID | 257 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
llah | +2.677 |
ible | +2.523 |
enegger | +2.453 |
IPM | +2.448 |
esters | +2.399 |
Neg logit contributions | |
proport | -3.271 |
suspic | -3.176 |
comr | -2.792 |
fortun | -2.623 |
stress | -2.469 |
Token | month |
Token ID | 1227 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
llah | +0.093 |
ible | +0.086 |
enegger | +0.085 |
IPM | +0.083 |
esters | +0.082 |
Neg logit contributions | |
proport | -0.127 |
suspic | -0.124 |
comr | -0.109 |
fortun | -0.104 |
stress | -0.098 |
Token | leading |
Token ID | 3756 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
llah | +0.384 |
ible | +0.352 |
enegger | +0.345 |
esters | +0.331 |
IPM | +0.330 |
Neg logit contributions | |
proport | -0.718 |
suspic | -0.704 |
comr | -0.631 |
fortun | -0.603 |
stress | -0.569 |
Token | up |
Token ID | 510 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
proport | +1.236 |
suspic | +1.212 |
comr | +1.088 |
fortun | +1.052 |
stress | +0.997 |
Neg logit contributions | |
llah | -0.571 |
ible | -0.509 |
enegger | -0.508 |
IPM | -0.487 |
esters | -0.476 |
Token | to |
Token ID | 284 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
proport | +0.030 |
suspic | +0.029 |
comr | +0.026 |
fortun | +0.025 |
stress | +0.023 |
Neg logit contributions | |
llah | -0.018 |
ible | -0.017 |
enegger | -0.017 |
IPM | -0.016 |
esters | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
llah | +0.240 |
ible | +0.222 |
enegger | +0.219 |
IPM | +0.214 |
esters | +0.212 |
Neg logit contributions | |
proport | -0.311 |
suspic | -0.303 |
comr | -0.265 |
fortun | -0.253 |
stress | -0.237 |
Token | retirement |
Token ID | 10737 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
proport | +1.415 |
suspic | +1.381 |
comr | +1.211 |
fortun | +1.161 |
stress | +1.082 |
Neg logit contributions | |
llah | -1.081 |
ible | -0.998 |
enegger | -0.993 |
IPM | -0.963 |
esters | -0.955 |
Token | one |
Token ID | 530 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
llah | +0.362 |
ible | +0.336 |
enegger | +0.333 |
IPM | +0.324 |
esters | +0.321 |
Neg logit contributions | |
proport | -0.481 |
suspic | -0.469 |
comr | -0.412 |
fortun | -0.394 |
stress | -0.370 |
Token | of |
Token ID | 286 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
proport | +0.585 |
suspic | +0.572 |
comr | +0.503 |
fortun | +0.480 |
stress | +0.450 |
Neg logit contributions | |
llah | -0.442 |
ible | -0.411 |
enegger | -0.403 |
IPM | -0.393 |
osal | -0.390 |
Token | many |
Token ID | 867 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
llah | +0.129 |
ible | +0.120 |
enegger | +0.119 |
IPM | +0.116 |
esters | +0.115 |
Neg logit contributions | |
proport | -0.165 |
suspic | -0.161 |
comr | -0.141 |
fortun | -0.134 |
stress | -0.125 |
Token | House |
Token ID | 2097 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
proport | +0.337 |
suspic | +0.329 |
comr | +0.290 |
fortun | +0.278 |
stress | +0.261 |
Neg logit contributions | |
llah | -0.236 |
ible | -0.217 |
enegger | -0.215 |
IPM | -0.209 |
esters | -0.207 |
Token | Democrats |
Token ID | 4956 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
proport | +1.055 |
suspic | +1.030 |
comr | +0.908 |
fortun | +0.870 |
stress | +0.814 |
Neg logit contributions | |
llah | -0.749 |
ible | -0.689 |
enegger | -0.685 |
IPM | -0.664 |
esters | -0.656 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
proport | +1.548 |
suspic | +1.513 |
comr | +1.332 |
fortun | +1.280 |
stress | +1.197 |
Neg logit contributions | |
llah | -1.082 |
ible | -0.991 |
enegger | -0.989 |
IPM | -0.955 |
osal | -0.943 |
Token | vote |
Token ID | 3015 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
llah | +0.146 |
ible | +0.134 |
enegger | +0.133 |
IPM | +0.129 |
esters | +0.127 |
Neg logit contributions | |
proport | -0.213 |
suspic | -0.208 |
comr | -0.184 |
fortun | -0.177 |
stress | -0.165 |
Token | against |
Token ID | 1028 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
llah | +1.352 |
ible | +1.237 |
enegger | +1.201 |
IPM | +1.177 |
esters | +1.159 |
Neg logit contributions | |
proport | -2.311 |
suspic | -2.257 |
comr | -2.024 |
fortun | -1.938 |
stress | -1.820 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
llah | +0.421 |
ible | +0.394 |
enegger | +0.388 |
IPM | +0.380 |
esters | +0.376 |
Neg logit contributions | |
proport | -0.525 |
suspic | -0.513 |
comr | -0.452 |
fortun | -0.428 |
stress | -0.399 |
Token | bill |
Token ID | 2855 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
llah | +0.090 |
ible | +0.083 |
enegger | +0.082 |
IPM | +0.080 |
esters | +0.079 |
Neg logit contributions | |
proport | -0.136 |
suspic | -0.133 |
comr | -0.117 |
fortun | -0.113 |
stress | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
llah | +0.674 |
ible | +0.620 |
enegger | +0.616 |
IPM | +0.594 |
esters | +0.590 |
Neg logit contributions | |
proport | -0.973 |
suspic | -0.953 |
comr | -0.842 |
fortun | -0.806 |
stress | -0.752 |
Token | ? |
Token ID | 30 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
llah | +0.076 |
ible | +0.070 |
enegger | +0.068 |
IPM | +0.067 |
esters | +0.066 |
Neg logit contributions | |
proport | -0.119 |
suspic | -0.117 |
comr | -0.103 |
fortun | -0.099 |
stress | -0.093 |
Token | And |
Token ID | 843 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
llah | +0.373 |
ible | +0.347 |
enegger | +0.344 |
IPM | +0.336 |
esters | +0.331 |
Neg logit contributions | |
proport | -0.459 |
suspic | -0.448 |
comr | -0.391 |
fortun | -0.372 |
stress | -0.346 |
Token | what |
Token ID | 644 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
proport | +0.790 |
suspic | +0.772 |
comr | +0.678 |
fortun | +0.650 |
stress | +0.607 |
Neg logit contributions | |
llah | -0.590 |
ible | -0.544 |
enegger | -0.541 |
IPM | -0.524 |
esters | -0.519 |
Token | better |
Token ID | 1365 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
llah | +0.999 |
ible | +0.917 |
enegger | +0.885 |
IPM | +0.877 |
esters | +0.865 |
Neg logit contributions | |
proport | -1.976 |
suspic | -1.916 |
comr | -1.714 |
fortun | -1.654 |
�� | -1.582 |
Token | way |
Token ID | 835 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
llah | +1.502 |
ible | +1.438 |
enegger | +1.392 |
IPM | +1.385 |
osal | +1.364 |
Neg logit contributions | |
proport | -1.581 |
suspic | -1.533 |
comr | -1.313 |
fortun | -1.243 |
�� | -1.165 |
Token | to |
Token ID | 284 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
llah | +0.074 |
ible | +0.068 |
enegger | +0.067 |
IPM | +0.065 |
esters | +0.065 |
Neg logit contributions | |
proport | -0.122 |
suspic | -0.119 |
comr | -0.106 |
fortun | -0.102 |
stress | -0.095 |
Token | get |
Token ID | 651 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
llah | +0.260 |
ible | +0.241 |
enegger | +0.237 |
IPM | +0.232 |
esters | +0.228 |
Neg logit contributions | |
proport | -0.361 |
suspic | -0.352 |
comr | -0.309 |
fortun | -0.297 |
stress | -0.276 |
Token | people |
Token ID | 661 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
proport | +0.712 |
suspic | +0.695 |
comr | +0.608 |
fortun | +0.582 |
stress | +0.545 |
Neg logit contributions | |
llah | -0.543 |
ible | -0.505 |
enegger | -0.499 |
IPM | -0.487 |
esters | -0.480 |
Token | to |
Token ID | 284 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
proport | +0.944 |
suspic | +0.921 |
comr | +0.813 |
fortun | +0.779 |
stress | +0.729 |
Neg logit contributions | |
llah | -0.661 |
ible | -0.612 |
enegger | -0.603 |
IPM | -0.587 |
esters | -0.580 |
Token | pay |
Token ID | 1414 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
llah | +0.035 |
ible | +0.032 |
enegger | +0.032 |
IPM | +0.031 |
esters | +0.030 |
Neg logit contributions | |
proport | -0.051 |
suspic | -0.050 |
comr | -0.044 |
fortun | -0.042 |
stress | -0.040 |
Token | attention |
Token ID | 3241 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
llah | +0.365 |
ible | +0.348 |
enegger | +0.344 |
IPM | +0.338 |
esters | +0.335 |
Neg logit contributions | |
proport | -0.236 |
suspic | -0.226 |
comr | -0.187 |
fortun | -0.174 |
�� | -0.155 |
Token | natural |
Token ID | 3288 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
proport | +0.761 |
suspic | +0.743 |
comr | +0.652 |
fortun | +0.624 |
stress | +0.581 |
Neg logit contributions | |
llah | -0.592 |
ible | -0.547 |
enegger | -0.544 |
IPM | -0.528 |
esters | -0.522 |
Token | enemy |
Token ID | 4472 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
proport | +0.310 |
suspic | +0.302 |
comr | +0.262 |
fortun | +0.250 |
stress | +0.232 |
Neg logit contributions | |
llah | -0.279 |
ible | -0.260 |
enegger | -0.258 |
IPM | -0.251 |
esters | -0.249 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
proport | +1.907 |
suspic | +1.864 |
comr | +1.637 |
fortun | +1.571 |
stress | +1.467 |
Neg logit contributions | |
llah | -1.430 |
ible | -1.319 |
enegger | -1.314 |
IPM | -1.275 |
esters | -1.261 |
Token | the |
Token ID | 262 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
llah | +0.113 |
ible | +0.105 |
enegger | +0.103 |
IPM | +0.101 |
esters | +0.100 |
Neg logit contributions | |
proport | -0.144 |
suspic | -0.140 |
comr | -0.123 |
fortun | -0.116 |
stress | -0.109 |
Token | British |
Token ID | 3517 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
llah | +0.470 |
ible | +0.434 |
enegger | +0.427 |
IPM | +0.417 |
esters | +0.409 |
Neg logit contributions | |
proport | -0.711 |
suspic | -0.692 |
comr | -0.613 |
fortun | -0.582 |
stress | -0.553 |
Token | crown |
Token ID | 12389 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
llah | +1.222 |
ible | +1.139 |
enegger | +1.121 |
IPM | +1.105 |
esters | +1.071 |
Neg logit contributions | |
proport | -1.631 |
suspic | -1.598 |
comr | -1.400 |
fortun | -1.334 |
stress | -1.255 |
Token | , |
Token ID | 11 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
llah | +1.906 |
ible | +1.793 |
enegger | +1.742 |
IPM | +1.702 |
osal | +1.665 |
Neg logit contributions | |
proport | -2.498 |
suspic | -2.446 |
comr | -2.127 |
fortun | -2.035 |
stress | -1.899 |
Token | to |
Token ID | 284 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
llah | +0.229 |
ible | +0.211 |
enegger | +0.209 |
IPM | +0.203 |
esters | +0.201 |
Neg logit contributions | |
proport | -0.327 |
suspic | -0.319 |
comr | -0.282 |
fortun | -0.269 |
stress | -0.253 |
Token | defeat |
Token ID | 7433 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
llah | +0.648 |
ible | +0.597 |
enegger | +0.591 |
IPM | +0.574 |
esters | +0.568 |
Neg logit contributions | |
proport | -0.900 |
suspic | -0.878 |
comr | -0.773 |
fortun | -0.741 |
stress | -0.693 |
Token | a |
Token ID | 257 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
llah | +0.624 |
ible | +0.579 |
enegger | +0.569 |
IPM | +0.557 |
esters | +0.548 |
Neg logit contributions | |
proport | -0.836 |
suspic | -0.811 |
comr | -0.716 |
fortun | -0.679 |
stress | -0.638 |
Token | greater |
Token ID | 3744 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
llah | +0.183 |
ible | +0.170 |
enegger | +0.166 |
IPM | +0.163 |
esters | +0.160 |
Neg logit contributions | |
proport | -0.255 |
suspic | -0.248 |
comr | -0.220 |
fortun | -0.208 |
stress | -0.197 |
Token | of |
Token ID | 286 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
llah | +1.347 |
ible | +1.250 |
enegger | +1.213 |
IPM | +1.190 |
esters | +1.188 |
Neg logit contributions | |
proport | -1.869 |
suspic | -1.836 |
comr | -1.595 |
fortun | -1.533 |
stress | -1.426 |
Token | the |
Token ID | 262 |
Feature activation | -5.34e-04 |
Pos logit contributions | |
llah | +0.025 |
ible | +0.023 |
enegger | +0.023 |
IPM | +0.023 |
esters | +0.023 |
Neg logit contributions | |
proport | -0.032 |
suspic | -0.031 |
comr | -0.027 |
fortun | -0.026 |
stress | -0.025 |
Token | D |
Token ID | 360 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
llah | +0.000 |
ible | +0.000 |
enegger | +0.000 |
IPM | +0.000 |
esters | +0.000 |
Neg logit contributions | |
proport | -0.001 |
suspic | -0.001 |
comr | -0.000 |
fortun | -0.000 |
stress | -0.000 |
Token | - |
Token ID | 12 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
llah | +0.287 |
ible | +0.268 |
enegger | +0.259 |
IPM | +0.256 |
esters | +0.255 |
Neg logit contributions | |
proport | -0.389 |
suspic | -0.380 |
comr | -0.332 |
fortun | -0.317 |
stress | -0.294 |
Token | Day |
Token ID | 12393 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
proport | +0.053 |
suspic | +0.053 |
comr | +0.046 |
fortun | +0.045 |
stress | +0.042 |
Neg logit contributions | |
llah | -0.030 |
ible | -0.028 |
enegger | -0.027 |
esters | -0.027 |
cible | -0.026 |
Token | land |
Token ID | 1956 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
llah | +0.348 |
ible | +0.319 |
IPM | +0.305 |
enegger | +0.299 |
esters | +0.295 |
Neg logit contributions | |
proport | -0.779 |
suspic | -0.766 |
comr | -0.687 |
fortun | -0.661 |
stress | -0.623 |
Token | ings |
Token ID | 654 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
llah | +1.897 |
ible | +1.762 |
osal | +1.542 |
cible | +1.536 |
esters | +1.496 |
Neg logit contributions | |
proport | -6.019 |
suspic | -5.987 |
comr | -5.458 |
fortun | -5.273 |
�� | -4.968 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
llah | +1.002 |
ible | +0.934 |
enegger | +0.912 |
IPM | +0.888 |
osal | +0.881 |
Neg logit contributions | |
proport | -1.528 |
suspic | -1.502 |
comr | -1.329 |
fortun | -1.270 |
stress | -1.181 |
Token |
|
Token ID | 198 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
proport | +0.103 |
suspic | +0.101 |
comr | +0.089 |
fortun | +0.085 |
stress | +0.079 |
Neg logit contributions | |
llah | -0.071 |
ible | -0.065 |
enegger | -0.065 |
IPM | -0.062 |
esters | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
llah | +0.384 |
enegger | +0.359 |
ible | +0.350 |
IPM | +0.342 |
esters | +0.341 |
Neg logit contributions | |
proport | -0.442 |
suspic | -0.431 |
comr | -0.377 |
fortun | -0.367 |
stress | -0.355 |
Token | The |
Token ID | 464 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
llah | +0.128 |
ible | +0.119 |
enegger | +0.118 |
IPM | +0.115 |
esters | +0.114 |
Neg logit contributions | |
proport | -0.164 |
suspic | -0.159 |
comr | -0.139 |
fortun | -0.133 |
stress | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
llah | +3.427 |
ible | +3.090 |
enegger | +2.968 |
cible | +2.885 |
osal | +2.878 |
Neg logit contributions | |
proport | -5.505 |
suspic | -5.451 |
comr | -4.854 |
fortun | -4.628 |
stress | -4.350 |
Token | Gh |
Token ID | 11972 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
llah | +0.198 |
ible | +0.182 |
enegger | +0.180 |
IPM | +0.175 |
esters | +0.173 |
Neg logit contributions | |
proport | -0.301 |
suspic | -0.294 |
comr | -0.260 |
fortun | -0.250 |
stress | -0.235 |
Token | out |
Token ID | 448 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
llah | +4.532 |
ible | +4.456 |
osal | +4.316 |
raq | +4.171 |
obic | +4.159 |
Neg logit contributions | |
proport | -5.807 |
suspic | -5.657 |
comr | -5.044 |
fortun | -4.682 |
�� | -4.304 |
Token | a |
Token ID | 64 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
proport | +0.230 |
suspic | +0.224 |
comr | +0.194 |
fortun | +0.185 |
stress | +0.172 |
Neg logit contributions | |
llah | -0.208 |
ible | -0.193 |
enegger | -0.192 |
IPM | -0.187 |
esters | -0.186 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
proport | +0.643 |
suspic | +0.629 |
comr | +0.554 |
fortun | +0.531 |
stress | +0.497 |
Neg logit contributions | |
llah | -0.454 |
ible | -0.417 |
enegger | -0.414 |
IPM | -0.401 |
esters | -0.397 |
Token | Damascus |
Token ID | 21028 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
llah | +0.332 |
ible | +0.305 |
enegger | +0.303 |
IPM | +0.293 |
esters | +0.290 |
Neg logit contributions | |
proport | -0.488 |
suspic | -0.477 |
comr | -0.421 |
fortun | -0.404 |
stress | -0.379 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
llah | +3.137 |
ible | +2.824 |
enegger | +2.753 |
IPM | +2.658 |
esters | +2.654 |
Neg logit contributions | |
proport | -4.993 |
suspic | -4.898 |
comr | -4.363 |
fortun | -4.173 |
stress | -3.918 |
Token | A |
Token ID | 317 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
llah | +0.324 |
ible | +0.297 |
enegger | +0.294 |
IPM | +0.285 |
esters | +0.281 |
Neg logit contributions | |
proport | -0.497 |
suspic | -0.487 |
comr | -0.430 |
fortun | -0.413 |
stress | -0.387 |
Token | by |
Token ID | 1525 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
llah | +0.721 |
ible | +0.663 |
enegger | +0.637 |
osal | +0.621 |
IPM | +0.620 |
Neg logit contributions | |
proport | -1.171 |
suspic | -1.154 |
comr | -1.021 |
fortun | -0.974 |
stress | -0.915 |
Token | an |
Token ID | 272 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
proport | +1.661 |
suspic | +1.618 |
comr | +1.399 |
fortun | +1.339 |
stress | +1.243 |
Neg logit contributions | |
llah | -1.525 |
enegger | -1.420 |
ible | -1.418 |
IPM | -1.384 |
esters | -1.364 |
Token | , |
Token ID | 11 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
llah | +0.217 |
ible | +0.199 |
enegger | +0.196 |
IPM | +0.190 |
esters | +0.188 |
Neg logit contributions | |
proport | -0.311 |
suspic | -0.304 |
comr | -0.269 |
fortun | -0.257 |
stress | -0.240 |
Token | ED |
Token ID | 1961 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
proport | +0.535 |
suspic | +0.521 |
comr | +0.456 |
fortun | +0.435 |
stress | +0.404 |
Neg logit contributions | |
llah | -0.428 |
ible | -0.397 |
enegger | -0.394 |
IPM | -0.383 |
esters | -0.379 |
Token | MON |
Token ID | 27857 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
proport | +0.090 |
suspic | +0.088 |
comr | +0.079 |
fortun | +0.076 |
stress | +0.071 |
Neg logit contributions | |
llah | -0.055 |
ible | -0.051 |
enegger | -0.050 |
IPM | -0.049 |
esters | -0.048 |
Token | TON |
Token ID | 11357 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
llah | +0.177 |
ible | +0.142 |
enegger | +0.140 |
IPM | +0.128 |
esters | +0.124 |
Neg logit contributions | |
proport | -0.856 |
suspic | -0.842 |
comr | -0.772 |
fortun | -0.750 |
stress | -0.718 |
Token | – |
Token ID | 784 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
llah | +2.076 |
ible | +1.944 |
enegger | +1.909 |
IPM | +1.882 |
esters | +1.833 |
Neg logit contributions | |
proport | -2.859 |
suspic | -2.799 |
comr | -2.458 |
fortun | -2.327 |
stress | -2.175 |
Token | Omar |
Token ID | 24980 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
proport | +0.440 |
suspic | +0.430 |
comr | +0.374 |
fortun | +0.357 |
stress | +0.331 |
Neg logit contributions | |
llah | -0.370 |
ible | -0.344 |
enegger | -0.342 |
IPM | -0.333 |
esters | -0.329 |
Token | Kh |
Token ID | 5311 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
llah | +1.165 |
ible | +1.073 |
enegger | +1.035 |
IPM | +1.006 |
osal | +1.006 |
Neg logit contributions | |
proport | -1.784 |
suspic | -1.762 |
comr | -1.548 |
fortun | -1.485 |
stress | -1.394 |
Token | adr |
Token ID | 41909 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
llah | +3.294 |
ible | +3.179 |
obic | +2.947 |
osal | +2.917 |
enegger | +2.911 |
Neg logit contributions | |
proport | -4.506 |
suspic | -4.406 |
comr | -3.886 |
fortun | -3.612 |
�� | -3.327 |
Token | has |
Token ID | 468 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
llah | +2.980 |
ible | +2.747 |
enegger | +2.714 |
IPM | +2.613 |
esters | +2.592 |
Neg logit contributions | |
proport | -4.459 |
suspic | -4.321 |
comr | -3.851 |
fortun | -3.638 |
�� | -3.451 |
Token | agreed |
Token ID | 4987 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
proport | +0.372 |
suspic | +0.363 |
comr | +0.318 |
fortun | +0.304 |
stress | +0.284 |
Neg logit contributions | |
llah | -0.285 |
ible | -0.263 |
enegger | -0.262 |
IPM | -0.254 |
esters | -0.251 |
Token | to |
Token ID | 284 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
llah | +0.703 |
ible | +0.651 |
enegger | +0.632 |
IPM | +0.613 |
esters | +0.605 |
Neg logit contributions | |
proport | -1.182 |
suspic | -1.153 |
comr | -1.022 |
fortun | -0.986 |
stress | -0.925 |
Token | remain |
Token ID | 3520 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
llah | +0.209 |
ible | +0.194 |
enegger | +0.192 |
IPM | +0.187 |
esters | +0.185 |
Neg logit contributions | |
proport | -0.271 |
suspic | -0.265 |
comr | -0.232 |
fortun | -0.222 |
stress | -0.207 |
Token | athing |
Token ID | 26927 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
llah | +0.057 |
ible | +0.053 |
enegger | +0.053 |
IPM | +0.051 |
esters | +0.051 |
Neg logit contributions | |
proport | -0.062 |
suspic | -0.061 |
comr | -0.052 |
fortun | -0.050 |
stress | -0.046 |
Token | system |
Token ID | 1080 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
llah | +0.942 |
ible | +0.870 |
enegger | +0.853 |
IPM | +0.836 |
osal | +0.827 |
Neg logit contributions | |
proport | -1.250 |
suspic | -1.224 |
comr | -1.075 |
fortun | -1.030 |
stress | -0.962 |
Token | used |
Token ID | 973 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
llah | +0.329 |
ible | +0.303 |
enegger | +0.300 |
IPM | +0.292 |
esters | +0.288 |
Neg logit contributions | |
proport | -0.463 |
suspic | -0.453 |
comr | -0.399 |
fortun | -0.383 |
stress | -0.358 |
Token | by |
Token ID | 416 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
proport | +0.766 |
suspic | +0.748 |
comr | +0.653 |
fortun | +0.625 |
stress | +0.582 |
Neg logit contributions | |
llah | -0.619 |
ible | -0.573 |
enegger | -0.570 |
IPM | -0.554 |
esters | -0.548 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
proport | +1.076 |
suspic | +1.050 |
comr | +0.920 |
fortun | +0.881 |
stress | +0.822 |
Neg logit contributions | |
llah | -0.831 |
ible | -0.768 |
enegger | -0.763 |
IPM | -0.741 |
esters | -0.733 |
Token | Mau |
Token ID | 28931 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
llah | +0.200 |
ible | +0.185 |
enegger | +0.183 |
IPM | +0.179 |
esters | +0.176 |
Neg logit contributions | |
proport | -0.272 |
suspic | -0.265 |
comr | -0.233 |
fortun | -0.223 |
stress | -0.210 |
Token | Mau |
Token ID | 28931 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
llah | +1.845 |
ible | +1.518 |
IPM | +1.441 |
esters | +1.347 |
osal | +1.315 |
Neg logit contributions | |
proport | -6.719 |
suspic | -6.650 |
comr | -6.068 |
fortun | -5.926 |
stress | -5.684 |
Token | , |
Token ID | 11 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
llah | +3.519 |
ible | +3.198 |
IPM | +3.080 |
enegger | +3.077 |
esters | +3.054 |
Neg logit contributions | |
proport | -5.509 |
suspic | -5.460 |
comr | -4.843 |
fortun | -4.645 |
stress | -4.355 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
llah | +0.258 |
ible | +0.237 |
enegger | +0.235 |
IPM | +0.228 |
esters | +0.226 |
Neg logit contributions | |
proport | -0.372 |
suspic | -0.363 |
comr | -0.320 |
fortun | -0.307 |
stress | -0.288 |
Token | denied |
Token ID | 6699 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
llah | +0.283 |
ible | +0.261 |
enegger | +0.258 |
IPM | +0.251 |
esters | +0.248 |
Neg logit contributions | |
proport | -0.405 |
suspic | -0.396 |
comr | -0.349 |
fortun | -0.334 |
stress | -0.314 |
Token | having |
Token ID | 1719 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
llah | +0.701 |
ible | +0.650 |
enegger | +0.635 |
IPM | +0.627 |
esters | +0.618 |
Neg logit contributions | |
proport | -0.917 |
suspic | -0.895 |
comr | -0.788 |
fortun | -0.750 |
stress | -0.708 |
Token |
|
Token ID | 198 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
llah | +0.478 |
ible | +0.443 |
enegger | +0.438 |
IPM | +0.427 |
esters | +0.421 |
Neg logit contributions | |
proport | -0.629 |
suspic | -0.615 |
comr | -0.539 |
fortun | -0.514 |
stress | -0.478 |
Token |
|
Token ID | 198 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
llah | +0.595 |
enegger | +0.556 |
ible | +0.543 |
IPM | +0.531 |
esters | +0.529 |
Neg logit contributions | |
proport | -0.691 |
suspic | -0.675 |
comr | -0.589 |
fortun | -0.574 |
stress | -0.553 |
Token | @ |
Token ID | 31 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
llah | +0.306 |
ible | +0.283 |
enegger | +0.281 |
IPM | +0.273 |
esters | +0.270 |
Neg logit contributions | |
proport | -0.388 |
suspic | -0.378 |
comr | -0.331 |
fortun | -0.316 |
stress | -0.295 |
Token | Ann |
Token ID | 18858 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
llah | +0.848 |
ible | +0.783 |
enegger | +0.767 |
IPM | +0.752 |
esters | +0.744 |
Neg logit contributions | |
proport | -1.152 |
suspic | -1.121 |
comr | -0.983 |
fortun | -0.941 |
stress | -0.872 |
Token | C |
Token ID | 34 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
proport | +1.138 |
suspic | +1.111 |
comr | +0.971 |
fortun | +0.928 |
stress | +0.864 |
Neg logit contributions | |
llah | -0.906 |
ible | -0.839 |
enegger | -0.833 |
IPM | -0.809 |
esters | -0.802 |
Token | oul |
Token ID | 2852 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
llah | +0.543 |
ible | +0.504 |
enegger | +0.499 |
IPM | +0.484 |
esters | +0.482 |
Neg logit contributions | |
proport | -0.653 |
suspic | -0.636 |
comr | -0.555 |
fortun | -0.530 |
stress | -0.491 |
Token | ter |
Token ID | 353 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
llah | +3.729 |
ible | +3.546 |
enegger | +3.425 |
esters | +3.417 |
osal | +3.364 |
Neg logit contributions | |
proport | -3.914 |
suspic | -3.788 |
comr | -3.326 |
fortun | -3.078 |
�� | -2.826 |
Token | HAVE |
Token ID | 21515 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
llah | +0.771 |
ible | +0.713 |
enegger | +0.709 |
IPM | +0.685 |
esters | +0.678 |
Neg logit contributions | |
proport | -1.040 |
suspic | -1.014 |
comr | -0.891 |
fortun | -0.848 |
stress | -0.791 |
Token | YOU |
Token ID | 7013 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
llah | +0.728 |
ible | +0.670 |
enegger | +0.665 |
IPM | +0.647 |
esters | +0.637 |
Neg logit contributions | |
proport | -0.998 |
suspic | -0.975 |
comr | -0.857 |
fortun | -0.821 |
stress | -0.768 |
Token | SE |
Token ID | 7946 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
proport | +0.467 |
suspic | +0.457 |
comr | +0.405 |
fortun | +0.389 |
stress | +0.365 |
Neg logit contributions | |
llah | -0.300 |
ible | -0.274 |
enegger | -0.272 |
IPM | -0.263 |
esters | -0.261 |
Token | EN |
Token ID | 1677 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
llah | +0.525 |
ible | +0.474 |
enegger | +0.465 |
IPM | +0.454 |
osal | +0.440 |
Neg logit contributions | |
proport | -1.053 |
suspic | -1.034 |
comr | -0.926 |
fortun | -0.890 |
stress | -0.843 |