Token | stance |
Token ID | 12046 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
rahim | +0.860 |
enhagen | +0.781 |
aho | +0.771 |
agara | +0.723 |
ertodd | +0.709 |
Neg logit contributions | |
� | -0.582 |
arium | -0.566 |
� | -0.548 |
之 | -0.548 |
Seymour | -0.532 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
rahim | +0.348 |
enhagen | +0.318 |
aho | +0.315 |
agara | +0.292 |
ertodd | +0.288 |
Neg logit contributions | |
� | -0.250 |
arium | -0.241 |
� | -0.235 |
之 | -0.233 |
Seymour | -0.227 |
Token |
|
Token ID | 198 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
rahim | +0.629 |
enhagen | +0.572 |
aho | +0.567 |
agara | +0.526 |
ertodd | +0.524 |
Neg logit contributions | |
� | -0.420 |
arium | -0.409 |
� | -0.397 |
之 | -0.393 |
Seymour | -0.382 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
rahim | +0.276 |
aho | +0.249 |
enhagen | +0.245 |
agara | +0.231 |
ertodd | +0.230 |
Neg logit contributions | |
� | -0.189 |
arium | -0.184 |
� | -0.179 |
之 | -0.178 |
Seymour | -0.174 |
Token | F |
Token ID | 37 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
rahim | +0.300 |
aho | +0.268 |
enhagen | +0.263 |
agara | +0.244 |
ertodd | +0.239 |
Neg logit contributions | |
� | -0.254 |
arium | -0.252 |
Seymour | -0.244 |
� | -0.242 |
之 | -0.241 |
Token | ears |
Token ID | 4127 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
� | +0.135 |
arium | +0.132 |
� | +0.128 |
之 | +0.127 |
Seymour | +0.126 |
Neg logit contributions | |
rahim | -0.188 |
enhagen | -0.171 |
aho | -0.169 |
agara | -0.158 |
ertodd | -0.156 |
Token | that |
Token ID | 326 |
Feature activation | +1.80e-04 |
Pos logit contributions | |
rahim | +3.564 |
enhagen | +3.272 |
aho | +3.244 |
agara | +2.982 |
ertodd | +2.885 |
Neg logit contributions | |
� | -2.771 |
arium | -2.647 |
� | -2.627 |
之 | -2.625 |
Seymour | -2.529 |
Token | Bruce |
Token ID | 11088 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
rahim | +0.001 |
enhagen | +0.001 |
aho | +0.001 |
agara | +0.001 |
ertodd | +0.001 |
Neg logit contributions | |
� | -0.000 |
arium | -0.000 |
� | -0.000 |
之 | -0.000 |
Seymour | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
rahim | +0.082 |
enhagen | +0.075 |
aho | +0.074 |
agara | +0.069 |
ertodd | +0.068 |
Neg logit contributions | |
� | -0.051 |
arium | -0.050 |
� | -0.048 |
之 | -0.048 |
Seymour | -0.047 |
Token | require |
Token ID | 2421 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
� | +0.092 |
arium | +0.090 |
� | +0.088 |
之 | +0.087 |
Seymour | +0.085 |
Neg logit contributions | |
rahim | -0.120 |
enhagen | -0.108 |
aho | -0.108 |
agara | -0.100 |
ertodd | -0.099 |
Token | post |
Token ID | 1281 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
� | +0.121 |
arium | +0.118 |
� | +0.116 |
之 | +0.114 |
Seymour | +0.112 |
Neg logit contributions | |
rahim | -0.180 |
enhagen | -0.164 |
aho | -0.162 |
agara | -0.153 |
ertodd | -0.151 |
Token | serves |
Token ID | 9179 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
rahim | +0.278 |
enhagen | +0.250 |
aho | +0.248 |
agara | +0.232 |
ertodd | +0.227 |
Neg logit contributions | |
� | -0.217 |
arium | -0.212 |
� | -0.207 |
之 | -0.206 |
Seymour | -0.200 |
Token | as |
Token ID | 355 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
rahim | +0.335 |
enhagen | +0.305 |
aho | +0.298 |
agara | +0.278 |
ertodd | +0.278 |
Neg logit contributions | |
� | -0.260 |
arium | -0.254 |
� | -0.246 |
之 | -0.245 |
Seymour | -0.238 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
rahim | +0.153 |
enhagen | +0.140 |
aho | +0.139 |
agara | +0.130 |
ertodd | +0.125 |
Neg logit contributions | |
� | -0.100 |
arium | -0.100 |
� | -0.097 |
之 | -0.096 |
Schwarzenegger | -0.091 |
Token | U |
Token ID | 471 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rahim | +0.415 |
enhagen | +0.380 |
aho | +0.379 |
agara | +0.353 |
ertodd | +0.344 |
Neg logit contributions | |
� | -0.239 |
arium | -0.238 |
� | -0.228 |
之 | -0.228 |
Seymour | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
rahim | +0.507 |
aho | +0.459 |
enhagen | +0.457 |
agara | +0.428 |
ertodd | +0.424 |
Neg logit contributions | |
� | -0.326 |
arium | -0.320 |
� | -0.310 |
之 | -0.310 |
Seymour | -0.303 |
Token | N |
Token ID | 45 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
rahim | +0.717 |
enhagen | +0.652 |
aho | +0.641 |
agara | +0.605 |
ertodd | +0.597 |
Neg logit contributions | |
arium | -0.467 |
� | -0.467 |
之 | -0.448 |
� | -0.447 |
Seymour | -0.433 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
rahim | +3.085 |
aho | +2.786 |
enhagen | +2.769 |
agara | +2.598 |
ertodd | +2.547 |
Neg logit contributions | |
� | -2.298 |
arium | -2.233 |
之 | -2.202 |
� | -2.186 |
Schwarzenegger | -2.118 |
Token | " |
Token ID | 366 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
rahim | +1.527 |
aho | +1.383 |
enhagen | +1.374 |
agara | +1.274 |
ertodd | +1.229 |
Neg logit contributions | |
� | -1.061 |
arium | -1.058 |
之 | -1.028 |
� | -1.018 |
Schwarzenegger | -0.979 |
Token | special |
Token ID | 20887 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
rahim | +0.709 |
aho | +0.635 |
enhagen | +0.629 |
agara | +0.587 |
circle | +0.563 |
Neg logit contributions | |
� | -0.517 |
arium | -0.517 |
之 | -0.498 |
Schwarzenegger | -0.493 |
Seymour | -0.493 |
Token | rapport |
Token ID | 49498 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
rahim | +0.170 |
aho | +0.156 |
enhagen | +0.156 |
agara | +0.146 |
ertodd | +0.142 |
Neg logit contributions | |
� | -0.102 |
arium | -0.099 |
之 | -0.097 |
� | -0.096 |
Seymour | -0.093 |
Token | eur |
Token ID | 23365 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
rahim | +0.009 |
enhagen | +0.009 |
aho | +0.008 |
agara | +0.008 |
ertodd | +0.008 |
Neg logit contributions | |
� | -0.006 |
arium | -0.006 |
之 | -0.006 |
� | -0.006 |
Schwarzenegger | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
� | +0.034 |
arium | +0.034 |
� | +0.032 |
之 | +0.032 |
Seymour | +0.031 |
Neg logit contributions | |
rahim | -0.046 |
enhagen | -0.042 |
aho | -0.041 |
ertodd | -0.038 |
agara | -0.038 |
Token | � |
Token ID | 251 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
� | +0.462 |
arium | +0.457 |
之 | +0.440 |
� | +0.436 |
Seymour | +0.435 |
Neg logit contributions | |
rahim | -0.663 |
enhagen | -0.601 |
aho | -0.598 |
agara | -0.560 |
ertodd | -0.556 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
� | +0.086 |
arium | +0.085 |
� | +0.081 |
之 | +0.081 |
Seymour | +0.080 |
Neg logit contributions | |
rahim | -0.114 |
enhagen | -0.103 |
aho | -0.102 |
ertodd | -0.095 |
agara | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
� | +0.438 |
arium | +0.429 |
� | +0.415 |
之 | +0.413 |
Seymour | +0.405 |
Neg logit contributions | |
rahim | -0.685 |
enhagen | -0.619 |
aho | -0.619 |
agara | -0.578 |
ertodd | -0.576 |
Token | F |
Token ID | 37 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
� | +0.340 |
arium | +0.339 |
之 | +0.325 |
Seymour | +0.324 |
� | +0.324 |
Neg logit contributions | |
rahim | -0.399 |
enhagen | -0.354 |
aho | -0.353 |
agara | -0.325 |
ertodd | -0.323 |
Token | ears |
Token ID | 4127 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
� | +0.291 |
arium | +0.285 |
� | +0.277 |
之 | +0.276 |
Seymour | +0.274 |
Neg logit contributions | |
rahim | -0.358 |
enhagen | -0.324 |
aho | -0.320 |
agara | -0.297 |
ertodd | -0.295 |
Token | over |
Token ID | 625 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
rahim | +3.140 |
enhagen | +2.872 |
aho | +2.815 |
agara | +2.587 |
ertodd | +2.537 |
Neg logit contributions | |
� | -2.282 |
arium | -2.212 |
之 | -2.170 |
� | -2.155 |
Seymour | -2.124 |
Token | Melbourne |
Token ID | 14819 |
Feature activation | -3.46e-04 |
Pos logit contributions | |
rahim | +0.203 |
enhagen | +0.184 |
aho | +0.180 |
agara | +0.169 |
ertodd | +0.166 |
Neg logit contributions | |
� | -0.145 |
arium | -0.145 |
� | -0.138 |
之 | -0.137 |
Seymour | -0.134 |
Token | fixes |
Token ID | 13040 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
� | +0.001 |
arium | +0.001 |
之 | +0.001 |
� | +0.001 |
Seymour | +0.001 |
Neg logit contributions | |
rahim | -0.001 |
enhagen | -0.001 |
aho | -0.001 |
agara | -0.001 |
ertodd | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
� | +0.489 |
arium | +0.484 |
� | +0.463 |
之 | +0.462 |
Seymour | +0.453 |
Neg logit contributions | |
rahim | -0.714 |
enhagen | -0.656 |
aho | -0.645 |
agara | -0.603 |
ertodd | -0.594 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
� | +0.252 |
arium | +0.248 |
� | +0.239 |
之 | +0.238 |
Seymour | +0.233 |
Neg logit contributions | |
rahim | -0.394 |
enhagen | -0.356 |
aho | -0.356 |
agara | -0.333 |
ertodd | -0.331 |
Token | girls |
Token ID | 4813 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
� | +0.142 |
arium | +0.141 |
� | +0.134 |
之 | +0.134 |
Seymour | +0.131 |
Neg logit contributions | |
rahim | -0.208 |
aho | -0.189 |
enhagen | -0.188 |
agara | -0.176 |
ertodd | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
rahim | +0.209 |
enhagen | +0.191 |
aho | +0.190 |
agara | +0.179 |
ertodd | +0.176 |
Neg logit contributions | |
� | -0.132 |
arium | -0.130 |
� | -0.125 |
之 | -0.124 |
Seymour | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
rahim | +0.108 |
enhagen | +0.098 |
aho | +0.098 |
agara | +0.091 |
ertodd | +0.090 |
Neg logit contributions | |
� | -0.075 |
arium | -0.074 |
� | -0.072 |
之 | -0.071 |
Seymour | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
rahim | +0.146 |
aho | +0.132 |
enhagen | +0.131 |
agara | +0.123 |
ertodd | +0.122 |
Neg logit contributions | |
� | -0.096 |
arium | -0.094 |
� | -0.091 |
之 | -0.090 |
Seymour | -0.089 |
Token | N |
Token ID | 45 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
rahim | +0.174 |
aho | +0.156 |
enhagen | +0.153 |
agara | +0.142 |
ertodd | +0.140 |
Neg logit contributions | |
� | -0.172 |
arium | -0.172 |
Seymour | -0.166 |
之 | -0.166 |
� | -0.166 |
Token | om |
Token ID | 296 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
rahim | +0.668 |
aho | +0.608 |
enhagen | +0.597 |
agara | +0.567 |
ertodd | +0.554 |
Neg logit contributions | |
� | -0.508 |
arium | -0.492 |
之 | -0.489 |
� | -0.483 |
Seymour | -0.476 |
Token | inate |
Token ID | 4559 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
rahim | +3.183 |
aho | +2.958 |
enhagen | +2.889 |
agara | +2.726 |
endas | +2.687 |
Neg logit contributions | |
� | -2.128 |
� | -1.999 |
之 | -1.991 |
arium | -1.937 |
Seymour | -1.923 |
Token | an |
Token ID | 281 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
rahim | +0.893 |
enhagen | +0.814 |
aho | +0.812 |
agara | +0.753 |
ertodd | +0.741 |
Neg logit contributions | |
� | -0.667 |
arium | -0.648 |
� | -0.640 |
之 | -0.640 |
Schwarzenegger | -0.608 |
Token | exceptional |
Token ID | 15313 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
rahim | +0.115 |
aho | +0.105 |
enhagen | +0.105 |
agara | +0.097 |
ertodd | +0.095 |
Neg logit contributions | |
� | -0.089 |
arium | -0.087 |
之 | -0.085 |
� | -0.085 |
Schwarzenegger | -0.081 |
Token | Peace |
Token ID | 12689 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
rahim | +0.104 |
aho | +0.095 |
enhagen | +0.094 |
agara | +0.089 |
ertodd | +0.087 |
Neg logit contributions | |
� | -0.072 |
arium | -0.070 |
� | -0.069 |
之 | -0.068 |
Seymour | -0.065 |
Token | Corps |
Token ID | 12778 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
� | +0.317 |
arium | +0.310 |
� | +0.299 |
之 | +0.299 |
Seymour | +0.290 |
Neg logit contributions | |
rahim | -0.511 |
enhagen | -0.467 |
aho | -0.466 |
agara | -0.436 |
ertodd | -0.435 |
Token | has |
Token ID | 468 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
rahim | +0.418 |
enhagen | +0.378 |
aho | +0.375 |
agara | +0.350 |
ertodd | +0.342 |
Neg logit contributions | |
� | -0.316 |
arium | -0.306 |
� | -0.302 |
之 | -0.300 |
Seymour | -0.289 |
Token | held |
Token ID | 2714 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
� | +0.072 |
arium | +0.071 |
� | +0.070 |
之 | +0.069 |
Seymour | +0.067 |
Neg logit contributions | |
rahim | -0.083 |
enhagen | -0.074 |
aho | -0.073 |
agara | -0.068 |
ertodd | -0.067 |
Token | his |
Token ID | 465 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
� | +0.042 |
arium | +0.041 |
� | +0.040 |
之 | +0.040 |
Seymour | +0.038 |
Neg logit contributions | |
rahim | -0.055 |
enhagen | -0.050 |
aho | -0.049 |
agara | -0.046 |
ertodd | -0.046 |
Token | U |
Token ID | 471 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
rahim | +0.459 |
enhagen | +0.418 |
aho | +0.412 |
agara | +0.383 |
ertodd | +0.379 |
Neg logit contributions | |
� | -0.356 |
arium | -0.350 |
� | -0.340 |
之 | -0.338 |
Seymour | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
rahim | +0.104 |
enhagen | +0.094 |
aho | +0.094 |
agara | +0.088 |
ertodd | +0.087 |
Neg logit contributions | |
� | -0.065 |
arium | -0.064 |
� | -0.062 |
之 | -0.062 |
Seymour | -0.061 |
Token | N |
Token ID | 45 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
rahim | +0.899 |
enhagen | +0.827 |
aho | +0.812 |
agara | +0.767 |
ertodd | +0.761 |
Neg logit contributions | |
� | -0.567 |
arium | -0.558 |
之 | -0.541 |
� | -0.540 |
Seymour | -0.523 |
Token | . |
Token ID | 13 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
rahim | +2.951 |
aho | +2.646 |
enhagen | +2.638 |
ertodd | +2.496 |
agara | +2.466 |
Neg logit contributions | |
� | -2.249 |
arium | -2.162 |
之 | -2.132 |
� | -2.132 |
Seymour | -2.129 |
Token | post |
Token ID | 1281 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
rahim | +1.718 |
enhagen | +1.541 |
aho | +1.535 |
agara | +1.419 |
ertodd | +1.401 |
Neg logit contributions | |
� | -1.395 |
arium | -1.372 |
之 | -1.355 |
� | -1.346 |
Seymour | -1.320 |
Token | for |
Token ID | 329 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
rahim | +0.975 |
enhagen | +0.890 |
aho | +0.875 |
agara | +0.811 |
ertodd | +0.806 |
Neg logit contributions | |
� | -0.727 |
arium | -0.692 |
之 | -0.683 |
� | -0.682 |
Seymour | -0.667 |
Token | three |
Token ID | 1115 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
rahim | +0.902 |
enhagen | +0.828 |
aho | +0.812 |
agara | +0.757 |
ertodd | +0.730 |
Neg logit contributions | |
� | -0.751 |
arium | -0.728 |
� | -0.720 |
之 | -0.712 |
Seymour | -0.676 |
Token | years |
Token ID | 812 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
rahim | +0.367 |
enhagen | +0.337 |
aho | +0.335 |
agara | +0.312 |
ertodd | +0.309 |
Neg logit contributions | |
� | -0.254 |
arium | -0.248 |
� | -0.241 |
之 | -0.241 |
Seymour | -0.233 |
Token | path |
Token ID | 3108 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
� | +0.039 |
arium | +0.038 |
� | +0.037 |
之 | +0.037 |
Seymour | +0.036 |
Neg logit contributions | |
rahim | -0.053 |
enhagen | -0.048 |
aho | -0.047 |
agara | -0.044 |
ertodd | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
� | +0.204 |
arium | +0.198 |
� | +0.194 |
之 | +0.193 |
Seymour | +0.188 |
Neg logit contributions | |
rahim | -0.304 |
enhagen | -0.279 |
aho | -0.275 |
agara | -0.256 |
ertodd | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
� | +0.190 |
arium | +0.184 |
� | +0.180 |
之 | +0.180 |
Seymour | +0.173 |
Neg logit contributions | |
rahim | -0.280 |
aho | -0.254 |
enhagen | -0.254 |
ertodd | -0.236 |
agara | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
� | +0.053 |
arium | +0.052 |
� | +0.051 |
之 | +0.050 |
Seymour | +0.049 |
Neg logit contributions | |
rahim | -0.081 |
aho | -0.073 |
enhagen | -0.072 |
agara | -0.068 |
ertodd | -0.067 |
Token | PO |
Token ID | 16402 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
rahim | +0.038 |
aho | +0.034 |
enhagen | +0.033 |
agara | +0.031 |
ertodd | +0.030 |
Neg logit contributions | |
� | -0.032 |
arium | -0.031 |
Seymour | -0.030 |
之 | -0.030 |
� | -0.030 |
Token | LL |
Token ID | 3069 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
rahim | +0.929 |
enhagen | +0.864 |
aho | +0.841 |
agara | +0.793 |
ertodd | +0.788 |
Neg logit contributions | |
� | -0.470 |
arium | -0.467 |
� | -0.444 |
之 | -0.443 |
Seymour | -0.434 |
Token | : |
Token ID | 25 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
rahim | +2.410 |
aho | +2.195 |
enhagen | +2.148 |
agara | +1.913 |
ertodd | +1.868 |
Neg logit contributions | |
arium | -2.464 |
� | -2.423 |
之 | -2.321 |
� | -2.320 |
Nguyen | -2.262 |
Token | Have |
Token ID | 11980 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
� | +0.781 |
arium | +0.769 |
� | +0.746 |
之 | +0.744 |
Seymour | +0.729 |
Neg logit contributions | |
rahim | -0.912 |
enhagen | -0.822 |
aho | -0.812 |
agara | -0.755 |
ertodd | -0.750 |
Token | you |
Token ID | 345 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
� | +0.196 |
arium | +0.191 |
之 | +0.189 |
� | +0.186 |
Seymour | +0.179 |
Neg logit contributions | |
rahim | -0.273 |
enhagen | -0.251 |
aho | -0.249 |
agara | -0.233 |
ertodd | -0.227 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
� | +0.862 |
arium | +0.846 |
� | +0.819 |
之 | +0.816 |
Seymour | +0.797 |
Neg logit contributions | |
rahim | -1.260 |
enhagen | -1.149 |
aho | -1.136 |
agara | -1.064 |
ertodd | -1.058 |
Token | Pokemon |
Token ID | 14878 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
� | +0.067 |
arium | +0.066 |
� | +0.064 |
之 | +0.064 |
Seymour | +0.062 |
Neg logit contributions | |
rahim | -0.102 |
enhagen | -0.094 |
aho | -0.092 |
agara | -0.086 |
ertodd | -0.086 |
Token | two |
Token ID | 734 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
� | +0.023 |
arium | +0.023 |
� | +0.022 |
之 | +0.022 |
Seymour | +0.021 |
Neg logit contributions | |
rahim | -0.028 |
enhagen | -0.026 |
aho | -0.025 |
agara | -0.024 |
ertodd | -0.023 |
Token | ? |
Token ID | 30 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
� | +0.205 |
arium | +0.200 |
� | +0.194 |
之 | +0.194 |
Seymour | +0.188 |
Neg logit contributions | |
rahim | -0.279 |
enhagen | -0.253 |
aho | -0.250 |
agara | -0.234 |
ertodd | -0.231 |
Token |
|
Token ID | 198 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
rahim | +0.213 |
enhagen | +0.191 |
aho | +0.191 |
ertodd | +0.178 |
agara | +0.176 |
Neg logit contributions | |
� | -0.150 |
arium | -0.147 |
� | -0.142 |
之 | -0.142 |
Seymour | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
� | +0.190 |
arium | +0.186 |
� | +0.181 |
之 | +0.180 |
Seymour | +0.176 |
Neg logit contributions | |
rahim | -0.288 |
aho | -0.260 |
enhagen | -0.258 |
agara | -0.242 |
ertodd | -0.241 |
Token | T |
Token ID | 51 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
arium | +0.196 |
� | +0.196 |
Seymour | +0.188 |
之 | +0.187 |
Nguyen | +0.186 |
Neg logit contributions | |
rahim | -0.301 |
aho | -0.272 |
enhagen | -0.268 |
agara | -0.250 |
ertodd | -0.249 |
Token | OM |
Token ID | 2662 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
rahim | +1.048 |
aho | +0.960 |
enhagen | +0.959 |
ertodd | +0.902 |
agara | +0.898 |
Neg logit contributions | |
� | -0.472 |
arium | -0.447 |
之 | -0.438 |
� | -0.434 |
Seymour | -0.431 |
Token | KING |
Token ID | 32957 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
rahim | +3.037 |
aho | +2.822 |
enhagen | +2.770 |
ertodd | +2.564 |
MPG | +2.523 |
Neg logit contributions | |
arium | -1.728 |
� | -1.662 |
� | -1.598 |
cens | -1.595 |
之 | -1.562 |
Token | : |
Token ID | 25 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
� | +0.059 |
arium | +0.058 |
� | +0.056 |
之 | +0.056 |
Seymour | +0.055 |
Neg logit contributions | |
rahim | -0.065 |
enhagen | -0.059 |
aho | -0.058 |
ertodd | -0.054 |
agara | -0.053 |
Token | Well |
Token ID | 3894 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
� | +0.975 |
arium | +0.959 |
� | +0.929 |
之 | +0.925 |
Seymour | +0.901 |
Neg logit contributions | |
rahim | -1.310 |
enhagen | -1.189 |
aho | -1.175 |
agara | -1.095 |
ertodd | -1.091 |
Token | , |
Token ID | 11 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
� | +1.392 |
arium | +1.361 |
� | +1.320 |
之 | +1.313 |
Seymour | +1.267 |
Neg logit contributions | |
rahim | -2.122 |
enhagen | -1.946 |
aho | -1.916 |
agara | -1.791 |
ertodd | -1.784 |
Token | that |
Token ID | 326 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
� | +0.283 |
arium | +0.275 |
� | +0.269 |
之 | +0.268 |
Seymour | +0.254 |
Neg logit contributions | |
rahim | -0.357 |
enhagen | -0.325 |
aho | -0.320 |
agara | -0.297 |
ertodd | -0.295 |
Token | ism |
Token ID | 1042 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
� | +0.075 |
arium | +0.072 |
� | +0.072 |
之 | +0.071 |
Seymour | +0.070 |
Neg logit contributions | |
rahim | -0.105 |
aho | -0.096 |
enhagen | -0.095 |
agara | -0.089 |
ertodd | -0.088 |
Token | was |
Token ID | 373 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
rahim | +0.972 |
enhagen | +0.887 |
aho | +0.881 |
agara | +0.827 |
ertodd | +0.813 |
Neg logit contributions | |
� | -0.641 |
arium | -0.620 |
� | -0.604 |
之 | -0.596 |
Seymour | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
rahim | +0.395 |
enhagen | +0.360 |
aho | +0.355 |
agara | +0.335 |
ertodd | +0.327 |
Neg logit contributions | |
� | -0.270 |
arium | -0.265 |
� | -0.256 |
之 | -0.255 |
Seymour | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
� | +0.425 |
arium | +0.417 |
� | +0.402 |
之 | +0.400 |
Seymour | +0.394 |
Neg logit contributions | |
rahim | -0.683 |
enhagen | -0.621 |
aho | -0.617 |
agara | -0.579 |
ertodd | -0.575 |
Token | n |
Token ID | 77 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
� | +0.186 |
arium | +0.184 |
� | +0.176 |
之 | +0.176 |
Seymour | +0.176 |
Neg logit contributions | |
rahim | -0.255 |
enhagen | -0.231 |
aho | -0.229 |
agara | -0.214 |
ertodd | -0.209 |
Token | our |
Token ID | 454 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
rahim | +0.029 |
aho | +0.026 |
enhagen | +0.026 |
agara | +0.024 |
ertodd | +0.024 |
Neg logit contributions | |
� | -0.024 |
arium | -0.023 |
� | -0.023 |
之 | -0.023 |
Seymour | -0.022 |
Token | ished |
Token ID | 1348 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
rahim | +3.180 |
aho | +2.852 |
enhagen | +2.846 |
agara | +2.726 |
ertodd | +2.640 |
Neg logit contributions | |
� | -1.636 |
arium | -1.586 |
� | -1.571 |
之 | -1.547 |
Seymour | -1.504 |
Token | by |
Token ID | 416 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
rahim | +0.478 |
enhagen | +0.434 |
aho | +0.430 |
agara | +0.405 |
ertodd | +0.396 |
Neg logit contributions | |
� | -0.341 |
arium | -0.335 |
� | -0.323 |
之 | -0.321 |
Seymour | -0.317 |
Token | the |
Token ID | 262 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
� | +0.119 |
arium | +0.117 |
之 | +0.113 |
� | +0.113 |
Seymour | +0.109 |
Neg logit contributions | |
rahim | -0.166 |
enhagen | -0.151 |
aho | -0.149 |
agara | -0.141 |
ertodd | -0.136 |
Token | realities |
Token ID | 22072 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
� | +0.117 |
arium | +0.116 |
之 | +0.111 |
� | +0.111 |
Seymour | +0.108 |
Neg logit contributions | |
rahim | -0.159 |
enhagen | -0.145 |
aho | -0.143 |
agara | -0.134 |
ertodd | -0.132 |
Token | of |
Token ID | 286 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
� | +0.115 |
arium | +0.112 |
� | +0.109 |
之 | +0.109 |
Seymour | +0.106 |
Neg logit contributions | |
rahim | -0.175 |
enhagen | -0.160 |
aho | -0.159 |
agara | -0.149 |
ertodd | -0.145 |
Token | African |
Token ID | 5510 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
rahim | +0.933 |
aho | +0.851 |
enhagen | +0.838 |
agara | +0.796 |
ertodd | +0.766 |
Neg logit contributions | |
� | -0.617 |
arium | -0.603 |
� | -0.581 |
之 | -0.577 |
Seymour | -0.563 |
Token | National |
Token ID | 2351 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
rahim | +0.247 |
aho | +0.222 |
enhagen | +0.221 |
agara | +0.208 |
ertodd | +0.198 |
Neg logit contributions | |
� | -0.198 |
arium | -0.194 |
� | -0.188 |
之 | -0.186 |
Seymour | -0.185 |
Token | Union |
Token ID | 4479 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
rahim | +0.630 |
aho | +0.581 |
enhagen | +0.572 |
agara | +0.551 |
ertodd | +0.539 |
Neg logit contributions | |
� | -0.280 |
arium | -0.265 |
� | -0.259 |
之 | -0.257 |
Seymour | -0.247 |
Token | ( |
Token ID | 357 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
rahim | +0.324 |
enhagen | +0.296 |
aho | +0.294 |
agara | +0.277 |
ertodd | +0.270 |
Neg logit contributions | |
� | -0.215 |
arium | -0.211 |
� | -0.205 |
之 | -0.203 |
Seymour | -0.198 |
Token | K |
Token ID | 42 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rahim | +0.175 |
enhagen | +0.161 |
aho | +0.159 |
agara | +0.147 |
ertodd | +0.143 |
Neg logit contributions | |
arium | -0.093 |
� | -0.092 |
Seymour | -0.089 |
之 | -0.087 |
Schwarzenegger | -0.087 |
Token | AN |
Token ID | 1565 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
rahim | +0.492 |
aho | +0.451 |
enhagen | +0.450 |
agara | +0.420 |
ertodd | +0.413 |
Neg logit contributions | |
� | -0.268 |
arium | -0.259 |
Seymour | -0.255 |
之 | -0.252 |
� | -0.250 |
Token | U |
Token ID | 52 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
rahim | +2.804 |
aho | +2.548 |
enhagen | +2.488 |
agara | +2.426 |
ertodd | +2.263 |
Neg logit contributions | |
arium | -1.877 |
之 | -1.775 |
Seymour | -1.770 |
� | -1.764 |
� | -1.748 |
Token | ), |
Token ID | 828 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
rahim | +0.381 |
aho | +0.332 |
enhagen | +0.332 |
agara | +0.304 |
ertodd | +0.292 |
Neg logit contributions | |
arium | -0.487 |
� | -0.485 |
Seymour | -0.471 |
� | -0.471 |
之 | -0.470 |
Token | which |
Token ID | 543 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
� | +0.008 |
arium | +0.008 |
之 | +0.008 |
� | +0.008 |
Seymour | +0.008 |
Neg logit contributions | |
rahim | -0.011 |
enhagen | -0.010 |
aho | -0.010 |
agara | -0.010 |
ertodd | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
rahim | +0.436 |
enhagen | +0.395 |
aho | +0.392 |
agara | +0.371 |
ertodd | +0.362 |
Neg logit contributions | |
� | -0.297 |
arium | -0.292 |
之 | -0.282 |
� | -0.281 |
Seymour | -0.272 |
Token | dominated |
Token ID | 13354 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
rahim | +0.115 |
enhagen | +0.103 |
aho | +0.101 |
agara | +0.094 |
ertodd | +0.091 |
Neg logit contributions | |
� | -0.129 |
arium | -0.128 |
之 | -0.124 |
� | -0.124 |
Seymour | -0.122 |
Token | do |
Token ID | 466 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
� | +0.117 |
arium | +0.115 |
之 | +0.111 |
� | +0.111 |
Seymour | +0.109 |
Neg logit contributions | |
rahim | -0.133 |
enhagen | -0.120 |
aho | -0.119 |
agara | -0.110 |
ertodd | -0.109 |
Token | ? |
Token ID | 30 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
� | +0.009 |
arium | +0.009 |
之 | +0.009 |
� | +0.009 |
Seymour | +0.009 |
Neg logit contributions | |
rahim | -0.015 |
enhagen | -0.013 |
aho | -0.013 |
agara | -0.012 |
ertodd | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
� | +0.181 |
arium | +0.178 |
� | +0.171 |
之 | +0.171 |
Seymour | +0.167 |
Neg logit contributions | |
rahim | -0.270 |
enhagen | -0.246 |
aho | -0.244 |
agara | -0.228 |
ertodd | -0.228 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
rahim | +0.630 |
aho | +0.569 |
enhagen | +0.560 |
agara | +0.526 |
ertodd | +0.525 |
Neg logit contributions | |
� | -0.431 |
arium | -0.420 |
� | -0.409 |
之 | -0.408 |
Seymour | -0.398 |
Token | Ex |
Token ID | 3109 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
rahim | +0.538 |
enhagen | +0.480 |
aho | +0.479 |
agara | +0.442 |
ertodd | +0.435 |
Neg logit contributions | |
� | -0.492 |
arium | -0.488 |
之 | -0.470 |
Seymour | -0.470 |
� | -0.469 |
Token | am |
Token ID | 321 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
rahim | +0.452 |
enhagen | +0.407 |
aho | +0.404 |
agara | +0.373 |
ertodd | +0.372 |
Neg logit contributions | |
� | -0.415 |
arium | -0.407 |
� | -0.397 |
之 | -0.395 |
Seymour | -0.391 |
Token | ining |
Token ID | 3191 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
rahim | +2.368 |
enhagen | +2.133 |
aho | +2.071 |
ertodd | +1.934 |
agara | +1.904 |
Neg logit contributions | |
� | -2.236 |
arium | -2.190 |
之 | -2.109 |
� | -2.105 |
Seymour | -2.076 |
Token | each |
Token ID | 1123 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
� | +0.106 |
arium | +0.104 |
� | +0.101 |
之 | +0.101 |
Seymour | +0.098 |
Neg logit contributions | |
rahim | -0.130 |
enhagen | -0.118 |
aho | -0.117 |
agara | -0.108 |
ertodd | -0.108 |
Token | one |
Token ID | 530 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rahim | +0.570 |
enhagen | +0.522 |
aho | +0.518 |
agara | +0.486 |
ertodd | +0.478 |
Neg logit contributions | |
� | -0.384 |
arium | -0.378 |
之 | -0.363 |
� | -0.363 |
Seymour | -0.355 |
Token | of |
Token ID | 286 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
� | +0.274 |
arium | +0.269 |
� | +0.259 |
之 | +0.258 |
Seymour | +0.252 |
Neg logit contributions | |
rahim | -0.428 |
enhagen | -0.393 |
aho | -0.387 |
agara | -0.364 |
ertodd | -0.361 |
Token | those |
Token ID | 883 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
� | +0.247 |
arium | +0.245 |
之 | +0.239 |
� | +0.237 |
Seymour | +0.234 |
Neg logit contributions | |
rahim | -0.188 |
enhagen | -0.167 |
aho | -0.163 |
agara | -0.149 |
ertodd | -0.145 |
Token | ship |
Token ID | 4074 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
rahim | +0.131 |
enhagen | +0.120 |
aho | +0.118 |
agara | +0.111 |
ertodd | +0.110 |
Neg logit contributions | |
� | -0.093 |
arium | -0.091 |
� | -0.088 |
之 | -0.087 |
Seymour | -0.085 |
Token | it |
Token ID | 340 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
rahim | +0.377 |
enhagen | +0.339 |
aho | +0.334 |
agara | +0.311 |
ertodd | +0.309 |
Neg logit contributions | |
� | -0.295 |
arium | -0.286 |
之 | -0.280 |
� | -0.280 |
Seymour | -0.272 |
Token | to |
Token ID | 284 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
� | +0.324 |
arium | +0.316 |
� | +0.305 |
之 | +0.304 |
Seymour | +0.296 |
Neg logit contributions | |
rahim | -0.541 |
enhagen | -0.495 |
aho | -0.489 |
agara | -0.459 |
ertodd | -0.457 |
Token | you |
Token ID | 345 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
� | +0.060 |
arium | +0.059 |
之 | +0.058 |
� | +0.057 |
Seymour | +0.055 |
Neg logit contributions | |
rahim | -0.086 |
enhagen | -0.078 |
aho | -0.077 |
agara | -0.072 |
ertodd | -0.071 |
Token | within |
Token ID | 1626 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
� | +0.018 |
arium | +0.018 |
� | +0.017 |
之 | +0.017 |
Seymour | +0.017 |
Neg logit contributions | |
rahim | -0.028 |
enhagen | -0.025 |
aho | -0.025 |
agara | -0.023 |
ertodd | -0.023 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
� | +0.357 |
arium | +0.348 |
之 | +0.341 |
� | +0.340 |
Seymour | +0.327 |
Neg logit contributions | |
rahim | -0.491 |
enhagen | -0.448 |
aho | -0.442 |
agara | -0.413 |
ertodd | -0.410 |
Token | business |
Token ID | 1597 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
rahim | +3.138 |
aho | +2.947 |
enhagen | +2.918 |
agara | +2.755 |
ertodd | +2.721 |
Neg logit contributions | |
� | -1.278 |
arium | -1.241 |
之 | -1.215 |
� | -1.193 |
Seymour | -1.162 |
Token | days |
Token ID | 1528 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
rahim | +1.353 |
aho | +1.232 |
enhagen | +1.226 |
ertodd | +1.149 |
agara | +1.142 |
Neg logit contributions | |
� | -0.738 |
arium | -0.730 |
之 | -0.703 |
� | -0.694 |
Nguyen | -0.687 |
Token | . |
Token ID | 13 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
rahim | +0.959 |
enhagen | +0.879 |
aho | +0.866 |
agara | +0.810 |
ertodd | +0.802 |
Neg logit contributions | |
� | -0.665 |
arium | -0.654 |
之 | -0.629 |
� | -0.629 |
Seymour | -0.618 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
rahim | +0.176 |
enhagen | +0.159 |
aho | +0.159 |
agara | +0.147 |
ertodd | +0.146 |
Neg logit contributions | |
� | -0.124 |
arium | -0.122 |
� | -0.118 |
之 | -0.117 |
Seymour | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
rahim | +0.598 |
aho | +0.540 |
enhagen | +0.532 |
agara | +0.500 |
ertodd | +0.498 |
Neg logit contributions | |
� | -0.405 |
arium | -0.395 |
� | -0.383 |
之 | -0.383 |
Seymour | -0.374 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
rahim | +0.149 |
aho | +0.135 |
enhagen | +0.132 |
agara | +0.124 |
ertodd | +0.124 |
Neg logit contributions | |
� | -0.102 |
arium | -0.100 |
之 | -0.097 |
� | -0.097 |
Seymour | -0.094 |
Token | " |
Token ID | 1 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
rahim | +0.124 |
aho | +0.112 |
enhagen | +0.110 |
agara | +0.103 |
ertodd | +0.101 |
Neg logit contributions | |
� | -0.098 |
arium | -0.096 |
之 | -0.094 |
� | -0.093 |
Seymour | -0.092 |
Token | I |
Token ID | 40 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
rahim | +0.591 |
aho | +0.530 |
enhagen | +0.523 |
agara | +0.483 |
ertodd | +0.477 |
Neg logit contributions | |
� | -0.558 |
arium | -0.551 |
之 | -0.536 |
� | -0.533 |
Seymour | -0.525 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
� | +0.019 |
arium | +0.019 |
� | +0.018 |
之 | +0.018 |
Seymour | +0.018 |
Neg logit contributions | |
rahim | -0.025 |
enhagen | -0.022 |
aho | -0.022 |
agara | -0.021 |
ertodd | -0.020 |
Token | ( |
Token ID | 357 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
rahim | +0.780 |
enhagen | +0.719 |
aho | +0.714 |
agara | +0.674 |
ertodd | +0.662 |
Neg logit contributions | |
� | -0.509 |
arium | -0.497 |
之 | -0.491 |
� | -0.481 |
Seymour | -0.460 |
Token | Con |
Token ID | 3103 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
rahim | +0.245 |
enhagen | +0.222 |
aho | +0.221 |
agara | +0.206 |
ertodd | +0.199 |
Neg logit contributions | |
� | -0.193 |
arium | -0.192 |
之 | -0.188 |
� | -0.184 |
Seymour | -0.182 |
Token | an |
Token ID | 272 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
rahim | +3.269 |
aho | +3.004 |
enhagen | +2.987 |
agara | +2.884 |
ertodd | +2.814 |
Neg logit contributions | |
� | -1.276 |
之 | -1.213 |
arium | -1.173 |
� | -1.150 |
Nguyen | -1.124 |
Token | ) |
Token ID | 8 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
rahim | +0.841 |
enhagen | +0.768 |
aho | +0.751 |
agara | +0.690 |
ertodd | +0.676 |
Neg logit contributions | |
� | -0.970 |
arium | -0.953 |
之 | -0.951 |
� | -0.940 |
Seymour | -0.911 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
rahim | +0.859 |
enhagen | +0.786 |
aho | +0.784 |
agara | +0.735 |
ertodd | +0.728 |
Neg logit contributions | |
� | -0.532 |
arium | -0.516 |
� | -0.508 |
之 | -0.506 |
Seymour | -0.485 |
Token | see |
Token ID | 766 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
� | +0.003 |
arium | +0.003 |
� | +0.003 |
之 | +0.003 |
Seymour | +0.003 |
Neg logit contributions | |
rahim | -0.005 |
enhagen | -0.004 |
aho | -0.004 |
agara | -0.004 |
ertodd | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
� | +0.084 |
arium | +0.082 |
之 | +0.080 |
� | +0.080 |
Seymour | +0.077 |
Neg logit contributions | |
rahim | -0.094 |
enhagen | -0.085 |
aho | -0.084 |
agara | -0.078 |
ertodd | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
� | +0.218 |
arium | +0.214 |
� | +0.206 |
之 | +0.205 |
Seymour | +0.202 |
Neg logit contributions | |
rahim | -0.329 |
enhagen | -0.300 |
aho | -0.297 |
agara | -0.278 |
ertodd | -0.276 |
Token | � |
Token ID | 447 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
� | +0.098 |
arium | +0.097 |
之 | +0.093 |
� | +0.093 |
Seymour | +0.092 |
Neg logit contributions | |
rahim | -0.121 |
enhagen | -0.108 |
aho | -0.108 |
ertodd | -0.099 |
agara | -0.099 |
Token | � |
Token ID | 251 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
� | +0.086 |
arium | +0.086 |
之 | +0.082 |
� | +0.081 |
Seymour | +0.081 |
Neg logit contributions | |
rahim | -0.131 |
aho | -0.118 |
enhagen | -0.118 |
agara | -0.111 |
ertodd | -0.110 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
rahim | +0.288 |
enhagen | +0.260 |
aho | +0.260 |
ertodd | +0.238 |
agara | +0.238 |
Neg logit contributions | |
� | -0.219 |
arium | -0.216 |
之 | -0.208 |
� | -0.208 |
Seymour | -0.205 |
Token | Image |
Token ID | 5159 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
� | +0.050 |
arium | +0.050 |
Seymour | +0.048 |
之 | +0.048 |
� | +0.048 |
Neg logit contributions | |
rahim | -0.057 |
aho | -0.051 |
enhagen | -0.051 |
agara | -0.047 |
ertodd | -0.046 |
Token | copyright |
Token ID | 6634 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
� | +0.004 |
arium | +0.004 |
之 | +0.004 |
� | +0.004 |
Seymour | +0.004 |
Neg logit contributions | |
rahim | -0.007 |
enhagen | -0.006 |
aho | -0.006 |
agara | -0.006 |
ertodd | -0.006 |
Token | publicity |
Token ID | 19403 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
rahim | +2.701 |
enhagen | +2.464 |
aho | +2.435 |
agara | +2.233 |
ertodd | +2.225 |
Neg logit contributions | |
� | -1.702 |
arium | -1.672 |
之 | -1.639 |
� | -1.591 |
urable | -1.531 |
Token | Image |
Token ID | 7412 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
rahim | +0.605 |
aho | +0.554 |
enhagen | +0.537 |
agara | +0.510 |
ertodd | +0.492 |
Neg logit contributions | |
� | -0.525 |
arium | -0.519 |
之 | -0.510 |
� | -0.500 |
Schwarzenegger | -0.491 |
Token | caption |
Token ID | 8305 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
� | +1.174 |
arium | +1.161 |
� | +1.118 |
之 | +1.111 |
Seymour | +1.094 |
Neg logit contributions | |
rahim | -1.639 |
enhagen | -1.493 |
aho | -1.472 |
agara | -1.380 |
ertodd | -1.374 |
Token | The |
Token ID | 383 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
rahim | +1.617 |
enhagen | +1.444 |
aho | +1.441 |
agara | +1.335 |
ertodd | +1.316 |
Neg logit contributions | |
� | -1.136 |
arium | -1.119 |
之 | -1.085 |
� | -1.078 |
urable | -1.039 |
Token | Greeks |
Token ID | 25059 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
rahim | +0.410 |
enhagen | +0.375 |
aho | +0.368 |
agara | +0.347 |
ertodd | +0.340 |
Neg logit contributions | |
� | -0.284 |
arium | -0.278 |
� | -0.272 |
之 | -0.271 |
Seymour | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
rahim | +0.152 |
enhagen | +0.139 |
aho | +0.138 |
agara | +0.128 |
ertodd | +0.126 |
Neg logit contributions | |
� | -0.110 |
arium | -0.107 |
� | -0.104 |
之 | -0.104 |
Seymour | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
rahim | +0.101 |
enhagen | +0.092 |
aho | +0.090 |
agara | +0.084 |
ertodd | +0.082 |
Neg logit contributions | |
� | -0.083 |
arium | -0.081 |
� | -0.079 |
之 | -0.078 |
Seymour | -0.076 |
Token | storm |
Token ID | 6388 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
rahim | +0.137 |
enhagen | +0.127 |
aho | +0.124 |
agara | +0.117 |
ertodd | +0.113 |
Neg logit contributions | |
� | -0.104 |
arium | -0.103 |
� | -0.099 |
之 | -0.099 |
Nguyen | -0.096 |
Token | extends |
Token ID | 14582 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
� | +0.125 |
arium | +0.122 |
� | +0.119 |
之 | +0.118 |
Seymour | +0.115 |
Neg logit contributions | |
rahim | -0.203 |
enhagen | -0.187 |
aho | -0.184 |
agara | -0.173 |
ertodd | -0.172 |
Token | as |
Token ID | 355 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rahim | +0.643 |
enhagen | +0.592 |
aho | +0.584 |
agara | +0.546 |
ertodd | +0.533 |
Neg logit contributions | |
� | -0.465 |
arium | -0.458 |
� | -0.444 |
之 | -0.437 |
Seymour | -0.425 |
Token | far |
Token ID | 1290 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
rahim | +0.431 |
enhagen | +0.391 |
aho | +0.389 |
agara | +0.362 |
ertodd | +0.354 |
Neg logit contributions | |
� | -0.357 |
arium | -0.354 |
� | -0.340 |
之 | -0.334 |
Seymour | -0.333 |
Token | south |
Token ID | 5366 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
rahim | +2.148 |
aho | +1.982 |
enhagen | +1.972 |
agara | +1.799 |
ertodd | +1.722 |
Neg logit contributions | |
� | -2.205 |
arium | -2.171 |
� | -2.097 |
之 | -2.080 |
Nguyen | -2.064 |
Token | as |
Token ID | 355 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
rahim | +0.060 |
enhagen | +0.055 |
aho | +0.055 |
agara | +0.051 |
ertodd | +0.050 |
Neg logit contributions | |
� | -0.046 |
arium | -0.045 |
之 | -0.044 |
� | -0.044 |
Nguyen | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
rahim | +1.329 |
aho | +1.218 |
enhagen | +1.214 |
agara | +1.133 |
ertodd | +1.083 |
Neg logit contributions | |
� | -0.947 |
arium | -0.925 |
� | -0.903 |
之 | -0.899 |
Schwarzenegger | -0.847 |
Token | city |
Token ID | 1748 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
rahim | +0.152 |
enhagen | +0.140 |
aho | +0.139 |
agara | +0.130 |
ertodd | +0.125 |
Neg logit contributions | |
� | -0.117 |
arium | -0.115 |
� | -0.111 |
之 | -0.111 |
Seymour | -0.106 |
Token | of |
Token ID | 286 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
� | +0.157 |
arium | +0.149 |
� | +0.148 |
之 | +0.146 |
Nguyen | +0.143 |
Neg logit contributions | |
rahim | -0.225 |
enhagen | -0.206 |
aho | -0.204 |
agara | -0.193 |
ertodd | -0.186 |
Token | ) |
Token ID | 8 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rahim | +0.294 |
enhagen | +0.259 |
aho | +0.259 |
agara | +0.235 |
ertodd | +0.224 |
Neg logit contributions | |
� | -0.366 |
arium | -0.356 |
之 | -0.354 |
� | -0.352 |
Schwarzenegger | -0.338 |
Token | Par |
Token ID | 2547 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
rahim | +0.507 |
aho | +0.460 |
enhagen | +0.459 |
agara | +0.427 |
ertodd | +0.417 |
Neg logit contributions | |
� | -0.332 |
arium | -0.326 |
之 | -0.317 |
� | -0.314 |
Seymour | -0.294 |
Token | cells |
Token ID | 46342 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
rahim | +0.440 |
aho | +0.337 |
enhagen | +0.332 |
agara | +0.266 |
ertodd | +0.256 |
Neg logit contributions | |
� | -1.390 |
之 | -1.370 |
arium | -1.353 |
� | -1.352 |
Seymour | -1.338 |
Token | standing |
Token ID | 5055 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
� | +0.251 |
arium | +0.249 |
� | +0.239 |
之 | +0.238 |
Seymour | +0.236 |
Neg logit contributions | |
rahim | -0.380 |
enhagen | -0.349 |
aho | -0.346 |
agara | -0.321 |
ertodd | -0.319 |
Token | over |
Token ID | 625 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
� | +0.222 |
arium | +0.218 |
� | +0.211 |
之 | +0.210 |
Seymour | +0.206 |
Neg logit contributions | |
rahim | -0.311 |
enhagen | -0.283 |
aho | -0.280 |
agara | -0.261 |
ertodd | -0.260 |
Token | there |
Token ID | 612 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
rahim | +0.173 |
enhagen | +0.157 |
aho | +0.155 |
agara | +0.143 |
ertodd | +0.142 |
Neg logit contributions | |
� | -0.140 |
arium | -0.139 |
之 | -0.136 |
� | -0.135 |
Nguyen | -0.128 |
Token | with |
Token ID | 351 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
rahim | +2.497 |
enhagen | +2.303 |
aho | +2.277 |
agara | +2.117 |
ertodd | +2.108 |
Neg logit contributions | |
� | -1.835 |
arium | -1.823 |
之 | -1.749 |
� | -1.744 |
Seymour | -1.727 |
Token | his |
Token ID | 465 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
rahim | +0.756 |
enhagen | +0.687 |
aho | +0.680 |
agara | +0.629 |
ertodd | +0.622 |
Neg logit contributions | |
� | -0.606 |
arium | -0.601 |
之 | -0.584 |
� | -0.579 |
urable | -0.553 |
Token | beaten |
Token ID | 13125 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
� | +0.103 |
arium | +0.101 |
� | +0.097 |
之 | +0.097 |
Seymour | +0.093 |
Neg logit contributions | |
rahim | -0.147 |
enhagen | -0.134 |
aho | -0.133 |
agara | -0.124 |
ertodd | -0.123 |
Token | team |
Token ID | 1074 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
rahim | +0.245 |
enhagen | +0.224 |
aho | +0.220 |
agara | +0.206 |
ertodd | +0.202 |
Neg logit contributions | |
� | -0.168 |
arium | -0.164 |
之 | -0.158 |
� | -0.158 |
Seymour | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
rahim | +1.040 |
enhagen | +0.949 |
aho | +0.940 |
agara | +0.876 |
ertodd | +0.865 |
Neg logit contributions | |
� | -0.709 |
arium | -0.695 |
� | -0.672 |
Seymour | -0.669 |
之 | -0.668 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
rahim | +0.452 |
enhagen | +0.413 |
aho | +0.407 |
agara | +0.382 |
ertodd | +0.379 |
Neg logit contributions | |
� | -0.302 |
arium | -0.291 |
� | -0.288 |
之 | -0.284 |
Seymour | -0.280 |
Token | � |
Token ID | 447 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
rahim | +0.493 |
enhagen | +0.442 |
aho | +0.441 |
ertodd | +0.407 |
agara | +0.407 |
Neg logit contributions | |
� | -0.389 |
arium | -0.385 |
� | -0.372 |
之 | -0.371 |
Seymour | -0.363 |
Token | � |
Token ID | 251 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
� | +0.153 |
arium | +0.151 |
之 | +0.146 |
Seymour | +0.144 |
� | +0.144 |
Neg logit contributions | |
rahim | -0.216 |
aho | -0.196 |
enhagen | -0.195 |
agara | -0.183 |
ertodd | -0.181 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
rahim | +0.445 |
enhagen | +0.402 |
aho | +0.398 |
ertodd | +0.370 |
agara | +0.369 |
Neg logit contributions | |
� | -0.313 |
arium | -0.309 |
� | -0.297 |
之 | -0.296 |
Seymour | -0.289 |
Token | Image |
Token ID | 5159 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
� | +0.026 |
arium | +0.026 |
Seymour | +0.025 |
之 | +0.025 |
� | +0.025 |
Neg logit contributions | |
rahim | -0.030 |
aho | -0.027 |
enhagen | -0.026 |
agara | -0.024 |
ertodd | -0.024 |
Token | copyright |
Token ID | 6634 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
� | +0.024 |
arium | +0.023 |
� | +0.022 |
之 | +0.022 |
Seymour | +0.022 |
Neg logit contributions | |
rahim | -0.036 |
enhagen | -0.033 |
aho | -0.033 |
agara | -0.031 |
ertodd | -0.030 |
Token | Deadline |
Token ID | 35954 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
rahim | +2.697 |
enhagen | +2.462 |
aho | +2.432 |
agara | +2.232 |
ertodd | +2.228 |
Neg logit contributions | |
� | -1.691 |
arium | -1.660 |
之 | -1.627 |
� | -1.581 |
urable | -1.520 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
rahim | +1.213 |
enhagen | +1.092 |
aho | +1.084 |
agara | +0.985 |
ertodd | +0.964 |
Neg logit contributions | |
� | -1.325 |
之 | -1.291 |
arium | -1.287 |
� | -1.279 |
Seymour | -1.251 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
rahim | +0.437 |
aho | +0.394 |
enhagen | +0.390 |
agara | +0.364 |
ertodd | +0.363 |
Neg logit contributions | |
� | -0.291 |
arium | -0.287 |
之 | -0.277 |
� | -0.276 |
Seymour | -0.269 |
Token | Police |
Token ID | 9039 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
rahim | +0.527 |
aho | +0.469 |
enhagen | +0.457 |
agara | +0.428 |
ertodd | +0.419 |
Neg logit contributions | |
arium | -0.458 |
� | -0.457 |
之 | -0.445 |
Seymour | -0.442 |
Nguyen | -0.437 |
Token | have |
Token ID | 423 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
� | +0.187 |
arium | +0.183 |
之 | +0.177 |
� | +0.177 |
Seymour | +0.171 |
Neg logit contributions | |
rahim | -0.268 |
enhagen | -0.245 |
aho | -0.242 |
agara | -0.226 |
ertodd | -0.222 |
Token | on |
Token ID | 319 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
rahim | +0.256 |
enhagen | +0.234 |
aho | +0.230 |
agara | +0.216 |
ertodd | +0.215 |
Neg logit contributions | |
� | -0.171 |
arium | -0.165 |
� | -0.163 |
之 | -0.161 |
Seymour | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
� | +0.329 |
arium | +0.320 |
� | +0.314 |
之 | +0.305 |
Nguyen | +0.296 |
Neg logit contributions | |
rahim | -0.554 |
enhagen | -0.516 |
aho | -0.506 |
agara | -0.478 |
ertodd | -0.472 |
Token | nation |
Token ID | 3277 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
rahim | +0.415 |
enhagen | +0.385 |
aho | +0.379 |
agara | +0.358 |
ertodd | +0.349 |
Neg logit contributions | |
� | -0.263 |
arium | -0.259 |
� | -0.252 |
之 | -0.246 |
Seymour | -0.239 |
Token | 's |
Token ID | 338 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
� | +0.253 |
arium | +0.244 |
� | +0.239 |
之 | +0.234 |
Nguyen | +0.233 |
Neg logit contributions | |
rahim | -0.454 |
enhagen | -0.424 |
aho | -0.414 |
ertodd | -0.396 |
agara | -0.393 |
Token | debt |
Token ID | 5057 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
rahim | +0.284 |
enhagen | +0.262 |
aho | +0.257 |
agara | +0.244 |
ertodd | +0.238 |
Neg logit contributions | |
� | -0.167 |
arium | -0.163 |
� | -0.159 |
之 | -0.156 |
Seymour | -0.152 |
Token | limit |
Token ID | 4179 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
rahim | +0.716 |
enhagen | +0.669 |
aho | +0.657 |
agara | +0.618 |
ertodd | +0.600 |
Neg logit contributions | |
� | -0.490 |
� | -0.466 |
arium | -0.464 |
之 | -0.457 |
Seymour | -0.452 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
rahim | +2.476 |
enhagen | +2.284 |
aho | +2.259 |
agara | +2.106 |
ertodd | +2.075 |
Neg logit contributions | |
� | -1.839 |
� | -1.778 |
arium | -1.744 |
之 | -1.726 |
Seymour | -1.694 |
Token | , |
Token ID | 11 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
rahim | +0.511 |
enhagen | +0.471 |
aho | +0.464 |
agara | +0.431 |
ertodd | +0.429 |
Neg logit contributions | |
� | -0.373 |
arium | -0.369 |
� | -0.357 |
之 | -0.351 |
Seymour | -0.345 |
Token | saying |
Token ID | 2282 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
rahim | +0.225 |
enhagen | +0.204 |
aho | +0.202 |
agara | +0.188 |
ertodd | +0.184 |
Neg logit contributions | |
� | -0.191 |
arium | -0.190 |
� | -0.185 |
之 | -0.183 |
Seymour | -0.179 |
Token | he |
Token ID | 339 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
� | +0.131 |
arium | +0.127 |
� | +0.125 |
之 | +0.123 |
Seymour | +0.120 |
Neg logit contributions | |
rahim | -0.178 |
enhagen | -0.162 |
aho | -0.160 |
agara | -0.150 |
ertodd | -0.149 |
Token | 's |
Token ID | 338 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
� | +0.388 |
arium | +0.371 |
� | +0.365 |
之 | +0.361 |
Seymour | +0.354 |
Neg logit contributions | |
rahim | -0.546 |
enhagen | -0.497 |
aho | -0.488 |
agara | -0.461 |
ertodd | -0.456 |
Token | i |
Token ID | 72 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
rahim | +0.347 |
enhagen | +0.319 |
aho | +0.314 |
ertodd | +0.293 |
agara | +0.288 |
Neg logit contributions | |
� | -0.207 |
arium | -0.198 |
� | -0.197 |
之 | -0.196 |
Seymour | -0.193 |
Token | Live |
Token ID | 7547 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
rahim | +0.652 |
enhagen | +0.599 |
aho | +0.595 |
agara | +0.561 |
ertodd | +0.544 |
Neg logit contributions | |
� | -0.367 |
arium | -0.358 |
之 | -0.343 |
� | -0.343 |
Seymour | -0.339 |
Token | with |
Token ID | 351 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
� | +0.005 |
arium | +0.005 |
Seymour | +0.005 |
� | +0.005 |
之 | +0.005 |
Neg logit contributions | |
rahim | -0.008 |
enhagen | -0.008 |
aho | -0.007 |
agara | -0.007 |
nings | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
rahim | +0.054 |
enhagen | +0.049 |
aho | +0.049 |
agara | +0.045 |
ertodd | +0.044 |
Neg logit contributions | |
� | -0.039 |
arium | -0.038 |
之 | -0.037 |
� | -0.036 |
Nguyen | -0.035 |
Token | d |
Token ID | 288 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
rahim | +0.094 |
enhagen | +0.085 |
aho | +0.084 |
agara | +0.079 |
ertodd | +0.078 |
Neg logit contributions | |
� | -0.074 |
arium | -0.073 |
� | -0.070 |
之 | -0.070 |
Seymour | -0.068 |
Token | our |
Token ID | 454 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
� | +0.200 |
arium | +0.196 |
之 | +0.191 |
� | +0.191 |
Seymour | +0.187 |
Neg logit contributions | |
rahim | -0.244 |
aho | -0.218 |
enhagen | -0.218 |
agara | -0.203 |
ertodd | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
rahim | +2.522 |
enhagen | +2.302 |
aho | +2.264 |
agara | +2.131 |
ertodd | +2.062 |
Neg logit contributions | |
� | -1.844 |
arium | -1.799 |
之 | -1.724 |
� | -1.724 |
Nguyen | -1.640 |
Token | very |
Token ID | 845 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
� | +0.260 |
arium | +0.257 |
之 | +0.246 |
� | +0.245 |
Nguyen | +0.237 |
Neg logit contributions | |
rahim | -0.345 |
enhagen | -0.312 |
aho | -0.309 |
agara | -0.289 |
ertodd | -0.285 |
Token | short |
Token ID | 1790 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
rahim | +0.177 |
enhagen | +0.159 |
aho | +0.158 |
agara | +0.146 |
ertodd | +0.144 |
Neg logit contributions | |
� | -0.142 |
arium | -0.140 |
� | -0.134 |
之 | -0.134 |
Seymour | -0.129 |
Token | review |
Token ID | 2423 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
rahim | +0.985 |
enhagen | +0.901 |
aho | +0.883 |
agara | +0.830 |
ertodd | +0.809 |
Neg logit contributions | |
� | -0.701 |
arium | -0.690 |
� | -0.660 |
之 | -0.658 |
Nguyen | -0.633 |
Token | because |
Token ID | 780 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rahim | +0.153 |
enhagen | +0.140 |
aho | +0.137 |
agara | +0.129 |
ertodd | +0.128 |
Neg logit contributions | |
� | -0.105 |
arium | -0.103 |
� | -0.100 |
之 | -0.100 |
Seymour | -0.098 |
Token | Gu |
Token ID | 1962 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
rahim | +0.895 |
aho | +0.809 |
enhagen | +0.798 |
agara | +0.745 |
ertodd | +0.724 |
Neg logit contributions | |
� | -0.717 |
arium | -0.705 |
之 | -0.684 |
� | -0.682 |
urable | -0.643 |
Token | illa |
Token ID | 5049 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.264 |
arium | +0.261 |
� | +0.252 |
之 | +0.251 |
Seymour | +0.248 |
Neg logit contributions | |
rahim | -0.308 |
enhagen | -0.277 |
aho | -0.273 |
agara | -0.255 |
ertodd | -0.254 |
Token | ume |
Token ID | 2454 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
� | +0.787 |
arium | +0.784 |
� | +0.761 |
之 | +0.759 |
Seymour | +0.750 |
Neg logit contributions | |
rahim | -0.562 |
enhagen | -0.493 |
aho | -0.479 |
agara | -0.437 |
ertodd | -0.435 |
Token | ( |
Token ID | 357 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
� | +0.112 |
arium | +0.109 |
� | +0.107 |
之 | +0.105 |
Seymour | +0.103 |
Neg logit contributions | |
rahim | -0.165 |
enhagen | -0.153 |
aho | -0.151 |
agara | -0.140 |
ertodd | -0.139 |
Token | nom |
Token ID | 26601 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
� | +0.331 |
arium | +0.329 |
之 | +0.320 |
� | +0.318 |
Seymour | +0.316 |
Neg logit contributions | |
rahim | -0.292 |
enhagen | -0.257 |
aho | -0.255 |
agara | -0.233 |
ertodd | -0.226 |
Token | inated |
Token ID | 3898 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
rahim | +1.076 |
aho | +0.970 |
enhagen | +0.946 |
agara | +0.871 |
ertodd | +0.840 |
Neg logit contributions | |
� | -1.346 |
arium | -1.290 |
� | -1.275 |
之 | -1.273 |
Seymour | -1.240 |
Token | five |
Token ID | 1936 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
rahim | +2.321 |
enhagen | +2.102 |
aho | +2.085 |
agara | +1.906 |
ertodd | +1.864 |
Neg logit contributions | |
� | -2.034 |
arium | -2.003 |
� | -1.939 |
之 | -1.930 |
Seymour | -1.855 |
Token | times |
Token ID | 1661 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
� | +0.044 |
arium | +0.044 |
之 | +0.042 |
� | +0.042 |
Seymour | +0.041 |
Neg logit contributions | |
rahim | -0.057 |
enhagen | -0.052 |
aho | -0.051 |
agara | -0.048 |
ertodd | -0.047 |
Token | for |
Token ID | 329 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
� | +0.375 |
arium | +0.370 |
之 | +0.357 |
� | +0.356 |
Seymour | +0.347 |
Neg logit contributions | |
rahim | -0.473 |
enhagen | -0.433 |
aho | -0.428 |
agara | -0.398 |
ertodd | -0.396 |
Token | Benson |
Token ID | 33940 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
� | +0.101 |
arium | +0.099 |
� | +0.097 |
之 | +0.096 |
Seymour | +0.091 |
Neg logit contributions | |
rahim | -0.133 |
enhagen | -0.120 |
aho | -0.120 |
agara | -0.111 |
ertodd | -0.110 |
Token | ), |
Token ID | 828 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
� | +0.188 |
arium | +0.184 |
� | +0.180 |
之 | +0.178 |
Seymour | +0.175 |
Neg logit contributions | |
rahim | -0.184 |
enhagen | -0.167 |
aho | -0.164 |
agara | -0.151 |
ertodd | -0.150 |
Token | Download |
Token ID | 10002 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
� | +0.189 |
arium | +0.187 |
之 | +0.180 |
� | +0.180 |
Seymour | +0.179 |
Neg logit contributions | |
rahim | -0.217 |
enhagen | -0.195 |
aho | -0.192 |
agara | -0.177 |
ertodd | -0.176 |
Token | The |
Token ID | 383 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
rahim | +2.005 |
enhagen | +1.831 |
aho | +1.810 |
agara | +1.677 |
ertodd | +1.643 |
Neg logit contributions | |
� | -1.525 |
arium | -1.515 |
� | -1.456 |
之 | -1.442 |
Seymour | -1.428 |
Token | Stan |
Token ID | 32140 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
rahim | +0.915 |
enhagen | +0.831 |
aho | +0.828 |
agara | +0.769 |
ertodd | +0.759 |
Neg logit contributions | |
� | -0.649 |
arium | -0.639 |
� | -0.619 |
之 | -0.617 |
Seymour | -0.604 |
Token | ley |
Token ID | 1636 |
Feature activation | -9.92e-03 |
Pos logit contributions | |
rahim | +0.178 |
enhagen | +0.161 |
aho | +0.160 |
agara | +0.147 |
ertodd | +0.146 |
Neg logit contributions | |
� | -0.161 |
arium | -0.155 |
� | -0.154 |
之 | -0.153 |
Seymour | -0.151 |
Token | Par |
Token ID | 10044 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
� | +0.027 |
arium | +0.026 |
� | +0.025 |
之 | +0.025 |
Seymour | +0.025 |
Neg logit contributions | |
rahim | -0.037 |
aho | -0.033 |
enhagen | -0.033 |
agara | -0.031 |
ertodd | -0.031 |
Token | ad |
Token ID | 324 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
rahim | +0.654 |
aho | +0.593 |
enhagen | +0.592 |
agara | +0.559 |
ertodd | +0.548 |
Neg logit contributions | |
� | -0.443 |
� | -0.425 |
之 | -0.423 |
arium | -0.419 |
Seymour | -0.411 |
Token | ox |
Token ID | 1140 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
rahim | +2.102 |
aho | +1.914 |
enhagen | +1.894 |
agara | +1.719 |
ertodd | +1.711 |
Neg logit contributions | |
� | -2.260 |
� | -2.165 |
之 | -2.145 |
Seymour | -2.119 |
arium | -2.108 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
rahim | +0.747 |
enhagen | +0.677 |
aho | +0.675 |
agara | +0.626 |
ertodd | +0.620 |
Neg logit contributions | |
� | -0.514 |
arium | -0.504 |
� | -0.489 |
之 | -0.486 |
Seymour | -0.482 |
Token | rar |
Token ID | 20040 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
rahim | +0.014 |
enhagen | +0.013 |
aho | +0.013 |
agara | +0.012 |
ertodd | +0.011 |
Neg logit contributions | |
� | -0.013 |
arium | -0.013 |
之 | -0.012 |
� | -0.012 |
Seymour | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
rahim | +0.652 |
enhagen | +0.594 |
aho | +0.589 |
agara | +0.546 |
ertodd | +0.542 |
Neg logit contributions | |
� | -0.458 |
arium | -0.451 |
� | -0.433 |
之 | -0.432 |
Seymour | -0.428 |
Token | N |
Token ID | 399 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
� | +0.466 |
arium | +0.458 |
� | +0.442 |
之 | +0.442 |
Seymour | +0.433 |
Neg logit contributions | |
rahim | -0.626 |
enhagen | -0.569 |
aho | -0.563 |
agara | -0.524 |
ertodd | -0.521 |
Token | followed |
Token ID | 3940 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
rahim | +0.508 |
enhagen | +0.462 |
aho | +0.456 |
agara | +0.430 |
ertodd | +0.424 |
Neg logit contributions | |
� | -0.333 |
arium | -0.326 |
� | -0.316 |
之 | -0.315 |
Seymour | -0.304 |
Token | criticism |
Token ID | 7734 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
� | +1.074 |
arium | +1.060 |
� | +1.028 |
之 | +1.018 |
Seymour | +0.978 |
Neg logit contributions | |
rahim | -1.648 |
enhagen | -1.508 |
aho | -1.475 |
agara | -1.395 |
ertodd | -1.377 |
Token | from |
Token ID | 422 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
� | +0.015 |
arium | +0.015 |
� | +0.014 |
之 | +0.014 |
Seymour | +0.013 |
Neg logit contributions | |
rahim | -0.021 |
enhagen | -0.019 |
aho | -0.019 |
agara | -0.018 |
ertodd | -0.017 |
Token | pro |
Token ID | 386 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
� | +0.638 |
arium | +0.629 |
� | +0.606 |
之 | +0.602 |
Seymour | +0.586 |
Neg logit contributions | |
rahim | -0.922 |
enhagen | -0.843 |
aho | -0.826 |
agara | -0.773 |
ertodd | -0.771 |
Token | - |
Token ID | 12 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
rahim | +0.049 |
enhagen | +0.045 |
aho | +0.045 |
agara | +0.042 |
ertodd | +0.042 |
Neg logit contributions | |
� | -0.021 |
arium | -0.020 |
之 | -0.019 |
� | -0.019 |
Seymour | -0.018 |
Token | Brexit |
Token ID | 40730 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
� | +0.279 |
arium | +0.276 |
之 | +0.264 |
� | +0.263 |
Seymour | +0.261 |
Neg logit contributions | |
rahim | -0.503 |
enhagen | -0.458 |
aho | -0.453 |
agara | -0.426 |
ertodd | -0.415 |
Token | campaigners |
Token ID | 35933 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
� | +1.864 |
arium | +1.830 |
� | +1.774 |
之 | +1.761 |
Seymour | +1.737 |
Neg logit contributions | |
rahim | -2.805 |
enhagen | -2.571 |
aho | -2.535 |
agara | -2.387 |
ertodd | -2.381 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
� | +0.231 |
arium | +0.229 |
� | +0.220 |
之 | +0.219 |
Seymour | +0.212 |
Neg logit contributions | |
rahim | -0.312 |
enhagen | -0.283 |
aho | -0.278 |
agara | -0.260 |
ertodd | -0.257 |
Token | MPs |
Token ID | 14952 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
� | +0.525 |
arium | +0.514 |
� | +0.498 |
之 | +0.495 |
Seymour | +0.481 |
Neg logit contributions | |
rahim | -0.735 |
enhagen | -0.667 |
aho | -0.654 |
agara | -0.612 |
ertodd | -0.610 |
Token | unhappy |
Token ID | 19283 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
� | +0.609 |
arium | +0.601 |
� | +0.580 |
之 | +0.577 |
Seymour | +0.562 |
Neg logit contributions | |
rahim | -0.808 |
enhagen | -0.733 |
aho | -0.722 |
agara | -0.674 |
ertodd | -0.668 |
Token | at |
Token ID | 379 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
� | +0.137 |
arium | +0.136 |
� | +0.131 |
之 | +0.131 |
Seymour | +0.125 |
Neg logit contributions | |
rahim | -0.206 |
enhagen | -0.189 |
aho | -0.185 |
agara | -0.172 |
ertodd | -0.172 |
Token | ( |
Token ID | 7 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
� | +0.883 |
arium | +0.873 |
� | +0.842 |
之 | +0.837 |
Seymour | +0.825 |
Neg logit contributions | |
rahim | -1.231 |
enhagen | -1.119 |
aho | -1.106 |
agara | -1.036 |
ertodd | -1.029 |
Token | vec |
Token ID | 35138 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
� | +0.307 |
arium | +0.304 |
� | +0.292 |
之 | +0.292 |
Seymour | +0.286 |
Neg logit contributions | |
rahim | -0.423 |
enhagen | -0.383 |
aho | -0.378 |
agara | -0.353 |
ertodd | -0.351 |
Token | ); |
Token ID | 1776 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
rahim | +0.610 |
enhagen | +0.563 |
aho | +0.557 |
agara | +0.528 |
ertodd | +0.526 |
Neg logit contributions | |
� | -0.302 |
arium | -0.296 |
之 | -0.285 |
� | -0.283 |
Seymour | -0.279 |
Token | RE |
Token ID | 4526 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
� | +0.335 |
arium | +0.330 |
� | +0.318 |
之 | +0.317 |
Seymour | +0.309 |
Neg logit contributions | |
rahim | -0.499 |
enhagen | -0.455 |
aho | -0.450 |
agara | -0.421 |
ertodd | -0.420 |
Token | F |
Token ID | 37 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
rahim | +0.393 |
enhagen | +0.356 |
aho | +0.351 |
ertodd | +0.327 |
agara | +0.326 |
Neg logit contributions | |
� | -0.316 |
arium | -0.314 |
� | -0.302 |
之 | -0.301 |
Seymour | -0.297 |
Token | LECT |
Token ID | 16779 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
� | +0.342 |
arium | +0.331 |
� | +0.321 |
之 | +0.320 |
Seymour | +0.309 |
Neg logit contributions | |
rahim | -0.597 |
enhagen | -0.553 |
aho | -0.542 |
agara | -0.514 |
ertodd | -0.511 |
Token | _ |
Token ID | 62 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +1.780 |
arium | +1.725 |
� | +1.678 |
之 | +1.664 |
Seymour | +1.622 |
Neg logit contributions | |
rahim | -2.895 |
enhagen | -2.670 |
aho | -2.617 |
agara | -2.490 |
ertodd | -2.457 |
Token | M |
Token ID | 44 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
arium | +0.376 |
� | +0.375 |
之 | +0.356 |
� | +0.355 |
Seymour | +0.353 |
Neg logit contributions | |
rahim | -0.567 |
enhagen | -0.514 |
aho | -0.513 |
agara | -0.476 |
ertodd | -0.472 |
Token | EMBER |
Token ID | 28952 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
rahim | +0.015 |
enhagen | +0.013 |
aho | +0.013 |
agara | +0.013 |
ertodd | +0.013 |
Neg logit contributions | |
� | -0.008 |
arium | -0.008 |
� | -0.008 |
之 | -0.008 |
Seymour | -0.008 |
Token | ( |
Token ID | 7 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
� | +1.111 |
arium | +1.094 |
� | +1.058 |
之 | +1.053 |
Seymour | +1.037 |
Neg logit contributions | |
rahim | -1.487 |
enhagen | -1.351 |
aho | -1.333 |
agara | -1.247 |
ertodd | -1.242 |
Token | i |
Token ID | 72 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
� | +0.402 |
arium | +0.397 |
� | +0.386 |
之 | +0.385 |
Seymour | +0.380 |
Neg logit contributions | |
rahim | -0.395 |
enhagen | -0.352 |
aho | -0.346 |
agara | -0.319 |
ertodd | -0.318 |
Token |
|
Token ID | 198 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
rahim | +0.212 |
enhagen | +0.194 |
aho | +0.192 |
ertodd | +0.179 |
agara | +0.178 |
Neg logit contributions | |
� | -0.147 |
arium | -0.142 |
� | -0.139 |
之 | -0.138 |
Seymour | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
rahim | +0.214 |
aho | +0.193 |
enhagen | +0.191 |
agara | +0.179 |
ertodd | +0.178 |
Neg logit contributions | |
� | -0.145 |
arium | -0.142 |
� | -0.137 |
之 | -0.137 |
Seymour | -0.134 |
Token | UN |
Token ID | 4944 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
rahim | +0.278 |
aho | +0.252 |
enhagen | +0.246 |
agara | +0.229 |
ertodd | +0.226 |
Neg logit contributions | |
arium | -0.195 |
� | -0.193 |
Seymour | -0.185 |
Nguyen | -0.184 |
之 | -0.183 |
Token | DE |
Token ID | 7206 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
arium | +0.099 |
� | +0.098 |
之 | +0.094 |
Seymour | +0.094 |
� | +0.093 |
Neg logit contributions | |
rahim | -0.139 |
aho | -0.127 |
enhagen | -0.125 |
agara | -0.116 |
ertodd | -0.113 |
Token | AD |
Token ID | 2885 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
rahim | +1.303 |
aho | +1.196 |
enhagen | +1.141 |
agara | +1.059 |
ertodd | +1.050 |
Neg logit contributions | |
arium | -1.041 |
� | -1.028 |
� | -0.996 |
Seymour | -0.994 |
之 | -0.987 |
Token | * |
Token ID | 9 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
rahim | +1.630 |
enhagen | +1.455 |
aho | +1.454 |
ertodd | +1.298 |
agara | +1.293 |
Neg logit contributions | |
arium | -1.174 |
� | -1.156 |
之 | -1.092 |
Nguyen | -1.072 |
� | -1.072 |
Token |
|
Token ID | 198 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
� | +1.755 |
arium | +1.726 |
� | +1.662 |
之 | +1.652 |
Seymour | +1.621 |
Neg logit contributions | |
rahim | -2.867 |
enhagen | -2.625 |
aho | -2.592 |
agara | -2.438 |
ertodd | -2.429 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
� | +0.201 |
arium | +0.197 |
� | +0.190 |
之 | +0.189 |
Seymour | +0.186 |
Neg logit contributions | |
rahim | -0.307 |
aho | -0.277 |
enhagen | -0.275 |
agara | -0.258 |
ertodd | -0.257 |
Token | + |
Token ID | 10 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
rahim | +0.086 |
aho | +0.078 |
enhagen | +0.077 |
agara | +0.071 |
ertodd | +0.071 |
Neg logit contributions | |
� | -0.062 |
arium | -0.062 |
Seymour | -0.059 |
之 | -0.059 |
� | -0.059 |
Token | Soul |
Token ID | 8653 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
� | +0.577 |
arium | +0.566 |
� | +0.550 |
之 | +0.548 |
Seymour | +0.530 |
Neg logit contributions | |
rahim | -0.786 |
aho | -0.703 |
enhagen | -0.701 |
agara | -0.652 |
ertodd | -0.647 |
Token | ful |
Token ID | 913 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
� | +0.262 |
arium | +0.248 |
� | +0.247 |
之 | +0.245 |
Seymour | +0.237 |
Neg logit contributions | |
rahim | -0.458 |
aho | -0.420 |
enhagen | -0.416 |
agara | -0.392 |
ertodd | -0.388 |
Token | drug |
Token ID | 2563 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
rahim | +0.302 |
aho | +0.275 |
enhagen | +0.275 |
agara | +0.259 |
ertodd | +0.253 |
Neg logit contributions | |
� | -0.204 |
arium | -0.203 |
之 | -0.195 |
� | -0.194 |
Nguyen | -0.185 |
Token | addict |
Token ID | 19678 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
rahim | +0.090 |
enhagen | +0.082 |
aho | +0.082 |
agara | +0.077 |
ertodd | +0.075 |
Neg logit contributions | |
� | -0.055 |
arium | -0.054 |
� | -0.052 |
之 | -0.052 |
Seymour | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
� | +0.535 |
arium | +0.526 |
� | +0.507 |
之 | +0.504 |
Seymour | +0.486 |
Neg logit contributions | |
rahim | -0.759 |
enhagen | -0.698 |
aho | -0.691 |
agara | -0.646 |
ertodd | -0.642 |
Token | The |
Token ID | 383 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
� | +0.018 |
arium | +0.017 |
� | +0.017 |
之 | +0.017 |
Seymour | +0.016 |
Neg logit contributions | |
rahim | -0.023 |
aho | -0.021 |
enhagen | -0.021 |
agara | -0.019 |
ertodd | -0.019 |
Token | common |
Token ID | 2219 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
� | +0.261 |
arium | +0.255 |
� | +0.248 |
之 | +0.247 |
Nguyen | +0.235 |
Neg logit contributions | |
rahim | -0.384 |
enhagen | -0.351 |
aho | -0.345 |
agara | -0.324 |
ertodd | -0.318 |
Token | denomin |
Token ID | 31457 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
rahim | +0.195 |
enhagen | +0.178 |
aho | +0.175 |
agara | +0.163 |
ertodd | +0.157 |
Neg logit contributions | |
� | -0.162 |
arium | -0.160 |
� | -0.154 |
之 | -0.153 |
Seymour | -0.152 |
Token | ator |
Token ID | 1352 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
� | +1.565 |
arium | +1.564 |
� | +1.477 |
之 | +1.465 |
Seymour | +1.440 |
Neg logit contributions | |
rahim | -2.966 |
enhagen | -2.729 |
aho | -2.680 |
agara | -2.540 |
ertodd | -2.533 |
Token | throughout |
Token ID | 3690 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
� | +0.621 |
arium | +0.609 |
� | +0.592 |
之 | +0.588 |
Seymour | +0.572 |
Neg logit contributions | |
rahim | -0.854 |
enhagen | -0.782 |
aho | -0.774 |
agara | -0.721 |
ertodd | -0.713 |
Token | these |
Token ID | 777 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
� | +0.170 |
arium | +0.167 |
之 | +0.162 |
� | +0.161 |
Nguyen | +0.156 |
Neg logit contributions | |
rahim | -0.207 |
enhagen | -0.190 |
aho | -0.188 |
agara | -0.174 |
ertodd | -0.170 |
Token | disparate |
Token ID | 37433 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
� | +0.085 |
arium | +0.083 |
之 | +0.081 |
� | +0.080 |
Nguyen | +0.077 |
Neg logit contributions | |
rahim | -0.124 |
enhagen | -0.112 |
aho | -0.112 |
agara | -0.104 |
ertodd | -0.103 |
Token | roles |
Token ID | 9176 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
� | +0.558 |
arium | +0.549 |
� | +0.530 |
之 | +0.529 |
Nguyen | +0.512 |
Neg logit contributions | |
rahim | -0.784 |
enhagen | -0.711 |
aho | -0.708 |
agara | -0.660 |
ertodd | -0.651 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
rahim | +0.625 |
enhagen | +0.585 |
aho | +0.580 |
agara | +0.546 |
ertodd | +0.543 |
Neg logit contributions | |
� | -0.311 |
arium | -0.293 |
� | -0.291 |
之 | -0.288 |
Seymour | -0.273 |
Token | : |
Token ID | 25 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
� | +0.585 |
arium | +0.572 |
� | +0.561 |
之 | +0.556 |
Seymour | +0.548 |
Neg logit contributions | |
rahim | -0.664 |
enhagen | -0.606 |
aho | -0.593 |
agara | -0.550 |
ertodd | -0.550 |
Token | " |
Token ID | 366 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
� | +0.747 |
arium | +0.726 |
� | +0.704 |
之 | +0.702 |
Seymour | +0.679 |
Neg logit contributions | |
rahim | -1.276 |
enhagen | -1.175 |
aho | -1.151 |
agara | -1.088 |
ertodd | -1.085 |
Token | 9 |
Token ID | 24 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
� | +0.298 |
arium | +0.294 |
之 | +0.285 |
Seymour | +0.283 |
� | +0.282 |
Neg logit contributions | |
rahim | -0.374 |
enhagen | -0.337 |
aho | -0.334 |
agara | -0.309 |
ertodd | -0.307 |
Token | - |
Token ID | 12 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
� | +0.057 |
arium | +0.056 |
� | +0.053 |
之 | +0.053 |
Seymour | +0.051 |
Neg logit contributions | |
rahim | -0.116 |
enhagen | -0.107 |
aho | -0.106 |
agara | -0.100 |
ertodd | -0.099 |
Token | to |
Token ID | 1462 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
� | +0.490 |
arium | +0.484 |
之 | +0.469 |
� | +0.468 |
Seymour | +0.464 |
Neg logit contributions | |
rahim | -0.591 |
enhagen | -0.534 |
aho | -0.526 |
agara | -0.490 |
ertodd | -0.490 |
Token | - |
Token ID | 12 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +1.129 |
arium | +1.099 |
� | +1.038 |
之 | +1.023 |
Seymour | +0.995 |
Neg logit contributions | |
rahim | -3.407 |
enhagen | -3.181 |
aho | -3.126 |
agara | -2.989 |
ertodd | -2.979 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
� | +0.300 |
arium | +0.298 |
之 | +0.283 |
� | +0.282 |
Seymour | +0.276 |
Neg logit contributions | |
rahim | -0.764 |
enhagen | -0.704 |
aho | -0.702 |
agara | -0.667 |
ertodd | -0.658 |
Token | Working |
Token ID | 14594 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
� | +0.466 |
arium | +0.459 |
� | +0.440 |
之 | +0.439 |
Seymour | +0.424 |
Neg logit contributions | |
rahim | -0.857 |
enhagen | -0.800 |
aho | -0.795 |
agara | -0.740 |
ertodd | -0.738 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
� | +0.783 |
arium | +0.768 |
之 | +0.747 |
� | +0.745 |
Nguyen | +0.725 |
Neg logit contributions | |
rahim | -0.674 |
enhagen | -0.597 |
aho | -0.597 |
agara | -0.534 |
ertodd | -0.529 |
Token | Education |
Token ID | 7868 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
rahim | +0.081 |
enhagen | +0.076 |
aho | +0.075 |
ertodd | +0.070 |
agara | +0.070 |
Neg logit contributions | |
� | -0.046 |
arium | -0.044 |
� | -0.043 |
之 | -0.043 |
Nguyen | -0.041 |
Token | music |
Token ID | 2647 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
� | +0.009 |
arium | +0.009 |
之 | +0.009 |
� | +0.009 |
Seymour | +0.008 |
Neg logit contributions | |
rahim | -0.014 |
enhagen | -0.012 |
aho | -0.012 |
agara | -0.011 |
ertodd | -0.011 |
Token | critic |
Token ID | 4014 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
� | +0.156 |
arium | +0.150 |
之 | +0.146 |
� | +0.146 |
Nguyen | +0.141 |
Neg logit contributions | |
rahim | -0.321 |
enhagen | -0.295 |
aho | -0.294 |
agara | -0.275 |
ertodd | -0.269 |
Token | Adam |
Token ID | 7244 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
rahim | +0.041 |
enhagen | +0.038 |
aho | +0.037 |
agara | +0.034 |
ertodd | +0.034 |
Neg logit contributions | |
� | -0.029 |
arium | -0.029 |
之 | -0.028 |
� | -0.028 |
Schwarzenegger | -0.026 |
Token | Ward |
Token ID | 12150 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
rahim | +0.269 |
enhagen | +0.244 |
aho | +0.242 |
agara | +0.225 |
ertodd | +0.223 |
Neg logit contributions | |
� | -0.172 |
arium | -0.169 |
� | -0.163 |
之 | -0.163 |
Seymour | -0.153 |
Token | reminis |
Token ID | 21484 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
� | +0.282 |
arium | +0.277 |
� | +0.269 |
之 | +0.268 |
Seymour | +0.262 |
Neg logit contributions | |
rahim | -0.356 |
enhagen | -0.326 |
aho | -0.318 |
agara | -0.296 |
ertodd | -0.293 |
Token | ces |
Token ID | 728 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
� | +0.826 |
arium | +0.804 |
� | +0.792 |
之 | +0.788 |
Seymour | +0.773 |
Neg logit contributions | |
rahim | -0.824 |
enhagen | -0.736 |
aho | -0.726 |
agara | -0.674 |
ertodd | -0.668 |
Token | about |
Token ID | 546 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
� | +2.077 |
arium | +2.051 |
� | +1.985 |
之 | +1.978 |
Seymour | +1.954 |
Neg logit contributions | |
rahim | -2.420 |
enhagen | -2.181 |
aho | -2.149 |
agara | -2.007 |
ertodd | -1.995 |
Token | digital |
Token ID | 4875 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
� | +1.398 |
arium | +1.373 |
� | +1.336 |
之 | +1.328 |
Seymour | +1.286 |
Neg logit contributions | |
rahim | -1.830 |
enhagen | -1.669 |
aho | -1.644 |
agara | -1.533 |
ertodd | -1.525 |
Token | music |
Token ID | 2647 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
rahim | +1.276 |
enhagen | +1.148 |
aho | +1.120 |
agara | +1.059 |
ertodd | +1.026 |
Neg logit contributions | |
� | -1.062 |
arium | -1.042 |
� | -1.011 |
之 | -1.008 |
Seymour | -0.992 |
Token | files |
Token ID | 3696 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
� | +0.281 |
arium | +0.273 |
� | +0.268 |
之 | +0.265 |
Seymour | +0.258 |
Neg logit contributions | |
rahim | -0.455 |
enhagen | -0.420 |
aho | -0.410 |
agara | -0.388 |
ertodd | -0.385 |
Token | that |
Token ID | 326 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
rahim | +0.480 |
enhagen | +0.441 |
aho | +0.433 |
agara | +0.406 |
ertodd | +0.401 |
Neg logit contributions | |
� | -0.333 |
arium | -0.326 |
� | -0.317 |
之 | -0.316 |
Seymour | -0.308 |
Token | and |
Token ID | 290 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
� | +0.287 |
arium | +0.282 |
� | +0.272 |
之 | +0.272 |
Seymour | +0.264 |
Neg logit contributions | |
rahim | -0.429 |
enhagen | -0.391 |
aho | -0.387 |
agara | -0.363 |
ertodd | -0.360 |
Token | night |
Token ID | 1755 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
� | +0.121 |
arium | +0.118 |
之 | +0.116 |
� | +0.115 |
Nguyen | +0.110 |
Neg logit contributions | |
rahim | -0.166 |
enhagen | -0.151 |
aho | -0.149 |
agara | -0.141 |
ertodd | -0.138 |
Token | ! |
Token ID | 0 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
rahim | +0.222 |
enhagen | +0.203 |
aho | +0.201 |
agara | +0.187 |
ertodd | +0.185 |
Neg logit contributions | |
� | -0.150 |
arium | -0.146 |
� | -0.142 |
之 | -0.142 |
Seymour | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
� | +0.058 |
arium | +0.057 |
之 | +0.055 |
� | +0.055 |
Seymour | +0.053 |
Neg logit contributions | |
rahim | -0.079 |
enhagen | -0.072 |
aho | -0.071 |
agara | -0.066 |
ertodd | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
rahim | +0.268 |
aho | +0.242 |
enhagen | +0.237 |
agara | +0.223 |
ertodd | +0.223 |
Neg logit contributions | |
� | -0.186 |
arium | -0.182 |
� | -0.177 |
之 | -0.177 |
Seymour | -0.172 |
Token | Rated |
Token ID | 15322 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
rahim | +0.118 |
enhagen | +0.107 |
aho | +0.106 |
agara | +0.100 |
ertodd | +0.099 |
Neg logit contributions | |
� | -0.077 |
arium | -0.075 |
� | -0.073 |
之 | -0.072 |
Seymour | -0.071 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
� | +1.821 |
arium | +1.787 |
� | +1.729 |
之 | +1.721 |
Seymour | +1.683 |
Neg logit contributions | |
rahim | -2.664 |
enhagen | -2.426 |
aho | -2.397 |
agara | -2.248 |
ertodd | -2.236 |
Token | out |
Token ID | 503 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
� | +0.432 |
arium | +0.421 |
� | +0.408 |
之 | +0.408 |
Seymour | +0.394 |
Neg logit contributions | |
rahim | -0.664 |
enhagen | -0.599 |
aho | -0.599 |
agara | -0.560 |
ertodd | -0.557 |
Token | of |
Token ID | 286 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
� | +0.380 |
arium | +0.372 |
� | +0.360 |
之 | +0.360 |
Seymour | +0.350 |
Neg logit contributions | |
rahim | -0.592 |
aho | -0.536 |
enhagen | -0.533 |
agara | -0.499 |
ertodd | -0.497 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
� | +0.348 |
arium | +0.342 |
� | +0.331 |
之 | +0.330 |
Seymour | +0.321 |
Neg logit contributions | |
rahim | -0.478 |
aho | -0.430 |
enhagen | -0.430 |
agara | -0.402 |
ertodd | -0.398 |
Token | by |
Token ID | 416 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
� | +0.659 |
arium | +0.649 |
� | +0.629 |
之 | +0.627 |
Seymour | +0.613 |
Neg logit contributions | |
rahim | -0.779 |
enhagen | -0.697 |
aho | -0.694 |
agara | -0.643 |
ertodd | -0.640 |
Token | forum |
Token ID | 27302 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
� | +0.330 |
arium | +0.315 |
之 | +0.311 |
� | +0.310 |
Seymour | +0.305 |
Neg logit contributions | |
rahim | -0.487 |
enhagen | -0.442 |
aho | -0.440 |
agara | -0.411 |
ertodd | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
� | +0.256 |
arium | +0.242 |
之 | +0.242 |
� | +0.240 |
Seymour | +0.237 |
Neg logit contributions | |
rahim | -0.362 |
aho | -0.330 |
enhagen | -0.327 |
agara | -0.304 |
ertodd | -0.303 |
Token | com |
Token ID | 785 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
� | +0.329 |
arium | +0.322 |
� | +0.314 |
之 | +0.314 |
Seymour | +0.308 |
Neg logit contributions | |
rahim | -0.364 |
enhagen | -0.326 |
aho | -0.325 |
agara | -0.300 |
ertodd | -0.297 |
Token | / |
Token ID | 14 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
� | +0.971 |
arium | +0.956 |
� | +0.921 |
之 | +0.914 |
Seymour | +0.900 |
Neg logit contributions | |
rahim | -1.639 |
enhagen | -1.503 |
aho | -1.480 |
agara | -1.403 |
ertodd | -1.390 |
Token | forums |
Token ID | 37141 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
� | +0.301 |
arium | +0.297 |
� | +0.288 |
之 | +0.287 |
Seymour | +0.283 |
Neg logit contributions | |
rahim | -0.355 |
enhagen | -0.319 |
aho | -0.316 |
agara | -0.293 |
ertodd | -0.290 |
Token | ... |
Token ID | 986 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
� | +1.026 |
arium | +1.016 |
� | +0.974 |
之 | +0.965 |
Seymour | +0.947 |
Neg logit contributions | |
rahim | -1.724 |
enhagen | -1.590 |
aho | -1.557 |
agara | -1.477 |
ertodd | -1.469 |
Token | with |
Token ID | 4480 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
� | +1.786 |
arium | +1.756 |
� | +1.693 |
之 | +1.682 |
Seymour | +1.650 |
Neg logit contributions | |
rahim | -2.664 |
enhagen | -2.431 |
aho | -2.396 |
agara | -2.254 |
ertodd | -2.245 |
Token | - |
Token ID | 12 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
� | +0.302 |
arium | +0.293 |
之 | +0.282 |
� | +0.282 |
Seymour | +0.278 |
Neg logit contributions | |
rahim | -0.639 |
enhagen | -0.588 |
aho | -0.586 |
agara | -0.550 |
ertodd | -0.546 |
Token | p |
Token ID | 79 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
� | +0.774 |
arium | +0.761 |
� | +0.737 |
之 | +0.734 |
Seymour | +0.724 |
Neg logit contributions | |
rahim | -1.092 |
enhagen | -0.994 |
aho | -0.982 |
agara | -0.919 |
ertodd | -0.910 |
Token | ics |
Token ID | 873 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
� | +0.668 |
arium | +0.647 |
� | +0.637 |
之 | +0.633 |
Seymour | +0.619 |
Neg logit contributions | |
rahim | -0.865 |
enhagen | -0.783 |
aho | -0.782 |
agara | -0.729 |
ertodd | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
� | +0.050 |
arium | +0.048 |
之 | +0.047 |
� | +0.047 |
Seymour | +0.046 |
Neg logit contributions | |
rahim | -0.081 |
enhagen | -0.074 |
aho | -0.074 |
agara | -0.069 |
ertodd | -0.069 |
Token | ( |
Token ID | 7 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
� | +1.111 |
arium | +1.094 |
� | +1.058 |
之 | +1.053 |
Seymour | +1.037 |
Neg logit contributions | |
rahim | -1.487 |
enhagen | -1.351 |
aho | -1.333 |
agara | -1.247 |
ertodd | -1.242 |
Token | i |
Token ID | 72 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
� | +0.402 |
arium | +0.397 |
� | +0.386 |
之 | +0.385 |
Seymour | +0.380 |
Neg logit contributions | |
rahim | -0.395 |
enhagen | -0.352 |
aho | -0.346 |
agara | -0.319 |
ertodd | -0.318 |
Token | ); |
Token ID | 1776 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
� | +0.141 |
arium | +0.139 |
� | +0.135 |
之 | +0.134 |
Seymour | +0.133 |
Neg logit contributions | |
rahim | -0.159 |
enhagen | -0.144 |
aho | -0.142 |
agara | -0.132 |
ertodd | -0.131 |
Token | RE |
Token ID | 4526 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
� | +0.531 |
arium | +0.522 |
� | +0.504 |
之 | +0.501 |
Seymour | +0.489 |
Neg logit contributions | |
rahim | -0.849 |
enhagen | -0.775 |
aho | -0.767 |
agara | -0.719 |
ertodd | -0.718 |
Token | F |
Token ID | 37 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
rahim | +0.433 |
enhagen | +0.392 |
aho | +0.387 |
agara | +0.361 |
ertodd | +0.360 |
Neg logit contributions | |
� | -0.333 |
arium | -0.328 |
� | -0.318 |
之 | -0.316 |
Seymour | -0.311 |
Token | LECT |
Token ID | 16779 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
� | +0.307 |
arium | +0.298 |
� | +0.289 |
之 | +0.288 |
Seymour | +0.277 |
Neg logit contributions | |
rahim | -0.532 |
enhagen | -0.494 |
aho | -0.484 |
agara | -0.458 |
ertodd | -0.456 |
Token | _ |
Token ID | 62 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
� | +1.672 |
arium | +1.612 |
� | +1.572 |
之 | +1.555 |
Seymour | +1.504 |
Neg logit contributions | |
rahim | -2.781 |
enhagen | -2.590 |
aho | -2.516 |
agara | -2.411 |
ertodd | -2.373 |
Token | M |
Token ID | 44 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
arium | +0.425 |
� | +0.424 |
之 | +0.403 |
� | +0.402 |
Seymour | +0.399 |
Neg logit contributions | |
rahim | -0.647 |
enhagen | -0.587 |
aho | -0.585 |
agara | -0.543 |
ertodd | -0.539 |
Token | EMBER |
Token ID | 28952 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
� | +0.098 |
arium | +0.096 |
� | +0.092 |
之 | +0.091 |
Seymour | +0.089 |
Neg logit contributions | |
rahim | -0.204 |
enhagen | -0.189 |
aho | -0.186 |
agara | -0.177 |
ertodd | -0.176 |
Token | ( |
Token ID | 7 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
� | +1.050 |
arium | +1.033 |
� | +1.001 |
之 | +0.996 |
Seymour | +0.979 |
Neg logit contributions | |
rahim | -1.361 |
enhagen | -1.234 |
aho | -1.216 |
agara | -1.138 |
ertodd | -1.132 |
Token | f |
Token ID | 69 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
� | +0.316 |
arium | +0.312 |
� | +0.301 |
之 | +0.300 |
Seymour | +0.295 |
Neg logit contributions | |
rahim | -0.450 |
enhagen | -0.409 |
aho | -0.404 |
agara | -0.377 |
ertodd | -0.376 |
Token | in |
Token ID | 287 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
� | +0.087 |
arium | +0.086 |
� | +0.083 |
之 | +0.082 |
Seymour | +0.081 |
Neg logit contributions | |
rahim | -0.152 |
enhagen | -0.141 |
aho | -0.139 |
agara | -0.130 |
ertodd | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
rahim | +0.838 |
enhagen | +0.762 |
aho | +0.753 |
ertodd | +0.699 |
agara | +0.696 |
Neg logit contributions | |
� | -0.639 |
arium | -0.633 |
之 | -0.613 |
� | -0.610 |
Seymour | -0.595 |
Token | macro |
Token ID | 15021 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
rahim | +0.244 |
enhagen | +0.223 |
aho | +0.219 |
agara | +0.204 |
ertodd | +0.204 |
Neg logit contributions | |
� | -0.183 |
arium | -0.181 |
� | -0.174 |
之 | -0.174 |
Seymour | -0.170 |
Token | RE |
Token ID | 4526 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
� | +0.293 |
arium | +0.288 |
� | +0.277 |
之 | +0.277 |
Seymour | +0.269 |
Neg logit contributions | |
rahim | -0.484 |
enhagen | -0.444 |
aho | -0.437 |
agara | -0.411 |
ertodd | -0.409 |
Token | F |
Token ID | 37 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
� | +0.506 |
arium | +0.499 |
� | +0.482 |
之 | +0.480 |
Seymour | +0.472 |
Neg logit contributions | |
rahim | -0.662 |
enhagen | -0.601 |
aho | -0.592 |
agara | -0.554 |
ertodd | -0.552 |
Token | LECT |
Token ID | 16779 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
� | +0.048 |
arium | +0.047 |
� | +0.046 |
之 | +0.045 |
Seymour | +0.044 |
Neg logit contributions | |
rahim | -0.079 |
enhagen | -0.073 |
aho | -0.072 |
agara | -0.068 |
ertodd | -0.067 |
Token | _ |
Token ID | 62 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
� | +1.731 |
arium | +1.699 |
� | +1.641 |
之 | +1.631 |
Seymour | +1.601 |
Neg logit contributions | |
rahim | -2.680 |
enhagen | -2.449 |
aho | -2.417 |
agara | -2.274 |
ertodd | -2.262 |
Token | CLASS |
Token ID | 31631 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
arium | +0.318 |
� | +0.315 |
之 | +0.298 |
� | +0.296 |
Seymour | +0.294 |
Neg logit contributions | |
rahim | -0.555 |
enhagen | -0.508 |
aho | -0.506 |
agara | -0.470 |
ertodd | -0.466 |
Token | _ |
Token ID | 62 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
� | +0.075 |
arium | +0.075 |
之 | +0.072 |
� | +0.072 |
Seymour | +0.071 |
Neg logit contributions | |
rahim | -0.102 |
enhagen | -0.093 |
aho | -0.093 |
ertodd | -0.086 |
agara | -0.086 |
Token | ST |
Token ID | 2257 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
rahim | +0.119 |
aho | +0.109 |
enhagen | +0.108 |
agara | +0.100 |
ertodd | +0.099 |
Neg logit contributions | |
arium | -0.075 |
� | -0.074 |
之 | -0.070 |
Nguyen | -0.070 |
Seymour | -0.070 |
Token | ART |
Token ID | 7227 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
rahim | +0.689 |
aho | +0.634 |
enhagen | +0.629 |
agara | +0.591 |
ertodd | +0.584 |
Neg logit contributions | |
arium | -0.312 |
� | -0.309 |
之 | -0.292 |
� | -0.290 |
Seymour | -0.286 |
Token | ( |
Token ID | 7 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
� | +1.050 |
arium | +1.033 |
� | +1.001 |
之 | +0.996 |
Seymour | +0.979 |
Neg logit contributions | |
rahim | -1.361 |
enhagen | -1.234 |
aho | -1.216 |
agara | -1.138 |
ertodd | -1.132 |
Token | f |
Token ID | 69 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
� | +0.316 |
arium | +0.312 |
� | +0.301 |
之 | +0.300 |
Seymour | +0.295 |
Neg logit contributions | |
rahim | -0.450 |
enhagen | -0.409 |
aho | -0.404 |
agara | -0.377 |
ertodd | -0.376 |
Token | ); |
Token ID | 1776 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
� | +0.265 |
arium | +0.262 |
� | +0.255 |
之 | +0.254 |
Seymour | +0.253 |
Neg logit contributions | |
rahim | -0.240 |
enhagen | -0.213 |
aho | -0.210 |
agara | -0.192 |
ertodd | -0.191 |
Token | RE |
Token ID | 4526 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
� | +0.622 |
arium | +0.611 |
� | +0.589 |
之 | +0.584 |
Seymour | +0.571 |
Neg logit contributions | |
rahim | -1.064 |
enhagen | -0.974 |
aho | -0.965 |
agara | -0.906 |
ertodd | -0.904 |
Token | F |
Token ID | 37 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
rahim | +0.373 |
enhagen | +0.337 |
aho | +0.333 |
agara | +0.311 |
ertodd | +0.310 |
Neg logit contributions | |
� | -0.286 |
arium | -0.282 |
� | -0.273 |
之 | -0.271 |
Seymour | -0.267 |
Token | LECT |
Token ID | 16779 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
� | +0.258 |
arium | +0.251 |
� | +0.243 |
之 | +0.242 |
Seymour | +0.234 |
Neg logit contributions | |
rahim | -0.441 |
enhagen | -0.408 |
aho | -0.400 |
agara | -0.378 |
ertodd | -0.376 |
Token | _ |
Token ID | 62 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
� | +1.659 |
arium | +1.599 |
� | +1.561 |
之 | +1.543 |
Seymour | +1.491 |
Neg logit contributions | |
rahim | -2.757 |
enhagen | -2.570 |
aho | -2.493 |
agara | -2.391 |
ertodd | -2.352 |
Token | CLASS |
Token ID | 31631 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
arium | +0.401 |
� | +0.401 |
之 | +0.380 |
� | +0.380 |
Seymour | +0.376 |
Neg logit contributions | |
rahim | -0.624 |
enhagen | -0.566 |
aho | -0.565 |
agara | -0.524 |
ertodd | -0.521 |
Token | _ |
Token ID | 62 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
� | +0.457 |
arium | +0.453 |
� | +0.435 |
之 | +0.433 |
Seymour | +0.430 |
Neg logit contributions | |
rahim | -0.630 |
enhagen | -0.576 |
aho | -0.571 |
ertodd | -0.531 |
agara | -0.530 |
Token | END |
Token ID | 10619 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
rahim | +0.309 |
aho | +0.280 |
enhagen | +0.278 |
agara | +0.258 |
ertodd | +0.255 |
Neg logit contributions | |
arium | -0.202 |
� | -0.197 |
Nguyen | -0.188 |
之 | -0.188 |
� | -0.187 |
Token | () |
Token ID | 3419 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
rahim | +0.165 |
enhagen | +0.148 |
aho | +0.147 |
agara | +0.134 |
ertodd | +0.134 |
Neg logit contributions | |
arium | -0.151 |
� | -0.151 |
� | -0.145 |
Seymour | -0.145 |
之 | -0.145 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
rahim | +0.073 |
enhagen | +0.067 |
aho | +0.065 |
agara | +0.061 |
ertodd | +0.060 |
Neg logit contributions | |
� | -0.054 |
arium | -0.053 |
之 | -0.052 |
� | -0.051 |
Nguyen | -0.049 |
Token | system |
Token ID | 1080 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
� | +0.722 |
arium | +0.708 |
� | +0.690 |
之 | +0.688 |
Seymour | +0.674 |
Neg logit contributions | |
rahim | -0.859 |
enhagen | -0.774 |
aho | -0.763 |
agara | -0.718 |
ertodd | -0.709 |
Token | . |
Token ID | 13 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
rahim | +0.462 |
enhagen | +0.423 |
aho | +0.418 |
agara | +0.393 |
ertodd | +0.391 |
Neg logit contributions | |
� | -0.309 |
arium | -0.298 |
� | -0.292 |
之 | -0.291 |
Nguyen | -0.281 |
Token |
|
Token ID | 198 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
rahim | +0.323 |
enhagen | +0.292 |
aho | +0.289 |
agara | +0.269 |
ertodd | +0.267 |
Neg logit contributions | |
� | -0.246 |
arium | -0.241 |
之 | -0.234 |
� | -0.233 |
Seymour | -0.224 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
� | +0.088 |
arium | +0.086 |
� | +0.083 |
之 | +0.083 |
Seymour | +0.081 |
Neg logit contributions | |
rahim | -0.132 |
aho | -0.119 |
enhagen | -0.118 |
agara | -0.111 |
ertodd | -0.110 |
Token | Rated |
Token ID | 15322 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
� | +0.103 |
arium | +0.101 |
� | +0.098 |
之 | +0.097 |
Seymour | +0.095 |
Neg logit contributions | |
rahim | -0.162 |
enhagen | -0.149 |
aho | -0.147 |
agara | -0.138 |
ertodd | -0.137 |
Token | 5 |
Token ID | 642 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
� | +1.770 |
arium | +1.737 |
� | +1.680 |
之 | +1.672 |
Seymour | +1.636 |
Neg logit contributions | |
rahim | -2.594 |
enhagen | -2.362 |
aho | -2.334 |
agara | -2.189 |
ertodd | -2.177 |
Token | out |
Token ID | 503 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
� | +0.217 |
arium | +0.212 |
之 | +0.205 |
� | +0.205 |
Seymour | +0.198 |
Neg logit contributions | |
rahim | -0.327 |
aho | -0.294 |
enhagen | -0.294 |
agara | -0.274 |
ertodd | -0.273 |
Token | of |
Token ID | 286 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
� | +0.172 |
arium | +0.168 |
之 | +0.163 |
� | +0.163 |
Seymour | +0.159 |
Neg logit contributions | |
rahim | -0.263 |
aho | -0.238 |
enhagen | -0.236 |
agara | -0.221 |
ertodd | -0.220 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
� | +0.151 |
arium | +0.148 |
� | +0.144 |
之 | +0.143 |
Seymour | +0.139 |
Neg logit contributions | |
rahim | -0.202 |
aho | -0.181 |
enhagen | -0.180 |
agara | -0.169 |
ertodd | -0.167 |
Token | by |
Token ID | 416 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
� | +0.452 |
arium | +0.445 |
� | +0.431 |
之 | +0.430 |
Seymour | +0.420 |
Neg logit contributions | |
rahim | -0.526 |
aho | -0.469 |
enhagen | -0.468 |
agara | -0.433 |
ertodd | -0.430 |
Token | 25 |
Token ID | 1495 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
� | +1.278 |
arium | +1.259 |
� | +1.212 |
之 | +1.207 |
Seymour | +1.189 |
Neg logit contributions | |
rahim | -1.928 |
enhagen | -1.754 |
aho | -1.738 |
agara | -1.627 |
ertodd | -1.618 |
Token | 67 |
Token ID | 3134 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
� | +0.632 |
arium | +0.621 |
� | +0.597 |
之 | +0.595 |
Seymour | +0.583 |
Neg logit contributions | |
rahim | -1.041 |
enhagen | -0.947 |
aho | -0.944 |
agara | -0.883 |
ertodd | -0.878 |
Token | "] |
Token ID | 8973 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
� | +0.704 |
arium | +0.690 |
� | +0.668 |
之 | +0.666 |
Seymour | +0.653 |
Neg logit contributions | |
rahim | -1.032 |
enhagen | -0.933 |
aho | -0.928 |
agara | -0.866 |
ertodd | -0.864 |
Token | [ |
Token ID | 685 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
� | +1.017 |
arium | +0.997 |
� | +0.956 |
之 | +0.950 |
Seymour | +0.929 |
Neg logit contributions | |
rahim | -2.042 |
enhagen | -1.885 |
aho | -1.858 |
agara | -1.762 |
ertodd | -1.752 |
Token | P |
Token ID | 47 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
� | +0.295 |
arium | +0.289 |
� | +0.282 |
之 | +0.281 |
Seymour | +0.277 |
Neg logit contributions | |
rahim | -0.343 |
enhagen | -0.308 |
aho | -0.306 |
ertodd | -0.279 |
agara | -0.279 |
Token | ly |
Token ID | 306 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
� | +0.672 |
arium | +0.656 |
之 | +0.640 |
� | +0.638 |
Seymour | +0.629 |
Neg logit contributions | |
rahim | -0.861 |
enhagen | -0.778 |
aho | -0.771 |
agara | -0.720 |
ertodd | -0.713 |
Token | Count |
Token ID | 12332 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
� | +1.616 |
arium | +1.526 |
� | +1.518 |
之 | +1.514 |
Nguyen | +1.461 |
Neg logit contributions | |
rahim | -2.740 |
enhagen | -2.541 |
aho | -2.510 |
agara | -2.403 |
ertodd | -2.384 |
Token | " |
Token ID | 366 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
� | +0.635 |
arium | +0.611 |
� | +0.595 |
之 | +0.585 |
Seymour | +0.571 |
Neg logit contributions | |
rahim | -1.405 |
enhagen | -1.307 |
aho | -1.290 |
agara | -1.246 |
ertodd | -1.228 |
Token | 94 |
Token ID | 5824 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
� | +0.304 |
arium | +0.300 |
� | +0.287 |
之 | +0.286 |
Seymour | +0.283 |
Neg logit contributions | |
rahim | -0.490 |
enhagen | -0.444 |
aho | -0.443 |
agara | -0.413 |
ertodd | -0.410 |
Token | "] |
Token ID | 8973 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
� | +0.651 |
arium | +0.642 |
� | +0.616 |
之 | +0.615 |
Seymour | +0.605 |
Neg logit contributions | |
rahim | -0.912 |
enhagen | -0.829 |
aho | -0.823 |
agara | -0.763 |
ertodd | -0.758 |
Token | [ |
Token ID | 685 |
Feature activation | -6.32e-04 |
Pos logit contributions | |
� | +0.932 |
arium | +0.914 |
� | +0.877 |
之 | +0.871 |
Seymour | +0.853 |
Neg logit contributions | |
rahim | -1.818 |
enhagen | -1.676 |
aho | -1.654 |
agara | -1.566 |
ertodd | -1.557 |
Token | AMD |
Token ID | 10324 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
� | +1.236 |
arium | +1.222 |
� | +1.181 |
之 | +1.178 |
Seymour | +1.145 |
Neg logit contributions | |
rahim | -1.554 |
enhagen | -1.412 |
aho | -1.406 |
agara | -1.295 |
ertodd | -1.287 |
Token | - |
Token ID | 12 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
� | +0.574 |
arium | +0.564 |
� | +0.546 |
之 | +0.543 |
Seymour | +0.532 |
Neg logit contributions | |
rahim | -0.817 |
enhagen | -0.750 |
aho | -0.742 |
agara | -0.686 |
ertodd | -0.684 |
Token | V |
Token ID | 53 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
� | +0.696 |
arium | +0.684 |
� | +0.660 |
之 | +0.657 |
Seymour | +0.646 |
Neg logit contributions | |
rahim | -1.043 |
enhagen | -0.956 |
aho | -0.944 |
agara | -0.884 |
ertodd | -0.880 |
Token | ). |
Token ID | 737 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
� | +0.787 |
arium | +0.775 |
� | +0.753 |
之 | +0.749 |
Seymour | +0.738 |
Neg logit contributions | |
rahim | -0.867 |
enhagen | -0.780 |
aho | -0.768 |
agara | -0.714 |
ertodd | -0.710 |
Token |
|
Token ID | 198 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
� | +1.074 |
arium | +1.055 |
� | +1.020 |
之 | +1.014 |
Seymour | +0.998 |
Neg logit contributions | |
rahim | -1.563 |
enhagen | -1.425 |
aho | -1.404 |
agara | -1.320 |
ertodd | -1.314 |
Token |
|
Token ID | 198 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
� | +1.512 |
arium | +1.471 |
� | +1.421 |
之 | +1.408 |
Seymour | +1.376 |
Neg logit contributions | |
rahim | -2.712 |
enhagen | -2.525 |
aho | -2.455 |
agara | -2.343 |
ertodd | -2.330 |
Token | The |
Token ID | 464 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
� | +1.974 |
arium | +1.931 |
� | +1.881 |
之 | +1.869 |
Seymour | +1.826 |
Neg logit contributions | |
rahim | -2.375 |
enhagen | -2.150 |
aho | -2.103 |
agara | -1.977 |
ertodd | -1.972 |
Token | first |
Token ID | 717 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
� | +0.981 |
arium | +0.967 |
� | +0.938 |
之 | +0.933 |
Seymour | +0.910 |
Neg logit contributions | |
rahim | -1.331 |
enhagen | -1.214 |
aho | -1.195 |
agara | -1.116 |
ertodd | -1.112 |
Token | instances |
Token ID | 10245 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
� | +0.335 |
arium | +0.332 |
� | +0.321 |
之 | +0.319 |
Seymour | +0.310 |
Neg logit contributions | |
rahim | -0.463 |
enhagen | -0.424 |
aho | -0.418 |
agara | -0.390 |
ertodd | -0.386 |
Token | on |
Token ID | 319 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
� | +0.383 |
arium | +0.374 |
� | +0.363 |
之 | +0.361 |
Seymour | +0.352 |
Neg logit contributions | |
rahim | -0.580 |
enhagen | -0.533 |
aho | -0.527 |
agara | -0.493 |
ertodd | -0.491 |
Token | EC |
Token ID | 13182 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
� | +0.160 |
arium | +0.159 |
� | +0.154 |
之 | +0.153 |
Seymour | +0.147 |
Neg logit contributions | |
rahim | -0.206 |
enhagen | -0.189 |
aho | -0.187 |
agara | -0.173 |
ertodd | -0.172 |
Token | ians |
Token ID | 1547 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
� | +0.794 |
arium | +0.776 |
� | +0.758 |
之 | +0.749 |
Seymour | +0.720 |
Neg logit contributions | |
rahim | -1.288 |
enhagen | -1.184 |
aho | -1.182 |
agara | -1.103 |
ertodd | -1.091 |
Token | Say |
Token ID | 13816 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
rahim | +0.119 |
enhagen | +0.107 |
aho | +0.107 |
agara | +0.100 |
ertodd | +0.098 |
Neg logit contributions | |
� | -0.086 |
arium | -0.083 |
之 | -0.082 |
� | -0.082 |
Seymour | -0.078 |
Token | School |
Token ID | 3961 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
� | +0.388 |
arium | +0.379 |
之 | +0.372 |
� | +0.370 |
Seymour | +0.352 |
Neg logit contributions | |
rahim | -0.515 |
enhagen | -0.467 |
aho | -0.464 |
agara | -0.434 |
ertodd | -0.422 |
Token | Should |
Token ID | 10358 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
� | +0.153 |
arium | +0.151 |
之 | +0.148 |
� | +0.147 |
Seymour | +0.141 |
Neg logit contributions | |
rahim | -0.215 |
aho | -0.194 |
enhagen | -0.193 |
agara | -0.179 |
ertodd | -0.176 |
Token | Start |
Token ID | 7253 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
� | +0.521 |
arium | +0.509 |
之 | +0.501 |
� | +0.500 |
Seymour | +0.485 |
Neg logit contributions | |
rahim | -0.646 |
enhagen | -0.577 |
aho | -0.576 |
agara | -0.535 |
ertodd | -0.524 |
Token | Later |
Token ID | 11450 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
� | +0.428 |
arium | +0.422 |
之 | +0.415 |
� | +0.412 |
Nguyen | +0.390 |
Neg logit contributions | |
rahim | -0.580 |
enhagen | -0.524 |
aho | -0.524 |
agara | -0.484 |
ertodd | -0.467 |
Token | For |
Token ID | 1114 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
� | +1.714 |
arium | +1.680 |
� | +1.625 |
之 | +1.617 |
Seymour | +1.583 |
Neg logit contributions | |
rahim | -2.630 |
enhagen | -2.402 |
aho | -2.372 |
agara | -2.230 |
ertodd | -2.216 |
Token | Te |
Token ID | 1665 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
� | +0.331 |
arium | +0.326 |
之 | +0.318 |
� | +0.314 |
Seymour | +0.300 |
Neg logit contributions | |
rahim | -0.413 |
aho | -0.371 |
enhagen | -0.368 |
agara | -0.340 |
ertodd | -0.332 |
Token | ens |
Token ID | 641 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
rahim | +0.005 |
enhagen | +0.005 |
aho | +0.005 |
agara | +0.005 |
ertodd | +0.004 |
Neg logit contributions | |
� | -0.005 |
arium | -0.005 |
之 | -0.005 |
� | -0.005 |
Seymour | -0.004 |
Token | ' |
Token ID | 6 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
� | +0.980 |
arium | +0.960 |
� | +0.932 |
之 | +0.930 |
Seymour | +0.903 |
Neg logit contributions | |
rahim | -1.385 |
enhagen | -1.255 |
aho | -1.247 |
agara | -1.167 |
ertodd | -1.152 |
Token | Health |
Token ID | 3893 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
� | +0.727 |
arium | +0.712 |
� | +0.697 |
之 | +0.692 |
Seymour | +0.659 |
Neg logit contributions | |
rahim | -1.046 |
aho | -0.942 |
enhagen | -0.940 |
agara | -0.877 |
ertodd | -0.863 |
Token | IC |
Token ID | 2149 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
rahim | +0.275 |
aho | +0.241 |
enhagen | +0.239 |
agara | +0.217 |
ertodd | +0.213 |
Neg logit contributions | |
� | -0.305 |
arium | -0.303 |
之 | -0.294 |
� | -0.293 |
Seymour | -0.287 |
Token | LES |
Token ID | 28378 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
rahim | +0.221 |
enhagen | +0.196 |
aho | +0.193 |
ertodd | +0.177 |
agara | +0.175 |
Neg logit contributions | |
� | -0.245 |
arium | -0.243 |
� | -0.238 |
之 | -0.237 |
Seymour | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
� | +0.237 |
arium | +0.234 |
� | +0.225 |
之 | +0.224 |
Seymour | +0.218 |
Neg logit contributions | |
rahim | -0.340 |
enhagen | -0.309 |
aho | -0.307 |
agara | -0.283 |
ertodd | -0.282 |
Token | LAT |
Token ID | 42355 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
� | +0.468 |
arium | +0.464 |
� | +0.444 |
之 | +0.441 |
Seymour | +0.431 |
Neg logit contributions | |
rahim | -0.695 |
enhagen | -0.630 |
aho | -0.625 |
agara | -0.579 |
ertodd | -0.575 |
Token | R |
Token ID | 49 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
� | +0.708 |
arium | +0.701 |
之 | +0.672 |
� | +0.669 |
Seymour | +0.650 |
Neg logit contributions | |
rahim | -1.138 |
enhagen | -1.044 |
aho | -1.036 |
agara | -0.966 |
ertodd | -0.956 |
Token | IN |
Token ID | 1268 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
� | +1.288 |
arium | +1.260 |
� | +1.220 |
之 | +1.210 |
Seymour | +1.186 |
Neg logit contributions | |
rahim | -2.212 |
enhagen | -2.022 |
aho | -2.014 |
agara | -1.876 |
ertodd | -1.864 |
Token | ES |
Token ID | 1546 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
� | +1.612 |
arium | +1.582 |
� | +1.527 |
之 | +1.514 |
Seymour | +1.486 |
Neg logit contributions | |
rahim | -2.712 |
enhagen | -2.485 |
aho | -2.463 |
agara | -2.310 |
ertodd | -2.298 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
� | +0.480 |
arium | +0.473 |
� | +0.456 |
之 | +0.453 |
Seymour | +0.442 |
Neg logit contributions | |
rahim | -0.729 |
enhagen | -0.664 |
aho | -0.659 |
agara | -0.614 |
ertodd | -0.607 |
Token | B |
Token ID | 347 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
� | +0.569 |
arium | +0.567 |
� | +0.542 |
之 | +0.537 |
Seymour | +0.525 |
Neg logit contributions | |
rahim | -0.905 |
enhagen | -0.823 |
aho | -0.818 |
agara | -0.760 |
ertodd | -0.755 |
Token | UN |
Token ID | 4944 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
� | +0.726 |
arium | +0.722 |
� | +0.686 |
之 | +0.682 |
Seymour | +0.673 |
Neg logit contributions | |
rahim | -1.224 |
enhagen | -1.111 |
aho | -1.107 |
agara | -1.036 |
ertodd | -1.021 |
Token | K |
Token ID | 42 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
rahim | +0.458 |
enhagen | +0.426 |
aho | +0.420 |
agara | +0.389 |
ertodd | +0.387 |
Neg logit contributions | |
arium | -0.290 |
� | -0.289 |
� | -0.278 |
之 | -0.278 |
Seymour | -0.273 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
arium | +0.071 |
� | +0.071 |
之 | +0.066 |
Seymour | +0.066 |
� | +0.065 |
Neg logit contributions | |
rahim | -0.153 |
aho | -0.140 |
enhagen | -0.138 |
agara | -0.131 |
ertodd | -0.129 |
Token | - |
Token ID | 12 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
arium | +0.517 |
� | +0.514 |
之 | +0.483 |
� | +0.475 |
Seymour | +0.474 |
Neg logit contributions | |
rahim | -1.106 |
aho | -1.007 |
enhagen | -0.976 |
ertodd | -0.936 |
agara | -0.934 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
arium | +0.344 |
� | +0.340 |
之 | +0.323 |
� | +0.314 |
Seymour | +0.310 |
Neg logit contributions | |
rahim | -0.653 |
aho | -0.592 |
enhagen | -0.590 |
agara | -0.554 |
ertodd | -0.546 |
Token | / |
Token ID | 14 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
� | +1.303 |
arium | +1.292 |
� | +1.246 |
之 | +1.240 |
Seymour | +1.208 |
Neg logit contributions | |
rahim | -1.957 |
enhagen | -1.769 |
aho | -1.759 |
agara | -1.634 |
ertodd | -1.627 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +0.603 |
arium | +0.596 |
� | +0.565 |
之 | +0.565 |
Seymour | +0.551 |
Neg logit contributions | |
rahim | -1.389 |
aho | -1.280 |
enhagen | -1.276 |
agara | -1.204 |
ertodd | -1.199 |
Token | "] |
Token ID | 8973 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
arium | +0.446 |
� | +0.445 |
� | +0.427 |
之 | +0.424 |
Schwarzenegger | +0.418 |
Neg logit contributions | |
rahim | -0.608 |
aho | -0.558 |
enhagen | -0.545 |
ertodd | -0.509 |
agara | -0.506 |
Token | [ |
Token ID | 685 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
� | +1.373 |
arium | +1.331 |
� | +1.290 |
之 | +1.276 |
Seymour | +1.248 |
Neg logit contributions | |
rahim | -2.915 |
enhagen | -2.726 |
aho | -2.643 |
agara | -2.534 |
ertodd | -2.519 |
Token | EC |
Token ID | 2943 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
� | +0.547 |
arium | +0.539 |
� | +0.520 |
之 | +0.519 |
Seymour | +0.509 |
Neg logit contributions | |
rahim | -0.670 |
aho | -0.598 |
enhagen | -0.598 |
agara | -0.555 |
ertodd | -0.546 |
Token | O |
Token ID | 46 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
rahim | +0.349 |
aho | +0.318 |
enhagen | +0.316 |
ertodd | +0.293 |
agara | +0.293 |
Neg logit contributions | |
arium | -0.197 |
� | -0.191 |
之 | -0.182 |
Seymour | -0.181 |
Schwarzenegger | -0.180 |
Token | " |
Token ID | 366 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
rahim | +0.239 |
enhagen | +0.216 |
aho | +0.216 |
agara | +0.199 |
ertodd | +0.196 |
Neg logit contributions | |
� | -0.147 |
arium | -0.147 |
之 | -0.138 |
� | -0.138 |
Seymour | -0.136 |
Token | A |
Token ID | 32 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
� | +0.903 |
arium | +0.894 |
� | +0.855 |
之 | +0.852 |
Seymour | +0.846 |
Neg logit contributions | |
rahim | -1.238 |
enhagen | -1.120 |
aho | -1.107 |
agara | -1.033 |
ertodd | -1.021 |
Token | me |
Token ID | 502 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
� | +0.077 |
arium | +0.075 |
之 | +0.074 |
� | +0.073 |
Nguyen | +0.070 |
Neg logit contributions | |
rahim | -0.092 |
enhagen | -0.084 |
aho | -0.082 |
agara | -0.076 |
ertodd | -0.075 |
Token | later |
Token ID | 1568 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
rahim | +0.145 |
enhagen | +0.134 |
aho | +0.133 |
agara | +0.125 |
ertodd | +0.124 |
Neg logit contributions | |
� | -0.075 |
arium | -0.073 |
� | -0.070 |
之 | -0.070 |
Seymour | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
� | +1.199 |
arium | +1.173 |
� | +1.134 |
之 | +1.130 |
Seymour | +1.101 |
Neg logit contributions | |
rahim | -1.846 |
enhagen | -1.687 |
aho | -1.668 |
agara | -1.566 |
ertodd | -1.556 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
rahim | +0.231 |
enhagen | +0.209 |
aho | +0.207 |
agara | +0.192 |
ertodd | +0.191 |
Neg logit contributions | |
� | -0.172 |
arium | -0.170 |
� | -0.164 |
之 | -0.164 |
Seymour | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
rahim | +0.487 |
aho | +0.439 |
enhagen | +0.429 |
agara | +0.400 |
ertodd | +0.396 |
Neg logit contributions | |
arium | -0.352 |
� | -0.349 |
之 | -0.335 |
Seymour | -0.334 |
� | -0.332 |
Token | Rated |
Token ID | 15322 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
rahim | +0.399 |
aho | +0.358 |
enhagen | +0.356 |
agara | +0.332 |
ertodd | +0.324 |
Neg logit contributions | |
� | -0.307 |
arium | -0.305 |
之 | -0.294 |
� | -0.291 |
Seymour | -0.291 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
� | +1.700 |
arium | +1.672 |
� | +1.615 |
之 | +1.605 |
Seymour | +1.579 |
Neg logit contributions | |
rahim | -2.569 |
enhagen | -2.348 |
aho | -2.313 |
agara | -2.176 |
ertodd | -2.167 |
Token | out |
Token ID | 503 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
rahim | +0.310 |
enhagen | +0.281 |
aho | +0.279 |
agara | +0.262 |
ertodd | +0.261 |
Neg logit contributions | |
� | -0.190 |
arium | -0.187 |
� | -0.179 |
之 | -0.179 |
Seymour | -0.175 |
Token | of |
Token ID | 286 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
� | +0.018 |
arium | +0.018 |
之 | +0.017 |
� | +0.017 |
Seymour | +0.017 |
Neg logit contributions | |
rahim | -0.029 |
aho | -0.026 |
enhagen | -0.026 |
agara | -0.024 |
ertodd | -0.024 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
� | +0.022 |
arium | +0.022 |
� | +0.021 |
之 | +0.021 |
Seymour | +0.021 |
Neg logit contributions | |
rahim | -0.031 |
enhagen | -0.028 |
aho | -0.028 |
agara | -0.026 |
ertodd | -0.026 |
Token | by |
Token ID | 416 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
� | +0.566 |
arium | +0.558 |
� | +0.540 |
之 | +0.538 |
Seymour | +0.528 |
Neg logit contributions | |
rahim | -0.683 |
enhagen | -0.613 |
aho | -0.609 |
agara | -0.565 |
ertodd | -0.561 |
Token | Sigma |
Token ID | 31669 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
� | +0.205 |
arium | +0.200 |
� | +0.194 |
之 | +0.190 |
Seymour | +0.185 |
Neg logit contributions | |
rahim | -0.343 |
enhagen | -0.314 |
aho | -0.310 |
ertodd | -0.293 |
agara | -0.290 |
Token | : |
Token ID | 25 |
Feature activation | -9.81e-03 |
Pos logit contributions | |
� | +0.955 |
arium | +0.936 |
� | +0.902 |
之 | +0.890 |
Seymour | +0.877 |
Neg logit contributions | |
rahim | -1.561 |
enhagen | -1.429 |
aho | -1.417 |
agara | -1.333 |
ertodd | -1.323 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
arium | +0.026 |
� | +0.026 |
� | +0.025 |
之 | +0.025 |
Seymour | +0.025 |
Neg logit contributions | |
rahim | -0.037 |
enhagen | -0.033 |
aho | -0.033 |
agara | -0.031 |
ertodd | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
� | +0.519 |
arium | +0.509 |
� | +0.492 |
之 | +0.489 |
Seymour | +0.480 |
Neg logit contributions | |
rahim | -0.821 |
enhagen | -0.744 |
aho | -0.742 |
agara | -0.694 |
ertodd | -0.692 |
Token | AS |
Token ID | 1921 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
arium | +0.352 |
� | +0.351 |
Seymour | +0.339 |
� | +0.338 |
之 | +0.335 |
Neg logit contributions | |
rahim | -0.378 |
aho | -0.337 |
enhagen | -0.336 |
agara | -0.310 |
ertodd | -0.304 |
Token | Q |
Token ID | 48 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
� | +0.266 |
arium | +0.265 |
� | +0.255 |
之 | +0.248 |
Seymour | +0.246 |
Neg logit contributions | |
rahim | -0.375 |
enhagen | -0.340 |
aho | -0.338 |
agara | -0.317 |
ertodd | -0.313 |
Token | ( |
Token ID | 357 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +1.692 |
arium | +1.674 |
� | +1.610 |
之 | +1.597 |
Seymour | +1.574 |
Neg logit contributions | |
rahim | -2.572 |
enhagen | -2.349 |
aho | -2.323 |
agara | -2.179 |
ertodd | -2.162 |
Token | The |
Token ID | 464 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
� | +0.512 |
arium | +0.505 |
� | +0.488 |
之 | +0.487 |
Seymour | +0.484 |
Neg logit contributions | |
rahim | -0.560 |
enhagen | -0.500 |
aho | -0.499 |
agara | -0.460 |
ertodd | -0.449 |
Token | American |
Token ID | 1605 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
rahim | +0.169 |
enhagen | +0.154 |
aho | +0.152 |
agara | +0.142 |
ertodd | +0.140 |
Neg logit contributions | |
� | -0.121 |
arium | -0.118 |
� | -0.115 |
之 | -0.113 |
Seymour | -0.110 |
Token | Society |
Token ID | 7023 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
rahim | +0.075 |
enhagen | +0.068 |
aho | +0.068 |
agara | +0.064 |
ertodd | +0.061 |
Neg logit contributions | |
� | -0.051 |
arium | -0.049 |
� | -0.048 |
之 | -0.047 |
Seymour | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
rahim | +0.086 |
enhagen | +0.079 |
aho | +0.078 |
agara | +0.073 |
ertodd | +0.073 |
Neg logit contributions | |
� | -0.056 |
arium | -0.055 |
� | -0.053 |
之 | -0.053 |
Seymour | -0.051 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
rahim | +0.480 |
aho | +0.437 |
enhagen | +0.431 |
agara | +0.401 |
ertodd | +0.397 |
Neg logit contributions | |
� | -0.310 |
arium | -0.305 |
之 | -0.293 |
Seymour | -0.290 |
Nguyen | -0.289 |
Token | : |
Token ID | 25 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
� | +0.070 |
arium | +0.069 |
� | +0.067 |
之 | +0.067 |
Seymour | +0.066 |
Neg logit contributions | |
rahim | -0.076 |
enhagen | -0.069 |
aho | -0.069 |
ertodd | -0.062 |
agara | -0.062 |
Token | 900 |
Token ID | 12865 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
� | +0.484 |
arium | +0.479 |
之 | +0.460 |
� | +0.455 |
Seymour | +0.453 |
Neg logit contributions | |
rahim | -0.727 |
aho | -0.658 |
enhagen | -0.653 |
agara | -0.608 |
ertodd | -0.602 |
Token | + |
Token ID | 10 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
� | +0.243 |
arium | +0.240 |
之 | +0.231 |
� | +0.231 |
Seymour | +0.226 |
Neg logit contributions | |
rahim | -0.335 |
enhagen | -0.308 |
aho | -0.304 |
agara | -0.280 |
ertodd | -0.275 |
Token | 30 |
Token ID | 1270 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
� | +0.219 |
arium | +0.217 |
之 | +0.208 |
� | +0.206 |
Seymour | +0.205 |
Neg logit contributions | |
rahim | -0.326 |
aho | -0.295 |
enhagen | -0.294 |
agara | -0.273 |
ertodd | -0.270 |
Token | "] |
Token ID | 8973 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
rahim | +0.040 |
enhagen | +0.036 |
aho | +0.036 |
ertodd | +0.033 |
agara | +0.033 |
Neg logit contributions | |
� | -0.036 |
arium | -0.036 |
� | -0.034 |
之 | -0.034 |
Seymour | -0.034 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
� | +1.626 |
arium | +1.596 |
� | +1.538 |
之 | +1.530 |
Seymour | +1.500 |
Neg logit contributions | |
rahim | -2.629 |
enhagen | -2.407 |
aho | -2.377 |
agara | -2.236 |
ertodd | -2.228 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
� | +1.099 |
arium | +1.061 |
Seymour | +1.028 |
之 | +1.028 |
� | +1.026 |
Neg logit contributions | |
rahim | -2.144 |
enhagen | -2.003 |
aho | -1.949 |
agara | -1.879 |
ertodd | -1.871 |
Token | d |
Token ID | 288 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
� | +0.819 |
arium | +0.808 |
� | +0.774 |
之 | +0.772 |
Seymour | +0.755 |
Neg logit contributions | |
rahim | -1.353 |
enhagen | -1.237 |
aho | -1.226 |
agara | -1.151 |
ertodd | -1.141 |
Token | 4 |
Token ID | 19 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
� | +0.476 |
arium | +0.464 |
之 | +0.453 |
Seymour | +0.453 |
� | +0.443 |
Neg logit contributions | |
rahim | -0.899 |
aho | -0.821 |
enhagen | -0.806 |
agara | -0.771 |
ertodd | -0.765 |
Token | { |
Token ID | 1391 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
rahim | +0.190 |
aho | +0.173 |
enhagen | +0.170 |
agara | +0.157 |
ertodd | +0.154 |
Neg logit contributions | |
� | -0.162 |
arium | -0.160 |
之 | -0.155 |
� | -0.154 |
Seymour | -0.151 |
Token | consider |
Token ID | 2074 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
rahim | +0.901 |
aho | +0.814 |
enhagen | +0.813 |
agara | +0.756 |
ertodd | +0.741 |
Neg logit contributions | |
� | -0.708 |
arium | -0.686 |
之 | -0.668 |
� | -0.665 |
Seymour | -0.647 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
� | +0.177 |
arium | +0.173 |
之 | +0.167 |
� | +0.167 |
Seymour | +0.162 |
Neg logit contributions | |
rahim | -0.253 |
enhagen | -0.233 |
aho | -0.226 |
agara | -0.217 |
ertodd | -0.209 |
Token | successful |
Token ID | 4388 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
rahim | +0.396 |
enhagen | +0.358 |
aho | +0.353 |
agara | +0.334 |
ertodd | +0.325 |
Neg logit contributions | |
� | -0.288 |
arium | -0.284 |
� | -0.276 |
之 | -0.273 |
Seymour | -0.264 |
Token | year |
Token ID | 614 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
rahim | +0.781 |
enhagen | +0.711 |
aho | +0.698 |
agara | +0.655 |
ertodd | +0.637 |
Neg logit contributions | |
� | -0.514 |
arium | -0.502 |
之 | -0.486 |
� | -0.485 |
Seymour | -0.467 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
rahim | +0.155 |
enhagen | +0.142 |
aho | +0.139 |
agara | +0.130 |
ertodd | +0.130 |
Neg logit contributions | |
� | -0.106 |
arium | -0.104 |
� | -0.100 |
之 | -0.100 |
Seymour | -0.098 |
Token | Marc |
Token ID | 13067 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
rahim | +0.706 |
enhagen | +0.641 |
aho | +0.629 |
agara | +0.590 |
ertodd | +0.572 |
Neg logit contributions | |
arium | -0.503 |
� | -0.503 |
之 | -0.477 |
� | -0.474 |
Schwarzenegger | -0.454 |
Token | Ber |
Token ID | 4312 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
rahim | +2.262 |
enhagen | +2.105 |
aho | +2.048 |
agara | +1.974 |
ertodd | +1.849 |
Neg logit contributions | |
arium | -1.323 |
� | -1.300 |
之 | -1.276 |
� | -1.226 |
Schwarzenegger | -1.163 |
Token | ge |
Token ID | 469 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
rahim | +1.437 |
enhagen | +1.321 |
aho | +1.316 |
agara | +1.243 |
ertodd | +1.235 |
Neg logit contributions | |
� | -0.610 |
arium | -0.597 |
之 | -0.567 |
� | -0.566 |
Seymour | -0.550 |
Token | vin |
Token ID | 7114 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
rahim | +0.505 |
enhagen | +0.454 |
aho | +0.448 |
agara | +0.416 |
ertodd | +0.414 |
Neg logit contributions | |
� | -0.448 |
arium | -0.441 |
� | -0.428 |
之 | -0.428 |
Seymour | -0.420 |
Token | completely |
Token ID | 3190 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
rahim | +0.501 |
enhagen | +0.459 |
aho | +0.453 |
agara | +0.424 |
ertodd | +0.413 |
Neg logit contributions | |
� | -0.381 |
arium | -0.375 |
� | -0.363 |
之 | -0.361 |
Seymour | -0.350 |
Token | overhaul |
Token ID | 18708 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
� | +0.556 |
arium | +0.548 |
� | +0.533 |
之 | +0.530 |
Seymour | +0.521 |
Neg logit contributions | |
rahim | -0.576 |
enhagen | -0.517 |
aho | -0.509 |
agara | -0.472 |
ertodd | -0.468 |
Token | witz |
Token ID | 28155 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rahim | +0.549 |
enhagen | +0.504 |
aho | +0.504 |
agara | +0.468 |
ertodd | +0.451 |
Neg logit contributions | |
� | -0.378 |
arium | -0.371 |
� | -0.357 |
之 | -0.356 |
Seymour | -0.341 |
Token | West |
Token ID | 2688 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
rahim | +0.467 |
enhagen | +0.430 |
aho | +0.429 |
agara | +0.399 |
ertodd | +0.383 |
Neg logit contributions | |
� | -0.321 |
arium | -0.314 |
之 | -0.302 |
� | -0.302 |
Seymour | -0.288 |
Token | chester |
Token ID | 35983 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
rahim | +0.238 |
enhagen | +0.216 |
aho | +0.213 |
agara | +0.199 |
ertodd | +0.193 |
Neg logit contributions | |
� | -0.193 |
arium | -0.188 |
� | -0.182 |
之 | -0.181 |
Seymour | -0.176 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
� | +0.147 |
arium | +0.145 |
� | +0.139 |
之 | +0.137 |
Seymour | +0.135 |
Neg logit contributions | |
rahim | -0.209 |
enhagen | -0.191 |
aho | -0.189 |
agara | -0.177 |
ertodd | -0.174 |
Token | hour |
Token ID | 1711 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
rahim | +0.138 |
enhagen | +0.127 |
aho | +0.126 |
agara | +0.119 |
ertodd | +0.118 |
Neg logit contributions | |
� | -0.064 |
arium | -0.062 |
之 | -0.059 |
� | -0.058 |
Seymour | -0.057 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
rahim | +0.103 |
enhagen | +0.094 |
aho | +0.093 |
agara | +0.087 |
ertodd | +0.086 |
Neg logit contributions | |
� | -0.077 |
arium | -0.075 |
� | -0.073 |
之 | -0.073 |
Seymour | -0.072 |
Token | Pretty |
Token ID | 20090 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
rahim | +2.175 |
aho | +1.956 |
enhagen | +1.934 |
agara | +1.791 |
ertodd | +1.782 |
Neg logit contributions | |
� | -1.605 |
arium | -1.587 |
之 | -1.537 |
� | -1.503 |
urable | -1.457 |
Token | simple |
Token ID | 2829 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
rahim | +0.296 |
enhagen | +0.266 |
aho | +0.265 |
agara | +0.246 |
ertodd | +0.241 |
Neg logit contributions | |
� | -0.230 |
arium | -0.227 |
之 | -0.219 |
� | -0.217 |
Seymour | -0.212 |
Token | Paul |
Token ID | 3362 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
� | +0.153 |
arium | +0.152 |
之 | +0.146 |
� | +0.145 |
Seymour | +0.141 |
Neg logit contributions | |
rahim | -0.218 |
enhagen | -0.198 |
aho | -0.197 |
agara | -0.184 |
ertodd | -0.181 |
Token | : |
Token ID | 25 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
rahim | +0.416 |
aho | +0.386 |
enhagen | +0.385 |
agara | +0.353 |
ertodd | +0.349 |
Neg logit contributions | |
� | -0.296 |
arium | -0.296 |
之 | -0.285 |
� | -0.278 |
Seymour | -0.271 |
Token |
|
Token ID | 198 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
� | +0.183 |
arium | +0.180 |
之 | +0.173 |
� | +0.173 |
Seymour | +0.168 |
Neg logit contributions | |
rahim | -0.270 |
enhagen | -0.244 |
aho | -0.242 |
agara | -0.227 |
ertodd | -0.225 |
Token | i |
Token ID | 72 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
rahim | +1.066 |
aho | +0.988 |
enhagen | +0.988 |
ertodd | +0.932 |
agara | +0.927 |
Neg logit contributions | |
� | -0.346 |
arium | -0.324 |
� | -0.310 |
之 | -0.307 |
Nguyen | -0.298 |
Token | - |
Token ID | 12 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
rahim | +0.609 |
enhagen | +0.566 |
aho | +0.565 |
ertodd | +0.534 |
agara | +0.532 |
Neg logit contributions | |
� | -0.283 |
arium | -0.270 |
� | -0.258 |
之 | -0.254 |
Seymour | -0.252 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
� | +0.305 |
arium | +0.293 |
� | +0.283 |
之 | +0.280 |
Seymour | +0.275 |
Neg logit contributions | |
rahim | -0.590 |
enhagen | -0.543 |
aho | -0.537 |
ertodd | -0.509 |
agara | -0.506 |
Token | ], |
Token ID | 4357 |
Feature activation | -8.67e-05 |
Pos logit contributions | |
� | +0.332 |
arium | +0.323 |
� | +0.309 |
之 | +0.306 |
Seymour | +0.302 |
Neg logit contributions | |
rahim | -0.519 |
enhagen | -0.478 |
aho | -0.472 |
ertodd | -0.445 |
agara | -0.440 |
Token | $ |
Token ID | 720 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
� | +0.000 |
arium | +0.000 |
� | +0.000 |
之 | +0.000 |
Seymour | +0.000 |
Neg logit contributions | |
rahim | -0.000 |
enhagen | -0.000 |
aho | -0.000 |
ertodd | -0.000 |
agara | -0.000 |
Token | font |
Token ID | 10331 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
rahim | +0.333 |
enhagen | +0.299 |
aho | +0.298 |
agara | +0.274 |
ertodd | +0.272 |
Neg logit contributions | |
� | -0.274 |
arium | -0.269 |
之 | -0.260 |
� | -0.258 |
Seymour | -0.258 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
rahim | +2.315 |
enhagen | +2.140 |
aho | +2.115 |
ertodd | +2.013 |
agara | +1.970 |
Neg logit contributions | |
� | -1.327 |
arium | -1.268 |
之 | -1.210 |
� | -1.209 |
Seymour | -1.201 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
� | +0.190 |
arium | +0.187 |
� | +0.182 |
之 | +0.180 |
Seymour | +0.179 |
Neg logit contributions | |
rahim | -0.152 |
aho | -0.134 |
enhagen | -0.134 |
ertodd | -0.123 |
agara | -0.121 |
Token | $ |
Token ID | 720 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
rahim | +0.515 |
enhagen | +0.465 |
aho | +0.465 |
ertodd | +0.430 |
agara | +0.430 |
Neg logit contributions | |
� | -0.344 |
arium | -0.338 |
� | -0.324 |
之 | -0.319 |
Nguyen | -0.318 |
Token | brush |
Token ID | 32680 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
rahim | +0.209 |
enhagen | +0.187 |
aho | +0.187 |
agara | +0.173 |
ertodd | +0.172 |
Neg logit contributions | |
� | -0.168 |
arium | -0.165 |
� | -0.159 |
之 | -0.158 |
Nguyen | -0.158 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
rahim | +1.078 |
enhagen | +0.997 |
aho | +0.981 |
ertodd | +0.933 |
agara | +0.924 |
Neg logit contributions | |
� | -0.591 |
arium | -0.559 |
� | -0.544 |
之 | -0.538 |
Seymour | -0.534 |
Token | while |
Token ID | 981 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
� | +0.509 |
arium | +0.500 |
� | +0.482 |
之 | +0.481 |
Seymour | +0.469 |
Neg logit contributions | |
rahim | -0.781 |
enhagen | -0.715 |
aho | -0.702 |
agara | -0.660 |
ertodd | -0.652 |
Token | on |
Token ID | 319 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
rahim | +0.314 |
enhagen | +0.284 |
aho | +0.281 |
agara | +0.263 |
ertodd | +0.259 |
Neg logit contributions | |
arium | -0.218 |
� | -0.218 |
之 | -0.208 |
� | -0.206 |
Seymour | -0.201 |
Token | � |
Token ID | 564 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
rahim | +1.027 |
enhagen | +0.962 |
aho | +0.941 |
agara | +0.875 |
ertodd | +0.851 |
Neg logit contributions | |
arium | -0.840 |
� | -0.837 |
之 | -0.815 |
� | -0.803 |
Schwarzenegger | -0.779 |
Token | � |
Token ID | 250 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
rahim | +0.282 |
enhagen | +0.259 |
aho | +0.256 |
agara | +0.242 |
ertodd | +0.238 |
Neg logit contributions | |
� | -0.182 |
arium | -0.180 |
Seymour | -0.173 |
之 | -0.172 |
Nguyen | -0.170 |
Token | v |
Token ID | 85 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
rahim | +0.314 |
enhagen | +0.285 |
aho | +0.279 |
agara | +0.261 |
ertodd | +0.255 |
Neg logit contributions | |
arium | -0.227 |
� | -0.227 |
之 | -0.217 |
Seymour | -0.217 |
� | -0.216 |
Token | ac |
Token ID | 330 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
rahim | +1.018 |
enhagen | +0.944 |
aho | +0.934 |
agara | +0.891 |
ertodd | +0.865 |
Neg logit contributions | |
� | -0.510 |
arium | -0.474 |
� | -0.466 |
之 | -0.466 |
Seymour | -0.460 |
Token | ation |
Token ID | 341 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
rahim | +1.665 |
enhagen | +1.536 |
aho | +1.503 |
agara | +1.390 |
ropolitan | +1.329 |
Neg logit contributions | |
� | -1.651 |
之 | -1.644 |
arium | -1.593 |
Seymour | -1.568 |
� | -1.560 |
Token | � |
Token ID | 447 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
rahim | +0.038 |
enhagen | +0.035 |
aho | +0.034 |
agara | +0.032 |
ertodd | +0.032 |
Neg logit contributions | |
� | -0.027 |
arium | -0.027 |
之 | -0.026 |
� | -0.026 |
Seymour | -0.025 |
Token | � |
Token ID | 251 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
� | +0.267 |
arium | +0.263 |
之 | +0.253 |
Seymour | +0.252 |
� | +0.252 |
Neg logit contributions | |
rahim | -0.363 |
enhagen | -0.331 |
aho | -0.329 |
agara | -0.308 |
ertodd | -0.304 |
Token | ; |
Token ID | 26 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
rahim | +0.360 |
enhagen | +0.331 |
aho | +0.326 |
agara | +0.305 |
ertodd | +0.302 |
Neg logit contributions | |
� | -0.226 |
arium | -0.224 |
� | -0.214 |
之 | -0.214 |
Seymour | -0.209 |
Token | a |
Token ID | 257 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
rahim | +0.712 |
enhagen | +0.640 |
aho | +0.629 |
agara | +0.588 |
ertodd | +0.579 |
Neg logit contributions | |
� | -0.517 |
arium | -0.514 |
之 | -0.494 |
� | -0.492 |
Seymour | -0.473 |
Token | media |
Token ID | 2056 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
rahim | +0.055 |
enhagen | +0.051 |
aho | +0.050 |
agara | +0.047 |
ertodd | +0.046 |
Neg logit contributions | |
� | -0.035 |
arium | -0.035 |
� | -0.034 |
之 | -0.033 |
Nguyen | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rahim | +1.043 |
enhagen | +0.957 |
aho | +0.934 |
agara | +0.884 |
ertodd | +0.868 |
Neg logit contributions | |
� | -0.688 |
arium | -0.681 |
之 | -0.660 |
� | -0.651 |
Nguyen | -0.636 |
Token | � |
Token ID | 564 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rahim | +0.487 |
enhagen | +0.440 |
aho | +0.437 |
agara | +0.415 |
ertodd | +0.405 |
Neg logit contributions | |
� | -0.319 |
arium | -0.316 |
� | -0.307 |
之 | -0.306 |
Seymour | -0.295 |
Token | � |
Token ID | 250 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
rahim | +0.479 |
enhagen | +0.432 |
aho | +0.431 |
agara | +0.407 |
ertodd | +0.398 |
Neg logit contributions | |
� | -0.353 |
arium | -0.347 |
Seymour | -0.336 |
之 | -0.333 |
Nguyen | -0.331 |
Token | b |
Token ID | 65 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
rahim | +0.104 |
enhagen | +0.093 |
aho | +0.093 |
agara | +0.088 |
ertodd | +0.084 |
Neg logit contributions | |
� | -0.073 |
arium | -0.071 |
之 | -0.069 |
� | -0.068 |
Seymour | -0.068 |
Token | unch |
Token ID | 3316 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
rahim | +0.614 |
aho | +0.533 |
enhagen | +0.530 |
agara | +0.489 |
ertodd | +0.481 |
Neg logit contributions | |
� | -0.665 |
arium | -0.644 |
之 | -0.641 |
� | -0.634 |
Seymour | -0.620 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
rahim | +2.354 |
enhagen | +2.160 |
aho | +2.112 |
ertodd | +2.001 |
agara | +1.991 |
Neg logit contributions | |
� | -1.647 |
arium | -1.640 |
之 | -1.596 |
Nguyen | -1.580 |
� | -1.578 |
Token | mag |
Token ID | 2153 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
rahim | +0.123 |
enhagen | +0.111 |
aho | +0.110 |
agara | +0.103 |
ertodd | +0.102 |
Neg logit contributions | |
arium | -0.089 |
� | -0.089 |
之 | -0.086 |
� | -0.085 |
Seymour | -0.083 |
Token | g |
Token ID | 70 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
rahim | +0.383 |
enhagen | +0.345 |
aho | +0.344 |
agara | +0.320 |
ertodd | +0.317 |
Neg logit contributions | |
� | -0.270 |
arium | -0.265 |
之 | -0.258 |
� | -0.257 |
Seymour | -0.250 |
Token | ots |
Token ID | 1747 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
� | +0.724 |
arium | +0.704 |
之 | +0.690 |
� | +0.690 |
Seymour | +0.675 |
Neg logit contributions | |
rahim | -0.797 |
enhagen | -0.715 |
aho | -0.707 |
agara | -0.660 |
ertodd | -0.652 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
rahim | +0.344 |
enhagen | +0.311 |
aho | +0.308 |
agara | +0.289 |
ertodd | +0.286 |
Neg logit contributions | |
� | -0.264 |
arium | -0.264 |
之 | -0.253 |
� | -0.252 |
Nguyen | -0.247 |
Token | how |
Token ID | 703 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
rahim | +0.148 |
enhagen | +0.135 |
aho | +0.133 |
agara | +0.125 |
ertodd | +0.122 |
Neg logit contributions | |
� | -0.113 |
arium | -0.111 |
� | -0.108 |
之 | -0.108 |
Seymour | -0.105 |
Token | many |
Token ID | 867 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
� | +0.039 |
arium | +0.039 |
� | +0.038 |
之 | +0.037 |
Seymour | +0.037 |
Neg logit contributions | |
rahim | -0.047 |
enhagen | -0.042 |
aho | -0.042 |
agara | -0.039 |
ertodd | -0.038 |
Token | turtles |
Token ID | 36288 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
rahim | +0.379 |
aho | +0.342 |
enhagen | +0.338 |
agara | +0.319 |
ertodd | +0.309 |
Neg logit contributions | |
� | -0.301 |
arium | -0.290 |
之 | -0.286 |
� | -0.284 |
Seymour | -0.274 |
Token | worldwide |
Token ID | 8688 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
� | +0.131 |
arium | +0.125 |
� | +0.124 |
之 | +0.124 |
Seymour | +0.119 |
Neg logit contributions | |
rahim | -0.170 |
enhagen | -0.155 |
aho | -0.155 |
agara | -0.145 |
ertodd | -0.142 |
Token | had |
Token ID | 550 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
� | +0.017 |
arium | +0.016 |
� | +0.016 |
之 | +0.016 |
Seymour | +0.016 |
Neg logit contributions | |
rahim | -0.022 |
enhagen | -0.020 |
aho | -0.020 |
agara | -0.019 |
ertodd | -0.019 |
Token | ingested |
Token ID | 44694 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
� | +0.286 |
arium | +0.281 |
� | +0.275 |
之 | +0.274 |
Seymour | +0.269 |
Neg logit contributions | |
rahim | -0.280 |
enhagen | -0.250 |
aho | -0.247 |
agara | -0.229 |
ertodd | -0.226 |
Token | debris |
Token ID | 16468 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
rahim | +0.540 |
enhagen | +0.488 |
aho | +0.488 |
agara | +0.456 |
ertodd | +0.445 |
Neg logit contributions | |
� | -0.440 |
arium | -0.427 |
� | -0.417 |
之 | -0.417 |
Seymour | -0.404 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
rahim | +0.735 |
enhagen | +0.676 |
aho | +0.673 |
agara | +0.625 |
ertodd | +0.616 |
Neg logit contributions | |
� | -0.529 |
arium | -0.503 |
之 | -0.494 |
� | -0.493 |
Seymour | -0.477 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
rahim | +0.622 |
enhagen | +0.566 |
aho | +0.566 |
ertodd | +0.524 |
agara | +0.522 |
Neg logit contributions | |
� | -0.435 |
arium | -0.424 |
之 | -0.412 |
� | -0.411 |
Seymour | -0.397 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
rahim | +0.510 |
aho | +0.461 |
enhagen | +0.455 |
agara | +0.428 |
ertodd | +0.425 |
Neg logit contributions | |
� | -0.346 |
arium | -0.338 |
之 | -0.328 |
� | -0.328 |
Seymour | -0.319 |
Token | " |
Token ID | 1 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
rahim | +0.551 |
aho | +0.498 |
enhagen | +0.482 |
agara | +0.452 |
ertodd | +0.442 |
Neg logit contributions | |
� | -0.459 |
arium | -0.455 |
Seymour | -0.442 |
之 | -0.441 |
Nguyen | -0.436 |
Token | NR |
Token ID | 24723 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
� | +0.304 |
arium | +0.299 |
� | +0.291 |
之 | +0.290 |
Seymour | +0.287 |
Neg logit contributions | |
rahim | -0.325 |
enhagen | -0.292 |
aho | -0.289 |
agara | -0.268 |
ertodd | -0.265 |
Token | restrictions |
Token ID | 8733 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
� | +0.728 |
arium | +0.717 |
� | +0.694 |
之 | +0.690 |
Seymour | +0.677 |
Neg logit contributions | |
rahim | -1.108 |
enhagen | -1.016 |
aho | -1.012 |
agara | -0.952 |
ertodd | -0.922 |
Token | on |
Token ID | 319 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
� | +0.246 |
arium | +0.240 |
� | +0.232 |
之 | +0.231 |
Seymour | +0.227 |
Neg logit contributions | |
rahim | -0.364 |
enhagen | -0.335 |
aho | -0.332 |
agara | -0.310 |
ertodd | -0.305 |
Token | my |
Token ID | 616 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
rahim | +0.359 |
enhagen | +0.335 |
aho | +0.332 |
agara | +0.308 |
ertodd | +0.302 |
Neg logit contributions | |
� | -0.254 |
arium | -0.248 |
之 | -0.240 |
� | -0.240 |
Nguyen | -0.232 |
Token | research |
Token ID | 2267 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
� | +0.024 |
arium | +0.024 |
� | +0.023 |
之 | +0.023 |
Seymour | +0.022 |
Neg logit contributions | |
rahim | -0.040 |
enhagen | -0.037 |
aho | -0.037 |
agara | -0.035 |
ertodd | -0.034 |
Token | back |
Token ID | 736 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
rahim | +0.177 |
enhagen | +0.163 |
aho | +0.162 |
agara | +0.150 |
ertodd | +0.148 |
Neg logit contributions | |
� | -0.118 |
arium | -0.116 |
� | -0.112 |
之 | -0.112 |
Seymour | -0.110 |
Token | in |
Token ID | 287 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
rahim | +0.960 |
enhagen | +0.885 |
aho | +0.868 |
agara | +0.811 |
ertodd | +0.791 |
Neg logit contributions | |
� | -0.660 |
arium | -0.649 |
之 | -0.627 |
� | -0.625 |
Seymour | -0.617 |
Token | the |
Token ID | 262 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
rahim | +0.408 |
aho | +0.381 |
enhagen | +0.381 |
agara | +0.352 |
ertodd | +0.343 |
Neg logit contributions | |
� | -0.256 |
arium | -0.249 |
� | -0.241 |
之 | -0.238 |
Nguyen | -0.226 |
Token | spring |
Token ID | 6076 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
rahim | +0.341 |
enhagen | +0.322 |
aho | +0.320 |
agara | +0.296 |
ertodd | +0.288 |
Neg logit contributions | |
� | -0.203 |
arium | -0.196 |
� | -0.190 |
之 | -0.189 |
Nguyen | -0.181 |
Token | of |
Token ID | 286 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
rahim | +0.054 |
enhagen | +0.050 |
aho | +0.050 |
agara | +0.046 |
ertodd | +0.045 |
Neg logit contributions | |
� | -0.037 |
arium | -0.036 |
� | -0.035 |
之 | -0.035 |
Nguyen | -0.034 |
Token | 2000 |
Token ID | 4751 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
rahim | +0.684 |
aho | +0.636 |
enhagen | +0.631 |
agara | +0.590 |
ertodd | +0.577 |
Neg logit contributions | |
� | -0.350 |
arium | -0.338 |
� | -0.327 |
之 | -0.323 |
Seymour | -0.305 |
Token | � |
Token ID | 564 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rahim | +0.601 |
aho | +0.539 |
enhagen | +0.536 |
agara | +0.497 |
ertodd | +0.497 |
Neg logit contributions | |
� | -0.443 |
arium | -0.439 |
� | -0.421 |
之 | -0.420 |
Seymour | -0.409 |
Token | � |
Token ID | 250 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
rahim | +0.428 |
aho | +0.389 |
enhagen | +0.388 |
agara | +0.364 |
ertodd | +0.363 |
Neg logit contributions | |
� | -0.249 |
arium | -0.246 |
之 | -0.234 |
� | -0.234 |
Seymour | -0.232 |
Token | I |
Token ID | 40 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
� | +0.220 |
arium | +0.218 |
� | +0.210 |
之 | +0.210 |
Seymour | +0.208 |
Neg logit contributions | |
rahim | -0.239 |
enhagen | -0.214 |
aho | -0.212 |
agara | -0.196 |
ertodd | -0.195 |
Token | am |
Token ID | 716 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
� | +0.021 |
arium | +0.021 |
� | +0.020 |
之 | +0.020 |
Seymour | +0.020 |
Neg logit contributions | |
rahim | -0.027 |
enhagen | -0.024 |
aho | -0.024 |
agara | -0.023 |
ertodd | -0.022 |
Token | so |
Token ID | 523 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
rahim | +0.110 |
aho | +0.098 |
enhagen | +0.097 |
agara | +0.092 |
ertodd | +0.089 |
Neg logit contributions | |
arium | -0.087 |
� | -0.087 |
� | -0.084 |
之 | -0.083 |
Seymour | -0.081 |
Token | very |
Token ID | 845 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rahim | +0.118 |
aho | +0.103 |
enhagen | +0.102 |
agara | +0.094 |
ertodd | +0.091 |
Neg logit contributions | |
arium | -0.137 |
� | -0.137 |
� | -0.132 |
之 | -0.131 |
Seymour | -0.129 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rahim | +0.355 |
aho | +0.309 |
enhagen | +0.306 |
agara | +0.282 |
ertodd | +0.272 |
Neg logit contributions | |
� | -0.433 |
arium | -0.432 |
� | -0.417 |
之 | -0.414 |
Seymour | -0.406 |
Token | about |
Token ID | 546 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
rahim | +0.448 |
enhagen | +0.408 |
aho | +0.406 |
agara | +0.379 |
ertodd | +0.367 |
Neg logit contributions | |
� | -0.339 |
arium | -0.338 |
之 | -0.324 |
� | -0.322 |
Nguyen | -0.312 |
Token | your |
Token ID | 534 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
rahim | +1.135 |
aho | +1.017 |
enhagen | +1.014 |
agara | +0.947 |
ertodd | +0.904 |
Neg logit contributions | |
arium | -1.110 |
� | -1.096 |
之 | -1.072 |
� | -1.057 |
Nguyen | -1.019 |
Token | father |
Token ID | 2988 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
� | +0.237 |
arium | +0.236 |
� | +0.227 |
之 | +0.226 |
Seymour | +0.219 |
Neg logit contributions | |
rahim | -0.330 |
aho | -0.297 |
enhagen | -0.297 |
agara | -0.279 |
ertodd | -0.272 |
Token | , |
Token ID | 11 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
rahim | +0.275 |
enhagen | +0.251 |
aho | +0.249 |
agara | +0.234 |
ertodd | +0.230 |
Neg logit contributions | |
arium | -0.193 |
� | -0.192 |
� | -0.186 |
之 | -0.183 |
Nguyen | -0.180 |
Token | I |
Token ID | 314 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
rahim | +0.527 |
enhagen | +0.476 |
aho | +0.473 |
agara | +0.438 |
ertodd | +0.435 |
Neg logit contributions | |
� | -0.448 |
arium | -0.443 |
� | -0.428 |
之 | -0.424 |
Seymour | -0.411 |
Token | used |
Token ID | 973 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
rahim | +0.945 |
enhagen | +0.848 |
aho | +0.838 |
agara | +0.777 |
ertodd | +0.769 |
Neg logit contributions | |
� | -0.885 |
arium | -0.872 |
� | -0.847 |
之 | -0.845 |
Seymour | -0.826 |
Token | Table |
Token ID | 8655 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
rahim | +0.439 |
enhagen | +0.401 |
aho | +0.394 |
agara | +0.368 |
ertodd | +0.361 |
Neg logit contributions | |
� | -0.329 |
arium | -0.327 |
� | -0.314 |
之 | -0.312 |
Nguyen | -0.301 |
Token | au |
Token ID | 559 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
� | +0.191 |
arium | +0.187 |
之 | +0.182 |
� | +0.182 |
Seymour | +0.178 |
Neg logit contributions | |
rahim | -0.204 |
enhagen | -0.184 |
aho | -0.183 |
agara | -0.168 |
ertodd | -0.165 |
Token | to |
Token ID | 284 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
rahim | +0.314 |
aho | +0.287 |
enhagen | +0.287 |
agara | +0.264 |
ertodd | +0.263 |
Neg logit contributions | |
� | -0.200 |
arium | -0.197 |
� | -0.190 |
之 | -0.189 |
Seymour | -0.187 |
Token | create |
Token ID | 2251 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
� | +0.258 |
arium | +0.253 |
� | +0.247 |
之 | +0.246 |
Seymour | +0.240 |
Neg logit contributions | |
rahim | -0.281 |
enhagen | -0.251 |
aho | -0.250 |
agara | -0.232 |
ertodd | -0.228 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
rahim | +1.156 |
enhagen | +1.057 |
aho | +1.046 |
agara | +0.975 |
ertodd | +0.946 |
Neg logit contributions | |
� | -0.832 |
arium | -0.825 |
� | -0.798 |
之 | -0.786 |
Schwarzenegger | -0.760 |
Token | visualization |
Token ID | 32704 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
rahim | +0.378 |
enhagen | +0.344 |
aho | +0.341 |
agara | +0.317 |
ertodd | +0.310 |
Neg logit contributions | |
� | -0.298 |
arium | -0.295 |
� | -0.285 |
之 | -0.282 |
Nguyen | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
rahim | +0.118 |
enhagen | +0.108 |
aho | +0.108 |
agara | +0.101 |
ertodd | +0.099 |
Neg logit contributions | |
� | -0.082 |
arium | -0.080 |
� | -0.078 |
之 | -0.077 |
Nguyen | -0.075 |
Token | I |
Token ID | 314 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
rahim | +0.864 |
aho | +0.781 |
enhagen | +0.774 |
agara | +0.719 |
ertodd | +0.710 |
Neg logit contributions | |
� | -0.660 |
arium | -0.651 |
� | -0.631 |
之 | -0.628 |
Seymour | -0.601 |
Token | combined |
Token ID | 5929 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
� | +0.169 |
arium | +0.166 |
� | +0.162 |
之 | +0.161 |
Seymour | +0.158 |
Neg logit contributions | |
rahim | -0.206 |
enhagen | -0.186 |
aho | -0.184 |
agara | -0.171 |
ertodd | -0.170 |
Token | in |
Token ID | 287 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
rahim | +0.410 |
enhagen | +0.376 |
aho | +0.368 |
ertodd | +0.345 |
agara | +0.344 |
Neg logit contributions | |
� | -0.281 |
arium | -0.278 |
� | -0.269 |
之 | -0.265 |
Seymour | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
rahim | +0.929 |
enhagen | +0.836 |
aho | +0.830 |
agara | +0.777 |
ertodd | +0.770 |
Neg logit contributions | |
� | -0.742 |
arium | -0.729 |
� | -0.710 |
之 | -0.702 |
Seymour | -0.688 |
Token | back |
Token ID | 736 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
rahim | +0.696 |
enhagen | +0.632 |
aho | +0.623 |
agara | +0.585 |
ertodd | +0.581 |
Neg logit contributions | |
� | -0.495 |
arium | -0.482 |
� | -0.469 |
之 | -0.464 |
Seymour | -0.452 |
Token | of |
Token ID | 286 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
rahim | +1.259 |
enhagen | +1.138 |
aho | +1.121 |
agara | +1.049 |
ertodd | +1.048 |
Neg logit contributions | |
� | -0.868 |
arium | -0.852 |
� | -0.830 |
之 | -0.828 |
Seymour | -0.821 |
Token | an |
Token ID | 281 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
rahim | +0.286 |
enhagen | +0.260 |
aho | +0.256 |
ertodd | +0.241 |
agara | +0.240 |
Neg logit contributions | |
� | -0.195 |
arium | -0.193 |
� | -0.187 |
之 | -0.185 |
Seymour | -0.179 |
Token | SUV |
Token ID | 26763 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
rahim | +0.435 |
enhagen | +0.395 |
aho | +0.391 |
agara | +0.366 |
ertodd | +0.363 |
Neg logit contributions | |
� | -0.313 |
arium | -0.306 |
� | -0.296 |
之 | -0.296 |
Seymour | -0.285 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
rahim | +0.202 |
enhagen | +0.184 |
aho | +0.182 |
agara | +0.170 |
ertodd | +0.170 |
Neg logit contributions | |
� | -0.134 |
arium | -0.132 |
� | -0.128 |
之 | -0.127 |
Seymour | -0.125 |
Token | wearing |
Token ID | 5762 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
rahim | +0.549 |
enhagen | +0.504 |
aho | +0.498 |
agara | +0.463 |
ertodd | +0.462 |
Neg logit contributions | |
� | -0.392 |
arium | -0.390 |
� | -0.375 |
之 | -0.373 |
Seymour | -0.366 |
Token | ripped |
Token ID | 19551 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
rahim | +0.252 |
enhagen | +0.230 |
aho | +0.229 |
agara | +0.215 |
ertodd | +0.213 |
Neg logit contributions | |
arium | -0.180 |
� | -0.179 |
� | -0.171 |
之 | -0.171 |
Seymour | -0.164 |
Token | jeans |
Token ID | 21029 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
� | +0.134 |
arium | +0.133 |
之 | +0.128 |
� | +0.127 |
Seymour | +0.122 |
Neg logit contributions | |
rahim | -0.179 |
enhagen | -0.162 |
aho | -0.162 |
agara | -0.152 |
ertodd | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
� | +0.414 |
arium | +0.412 |
� | +0.395 |
之 | +0.391 |
Seymour | +0.383 |
Neg logit contributions | |
rahim | -0.642 |
enhagen | -0.587 |
aho | -0.584 |
agara | -0.546 |
ertodd | -0.540 |
Token | pen |
Token ID | 3112 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
� | +0.510 |
arium | +0.502 |
� | +0.486 |
之 | +0.483 |
Seymour | +0.475 |
Neg logit contributions | |
rahim | -0.685 |
enhagen | -0.622 |
aho | -0.614 |
agara | -0.575 |
ertodd | -0.572 |
Token | last |
Token ID | 938 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
� | +0.314 |
arium | +0.308 |
� | +0.299 |
之 | +0.299 |
Seymour | +0.291 |
Neg logit contributions | |
rahim | -0.484 |
enhagen | -0.446 |
aho | -0.438 |
agara | -0.408 |
ertodd | -0.408 |
Token | year |
Token ID | 614 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
� | +0.449 |
arium | +0.441 |
之 | +0.425 |
� | +0.425 |
Seymour | +0.413 |
Neg logit contributions | |
rahim | -0.726 |
enhagen | -0.668 |
aho | -0.656 |
agara | -0.616 |
ertodd | -0.612 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
� | +0.649 |
arium | +0.638 |
� | +0.612 |
之 | +0.611 |
Seymour | +0.599 |
Neg logit contributions | |
rahim | -0.995 |
enhagen | -0.919 |
aho | -0.904 |
agara | -0.843 |
ertodd | -0.842 |
Token | am |
Token ID | 716 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
rahim | +0.021 |
enhagen | +0.019 |
aho | +0.019 |
agara | +0.018 |
ertodd | +0.017 |
Neg logit contributions | |
� | -0.014 |
arium | -0.014 |
� | -0.013 |
之 | -0.013 |
Seymour | -0.013 |
Token | assing |
Token ID | 19696 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
� | +0.135 |
arium | +0.131 |
之 | +0.126 |
� | +0.126 |
Seymour | +0.123 |
Neg logit contributions | |
rahim | -0.204 |
enhagen | -0.186 |
aho | -0.183 |
agara | -0.171 |
ertodd | -0.169 |
Token | a |
Token ID | 257 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
� | +0.587 |
arium | +0.579 |
� | +0.560 |
之 | +0.557 |
Seymour | +0.540 |
Neg logit contributions | |
rahim | -0.856 |
enhagen | -0.785 |
aho | -0.772 |
agara | -0.722 |
ertodd | -0.716 |
Token | 2 |
Token ID | 362 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
rahim | +0.133 |
enhagen | +0.121 |
aho | +0.119 |
agara | +0.111 |
ertodd | +0.110 |
Neg logit contributions | |
� | -0.095 |
arium | -0.093 |
� | -0.090 |
之 | -0.090 |
Seymour | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
� | +0.122 |
arium | +0.121 |
� | +0.116 |
之 | +0.115 |
Schwarzenegger | +0.112 |
Neg logit contributions | |
rahim | -0.179 |
enhagen | -0.164 |
aho | -0.163 |
agara | -0.151 |
ertodd | -0.150 |
Token | 17 |
Token ID | 1558 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
� | +0.029 |
arium | +0.028 |
之 | +0.027 |
� | +0.027 |
Seymour | +0.027 |
Neg logit contributions | |
rahim | -0.043 |
aho | -0.040 |
enhagen | -0.039 |
agara | -0.037 |
ertodd | -0.036 |
Token | ERA |
Token ID | 18802 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
� | +0.192 |
arium | +0.190 |
之 | +0.183 |
� | +0.182 |
Seymour | +0.178 |
Neg logit contributions | |
rahim | -0.261 |
enhagen | -0.240 |
aho | -0.238 |
agara | -0.221 |
ertodd | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
rahim | +0.064 |
enhagen | +0.059 |
aho | +0.058 |
agara | +0.054 |
ertodd | +0.053 |
Neg logit contributions | |
� | -0.044 |
arium | -0.043 |
� | -0.041 |
之 | -0.041 |
Seymour | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
� | +0.063 |
arium | +0.062 |
� | +0.060 |
之 | +0.060 |
Seymour | +0.058 |
Neg logit contributions | |
rahim | -0.080 |
enhagen | -0.073 |
aho | -0.072 |
agara | -0.067 |
ertodd | -0.066 |
Token | due |
Token ID | 2233 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
� | +0.012 |
arium | +0.012 |
� | +0.012 |
之 | +0.012 |
Seymour | +0.011 |
Neg logit contributions | |
rahim | -0.018 |
enhagen | -0.017 |
aho | -0.016 |
agara | -0.015 |
ertodd | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
rahim | +0.020 |
enhagen | +0.018 |
aho | +0.018 |
agara | +0.017 |
ertodd | +0.017 |
Neg logit contributions | |
� | -0.012 |
arium | -0.012 |
� | -0.012 |
之 | -0.012 |
Seymour | -0.011 |
Token | problems |
Token ID | 2761 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
rahim | +0.114 |
enhagen | +0.105 |
aho | +0.103 |
agara | +0.098 |
ertodd | +0.095 |
Neg logit contributions | |
� | -0.084 |
arium | -0.083 |
� | -0.080 |
之 | -0.080 |
Nguyen | -0.077 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
� | +0.371 |
arium | +0.365 |
� | +0.352 |
之 | +0.349 |
Seymour | +0.340 |
Neg logit contributions | |
rahim | -0.607 |
enhagen | -0.558 |
aho | -0.552 |
agara | -0.520 |
ertodd | -0.512 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
� | +0.315 |
arium | +0.309 |
� | +0.300 |
之 | +0.298 |
Seymour | +0.290 |
Neg logit contributions | |
rahim | -0.421 |
enhagen | -0.384 |
aho | -0.378 |
agara | -0.354 |
ertodd | -0.351 |
Token | star |
Token ID | 3491 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
rahim | +0.115 |
enhagen | +0.105 |
aho | +0.103 |
agara | +0.097 |
ertodd | +0.096 |
Neg logit contributions | |
� | -0.088 |
arium | -0.086 |
� | -0.084 |
之 | -0.083 |
Seymour | -0.081 |
Token | tracker |
Token ID | 30013 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
rahim | +0.513 |
enhagen | +0.472 |
aho | +0.463 |
agara | +0.443 |
ertodd | +0.429 |
Neg logit contributions | |
� | -0.364 |
� | -0.349 |
arium | -0.343 |
之 | -0.343 |
Nguyen | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
rahim | +0.298 |
enhagen | +0.276 |
aho | +0.270 |
agara | +0.255 |
ertodd | +0.250 |
Neg logit contributions | |
� | -0.206 |
arium | -0.201 |
� | -0.197 |
之 | -0.195 |
Seymour | -0.188 |
Token | was |
Token ID | 373 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
rahim | +0.244 |
enhagen | +0.222 |
aho | +0.219 |
agara | +0.204 |
ertodd | +0.201 |
Neg logit contributions | |
� | -0.199 |
arium | -0.194 |
� | -0.190 |
之 | -0.189 |
Seymour | -0.184 |
Token | going |
Token ID | 1016 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
� | +0.022 |
arium | +0.021 |
� | +0.021 |
之 | +0.020 |
Seymour | +0.020 |
Neg logit contributions | |
rahim | -0.031 |
enhagen | -0.028 |
aho | -0.028 |
agara | -0.026 |
ertodd | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
rahim | +0.061 |
enhagen | +0.057 |
aho | +0.055 |
agara | +0.052 |
ertodd | +0.051 |
Neg logit contributions | |
� | -0.037 |
arium | -0.037 |
� | -0.035 |
之 | -0.035 |
Seymour | -0.034 |
Token | be |
Token ID | 307 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
� | +0.087 |
arium | +0.086 |
之 | +0.083 |
� | +0.083 |
Seymour | +0.080 |
Neg logit contributions | |
rahim | -0.111 |
enhagen | -0.101 |
aho | -0.101 |
agara | -0.094 |
ertodd | -0.092 |
Token | around |
Token ID | 1088 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
rahim | +0.166 |
enhagen | +0.151 |
aho | +0.150 |
agara | +0.141 |
ertodd | +0.138 |
Neg logit contributions | |
� | -0.119 |
arium | -0.118 |
� | -0.114 |
之 | -0.113 |
Seymour | -0.110 |
Token | for |
Token ID | 329 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
� | +0.238 |
arium | +0.234 |
之 | +0.226 |
� | +0.226 |
Seymour | +0.216 |
Neg logit contributions | |
rahim | -0.338 |
enhagen | -0.311 |
aho | -0.305 |
agara | -0.285 |
ertodd | -0.280 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
rahim | +0.044 |
enhagen | +0.041 |
aho | +0.040 |
agara | +0.038 |
ertodd | +0.037 |
Neg logit contributions | |
� | -0.033 |
arium | -0.032 |
� | -0.031 |
之 | -0.031 |
Seymour | -0.030 |
Token | while |
Token ID | 981 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
� | +0.274 |
arium | +0.271 |
� | +0.263 |
之 | +0.261 |
Seymour | +0.255 |
Neg logit contributions | |
rahim | -0.386 |
enhagen | -0.352 |
aho | -0.346 |
agara | -0.326 |
ertodd | -0.323 |
Token | in |
Token ID | 287 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
rahim | +1.181 |
enhagen | +1.086 |
aho | +1.073 |
agara | +1.009 |
ertodd | +0.979 |
Neg logit contributions | |
� | -0.888 |
arium | -0.884 |
之 | -0.857 |
� | -0.850 |
Seymour | -0.827 |
Token | the |
Token ID | 262 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
rahim | +0.510 |
enhagen | +0.468 |
aho | +0.466 |
agara | +0.435 |
ertodd | +0.426 |
Neg logit contributions | |
� | -0.354 |
arium | -0.350 |
� | -0.337 |
之 | -0.333 |
Seymour | -0.323 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
� | +0.062 |
arium | +0.060 |
� | +0.059 |
之 | +0.058 |
Seymour | +0.057 |
Neg logit contributions | |
rahim | -0.100 |
enhagen | -0.092 |
aho | -0.091 |
agara | -0.085 |
ertodd | -0.084 |
Token | presidential |
Token ID | 4787 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
rahim | +0.015 |
enhagen | +0.014 |
aho | +0.014 |
agara | +0.013 |
ertodd | +0.013 |
Neg logit contributions | |
� | -0.009 |
arium | -0.009 |
� | -0.009 |
之 | -0.008 |
Seymour | -0.008 |
Token | lived |
Token ID | 5615 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
� | +0.592 |
arium | +0.580 |
� | +0.565 |
之 | +0.562 |
Seymour | +0.552 |
Neg logit contributions | |
rahim | -0.724 |
enhagen | -0.654 |
aho | -0.648 |
agara | -0.607 |
ertodd | -0.597 |
Token | on |
Token ID | 319 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
� | +0.138 |
arium | +0.136 |
� | +0.131 |
之 | +0.130 |
Seymour | +0.127 |
Neg logit contributions | |
rahim | -0.206 |
enhagen | -0.187 |
aho | -0.186 |
agara | -0.174 |
ertodd | -0.172 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
� | +0.174 |
arium | +0.168 |
� | +0.165 |
之 | +0.164 |
Schwarzenegger | +0.158 |
Neg logit contributions | |
rahim | -0.233 |
enhagen | -0.209 |
aho | -0.208 |
agara | -0.198 |
ertodd | -0.192 |
Token | first |
Token ID | 717 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
rahim | +0.425 |
enhagen | +0.385 |
aho | +0.380 |
agara | +0.362 |
ertodd | +0.354 |
Neg logit contributions | |
� | -0.297 |
arium | -0.288 |
� | -0.280 |
之 | -0.279 |
Schwarzenegger | -0.268 |
Token | floor |
Token ID | 4314 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
rahim | +0.221 |
enhagen | +0.202 |
aho | +0.201 |
agara | +0.192 |
ertodd | +0.187 |
Neg logit contributions | |
� | -0.118 |
arium | -0.114 |
之 | -0.111 |
� | -0.110 |
Seymour | -0.106 |
Token | of |
Token ID | 286 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
� | +0.557 |
arium | +0.537 |
� | +0.526 |
之 | +0.523 |
Schwarzenegger | +0.510 |
Neg logit contributions | |
rahim | -0.841 |
enhagen | -0.770 |
aho | -0.758 |
agara | -0.716 |
ertodd | -0.705 |
Token | the |
Token ID | 262 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
rahim | +0.060 |
enhagen | +0.054 |
aho | +0.054 |
agara | +0.051 |
ertodd | +0.050 |
Neg logit contributions | |
� | -0.045 |
arium | -0.044 |
� | -0.043 |
之 | -0.043 |
Schwarzenegger | -0.041 |
Token | bung |
Token ID | 43974 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
rahim | +0.318 |
enhagen | +0.286 |
aho | +0.284 |
agara | +0.270 |
ertodd | +0.263 |
Neg logit contributions | |
� | -0.221 |
arium | -0.213 |
� | -0.210 |
之 | -0.209 |
Schwarzenegger | -0.200 |
Token | al |
Token ID | 282 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
� | +0.031 |
之 | +0.028 |
� | +0.028 |
arium | +0.028 |
Seymour | +0.027 |
Neg logit contributions | |
rahim | -0.093 |
enhagen | -0.087 |
aho | -0.086 |
agara | -0.082 |
ertodd | -0.079 |
Token | ow |
Token ID | 322 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
rahim | +0.255 |
enhagen | +0.234 |
aho | +0.229 |
ertodd | +0.217 |
agara | +0.217 |
Neg logit contributions | |
� | -0.147 |
arium | -0.146 |
� | -0.138 |
之 | -0.137 |
Seymour | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
� | +0.009 |
arium | +0.009 |
� | +0.009 |
之 | +0.009 |
Schwarzenegger | +0.008 |
Neg logit contributions | |
rahim | -0.013 |
enhagen | -0.012 |
aho | -0.011 |
agara | -0.011 |
ertodd | -0.011 |
Token | youth |
Token ID | 6205 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rahim | +0.083 |
aho | +0.075 |
enhagen | +0.075 |
agara | +0.070 |
ertodd | +0.067 |
Neg logit contributions | |
� | -0.063 |
arium | -0.063 |
之 | -0.060 |
� | -0.060 |
Seymour | -0.058 |
Token | that |
Token ID | 326 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
� | +0.274 |
arium | +0.269 |
� | +0.260 |
之 | +0.257 |
Seymour | +0.252 |
Neg logit contributions | |
rahim | -0.404 |
enhagen | -0.367 |
aho | -0.367 |
agara | -0.343 |
ertodd | -0.335 |
Token | takes |
Token ID | 2753 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
� | +0.248 |
arium | +0.240 |
� | +0.234 |
之 | +0.232 |
Seymour | +0.227 |
Neg logit contributions | |
rahim | -0.391 |
enhagen | -0.358 |
aho | -0.354 |
agara | -0.333 |
ertodd | -0.330 |
Token | account |
Token ID | 1848 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.391 |
arium | +0.385 |
� | +0.372 |
之 | +0.371 |
Seymour | +0.362 |
Neg logit contributions | |
rahim | -0.528 |
enhagen | -0.476 |
aho | -0.474 |
agara | -0.443 |
ertodd | -0.432 |
Token | of |
Token ID | 286 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
� | +0.517 |
arium | +0.508 |
� | +0.490 |
之 | +0.485 |
Seymour | +0.478 |
Neg logit contributions | |
rahim | -0.840 |
enhagen | -0.768 |
aho | -0.759 |
agara | -0.714 |
ertodd | -0.710 |
Token | their |
Token ID | 511 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
� | +0.812 |
arium | +0.802 |
� | +0.776 |
之 | +0.768 |
Seymour | +0.750 |
Neg logit contributions | |
rahim | -1.104 |
enhagen | -1.001 |
aho | -0.993 |
agara | -0.928 |
ertodd | -0.912 |
Token | experiences |
Token ID | 6461 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
� | +0.491 |
arium | +0.483 |
� | +0.467 |
之 | +0.462 |
Seymour | +0.452 |
Neg logit contributions | |
rahim | -0.747 |
enhagen | -0.680 |
aho | -0.674 |
agara | -0.633 |
ertodd | -0.625 |
Token | and |
Token ID | 290 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
rahim | +0.267 |
aho | +0.243 |
enhagen | +0.243 |
agara | +0.226 |
ertodd | +0.221 |
Neg logit contributions | |
� | -0.183 |
arium | -0.178 |
� | -0.173 |
之 | -0.170 |
Seymour | -0.169 |
Token | needs |
Token ID | 2476 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
rahim | +0.177 |
enhagen | +0.161 |
aho | +0.160 |
agara | +0.149 |
ertodd | +0.146 |
Neg logit contributions | |
� | -0.130 |
arium | -0.126 |
� | -0.124 |
之 | -0.122 |
Seymour | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
� | +0.431 |
arium | +0.419 |
� | +0.406 |
之 | +0.402 |
Seymour | +0.400 |
Neg logit contributions | |
rahim | -0.638 |
enhagen | -0.585 |
aho | -0.580 |
agara | -0.540 |
ertodd | -0.532 |
Token | AIR |
Token ID | 31600 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
� | +0.194 |
arium | +0.192 |
� | +0.187 |
之 | +0.184 |
Seymour | +0.179 |
Neg logit contributions | |
rahim | -0.250 |
enhagen | -0.223 |
aho | -0.223 |
agara | -0.206 |
ertodd | -0.203 |
Token | even |
Token ID | 772 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
� | +0.015 |
arium | +0.015 |
� | +0.014 |
之 | +0.014 |
Seymour | +0.014 |
Neg logit contributions | |
rahim | -0.021 |
enhagen | -0.019 |
aho | -0.019 |
agara | -0.018 |
ertodd | -0.018 |
Token | while |
Token ID | 981 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
� | +0.246 |
arium | +0.241 |
� | +0.233 |
之 | +0.231 |
Seymour | +0.227 |
Neg logit contributions | |
rahim | -0.327 |
enhagen | -0.296 |
aho | -0.295 |
agara | -0.273 |
ertodd | -0.267 |
Token | their |
Token ID | 511 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
� | +0.399 |
arium | +0.392 |
� | +0.377 |
之 | +0.376 |
Seymour | +0.367 |
Neg logit contributions | |
rahim | -0.551 |
enhagen | -0.501 |
aho | -0.498 |
agara | -0.464 |
ertodd | -0.458 |
Token | local |
Token ID | 1957 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
� | +0.381 |
arium | +0.375 |
� | +0.362 |
之 | +0.361 |
Seymour | +0.353 |
Neg logit contributions | |
rahim | -0.487 |
enhagen | -0.441 |
aho | -0.437 |
agara | -0.408 |
ertodd | -0.402 |
Token | social |
Token ID | 1919 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
� | +0.089 |
arium | +0.087 |
� | +0.085 |
之 | +0.084 |
Seymour | +0.083 |
Neg logit contributions | |
rahim | -0.107 |
enhagen | -0.097 |
aho | -0.096 |
agara | -0.089 |
ertodd | -0.087 |
Token | Time |
Token ID | 3862 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
� | +0.446 |
arium | +0.439 |
� | +0.429 |
之 | +0.425 |
Seymour | +0.418 |
Neg logit contributions | |
rahim | -0.536 |
enhagen | -0.482 |
aho | -0.481 |
agara | -0.450 |
ertodd | -0.438 |
Token | remains |
Token ID | 3793 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
� | +1.612 |
arium | +1.583 |
� | +1.540 |
之 | +1.531 |
Seymour | +1.499 |
Neg logit contributions | |
rahim | -2.013 |
enhagen | -1.827 |
aho | -1.812 |
agara | -1.694 |
ertodd | -1.669 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
� | +0.077 |
arium | +0.075 |
� | +0.073 |
之 | +0.073 |
Seymour | +0.071 |
Neg logit contributions | |
rahim | -0.102 |
enhagen | -0.092 |
aho | -0.092 |
agara | -0.086 |
ertodd | -0.084 |
Token | Local |
Token ID | 10714 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
rahim | +0.046 |
aho | +0.041 |
enhagen | +0.041 |
agara | +0.038 |
ertodd | +0.038 |
Neg logit contributions | |
� | -0.034 |
arium | -0.034 |
� | -0.032 |
之 | -0.032 |
Seymour | -0.031 |
Token | social |
Token ID | 1919 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
rahim | +0.044 |
enhagen | +0.040 |
aho | +0.039 |
agara | +0.037 |
ertodd | +0.036 |
Neg logit contributions | |
� | -0.039 |
arium | -0.038 |
� | -0.037 |
之 | -0.037 |
Seymour | -0.036 |
Token | times |
Token ID | 1661 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
� | +0.180 |
arium | +0.176 |
� | +0.170 |
之 | +0.170 |
Seymour | +0.166 |
Neg logit contributions | |
rahim | -0.234 |
aho | -0.212 |
enhagen | -0.212 |
agara | -0.199 |
ertodd | -0.192 |
Token | uster |
Token ID | 5819 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
rahim | +0.965 |
aho | +0.820 |
enhagen | +0.783 |
agara | +0.735 |
ertodd | +0.717 |
Neg logit contributions | |
� | -1.385 |
之 | -1.325 |
arium | -1.321 |
� | -1.305 |
Seymour | -1.286 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
rahim | +0.449 |
enhagen | +0.412 |
aho | +0.406 |
agara | +0.381 |
ertodd | +0.377 |
Neg logit contributions | |
� | -0.309 |
arium | -0.303 |
� | -0.292 |
之 | -0.292 |
Seymour | -0.286 |
Token | Perhaps |
Token ID | 8673 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
rahim | +0.332 |
enhagen | +0.298 |
aho | +0.297 |
ertodd | +0.273 |
agara | +0.273 |
Neg logit contributions | |
� | -0.257 |
arium | -0.254 |
� | -0.245 |
之 | -0.244 |
Seymour | -0.237 |
Token | the |
Token ID | 262 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
rahim | +0.823 |
enhagen | +0.749 |
aho | +0.736 |
agara | +0.690 |
ertodd | +0.684 |
Neg logit contributions | |
� | -0.597 |
arium | -0.586 |
� | -0.567 |
之 | -0.565 |
Seymour | -0.544 |
Token | tru |
Token ID | 45768 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
rahim | +0.140 |
enhagen | +0.128 |
aho | +0.126 |
agara | +0.118 |
ertodd | +0.117 |
Neg logit contributions | |
� | -0.095 |
arium | -0.093 |
� | -0.090 |
之 | -0.089 |
Seymour | -0.087 |
Token | est |
Token ID | 395 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
� | +0.864 |
arium | +0.851 |
� | +0.828 |
之 | +0.824 |
Seymour | +0.811 |
Neg logit contributions | |
rahim | -0.980 |
enhagen | -0.884 |
aho | -0.873 |
agara | -0.812 |
ertodd | -0.802 |
Token | sentence |
Token ID | 6827 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
� | +1.328 |
arium | +1.306 |
� | +1.264 |
之 | +1.256 |
Seymour | +1.233 |
Neg logit contributions | |
rahim | -1.877 |
enhagen | -1.709 |
aho | -1.687 |
agara | -1.582 |
ertodd | -1.573 |
Token | of |
Token ID | 286 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
� | +0.333 |
arium | +0.326 |
� | +0.316 |
之 | +0.313 |
Seymour | +0.305 |
Neg logit contributions | |
rahim | -0.516 |
enhagen | -0.471 |
aho | -0.466 |
agara | -0.438 |
ertodd | -0.434 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
� | +0.296 |
arium | +0.294 |
� | +0.283 |
之 | +0.281 |
Seymour | +0.274 |
Neg logit contributions | |
rahim | -0.355 |
enhagen | -0.323 |
aho | -0.316 |
agara | -0.295 |
ertodd | -0.290 |
Token | convention |
Token ID | 9831 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +0.342 |
arium | +0.336 |
� | +0.323 |
之 | +0.321 |
Seymour | +0.314 |
Neg logit contributions | |
rahim | -0.570 |
enhagen | -0.523 |
aho | -0.516 |
agara | -0.486 |
ertodd | -0.483 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
rahim | +0.799 |
enhagen | +0.732 |
aho | +0.725 |
agara | +0.681 |
ertodd | +0.670 |
Neg logit contributions | |
� | -0.556 |
arium | -0.542 |
� | -0.528 |
之 | -0.525 |
Seymour | -0.519 |
Token | AH |
Token ID | 28159 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
� | +0.607 |
arium | +0.597 |
之 | +0.578 |
� | +0.577 |
Seymour | +0.554 |
Neg logit contributions | |
rahim | -0.851 |
enhagen | -0.779 |
aho | -0.771 |
agara | -0.718 |
ertodd | -0.707 |
Token | VA |
Token ID | 11731 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
� | +0.717 |
arium | +0.704 |
之 | +0.668 |
� | +0.665 |
Seymour | +0.646 |
Neg logit contributions | |
rahim | -1.610 |
aho | -1.480 |
enhagen | -1.476 |
agara | -1.388 |
ertodd | -1.371 |
Token | ( |
Token ID | 357 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
� | +1.051 |
arium | +1.034 |
� | +1.002 |
之 | +0.996 |
Seymour | +0.971 |
Neg logit contributions | |
rahim | -1.472 |
enhagen | -1.343 |
aho | -1.328 |
agara | -1.240 |
ertodd | -1.228 |
Token | IPS |
Token ID | 47643 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
� | +0.128 |
arium | +0.127 |
� | +0.122 |
之 | +0.122 |
Seymour | +0.120 |
Neg logit contributions | |
rahim | -0.170 |
enhagen | -0.154 |
aho | -0.153 |
agara | -0.142 |
ertodd | -0.140 |
Token | - |
Token ID | 12 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
rahim | +0.260 |
enhagen | +0.235 |
aho | +0.233 |
agara | +0.210 |
ertodd | +0.206 |
Neg logit contributions | |
� | -0.300 |
arium | -0.299 |
之 | -0.292 |
� | -0.291 |
Seymour | -0.285 |
Token | type |
Token ID | 4906 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
� | +0.871 |
arium | +0.860 |
� | +0.833 |
之 | +0.829 |
Seymour | +0.816 |
Neg logit contributions | |
rahim | -1.164 |
enhagen | -1.063 |
aho | -1.053 |
agara | -0.980 |
ertodd | -0.973 |
Token | ) |
Token ID | 8 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
� | +1.561 |
arium | +1.540 |
� | +1.498 |
之 | +1.492 |
Seymour | +1.472 |
Neg logit contributions | |
rahim | -1.506 |
enhagen | -1.345 |
aho | -1.321 |
agara | -1.222 |
ertodd | -1.216 |
Token | @ |
Token ID | 2488 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
� | +0.202 |
arium | +0.199 |
� | +0.193 |
之 | +0.192 |
Seymour | +0.186 |
Neg logit contributions | |
rahim | -0.274 |
enhagen | -0.251 |
aho | -0.248 |
agara | -0.231 |
ertodd | -0.227 |
Token | 144 |
Token ID | 20224 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
� | +0.452 |
arium | +0.444 |
� | +0.429 |
之 | +0.427 |
Seymour | +0.417 |
Neg logit contributions | |
rahim | -0.663 |
enhagen | -0.606 |
aho | -0.598 |
agara | -0.561 |
ertodd | -0.556 |
Token | Hz |
Token ID | 7399 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
rahim | +0.144 |
enhagen | +0.127 |
aho | +0.126 |
agara | +0.114 |
ertodd | +0.113 |
Neg logit contributions | |
� | -0.171 |
arium | -0.170 |
之 | -0.164 |
� | -0.164 |
Seymour | -0.162 |
Token | ( |
Token ID | 357 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
rahim | +0.980 |
enhagen | +0.895 |
aho | +0.890 |
agara | +0.821 |
ertodd | +0.812 |
Neg logit contributions | |
� | -0.693 |
arium | -0.689 |
� | -0.660 |
之 | -0.650 |
Schwarzenegger | -0.631 |
Token | or |
Token ID | 273 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
� | +0.239 |
arium | +0.229 |
� | +0.228 |
之 | +0.228 |
Seymour | +0.225 |
Neg logit contributions | |
rahim | -0.313 |
enhagen | -0.288 |
aho | -0.285 |
agara | -0.266 |
ertodd | -0.262 |
Token | ice |
Token ID | 501 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
� | +0.997 |
arium | +0.968 |
� | +0.944 |
之 | +0.938 |
Seymour | +0.921 |
Neg logit contributions | |
rahim | -1.352 |
enhagen | -1.234 |
aho | -1.219 |
agara | -1.138 |
ertodd | -1.132 |
Token | y |
Token ID | 88 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
� | +0.239 |
arium | +0.232 |
之 | +0.227 |
� | +0.225 |
Nguyen | +0.217 |
Neg logit contributions | |
rahim | -0.372 |
enhagen | -0.350 |
aho | -0.343 |
agara | -0.321 |
ertodd | -0.320 |
Token | , |
Token ID | 11 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
rahim | +0.040 |
enhagen | +0.037 |
aho | +0.036 |
agara | +0.034 |
ertodd | +0.033 |
Neg logit contributions | |
� | -0.027 |
arium | -0.027 |
� | -0.026 |
之 | -0.026 |
Nguyen | -0.025 |
Token | prick |
Token ID | 41409 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
� | +0.131 |
arium | +0.130 |
之 | +0.125 |
� | +0.125 |
Seymour | +0.121 |
Neg logit contributions | |
rahim | -0.164 |
enhagen | -0.150 |
aho | -0.149 |
agara | -0.137 |
ertodd | -0.137 |
Token | ly |
Token ID | 306 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
� | +0.578 |
arium | +0.562 |
� | +0.552 |
之 | +0.552 |
Seymour | +0.539 |
Neg logit contributions | |
rahim | -0.661 |
enhagen | -0.614 |
aho | -0.598 |
agara | -0.554 |
ertodd | -0.547 |
Token | , |
Token ID | 11 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
� | +1.182 |
arium | +1.167 |
� | +1.121 |
之 | +1.120 |
Seymour | +1.084 |
Neg logit contributions | |
rahim | -1.816 |
enhagen | -1.674 |
aho | -1.650 |
agara | -1.545 |
ertodd | -1.537 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
rahim | +0.311 |
enhagen | +0.287 |
aho | +0.283 |
agara | +0.264 |
ertodd | +0.261 |
Neg logit contributions | |
� | -0.228 |
arium | -0.226 |
� | -0.218 |
之 | -0.217 |
Seymour | -0.211 |
Token | herbal |
Token ID | 35867 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
rahim | +0.090 |
enhagen | +0.082 |
aho | +0.082 |
agara | +0.075 |
ertodd | +0.075 |
Neg logit contributions | |
� | -0.075 |
arium | -0.075 |
� | -0.073 |
之 | -0.072 |
Seymour | -0.071 |
Token | ming |
Token ID | 42434 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
rahim | +0.010 |
enhagen | +0.009 |
aho | +0.009 |
agara | +0.008 |
ertodd | +0.008 |
Neg logit contributions | |
� | -0.007 |
arium | -0.007 |
� | -0.007 |
之 | -0.006 |
Seymour | -0.006 |
Token | les |
Token ID | 829 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
� | +0.122 |
arium | +0.117 |
� | +0.115 |
之 | +0.115 |
Seymour | +0.111 |
Neg logit contributions | |
rahim | -0.131 |
enhagen | -0.119 |
aho | -0.116 |
ertodd | -0.107 |
agara | -0.107 |
Token | high |
Token ID | 1029 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
� | +0.200 |
arium | +0.195 |
� | +0.190 |
之 | +0.188 |
Seymour | +0.182 |
Neg logit contributions | |
rahim | -0.286 |
enhagen | -0.261 |
aho | -0.257 |
agara | -0.241 |
ertodd | -0.238 |
Token | unemployment |
Token ID | 10681 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
� | +0.115 |
arium | +0.114 |
� | +0.107 |
之 | +0.107 |
Seymour | +0.106 |
Neg logit contributions | |
rahim | -0.248 |
enhagen | -0.228 |
aho | -0.226 |
agara | -0.213 |
ertodd | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | +7.85e-04 |
Pos logit contributions | |
rahim | +0.083 |
enhagen | +0.076 |
aho | +0.075 |
agara | +0.071 |
ertodd | +0.070 |
Neg logit contributions | |
� | -0.055 |
arium | -0.054 |
� | -0.052 |
之 | -0.052 |
Seymour | -0.051 |
Token | falling |
Token ID | 7463 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
rahim | +0.003 |
enhagen | +0.003 |
aho | +0.003 |
agara | +0.002 |
ertodd | +0.002 |
Neg logit contributions | |
� | -0.002 |
arium | -0.002 |
� | -0.002 |
之 | -0.002 |
Seymour | -0.002 |
Token | home |
Token ID | 1363 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
� | +0.500 |
arium | +0.486 |
� | +0.474 |
之 | +0.471 |
Seymour | +0.457 |
Neg logit contributions | |
rahim | -0.802 |
enhagen | -0.730 |
aho | -0.727 |
agara | -0.685 |
ertodd | -0.672 |
Token | values |
Token ID | 3815 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
� | +0.735 |
arium | +0.708 |
之 | +0.700 |
� | +0.696 |
Seymour | +0.680 |
Neg logit contributions | |
rahim | -1.109 |
enhagen | -1.007 |
aho | -0.999 |
agara | -0.949 |
ertodd | -0.921 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
� | +1.092 |
arium | +1.071 |
� | +1.032 |
之 | +1.026 |
Seymour | +1.006 |
Neg logit contributions | |
rahim | -1.847 |
enhagen | -1.695 |
aho | -1.673 |
agara | -1.577 |
ertodd | -1.570 |
Token | declining |
Token ID | 18080 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
� | +0.039 |
arium | +0.038 |
� | +0.037 |
之 | +0.037 |
Seymour | +0.035 |
Neg logit contributions | |
rahim | -0.056 |
enhagen | -0.052 |
aho | -0.051 |
agara | -0.048 |
ertodd | -0.047 |
Token | tax |
Token ID | 1687 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
rahim | +0.389 |
enhagen | +0.354 |
aho | +0.352 |
agara | +0.332 |
ertodd | +0.327 |
Neg logit contributions | |
� | -0.245 |
arium | -0.239 |
� | -0.233 |
之 | -0.230 |
Seymour | -0.222 |
Token | revenues |
Token ID | 13089 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
� | +0.465 |
arium | +0.456 |
� | +0.441 |
之 | +0.439 |
Seymour | +0.431 |
Neg logit contributions | |
rahim | -0.742 |
enhagen | -0.678 |
aho | -0.671 |
agara | -0.632 |
ertodd | -0.627 |
Token | continue |
Token ID | 2555 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
� | +0.456 |
arium | +0.449 |
� | +0.435 |
之 | +0.432 |
Seymour | +0.425 |
Neg logit contributions | |
rahim | -0.594 |
enhagen | -0.539 |
aho | -0.531 |
agara | -0.497 |
ertodd | -0.494 |